tests/test_deep_cleaning.py

@@ -23,7 +23,6 @@ class TestZipMetadata(unittest.TestCase):
                 self.assertEqual(inside_p.get_meta(), {})
         shutil.rmtree(tempdir)
 
-
     def __check_zip_meta(self, p):
         zipin = zipfile.ZipFile(p.filename)
         for item in zipin.infolist():
@@ -31,13 +30,13 @@ class TestZipMetadata(unittest.TestCase):
             self.assertEqual(item.date_time, (1980, 1, 1, 0, 0, 0))
             self.assertEqual(item.create_system, 3)  # 3 is UNIX
 
-
     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)
@@ -51,7 +50,6 @@ class TestZipMetadata(unittest.TestCase):
         os.remove('./tests/data/clean.docx')
         os.remove('./tests/data/clean.cleaned.docx')
 
-
     def test_libreoffice(self):
         shutil.copy('./tests/data/dirty.odt', './tests/data/clean.odt')
         p = office.LibreOfficeParser('./tests/data/clean.odt')
@@ -70,3 +68,103 @@ class TestZipMetadata(unittest.TestCase):
 
         os.remove('./tests/data/clean.odt')
         os.remove('./tests/data/clean.cleaned.odt')
+
+
+class TestZipOrder(unittest.TestCase):
+    def test_libreoffice(self):
+        shutil.copy('./tests/data/dirty.odt', './tests/data/clean.odt')
+        p = office.LibreOfficeParser('./tests/data/clean.odt')
+
+        meta = p.get_meta()
+        self.assertIsNotNone(meta)
+
+        is_unordered = False
+        with zipfile.ZipFile('./tests/data/clean.odt') as zin:
+            previous_name = ''
+            for item in zin.infolist():
+                if previous_name == '':
+                    if item.filename == 'mimetype':
+                        continue
+                    previous_name = item.filename
+                    continue
+                elif item.filename < previous_name:
+                    is_unordered = True
+                    break
+        self.assertTrue(is_unordered)
+
+        ret = p.remove_all()
+        self.assertTrue(ret)
+
+        with zipfile.ZipFile('./tests/data/clean.cleaned.odt') as zin:
+            previous_name = ''
+            for item in zin.infolist():
+                if previous_name == '':
+                    if item.filename == 'mimetype':
+                        continue
+                    previous_name = item.filename
+                    continue
+                self.assertGreaterEqual(item.filename, previous_name)
+
+        os.remove('./tests/data/clean.odt')
+        os.remove('./tests/data/clean.cleaned.odt')
+
+class TestRsidRemoval(unittest.TestCase):
+    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')
+
+
+class TestNsidRemoval(unittest.TestCase):
+    def test_office(self):
+        shutil.copy('./tests/data/dirty_with_nsid.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, 1190)
+
+        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:nsid')
+                self.assertEqual(num, 0)
+
+        os.remove('./tests/data/clean.docx')
+        os.remove('./tests/data/clean.cleaned.docx')