From 9192fddc5e742b1050c273859c7e86ed56af07e8 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Mon, 15 Nov 2021 10:12:54 -0500 Subject: [PATCH 01/57] use jinja2 for code generation, working towards generating C code for fast table lookup, and to provide a platform to generate code for other languages. --- .python-version | 5 - bin/update-tables.py | 233 +++++++++++++++++------------------- docs/unicode_version.rst | 1 + tox.ini | 24 ++-- wcwidth/unicode_versions.py | 3 +- 5 files changed, 126 insertions(+), 140 deletions(-) delete mode 100644 .python-version diff --git a/.python-version b/.python-version deleted file mode 100644 index faa8a45..0000000 --- a/.python-version +++ /dev/null @@ -1,5 +0,0 @@ -3.8.2 -3.7.6 -3.6.9 -3.5.9 -2.7.17 diff --git a/bin/update-tables.py b/bin/update-tables.py index d4939c5..5b3a9e5 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -4,8 +4,6 @@ https://github.com/jquast/wcwidth """ -from __future__ import print_function - # std imports import os import re @@ -16,13 +14,10 @@ import datetime import collections import unicodedata +from urllib.request import urlopen -try: - # py2 - from urllib2 import urlopen -except ImportError: - # py3 - from urllib.request import urlopen +# third party +import jinja2 URL_UNICODE_DERIVED_AGE = 'http://www.unicode.org/Public/UCD/latest/ucd/DerivedAge.txt' EXCLUDE_VERSIONS = ['2.0.0', '2.1.2', '3.0.0', '3.1.0', '3.2.0', '4.0.0'] @@ -30,43 +25,22 @@ os.path.join( os.path.dirname(__file__), os.path.pardir)) -PATH_DOCS = os.path.join(PATH_UP, 'docs') PATH_DATA = os.path.join(PATH_UP, 'data') -PATH_CODE = os.path.join(PATH_UP, 'wcwidth') -FILE_RST = os.path.join(PATH_DOCS, 'unicode_version.rst') -FILE_PATCH_FROM = "release files:" -FILE_PATCH_TO = "=======" - - -# use chr() for py3.x, -# unichr() for py2.x -try: - _ = unichr(0) -except NameError as err: - if err.args[0] == "name 'unichr' is not defined": - # pylint: disable=C0103,W0622 - # Invalid constant name "unichr" (col 8) - # Redefining built-in 'unichr' (col 8) - unichr = chr - else: - raise - +THIS_FILEPATH = os.path.relpath(__file__, os.path.join(PATH_UP, os.path.pardir)) # "wcwidth/bin/update-tables.py" +JINJA_ENV = jinja2.Environment( + loader=jinja2.FileSystemLoader(os.path.join(PATH_UP, 'code_templates')), + keep_trailing_newline=True) TableDef = collections.namedtuple('table', ['version', 'date', 'values']) +RenderDef = collections.namedtuple('render', ['jinja_filename', 'output_filename', 'fn_data']) -def main(): - """Update east-asian, combining and zero width tables.""" - versions = get_unicode_versions() - do_east_asian(versions) - do_zero_width(versions) - do_rst_file_update() - do_unicode_versions(versions) - - -def get_unicode_versions(): +# version codes are used by most templates +# TODO: memoize +def fetch_unicode_versions(): """Fetch, determine, and return Unicode Versions for processing.""" - fname = os.path.join(PATH_DATA, 'DerivedAge.txt') + + fname = os.path.join(PATH_DATA, os.path.basename(URL_UNICODE_DERIVED_AGE)) do_retrieve(url=URL_UNICODE_DERIVED_AGE, fname=fname) pattern = re.compile(r'#.*assigned in Unicode ([0-9.]+)') versions = [] @@ -76,45 +50,81 @@ def get_unicode_versions(): if version not in EXCLUDE_VERSIONS: versions.append(version) versions.sort(key=lambda ver: list(map(int, ver.split('.')))) - return versions + return {'versions': versions} -def do_rst_file_update(): - """Patch unicode_versions.rst to reflect the data files used in release.""" - - # read in, - data_in = codecs.open(FILE_RST, 'r', 'utf8').read() - - # search for beginning and end positions, - pos_begin = data_in.find(FILE_PATCH_FROM) - assert pos_begin != -1, (pos_begin, FILE_PATCH_FROM) - pos_begin += len(FILE_PATCH_FROM) - data_out = data_in[:pos_begin] + '\n\n' - - # find all filenames with a version number in it, - # sort filenames by name, then dotted number, ascending +def fetch_source_headers(): glob_pattern = os.path.join(PATH_DATA, '*[0-9]*.txt') filenames = glob.glob(glob_pattern) - filenames.sort(key=lambda ver: [ver.split( - '-')[0]] + list(map(int, ver.split('-')[-1][:-4].split('.')))) + filenames.sort(key=lambda filename: make_sortable_source_name(filename)) + headers = [] + for filename in filenames: + if header_description := fetch_source_description(filename): + headers.append(header_description) + return {'source_headers': headers} + + +CODEGEN_DEFINITIONS = [ + RenderDef(jinja_filename='unicode_versions.py.j2', + output_filename=os.path.join(PATH_UP, 'code', 'unicode_versions.py'), + fn_data=fetch_unicode_versions), + RenderDef(jinja_filename='unicode_version.rst.j2', + output_filename=os.path.join(PATH_UP, 'docs', 'unicode_version.rst'), + fn_data=fetch_source_headers) + RenderDef(jinja_filename='table_wide.py.j2', + output_filename=os.path.join(PATH_UP, 'code', 'table_wide.py'), + fn_data=fetch_table_wide_data), +# RenderDef(jinja_filename='table_zero.py.j2', +# output_filename=os.path.join(PATH_CODE, f'table_zero.py'), +# fn_data=fetch_table_zero_data) +] - # copy file description as-is, formatted - for fpath in filenames: - if description := describe_file_header(fpath): - data_out += f'\n{description}' - # write. - print(f"patching {FILE_RST} ..") - codecs.open( - FILE_RST, 'w', 'utf8').write(data_out) - - -def do_east_asian(versions): +def main(): + """Update east-asian, combining and zero width tables.""" + for render_def in CODEGEN_DEFINITIONS: + with open(render_def.output_filename, 'w') as fout: + fout.write(render_template(render_def.jinja_filename, **render_def.fn_data())) + +def render_template(jinja_filename, utc_now=UTC_NOW, this_filepath=THIS_FILEPATH, **kwargs): + return JINJA_ENV.get_template(jinja_filename).render( + utc_now=datetime.datetime.utcnow().strftime("%Y-%m-%d %H:%M:%S UTC"), + this_filepath=THIS_FILEPATH, + **kwargs) + +# do_rst_file_update() + #render_unicode_versions(versions) + #render_table_wide(versions) + #render_table_wide(versions) + +# functions for rendering unicode_version.rst +# + +def make_sortable_source_name(filename): + # make a sortable filename of unicode text file, + # + # >>> make_sorted_name("DerivedGeneralCategory-5.0.0.txt") + # ('DerivedGeneralCategory', 5, 0, 0) + basename, remaining = filename.split('-', 1) + version_numbers, _extension = os.path.splitext(remaining) + return (basename, *list(map(int, version_numbers.split('.')))) + +def fetch_source_description(filename): + # read first two lines, strip leading # + header_twolines = [ + line.lstrip('# ').rstrip() + for line in codecs.open(filename, 'r', 'utf8') + .readlines()[:2] + ] + if len(header_twolines) == 2: + return header_twolines + +def fetch_table_wide_data(): """Fetch and update east-asian tables.""" table = {} - for version in versions: + for version in fetch_unicode_versions(): fin = os.path.join(PATH_DATA, 'EastAsianWidth-{version}.txt') - fout = os.path.join(PATH_CODE, 'table_wide.py') + #fout = os.path.join(PATH_CODE, 'table_wide.py') url = ('http://www.unicode.org/Public/{version}/' 'ucd/EastAsianWidth.txt') try: @@ -127,14 +137,17 @@ def do_east_asian(versions): table[version] = parse_east_asian( fname=fin.format(version=version), properties=(u'W', u'F',)) - do_write_table(fname=fout, variable='WIDE_EASTASIAN', table=table) + return { + 'table': table, + 'variable': 'WIDE_EASTASIAN', + } -def do_zero_width(versions): +def fetch_table_zero_data(): """Fetch and update zero width tables.""" table = {} - fout = os.path.join(PATH_CODE, 'table_zero.py') - for version in versions: + #fout = os.path.join(PATH_CODE, 'table_zero.py') + for version in fetch_unicode_versions(): fin = os.path.join(PATH_DATA, 'DerivedGeneralCategory-{version}.txt') url = ('http://www.unicode.org/Public/{version}/ucd/extracted/' 'DerivedGeneralCategory.txt') @@ -148,9 +161,11 @@ def do_zero_width(versions): table[version] = parse_category( fname=fin.format(version=version), categories=('Me', 'Mn',)) - do_write_table(fname=fout, variable='ZERO_WIDTH', table=table) + return table + +# todo translate before jinja def make_table(values): """Return a tuple of lookup tables for given values.""" table = collections.deque() @@ -168,6 +183,25 @@ def make_table(values): return tuple(table) + +#def do_unicode_versions(versions, lang): +# """Write unicode_versions.py function list_versions().""" +# jinja_filename = +# output_filename = +# with open(output_filename, 'w') as fout: +# fout.write( +# +# +# +# do_unicode_versions(versions, lang='py') +# val = fetch_east_asian_table(versions, lang='py') +# assert False, val +# assert False +# #do_write_table(fname=fout, variable='WIDE_EASTASIAN', table=table, lang=lang) +# fetch_zero_width_table(versions, lang='py') +# #do_write_table(fname=fout, variable='ZERO_WIDTH', table=table, lang=lang) + + def do_retrieve(url, fname): """Retrieve given url to target filepath fname.""" folder = os.path.dirname(fname) @@ -188,20 +222,6 @@ def do_retrieve(url, fname): return fname -def describe_file_header(fpath): - header_2 = [line.lstrip('# ').rstrip() for line in - codecs.open(fpath, 'r', 'utf8').readlines()[:2]] - # fmt: - # - # ``EastAsianWidth-8.0.0.txt`` - # *2015-02-10, 21:00:00 GMT [KW, LI]* - fmt = '``{0}``\n *{1}*\n' - if len(header_2) == 0: - return '' - assert len(header_2) == 2, (fpath, header_2) - return fmt.format(*header_2) - - def parse_east_asian(fname, properties=(u'W', u'F',)): """Parse unicode east-asian width tables.""" print(f'parsing {fname}: ', end='', flush=True) @@ -253,7 +273,7 @@ def parse_category(fname, categories): return TableDef(version, date, sorted(values)) -def do_write_table(fname, variable, table): +def do_write_table(fname, variable, table, lang): """Write combining tables to filesystem as python code.""" # pylint: disable=R0914 # Too many local variables (19/15) (col 4) @@ -276,7 +296,7 @@ def do_write_table(fname, variable, table): f"{indent}#") for start, end in make_table(version_table.values): - ucs_start, ucs_end = unichr(start), unichr(end) + ucs_start, ucs_end = chr(start), chr(end) hex_start, hex_end = (f'0x{start:05x}', f'0x{end:05x}') try: name_start = string.capwords(unicodedata.name(ucs_start)) @@ -296,38 +316,5 @@ def do_write_table(fname, variable, table): print("complete.") -def do_unicode_versions(versions): - """Write unicode_versions.py function list_versions().""" - fname = os.path.join(PATH_CODE, 'unicode_versions.py') - print(f"writing {fname} ... ", end='') - - utc_now = datetime.datetime.utcnow() - version_tuples_str = '\n '.join( - f'"{ver}",' for ver in versions) - with open(fname, 'w') as fp: - fp.write(f"""\"\"\" -Exports function list_versions() for unicode version level support. - -This code generated by {__file__} on {utc_now}. -\"\"\" - - -def list_versions(): - \"\"\" - Return Unicode version levels supported by this module release. - - Any of the version strings returned may be used as keyword argument - ``unicode_version`` to the ``wcwidth()`` family of functions. - - :returns: Supported Unicode version numbers in ascending sorted order. - :rtype: list[str] - \"\"\" - return ( - {version_tuples_str} - ) -""") - print('done.') - - if __name__ == '__main__': main() diff --git a/docs/unicode_version.rst b/docs/unicode_version.rst index 0719b80..9a5e282 100644 --- a/docs/unicode_version.rst +++ b/docs/unicode_version.rst @@ -102,3 +102,4 @@ release files: ``EastAsianWidth-13.0.0.txt`` *Date: 2029-01-21, 18:14:00 GMT [KW, LI]* + diff --git a/tox.ini b/tox.ini index 9ec5f40..7282dc7 100644 --- a/tox.ini +++ b/tox.ini @@ -59,19 +59,23 @@ precision = 1 source = wcwidth/ [testenv:compile] -basepython = python3.8 +basepython = python3.9 commands = python -m compileall {toxinidir}/wcwidth [testenv:update] usedevelop = true -basepython = python3.8 -deps = +basepython = python3.9 +deps = jinja2 + requests commands = python {toxinidir}/bin/update-tables.py - python -mcompileall {toxinidir}/wcwidth/table_zero.py \ - {toxinidir}/wcwidth/table_wide.py +# TODO +# +# python -mcompileall {toxinidir}/wcwidth/table_zero.py \ +# {toxinidir}/wcwidth/table_wide.py +# TODO: and most certainly compile any C code .. [testenv:autopep8] -basepython = python3.8 +basepython = python3.9 deps = autopep8==1.4.4 commands = {envbindir}/autopep8 \ @@ -96,14 +100,14 @@ commands = {toxinidir}/bin \ {toxinidir}/setup.py \ {toxinidir}/docs/conf.py -basepython = python3.8 +basepython = python3.9 [testenv:isort] deps = {[testenv]deps} -r docs/requirements.txt isort==4.3.21 commands = {envbindir}/isort --quiet --apply --recursive -basepython = python3.8 +basepython = python3.9 [testenv:pylint] deps = pylint==2.5.2 @@ -132,7 +136,7 @@ commands = {envbindir}/pydocstyle --source --explain {toxinidir}/blessed deps = -rrequirements-develop.txt usedevelop = true commands = prospector {posargs:--no-autodetect --die-on-tool-error} -basepython = python3.8 +basepython = python3.9 [testenv:docs] deps = sphinx @@ -147,7 +151,7 @@ deps = -r {toxinidir}/docs/requirements.txt commands = {envbindir}/sphinx-build -v -W -d {toxinidir}/docs/_build/doctrees -b linkcheck docs docs/_build/linkcheck [testenv:codecov] -basepython = python{env:TOXPYTHON:{env:TRAVIS_PYTHON_VERSION:3.8}} +basepython = python{env:TOXPYTHON:{env:TRAVIS_PYTHON_VERSION:3.9}} passenv = TOXENV CI TRAVIS TRAVIS_* CODECOV_* deps = codecov>=1.4.0 tenacity==6.1.0 diff --git a/wcwidth/unicode_versions.py b/wcwidth/unicode_versions.py index 24119f9..25ec93f 100644 --- a/wcwidth/unicode_versions.py +++ b/wcwidth/unicode_versions.py @@ -1,10 +1,9 @@ """ Exports function list_versions() for unicode version level support. -This code generated by bin/update-tables.py on 2020-06-23 15:58:44.035540. +This code generated by wcwidth/bin/update-tables.py on 2021-10-01 19:03:52 UTC. """ - def list_versions(): """ Return Unicode version levels supported by this module release. From c03d1b5afc87084637d2788f812d0d7ef8a368c4 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Mon, 15 Nov 2021 10:16:50 -0500 Subject: [PATCH 02/57] add code templates for python --- code_templates/python_table_width.py.j2 | 0 code_templates/unicode_version.rst.j2 | 12 ++++++++++++ code_templates/unicode_versions.py.j2 | 21 +++++++++++++++++++++ 3 files changed, 33 insertions(+) create mode 100644 code_templates/python_table_width.py.j2 create mode 100644 code_templates/unicode_version.rst.j2 create mode 100644 code_templates/unicode_versions.py.j2 diff --git a/code_templates/python_table_width.py.j2 b/code_templates/python_table_width.py.j2 new file mode 100644 index 0000000..e69de29 diff --git a/code_templates/unicode_version.rst.j2 b/code_templates/unicode_version.rst.j2 new file mode 100644 index 0000000..8eef371 --- /dev/null +++ b/code_templates/unicode_version.rst.j2 @@ -0,0 +1,12 @@ +===================== +Unicode release files +===================== + +This library aims to be forward-looking, portable, and most correct. +The most current release of this API is based on the Unicode Standard +release files: + +{% for line1, line2 in source_headers %} +``{{line1}}`` + *{{line2}}* +{% endfor %} diff --git a/code_templates/unicode_versions.py.j2 b/code_templates/unicode_versions.py.j2 new file mode 100644 index 0000000..e31926c --- /dev/null +++ b/code_templates/unicode_versions.py.j2 @@ -0,0 +1,21 @@ +""" +Exports function list_versions() for unicode version level support. + +This code generated by {{this_filepath}} on {{utc_now}}. +""" + +def list_versions(): + """ + Return Unicode version levels supported by this module release. + + Any of the version strings returned may be used as keyword argument + ``unicode_version`` to the ``wcwidth()`` family of functions. + + :returns: Supported Unicode version numbers in ascending sorted order. + :rtype: list[str] + """ + return ( +{%- for version in versions %} + "{{version}}", +{%- endfor %} + ) From cd98f5ed1c49897d82752271a00ddf0955709fbe Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Mon, 15 Nov 2021 10:20:48 -0500 Subject: [PATCH 03/57] narf --- bin/update-tables.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/bin/update-tables.py b/bin/update-tables.py index 5b3a9e5..f31570f 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -160,6 +160,9 @@ def fetch_table_zero_data(): else: table[version] = parse_category( fname=fin.format(version=version), + # todo: test whether all of category, 'Cf' should be excluded, + # or, just a subset, see issue about 2060..2064 range + # https://github.com/jquast/wcwidth/issues/26 categories=('Me', 'Mn',)) return table From 102e57e5e4cddfe3c44aadbe7ca46927b5cbc600 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Mon, 15 Nov 2021 10:21:35 -0500 Subject: [PATCH 04/57] narf --- bin/update-tables.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index f31570f..43b73d7 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -160,8 +160,8 @@ def fetch_table_zero_data(): else: table[version] = parse_category( fname=fin.format(version=version), - # todo: test whether all of category, 'Cf' should be excluded, - # or, just a subset, see issue about 2060..2064 range + # todo: test whether all of category, 'Cf' should be 'zero + # width', or, just the subset 2060..2064, see open issue # https://github.com/jquast/wcwidth/issues/26 categories=('Me', 'Mn',)) return table From 7b73991777931d41593f9df396de8a258284d73e Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:14:18 -0400 Subject: [PATCH 05/57] small comment --- wcwidth/wcwidth.py | 1 + 1 file changed, 1 insertion(+) diff --git a/wcwidth/wcwidth.py b/wcwidth/wcwidth.py index 931bd0b..e543f9a 100644 --- a/wcwidth/wcwidth.py +++ b/wcwidth/wcwidth.py @@ -216,6 +216,7 @@ def wcwidth(wc, unicode_version='auto'): if _bisearch(ucs, ZERO_WIDTH[_unicode_version]): return 0 + # "Wide AastAsian" (and emojis) return 1 + _bisearch(ucs, WIDE_EASTASIAN[_unicode_version]) From ef33e1d18f90bf637cb17f898a6c6526bcc0b53a Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:14:58 -0400 Subject: [PATCH 06/57] v14 support --- docs/unicode_version.rst | 6 + wcwidth/table_wide.py | 608 ++++--- wcwidth/table_zero.py | 3181 ++++++++++++++++++++--------------- wcwidth/unicode_versions.py | 3 +- 4 files changed, 2211 insertions(+), 1587 deletions(-) diff --git a/docs/unicode_version.rst b/docs/unicode_version.rst index 9a5e282..b70071c 100644 --- a/docs/unicode_version.rst +++ b/docs/unicode_version.rst @@ -55,6 +55,9 @@ release files: ``DerivedGeneralCategory-13.0.0.txt`` *Date: 2019-10-21, 14:30:32 GMT* +``DerivedGeneralCategory-14.0.0.txt`` + *Date: 2021-07-10, 00:35:08 GMT* + ``EastAsianWidth-4.1.0.txt`` *Date: 2005-03-17, 15:21:00 PST [KW]* @@ -103,3 +106,6 @@ release files: ``EastAsianWidth-13.0.0.txt`` *Date: 2029-01-21, 18:14:00 GMT [KW, LI]* +``EastAsianWidth-14.0.0.txt`` + *Date: 2021-07-06, 09:58:53 GMT [KW, LI]* + diff --git a/wcwidth/table_wide.py b/wcwidth/table_wide.py index 4fe575c..d4dd390 100644 --- a/wcwidth/table_wide.py +++ b/wcwidth/table_wide.py @@ -1,12 +1,16 @@ -"""Wide_Eastasian table, created by bin/update-tables.py.""" -# Generated: 2020-06-23T15:58:41.860748 +""" +Exports WIDE_EASTASIAN table keyed by supporting unicode version level. + +This code generated by wcwidth/bin/update-tables.py on 2022-03-20 21:12:52 UTC. +""" WIDE_EASTASIAN = { '4.1.0': ( # Source: EastAsianWidth-4.1.0.txt # Date: 2005-03-17, 15:21:00 PST [KW] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x01159,), # Hangul Choseong Kiyeok ..Hangul Choseong Yeorinhi - (0x0115f, 0x0115f,), # Hangul Choseong Filler ..Hangul Choseong Filler + (0x0115f, 0x0115f,), # Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified @@ -37,14 +41,15 @@ (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '5.0.0': ( # Source: EastAsianWidth-5.0.0.txt # Date: 2006-02-15, 14:39:00 PST [KW] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x01159,), # Hangul Choseong Kiyeok ..Hangul Choseong Yeorinhi - (0x0115f, 0x0115f,), # Hangul Choseong Filler ..Hangul Choseong Filler + (0x0115f, 0x0115f,), # Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified @@ -75,14 +80,15 @@ (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '5.1.0': ( # Source: EastAsianWidth-5.1.0.txt # Date: 2008-03-20, 17:42:00 PDT [KW] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x01159,), # Hangul Choseong Kiyeok ..Hangul Choseong Yeorinhi - (0x0115f, 0x0115f,), # Hangul Choseong Filler ..Hangul Choseong Filler + (0x0115f, 0x0115f,), # Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified @@ -113,12 +119,13 @@ (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '5.2.0': ( # Source: EastAsianWidth-5.2.0.txt # Date: 2009-06-09, 17:47:00 PDT [KW] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x011a3, 0x011a7,), # Hangul Jungseong A-eu ..Hangul Jungseong O-yae (0x011fa, 0x011ff,), # Hangul Jongseong Kiyeok-..Hangul Jongseong Ssangni @@ -137,7 +144,7 @@ (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto (0x03250, 0x032fe,), # Partnership Sign ..Circled Katakana Wo - (0x03300, 0x04dbf,), # Square Apaato ..(nil) + (0x03300, 0x04dbf,), # Square Apaato ..Cjk Unified Ideograph-4d (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo @@ -151,16 +158,17 @@ (0x0fe68, 0x0fe6b,), # Small Reverse Solidus ..Small Commercial At (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign - (0x1f200, 0x1f200,), # Square Hiragana Hoka ..Square Hiragana Hoka + (0x1f200, 0x1f200,), # Square Hiragana Hoka (0x1f210, 0x1f231,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo (0x1f240, 0x1f248,), # Tortoise Shell Bracketed..Tortoise Shell Bracketed (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '6.0.0': ( # Source: EastAsianWidth-6.0.0.txt # Date: 2010-08-17, 12:17:00 PDT [KW] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x011a3, 0x011a7,), # Hangul Jungseong A-eu ..Hangul Jungseong O-yae (0x011fa, 0x011ff,), # Hangul Jongseong Kiyeok-..Hangul Jongseong Ssangni @@ -179,7 +187,7 @@ (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto (0x03250, 0x032fe,), # Partnership Sign ..Circled Katakana Wo - (0x03300, 0x04dbf,), # Square Apaato ..(nil) + (0x03300, 0x04dbf,), # Square Apaato ..Cjk Unified Ideograph-4d (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo @@ -200,12 +208,13 @@ (0x1f250, 0x1f251,), # Circled Ideograph Advant..Circled Ideograph Accept (0x20000, 0x2f73f,), # Cjk Unified Ideograph-20..(nil) (0x2b740, 0x2fffd,), # Cjk Unified Ideograph-2b..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '6.1.0': ( # Source: EastAsianWidth-6.1.0.txt # Date: 2011-09-19, 18:46:00 GMT [KW] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x011a3, 0x011a7,), # Hangul Jungseong A-eu ..Hangul Jungseong O-yae (0x011fa, 0x011ff,), # Hangul Jongseong Kiyeok-..Hangul Jongseong Ssangni @@ -224,7 +233,7 @@ (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto (0x03250, 0x032fe,), # Partnership Sign ..Circled Katakana Wo - (0x03300, 0x04dbf,), # Square Apaato ..(nil) + (0x03300, 0x04dbf,), # Square Apaato ..Cjk Unified Ideograph-4d (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo @@ -244,12 +253,13 @@ (0x1f240, 0x1f248,), # Tortoise Shell Bracketed..Tortoise Shell Bracketed (0x1f250, 0x1f251,), # Circled Ideograph Advant..Circled Ideograph Accept (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '6.2.0': ( # Source: EastAsianWidth-6.2.0.txt # Date: 2012-05-15, 18:30:00 GMT [KW] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap @@ -266,7 +276,7 @@ (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto (0x03250, 0x032fe,), # Partnership Sign ..Circled Katakana Wo - (0x03300, 0x04dbf,), # Square Apaato ..(nil) + (0x03300, 0x04dbf,), # Square Apaato ..Cjk Unified Ideograph-4d (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo @@ -284,12 +294,13 @@ (0x1f240, 0x1f248,), # Tortoise Shell Bracketed..Tortoise Shell Bracketed (0x1f250, 0x1f251,), # Circled Ideograph Advant..Circled Ideograph Accept (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '6.3.0': ( # Source: EastAsianWidth-6.3.0.txt # Date: 2013-02-05, 20:09:00 GMT [KW, LI] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap @@ -306,7 +317,7 @@ (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto (0x03250, 0x032fe,), # Partnership Sign ..Circled Katakana Wo - (0x03300, 0x04dbf,), # Square Apaato ..(nil) + (0x03300, 0x04dbf,), # Square Apaato ..Cjk Unified Ideograph-4d (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo @@ -324,12 +335,13 @@ (0x1f240, 0x1f248,), # Tortoise Shell Bracketed..Tortoise Shell Bracketed (0x1f250, 0x1f251,), # Circled Ideograph Advant..Circled Ideograph Accept (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '7.0.0': ( # Source: EastAsianWidth-7.0.0.txt # Date: 2014-02-28, 23:15:00 GMT [KW, LI] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap @@ -346,7 +358,7 @@ (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto (0x03250, 0x032fe,), # Partnership Sign ..Circled Katakana Wo - (0x03300, 0x04dbf,), # Square Apaato ..(nil) + (0x03300, 0x04dbf,), # Square Apaato ..Cjk Unified Ideograph-4d (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo @@ -364,12 +376,13 @@ (0x1f240, 0x1f248,), # Tortoise Shell Bracketed..Tortoise Shell Bracketed (0x1f250, 0x1f251,), # Circled Ideograph Advant..Circled Ideograph Accept (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '8.0.0': ( # Source: EastAsianWidth-8.0.0.txt # Date: 2015-02-10, 21:00:00 GMT [KW, LI] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap @@ -386,7 +399,7 @@ (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto (0x03250, 0x032fe,), # Partnership Sign ..Circled Katakana Wo - (0x03300, 0x04dbf,), # Square Apaato ..(nil) + (0x03300, 0x04dbf,), # Square Apaato ..Cjk Unified Ideograph-4d (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo @@ -404,47 +417,48 @@ (0x1f240, 0x1f248,), # Tortoise Shell Bracketed..Tortoise Shell Bracketed (0x1f250, 0x1f251,), # Circled Ideograph Advant..Circled Ideograph Accept (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '9.0.0': ( # Source: EastAsianWidth-9.0.0.txt # Date: 2016-05-27, 17:00:00 GMT [KW, LI] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub - (0x023f0, 0x023f0,), # Alarm Clock ..Alarm Clock - (0x023f3, 0x023f3,), # Hourglass With Flowing S..Hourglass With Flowing S + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing S (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage (0x02648, 0x02653,), # Aries ..Pisces - (0x0267f, 0x0267f,), # Wheelchair Symbol ..Wheelchair Symbol - (0x02693, 0x02693,), # Anchor ..Anchor - (0x026a1, 0x026a1,), # High Voltage Sign ..High Voltage Sign + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle (0x026bd, 0x026be,), # Soccer Ball ..Baseball (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud - (0x026ce, 0x026ce,), # Ophiuchus ..Ophiuchus - (0x026d4, 0x026d4,), # No Entry ..No Entry - (0x026ea, 0x026ea,), # Church ..Church + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church (0x026f2, 0x026f3,), # Fountain ..Flag In Hole - (0x026f5, 0x026f5,), # Sailboat ..Sailboat - (0x026fa, 0x026fa,), # Tent ..Tent - (0x026fd, 0x026fd,), # Fuel Pump ..Fuel Pump - (0x02705, 0x02705,), # White Heavy Check Mark ..White Heavy Check Mark + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand - (0x02728, 0x02728,), # Sparkles ..Sparkles - (0x0274c, 0x0274c,), # Cross Mark ..Cross Mark - (0x0274e, 0x0274e,), # Negative Squared Cross M..Negative Squared Cross M + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross M (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O - (0x02757, 0x02757,), # Heavy Exclamation Mark S..Heavy Exclamation Mark S + (0x02757, 0x02757,), # Heavy Exclamation Mark S (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign - (0x027b0, 0x027b0,), # Curly Loop ..Curly Loop - (0x027bf, 0x027bf,), # Double Curly Loop ..Double Curly Loop + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square - (0x02b50, 0x02b50,), # White Medium Star ..White Medium Star - (0x02b55, 0x02b55,), # Heavy Large Circle ..Heavy Large Circle + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute @@ -459,7 +473,7 @@ (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto (0x03250, 0x032fe,), # Partnership Sign ..Circled Katakana Wo - (0x03300, 0x04dbf,), # Square Apaato ..(nil) + (0x03300, 0x04dbf,), # Square Apaato ..Cjk Unified Ideograph-4d (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo @@ -471,13 +485,13 @@ (0x0fe68, 0x0fe6b,), # Small Reverse Solidus ..Small Commercial At (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign - (0x16fe0, 0x16fe0,), # Tangut Iteration Mark ..Tangut Iteration Mark - (0x17000, 0x187ec,), # (nil) ..(nil) + (0x16fe0, 0x16fe0,), # Tangut Iteration Mark + (0x17000, 0x187ec,), # (nil) (0x18800, 0x18af2,), # Tangut Component-001 ..Tangut Component-755 (0x1b000, 0x1b001,), # Katakana Letter Archaic ..Hiragana Letter Archaic - (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon ..Mahjong Tile Red Dragon - (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker..Playing Card Black Joker - (0x1f18e, 0x1f18e,), # Negative Squared Ab ..Negative Squared Ab + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker + (0x1f18e, 0x1f18e,), # Negative Squared Ab (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo @@ -490,72 +504,73 @@ (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And (0x1f3e0, 0x1f3f0,), # House Building ..European Castle - (0x1f3f4, 0x1f3f4,), # Waving Black Flag ..Waving Black Flag + (0x1f3f4, 0x1f3f4,), # Waving Black Flag (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints - (0x1f440, 0x1f440,), # Eyes ..Eyes + (0x1f440, 0x1f440,), # Eyes (0x1f442, 0x1f4fc,), # Ear ..Videocassette (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty - (0x1f57a, 0x1f57a,), # Man Dancing ..Man Dancing + (0x1f57a, 0x1f57a,), # Man Dancing (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be - (0x1f5a4, 0x1f5a4,), # Black Heart ..Black Heart + (0x1f5a4, 0x1f5a4,), # Black Heart (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage - (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation ..Sleeping Accommodation + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving (0x1f6f4, 0x1f6f6,), # Scooter ..Canoe (0x1f910, 0x1f91e,), # Zipper-mouth Face ..Hand With Index And Midd (0x1f920, 0x1f927,), # Face With Cowboy Hat ..Sneezing Face - (0x1f930, 0x1f930,), # Pregnant Woman ..Pregnant Woman + (0x1f930, 0x1f930,), # Pregnant Woman (0x1f933, 0x1f93e,), # Selfie ..Handball (0x1f940, 0x1f94b,), # Wilted Flower ..Martial Arts Uniform (0x1f950, 0x1f95e,), # Croissant ..Pancakes (0x1f980, 0x1f991,), # Crab ..Squid - (0x1f9c0, 0x1f9c0,), # Cheese Wedge ..Cheese Wedge + (0x1f9c0, 0x1f9c0,), # Cheese Wedge (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '10.0.0': ( # Source: EastAsianWidth-10.0.0.txt # Date: 2017-03-08, 02:00:00 GMT [KW, LI] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub - (0x023f0, 0x023f0,), # Alarm Clock ..Alarm Clock - (0x023f3, 0x023f3,), # Hourglass With Flowing S..Hourglass With Flowing S + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing S (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage (0x02648, 0x02653,), # Aries ..Pisces - (0x0267f, 0x0267f,), # Wheelchair Symbol ..Wheelchair Symbol - (0x02693, 0x02693,), # Anchor ..Anchor - (0x026a1, 0x026a1,), # High Voltage Sign ..High Voltage Sign + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle (0x026bd, 0x026be,), # Soccer Ball ..Baseball (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud - (0x026ce, 0x026ce,), # Ophiuchus ..Ophiuchus - (0x026d4, 0x026d4,), # No Entry ..No Entry - (0x026ea, 0x026ea,), # Church ..Church + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church (0x026f2, 0x026f3,), # Fountain ..Flag In Hole - (0x026f5, 0x026f5,), # Sailboat ..Sailboat - (0x026fa, 0x026fa,), # Tent ..Tent - (0x026fd, 0x026fd,), # Fuel Pump ..Fuel Pump - (0x02705, 0x02705,), # White Heavy Check Mark ..White Heavy Check Mark + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand - (0x02728, 0x02728,), # Sparkles ..Sparkles - (0x0274c, 0x0274c,), # Cross Mark ..Cross Mark - (0x0274e, 0x0274e,), # Negative Squared Cross M..Negative Squared Cross M + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross M (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O - (0x02757, 0x02757,), # Heavy Exclamation Mark S..Heavy Exclamation Mark S + (0x02757, 0x02757,), # Heavy Exclamation Mark S (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign - (0x027b0, 0x027b0,), # Curly Loop ..Curly Loop - (0x027bf, 0x027bf,), # Double Curly Loop ..Double Curly Loop + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square - (0x02b50, 0x02b50,), # White Medium Star ..White Medium Star - (0x02b55, 0x02b55,), # Heavy Large Circle ..Heavy Large Circle + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute @@ -570,7 +585,7 @@ (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto (0x03250, 0x032fe,), # Partnership Sign ..Circled Katakana Wo - (0x03300, 0x04dbf,), # Square Apaato ..(nil) + (0x03300, 0x04dbf,), # Square Apaato ..Cjk Unified Ideograph-4d (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo @@ -583,13 +598,13 @@ (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign (0x16fe0, 0x16fe1,), # Tangut Iteration Mark ..Nushu Iteration Mark - (0x17000, 0x187ec,), # (nil) ..(nil) + (0x17000, 0x187ec,), # (nil) (0x18800, 0x18af2,), # Tangut Component-001 ..Tangut Component-755 (0x1b000, 0x1b11e,), # Katakana Letter Archaic ..Hentaigana Letter N-mu-m (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb - (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon ..Mahjong Tile Red Dragon - (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker..Playing Card Black Joker - (0x1f18e, 0x1f18e,), # Negative Squared Ab ..Negative Squared Ab + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker + (0x1f18e, 0x1f18e,), # Negative Squared Ab (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo @@ -603,19 +618,19 @@ (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And (0x1f3e0, 0x1f3f0,), # House Building ..European Castle - (0x1f3f4, 0x1f3f4,), # Waving Black Flag ..Waving Black Flag + (0x1f3f4, 0x1f3f4,), # Waving Black Flag (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints - (0x1f440, 0x1f440,), # Eyes ..Eyes + (0x1f440, 0x1f440,), # Eyes (0x1f442, 0x1f4fc,), # Ear ..Videocassette (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty - (0x1f57a, 0x1f57a,), # Man Dancing ..Man Dancing + (0x1f57a, 0x1f57a,), # Man Dancing (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be - (0x1f5a4, 0x1f5a4,), # Black Heart ..Black Heart + (0x1f5a4, 0x1f5a4,), # Black Heart (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage - (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation ..Sleeping Accommodation + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving (0x1f6f4, 0x1f6f8,), # Scooter ..Flying Saucer @@ -623,50 +638,51 @@ (0x1f940, 0x1f94c,), # Wilted Flower ..Curling Stone (0x1f950, 0x1f96b,), # Croissant ..Canned Food (0x1f980, 0x1f997,), # Crab ..Cricket - (0x1f9c0, 0x1f9c0,), # Cheese Wedge ..Cheese Wedge + (0x1f9c0, 0x1f9c0,), # Cheese Wedge (0x1f9d0, 0x1f9e6,), # Face With Monocle ..Socks (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '11.0.0': ( # Source: EastAsianWidth-11.0.0.txt # Date: 2018-05-14, 09:41:59 GMT [KW, LI] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub - (0x023f0, 0x023f0,), # Alarm Clock ..Alarm Clock - (0x023f3, 0x023f3,), # Hourglass With Flowing S..Hourglass With Flowing S + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing S (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage (0x02648, 0x02653,), # Aries ..Pisces - (0x0267f, 0x0267f,), # Wheelchair Symbol ..Wheelchair Symbol - (0x02693, 0x02693,), # Anchor ..Anchor - (0x026a1, 0x026a1,), # High Voltage Sign ..High Voltage Sign + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle (0x026bd, 0x026be,), # Soccer Ball ..Baseball (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud - (0x026ce, 0x026ce,), # Ophiuchus ..Ophiuchus - (0x026d4, 0x026d4,), # No Entry ..No Entry - (0x026ea, 0x026ea,), # Church ..Church + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church (0x026f2, 0x026f3,), # Fountain ..Flag In Hole - (0x026f5, 0x026f5,), # Sailboat ..Sailboat - (0x026fa, 0x026fa,), # Tent ..Tent - (0x026fd, 0x026fd,), # Fuel Pump ..Fuel Pump - (0x02705, 0x02705,), # White Heavy Check Mark ..White Heavy Check Mark + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand - (0x02728, 0x02728,), # Sparkles ..Sparkles - (0x0274c, 0x0274c,), # Cross Mark ..Cross Mark - (0x0274e, 0x0274e,), # Negative Squared Cross M..Negative Squared Cross M + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross M (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O - (0x02757, 0x02757,), # Heavy Exclamation Mark S..Heavy Exclamation Mark S + (0x02757, 0x02757,), # Heavy Exclamation Mark S (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign - (0x027b0, 0x027b0,), # Curly Loop ..Curly Loop - (0x027bf, 0x027bf,), # Double Curly Loop ..Double Curly Loop + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square - (0x02b50, 0x02b50,), # White Medium Star ..White Medium Star - (0x02b55, 0x02b55,), # Heavy Large Circle ..Heavy Large Circle + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute @@ -681,7 +697,7 @@ (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto (0x03250, 0x032fe,), # Partnership Sign ..Circled Katakana Wo - (0x03300, 0x04dbf,), # Square Apaato ..(nil) + (0x03300, 0x04dbf,), # Square Apaato ..Cjk Unified Ideograph-4d (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo @@ -694,13 +710,13 @@ (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign (0x16fe0, 0x16fe1,), # Tangut Iteration Mark ..Nushu Iteration Mark - (0x17000, 0x187f1,), # (nil) ..(nil) + (0x17000, 0x187f1,), # (nil) (0x18800, 0x18af2,), # Tangut Component-001 ..Tangut Component-755 (0x1b000, 0x1b11e,), # Katakana Letter Archaic ..Hentaigana Letter N-mu-m (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb - (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon ..Mahjong Tile Red Dragon - (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker..Playing Card Black Joker - (0x1f18e, 0x1f18e,), # Negative Squared Ab ..Negative Squared Ab + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker + (0x1f18e, 0x1f18e,), # Negative Squared Ab (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo @@ -714,72 +730,73 @@ (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And (0x1f3e0, 0x1f3f0,), # House Building ..European Castle - (0x1f3f4, 0x1f3f4,), # Waving Black Flag ..Waving Black Flag + (0x1f3f4, 0x1f3f4,), # Waving Black Flag (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints - (0x1f440, 0x1f440,), # Eyes ..Eyes + (0x1f440, 0x1f440,), # Eyes (0x1f442, 0x1f4fc,), # Ear ..Videocassette (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty - (0x1f57a, 0x1f57a,), # Man Dancing ..Man Dancing + (0x1f57a, 0x1f57a,), # Man Dancing (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be - (0x1f5a4, 0x1f5a4,), # Black Heart ..Black Heart + (0x1f5a4, 0x1f5a4,), # Black Heart (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage - (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation ..Sleeping Accommodation + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving (0x1f6f4, 0x1f6f9,), # Scooter ..Skateboard (0x1f910, 0x1f93e,), # Zipper-mouth Face ..Handball (0x1f940, 0x1f970,), # Wilted Flower ..Smiling Face With Smilin (0x1f973, 0x1f976,), # Face With Party Horn And..Freezing Face - (0x1f97a, 0x1f97a,), # Face With Pleading Eyes ..Face With Pleading Eyes + (0x1f97a, 0x1f97a,), # Face With Pleading Eyes (0x1f97c, 0x1f9a2,), # Lab Coat ..Swan (0x1f9b0, 0x1f9b9,), # Emoji Component Red Hair..Supervillain (0x1f9c0, 0x1f9c2,), # Cheese Wedge ..Salt Shaker (0x1f9d0, 0x1f9ff,), # Face With Monocle ..Nazar Amulet (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '12.0.0': ( # Source: EastAsianWidth-12.0.0.txt # Date: 2019-01-21, 14:12:58 GMT [KW, LI] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub - (0x023f0, 0x023f0,), # Alarm Clock ..Alarm Clock - (0x023f3, 0x023f3,), # Hourglass With Flowing S..Hourglass With Flowing S + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing S (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage (0x02648, 0x02653,), # Aries ..Pisces - (0x0267f, 0x0267f,), # Wheelchair Symbol ..Wheelchair Symbol - (0x02693, 0x02693,), # Anchor ..Anchor - (0x026a1, 0x026a1,), # High Voltage Sign ..High Voltage Sign + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle (0x026bd, 0x026be,), # Soccer Ball ..Baseball (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud - (0x026ce, 0x026ce,), # Ophiuchus ..Ophiuchus - (0x026d4, 0x026d4,), # No Entry ..No Entry - (0x026ea, 0x026ea,), # Church ..Church + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church (0x026f2, 0x026f3,), # Fountain ..Flag In Hole - (0x026f5, 0x026f5,), # Sailboat ..Sailboat - (0x026fa, 0x026fa,), # Tent ..Tent - (0x026fd, 0x026fd,), # Fuel Pump ..Fuel Pump - (0x02705, 0x02705,), # White Heavy Check Mark ..White Heavy Check Mark + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand - (0x02728, 0x02728,), # Sparkles ..Sparkles - (0x0274c, 0x0274c,), # Cross Mark ..Cross Mark - (0x0274e, 0x0274e,), # Negative Squared Cross M..Negative Squared Cross M + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross M (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O - (0x02757, 0x02757,), # Heavy Exclamation Mark S..Heavy Exclamation Mark S + (0x02757, 0x02757,), # Heavy Exclamation Mark S (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign - (0x027b0, 0x027b0,), # Curly Loop ..Curly Loop - (0x027bf, 0x027bf,), # Double Curly Loop ..Double Curly Loop + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square - (0x02b50, 0x02b50,), # White Medium Star ..White Medium Star - (0x02b55, 0x02b55,), # Heavy Large Circle ..Heavy Large Circle + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute @@ -794,7 +811,7 @@ (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto (0x03250, 0x032fe,), # Partnership Sign ..Circled Katakana Wo - (0x03300, 0x04dbf,), # Square Apaato ..(nil) + (0x03300, 0x04dbf,), # Square Apaato ..Cjk Unified Ideograph-4d (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo @@ -807,15 +824,15 @@ (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign (0x16fe0, 0x16fe3,), # Tangut Iteration Mark ..Old Chinese Iteration Ma - (0x17000, 0x187f7,), # (nil) ..(nil) + (0x17000, 0x187f7,), # (nil) (0x18800, 0x18af2,), # Tangut Component-001 ..Tangut Component-755 (0x1b000, 0x1b11e,), # Katakana Letter Archaic ..Hentaigana Letter N-mu-m (0x1b150, 0x1b152,), # Hiragana Letter Small Wi..Hiragana Letter Small Wo (0x1b164, 0x1b167,), # Katakana Letter Small Wi..Katakana Letter Small N (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb - (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon ..Mahjong Tile Red Dragon - (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker..Playing Card Black Joker - (0x1f18e, 0x1f18e,), # Negative Squared Ab ..Negative Squared Ab + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker + (0x1f18e, 0x1f18e,), # Negative Squared Ab (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo @@ -829,21 +846,21 @@ (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And (0x1f3e0, 0x1f3f0,), # House Building ..European Castle - (0x1f3f4, 0x1f3f4,), # Waving Black Flag ..Waving Black Flag + (0x1f3f4, 0x1f3f4,), # Waving Black Flag (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints - (0x1f440, 0x1f440,), # Eyes ..Eyes + (0x1f440, 0x1f440,), # Eyes (0x1f442, 0x1f4fc,), # Ear ..Videocassette (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty - (0x1f57a, 0x1f57a,), # Man Dancing ..Man Dancing + (0x1f57a, 0x1f57a,), # Man Dancing (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be - (0x1f5a4, 0x1f5a4,), # Black Heart ..Black Heart + (0x1f5a4, 0x1f5a4,), # Black Heart (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage - (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation ..Sleeping Accommodation + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley - (0x1f6d5, 0x1f6d5,), # Hindu Temple ..Hindu Temple + (0x1f6d5, 0x1f6d5,), # Hindu Temple (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving (0x1f6f4, 0x1f6fa,), # Scooter ..Auto Rickshaw (0x1f7e0, 0x1f7eb,), # Large Orange Circle ..Large Brown Square @@ -858,47 +875,48 @@ (0x1fa80, 0x1fa82,), # Yo-yo ..Parachute (0x1fa90, 0x1fa95,), # Ringed Planet ..Banjo (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '12.1.0': ( # Source: EastAsianWidth-12.1.0.txt # Date: 2019-03-31, 22:01:58 GMT [KW, LI] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub - (0x023f0, 0x023f0,), # Alarm Clock ..Alarm Clock - (0x023f3, 0x023f3,), # Hourglass With Flowing S..Hourglass With Flowing S + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing S (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage (0x02648, 0x02653,), # Aries ..Pisces - (0x0267f, 0x0267f,), # Wheelchair Symbol ..Wheelchair Symbol - (0x02693, 0x02693,), # Anchor ..Anchor - (0x026a1, 0x026a1,), # High Voltage Sign ..High Voltage Sign + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle (0x026bd, 0x026be,), # Soccer Ball ..Baseball (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud - (0x026ce, 0x026ce,), # Ophiuchus ..Ophiuchus - (0x026d4, 0x026d4,), # No Entry ..No Entry - (0x026ea, 0x026ea,), # Church ..Church + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church (0x026f2, 0x026f3,), # Fountain ..Flag In Hole - (0x026f5, 0x026f5,), # Sailboat ..Sailboat - (0x026fa, 0x026fa,), # Tent ..Tent - (0x026fd, 0x026fd,), # Fuel Pump ..Fuel Pump - (0x02705, 0x02705,), # White Heavy Check Mark ..White Heavy Check Mark + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand - (0x02728, 0x02728,), # Sparkles ..Sparkles - (0x0274c, 0x0274c,), # Cross Mark ..Cross Mark - (0x0274e, 0x0274e,), # Negative Squared Cross M..Negative Squared Cross M + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross M (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O - (0x02757, 0x02757,), # Heavy Exclamation Mark S..Heavy Exclamation Mark S + (0x02757, 0x02757,), # Heavy Exclamation Mark S (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign - (0x027b0, 0x027b0,), # Curly Loop ..Curly Loop - (0x027bf, 0x027bf,), # Double Curly Loop ..Double Curly Loop + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square - (0x02b50, 0x02b50,), # White Medium Star ..White Medium Star - (0x02b55, 0x02b55,), # Heavy Large Circle ..Heavy Large Circle + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute @@ -912,7 +930,7 @@ (0x031c0, 0x031e3,), # Cjk Stroke T ..Cjk Stroke Q (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto - (0x03250, 0x04dbf,), # Partnership Sign ..(nil) + (0x03250, 0x04dbf,), # Partnership Sign ..Cjk Unified Ideograph-4d (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo @@ -925,15 +943,15 @@ (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign (0x16fe0, 0x16fe3,), # Tangut Iteration Mark ..Old Chinese Iteration Ma - (0x17000, 0x187f7,), # (nil) ..(nil) + (0x17000, 0x187f7,), # (nil) (0x18800, 0x18af2,), # Tangut Component-001 ..Tangut Component-755 (0x1b000, 0x1b11e,), # Katakana Letter Archaic ..Hentaigana Letter N-mu-m (0x1b150, 0x1b152,), # Hiragana Letter Small Wi..Hiragana Letter Small Wo (0x1b164, 0x1b167,), # Katakana Letter Small Wi..Katakana Letter Small N (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb - (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon ..Mahjong Tile Red Dragon - (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker..Playing Card Black Joker - (0x1f18e, 0x1f18e,), # Negative Squared Ab ..Negative Squared Ab + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker + (0x1f18e, 0x1f18e,), # Negative Squared Ab (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo @@ -947,21 +965,21 @@ (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And (0x1f3e0, 0x1f3f0,), # House Building ..European Castle - (0x1f3f4, 0x1f3f4,), # Waving Black Flag ..Waving Black Flag + (0x1f3f4, 0x1f3f4,), # Waving Black Flag (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints - (0x1f440, 0x1f440,), # Eyes ..Eyes + (0x1f440, 0x1f440,), # Eyes (0x1f442, 0x1f4fc,), # Ear ..Videocassette (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty - (0x1f57a, 0x1f57a,), # Man Dancing ..Man Dancing + (0x1f57a, 0x1f57a,), # Man Dancing (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be - (0x1f5a4, 0x1f5a4,), # Black Heart ..Black Heart + (0x1f5a4, 0x1f5a4,), # Black Heart (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage - (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation ..Sleeping Accommodation + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley - (0x1f6d5, 0x1f6d5,), # Hindu Temple ..Hindu Temple + (0x1f6d5, 0x1f6d5,), # Hindu Temple (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving (0x1f6f4, 0x1f6fa,), # Scooter ..Auto Rickshaw (0x1f7e0, 0x1f7eb,), # Large Orange Circle ..Large Brown Square @@ -976,47 +994,48 @@ (0x1fa80, 0x1fa82,), # Yo-yo ..Parachute (0x1fa90, 0x1fa95,), # Ringed Planet ..Banjo (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '13.0.0': ( # Source: EastAsianWidth-13.0.0.txt # Date: 2029-01-21, 18:14:00 GMT [KW, LI] # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub - (0x023f0, 0x023f0,), # Alarm Clock ..Alarm Clock - (0x023f3, 0x023f3,), # Hourglass With Flowing S..Hourglass With Flowing S + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing S (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage (0x02648, 0x02653,), # Aries ..Pisces - (0x0267f, 0x0267f,), # Wheelchair Symbol ..Wheelchair Symbol - (0x02693, 0x02693,), # Anchor ..Anchor - (0x026a1, 0x026a1,), # High Voltage Sign ..High Voltage Sign + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle (0x026bd, 0x026be,), # Soccer Ball ..Baseball (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud - (0x026ce, 0x026ce,), # Ophiuchus ..Ophiuchus - (0x026d4, 0x026d4,), # No Entry ..No Entry - (0x026ea, 0x026ea,), # Church ..Church + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church (0x026f2, 0x026f3,), # Fountain ..Flag In Hole - (0x026f5, 0x026f5,), # Sailboat ..Sailboat - (0x026fa, 0x026fa,), # Tent ..Tent - (0x026fd, 0x026fd,), # Fuel Pump ..Fuel Pump - (0x02705, 0x02705,), # White Heavy Check Mark ..White Heavy Check Mark + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand - (0x02728, 0x02728,), # Sparkles ..Sparkles - (0x0274c, 0x0274c,), # Cross Mark ..Cross Mark - (0x0274e, 0x0274e,), # Negative Squared Cross M..Negative Squared Cross M + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross M (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O - (0x02757, 0x02757,), # Heavy Exclamation Mark S..Heavy Exclamation Mark S + (0x02757, 0x02757,), # Heavy Exclamation Mark S (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign - (0x027b0, 0x027b0,), # Curly Loop ..Curly Loop - (0x027bf, 0x027bf,), # Double Curly Loop ..Double Curly Loop + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square - (0x02b50, 0x02b50,), # White Medium Star ..White Medium Star - (0x02b55, 0x02b55,), # Heavy Large Circle ..Heavy Large Circle + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute @@ -1029,7 +1048,7 @@ (0x03190, 0x031e3,), # Ideographic Annotation L..Cjk Stroke Q (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto - (0x03250, 0x04dbf,), # Partnership Sign ..(nil) + (0x03250, 0x04dbf,), # Partnership Sign ..Cjk Unified Ideograph-4d (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo @@ -1041,18 +1060,18 @@ (0x0fe68, 0x0fe6b,), # Small Reverse Solidus ..Small Commercial At (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign - (0x16fe0, 0x16fe4,), # Tangut Iteration Mark ..(nil) - (0x16ff0, 0x16ff1,), # (nil) ..(nil) - (0x17000, 0x187f7,), # (nil) ..(nil) - (0x18800, 0x18cd5,), # Tangut Component-001 ..(nil) - (0x18d00, 0x18d08,), # (nil) ..(nil) + (0x16fe0, 0x16fe4,), # Tangut Iteration Mark ..Khitan Small Script Fill + (0x16ff0, 0x16ff1,), # Vietnamese Alternate Rea..Vietnamese Alternate Rea + (0x17000, 0x187f7,), # (nil) + (0x18800, 0x18cd5,), # Tangut Component-001 ..Khitan Small Script Char + (0x18d00, 0x18d08,), # (nil) (0x1b000, 0x1b11e,), # Katakana Letter Archaic ..Hentaigana Letter N-mu-m (0x1b150, 0x1b152,), # Hiragana Letter Small Wi..Hiragana Letter Small Wo (0x1b164, 0x1b167,), # Katakana Letter Small Wi..Katakana Letter Small N (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb - (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon ..Mahjong Tile Red Dragon - (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker..Playing Card Black Joker - (0x1f18e, 0x1f18e,), # Negative Squared Ab ..Negative Squared Ab + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker + (0x1f18e, 0x1f18e,), # Negative Squared Ab (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo @@ -1066,37 +1085,164 @@ (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And (0x1f3e0, 0x1f3f0,), # House Building ..European Castle - (0x1f3f4, 0x1f3f4,), # Waving Black Flag ..Waving Black Flag + (0x1f3f4, 0x1f3f4,), # Waving Black Flag (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints - (0x1f440, 0x1f440,), # Eyes ..Eyes + (0x1f440, 0x1f440,), # Eyes (0x1f442, 0x1f4fc,), # Ear ..Videocassette (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty - (0x1f57a, 0x1f57a,), # Man Dancing ..Man Dancing + (0x1f57a, 0x1f57a,), # Man Dancing (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be - (0x1f5a4, 0x1f5a4,), # Black Heart ..Black Heart + (0x1f5a4, 0x1f5a4,), # Black Heart (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage - (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation ..Sleeping Accommodation + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley - (0x1f6d5, 0x1f6d7,), # Hindu Temple ..(nil) + (0x1f6d5, 0x1f6d7,), # Hindu Temple ..Elevator (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving - (0x1f6f4, 0x1f6fc,), # Scooter ..(nil) + (0x1f6f4, 0x1f6fc,), # Scooter ..Roller Skate (0x1f7e0, 0x1f7eb,), # Large Orange Circle ..Large Brown Square - (0x1f90c, 0x1f93a,), # (nil) ..Fencer + (0x1f90c, 0x1f93a,), # Pinched Fingers ..Fencer (0x1f93c, 0x1f945,), # Wrestlers ..Goal Net - (0x1f947, 0x1f978,), # First Place Medal ..(nil) - (0x1f97a, 0x1f9cb,), # Face With Pleading Eyes ..(nil) + (0x1f947, 0x1f978,), # First Place Medal ..Disguised Face + (0x1f97a, 0x1f9cb,), # Face With Pleading Eyes ..Bubble Tea (0x1f9cd, 0x1f9ff,), # Standing Person ..Nazar Amulet - (0x1fa70, 0x1fa74,), # Ballet Shoes ..