Skip to content
Snippets Groups Projects
Unverified Commit 5e477c1d authored by The Stranjer's avatar The Stranjer Committed by GitHub
Browse files

Set charset to utf-8 when adding headers for certain text content types (#7044)

Fixes #7043
parent 7581d30e
No related branches found
No related tags found
No related merge requests found
Fix a bug that renders UTF-8 text files incorrectly when loaded from media. Contributed by @TheStranjer.
......@@ -30,6 +30,22 @@ from synapse.util.stringutils import is_ascii
logger = logging.getLogger(__name__)
# list all text content types that will have the charset default to UTF-8 when
# none is given
TEXT_CONTENT_TYPES = [
"text/css",
"text/csv",
"text/html",
"text/calendar",
"text/plain",
"text/javascript",
"application/json",
"application/ld+json",
"application/rtf",
"image/svg+xml",
"text/xml",
]
def parse_media_id(request):
try:
......@@ -96,7 +112,14 @@ def add_file_headers(request, media_type, file_size, upload_name):
def _quote(x):
return urllib.parse.quote(x.encode("utf-8"))
request.setHeader(b"Content-Type", media_type.encode("UTF-8"))
# Default to a UTF-8 charset for text content types.
# ex, uses UTF-8 for 'text/css' but not 'text/css; charset=UTF-16'
if media_type.lower() in TEXT_CONTENT_TYPES:
content_type = media_type + "; charset=UTF-8"
else:
content_type = media_type
request.setHeader(b"Content-Type", content_type.encode("UTF-8"))
if upload_name:
# RFC6266 section 4.1 [1] defines both `filename` and `filename*`.
#
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment