From 55214206b5f0f1c12fec378967f89ef4cb5674f9 Mon Sep 17 00:00:00 2001
From: jvoisin
Date: Wed, 27 Feb 2019 23:53:07 +0100
Subject: Improve the previous commit

- More tests
- More documentation
- Minor code cleanup
---
 tests/test_corrupted_files.py |  4 +---
 tests/test_libmat2.py         | 27 +++++++++++++++++++++++++++
 2 files changed, 28 insertions(+), 3 deletions(-)

(limited to 'tests')

diff --git a/tests/test_corrupted_files.py b/tests/test_corrupted_files.py
index b2cec00..4a16d51 100644
--- a/tests/test_corrupted_files.py
+++ b/tests/test_corrupted_files.py
@@ -269,9 +269,6 @@ 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):
@@ -281,6 +278,7 @@ class TestCorruptedFiles(unittest.TestCase):
             p.remove_all()
         os.remove('./tests/data/clean.html')
 
+
     def test_epub(self):
         with zipfile.ZipFile('./tests/data/clean.epub', 'w') as zout:
             zout.write('./tests/data/dirty.jpg', 'OEBPS/content.opf')
diff --git a/tests/test_libmat2.py b/tests/test_libmat2.py
index f4b1890..46e234e 100644
--- a/tests/test_libmat2.py
+++ b/tests/test_libmat2.py
@@ -633,6 +633,33 @@ class TestCleaning(unittest.TestCase):
         os.remove('./tests/data/clean.cleaned.html')
         os.remove('./tests/data/clean.cleaned.cleaned.html')
 
+        with open('./tests/data/clean.html', 'w') as f:
+            f.write('<title><title><pouet/><meta/></title></title><test/>')
+        p = web.HTMLParser('./tests/data/clean.html')
+        self.assertTrue(p.remove_all())
+        with open('./tests/data/clean.cleaned.html', 'r') as f:
+            self.assertEqual(f.read(), '<title></title><test/>')
+        os.remove('./tests/data/clean.html')
+        os.remove('./tests/data/clean.cleaned.html')
+
+        with open('./tests/data/clean.html', 'w') as f:
+            f.write('<test><title>Some<b>metadata</b><br/></title></test>')
+        p = web.HTMLParser('./tests/data/clean.html')
+        self.assertTrue(p.remove_all())
+        with open('./tests/data/clean.cleaned.html', 'r') as f:
+            self.assertEqual(f.read(), '<test><title></title></test>')
+        os.remove('./tests/data/clean.html')
+        os.remove('./tests/data/clean.cleaned.html')
+
+        with open('./tests/data/clean.html', 'w') as f:
+            f.write('<meta><meta/></meta>')
+        p = web.HTMLParser('./tests/data/clean.html')
+        self.assertTrue(p.remove_all())
+        with open('./tests/data/clean.cleaned.html', 'r') as f:
+            self.assertEqual(f.read(), '')
+        os.remove('./tests/data/clean.html')
+        os.remove('./tests/data/clean.cleaned.html')
+
 
     def test_epub(self):
         shutil.copy('./tests/data/dirty.epub', './tests/data/clean.epub')
-- 
cgit v1.3