Refactor a bit office get_meta handling
This should make easier to get more metadata from archive-based file formats.
This commit is contained in:
parent
54e50450ad
commit
b9a62d798a
3 changed files with 34 additions and 25 deletions
|
@ -131,9 +131,9 @@ class TestGetMeta(unittest.TestCase):
|
|||
def test_docx(self):
|
||||
p = office.MSOfficeParser('./tests/data/dirty.docx')
|
||||
meta = p.get_meta()
|
||||
self.assertEqual(meta['cp:lastModifiedBy'], 'Julien Voisin')
|
||||
self.assertEqual(meta['dc:creator'], 'julien voisin')
|
||||
self.assertEqual(meta['Application'], 'LibreOffice/5.4.5.1$Linux_X86_64 LibreOffice_project/40m0$Build-1')
|
||||
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_libreoffice(self):
|
||||
p = office.LibreOfficeParser('./tests/data/dirty.odt')
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue