1"""
2Tests for the html module functions.
3"""
4
5import html
6import unittest
7
8
9class HtmlTests(unittest.TestCase):
10    def test_escape(self):
11        self.assertEqual(
12            html.escape('\'<script>"&foo;"</script>\''),
13            '&#x27;&lt;script&gt;&quot;&amp;foo;&quot;&lt;/script&gt;&#x27;')
14        self.assertEqual(
15            html.escape('\'<script>"&foo;"</script>\'', False),
16            '\'&lt;script&gt;"&amp;foo;"&lt;/script&gt;\'')
17
18    def test_unescape(self):
19        numeric_formats = ['&#%d', '&#%d;', '&#x%x', '&#x%x;']
20        errmsg = 'unescape(%r) should have returned %r'
21        def check(text, expected):
22            self.assertEqual(html.unescape(text), expected,
23                             msg=errmsg % (text, expected))
24        def check_num(num, expected):
25            for format in numeric_formats:
26                text = format % num
27                self.assertEqual(html.unescape(text), expected,
28                                 msg=errmsg % (text, expected))
29        # check text with no character references
30        check('no character references', 'no character references')
31        # check & followed by invalid chars
32        check('&\n&\t& &&', '&\n&\t& &&')
33        # check & followed by numbers and letters
34        check('&0 &9 &a &0; &9; &a;', '&0 &9 &a &0; &9; &a;')
35        # check incomplete entities at the end of the string
36        for x in ['&', '&#', '&#x', '&#X', '&#y', '&#xy', '&#Xy']:
37            check(x, x)
38            check(x+';', x+';')
39        # check several combinations of numeric character references,
40        # possibly followed by different characters
41        formats = ['&#%d', '&#%07d', '&#%d;', '&#%07d;',
42                   '&#x%x', '&#x%06x', '&#x%x;', '&#x%06x;',
43                   '&#x%X', '&#x%06X', '&#X%x;', '&#X%06x;']
44        for num, char in zip([65, 97, 34, 38, 0x2603, 0x101234],
45                             ['A', 'a', '"', '&', '\u2603', '\U00101234']):
46            for s in formats:
47                check(s % num, char)
48                for end in [' ', 'X']:
49                    check((s+end) % num, char+end)
50        # check invalid code points
51        for cp in [0xD800, 0xDB00, 0xDC00, 0xDFFF, 0x110000]:
52            check_num(cp, '\uFFFD')
53        # check more invalid code points
54        for cp in [0x1, 0xb, 0xe, 0x7f, 0xfffe, 0xffff, 0x10fffe, 0x10ffff]:
55            check_num(cp, '')
56        # check invalid numbers
57        for num, ch in zip([0x0d, 0x80, 0x95, 0x9d], '\r\u20ac\u2022\x9d'):
58            check_num(num, ch)
59        # check small numbers
60        check_num(0, '\uFFFD')
61        check_num(9, '\t')
62        # check a big number
63        check_num(1000000000000000000, '\uFFFD')
64        # check that multiple trailing semicolons are handled correctly
65        for e in ['&quot;;', '&#34;;', '&#x22;;', '&#X22;;']:
66            check(e, '";')
67        # check that semicolons in the middle don't create problems
68        for e in ['&quot;quot;', '&#34;quot;', '&#x22;quot;', '&#X22;quot;']:
69            check(e, '"quot;')
70        # check triple adjacent charrefs
71        for e in ['&quot', '&#34', '&#x22', '&#X22']:
72            check(e*3, '"""')
73            check((e+';')*3, '"""')
74        # check that the case is respected
75        for e in ['&amp', '&amp;', '&AMP', '&AMP;']:
76            check(e, '&')
77        for e in ['&Amp', '&Amp;']:
78            check(e, e)
79        # check that non-existent named entities are returned unchanged
80        check('&svadilfari;', '&svadilfari;')
81        # the following examples are in the html5 specs
82        check('&notit', '¬it')
83        check('&notit;', '¬it;')
84        check('&notin', '¬in')
85        check('&notin;', '∉')
86        # a similar example with a long name
87        check('&notReallyAnExistingNamedCharacterReference;',
88              '¬ReallyAnExistingNamedCharacterReference;')
89        # longest valid name
90        check('&CounterClockwiseContourIntegral;', '∳')
91        # check a charref that maps to two unicode chars
92        check('&acE;', '\u223E\u0333')
93        check('&acE', '&acE')
94        # see #12888
95        check('&#123; ' * 1050, '{ ' * 1050)
96        # see #15156
97        check('&Eacuteric&Eacute;ric&alphacentauri&alpha;centauri',
98              'ÉricÉric&alphacentauriαcentauri')
99        check('&co;', '&co;')
100
101
102if __name__ == '__main__':
103    unittest.main()
104