def test_policy_unknown(self):
shutil.copy('./tests/data/embedded.docx', './tests/data/clean.docx')
p = office.MSOfficeParser('./tests/data/clean.docx')
with self.assertRaises(ValueError):
p.unknown_member_policy = UnknownMemberPolicy(
'unknown_policy_name_totally_invalid')
os.remove('./tests/data/clean.docx')
def test_office(self):
shutil.copy('./tests/data/office_revision_session_ids.docx',
'./tests/data/clean.docx')
p = office.MSOfficeParser('./tests/data/clean.docx')
meta = p.get_meta()
self.assertIsNotNone(meta)
how_many_rsid = False
with zipfile.ZipFile('./tests/data/clean.docx') as zin:
for item in zin.infolist():
if not item.filename.endswith('.xml'):
continue
num = zin.read(item).decode('utf-8').lower().count('w:rsid')
how_many_rsid += num
self.assertEqual(how_many_rsid, 11)
ret = p.remove_all()
self.assertTrue(ret)
with zipfile.ZipFile('./tests/data/clean.cleaned.docx') as zin:
for item in zin.infolist():
if not item.filename.endswith('.xml'):
continue
num = zin.read(item).decode('utf-8').lower().count('w:rsid')
self.assertEqual(num, 0)
os.remove('./tests/data/clean.docx')
os.remove('./tests/data/clean.cleaned.docx')
def test_office_incomplete(self):
shutil.copy('./tests/data/malformed_content_types.docx',
'./tests/data/clean.docx')
p = office.MSOfficeParser('./tests/data/clean.docx')
self.assertIsNotNone(p)
self.assertFalse(p.remove_all())
os.remove('./tests/data/clean.docx')
def test_policy_keep(self):
shutil.copy('./tests/data/embedded.docx', './tests/data/clean.docx')
p = office.MSOfficeParser('./tests/data/clean.docx')
p.unknown_member_policy = UnknownMemberPolicy.KEEP
self.assertTrue(p.remove_all())
os.remove('./tests/data/clean.docx')
os.remove('./tests/data/clean.cleaned.docx')
def test_policy_keep(self):
shutil.copy('./tests/data/embedded.docx', self.target)
p = office.MSOfficeParser(self.target)
p.unknown_member_policy = UnknownMemberPolicy.KEEP
self.assertTrue(p.remove_all())
os.remove(p.filename)
os.remove(p.output_filename)
def test_office(self):
shutil.copy('./tests/data/dirty.docx', './tests/data/clean.docx')
p = office.MSOfficeParser('./tests/data/clean.docx')
meta = p.get_meta()
self.assertIsNotNone(meta)
ret = p.remove_all()
self.assertTrue(ret)
p = office.MSOfficeParser('./tests/data/clean.cleaned.docx')
self.assertEqual(p.get_meta(), {})
self.assertTrue(p.remove_all())
os.remove('./tests/data/clean.docx')
os.remove('./tests/data/clean.cleaned.docx')
os.remove('./tests/data/clean.cleaned.cleaned.docx')
def test_complex_pptx(self):
target = './tests/data/clean.pptx'
shutil.copy('./tests/data/narrated_powerpoint_presentation.pptx',
target)
p = office.MSOfficeParser(target)
self.assertTrue(p.remove_all())
os.remove(target)
os.remove(p.output_filename)
def test_office(self):
shutil.copy('./tests/data/dirty.docx', './tests/data/clean.docx')
p = office.MSOfficeParser('./tests/data/clean.docx')
meta = p.get_meta()
self.assertIsNotNone(meta)
self.assertEqual(meta['word/media/image1.png']['Comment'], 'This is a comment, be careful!')
ret = p.remove_all()
self.assertTrue(ret)
p = office.MSOfficeParser('./tests/data/clean.cleaned.docx')
self.assertEqual(p.get_meta(), {})
self.__check_zip_meta(p)
self.__check_deep_meta(p)
os.remove('./tests/data/clean.docx')
os.remove('./tests/data/clean.cleaned.docx')
def test_docx(self):
p = office.MSOfficeParser('./tests/data/dirty.docx')
meta = p.get_meta()
self.assertEqual(meta['docProps/core.xml']['cp:lastModifiedBy'],
'Julien Voisin')
self.assertEqual(meta['docProps/core.xml']['dc:creator'],
'julien voisin')
self.assertEqual(
meta['docProps/app.xml']['Application'],
'LibreOffice/5.4.5.1$Linux_X86_64 LibreOffice_project/40m0$Build-1'
)
def test_msoffice(self):
with zipfile.ZipFile('./tests/data/revision.docx') as zipin:
c = zipin.open('word/document.xml')
content = c.read()
r = b'<w:ins w:id="1" w:author="Unknown Author" w:date="2018-06-28T23:48:00Z">'
self.assertIn(r, content)
shutil.copy('./tests/data/revision.docx',
'./tests/data/revision_clean.docx')
p = office.MSOfficeParser('./tests/data/revision_clean.docx')
self.assertTrue(p.remove_all())
with zipfile.ZipFile(
'./tests/data/revision_clean.cleaned.docx') as zipin:
c = zipin.open('word/document.xml')
content = c.read()
r = b'<w:ins w:id="1" w:author="Unknown Author" w:date="2018-06-28T23:48:00Z">'
self.assertNotIn(r, content)
os.remove('./tests/data/revision_clean.docx')
os.remove('./tests/data/revision_clean.cleaned.docx')
def test_docx_with_py(self):
shutil.copy('./tests/data/embedded.docx', './tests/data/clean.docx')
p = office.MSOfficeParser('./tests/data/clean.docx')
self.assertFalse(p.remove_all())
os.remove('./tests/data/clean.docx')
def test_office_broken(self):
shutil.copy('./tests/data/broken_xml_content_types.docx',
'./tests/data/clean.docx')
with self.assertRaises(ValueError):
office.MSOfficeParser('./tests/data/clean.docx')
os.remove('./tests/data/clean.docx')
def test_docx(self):
shutil.copy('./tests/data/dirty.png', './tests/data/clean.docx')
with self.assertRaises(ValueError):
office.MSOfficeParser('./tests/data/clean.docx')
os.remove('./tests/data/clean.docx')
def test_office_incomplete(self):
shutil.copy('./tests/data/malformed_content_types.docx',
'./tests/data/clean.docx')
with self.assertRaises(ValueError):
office.MSOfficeParser('./tests/data/clean.docx')
os.remove('./tests/data/clean.docx')
