rel
[librarian.git] / tests / test_text.py
index 020c571..c566a48 100644 (file)
@@ -1,41 +1,64 @@
 # -*- coding: utf-8 -*-
-from librarian import text, NoDublinCore
+#
+# This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
+# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
+#
+from __future__ import unicode_literals
+
+import unittest
+from librarian import NoDublinCore
+from librarian.builders import builders
+from librarian.parser import WLDocument as LegacyWLDocument
+from librarian.document import WLDocument
 from nose.tools import *
-from utils import get_fixture, remove_output_file
+from .utils import get_fixture
 
 
-def teardown_transform():
-    remove_output_file('text', 'asnyk_miedzy_nami.txt')
+class TextTests(unittest.TestCase):
+    maxDiff = None
 
+    def test_transform_legacy(self):
+        expected_output_file_path = get_fixture('text', 'asnyk_miedzy_nami_expected.txt')
+
+        text = LegacyWLDocument.from_file(
+            get_fixture('text', 'miedzy-nami-nic-nie-bylo.xml')
+        ).as_text().get_bytes().decode('utf-8')
+
+        with open(expected_output_file_path, 'rb') as f:
+            self.assertEqual(text, f.read().decode('utf-8'))
+
+    def test_transform(self):
+        expected_output_file_path = get_fixture('text', 'asnyk_miedzy_nami_expected.txt')
+
+        text = WLDocument(
+            filename=get_fixture('text', 'miedzy-nami-nic-nie-bylo.xml')
+        ).build(builders['txt']).get_bytes().decode('utf-8')
+
+        with open(expected_output_file_path, 'rb') as f:
+            self.assertEqual(text, f.read().decode('utf-8'))
 
-@with_setup(None, teardown_transform)
-def test_transform():
-    output_file_path = get_fixture('text', 'asnyk_miedzy_nami.txt')
-    expected_output_file_path = get_fixture('text', 'asnyk_miedzy_nami_expected.txt')
-    
-    text.transform(
-        get_fixture('text', 'asnyk_miedzy_nami.xml'),
-        output_file_path,
-    )
     
-    assert_equal(file(output_file_path).read(), file(expected_output_file_path).read())
+    def test_transform_raw(self):
+        expected_output_file_path = get_fixture('text', 'asnyk_miedzy_nami_expected_raw.txt')
+
+        text = LegacyWLDocument.from_file(
+            get_fixture('text', 'miedzy-nami-nic-nie-bylo.xml')
+        ).as_text(flags=['raw-text']).get_bytes().decode('utf-8')
+
+        with open(expected_output_file_path, 'rb') as f:
+            self.assertEqual(text, f.read().decode('utf-8'))
 
 
-@with_setup(None, teardown_transform)
 @raises(NoDublinCore)
 def test_no_dublincore():
-    text.transform(
-        get_fixture('text', 'asnyk_miedzy_nami_nodc.xml'),
-        get_fixture('text', 'asnyk_miedzy_nami_nodc.txt'),
-    )
+    LegacyWLDocument.from_file(
+            get_fixture('text', 'asnyk_miedzy_nami_nodc.xml')
+        ).as_text()
 
 
-@with_setup(None, teardown_transform)
 def test_passing_parse_dublincore_to_transform():
-    """Passing parse_dublincore=False to transform omits DublinCore parsing."""
-    text.transform(
-        get_fixture('text', 'asnyk_miedzy_nami_nodc.xml'),
-        get_fixture('text', 'asnyk_miedzy_nami.txt'),
-        parse_dublincore=False,
-    )
-    
\ No newline at end of file
+    """Passing parse_dublincore=False to the constructor omits DublinCore parsing."""
+    LegacyWLDocument.from_file(
+            get_fixture('text', 'asnyk_miedzy_nami_nodc.xml'),
+            parse_dublincore=False,
+        ).as_text()