Fixed #27007 -- Handled non-UTF-8 bytes objects for text/* attachments.

The fallback logic which allows non-UTF-8 encoded files to be passed to
attach_file() even when a `text/*` mime type has been specified is
moved to attach(). Both functions now fall back to a content type of
`application/octet-stream`.

A side effect is that a file's content is decoded in memory instead of
opening it in text mode and reading it into a string.

Some mimetype-related logic in _create_attachment() has become
obsolete as the code moved from attach_file() to attach() already
handles this.

1 files changed, 25 insertions, 0 deletions

diff --git a/tests/mail/tests.py b/tests/mail/tests.py
index 0f0eb5bdf1..3d1a74518f 100644
--- a/tests/mail/tests.py
+++ b/tests/mail/tests.py
@@ -422,6 +422,31 @@ class MailTests(HeadersCheckMixin, SimpleTestCase):
         self.assertEqual(content, b'file content')
         self.assertEqual(mimetype, 'text/plain')
 
+    def test_attach_utf8_text_as_bytes(self):
+        """
+        Non-ASCII characters encoded as valid UTF-8 are correctly transported
+        and decoded.
+        """
+        msg = EmailMessage('subject', 'body', 'from@example.com', ['to@example.com'])
+        msg.attach('file.txt', b'\xc3\xa4')  # UTF-8 encoded a umlaut.
+        filename, content, mimetype = self.get_decoded_attachments(msg)[0]
+        self.assertEqual(filename, 'file.txt')
+        self.assertEqual(content, b'\xc3\xa4')
+        self.assertEqual(mimetype, 'text/plain')
+
+    def test_attach_non_utf8_text_as_bytes(self):
+        """
+        Binary data that can't be decoded as UTF-8 overrides the MIME type
+        instead of decoding the data.
+        """
+        msg = EmailMessage('subject', 'body', 'from@example.com', ['to@example.com'])
+        msg.attach('file.txt', b'\xff')  # Invalid UTF-8.
+        filename, content, mimetype = self.get_decoded_attachments(msg)[0]
+        self.assertEqual(filename, 'file.txt')
+        # Content should be passed through unmodified.
+        self.assertEqual(content, b'\xff')
+        self.assertEqual(mimetype, 'application/octet-stream')
+
     def test_dummy_backend(self):
         """
         Make sure that dummy backends returns correct number of sent messages