blob: 9bbfa54ebd5186444aaa786905e66a38f21be919 [file] [log] [blame]
Guido van Rossum337c6d41997-07-15 18:42:58 +00001#!/usr/bin/env python
2# -*- mode: python -*-
3# $Id$
4
Guido van Rossumdfa67901997-12-08 17:12:06 +00005# Re test suite and benchmark suite v1.5b2
Guido van Rossum8e0ce301997-07-11 19:34:44 +00006
7# The 3 possible outcomes for each pattern
8[SUCCEED, FAIL, SYNTAX_ERROR] = range(3)
9
10# Benchmark suite (needs expansion)
11#
12# The benchmark suite does not test correctness, just speed. The
13# first element of each tuple is the regex pattern; the second is a
14# string to match it against. The benchmarking code will embed the
15# second string inside several sizes of padding, to test how regex
16# matching performs on large strings.
17
18benchmarks = [
19 ('Python', 'Python'), # Simple text literal
20 ('.*Python', 'Python'), # Bad text literal
21 ('.*Python.*', 'Python'), # Worse text literal
22 ('.*(Python)', 'Python'), # Bad text literal with grouping
Guido van Rossum16bd0ff1997-07-15 18:45:20 +000023
Guido van Rossum8e0ce301997-07-11 19:34:44 +000024 ('(Python|Perl|Tcl', 'Perl'), # Alternation
25 ('(Python|Perl|Tcl)', 'Perl'), # Grouped alternation
26 ('(Python)\\1', 'PythonPython'), # Backreference
27 ('([0a-z][a-z]*,)+', 'a5,b7,c9,'), # Disable the fastmap optimization
28 ('([a-z][a-z0-9]*,)+', 'a5,b7,c9,') # A few sets
29]
30
31# Test suite (for verifying correctness)
32#
33# The test suite is a list of 5- or 3-tuples. The 5 parts of a
34# complete tuple are:
35# element 0: a string containing the pattern
36# 1: the string to match against the pattern
37# 2: the expected result (SUCCEED, FAIL, SYNTAX_ERROR)
38# 3: a string that will be eval()'ed to produce a test string.
39# This is an arbitrary Python expression; the available
40# variables are "found" (the whole match), and "g1", "g2", ...
Guido van Rossum16bd0ff1997-07-15 18:45:20 +000041# up to "g99" contain the contents of each group, or the
42# string 'None' if the group wasn't given a value, or the
43# string 'Error' if the group index was out of range;
44# also "groups", the return value of m.group() (a tuple).
Guido van Rossum8e0ce301997-07-11 19:34:44 +000045# 4: The expected result of evaluating the expression.
46# If the two don't match, an error is reported.
47#
48# If the regex isn't expected to work, the latter two elements can be omitted.
49
Guido van Rossumdfa67901997-12-08 17:12:06 +000050tests = [
51 # Test ?P< and ?P= extensions
52 ('(?P<foo_123', '', SYNTAX_ERROR), # Unterminated group identifier
53 ('(?P<1>a)', '', SYNTAX_ERROR), # Begins with a digit
54 ('(?P<!>a)', '', SYNTAX_ERROR), # Begins with an illegal char
55 ('(?P<foo!>a)', '', SYNTAX_ERROR), # Begins with an illegal char
56
57 # Same tests, for the ?P= form
58 ('(?P<foo_123>a)(?P=foo_123', 'aa', SYNTAX_ERROR),
59 ('(?P<foo_123>a)(?P=1)', 'aa', SYNTAX_ERROR),
60 ('(?P<foo_123>a)(?P=!)', 'aa', SYNTAX_ERROR),
61 ('(?P<foo_123>a)(?P=foo_124', 'aa', SYNTAX_ERROR), # Backref to undefined group
62
63 ('(?P<foo_123>a)', 'a', SUCCEED, 'g1', 'a'),
64 ('(?P<foo_123>a)(?P=foo_123)', 'aa', SUCCEED, 'g1', 'a'),
65
66 # Test octal escapes
67 ('\\1', 'a', SYNTAX_ERROR),
68 ('\\09', chr(0) + '9', SUCCEED, 'found', chr(0) + '9'),
69 ('\\141', 'a', SUCCEED, 'found', 'a'),
70 ('(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)\\119', 'abcdefghijklk9', SUCCEED, 'found+"-"+g11', 'abcdefghijklk9-k'),
71
72 # Test that a literal \0 is handled everywhere
73 ('\0', '\0', SUCCEED, 'found', '\0'),
74 (r'\0', '\0', SUCCEED, 'found', '\0'),
75 ('[\0a]', '\0', SUCCEED, 'found', '\0'),
76 ('[a\0]', '\0', SUCCEED, 'found', '\0'),
77 ('[^a\0]', '\0', FAIL),
78 (r'[\0a]', '\0', SUCCEED, 'found', '\0'),
79 (r'[a\0]', '\0', SUCCEED, 'found', '\0'),
80 (r'[^a\0]', '\0', FAIL),
81
82 # Test various letter escapes
83 (r'\a[\b]\f\n\r\t\v', '\a\b\f\n\r\t\v', SUCCEED, 'found', '\a\b\f\n\r\t\v'),
84 (r'[\a][\b][\f][\n][\r][\t][\v]', '\a\b\f\n\r\t\v', SUCCEED, 'found', '\a\b\f\n\r\t\v'),
85 (r'\u', '', SYNTAX_ERROR), # A Perl escape
86 (r'\c\e\g\h\i\j\k\m\o\p\q\y\z', 'ceghijkmopqyz', SUCCEED, 'found', 'ceghijkmopqyz'),
87 (r'\xff', '\377', SUCCEED, 'found', chr(255)),
88 (r'\x00ffffffffffffff', '\377', SUCCEED, 'found', chr(255)),
89 (r'\x00f', '\017', SUCCEED, 'found', chr(15)),
90 (r'\x00fe', '\376', SUCCEED, 'found', chr(254)),
91
92 (r"^\w+=(\\[\000-\277]|[^\n\\])*", "SRC=eval.c g.c blah blah blah \\\\\n\tapes.c",
93 SUCCEED, 'found', "SRC=eval.c g.c blah blah blah \\\\"),
94
95 # Test that . only matches \n in DOTALL mode
96 ('a.b', 'acb', SUCCEED, 'found', 'acb'),
97 ('a.b', 'a\nb', FAIL),
98 ('a.*b', 'acc\nccb', FAIL),
99 ('a.{4,5}b', 'acc\nccb', FAIL),
100 ('a.b', 'a\rb', SUCCEED, 'found', 'a\rb'),
101 ('a.b(?s)', 'a\nb', SUCCEED, 'found', 'a\nb'),
102 ('a.*(?s)b', 'acc\nccb', SUCCEED, 'found', 'acc\nccb'),
103 ('(?s)a.{4,5}b', 'acc\nccb', SUCCEED, 'found', 'acc\nccb'),
104 ('(?s)a.b', 'a\nb', SUCCEED, 'found', 'a\nb'),
105
Guido van Rossum337c6d41997-07-15 18:42:58 +0000106 ('abc', 'abc', SUCCEED, 'found', 'abc'),
107 ('abc', 'xbc', FAIL),
108 ('abc', 'axc', FAIL),
109 ('abc', 'abx', FAIL),
110 ('abc', 'xabcy', SUCCEED, 'found', 'abc'),
111 ('abc', 'ababc', SUCCEED, 'found', 'abc'),
112 ('ab*c', 'abc', SUCCEED, 'found', 'abc'),
113 ('ab*bc', 'abc', SUCCEED, 'found', 'abc'),
114 ('ab*bc', 'abbc', SUCCEED, 'found', 'abbc'),
115 ('ab*bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