(nil) + (0x1fa70, 0x1fa74,), # Ballet Shoes ..Thong Sandal (0x1fa78, 0x1fa7a,), # Drop Of Blood ..Stethoscope - (0x1fa80, 0x1fa86,), # Yo-yo ..(nil) - (0x1fa90, 0x1faa8,), # Ringed Planet ..(nil) - (0x1fab0, 0x1fab6,), # (nil) ..(nil) - (0x1fac0, 0x1fac2,), # (nil) ..(nil) - (0x1fad0, 0x1fad6,), # (nil) ..(nil) + (0x1fa80, 0x1fa86,), # Yo-yo ..Nesting Dolls + (0x1fa90, 0x1faa8,), # Ringed Planet ..Rock + (0x1fab0, 0x1fab6,), # Fly ..Feather + (0x1fac0, 0x1fac2,), # Anatomical Heart ..People Hugging + (0x1fad0, 0x1fad6,), # Blueberries ..Teapot (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) - (0x30000, 0x3fffd,), # (nil) ..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) + ), + '14.0.0': ( + # Source: EastAsianWidth-14.0.0.txt + # Date: 2021-07-06, 09:58:53 GMT [KW, LI] + # + (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler + (0x0231a, 0x0231b,), # Watch ..Hourglass + (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra + (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing S + (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar + (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage + (0x02648, 0x02653,), # Aries ..Pisces + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign + (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle + (0x026bd, 0x026be,), # Soccer Ball ..Baseball + (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church + (0x026f2, 0x026f3,), # Fountain ..Flag In Hole + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark + (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross M + (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O + (0x02757, 0x02757,), # Heavy Exclamation Mark S + (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop + (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle + (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap + (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified + (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute + (0x02ff0, 0x02ffb,), # Ideographic Description ..Ideographic Description + (0x03000, 0x0303e,), # Ideographic Space ..Ideographic Variation In + (0x03041, 0x03096,), # Hiragana Letter Small A ..Hiragana Letter Small Ke + (0x03099, 0x030ff,), # Combining Katakana-hirag..Katakana Digraph Koto + (0x03105, 0x0312f,), # Bopomofo Letter B ..Bopomofo Letter Nn + (0x03131, 0x0318e,), # Hangul Letter Kiyeok ..Hangul Letter Araeae + (0x03190, 0x031e3,), # Ideographic Annotation L..Cjk Stroke Q + (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha + (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto + (0x03250, 0x04dbf,), # Partnership Sign ..Cjk Unified Ideograph-4d + (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr + (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke + (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo + (0x0ac00, 0x0d7a3,), # Hangul Syllable Ga ..Hangul Syllable Hih + (0x0f900, 0x0faff,), # Cjk Compatibility Ideogr..(nil) + (0x0fe10, 0x0fe19,), # Presentation Form For Ve..Presentation Form For Ve + (0x0fe30, 0x0fe52,), # Presentation Form For Ve..Small Full Stop + (0x0fe54, 0x0fe66,), # Small Semicolon ..Small Equals Sign + (0x0fe68, 0x0fe6b,), # Small Reverse Solidus ..Small Commercial At + (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa + (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign + (0x16fe0, 0x16fe4,), # Tangut Iteration Mark ..Khitan Small Script Fill + (0x16ff0, 0x16ff1,), # Vietnamese Alternate Rea..Vietnamese Alternate Rea + (0x17000, 0x187f7,), # (nil) + (0x18800, 0x18cd5,), # Tangut Component-001 ..Khitan Small Script Char + (0x18d00, 0x18d08,), # (nil) + (0x1aff0, 0x1aff3,), # (nil) + (0x1aff5, 0x1affb,), # (nil) + (0x1affd, 0x1affe,), # (nil) + (0x1b000, 0x1b122,), # Katakana Letter Archaic ..(nil) + (0x1b150, 0x1b152,), # Hiragana Letter Small Wi..Hiragana Letter Small Wo + (0x1b164, 0x1b167,), # Katakana Letter Small Wi..Katakana Letter Small N + (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker + (0x1f18e, 0x1f18e,), # Negative Squared Ab + (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs + (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa + (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo + (0x1f240, 0x1f248,), # Tortoise Shell Bracketed..Tortoise Shell Bracketed + (0x1f250, 0x1f251,), # Circled Ideograph Advant..Circled Ideograph Accept + (0x1f260, 0x1f265,), # Rounded Symbol For Fu ..Rounded Symbol For Cai + (0x1f300, 0x1f320,), # Cyclone ..Shooting Star + (0x1f32d, 0x1f335,), # Hot Dog ..Cactus + (0x1f337, 0x1f37c,), # Tulip ..Baby Bottle + (0x1f37e, 0x1f393,), # Bottle With Popping Cork..Graduation Cap + (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer + (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And + (0x1f3e0, 0x1f3f0,), # House Building ..European Castle + (0x1f3f4, 0x1f3f4,), # Waving Black Flag + (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints + (0x1f440, 0x1f440,), # Eyes + (0x1f442, 0x1f4fc,), # Ear ..Videocassette + (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red + (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch + (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty + (0x1f57a, 0x1f57a,), # Man Dancing + (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be + (0x1f5a4, 0x1f5a4,), # Black Heart + (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands + (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation + (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley + (0x1f6d5, 0x1f6d7,), # Hindu Temple ..Elevator + (0x1f6dd, 0x1f6df,), # (nil) + (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving + (0x1f6f4, 0x1f6fc,), # Scooter ..Roller Skate + (0x1f7e0, 0x1f7eb,), # Large Orange Circle ..Large Brown Square + (0x1f7f0, 0x1f7f0,), # (nil) + (0x1f90c, 0x1f93a,), # Pinched Fingers ..Fencer + (0x1f93c, 0x1f945,), # Wrestlers ..Goal Net + (0x1f947, 0x1f9ff,), # First Place Medal ..Nazar Amulet + (0x1fa70, 0x1fa74,), # Ballet Shoes ..Thong Sandal + (0x1fa78, 0x1fa7c,), # Drop Of Blood ..(nil) + (0x1fa80, 0x1fa86,), # Yo-yo ..Nesting Dolls + (0x1fa90, 0x1faac,), # Ringed Planet ..(nil) + (0x1fab0, 0x1faba,), # Fly ..(nil) + (0x1fac0, 0x1fac5,), # Anatomical Heart ..(nil) + (0x1fad0, 0x1fad9,), # Blueberries ..(nil) + (0x1fae0, 0x1fae7,), # (nil) + (0x1faf0, 0x1faf6,), # (nil) + (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), } diff --git a/wcwidth/table_zero.py b/wcwidth/table_zero.py index 73aa689..4e3bcff 100644 --- a/wcwidth/table_zero.py +++ b/wcwidth/table_zero.py @@ -1,360 +1,376 @@ -"""Zero_Width table, created by bin/update-tables.py.""" -# Generated: 2020-06-23T15:58:43.900697 +""" +Exports ZERO_WIDTH table keyed by supporting unicode version level. + +This code generated by wcwidth/bin/update-tables.py on 2022-03-20 21:12:52 UTC. +""" ZERO_WIDTH = { '4.1.0': ( # Source: DerivedGeneralCategory-4.1.0.txt # Date: 2005-02-26, 02:35:50 GMT [MD] # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00486,), # Combining Cyrillic Titlo..Combining Cyrillic Psili - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli (0x00591, 0x005b9,), # Hebrew Accent Etnahta ..Hebrew Point Holam (0x005bb, 0x005bd,), # Hebrew Point Qubuts ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x00615,), # Arabic Sign Sallallahou ..Arabic Small High Tah (0x0064b, 0x0065e,), # Arabic Fathatan ..Arabic Fatha With Two Do - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen - (0x006de, 0x006e4,), # Arabic Start Of Rub El H..Arabic Small High Madda + (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x00901, 0x00902,), # Devanagari Sign Candrabi..Devanagari Sign Anusvara - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00954,), # Devanagari Stress Sign U..Devanagari Acute Accent (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b43,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00d41, 0x00d43,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f90, 0x00f97,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu - (0x01032, 0x01032,), # Myanmar Vowel Sign Ai ..Myanmar Vowel Sign Ai + (0x01032, 0x01032,), # Myanmar Vowel Sign Ai (0x01036, 0x01037,), # Myanmar Sign Anusvara ..Myanmar Sign Dot Below - (0x01039, 0x01039,), # Myanmar Sign Virama ..Myanmar Sign Virama + (0x01039, 0x01039,), # Myanmar Sign Virama (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal - (0x0135f, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin + (0x0135f, 0x0135f,), # Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod (0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U (0x01dc0, 0x01dc3,), # Combining Dotted Grave A..Combining Suspension Mar - (0x020d0, 0x020eb,), # Combining Left Harpoon A..Combining Long Double So + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020eb,), # Combining Reverse Solidu..Combining Long Double So (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe23,), # Combining Ligature Left ..Combining Double Tilde R (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining (0x1d185, 0x1d18b,), # Musical Symbol Combining..Musical Symbol Combining (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x006de, 0x006de,), # Arabic Start Of Rub El H + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa ), '5.0.0': ( # Source: DerivedGeneralCategory-5.0.0.txt # Date: 2006-02-27, 23:41:27 GMT [MD] # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00486,), # Combining Cyrillic Titlo..Combining Cyrillic Psili - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x00615,), # Arabic Sign Sallallahou ..Arabic Small High Tah (0x0064b, 0x0065e,), # Arabic Fathatan ..Arabic Fatha With Two Do - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen - (0x006de, 0x006e4,), # Arabic Start Of Rub El H..Arabic Small High Madda + (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot (0x00901, 0x00902,), # Devanagari Sign Candrabi..Devanagari Sign Anusvara - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00954,), # Devanagari Stress Sign U..Devanagari Acute Accent (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b43,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d41, 0x00d43,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f90, 0x00f97,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu - (0x01032, 0x01032,), # Myanmar Vowel Sign Ai ..Myanmar Vowel Sign Ai + (0x01032, 0x01032,), # Myanmar Vowel Sign Ai (0x01036, 0x01037,), # Myanmar Sign Anusvara ..Myanmar Sign Dot Below - (0x01039, 0x01039,), # Myanmar Sign Virama ..Myanmar Sign Virama + (0x01039, 0x01039,), # Myanmar Sign Virama (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal - (0x0135f, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin + (0x0135f, 0x0135f,), # Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod (0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01dc0, 0x01dca,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfe, 0x01dff,), # Combining Left Arrowhead..Combining Right Arrowhea - (0x020d0, 0x020ef,), # Combining Left Harpoon A..Combining Right Arrow Be + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020ef,), # Combining Reverse Solidu..Combining Right Arrow Be (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe23,), # Combining Ligature Left ..Combining Double Tilde R (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining (0x1d185, 0x1d18b,), # Musical Symbol Combining..Musical Symbol Combining (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x006de, 0x006de,), # Arabic Start Of Rub El H + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa ), '5.1.0': ( # Source: DerivedGeneralCategory-5.1.0.txt # Date: 2008-03-20, 17:54:57 GMT [MD] # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065e,), # Arabic Fathatan ..Arabic Fatha With Two Do - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen - (0x006de, 0x006e4,), # Arabic Start Of Rub El H..Arabic Small High Madda + (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot (0x00901, 0x00902,), # Devanagari Sign Candrabi..Devanagari Sign Anusvara - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00954,), # Devanagari Stress Sign U..Devanagari Acute Accent (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f90, 0x00f97,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -362,30 +378,30 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S..Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign S (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci..Myanmar Sign Shan Counci - (0x0135f, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0135f, 0x0135f,), # Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod (0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan @@ -394,59 +410,67 @@ (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfe, 0x01dff,), # Combining Left Arrowhead..Combining Right Arrowhea - (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a67c, 0x0a67d,), # Combining Cyrillic Kavyk..Combining Cyrillic Payer - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama ..Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe26,), # Combining Ligature Left ..Combining Conjoining Mac - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi..Phaistos Disc Sign Combi + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining (0x1d185, 0x1d18b,), # Musical Symbol Combining..Musical Symbol Combining (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x006de, 0x006de,), # Arabic Start Of Rub El H + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '5.2.0': ( # Source: DerivedGeneralCategory-5.2.0.txt # Date: 2009-08-22, 04:58:21 GMT [MD] # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065e,), # Arabic Fathatan ..Arabic Fatha With Two Do - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen - (0x006de, 0x006e4,), # Arabic Start Of Rub El H..Arabic Small High Madda + (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -455,73 +479,73 @@ (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U (0x00829, 0x0082d,), # Samaritan Vowel Sign Lon..Samaritan Mark Nequdaa (0x00900, 0x00902,), # Devanagari Sign Inverted..Devanagari Sign Anusvara - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00955,), # Devanagari Stress Sign U..Devanagari Vowel Sign Ca (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f90, 0x00f97,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -529,38 +553,38 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S..Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign S (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci..Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton..Myanmar Vowel Sign Aiton - (0x0135f, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0135f, 0x0135f,), # Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod (0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot ..Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai ..Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt..Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan @@ -570,51 +594,53 @@ (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak ..Vedic Sign Tiryak + (0x01ced, 0x01ced,), # Vedic Sign Tiryak (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfd, 0x01dff,), # Combining Almost Equal T..Combining Right Arrowhea - (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a67c, 0x0a67d,), # Combining Cyrillic Kavyk..Combining Cyrillic Payer (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama ..Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar - (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu..Javanese Sign Cecak Telu + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe..Javanese Vowel Sign Pepe + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang ..Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho ..Tai Viet Tone Mai Tho - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek ..Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe26,), # Combining Ligature Left ..Combining Conjoining Mac - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi..Phaistos Disc Sign Combi + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x11080, 0x11081,), # Kaithi Sign Candrabindu ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai (0x110b9, 0x110ba,), # Kaithi Sign Virama ..Kaithi Sign Nukta @@ -624,26 +650,32 @@ (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x006de, 0x006de,), # Arabic Start Of Rub El H + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '6.0.0': ( # Source: DerivedGeneralCategory-6.0.0.txt # Date: 2010-08-19, 00:48:09 GMT [MD] # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -653,74 +685,74 @@ (0x00829, 0x0082d,), # Samaritan Vowel Sign Lon..Samaritan Mark Nequdaa (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x00900, 0x00902,), # Devanagari Sign Inverted..Devanagari Sign Anusvara - (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe..Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -728,98 +760,100 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S..Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign S (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci..Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton..Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod (0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot ..Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai ..Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt..Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan - (0x01be6, 0x01be6,), # Batak Sign Tompi ..Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O ..Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak ..Vedic Sign Tiryak + (0x01ced, 0x01ced,), # Vedic Sign Tiryak (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea - (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine..Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a67c, 0x0a67d,), # Combining Cyrillic Kavyk..Combining Cyrillic Payer (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama ..Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar - (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu..Javanese Sign Cecak Telu + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe..Javanese Vowel Sign Pepe + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang ..Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho ..Tai Viet Tone Mai Tho - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek ..Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe26,), # Combining Ligature Left ..Combining Conjoining Mac - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi..Phaistos Disc Sign Combi + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama - (0x11001, 0x11001,), # Brahmi Sign Anusvara ..Brahmi Sign Anusvara + (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x11080, 0x11081,), # Kaithi Sign Candrabindu ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -830,26 +864,31 @@ (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '6.1.0': ( # Source: DerivedGeneralCategory-6.1.0.txt # Date: 2011-11-27, 05:10:22 GMT [MD] # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -860,74 +899,74 @@ (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x008e4, 0x008fe,), # Arabic Curly Fatha ..Arabic Damma With Dot (0x00900, 0x00902,), # Devanagari Sign Inverted..Devanagari Sign Anusvara - (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe..Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -935,10 +974,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S..Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign S (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci..Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton..Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -946,93 +985,95 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot ..Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai ..Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt..Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan - (0x01bab, 0x01bab,), # Sundanese Sign Virama ..Sundanese Sign Virama - (0x01be6, 0x01be6,), # Batak Sign Tompi ..Batak Sign Tompi + (0x01bab, 0x01bab,), # Sundanese Sign Virama + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O ..Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak ..Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above ..Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea - (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine..Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer - (0x0a69f, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette + (0x0a69f, 0x0a69f,), # Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama ..Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar - (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu..Javanese Sign Cecak Telu + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe..Javanese Vowel Sign Pepe + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang ..Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho ..Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama ..Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek ..Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe26,), # Combining Ligature Left ..Combining Conjoining Mac - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi..Phaistos Disc Sign Combi + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama - (0x11001, 0x11001,), # Brahmi Sign Anusvara ..Brahmi Sign Anusvara + (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x11080, 0x11081,), # Kaithi Sign Candrabindu ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -1042,10 +1083,10 @@ (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O - (0x116ab, 0x116ab,), # Takri Sign Anusvara ..Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa ..Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta ..Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining @@ -1053,26 +1094,31 @@ (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '6.2.0': ( # Source: DerivedGeneralCategory-6.2.0.txt # Date: 2012-05-20, 00:42:34 GMT [MD] # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -1083,74 +1129,74 @@ (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x008e4, 0x008fe,), # Arabic Curly Fatha ..Arabic Damma With Dot (0x00900, 0x00902,), # Devanagari Sign Inverted..Devanagari Sign Anusvara - (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe..Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -1158,10 +1204,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S..Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign S (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci..Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton..Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -1169,93 +1215,95 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot ..Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai ..Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt..Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan - (0x01bab, 0x01bab,), # Sundanese Sign Virama ..Sundanese Sign Virama - (0x01be6, 0x01be6,), # Batak Sign Tompi ..Batak Sign Tompi + (0x01bab, 0x01bab,), # Sundanese Sign Virama + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O ..Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak ..Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above ..Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea - (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine..Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer - (0x0a69f, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette + (0x0a69f, 0x0a69f,), # Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama ..Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar - (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu..Javanese Sign Cecak Telu + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe..Javanese Vowel Sign Pepe + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang ..Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho ..Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama ..Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek ..Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe26,), # Combining Ligature Left ..Combining Conjoining Mac - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi..Phaistos Disc Sign Combi + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama - (0x11001, 0x11001,), # Brahmi Sign Anusvara ..Brahmi Sign Anusvara + (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x11080, 0x11081,), # Kaithi Sign Candrabindu ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -1265,10 +1313,10 @@ (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O - (0x116ab, 0x116ab,), # Takri Sign Anusvara ..Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa ..Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta ..Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining @@ -1276,26 +1324,31 @@ (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '6.3.0': ( # Source: DerivedGeneralCategory-6.3.0.txt # Date: 2013-07-05, 14:08:45 GMT [MD] # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -1306,74 +1359,74 @@ (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x008e4, 0x008fe,), # Arabic Curly Fatha ..Arabic Damma With Dot (0x00900, 0x00902,), # Devanagari Sign Inverted..Devanagari Sign Anusvara - (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe..Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -1381,10 +1434,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S..Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign S (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci..Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton..Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -1392,94 +1445,96 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae ..Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot ..Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai ..Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt..Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan - (0x01bab, 0x01bab,), # Sundanese Sign Virama ..Sundanese Sign Virama - (0x01be6, 0x01be6,), # Batak Sign Tompi ..Batak Sign Tompi + (0x01bab, 0x01bab,), # Sundanese Sign Virama + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O ..Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak ..Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above ..Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea - (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine..Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer - (0x0a69f, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette + (0x0a69f, 0x0a69f,), # Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama ..Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar - (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu..Javanese Sign Cecak Telu + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe..Javanese Vowel Sign Pepe + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang ..Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho ..Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama ..Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek ..Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe26,), # Combining Ligature Left ..Combining Conjoining Mac - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi..Phaistos Disc Sign Combi + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama - (0x11001, 0x11001,), # Brahmi Sign Anusvara ..Brahmi Sign Anusvara + (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x11080, 0x11081,), # Kaithi Sign Candrabindu ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -1489,10 +1544,10 @@ (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O - (0x116ab, 0x116ab,), # Takri Sign Anusvara ..Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa ..Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta ..Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining @@ -1500,26 +1555,31 @@ (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '7.0.0': ( # Source: DerivedGeneralCategory-7.0.0.txt # Date: 2014-02-07, 18:42:12 GMT [MD] # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -1529,77 +1589,77 @@ (0x00829, 0x0082d,), # Samaritan Vowel Sign Lon..Samaritan Mark Nequdaa (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x008e4, 0x00902,), # Arabic Curly Fatha ..Devanagari Sign Anusvara - (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe..Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca..Telugu Sign Combining Ca + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Ca (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00c81, 0x00c81,), # Kannada Sign Candrabindu..Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00c81, 0x00c81,), # Kannada Sign Candrabindu + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal - (0x00d01, 0x00d01,), # Malayalam Sign Candrabin..Malayalam Sign Candrabin + (0x00d01, 0x00d01,), # Malayalam Sign Candrabin (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -1607,10 +1667,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S..Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign S (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci..Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton..Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -1618,101 +1678,103 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae ..Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot ..Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai ..Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt..Tai Tham Combining Crypt - (0x01ab0, 0x01abe,), # Combining Doubled Circum..Combining Parentheses Ov + (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi ..Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O ..Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak ..Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above ..Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df5,), # Combining Dotted Grave A..Combining Up Tack Above (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea - (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine..Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer - (0x0a69f, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette + (0x0a69f, 0x0a69f,), # Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama ..Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar - (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu..Javanese Sign Cecak Telu + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe..Javanese Vowel Sign Pepe - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw ..Myanmar Sign Shan Saw + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T..Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang ..Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho ..Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama ..Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek ..Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2d,), # Combining Ligature Left ..Combining Conjoining Mac - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi..Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M..Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x102e0, 0x102e0,), # Coptic Epact Thousands M (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation - (0x11001, 0x11001,), # Brahmi Sign Anusvara ..Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -1720,33 +1782,33 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta ..Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara ..Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x112df, 0x112df,), # Khudawadi Sign Anusvara ..Khudawadi Sign Anusvara + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama - (0x11301, 0x11301,), # Grantha Sign Candrabindu..Grantha Sign Candrabindu - (0x1133c, 0x1133c,), # Grantha Sign Nukta ..Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii ..Grantha Vowel Sign Ii + (0x11301, 0x11301,), # Grantha Sign Candrabindu + (0x1133c, 0x1133c,), # Grantha Sign Nukta + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short..Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal (0x115bc, 0x115bd,), # Siddham Sign Candrabindu..Siddham Sign Anusvara (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara ..Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara ..Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa ..Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta ..Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below @@ -1758,26 +1820,32 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '8.0.0': ( # Source: DerivedGeneralCategory-8.0.0.txt # Date: 2015-02-13, 13:47:11 GMT [MD] # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -1787,77 +1855,77 @@ (0x00829, 0x0082d,), # Samaritan Vowel Sign Lon..Samaritan Mark Nequdaa (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara - (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe..Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca..Telugu Sign Combining Ca + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Ca (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00c81, 0x00c81,), # Kannada Sign Candrabindu..Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00c81, 0x00c81,), # Kannada Sign Candrabindu + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal - (0x00d01, 0x00d01,), # Malayalam Sign Candrabin..Malayalam Sign Candrabin + (0x00d01, 0x00d01,), # Malayalam Sign Candrabin (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -1865,10 +1933,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S..Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign S (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci..Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton..Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -1876,101 +1944,103 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae ..Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot ..Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai ..Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt..Tai Tham Combining Crypt - (0x01ab0, 0x01abe,), # Combining Doubled Circum..Combining Parentheses Ov + (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi ..Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O ..Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak ..Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above ..Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df5,), # Combining Dotted Grave A..Combining Up Tack Above (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea - (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine..Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama ..Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar - (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu..Javanese Sign Cecak Telu + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe..Javanese Vowel Sign Pepe - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw ..Myanmar Sign Shan Saw + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T..Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang ..Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho ..Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama ..Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek ..Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi..Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M..Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x102e0, 0x102e0,), # Coptic Epact Thousands M (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation - (0x11001, 0x11001,), # Brahmi Sign Anusvara ..Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -1978,22 +2048,22 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta ..Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111ca, 0x111cc,), # Sharada Sign Nukta ..Sharada Extra Short Vowe (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara ..Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x112df, 0x112df,), # Khudawadi Sign Anusvara ..Khudawadi Sign Anusvara + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu - (0x1133c, 0x1133c,), # Grantha Sign Nukta ..Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii ..Grantha Vowel Sign Ii + (0x1133c, 0x1133c,), # Grantha Sign Nukta + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short..Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -2001,12 +2071,12 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara ..Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara ..Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa ..Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta ..Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer @@ -2021,32 +2091,38 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T..Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea..Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body T + (0x1da84, 0x1da84,), # Signwriting Location Hea (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '9.0.0': ( # Source: DerivedGeneralCategory-9.0.0.txt # Date: 2016-06-01, 10:34:26 GMT # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -2057,77 +2133,77 @@ (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x008d4, 0x008e1,), # Arabic Small High Word A..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara - (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe..Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca..Telugu Sign Combining Ca + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Ca (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00c81, 0x00c81,), # Kannada Sign Candrabindu..Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00c81, 0x00c81,), # Kannada Sign Candrabindu + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal - (0x00d01, 0x00d01,), # Malayalam Sign Candrabin..Malayalam Sign Candrabin + (0x00d01, 0x00d01,), # Malayalam Sign Candrabin (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -2135,10 +2211,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S..Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign S (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci..Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton..Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -2146,102 +2222,104 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae ..Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot ..Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai ..Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt..Tai Tham Combining Crypt - (0x01ab0, 0x01abe,), # Combining Doubled Circum..Combining Parentheses Ov + (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi ..Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O ..Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak ..Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above ..Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df5,), # Combining Dotted Grave A..Combining Up Tack Above (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea - (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine..Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar - (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu..Javanese Sign Cecak Telu + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe..Javanese Vowel Sign Pepe - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw ..Myanmar Sign Shan Saw + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T..Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang ..Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho ..Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama ..Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek ..Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi..Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M..Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x102e0, 0x102e0,), # Coptic Epact Thousands M (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation - (0x11001, 0x11001,), # Brahmi Sign Anusvara ..Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -2249,26 +2327,26 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta ..Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111ca, 0x111cc,), # Sharada Sign Nukta ..Sharada Extra Short Vowe (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara ..Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x1123e, 0x1123e,), # Khojki Sign Sukun ..Khojki Sign Sukun - (0x112df, 0x112df,), # Khudawadi Sign Anusvara ..Khudawadi Sign Anusvara + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu - (0x1133c, 0x1133c,), # Grantha Sign Nukta ..Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii ..Grantha Vowel Sign Ii + (0x1133c, 0x1133c,), # Grantha Sign Nukta + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara - (0x11446, 0x11446,), # Newa Sign Nukta ..Newa Sign Nukta + (0x11446, 0x11446,), # Newa Sign Nukta (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short..Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -2276,18 +2354,18 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara ..Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara ..Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa ..Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta ..Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara - (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama ..Bhaiksuki Sign Virama + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E @@ -2303,8 +2381,8 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T..Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea..Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body T + (0x1da84, 0x1da84,), # Signwriting Location Hea (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let @@ -2315,26 +2393,32 @@ (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '10.0.0': ( # Source: DerivedGeneralCategory-10.0.0.txt # Date: 2017-03-08, 08:41:49 GMT # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -2345,79 +2429,79 @@ (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x008d4, 0x008e1,), # Arabic Small High Word A..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara - (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe..Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca..Telugu Sign Combining Ca + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Ca (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00c81, 0x00c81,), # Kannada Sign Candrabindu..Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00c81, 0x00c81,), # Kannada Sign Candrabindu + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d00, 0x00d01,), # Malayalam Sign Combining..Malayalam Sign Candrabin (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -2425,10 +2509,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S..Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign S (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci..Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton..Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -2436,102 +2520,104 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae ..Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot ..Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai ..Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt..Tai Tham Combining Crypt - (0x01ab0, 0x01abe,), # Combining Doubled Circum..Combining Parentheses Ov + (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi ..Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O ..Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak ..Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above ..Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea - (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine..Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar - (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu..Javanese Sign Cecak Telu + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe..Javanese Vowel Sign Pepe - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw ..Myanmar Sign Shan Saw + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T..Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang ..Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho ..Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama ..Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek ..Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi..Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M..Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x102e0, 0x102e0,), # Coptic Epact Thousands M (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation - (0x11001, 0x11001,), # Brahmi Sign Anusvara ..Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -2539,26 +2625,26 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta ..Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111ca, 0x111cc,), # Sharada Sign Nukta ..Sharada Extra Short Vowe (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara ..Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x1123e, 0x1123e,), # Khojki Sign Sukun ..Khojki Sign Sukun - (0x112df, 0x112df,), # Khudawadi Sign Anusvara ..Khudawadi Sign Anusvara + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu - (0x1133c, 0x1133c,), # Grantha Sign Nukta ..Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii ..Grantha Vowel Sign Ii + (0x1133c, 0x1133c,), # Grantha Sign Nukta + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara - (0x11446, 0x11446,), # Newa Sign Nukta ..Newa Sign Nukta + (0x11446, 0x11446,), # Newa Sign Nukta (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short..Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -2566,12 +2652,12 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara ..Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara ..Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa ..Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta ..Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer @@ -2579,23 +2665,23 @@ (0x11a09, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L (0x11a33, 0x11a38,), # Zanabazar Square Final C..Zanabazar Square Sign An (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster - (0x11a47, 0x11a47,), # Zanabazar Square Subjoin..Zanabazar Square Subjoin + (0x11a47, 0x11a47,), # Zanabazar Square Subjoin (0x11a51, 0x11a56,), # Soyombo Vowel Sign I ..Soyombo Vowel Sign Oe (0x11a59, 0x11a5b,), # Soyombo Vowel Sign Vocal..Soyombo Vowel Length Mar (0x11a8a, 0x11a96,), # Soyombo Final Consonant ..Soyombo Sign Anusvara (0x11a98, 0x11a99,), # Soyombo Gemination Mark ..Soyombo Subjoiner (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara - (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama ..Bhaiksuki Sign Virama + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E (0x11cb5, 0x11cb6,), # Marchen Sign Anusvara ..Marchen Sign Candrabindu (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign - (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama - (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara ..Masaram Gondi Ra-kara + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below @@ -2607,8 +2693,8 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T..Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea..Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body T + (0x1da84, 0x1da84,), # Signwriting Location Hea (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let @@ -2619,30 +2705,36 @@ (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '11.0.0': ( # Source: DerivedGeneralCategory-11.0.0.txt # Date: 2018-02-21, 05:34:04 GMT # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot - (0x007fd, 0x007fd,), # Nko Dantayalan ..Nko Dantayalan + (0x007fd, 0x007fd,), # Nko Dantayalan (0x00816, 0x00819,), # Samaritan Mark In ..Samaritan Mark Dagesh (0x0081b, 0x00823,), # Samaritan Mark Epentheti..Samaritan Vowel Sign A (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U @@ -2650,81 +2742,81 @@ (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x008d3, 0x008e1,), # Arabic Small Low Waw ..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara - (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe..Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal - (0x009fe, 0x009fe,), # Bengali Sandhi Mark ..Bengali Sandhi Mark + (0x009fe, 0x009fe,), # Bengali Sandhi Mark (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca..Telugu Sign Combining Ca - (0x00c04, 0x00c04,), # Telugu Sign Combining An..Telugu Sign Combining An + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Ca + (0x00c04, 0x00c04,), # Telugu Sign Combining An (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00c81, 0x00c81,), # Kannada Sign Candrabindu..Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00c81, 0x00c81,), # Kannada Sign Candrabindu + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d00, 0x00d01,), # Malayalam Sign Combining..Malayalam Sign Candrabin (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -2732,10 +2824,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S..Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign S (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci..Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton..Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -2743,105 +2835,107 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae ..Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot ..Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai ..Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt..Tai Tham Combining Crypt - (0x01ab0, 0x01abe,), # Combining Doubled Circum..Combining Parentheses Ov + (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi ..Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O ..Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak ..Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above ..Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea - (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine..Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig - (0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay..Devanagari Vowel Sign Ay + (0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar - (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu..Javanese Sign Cecak Telu + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe..Javanese Vowel Sign Pepe - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw ..Myanmar Sign Shan Saw + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T..Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang ..Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho ..Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama ..Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek ..Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi..Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M..Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x102e0, 0x102e0,), # Coptic Epact Thousands M (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation (0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke - (0x11001, 0x11001,), # Brahmi Sign Anusvara ..Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -2849,27 +2943,27 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta ..Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111c9, 0x111cc,), # Sharada Sandhi Mark ..Sharada Extra Short Vowe (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara ..Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x1123e, 0x1123e,), # Khojki Sign Sukun ..Khojki Sign Sukun - (0x112df, 0x112df,), # Khudawadi Sign Anusvara ..Khudawadi Sign Anusvara + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu (0x1133b, 0x1133c,), # Combining Bindu Below ..Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii ..Grantha Vowel Sign Ii + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara - (0x11446, 0x11446,), # Newa Sign Nukta ..Newa Sign Nukta - (0x1145e, 0x1145e,), # Newa Sandhi Mark ..Newa Sandhi Mark + (0x11446, 0x11446,), # Newa Sign Nukta + (0x1145e, 0x1145e,), # Newa Sandhi Mark (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short..Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -2877,12 +2971,12 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara ..Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara ..Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa ..Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta ..Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer @@ -2891,26 +2985,26 @@ (0x11a01, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L (0x11a33, 0x11a38,), # Zanabazar Square Final C..Zanabazar Square Sign An (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster - (0x11a47, 0x11a47,), # Zanabazar Square Subjoin..Zanabazar Square Subjoin + (0x11a47, 0x11a47,), # Zanabazar Square Subjoin (0x11a51, 0x11a56,), # Soyombo Vowel Sign I ..Soyombo Vowel Sign Oe (0x11a59, 0x11a5b,), # Soyombo Vowel Sign Vocal..Soyombo Vowel Length Mar (0x11a8a, 0x11a96,), # Soyombo Final Consonant ..Soyombo Sign Anusvara (0x11a98, 0x11a99,), # Soyombo Gemination Mark ..Soyombo Subjoiner (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara - (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama ..Bhaiksuki Sign Virama + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E (0x11cb5, 0x11cb6,), # Marchen Sign Anusvara ..Marchen Sign Candrabindu (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign - (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama - (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara ..Masaram Gondi Ra-kara + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara (0x11d90, 0x11d91,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign - (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusv..Gunjala Gondi Sign Anusv - (0x11d97, 0x11d97,), # Gunjala Gondi Virama ..Gunjala Gondi Virama + (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusv + (0x11d97, 0x11d97,), # Gunjala Gondi Virama (0x11ef3, 0x11ef4,), # Makasar Vowel Sign I ..Makasar Vowel Sign U (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta @@ -2923,8 +3017,8 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T..Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea..Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body T + (0x1da84, 0x1da84,), # Signwriting Location Hea (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let @@ -2935,30 +3029,36 @@ (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '12.0.0': ( # Source: DerivedGeneralCategory-12.0.0.txt # Date: 2019-01-22, 08:18:28 GMT # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot - (0x007fd, 0x007fd,), # Nko Dantayalan ..Nko Dantayalan + (0x007fd, 0x007fd,), # Nko Dantayalan (0x00816, 0x00819,), # Samaritan Mark In ..Samaritan Mark Dagesh (0x0081b, 0x00823,), # Samaritan Mark Epentheti..Samaritan Vowel Sign A (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U @@ -2966,80 +3066,80 @@ (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x008d3, 0x008e1,), # Arabic Small Low Waw ..