security-and-privacy/mat2
security-and-privacy/mat2
1
0
Fork 0
mirror of synced 2025-02-22 10:28:03 +01:00
Code Releases Activity

Significantly improve portability

Browse Source
This commit is contained in:
jvoisin 2025-01-09 01:21:31 +01:00
parent 70d236a062
commit 6c966f2afa
4 changed files with 18 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
libmat2/office.py
View File

@ -525,7 +525,7 @@ class MSOfficeParser(ZipParser):
# see: https://docs.microsoft.com/en-us/dotnet/framework/wpf/advanced/mc-ignorable-attribute # see: https://docs.microsoft.com/en-us/dotnet/framework/wpf/advanced/mc-ignorable-attribute
with open(full_path, 'rb') as f: with open(full_path, 'rb') as f:
text = f.read() text = f.read()
out = re.sub(b'mc:Ignorable="[^"]*"', b'', text, 1) out = re.sub(b'mc:Ignorable="[^"]*"', b'', text, count=1)
with open(full_path, 'wb') as f: with open(full_path, 'wb') as f:
f.write(out) f.write(out)

4
libmat2/pdf.py
View File

@ -136,8 +136,8 @@ class PDFParser(abstract.AbstractParser):
# It should(tm) be alright though, because cairo's output format # It should(tm) be alright though, because cairo's output format
# for metadata is fixed. # for metadata is fixed.
with open(out_file, 'rb') as f: with open(out_file, 'rb') as f:
out = re.sub(rb'<<[\s\n]*/Producer.*?>>', b' << >>', f.read(), 0, out = re.sub(rb'<<[\s\n]*/Producer.*?>>', b' << >>', f.read(),
re.DOTALL | re.IGNORECASE) count=0, flags=re.DOTALL | re.IGNORECASE)
with open(out_file, 'wb') as f: with open(out_file, 'wb') as f:
f.write(out) f.write(out)

2
libmat2/web.py
View File

@ -20,7 +20,7 @@ class CSSParser(abstract.AbstractParser):
content = f.read() content = f.read()
except UnicodeDecodeError: # pragma: no cover except UnicodeDecodeError: # pragma: no cover
raise ValueError raise ValueError
cleaned = re.sub(r'/\*.*?\*/', '', content, 0, self.flags) cleaned = re.sub(r'/\*.*?\*/', '', content, count=0, flags=self.flags)
with open(self.output_filename, 'w', encoding='utf-8') as f: with open(self.output_filename, 'w', encoding='utf-8') as f:
f.write(cleaned) f.write(cleaned)
return True return True

17
tests/test_libmat2.py
View File

@ -508,8 +508,11 @@ class TestCleaning(unittest.TestCase):
'TrackID': 1, 'TrackID': 1,
'TrackLayer': 0, 'TrackLayer': 0,
'TransferCharacteristics': 'BT.709', 'TransferCharacteristics': 'BT.709',
'VideoFullRangeFlag': 0, 'VideoFullRangeFlag': 'Limited',
}, },
'extra_expected_meta': {
'VideoFullRangeFlag': 0,
}
},{ },{
'name': 'wmv', 'name': 'wmv',
'ffmpeg': 1, 'ffmpeg': 1,
@ -522,7 +525,10 @@ class TestCleaning(unittest.TestCase):
'name': 'heic', 'name': 'heic',
'parser': images.HEICParser, 'parser': images.HEICParser,
'meta': {}, 'meta': {},
'expected_meta': {}, 'expected_meta': {
'ExifByteOrder': 'Big-endian (Motorola, MM)',
'Warning': 'Bad IFD0 directory',
},
} }
] ]
@ -558,7 +564,12 @@ class TestCleaning(unittest.TestCase):
if meta: if meta:
for k, v in p2.get_meta().items(): for k, v in p2.get_meta().items():
self.assertIn(k, case['expected_meta'], '"%s" is not in "%s" (%s)' % (k, case['expected_meta'], case['name'])) self.assertIn(k, case['expected_meta'], '"%s" is not in "%s" (%s)' % (k, case['expected_meta'], case['name']))
self.assertIn(str(case['expected_meta'][k]), str(v)) if str(case['expected_meta'][k]) in str(v):
continue
if 'extra_expected_meta' in case and k in case['extra_expected_meta']:
if str(case['extra_expected_meta'][k]) in str(v):
continue
self.assertTrue(False, "got a different value (%s) than excepted (%s) for %s" % (str(v), meta, k))
self.assertTrue(p2.remove_all()) self.assertTrue(p2.remove_all())
os.remove(target) os.remove(target)