116 ('ab+bc', 'abbc', SUCCEED, 'found', 'abbc'),
117 ('ab+bc', 'abc', FAIL),
118 ('ab+bc', 'abq', FAIL),
119 ('ab+bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
120 ('ab?bc', 'abbc', SUCCEED, 'found', 'abbc'),
121 ('ab?bc', 'abc', SUCCEED, 'found', 'abc'),
122 ('ab?bc', 'abbbbc', FAIL),
123 ('ab?c', 'abc', SUCCEED, 'found', 'abc'),
124 ('^abc$', 'abc', SUCCEED, 'found', 'abc'),
125 ('^abc$', 'abcc', FAIL),
126 ('^abc', 'abcc', SUCCEED, 'found', 'abc'),
127 ('^abc$', 'aabc', FAIL),
128 ('abc$', 'aabc', SUCCEED, 'found', 'abc'),
129 ('^', 'abc', SUCCEED, 'found+"-"', '-'),
130 ('$', 'abc', SUCCEED, 'found+"-"', '-'),
131 ('a.c', 'abc', SUCCEED, 'found', 'abc'),
132 ('a.c', 'axc', SUCCEED, 'found', 'axc'),
133 ('a.*c', 'axyzc', SUCCEED, 'found', 'axyzc'),
134 ('a.*c', 'axyzd', FAIL),
135 ('a[bc]d', 'abc', FAIL),
136 ('a[bc]d', 'abd', SUCCEED, 'found', 'abd'),
137 ('a[b-d]e', 'abd', FAIL),
138 ('a[b-d]e', 'ace', SUCCEED, 'found', 'ace'),
139 ('a[b-d]', 'aac', SUCCEED, 'found', 'ac'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000140 ('a[-b]', 'a-', SUCCEED, 'found', 'a-'),
Guido van Rossum337c6d41997-07-15 18:42:58 +0000141 ('a[\\-b]', 'a-', SUCCEED, 'found', 'a-'),
142 ('a[b-]', 'a-', SYNTAX_ERROR),
143 ('a[]b', '-', SYNTAX_ERROR),
144 ('a[', '-', SYNTAX_ERROR),
145 ('a\\', '-', SYNTAX_ERROR),
146 ('abc)', '-', SYNTAX_ERROR),
147 ('(abc', '-', SYNTAX_ERROR),
148 ('a]', 'a]', SUCCEED, 'found', 'a]'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000149 ('a[]]b', 'a]b', SUCCEED, 'found', 'a]b'),
Guido van Rossum337c6d41997-07-15 18:42:58 +0000150 ('a[\]]b', 'a]b', SUCCEED, 'found', 'a]b'),
151 ('a[^bc]d', 'aed', SUCCEED, 'found', 'aed'),
152 ('a[^bc]d', 'abd', FAIL),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000153 ('a[^-b]c', 'adc', SUCCEED, 'found', 'adc'),
154 ('a[^-b]c', 'a-c', FAIL),
155 ('a[^]b]c', 'a]c', FAIL),
156 ('a[^]b]c', 'adc', SUCCEED, 'found', 'adc'),
Guido van Rossum337c6d41997-07-15 18:42:58 +0000157 ('\\ba\\b', 'a-', SUCCEED, '"-"', '-'),
158 ('\\ba\\b', '-a', SUCCEED, '"-"', '-'),
159 ('\\ba\\b', '-a-', SUCCEED, '"-"', '-'),
160 ('\\by\\b', 'xy', FAIL),
161 ('\\by\\b', 'yz', FAIL),
162 ('\\by\\b', 'xyz', FAIL),
Guido van Rossumcf005051997-08-15 15:44:58 +0000163 ('x\\b', 'xyz', FAIL),
164 ('x\\B', 'xyz', SUCCEED, '"-"', '-'),
165 ('\\Bz', 'xyz', SUCCEED, '"-"', '-'),
166 ('z\\B', 'xyz', FAIL),
167 ('\\Bx', 'xyz', FAIL),
168 ('\\Ba\\B', 'a-', FAIL, '"-"', '-'),
169 ('\\Ba\\B', '-a', FAIL, '"-"', '-'),
170 ('\\Ba\\B', '-a-', FAIL, '"-"', '-'),
171 ('\\By\\B', 'xy', FAIL),
172 ('\\By\\B', 'yz', FAIL),
173 ('\\By\\b', 'xy', SUCCEED, '"-"', '-'),
174 ('\\by\\B', 'yz', SUCCEED, '"-"', '-'),
175 ('\\By\\B', 'xyz', SUCCEED, '"-"', '-'),
