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This repository has been archived by the owner on Apr 26, 2024.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

Fix URL preview errors when previewing XML documents #11196

Merged
merged 3 commits into from
Oct 27, 2021
Merged

Fix URL preview errors when previewing XML documents #11196

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
14ad75e
Pass a byte string into the etree parser.
clokep Oct 27, 2021
9387c1b
Newsfragment
clokep Oct 27, 2021
5ab19e0
Lint.
clokep Oct 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/11196.bugfix
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Fix a bug introduced in v1.46.0rc1 where URL previews of some XML documents would fail.
4 changes: 2 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 @@ -732,11 +732,11 @@ def decode_body(
from lxml import etree

# Create an HTML parser.
parser = etree.HTMLParser(recover=True, encoding="utf-8")
parser = etree.HTMLParser(recover=True, encoding=encoding)

# Attempt to parse the body. Returns None if the body was successfully
# parsed, but no tree was found.
return etree.fromstring(body_str, parser)
return etree.fromstring(body, parser)


def _calc_og(tree: "etree.Element", media_uri: str) -> Dict[str, Optional[str]]:
Expand Down
15 changes: 15 additions & 0 deletions tests/test_preview.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -277,6 +277,21 @@ def test_no_tree(self):
tree = decode_body(html, "http://example.com/test.html")
self.assertIsNone(tree)

def test_xml(self):
"""Test decoding XML and ensure it works properly."""
# Note that the strip() call is important to ensure the xml tag starts
# at the initial byte.
html = b"""
<?xml version="1.0" encoding="UTF-8"?>

<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head><title>Foo</title></head><body>Some text.</body></html>
""".strip()
tree = decode_body(html, "http://example.com/test.html")
og = _calc_og(tree, "http://example.com/test.html")
self.assertEqual(og, {"og:title": "Foo", "og:description": "Some text."})

def test_invalid_encoding(self):
"""An invalid character encoding should be ignored and treated as UTF-8, if possible."""
html = b"""
Expand Down