upload: Allow uploads to set charset.

Previously, the `user_file.content_type` only contained the MIME type
of the uploaded file; no other parameters were included, meaning that
a file a client specified as `content-type: text/plain; charset=big5`
would be stored with an `Attachment.content_type` of `text/plain`.

Re-construct the full content-type header from `content_type_extra`,
which includes those parameters.

We do not include a test because Django does not support specifying
such parameters in the upload path.

zerver/lib/upload/__init__.py

@@ -5,6 +5,7 @@ import re
 import unicodedata
 from collections.abc import Callable, Iterator
 from datetime import datetime
+from email.message import EmailMessage
 from typing import IO, Any
 from urllib.parse import unquote, urljoin
 
@@ -80,9 +81,9 @@ def get_file_info(user_file: UploadedFile) -> tuple[str, str]:
     uploaded_file_name = user_file.name
     assert uploaded_file_name is not None
 
-    content_type = user_file.content_type
     # It appears Django's UploadedFile.content_type defaults to an empty string,
     # even though the value is documented as `str | None`. So we check for both.
+    content_type = user_file.content_type
     if content_type is None or content_type == "":
         guessed_type = guess_type(uploaded_file_name)[0]
         if guessed_type is not None:
@@ -92,6 +93,13 @@ def get_file_info(user_file: UploadedFile) -> tuple[str, str]:
             # different content-type from the filename.
             content_type = "application/octet-stream"
 
+    fake_msg = EmailMessage()
+    extras = {}
+    if user_file.content_type_extra:
+        extras = {k: v.decode() if v else None for k, v in user_file.content_type_extra.items()}  # type: ignore[attr-defined]  # https://github.com/typeddjango/django-stubs/pull/2754
+    fake_msg.add_header("content-type", content_type, **extras)
+    content_type = fake_msg["content-type"]
+
     uploaded_file_name = unquote(uploaded_file_name)
 
     return uploaded_file_name, content_type

zerver/tests/test_upload.py

@@ -1,5 +1,6 @@
 import os
 import re
+import tempfile
 from datetime import timedelta
 from io import StringIO
 from unittest import mock
@@ -215,6 +216,26 @@ class FileUploadTest(UploadSerializeMixin, ZulipTestCase):
         self.assertEqual(result["Content-Type"], "image/png")
         consume_response(result)
 
+    def test_content_type_charset_specified(self) -> None:
+        with tempfile.NamedTemporaryFile() as uploaded_file:
+            uploaded_file.write("नाम में क्या रक्खा हे".encode())
+            uploaded_file.seek(0)
+            uploaded_file.content_type = "text/plain; test-key=test_value; charset=big5"  # type: ignore[attr-defined]
+
+            result = self.api_post(
+                self.example_user("hamlet"), "/api/v1/user_uploads", {"file": uploaded_file}
+            )
+
+        self.login("hamlet")
+        response_dict = self.assert_json_success(result)
+        url = response_dict["url"]
+        result = self.client_get(url)
+        self.assertEqual(result.status_code, 200)
+        self.assertEqual(
+            result["Content-Type"], 'text/plain; test-key="test_value"; charset="big5"'
+        )
+        consume_response(result)
+
     # This test will go through the code path for uploading files onto LOCAL storage
     # when Zulip is in DEVELOPMENT mode.
     def test_file_upload_authed(self) -> None: