# 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 *
import codecs
from datetime import date
+
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()
- 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])
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
- 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
- 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):
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, 03))
+ 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"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))
-