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara - (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe..Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal - (0x009fe, 0x009fe,), # Bengali Sandhi Mark ..Bengali Sandhi Mark + (0x009fe, 0x009fe,), # Bengali Sandhi Mark (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca..Telugu Sign Combining Ca - (0x00c04, 0x00c04,), # Telugu Sign Combining An..Telugu Sign Combining An + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Ca + (0x00c04, 0x00c04,), # Telugu Sign Combining An (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00c81, 0x00c81,), # Kannada Sign Candrabindu..Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00c81, 0x00c81,), # Kannada Sign Candrabindu + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d00, 0x00d01,), # Malayalam Sign Combining..Malayalam Sign Candrabin (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00ebc,), # Lao Vowel Sign I ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -3047,10 +3147,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S..Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign S (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci..Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton..Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -3058,105 +3158,107 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae ..Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot ..Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai ..Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt..Tai Tham Combining Crypt - (0x01ab0, 0x01abe,), # Combining Doubled Circum..Combining Parentheses Ov + (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi ..Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O ..Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak ..Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above ..Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea - (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine..Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig - (0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay..Devanagari Vowel Sign Ay + (0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar - (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu..Javanese Sign Cecak Telu + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku (0x0a9bc, 0x0a9bd,), # Javanese Vowel Sign Pepe..Javanese Consonant Sign - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw ..Myanmar Sign Shan Saw + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T..Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang ..Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho ..Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama ..Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek ..Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi..Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M..Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x102e0, 0x102e0,), # Coptic Epact Thousands M (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation (0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke - (0x11001, 0x11001,), # Brahmi Sign Anusvara ..Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -3164,27 +3266,27 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta ..Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111c9, 0x111cc,), # Sharada Sandhi Mark ..Sharada Extra Short Vowe (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara ..Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x1123e, 0x1123e,), # Khojki Sign Sukun ..Khojki Sign Sukun - (0x112df, 0x112df,), # Khudawadi Sign Anusvara ..Khudawadi Sign Anusvara + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu (0x1133b, 0x1133c,), # Combining Bindu Below ..Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii ..Grantha Vowel Sign Ii + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara - (0x11446, 0x11446,), # Newa Sign Nukta ..Newa Sign Nukta - (0x1145e, 0x1145e,), # Newa Sandhi Mark ..Newa Sandhi Mark + (0x11446, 0x11446,), # Newa Sign Nukta + (0x1145e, 0x1145e,), # Newa Sandhi Mark (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short..Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -3192,12 +3294,12 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara ..Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara ..Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa ..Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta ..Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer @@ -3205,34 +3307,34 @@ (0x11839, 0x1183a,), # Dogra Sign Virama ..Dogra Sign Nukta (0x119d4, 0x119d7,), # Nandinagari Vowel Sign U..Nandinagari Vowel Sign V (0x119da, 0x119db,), # Nandinagari Vowel Sign E..Nandinagari Vowel Sign A - (0x119e0, 0x119e0,), # Nandinagari Sign Virama ..Nandinagari Sign Virama + (0x119e0, 0x119e0,), # Nandinagari Sign Virama (0x11a01, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L (0x11a33, 0x11a38,), # Zanabazar Square Final C..Zanabazar Square Sign An (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster - (0x11a47, 0x11a47,), # Zanabazar Square Subjoin..Zanabazar Square Subjoin + (0x11a47, 0x11a47,), # Zanabazar Square Subjoin (0x11a51, 0x11a56,), # Soyombo Vowel Sign I ..Soyombo Vowel Sign Oe (0x11a59, 0x11a5b,), # Soyombo Vowel Sign Vocal..Soyombo Vowel Length Mar (0x11a8a, 0x11a96,), # Soyombo Final Consonant ..Soyombo Sign Anusvara (0x11a98, 0x11a99,), # Soyombo Gemination Mark ..Soyombo Subjoiner (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara - (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama ..Bhaiksuki Sign Virama + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E (0x11cb5, 0x11cb6,), # Marchen Sign Anusvara ..Marchen Sign Candrabindu (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign - (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama - (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara ..Masaram Gondi Ra-kara + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara (0x11d90, 0x11d91,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign - (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusv..Gunjala Gondi Sign Anusv - (0x11d97, 0x11d97,), # Gunjala Gondi Virama ..Gunjala Gondi Virama + (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusv + (0x11d97, 0x11d97,), # Gunjala Gondi Virama (0x11ef3, 0x11ef4,), # Makasar Vowel Sign I ..Makasar Vowel Sign U (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta - (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modi..Miao Sign Consonant Modi + (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modi (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below (0x1bc9d, 0x1bc9e,), # Duployan Thick Letter Se..Duployan Double Mark (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining @@ -3242,8 +3344,8 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T..Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea..Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body T + (0x1da84, 0x1da84,), # Signwriting Location Hea (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let @@ -3256,30 +3358,36 @@ (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '12.1.0': ( # Source: DerivedGeneralCategory-12.1.0.txt # Date: 2019-03-10, 10:53:08 GMT # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot - (0x007fd, 0x007fd,), # Nko Dantayalan ..Nko Dantayalan + (0x007fd, 0x007fd,), # Nko Dantayalan (0x00816, 0x00819,), # Samaritan Mark In ..Samaritan Mark Dagesh (0x0081b, 0x00823,), # Samaritan Mark Epentheti..Samaritan Vowel Sign A (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U @@ -3287,80 +3395,80 @@ (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x008d3, 0x008e1,), # Arabic Small Low Waw ..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara - (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe..Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal - (0x009fe, 0x009fe,), # Bengali Sandhi Mark ..Bengali Sandhi Mark + (0x009fe, 0x009fe,), # Bengali Sandhi Mark (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark ..Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca..Telugu Sign Combining Ca - (0x00c04, 0x00c04,), # Telugu Sign Combining An..Telugu Sign Combining An + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Ca + (0x00c04, 0x00c04,), # Telugu Sign Combining An (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00c81, 0x00c81,), # Kannada Sign Candrabindu..Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00c81, 0x00c81,), # Kannada Sign Candrabindu + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d00, 0x00d01,), # Malayalam Sign Combining..Malayalam Sign Candrabin (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00ebc,), # Lao Vowel Sign I ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -3368,10 +3476,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S..Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign S (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci..Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton..Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -3379,105 +3487,107 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae ..Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot ..Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai ..Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt..Tai Tham Combining Crypt - (0x01ab0, 0x01abe,), # Combining Doubled Circum..Combining Parentheses Ov + (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi ..Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O ..Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak ..Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above ..Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea - (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine..Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig - (0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay..Devanagari Vowel Sign Ay + (0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar - (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu..Javanese Sign Cecak Telu + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku (0x0a9bc, 0x0a9bd,), # Javanese Vowel Sign Pepe..Javanese Consonant Sign - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw ..Myanmar Sign Shan Saw + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T..Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang ..Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho ..Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama ..Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek ..Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi..Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M..Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x102e0, 0x102e0,), # Coptic Epact Thousands M (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation (0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke - (0x11001, 0x11001,), # Brahmi Sign Anusvara ..Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -3485,27 +3595,27 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta ..Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111c9, 0x111cc,), # Sharada Sandhi Mark ..Sharada Extra Short Vowe (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara ..Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x1123e, 0x1123e,), # Khojki Sign Sukun ..Khojki Sign Sukun - (0x112df, 0x112df,), # Khudawadi Sign Anusvara ..Khudawadi Sign Anusvara + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu (0x1133b, 0x1133c,), # Combining Bindu Below ..Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii ..Grantha Vowel Sign Ii + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara - (0x11446, 0x11446,), # Newa Sign Nukta ..Newa Sign Nukta - (0x1145e, 0x1145e,), # Newa Sandhi Mark ..Newa Sandhi Mark + (0x11446, 0x11446,), # Newa Sign Nukta + (0x1145e, 0x1145e,), # Newa Sandhi Mark (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short..Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -3513,12 +3623,12 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara ..Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara ..Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa ..Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta ..Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer @@ -3526,34 +3636,34 @@ (0x11839, 0x1183a,), # Dogra Sign Virama ..Dogra Sign Nukta (0x119d4, 0x119d7,), # Nandinagari Vowel Sign U..Nandinagari Vowel Sign V (0x119da, 0x119db,), # Nandinagari Vowel Sign E..Nandinagari Vowel Sign A - (0x119e0, 0x119e0,), # Nandinagari Sign Virama ..Nandinagari Sign Virama + (0x119e0, 0x119e0,), # Nandinagari Sign Virama (0x11a01, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L (0x11a33, 0x11a38,), # Zanabazar Square Final C..Zanabazar Square Sign An (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster - (0x11a47, 0x11a47,), # Zanabazar Square Subjoin..Zanabazar Square Subjoin + (0x11a47, 0x11a47,), # Zanabazar Square Subjoin (0x11a51, 0x11a56,), # Soyombo Vowel Sign I ..Soyombo Vowel Sign Oe (0x11a59, 0x11a5b,), # Soyombo Vowel Sign Vocal..Soyombo Vowel Length Mar (0x11a8a, 0x11a96,), # Soyombo Final Consonant ..Soyombo Sign Anusvara (0x11a98, 0x11a99,), # Soyombo Gemination Mark ..Soyombo Subjoiner (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara - (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama ..Bhaiksuki Sign Virama + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E (0x11cb5, 0x11cb6,), # Marchen Sign Anusvara ..Marchen Sign Candrabindu (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign - (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama - (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara ..Masaram Gondi Ra-kara + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara (0x11d90, 0x11d91,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign - (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusv..Gunjala Gondi Sign Anusv - (0x11d97, 0x11d97,), # Gunjala Gondi Virama ..Gunjala Gondi Virama + (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusv + (0x11d97, 0x11d97,), # Gunjala Gondi Virama (0x11ef3, 0x11ef4,), # Makasar Vowel Sign I ..Makasar Vowel Sign U (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta - (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modi..Miao Sign Consonant Modi + (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modi (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below (0x1bc9d, 0x1bc9e,), # Duployan Thick Letter Se..Duployan Double Mark (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining @@ -3563,8 +3673,8 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T..Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea..Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body T + (0x1da84, 0x1da84,), # Signwriting Location Hea (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let @@ -3577,30 +3687,36 @@ (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '13.0.0': ( # Source: DerivedGeneralCategory-13.0.0.txt # Date: 2019-10-21, 14:30:32 GMT # + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe ..Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata..Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip..Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscrip (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip..Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscrip (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot - (0x007fd, 0x007fd,), # Nko Dantayalan ..Nko Dantayalan + (0x007fd, 0x007fd,), # Nko Dantayalan (0x00816, 0x00819,), # Samaritan Mark In ..Samaritan Mark Dagesh (0x0081b, 0x00823,), # Samaritan Mark Epentheti..Samaritan Vowel Sign A (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U @@ -3608,81 +3724,81 @@ (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x008d3, 0x008e1,), # Arabic Small Low Waw ..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara - (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe..Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta ..Devanagari Sign Nukta + (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama ..Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo - (0x00981, 0x00981,), # Bengali Sign Candrabindu..Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta ..Bengali Sign Nukta + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama ..Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal - (0x009fe, 0x009fe,), # Bengali Sandhi Mark ..Bengali Sandhi Mark + (0x009fe, 0x009fe,), # Bengali Sandhi Mark (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta ..Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat ..Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash ..Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta ..Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama ..Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu ..Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta ..Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I ..Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama ..Oriya Sign Virama - (0x00b55, 0x00b56,), # (nil) ..Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b55, 0x00b56,), # Oriya Sign Overline ..Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara ..Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii ..Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama ..Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca..Telugu Sign Combining Ca - (0x00c04, 0x00c04,), # Telugu Sign Combining An..Telugu Sign Combining An + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Ca + (0x00c04, 0x00c04,), # Telugu Sign Combining An (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00c81, 0x00c81,), # Kannada Sign Candrabindu..Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta ..Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I ..Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E ..Kannada Vowel Sign E + (0x00c81, 0x00c81,), # Kannada Sign Candrabindu + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d00, 0x00d01,), # Malayalam Sign Combining..Malayalam Sign Candrabin (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama ..Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00d81, 0x00d81,), # (nil) ..(nil) - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna ..Sinhala Sign Al-lakuna + (0x00d81, 0x00d81,), # Sinhala Sign Candrabindu + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga ..Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a..Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan ..Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00ebc,), # Lao Vowel Sign I ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung ..Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru ..Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda..Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -3690,10 +3806,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S..Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign S (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci..Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton..Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -3701,107 +3817,110 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit ..Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan ..Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv..Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusv (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae ..Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign ..Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot ..Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai ..Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt..Tai Tham Combining Crypt - (0x01ab0, 0x01ac0,), # Combining Doubled Circum..(nil) + (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be + (0x01abf, 0x01ac0,), # Combining Latin Small Le..Combining Latin Small Le (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan ..Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L..Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe..Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi ..Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O ..Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak ..Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above ..Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea - (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine..Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva..Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant..Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva..Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a82c, 0x0a82c,), # (nil) ..(nil) + (0x0a82c, 0x0a82c,), # Syloti Nagri Sign Altern (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig - (0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay..Devanagari Vowel Sign Ay + (0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar - (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu..Javanese Sign Cecak Telu + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku (0x0a9bc, 0x0a9bd,), # Javanese Vowel Sign Pepe..Javanese Consonant Sign - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw ..Myanmar Sign Shan Saw + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina..Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T..Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang ..Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho ..Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama ..Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek ..Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani..Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi..Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M..Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x102e0, 0x102e0,), # Coptic Epact Thousands M (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama ..Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation (0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas - (0x10eab, 0x10eac,), # (nil) ..(nil) + (0x10eab, 0x10eac,), # Yezidi Combining Hamza M..Yezidi Combining Madda M (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke - (0x11001, 0x11001,), # Brahmi Sign Anusvara ..Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -3809,28 +3928,28 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta ..Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111c9, 0x111cc,), # Sharada Sandhi Mark ..Sharada Extra Short Vowe - (0x111cf, 0x111cf,), # (nil) ..(nil) + (0x111cf, 0x111cf,), # Sharada Sign Inverted Ca (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara ..Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x1123e, 0x1123e,), # Khojki Sign Sukun ..Khojki Sign Sukun - (0x112df, 0x112df,), # Khudawadi Sign Anusvara ..Khudawadi Sign Anusvara + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu (0x1133b, 0x1133c,), # Combining Bindu Below ..Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii ..Grantha Vowel Sign Ii + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara - (0x11446, 0x11446,), # Newa Sign Nukta ..Newa Sign Nukta - (0x1145e, 0x1145e,), # Newa Sandhi Mark ..Newa Sandhi Mark + (0x11446, 0x11446,), # Newa Sign Nukta + (0x1145e, 0x1145e,), # Newa Sandhi Mark (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short..Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -3838,52 +3957,52 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara ..Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara ..Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa ..Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta ..Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer (0x1182f, 0x11837,), # Dogra Vowel Sign U ..Dogra Sign Anusvara (0x11839, 0x1183a,), # Dogra Sign Virama ..Dogra Sign Nukta - (0x1193b, 0x1193c,), # (nil) ..(nil) - (0x1193e, 0x1193e,), # (nil) ..(nil) - (0x11943, 0x11943,), # (nil) ..(nil) + (0x1193b, 0x1193c,), # Dives Akuru Sign Anusvar..Dives Akuru Sign Candrab + (0x1193e, 0x1193e,), # Dives Akuru Virama + (0x11943, 0x11943,), # Dives Akuru Sign Nukta (0x119d4, 0x119d7,), # Nandinagari Vowel Sign U..Nandinagari Vowel Sign V (0x119da, 0x119db,), # Nandinagari Vowel Sign E..Nandinagari Vowel Sign A - (0x119e0, 0x119e0,), # Nandinagari Sign Virama ..Nandinagari Sign Virama + (0x119e0, 0x119e0,), # Nandinagari Sign Virama (0x11a01, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L (0x11a33, 0x11a38,), # Zanabazar Square Final C..Zanabazar Square Sign An (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster - (0x11a47, 0x11a47,), # Zanabazar Square Subjoin..Zanabazar Square Subjoin + (0x11a47, 0x11a47,), # Zanabazar Square Subjoin (0x11a51, 0x11a56,), # Soyombo Vowel Sign I ..Soyombo Vowel Sign Oe (0x11a59, 0x11a5b,), # Soyombo Vowel Sign Vocal..Soyombo Vowel Length Mar (0x11a8a, 0x11a96,), # Soyombo Final Consonant ..Soyombo Sign Anusvara (0x11a98, 0x11a99,), # Soyombo Gemination Mark ..Soyombo Subjoiner (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara - (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama ..Bhaiksuki Sign Virama + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E (0x11cb5, 0x11cb6,), # Marchen Sign Anusvara ..Marchen Sign Candrabindu (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign - (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama - (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara ..Masaram Gondi Ra-kara + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara (0x11d90, 0x11d91,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign - (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusv..Gunjala Gondi Sign Anusv - (0x11d97, 0x11d97,), # Gunjala Gondi Virama ..Gunjala Gondi Virama + (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusv + (0x11d97, 0x11d97,), # Gunjala Gondi Virama (0x11ef3, 0x11ef4,), # Makasar Vowel Sign I ..Makasar Vowel Sign U (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta - (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modi..Miao Sign Consonant Modi + (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modi (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below - (0x16fe4, 0x16fe4,), # (nil) ..(nil) + (0x16fe4, 0x16fe4,), # Khitan Small Script Fill (0x1bc9d, 0x1bc9e,), # Duployan Thick Letter Se..Duployan Double Mark (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining @@ -3892,8 +4011,8 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T..Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea..Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body T + (0x1da84, 0x1da84,), # Signwriting Location Hea (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let @@ -3906,5 +4025,357 @@ (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous + ), + '14.0.0': ( + # Source: DerivedGeneralCategory-14.0.0.txt + # Date: 2021-07-10, 00:35:08 GMT + # + (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le + (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg + (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot + (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra + (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below + (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen + (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda + (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon + (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem + (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh + (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun + (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot + (0x007fd, 0x007fd,), # Nko Dantayalan + (0x00816, 0x00819,), # Samaritan Mark In ..Samaritan Mark Dagesh + (0x0081b, 0x00823,), # Samaritan Mark Epentheti..Samaritan Vowel Sign A + (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U + (0x00829, 0x0082d,), # Samaritan Vowel Sign Lon..Samaritan Mark Nequdaa + (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark + (0x00898, 0x0089f,), # (nil) + (0x008ca, 0x008e1,), # (nil) ..Arabic Small High Sign S + (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara + (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe + (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai + (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu + (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal + (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal + (0x009fe, 0x009fe,), # Bengali Sandhi Mark + (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu + (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai + (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara + (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand + (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai + (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca + (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b55, 0x00b56,), # Oriya Sign Overline ..Oriya Ai Length Mark + (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Ca + (0x00c04, 0x00c04,), # Telugu Sign Combining An + (0x00c3c, 0x00c3c,), # (nil) + (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii + (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai + (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama + (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark + (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali + (0x00c81, 0x00c81,), # Kannada Sign Candrabindu + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama + (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal + (0x00d00, 0x00d01,), # Malayalam Sign Combining..Malayalam Sign Candrabin + (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular + (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc + (0x00d81, 0x00d81,), # Sinhala Sign Candrabindu + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga + (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu + (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb4, 0x00ebc,), # Lao Vowel Sign I ..Lao Semivowel Sign Lo + (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita + (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga + (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta + (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags + (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter + (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu + (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below + (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat + (0x0103d, 0x0103e,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M + (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal + (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M + (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah + (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan + (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin + (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama + (0x01732, 0x01733,), # Hanunoo Vowel Sign I ..Hanunoo Vowel Sign U + (0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U + (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U + (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa + (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua + (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat + (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation + (0x0180f, 0x0180f,), # (nil) + (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U + (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O + (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i + (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B + (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue + (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be + (0x01abf, 0x01ace,), # Combining Latin Small Le..(nil) + (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang + (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol + (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar + (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan + (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan + (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign + (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H + (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T + (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta + (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha + (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash + (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A + (0x01dc0, 0x01dff,), # Combining Dotted Grave A..Combining Right Arrowhea + (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov + (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine + (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette + (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton + (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag + (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer + (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette + (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign + (0x0a82c, 0x0a82c,), # Syloti Nagri Sign Altern + (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi + (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig + (0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay + (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop + (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R + (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu + (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku + (0x0a9bc, 0x0a9bd,), # Javanese Vowel Sign Pepe..Javanese Consonant Sign + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw + (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe + (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue + (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U + (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia + (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 + (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x102e0, 0x102e0,), # Coptic Epact Thousands M + (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let + (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo + (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O + (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga + (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo + (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation + (0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas + (0x10eab, 0x10eac,), # Yezidi Combining Hamza M..Yezidi Combining Madda M + (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke + (0x10f82, 0x10f85,), # (nil) + (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama + (0x11070, 0x11070,), # (nil) + (0x11073, 0x11074,), # (nil) + (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara + (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai + (0x110b9, 0x110ba,), # Kaithi Sign Virama ..Kaithi Sign Nukta + (0x110c2, 0x110c2,), # (nil) + (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga + (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu + (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa + (0x11173, 0x11173,), # Mahajani Sign Nukta + (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara + (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O + (0x111c9, 0x111cc,), # Sharada Sandhi Mark ..Sharada Extra Short Vowe + (0x111cf, 0x111cf,), # Sharada Sign Inverted Ca + (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai + (0x11234, 0x11234,), # Khojki Sign Anusvara + (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x112df, 0x112df,), # Khudawadi Sign Anusvara + (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama + (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu + (0x1133b, 0x1133c,), # Combining Bindu Below ..Grantha Sign Nukta + (0x11340, 0x11340,), # Grantha Vowel Sign Ii + (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit + (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter + (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai + (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara + (0x11446, 0x11446,), # Newa Sign Nukta + (0x1145e, 0x1145e,), # Newa Sandhi Mark + (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short + (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara + (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta + (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal + (0x115bc, 0x115bd,), # Siddham Sign Candrabindu..Siddham Sign Anusvara + (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta + (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter + (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai + (0x1163d, 0x1163d,), # Modi Sign Anusvara + (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa + (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au + (0x116b7, 0x116b7,), # Takri Sign Nukta + (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi + (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu + (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer + (0x1182f, 0x11837,), # Dogra Vowel Sign U ..Dogra Sign Anusvara + (0x11839, 0x1183a,), # Dogra Sign Virama ..Dogra Sign Nukta + (0x1193b, 0x1193c,), # Dives Akuru Sign Anusvar..Dives Akuru Sign Candrab + (0x1193e, 0x1193e,), # Dives Akuru Virama + (0x11943, 0x11943,), # Dives Akuru Sign Nukta + (0x119d4, 0x119d7,), # Nandinagari Vowel Sign U..Nandinagari Vowel Sign V + (0x119da, 0x119db,), # Nandinagari Vowel Sign E..Nandinagari Vowel Sign A + (0x119e0, 0x119e0,), # Nandinagari Sign Virama + (0x11a01, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L + (0x11a33, 0x11a38,), # Zanabazar Square Final C..Zanabazar Square Sign An + (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster + (0x11a47, 0x11a47,), # Zanabazar Square Subjoin + (0x11a51, 0x11a56,), # Soyombo Vowel Sign I ..Soyombo Vowel Sign Oe + (0x11a59, 0x11a5b,), # Soyombo Vowel Sign Vocal..Soyombo Vowel Length Mar + (0x11a8a, 0x11a96,), # Soyombo Final Consonant ..Soyombo Sign Anusvara + (0x11a98, 0x11a99,), # Soyombo Gemination Mark ..Soyombo Subjoiner + (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc + (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama + (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter + (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa + (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E + (0x11cb5, 0x11cb6,), # Marchen Sign Anusvara ..Marchen Sign Candrabindu + (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign + (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign + (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara + (0x11d90, 0x11d91,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign + (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusv + (0x11d97, 0x11d97,), # Gunjala Gondi Virama + (0x11ef3, 0x11ef4,), # Makasar Vowel Sign I ..Makasar Vowel Sign U + (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High + (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta + (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modi + (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below + (0x16fe4, 0x16fe4,), # Khitan Small Script Fill + (0x1bc9d, 0x1bc9e,), # Duployan Thick Letter Se..Duployan Double Mark + (0x1cf00, 0x1cf2d,), # (nil) + (0x1cf30, 0x1cf46,), # (nil) + (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d185, 0x1d18b,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical + (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking + (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement + (0x1da75, 0x1da75,), # Signwriting Upper Body T + (0x1da84, 0x1da84,), # Signwriting Location Hea + (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie + (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod + (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e008, 0x1e018,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e01b, 0x1e021,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e023, 0x1e024,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e026, 0x1e02a,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e130, 0x1e136,), # Nyiakeng Puachue Hmong T..Nyiakeng Puachue Hmong T + (0x1e2ae, 0x1e2ae,), # (nil) + (0x1e2ec, 0x1e2ef,), # Wancho Tone Tup ..Wancho Tone Koini + (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining + (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta + (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli + (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ + (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa + (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), } diff --git a/wcwidth/unicode_versions.py b/wcwidth/unicode_versions.py index 25ec93f..ba45fb7 100644 --- a/wcwidth/unicode_versions.py +++ b/wcwidth/unicode_versions.py @@ -1,7 +1,7 @@ """ Exports function list_versions() for unicode version level support. -This code generated by wcwidth/bin/update-tables.py on 2021-10-01 19:03:52 UTC. +This code generated by wcwidth/bin/update-tables.py on 2022-03-20 21:12:52 UTC. """ def list_versions(): @@ -31,4 +31,5 @@ def list_versions(): "12.0.0", "12.1.0", "13.0.0", + "14.0.0", ) From 2e12375f5ce5cabe06a41b41b1597a9e8350ef83 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:15:34 -0400 Subject: [PATCH 07/57] complete using jinja2 for code generation --- bin/update-tables.py | 373 +++++++++++++----------------- code_templates/python_table.py.j2 | 17 ++ 2 files changed, 177 insertions(+), 213 deletions(-) create mode 100644 code_templates/python_table.py.j2 diff --git a/bin/update-tables.py b/bin/update-tables.py index 43b73d7..8f3ef3a 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -2,44 +2,61 @@ """ Update the python Unicode tables for wcwidth. +This should be executed through tox, + + $ tox -e update + +Use argument --check-last-modified if data files were previously downloaded, +but will refresh by last-modified check using HEAD request from unicode.org +URLs. + + $ tox -e update -- --check-last-modified + https://github.com/jquast/wcwidth """ # std imports import os import re +import sys import glob import codecs import string import urllib +import logging import datetime +import functools import collections import unicodedata -from urllib.request import urlopen # third party import jinja2 +import tenacity +import requests +import dateutil.parser + URL_UNICODE_DERIVED_AGE = 'http://www.unicode.org/Public/UCD/latest/ucd/DerivedAge.txt' +URL_EASTASIAN_WIDTH = 'http://www.unicode.org/Public/{version}/ucd/EastAsianWidth.txt' +URL_DERIVED_CATEGORY = 'http://www.unicode.org/Public/{version}/ucd/extracted/DerivedGeneralCategory.txt' EXCLUDE_VERSIONS = ['2.0.0', '2.1.2', '3.0.0', '3.1.0', '3.2.0', '4.0.0'] -PATH_UP = os.path.relpath( - os.path.join( - os.path.dirname(__file__), - os.path.pardir)) +PATH_UP = os.path.relpath(os.path.join(os.path.dirname(__file__), os.path.pardir)) PATH_DATA = os.path.join(PATH_UP, 'data') THIS_FILEPATH = os.path.relpath(__file__, os.path.join(PATH_UP, os.path.pardir)) # "wcwidth/bin/update-tables.py" JINJA_ENV = jinja2.Environment( loader=jinja2.FileSystemLoader(os.path.join(PATH_UP, 'code_templates')), keep_trailing_newline=True) - +UTC_NOW = datetime.datetime.utcnow().strftime("%Y-%m-%d %H:%M:%S UTC") +CONNECT_TIMEOUT = int(os.environ.get('CONNECT_TIMEOUT', '10')) +FETCH_BLOCKSIZE = int(os.environ.get('FETCH_BLOCKSIZE', '4096')) +MAX_RETRIES = int(os.environ.get('MAX_RETRIES', '10')) TableDef = collections.namedtuple('table', ['version', 'date', 'values']) -RenderDef = collections.namedtuple('render', ['jinja_filename', 'output_filename', 'fn_data']) - +RenderDefinition = collections.namedtuple('render', ['jinja_filename', 'output_filename', 'fn_data']) +logging.basicConfig(stream=sys.stderr, level=logging.DEBUG) +logger = logging.getLogger(__name__) -# version codes are used by most templates -# TODO: memoize +@functools.cache def fetch_unicode_versions(): """Fetch, determine, and return Unicode Versions for processing.""" - fname = os.path.join(PATH_DATA, os.path.basename(URL_UNICODE_DERIVED_AGE)) do_retrieve(url=URL_UNICODE_DERIVED_AGE, fname=fname) pattern = re.compile(r'#.*assigned in Unicode ([0-9.]+)') @@ -59,46 +76,48 @@ def fetch_source_headers(): filenames.sort(key=lambda filename: make_sortable_source_name(filename)) headers = [] for filename in filenames: - if header_description := fetch_source_description(filename): + if header_description := cite_source_description(filename): headers.append(header_description) return {'source_headers': headers} -CODEGEN_DEFINITIONS = [ - RenderDef(jinja_filename='unicode_versions.py.j2', - output_filename=os.path.join(PATH_UP, 'code', 'unicode_versions.py'), - fn_data=fetch_unicode_versions), - RenderDef(jinja_filename='unicode_version.rst.j2', - output_filename=os.path.join(PATH_UP, 'docs', 'unicode_version.rst'), - fn_data=fetch_source_headers) - RenderDef(jinja_filename='table_wide.py.j2', - output_filename=os.path.join(PATH_UP, 'code', 'table_wide.py'), - fn_data=fetch_table_wide_data), -# RenderDef(jinja_filename='table_zero.py.j2', -# output_filename=os.path.join(PATH_CODE, f'table_zero.py'), -# fn_data=fetch_table_zero_data) -] +def fetch_table_wide_data(): + """Fetch and update east-asian tables.""" + table = {} + for version in fetch_unicode_versions()['versions']: + fname = os.path.join(PATH_DATA, f'EastAsianWidth-{version}.txt') + do_retrieve(url=URL_EASTASIAN_WIDTH.format(version=version), fname=fname) + table[version] = parse_category(fname=fname, category_codes=('W', 'F',)) + return {'table': table, 'variable_name': 'WIDE_EASTASIAN'} +def fetch_table_zero_data(): + """Fetch and update zero width tables.""" + table = {} + for version in fetch_unicode_versions()['versions']: + fname = os.path.join(PATH_DATA, f'DerivedGeneralCategory-{version}.txt') + do_retrieve(url=URL_DERIVED_CATEGORY.format(version=version), fname=fname) + # TODO: test whether all of category, 'Cf' should be 'zero + # width', or, just the subset 2060..2064, see open issue + # https://github.com/jquast/wcwidth/issues/26 + table[version] = parse_category(fname=fname, category_codes=('Me', 'Mn',)) + return {'table': table, 'variable_name': 'ZERO_WIDTH'} -def main(): - """Update east-asian, combining and zero width tables.""" - for render_def in CODEGEN_DEFINITIONS: - with open(render_def.output_filename, 'w') as fout: - fout.write(render_template(render_def.jinja_filename, **render_def.fn_data())) def render_template(jinja_filename, utc_now=UTC_NOW, this_filepath=THIS_FILEPATH, **kwargs): return JINJA_ENV.get_template(jinja_filename).render( - utc_now=datetime.datetime.utcnow().strftime("%Y-%m-%d %H:%M:%S UTC"), + utc_now=utc_now, this_filepath=THIS_FILEPATH, **kwargs) -# do_rst_file_update() - #render_unicode_versions(versions) - #render_table_wide(versions) - #render_table_wide(versions) - -# functions for rendering unicode_version.rst -# +def cite_source_description(filename): + """Return unicode.org source data file's own description as citation.""" + header_twolines = [ + line.lstrip('# ').rstrip() + for line in codecs.open(filename, 'r', 'utf8') + .readlines()[:2] + ] + if len(header_twolines) == 2: + return header_twolines def make_sortable_source_name(filename): # make a sortable filename of unicode text file, @@ -109,214 +128,142 @@ def make_sortable_source_name(filename): version_numbers, _extension = os.path.splitext(remaining) return (basename, *list(map(int, version_numbers.split('.')))) -def fetch_source_description(filename): - # read first two lines, strip leading # - header_twolines = [ - line.lstrip('# ').rstrip() - for line in codecs.open(filename, 'r', 'utf8') - .readlines()[:2] - ] - if len(header_twolines) == 2: - return header_twolines - -def fetch_table_wide_data(): - """Fetch and update east-asian tables.""" - table = {} - for version in fetch_unicode_versions(): - fin = os.path.join(PATH_DATA, 'EastAsianWidth-{version}.txt') - #fout = os.path.join(PATH_CODE, 'table_wide.py') - url = ('http://www.unicode.org/Public/{version}/' - 'ucd/EastAsianWidth.txt') - try: - do_retrieve(url=url.format(version=version), - fname=fin.format(version=version)) - except urllib.error.HTTPError as err: - if err.code != 404: - raise - else: - table[version] = parse_east_asian( - fname=fin.format(version=version), - properties=(u'W', u'F',)) - return { - 'table': table, - 'variable': 'WIDE_EASTASIAN', - } - - -def fetch_table_zero_data(): - """Fetch and update zero width tables.""" - table = {} - #fout = os.path.join(PATH_CODE, 'table_zero.py') - for version in fetch_unicode_versions(): - fin = os.path.join(PATH_DATA, 'DerivedGeneralCategory-{version}.txt') - url = ('http://www.unicode.org/Public/{version}/ucd/extracted/' - 'DerivedGeneralCategory.txt') - try: - do_retrieve(url=url.format(version=version), - fname=fin.format(version=version)) - except urllib.error.HTTPError as err: - if err.code != 404: - raise - else: - table[version] = parse_category( - fname=fin.format(version=version), - # todo: test whether all of category, 'Cf' should be 'zero - # width', or, just the subset 2060..2064, see open issue - # https://github.com/jquast/wcwidth/issues/26 - categories=('Me', 'Mn',)) - return table - - - -# todo translate before jinja def make_table(values): """Return a tuple of lookup tables for given values.""" - table = collections.deque() start, end = values[0], values[0] + table = collections.deque() + table.append((start, end)) for num, value in enumerate(values): - if num == 0: - table.append((value, value,)) + try: + start, end = table.pop() + except IndexError: + # first item + table.append((value, value)) continue - start, end = table.pop() if end == value - 1: + # continuation of existing range table.append((start, value,)) else: + # put back existing range, table.append((start, end,)) + # and start a new one table.append((value, value,)) return tuple(table) - - -#def do_unicode_versions(versions, lang): -# """Write unicode_versions.py function list_versions().""" -# jinja_filename = -# output_filename = -# with open(output_filename, 'w') as fout: -# fout.write( -# -# -# -# do_unicode_versions(versions, lang='py') -# val = fetch_east_asian_table(versions, lang='py') -# assert False, val -# assert False -# #do_write_table(fname=fout, variable='WIDE_EASTASIAN', table=table, lang=lang) -# fetch_zero_width_table(versions, lang='py') -# #do_write_table(fname=fout, variable='ZERO_WIDTH', table=table, lang=lang) - - -def do_retrieve(url, fname): - """Retrieve given url to target filepath fname.""" - folder = os.path.dirname(fname) - if not os.path.exists(folder): - os.makedirs(folder) - print(f"{folder}{os.path.sep} created.") - if not os.path.exists(fname): +def convert_values_to_string_table(values): + """Convert integers into string table of (hex_start, hex_end, txt_description).""" + pytable_values = [] + for start, end in values: + hex_start, hex_end = (f'0x{start:05x}', f'0x{end:05x}') + ucs_start, ucs_end = chr(start), chr(end) + name_start, name_end = '(nil)', '(nil)' try: - with open(fname, 'wb') as fout: - print(f"retrieving {url}: ", end='', flush=True) - resp = urlopen(url) - fout.write(resp.read()) - except BaseException: - print('failed') - os.unlink(fname) - raise - print(f"{fname} saved.") - return fname - - -def parse_east_asian(fname, properties=(u'W', u'F',)): - """Parse unicode east-asian width tables.""" - print(f'parsing {fname}: ', end='', flush=True) - version, date, values = None, None, [] - for line in open(fname, 'rb'): - uline = line.decode('utf-8') - if version is None: - version = uline.split(None, 1)[1].rstrip() - continue - if date is None: - date = uline.split(':', 1)[1].rstrip() - continue - if uline.startswith('#') or not uline.lstrip(): - continue - addrs, details = uline.split(';', 1) - if any(details.startswith(property) - for property in properties): - start, stop = addrs, addrs - if '..' in addrs: - start, stop = addrs.split('..') - values.extend(range(int(start, 16), int(stop, 16) + 1)) - print('ok') - return TableDef(version, date, values) - - -def parse_category(fname, categories): - """Parse unicode category tables.""" + name_start = string.capwords(unicodedata.name(ucs_start)) + except ValueError: + pass + try: + name_end = string.capwords(unicodedata.name(ucs_end)) + except ValueError: + pass + txt_description = f'{name_start[:24].rstrip():24s}' + if name_start != name_end: + txt_description += f'..{name_end[:24].rstrip()}' + pytable_values.append((hex_start, hex_end, txt_description)) + return pytable_values + + +def parse_category(fname, category_codes=('Me', 'Mn',)): + """Parse value ranges of unicode data files, by given categories into string tables.""" print(f'parsing {fname}: ', end='', flush=True) version, date, values = None, None, [] for line in open(fname, 'rb'): uline = line.decode('utf-8') if version is None: + # pull "version string" from first line of source file version = uline.split(None, 1)[1].rstrip() continue if date is None: + # and "date string" from second line date = uline.split(':', 1)[1].rstrip() continue if uline.startswith('#') or not uline.lstrip(): + # ignore any further comments or empty lines continue addrs, details = uline.split(';', 1) addrs, details = addrs.rstrip(), details.lstrip() - if any(details.startswith(f'{value} #') - for value in categories): - start, stop = addrs, addrs + if any(details.startswith(f'{category_code}') + for category_code in category_codes): if '..' in addrs: start, stop = addrs.split('..') + else: + start, stop = addrs, addrs values.extend(range(int(start, 16), int(stop, 16) + 1)) + txt_values = convert_values_to_string_table(make_table(values)) print('ok') - return TableDef(version, date, sorted(values)) - + return TableDef(version, date, txt_values) -def do_write_table(fname, variable, table, lang): - """Write combining tables to filesystem as python code.""" - # pylint: disable=R0914 - # Too many local variables (19/15) (col 4) - utc_now = datetime.datetime.utcnow() - indent = ' ' * 8 - with open(fname, 'w') as fout: - print(f"writing {fname} ... ", end='') - fout.write( - f'"""{variable.title()} table, created by bin/update-tables.py."""