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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
|
PCRE2 version 10.32-RC1 2018-02-19
# This is a specialized test for checking, when PCRE2 is compiled with the
# EBCDIC option but in an ASCII environment, that newline, white space, and \c
# functionality is working. It catches cases where explicit values such as 0x0a
# have been used instead of names like CHAR_LF. Needless to say, it is not a
# genuine EBCDIC test! In patterns, alphabetic characters that follow a
# backslash must be in EBCDIC code. In data, NL, NEL, LF, ESC, and DEL must be
# in EBCDIC, but can of course be specified as escapes.
# Test default newline and variations
/^A/m
ABC
0: A
12\x15ABC
0: A
/^A/m,newline=any
12\x15ABC
0: A
12\x0dABC
0: A
12\x0d\x15ABC
0: A
12\x25ABC
0: A
/^A/m,newline=anycrlf
12\x15ABC
0: A
12\x0dABC
0: A
12\x0d\x15ABC
0: A
** Fail
No match
12\x25ABC
No match
# Test \h
/^A\ˆ/
A B
0: A\x20
A\x41B
0: AA
# Test \H
/^A\È/
AB
0: AB
A\x42B
0: AB
** Fail
No match
A B
No match
A\x41B
No match
# Test \R
/^A\Ù/
A\x15B
0: A\x15
A\x0dB
0: A\x0d
A\x25B
0: A\x25
A\x0bB
0: A\x0b
A\x0cB
0: A\x0c
** Fail
No match
A B
No match
# Test \v
/^A\¥/
A\x15B
0: A\x15
A\x0dB
0: A\x0d
A\x25B
0: A\x25
A\x0bB
0: A\x0b
A\x0cB
0: A\x0c
** Fail
No match
A B
No match
# Test \V
/^A\å/
A B
0: A\x20
** Fail
No match
A\x15B
No match
A\x0dB
No match
A\x25B
No match
A\x0bB
No match
A\x0cB
No match
# For repeated items, use an atomic group so that the output is the same
# for DFA matching (otherwise it may show multiple matches).
# Test \h+
/^A(?>\ˆ+)/
A B
0: A\x20
# Test \H+
/^A(?>\È+)/
AB
0: AB
** Fail
No match
A B
No match
# Test \R+
/^A(?>\Ù+)/
A\x15B
0: A\x15
A\x0dB
0: A\x0d
A\x25B
0: A\x25
A\x0bB
0: A\x0b
A\x0cB
0: A\x0c
** Fail
No match
A B
No match
# Test \v+
/^A(?>\¥+)/
A\x15B
0: A\x15
A\x0dB
0: A\x0d
A\x25B
0: A\x25
A\x0bB
0: A\x0b
A\x0cB
0: A\x0c
** Fail
No match
A B
No match
# Test \V+
/^A(?>\å+)/
A B
0: A\x20B
** Fail
No match
A\x15B
No match
A\x0dB
No match
A\x25B
No match
A\x0bB
No match
A\x0cB
No match
# Test \c functionality
/\ƒ@\ƒA\ƒb\ƒC\ƒd\ƒE\ƒf\ƒG\ƒh\ƒI\ƒJ\ƒK\ƒl\ƒm\ƒN\ƒO\ƒp\ƒq\ƒr\ƒS\ƒT\ƒu\ƒV\ƒW\ƒX\ƒy\ƒZ/
\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f
0: \x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a
/\ƒ[\ƒ\\ƒ]\ƒ^\ƒ_/
\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f
0: \x1b\x1c\x1d\x1e\x1f
/\ƒ?/
A\xffB
0: \xff
/\ƒ&/
Failed: error 168 at offset 3: \c\x20must\x20be\x20followed\x20by\x20a\x20letter\x20or\x20one\x20of\x20[\]^_\x3f
# End
|
