Page Menu
Home
Software Heritage
Search
Configure Global Search
Log In
Files
F9311750
D896.id2877.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
D896.id2877.diff
View Options
diff --git a/debian/control b/debian/control
--- a/debian/control
+++ b/debian/control
@@ -10,7 +10,7 @@
python3-hypothesis (>= 3.11.0~),
python3-pytest,
python3-pygments,
- python3-magic,
+ python3-magic (>= 2:0.4.13),
python3-pyld,
python3-setuptools,
python3-swh.core (>= 0.0.44~),
diff --git a/requirements.txt b/requirements.txt
--- a/requirements.txt
+++ b/requirements.txt
@@ -2,6 +2,6 @@
pygments
click
chardet
-file_magic
+python-magic >= 0.4.13
pyld
xmltodict
diff --git a/swh/indexer/mimetype.py b/swh/indexer/mimetype.py
--- a/swh/indexer/mimetype.py
+++ b/swh/indexer/mimetype.py
@@ -5,10 +5,13 @@
import magic
-from swh.model import hashutil
-
from .indexer import ContentIndexer, ContentRangeIndexer
+if not hasattr(magic.Magic, 'from_buffer'):
+ raise ImportError(
+ 'Expected "import magic" to import python-magic, but file_magic '
+ 'was imported instead.')
+
def compute_mimetype_encoding(raw_content):
"""Determine mimetype and encoding from the raw content.
@@ -21,10 +24,12 @@
(as bytes).
"""
- r = magic.detect_from_content(raw_content)
+ m = magic.Magic(mime=True, mime_encoding=True)
+ res = m.from_buffer(raw_content)
+ (mimetype, encoding) = res.split('; charset=')
return {
- 'mimetype': r.mime_type,
- 'encoding': r.encoding,
+ 'mimetype': mimetype,
+ 'encoding': encoding,
}
@@ -67,17 +72,11 @@
- **encoding** (bytes): encoding in bytes
"""
- try:
- properties = compute_mimetype_encoding(data)
- properties.update({
- 'id': id,
- 'indexer_configuration_id': self.tool['id'],
- })
- except TypeError:
- self.log.error('Detecting mimetype error for id %s' % (
- hashutil.hash_to_hex(id), ))
- return None
-
+ properties = compute_mimetype_encoding(data)
+ properties.update({
+ 'id': id,
+ 'indexer_configuration_id': self.tool['id'],
+ })
return properties
def persist_index_computations(self, results, policy_update):
diff --git a/swh/indexer/origin_head.py b/swh/indexer/origin_head.py
--- a/swh/indexer/origin_head.py
+++ b/swh/indexer/origin_head.py
@@ -29,8 +29,8 @@
'configuration': {},
}),
'tasks': ('dict', {
- 'revision_metadata': 'revision_metadata',
- 'origin_intrinsic_metadata': 'origin_metadata',
+ 'revision_metadata': 'indexer_revision_metadata',
+ 'origin_intrinsic_metadata': 'indexer_origin_metadata',
})
}
File Metadata
Details
Attached
Mime Type
text/plain
Expires
Wed, Jul 2, 10:30 AM (2 w, 5 d ago)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
3229805
Attached To
D896: Use python-magic instead of file_magic.
Event Timeline
Log In to Comment