def test_read_gold_standard(self):
all_files = data_processing.get_list_all_corrected_files(FIXTURES)
all_files.sort()
chars = {'ascii':u'ascii yo!', 'iso-8859-1':u'\xd3', 'utf-8':u'\xae', 'utf-16':u'\xae'}
for e in chars:
content_comments = data_processing.read_gold_standard(
FIXTURES, e)
actual_content = (u"Content here\nmore content\n" + chars[e] + u"\n")
self.assertEqual(content_comments[0], actual_content)
self.assertEqual(content_comments[1], '\nsome comments\n')
def test_list_all_files(self):
prefixes = ['bbc.co.story', 'f1', 'sad8-2sdkfj']
datadir = tempfile.mkdtemp()
os.mkdir(datadir + '/Corrected')
for froot in prefixes:
with open(datadir + '/Corrected/%s.html.corrected.txt' % froot, 'w') as f:
f.write('.')
all_files = data_processing.get_list_all_corrected_files(datadir)
all_files.sort()
self.assertEqual(all_files,
[('%s/Corrected/%s.html.corrected.txt' %
(datadir, froot), froot)
for froot in prefixes])
rmtree(datadir)