\n' - f"# Generated: {utc_now.isoformat()}\n" - f"{variable} = {{\n") +def is_url_newer(url, fname): + if not os.path.exists(fname): + return True + if '--check-last-modified' in sys.argv[1:]: + resp = requests.head(url, timeout=CONNECT_TIMEOUT) + resp.raise_for_status() + remote_url_dt = dateutil.parser.parse(resp.headers['Last-Modified']).astimezone() + local_file_dt = datetime.datetime.fromtimestamp(os.path.getmtime(fname)).astimezone() + return remote_url_dt > local_file_dt + return False + +@tenacity.retry(reraise=True, wait=tenacity.wait_none(), + retry=tenacity.retry_if_exception_type(requests.exceptions.RequestException), + stop=tenacity.stop_after_attempt(MAX_RETRIES), + before_sleep=tenacity.before_sleep_log(logger, logging.DEBUG)) +def do_retrieve(url, fname): + """Retrieve given url to target filepath fname.""" + folder = os.path.dirname(fname) + if not os.path.exists(folder): + os.makedirs(folder) + if not is_url_newer(url, fname): + return + resp = requests.get(url, timeout=CONNECT_TIMEOUT) + resp.raise_for_status() + print(f"saving {fname}: ", end='', flush=True) + with open(fname , 'wb') as fout: + for chunk in resp.iter_content(FETCH_BLOCKSIZE): + fout.write(chunk) + print('.', end='', flush=True) + print('ok') - for version_key, version_table in table.items(): - if not version_table.values: - continue - fout.write( - f"{indent[:-4]}'{version_key}': (\n" - f"{indent}# Source: {version_table.version}\n" - f"{indent}# Date: {version_table.date}\n" - f"{indent}#") - for start, end in make_table(version_table.values): - ucs_start, ucs_end = chr(start), chr(end) - hex_start, hex_end = (f'0x{start:05x}', f'0x{end:05x}') - try: - name_start = string.capwords(unicodedata.name(ucs_start)) - except ValueError: - name_start = u'(nil)' - try: - name_end = string.capwords(unicodedata.name(ucs_end)) - except ValueError: - name_end = u'(nil)' - fout.write(f'\n{indent}') - comment_startpart = name_start[:24].rstrip() - comment_endpart = name_end[:24].rstrip() - fout.write(f'({hex_start}, {hex_end},),') - fout.write(f' # {comment_startpart:24s}..{comment_endpart}') - fout.write(f'\n{indent[:-4]}),\n') - fout.write('}\n') - print("complete.") +def main(): + """Update east-asian, combining and zero width tables.""" + # This defines which jinja source templates map to which output filenames, + # and what function defines the source data. We hope to add more source + # language options using jinja2 templates, with minimal modification of the + # code. + CODEGEN_DEFINITIONS = [ + RenderDefinition( + jinja_filename='unicode_versions.py.j2', + output_filename=os.path.join(PATH_UP, 'wcwidth', 'unicode_versions.py'), + fn_data=fetch_unicode_versions), + RenderDefinition( + jinja_filename='unicode_version.rst.j2', + output_filename=os.path.join(PATH_UP, 'docs', 'unicode_version.rst'), + fn_data=fetch_source_headers), + RenderDefinition( + jinja_filename='python_table.py.j2', + output_filename=os.path.join(PATH_UP, 'wcwidth', 'table_wide.py'), + fn_data=fetch_table_wide_data), + RenderDefinition( + jinja_filename='python_table.py.j2', + output_filename=os.path.join(PATH_UP, 'wcwidth', 'table_zero.py'), + fn_data=fetch_table_zero_data) + ] + for render_def in CODEGEN_DEFINITIONS: + with open(render_def.output_filename, 'w') as fout: + data = render_def.fn_data() + print(f'write {render_def.output_filename}: ', flush=True, end='') + fout.write(render_template(render_def.jinja_filename, **data)) + print('ok') if __name__ == '__main__': diff --git a/code_templates/python_table.py.j2 b/code_templates/python_table.py.j2 new file mode 100644 index 0000000..8c0e340 --- /dev/null +++ b/code_templates/python_table.py.j2 @@ -0,0 +1,17 @@ +""" +Exports {{ variable_name }} table keyed by supporting unicode version level. + +This code generated by {{this_filepath}} on {{utc_now}}. +""" +{{ variable_name }} = { +{%- for table_version, (version_txt, version_date, txt_values) in table.items() %} + '{{ table_version }}': ( + # Source: {{ version_txt }} + # Date: {{ version_date }} + # +{%- for hex_start, hex_end, txt_description in txt_values %} + ({{ hex_start }}, {{ hex_end }},), # {{txt_description}} +{%- endfor %} + ), +{%- endfor %} +} From ad07e2d25868d92d3c684fff98048ad252bd53f6 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:15:39 -0400 Subject: [PATCH 08/57] use pip-compile & python3.10 for development --- MANIFEST.in | 4 +- bin/run_codecov.py | 42 ------------------- docs/requirements.txt | 2 - requirements-develop.txt | 1 + requirements-docs.in | 2 + requirements-tests.in | 12 ++++++ requirements-tests.txt | 91 ++++++++++++++++++++++++++++++++++++++++ requirements-update.in | 4 ++ requirements-update.txt | 26 ++++++++++++ tox.ini | 73 +++++++++++++------------------- 10 files changed, 168 insertions(+), 89 deletions(-) delete mode 100644 bin/run_codecov.py create mode 100644 requirements-docs.in create mode 100644 requirements-tests.in create mode 100644 requirements-tests.txt create mode 100644 requirements-update.in create mode 100644 requirements-update.txt diff --git a/MANIFEST.in b/MANIFEST.in index 48e772c..8144aa2 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -1,2 +1,2 @@ -include LICENSE *.rst -recursive-include tests *.py \ No newline at end of file +include LICENSE +recursive-include *.py *.j2 *.rst diff --git a/bin/run_codecov.py b/bin/run_codecov.py deleted file mode 100644 index 3c6649a..0000000 --- a/bin/run_codecov.py +++ /dev/null @@ -1,42 +0,0 @@ -"""Workaround for https://github.com/codecov/codecov-python/issues/158.""" - -# std imports -import sys -import time - -# 3rd party -import codecov - -RETRIES = 5 -TIMEOUT = 2 - - -def main(): - """Run codecov up to RETRIES times On the final attempt, let it exit normally.""" - - # Make a copy of argv and make sure --required is in it - args = sys.argv[1:] - if '--required' not in args: - args.append('--required') - - for num in range(1, RETRIES + 1): - - print('Running codecov attempt %d: ' % num) - # On the last, let codecov handle the exit - if num == RETRIES: - codecov.main() - - try: - codecov.main(*args) - except SystemExit as err: - # If there's no exit code, it was successful - if err.code: - time.sleep(TIMEOUT) - else: - sys.exit(err.code) - else: - break - - -if __name__ == '__main__': - main() diff --git a/docs/requirements.txt b/docs/requirements.txt index 2a8503d..ab3f3dd 100644 --- a/docs/requirements.txt +++ b/docs/requirements.txt @@ -1,4 +1,2 @@ Sphinx -sphinx-paramlinks sphinx_rtd_theme -sphinxcontrib-manpage diff --git a/requirements-develop.txt b/requirements-develop.txt index 936bcb9..018a884 100644 --- a/requirements-develop.txt +++ b/requirements-develop.txt @@ -1,2 +1,3 @@ +# This is just for the bin/wcwidth-browser.py script blessed>=1.14.1,<2 docopt==0.6.2 diff --git a/requirements-docs.in b/requirements-docs.in new file mode 100644 index 0000000..ab3f3dd --- /dev/null +++ b/requirements-docs.in @@ -0,0 +1,2 @@ +Sphinx +sphinx_rtd_theme diff --git a/requirements-tests.in b/requirements-tests.in new file mode 100644 index 0000000..f90c294 --- /dev/null +++ b/requirements-tests.in @@ -0,0 +1,12 @@ +pytest +pytest-cov +flake8 +autopep8 +docformatter +isort +pylint +pydocstyle +restructuredtext_lint +doc8 +pygments + diff --git a/requirements-tests.txt b/requirements-tests.txt new file mode 100644 index 0000000..121a046 --- /dev/null +++ b/requirements-tests.txt @@ -0,0 +1,91 @@ +# +# This file is autogenerated by pip-compile with python 3.10 +# To update, run: +# +# pip-compile --no-emit-index-url --output-file=requirements-tests.txt requirements-tests.in +# +astroid==2.9.3 + # via pylint +attrs==21.4.0 + # via pytest +autopep8==1.6.0 + # via -r requirements-tests.in +coverage[toml]==6.3.2 + # via pytest-cov +doc8==0.10.1 + # via -r requirements-tests.in +docformatter==1.4 + # via -r requirements-tests.in +docutils==0.18.1 + # via + # doc8 + # restructuredtext-lint +flake8==4.0.1 + # via -r requirements-tests.in +iniconfig==1.1.1 + # via pytest +isort==5.10.1 + # via + # -r requirements-tests.in + # pylint +lazy-object-proxy==1.7.1 + # via astroid +mccabe==0.6.1 + # via + # flake8 + # pylint +packaging==21.3 + # via pytest +pbr==5.8.1 + # via stevedore +platformdirs==2.5.1 + # via pylint +pluggy==1.0.0 + # via pytest +py==1.11.0 + # via pytest +pycodestyle==2.8.0 + # via + # autopep8 + # flake8 +pydocstyle==6.1.1 + # via -r requirements-tests.in +pyflakes==2.4.0 + # via flake8 +pygments==2.11.2 + # via + # -r requirements-tests.in + # doc8 +pylint==2.12.2 + # via -r requirements-tests.in +pyparsing==3.0.7 + # via packaging +pytest==7.1.1 + # via + # -r requirements-tests.in + # pytest-cov +pytest-cov==3.0.0 + # via -r requirements-tests.in +restructuredtext-lint==1.4.0 + # via + # -r requirements-tests.in + # doc8 +snowballstemmer==2.2.0 + # via pydocstyle +stevedore==3.5.0 + # via doc8 +toml==0.10.2 + # via + # autopep8 + # pylint +tomli==2.0.1 + # via + # coverage + # pytest +untokenize==0.1.1 + # via docformatter +wrapt==1.13.3 + # via astroid + +# The following packages are considered to be unsafe in a requirements file: +# setuptools diff --git a/requirements-update.in b/requirements-update.in new file mode 100644 index 0000000..6db199e --- /dev/null +++ b/requirements-update.in @@ -0,0 +1,4 @@ +jinja2 +requests +tenacity +python-dateutil diff --git a/requirements-update.txt b/requirements-update.txt new file mode 100644 index 0000000..844da0e --- /dev/null +++ b/requirements-update.txt @@ -0,0 +1,26 @@ +# +# This file is autogenerated by pip-compile with python 3.10 +# To update, run: +# +# pip-compile --no-emit-index-url --output-file=requirements-update.txt requirements-update.in +# +certifi==2021.10.8 + # via requests +charset-normalizer==2.0.12 + # via requests +idna==3.3 + # via requests +jinja2==3.0.3 + # via -r requirements-update.in +markupsafe==2.1.1 + # via jinja2 +python-dateutil==2.8.2 + # via -r requirements-update.in +requests==2.27.1 + # via -r requirements-update.in +six==1.16.0 + # via python-dateutil +tenacity==8.0.1 + # via -r requirements-update.in +urllib3==1.26.9 + # via requests diff --git a/tox.ini b/tox.ini index 7282dc7..8adbe1b 100644 --- a/tox.ini +++ b/tox.ini @@ -3,8 +3,7 @@ envlist = update, compile, autopep8, docformatter, isort, pylint, flake8, flake8 skip_missing_interpreters = true [testenv] -deps = pytest==4.6.10 - pytest-cov==2.8.1 +deps = requirements-tests.txt commands = {envpython} -m pytest --cov-config={toxinidir}/tox.ini {posargs:\ --strict --verbose \ --junit-xml=.tox/results.{envname}.xml \ @@ -43,7 +42,6 @@ junit_family = xunit1 [flake8] max-line-length = 100 exclude = .tox,build -deps = flake8==3.8.2 [coverage:run] branch = True @@ -59,24 +57,24 @@ precision = 1 source = wcwidth/ [testenv:compile] -basepython = python3.9 +basepython = python3.10 commands = python -m compileall {toxinidir}/wcwidth +[testenv:update_requirements] +basepython = python3.10 +deps = pip-tools +commands = pip-compile --no-emit-index-url requirements-update.in -o requirements-update.txt + pip-compile --no-emit-index-url requirements-tests.in -o requirements-tests.txt + pip-compile --no-emit-index-url requirements-docs.in -o docs/requirements.txt + [testenv:update] +basepython = python3.10 usedevelop = true -basepython = python3.9 -deps = jinja2 - requests -commands = python {toxinidir}/bin/update-tables.py -# TODO -# -# python -mcompileall {toxinidir}/wcwidth/table_zero.py \ -# {toxinidir}/wcwidth/table_wide.py -# TODO: and most certainly compile any C code .. +deps = -r requirements-update.txt +commands = python {toxinidir}/bin/update-tables.py {posargs} [testenv:autopep8] -basepython = python3.9 -deps = autopep8==1.4.4 +basepython = python3.10 commands = {envbindir}/autopep8 \ --in-place \ @@ -86,9 +84,7 @@ commands = wcwidth/ bin/ tests/ setup.py [testenv:docformatter] -deps = - docformatter==1.3.1 - untokenize==0.1.1 +basepython = python3.10 commands = {envbindir}/docformatter \ --in-place \ @@ -100,65 +96,56 @@ commands = {toxinidir}/bin \ {toxinidir}/setup.py \ {toxinidir}/docs/conf.py -basepython = python3.9 [testenv:isort] -deps = {[testenv]deps} - -r docs/requirements.txt - isort==4.3.21 +basepython = python3.10 commands = {envbindir}/isort --quiet --apply --recursive -basepython = python3.9 [testenv:pylint] -deps = pylint==2.5.2 +basepython = python3.10 commands = {envbindir}/pylint --rcfile={toxinidir}/.pylintrc \ --ignore=tests,docs,setup.py,conf.py,build,distutils,.pyenv,.git,.tox \ {posargs:{toxinidir}}/wcwidth [testenv:flake8] -deps = {[flake8]deps} +basepython = python3.10 commands = {envbindir}/flake8 --ignore=F401,W503,W504 --exclude=tests setup.py docs/ wcwidth/ bin/ [testenv:flake8_tests] -deps = {[flake8]deps} +basepython = python3.10 commands = {envbindir}/flake8 --ignore=W503,W504,F811,F401 tests/ bin/ [testenv:pydocstyle] -deps = pydocstyle==5.0.2 - restructuredtext_lint==1.3.0 - doc8==0.8.0 - pygments +basepython = python3.10 commands = {envbindir}/pydocstyle --source --explain {toxinidir}/blessed {envbindir}/rst-lint README.rst {envbindir}/doc8 --ignore-path docs/_build --ignore D000 docs -[testenv:check] -deps = -rrequirements-develop.txt -usedevelop = true -commands = prospector {posargs:--no-autodetect --die-on-tool-error} -basepython = python3.9 - [testenv:docs] -deps = sphinx +basepython = python3.10 +deps = -r {toxinidir}/docs/requirements.txt commands = sphinx-build docs/ build/sphinx [testenv:sphinx] +basepython = python3.10 deps = -r {toxinidir}/docs/requirements.txt commands = {envbindir}/sphinx-build {posargs:-v -W -d {toxinidir}/docs/_build/doctrees -b html docs {toxinidir}/docs/_build/html} [testenv:linkcheck] +basepython = python3.10 deps = -r {toxinidir}/docs/requirements.txt commands = {envbindir}/sphinx-build -v -W -d {toxinidir}/docs/_build/doctrees -b linkcheck docs docs/_build/linkcheck [testenv:codecov] -basepython = python{env:TOXPYTHON:{env:TRAVIS_PYTHON_VERSION:3.9}} +basepython = python{env:TOXPYTHON:{env:TRAVIS_PYTHON_VERSION:3.10}} passenv = TOXENV CI TRAVIS TRAVIS_* CODECOV_* -deps = codecov>=1.4.0 - tenacity==6.1.0 -# commands = codecov -e TOXENV -# Workaround for https://github.com/codecov/codecov-python/issues/158 -commands = {envpython} bin/run_codecov.py -e TOXENV +deps = codecov +commands = codecov -e TOXENV +# Run a command using requirements-develop.txt, for example: +# +# tox -e update -- bin/wcwidth-browser.py [testenv:develop] +basepython = python3.10 deps = -rrequirements-develop.txt commands = {posargs} From 6d4fa362e548c987e32adbdd87e9e045592db0e0 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:18:30 -0400 Subject: [PATCH 09/57] lint --- bin/update-tables.py | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 8f3ef3a..2038fa4 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -28,32 +28,35 @@ import collections import unicodedata +# 3rd party # third party import jinja2 -import tenacity import requests +import tenacity import dateutil.parser - URL_UNICODE_DERIVED_AGE = 'http://www.unicode.org/Public/UCD/latest/ucd/DerivedAge.txt' -URL_EASTASIAN_WIDTH = 'http://www.unicode.org/Public/{version}/ucd/EastAsianWidth.txt' -URL_DERIVED_CATEGORY = 'http://www.unicode.org/Public/{version}/ucd/extracted/DerivedGeneralCategory.txt' +URL_EASTASIAN_WIDTH = 'http://www.unicode.org/Public/{version}/ucd/EastAsianWidth.txt' +URL_DERIVED_CATEGORY = 'http://www.unicode.org/Public/{version}/ucd/extracted/DerivedGeneralCategory.txt' EXCLUDE_VERSIONS = ['2.0.0', '2.1.2', '3.0.0', '3.1.0', '3.2.0', '4.0.0'] PATH_UP = os.path.relpath(os.path.join(os.path.dirname(__file__), os.path.pardir)) PATH_DATA = os.path.join(PATH_UP, 'data') -THIS_FILEPATH = os.path.relpath(__file__, os.path.join(PATH_UP, os.path.pardir)) # "wcwidth/bin/update-tables.py" +THIS_FILEPATH = os.path.relpath(__file__, os.path.join( + PATH_UP, os.path.pardir)) # "wcwidth/bin/update-tables.py" JINJA_ENV = jinja2.Environment( - loader=jinja2.FileSystemLoader(os.path.join(PATH_UP, 'code_templates')), - keep_trailing_newline=True) + loader=jinja2.FileSystemLoader(os.path.join(PATH_UP, 'code_templates')), + keep_trailing_newline=True) UTC_NOW = datetime.datetime.utcnow().strftime("%Y-%m-%d %H:%M:%S UTC") CONNECT_TIMEOUT = int(os.environ.get('CONNECT_TIMEOUT', '10')) FETCH_BLOCKSIZE = int(os.environ.get('FETCH_BLOCKSIZE', '4096')) MAX_RETRIES = int(os.environ.get('MAX_RETRIES', '10')) TableDef = collections.namedtuple('table', ['version', 'date', 'values']) -RenderDefinition = collections.namedtuple('render', ['jinja_filename', 'output_filename', 'fn_data']) +RenderDefinition = collections.namedtuple( + 'render', ['jinja_filename', 'output_filename', 'fn_data']) logging.basicConfig(stream=sys.stderr, level=logging.DEBUG) logger = logging.getLogger(__name__) + @functools.cache def fetch_unicode_versions(): """Fetch, determine, and return Unicode Versions for processing.""" @@ -90,6 +93,7 @@ def fetch_table_wide_data(): table[version] = parse_category(fname=fname, category_codes=('W', 'F',)) return {'table': table, 'variable_name': 'WIDE_EASTASIAN'} + def fetch_table_zero_data(): """Fetch and update zero width tables.""" table = {} @@ -109,6 +113,7 @@ def render_template(jinja_filename, utc_now=UTC_NOW, this_filepath=THIS_FILEPATH this_filepath=THIS_FILEPATH, **kwargs) + def cite_source_description(filename): """Return unicode.org source data file's own description as citation.""" header_twolines = [ @@ -119,6 +124,7 @@ def cite_source_description(filename): if len(header_twolines) == 2: return header_twolines + def make_sortable_source_name(filename): # make a sortable filename of unicode text file, # @@ -128,6 +134,7 @@ def make_sortable_source_name(filename): version_numbers, _extension = os.path.splitext(remaining) return (basename, *list(map(int, version_numbers.split('.')))) + def make_table(values): """Return a tuple of lookup tables for given values.""" start, end = values[0], values[0] @@ -150,6 +157,7 @@ def make_table(values): table.append((value, value,)) return tuple(table) + def convert_values_to_string_table(values): """Convert integers into string table of (hex_start, hex_end, txt_description).""" pytable_values = [] @@ -202,6 +210,7 @@ def parse_category(fname, category_codes=('Me', 'Mn',)): print('ok') return TableDef(version, date, txt_values) + def is_url_newer(url, fname): if not os.path.exists(fname): return True @@ -213,6 +222,7 @@ def is_url_newer(url, fname): return remote_url_dt > local_file_dt return False + @tenacity.retry(reraise=True, wait=tenacity.wait_none(), retry=tenacity.retry_if_exception_type(requests.exceptions.RequestException), stop=tenacity.stop_after_attempt(MAX_RETRIES), @@ -227,7 +237,7 @@ def do_retrieve(url, fname): resp = requests.get(url, timeout=CONNECT_TIMEOUT) resp.raise_for_status() print(f"saving {fname}: ", end='', flush=True) - with open(fname , 'wb') as fout: + with open(fname, 'wb') as fout: for chunk in resp.iter_content(FETCH_BLOCKSIZE): fout.write(chunk) print('.', end='', flush=True) From 589ebc5e96630a1a7862a8f42280dcbcb0d56315 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:32:01 -0400 Subject: [PATCH 10/57] isort added these, fine enough --- wcwidth/wcwidth.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/wcwidth/wcwidth.py b/wcwidth/wcwidth.py index e543f9a..6162cdd 100644 --- a/wcwidth/wcwidth.py +++ b/wcwidth/wcwidth.py @@ -73,9 +73,11 @@ from .unicode_versions import list_versions try: + # std imports from functools import lru_cache except ImportError: # lru_cache was added in Python 3.2 + # 3rd party from backports.functools_lru_cache import lru_cache # global cache From 3f9ee7bb3e76132e4788667bc81367e23e053318 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:32:16 -0400 Subject: [PATCH 11/57] small small linting/whitespace kill changes --- wcwidth/table_wide.py | 468 +++--- wcwidth/table_zero.py | 2792 +++++++++++++++++------------------ wcwidth/unicode_versions.py | 3 +- 3 files changed, 1632 insertions(+), 1631 deletions(-) diff --git a/wcwidth/table_wide.py b/wcwidth/table_wide.py index d4dd390..fe517db 100644 --- a/wcwidth/table_wide.py +++ b/wcwidth/table_wide.py @@ -1,16 +1,16 @@ """ Exports WIDE_EASTASIAN table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2022-03-20 21:12:52 UTC. +This code generated by wcwidth/bin/update-tables.py on 2022-03-20 21:29:31 UTC. """ WIDE_EASTASIAN = { '4.1.0': ( # Source: EastAsianWidth-4.1.0.txt # Date: 2005-03-17, 15:21:00 PST [KW] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x01159,), # Hangul Choseong Kiyeok ..Hangul Choseong Yeorinhi - (0x0115f, 0x0115f,), # Hangul Choseong Filler + (0x0115f, 0x0115f,), # Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified @@ -47,9 +47,9 @@ # Source: EastAsianWidth-5.0.0.txt # Date: 2006-02-15, 14:39:00 PST [KW] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x01159,), # Hangul Choseong Kiyeok ..Hangul Choseong Yeorinhi - (0x0115f, 0x0115f,), # Hangul Choseong Filler + (0x0115f, 0x0115f,), # Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified @@ -86,9 +86,9 @@ # Source: EastAsianWidth-5.1.0.txt # Date: 2008-03-20, 17:42:00 PDT [KW] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x01159,), # Hangul Choseong Kiyeok ..Hangul Choseong Yeorinhi - (0x0115f, 0x0115f,), # Hangul Choseong Filler + (0x0115f, 0x0115f,), # Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified @@ -125,7 +125,7 @@ # Source: EastAsianWidth-5.2.0.txt # Date: 2009-06-09, 17:47:00 PDT [KW] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x011a3, 0x011a7,), # Hangul Jungseong A-eu ..Hangul Jungseong O-yae (0x011fa, 0x011ff,), # Hangul Jongseong Kiyeok-..Hangul Jongseong Ssangni @@ -158,7 +158,7 @@ (0x0fe68, 0x0fe6b,), # Small Reverse Solidus ..Small Commercial At (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign - (0x1f200, 0x1f200,), # Square Hiragana Hoka + (0x1f200, 0x1f200,), # Square Hiragana Hoka (0x1f210, 0x1f231,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo (0x1f240, 0x1f248,), # Tortoise Shell Bracketed..Tortoise Shell Bracketed (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) @@ -168,7 +168,7 @@ # Source: EastAsianWidth-6.0.0.txt # Date: 2010-08-17, 12:17:00 PDT [KW] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x011a3, 0x011a7,), # Hangul Jungseong A-eu ..Hangul Jungseong O-yae (0x011fa, 0x011ff,), # Hangul Jongseong Kiyeok-..Hangul Jongseong Ssangni @@ -214,7 +214,7 @@ # Source: EastAsianWidth-6.1.0.txt # Date: 2011-09-19, 18:46:00 GMT [KW] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x011a3, 0x011a7,), # Hangul Jungseong A-eu ..Hangul Jungseong O-yae (0x011fa, 0x011ff,), # Hangul Jongseong Kiyeok-..Hangul Jongseong Ssangni @@ -259,7 +259,7 @@ # Source: EastAsianWidth-6.2.0.txt # Date: 2012-05-15, 18:30:00 GMT [KW] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap @@ -300,7 +300,7 @@ # Source: EastAsianWidth-6.3.0.txt # Date: 2013-02-05, 20:09:00 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap @@ -341,7 +341,7 @@ # Source: EastAsianWidth-7.0.0.txt # Date: 2014-02-28, 23:15:00 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap @@ -382,7 +382,7 @@ # Source: EastAsianWidth-8.0.0.txt # Date: 2015-02-10, 21:00:00 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap @@ -423,42 +423,42 @@ # Source: EastAsianWidth-9.0.0.txt # Date: 2016-05-27, 17:00:00 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub - (0x023f0, 0x023f0,), # Alarm Clock - (0x023f3, 0x023f3,), # Hourglass With Flowing S + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing Sand (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage (0x02648, 0x02653,), # Aries ..Pisces - (0x0267f, 0x0267f,), # Wheelchair Symbol - (0x02693, 0x02693,), # Anchor - (0x026a1, 0x026a1,), # High Voltage Sign + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle (0x026bd, 0x026be,), # Soccer Ball ..Baseball (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud - (0x026ce, 0x026ce,), # Ophiuchus - (0x026d4, 0x026d4,), # No Entry - (0x026ea, 0x026ea,), # Church + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church (0x026f2, 0x026f3,), # Fountain ..Flag In Hole - (0x026f5, 0x026f5,), # Sailboat - (0x026fa, 0x026fa,), # Tent - (0x026fd, 0x026fd,), # Fuel Pump - (0x02705, 0x02705,), # White Heavy Check Mark + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand - (0x02728, 0x02728,), # Sparkles - (0x0274c, 0x0274c,), # Cross Mark - (0x0274e, 0x0274e,), # Negative Squared Cross M + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross Mark (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O - (0x02757, 0x02757,), # Heavy Exclamation Mark S + (0x02757, 0x02757,), # Heavy Exclamation Mark Symbol (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign - (0x027b0, 0x027b0,), # Curly Loop - (0x027bf, 0x027bf,), # Double Curly Loop + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square - (0x02b50, 0x02b50,), # White Medium Star - (0x02b55, 0x02b55,), # Heavy Large Circle + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute @@ -485,13 +485,13 @@ (0x0fe68, 0x0fe6b,), # Small Reverse Solidus ..Small Commercial At (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign - (0x16fe0, 0x16fe0,), # Tangut Iteration Mark - (0x17000, 0x187ec,), # (nil) + (0x16fe0, 0x16fe0,), # Tangut Iteration Mark + (0x17000, 0x187ec,), # (nil) (0x18800, 0x18af2,), # Tangut Component-001 ..Tangut Component-755 (0x1b000, 0x1b001,), # Katakana Letter Archaic ..Hiragana Letter Archaic - (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker - (0x1f18e, 0x1f18e,), # Negative Squared Ab + (0x1f18e, 0x1f18e,), # Negative Squared Ab (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo @@ -504,30 +504,30 @@ (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And (0x1f3e0, 0x1f3f0,), # House Building ..European Castle - (0x1f3f4, 0x1f3f4,), # Waving Black Flag + (0x1f3f4, 0x1f3f4,), # Waving Black Flag (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints - (0x1f440, 0x1f440,), # Eyes + (0x1f440, 0x1f440,), # Eyes (0x1f442, 0x1f4fc,), # Ear ..Videocassette (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty - (0x1f57a, 0x1f57a,), # Man Dancing + (0x1f57a, 0x1f57a,), # Man Dancing (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be - (0x1f5a4, 0x1f5a4,), # Black Heart + (0x1f5a4, 0x1f5a4,), # Black Heart (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage - (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving (0x1f6f4, 0x1f6f6,), # Scooter ..Canoe (0x1f910, 0x1f91e,), # Zipper-mouth Face ..Hand With Index And Midd (0x1f920, 0x1f927,), # Face With Cowboy Hat ..Sneezing Face - (0x1f930, 0x1f930,), # Pregnant Woman + (0x1f930, 0x1f930,), # Pregnant Woman (0x1f933, 0x1f93e,), # Selfie ..Handball (0x1f940, 0x1f94b,), # Wilted Flower ..Martial Arts Uniform (0x1f950, 0x1f95e,), # Croissant ..Pancakes (0x1f980, 0x1f991,), # Crab ..Squid - (0x1f9c0, 0x1f9c0,), # Cheese Wedge + (0x1f9c0, 0x1f9c0,), # Cheese Wedge (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), @@ -535,42 +535,42 @@ # Source: EastAsianWidth-10.0.0.txt # Date: 2017-03-08, 02:00:00 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub - (0x023f0, 0x023f0,), # Alarm Clock - (0x023f3, 0x023f3,), # Hourglass With Flowing S + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing Sand (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage (0x02648, 0x02653,), # Aries ..Pisces - (0x0267f, 0x0267f,), # Wheelchair Symbol - (0x02693, 0x02693,), # Anchor - (0x026a1, 0x026a1,), # High Voltage Sign + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle (0x026bd, 0x026be,), # Soccer Ball ..Baseball (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud - (0x026ce, 0x026ce,), # Ophiuchus - (0x026d4, 0x026d4,), # No Entry - (0x026ea, 0x026ea,), # Church + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church (0x026f2, 0x026f3,), # Fountain ..Flag In Hole - (0x026f5, 0x026f5,), # Sailboat - (0x026fa, 0x026fa,), # Tent - (0x026fd, 0x026fd,), # Fuel Pump - (0x02705, 0x02705,), # White Heavy Check Mark + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand - (0x02728, 0x02728,), # Sparkles - (0x0274c, 0x0274c,), # Cross Mark - (0x0274e, 0x0274e,), # Negative Squared Cross M + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross Mark (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O - (0x02757, 0x02757,), # Heavy Exclamation Mark S + (0x02757, 0x02757,), # Heavy Exclamation Mark Symbol (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign - (0x027b0, 0x027b0,), # Curly Loop - (0x027bf, 0x027bf,), # Double Curly Loop + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square - (0x02b50, 0x02b50,), # White Medium Star - (0x02b55, 0x02b55,), # Heavy Large Circle + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute @@ -598,13 +598,13 @@ (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign (0x16fe0, 0x16fe1,), # Tangut Iteration Mark ..Nushu Iteration Mark - (0x17000, 0x187ec,), # (nil) + (0x17000, 0x187ec,), # (nil) (0x18800, 0x18af2,), # Tangut Component-001 ..Tangut Component-755 (0x1b000, 0x1b11e,), # Katakana Letter Archaic ..Hentaigana Letter N-mu-m (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb - (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker - (0x1f18e, 0x1f18e,), # Negative Squared Ab + (0x1f18e, 0x1f18e,), # Negative Squared Ab (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo @@ -618,19 +618,19 @@ (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And (0x1f3e0, 0x1f3f0,), # House Building ..European Castle - (0x1f3f4, 0x1f3f4,), # Waving Black Flag + (0x1f3f4, 0x1f3f4,), # Waving Black Flag (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints - (0x1f440, 0x1f440,), # Eyes + (0x1f440, 0x1f440,), # Eyes (0x1f442, 0x1f4fc,), # Ear ..Videocassette (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty - (0x1f57a, 0x1f57a,), # Man Dancing + (0x1f57a, 0x1f57a,), # Man Dancing (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be - (0x1f5a4, 0x1f5a4,), # Black Heart + (0x1f5a4, 0x1f5a4,), # Black Heart (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage - (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving (0x1f6f4, 0x1f6f8,), # Scooter ..Flying Saucer @@ -638,7 +638,7 @@ (0x1f940, 0x1f94c,), # Wilted Flower ..Curling Stone (0x1f950, 0x1f96b,), # Croissant ..Canned Food (0x1f980, 0x1f997,), # Crab ..Cricket - (0x1f9c0, 0x1f9c0,), # Cheese Wedge + (0x1f9c0, 0x1f9c0,), # Cheese Wedge (0x1f9d0, 0x1f9e6,), # Face With Monocle ..Socks (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) @@ -647,42 +647,42 @@ # Source: EastAsianWidth-11.0.0.txt # Date: 2018-05-14, 09:41:59 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub - (0x023f0, 0x023f0,), # Alarm Clock - (0x023f3, 0x023f3,), # Hourglass With Flowing S + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing Sand (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage (0x02648, 0x02653,), # Aries ..Pisces - (0x0267f, 0x0267f,), # Wheelchair Symbol - (0x02693, 0x02693,), # Anchor - (0x026a1, 0x026a1,), # High Voltage Sign + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle (0x026bd, 0x026be,), # Soccer Ball ..Baseball (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud - (0x026ce, 0x026ce,), # Ophiuchus - (0x026d4, 0x026d4,), # No Entry - (0x026ea, 0x026ea,), # Church + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church (0x026f2, 0x026f3,), # Fountain ..Flag In Hole - (0x026f5, 0x026f5,), # Sailboat - (0x026fa, 0x026fa,), # Tent - (0x026fd, 0x026fd,), # Fuel Pump - (0x02705, 0x02705,), # White Heavy Check Mark + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand - (0x02728, 0x02728,), # Sparkles - (0x0274c, 0x0274c,), # Cross Mark - (0x0274e, 0x0274e,), # Negative Squared Cross M + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross Mark (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O - (0x02757, 0x02757,), # Heavy Exclamation Mark S + (0x02757, 0x02757,), # Heavy Exclamation Mark Symbol (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign - (0x027b0, 0x027b0,), # Curly Loop - (0x027bf, 0x027bf,), # Double Curly Loop + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square - (0x02b50, 0x02b50,), # White Medium Star - (0x02b55, 0x02b55,), # Heavy Large Circle + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute @@ -710,13 +710,13 @@ (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign (0x16fe0, 0x16fe1,), # Tangut Iteration Mark ..Nushu Iteration Mark - (0x17000, 0x187f1,), # (nil) + (0x17000, 0x187f1,), # (nil) (0x18800, 0x18af2,), # Tangut Component-001 ..Tangut Component-755 (0x1b000, 0x1b11e,), # Katakana Letter Archaic ..Hentaigana Letter N-mu-m (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb - (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker - (0x1f18e, 0x1f18e,), # Negative Squared Ab + (0x1f18e, 0x1f18e,), # Negative Squared Ab (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo @@ -730,26 +730,26 @@ (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And (0x1f3e0, 0x1f3f0,), # House Building ..European Castle - (0x1f3f4, 0x1f3f4,), # Waving Black Flag + (0x1f3f4, 0x1f3f4,), # Waving Black Flag (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints - (0x1f440, 0x1f440,), # Eyes + (0x1f440, 0x1f440,), # Eyes (0x1f442, 0x1f4fc,), # Ear ..Videocassette (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty - (0x1f57a, 0x1f57a,), # Man Dancing + (0x1f57a, 0x1f57a,), # Man Dancing (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be - (0x1f5a4, 0x1f5a4,), # Black Heart + (0x1f5a4, 0x1f5a4,), # Black Heart (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage - (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving (0x1f6f4, 0x1f6f9,), # Scooter ..Skateboard (0x1f910, 0x1f93e,), # Zipper-mouth Face ..Handball (0x1f940, 0x1f970,), # Wilted Flower ..Smiling Face With Smilin (0x1f973, 0x1f976,), # Face With Party Horn And..Freezing Face - (0x1f97a, 0x1f97a,), # Face With Pleading Eyes + (0x1f97a, 0x1f97a,), # Face With Pleading Eyes (0x1f97c, 0x1f9a2,), # Lab Coat ..Swan (0x1f9b0, 0x1f9b9,), # Emoji Component Red Hair..Supervillain (0x1f9c0, 0x1f9c2,), # Cheese Wedge ..Salt Shaker @@ -761,42 +761,42 @@ # Source: EastAsianWidth-12.0.0.txt # Date: 2019-01-21, 14:12:58 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub - (0x023f0, 0x023f0,), # Alarm Clock - (0x023f3, 0x023f3,), # Hourglass With Flowing S + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing Sand (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage (0x02648, 0x02653,), # Aries ..Pisces - (0x0267f, 0x0267f,), # Wheelchair Symbol - (0x02693, 0x02693,), # Anchor - (0x026a1, 0x026a1,), # High Voltage Sign + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle (0x026bd, 0x026be,), # Soccer Ball ..Baseball (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud - (0x026ce, 0x026ce,), # Ophiuchus - (0x026d4, 0x026d4,), # No Entry - (0x026ea, 0x026ea,), # Church + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church (0x026f2, 0x026f3,), # Fountain ..Flag In Hole - (0x026f5, 0x026f5,), # Sailboat - (0x026fa, 0x026fa,), # Tent - (0x026fd, 0x026fd,), # Fuel Pump - (0x02705, 0x02705,), # White Heavy Check Mark + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand - (0x02728, 0x02728,), # Sparkles - (0x0274c, 0x0274c,), # Cross Mark - (0x0274e, 0x0274e,), # Negative Squared Cross M + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross Mark (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O - (0x02757, 0x02757,), # Heavy Exclamation Mark S + (0x02757, 0x02757,), # Heavy Exclamation Mark Symbol (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign - (0x027b0, 0x027b0,), # Curly Loop - (0x027bf, 0x027bf,), # Double Curly Loop + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square - (0x02b50, 0x02b50,), # White Medium Star - (0x02b55, 0x02b55,), # Heavy Large Circle + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute @@ -824,15 +824,15 @@ (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign (0x16fe0, 0x16fe3,), # Tangut Iteration Mark ..Old Chinese Iteration Ma - (0x17000, 0x187f7,), # (nil) + (0x17000, 0x187f7,), # (nil) (0x18800, 0x18af2,), # Tangut Component-001 ..Tangut Component-755 (0x1b000, 0x1b11e,), # Katakana Letter Archaic ..Hentaigana Letter N-mu-m (0x1b150, 0x1b152,), # Hiragana Letter Small Wi..Hiragana Letter Small Wo (0x1b164, 0x1b167,), # Katakana Letter Small Wi..Katakana Letter Small N (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb - (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker - (0x1f18e, 0x1f18e,), # Negative Squared Ab + (0x1f18e, 0x1f18e,), # Negative Squared Ab (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo @@ -846,21 +846,21 @@ (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And (0x1f3e0, 0x1f3f0,), # House Building ..European Castle - (0x1f3f4, 0x1f3f4,), # Waving Black Flag + (0x1f3f4, 0x1f3f4,), # Waving Black Flag (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints - (0x1f440, 0x1f440,), # Eyes + (0x1f440, 0x1f440,), # Eyes (0x1f442, 0x1f4fc,), # Ear ..Videocassette (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty - (0x1f57a, 0x1f57a,), # Man Dancing + (0x1f57a, 0x1f57a,), # Man Dancing (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be - (0x1f5a4, 0x1f5a4,), # Black Heart + (0x1f5a4, 0x1f5a4,), # Black Heart (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage - (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley - (0x1f6d5, 0x1f6d5,), # Hindu Temple + (0x1f6d5, 0x1f6d5,), # Hindu Temple (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving (0x1f6f4, 0x1f6fa,), # Scooter ..Auto Rickshaw (0x1f7e0, 0x1f7eb,), # Large Orange Circle ..Large Brown Square @@ -881,42 +881,42 @@ # Source: EastAsianWidth-12.1.0.txt # Date: 2019-03-31, 22:01:58 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub - (0x023f0, 0x023f0,), # Alarm Clock - (0x023f3, 0x023f3,), # Hourglass With Flowing S + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing Sand (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage (0x02648, 0x02653,), # Aries ..Pisces - (0x0267f, 0x0267f,), # Wheelchair Symbol - (0x02693, 0x02693,), # Anchor - (0x026a1, 0x026a1,), # High Voltage Sign + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle (0x026bd, 0x026be,), # Soccer Ball ..Baseball (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud - (0x026ce, 0x026ce,), # Ophiuchus - (0x026d4, 0x026d4,), # No Entry - (0x026ea, 0x026ea,), # Church + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church (0x026f2, 0x026f3,), # Fountain ..Flag In Hole - (0x026f5, 0x026f5,), # Sailboat - (0x026fa, 0x026fa,), # Tent - (0x026fd, 0x026fd,), # Fuel Pump - (0x02705, 0x02705,), # White Heavy Check Mark + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand - (0x02728, 0x02728,), # Sparkles - (0x0274c, 0x0274c,), # Cross Mark - (0x0274e, 0x0274e,), # Negative Squared Cross M + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross Mark (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O - (0x02757, 0x02757,), # Heavy Exclamation Mark S + (0x02757, 0x02757,), # Heavy Exclamation Mark Symbol (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign - (0x027b0, 0x027b0,), # Curly Loop - (0x027bf, 0x027bf,), # Double Curly Loop + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square - (0x02b50, 0x02b50,), # White Medium Star - (0x02b55, 0x02b55,), # Heavy Large Circle + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute @@ -943,15 +943,15 @@ (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign (0x16fe0, 0x16fe3,), # Tangut Iteration Mark ..Old Chinese Iteration Ma - (0x17000, 0x187f7,), # (nil) + (0x17000, 0x187f7,), # (nil) (0x18800, 0x18af2,), # Tangut Component-001 ..Tangut Component-755 (0x1b000, 0x1b11e,), # Katakana Letter Archaic ..Hentaigana Letter N-mu-m (0x1b150, 0x1b152,), # Hiragana Letter Small Wi..Hiragana Letter Small Wo (0x1b164, 0x1b167,), # Katakana Letter Small Wi..Katakana Letter Small N (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb - (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker - (0x1f18e, 0x1f18e,), # Negative Squared Ab + (0x1f18e, 0x1f18e,), # Negative Squared Ab (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo @@ -965,21 +965,21 @@ (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And (0x1f3e0, 0x1f3f0,), # House Building ..European Castle - (0x1f3f4, 0x1f3f4,), # Waving Black Flag + (0x1f3f4, 0x1f3f4,), # Waving Black Flag (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints - (0x1f440, 0x1f440,), # Eyes + (0x1f440, 0x1f440,), # Eyes (0x1f442, 0x1f4fc,), # Ear ..Videocassette (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty - (0x1f57a, 0x1f57a,), # Man Dancing + (0x1f57a, 0x1f57a,), # Man Dancing (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be - (0x1f5a4, 0x1f5a4,), # Black Heart + (0x1f5a4, 0x1f5a4,), # Black Heart (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage - (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley - (0x1f6d5, 0x1f6d5,), # Hindu Temple + (0x1f6d5, 0x1f6d5,), # Hindu Temple (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving (0x1f6f4, 0x1f6fa,), # Scooter ..Auto Rickshaw (0x1f7e0, 0x1f7eb,), # Large Orange Circle ..Large Brown Square @@ -1000,42 +1000,42 @@ # Source: EastAsianWidth-13.0.0.txt # Date: 2029-01-21, 18:14:00 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub - (0x023f0, 0x023f0,), # Alarm Clock - (0x023f3, 0x023f3,), # Hourglass With Flowing S + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing Sand (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage (0x02648, 0x02653,), # Aries ..Pisces - (0x0267f, 0x0267f,), # Wheelchair Symbol - (0x02693, 0x02693,), # Anchor - (0x026a1, 0x026a1,), # High Voltage Sign + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle (0x026bd, 0x026be,), # Soccer Ball ..Baseball (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud - (0x026ce, 0x026ce,), # Ophiuchus - (0x026d4, 0x026d4,), # No Entry - (0x026ea, 0x026ea,), # Church + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church (0x026f2, 0x026f3,), # Fountain ..Flag In Hole - (0x026f5, 0x026f5,), # Sailboat - (0x026fa, 0x026fa,), # Tent - (0x026fd, 0x026fd,), # Fuel Pump - (0x02705, 0x02705,), # White Heavy Check Mark + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand - (0x02728, 0x02728,), # Sparkles - (0x0274c, 0x0274c,), # Cross Mark - (0x0274e, 0x0274e,), # Negative Squared Cross M + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross Mark (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O - (0x02757, 0x02757,), # Heavy Exclamation Mark S + (0x02757, 0x02757,), # Heavy Exclamation Mark Symbol (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign - (0x027b0, 0x027b0,), # Curly Loop - (0x027bf, 0x027bf,), # Double Curly Loop + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square - (0x02b50, 0x02b50,), # White Medium Star - (0x02b55, 0x02b55,), # Heavy Large Circle + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute @@ -1062,16 +1062,16 @@ (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign (0x16fe0, 0x16fe4,), # Tangut Iteration Mark ..Khitan Small Script Fill (0x16ff0, 0x16ff1,), # Vietnamese Alternate Rea..Vietnamese Alternate Rea - (0x17000, 0x187f7,), # (nil) + (0x17000, 0x187f7,), # (nil) (0x18800, 0x18cd5,), # Tangut Component-001 ..Khitan Small Script Char - (0x18d00, 0x18d08,), # (nil) + (0x18d00, 0x18d08,), # (nil) (0x1b000, 0x1b11e,), # Katakana Letter Archaic ..Hentaigana Letter N-mu-m (0x1b150, 0x1b152,), # Hiragana Letter Small Wi..Hiragana Letter Small Wo (0x1b164, 0x1b167,), # Katakana Letter Small Wi..Katakana Letter Small N (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb - (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker - (0x1f18e, 0x1f18e,), # Negative Squared Ab + (0x1f18e, 0x1f18e,), # Negative Squared Ab (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo @@ -1085,19 +1085,19 @@ (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And (0x1f3e0, 0x1f3f0,), # House Building ..European Castle - (0x1f3f4, 0x1f3f4,), # Waving Black Flag + (0x1f3f4, 0x1f3f4,), # Waving Black Flag (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints - (0x1f440, 0x1f440,), # Eyes + (0x1f440, 0x1f440,), # Eyes (0x1f442, 0x1f4fc,), # Ear ..Videocassette (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty - (0x1f57a, 0x1f57a,), # Man Dancing + (0x1f57a, 0x1f57a,), # Man Dancing (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be - (0x1f5a4, 0x1f5a4,), # Black Heart + (0x1f5a4, 0x1f5a4,), # Black Heart (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage - (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley (0x1f6d5, 0x1f6d7,), # Hindu Temple ..Elevator (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving @@ -1122,42 +1122,42 @@ # Source: EastAsianWidth-14.0.0.txt # Date: 2021-07-06, 09:58:53 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok + (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub - (0x023f0, 0x023f0,), # Alarm Clock - (0x023f3, 0x023f3,), # Hourglass With Flowing S + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing Sand (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage (0x02648, 0x02653,), # Aries ..Pisces - (0x0267f, 0x0267f,), # Wheelchair Symbol - (0x02693, 0x02693,), # Anchor - (0x026a1, 0x026a1,), # High Voltage Sign + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle (0x026bd, 0x026be,), # Soccer Ball ..Baseball (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud - (0x026ce, 0x026ce,), # Ophiuchus - (0x026d4, 0x026d4,), # No Entry - (0x026ea, 0x026ea,), # Church + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church (0x026f2, 0x026f3,), # Fountain ..Flag In Hole - (0x026f5, 0x026f5,), # Sailboat - (0x026fa, 0x026fa,), # Tent - (0x026fd, 0x026fd,), # Fuel Pump - (0x02705, 0x02705,), # White Heavy Check Mark + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand - (0x02728, 0x02728,), # Sparkles - (0x0274c, 0x0274c,), # Cross Mark - (0x0274e, 0x0274e,), # Negative Squared Cross M + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross Mark (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O - (0x02757, 0x02757,), # Heavy Exclamation Mark S + (0x02757, 0x02757,), # Heavy Exclamation Mark Symbol (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign - (0x027b0, 0x027b0,), # Curly Loop - (0x027bf, 0x027bf,), # Double Curly Loop + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square - (0x02b50, 0x02b50,), # White Medium Star - (0x02b55, 0x02b55,), # Heavy Large Circle + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute @@ -1184,19 +1184,19 @@ (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign (0x16fe0, 0x16fe4,), # Tangut Iteration Mark ..Khitan Small Script Fill (0x16ff0, 0x16ff1,), # Vietnamese Alternate Rea..Vietnamese Alternate Rea - (0x17000, 0x187f7,), # (nil) + (0x17000, 0x187f7,), # (nil) (0x18800, 0x18cd5,), # Tangut Component-001 ..Khitan Small Script Char - (0x18d00, 0x18d08,), # (nil) - (0x1aff0, 0x1aff3,), # (nil) - (0x1aff5, 0x1affb,), # (nil) - (0x1affd, 0x1affe,), # (nil) + (0x18d00, 0x18d08,), # (nil) + (0x1aff0, 0x1aff3,), # (nil) + (0x1aff5, 0x1affb,), # (nil) + (0x1affd, 0x1affe,), # (nil) (0x1b000, 0x1b122,), # Katakana Letter Archaic ..(nil) (0x1b150, 0x1b152,), # Hiragana Letter Small Wi..Hiragana Letter Small Wo (0x1b164, 0x1b167,), # Katakana Letter Small Wi..Katakana Letter Small N (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb - (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker - (0x1f18e, 0x1f18e,), # Negative Squared Ab + (0x1f18e, 0x1f18e,), # Negative Squared Ab (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo @@ -1210,26 +1210,26 @@ (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And (0x1f3e0, 0x1f3f0,), # House Building ..European Castle - (0x1f3f4, 0x1f3f4,), # Waving Black Flag + (0x1f3f4, 0x1f3f4,), # Waving Black Flag (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints - (0x1f440, 0x1f440,), # Eyes + (0x1f440, 0x1f440,), # Eyes (0x1f442, 0x1f4fc,), # Ear ..Videocassette (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty - (0x1f57a, 0x1f57a,), # Man Dancing + (0x1f57a, 0x1f57a,), # Man Dancing (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be - (0x1f5a4, 0x1f5a4,), # Black Heart + (0x1f5a4, 0x1f5a4,), # Black Heart (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage - (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley (0x1f6d5, 0x1f6d7,), # Hindu Temple ..Elevator - (0x1f6dd, 0x1f6df,), # (nil) + (0x1f6dd, 0x1f6df,), # (nil) (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving (0x1f6f4, 0x1f6fc,), # Scooter ..Roller Skate (0x1f7e0, 0x1f7eb,), # Large Orange Circle ..Large Brown Square - (0x1f7f0, 0x1f7f0,), # (nil) + (0x1f7f0, 0x1f7f0,), # (nil) (0x1f90c, 0x1f93a,), # Pinched Fingers ..Fencer (0x1f93c, 0x1f945,), # Wrestlers ..Goal Net (0x1f947, 0x1f9ff,), # First Place Medal ..Nazar Amulet @@ -1240,8 +1240,8 @@ (0x1fab0, 0x1faba,), # Fly ..(nil) (0x1fac0, 0x1fac5,), # Anatomical Heart ..(nil) (0x1fad0, 0x1fad9,), # Blueberries ..(nil) - (0x1fae0, 0x1fae7,), # (nil) - (0x1faf0, 0x1faf6,), # (nil) + (0x1fae0, 0x1fae7,), # (nil) + (0x1faf0, 0x1faf6,), # (nil) (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), diff --git a/wcwidth/table_zero.py b/wcwidth/table_zero.py index 4e3bcff..78845ba 100644 --- a/wcwidth/table_zero.py +++ b/wcwidth/table_zero.py @@ -1,132 +1,132 @@ """ Exports ZERO_WIDTH table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2022-03-20 21:12:52 UTC. +This code generated by wcwidth/bin/update-tables.py on 2022-03-20 21:29:31 UTC. """ ZERO_WIDTH = { '4.1.0': ( # Source: DerivedGeneralCategory-4.1.0.txt # Date: 2005-02-26, 02:35:50 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00486,), # Combining Cyrillic Titlo..Combining Cyrillic Psili (0x00591, 0x005b9,), # Hebrew Accent Etnahta ..Hebrew Point Holam (0x005bb, 0x005bd,), # Hebrew Point Qubuts ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x00615,), # Arabic Sign Sallallahou ..Arabic Small High Tah (0x0064b, 0x0065e,), # Arabic Fathatan ..Arabic Fatha With Two Do - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x00901, 0x00902,), # Devanagari Sign Candrabi..Devanagari Sign Anusvara - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00954,), # Devanagari Stress Sign U..Devanagari Acute Accent (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b43,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00d41, 0x00d43,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f90, 0x00f97,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu - (0x01032, 0x01032,), # Myanmar Vowel Sign Ai + (0x01032, 0x01032,), # Myanmar Vowel Sign Ai (0x01036, 0x01037,), # Myanmar Sign Anusvara ..Myanmar Sign Dot Below - (0x01039, 0x01039,), # Myanmar Sign Virama + (0x01039, 0x01039,), # Myanmar Sign Virama (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal - (0x0135f, 0x0135f,), # Ethiopic Combining Gemin + (0x0135f, 0x0135f,), # Ethiopic Combining Gemination Mark (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod (0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U (0x01dc0, 0x01dc3,), # Combining Dotted Grave A..Combining Suspension Mar (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020eb,), # Combining Reverse Solidu..Combining Long Double So (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe23,), # Combining Ligature Left ..Combining Double Tilde R (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining (0x1d185, 0x1d18b,), # Musical Symbol Combining..Musical Symbol Combining @@ -134,7 +134,7 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x006de, 0x006de,), # Arabic Start Of Rub El H + (0x006de, 0x006de,), # Arabic Start Of Rub El Hizb (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa ), @@ -142,133 +142,133 @@ # Source: DerivedGeneralCategory-5.0.0.txt # Date: 2006-02-27, 23:41:27 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00486,), # Combining Cyrillic Titlo..Combining Cyrillic Psili (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x00615,), # Arabic Sign Sallallahou ..Arabic Small High Tah (0x0064b, 0x0065e,), # Arabic Fathatan ..Arabic Fatha With Two Do - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot (0x00901, 0x00902,), # Devanagari Sign Candrabi..Devanagari Sign Anusvara - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00954,), # Devanagari Stress Sign U..Devanagari Acute Accent (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b43,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d41, 0x00d43,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f90, 0x00f97,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu - (0x01032, 0x01032,), # Myanmar Vowel Sign Ai + (0x01032, 0x01032,), # Myanmar Vowel Sign Ai (0x01036, 0x01037,), # Myanmar Sign Anusvara ..Myanmar Sign Dot Below - (0x01039, 0x01039,), # Myanmar Sign Virama + (0x01039, 0x01039,), # Myanmar Sign Virama (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal - (0x0135f, 0x0135f,), # Ethiopic Combining Gemin + (0x0135f, 0x0135f,), # Ethiopic Combining Gemination Mark (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod (0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01dc0, 0x01dca,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfe, 0x01dff,), # Combining Left Arrowhead..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020ef,), # Combining Reverse Solidu..Combining Right Arrow Be (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe23,), # Combining Ligature Left ..Combining Double Tilde R (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining (0x1d185, 0x1d18b,), # Musical Symbol Combining..Musical Symbol Combining @@ -276,7 +276,7 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x006de, 0x006de,), # Arabic Start Of Rub El H + (0x006de, 0x006de,), # Arabic Start Of Rub El Hizb (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa ), @@ -284,93 +284,93 @@ # Source: DerivedGeneralCategory-5.1.0.txt # Date: 2008-03-20, 17:54:57 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065e,), # Arabic Fathatan ..Arabic Fatha With Two Do - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot (0x00901, 0x00902,), # Devanagari Sign Candrabi..Devanagari Sign Anusvara - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00954,), # Devanagari Stress Sign U..Devanagari Acute Accent (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f90, 0x00f97,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -378,30 +378,30 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0135f, 0x0135f,), # Ethiopic Combining Gemin + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0135f, 0x0135f,), # Ethiopic Combining Gemination Mark (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod (0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan @@ -411,34 +411,34 @@ (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfe, 0x01dff,), # Combining Left Arrowhead..