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
137
138
139
140
|
#!/usr/bin/env python3
import base, unittest
from ptk.regex import RegexTokenizer, RegexParser, RegularExpression, LitteralCharacterClass, \
RegexParseError, buildRegex
class RegexParserTestCaseMixin(object):
# It's a bit of a PITA to test for RegularExpression objects equality, so we check
# matched strings
def _parse(self, rx):
return buildRegex(rx)
def _match(self, rx, s):
return rx.match(s)
def test_newline(self):
rx = self._parse(r'\n')
self.assertTrue(self._match(rx, '\n'))
def test_concat(self):
rx = self._parse('ab')
self.assertFalse(self._match(rx, 'a'))
self.assertTrue(self._match(rx, 'ab'))
self.assertFalse(self._match(rx, 'abc'))
def test_union(self):
rx = self._parse('a|b')
self.assertTrue(self._match(rx, 'a'))
self.assertTrue(self._match(rx, 'b'))
self.assertFalse(self._match(rx, 'ab'))
self.assertFalse(self._match(rx, 'c'))
def test_kleene(self):
rx = self._parse('a*')
self.assertTrue(self._match(rx, ''))
self.assertTrue(self._match(rx, 'a'))
self.assertTrue(self._match(rx, 'aa'))
self.assertFalse(self._match(rx, 'b'))
def test_closure(self):
rx = self._parse('a+')
self.assertFalse(self._match(rx, ''))
self.assertTrue(self._match(rx, 'a'))
self.assertTrue(self._match(rx, 'aa'))
self.assertFalse(self._match(rx, 'b'))
def test_exp_single(self):
rx = self._parse('a{2}')
self.assertFalse(self._match(rx, ''))
self.assertFalse(self._match(rx, 'a'))
self.assertTrue(self._match(rx, 'aa'))
self.assertFalse(self._match(rx, 'aaa'))
def test_exp_both(self):
rx = self._parse('a{2-3}')
self.assertFalse(self._match(rx, ''))
self.assertFalse(self._match(rx, 'a'))
self.assertTrue(self._match(rx, 'aa'))
self.assertTrue(self._match(rx, 'aaa'))
self.assertFalse(self._match(rx, 'aaaa'))
def test_class(self):
rx = self._parse('[a-c]')
self.assertTrue(self._match(rx, 'a'))
self.assertTrue(self._match(rx, 'b'))
self.assertTrue(self._match(rx, 'c'))
self.assertFalse(self._match(rx, 'd'))
def test_any(self):
rx = self._parse('.')
self.assertTrue(self._match(rx, 'U'))
self.assertFalse(self._match(rx, '\n'))
def test_prio_1(self):
rx = self._parse('a|b*')
self.assertTrue(self._match(rx, 'a'))
self.assertTrue(self._match(rx, 'b'))
self.assertTrue(self._match(rx, 'bb'))
self.assertFalse(self._match(rx, 'ab'))
def test_prio_2(self):
rx = self._parse('ab*')
self.assertTrue(self._match(rx, 'a'))
self.assertTrue(self._match(rx, 'ab'))
self.assertTrue(self._match(rx, 'abb'))
self.assertFalse(self._match(rx, 'abab'))
def test_prio_3(self):
rx = self._parse('a|bc')
self.assertTrue(self._match(rx, 'a'))
self.assertTrue(self._match(rx, 'bc'))
self.assertFalse(self._match(rx, 'ac'))
def test_paren(self):
rx = self._parse('(ab)*')
self.assertTrue(self._match(rx, 'ab'))
self.assertTrue(self._match(rx, 'abab'))
self.assertFalse(self._match(rx, 'abb'))
def test_crlf(self):
rx = self._parse(r'\r\n')
self.assertTrue(self._match(rx, '\r\n'))
def test_extra_tokens(self):
try:
rx = self._parse('ab(')
except RegexParseError:
pass
else:
self.fail()
def test_missing_paren(self):
try:
rx = self._parse('(a')
except RegexParseError:
pass
else:
self.fail()
class RegexParserUnicodeTestCase(RegexParserTestCaseMixin, unittest.TestCase):
pass
class RegexParserBytesTestCase(RegexParserTestCaseMixin, unittest.TestCase):
def _parse(self, rx):
if isinstance(rx, str):
rx = rx.encode('UTF-8')
return super()._parse(rx)
def _match(self, rx, s):
if isinstance(s, str):
s = s.encode('UTF-8')
return super()._match(rx, s)
if __name__ == '__main__':
unittest.main()
|