Guido van Rossum337c6d41997-07-15 18:42:58 +0000176 ('ab|cd', 'abc', SUCCEED, 'found', 'ab'),
177 ('ab|cd', 'abcd', SUCCEED, 'found', 'ab'),
178 ('()ef', 'def', SUCCEED, 'found+"-"+g1', 'ef-'),
179 ('$b', 'b', FAIL),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000180 ('a\\(b', 'a(b', SUCCEED, 'found+"-"+g1', 'a(b-Error'),
Guido van Rossum337c6d41997-07-15 18:42:58 +0000181 ('a\\(*b', 'ab', SUCCEED, 'found', 'ab'),
182 ('a\\(*b', 'a((b', SUCCEED, 'found', 'a((b'),
183 ('a\\\\b', 'a\\b', SUCCEED, 'found', 'a\\b'),
184 ('((a))', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'a-a-a'),
185 ('(a)b(c)', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'abc-a-c'),
186 ('a+b+c', 'aabbabc', SUCCEED, 'found', 'abc'),
187 ('(a+|b)*', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'),
188 ('(a+|b)+', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'),
189 ('(a+|b)?', 'ab', SUCCEED, 'found+"-"+g1', 'a-a'),
190 (')(', '-', SYNTAX_ERROR),
191 ('[^ab]*', 'cde', SUCCEED, 'found', 'cde'),
192 ('abc', '', FAIL),
193 ('a*', '', SUCCEED, 'found', ''),
194 ('a|b|c|d|e', 'e', SUCCEED, 'found', 'e'),
195 ('(a|b|c|d|e)f', 'ef', SUCCEED, 'found+"-"+g1', 'ef-e'),
196 ('abcd*efg', 'abcdefg', SUCCEED, 'found', 'abcdefg'),
197 ('ab*', 'xabyabbbz', SUCCEED, 'found', 'ab'),
198 ('ab*', 'xayabbbz', SUCCEED, 'found', 'a'),
199 ('(ab|cd)e', 'abcde', SUCCEED, 'found+"-"+g1', 'cde-cd'),
200 ('[abhgefdc]ij', 'hij', SUCCEED, 'found', 'hij'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000201 ('^(ab|cd)e', 'abcde', FAIL, 'xg1y', 'xy'),
Guido van Rossum337c6d41997-07-15 18:42:58 +0000202 ('(abc|)ef', 'abcdef', SUCCEED, 'found+"-"+g1', 'ef-'),
203 ('(a|b)c*d', 'abcd', SUCCEED, 'found+"-"+g1', 'bcd-b'),
204 ('(ab|ab*)bc', 'abc', SUCCEED, 'found+"-"+g1', 'abc-a'),
205 ('a([bc]*)c*', 'abc', SUCCEED, 'found+"-"+g1', 'abc-bc'),
206 ('a([bc]*)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'),
207 ('a([bc]+)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'),
208 ('a([bc]*)(c+d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-b-cd'),
209 ('a[bcd]*dcdcde', 'adcdcde', SUCCEED, 'found', 'adcdcde'),
210 ('a[bcd]+dcdcde', 'adcdcde', FAIL),
211 ('(ab|a)b*c', 'abc', SUCCEED, 'found+"-"+g1', 'abc-ab'),
212 ('((a)(b)c)(d)', 'abcd', SUCCEED, 'g1+"-"+g2+"-"+g3+"-"+g4', 'abc-a-b-d'),
213 ('[a-zA-Z_][a-zA-Z0-9_]*', 'alpha', SUCCEED, 'found', 'alpha'),
214 ('^a(bc+|b[eh])g|.h$', 'abh', SUCCEED, 'found+"-"+g1', 'bh-None'),
215 ('(bc+d$|ef*g.|h?i(j|k))', 'effgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'),
216 ('(bc+d$|ef*g.|h?i(j|k))', 'ij', SUCCEED, 'found+"-"+g1+"-"+g2', 'ij-ij-j'),
217 ('(bc+d$|ef*g.|h?i(j|k))', 'effg', FAIL),
218 ('(bc+d$|ef*g.|h?i(j|k))', 'bcdd', FAIL),
219 ('(bc+d$|ef*g.|h?i(j|k))', 'reffgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'),
220 ('(((((((((a)))))))))', 'a', SUCCEED, 'found', 'a'),
221 ('multiple words of text', 'uh-uh', FAIL),
222 ('multiple words', 'multiple words, yeah', SUCCEED, 'found', 'multiple words'),
223 ('(.*)c(.*)', 'abcde', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcde-ab-de'),
224 ('\\((.*), (.*)\\)', '(a, b)', SUCCEED, 'g2+"-"+g1', 'b-a'),
225 ('[k]', 'ab', FAIL),
226 ('a[-]?c', 'ac', SUCCEED, 'found', 'ac'),
227 ('(abc)\\1', 'abcabc', SUCCEED, 'g1', 'abc'),
228 ('([a-c]*)\\1', 'abcabc', SUCCEED, 'g1', 'abc'),
229 ('^(.+)?B', 'AB', SUCCEED, 'g1', 'A'),
230 ('(a+).\\1$', 'aaaaa', SUCCEED, 'found+"-"+g1', 'aaaaa-aa'),
231 ('^(a+).\\1$', 'aaaa', FAIL),
232 ('(abc)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'),
233 ('([a-c]+)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'),
234 ('(a)\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'),
235 ('(a+)\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'),
236 ('(a+)+\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'),
237 ('(a).+\\1', 'aba', SUCCEED, 'found+"-"+g1', 'aba-a'),
238 ('(a)ba*\\1', 'aba', SUCCEED, 'found+"-"+g1', 'aba-a'),
239 ('(aa|a)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'),
240 ('(a|aa)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'),
241 ('(a+)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'),
242 ('([abc]*)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'),
243 ('(a)(b)c|ab', 'ab', SUCCEED, 'found+"-"+g1+"-"+g2', 'ab-None-None'),
244 ('(a)+x', 'aaax', SUCCEED, 'found+"-"+g1', 'aaax-a'),
245 ('([ac])+x', 'aacx', SUCCEED, 'found+"-"+g1', 'aacx-c'),
246 ('([^/]*/)*sub1/', 'd:msgs/tdir/sub1/trial/away.cpp', SUCCEED, 'found+"-"+g1', 'd:msgs/tdir/sub1/-tdir/'),
247 ('([^.]*)\\.([^:]*):[T ]+(.*)', 'track1.title:TBlah blah blah', SUCCEED, 'found+"-"+g1+"-"+g2+"-"+g3', 'track1.title:TBlah blah blah-track1-title-Blah blah blah'),
248 ('([^N]*N)+', 'abNNxyzN', SUCCEED, 'found+"-"+g1', 'abNNxyzN-xyzN'),
249 ('([^N]*N)+', 'abNNxyz', SUCCEED, 'found+"-"+g1', 'abNN-N'),
250 ('([abc]*)x', 'abcx', SUCCEED, 'found+"-"+g1', 'abcx-abc'),
251 ('([abc]*)x', 'abc', FAIL),
252 ('([xyz]*)x', 'abcx', SUCCEED, 'found+"-"+g1', 'x-'),
253 ('(a)+b|aac', 'aac', SUCCEED, 'found+"-"+g1', 'aac-None'),
254
255 # Test symbolic groups
256
257 ('(?P<i d>aaa)a', 'aaaa', SYNTAX_ERROR),
258 ('(?P<id>aaa)a', 'aaaa', SUCCEED, 'found+"-"+id', 'aaaa-aaa'),
259 ('(?P<id>aa)(?P=id)', 'aaaa', SUCCEED, 'found+"-"+id', 'aaaa-aa'),
260 ('(?P<id>aa)(?P=xd)', 'aaaa', SYNTAX_ERROR),
261
262 # Test octal escapes/memory references
263
264 ('\\1', 'a', SYNTAX_ERROR),
