Skip to content
This repository has been archived by the owner on Apr 26, 2024. It is now read-only.

Support underscores (in addition to hyphens) for charset detection. #10410

Merged
merged 7 commits into from
Jul 27, 2021
Merged

Support underscores (in addition to hyphens) for charset detection. #10410

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
20030bc
issue:#10307, #prev-pull-request:#10306
srividyut Jul 16, 2021
a2a8c9e
Rename 10306.bugfix to 10410.bugfix
srividyut Jul 16, 2021
d3f581e
Update changelog.d/10410.bugfix
srividyut Jul 16, 2021
973e782
Added source code to "tests.test_preview.MediaEncodingTestCase(test_p…
srividyut Jul 16, 2021
27f6b04
Merge branch 'preview_url' of https://github.com/srividyut/synapse in…
srividyut Jul 16, 2021
b9bbe4b
Added source code to test_preview
srividyut Jul 16, 2021
53f9789
Separate tests.
clokep Jul 27, 2021
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
1 change: 1 addition & 0 deletions changelog.d/10410.bugfix
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Improve character set detection in URL previews by supporting underscores (in addition to hyphens). Contributed by @srividyut.
6 changes: 4 additions & 2 deletions synapse/rest/media/v1/preview_url_resource.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,9 +58,11 @@

logger = logging.getLogger(__name__)

_charset_match = re.compile(br'<\s*meta[^>]*charset\s*=\s*"?([a-z0-9-]+)"?', flags=re.I)
_charset_match = re.compile(
br'<\s*meta[^>]*charset\s*=\s*"?([a-z0-9_-]+)"?', flags=re.I
)
_xml_encoding_match = re.compile(
br'\s*<\s*\?\s*xml[^>]*encoding="([a-z0-9-]+)"', flags=re.I
br'\s*<\s*\?\s*xml[^>]*encoding="([a-z0-9_-]+)"', flags=re.I
)
_content_type_match = re.compile(r'.*; *charset="?(.*?)"?(;|$)', flags=re.I)

Expand Down
13 changes: 13 additions & 0 deletions tests/test_preview.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -325,6 +325,19 @@ def test_meta_charset(self):
)
self.assertEqual(encoding, "ascii")

def test_meta_charset_underscores(self):
"""A character encoding contains underscore."""
clokep marked this conversation as resolved.
Show resolved Hide resolved
encoding = get_html_media_encoding(
b"""
<html>
<head><meta charset="Shift_JIS">
</head>
</html>
""",
"text/html",
)
self.assertEqual(encoding, "Shift_JIS")

def test_xml_encoding(self):
"""A character encoding is found via the meta tag."""
encoding = get_html_media_encoding(
Expand Down