diff --git a/libmat2/video.py b/libmat2/video.py
index a5029c031454bf6df9c0c91ccfdac4b9a513a9f4..825df92e766e83c7b18b076bd28e878bdf4fec4d 100644
--- a/libmat2/video.py
+++ b/libmat2/video.py
@@ -9,7 +9,14 @@ from . import exiftool
class AbstractFFmpegParser(exiftool.ExiftoolParser):
""" Abstract parser for all FFmpeg-based ones, mainly for video. """
+ # Some fileformats have mandatory metadata fields
+ meta_key_value_whitelist = {} # type: Dict[str, Union[str, int]]
+
def remove_all(self) -> bool:
+ if self.meta_key_value_whitelist:
+ logging.warning('The format of "%s" (video/mp4) has some mandatory '
+ 'metadata fields; mat2 filled them with standard '
+ 'data.', self.filename)
cmd = [_get_ffmpeg_path(),
'-i', self.filename, # input file
'-y', # overwrite existing output file
@@ -31,6 +38,41 @@ class AbstractFFmpegParser(exiftool.ExiftoolParser):
return False
return True
+ def get_meta(self) -> Dict[str, Union[str, dict]]:
+ meta = super().get_meta()
+
+ ret = dict() # type: Dict[str, Union[str, dict]]
+ for key, value in meta.items():
+ if key in self.meta_key_value_whitelist.keys():
+ if value == self.meta_key_value_whitelist[key]:
+ continue
+ ret[key] = value
+ return ret
+
+
+class WMVParser(AbstractFFmpegParser):
+ mimetypes = {'video/x-ms-wmv', }
+ meta_whitelist = {'AudioChannels', 'AudioCodecID', 'AudioCodecName',
+ 'ErrorCorrectionType', 'AudioSampleRate', 'DataPackets',
+ 'Directory', 'Duration', 'ExifToolVersion',
+ 'FileAccessDate', 'FileInodeChangeDate', 'FileLength',
+ 'FileModifyDate', 'FileName', 'FilePermissions',
+ 'FileSize', 'FileType', 'FileTypeExtension',
+ 'FrameCount', 'FrameRate', 'ImageHeight', 'ImageSize',
+ 'ImageWidth', 'MIMEType', 'MaxBitrate', 'MaxPacketSize',
+ 'Megapixels', 'MinPacketSize', 'Preroll', 'SendDuration',
+ 'SourceFile', 'StreamNumber', 'VideoCodecName', }
+ meta_key_value_whitelist = { # some metadata are mandatory :/
+ 'AudioCodecDescription': '',
+ 'CreationDate': '0000:00:00 00:00:00Z',
+ 'FileID': '00000000-0000-0000-0000-000000000000',
+ 'Flags': 2, # FIXME: What is this? Why 2?
+ 'ModifyDate': '0000:00:00 00:00:00',
+ 'TimeOffset': '0 s',
+ 'VideoCodecDescription': '',
+ 'StreamType': 'Audio',
+ }
+
class AVIParser(AbstractFFmpegParser):
mimetypes = {'video/x-msvideo', }
@@ -51,6 +93,7 @@ class AVIParser(AbstractFFmpegParser):
'SampleRate', 'AvgBytesPerSec', 'BitsPerSample',
'Duration', 'ImageSize', 'Megapixels'}
+
class MP4Parser(AbstractFFmpegParser):
mimetypes = {'video/mp4', }
meta_whitelist = {'AudioFormat', 'AvgBitrate', 'Balance', 'TrackDuration',
@@ -84,23 +127,6 @@ class MP4Parser(AbstractFFmpegParser):
'TrackVolume': '0.00%',
}
- def remove_all(self) -> bool:
- logging.warning('The format of "%s" (video/mp4) has some mandatory '
- 'metadata fields; mat2 filled them with standard data.',
- self.filename)
- return super().remove_all()
-
- def get_meta(self) -> Dict[str, Union[str, dict]]:
- meta = super().get_meta()
-
- ret = dict() # type: Dict[str, Union[str, dict]]
- for key, value in meta.items():
- if key in self.meta_key_value_whitelist.keys():
- if value == self.meta_key_value_whitelist[key]:
- continue
- ret[key] = value
- return ret
-
def _get_ffmpeg_path() -> str: # pragma: no cover
ffmpeg_path = '/usr/bin/ffmpeg'
diff --git a/tests/data/dirty.wmv b/tests/data/dirty.wmv
new file mode 100644
index 0000000000000000000000000000000000000000..b007f4c4924e49f1548f454b2b0d4173daa487e7
Binary files /dev/null and b/tests/data/dirty.wmv differ
diff --git a/tests/test_libmat2.py b/tests/test_libmat2.py
index e3072a8b5ec1f8f481ee8f6eff00b2abaaf7c290..9152b2fd373036a8890ea3af145b68fde96c8f75 100644
--- a/tests/test_libmat2.py
+++ b/tests/test_libmat2.py
@@ -165,6 +165,11 @@ class TestGetMeta(unittest.TestCase):
self.assertEqual(meta['tests/data/dirty.docx']['word/media/image1.png']['Comment'], 'This is a comment, be careful!')
os.remove('./tests/data/dirty.zip')
+ def test_wmv(self):
+ p, mimetype = parser_factory.get_parser('./tests/data/dirty.wmv')
+ self.assertEqual(mimetype, 'video/x-ms-wmv')
+ meta = p.get_meta()
+ self.assertEqual(meta['EncodingSettings'], 'Lavf52.103.0')
class TestRemovingThumbnails(unittest.TestCase):
def test_odt(self):
@@ -544,3 +549,26 @@ class TestCleaning(unittest.TestCase):
os.remove('./tests/data/clean.mp4')
os.remove('./tests/data/clean.cleaned.mp4')
os.remove('./tests/data/clean.cleaned.cleaned.mp4')
+
+ def test_wmv(self):
+ try:
+ video._get_ffmpeg_path()
+ except RuntimeError:
+ raise unittest.SkipTest
+
+ shutil.copy('./tests/data/dirty.wmv', './tests/data/clean.wmv')
+ p = video.WMVParser('./tests/data/clean.wmv')
+
+ meta = p.get_meta()
+ self.assertEqual(meta['EncodingSettings'], 'Lavf52.103.0')
+
+ ret = p.remove_all()
+ self.assertTrue(ret)
+
+ p = video.WMVParser('./tests/data/clean.cleaned.wmv')
+ self.assertNotIn('EncodingSettings', p.get_meta())
+ self.assertTrue(p.remove_all())
+
+ os.remove('./tests/data/clean.wmv')
+ os.remove('./tests/data/clean.cleaned.wmv')
+ os.remove('./tests/data/clean.cleaned.cleaned.wmv')