From 3d2842802c4cd4afb749856d30c58f64626a51ce Mon Sep 17 00:00:00 2001
From: jvoisin
Date: Thu, 20 Sep 2018 01:13:59 +0200
Subject: Split the tests

---
 tests/test_deep_cleaning.py | 72 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 72 insertions(+)
 create mode 100644 tests/test_deep_cleaning.py

(limited to 'tests/test_deep_cleaning.py')

diff --git a/tests/test_deep_cleaning.py b/tests/test_deep_cleaning.py
new file mode 100644
index 0000000..8c6f257
--- /dev/null
+++ b/tests/test_deep_cleaning.py
@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+
+import unittest
+import shutil
+import os
+import zipfile
+import tempfile
+
+from libmat2 import office, parser_factory
+
+class TestZipMetadata(unittest.TestCase):
+    def __check_deep_meta(self, p):
+        tempdir = tempfile.mkdtemp()
+        zipin = zipfile.ZipFile(p.filename)
+        zipin.extractall(tempdir)
+
+        for subdir, dirs, files in os.walk(tempdir):
+            for f in files:
+                complete_path = os.path.join(subdir, f)
+                inside_p, _ = parser_factory.get_parser(complete_path)
+                if inside_p is None:
+                    continue
+                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():
+            self.assertEqual(item.comment, b'')
+            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)
+
+        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_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)
+
+        ret = p.remove_all()
+        self.assertTrue(ret)
+
+        p = office.LibreOfficeParser('./tests/data/clean.cleaned.odt')
+        self.assertEqual(p.get_meta(), {})
+
+        self.__check_zip_meta(p)
+        self.__check_deep_meta(p)
+
+        os.remove('./tests/data/clean.odt')
+        os.remove('./tests/data/clean.cleaned.odt')
-- 
cgit v1.3