fixes for edge cases

[librarian.git] / tests / test_text.py

diff --git a/tests/test_text.py b/tests/test_text.py
old mode 100755 (executable)
new mode 100644 (file)
index 00fd787..c566a48
--- a/tests/test_text.py
+++ b/tests/test_text.py
@@ -1,22 +1,64 @@
-#!/usr/bin/env python
-# encoding: utf-8
+# -*- coding: utf-8 -*-
+#
+# 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
 
 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

 
 

-from utils import get_file_path
-from librarian import dcparser
-from librarian import text, NoDublinCore

 
 

+class TextTests(unittest.TestCase):
+    maxDiff = None

 
 

-class TestXML(unittest.TestCase):
-    def test_no_dublincore(self):
-        try:
-            text.transform(get_file_path('text', 'asnyk_miedzy_nami.xml'),
-                           get_file_path('text', 'asnyk_miedzy_nami.txt'))
-            self.fail()
-        except NoDublinCore, e:
-            pass
+    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')

 
 

-if __name__ == '__main__':
-    unittest.main()
+        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'))
+
+    
+    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'))
+
+
+@raises(NoDublinCore)
+def test_no_dublincore():
+    LegacyWLDocument.from_file(
+            get_fixture('text', 'asnyk_miedzy_nami_nodc.xml')
+        ).as_text()
+
+
+def test_passing_parse_dublincore_to_transform():
+    """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()