Python code coverage for Lib/test/test_html.py

#	count	content
1	n/a	"""
2	n/a	Tests for the html module functions.
3	n/a	"""
4	n/a
5	n/a	import html
6	n/a	import unittest
7	n/a
8	n/a
9	n/a	class HtmlTests(unittest.TestCase):
10	n/a	def test_escape(self):
11	n/a	self.assertEqual(
12	n/a	html.escape('\'<script>"&foo;"</script>\''),
13	n/a	''<script>"&foo;"</script>'')
14	n/a	self.assertEqual(
15	n/a	html.escape('\'<script>"&foo;"</script>\'', False),
16	n/a	'\'<script>"&foo;"</script>\'')
17	n/a
18	n/a	def test_unescape(self):
19	n/a	numeric_formats = ['&#%d', '&#%d;', '&#x%x', '&#x%x;']
20	n/a	errmsg = 'unescape(%r) should have returned %r'
21	n/a	def check(text, expected):
22	n/a	self.assertEqual(html.unescape(text), expected,
23	n/a	msg=errmsg % (text, expected))
24	n/a	def check_num(num, expected):
25	n/a	for format in numeric_formats:
26	n/a	text = format % num
27	n/a	self.assertEqual(html.unescape(text), expected,
28	n/a	msg=errmsg % (text, expected))
29	n/a	# check text with no character references
30	n/a	check('no character references', 'no character references')
31	n/a	# check & followed by invalid chars
32	n/a	check('&\n&\t& &&', '&\n&\t& &&')
33	n/a	# check & followed by numbers and letters
34	n/a	check('&0 &9 &a &0; &9; &a;', '&0 &9 &a &0; &9; &a;')
35	n/a	# check incomplete entities at the end of the string
36	n/a	for x in ['&', '&#', '&#x', '&#X', '&#y', '&#xy', '&#Xy']:
37	n/a	check(x, x)
38	n/a	check(x+';', x+';')
39	n/a	# check several combinations of numeric character references,
40	n/a	# possibly followed by different characters
41	n/a	formats = ['&#%d', '&#%07d', '&#%d;', '&#%07d;',
42	n/a	'&#x%x', '&#x%06x', '&#x%x;', '&#x%06x;',
43	n/a	'&#x%X', '&#x%06X', '&#X%x;', '&#X%06x;']
44	n/a	for num, char in zip([65, 97, 34, 38, 0x2603, 0x101234],
45	n/a	['A', 'a', '"', '&', '\u2603', '\U00101234']):
46	n/a	for s in formats:
47	n/a	check(s % num, char)
48	n/a	for end in [' ', 'X']:
49	n/a	check((s+end) % num, char+end)
50	n/a	# check invalid code points
51	n/a	for cp in [0xD800, 0xDB00, 0xDC00, 0xDFFF, 0x110000]:
52	n/a	check_num(cp, '\uFFFD')
53	n/a	# check more invalid code points
54	n/a	for cp in [0x1, 0xb, 0xe, 0x7f, 0xfffe, 0xffff, 0x10fffe, 0x10ffff]:
55	n/a	check_num(cp, '')
56	n/a	# check invalid numbers
57	n/a	for num, ch in zip([0x0d, 0x80, 0x95, 0x9d], '\r\u20ac\u2022\x9d'):
58	n/a	check_num(num, ch)
59	n/a	# check small numbers
60	n/a	check_num(0, '\uFFFD')
61	n/a	check_num(9, '\t')
62	n/a	# check a big number
63	n/a	check_num(1000000000000000000, '\uFFFD')
64	n/a	# check that multiple trailing semicolons are handled correctly
65	n/a	for e in ['";', '";', '";', '&#X22;;']:
66	n/a	check(e, '";')
67	n/a	# check that semicolons in the middle don't create problems
68	n/a	for e in ['"quot;', '"quot;', '"quot;', '&#X22;quot;']:
69	n/a	check(e, '"quot;')
70	n/a	# check triple adjacent charrefs
71	n/a	for e in ['&quot', '&#34', '&#x22', '&#X22']:
72	n/a	check(e*3, '"""')
73	n/a	check((e+';')*3, '"""')
74	n/a	# check that the case is respected
75	n/a	for e in ['&amp', '&', '&AMP', '&AMP;']:
76	n/a	check(e, '&')
77	n/a	for e in ['&Amp', '&Amp;']:
78	n/a	check(e, e)
79	n/a	# check that non-existent named entities are returned unchanged
80	n/a	check('&svadilfari;', '&svadilfari;')
81	n/a	# the following examples are in the html5 specs
82	n/a	check('&notit', 'Â¬it')
83	n/a	check('&notit;', 'Â¬it;')
84	n/a	check('&notin', 'Â¬in')
85	n/a	check('∉', 'âˆ‰')
86	n/a	# a similar example with a long name
87	n/a	check('&notReallyAnExistingNamedCharacterReference;',
88	n/a	'Â¬ReallyAnExistingNamedCharacterReference;')
89	n/a	# longest valid name
90	n/a	check('&CounterClockwiseContourIntegral;', 'âˆ³')
91	n/a	# check a charref that maps to two unicode chars
92	n/a	check('&acE;', '\u223E\u0333')
93	n/a	check('&acE', '&acE')
94	n/a	# see #12888
95	n/a	check('{ ' * 1050, '{ ' * 1050)
96	n/a	# see #15156
97	n/a	check('&EacutericÉric&alphacentauriαcentauri',
98	n/a	'Ã‰ricÃ‰ric&alphacentauriÎ±centauri')
99	n/a	check('&co;', '&co;')
100	n/a
101	n/a
102	n/a	if __name__ == '__main__':
103	n/a	unittest.main()