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a67c, 0x0a67d,), # Combining Cyrillic Kavyk..Combining Cyrillic Payer - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe26,), # Combining Ligature Left ..Combining Conjoining Mac - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining (0x1d185, 0x1d18b,), # Musical Symbol Combining..Musical Symbol Combining @@ -446,7 +446,7 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x006de, 0x006de,), # Arabic Start Of Rub El H + (0x006de, 0x006de,), # Arabic Start Of Rub El Hizb (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous @@ -455,22 +455,22 @@ # Source: DerivedGeneralCategory-5.2.0.txt # Date: 2009-08-22, 04:58:21 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065e,), # Arabic Fathatan ..Arabic Fatha With Two Do - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -479,73 +479,73 @@ (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U (0x00829, 0x0082d,), # Samaritan Vowel Sign Lon..Samaritan Mark Nequdaa (0x00900, 0x00902,), # Devanagari Sign Inverted..Devanagari Sign Anusvara - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00955,), # Devanagari Stress Sign U..Devanagari Vowel Sign Ca (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f90, 0x00f97,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -553,38 +553,38 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton - (0x0135f, 0x0135f,), # Ethiopic Combining Gemin + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai + (0x0135f, 0x0135f,), # Ethiopic Combining Gemination Mark (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod (0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan @@ -594,11 +594,11 @@ (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01ced, 0x01ced,), # Vedic Sign Tiryak (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfd, 0x01dff,), # Combining Almost Equal T..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette @@ -607,40 +607,40 @@ (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a67c, 0x0a67d,), # Combining Cyrillic Kavyk..Combining Cyrillic Payer (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepet (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe26,), # Combining Ligature Left ..Combining Conjoining Mac - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x11080, 0x11081,), # Kaithi Sign Candrabindu ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai (0x110b9, 0x110ba,), # Kaithi Sign Virama ..Kaithi Sign Nukta @@ -651,7 +651,7 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x006de, 0x006de,), # Arabic Start Of Rub El H + (0x006de, 0x006de,), # Arabic Start Of Rub El Hizb (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous @@ -660,22 +660,22 @@ # Source: DerivedGeneralCategory-6.0.0.txt # Date: 2010-08-19, 00:48:09 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -686,73 +686,73 @@ (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x00900, 0x00902,), # Devanagari Sign Inverted..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -760,100 +760,100 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod (0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan - (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01ced, 0x01ced,), # Vedic Sign Tiryak (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a67c, 0x0a67d,), # Combining Cyrillic Kavyk..Combining Cyrillic Payer (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepet (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe26,), # Combining Ligature Left ..Combining Conjoining Mac - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama - (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x11080, 0x11081,), # Kaithi Sign Candrabindu ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -873,22 +873,22 @@ # Source: DerivedGeneralCategory-6.1.0.txt # Date: 2011-11-27, 05:10:22 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -900,73 +900,73 @@ (0x008e4, 0x008fe,), # Arabic Curly Fatha ..Arabic Damma With Dot (0x00900, 0x00902,), # Devanagari Sign Inverted..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -974,10 +974,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -985,95 +985,95 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan - (0x01bab, 0x01bab,), # Sundanese Sign Virama - (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01bab, 0x01bab,), # Sundanese Sign Virama + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer - (0x0a69f, 0x0a69f,), # Combining Cyrillic Lette + (0x0a69f, 0x0a69f,), # Combining Cyrillic Letter Iotified E (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepet (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe26,), # Combining Ligature Left ..Combining Conjoining Mac - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama - (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x11080, 0x11081,), # Kaithi Sign Candrabindu ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -1083,10 +1083,10 @@ (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O - (0x116ab, 0x116ab,), # Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining @@ -1103,22 +1103,22 @@ # Source: DerivedGeneralCategory-6.2.0.txt # Date: 2012-05-20, 00:42:34 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -1130,73 +1130,73 @@ (0x008e4, 0x008fe,), # Arabic Curly Fatha ..Arabic Damma With Dot (0x00900, 0x00902,), # Devanagari Sign Inverted..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -1204,10 +1204,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -1215,95 +1215,95 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan - (0x01bab, 0x01bab,), # Sundanese Sign Virama - (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01bab, 0x01bab,), # Sundanese Sign Virama + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer - (0x0a69f, 0x0a69f,), # Combining Cyrillic Lette + (0x0a69f, 0x0a69f,), # Combining Cyrillic Letter Iotified E (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepet (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe26,), # Combining Ligature Left ..Combining Conjoining Mac - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama - (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x11080, 0x11081,), # Kaithi Sign Candrabindu ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -1313,10 +1313,10 @@ (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O - (0x116ab, 0x116ab,), # Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining @@ -1333,22 +1333,22 @@ # Source: DerivedGeneralCategory-6.3.0.txt # Date: 2013-07-05, 14:08:45 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -1360,73 +1360,73 @@ (0x008e4, 0x008fe,), # Arabic Curly Fatha ..Arabic Damma With Dot (0x00900, 0x00902,), # Devanagari Sign Inverted..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -1434,10 +1434,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -1445,96 +1445,96 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan - (0x01bab, 0x01bab,), # Sundanese Sign Virama - (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01bab, 0x01bab,), # Sundanese Sign Virama + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer - (0x0a69f, 0x0a69f,), # Combining Cyrillic Lette + (0x0a69f, 0x0a69f,), # Combining Cyrillic Letter Iotified E (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepet (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe26,), # Combining Ligature Left ..Combining Conjoining Mac - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama - (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x11080, 0x11081,), # Kaithi Sign Candrabindu ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -1544,10 +1544,10 @@ (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O - (0x116ab, 0x116ab,), # Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining @@ -1564,22 +1564,22 @@ # Source: DerivedGeneralCategory-7.0.0.txt # Date: 2014-02-07, 18:42:12 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -1590,76 +1590,76 @@ (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x008e4, 0x00902,), # Arabic Curly Fatha ..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Candrabindu Above (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali (0x00c81, 0x00c81,), # Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal - (0x00d01, 0x00d01,), # Malayalam Sign Candrabin + (0x00d01, 0x00d01,), # Malayalam Sign Candrabindu (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -1667,10 +1667,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -1678,103 +1678,103 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df5,), # Combining Dotted Grave A..Combining Up Tack Above (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer - (0x0a69f, 0x0a69f,), # Combining Cyrillic Lette + (0x0a69f, 0x0a69f,), # Combining Cyrillic Letter Iotified E (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepet + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing Tone-2 + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2d,), # Combining Ligature Left ..Combining Conjoining Mac - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke + (0x102e0, 0x102e0,), # Coptic Epact Thousands Mark (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation - (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -1782,33 +1782,33 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x112df, 0x112df,), # Khudawadi Sign Anusvara + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11301, 0x11301,), # Grantha Sign Candrabindu - (0x1133c, 0x1133c,), # Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii + (0x1133c, 0x1133c,), # Grantha Sign Nukta + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short E (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal (0x115bc, 0x115bd,), # Siddham Sign Candrabindu..Siddham Sign Anusvara (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below @@ -1821,7 +1821,7 @@ (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x01abe, 0x01abe,), # Combining Parentheses Overlay (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous @@ -1830,22 +1830,22 @@ # Source: DerivedGeneralCategory-8.0.0.txt # Date: 2015-02-13, 13:47:11 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -1856,76 +1856,76 @@ (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Candrabindu Above (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali (0x00c81, 0x00c81,), # Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal - (0x00d01, 0x00d01,), # Malayalam Sign Candrabin + (0x00d01, 0x00d01,), # Malayalam Sign Candrabindu (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -1933,10 +1933,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -1944,54 +1944,54 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df5,), # Combining Dotted Grave A..Combining Up Tack Above (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag @@ -1999,48 +1999,48 @@ (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama + (0x0a8c4, 0x0a8c4,), # Saurashtra Sign Virama (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepet + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing Tone-2 + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke + (0x102e0, 0x102e0,), # Coptic Epact Thousands Mark (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation - (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -2048,22 +2048,22 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111ca, 0x111cc,), # Sharada Sign Nukta ..Sharada Extra Short Vowe (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x112df, 0x112df,), # Khudawadi Sign Anusvara + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu - (0x1133c, 0x1133c,), # Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii + (0x1133c, 0x1133c,), # Grantha Sign Nukta + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short E (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -2071,12 +2071,12 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer @@ -2091,14 +2091,14 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body Tilting From Hip Joints + (0x1da84, 0x1da84,), # Signwriting Location Head Neck (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x01abe, 0x01abe,), # Combining Parentheses Overlay (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous @@ -2107,22 +2107,22 @@ # Source: DerivedGeneralCategory-9.0.0.txt # Date: 2016-06-01, 10:34:26 GMT # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -2134,76 +2134,76 @@ (0x008d4, 0x008e1,), # Arabic Small High Word A..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Candrabindu Above (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali (0x00c81, 0x00c81,), # Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal - (0x00d01, 0x00d01,), # Malayalam Sign Candrabin + (0x00d01, 0x00d01,), # Malayalam Sign Candrabindu (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -2211,10 +2211,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -2222,55 +2222,55 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df5,), # Combining Dotted Grave A..Combining Up Tack Above (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag @@ -2278,9 +2278,9 @@ (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig @@ -2289,37 +2289,37 @@ (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepet + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing Tone-2 + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke + (0x102e0, 0x102e0,), # Coptic Epact Thousands Mark (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation - (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -2327,26 +2327,26 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111ca, 0x111cc,), # Sharada Sign Nukta ..Sharada Extra Short Vowe (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x1123e, 0x1123e,), # Khojki Sign Sukun - (0x112df, 0x112df,), # Khudawadi Sign Anusvara + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu - (0x1133c, 0x1133c,), # Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii + (0x1133c, 0x1133c,), # Grantha Sign Nukta + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara - (0x11446, 0x11446,), # Newa Sign Nukta + (0x11446, 0x11446,), # Newa Sign Nukta (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short E (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -2354,18 +2354,18 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara - (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E @@ -2381,8 +2381,8 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body Tilting From Hip Joints + (0x1da84, 0x1da84,), # Signwriting Location Head Neck (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let @@ -2394,7 +2394,7 @@ (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x01abe, 0x01abe,), # Combining Parentheses Overlay (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous @@ -2403,22 +2403,22 @@ # Source: DerivedGeneralCategory-10.0.0.txt # Date: 2017-03-08, 08:41:49 GMT # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot @@ -2430,78 +2430,78 @@ (0x008d4, 0x008e1,), # Arabic Small High Word A..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Candrabindu Above (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali (0x00c81, 0x00c81,), # Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d00, 0x00d01,), # Malayalam Sign Combining..Malayalam Sign Candrabin (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -2509,10 +2509,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -2520,55 +2520,55 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag @@ -2576,9 +2576,9 @@ (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig @@ -2587,37 +2587,37 @@ (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepet + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing Tone-2 + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke + (0x102e0, 0x102e0,), # Coptic Epact Thousands Mark (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation - (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -2625,26 +2625,26 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111ca, 0x111cc,), # Sharada Sign Nukta ..Sharada Extra Short Vowe (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x1123e, 0x1123e,), # Khojki Sign Sukun - (0x112df, 0x112df,), # Khudawadi Sign Anusvara + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu - (0x1133c, 0x1133c,), # Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii + (0x1133c, 0x1133c,), # Grantha Sign Nukta + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara - (0x11446, 0x11446,), # Newa Sign Nukta + (0x11446, 0x11446,), # Newa Sign Nukta (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short E (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -2652,12 +2652,12 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer @@ -2665,23 +2665,23 @@ (0x11a09, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L (0x11a33, 0x11a38,), # Zanabazar Square Final C..Zanabazar Square Sign An (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster - (0x11a47, 0x11a47,), # Zanabazar Square Subjoin + (0x11a47, 0x11a47,), # Zanabazar Square Subjoiner (0x11a51, 0x11a56,), # Soyombo Vowel Sign I ..Soyombo Vowel Sign Oe (0x11a59, 0x11a5b,), # Soyombo Vowel Sign Vocal..Soyombo Vowel Length Mar (0x11a8a, 0x11a96,), # Soyombo Final Consonant ..Soyombo Sign Anusvara (0x11a98, 0x11a99,), # Soyombo Gemination Mark ..Soyombo Subjoiner (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara - (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E (0x11cb5, 0x11cb6,), # Marchen Sign Anusvara ..Marchen Sign Candrabindu (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign - (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign E (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama - (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below @@ -2693,8 +2693,8 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body Tilting From Hip Joints + (0x1da84, 0x1da84,), # Signwriting Location Head Neck (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let @@ -2706,7 +2706,7 @@ (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x01abe, 0x01abe,), # Combining Parentheses Overlay (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous @@ -2715,26 +2715,26 @@ # Source: DerivedGeneralCategory-11.0.0.txt # Date: 2018-02-21, 05:34:04 GMT # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot - (0x007fd, 0x007fd,), # Nko Dantayalan + (0x007fd, 0x007fd,), # Nko Dantayalan (0x00816, 0x00819,), # Samaritan Mark In ..Samaritan Mark Dagesh (0x0081b, 0x00823,), # Samaritan Mark Epentheti..Samaritan Vowel Sign A (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U @@ -2743,80 +2743,80 @@ (0x008d3, 0x008e1,), # Arabic Small Low Waw ..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal - (0x009fe, 0x009fe,), # Bengali Sandhi Mark + (0x009fe, 0x009fe,), # Bengali Sandhi Mark (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca - (0x00c04, 0x00c04,), # Telugu Sign Combining An + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Candrabindu Above + (0x00c04, 0x00c04,), # Telugu Sign Combining Anusvara Above (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali (0x00c81, 0x00c81,), # Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d00, 0x00d01,), # Malayalam Sign Combining..Malayalam Sign Candrabin (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00eb9,), # Lao Vowel Sign I ..Lao Vowel Sign Uu (0x00ebb, 0x00ebc,), # Lao Vowel Sign Mai Kon ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -2824,10 +2824,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -2835,55 +2835,55 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag @@ -2891,9 +2891,9 @@ (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig @@ -2903,39 +2903,39 @@ (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku - (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepe - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw + (0x0a9bc, 0x0a9bc,), # Javanese Vowel Sign Pepet + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing Tone-2 + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke + (0x102e0, 0x102e0,), # Coptic Epact Thousands Mark (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation (0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke - (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -2943,27 +2943,27 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111c9, 0x111cc,), # Sharada Sandhi Mark ..Sharada Extra Short Vowe (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x1123e, 0x1123e,), # Khojki Sign Sukun - (0x112df, 0x112df,), # Khudawadi Sign Anusvara + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu (0x1133b, 0x1133c,), # Combining Bindu Below ..Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara - (0x11446, 0x11446,), # Newa Sign Nukta - (0x1145e, 0x1145e,), # Newa Sandhi Mark + (0x11446, 0x11446,), # Newa Sign Nukta + (0x1145e, 0x1145e,), # Newa Sandhi Mark (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short E (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -2971,12 +2971,12 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer @@ -2985,26 +2985,26 @@ (0x11a01, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L (0x11a33, 0x11a38,), # Zanabazar Square Final C..Zanabazar Square Sign An (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster - (0x11a47, 0x11a47,), # Zanabazar Square Subjoin + (0x11a47, 0x11a47,), # Zanabazar Square Subjoiner (0x11a51, 0x11a56,), # Soyombo Vowel Sign I ..Soyombo Vowel Sign Oe (0x11a59, 0x11a5b,), # Soyombo Vowel Sign Vocal..Soyombo Vowel Length Mar (0x11a8a, 0x11a96,), # Soyombo Final Consonant ..Soyombo Sign Anusvara (0x11a98, 0x11a99,), # Soyombo Gemination Mark ..Soyombo Subjoiner (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara - (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E (0x11cb5, 0x11cb6,), # Marchen Sign Anusvara ..Marchen Sign Candrabindu (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign - (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign E (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama - (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara (0x11d90, 0x11d91,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign - (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusv - (0x11d97, 0x11d97,), # Gunjala Gondi Virama + (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusvara + (0x11d97, 0x11d97,), # Gunjala Gondi Virama (0x11ef3, 0x11ef4,), # Makasar Vowel Sign I ..Makasar Vowel Sign U (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta @@ -3017,8 +3017,8 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body Tilting From Hip Joints + (0x1da84, 0x1da84,), # Signwriting Location Head Neck (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let @@ -3030,7 +3030,7 @@ (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x01abe, 0x01abe,), # Combining Parentheses Overlay (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous @@ -3039,26 +3039,26 @@ # Source: DerivedGeneralCategory-12.0.0.txt # Date: 2019-01-22, 08:18:28 GMT # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot - (0x007fd, 0x007fd,), # Nko Dantayalan + (0x007fd, 0x007fd,), # Nko Dantayalan (0x00816, 0x00819,), # Samaritan Mark In ..Samaritan Mark Dagesh (0x0081b, 0x00823,), # Samaritan Mark Epentheti..Samaritan Vowel Sign A (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U @@ -3067,79 +3067,79 @@ (0x008d3, 0x008e1,), # Arabic Small Low Waw ..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal - (0x009fe, 0x009fe,), # Bengali Sandhi Mark + (0x009fe, 0x009fe,), # Bengali Sandhi Mark (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca - (0x00c04, 0x00c04,), # Telugu Sign Combining An + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Candrabindu Above + (0x00c04, 0x00c04,), # Telugu Sign Combining Anusvara Above (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali (0x00c81, 0x00c81,), # Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d00, 0x00d01,), # Malayalam Sign Combining..Malayalam Sign Candrabin (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00ebc,), # Lao Vowel Sign I ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -3147,10 +3147,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -3158,55 +3158,55 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag @@ -3214,9 +3214,9 @@ (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig @@ -3227,38 +3227,38 @@ (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku (0x0a9bc, 0x0a9bd,), # Javanese Vowel Sign Pepe..Javanese Consonant Sign - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing Tone-2 + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke + (0x102e0, 0x102e0,), # Coptic Epact Thousands Mark (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation (0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke - (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -3266,27 +3266,27 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111c9, 0x111cc,), # Sharada Sandhi Mark ..Sharada Extra Short Vowe (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x1123e, 0x1123e,), # Khojki Sign Sukun - (0x112df, 0x112df,), # Khudawadi Sign Anusvara + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu (0x1133b, 0x1133c,), # Combining Bindu Below ..Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara - (0x11446, 0x11446,), # Newa Sign Nukta - (0x1145e, 0x1145e,), # Newa Sandhi Mark + (0x11446, 0x11446,), # Newa Sign Nukta + (0x1145e, 0x1145e,), # Newa Sandhi Mark (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short E (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -3294,12 +3294,12 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer @@ -3307,34 +3307,34 @@ (0x11839, 0x1183a,), # Dogra Sign Virama ..Dogra Sign Nukta (0x119d4, 0x119d7,), # Nandinagari Vowel Sign U..Nandinagari Vowel Sign V (0x119da, 0x119db,), # Nandinagari Vowel Sign E..Nandinagari Vowel Sign A - (0x119e0, 0x119e0,), # Nandinagari Sign Virama + (0x119e0, 0x119e0,), # Nandinagari Sign Virama (0x11a01, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L (0x11a33, 0x11a38,), # Zanabazar Square Final C..Zanabazar Square Sign An (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster - (0x11a47, 0x11a47,), # Zanabazar Square Subjoin + (0x11a47, 0x11a47,), # Zanabazar Square Subjoiner (0x11a51, 0x11a56,), # Soyombo Vowel Sign I ..Soyombo Vowel Sign Oe (0x11a59, 0x11a5b,), # Soyombo Vowel Sign Vocal..Soyombo Vowel Length Mar (0x11a8a, 0x11a96,), # Soyombo Final Consonant ..Soyombo Sign Anusvara (0x11a98, 0x11a99,), # Soyombo Gemination Mark ..Soyombo Subjoiner (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara - (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E (0x11cb5, 0x11cb6,), # Marchen Sign Anusvara ..Marchen Sign Candrabindu (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign - (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign E (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama - (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara (0x11d90, 0x11d91,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign - (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusv - (0x11d97, 0x11d97,), # Gunjala Gondi Virama + (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusvara + (0x11d97, 0x11d97,), # Gunjala Gondi Virama (0x11ef3, 0x11ef4,), # Makasar Vowel Sign I ..Makasar Vowel Sign U (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta - (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modi + (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modifier Bar (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below (0x1bc9d, 0x1bc9e,), # Duployan Thick Letter Se..Duployan Double Mark (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining @@ -3344,8 +3344,8 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body Tilting From Hip Joints + (0x1da84, 0x1da84,), # Signwriting Location Head Neck (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let @@ -3359,7 +3359,7 @@ (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x01abe, 0x01abe,), # Combining Parentheses Overlay (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous @@ -3368,26 +3368,26 @@ # Source: DerivedGeneralCategory-12.1.0.txt # Date: 2019-03-10, 10:53:08 GMT # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot - (0x007fd, 0x007fd,), # Nko Dantayalan + (0x007fd, 0x007fd,), # Nko Dantayalan (0x00816, 0x00819,), # Samaritan Mark In ..Samaritan Mark Dagesh (0x0081b, 0x00823,), # Samaritan Mark Epentheti..Samaritan Vowel Sign A (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U @@ -3396,79 +3396,79 @@ (0x008d3, 0x008e1,), # Arabic Small Low Waw ..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal - (0x009fe, 0x009fe,), # Bengali Sandhi Mark + (0x009fe, 0x009fe,), # Bengali Sandhi Mark (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama - (0x00b56, 0x00b56,), # Oriya Ai Length Mark + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b56, 0x00b56,), # Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca - (0x00c04, 0x00c04,), # Telugu Sign Combining An + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Candrabindu Above + (0x00c04, 0x00c04,), # Telugu Sign Combining Anusvara Above (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali (0x00c81, 0x00c81,), # Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d00, 0x00d01,), # Malayalam Sign Combining..Malayalam Sign Candrabin (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00ebc,), # Lao Vowel Sign I ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -3476,10 +3476,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -3487,55 +3487,55 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag @@ -3543,9 +3543,9 @@ (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig @@ -3556,38 +3556,38 @@ (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku (0x0a9bc, 0x0a9bd,), # Javanese Vowel Sign Pepe..Javanese Consonant Sign - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing Tone-2 + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke + (0x102e0, 0x102e0,), # Coptic Epact Thousands Mark (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation (0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke - (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -3595,27 +3595,27 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111c9, 0x111cc,), # Sharada Sandhi Mark ..Sharada Extra Short Vowe (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x1123e, 0x1123e,), # Khojki Sign Sukun - (0x112df, 0x112df,), # Khudawadi Sign Anusvara + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu (0x1133b, 0x1133c,), # Combining Bindu Below ..Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara - (0x11446, 0x11446,), # Newa Sign Nukta - (0x1145e, 0x1145e,), # Newa Sandhi Mark + (0x11446, 0x11446,), # Newa Sign Nukta + (0x1145e, 0x1145e,), # Newa Sandhi Mark (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short E (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -3623,12 +3623,12 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer @@ -3636,34 +3636,34 @@ (0x11839, 0x1183a,), # Dogra Sign Virama ..Dogra Sign Nukta (0x119d4, 0x119d7,), # Nandinagari Vowel Sign U..Nandinagari Vowel Sign V (0x119da, 0x119db,), # Nandinagari Vowel Sign E..Nandinagari Vowel Sign A - (0x119e0, 0x119e0,), # Nandinagari Sign Virama + (0x119e0, 0x119e0,), # Nandinagari Sign Virama (0x11a01, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L (0x11a33, 0x11a38,), # Zanabazar Square Final C..Zanabazar Square Sign An (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster - (0x11a47, 0x11a47,), # Zanabazar Square Subjoin + (0x11a47, 0x11a47,), # Zanabazar Square Subjoiner (0x11a51, 0x11a56,), # Soyombo Vowel Sign I ..Soyombo Vowel Sign Oe (0x11a59, 0x11a5b,), # Soyombo Vowel Sign Vocal..Soyombo Vowel Length Mar (0x11a8a, 0x11a96,), # Soyombo Final Consonant ..Soyombo Sign Anusvara (0x11a98, 0x11a99,), # Soyombo Gemination Mark ..Soyombo Subjoiner (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara - (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E (0x11cb5, 0x11cb6,), # Marchen Sign Anusvara ..Marchen Sign Candrabindu (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign - (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign E (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama - (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara (0x11d90, 0x11d91,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign - (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusv - (0x11d97, 0x11d97,), # Gunjala Gondi Virama + (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusvara + (0x11d97, 0x11d97,), # Gunjala Gondi Virama (0x11ef3, 0x11ef4,), # Makasar Vowel Sign I ..Makasar Vowel Sign U (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta - (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modi + (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modifier Bar (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below (0x1bc9d, 0x1bc9e,), # Duployan Thick Letter Se..Duployan Double Mark (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining @@ -3673,8 +3673,8 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body Tilting From Hip Joints + (0x1da84, 0x1da84,), # Signwriting Location Head Neck (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let @@ -3688,7 +3688,7 @@ (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x01abe, 0x01abe,), # Combining Parentheses Overlay (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous @@ -3697,26 +3697,26 @@ # Source: DerivedGeneralCategory-13.0.0.txt # Date: 2019-10-21, 14:30:32 GMT # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot - (0x007fd, 0x007fd,), # Nko Dantayalan + (0x007fd, 0x007fd,), # Nko Dantayalan (0x00816, 0x00819,), # Samaritan Mark In ..Samaritan Mark Dagesh (0x0081b, 0x00823,), # Samaritan Mark Epentheti..Samaritan Vowel Sign A (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U @@ -3725,80 +3725,80 @@ (0x008d3, 0x008e1,), # Arabic Small Low Waw ..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal - (0x009fe, 0x009fe,), # Bengali Sandhi Mark + (0x009fe, 0x009fe,), # Bengali Sandhi Mark (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b4d, 0x00b4d,), # Oriya Sign Virama (0x00b55, 0x00b56,), # Oriya Sign Overline ..Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca - (0x00c04, 0x00c04,), # Telugu Sign Combining An + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Candrabindu Above + (0x00c04, 0x00c04,), # Telugu Sign Combining Anusvara Above (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali (0x00c81, 0x00c81,), # Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d00, 0x00d01,), # Malayalam Sign Combining..Malayalam Sign Candrabin (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc (0x00d81, 0x00d81,), # Sinhala Sign Candrabindu - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00ebc,), # Lao Vowel Sign I ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -3806,10 +3806,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01734,), # Hanunoo Vowel Sign I ..Hanunoo Sign Pamudpod @@ -3817,56 +3817,56 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01abf, 0x01ac0,), # Combining Latin Small Le..Combining Latin Small Le (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag @@ -3874,11 +3874,11 @@ (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a82c, 0x0a82c,), # Syloti Nagri Sign Altern + (0x0a82c, 0x0a82c,), # Syloti Nagri Sign Alternate Hasanta (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay @@ -3888,39 +3888,39 @@ (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku (0x0a9bc, 0x0a9bd,), # Javanese Vowel Sign Pepe..Javanese Consonant Sign - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing Tone-2 + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke + (0x102e0, 0x102e0,), # Coptic Epact Thousands Mark (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation (0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas (0x10eab, 0x10eac,), # Yezidi Combining Hamza M..Yezidi Combining Madda M (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke - (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai @@ -3928,28 +3928,28 @@ (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111c9, 0x111cc,), # Sharada Sandhi Mark ..Sharada Extra Short Vowe - (0x111cf, 0x111cf,), # Sharada Sign Inverted Ca + (0x111cf, 0x111cf,), # Sharada Sign Inverted Candrabindu (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x1123e, 0x1123e,), # Khojki Sign Sukun - (0x112df, 0x112df,), # Khudawadi Sign Anusvara + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu (0x1133b, 0x1133c,), # Combining Bindu Below ..Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara - (0x11446, 0x11446,), # Newa Sign Nukta - (0x1145e, 0x1145e,), # Newa Sandhi Mark + (0x11446, 0x11446,), # Newa Sign Nukta + (0x1145e, 0x1145e,), # Newa Sandhi Mark (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short E (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -3957,52 +3957,52 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer (0x1182f, 0x11837,), # Dogra Vowel Sign U ..Dogra Sign Anusvara (0x11839, 0x1183a,), # Dogra Sign Virama ..Dogra Sign Nukta (0x1193b, 0x1193c,), # Dives Akuru Sign Anusvar..Dives Akuru Sign Candrab - (0x1193e, 0x1193e,), # Dives Akuru Virama - (0x11943, 0x11943,), # Dives Akuru Sign Nukta + (0x1193e, 0x1193e,), # Dives Akuru Virama + (0x11943, 0x11943,), # Dives Akuru Sign Nukta (0x119d4, 0x119d7,), # Nandinagari Vowel Sign U..Nandinagari Vowel Sign V (0x119da, 0x119db,), # Nandinagari Vowel Sign E..Nandinagari Vowel Sign A - (0x119e0, 0x119e0,), # Nandinagari Sign Virama + (0x119e0, 0x119e0,), # Nandinagari Sign Virama (0x11a01, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L (0x11a33, 0x11a38,), # Zanabazar Square Final C..Zanabazar Square Sign An (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster - (0x11a47, 0x11a47,), # Zanabazar Square Subjoin + (0x11a47, 0x11a47,), # Zanabazar Square Subjoiner (0x11a51, 0x11a56,), # Soyombo Vowel Sign I ..Soyombo Vowel Sign Oe (0x11a59, 0x11a5b,), # Soyombo Vowel Sign Vocal..Soyombo Vowel Length Mar (0x11a8a, 0x11a96,), # Soyombo Final Consonant ..Soyombo Sign Anusvara (0x11a98, 0x11a99,), # Soyombo Gemination Mark ..Soyombo Subjoiner (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara - (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E (0x11cb5, 0x11cb6,), # Marchen Sign Anusvara ..Marchen Sign Candrabindu (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign - (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign E (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama - (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara (0x11d90, 0x11d91,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign - (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusv - (0x11d97, 0x11d97,), # Gunjala Gondi Virama + (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusvara + (0x11d97, 0x11d97,), # Gunjala Gondi Virama (0x11ef3, 0x11ef4,), # Makasar Vowel Sign I ..Makasar Vowel Sign U (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta - (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modi + (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modifier Bar (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below - (0x16fe4, 0x16fe4,), # Khitan Small Script Fill + (0x16fe4, 0x16fe4,), # Khitan Small Script Filler (0x1bc9d, 0x1bc9e,), # Duployan Thick Letter Se..Duployan Double Mark (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining @@ -4011,8 +4011,8 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body Tilting From Hip Joints + (0x1da84, 0x1da84,), # Signwriting Location Head Neck (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let @@ -4026,7 +4026,7 @@ (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x01abe, 0x01abe,), # Combining Parentheses Overlay (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous @@ -4035,110 +4035,110 @@ # Source: DerivedGeneralCategory-14.0.0.txt # Date: 2021-07-10, 00:35:08 GMT # - (0x00300, 0x00300,), # Combining Grave Accent + (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg - (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot - (0x005c7, 0x005c7,), # Hebrew Point Qamats Qata + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below - (0x00670, 0x00670,), # Arabic Letter Superscrip + (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem - (0x00711, 0x00711,), # Syriac Letter Superscrip + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot - (0x007fd, 0x007fd,), # Nko Dantayalan + (0x007fd, 0x007fd,), # Nko Dantayalan (0x00816, 0x00819,), # Samaritan Mark In ..Samaritan Mark Dagesh (0x0081b, 0x00823,), # Samaritan Mark Epentheti..Samaritan Vowel Sign A (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U (0x00829, 0x0082d,), # Samaritan Vowel Sign Lon..Samaritan Mark Nequdaa (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark - (0x00898, 0x0089f,), # (nil) + (0x00898, 0x0089f,), # (nil) (0x008ca, 0x008e1,), # (nil) ..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe - (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x0093c, 0x0093c,), # Devanagari Sign Nukta (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai - (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x0094d, 0x0094d,), # Devanagari Sign Virama (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo (0x00981, 0x00981,), # Bengali Sign Candrabindu - (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009bc, 0x009bc,), # Bengali Sign Nukta (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal - (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009cd, 0x009cd,), # Bengali Sign Virama (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal - (0x009fe, 0x009fe,), # Bengali Sandhi Mark + (0x009fe, 0x009fe,), # Bengali Sandhi Mark (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi - (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama - (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak - (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara - (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00abc, 0x00abc,), # Gujarati Sign Nukta (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai - (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00acd, 0x00acd,), # Gujarati Sign Virama (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle - (0x00b01, 0x00b01,), # Oriya Sign Candrabindu - (0x00b3c, 0x00b3c,), # Oriya Sign Nukta - (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic - (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b4d, 0x00b4d,), # Oriya Sign Virama (0x00b55, 0x00b56,), # Oriya Sign Overline ..Oriya Ai Length Mark (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic - (0x00b82, 0x00b82,), # Tamil Sign Anusvara - (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii - (0x00bcd, 0x00bcd,), # Tamil Sign Virama - (0x00c00, 0x00c00,), # Telugu Sign Combining Ca - (0x00c04, 0x00c04,), # Telugu Sign Combining An - (0x00c3c, 0x00c3c,), # (nil) + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Candrabindu Above + (0x00c04, 0x00c04,), # Telugu Sign Combining Anusvara Above + (0x00c3c, 0x00c3c,), # (nil) (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali (0x00c81, 0x00c81,), # Kannada Sign Candrabindu - (0x00cbc, 0x00cbc,), # Kannada Sign Nukta - (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I - (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal (0x00d00, 0x00d01,), # Malayalam Sign Combining..Malayalam Sign Candrabin (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc - (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc (0x00d81, 0x00d81,), # Sinhala Sign Candrabindu - (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti - (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga - (0x00e31, 0x00e31,), # Thai Character Mai Han-a + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan - (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan (0x00eb4, 0x00ebc,), # Lao Vowel Sign I ..Lao Semivowel Sign Lo (0x00ec8, 0x00ecd,), # Lao Tone Mai Ek ..Lao Niggahita (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig - (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung - (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung - (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter - (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gda + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat @@ -4146,10 +4146,10 @@ (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah - (0x01082, 0x01082,), # Myanmar Consonant Sign S + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan - (0x0108d, 0x0108d,), # Myanmar Sign Shan Counci - (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama (0x01732, 0x01733,), # Hanunoo Vowel Sign I ..Hanunoo Vowel Sign U @@ -4157,56 +4157,56 @@ (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua - (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c6, 0x017c6,), # Khmer Sign Nikahit (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat - (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x0180f, 0x0180f,), # (nil) + (0x0180f, 0x0180f,), # (nil) (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal - (0x018a9, 0x018a9,), # Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O - (0x01932, 0x01932,), # Limbu Small Letter Anusv + (0x01932, 0x01932,), # Limbu Small Letter Anusvara (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U - (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae - (0x01a56, 0x01a56,), # Tai Tham Consonant Sign + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign - (0x01a60, 0x01a60,), # Tai Tham Sign Sakot - (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue - (0x01a7f, 0x01a7f,), # Tai Tham Combining Crypt + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be (0x01abf, 0x01ace,), # Combining Latin Small Le..(nil) (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang - (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R - (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La L - (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepe + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign - (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01be6, 0x01be6,), # Batak Sign Tompi (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee - (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda - (0x01ced, 0x01ced,), # Vedic Sign Tiryak - (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01dff,), # Combining Dotted Grave A..Combining Right Arrowhea (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arr + (0x020e1, 0x020e1,), # Combining Left Right Arrow Above (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu - (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joine + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag @@ -4214,11 +4214,11 @@ (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk - (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisva - (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasant - (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusva + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign - (0x0a82c, 0x0a82c,), # Syloti Nagri Sign Altern + (0x0a82c, 0x0a82c,), # Syloti Nagri Sign Alternate Hasanta (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig (0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay @@ -4228,72 +4228,72 @@ (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku (0x0a9bc, 0x0a9bd,), # Javanese Vowel Sign Pepe..Javanese Consonant Sign - (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa - (0x0aa43, 0x0aa43,), # Cham Consonant Sign Fina - (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Fina - (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing T - (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing Tone-2 + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek - (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign - (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama - (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign - (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign - (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek - (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spani + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo - (0x101fd, 0x101fd,), # Phaistos Disc Sign Combi - (0x102e0, 0x102e0,), # Coptic Epact Thousands M + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke + (0x102e0, 0x102e0,), # Coptic Epact Thousands Mark (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo - (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10a3f, 0x10a3f,), # Kharoshthi Virama (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation (0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas (0x10eab, 0x10eac,), # Yezidi Combining Hamza M..Yezidi Combining Madda M (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke - (0x10f82, 0x10f85,), # (nil) - (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x10f82, 0x10f85,), # (nil) + (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama - (0x11070, 0x11070,), # (nil) - (0x11073, 0x11074,), # (nil) + (0x11070, 0x11070,), # (nil) + (0x11073, 0x11074,), # (nil) (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai (0x110b9, 0x110ba,), # Kaithi Sign Virama ..Kaithi Sign Nukta - (0x110c2, 0x110c2,), # (nil) + (0x110c2, 0x110c2,), # (nil) (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa - (0x11173, 0x11173,), # Mahajani Sign Nukta + (0x11173, 0x11173,), # Mahajani Sign Nukta (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O (0x111c9, 0x111cc,), # Sharada Sandhi Mark ..Sharada Extra Short Vowe - (0x111cf, 0x111cf,), # Sharada Sign Inverted Ca + (0x111cf, 0x111cf,), # Sharada Sign Inverted Candrabindu (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai - (0x11234, 0x11234,), # Khojki Sign Anusvara + (0x11234, 0x11234,), # Khojki Sign Anusvara (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda - (0x1123e, 0x1123e,), # Khojki Sign Sukun - (0x112df, 0x112df,), # Khudawadi Sign Anusvara + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x112df, 0x112df,), # Khudawadi Sign Anusvara (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu (0x1133b, 0x1133c,), # Combining Bindu Below ..Grantha Sign Nukta - (0x11340, 0x11340,), # Grantha Vowel Sign Ii + (0x11340, 0x11340,), # Grantha Vowel Sign Ii (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara - (0x11446, 0x11446,), # Newa Sign Nukta - (0x1145e, 0x1145e,), # Newa Sandhi Mark + (0x11446, 0x11446,), # Newa Sign Nukta + (0x1145e, 0x1145e,), # Newa Sandhi Mark (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal - (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short E (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal @@ -4301,55 +4301,55 @@ (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai - (0x1163d, 0x1163d,), # Modi Sign Anusvara + (0x1163d, 0x1163d,), # Modi Sign Anusvara (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra - (0x116ab, 0x116ab,), # Takri Sign Anusvara - (0x116ad, 0x116ad,), # Takri Vowel Sign Aa + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au - (0x116b7, 0x116b7,), # Takri Sign Nukta + (0x116b7, 0x116b7,), # Takri Sign Nukta (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer (0x1182f, 0x11837,), # Dogra Vowel Sign U ..Dogra Sign Anusvara (0x11839, 0x1183a,), # Dogra Sign Virama ..Dogra Sign Nukta (0x1193b, 0x1193c,), # Dives Akuru Sign Anusvar..Dives Akuru Sign Candrab - (0x1193e, 0x1193e,), # Dives Akuru Virama - (0x11943, 0x11943,), # Dives Akuru Sign Nukta + (0x1193e, 0x1193e,), # Dives Akuru Virama + (0x11943, 0x11943,), # Dives Akuru Sign Nukta (0x119d4, 0x119d7,), # Nandinagari Vowel Sign U..Nandinagari Vowel Sign V (0x119da, 0x119db,), # Nandinagari Vowel Sign E..Nandinagari Vowel Sign A - (0x119e0, 0x119e0,), # Nandinagari Sign Virama + (0x119e0, 0x119e0,), # Nandinagari Sign Virama (0x11a01, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L (0x11a33, 0x11a38,), # Zanabazar Square Final C..Zanabazar Square Sign An (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster - (0x11a47, 0x11a47,), # Zanabazar Square Subjoin + (0x11a47, 0x11a47,), # Zanabazar Square Subjoiner (0x11a51, 0x11a56,), # Soyombo Vowel Sign I ..Soyombo Vowel Sign Oe (0x11a59, 0x11a5b,), # Soyombo Vowel Sign Vocal..Soyombo Vowel Length Mar (0x11a8a, 0x11a96,), # Soyombo Final Consonant ..Soyombo Sign Anusvara (0x11a98, 0x11a99,), # Soyombo Gemination Mark ..Soyombo Subjoiner (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara - (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E (0x11cb5, 0x11cb6,), # Marchen Sign Anusvara ..Marchen Sign Candrabindu (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign - (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign E (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama - (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara (0x11d90, 0x11d91,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign - (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusv - (0x11d97, 0x11d97,), # Gunjala Gondi Virama + (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusvara + (0x11d97, 0x11d97,), # Gunjala Gondi Virama (0x11ef3, 0x11ef4,), # Makasar Vowel Sign I ..Makasar Vowel Sign U (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta - (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modi + (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modifier Bar (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below - (0x16fe4, 0x16fe4,), # Khitan Small Script Fill + (0x16fe4, 0x16fe4,), # Khitan Small Script Filler (0x1bc9d, 0x1bc9e,), # Duployan Thick Letter Se..Duployan Double Mark - (0x1cf00, 0x1cf2d,), # (nil) - (0x1cf30, 0x1cf46,), # (nil) + (0x1cf00, 0x1cf2d,), # (nil) + (0x1cf30, 0x1cf46,), # (nil) (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining (0x1d185, 0x1d18b,), # Musical Symbol Combining..Musical Symbol Combining @@ -4357,8 +4357,8 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement - (0x1da75, 0x1da75,), # Signwriting Upper Body T - (0x1da84, 0x1da84,), # Signwriting Location Hea + (0x1da75, 0x1da75,), # Signwriting Upper Body Tilting From Hip Joints + (0x1da84, 0x1da84,), # Signwriting Location Head Neck (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let @@ -4367,13 +4367,13 @@ (0x1e023, 0x1e024,), # Combining Glagolitic Let..Combining Glagolitic Let (0x1e026, 0x1e02a,), # Combining Glagolitic Let..Combining Glagolitic Let (0x1e130, 0x1e136,), # Nyiakeng Puachue Hmong T..Nyiakeng Puachue Hmong T - (0x1e2ae, 0x1e2ae,), # (nil) + (0x1e2ae, 0x1e2ae,), # (nil) (0x1e2ec, 0x1e2ef,), # Wancho Tone Tup ..Wancho Tone Koini (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Ov + (0x01abe, 0x01abe,), # Combining Parentheses Overlay (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous diff --git a/wcwidth/unicode_versions.py b/wcwidth/unicode_versions.py index ba45fb7..307a0b2 100644 --- a/wcwidth/unicode_versions.py +++ b/wcwidth/unicode_versions.py @@ -1,9 +1,10 @@ """ Exports function list_versions() for unicode version level support. -This code generated by wcwidth/bin/update-tables.py on 2022-03-20 21:12:52 UTC. +This code generated by wcwidth/bin/update-tables.py on 2022-03-20 21:29:31 UTC. """ + def list_versions(): """ Return Unicode version levels supported by this module release. From b5739e4de5482d613a002215ae69282ac3c8b6a2 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:32:32 -0400 Subject: [PATCH 12/57] small linting --- bin/new-wide-by-version.