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This repository has been archived by the owner on Apr 26, 2024.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

Commit

Permalink
Set charset to utf-8 when adding headers for certain text content typ…
Browse files Browse the repository at this point in the history
…es (#7044)

Fixes #7043
  • Loading branch information
TheStranjer authored Mar 17, 2020
1 parent 7581d30 commit 5e477c1
Show file tree
Hide file tree
Showing 2 changed files with 25 additions and 1 deletion.
1 change: 1 addition & 0 deletions changelog.d/7044.bugfix
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Fix a bug that renders UTF-8 text files incorrectly when loaded from media. Contributed by @TheStranjer.
25 changes: 24 additions & 1 deletion synapse/rest/media/v1/_base.py
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,22 @@

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:
Expand Down Expand Up @@ -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*`.
#
Expand Down

0 comments on commit 5e477c1

Please sign in to comment.