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
|
#!/usr/bin/env python3
import base, unittest
from ptk.regex import RegularExpression, LitteralCharacterClass
class RegexTestMixin(object):
def test_deadend(self):
rx = RegularExpression.concat(
RegularExpression.fromClass(LitteralCharacterClass(self.t('<')[0])),
RegularExpression.fromClass(LitteralCharacterClass(self.t('=')[0]))
)
rx.start()
rx.feed(self.t('<')[0]) # byte/char
self.assertFalse(rx.isDeadEnd())
def test_newline(self):
rx = RegularExpression.fromClass(LitteralCharacterClass(self.t('\n')[0]))
self.assertTrue(rx.match(self.t('\n')))
def test_class(self):
rx = RegularExpression.fromClass(LitteralCharacterClass(self.t('a')[0]))
self.assertTrue(rx.match(self.t('a')))
self.assertFalse(rx.match(self.t('b')))
def test_concat(self):
rx = RegularExpression.concat(
RegularExpression.fromClass(LitteralCharacterClass(self.t('a')[0])),
RegularExpression.fromClass(LitteralCharacterClass(self.t('b')[0])),
RegularExpression.fromClass(LitteralCharacterClass(self.t('c')[0]))
)
self.assertTrue(rx.match(self.t('abc')))
self.assertFalse(rx.match(self.t('ab')))
def test_union(self):
rx = RegularExpression.union(
RegularExpression.fromClass(LitteralCharacterClass(self.t('a')[0])),
RegularExpression.fromClass(LitteralCharacterClass(self.t('b')[0])),
RegularExpression.fromClass(LitteralCharacterClass(self.t('c')[0]))
)
self.assertTrue(rx.match(self.t('a')))
self.assertTrue(rx.match(self.t('b')))
self.assertTrue(rx.match(self.t('c')))
self.assertFalse(rx.match(self.t('d')))
def test_kleene(self):
rx = RegularExpression.kleene(RegularExpression.fromClass(LitteralCharacterClass(self.t('a')[0])))
self.assertTrue(rx.match(self.t('')))
self.assertTrue(rx.match(self.t('a')))
self.assertTrue(rx.match(self.t('aa')))
self.assertFalse(rx.match(self.t('ab')))
def test_exponent(self):
rx = RegularExpression.exponent(RegularExpression.fromClass(LitteralCharacterClass(self.t('a')[0])), 2, 3)
self.assertFalse(rx.match(self.t('a')))
self.assertTrue(rx.match(self.t('aa')))
self.assertTrue(rx.match(self.t('aaa')))
self.assertFalse(rx.match(self.t('aaaa')))
def test_exponent_min(self):
rx = RegularExpression.exponent(RegularExpression.fromClass(LitteralCharacterClass(self.t('a')[0])), 2)
self.assertFalse(rx.match(self.t('a')))
self.assertTrue(rx.match(self.t('aa')))
self.assertTrue(rx.match(self.t('aaa')))
def test_exponent_null(self):
rx = RegularExpression.exponent(RegularExpression.fromClass(LitteralCharacterClass(self.t('a')[0])), 0, 1)
self.assertTrue(rx.match(self.t('')))
self.assertTrue(rx.match(self.t('a')))
self.assertFalse(rx.match(self.t('aa')))
class UnicodeRegexTest(RegexTestMixin, unittest.TestCase):
def t(self, s):
return s
class BytesRegexTest(RegexTestMixin, unittest.TestCase):
def t(self, s):
return s.encode('ascii')
if __name__ == '__main__':
unittest.main()
|
