1
0
Fork 0
mirror of synced 2025-07-04 04:17:29 +02:00

Implement lightweight cleaning for png and tiff

This commit is contained in:
jvoisin 2018-10-23 16:14:21 +02:00
parent 38df679a88
commit f1a071d460
7 changed files with 111 additions and 43 deletions

View file

@ -212,42 +212,6 @@ class TestRevisionsCleaning(unittest.TestCase):
os.remove('./tests/data/revision_clean.docx')
os.remove('./tests/data/revision_clean.cleaned.docx')
class TestLightWeightCleaning(unittest.TestCase):
def test_pdf(self):
shutil.copy('./tests/data/dirty.pdf', './tests/data/clean.pdf')
p = pdf.PDFParser('./tests/data/clean.pdf')
meta = p.get_meta()
self.assertEqual(meta['producer'], 'pdfTeX-1.40.14')
p.lightweight_cleaning = True
ret = p.remove_all()
self.assertTrue(ret)
p = pdf.PDFParser('./tests/data/clean.cleaned.pdf')
expected_meta = {'creation-date': -1, 'format': 'PDF-1.5', 'mod-date': -1}
self.assertEqual(p.get_meta(), expected_meta)
os.remove('./tests/data/clean.pdf')
os.remove('./tests/data/clean.cleaned.pdf')
def test_png(self):
shutil.copy('./tests/data/dirty.png', './tests/data/clean.png')
p = images.PNGParser('./tests/data/clean.png')
meta = p.get_meta()
self.assertEqual(meta['Comment'], 'This is a comment, be careful!')
p.lightweight_cleaning = True
ret = p.remove_all()
self.assertTrue(ret)
p = images.PNGParser('./tests/data/clean.cleaned.png')
self.assertEqual(p.get_meta(), {})
os.remove('./tests/data/clean.png')
os.remove('./tests/data/clean.cleaned.png')
class TestCleaning(unittest.TestCase):
def test_pdf(self):
shutil.copy('./tests/data/dirty.pdf', './tests/data/clean.pdf')