test_html.py revision d3faf43f9ba7da0ae504c9186b10d0fa3a8eb300 
1"""
2Tests for the html module functions.
3"""
4
5import html
6import unittest
7from test.support import run_unittest
8
9
10class HtmlTests(unittest.TestCase):
11    def test_escape(self):
12        self.assertEqual(
13            html.escape('\'<script>"&foo;"</script>\''),
14            '&#x27;&lt;script&gt;&quot;&amp;foo;&quot;&lt;/script&gt;&#x27;')
15        self.assertEqual(
16            html.escape('\'<script>"&foo;"</script>\'', False),
17            '\'&lt;script&gt;"&amp;foo;"&lt;/script&gt;\'')
18
19    def test_unescape(self):
20        numeric_formats = ['&#%d', '&#%d;', '&#x%x', '&#x%x;']
21        errmsg = 'unescape(%r) should have returned %r'
22        def check(text, expected):
23            self.assertEqual(html.unescape(text), expected,
24                             msg=errmsg % (text, expected))
25        def check_num(num, expected):
26            for format in numeric_formats:
27                text = format % num
28                self.assertEqual(html.unescape(text), expected,
29                                 msg=errmsg % (text, expected))
30        # check text with no character references
31        check('no character references', 'no character references')
32        # check & followed by invalid chars
33        check('&\n&\t& &&', '&\n&\t& &&')
34        # check & followed by numbers and letters
35        check('&0 &9 &a &0; &9; &a;', '&0 &9 &a &0; &9; &a;')
36        # check incomplete entities at the end of the string
37        for x in ['&', '&#', '&#x', '&#X', '&#y', '&#xy', '&#Xy']:
38            check(x, x)
39            check(x+';', x+';')
40        # check several combinations of numeric character references,
41        # possibly followed by different characters
42        formats = ['&#%d', '&#%07d', '&#%d;', '&#%07d;',
43                   '&#x%x', '&#x%06x', '&#x%x;', '&#x%06x;',
44                   '&#x%X', '&#x%06X', '&#X%x;', '&#X%06x;']
45        for num, char in zip([65, 97, 34, 38, 0x2603, 0x101234],
46                             ['A', 'a', '"', '&', '\u2603', '\U00101234']):
47            for s in formats:
48                check(s % num, char)
49                for end in [' ', 'X']:
50                    check((s+end) % num, char+end)
51        # check invalid code points
52        for cp in [0xD800, 0xDB00, 0xDC00, 0xDFFF, 0x110000]:
53            check_num(cp, '\uFFFD')
54        # check more invalid code points
55        for cp in [0x1, 0xb, 0xe, 0x7f, 0xfffe, 0xffff, 0x10fffe, 0x10ffff]:
56            check_num(cp, '')
57        # check invalid numbers
58        for num, ch in zip([0x0d, 0x80, 0x95, 0x9d], '\r\u20ac\u2022\x9d'):
59            check_num(num, ch)
60        # check small numbers
61        check_num(0, '\uFFFD')
62        check_num(9, '\t')
63        # check a big number
64        check_num(1000000000000000000, '\uFFFD')
65        # check that multiple trailing semicolons are handled correctly
66        for e in ['&quot;;', '&#34;;', '&#x22;;', '&#X22;;']:
67            check(e, '";')
68        # check that semicolons in the middle don't create problems
69        for e in ['&quot;quot;', '&#34;quot;', '&#x22;quot;', '&#X22;quot;']:
70            check(e, '"quot;')
71        # check triple adjacent charrefs
72        for e in ['&quot', '&#34', '&#x22', '&#X22']:
73            check(e*3, '"""')
74            check((e+';')*3, '"""')
75        # check that the case is respected
76        for e in ['&amp', '&amp;', '&AMP', '&AMP;']:
77            check(e, '&')
78        for e in ['&Amp', '&Amp;']:
79            check(e, e)
80        # check that non-existent named entities are returned unchanged
81        check('&svadilfari;', '&svadilfari;')
82        # the following examples are in the html5 specs
83        check('&notit', '¬it')
84        check('&notit;', '¬it;')
85        check('&notin', '¬in')
86        check('&notin;', '∉')
87        # a similar example with a long name
88        check('&notReallyAnExistingNamedCharacterReference;',
89              '¬ReallyAnExistingNamedCharacterReference;')
90        # longest valid name
91        check('&CounterClockwiseContourIntegral;', '∳')
92        # check a charref that maps to two unicode chars
93        check('&acE;', '\u223E\u0333')
94        check('&acE', '&acE')
95        # see #12888
96        check('&#123; ' * 1050, '{ ' * 1050)
97        # see #15156
98        check('&Eacuteric&Eacute;ric&alphacentauri&alpha;centauri',
99              'ÉricÉric&alphacentauriαcentauri')
100        check('&co;', '&co;')
101
102
103if __name__ == '__main__':
104    unittest.main()
105