265 ('\\09', chr(0) + '9', SUCCEED, 'found', chr(0) + '9'),
266 ('\\141', 'a', SUCCEED, 'found', 'a'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000267 ('(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)\\119', 'abcdefghijklk9', SUCCEED, 'found+"-"+g11', 'abcdefghijklk9-k'),
Guido van Rossum337c6d41997-07-15 18:42:58 +0000268
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000269 # All tests from Perl
270
271 ('abc', 'abc', SUCCEED, 'found', 'abc'),
272 ('abc', 'xbc', FAIL),
273 ('abc', 'axc', FAIL),
274 ('abc', 'abx', FAIL),
275 ('abc', 'xabcy', SUCCEED, 'found', 'abc'),
276 ('abc', 'ababc', SUCCEED, 'found', 'abc'),
277 ('ab*c', 'abc', SUCCEED, 'found', 'abc'),
278 ('ab*bc', 'abc', SUCCEED, 'found', 'abc'),
279 ('ab*bc', 'abbc', SUCCEED, 'found', 'abbc'),
280 ('ab*bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
281 ('ab{0,}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
282 ('ab+bc', 'abbc', SUCCEED, 'found', 'abbc'),
283 ('ab+bc', 'abc', FAIL),
284 ('ab+bc', 'abq', FAIL),
285 ('ab{1,}bc', 'abq', FAIL),
286 ('ab+bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
287 ('ab{1,}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
288 ('ab{1,3}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
289 ('ab{3,4}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
290 ('ab{4,5}bc', 'abbbbc', FAIL),
291 ('ab?bc', 'abbc', SUCCEED, 'found', 'abbc'),
292 ('ab?bc', 'abc', SUCCEED, 'found', 'abc'),
293 ('ab{0,1}bc', 'abc', SUCCEED, 'found', 'abc'),
294 ('ab?bc', 'abbbbc', FAIL),
295 ('ab?c', 'abc', SUCCEED, 'found', 'abc'),
296 ('ab{0,1}c', 'abc', SUCCEED, 'found', 'abc'),
297 ('^abc$', 'abc', SUCCEED, 'found', 'abc'),
298 ('^abc$', 'abcc', FAIL),
299 ('^abc', 'abcc', SUCCEED, 'found', 'abc'),
300 ('^abc$', 'aabc', FAIL),
301 ('abc$', 'aabc', SUCCEED, 'found', 'abc'),
302 ('^', 'abc', SUCCEED, 'found', ''),
303 ('$', 'abc', SUCCEED, 'found', ''),
304 ('a.c', 'abc', SUCCEED, 'found', 'abc'),
305 ('a.c', 'axc', SUCCEED, 'found', 'axc'),
306 ('a.*c', 'axyzc', SUCCEED, 'found', 'axyzc'),
307 ('a.*c', 'axyzd', FAIL),
308 ('a[bc]d', 'abc', FAIL),
309 ('a[bc]d', 'abd', SUCCEED, 'found', 'abd'),
310 ('a[b-d]e', 'abd', FAIL),
311 ('a[b-d]e', 'ace', SUCCEED, 'found', 'ace'),
312 ('a[b-d]', 'aac', SUCCEED, 'found', 'ac'),
313 ('a[-b]', 'a-', SUCCEED, 'found', 'a-'),
314 ('a[b-]', 'a-', SUCCEED, 'found', 'a-'),
315 ('a[b-a]', '-', SYNTAX_ERROR),
316 ('a[]b', '-', SYNTAX_ERROR),
317 ('a[', '-', SYNTAX_ERROR),
318 ('a]', 'a]', SUCCEED, 'found', 'a]'),
319 ('a[]]b', 'a]b', SUCCEED, 'found', 'a]b'),
320 ('a[^bc]d', 'aed', SUCCEED, 'found', 'aed'),
321 ('a[^bc]d', 'abd', FAIL),
322 ('a[^-b]c', 'adc', SUCCEED, 'found', 'adc'),
323 ('a[^-b]c', 'a-c', FAIL),