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/bin/new-wide-by-version.py b/bin/new-wide-by-version.py index dedf2cd..18588c0 100755 --- a/bin/new-wide-by-version.py +++ b/bin/new-wide-by-version.py @@ -18,11 +18,11 @@ import sys import json +# local +from wcwidth import WIDE_EASTASIAN, _bisearch -# List new WIDE characters at each unicode version. -# def main(): - from wcwidth import WIDE_EASTASIAN, _bisearch + """List new WIDE characters at each unicode version.""" versions = list(WIDE_EASTASIAN.keys()) results = {} for version in versions: From 47b1969707614ad4d471fc56d872229f4b8709a7 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:32:41 -0400 Subject: [PATCH 13/57] use https, remove extra whitespace --- bin/update-tables.py | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 2038fa4..371e83c 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -35,9 +35,9 @@ import tenacity import dateutil.parser -URL_UNICODE_DERIVED_AGE = 'http://www.unicode.org/Public/UCD/latest/ucd/DerivedAge.txt' -URL_EASTASIAN_WIDTH = 'http://www.unicode.org/Public/{version}/ucd/EastAsianWidth.txt' -URL_DERIVED_CATEGORY = 'http://www.unicode.org/Public/{version}/ucd/extracted/DerivedGeneralCategory.txt' +URL_UNICODE_DERIVED_AGE = 'https://www.unicode.org/Public/UCD/latest/ucd/DerivedAge.txt' +URL_EASTASIAN_WIDTH = 'https://www.unicode.org/Public/{version}/ucd/EastAsianWidth.txt' +URL_DERIVED_CATEGORY = 'https://www.unicode.org/Public/{version}/ucd/extracted/DerivedGeneralCategory.txt' EXCLUDE_VERSIONS = ['2.0.0', '2.1.2', '3.0.0', '3.1.0', '3.2.0', '4.0.0'] PATH_UP = os.path.relpath(os.path.join(os.path.dirname(__file__), os.path.pardir)) PATH_DATA = os.path.join(PATH_UP, 'data') @@ -173,9 +173,10 @@ def convert_values_to_string_table(values): name_end = string.capwords(unicodedata.name(ucs_end)) except ValueError: pass - txt_description = f'{name_start[:24].rstrip():24s}' if name_start != name_end: - txt_description += f'..{name_end[:24].rstrip()}' + txt_description = f'{name_start[:24].rstrip():24s}..{name_end[:24].rstrip()}' + else: + txt_description = f'{name_start[:48]}' pytable_values.append((hex_start, hex_end, txt_description)) return pytable_values From 3799a0be3e71e6f4fcb35d15daebcc6b5dfea718 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:33:04 -0400 Subject: [PATCH 14/57] isort did this --- docs/conf.py | 1 - 1 file changed, 1 deletion(-) diff --git a/docs/conf.py b/docs/conf.py index 37bd9a2..8cfef55 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -22,7 +22,6 @@ sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), os.path.pardir))) # local -# 3rd-party imports import wcwidth # -- General configuration ------------------------------------------------ From df0d5a9ba847b90a4cf8377ba175eba977c6e9f2 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:33:20 -0400 Subject: [PATCH 15/57] small tox and linting updates --- .pylintrc | 4 +++- tox.ini | 21 +++++++++------------ 2 files changed, 12 insertions(+), 13 deletions(-) diff --git a/.pylintrc b/.pylintrc index 074ebb1..48a3a31 100644 --- a/.pylintrc +++ b/.pylintrc @@ -23,7 +23,9 @@ disable= too-many-lines, inconsistent-return-statements, too-many-return-statements, - too-many-boolean-expressions + too-many-boolean-expressions, + redundant-u-string-prefix, + consider-using-f-string, [FORMAT] max-line-length: 100 diff --git a/tox.ini b/tox.ini index 8adbe1b..117b993 100644 --- a/tox.ini +++ b/tox.ini @@ -1,9 +1,9 @@ [tox] -envlist = update, compile, autopep8, docformatter, isort, pylint, flake8, flake8_tests, pydocstyle, docs, py26, py27, py34, py35, py36 +envlist = update, compile, autopep8, docformatter, isort, pylint, flake8, pydocstyle, docs, py26, py27, py34, py35, py36 skip_missing_interpreters = true [testenv] -deps = requirements-tests.txt +deps = -r requirements-tests.txt commands = {envpython} -m pytest --cov-config={toxinidir}/tox.ini {posargs:\ --strict --verbose \ --junit-xml=.tox/results.{envname}.xml \ @@ -40,8 +40,9 @@ filterwarnings = junit_family = xunit1 [flake8] -max-line-length = 100 exclude = .tox,build +max-line-length = 100 +ignore = E402,E501,F401,W503,W504 [coverage:run] branch = True @@ -58,7 +59,7 @@ source = wcwidth/ [testenv:compile] basepython = python3.10 -commands = python -m compileall {toxinidir}/wcwidth +commands = python -m compileall {toxinidir}/wcwidth {toxinidir}/bin {toxinidir}/tests {toxinidir}/docs [testenv:update_requirements] basepython = python3.10 @@ -99,7 +100,7 @@ commands = [testenv:isort] basepython = python3.10 -commands = {envbindir}/isort --quiet --apply --recursive +commands = {envbindir}/isort --quiet --apply --recursive wcwidth tests bin [testenv:pylint] basepython = python3.10 @@ -109,17 +110,13 @@ commands = {envbindir}/pylint --rcfile={toxinidir}/.pylintrc \ [testenv:flake8] basepython = python3.10 -commands = {envbindir}/flake8 --ignore=F401,W503,W504 --exclude=tests setup.py docs/ wcwidth/ bin/ - -[testenv:flake8_tests] -basepython = python3.10 -commands = {envbindir}/flake8 --ignore=W503,W504,F811,F401 tests/ bin/ +commands = {envbindir}/flake8 --exclude=tests setup.py docs/ wcwidth/ bin/ tests/ [testenv:pydocstyle] basepython = python3.10 -commands = {envbindir}/pydocstyle --source --explain {toxinidir}/blessed +commands = {envbindir}/pydocstyle --source --explain {toxinidir}/wcwidth {envbindir}/rst-lint README.rst - {envbindir}/doc8 --ignore-path docs/_build --ignore D000 docs + {envbindir}/doc8 --ignore-path docs/_build --ignore-path docs/requirements.txt --ignore D000 docs [testenv:docs] basepython = python3.10 From 329ee1632c18c5242a764ef61880fe1a6138a142 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:33:32 -0400 Subject: [PATCH 16/57] use result of pip-compile --- docs/requirements.txt | 60 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 58 insertions(+), 2 deletions(-) diff --git a/docs/requirements.txt b/docs/requirements.txt index ab3f3dd..5790316 100644 --- a/docs/requirements.txt +++ b/docs/requirements.txt @@ -1,2 +1,58 @@ -Sphinx -sphinx_rtd_theme +# +# This file is autogenerated by pip-compile with python 3.10 +# To update, run: +# +# pip-compile --no-emit-index-url --output-file=docs/requirements.txt requirements-docs.in +# +alabaster==0.7.12 + # via sphinx +babel==2.9.1 + # via sphinx +certifi==2021.10.8 + # via requests +charset-normalizer==2.0.12 + # via requests +docutils==0.17.1 + # via + # sphinx + # sphinx-rtd-theme +idna==3.3 + # via requests +imagesize==1.3.0 + # via sphinx +jinja2==3.0.3 + # via sphinx +markupsafe==2.1.1 + # via jinja2 +packaging==21.3 + # via sphinx +pygments==2.11.2 + # via sphinx +pyparsing==3.0.7 + # via packaging +pytz==2022.1 + # via babel +requests==2.27.1 + # via sphinx +snowballstemmer==2.2.0 + # via sphinx +sphinx==4.4.0 + # via + # -r requirements-docs.in + # sphinx-rtd-theme +sphinx-rtd-theme==1.0.0 + # via -r requirements-docs.in +sphinxcontrib-applehelp==1.0.2 + # via sphinx +sphinxcontrib-devhelp==1.0.2 + # via sphinx +sphinxcontrib-htmlhelp==2.0.0 + # via sphinx +sphinxcontrib-jsmath==1.0.1 + # via sphinx +sphinxcontrib-qthelp==1.0.3 + # via sphinx +sphinxcontrib-serializinghtml==1.1.5 + # via sphinx +urllib3==1.26.9 + # via requests From 72f780eb2dfa183023b5cd48650f7926f3c0e043 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:43:18 -0400 Subject: [PATCH 17/57] use older dependencies to support python3.6 --- requirements-tests.in | 5 +++-- requirements-tests.txt | 36 ++++++++++++++++++++++++------------ 2 files changed, 27 insertions(+), 14 deletions(-) diff --git a/requirements-tests.in b/requirements-tests.in index f90c294..0bbf968 100644 --- a/requirements-tests.in +++ b/requirements-tests.in @@ -1,10 +1,11 @@ -pytest +pytest<7 pytest-cov +coverage[toml]<6 flake8 autopep8 docformatter isort -pylint +pylint<2.10 pydocstyle restructuredtext_lint doc8 diff --git a/requirements-tests.txt b/requirements-tests.txt index 121a046..ea3a1ca 100644 --- a/requirements-tests.txt +++ b/requirements-tests.txt @@ -1,17 +1,19 @@ # -# This file is autogenerated by pip-compile with python 3.10 +# This file is autogenerated by pip-compile with python 3.6 # To update, run: # # pip-compile --no-emit-index-url --output-file=requirements-tests.txt requirements-tests.in # -astroid==2.9.3 +astroid==2.6.6 # via pylint attrs==21.4.0 # via pytest autopep8==1.6.0 # via -r requirements-tests.in -coverage[toml]==6.3.2 - # via pytest-cov +coverage[toml]==5.5 + # via + # -r requirements-tests.in + # pytest-cov doc8==0.10.1 # via -r requirements-tests.in docformatter==1.4 @@ -22,6 +24,12 @@ docutils==0.18.1 # restructuredtext-lint flake8==4.0.1 # via -r requirements-tests.in +importlib-metadata==4.2.0 + # via + # flake8 + # pluggy + # pytest + # stevedore iniconfig==1.1.1 # via pytest isort==5.10.1 @@ -38,8 +46,6 @@ packaging==21.3 # via pytest pbr==5.8.1 # via stevedore -platformdirs==2.5.1 - # via pylint pluggy==1.0.0 # via pytest py==1.11.0 @@ -56,11 +62,11 @@ pygments==2.11.2 # via # -r requirements-tests.in # doc8 -pylint==2.12.2 +pylint==2.9.6 # via -r requirements-tests.in pyparsing==3.0.7 # via packaging -pytest==7.1.1 +pytest==6.2.5 # via # -r requirements-tests.in # pytest-cov @@ -77,15 +83,21 @@ stevedore==3.5.0 toml==0.10.2 # via # autopep8 - # pylint -tomli==2.0.1 - # via # coverage + # pylint # pytest +typed-ast==1.4.3 + # via astroid +typing-extensions==4.1.1 + # via + # astroid + # importlib-metadata untokenize==0.1.1 # via docformatter -wrapt==1.13.3 +wrapt==1.12.1 # via astroid +zipp==3.6.0 + # via importlib-metadata # The following packages are considered to be unsafe in a requirements file: # setuptools From 02c1bb75821c3973714760f7cd7f0a50f52beb67 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:43:35 -0400 Subject: [PATCH 18/57] lint --- bin/new-wide-by-version.py | 1 + 1 file changed, 1 insertion(+) diff --git a/bin/new-wide-by-version.py b/bin/new-wide-by-version.py index 18588c0..584d92a 100755 --- a/bin/new-wide-by-version.py +++ b/bin/new-wide-by-version.py @@ -21,6 +21,7 @@ # local from wcwidth import WIDE_EASTASIAN, _bisearch + def main(): """List new WIDE characters at each unicode version.""" versions = list(WIDE_EASTASIAN.keys()) From 8934085a63cfabf4bc79f7d630eae4b76b3d6fa5 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:43:40 -0400 Subject: [PATCH 19/57] remove older options for python3.6 --- tox.ini | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tox.ini b/tox.ini index 117b993..1d39c25 100644 --- a/tox.ini +++ b/tox.ini @@ -5,7 +5,7 @@ skip_missing_interpreters = true [testenv] deps = -r requirements-tests.txt commands = {envpython} -m pytest --cov-config={toxinidir}/tox.ini {posargs:\ - --strict --verbose \ + --verbose \ --junit-xml=.tox/results.{envname}.xml \ --durations=3 \ } \ @@ -30,7 +30,6 @@ known_third_party = codecov,docopt,blessed atomic = true [pytest] -looponfailroots = wcwidth norecursedirs = .git .tox build addopts = --disable-pytest-warnings --cov-append --cov-report=html --color=yes --ignore=setup.py --ignore=.tox From 85cb10099470c8bff685679efd301e1cbe07cb6a Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:54:30 -0400 Subject: [PATCH 20/57] seperate test requirements,<=python3.8,>=python3.9 --- ...ements-tests.in => requirements-tests38.in | 0 requirements-tests38.txt | 89 ++++++++++++++++++ requirements-tests39.in | 12 +++ requirements-tests39.txt | 91 +++++++++++++++++++ 4 files changed, 192 insertions(+) rename requirements-tests.in => requirements-tests38.in (100%) create mode 100644 requirements-tests38.txt create mode 100644 requirements-tests39.in create mode 100644 requirements-tests39.txt diff --git a/requirements-tests.in b/requirements-tests38.in similarity index 100% rename from requirements-tests.in rename to requirements-tests38.in diff --git a/requirements-tests38.txt b/requirements-tests38.txt new file mode 100644 index 0000000..8f14393 --- /dev/null +++ b/requirements-tests38.txt @@ -0,0 +1,89 @@ +# +# This file is autogenerated by pip-compile with python 3.10 +# To update, run: +# +# pip-compile --no-emit-index-url --output-file=requirements-tests38.txt requirements-tests38.in +# +astroid==2.6.6 + # via pylint +attrs==21.4.0 + # via pytest +autopep8==1.6.0 + # via -r requirements-tests38.in +coverage[toml]==5.5 + # via + # -r requirements-tests38.in + # pytest-cov +doc8==0.10.1 + # via -r requirements-tests38.in +docformatter==1.4 + # via -r requirements-tests38.in +docutils==0.18.1 + # via + # doc8 + # restructuredtext-lint +flake8==4.0.1 + # via -r requirements-tests38.in +iniconfig==1.1.1 + # via pytest +isort==5.10.1 + # via + # -r requirements-tests38.in + # pylint +lazy-object-proxy==1.7.1 + # via astroid +mccabe==0.6.1 + # via + # flake8 + # pylint +packaging==21.3 + # via pytest +pbr==5.8.1 + # via stevedore +pluggy==1.0.0 + # via pytest +py==1.11.0 + # via pytest +pycodestyle==2.8.0 + # via + # autopep8 + # flake8 +pydocstyle==6.1.1 + # via -r requirements-tests38.in +pyflakes==2.4.0 + # via flake8 +pygments==2.11.2 + # via + # -r requirements-tests38.in + # doc8 +pylint==2.9.6 + # via -r requirements-tests38.in +pyparsing==3.0.7 + # via packaging +pytest==6.2.5 + # via + # -r requirements-tests38.in + # pytest-cov +pytest-cov==3.0.0 + # via -r requirements-tests38.in +restructuredtext-lint==1.4.0 + # via + # -r requirements-tests38.in + # doc8 +snowballstemmer==2.2.0 + # via pydocstyle +stevedore==3.5.0 + # via doc8 +toml==0.10.2 + # via + # autopep8 + # coverage + # pylint + # pytest +untokenize==0.1.1 + # via docformatter +wrapt==1.12.1 + # via astroid + +# The following packages are considered to be unsafe in a requirements file: +# setuptools diff --git a/requirements-tests39.in b/requirements-tests39.in new file mode 100644 index 0000000..f90c294 --- /dev/null +++ b/requirements-tests39.in @@ -0,0 +1,12 @@ +pytest +pytest-cov +flake8 +autopep8 +docformatter +isort +pylint +pydocstyle +restructuredtext_lint +doc8 +pygments + diff --git a/requirements-tests39.txt b/requirements-tests39.txt new file mode 100644 index 0000000..9709274 --- /dev/null +++ b/requirements-tests39.txt @@ -0,0 +1,91 @@ +# +# This file is autogenerated by pip-compile with python 3.10 +# To update, run: +# +# pip-compile --no-emit-index-url --output-file=requirements-tests39.txt requirements-tests39.in +# +astroid==2.9.3 + # via pylint +attrs==21.4.0 + # via pytest +autopep8==1.6.0 + # via -r requirements-tests39.in +coverage[toml]==6.3.2 + # via pytest-cov +doc8==0.10.1 + # via -r requirements-tests39.in +docformatter==1.4 + # via -r requirements-tests39.in +docutils==0.18.1 + # via + # doc8 + # restructuredtext-lint +flake8==4.0.1 + # via -r requirements-tests39.in +iniconfig==1.1.1 + # via pytest +isort==5.10.1 + # via + # -r requirements-tests39.in + # pylint +lazy-object-proxy==1.7.1 + # via astroid +mccabe==0.6.1 + # via + # flake8 + # pylint +packaging==21.3 + # via pytest +pbr==5.8.1 + # via stevedore +platformdirs==2.5.1 + # via pylint +pluggy==1.0.0 + # via pytest +py==1.11.0 + # via pytest +pycodestyle==2.8.0 + # via + # autopep8 + # flake8 +pydocstyle==6.1.1 + # via -r requirements-tests39.in +pyflakes==2.4.0 + # via flake8 +pygments==2.11.2 + # via + # -r requirements-tests39.in + # doc8 +pylint==2.12.2 + # via -r requirements-tests39.in +pyparsing==3.0.7 + # via packaging +pytest==7.1.1 + # via + # -r requirements-tests39.in + # pytest-cov +pytest-cov==3.0.0 + # via -r requirements-tests39.in +restructuredtext-lint==1.4.0 + # via + # -r requirements-tests39.in + # doc8 +snowballstemmer==2.2.0 + # via pydocstyle +stevedore==3.5.0 + # via doc8 +toml==0.10.2 + # via + # autopep8 + # pylint +tomli==2.0.1 + # via + # coverage + # pytest +untokenize==0.1.1 + # via docformatter +wrapt==1.13.3 + # via astroid + +# The following packages are considered to be unsafe in a requirements file: +# setuptools From 75a93df76c2fb101cddbadb213221abf2e7ac8c5 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:55:33 -0400 Subject: [PATCH 21/57] split requirements versions --- tox.ini | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/tox.ini b/tox.ini index 1d39c25..9065746 100644 --- a/tox.ini +++ b/tox.ini @@ -1,9 +1,9 @@ [tox] -envlist = update, compile, autopep8, docformatter, isort, pylint, flake8, pydocstyle, docs, py26, py27, py34, py35, py36 +envlist = update, compile, autopep8, docformatter, isort, pylint, flake8, pydocstyle, docs, py26, py27, py34, py35, py36, py37, py38, py39, py310 skip_missing_interpreters = true [testenv] -deps = -r requirements-tests.txt +deps = -r requirements-tests39.txt commands = {envpython} -m pytest --cov-config={toxinidir}/tox.ini {posargs:\ --verbose \ --junit-xml=.tox/results.{envname}.xml \ @@ -64,9 +64,19 @@ commands = python -m compileall {toxinidir}/wcwidth {toxinidir}/bin {toxinidir}/ basepython = python3.10 deps = pip-tools commands = pip-compile --no-emit-index-url requirements-update.in -o requirements-update.txt - pip-compile --no-emit-index-url requirements-tests.in -o requirements-tests.txt + pip-compile --no-emit-index-url requirements-tests38.in -o requirements-tests38.txt + pip-compile --no-emit-index-url requirements-tests39.in -o requirements-tests39.txt pip-compile --no-emit-index-url requirements-docs.in -o docs/requirements.txt +[testenv:py38] +deps = -r requirements-tests38.txt + +[testenv:py37] +deps = -r requirements-tests38.txt + +[testenv:py36] +deps = -r requirements-tests38.txt + [testenv:update] basepython = python3.10 usedevelop = true From 11216b6048ec187c786948a5c8b9e72a07914875 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:55:44 -0400 Subject: [PATCH 22/57] split requirements version --- requirements-tests.txt | 103 ----------------------------------------- 1 file changed, 103 deletions(-) delete mode 100644 requirements-tests.txt diff --git a/requirements-tests.txt b/requirements-tests.txt deleted file mode 100644 index ea3a1ca..0000000 --- a/requirements-tests.txt +++ /dev/null @@ -1,103 +0,0 @@ -# -# This file is autogenerated by pip-compile with python 3.6 -# To update, run: -# -# pip-compile --no-emit-index-url --output-file=requirements-tests.txt requirements-tests.in -# -astroid==2.6.6 - # via pylint -attrs==21.4.0 - # via pytest -autopep8==1.6.0 - # via -r requirements-tests.in -coverage[toml]==5.5 - # via - # -r requirements-tests.in - # pytest-cov -doc8==0.10.1 - # via -r requirements-tests.in -docformatter==1.4 - # via -r requirements-tests.in -docutils==0.18.1 - # via - # doc8 - # restructuredtext-lint -flake8==4.0.1 - # via -r requirements-tests.in -importlib-metadata==4.2.0 - # via - # flake8 - # pluggy - # pytest - # stevedore -iniconfig==1.1.1 - # via pytest -isort==5.10.1 - # via - # -r requirements-tests.in - # pylint -lazy-object-proxy==1.7.1 - # via astroid -mccabe==0.6.1 - # via - # flake8 - # pylint -packaging==21.3 - # via pytest -pbr==5.8.1 - # via stevedore -pluggy==1.0.0 - # via pytest -py==1.11.0 - # via pytest -pycodestyle==2.8.0 - # via - # autopep8 - # flake8 -pydocstyle==6.1.1 - # via -r requirements-tests.in -pyflakes==2.4.0 - # via flake8 -pygments==2.11.2 - # via - # -r requirements-tests.in - # doc8 -pylint==2.9.6 - # via -r requirements-tests.in -pyparsing==3.0.7 - # via packaging -pytest==6.2.5 - # via - # -r requirements-tests.in - # pytest-cov -pytest-cov==3.0.0 - # via -r requirements-tests.in -restructuredtext-lint==1.4.0 - # via - # -r requirements-tests.in - # doc8 -snowballstemmer==2.2.0 - # via pydocstyle -stevedore==3.5.0 - # via doc8 -toml==0.10.2 - # via - # autopep8 - # coverage - # pylint - # pytest -typed-ast==1.4.3 - # via astroid -typing-extensions==4.1.1 - # via - # astroid - # importlib-metadata -untokenize==0.1.1 - # via docformatter -wrapt==1.12.1 - # via astroid -zipp==3.6.0 - # via importlib-metadata - -# The following packages are considered to be unsafe in a requirements file: -# setuptools From 0e5718e60d03f878878535c909553b3147011248 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 17:55:58 -0400 Subject: [PATCH 23/57] ignore pycharm --- .gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/.gitignore b/.gitignore index 4411244..e8bf2cc 100644 --- a/.gitignore +++ b/.gitignore @@ -13,3 +13,4 @@ htmlcov .coveralls.yml data .DS_Store +.idea From b0dad96ab74c0630c9085aabff0c3acd06af233e Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 18:45:08 -0400 Subject: [PATCH 24/57] bugfix in codegen --- bin/update-tables.py | 15 +-- wcwidth/table_wide.py | 22 +--- wcwidth/table_zero.py | 256 +++++++++--------------------------- wcwidth/unicode_versions.py | 3 +- 4 files changed, 71 insertions(+), 225 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 371e83c..ee6d44e 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -140,13 +140,8 @@ def make_table(values): start, end = values[0], values[0] table = collections.deque() table.append((start, end)) - for num, value in enumerate(values): - try: - start, end = table.pop() - except IndexError: - # first item - table.append((value, value)) - continue + for value in values[1:]: + start, end = table.pop() if end == value - 1: # continuation of existing range table.append((start, value,)) @@ -184,7 +179,7 @@ def convert_values_to_string_table(values): def parse_category(fname, category_codes=('Me', 'Mn',)): """Parse value ranges of unicode data files, by given categories into string tables.""" print(f'parsing {fname}: ', end='', flush=True) - version, date, values = None, None, [] + version, date, values = None, None, set() for line in open(fname, 'rb'): uline = line.decode('utf-8') if version is None: @@ -206,8 +201,8 @@ def parse_category(fname, category_codes=('Me', 'Mn',)): start, stop = addrs.split('..') else: start, stop = addrs, addrs - values.extend(range(int(start, 16), int(stop, 16) + 1)) - txt_values = convert_values_to_string_table(make_table(values)) + values.update(range(int(start, 16), int(stop, 16) + 1)) + txt_values = convert_values_to_string_table(make_table(sorted(values))) print('ok') return TableDef(version, date, txt_values) diff --git a/wcwidth/table_wide.py b/wcwidth/table_wide.py index fe517db..9a5ffd8 100644 --- a/wcwidth/table_wide.py +++ b/wcwidth/table_wide.py @@ -1,14 +1,13 @@ """ Exports WIDE_EASTASIAN table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2022-03-20 21:29:31 UTC. +This code generated by wcwidth/bin/update-tables.py on 2022-03-20 22:43:45 UTC. """ WIDE_EASTASIAN = { '4.1.0': ( # Source: EastAsianWidth-4.1.0.txt # Date: 2005-03-17, 15:21:00 PST [KW] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x01159,), # Hangul Choseong Kiyeok ..Hangul Choseong Yeorinhi (0x0115f, 0x0115f,), # Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra @@ -47,7 +46,6 @@ # Source: EastAsianWidth-5.0.0.txt # Date: 2006-02-15, 14:39:00 PST [KW] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x01159,), # Hangul Choseong Kiyeok ..Hangul Choseong Yeorinhi (0x0115f, 0x0115f,), # Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra @@ -86,7 +84,6 @@ # Source: EastAsianWidth-5.1.0.txt # Date: 2008-03-20, 17:42:00 PDT [KW] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x01159,), # Hangul Choseong Kiyeok ..Hangul Choseong Yeorinhi (0x0115f, 0x0115f,), # Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra @@ -125,7 +122,6 @@ # Source: EastAsianWidth-5.2.0.txt # Date: 2009-06-09, 17:47:00 PDT [KW] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x011a3, 0x011a7,), # Hangul Jungseong A-eu ..Hangul Jungseong O-yae (0x011fa, 0x011ff,), # Hangul Jongseong Kiyeok-..Hangul Jongseong Ssangni @@ -168,7 +164,6 @@ # Source: EastAsianWidth-6.0.0.txt # Date: 2010-08-17, 12:17:00 PDT [KW] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x011a3, 0x011a7,), # Hangul Jungseong A-eu ..Hangul Jungseong O-yae (0x011fa, 0x011ff,), # Hangul Jongseong Kiyeok-..Hangul Jongseong Ssangni @@ -206,15 +201,13 @@ (0x1f210, 0x1f23a,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo (0x1f240, 0x1f248,), # Tortoise Shell Bracketed..Tortoise Shell Bracketed (0x1f250, 0x1f251,), # Circled Ideograph Advant..Circled Ideograph Accept - (0x20000, 0x2f73f,), # Cjk Unified Ideograph-20..(nil) - (0x2b740, 0x2fffd,), # Cjk Unified Ideograph-2b..(nil) + (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), '6.1.0': ( # Source: EastAsianWidth-6.1.0.txt # Date: 2011-09-19, 18:46:00 GMT [KW] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x011a3, 0x011a7,), # Hangul Jungseong A-eu ..Hangul Jungseong O-yae (0x011fa, 0x011ff,), # Hangul Jongseong Kiyeok-..Hangul Jongseong Ssangni @@ -259,7 +252,6 @@ # Source: EastAsianWidth-6.2.0.txt # Date: 2012-05-15, 18:30:00 GMT [KW] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap @@ -300,7 +292,6 @@ # Source: EastAsianWidth-6.3.0.txt # Date: 2013-02-05, 20:09:00 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap @@ -341,7 +332,6 @@ # Source: EastAsianWidth-7.0.0.txt # Date: 2014-02-28, 23:15:00 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap @@ -382,7 +372,6 @@ # Source: EastAsianWidth-8.0.0.txt # Date: 2015-02-10, 21:00:00 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap @@ -423,7 +412,6 @@ # Source: EastAsianWidth-9.0.0.txt # Date: 2016-05-27, 17:00:00 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra @@ -535,7 +523,6 @@ # Source: EastAsianWidth-10.0.0.txt # Date: 2017-03-08, 02:00:00 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra @@ -647,7 +634,6 @@ # Source: EastAsianWidth-11.0.0.txt # Date: 2018-05-14, 09:41:59 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra @@ -761,7 +747,6 @@ # Source: EastAsianWidth-12.0.0.txt # Date: 2019-01-21, 14:12:58 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra @@ -881,7 +866,6 @@ # Source: EastAsianWidth-12.1.0.txt # Date: 2019-03-31, 22:01:58 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra @@ -1000,7 +984,6 @@ # Source: EastAsianWidth-13.0.0.txt # Date: 2029-01-21, 18:14:00 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra @@ -1122,7 +1105,6 @@ # Source: EastAsianWidth-14.0.0.txt # Date: 2021-07-06, 09:58:53 GMT [KW, LI] # - (0x01100, 0x01100,), # Hangul Choseong Kiyeok (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra diff --git a/wcwidth/table_zero.py b/wcwidth/table_zero.py index 78845ba..48b2b04 100644 --- a/wcwidth/table_zero.py +++ b/wcwidth/table_zero.py @@ -1,16 +1,16 @@ """ Exports ZERO_WIDTH table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2022-03-20 21:29:31 UTC. +This code generated by wcwidth/bin/update-tables.py on 2022-03-20 22:43:45 UTC. """ ZERO_WIDTH = { '4.1.0': ( # Source: DerivedGeneralCategory-4.1.0.txt # Date: 2005-02-26, 02:35:50 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00486,), # Combining Cyrillic Titlo..Combining Cyrillic Psili + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli (0x00591, 0x005b9,), # Hebrew Accent Etnahta ..Hebrew Point Holam (0x005bb, 0x005bd,), # Hebrew Point Qubuts ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe @@ -21,7 +21,7 @@ (0x0064b, 0x0065e,), # Arabic Fathatan ..Arabic Fatha With Two Do (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen - (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda + (0x006de, 0x006e4,), # Arabic Start Of Rub El H..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem (0x00711, 0x00711,), # Syriac Letter Superscript Alaph @@ -111,9 +111,7 @@ (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U (0x01dc0, 0x01dc3,), # Combining Dotted Grave A..Combining Suspension Mar - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020eb,), # Combining Reverse Solidu..Combining Long Double So + (0x020d0, 0x020eb,), # Combining Left Harpoon A..Combining Long Double So (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta @@ -133,18 +131,14 @@ (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x006de, 0x006de,), # Arabic Start Of Rub El Hizb - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa ), '5.0.0': ( # Source: DerivedGeneralCategory-5.0.0.txt # Date: 2006-02-27, 23:41:27 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00486,), # Combining Cyrillic Titlo..Combining Cyrillic Psili + (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -154,7 +148,7 @@ (0x0064b, 0x0065e,), # Arabic Fathatan ..Arabic Fatha With Two Do (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen - (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda + (0x006de, 0x006e4,), # Arabic Start Of Rub El H..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem (0x00711, 0x00711,), # Syriac Letter Superscript Alaph @@ -253,9 +247,7 @@ (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol (0x01dc0, 0x01dca,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfe, 0x01dff,), # Combining Left Arrowhead..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020ef,), # Combining Reverse Solidu..Combining Right Arrow Be + (0x020d0, 0x020ef,), # Combining Left Harpoon A..Combining Right Arrow Be (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta @@ -275,18 +267,13 @@ (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x006de, 0x006de,), # Arabic Start Of Rub El Hizb - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa ), '5.1.0': ( # Source: DerivedGeneralCategory-5.1.0.txt # Date: 2008-03-20, 17:54:57 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -296,7 +283,7 @@ (0x0064b, 0x0065e,), # Arabic Fathatan ..Arabic Fatha With Two Do (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen - (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda + (0x006de, 0x006e4,), # Arabic Start Of Rub El H..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem (0x00711, 0x00711,), # Syriac Letter Superscript Alaph @@ -410,13 +397,11 @@ (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfe, 0x01dff,), # Combining Left Arrowhead..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a67c, 0x0a67d,), # Combining Cyrillic Kavyk..Combining Cyrillic Payer (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta @@ -445,19 +430,13 @@ (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x006de, 0x006de,), # Arabic Start Of Rub El Hizb - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '5.2.0': ( # Source: DerivedGeneralCategory-5.2.0.txt # Date: 2009-08-22, 04:58:21 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -467,7 +446,7 @@ (0x0064b, 0x0065e,), # Arabic Fathatan ..Arabic Fatha With Two Do (0x00670, 0x00670,), # Arabic Letter Superscript Alef (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen - (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda + (0x006de, 0x006e4,), # Arabic Start Of Rub El H..Arabic Small High Madda (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem (0x00711, 0x00711,), # Syriac Letter Superscript Alaph @@ -597,14 +576,12 @@ (0x01ced, 0x01ced,), # Vedic Sign Tiryak (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfd, 0x01dff,), # Combining Almost Equal T..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a67c, 0x0a67d,), # Combining Cyrillic Kavyk..Combining Cyrillic Payer (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara @@ -650,19 +627,13 @@ (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x006de, 0x006de,), # Arabic Start Of Rub El Hizb - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '6.0.0': ( # Source: DerivedGeneralCategory-6.0.0.txt # Date: 2010-08-19, 00:48:09 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -808,15 +779,13 @@ (0x01ced, 0x01ced,), # Vedic Sign Tiryak (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302f,), # Ideographic Level Tone M..Hangul Double Dot Tone M (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a67c, 0x0a67d,), # Combining Cyrillic Kavyk..Combining Cyrillic Payer (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara @@ -864,18 +833,13 @@ (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '6.1.0': ( # Source: DerivedGeneralCategory-6.1.0.txt # Date: 2011-11-27, 05:10:22 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -1025,15 +989,13 @@ (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69f, 0x0a69f,), # Combining Cyrillic Letter Iotified E (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk @@ -1094,18 +1056,13 @@ (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '6.2.0': ( # Source: DerivedGeneralCategory-6.2.0.txt # Date: 2012-05-20, 00:42:34 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -1255,15 +1212,13 @@ (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69f, 0x0a69f,), # Combining Cyrillic Letter Iotified E (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk @@ -1324,18 +1279,13 @@ (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '6.3.0': ( # Source: DerivedGeneralCategory-6.3.0.txt # Date: 2013-07-05, 14:08:45 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -1486,15 +1436,13 @@ (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01dc0, 0x01de6,), # Combining Dotted Grave A..Combining Latin Small Le (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69f, 0x0a69f,), # Combining Cyrillic Letter Iotified E (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk @@ -1555,18 +1503,13 @@ (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '7.0.0': ( # Source: DerivedGeneralCategory-7.0.0.txt # Date: 2014-02-07, 18:42:12 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -1696,7 +1639,7 @@ (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot - (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be + (0x01ab0, 0x01abe,), # Combining Doubled Circum..Combining Parentheses Ov (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R @@ -1721,15 +1664,13 @@ (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df5,), # Combining Dotted Grave A..Combining Up Tack Above (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69f, 0x0a69f,), # Combining Cyrillic Letter Iotified E (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk @@ -1820,19 +1761,13 @@ (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Overlay - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '8.0.0': ( # Source: DerivedGeneralCategory-8.0.0.txt # Date: 2015-02-13, 13:47:11 GMT [MD] # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -1962,7 +1897,7 @@ (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot - (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be + (0x01ab0, 0x01abe,), # Combining Doubled Circum..Combining Parentheses Ov (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R @@ -1987,15 +1922,13 @@ (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df5,), # Combining Dotted Grave A..Combining Up Tack Above (0x01dfc, 0x01dff,), # Combining Double Inverte..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk @@ -2097,19 +2030,13 @@ (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Overlay - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '9.0.0': ( # Source: DerivedGeneralCategory-9.0.0.txt # Date: 2016-06-01, 10:34:26 GMT # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -2241,7 +2168,7 @@ (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot - (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be + (0x01ab0, 0x01abe,), # Combining Doubled Circum..Combining Parentheses Ov (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R @@ -2266,15 +2193,13 @@ (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df5,), # Combining Dotted Grave A..Combining Up Tack Above (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk @@ -2393,19 +2318,13 @@ (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Overlay - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '10.0.0': ( # Source: DerivedGeneralCategory-10.0.0.txt # Date: 2017-03-08, 08:41:49 GMT # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -2539,7 +2458,7 @@ (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot - (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be + (0x01ab0, 0x01abe,), # Combining Doubled Circum..Combining Parentheses Ov (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R @@ -2564,15 +2483,13 @@ (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk @@ -2705,19 +2622,13 @@ (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Overlay - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '11.0.0': ( # Source: DerivedGeneralCategory-11.0.0.txt # Date: 2018-02-21, 05:34:04 GMT # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -2854,7 +2765,7 @@ (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot - (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be + (0x01ab0, 0x01abe,), # Combining Doubled Circum..Combining Parentheses Ov (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R @@ -2879,15 +2790,13 @@ (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk @@ -3029,19 +2938,13 @@ (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Overlay - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '12.0.0': ( # Source: DerivedGeneralCategory-12.0.0.txt # Date: 2019-01-22, 08:18:28 GMT # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -3177,7 +3080,7 @@ (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot - (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be + (0x01ab0, 0x01abe,), # Combining Doubled Circum..Combining Parentheses Ov (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R @@ -3202,15 +3105,13 @@ (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk @@ -3358,19 +3259,13 @@ (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Overlay - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '12.1.0': ( # Source: DerivedGeneralCategory-12.1.0.txt # Date: 2019-03-10, 10:53:08 GMT # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -3506,7 +3401,7 @@ (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot - (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be + (0x01ab0, 0x01abe,), # Combining Doubled Circum..Combining Parentheses Ov (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R @@ -3531,15 +3426,13 @@ (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk @@ -3687,19 +3580,13 @@ (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Overlay - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '13.0.0': ( # Source: DerivedGeneralCategory-13.0.0.txt # Date: 2019-10-21, 14:30:32 GMT # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -3836,8 +3723,7 @@ (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot - (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be - (0x01abf, 0x01ac0,), # Combining Latin Small Le..Combining Latin Small Le + (0x01ab0, 0x01ac0,), # Combining Doubled Circum..Combining Latin Small Le (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R @@ -3862,15 +3748,13 @@ (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01df9,), # Combining Dotted Grave A..Combining Wide Inverted (0x01dfb, 0x01dff,), # Combining Deletion Mark ..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk @@ -4025,19 +3909,13 @@ (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Overlay - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), '14.0.0': ( # Source: DerivedGeneralCategory-14.0.0.txt # Date: 2021-07-10, 00:35:08 GMT # - (0x00300, 0x00300,), # Combining Grave Accent (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le - (0x00483, 0x00487,), # Combining Cyrillic Titlo..Combining Cyrillic Pokry + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg (0x005bf, 0x005bf,), # Hebrew Point Rafe (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot @@ -4177,8 +4055,7 @@ (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot - (0x01ab0, 0x01abd,), # Combining Doubled Circum..Combining Parentheses Be - (0x01abf, 0x01ace,), # Combining Latin Small Le..(nil) + (0x01ab0, 0x01ace,), # Combining Doubled Circum..(nil) (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R @@ -4202,15 +4079,13 @@ (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A (0x01dc0, 0x01dff,), # Combining Dotted Grave A..Combining Right Arrowhea - (0x020d0, 0x020dc,), # Combining Left Harpoon A..Combining Four Dots Abov - (0x020e1, 0x020e1,), # Combining Left Right Arrow Above - (0x020e5, 0x020f0,), # Combining Reverse Solidu..Combining Asterisk Above + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag - (0x0a66f, 0x0a66f,), # Combining Cyrillic Vzmet + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk @@ -4372,10 +4247,5 @@ (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 - (0x00488, 0x00489,), # Combining Cyrillic Hundr..Combining Cyrillic Milli - (0x01abe, 0x01abe,), # Combining Parentheses Overlay - (0x020dd, 0x020e0,), # Combining Enclosing Circ..Combining Enclosing Circ - (0x020e2, 0x020e4,), # Combining Enclosing Scre..Combining Enclosing Upwa - (0x0a670, 0x0a672,), # Combining Cyrillic Ten M..Combining Cyrillic Thous ), } diff --git a/wcwidth/unicode_versions.py b/wcwidth/unicode_versions.py index 307a0b2..d5ee547 100644 --- a/wcwidth/unicode_versions.py +++ b/wcwidth/unicode_versions.py @@ -1,10 +1,9 @@ """ Exports function list_versions() for unicode version level support. -This code generated by wcwidth/bin/update-tables.py on 2022-03-20 21:29:31 UTC. +This code generated by wcwidth/bin/update-tables.py on 2022-03-20 22:43:45 UTC. """ - def list_versions(): """ Return Unicode version levels supported by this module release. From bbe041b7112d0b8cbdd4f0990863c1ce2b6ef378 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sun, 20 Mar 2022 19:11:23 -0400 Subject: [PATCH 25/57] yarr --- bin/update-tables.py | 1 - docs/intro.rst | 4 ++-- tox.ini | 8 -------- 3 files changed, 2 insertions(+), 11 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index ee6d44e..28453df 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -21,7 +21,6 @@ import glob import codecs import string -import urllib import logging import datetime import functools diff --git a/docs/intro.rst b/docs/intro.rst index b865c4a..a4c88ff 100644 --- a/docs/intro.rst +++ b/docs/intro.rst @@ -111,14 +111,14 @@ Execute unit tests using tox_:: Regenerate python code tables from latest Unicode Specification data files:: - tox -eupdate + tox -e update Supplementary tools for browsing and testing terminals for wide unicode characters are found in the `bin/`_ of this project's source code. Just ensure to first ``pip install -erequirements-develop.txt`` from this projects main folder. For example, an interactive browser for testing:: - ./bin/wcwidth-browser.py + python ./bin/wcwidth-browser.py Uses ---- diff --git a/tox.ini b/tox.ini index 9065746..e0d570c 100644 --- a/tox.ini +++ b/tox.ini @@ -147,11 +147,3 @@ basepython = python{env:TOXPYTHON:{env:TRAVIS_PYTHON_VERSION:3.10}} passenv = TOXENV CI TRAVIS TRAVIS_* CODECOV_* deps = codecov commands = codecov -e TOXENV - -# Run a command using requirements-develop.txt, for example: -# -# tox -e update -- bin/wcwidth-browser.py -[testenv:develop] -basepython = python3.10 -deps = -rrequirements-develop.txt -commands = {posargs} From b1276fa1c74288b36ba460878c98e847582f15fa Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Mon, 21 Mar 2022 23:40:20 +0800 Subject: [PATCH 26/57] Remove duplicated comment --- bin/update-tables.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 28453df..b27a043 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -28,7 +28,6 @@ import unicodedata # 3rd party -# third party import jinja2 import requests import tenacity @@ -38,20 +37,25 @@ URL_EASTASIAN_WIDTH = 'https://www.unicode.org/Public/{version}/ucd/EastAsianWidth.txt' URL_DERIVED_CATEGORY = 'https://www.unicode.org/Public/{version}/ucd/extracted/DerivedGeneralCategory.txt' EXCLUDE_VERSIONS = ['2.0.0', '2.1.2', '3.0.0', '3.1.0', '3.2.0', '4.0.0'] + PATH_UP = os.path.relpath(os.path.join(os.path.dirname(__file__), os.path.pardir)) PATH_DATA = os.path.join(PATH_UP, 'data') THIS_FILEPATH = os.path.relpath(__file__, os.path.join( PATH_UP, os.path.pardir)) # "wcwidth/bin/update-tables.py" + JINJA_ENV = jinja2.Environment( loader=jinja2.FileSystemLoader(os.path.join(PATH_UP, 'code_templates')), keep_trailing_newline=True) UTC_NOW = datetime.datetime.utcnow().strftime("%Y-%m-%d %H:%M:%S UTC") + CONNECT_TIMEOUT = int(os.environ.get('CONNECT_TIMEOUT', '10')) FETCH_BLOCKSIZE = int(os.environ.get('FETCH_BLOCKSIZE', '4096')) MAX_RETRIES = int(os.environ.get('MAX_RETRIES', '10')) + TableDef = collections.namedtuple('table', ['version', 'date', 'values']) RenderDefinition = collections.namedtuple( 'render', ['jinja_filename', 'output_filename', 'fn_data']) + logging.basicConfig(stream=sys.stderr, level=logging.DEBUG) logger = logging.getLogger(__name__) From 1d1164887578ab6f39bd1d5aa3aaae12252f392b Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Sun, 6 Mar 2022 07:00:46 +0800 Subject: [PATCH 27/57] Remove python2 compat code for `bin/update-tables.py` Cherry picked from commit 8c763ab (GH-58) --- bin/update-tables.py | 61 ++++++++++++++++++++++---------------------- 1 file changed, 31 insertions(+), 30 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index b27a043..a24413a 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -19,7 +19,6 @@ import re import sys import glob -import codecs import string import logging import datetime @@ -33,6 +32,7 @@ import tenacity import dateutil.parser + URL_UNICODE_DERIVED_AGE = 'https://www.unicode.org/Public/UCD/latest/ucd/DerivedAge.txt' URL_EASTASIAN_WIDTH = 'https://www.unicode.org/Public/{version}/ucd/EastAsianWidth.txt' URL_DERIVED_CATEGORY = 'https://www.unicode.org/Public/{version}/ucd/extracted/DerivedGeneralCategory.txt' @@ -67,11 +67,12 @@ def fetch_unicode_versions(): do_retrieve(url=URL_UNICODE_DERIVED_AGE, fname=fname) pattern = re.compile(r'#.*assigned in Unicode ([0-9.]+)') versions = [] - for line in open(fname, 'r'): - if match := re.match(pattern, line): - version = match.group(1) - if version not in EXCLUDE_VERSIONS: - versions.append(version) + with open(fname, encoding='utf-8') as f: + for line in f: + if match := re.match(pattern, line): + version = match.group(1) + if version not in EXCLUDE_VERSIONS: + versions.append(version) versions.sort(key=lambda ver: list(map(int, ver.split('.')))) return {'versions': versions} @@ -121,7 +122,7 @@ def cite_source_description(filename): """Return unicode.org source data file's own description as citation.""" header_twolines = [ line.lstrip('# ').rstrip() - for line in codecs.open(filename, 'r', 'utf8') + for line in open(filename, encoding='utf-8') .readlines()[:2] ] if len(header_twolines) == 2: @@ -183,28 +184,28 @@ def parse_category(fname, category_codes=('Me', 'Mn',)): """Parse value ranges of unicode data files, by given categories into string tables.""" print(f'parsing {fname}: ', end='', flush=True) version, date, values = None, None, set() - for line in open(fname, 'rb'): - uline = line.decode('utf-8') - if version is None: - # pull "version string" from first line of source file - version = uline.split(None, 1)[1].rstrip() - continue - if date is None: - # and "date string" from second line - date = uline.split(':', 1)[1].rstrip() - continue - if uline.startswith('#') or not uline.lstrip(): - # ignore any further comments or empty lines - continue - addrs, details = uline.split(';', 1) - addrs, details = addrs.rstrip(), details.lstrip() - if any(details.startswith(f'{category_code}') - for category_code in category_codes): - if '..' in addrs: - start, stop = addrs.split('..') - else: - start, stop = addrs, addrs - values.update(range(int(start, 16), int(stop, 16) + 1)) + with open(fname, encoding='utf-8') as f: + for line in f: + if version is None: + # pull "version string" from first line of source file + version = line.split(None, 1)[1].rstrip() + continue + if date is None: + # and "date string" from second line + date = line.split(':', 1)[1].rstrip() + continue + if line.startswith('#') or not line.lstrip(): + # ignore any further comments or empty lines + continue + addrs, details = line.split(';', 1) + addrs, details = addrs.rstrip(), details.lstrip() + if any(details.startswith(f'{category_code}') + for category_code in category_codes): + if '..' in addrs: + start, stop = addrs.split('..') + else: + start, stop = addrs, addrs + values.update(range(int(start, 16), int(stop, 16) + 1)) txt_values = convert_values_to_string_table(make_table(sorted(values))) print('ok') return TableDef(version, date, txt_values) @@ -268,7 +269,7 @@ def main(): fn_data=fetch_table_zero_data) ] for render_def in CODEGEN_DEFINITIONS: - with open(render_def.output_filename, 'w') as fout: + with open(render_def.output_filename, 'w', encoding='utf-8') as fout: data = render_def.fn_data() print(f'write {render_def.output_filename}: ', flush=True, end='') fout.write(render_template(render_def.jinja_filename, **data)) From 48adfb23eb35e9ea8408eaa769949a6c59316874 Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Tue, 22 Mar 2022 01:05:32 +0800 Subject: [PATCH 28/57] Introduce dataclasses and type hints Cherry picked from commit 8b7621e (GH-58) --- bin/update-tables.py | 63 +++++++++++++++++++++++++++++++++----------- 1 file changed, 47 insertions(+), 16 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index a24413a..04ac24e 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -14,6 +14,10 @@ https://github.com/jquast/wcwidth """ + + +from __future__ import annotations + # std imports import os import re @@ -25,6 +29,7 @@ import functools import collections import unicodedata +from dataclasses import dataclass # 3rd party import jinja2 @@ -52,29 +57,53 @@ FETCH_BLOCKSIZE = int(os.environ.get('FETCH_BLOCKSIZE', '4096')) MAX_RETRIES = int(os.environ.get('MAX_RETRIES', '10')) +logging.basicConfig(stream=sys.stderr, level=logging.DEBUG) +logger = logging.getLogger(__name__) + + +@dataclass(order=True, frozen=True) +class UnicodeVersion: + """A class for camparable unicode version""" + major: int + minor: int + micro: int + + @classmethod + def parse(cls, version_str: str) -> UnicodeVersion: + """parse a version string + >>> UnicodeVersion.parse("14.0.0") + UnicodeVersion(major=14, minor=0, micro=0) + """ + return cls(*map(int, version_str.split(".")[:3])) + + def __str__(self): + """ + >>> str(UnicodeVersion(12, 1, 0)) + '12.1.0' + """ + return f'{self.major}.{self.minor}.{self.micro}' + + TableDef = collections.namedtuple('table', ['version', 'date', 'values']) RenderDefinition = collections.namedtuple( 'render', ['jinja_filename', 'output_filename', 'fn_data']) -logging.basicConfig(stream=sys.stderr, level=logging.DEBUG) -logger = logging.getLogger(__name__) - @functools.cache -def fetch_unicode_versions(): +def fetch_unicode_versions() -> list[UnicodeVersion]: """Fetch, determine, and return Unicode Versions for processing.""" fname = os.path.join(PATH_DATA, os.path.basename(URL_UNICODE_DERIVED_AGE)) do_retrieve(url=URL_UNICODE_DERIVED_AGE, fname=fname) pattern = re.compile(r'#.*assigned in Unicode ([0-9.]+)') - versions = [] + versions: list[UnicodeVersion] = [] with open(fname, encoding='utf-8') as f: for line in f: if match := re.match(pattern, line): version = match.group(1) if version not in EXCLUDE_VERSIONS: - versions.append(version) - versions.sort(key=lambda ver: list(map(int, ver.split('.')))) - return {'versions': versions} + versions.append(UnicodeVersion.parse(version)) + versions.sort() + return versions def fetch_source_headers(): @@ -88,20 +117,20 @@ def fetch_source_headers(): return {'source_headers': headers} -def fetch_table_wide_data(): +def fetch_table_wide_data() -> dict: """Fetch and update east-asian tables.""" table = {} - for version in fetch_unicode_versions()['versions']: + for version in fetch_unicode_versions(): fname = os.path.join(PATH_DATA, f'EastAsianWidth-{version}.txt') do_retrieve(url=URL_EASTASIAN_WIDTH.format(version=version), fname=fname) table[version] = parse_category(fname=fname, category_codes=('W', 'F',)) return {'table': table, 'variable_name': 'WIDE_EASTASIAN'} -def fetch_table_zero_data(): +def fetch_table_zero_data() -> dict: """Fetch and update zero width tables.""" table = {} - for version in fetch_unicode_versions()['versions']: + for version in fetch_unicode_versions(): fname = os.path.join(PATH_DATA, f'DerivedGeneralCategory-{version}.txt') do_retrieve(url=URL_DERIVED_CATEGORY.format(version=version), fname=fname) # TODO: test whether all of category, 'Cf' should be 'zero @@ -180,10 +209,12 @@ def convert_values_to_string_table(values): return pytable_values -def parse_category(fname, category_codes=('Me', 'Mn',)): +def parse_category(fname: str, category_codes=('Me', 'Mn',)) -> TableDef: """Parse value ranges of unicode data files, by given categories into string tables.""" print(f'parsing {fname}: ', end='', flush=True) - version, date, values = None, None, set() + version = None + date = None + values: set[int] = set() with open(fname, encoding='utf-8') as f: for line in f: if version is None: @@ -244,7 +275,7 @@ def do_retrieve(url, fname): print('ok') -def main(): +def main() -> None: """Update east-asian, combining and zero width tables.""" # This defines which jinja source templates map to which output filenames, # and what function defines the source data. We hope to add more source @@ -254,7 +285,7 @@ def main(): RenderDefinition( jinja_filename='unicode_versions.py.j2', output_filename=os.path.join(PATH_UP, 'wcwidth', 'unicode_versions.py'), - fn_data=fetch_unicode_versions), + fn_data=lambda: {'versions': fetch_unicode_versions()}), RenderDefinition( jinja_filename='unicode_version.rst.j2', output_filename=os.path.join(PATH_UP, 'docs', 'unicode_version.rst'), From bf6249948620ab04be48f1474223334c758646e9 Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Tue, 22 Mar 2022 02:35:39 +0800 Subject: [PATCH 29/57] Move `logging.basicConfig` to the main function --- bin/update-tables.