From 73d2966e8c10eb6c083a2abacc53f3297d16376e Mon Sep 17 00:00:00 2001
From: jvoisin
Date: Wed, 27 Feb 2019 23:04:38 +0100
Subject: Improve epub support

---
 tests/test_corrupted_files.py | 7 +++++--
 tests/test_libmat2.py         | 6 +++++-
 2 files changed, 10 insertions(+), 3 deletions(-)

(limited to 'tests')

diff --git a/tests/test_corrupted_files.py b/tests/test_corrupted_files.py
index 53c856a..b2cec00 100644
--- a/tests/test_corrupted_files.py
+++ b/tests/test_corrupted_files.py
@@ -253,13 +253,13 @@ class TestCorruptedFiles(unittest.TestCase):
         os.remove('./tests/data/clean.cleaned.html')
 
         with open('./tests/data/clean.html', 'w') as f:
-            f.write('</close>')
+            f.write('</meta>')
         with self.assertRaises(ValueError):
             web.HTMLParser('./tests/data/clean.html')
         os.remove('./tests/data/clean.html')
 
         with open('./tests/data/clean.html', 'w') as f:
-            f.write('<notclosed>')
+            f.write('<meta><a>test</a><set/></meta><title></title><meta>')
         p = web.HTMLParser('./tests/data/clean.html')
         with self.assertRaises(ValueError):
             p.get_meta()
@@ -269,6 +269,9 @@ class TestCorruptedFiles(unittest.TestCase):
         os.remove('./tests/data/clean.html')
 
         with open('./tests/data/clean.html', 'w') as f:
+            f.write('<meta><meta/></meta>')
+            f.write('<title><title>pouet</title></title>')
+            f.write('<title><mysupertag/></title>')
             f.write('<doctitle><br/></doctitle><br/><notclosed>')
         p = web.HTMLParser('./tests/data/clean.html')
         with self.assertRaises(ValueError):
diff --git a/tests/test_libmat2.py b/tests/test_libmat2.py
index 249c56d..f4b1890 100644
--- a/tests/test_libmat2.py
+++ b/tests/test_libmat2.py
@@ -3,6 +3,7 @@
 import unittest
 import shutil
 import os
+import re
 import zipfile
 
 from libmat2 import pdf, images, audio, office, parser_factory, torrent, harmless
@@ -644,7 +645,10 @@ class TestCleaning(unittest.TestCase):
         self.assertTrue(ret)
 
         p = epub.EPUBParser('./tests/data/clean.cleaned.epub')
-        self.assertEqual(p.get_meta(), {})
+        meta = p.get_meta()
+        res = re.match(meta['OEBPS/content.opf']['metadata'], '^<dc:identifier>[0-9a-f-]+</dc:identifier><dc:title /><dc:language />$')
+        self.assertNotEqual(res, False)
+
         self.assertTrue(p.remove_all())
 
         os.remove('./tests/data/clean.epub')
-- 
cgit v1.3