Page Menu
Home
Software Heritage
Search
Configure Global Search
Log In
Files
F7147832
D2766.id9866.diff
No One
Temporary
Actions
View File
Edit File
Delete File
View Transforms
Subscribe
Mute Notifications
Award Token
Flag For Later
Size
2 KB
Subscribers
None
D2766.id9866.diff
View Options
diff --git a/swh/indexer/mimetype.py b/swh/indexer/mimetype.py
--- a/swh/indexer/mimetype.py
+++ b/swh/indexer/mimetype.py
@@ -26,7 +26,10 @@
"""
m = magic.Magic(mime=True, mime_encoding=True)
res = m.from_buffer(raw_content)
- (mimetype, encoding) = res.split('; charset=')
+ try:
+ mimetype, encoding = res.split('; charset=')
+ except ValueError:
+ mimetype, encoding = res, ''
return {
'mimetype': mimetype,
'encoding': encoding,
diff --git a/swh/indexer/tests/test_mimetype.py b/swh/indexer/tests/test_mimetype.py
--- a/swh/indexer/tests/test_mimetype.py
+++ b/swh/indexer/tests/test_mimetype.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2017-2018 The Software Heritage developers
+# Copyright (C) 2017-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
@@ -18,18 +18,19 @@
)
-class BasicTest(unittest.TestCase):
- def test_compute_mimetype_encoding(self):
- """Compute mimetype encoding should return results"""
- for _input, _mimetype, _encoding in [
- ('du français'.encode(), 'text/plain', 'utf-8'),
- (b'def __init__(self):', 'text/x-python', 'us-ascii')]:
-
- actual_result = compute_mimetype_encoding(_input)
- self.assertEqual(actual_result, {
- 'mimetype': _mimetype,
- 'encoding': _encoding
- })
+def test_compute_mimetype_encoding():
+ """Compute mimetype encoding should return results"""
+ for _input, _mimetype, _encoding in [
+ ('du français'.encode(), 'text/plain', 'utf-8'),
+ (b'def __init__(self):', 'text/x-python', 'us-ascii'),
+ (b'\xff\xfe\x00\x00\x00\x00\xff\xfe\xff\xff',
+ 'application/octet-stream', '')
+ ]:
+ actual_result = compute_mimetype_encoding(_input)
+ assert actual_result == {
+ 'mimetype': _mimetype,
+ 'encoding': _encoding
+ }
CONFIG = {
File Metadata
Details
Attached
Mime Type
text/plain
Expires
Thu, Jan 23, 1:40 AM (1 w, 3 d ago)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
3222794
Attached To
D2766: mimetype: Make the parsing more resilient
Event Timeline
Log In to Comment