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 04ac24e..3b9a723 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -57,7 +57,6 @@ FETCH_BLOCKSIZE = int(os.environ.get('FETCH_BLOCKSIZE', '4096')) MAX_RETRIES = int(os.environ.get('MAX_RETRIES', '10')) -logging.basicConfig(stream=sys.stderr, level=logging.DEBUG) logger = logging.getLogger(__name__) @@ -277,6 +276,8 @@ def do_retrieve(url, fname): def main() -> None: """Update east-asian, combining and zero width tables.""" + logging.basicConfig(stream=sys.stderr, level=logging.DEBUG) + # This defines which jinja source templates map to which output filenames, # and what function defines the source data. We hope to add more source # language options using jinja2 templates, with minimal modification of the From a97204c0c4415c472ede7d3127f60098acb8eb40 Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Tue, 22 Mar 2022 03:05:15 +0800 Subject: [PATCH 30/57] Rewrite table parsing logic Cherry picked from commit 50e3d41 and commit e7de09f (GH-58) --- bin/update-tables.py | 86 ++++++++++++++++++++----------- code_templates/python_table.py.j2 | 8 +-- tox.ini | 5 +- 3 files changed, 64 insertions(+), 35 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 3b9a723..0fb2fdb 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -31,13 +31,14 @@ import unicodedata from dataclasses import dataclass +from typing import Iterable, Iterator, Container + # 3rd party import jinja2 import requests import tenacity import dateutil.parser - URL_UNICODE_DERIVED_AGE = 'https://www.unicode.org/Public/UCD/latest/ucd/DerivedAge.txt' URL_EASTASIAN_WIDTH = 'https://www.unicode.org/Public/{version}/ucd/EastAsianWidth.txt' URL_DERIVED_CATEGORY = 'https://www.unicode.org/Public/{version}/ucd/extracted/DerivedGeneralCategory.txt' @@ -83,7 +84,21 @@ def __str__(self): return f'{self.major}.{self.minor}.{self.micro}' -TableDef = collections.namedtuple('table', ['version', 'date', 'values']) +@dataclass(frozen=True) +class TableEntry: + """An entry of a unicode table""" + code_range: range | None + properties: tuple[str, ...] + comment: str + + +@dataclass +class TableDef: + filename: str + date: str + values: list[tuple[str, str, str]] + + RenderDefinition = collections.namedtuple( 'render', ['jinja_filename', 'output_filename', 'fn_data']) @@ -118,7 +133,7 @@ def fetch_source_headers(): def fetch_table_wide_data() -> dict: """Fetch and update east-asian tables.""" - table = {} + table: dict[UnicodeVersion, TableDef] = {} for version in fetch_unicode_versions(): fname = os.path.join(PATH_DATA, f'EastAsianWidth-{version}.txt') do_retrieve(url=URL_EASTASIAN_WIDTH.format(version=version), fname=fname) @@ -128,7 +143,7 @@ def fetch_table_wide_data() -> dict: def fetch_table_zero_data() -> dict: """Fetch and update zero width tables.""" - table = {} + table: dict[UnicodeVersion, TableDef] = {} for version in fetch_unicode_versions(): fname = os.path.join(PATH_DATA, f'DerivedGeneralCategory-{version}.txt') do_retrieve(url=URL_DERIVED_CATEGORY.format(version=version), fname=fname) @@ -208,34 +223,47 @@ def convert_values_to_string_table(values): return pytable_values -def parse_category(fname: str, category_codes=('Me', 'Mn',)) -> TableDef: +def parse_unicode_table(file: Iterable[str]) -> Iterator[TableEntry]: + """Parse unicode tables. + See details: https://www.unicode.org/reports/tr44/#Format_Conventions + """ + for line in file: + data, _, comment = line.partition('#') + data_fields: Iterator[str] = (field.strip() for field in data.split(';')) + code_points_str, *properties = data_fields + + if not code_points_str: + yield TableEntry(None, tuple(properties), comment) + continue + + if '..' in code_points_str: + start, end = code_points_str.split('..') + else: + start = end = code_points_str + code_range = range(int(start, base=16), + int(end, base=16) + 1) + + yield TableEntry(code_range, tuple(properties), comment) + + +def parse_category(fname: str, category_codes: Container) -> TableDef: """Parse value ranges of unicode data files, by given categories into string tables.""" print(f'parsing {fname}: ', end='', flush=True) - version = None - date = None - values: set[int] = set() + with open(fname, encoding='utf-8') as f: - for line in f: - if version is None: - # pull "version string" from first line of source file - version = line.split(None, 1)[1].rstrip() - continue - if date is None: - # and "date string" from second line - date = line.split(':', 1)[1].rstrip() - continue - if line.startswith('#') or not line.lstrip(): - # ignore any further comments or empty lines - continue - addrs, details = line.split(';', 1) - addrs, details = addrs.rstrip(), details.lstrip() - if any(details.startswith(f'{category_code}') - for category_code in category_codes): - if '..' in addrs: - start, stop = addrs.split('..') - else: - start, stop = addrs, addrs - values.update(range(int(start, 16), int(stop, 16) + 1)) + table_iter = parse_unicode_table(f) + + # pull "version string" from first line of source file + version = next(table_iter).comment.strip() + # and "date string" from second line + date = next(table_iter).comment.split(':', 1)[1].strip() + + values: set[int] = set() + for entry in table_iter: + if (entry.code_range is not None + and entry.properties[0] in category_codes): + values.update(entry.code_range) + txt_values = convert_values_to_string_table(make_table(sorted(values))) print('ok') return TableDef(version, date, txt_values) diff --git a/code_templates/python_table.py.j2 b/code_templates/python_table.py.j2 index 8c0e340..3656b39 100644 --- a/code_templates/python_table.py.j2 +++ b/code_templates/python_table.py.j2 @@ -4,12 +4,12 @@ Exports {{ variable_name }} table keyed by supporting unicode version level. This code generated by {{this_filepath}} on {{utc_now}}. """ {{ variable_name }} = { -{%- for table_version, (version_txt, version_date, txt_values) in table.items() %} +{%- for table_version, table_def in table.items() %} '{{ table_version }}': ( - # Source: {{ version_txt }} - # Date: {{ version_date }} + # Source: {{ table_def.filename }} + # Date: {{ table_def.date }} # -{%- for hex_start, hex_end, txt_description in txt_values %} +{%- for hex_start, hex_end, txt_description in table_def.values %} ({{ hex_start }}, {{ hex_end }},), # {{txt_description}} {%- endfor %} ), diff --git a/tox.ini b/tox.ini index e0d570c..db55670 100644 --- a/tox.ini +++ b/tox.ini @@ -23,10 +23,11 @@ import_heading_stdlib = std imports import_heading_thirdparty = 3rd party import_heading_firstparty = local import_heading_localfolder = local -sections=FUTURE,STDLIB,THIRDPARTY,FIRSTPARTY,LOCALFOLDER +sections=FUTURE,STDLIB,TYPING_STDLIB,THIRDPARTY,FIRSTPARTY,LOCALFOLDER no_lines_before=LOCALFOLDER known_first_party = wcwidth known_third_party = codecov,docopt,blessed +known_typing_stdlib = typing,typing_extensions atomic = true [pytest] @@ -41,7 +42,7 @@ junit_family = xunit1 [flake8] exclude = .tox,build max-line-length = 100 -ignore = E402,E501,F401,W503,W504 +ignore = E402,E501,F401,W503,W504 [coverage:run] branch = True From de0a3cd24336182ea893b0b0de109a9e73537617 Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Tue, 22 Mar 2022 03:19:25 +0800 Subject: [PATCH 31/57] Modify `cite_source_description` --- bin/update-tables.py | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 0fb2fdb..6aa473c 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -161,15 +161,14 @@ def render_template(jinja_filename, utc_now=UTC_NOW, this_filepath=THIS_FILEPATH **kwargs) -def cite_source_description(filename): +def cite_source_description(filename: str) -> tuple[str, str]: """Return unicode.org source data file's own description as citation.""" - header_twolines = [ - line.lstrip('# ').rstrip() - for line in open(filename, encoding='utf-8') - .readlines()[:2] - ] - if len(header_twolines) == 2: - return header_twolines + with open(filename, encoding='utf-8') as f: + entry_iter = parse_unicode_table(f) + fname = next(entry_iter).comment.strip() + date = next(entry_iter).comment.strip() + + return fname, date def make_sortable_source_name(filename): From 8fbdf02db0814c4d503199d153c5bc652407b11b Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Tue, 22 Mar 2022 03:47:13 +0800 Subject: [PATCH 32/57] Add some type hints Only a stack is needed in `make_table`, so deque is not necessary, a list is good enough. --- bin/update-tables.py | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 6aa473c..c04f1e3 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -31,7 +31,7 @@ import unicodedata from dataclasses import dataclass -from typing import Iterable, Iterator, Container +from typing import Iterable, Iterator, Container, Collection # 3rd party import jinja2 @@ -171,22 +171,24 @@ def cite_source_description(filename: str) -> tuple[str, str]: return fname, date -def make_sortable_source_name(filename): - # make a sortable filename of unicode text file, - # - # >>> make_sorted_name("DerivedGeneralCategory-5.0.0.txt") - # ('DerivedGeneralCategory', 5, 0, 0) +def make_sortable_source_name(filename: str) -> tuple: + """make a sortable filename of unicode text file + >>> make_sorted_name("DerivedGeneralCategory-5.0.0.txt") + ('DerivedGeneralCategory', 5, 0, 0) + """ basename, remaining = filename.split('-', 1) version_numbers, _extension = os.path.splitext(remaining) return (basename, *list(map(int, version_numbers.split('.')))) -def make_table(values): +def make_table(values: Collection[int]) -> tuple[tuple[int, int], ...]: """Return a tuple of lookup tables for given values.""" - start, end = values[0], values[0] - table = collections.deque() + table: list[tuple[int, int]] = [] + values_iter = iter(values) + start = end = next(values_iter) table.append((start, end)) - for value in values[1:]: + + for value in values_iter: start, end = table.pop() if end == value - 1: # continuation of existing range @@ -199,9 +201,11 @@ def make_table(values): return tuple(table) -def convert_values_to_string_table(values): +def convert_values_to_string_table( + values: Collection[tuple[int, int]], +) -> list[tuple[str, str, str]]: """Convert integers into string table of (hex_start, hex_end, txt_description).""" - pytable_values = [] + pytable_values: list[tuple[str, str, str]] = [] for start, end in values: hex_start, hex_end = (f'0x{start:05x}', f'0x{end:05x}') ucs_start, ucs_end = chr(start), chr(end) From e8771c4e12b6f90b2379d5b73109d3002b2aeae7 Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Sun, 6 Mar 2022 08:07:01 +0800 Subject: [PATCH 33/57] Use regex instead of glob Cherry picked from commit 0a9cdf7 and commit 82f550f (GH-58) --- bin/update-tables.py | 30 ++++++++++++++++++++++-------- 1 file changed, 22 insertions(+), 8 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index c04f1e3..ef834a6 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -22,7 +22,6 @@ import os import re import sys -import glob import string import logging import datetime @@ -120,14 +119,29 @@ def fetch_unicode_versions() -> list[UnicodeVersion]: return versions -def fetch_source_headers(): - glob_pattern = os.path.join(PATH_DATA, '*[0-9]*.txt') - filenames = glob.glob(glob_pattern) - filenames.sort(key=lambda filename: make_sortable_source_name(filename)) - headers = [] +def fetch_source_headers() -> dict[str, list[tuple[str, str]]]: + # find all filenames with a version number in it, + # sort filenames by name, then dotted number, ascending + pattern = re.compile( + r'^(DerivedGeneralCategory|EastAsianWidth)-(\d+)\.(\d+)\.(\d+)\.txt$') + filename_matches = [] + for fname in os.listdir(PATH_DATA): + if match := re.search(pattern, fname): + filename_matches.append(match) + + filename_matches.sort(key = lambda m: ( + m.group(1), + int(m.group(2)), + int(m.group(3)), + int(m.group(4)), + )) + filenames = [os.path.join(PATH_DATA, match.string) + for match in filename_matches] + + headers: list[tuple[str, str]] = [] for filename in filenames: - if header_description := cite_source_description(filename): - headers.append(header_description) + header_description = cite_source_description(filename) + headers.append(header_description) return {'source_headers': headers} From 70d45e574fc422f3ae99c2a44e276a0a89d170b8 Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Tue, 22 Mar 2022 04:27:12 +0800 Subject: [PATCH 34/57] Make sure `THIS_FILENAME` is seperated bt `/` on Windows --- bin/update-tables.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index ef834a6..5b61a48 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -28,6 +28,7 @@ import functools import collections import unicodedata +from pathlib import Path from dataclasses import dataclass from typing import Iterable, Iterator, Container, Collection @@ -45,8 +46,10 @@ PATH_UP = os.path.relpath(os.path.join(os.path.dirname(__file__), os.path.pardir)) PATH_DATA = os.path.join(PATH_UP, 'data') -THIS_FILEPATH = os.path.relpath(__file__, os.path.join( - PATH_UP, os.path.pardir)) # "wcwidth/bin/update-tables.py" +# "wcwidth/bin/update-tables.py", even on Windows +# not really a path, if the git repo isn't named "wcwidth" +THIS_FILEPATH = ('wcwidth/' + + Path(__file__).resolve().relative_to(Path(PATH_UP).resolve()).as_posix()) JINJA_ENV = jinja2.Environment( loader=jinja2.FileSystemLoader(os.path.join(PATH_UP, 'code_templates')), @@ -168,7 +171,7 @@ def fetch_table_zero_data() -> dict: return {'table': table, 'variable_name': 'ZERO_WIDTH'} -def render_template(jinja_filename, utc_now=UTC_NOW, this_filepath=THIS_FILEPATH, **kwargs): +def render_template(jinja_filename, utc_now=UTC_NOW, **kwargs): return JINJA_ENV.get_template(jinja_filename).render( utc_now=utc_now, this_filepath=THIS_FILEPATH, From c161f925dda44fe1ea75993f810721e7fd4e1c3b Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Tue, 22 Mar 2022 07:51:05 +0800 Subject: [PATCH 35/57] Rewrite template rendering by dataclasses --- bin/update-tables.py | 165 ++++++++++++++++++++++++++++++------------- 1 file changed, 116 insertions(+), 49 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 5b61a48..2e2f6b9 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -26,12 +26,11 @@ import logging import datetime import functools -import collections import unicodedata from pathlib import Path -from dataclasses import dataclass +from dataclasses import field, fields, dataclass -from typing import Iterable, Iterator, Container, Collection +from typing import Any, Mapping, Iterable, Iterator, Sequence, Container, Collection # 3rd party import jinja2 @@ -101,8 +100,103 @@ class TableDef: values: list[tuple[str, str, str]] -RenderDefinition = collections.namedtuple( - 'render', ['jinja_filename', 'output_filename', 'fn_data']) +@dataclass(frozen=True) +class RenderContext: + + def to_dict(self) -> dict[str, Any]: + return {field.name: getattr(self, field.name) + for field in fields(self)} + + +@dataclass(frozen=True) +class UnicodeVersionPyRenderCtx(RenderContext): + versions: Collection[UnicodeVersion] + + +@dataclass(frozen=True) +class UnicodeVersionRstRenderCtx(RenderContext): + source_headers: Sequence[tuple[str, str]] + + +@dataclass(frozen=True) +class UnicodeTableRenderCtx(RenderContext): + variable_name: str + table: Mapping[UnicodeVersion, TableDef] + + +@dataclass +class RenderDefinition: + """Base class, do not instantiate it directly.""" + jinja_filename: str + output_filename: str + render_context: RenderContext + + _template: jinja2.Template = field(init=False, repr=False) + _render_context: dict[str, Any] = field(init=False, repr=False) + + def __post_init__(self): + self._template = JINJA_ENV.get_template(self.jinja_filename) + self._render_context = { + 'utc_now': UTC_NOW, + 'this_filepath': THIS_FILEPATH, + **self.render_context.to_dict(), + } + + def render(self) -> str: + """just like jinja2.Template.render""" + return self._template.render(self._render_context) + + def generate(self) -> Iterator[str]: + """just like jinja2.Template.generate""" + return self._template.generate(self._render_context) + + +@dataclass +class UnicodeVersionPyRenderDef(RenderDefinition): + render_context: UnicodeVersionPyRenderCtx + + @classmethod + def new(cls, context: UnicodeVersionPyRenderCtx): + return cls( + jinja_filename='unicode_versions.py.j2', + output_filename=os.path.join(PATH_UP, 'wcwidth', 'unicode_versions.py'), + render_context=context, + ) + + +@dataclass +class UnicodeVersionRstRenderDef(RenderDefinition): + render_context: UnicodeVersionRstRenderCtx + + @classmethod + def new(cls, context: UnicodeVersionRstRenderCtx): + return cls( + jinja_filename='unicode_version.rst.j2', + output_filename=os.path.join(PATH_UP, 'docs', 'unicode_version.rst'), + render_context=context, + ) + + +@dataclass +class UnicodeTableRenderDef(RenderDefinition): + render_context: UnicodeTableRenderCtx + + @classmethod + def new(cls, filename: str, context: UnicodeTableRenderCtx): + _, ext = os.path.splitext(filename) + if ext == '.py': + jinja_filename = 'python_table.py.j2' + elif ext == '.c': + # TODO + jinja_filename = 'c_table.c.j2' + else: + raise ValueError('filename must be a Python or a C file') + + return cls( + jinja_filename=jinja_filename, + output_filename=os.path.join(PATH_UP, 'wcwidth', filename), + render_context=context, + ) @functools.cache @@ -122,7 +216,7 @@ def fetch_unicode_versions() -> list[UnicodeVersion]: return versions -def fetch_source_headers() -> dict[str, list[tuple[str, str]]]: +def fetch_source_headers() -> UnicodeVersionRstRenderCtx: # find all filenames with a version number in it, # sort filenames by name, then dotted number, ascending pattern = re.compile( @@ -145,20 +239,20 @@ def fetch_source_headers() -> dict[str, list[tuple[str, str]]]: for filename in filenames: header_description = cite_source_description(filename) headers.append(header_description) - return {'source_headers': headers} + return UnicodeVersionRstRenderCtx(headers) -def fetch_table_wide_data() -> dict: +def fetch_table_wide_data() -> UnicodeTableRenderCtx: """Fetch and update east-asian tables.""" table: dict[UnicodeVersion, TableDef] = {} for version in fetch_unicode_versions(): fname = os.path.join(PATH_DATA, f'EastAsianWidth-{version}.txt') do_retrieve(url=URL_EASTASIAN_WIDTH.format(version=version), fname=fname) table[version] = parse_category(fname=fname, category_codes=('W', 'F',)) - return {'table': table, 'variable_name': 'WIDE_EASTASIAN'} + return UnicodeTableRenderCtx('WIDE_EASTASIAN', table) -def fetch_table_zero_data() -> dict: +def fetch_table_zero_data() -> UnicodeTableRenderCtx: """Fetch and update zero width tables.""" table: dict[UnicodeVersion, TableDef] = {} for version in fetch_unicode_versions(): @@ -168,14 +262,7 @@ def fetch_table_zero_data() -> dict: # width', or, just the subset 2060..2064, see open issue # https://github.com/jquast/wcwidth/issues/26 table[version] = parse_category(fname=fname, category_codes=('Me', 'Mn',)) - return {'table': table, 'variable_name': 'ZERO_WIDTH'} - - -def render_template(jinja_filename, utc_now=UTC_NOW, **kwargs): - return JINJA_ENV.get_template(jinja_filename).render( - utc_now=utc_now, - this_filepath=THIS_FILEPATH, - **kwargs) + return UnicodeTableRenderCtx('ZERO_WIDTH', table) def cite_source_description(filename: str) -> tuple[str, str]: @@ -188,16 +275,6 @@ def cite_source_description(filename: str) -> tuple[str, str]: return fname, date -def make_sortable_source_name(filename: str) -> tuple: - """make a sortable filename of unicode text file - >>> make_sorted_name("DerivedGeneralCategory-5.0.0.txt") - ('DerivedGeneralCategory', 5, 0, 0) - """ - basename, remaining = filename.split('-', 1) - version_numbers, _extension = os.path.splitext(remaining) - return (basename, *list(map(int, version_numbers.split('.')))) - - def make_table(values: Collection[int]) -> tuple[tuple[int, int], ...]: """Return a tuple of lookup tables for given values.""" table: list[tuple[int, int]] = [] @@ -330,29 +407,19 @@ def main() -> None: # and what function defines the source data. We hope to add more source # language options using jinja2 templates, with minimal modification of the # code. - CODEGEN_DEFINITIONS = [ - RenderDefinition( - jinja_filename='unicode_versions.py.j2', - output_filename=os.path.join(PATH_UP, 'wcwidth', 'unicode_versions.py'), - fn_data=lambda: {'versions': fetch_unicode_versions()}), - RenderDefinition( - jinja_filename='unicode_version.rst.j2', - output_filename=os.path.join(PATH_UP, 'docs', 'unicode_version.rst'), - fn_data=fetch_source_headers), - RenderDefinition( - jinja_filename='python_table.py.j2', - output_filename=os.path.join(PATH_UP, 'wcwidth', 'table_wide.py'), - fn_data=fetch_table_wide_data), - RenderDefinition( - jinja_filename='python_table.py.j2', - output_filename=os.path.join(PATH_UP, 'wcwidth', 'table_zero.py'), - fn_data=fetch_table_zero_data) - ] - for render_def in CODEGEN_DEFINITIONS: + def get_codegen_definitions() -> Iterator[RenderDefinition]: + yield UnicodeVersionPyRenderDef.new( + UnicodeVersionPyRenderCtx(fetch_unicode_versions()) + ) + yield UnicodeVersionRstRenderDef.new(fetch_source_headers()) + yield UnicodeTableRenderDef.new('table_wide.py', fetch_table_wide_data()) + yield UnicodeTableRenderDef.new('table_zero.py', fetch_table_zero_data()) + + for render_def in get_codegen_definitions(): with open(render_def.output_filename, 'w', encoding='utf-8') as fout: - data = render_def.fn_data() print(f'write {render_def.output_filename}: ', flush=True, end='') - fout.write(render_template(render_def.jinja_filename, **data)) + for data in render_def.generate(): + fout.write(data) print('ok') From 5e4ae4a0548b8f5ee3403b1b115e8b80f826678e Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Wed, 22 Jun 2022 19:52:43 -0400 Subject: [PATCH 36/57] prepare 0.2.6 for release, document 0.2.5 --- docs/intro.rst | 12 ++++++++++-- setup.py | 2 +- wcwidth/__init__.py | 11 +---------- 3 files changed, 12 insertions(+), 13 deletions(-) diff --git a/docs/intro.rst b/docs/intro.rst index a4c88ff..f7dac13 100644 --- a/docs/intro.rst +++ b/docs/intro.rst @@ -168,6 +168,16 @@ Other Languages History ------- +0.2.6 *2022-06-022* + * **Updated** tables to include Unicode Specification 14.0.0. + * **Changed** developer tools to use pip-compile, and to use jinja2 templates + for code generation in `bin/update-tables.py` to prepare for possible + compiler optimization release. + +0.2.1 .. 0.2.5 *2020-06-23* + * **Repository** changes to update tests and packaging issues, and + begin tagging repository with matching release versions. + 0.2.0 *2020-06-01* * **Enhancement**: Unicode version may be selected by exporting the Environment variable ``UNICODE_VERSION``, such as ``13.0``, or ``6.3.0``. @@ -177,8 +187,6 @@ History * **Updated** tables for *all* Unicode Specifications with files published in a programmatically consumable format, versions 4.1.0 through 13.0 - that are published - , versions 0.1.9 *2020-03-22* * **Performance** optimization by `Avram Lubkin`_, `PR #35`_. diff --git a/setup.py b/setup.py index 2d3cd47..85c5fef 100755 --- a/setup.py +++ b/setup.py @@ -44,7 +44,7 @@ def main(): setuptools.setup( name='wcwidth', # NOTE: manually manage __version__ in wcwidth/__init__.py ! - version='0.2.5', + version='0.2.6', description=( "Measures the displayed width of unicode strings in a terminal"), long_description=codecs.open( diff --git a/wcwidth/__init__.py b/wcwidth/__init__.py index a9008f8..ec554c3 100644 --- a/wcwidth/__init__.py +++ b/wcwidth/__init__.py @@ -22,16 +22,7 @@ # 'from wcwidth import *', but also to say, "This is the public API". __all__ = ('wcwidth', 'wcswidth', 'list_versions') -# I used to use a _get_package_version() function to use the `pkg_resources' -# module to parse the package version from our version.json file, but this blew -# some folks up, or more particularly, just the `xonsh' shell. -# -# Yikes! I always wanted to like xonsh and tried it many times but issues like -# these always bit me, too, so I can sympathize -- this version is now manually -# kept in sync with version.json to help them out. Shucks, this variable is just -# for legacy, from the days before 'pip freeze' was a thing. -# # We also used pkg_resources to load unicode version tables from version.json, # generated by bin/update-tables.py, but some environments are unable to # import pkg_resources for one reason or another, yikes! -__version__ = '0.2.5' +__version__ = '0.2.6' From 0a7a83fe98443014ed3f6e2c3c89956ac74c2fa0 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Fri, 13 Jan 2023 10:48:17 -0500 Subject: [PATCH 37/57] remove 'tenacity', use requests retry handler --- bin/update-tables.py | 24 +++++++++++++++--------- requirements-update.in | 1 - requirements-update.txt | 2 -- 3 files changed, 15 insertions(+), 12 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 2e2f6b9..9f7b2d8 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -27,6 +27,7 @@ import datetime import functools import unicodedata +import urllib3.util from pathlib import Path from dataclasses import field, fields, dataclass @@ -35,7 +36,6 @@ # 3rd party import jinja2 import requests -import tenacity import dateutil.parser URL_UNICODE_DERIVED_AGE = 'https://www.unicode.org/Public/UCD/latest/ucd/DerivedAge.txt' @@ -58,6 +58,7 @@ CONNECT_TIMEOUT = int(os.environ.get('CONNECT_TIMEOUT', '10')) FETCH_BLOCKSIZE = int(os.environ.get('FETCH_BLOCKSIZE', '4096')) MAX_RETRIES = int(os.environ.get('MAX_RETRIES', '10')) +BACKOFF_FACTOR = float(os.environ.get('BACKOFF_FACTOR', '0.1')) logger = logging.getLogger(__name__) @@ -202,7 +203,7 @@ def new(cls, filename: str, context: UnicodeTableRenderCtx): @functools.cache def fetch_unicode_versions() -> list[UnicodeVersion]: """Fetch, determine, and return Unicode Versions for processing.""" - fname = os.path.join(PATH_DATA, os.path.basename(URL_UNICODE_DERIVED_AGE)) + fname = os.path.join(PATH_DATA, URL_UNICODE_DERIVED_AGE.rsplit('/', 1)[-1]) do_retrieve(url=URL_UNICODE_DERIVED_AGE, fname=fname) pattern = re.compile(r'#.*assigned in Unicode ([0-9.]+)') versions: list[UnicodeVersion] = [] @@ -276,7 +277,11 @@ def cite_source_description(filename: str) -> tuple[str, str]: def make_table(values: Collection[int]) -> tuple[tuple[int, int], ...]: - """Return a tuple of lookup tables for given values.""" + """Return a tuple of lookup tables for given values. + >>> make_table([0,1,2,5,6,7,9]) + ((0, 2), (5, 7), (9, 9)) + + """ table: list[tuple[int, int]] = [] values_iter = iter(values) start = end = next(values_iter) @@ -370,6 +375,7 @@ def is_url_newer(url, fname): if not os.path.exists(fname): return True if '--check-last-modified' in sys.argv[1:]: + # XXX resp = requests.head(url, timeout=CONNECT_TIMEOUT) resp.raise_for_status() remote_url_dt = dateutil.parser.parse(resp.headers['Last-Modified']).astimezone() @@ -378,10 +384,6 @@ def is_url_newer(url, fname): return False -@tenacity.retry(reraise=True, wait=tenacity.wait_none(), - retry=tenacity.retry_if_exception_type(requests.exceptions.RequestException), - stop=tenacity.stop_after_attempt(MAX_RETRIES), - before_sleep=tenacity.before_sleep_log(logger, logging.DEBUG)) def do_retrieve(url, fname): """Retrieve given url to target filepath fname.""" folder = os.path.dirname(fname) @@ -389,13 +391,17 @@ def do_retrieve(url, fname): os.makedirs(folder) if not is_url_newer(url, fname): return - resp = requests.get(url, timeout=CONNECT_TIMEOUT) + session = requests.Session() + retries = urllib3.util.Retry(total=MAX_RETRIES, + backoff_factor=BACKOFF_FACTOR, + status_forcelist=[500, 502, 503, 504]) + session.mount('https://', requests.adapters.HTTPAdapter(max_retries=retries)) + resp = session.get(url, timeout=CONNECT_TIMEOUT) resp.raise_for_status() print(f"saving {fname}: ", end='', flush=True) with open(fname, 'wb') as fout: for chunk in resp.iter_content(FETCH_BLOCKSIZE): fout.write(chunk) - print('.', end='', flush=True) print('ok') diff --git a/requirements-update.in b/requirements-update.in index 6db199e..7225627 100644 --- a/requirements-update.in +++ b/requirements-update.in @@ -1,4 +1,3 @@ jinja2 requests -tenacity python-dateutil diff --git a/requirements-update.txt b/requirements-update.txt index 844da0e..3c26bef 100644 --- a/requirements-update.txt +++ b/requirements-update.txt @@ -20,7 +20,5 @@ requests==2.27.1 # via -r requirements-update.in six==1.16.0 # via python-dateutil -tenacity==8.0.1 - # via -r requirements-update.in urllib3==1.26.9 # via requests From 72109bea759e48f0e16cbfd559b1cdcdcde45ded Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Fri, 13 Jan 2023 10:50:34 -0500 Subject: [PATCH 38/57] small fix of keywords in setup.py --- setup.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/setup.py b/setup.py index 85c5fef..fce95f4 100755 --- a/setup.py +++ b/setup.py @@ -82,7 +82,7 @@ def main(): 'combining', 'console', 'eastasian', - 'emoji' + 'emoji', 'emulator', 'terminal', 'unicode', From a28f45c72810d89e3e680ac848656041ae2298eb Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Fri, 13 Jan 2023 11:01:58 -0500 Subject: [PATCH 39/57] fix combining in wcwidth-browser --- bin/wcwidth-browser.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/bin/wcwidth-browser.py b/bin/wcwidth-browser.py index 4f53960..7d05ba6 100755 --- a/bin/wcwidth-browser.py +++ b/bin/wcwidth-browser.py @@ -117,7 +117,7 @@ def __init__(self, width=1): self.characters = [] letters_o = ('o' * width) last_version = list_versions()[-1] - for (begin, end) in ZERO_WIDTH[last_version].items(): + for (begin, end) in ZERO_WIDTH[last_version]: for val in [_val for _val in range(begin, end + 1) if _val <= LIMIT_UCS]: From a2dc0c99460ec58e96f63ca6e951e24f50b41a48 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Fri, 13 Jan 2023 11:02:27 -0500 Subject: [PATCH 40/57] use '--check-last-modified' in 'tox -e update' --- tox.ini | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tox.ini b/tox.ini index db55670..4f1304b 100644 --- a/tox.ini +++ b/tox.ini @@ -82,7 +82,7 @@ deps = -r requirements-tests38.txt basepython = python3.10 usedevelop = true deps = -r requirements-update.txt -commands = python {toxinidir}/bin/update-tables.py {posargs} +commands = python {toxinidir}/bin/update-tables.py {posargs:--check-last-modified} [testenv:autopep8] basepython = python3.10 From c6210eaf3e95fc36007d560a38cc1f73432817eb Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Fri, 13 Jan 2023 11:02:40 -0500 Subject: [PATCH 41/57] Update latest unicode to to version 15.0 --- wcwidth/table_wide.py | 162 +++++++++++++-- wcwidth/table_zero.py | 384 ++++++++++++++++++++++++++++++++++-- wcwidth/unicode_versions.py | 3 +- 3 files changed, 512 insertions(+), 37 deletions(-) diff --git a/wcwidth/table_wide.py b/wcwidth/table_wide.py index 9a5ffd8..66ef07c 100644 --- a/wcwidth/table_wide.py +++ b/wcwidth/table_wide.py @@ -1,12 +1,12 @@ """ Exports WIDE_EASTASIAN table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2022-03-20 22:43:45 UTC. +This code generated by wcwidth/bin/update-tables.py on 2023-01-13 15:46:31 UTC. """ WIDE_EASTASIAN = { '4.1.0': ( # Source: EastAsianWidth-4.1.0.txt - # Date: 2005-03-17, 15:21:00 PST [KW] + # Date: 2005-03-17, 15:21:00 PST [KW] # (0x01100, 0x01159,), # Hangul Choseong Kiyeok ..Hangul Choseong Yeorinhi (0x0115f, 0x0115f,), # Hangul Choseong Filler @@ -44,7 +44,7 @@ ), '5.0.0': ( # Source: EastAsianWidth-5.0.0.txt - # Date: 2006-02-15, 14:39:00 PST [KW] + # Date: 2006-02-15, 14:39:00 PST [KW] # (0x01100, 0x01159,), # Hangul Choseong Kiyeok ..Hangul Choseong Yeorinhi (0x0115f, 0x0115f,), # Hangul Choseong Filler @@ -82,7 +82,7 @@ ), '5.1.0': ( # Source: EastAsianWidth-5.1.0.txt - # Date: 2008-03-20, 17:42:00 PDT [KW] + # Date: 2008-03-20, 17:42:00 PDT [KW] # (0x01100, 0x01159,), # Hangul Choseong Kiyeok ..Hangul Choseong Yeorinhi (0x0115f, 0x0115f,), # Hangul Choseong Filler @@ -120,7 +120,7 @@ ), '5.2.0': ( # Source: EastAsianWidth-5.2.0.txt - # Date: 2009-06-09, 17:47:00 PDT [KW] + # Date: 2009-06-09, 17:47:00 PDT [KW] # (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x011a3, 0x011a7,), # Hangul Jungseong A-eu ..Hangul Jungseong O-yae @@ -162,7 +162,7 @@ ), '6.0.0': ( # Source: EastAsianWidth-6.0.0.txt - # Date: 2010-08-17, 12:17:00 PDT [KW] + # Date: 2010-08-17, 12:17:00 PDT [KW] # (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x011a3, 0x011a7,), # Hangul Jungseong A-eu ..Hangul Jungseong O-yae @@ -206,7 +206,7 @@ ), '6.1.0': ( # Source: EastAsianWidth-6.1.0.txt - # Date: 2011-09-19, 18:46:00 GMT [KW] + # Date: 2011-09-19, 18:46:00 GMT [KW] # (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x011a3, 0x011a7,), # Hangul Jungseong A-eu ..Hangul Jungseong O-yae @@ -250,7 +250,7 @@ ), '6.2.0': ( # Source: EastAsianWidth-6.2.0.txt - # Date: 2012-05-15, 18:30:00 GMT [KW] + # Date: 2012-05-15, 18:30:00 GMT [KW] # (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra @@ -290,7 +290,7 @@ ), '6.3.0': ( # Source: EastAsianWidth-6.3.0.txt - # Date: 2013-02-05, 20:09:00 GMT [KW, LI] + # Date: 2013-02-05, 20:09:00 GMT [KW, LI] # (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra @@ -330,7 +330,7 @@ ), '7.0.0': ( # Source: EastAsianWidth-7.0.0.txt - # Date: 2014-02-28, 23:15:00 GMT [KW, LI] + # Date: 2014-02-28, 23:15:00 GMT [KW, LI] # (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra @@ -370,7 +370,7 @@ ), '8.0.0': ( # Source: EastAsianWidth-8.0.0.txt - # Date: 2015-02-10, 21:00:00 GMT [KW, LI] + # Date: 2015-02-10, 21:00:00 GMT [KW, LI] # (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra @@ -410,7 +410,7 @@ ), '9.0.0': ( # Source: EastAsianWidth-9.0.0.txt - # Date: 2016-05-27, 17:00:00 GMT [KW, LI] + # Date: 2016-05-27, 17:00:00 GMT [KW, LI] # (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass @@ -521,7 +521,7 @@ ), '10.0.0': ( # Source: EastAsianWidth-10.0.0.txt - # Date: 2017-03-08, 02:00:00 GMT [KW, LI] + # Date: 2017-03-08, 02:00:00 GMT [KW, LI] # (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass @@ -632,7 +632,7 @@ ), '11.0.0': ( # Source: EastAsianWidth-11.0.0.txt - # Date: 2018-05-14, 09:41:59 GMT [KW, LI] + # Date: 2018-05-14, 09:41:59 GMT [KW, LI] # (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass @@ -745,7 +745,7 @@ ), '12.0.0': ( # Source: EastAsianWidth-12.0.0.txt - # Date: 2019-01-21, 14:12:58 GMT [KW, LI] + # Date: 2019-01-21, 14:12:58 GMT [KW, LI] # (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass @@ -864,7 +864,7 @@ ), '12.1.0': ( # Source: EastAsianWidth-12.1.0.txt - # Date: 2019-03-31, 22:01:58 GMT [KW, LI] + # Date: 2019-03-31, 22:01:58 GMT [KW, LI] # (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass @@ -982,7 +982,7 @@ ), '13.0.0': ( # Source: EastAsianWidth-13.0.0.txt - # Date: 2029-01-21, 18:14:00 GMT [KW, LI] + # Date: 2029-01-21, 18:14:00 GMT [KW, LI] # (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass @@ -1103,7 +1103,7 @@ ), '14.0.0': ( # Source: EastAsianWidth-14.0.0.txt - # Date: 2021-07-06, 09:58:53 GMT [KW, LI] + # Date: 2021-07-06, 09:58:53 GMT [KW, LI] # (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler (0x0231a, 0x0231b,), # Watch ..Hourglass @@ -1227,4 +1227,130 @@ (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), + '15.0.0': ( + # Source: EastAsianWidth-15.0.0.txt + # Date: 2022-05-24, 17:40:20 GMT [KW, LI] + # + (0x01100, 0x0115f,), # Hangul Choseong Kiyeok ..Hangul Choseong Filler + (0x0231a, 0x0231b,), # Watch ..Hourglass + (0x02329, 0x0232a,), # Left-pointing Angle Brac..Right-pointing Angle Bra + (0x023e9, 0x023ec,), # Black Right-pointing Dou..Black Down-pointing Doub + (0x023f0, 0x023f0,), # Alarm Clock + (0x023f3, 0x023f3,), # Hourglass With Flowing Sand + (0x025fd, 0x025fe,), # White Medium Small Squar..Black Medium Small Squar + (0x02614, 0x02615,), # Umbrella With Rain Drops..Hot Beverage + (0x02648, 0x02653,), # Aries ..Pisces + (0x0267f, 0x0267f,), # Wheelchair Symbol + (0x02693, 0x02693,), # Anchor + (0x026a1, 0x026a1,), # High Voltage Sign + (0x026aa, 0x026ab,), # Medium White Circle ..Medium Black Circle + (0x026bd, 0x026be,), # Soccer Ball ..Baseball + (0x026c4, 0x026c5,), # Snowman Without Snow ..Sun Behind Cloud + (0x026ce, 0x026ce,), # Ophiuchus + (0x026d4, 0x026d4,), # No Entry + (0x026ea, 0x026ea,), # Church + (0x026f2, 0x026f3,), # Fountain ..Flag In Hole + (0x026f5, 0x026f5,), # Sailboat + (0x026fa, 0x026fa,), # Tent + (0x026fd, 0x026fd,), # Fuel Pump + (0x02705, 0x02705,), # White Heavy Check Mark + (0x0270a, 0x0270b,), # Raised Fist ..Raised Hand + (0x02728, 0x02728,), # Sparkles + (0x0274c, 0x0274c,), # Cross Mark + (0x0274e, 0x0274e,), # Negative Squared Cross Mark + (0x02753, 0x02755,), # Black Question Mark Orna..White Exclamation Mark O + (0x02757, 0x02757,), # Heavy Exclamation Mark Symbol + (0x02795, 0x02797,), # Heavy Plus Sign ..Heavy Division Sign + (0x027b0, 0x027b0,), # Curly Loop + (0x027bf, 0x027bf,), # Double Curly Loop + (0x02b1b, 0x02b1c,), # Black Large Square ..White Large Square + (0x02b50, 0x02b50,), # White Medium Star + (0x02b55, 0x02b55,), # Heavy Large Circle + (0x02e80, 0x02e99,), # Cjk Radical Repeat ..Cjk Radical Rap + (0x02e9b, 0x02ef3,), # Cjk Radical Choke ..Cjk Radical C-simplified + (0x02f00, 0x02fd5,), # Kangxi Radical One ..Kangxi Radical Flute + (0x02ff0, 0x02ffb,), # Ideographic Description ..Ideographic Description + (0x03000, 0x0303e,), # Ideographic Space ..Ideographic Variation In + (0x03041, 0x03096,), # Hiragana Letter Small A ..Hiragana Letter Small Ke + (0x03099, 0x030ff,), # Combining Katakana-hirag..Katakana Digraph Koto + (0x03105, 0x0312f,), # Bopomofo Letter B ..Bopomofo Letter Nn + (0x03131, 0x0318e,), # Hangul Letter Kiyeok ..Hangul Letter Araeae + (0x03190, 0x031e3,), # Ideographic Annotation L..Cjk Stroke Q + (0x031f0, 0x0321e,), # Katakana Letter Small Ku..Parenthesized Korean Cha + (0x03220, 0x03247,), # Parenthesized Ideograph ..Circled Ideograph Koto + (0x03250, 0x04dbf,), # Partnership Sign ..Cjk Unified Ideograph-4d + (0x04e00, 0x0a48c,), # Cjk Unified Ideograph-4e..Yi Syllable Yyr + (0x0a490, 0x0a4c6,), # Yi Radical Qot ..Yi Radical Ke + (0x0a960, 0x0a97c,), # Hangul Choseong Tikeut-m..Hangul Choseong Ssangyeo + (0x0ac00, 0x0d7a3,), # Hangul Syllable Ga ..Hangul Syllable Hih + (0x0f900, 0x0faff,), # Cjk Compatibility Ideogr..(nil) + (0x0fe10, 0x0fe19,), # Presentation Form For Ve..Presentation Form For Ve + (0x0fe30, 0x0fe52,), # Presentation Form For Ve..Small Full Stop + (0x0fe54, 0x0fe66,), # Small Semicolon ..Small Equals Sign + (0x0fe68, 0x0fe6b,), # Small Reverse Solidus ..Small Commercial At + (0x0ff01, 0x0ff60,), # Fullwidth Exclamation Ma..Fullwidth Right White Pa + (0x0ffe0, 0x0ffe6,), # Fullwidth Cent Sign ..Fullwidth Won Sign + (0x16fe0, 0x16fe4,), # Tangut Iteration Mark ..Khitan Small Script Fill + (0x16ff0, 0x16ff1,), # Vietnamese Alternate Rea..Vietnamese Alternate Rea + (0x17000, 0x187f7,), # (nil) + (0x18800, 0x18cd5,), # Tangut Component-001 ..Khitan Small Script Char + (0x18d00, 0x18d08,), # (nil) + (0x1aff0, 0x1aff3,), # (nil) + (0x1aff5, 0x1affb,), # (nil) + (0x1affd, 0x1affe,), # (nil) + (0x1b000, 0x1b122,), # Katakana Letter Archaic ..(nil) + (0x1b132, 0x1b132,), # (nil) + (0x1b150, 0x1b152,), # Hiragana Letter Small Wi..Hiragana Letter Small Wo + (0x1b155, 0x1b155,), # (nil) + (0x1b164, 0x1b167,), # Katakana Letter Small Wi..Katakana Letter Small N + (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb + (0x1f004, 0x1f004,), # Mahjong Tile Red Dragon + (0x1f0cf, 0x1f0cf,), # Playing Card Black Joker + (0x1f18e, 0x1f18e,), # Negative Squared Ab + (0x1f191, 0x1f19a,), # Squared Cl ..Squared Vs + (0x1f200, 0x1f202,), # Square Hiragana Hoka ..Squared Katakana Sa + (0x1f210, 0x1f23b,), # Squared Cjk Unified Ideo..Squared Cjk Unified Ideo + (0x1f240, 0x1f248,), # Tortoise Shell Bracketed..Tortoise Shell Bracketed + (0x1f250, 0x1f251,), # Circled Ideograph Advant..Circled Ideograph Accept + (0x1f260, 0x1f265,), # Rounded Symbol For Fu ..Rounded Symbol For Cai + (0x1f300, 0x1f320,), # Cyclone ..Shooting Star + (0x1f32d, 0x1f335,), # Hot Dog ..Cactus + (0x1f337, 0x1f37c,), # Tulip ..Baby Bottle + (0x1f37e, 0x1f393,), # Bottle With Popping Cork..Graduation Cap + (0x1f3a0, 0x1f3ca,), # Carousel Horse ..Swimmer + (0x1f3cf, 0x1f3d3,), # Cricket Bat And Ball ..Table Tennis Paddle And + (0x1f3e0, 0x1f3f0,), # House Building ..European Castle + (0x1f3f4, 0x1f3f4,), # Waving Black Flag + (0x1f3f8, 0x1f43e,), # Badminton Racquet And Sh..Paw Prints + (0x1f440, 0x1f440,), # Eyes + (0x1f442, 0x1f4fc,), # Ear ..Videocassette + (0x1f4ff, 0x1f53d,), # Prayer Beads ..Down-pointing Small Red + (0x1f54b, 0x1f54e,), # Kaaba ..Menorah With Nine Branch + (0x1f550, 0x1f567,), # Clock Face One Oclock ..Clock Face Twelve-thirty + (0x1f57a, 0x1f57a,), # Man Dancing + (0x1f595, 0x1f596,), # Reversed Hand With Middl..Raised Hand With Part Be + (0x1f5a4, 0x1f5a4,), # Black Heart + (0x1f5fb, 0x1f64f,), # Mount Fuji ..Person With Folded Hands + (0x1f680, 0x1f6c5,), # Rocket ..Left Luggage + (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation + (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley + (0x1f6d5, 0x1f6d7,), # Hindu Temple ..Elevator + (0x1f6dc, 0x1f6df,), # (nil) + (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving + (0x1f6f4, 0x1f6fc,), # Scooter ..Roller Skate + (0x1f7e0, 0x1f7eb,), # Large Orange Circle ..Large Brown Square + (0x1f7f0, 0x1f7f0,), # (nil) + (0x1f90c, 0x1f93a,), # Pinched Fingers ..Fencer + (0x1f93c, 0x1f945,), # Wrestlers ..Goal Net + (0x1f947, 0x1f9ff,), # First Place Medal ..Nazar Amulet + (0x1fa70, 0x1fa7c,), # Ballet Shoes ..(nil) + (0x1fa80, 0x1fa88,), # Yo-yo ..(nil) + (0x1fa90, 0x1fabd,), # Ringed Planet ..(nil) + (0x1fabf, 0x1fac5,), # (nil) + (0x1face, 0x1fadb,), # (nil) + (0x1fae0, 0x1fae8,), # (nil) + (0x1faf0, 0x1faf8,), # (nil) + (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) + (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) + ), } diff --git a/wcwidth/table_zero.py b/wcwidth/table_zero.py index 48b2b04..d55c4c5 100644 --- a/wcwidth/table_zero.py +++ b/wcwidth/table_zero.py @@ -1,12 +1,12 @@ """ Exports ZERO_WIDTH table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2022-03-20 22:43:45 UTC. +This code generated by wcwidth/bin/update-tables.py on 2023-01-13 15:46:31 UTC. """ ZERO_WIDTH = { '4.1.0': ( # Source: DerivedGeneralCategory-4.1.0.txt - # Date: 2005-02-26, 02:35:50 GMT [MD] + # Date: 2005-02-26, 02:35:50 GMT [MD] # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00486,), # Combining Cyrillic Titlo..Combining Cyrillic Psili @@ -134,7 +134,7 @@ ), '5.0.0': ( # Source: DerivedGeneralCategory-5.0.0.txt - # Date: 2006-02-27, 23:41:27 GMT [MD] + # Date: 2006-02-27, 23:41:27 GMT [MD] # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00486,), # Combining Cyrillic Titlo..Combining Cyrillic Psili @@ -270,7 +270,7 @@ ), '5.1.0': ( # Source: DerivedGeneralCategory-5.1.0.txt - # Date: 2008-03-20, 17:54:57 GMT [MD] + # Date: 2008-03-20, 17:54:57 GMT [MD] # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -433,7 +433,7 @@ ), '5.2.0': ( # Source: DerivedGeneralCategory-5.2.0.txt - # Date: 2009-08-22, 04:58:21 GMT [MD] + # Date: 2009-08-22, 04:58:21 GMT [MD] # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -630,7 +630,7 @@ ), '6.0.0': ( # Source: DerivedGeneralCategory-6.0.0.txt - # Date: 2010-08-19, 00:48:09 GMT [MD] + # Date: 2010-08-19, 00:48:09 GMT [MD] # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -836,7 +836,7 @@ ), '6.1.0': ( # Source: DerivedGeneralCategory-6.1.0.txt - # Date: 2011-11-27, 05:10:22 GMT [MD] + # Date: 2011-11-27, 05:10:22 GMT [MD] # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -1059,7 +1059,7 @@ ), '6.2.0': ( # Source: DerivedGeneralCategory-6.2.0.txt - # Date: 2012-05-20, 00:42:34 GMT [MD] + # Date: 2012-05-20, 00:42:34 GMT [MD] # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -1282,7 +1282,7 @@ ), '6.3.0': ( # Source: DerivedGeneralCategory-6.3.0.txt - # Date: 2013-07-05, 14:08:45 GMT [MD] + # Date: 2013-07-05, 14:08:45 GMT [MD] # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -1506,7 +1506,7 @@ ), '7.0.0': ( # Source: DerivedGeneralCategory-7.0.0.txt - # Date: 2014-02-07, 18:42:12 GMT [MD] + # Date: 2014-02-07, 18:42:12 GMT [MD] # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -1764,7 +1764,7 @@ ), '8.0.0': ( # Source: DerivedGeneralCategory-8.0.0.txt - # Date: 2015-02-13, 13:47:11 GMT [MD] + # Date: 2015-02-13, 13:47:11 GMT [MD] # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -2033,7 +2033,7 @@ ), '9.0.0': ( # Source: DerivedGeneralCategory-9.0.0.txt - # Date: 2016-06-01, 10:34:26 GMT + # Date: 2016-06-01, 10:34:26 GMT # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -2321,7 +2321,7 @@ ), '10.0.0': ( # Source: DerivedGeneralCategory-10.0.0.txt - # Date: 2017-03-08, 08:41:49 GMT + # Date: 2017-03-08, 08:41:49 GMT # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -2625,7 +2625,7 @@ ), '11.0.0': ( # Source: DerivedGeneralCategory-11.0.0.txt - # Date: 2018-02-21, 05:34:04 GMT + # Date: 2018-02-21, 05:34:04 GMT # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -2941,7 +2941,7 @@ ), '12.0.0': ( # Source: DerivedGeneralCategory-12.0.0.txt - # Date: 2019-01-22, 08:18:28 GMT + # Date: 2019-01-22, 08:18:28 GMT # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -3262,7 +3262,7 @@ ), '12.1.0': ( # Source: DerivedGeneralCategory-12.1.0.txt - # Date: 2019-03-10, 10:53:08 GMT + # Date: 2019-03-10, 10:53:08 GMT # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -3583,7 +3583,7 @@ ), '13.0.0': ( # Source: DerivedGeneralCategory-13.0.0.txt - # Date: 2019-10-21, 14:30:32 GMT + # Date: 2019-10-21, 14:30:32 GMT # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -3912,7 +3912,7 @@ ), '14.0.0': ( # Source: DerivedGeneralCategory-14.0.0.txt - # Date: 2021-07-10, 00:35:08 GMT + # Date: 2021-07-10, 00:35:08 GMT # (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli @@ -4248,4 +4248,352 @@ (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 ), + '15.0.0': ( + # Source: DerivedGeneralCategory-15.0.0.txt + # Date: 2022-04-26, 23:14:35 GMT + # + (0x00300, 0x0036f,), # Combining Grave Accent ..Combining Latin Small Le + (0x00483, 0x00489,), # Combining Cyrillic Titlo..Combining Cyrillic Milli + (0x00591, 0x005bd,), # Hebrew Accent Etnahta ..Hebrew Point Meteg + (0x005bf, 0x005bf,), # Hebrew Point Rafe + (0x005c1, 0x005c2,), # Hebrew Point Shin Dot ..Hebrew Point Sin Dot + (0x005c4, 0x005c5,), # Hebrew Mark Upper Dot ..Hebrew Mark Lower Dot + (0x005c7, 0x005c7,), # Hebrew Point Qamats Qatan + (0x00610, 0x0061a,), # Arabic Sign Sallallahou ..Arabic Small Kasra + (0x0064b, 0x0065f,), # Arabic Fathatan ..Arabic Wavy Hamza Below + (0x00670, 0x00670,), # Arabic Letter Superscript Alef + (0x006d6, 0x006dc,), # Arabic Small High Ligatu..Arabic Small High Seen + (0x006df, 0x006e4,), # Arabic Small High Rounde..Arabic Small High Madda + (0x006e7, 0x006e8,), # Arabic Small High Yeh ..Arabic Small High Noon + (0x006ea, 0x006ed,), # Arabic Empty Centre Low ..Arabic Small Low Meem + (0x00711, 0x00711,), # Syriac Letter Superscript Alaph + (0x00730, 0x0074a,), # Syriac Pthaha Above ..Syriac Barrekh + (0x007a6, 0x007b0,), # Thaana Abafili ..Thaana Sukun + (0x007eb, 0x007f3,), # Nko Combining Short High..Nko Combining Double Dot + (0x007fd, 0x007fd,), # Nko Dantayalan + (0x00816, 0x00819,), # Samaritan Mark In ..Samaritan Mark Dagesh + (0x0081b, 0x00823,), # Samaritan Mark Epentheti..Samaritan Vowel Sign A + (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U + (0x00829, 0x0082d,), # Samaritan Vowel Sign Lon..Samaritan Mark Nequdaa + (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark + (0x00898, 0x0089f,), # (nil) + (0x008ca, 0x008e1,), # (nil) ..Arabic Small High Sign S + (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara + (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe + (0x0093c, 0x0093c,), # Devanagari Sign Nukta + (0x00941, 0x00948,), # Devanagari Vowel Sign U ..Devanagari Vowel Sign Ai + (0x0094d, 0x0094d,), # Devanagari Sign Virama + (0x00951, 0x00957,), # Devanagari Stress Sign U..Devanagari Vowel Sign Uu + (0x00962, 0x00963,), # Devanagari Vowel Sign Vo..Devanagari Vowel Sign Vo + (0x00981, 0x00981,), # Bengali Sign Candrabindu + (0x009bc, 0x009bc,), # Bengali Sign Nukta + (0x009c1, 0x009c4,), # Bengali Vowel Sign U ..Bengali Vowel Sign Vocal + (0x009cd, 0x009cd,), # Bengali Sign Virama + (0x009e2, 0x009e3,), # Bengali Vowel Sign Vocal..Bengali Vowel Sign Vocal + (0x009fe, 0x009fe,), # Bengali Sandhi Mark + (0x00a01, 0x00a02,), # Gurmukhi Sign Adak Bindi..Gurmukhi Sign Bindi + (0x00a3c, 0x00a3c,), # Gurmukhi Sign Nukta + (0x00a41, 0x00a42,), # Gurmukhi Vowel Sign U ..Gurmukhi Vowel Sign Uu + (0x00a47, 0x00a48,), # Gurmukhi Vowel Sign Ee ..Gurmukhi Vowel Sign Ai + (0x00a4b, 0x00a4d,), # Gurmukhi Vowel Sign Oo ..Gurmukhi Sign Virama + (0x00a51, 0x00a51,), # Gurmukhi Sign Udaat + (0x00a70, 0x00a71,), # Gurmukhi Tippi ..Gurmukhi Addak + (0x00a75, 0x00a75,), # Gurmukhi Sign Yakash + (0x00a81, 0x00a82,), # Gujarati Sign Candrabind..Gujarati Sign Anusvara + (0x00abc, 0x00abc,), # Gujarati Sign Nukta + (0x00ac1, 0x00ac5,), # Gujarati Vowel Sign U ..Gujarati Vowel Sign Cand + (0x00ac7, 0x00ac8,), # Gujarati Vowel Sign E ..Gujarati Vowel Sign Ai + (0x00acd, 0x00acd,), # Gujarati Sign Virama + (0x00ae2, 0x00ae3,), # Gujarati Vowel Sign Voca..Gujarati Vowel Sign Voca + (0x00afa, 0x00aff,), # Gujarati Sign Sukun ..Gujarati Sign Two-circle + (0x00b01, 0x00b01,), # Oriya Sign Candrabindu + (0x00b3c, 0x00b3c,), # Oriya Sign Nukta + (0x00b3f, 0x00b3f,), # Oriya Vowel Sign I + (0x00b41, 0x00b44,), # Oriya Vowel Sign U ..Oriya Vowel Sign Vocalic + (0x00b4d, 0x00b4d,), # Oriya Sign Virama + (0x00b55, 0x00b56,), # Oriya Sign Overline ..Oriya Ai Length Mark + (0x00b62, 0x00b63,), # Oriya Vowel Sign Vocalic..Oriya Vowel Sign Vocalic + (0x00b82, 0x00b82,), # Tamil Sign Anusvara + (0x00bc0, 0x00bc0,), # Tamil Vowel Sign Ii + (0x00bcd, 0x00bcd,), # Tamil Sign Virama + (0x00c00, 0x00c00,), # Telugu Sign Combining Candrabindu Above + (0x00c04, 0x00c04,), # Telugu Sign Combining Anusvara Above + (0x00c3c, 0x00c3c,), # (nil) + (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii + (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai + (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama + (0x00c55, 0x00c56,), # Telugu Length Mark ..Telugu Ai Length Mark + (0x00c62, 0x00c63,), # Telugu Vowel Sign Vocali..Telugu Vowel Sign Vocali + (0x00c81, 0x00c81,), # Kannada Sign Candrabindu + (0x00cbc, 0x00cbc,), # Kannada Sign Nukta + (0x00cbf, 0x00cbf,), # Kannada Vowel Sign I + (0x00cc6, 0x00cc6,), # Kannada Vowel Sign E + (0x00ccc, 0x00ccd,), # Kannada Vowel Sign Au ..Kannada Sign Virama + (0x00ce2, 0x00ce3,), # Kannada Vowel Sign Vocal..Kannada Vowel Sign Vocal + (0x00d00, 0x00d01,), # Malayalam Sign Combining..Malayalam Sign Candrabin + (0x00d3b, 0x00d3c,), # Malayalam Sign Vertical ..Malayalam Sign Circular + (0x00d41, 0x00d44,), # Malayalam Vowel Sign U ..Malayalam Vowel Sign Voc + (0x00d4d, 0x00d4d,), # Malayalam Sign Virama + (0x00d62, 0x00d63,), # Malayalam Vowel Sign Voc..Malayalam Vowel Sign Voc + (0x00d81, 0x00d81,), # Sinhala Sign Candrabindu + (0x00dca, 0x00dca,), # Sinhala Sign Al-lakuna + (0x00dd2, 0x00dd4,), # Sinhala Vowel Sign Ketti..Sinhala Vowel Sign Ketti + (0x00dd6, 0x00dd6,), # Sinhala Vowel Sign Diga Paa-pilla + (0x00e31, 0x00e31,), # Thai Character Mai Han-akat + (0x00e34, 0x00e3a,), # Thai Character Sara I ..Thai Character Phinthu + (0x00e47, 0x00e4e,), # Thai Character Maitaikhu..Thai Character Yamakkan + (0x00eb1, 0x00eb1,), # Lao Vowel Sign Mai Kan + (0x00eb4, 0x00ebc,), # Lao Vowel Sign I ..Lao Semivowel Sign Lo + (0x00ec8, 0x00ece,), # Lao Tone Mai Ek ..(nil) + (0x00f18, 0x00f19,), # Tibetan Astrological Sig..Tibetan Astrological Sig + (0x00f35, 0x00f35,), # Tibetan Mark Ngas Bzung Nyi Zla + (0x00f37, 0x00f37,), # Tibetan Mark Ngas Bzung Sgor Rtags + (0x00f39, 0x00f39,), # Tibetan Mark Tsa -phru + (0x00f71, 0x00f7e,), # Tibetan Vowel Sign Aa ..Tibetan Sign Rjes Su Nga + (0x00f80, 0x00f84,), # Tibetan Vowel Sign Rever..Tibetan Mark Halanta + (0x00f86, 0x00f87,), # Tibetan Sign Lci Rtags ..Tibetan Sign Yang Rtags + (0x00f8d, 0x00f97,), # Tibetan Subjoined Sign L..Tibetan Subjoined Letter + (0x00f99, 0x00fbc,), # Tibetan Subjoined Letter..Tibetan Subjoined Letter + (0x00fc6, 0x00fc6,), # Tibetan Symbol Padma Gdan + (0x0102d, 0x01030,), # Myanmar Vowel Sign I ..Myanmar Vowel Sign Uu + (0x01032, 0x01037,), # Myanmar Vowel Sign Ai ..Myanmar Sign Dot Below + (0x01039, 0x0103a,), # Myanmar Sign Virama ..Myanmar Sign Asat + (0x0103d, 0x0103e,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M + (0x01058, 0x01059,), # Myanmar Vowel Sign Vocal..Myanmar Vowel Sign Vocal + (0x0105e, 0x01060,), # Myanmar Consonant Sign M..Myanmar Consonant Sign M + (0x01071, 0x01074,), # Myanmar Vowel Sign Geba ..Myanmar Vowel Sign Kayah + (0x01082, 0x01082,), # Myanmar Consonant Sign Shan Medial Wa + (0x01085, 0x01086,), # Myanmar Vowel Sign Shan ..Myanmar Vowel Sign Shan + (0x0108d, 0x0108d,), # Myanmar Sign Shan Council Emphatic Tone + (0x0109d, 0x0109d,), # Myanmar Vowel Sign Aiton Ai + (0x0135d, 0x0135f,), # Ethiopic Combining Gemin..Ethiopic Combining Gemin + (0x01712, 0x01714,), # Tagalog Vowel Sign I ..Tagalog Sign Virama + (0x01732, 0x01733,), # Hanunoo Vowel Sign I ..Hanunoo Vowel Sign U + (0x01752, 0x01753,), # Buhid Vowel Sign I ..Buhid Vowel Sign U + (0x01772, 0x01773,), # Tagbanwa Vowel Sign I ..Tagbanwa Vowel Sign U + (0x017b4, 0x017b5,), # Khmer Vowel Inherent Aq ..Khmer Vowel Inherent Aa + (0x017b7, 0x017bd,), # Khmer Vowel Sign I ..Khmer Vowel Sign Ua + (0x017c6, 0x017c6,), # Khmer Sign Nikahit + (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat + (0x017dd, 0x017dd,), # Khmer Sign Atthacan + (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation + (0x0180f, 0x0180f,), # (nil) + (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal + (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga + (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U + (0x01927, 0x01928,), # Limbu Vowel Sign E ..Limbu Vowel Sign O + (0x01932, 0x01932,), # Limbu Small Letter Anusvara + (0x01939, 0x0193b,), # Limbu Sign Mukphreng ..Limbu Sign Sa-i + (0x01a17, 0x01a18,), # Buginese Vowel Sign I ..Buginese Vowel Sign U + (0x01a1b, 0x01a1b,), # Buginese Vowel Sign Ae + (0x01a56, 0x01a56,), # Tai Tham Consonant Sign Medial La + (0x01a58, 0x01a5e,), # Tai Tham Sign Mai Kang L..Tai Tham Consonant Sign + (0x01a60, 0x01a60,), # Tai Tham Sign Sakot + (0x01a62, 0x01a62,), # Tai Tham Vowel Sign Mai Sat + (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B + (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue + (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot + (0x01ab0, 0x01ace,), # Combining Doubled Circum..