Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

wikipedia: refine no-consume logic for section hatnotes #2225

Merged
merged 1 commit into from
Dec 26, 2021
Merged

wikipedia: refine no-consume logic for section hatnotes #2225

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 21 additions & 6 deletions sopel/modules/wikipedia.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,9 +22,17 @@


class WikiParser(HTMLParser):
NO_CONSUME_TAGS = ('sup', 'style')
"""Tags whose contents should always be ignored.

These are used in things like inline citations or section "hatnotes", none
of which are useful output for IRC.
"""

def __init__(self, section_name):
HTMLParser.__init__(self)
self.consume = True
self.no_consume_depth = 0
self.is_header = False
self.section_name = section_name

Expand All @@ -36,8 +44,9 @@ def __init__(self, section_name):
self.result = ''

def handle_starttag(self, tag, attrs):
if tag == 'sup': # don't consume anything in superscript (citation-related tags)
if tag in self.NO_CONSUME_TAGS:
self.consume = False
self.no_consume_depth += 1

elif re.match(r'^h\d$', tag):
self.is_header = True
Expand All @@ -51,14 +60,17 @@ def handle_starttag(self, tag, attrs):
self.span_depth += 1

elif tag == 'div':
# We want to skip thumbnail text and the inexplicable table of contents,
# and as such also need to track div depth
# We want to skip thumbnail text, the table of contents, and section "hatnotes".
# This also requires tracking div nesting level.
if self.div_depth:
self.div_depth += 1
else:
for attr in attrs:
if attr[0] == 'class' and ('thumb' in attr[1] or attr[1] == 'toc'):
if attr[0] == 'class' and (
'thumb' in attr[1] or 'hatnote' in attr[1] or attr[1] == 'toc'
):
self.div_depth += 1
break

elif tag == 'table':
# Message box templates are what we want to ignore here
Expand All @@ -85,8 +97,11 @@ def handle_starttag(self, tag, attrs):
self.citations = True # once we hit citations, we can stop

def handle_endtag(self, tag):
if not self.consume and tag == 'sup':
self.consume = True
if not self.consume and tag in self.NO_CONSUME_TAGS:
if self.no_consume_depth:
self.no_consume_depth -= 1
if not self.no_consume_depth:
self.consume = True
if self.is_header and re.match(r'^h\d$', tag):
self.is_header = False
if self.span_depth and tag == 'span':
Expand Down