Better handling of multipart DAISY.

[librarian.git] / tests / test_dcparser.py

diff --git a/tests/test_dcparser.py b/tests/test_dcparser.py
index ee29bc9..4dab764 100644 (file)
--- a/tests/test_dcparser.py
+++ b/tests/test_dcparser.py
@@ -3,18 +3,21 @@
 # This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
 # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
 #
 # 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
+

 from librarian import dcparser
 from lxml import etree
 from nose.tools import *
 from os.path import splitext
 from tests.utils import get_all_fixtures
 import codecs
 from librarian import dcparser
 from lxml import etree
 from nose.tools import *
 from os.path import splitext
 from tests.utils import get_all_fixtures
 import codecs

+from datetime import date

 
 
 def check_dcparser(xml_file, result_file):
 
 
 def check_dcparser(xml_file, result_file):

-    xml = file(xml_file).read()
+    xml = open(xml_file, 'rb').read()

     result = codecs.open(result_file, encoding='utf-8').read()
     result = codecs.open(result_file, encoding='utf-8').read()

-    info = dcparser.BookInfo.from_string(xml).to_dict()
+    info = dcparser.BookInfo.from_bytes(xml).to_dict()

     should_be = eval(result)
     for key in should_be:
         assert_equals(info[key], should_be[key])
     should_be = eval(result)
     for key in should_be:
         assert_equals(info[key], should_be[key])


@@ -27,13 +30,13 @@ def test_dcparser():
 
 
 def check_serialize(xml_file):
 
 
 def check_serialize(xml_file):

-    xml = file(xml_file).read()
-    info = dcparser.BookInfo.from_string(xml)
+    xml = open(xml_file, 'rb').read()
+    info = dcparser.BookInfo.from_bytes(xml)

 
     # serialize
 
     # serialize

-    serialized = etree.tostring(info.to_etree(), encoding=unicode).encode('utf-8')
+    serialized = etree.tostring(info.to_etree(), encoding='unicode').encode('utf-8')

     # then parse again
     # then parse again

-    info_bis = dcparser.BookInfo.from_string(serialized)
+    info_bis = dcparser.BookInfo.from_bytes(serialized)

 
     # check if they are the same
     for key in vars(info):
 
     # check if they are the same
     for key in vars(info):


@@ -46,3 +49,13 @@ def test_serialize():
     for fixture in get_all_fixtures('dcparser', '*.xml'):
         yield check_serialize, fixture
 
     for fixture in get_all_fixtures('dcparser', '*.xml'):
         yield check_serialize, fixture
 

+
+def test_asdate():
+    assert_equals(dcparser.as_date(u"2010-10-03"), date(2010, 10, 3))
+    assert_equals(dcparser.as_date(u"2011"), date(2011, 1, 1))
+    assert_equals(dcparser.as_date(u"2 poł. XIX w."), date(1950, 1, 1))
+    assert_equals(dcparser.as_date(u"XVII w., l. 20"), date(1720, 1, 1))
+    assert_equals(dcparser.as_date(u"po 1460"), date(1460, 1, 1))
+    assert_equals(dcparser.as_date(u"ok. 1813-1814"), date(1813, 1, 1))
+    assert_equals(dcparser.as_date(u"ok.1876-ok.1886"), date(1876, 1, 1))
+    assert_equals(dcparser.as_date(u"1893/1894"), date(1893, 1, 1))