(nil) + (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang + (0x01b34, 0x01b34,), # Balinese Sign Rerekan + (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R + (0x01b3c, 0x01b3c,), # Balinese Vowel Sign La Lenga + (0x01b42, 0x01b42,), # Balinese Vowel Sign Pepet + (0x01b6b, 0x01b73,), # Balinese Musical Symbol ..Balinese Musical Symbol + (0x01b80, 0x01b81,), # Sundanese Sign Panyecek ..Sundanese Sign Panglayar + (0x01ba2, 0x01ba5,), # Sundanese Consonant Sign..Sundanese Vowel Sign Pan + (0x01ba8, 0x01ba9,), # Sundanese Vowel Sign Pam..Sundanese Vowel Sign Pan + (0x01bab, 0x01bad,), # Sundanese Sign Virama ..Sundanese Consonant Sign + (0x01be6, 0x01be6,), # Batak Sign Tompi + (0x01be8, 0x01be9,), # Batak Vowel Sign Pakpak ..Batak Vowel Sign Ee + (0x01bed, 0x01bed,), # Batak Vowel Sign Karo O + (0x01bef, 0x01bf1,), # Batak Vowel Sign U For S..Batak Consonant Sign H + (0x01c2c, 0x01c33,), # Lepcha Vowel Sign E ..Lepcha Consonant Sign T + (0x01c36, 0x01c37,), # Lepcha Sign Ran ..Lepcha Sign Nukta + (0x01cd0, 0x01cd2,), # Vedic Tone Karshana ..Vedic Tone Prenkha + (0x01cd4, 0x01ce0,), # Vedic Sign Yajurvedic Mi..Vedic Tone Rigvedic Kash + (0x01ce2, 0x01ce8,), # Vedic Sign Visarga Svari..Vedic Sign Visarga Anuda + (0x01ced, 0x01ced,), # Vedic Sign Tiryak + (0x01cf4, 0x01cf4,), # Vedic Tone Candra Above + (0x01cf8, 0x01cf9,), # Vedic Tone Ring Above ..Vedic Tone Double Ring A + (0x01dc0, 0x01dff,), # Combining Dotted Grave A..Combining Right Arrowhea + (0x020d0, 0x020f0,), # Combining Left Harpoon A..Combining Asterisk Above + (0x02cef, 0x02cf1,), # Coptic Combining Ni Abov..Coptic Combining Spiritu + (0x02d7f, 0x02d7f,), # Tifinagh Consonant Joiner + (0x02de0, 0x02dff,), # Combining Cyrillic Lette..Combining Cyrillic Lette + (0x0302a, 0x0302d,), # Ideographic Level Tone M..Ideographic Entering Ton + (0x03099, 0x0309a,), # Combining Katakana-hirag..Combining Katakana-hirag + (0x0a66f, 0x0a672,), # Combining Cyrillic Vzmet..Combining Cyrillic Thous + (0x0a674, 0x0a67d,), # Combining Cyrillic Lette..Combining Cyrillic Payer + (0x0a69e, 0x0a69f,), # Combining Cyrillic Lette..Combining Cyrillic Lette + (0x0a6f0, 0x0a6f1,), # Bamum Combining Mark Koq..Bamum Combining Mark Tuk + (0x0a802, 0x0a802,), # Syloti Nagri Sign Dvisvara + (0x0a806, 0x0a806,), # Syloti Nagri Sign Hasanta + (0x0a80b, 0x0a80b,), # Syloti Nagri Sign Anusvara + (0x0a825, 0x0a826,), # Syloti Nagri Vowel Sign ..Syloti Nagri Vowel Sign + (0x0a82c, 0x0a82c,), # Syloti Nagri Sign Alternate Hasanta + (0x0a8c4, 0x0a8c5,), # Saurashtra Sign Virama ..Saurashtra Sign Candrabi + (0x0a8e0, 0x0a8f1,), # Combining Devanagari Dig..Combining Devanagari Sig + (0x0a8ff, 0x0a8ff,), # Devanagari Vowel Sign Ay + (0x0a926, 0x0a92d,), # Kayah Li Vowel Ue ..Kayah Li Tone Calya Plop + (0x0a947, 0x0a951,), # Rejang Vowel Sign I ..Rejang Consonant Sign R + (0x0a980, 0x0a982,), # Javanese Sign Panyangga ..Javanese Sign Layar + (0x0a9b3, 0x0a9b3,), # Javanese Sign Cecak Telu + (0x0a9b6, 0x0a9b9,), # Javanese Vowel Sign Wulu..Javanese Vowel Sign Suku + (0x0a9bc, 0x0a9bd,), # Javanese Vowel Sign Pepe..Javanese Consonant Sign + (0x0a9e5, 0x0a9e5,), # Myanmar Sign Shan Saw + (0x0aa29, 0x0aa2e,), # Cham Vowel Sign Aa ..Cham Vowel Sign Oe + (0x0aa31, 0x0aa32,), # Cham Vowel Sign Au ..Cham Vowel Sign Ue + (0x0aa35, 0x0aa36,), # Cham Consonant Sign La ..Cham Consonant Sign Wa + (0x0aa43, 0x0aa43,), # Cham Consonant Sign Final Ng + (0x0aa4c, 0x0aa4c,), # Cham Consonant Sign Final M + (0x0aa7c, 0x0aa7c,), # Myanmar Sign Tai Laing Tone-2 + (0x0aab0, 0x0aab0,), # Tai Viet Mai Kang + (0x0aab2, 0x0aab4,), # Tai Viet Vowel I ..Tai Viet Vowel U + (0x0aab7, 0x0aab8,), # Tai Viet Mai Khit ..Tai Viet Vowel Ia + (0x0aabe, 0x0aabf,), # Tai Viet Vowel Am ..Tai Viet Tone Mai Ek + (0x0aac1, 0x0aac1,), # Tai Viet Tone Mai Tho + (0x0aaec, 0x0aaed,), # Meetei Mayek Vowel Sign ..Meetei Mayek Vowel Sign + (0x0aaf6, 0x0aaf6,), # Meetei Mayek Virama + (0x0abe5, 0x0abe5,), # Meetei Mayek Vowel Sign Anap + (0x0abe8, 0x0abe8,), # Meetei Mayek Vowel Sign Unap + (0x0abed, 0x0abed,), # Meetei Mayek Apun Iyek + (0x0fb1e, 0x0fb1e,), # Hebrew Point Judeo-spanish Varika + (0x0fe00, 0x0fe0f,), # Variation Selector-1 ..Variation Selector-16 + (0x0fe20, 0x0fe2f,), # Combining Ligature Left ..Combining Cyrillic Titlo + (0x101fd, 0x101fd,), # Phaistos Disc Sign Combining Oblique Stroke + (0x102e0, 0x102e0,), # Coptic Epact Thousands Mark + (0x10376, 0x1037a,), # Combining Old Permic Let..Combining Old Permic Let + (0x10a01, 0x10a03,), # Kharoshthi Vowel Sign I ..Kharoshthi Vowel Sign Vo + (0x10a05, 0x10a06,), # Kharoshthi Vowel Sign E ..Kharoshthi Vowel Sign O + (0x10a0c, 0x10a0f,), # Kharoshthi Vowel Length ..Kharoshthi Sign Visarga + (0x10a38, 0x10a3a,), # Kharoshthi Sign Bar Abov..Kharoshthi Sign Dot Belo + (0x10a3f, 0x10a3f,), # Kharoshthi Virama + (0x10ae5, 0x10ae6,), # Manichaean Abbreviation ..Manichaean Abbreviation + (0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas + (0x10eab, 0x10eac,), # Yezidi Combining Hamza M..Yezidi Combining Madda M + (0x10efd, 0x10eff,), # (nil) + (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke + (0x10f82, 0x10f85,), # (nil) + (0x11001, 0x11001,), # Brahmi Sign Anusvara + (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama + (0x11070, 0x11070,), # (nil) + (0x11073, 0x11074,), # (nil) + (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara + (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai + (0x110b9, 0x110ba,), # Kaithi Sign Virama ..Kaithi Sign Nukta + (0x110c2, 0x110c2,), # (nil) + (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga + (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu + (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa + (0x11173, 0x11173,), # Mahajani Sign Nukta + (0x11180, 0x11181,), # Sharada Sign Candrabindu..Sharada Sign Anusvara + (0x111b6, 0x111be,), # Sharada Vowel Sign U ..Sharada Vowel Sign O + (0x111c9, 0x111cc,), # Sharada Sandhi Mark ..Sharada Extra Short Vowe + (0x111cf, 0x111cf,), # Sharada Sign Inverted Candrabindu + (0x1122f, 0x11231,), # Khojki Vowel Sign U ..Khojki Vowel Sign Ai + (0x11234, 0x11234,), # Khojki Sign Anusvara + (0x11236, 0x11237,), # Khojki Sign Nukta ..Khojki Sign Shadda + (0x1123e, 0x1123e,), # Khojki Sign Sukun + (0x11241, 0x11241,), # (nil) + (0x112df, 0x112df,), # Khudawadi Sign Anusvara + (0x112e3, 0x112ea,), # Khudawadi Vowel Sign U ..Khudawadi Sign Virama + (0x11300, 0x11301,), # Grantha Sign Combining A..Grantha Sign Candrabindu + (0x1133b, 0x1133c,), # Combining Bindu Below ..Grantha Sign Nukta + (0x11340, 0x11340,), # Grantha Vowel Sign Ii + (0x11366, 0x1136c,), # Combining Grantha Digit ..Combining Grantha Digit + (0x11370, 0x11374,), # Combining Grantha Letter..Combining Grantha Letter + (0x11438, 0x1143f,), # Newa Vowel Sign U ..Newa Vowel Sign Ai + (0x11442, 0x11444,), # Newa Sign Virama ..Newa Sign Anusvara + (0x11446, 0x11446,), # Newa Sign Nukta + (0x1145e, 0x1145e,), # Newa Sandhi Mark + (0x114b3, 0x114b8,), # Tirhuta Vowel Sign U ..Tirhuta Vowel Sign Vocal + (0x114ba, 0x114ba,), # Tirhuta Vowel Sign Short E + (0x114bf, 0x114c0,), # Tirhuta Sign Candrabindu..Tirhuta Sign Anusvara + (0x114c2, 0x114c3,), # Tirhuta Sign Virama ..Tirhuta Sign Nukta + (0x115b2, 0x115b5,), # Siddham Vowel Sign U ..Siddham Vowel Sign Vocal + (0x115bc, 0x115bd,), # Siddham Sign Candrabindu..Siddham Sign Anusvara + (0x115bf, 0x115c0,), # Siddham Sign Virama ..Siddham Sign Nukta + (0x115dc, 0x115dd,), # Siddham Vowel Sign Alter..Siddham Vowel Sign Alter + (0x11633, 0x1163a,), # Modi Vowel Sign U ..Modi Vowel Sign Ai + (0x1163d, 0x1163d,), # Modi Sign Anusvara + (0x1163f, 0x11640,), # Modi Sign Virama ..Modi Sign Ardhacandra + (0x116ab, 0x116ab,), # Takri Sign Anusvara + (0x116ad, 0x116ad,), # Takri Vowel Sign Aa + (0x116b0, 0x116b5,), # Takri Vowel Sign U ..Takri Vowel Sign Au + (0x116b7, 0x116b7,), # Takri Sign Nukta + (0x1171d, 0x1171f,), # Ahom Consonant Sign Medi..Ahom Consonant Sign Medi + (0x11722, 0x11725,), # Ahom Vowel Sign I ..Ahom Vowel Sign Uu + (0x11727, 0x1172b,), # Ahom Vowel Sign Aw ..Ahom Sign Killer + (0x1182f, 0x11837,), # Dogra Vowel Sign U ..Dogra Sign Anusvara + (0x11839, 0x1183a,), # Dogra Sign Virama ..Dogra Sign Nukta + (0x1193b, 0x1193c,), # Dives Akuru Sign Anusvar..Dives Akuru Sign Candrab + (0x1193e, 0x1193e,), # Dives Akuru Virama + (0x11943, 0x11943,), # Dives Akuru Sign Nukta + (0x119d4, 0x119d7,), # Nandinagari Vowel Sign U..Nandinagari Vowel Sign V + (0x119da, 0x119db,), # Nandinagari Vowel Sign E..Nandinagari Vowel Sign A + (0x119e0, 0x119e0,), # Nandinagari Sign Virama + (0x11a01, 0x11a0a,), # Zanabazar Square Vowel S..Zanabazar Square Vowel L + (0x11a33, 0x11a38,), # Zanabazar Square Final C..Zanabazar Square Sign An + (0x11a3b, 0x11a3e,), # Zanabazar Square Cluster..Zanabazar Square Cluster + (0x11a47, 0x11a47,), # Zanabazar Square Subjoiner + (0x11a51, 0x11a56,), # Soyombo Vowel Sign I ..Soyombo Vowel Sign Oe + (0x11a59, 0x11a5b,), # Soyombo Vowel Sign Vocal..Soyombo Vowel Length Mar + (0x11a8a, 0x11a96,), # Soyombo Final Consonant ..Soyombo Sign Anusvara + (0x11a98, 0x11a99,), # Soyombo Gemination Mark ..Soyombo Subjoiner + (0x11c30, 0x11c36,), # Bhaiksuki Vowel Sign I ..Bhaiksuki Vowel Sign Voc + (0x11c38, 0x11c3d,), # Bhaiksuki Vowel Sign E ..Bhaiksuki Sign Anusvara + (0x11c3f, 0x11c3f,), # Bhaiksuki Sign Virama + (0x11c92, 0x11ca7,), # Marchen Subjoined Letter..Marchen Subjoined Letter + (0x11caa, 0x11cb0,), # Marchen Subjoined Letter..Marchen Vowel Sign Aa + (0x11cb2, 0x11cb3,), # Marchen Vowel Sign U ..Marchen Vowel Sign E + (0x11cb5, 0x11cb6,), # Marchen Sign Anusvara ..Marchen Sign Candrabindu + (0x11d31, 0x11d36,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign + (0x11d3a, 0x11d3a,), # Masaram Gondi Vowel Sign E + (0x11d3c, 0x11d3d,), # Masaram Gondi Vowel Sign..Masaram Gondi Vowel Sign + (0x11d3f, 0x11d45,), # Masaram Gondi Vowel Sign..Masaram Gondi Virama + (0x11d47, 0x11d47,), # Masaram Gondi Ra-kara + (0x11d90, 0x11d91,), # Gunjala Gondi Vowel Sign..Gunjala Gondi Vowel Sign + (0x11d95, 0x11d95,), # Gunjala Gondi Sign Anusvara + (0x11d97, 0x11d97,), # Gunjala Gondi Virama + (0x11ef3, 0x11ef4,), # Makasar Vowel Sign I ..Makasar Vowel Sign U + (0x11f00, 0x11f01,), # (nil) + (0x11f36, 0x11f3a,), # (nil) + (0x11f40, 0x11f40,), # (nil) + (0x11f42, 0x11f42,), # (nil) + (0x13440, 0x13440,), # (nil) + (0x13447, 0x13455,), # (nil) + (0x16af0, 0x16af4,), # Bassa Vah Combining High..Bassa Vah Combining High + (0x16b30, 0x16b36,), # Pahawh Hmong Mark Cim Tu..Pahawh Hmong Mark Cim Ta + (0x16f4f, 0x16f4f,), # Miao Sign Consonant Modifier Bar + (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below + (0x16fe4, 0x16fe4,), # Khitan Small Script Filler + (0x1bc9d, 0x1bc9e,), # Duployan Thick Letter Se..Duployan Double Mark + (0x1cf00, 0x1cf2d,), # (nil) + (0x1cf30, 0x1cf46,), # (nil) + (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d185, 0x1d18b,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d1aa, 0x1d1ad,), # Musical Symbol Combining..Musical Symbol Combining + (0x1d242, 0x1d244,), # Combining Greek Musical ..Combining Greek Musical + (0x1da00, 0x1da36,), # Signwriting Head Rim ..Signwriting Air Sucking + (0x1da3b, 0x1da6c,), # Signwriting Mouth Closed..Signwriting Excitement + (0x1da75, 0x1da75,), # Signwriting Upper Body Tilting From Hip Joints + (0x1da84, 0x1da84,), # Signwriting Location Head Neck + (0x1da9b, 0x1da9f,), # Signwriting Fill Modifie..Signwriting Fill Modifie + (0x1daa1, 0x1daaf,), # Signwriting Rotation Mod..Signwriting Rotation Mod + (0x1e000, 0x1e006,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e008, 0x1e018,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e01b, 0x1e021,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e023, 0x1e024,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e026, 0x1e02a,), # Combining Glagolitic Let..Combining Glagolitic Let + (0x1e08f, 0x1e08f,), # (nil) + (0x1e130, 0x1e136,), # Nyiakeng Puachue Hmong T..Nyiakeng Puachue Hmong T + (0x1e2ae, 0x1e2ae,), # (nil) + (0x1e2ec, 0x1e2ef,), # Wancho Tone Tup ..Wancho Tone Koini + (0x1e4ec, 0x1e4ef,), # (nil) + (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining + (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta + (0xe0100, 0xe01ef,), # Variation Selector-17 ..Variation Selector-256 + ), } diff --git a/wcwidth/unicode_versions.py b/wcwidth/unicode_versions.py index d5ee547..3c0ca4a 100644 --- a/wcwidth/unicode_versions.py +++ b/wcwidth/unicode_versions.py @@ -1,7 +1,7 @@ """ Exports function list_versions() for unicode version level support. -This code generated by wcwidth/bin/update-tables.py on 2022-03-20 22:43:45 UTC. +This code generated by wcwidth/bin/update-tables.py on 2023-01-13 15:46:31 UTC. """ def list_versions(): @@ -32,4 +32,5 @@ def list_versions(): "12.1.0", "13.0.0", "14.0.0", + "15.0.0", ) From c3c9753698bed1662e4c83d92bb977aaa28c0e44 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Fri, 13 Jan 2023 11:03:32 -0500 Subject: [PATCH 42/57] add 15.0.0 to release notes --- docs/intro.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/intro.rst b/docs/intro.rst index f7dac13..0be6ac3 100644 --- a/docs/intro.rst +++ b/docs/intro.rst @@ -169,7 +169,7 @@ History ------- 0.2.6 *2022-06-022* - * **Updated** tables to include Unicode Specification 14.0.0. + * **Updated** tables to include Unicode Specification 14.0.0 and 15.0.0. * **Changed** developer tools to use pip-compile, and to use jinja2 templates for code generation in `bin/update-tables.py` to prepare for possible compiler optimization release. From 7151661fbe6e5cd7e234aa51e5c04e1089f45e59 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Fri, 13 Jan 2023 19:37:24 -0500 Subject: [PATCH 43/57] small fixes to browser --- bin/wcwidth-browser.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/bin/wcwidth-browser.py b/bin/wcwidth-browser.py index 7d05ba6..57b59d9 100755 --- a/bin/wcwidth-browser.py +++ b/bin/wcwidth-browser.py @@ -74,7 +74,7 @@ class WcWideCharacterGenerator(object): # pylint: disable=R0903 # Too few public methods (0/2) - def __init__(self, width=2, unicode_version='auto'): + def __init__(self, width, unicode_version): """ Class constructor. @@ -107,7 +107,7 @@ class WcCombinedCharacterGenerator(object): # pylint: disable=R0903 # Too few public methods (0/2) - def __init__(self, width=1): + def __init__(self, width, unicode_version): """ Class constructor. @@ -116,8 +116,8 @@ def __init__(self, width=1): """ self.characters = [] letters_o = ('o' * width) - last_version = list_versions()[-1] - for (begin, end) in ZERO_WIDTH[last_version]: + #last_version = list_versions()[-1] + for (begin, end) in ZERO_WIDTH[unicode_version]: for val in [_val for _val in range(begin, end + 1) if _val <= LIMIT_UCS]: @@ -318,7 +318,7 @@ def initialize_page_data(self): if self.term.is_a_tty: self.display_initialize() self.character_generator = self.character_factory( - self.screen.wide) + self.screen.wide, self.unicode_version) self._page_data = list() while True: try: From 70b68eae5a0d94f9dcafc1296eb47facebcbd55a Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Fri, 13 Jan 2023 19:37:34 -0500 Subject: [PATCH 44/57] update release date --- docs/intro.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/intro.rst b/docs/intro.rst index 0be6ac3..f581001 100644 --- a/docs/intro.rst +++ b/docs/intro.rst @@ -168,7 +168,7 @@ Other Languages History ------- -0.2.6 *2022-06-022* +0.2.6 *2023-01-14* * **Updated** tables to include Unicode Specification 14.0.0 and 15.0.0. * **Changed** developer tools to use pip-compile, and to use jinja2 templates for code generation in `bin/update-tables.py` to prepare for possible From 15acf3da869f8e50040da5af8516917f0b2b8e75 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Fri, 13 Jan 2023 19:48:40 -0500 Subject: [PATCH 45/57] small fixes --- bin/update-tables.py | 20 +++++++++++--------- docs/unicode_version.rst | 6 ++++++ tox.ini | 6 +++--- wcwidth/table_wide.py | 2 +- wcwidth/table_zero.py | 2 +- wcwidth/unicode_versions.py | 2 +- 6 files changed, 23 insertions(+), 15 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 9f7b2d8..5d3c88b 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -1,21 +1,19 @@ #!/usr/bin/env python """ -Update the python Unicode tables for wcwidth. +Update the Unicode code tables for wcwidth. This is code generation using jinja2. This should be executed through tox, $ tox -e update -Use argument --check-last-modified if data files were previously downloaded, -but will refresh by last-modified check using HEAD request from unicode.org -URLs. +If data files were previously downloaded, but will refresh by last-modified +check using HEAD request from unicode.org URLs, unless --no-check-last-modified +is used: $ tox -e update -- --check-last-modified https://github.com/jquast/wcwidth """ - - from __future__ import annotations # std imports @@ -374,9 +372,13 @@ def parse_category(fname: str, category_codes: Container) -> TableDef: def is_url_newer(url, fname): if not os.path.exists(fname): return True - if '--check-last-modified' in sys.argv[1:]: - # XXX - resp = requests.head(url, timeout=CONNECT_TIMEOUT) + if '--no-check-last-modified' not in sys.argv[1:]: + session = requests.Session() + retries = urllib3.util.Retry(total=MAX_RETRIES, + backoff_factor=BACKOFF_FACTOR, + status_forcelist=[500, 502, 503, 504]) + session.mount('https://', requests.adapters.HTTPAdapter(max_retries=retries)) + resp = session.head(url, timeout=CONNECT_TIMEOUT) resp.raise_for_status() remote_url_dt = dateutil.parser.parse(resp.headers['Last-Modified']).astimezone() local_file_dt = datetime.datetime.fromtimestamp(os.path.getmtime(fname)).astimezone() diff --git a/docs/unicode_version.rst b/docs/unicode_version.rst index b70071c..a2882b0 100644 --- a/docs/unicode_version.rst +++ b/docs/unicode_version.rst @@ -58,6 +58,9 @@ release files: ``DerivedGeneralCategory-14.0.0.txt`` *Date: 2021-07-10, 00:35:08 GMT* +``DerivedGeneralCategory-15.0.0.txt`` + *Date: 2022-04-26, 23:14:35 GMT* + ``EastAsianWidth-4.1.0.txt`` *Date: 2005-03-17, 15:21:00 PST [KW]* @@ -109,3 +112,6 @@ release files: ``EastAsianWidth-14.0.0.txt`` *Date: 2021-07-06, 09:58:53 GMT [KW, LI]* +``EastAsianWidth-15.0.0.txt`` + *Date: 2022-05-24, 17:40:20 GMT [KW, LI]* + diff --git a/tox.ini b/tox.ini index 4f1304b..8ece031 100644 --- a/tox.ini +++ b/tox.ini @@ -11,7 +11,7 @@ commands = {envpython} -m pytest --cov-config={toxinidir}/tox.ini {posargs:\ } \ --log-format='%(levelname)s %(relativeCreated)2.2f %(filename)s:%(lineno)d %(message)s' \ tests -passenv = TEST_QUICK TEST_KEYBOARD TEST_RAW +passenv = TEST_QUICK,TEST_KEYBOARD,TEST_RAW [isort] @@ -82,7 +82,7 @@ deps = -r requirements-tests38.txt basepython = python3.10 usedevelop = true deps = -r requirements-update.txt -commands = python {toxinidir}/bin/update-tables.py {posargs:--check-last-modified} +commands = python {toxinidir}/bin/update-tables.py {posargs} [testenv:autopep8] basepython = python3.10 @@ -145,6 +145,6 @@ commands = {envbindir}/sphinx-build -v -W -d {toxinidir}/docs/_build/doctrees -b [testenv:codecov] basepython = python{env:TOXPYTHON:{env:TRAVIS_PYTHON_VERSION:3.10}} -passenv = TOXENV CI TRAVIS TRAVIS_* CODECOV_* +passenv = TOXENV,CI,TRAVIS,TRAVIS_*,CODECOV_* deps = codecov commands = codecov -e TOXENV diff --git a/wcwidth/table_wide.py b/wcwidth/table_wide.py index 66ef07c..682eff3 100644 --- a/wcwidth/table_wide.py +++ b/wcwidth/table_wide.py @@ -1,7 +1,7 @@ """ Exports WIDE_EASTASIAN table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2023-01-13 15:46:31 UTC. +This code generated by wcwidth/bin/update-tables.py on 2023-01-14 00:47:46 UTC. """ WIDE_EASTASIAN = { '4.1.0': ( diff --git a/wcwidth/table_zero.py b/wcwidth/table_zero.py index d55c4c5..d41606f 100644 --- a/wcwidth/table_zero.py +++ b/wcwidth/table_zero.py @@ -1,7 +1,7 @@ """ Exports ZERO_WIDTH table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2023-01-13 15:46:31 UTC. +This code generated by wcwidth/bin/update-tables.py on 2023-01-14 00:47:46 UTC. """ ZERO_WIDTH = { '4.1.0': ( diff --git a/wcwidth/unicode_versions.py b/wcwidth/unicode_versions.py index 3c0ca4a..39047d0 100644 --- a/wcwidth/unicode_versions.py +++ b/wcwidth/unicode_versions.py @@ -1,7 +1,7 @@ """ Exports function list_versions() for unicode version level support. -This code generated by wcwidth/bin/update-tables.py on 2023-01-13 15:46:31 UTC. +This code generated by wcwidth/bin/update-tables.py on 2023-01-14 00:47:46 UTC. """ def list_versions(): From 71675bda1ae87a171ee71bca364ab48e735867e1 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Fri, 13 Jan 2023 19:54:12 -0500 Subject: [PATCH 46/57] lint/style changes --- bin/update-tables.py | 27 ++++++++++++++++----------- bin/wcwidth-browser.py | 1 - code_templates/unicode_versions.py.j2 | 1 + wcwidth/table_wide.py | 2 +- wcwidth/table_zero.py | 2 +- wcwidth/unicode_versions.py | 3 ++- 6 files changed, 21 insertions(+), 15 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 5d3c88b..1fda3fe 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -25,7 +25,6 @@ import datetime import functools import unicodedata -import urllib3.util from pathlib import Path from dataclasses import field, fields, dataclass @@ -34,6 +33,7 @@ # 3rd party import jinja2 import requests +import urllib3.util import dateutil.parser URL_UNICODE_DERIVED_AGE = 'https://www.unicode.org/Public/UCD/latest/ucd/DerivedAge.txt' @@ -46,7 +46,7 @@ # "wcwidth/bin/update-tables.py", even on Windows # not really a path, if the git repo isn't named "wcwidth" THIS_FILEPATH = ('wcwidth/' + - Path(__file__).resolve().relative_to(Path(PATH_UP).resolve()).as_posix()) + Path(__file__).resolve().relative_to(Path(PATH_UP).resolve()).as_posix()) JINJA_ENV = jinja2.Environment( loader=jinja2.FileSystemLoader(os.path.join(PATH_UP, 'code_templates')), @@ -63,14 +63,16 @@ @dataclass(order=True, frozen=True) class UnicodeVersion: - """A class for camparable unicode version""" + """A class for camparable unicode version.""" major: int minor: int micro: int @classmethod def parse(cls, version_str: str) -> UnicodeVersion: - """parse a version string + """ + parse a version string. + >>> UnicodeVersion.parse("14.0.0") UnicodeVersion(major=14, minor=0, micro=0) """ @@ -86,7 +88,7 @@ def __str__(self): @dataclass(frozen=True) class TableEntry: - """An entry of a unicode table""" + """An entry of a unicode table.""" code_range: range | None properties: tuple[str, ...] comment: str @@ -142,11 +144,11 @@ def __post_init__(self): } def render(self) -> str: - """just like jinja2.Template.render""" + """just like jinja2.Template.render.""" return self._template.render(self._render_context) def generate(self) -> Iterator[str]: - """just like jinja2.Template.generate""" + """just like jinja2.Template.generate.""" return self._template.generate(self._render_context) @@ -225,7 +227,7 @@ def fetch_source_headers() -> UnicodeVersionRstRenderCtx: if match := re.search(pattern, fname): filename_matches.append(match) - filename_matches.sort(key = lambda m: ( + filename_matches.sort(key=lambda m: ( m.group(1), int(m.group(2)), int(m.group(3)), @@ -275,10 +277,11 @@ def cite_source_description(filename: str) -> tuple[str, str]: def make_table(values: Collection[int]) -> tuple[tuple[int, int], ...]: - """Return a tuple of lookup tables for given values. + """ + Return a tuple of lookup tables for given values. + >>> make_table([0,1,2,5,6,7,9]) ((0, 2), (5, 7), (9, 9)) - """ table: list[tuple[int, int]] = [] values_iter = iter(values) @@ -324,7 +327,9 @@ def convert_values_to_string_table( def parse_unicode_table(file: Iterable[str]) -> Iterator[TableEntry]: - """Parse unicode tables. + """ + Parse unicode tables. + See details: https://www.unicode.org/reports/tr44/#Format_Conventions """ for line in file: diff --git a/bin/wcwidth-browser.py b/bin/wcwidth-browser.py index 57b59d9..fb6ac19 100755 --- a/bin/wcwidth-browser.py +++ b/bin/wcwidth-browser.py @@ -116,7 +116,6 @@ def __init__(self, width, unicode_version): """ self.characters = [] letters_o = ('o' * width) - #last_version = list_versions()[-1] for (begin, end) in ZERO_WIDTH[unicode_version]: for val in [_val for _val in range(begin, end + 1) diff --git a/code_templates/unicode_versions.py.j2 b/code_templates/unicode_versions.py.j2 index e31926c..09794f1 100644 --- a/code_templates/unicode_versions.py.j2 +++ b/code_templates/unicode_versions.py.j2 @@ -4,6 +4,7 @@ Exports function list_versions() for unicode version level support. This code generated by {{this_filepath}} on {{utc_now}}. """ + def list_versions(): """ Return Unicode version levels supported by this module release. diff --git a/wcwidth/table_wide.py b/wcwidth/table_wide.py index 682eff3..2fda209 100644 --- a/wcwidth/table_wide.py +++ b/wcwidth/table_wide.py @@ -1,7 +1,7 @@ """ Exports WIDE_EASTASIAN table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2023-01-14 00:47:46 UTC. +This code generated by wcwidth/bin/update-tables.py on 2023-01-14 00:53:07 UTC. """ WIDE_EASTASIAN = { '4.1.0': ( diff --git a/wcwidth/table_zero.py b/wcwidth/table_zero.py index d41606f..ebe76d9 100644 --- a/wcwidth/table_zero.py +++ b/wcwidth/table_zero.py @@ -1,7 +1,7 @@ """ Exports ZERO_WIDTH table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2023-01-14 00:47:46 UTC. +This code generated by wcwidth/bin/update-tables.py on 2023-01-14 00:53:07 UTC. """ ZERO_WIDTH = { '4.1.0': ( diff --git a/wcwidth/unicode_versions.py b/wcwidth/unicode_versions.py index 39047d0..cd33688 100644 --- a/wcwidth/unicode_versions.py +++ b/wcwidth/unicode_versions.py @@ -1,9 +1,10 @@ """ Exports function list_versions() for unicode version level support. -This code generated by wcwidth/bin/update-tables.py on 2023-01-14 00:47:46 UTC. +This code generated by wcwidth/bin/update-tables.py on 2023-01-14 00:53:07 UTC. """ + def list_versions(): """ Return Unicode version levels supported by this module release. From 2fe49837cdd5b1b5ed912bb38eeb2125e4ea9082 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Fri, 13 Jan 2023 19:57:08 -0500 Subject: [PATCH 47/57] spellfixes by @kianmeng in #65 --- bin/new-wide-by-version.py | 2 +- docs/api.rst | 2 +- docs/intro.rst | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/bin/new-wide-by-version.py b/bin/new-wide-by-version.py index 584d92a..b0ec5ad 100755 --- a/bin/new-wide-by-version.py +++ b/bin/new-wide-by-version.py @@ -11,7 +11,7 @@ ... Means that chr(12752) through chr(12754) are new WIDE values -for Unicode vesion 5.0.0, and were not WIDE values for the +for Unicode version 5.0.0, and were not WIDE values for the previous version (4.1.0). """ # std imports diff --git a/docs/api.rst b/docs/api.rst index da57fab..6de994c 100644 --- a/docs/api.rst +++ b/docs/api.rst @@ -2,7 +2,7 @@ Public API ========== -This package follows SEMVER_ rules for version, therefor, for all of the +This package follows SEMVER_ rules for version, therefore, for all of the given functions signatures, at example version 1.1.1, you may use version dependency ``>=1.1.1,<2.0`` for forward compatibility of future wcwidth versions. diff --git a/docs/intro.rst b/docs/intro.rst index f581001..813e244 100644 --- a/docs/intro.rst +++ b/docs/intro.rst @@ -8,7 +8,7 @@ This library is mainly for CLI programs that carefully produce output for Terminals, or make pretend to be an emulator. **Problem Statement**: The printable length of *most* strings are equal to the -number of cells they occupy on the screen ``1 charater : 1 cell``. However, +number of cells they occupy on the screen ``1 character : 1 cell``. However, there are categories of characters that *occupy 2 cells* (full-wide), and others that *occupy 0* cells (zero-width). From e05f9258be6ac5ccae33bb34fb5fb88ebbedbd04 Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Sat, 14 Jan 2023 11:08:49 +0800 Subject: [PATCH 48/57] Reuse requests.Session --- bin/update-tables.py | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 1fda3fe..4631283 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -374,15 +374,21 @@ def parse_category(fname: str, category_codes: Container) -> TableDef: return TableDef(version, date, txt_values) +@functools.cache +def get_http_session() -> requests.Session: + session = requests.Session() + retries = urllib3.util.Retry(total=MAX_RETRIES, + backoff_factor=BACKOFF_FACTOR, + status_forcelist=[500, 502, 503, 504]) + session.mount('https://', requests.adapters.HTTPAdapter(max_retries=retries)) + return session + + def is_url_newer(url, fname): if not os.path.exists(fname): return True if '--no-check-last-modified' not in sys.argv[1:]: - session = requests.Session() - retries = urllib3.util.Retry(total=MAX_RETRIES, - backoff_factor=BACKOFF_FACTOR, - status_forcelist=[500, 502, 503, 504]) - session.mount('https://', requests.adapters.HTTPAdapter(max_retries=retries)) + session = get_http_session() resp = session.head(url, timeout=CONNECT_TIMEOUT) resp.raise_for_status() remote_url_dt = dateutil.parser.parse(resp.headers['Last-Modified']).astimezone() @@ -398,11 +404,7 @@ def do_retrieve(url, fname): os.makedirs(folder) if not is_url_newer(url, fname): return - session = requests.Session() - retries = urllib3.util.Retry(total=MAX_RETRIES, - backoff_factor=BACKOFF_FACTOR, - status_forcelist=[500, 502, 503, 504]) - session.mount('https://', requests.adapters.HTTPAdapter(max_retries=retries)) + session = get_http_session() resp = session.get(url, timeout=CONNECT_TIMEOUT) resp.raise_for_status() print(f"saving {fname}: ", end='', flush=True) From 22e89550d90e1b71400bfff1270923ba591b0c05 Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Sat, 14 Jan 2023 11:15:38 +0800 Subject: [PATCH 49/57] Add `--debug` option --- bin/update-tables.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 4631283..852dd37 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -416,7 +416,11 @@ def do_retrieve(url, fname): def main() -> None: """Update east-asian, combining and zero width tables.""" - logging.basicConfig(stream=sys.stderr, level=logging.DEBUG) + if "--debug" in sys.argv[1:]: + loglevel = logging.DEBUG + else: + loglevel = logging.WARNING + logging.basicConfig(stream=sys.stderr, level=loglevel) # This defines which jinja source templates map to which output filenames, # and what function defines the source data. We hope to add more source From 5afb684274a61e5ad055b27f01bcb8f97b876e1a Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Sat, 14 Jan 2023 11:24:27 +0800 Subject: [PATCH 50/57] Always use LF for generated files --- bin/update-tables.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 852dd37..5d0729e 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -435,7 +435,7 @@ def get_codegen_definitions() -> Iterator[RenderDefinition]: yield UnicodeTableRenderDef.new('table_zero.py', fetch_table_zero_data()) for render_def in get_codegen_definitions(): - with open(render_def.output_filename, 'w', encoding='utf-8') as fout: + with open(render_def.output_filename, 'w', encoding='utf-8', newline='\n') as fout: print(f'write {render_def.output_filename}: ', flush=True, end='') for data in render_def.generate(): fout.write(data) From 118d96825418b76cf16e1c57a5fa63ca4d5e127c Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Sat, 14 Jan 2023 11:29:17 +0800 Subject: [PATCH 51/57] Update comments with Python 3.11 unicodedata --- wcwidth/table_wide.py | 48 ++++++++++++++++++++--------------------- wcwidth/table_zero.py | 50 +++++++++++++++++++++---------------------- 2 files changed, 49 insertions(+), 49 deletions(-) diff --git a/wcwidth/table_wide.py b/wcwidth/table_wide.py index 2fda209..9f8cd0a 100644 --- a/wcwidth/table_wide.py +++ b/wcwidth/table_wide.py @@ -1,7 +1,7 @@ """ Exports WIDE_EASTASIAN table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2023-01-14 00:53:07 UTC. +This code generated by wcwidth/bin/update-tables.py on 2023-01-14 03:25:41 UTC. """ WIDE_EASTASIAN = { '4.1.0': ( @@ -1169,10 +1169,10 @@ (0x17000, 0x187f7,), # (nil) (0x18800, 0x18cd5,), # Tangut Component-001 ..Khitan Small Script Char (0x18d00, 0x18d08,), # (nil) - (0x1aff0, 0x1aff3,), # (nil) - (0x1aff5, 0x1affb,), # (nil) - (0x1affd, 0x1affe,), # (nil) - (0x1b000, 0x1b122,), # Katakana Letter Archaic ..(nil) + (0x1aff0, 0x1aff3,), # Katakana Letter Minnan T..Katakana Letter Minnan T + (0x1aff5, 0x1affb,), # Katakana Letter Minnan T..Katakana Letter Minnan N + (0x1affd, 0x1affe,), # Katakana Letter Minnan N..Katakana Letter Minnan N + (0x1b000, 0x1b122,), # Katakana Letter Archaic ..Katakana Letter Archaic (0x1b150, 0x1b152,), # Hiragana Letter Small Wi..Hiragana Letter Small Wo (0x1b164, 0x1b167,), # Katakana Letter Small Wi..Katakana Letter Small N (0x1b170, 0x1b2fb,), # Nushu Character-1b170 ..Nushu Character-1b2fb @@ -1207,23 +1207,23 @@ (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley (0x1f6d5, 0x1f6d7,), # Hindu Temple ..Elevator - (0x1f6dd, 0x1f6df,), # (nil) + (0x1f6dd, 0x1f6df,), # Playground Slide ..Ring Buoy (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving (0x1f6f4, 0x1f6fc,), # Scooter ..Roller Skate (0x1f7e0, 0x1f7eb,), # Large Orange Circle ..Large Brown Square - (0x1f7f0, 0x1f7f0,), # (nil) + (0x1f7f0, 0x1f7f0,), # Heavy Equals Sign (0x1f90c, 0x1f93a,), # Pinched Fingers ..Fencer (0x1f93c, 0x1f945,), # Wrestlers ..Goal Net (0x1f947, 0x1f9ff,), # First Place Medal ..Nazar Amulet (0x1fa70, 0x1fa74,), # Ballet Shoes ..Thong Sandal - (0x1fa78, 0x1fa7c,), # Drop Of Blood ..(nil) + (0x1fa78, 0x1fa7c,), # Drop Of Blood ..Crutch (0x1fa80, 0x1fa86,), # Yo-yo ..Nesting Dolls - (0x1fa90, 0x1faac,), # Ringed Planet ..(nil) - (0x1fab0, 0x1faba,), # Fly ..(nil) - (0x1fac0, 0x1fac5,), # Anatomical Heart ..(nil) - (0x1fad0, 0x1fad9,), # Blueberries ..(nil) - (0x1fae0, 0x1fae7,), # (nil) - (0x1faf0, 0x1faf6,), # (nil) + (0x1fa90, 0x1faac,), # Ringed Planet ..Hamsa + (0x1fab0, 0x1faba,), # Fly ..Nest With Eggs + (0x1fac0, 0x1fac5,), # Anatomical Heart ..Person With Crown + (0x1fad0, 0x1fad9,), # Blueberries ..Jar + (0x1fae0, 0x1fae7,), # Melting Face ..Bubbles + (0x1faf0, 0x1faf6,), # Hand With Index Finger A..Heart Hands (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), @@ -1295,10 +1295,10 @@ (0x17000, 0x187f7,), # (nil) (0x18800, 0x18cd5,), # Tangut Component-001 ..Khitan Small Script Char (0x18d00, 0x18d08,), # (nil) - (0x1aff0, 0x1aff3,), # (nil) - (0x1aff5, 0x1affb,), # (nil) - (0x1affd, 0x1affe,), # (nil) - (0x1b000, 0x1b122,), # Katakana Letter Archaic ..(nil) + (0x1aff0, 0x1aff3,), # Katakana Letter Minnan T..Katakana Letter Minnan T + (0x1aff5, 0x1affb,), # Katakana Letter Minnan T..Katakana Letter Minnan N + (0x1affd, 0x1affe,), # Katakana Letter Minnan N..Katakana Letter Minnan N + (0x1b000, 0x1b122,), # Katakana Letter Archaic ..Katakana Letter Archaic (0x1b132, 0x1b132,), # (nil) (0x1b150, 0x1b152,), # Hiragana Letter Small Wi..Hiragana Letter Small Wo (0x1b155, 0x1b155,), # (nil) @@ -1335,21 +1335,21 @@ (0x1f6cc, 0x1f6cc,), # Sleeping Accommodation (0x1f6d0, 0x1f6d2,), # Place Of Worship ..Shopping Trolley (0x1f6d5, 0x1f6d7,), # Hindu Temple ..Elevator - (0x1f6dc, 0x1f6df,), # (nil) + (0x1f6dc, 0x1f6df,), # (nil) ..Ring Buoy (0x1f6eb, 0x1f6ec,), # Airplane Departure ..Airplane Arriving (0x1f6f4, 0x1f6fc,), # Scooter ..Roller Skate (0x1f7e0, 0x1f7eb,), # Large Orange Circle ..Large Brown Square - (0x1f7f0, 0x1f7f0,), # (nil) + (0x1f7f0, 0x1f7f0,), # Heavy Equals Sign (0x1f90c, 0x1f93a,), # Pinched Fingers ..Fencer (0x1f93c, 0x1f945,), # Wrestlers ..Goal Net (0x1f947, 0x1f9ff,), # First Place Medal ..Nazar Amulet - (0x1fa70, 0x1fa7c,), # Ballet Shoes ..(nil) + (0x1fa70, 0x1fa7c,), # Ballet Shoes ..Crutch (0x1fa80, 0x1fa88,), # Yo-yo ..(nil) (0x1fa90, 0x1fabd,), # Ringed Planet ..(nil) - (0x1fabf, 0x1fac5,), # (nil) + (0x1fabf, 0x1fac5,), # (nil) ..Person With Crown (0x1face, 0x1fadb,), # (nil) - (0x1fae0, 0x1fae8,), # (nil) - (0x1faf0, 0x1faf8,), # (nil) + (0x1fae0, 0x1fae8,), # Melting Face ..(nil) + (0x1faf0, 0x1faf8,), # Hand With Index Finger A..(nil) (0x20000, 0x2fffd,), # Cjk Unified Ideograph-20..(nil) (0x30000, 0x3fffd,), # Cjk Unified Ideograph-30..(nil) ), diff --git a/wcwidth/table_zero.py b/wcwidth/table_zero.py index ebe76d9..a4abaea 100644 --- a/wcwidth/table_zero.py +++ b/wcwidth/table_zero.py @@ -1,7 +1,7 @@ """ Exports ZERO_WIDTH table keyed by supporting unicode version level. -This code generated by wcwidth/bin/update-tables.py on 2023-01-14 00:53:07 UTC. +This code generated by wcwidth/bin/update-tables.py on 2023-01-14 03:25:41 UTC. """ ZERO_WIDTH = { '4.1.0': ( @@ -3938,8 +3938,8 @@ (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U (0x00829, 0x0082d,), # Samaritan Vowel Sign Lon..Samaritan Mark Nequdaa (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark - (0x00898, 0x0089f,), # (nil) - (0x008ca, 0x008e1,), # (nil) ..Arabic Small High Sign S + (0x00898, 0x0089f,), # Arabic Small High Word A..Arabic Half Madda Over M + (0x008ca, 0x008e1,), # Arabic Small High Farsi ..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe (0x0093c, 0x0093c,), # Devanagari Sign Nukta @@ -3980,7 +3980,7 @@ (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c00, 0x00c00,), # Telugu Sign Combining Candrabindu Above (0x00c04, 0x00c04,), # Telugu Sign Combining Anusvara Above - (0x00c3c, 0x00c3c,), # (nil) + (0x00c3c, 0x00c3c,), # Telugu Sign Nukta (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama @@ -4039,7 +4039,7 @@ (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x0180f, 0x0180f,), # (nil) + (0x0180f, 0x0180f,), # Mongolian Free Variation Selector Four (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U @@ -4055,7 +4055,7 @@ (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot - (0x01ab0, 0x01ace,), # Combining Doubled Circum..(nil) + (0x01ab0, 0x01ace,), # Combining Doubled Circum..Combining Latin Small Le (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R @@ -4135,15 +4135,15 @@ (0x10d24, 0x10d27,), # Hanifi Rohingya Sign Har..Hanifi Rohingya Sign Tas (0x10eab, 0x10eac,), # Yezidi Combining Hamza M..Yezidi Combining Madda M (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke - (0x10f82, 0x10f85,), # (nil) + (0x10f82, 0x10f85,), # Old Uyghur Combining Dot..Old Uyghur Combining Two (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama - (0x11070, 0x11070,), # (nil) - (0x11073, 0x11074,), # (nil) + (0x11070, 0x11070,), # Brahmi Sign Old Tamil Virama + (0x11073, 0x11074,), # Brahmi Vowel Sign Old Ta..Brahmi Vowel Sign Old Ta (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai (0x110b9, 0x110ba,), # Kaithi Sign Virama ..Kaithi Sign Nukta - (0x110c2, 0x110c2,), # (nil) + (0x110c2, 0x110c2,), # Kaithi Vowel Sign Vocalic R (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa @@ -4223,8 +4223,8 @@ (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below (0x16fe4, 0x16fe4,), # Khitan Small Script Filler (0x1bc9d, 0x1bc9e,), # Duployan Thick Letter Se..Duployan Double Mark - (0x1cf00, 0x1cf2d,), # (nil) - (0x1cf30, 0x1cf46,), # (nil) + (0x1cf00, 0x1cf2d,), # Znamenny Combining Mark ..Znamenny Combining Mark + (0x1cf30, 0x1cf46,), # Znamenny Combining Tonal..Znamenny Priznak Modifie (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining (0x1d185, 0x1d18b,), # Musical Symbol Combining..Musical Symbol Combining @@ -4242,7 +4242,7 @@ (0x1e023, 0x1e024,), # Combining Glagolitic Let..Combining Glagolitic Let (0x1e026, 0x1e02a,), # Combining Glagolitic Let..Combining Glagolitic Let (0x1e130, 0x1e136,), # Nyiakeng Puachue Hmong T..Nyiakeng Puachue Hmong T - (0x1e2ae, 0x1e2ae,), # (nil) + (0x1e2ae, 0x1e2ae,), # Toto Sign Rising Tone (0x1e2ec, 0x1e2ef,), # Wancho Tone Tup ..Wancho Tone Koini (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining (0x1e944, 0x1e94a,), # Adlam Alif Lengthener ..Adlam Nukta @@ -4276,8 +4276,8 @@ (0x00825, 0x00827,), # Samaritan Vowel Sign Sho..Samaritan Vowel Sign U (0x00829, 0x0082d,), # Samaritan Vowel Sign Lon..Samaritan Mark Nequdaa (0x00859, 0x0085b,), # Mandaic Affrication Mark..Mandaic Gemination Mark - (0x00898, 0x0089f,), # (nil) - (0x008ca, 0x008e1,), # (nil) ..Arabic Small High Sign S + (0x00898, 0x0089f,), # Arabic Small High Word A..Arabic Half Madda Over M + (0x008ca, 0x008e1,), # Arabic Small High Farsi ..Arabic Small High Sign S (0x008e3, 0x00902,), # Arabic Turned Damma Belo..Devanagari Sign Anusvara (0x0093a, 0x0093a,), # Devanagari Vowel Sign Oe (0x0093c, 0x0093c,), # Devanagari Sign Nukta @@ -4318,7 +4318,7 @@ (0x00bcd, 0x00bcd,), # Tamil Sign Virama (0x00c00, 0x00c00,), # Telugu Sign Combining Candrabindu Above (0x00c04, 0x00c04,), # Telugu Sign Combining Anusvara Above - (0x00c3c, 0x00c3c,), # (nil) + (0x00c3c, 0x00c3c,), # Telugu Sign Nukta (0x00c3e, 0x00c40,), # Telugu Vowel Sign Aa ..Telugu Vowel Sign Ii (0x00c46, 0x00c48,), # Telugu Vowel Sign E ..Telugu Vowel Sign Ai (0x00c4a, 0x00c4d,), # Telugu Vowel Sign O ..Telugu Sign Virama @@ -4377,7 +4377,7 @@ (0x017c9, 0x017d3,), # Khmer Sign Muusikatoan ..Khmer Sign Bathamasat (0x017dd, 0x017dd,), # Khmer Sign Atthacan (0x0180b, 0x0180d,), # Mongolian Free Variation..Mongolian Free Variation - (0x0180f, 0x0180f,), # (nil) + (0x0180f, 0x0180f,), # Mongolian Free Variation Selector Four (0x01885, 0x01886,), # Mongolian Letter Ali Gal..Mongolian Letter Ali Gal (0x018a9, 0x018a9,), # Mongolian Letter Ali Gali Dagalga (0x01920, 0x01922,), # Limbu Vowel Sign A ..Limbu Vowel Sign U @@ -4393,7 +4393,7 @@ (0x01a65, 0x01a6c,), # Tai Tham Vowel Sign I ..Tai Tham Vowel Sign Oa B (0x01a73, 0x01a7c,), # Tai Tham Vowel Sign Oa A..Tai Tham Sign Khuen-lue (0x01a7f, 0x01a7f,), # Tai Tham Combining Cryptogrammic Dot - (0x01ab0, 0x01ace,), # Combining Doubled Circum..(nil) + (0x01ab0, 0x01ace,), # Combining Doubled Circum..Combining Latin Small Le (0x01b00, 0x01b03,), # Balinese Sign Ulu Ricem ..Balinese Sign Surang (0x01b34, 0x01b34,), # Balinese Sign Rerekan (0x01b36, 0x01b3a,), # Balinese Vowel Sign Ulu ..Balinese Vowel Sign Ra R @@ -4474,15 +4474,15 @@ (0x10eab, 0x10eac,), # Yezidi Combining Hamza M..Yezidi Combining Madda M (0x10efd, 0x10eff,), # (nil) (0x10f46, 0x10f50,), # Sogdian Combining Dot Be..Sogdian Combining Stroke - (0x10f82, 0x10f85,), # (nil) + (0x10f82, 0x10f85,), # Old Uyghur Combining Dot..Old Uyghur Combining Two (0x11001, 0x11001,), # Brahmi Sign Anusvara (0x11038, 0x11046,), # Brahmi Vowel Sign Aa ..Brahmi Virama - (0x11070, 0x11070,), # (nil) - (0x11073, 0x11074,), # (nil) + (0x11070, 0x11070,), # Brahmi Sign Old Tamil Virama + (0x11073, 0x11074,), # Brahmi Vowel Sign Old Ta..Brahmi Vowel Sign Old Ta (0x1107f, 0x11081,), # Brahmi Number Joiner ..Kaithi Sign Anusvara (0x110b3, 0x110b6,), # Kaithi Vowel Sign U ..Kaithi Vowel Sign Ai (0x110b9, 0x110ba,), # Kaithi Sign Virama ..Kaithi Sign Nukta - (0x110c2, 0x110c2,), # (nil) + (0x110c2, 0x110c2,), # Kaithi Vowel Sign Vocalic R (0x11100, 0x11102,), # Chakma Sign Candrabindu ..Chakma Sign Visarga (0x11127, 0x1112b,), # Chakma Vowel Sign A ..Chakma Vowel Sign Uu (0x1112d, 0x11134,), # Chakma Vowel Sign Ai ..Chakma Maayyaa @@ -4569,8 +4569,8 @@ (0x16f8f, 0x16f92,), # Miao Tone Right ..Miao Tone Below (0x16fe4, 0x16fe4,), # Khitan Small Script Filler (0x1bc9d, 0x1bc9e,), # Duployan Thick Letter Se..Duployan Double Mark - (0x1cf00, 0x1cf2d,), # (nil) - (0x1cf30, 0x1cf46,), # (nil) + (0x1cf00, 0x1cf2d,), # Znamenny Combining Mark ..Znamenny Combining Mark + (0x1cf30, 0x1cf46,), # Znamenny Combining Tonal..Znamenny Priznak Modifie (0x1d167, 0x1d169,), # Musical Symbol Combining..Musical Symbol Combining (0x1d17b, 0x1d182,), # Musical Symbol Combining..Musical Symbol Combining (0x1d185, 0x1d18b,), # Musical Symbol Combining..Musical Symbol Combining @@ -4589,7 +4589,7 @@ (0x1e026, 0x1e02a,), # Combining Glagolitic Let..Combining Glagolitic Let (0x1e08f, 0x1e08f,), # (nil) (0x1e130, 0x1e136,), # Nyiakeng Puachue Hmong T..Nyiakeng Puachue Hmong T - (0x1e2ae, 0x1e2ae,), # (nil) + (0x1e2ae, 0x1e2ae,), # Toto Sign Rising Tone (0x1e2ec, 0x1e2ef,), # Wancho Tone Tup ..Wancho Tone Koini (0x1e4ec, 0x1e4ef,), # (nil) (0x1e8d0, 0x1e8d6,), # Mende Kikakui Combining ..Mende Kikakui Combining From f9076b8af39bef935716e11f42cb635260625fb8 Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Sat, 14 Jan 2023 11:49:05 +0800 Subject: [PATCH 52/57] Add more type hints for `mypy --strict` --- bin/update-tables.py | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 5d0729e..6e52e22 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -29,6 +29,7 @@ from dataclasses import field, fields, dataclass from typing import Any, Mapping, Iterable, Iterator, Sequence, Container, Collection +from typing_extensions import Self # 3rd party import jinja2 @@ -78,7 +79,7 @@ def parse(cls, version_str: str) -> UnicodeVersion: """ return cls(*map(int, version_str.split(".")[:3])) - def __str__(self): + def __str__(self) -> str: """ >>> str(UnicodeVersion(12, 1, 0)) '12.1.0' @@ -135,7 +136,7 @@ class RenderDefinition: _template: jinja2.Template = field(init=False, repr=False) _render_context: dict[str, Any] = field(init=False, repr=False) - def __post_init__(self): + def __post_init__(self) -> None: self._template = JINJA_ENV.get_template(self.jinja_filename) self._render_context = { 'utc_now': UTC_NOW, @@ -157,7 +158,7 @@ class UnicodeVersionPyRenderDef(RenderDefinition): render_context: UnicodeVersionPyRenderCtx @classmethod - def new(cls, context: UnicodeVersionPyRenderCtx): + def new(cls, context: UnicodeVersionPyRenderCtx) -> Self: return cls( jinja_filename='unicode_versions.py.j2', output_filename=os.path.join(PATH_UP, 'wcwidth', 'unicode_versions.py'), @@ -170,7 +171,7 @@ class UnicodeVersionRstRenderDef(RenderDefinition): render_context: UnicodeVersionRstRenderCtx @classmethod - def new(cls, context: UnicodeVersionRstRenderCtx): + def new(cls, context: UnicodeVersionRstRenderCtx) -> Self: return cls( jinja_filename='unicode_version.rst.j2', output_filename=os.path.join(PATH_UP, 'docs', 'unicode_version.rst'), @@ -183,7 +184,7 @@ class UnicodeTableRenderDef(RenderDefinition): render_context: UnicodeTableRenderCtx @classmethod - def new(cls, filename: str, context: UnicodeTableRenderCtx): + def new(cls, filename: str, context: UnicodeTableRenderCtx) -> Self: _, ext = os.path.splitext(filename) if ext == '.py': jinja_filename = 'python_table.py.j2' @@ -351,7 +352,7 @@ def parse_unicode_table(file: Iterable[str]) -> Iterator[TableEntry]: yield TableEntry(code_range, tuple(properties), comment) -def parse_category(fname: str, category_codes: Container) -> TableDef: +def parse_category(fname: str, category_codes: Container[str]) -> TableDef: """Parse value ranges of unicode data files, by given categories into string tables.""" print(f'parsing {fname}: ', end='', flush=True) @@ -384,7 +385,7 @@ def get_http_session() -> requests.Session: return session -def is_url_newer(url, fname): +def is_url_newer(url: str, fname: str) -> bool: if not os.path.exists(fname): return True if '--no-check-last-modified' not in sys.argv[1:]: @@ -397,7 +398,7 @@ def is_url_newer(url, fname): return False -def do_retrieve(url, fname): +def do_retrieve(url: str, fname: str) -> None: """Retrieve given url to target filepath fname.""" folder = os.path.dirname(fname) if not os.path.exists(folder): From 375f475c5005ff640aa786c0b7dc3c017d321bf7 Mon Sep 17 00:00:00 2001 From: GalaxySnail Date: Sun, 15 Jan 2023 11:44:44 +0800 Subject: [PATCH 53/57] Set MAX_RETRIES to 6 --- bin/update-tables.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 6e52e22..0ff6ffc 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -56,7 +56,7 @@ CONNECT_TIMEOUT = int(os.environ.get('CONNECT_TIMEOUT', '10')) FETCH_BLOCKSIZE = int(os.environ.get('FETCH_BLOCKSIZE', '4096')) -MAX_RETRIES = int(os.environ.get('MAX_RETRIES', '10')) +MAX_RETRIES = int(os.environ.get('MAX_RETRIES', '6')) BACKOFF_FACTOR = float(os.environ.get('BACKOFF_FACTOR', '0.1')) logger = logging.getLogger(__name__) From 793bc92ae48cbb721657189d00e337e96f8a319a Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sat, 14 Jan 2023 22:40:45 -0500 Subject: [PATCH 54/57] updates pylint & friends for python3.11-compatible requirements --- requirements-tests39.in | 4 +++- requirements-tests39.txt | 26 +++++++++++++++----------- 2 files changed, 18 insertions(+), 12 deletions(-) diff --git a/requirements-tests39.in b/requirements-tests39.in index 34b298d..21c505b 100644 --- a/requirements-tests39.in +++ b/requirements-tests39.in @@ -5,9 +5,11 @@ flake8 autopep8 docformatter isort -pylint pydocstyle restructuredtext_lint doc8 pygments +pylint>=2.15 +astroid>=2.11 +wrapt>=1.14 diff --git a/requirements-tests39.txt b/requirements-tests39.txt index 4c5b242..465cecb 100644 --- a/requirements-tests39.txt +++ b/requirements-tests39.txt @@ -4,14 +4,18 @@ # # pip-compile --no-emit-index-url --output-file=requirements-tests39.txt requirements-tests39.in # -astroid==2.9.3 - # via pylint +astroid==2.13.2 + # via + # -r requirements-tests39.in + # pylint attrs==21.4.0 # via pytest autopep8==1.6.0 # via -r requirements-tests39.in coverage[toml]==6.3.2 # via pytest-cov +dill==0.3.6 + # via pylint doc8==0.10.1 # via -r requirements-tests39.in docformatter==1.4 @@ -56,7 +60,7 @@ pygments==2.11.2 # via # -r requirements-tests39.in # doc8 -pylint==2.12.2 +pylint==2.15.10 # via -r requirements-tests39.in pyparsing==3.0.7 # via packaging @@ -75,21 +79,21 @@ snowballstemmer==2.2.0 stevedore==3.5.0 # via doc8 toml==0.10.2 - # via - # autopep8 - # pylint + # via autopep8 tomli==2.0.1 # via # coverage + # pylint # pytest +tomlkit==0.11.6 + # via pylint typing-extensions==4.4.0 # via # astroid # pylint untokenize==0.1.1 # via docformatter -wrapt==1.13.3 - # via astroid - -# The following packages are considered to be unsafe in a requirements file: -# setuptools +wrapt==1.14.1 + # via + # -r requirements-tests39.in + # astroid From 3cf9c91946bb46cf9ee1f2caccc19a7152a765e9 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sat, 14 Jan 2023 22:44:20 -0500 Subject: [PATCH 55/57] change retries 10 -> 6 --- bin/update-tables.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/bin/update-tables.py b/bin/update-tables.py index 6e52e22..0ff6ffc 100644 --- a/bin/update-tables.py +++ b/bin/update-tables.py @@ -56,7 +56,7 @@ CONNECT_TIMEOUT = int(os.environ.get('CONNECT_TIMEOUT', '10')) FETCH_BLOCKSIZE = int(os.environ.get('FETCH_BLOCKSIZE', '4096')) -MAX_RETRIES = int(os.environ.get('MAX_RETRIES', '10')) +MAX_RETRIES = int(os.environ.get('MAX_RETRIES', '6')) BACKOFF_FACTOR = float(os.environ.get('BACKOFF_FACTOR', '0.1')) logger = logging.getLogger(__name__) From 1180fa1592b9feb164a56bf0730bfec16c492ad5 Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sat, 14 Jan 2023 22:44:29 -0500 Subject: [PATCH 56/57] python3.11 in tox.ini --- tox.ini | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) diff --git a/tox.ini b/tox.ini index 56fcffb..a29ed54 100644 --- a/tox.ini +++ b/tox.ini @@ -57,12 +57,17 @@ precision = 1 [coverage:paths] source = wcwidth/ +# wcwidth itself has no 3rd party dependencies, but to ensure the best available +# version for the newest to oldest python versions for testing, must also use some +# targeted versions to 'compile' those requirements into their frozen form, +# otherwise incompatible packages would be pinned. At the time of this writing the +# files compiled for version 3.9 through 3.11 are compiled by python3.11. [testenv:compile] -basepython = python3.10 +basepython = python3.11 commands = python -m compileall {toxinidir}/wcwidth {toxinidir}/bin {toxinidir}/tests {toxinidir}/docs [testenv:update_requirements] -basepython = python3.10 +basepython = python3.11 deps = pip-tools commands = pip-compile --resolver=backtracking --no-emit-index-url requirements-update.in -o requirements-update.txt pip-compile --resolver=backtracking --no-emit-index-url requirements-docs.in -o docs/requirements.txt @@ -92,13 +97,13 @@ deps = -r requirements-tests37.txt deps = -r requirements-tests36.txt [testenv:update] -basepython = python3.10 +basepython = python3.11 usedevelop = true deps = -r requirements-update.txt commands = python {toxinidir}/bin/update-tables.py {posargs} [testenv:autopep8] -basepython = python3.10 +basepython = python3.11 commands = {envbindir}/autopep8 \ --in-place \ @@ -108,7 +113,7 @@ commands = wcwidth/ bin/ tests/ setup.py [testenv:docformatter] -basepython = python3.10 +basepython = python3.11 commands = {envbindir}/docformatter \ --in-place \ @@ -122,37 +127,37 @@ commands = {toxinidir}/docs/conf.py [testenv:isort] -basepython = python3.10 +basepython = python3.11 commands = {envbindir}/isort --quiet --apply --recursive wcwidth tests bin [testenv:pylint] -basepython = python3.10 +basepython = python3.11 commands = {envbindir}/pylint --rcfile={toxinidir}/.pylintrc \ --ignore=tests,docs,setup.py,conf.py,build,distutils,.pyenv,.git,.tox \ {posargs:{toxinidir}}/wcwidth [testenv:flake8] -basepython = python3.10 +basepython = python3.11 commands = {envbindir}/flake8 --exclude=tests setup.py docs/ wcwidth/ bin/ tests/ [testenv:pydocstyle] -basepython = python3.10 +basepython = python3.11 commands = {envbindir}/pydocstyle --source --explain {toxinidir}/wcwidth {envbindir}/rst-lint README.rst {envbindir}/doc8 --ignore-path docs/_build --ignore-path docs/requirements.txt --ignore D000 docs [testenv:docs] -basepython = python3.10 +basepython = python3.11 deps = -r {toxinidir}/docs/requirements.txt commands = sphinx-build docs/ build/sphinx [testenv:sphinx] -basepython = python3.10 +basepython = python3.11 deps = -r {toxinidir}/docs/requirements.txt commands = {envbindir}/sphinx-build {posargs:-v -W -d {toxinidir}/docs/_build/doctrees -b html docs {toxinidir}/docs/_build/html} [testenv:linkcheck] -basepython = python3.10 +basepython = python3.11 deps = -r {toxinidir}/docs/requirements.txt commands = {envbindir}/sphinx-build -v -W -d {toxinidir}/docs/_build/doctrees -b linkcheck docs docs/_build/linkcheck From bfdf76be4e8c6e29063bd70399c0298c895b700a Mon Sep 17 00:00:00 2001 From: Jeff Quast Date: Sat, 14 Jan 2023 22:44:41 -0500 Subject: [PATCH 57/57] ignore isort comment rewrite in test_core.py --- tests/test_core.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tests/test_core.py b/tests/test_core.py index ab5cf82..c8f791c 100755 --- a/tests/test_core.py +++ b/tests/test_core.py @@ -1,9 +1,10 @@ # coding: utf-8 -"""Core tests for wcwidth module.""" -# 3rd party +"""Core tests for wcwidth module. isort:skip_file""" try: + # std import import importlib.metadata as importmeta except ImportError: + # 3rd party for python3.7 and earlier import importlib_metadata as importmeta # local