From fc924239febb3f186585d9ea6c263e1cb7dc690d Mon Sep 17 00:00:00 2001
From: jvoisin
Date: Sun, 1 Sep 2019 13:34:26 +0200
Subject: Add a test for nsid cleaning

---
 tests/test_deep_cleaning.py | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

(limited to 'tests/test_deep_cleaning.py')

diff --git a/tests/test_deep_cleaning.py b/tests/test_deep_cleaning.py
index ccd4955..aab46c7 100644
--- a/tests/test_deep_cleaning.py
+++ b/tests/test_deep_cleaning.py
@@ -137,3 +137,34 @@ class TestRsidRemoval(unittest.TestCase):
 
         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')
-- 
cgit v1.3