diff options
Diffstat (limited to 'synapse')
| -rw-r--r-- | synapse/__init__.py | 2 | ||||
| -rw-r--r-- | synapse/rest/media/v1/preview_url_resource.py | 9 |
2 files changed, 7 insertions, 4 deletions
diff --git a/synapse/__init__.py b/synapse/__init__.py index 355b36fc63..5ef34bce40 100644 --- a/synapse/__init__.py +++ b/synapse/__init__.py @@ -47,7 +47,7 @@ try: except ImportError: pass -__version__ = "1.46.0rc1" +__version__ = "1.46.0" if bool(os.environ.get("SYNAPSE_TEST_PATCH_LOG_CONTEXTS", False)): # We import here so that we don't have to install a bunch of deps when 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]]: |