diff options
| author | Erik Johnston <erik@matrix.org> | 2021-11-08 11:34:03 +0000 |
|---|---|---|
| committer | Erik Johnston <erik@matrix.org> | 2021-11-08 11:34:03 +0000 |
| commit | 58864265d15809e824bb6cb02e4c3a9f533e4aae (patch) | |
| tree | 7578438369ce85ce6c189acee879578ad77ec007 /synapse/rest/media/v1/preview_url_resource.py | |
| parent | Add spans for sync (diff) | |
| parent | Blacklist new sytest validation test (#11270) (diff) | |
| download | synapse-58864265d15809e824bb6cb02e4c3a9f533e4aae.tar.xz | |
Merge remote-tracking branch 'origin/develop' into erikj/slow_sync_diag
Diffstat (limited to 'synapse/rest/media/v1/preview_url_resource.py')
| -rw-r--r-- | synapse/rest/media/v1/preview_url_resource.py | 9 |
1 files changed, 6 insertions, 3 deletions
diff --git a/synapse/rest/media/v1/preview_url_resource.py b/synapse/rest/media/v1/preview_url_resource.py index 278fd901e2..8ca97b5b18 100644 --- a/synapse/rest/media/v1/preview_url_resource.py +++ b/synapse/rest/media/v1/preview_url_resource.py @@ -718,9 +718,12 @@ def decode_body( if not body: return None + # The idea here is that multiple encodings are tried until one works. + # Unfortunately the result is never used and then LXML will decode the string + # again with the found encoding. for encoding in get_html_media_encodings(body, content_type): try: - body_str = body.decode(encoding) + body.decode(encoding) except Exception: pass else: @@ -732,11 +735,11 @@ 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]]: |