1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
|
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import warnings
from django.test import SimpleTestCase
from django.utils import text
class TestUtilsText(SimpleTestCase):
# In Django 1.6 truncate_words() and truncate_html_words() will be removed
# so these tests will need to be adapted accordingly
def test_truncate_chars(self):
truncator = text.Truncator(
'The quick brown fox jumped over the lazy dog.'
)
self.assertEqual('The quick brown fox jumped over the lazy dog.',
truncator.chars(100)),
self.assertEqual('The quick brown fox ...',
truncator.chars(23)),
self.assertEqual('The quick brown fo.....',
truncator.chars(23, '.....')),
# Ensure that we normalize our unicode data first
nfc = text.Truncator('o\xfco\xfco\xfco\xfc')
nfd = text.Truncator('ou\u0308ou\u0308ou\u0308ou\u0308')
self.assertEqual('oüoüoüoü', nfc.chars(8))
self.assertEqual('oüoüoüoü', nfd.chars(8))
self.assertEqual('oü...', nfc.chars(5))
self.assertEqual('oü...', nfd.chars(5))
# Ensure the final length is calculated correctly when there are
# combining characters with no precomposed form, and that combining
# characters are not split up.
truncator = text.Truncator('-B\u030AB\u030A----8')
self.assertEqual('-B\u030A...', truncator.chars(5))
self.assertEqual('-B\u030AB\u030A-...', truncator.chars(7))
self.assertEqual('-B\u030AB\u030A----8', truncator.chars(8))
# Ensure the length of the end text is correctly calculated when it
# contains combining characters with no precomposed form.
truncator = text.Truncator('-----')
self.assertEqual('---B\u030A', truncator.chars(4, 'B\u030A'))
self.assertEqual('-----', truncator.chars(5, 'B\u030A'))
# Make a best effort to shorten to the desired length, but requesting
# a length shorter than the ellipsis shouldn't break
self.assertEqual('...', text.Truncator('asdf').chars(1))
def test_truncate_words(self):
truncator = text.Truncator('The quick brown fox jumped over the lazy '
'dog.')
self.assertEqual('The quick brown fox jumped over the lazy dog.',
truncator.words(10))
self.assertEqual('The quick brown fox...', truncator.words(4))
self.assertEqual('The quick brown fox[snip]',
truncator.words(4, '[snip]'))
def test_truncate_html_words(self):
truncator = text.Truncator('<p><strong><em>The quick brown fox jumped '
'over the lazy dog.</em></strong></p>')
self.assertEqual('<p><strong><em>The quick brown fox jumped over the '
'lazy dog.</em></strong></p>', truncator.words(10, html=True))
self.assertEqual('<p><strong><em>The quick brown fox...</em>'
'</strong></p>', truncator.words(4, html=True))
self.assertEqual('<p><strong><em>The quick brown fox....</em>'
'</strong></p>', truncator.words(4, '....', html=True))
self.assertEqual('<p><strong><em>The quick brown fox</em></strong>'
'</p>', truncator.words(4, '', html=True))
# Test with new line inside tag
truncator = text.Truncator('<p>The quick <a href="xyz.html"\n'
'id="mylink">brown fox</a> jumped over the lazy dog.</p>')
self.assertEqual('<p>The quick <a href="xyz.html"\n'
'id="mylink">brown...</a></p>', truncator.words(3, '...', html=True))
def test_old_truncate_words(self):
with warnings.catch_warnings(record=True) as w:
warnings.simplefilter("always")
self.assertEqual('The quick brown fox jumped over the lazy dog.',
text.truncate_words('The quick brown fox jumped over the lazy dog.', 10))
self.assertEqual('The quick brown fox ...',
text.truncate_words('The quick brown fox jumped over the lazy dog.', 4))
self.assertEqual('The quick brown fox ....',
text.truncate_words('The quick brown fox jumped over the lazy dog.', 4, '....'))
self.assertGreater(len(w), 0)
def test_old_truncate_html_words(self):
with warnings.catch_warnings(record=True) as w:
warnings.simplefilter("always")
self.assertEqual('<p><strong><em>The quick brown fox jumped over the lazy dog.</em></strong></p>',
text.truncate_html_words('<p><strong><em>The quick brown fox jumped over the lazy dog.</em></strong></p>', 10))
self.assertEqual('<p><strong><em>The quick brown fox ...</em></strong></p>',
text.truncate_html_words('<p><strong><em>The quick brown fox jumped over the lazy dog.</em></strong></p>', 4))
self.assertEqual('<p><strong><em>The quick brown fox ....</em></strong></p>',
text.truncate_html_words('<p><strong><em>The quick brown fox jumped over the lazy dog.</em></strong></p>', 4, '....'))
self.assertEqual('<p><strong><em>The quick brown fox</em></strong></p>',
text.truncate_html_words('<p><strong><em>The quick brown fox jumped over the lazy dog.</em></strong></p>', 4, None))
self.assertGreater(len(w), 0)
def test_wrap(self):
digits = '1234 67 9'
self.assertEqual(text.wrap(digits, 100), '1234 67 9')
self.assertEqual(text.wrap(digits, 9), '1234 67 9')
self.assertEqual(text.wrap(digits, 8), '1234 67\n9')
self.assertEqual(text.wrap('short\na long line', 7),
'short\na long\nline')
self.assertEqual(text.wrap('do-not-break-long-words please? ok', 8),
'do-not-break-long-words\nplease?\nok')
long_word = 'l%sng' % ('o' * 20)
self.assertEqual(text.wrap(long_word, 20), long_word)
self.assertEqual(text.wrap('a %s word' % long_word, 10),
'a\n%s\nword' % long_word)
def test_slugify(self):
items = (
('Hello, World!', 'hello-world'),
('spam & eggs', 'spam-eggs'),
)
for value, output in items:
self.assertEqual(text.slugify(value), output)
def test_unescape_entities(self):
items = [
('', ''),
('foo', 'foo'),
('&', '&'),
('&', '&'),
('&', '&'),
('foo & bar', 'foo & bar'),
('foo & bar', 'foo & bar'),
]
for value, output in items:
self.assertEqual(text.unescape_entities(value), output)
|
