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
|
try:
import re
except ImportError:
print("SKIP")
raise SystemExit
r = re.compile(".+")
m = r.match("abc")
print(m.group(0))
try:
m.group(1)
except IndexError:
print("IndexError")
# conversion of re and match to string
str(r)
str(m)
r = re.compile("(.+)1")
m = r.match("xyz781")
print(m.group(0))
print(m.group(1))
try:
m.group(2)
except IndexError:
print("IndexError")
r = re.compile("[a-cu-z]")
m = r.match("a")
print(m.group(0))
m = r.match("z")
print(m.group(0))
m = r.match("d")
print(m)
m = r.match("A")
print(m)
print("===")
r = re.compile("[^a-cu-z]")
m = r.match("a")
print(m)
m = r.match("z")
print(m)
m = r.match("d")
print(m.group(0))
m = r.match("A")
print(m.group(0))
print("===")
# '-' character within character class block
print(re.match("[-a]+", "-a]d").group(0))
print(re.match("[a-]+", "-a]d").group(0))
print("===")
r = re.compile("o+")
m = r.search("foobar")
print(m.group(0))
try:
m.group(1)
except IndexError:
print("IndexError")
m = re.match(".*", "foo")
print(m.group(0))
m = re.search("w.r", "hello world")
print(m.group(0))
m = re.match("a+?", "ab")
print(m.group(0))
m = re.match("a*?", "ab")
print(m.group(0))
m = re.match("^ab$", "ab")
print(m.group(0))
m = re.match("a|b", "b")
print(m.group(0))
m = re.match("a|b|c", "c")
print(m.group(0))
# Case where anchors fail to match
r = re.compile("^b|b$")
m = r.search("abc")
print(m)
try:
re.compile("*")
except:
print("Caught invalid regex")
# bytes objects
m = re.match(rb"a+?", b"ab")
print(m.group(0))
print("===")
# escaping
m = re.match(r"a\.c", "a.c")
print(m.group(0) if m else "")
m = re.match(r"a\.b", "abc")
print(m is None)
m = re.match(r"a\.b", "a\\bc")
print(m is None)
m = re.match(r"[a\-z]", "abc")
print(m.group(0))
m = re.match(r"[.\]]*", ".].]a")
print(m.group(0))
m = re.match(r"[.\]+]*", ".]+.]a")
print(m.group(0))
m = re.match(r"[a-f0-9x\-yz]*", "abxcd1-23")
print(m.group(0))
m = re.match(r"[a\\b]*", "a\\aa\\bb\\bbab")
print(m.group(0))
m = re.search(r"[a\-z]", "-")
print(m.group(0))
m = re.search(r"[a\-z]", "f")
print(m is None)
m = re.search(r"[a\]z]", "a")
print(m.group(0))
print(re.compile(r"[-a]").split("foo-bar"))
print(re.compile(r"[a-]").split("foo-bar"))
print(re.compile(r"[ax\-]").split("foo-bar"))
print(re.compile(r"[a\-x]").split("foo-bar"))
print(re.compile(r"[\-ax]").split("foo-bar"))
print("===")
# Module functions take str/bytes/re.
for f in (re.match, re.search):
print(f(".", "foo").group(0))
print(f(b".", b"foo").group(0))
print(f(re.compile("."), "foo").group(0))
try:
f(123, "a")
except TypeError:
print("TypeError")
print("===")
|
