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

1 files changed, 4 insertions, 2 deletions

diff --git a/synapse/rest/media/v1/preview_url_resource.py b/synapse/rest/media/v1/preview_url_resource.py

index 172212ee3a..0f051d4041 100644
--- a/synapse/rest/media/v1/preview_url_resource.py
+++ b/synapse/rest/media/v1/preview_url_resource.py
@@ -58,9 +58,11 @@ if TYPE_CHECKING:
 
 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)