bit longer author field
[librarian.git] / tests / test_html.py
old mode 100755 (executable)
new mode 100644 (file)
index dcb19fc..1d698fd
@@ -1,60 +1,55 @@
-# -*- coding: utf-8 -*-
+# This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
+# Copyright © Fundacja Wolne Lektury. See NOTICE for more information.
 #
-#    This file is part of Librarian.
-#
-#    Copyright © 2008,2009,2010 Fundacja Nowoczesna Polska <fundacja@nowoczesnapolska.org.pl>
-#    
-#    For full list of contributors see AUTHORS file. 
-#
-#    This program is free software: you can redistribute it and/or modify
-#    it under the terms of the GNU Affero General Public License as published by
-#    the Free Software Foundation, either version 3 of the License, or
-#    (at your option) any later version.
-#
-#    This program is distributed in the hope that it will be useful,
-#    but WITHOUT ANY WARRANTY; without even the implied warranty of
-#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-#    GNU Affero General Public License for more details.
-#
-#    You should have received a copy of the GNU Affero General Public License
-#    along with this program.  If not, see <http://www.gnu.org/licenses/>.
-#
-from librarian import html, NoDublinCore
-from nose.tools import *
-from utils import get_fixture, remove_output_file
-
-
-def teardown_transform():
-    remove_output_file('text', 'asnyk_miedzy_nami.html')
-
-
-@with_setup(None, teardown_transform)
-def test_transform():
-    output_file_path = get_fixture('text', 'asnyk_miedzy_nami.html')
-    expected_output_file_path = get_fixture('text', 'asnyk_miedzy_nami_expected.html')
-    
-    html.transform(
-        get_fixture('text', 'asnyk_miedzy_nami.xml'),
-        output_file_path,
-    )
-    
-    assert_equal(file(output_file_path).read(), file(expected_output_file_path).read())
-
-
-@with_setup(None, teardown_transform)
-@raises(NoDublinCore)
-def test_no_dublincore():
-    html.transform(
-        get_fixture('text', 'asnyk_miedzy_nami_nodc.xml'),
-        get_fixture('text', 'asnyk_miedzy_nami_nodc.html'),
-    )
-
-
-@with_setup(None, teardown_transform)
-def test_passing_parse_dublincore_to_transform():
-    """Passing parse_dublincore=False to transform omits DublinCore parsing."""
-    html.transform(
-        get_fixture('text', 'asnyk_miedzy_nami_nodc.xml'),
-        get_fixture('text', 'asnyk_miedzy_nami.html'),
-        parse_dublincore=False,
-    )
+import re
+from unittest import TestCase
+from librarian import NoDublinCore
+from librarian.builders import builders
+from librarian.document import WLDocument
+from librarian.parser import WLDocument as LegacyWLDocument
+from .utils import get_fixture
+
+
+class TransformTest(TestCase):
+    maxDiff = None
+
+    def test_transform_legacy(self):
+        expected_output_file_path = get_fixture('text', 'asnyk_miedzy_nami_expected.legacy.html')
+
+        html = LegacyWLDocument.from_file(
+            get_fixture('text', 'miedzy-nami-nic-nie-bylo.xml')
+        ).as_html().get_bytes().decode('utf-8')
+
+        html = re.sub(r'idm\d+', 'idmNNN', html)
+        with open(expected_output_file_path) as f:
+            self.assertEqual(f.read(), html)
+
+    def test_transform(self):
+        expected_output_file_path = get_fixture('text', 'asnyk_miedzy_nami_expected.html')
+        html = WLDocument(
+            filename=get_fixture('text', 'miedzy-nami-nic-nie-bylo.xml')
+        ).build(builders['html']).get_bytes().decode('utf-8')
+
+        with open(expected_output_file_path) as f:
+            self.assertEqual(html, f.read())
+
+    def test_no_dublincore(self):
+        with self.assertRaises(NoDublinCore):
+            LegacyWLDocument.from_file(
+                get_fixture('text', 'asnyk_miedzy_nami_nodc.xml')
+            ).as_html()
+
+    def test_passing_parse_dublincore_to_transform(self):
+        """Passing parse_dublincore=False to transform omits DublinCore parsing."""
+        LegacyWLDocument.from_file(
+            get_fixture('text', 'asnyk_miedzy_nami_nodc.xml'),
+            parse_dublincore=False,
+        ).as_html()
+
+    def test_empty(self):
+        self.assertIsNone(
+            LegacyWLDocument.from_bytes(
+                b'<utwor />',
+                parse_dublincore=False,
+            ).as_html()
+        )