324 ('a[^]b]c', 'a]c', FAIL),
325 ('a[^]b]c', 'adc', SUCCEED, 'found', 'adc'),
326 ('ab|cd', 'abc', SUCCEED, 'found', 'ab'),
327 ('ab|cd', 'abcd', SUCCEED, 'found', 'ab'),
328 ('()ef', 'def', SUCCEED, 'found+"-"+g1', 'ef-'),
329 ('*a', '-', SYNTAX_ERROR),
330 ('(*)b', '-', SYNTAX_ERROR),
331 ('$b', 'b', FAIL),
332 ('a\\', '-', SYNTAX_ERROR),
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000333 ('a\\(b', 'a(b', SUCCEED, 'found+"-"+g1', 'a(b-Error'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000334 ('a\\(*b', 'ab', SUCCEED, 'found', 'ab'),
335 ('a\\(*b', 'a((b', SUCCEED, 'found', 'a((b'),
336 ('a\\\\b', 'a\\b', SUCCEED, 'found', 'a\\b'),
337 ('abc)', '-', SYNTAX_ERROR),
338 ('(abc', '-', SYNTAX_ERROR),
339 ('((a))', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'a-a-a'),
340 ('(a)b(c)', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'abc-a-c'),
341 ('a+b+c', 'aabbabc', SUCCEED, 'found', 'abc'),
342 ('a{1,}b{1,}c', 'aabbabc', SUCCEED, 'found', 'abc'),
Guido van Rossum06c0ec91997-07-17 22:36:39 +0000343 ('a**', '-', SYNTAX_ERROR),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000344 ('a.+?c', 'abcabc', SUCCEED, 'found', 'abc'),
345 ('(a+|b)*', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'),
346 ('(a+|b){0,}', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'),
347 ('(a+|b)+', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'),
348 ('(a+|b){1,}', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'),
349 ('(a+|b)?', 'ab', SUCCEED, 'found+"-"+g1', 'a-a'),
350 ('(a+|b){0,1}', 'ab', SUCCEED, 'found+"-"+g1', 'a-a'),
351 (')(', '-', SYNTAX_ERROR),
352 ('[^ab]*', 'cde', SUCCEED, 'found', 'cde'),
353 ('abc', '', FAIL),
354 ('a*', '', SUCCEED, 'found', ''),
355 ('([abc])*d', 'abbbcd', SUCCEED, 'found+"-"+g1', 'abbbcd-c'),
356 ('([abc])*bcd', 'abcd', SUCCEED, 'found+"-"+g1', 'abcd-a'),
357 ('a|b|c|d|e', 'e', SUCCEED, 'found', 'e'),
358 ('(a|b|c|d|e)f', 'ef', SUCCEED, 'found+"-"+g1', 'ef-e'),
359 ('abcd*efg', 'abcdefg', SUCCEED, 'found', 'abcdefg'),
360 ('ab*', 'xabyabbbz', SUCCEED, 'found', 'ab'),
361 ('ab*', 'xayabbbz', SUCCEED, 'found', 'a'),
362 ('(ab|cd)e', 'abcde', SUCCEED, 'found+"-"+g1', 'cde-cd'),
363 ('[abhgefdc]ij', 'hij', SUCCEED, 'found', 'hij'),
364 ('^(ab|cd)e', 'abcde', FAIL),
365 ('(abc|)ef', 'abcdef', SUCCEED, 'found+"-"+g1', 'ef-'),
366 ('(a|b)c*d', 'abcd', SUCCEED, 'found+"-"+g1', 'bcd-b'),
367 ('(ab|ab*)bc', 'abc', SUCCEED, 'found+"-"+g1', 'abc-a'),
368 ('a([bc]*)c*', 'abc', SUCCEED, 'found+"-"+g1', 'abc-bc'),
369 ('a([bc]*)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'),
370 ('a([bc]+)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'),
371 ('a([bc]*)(c+d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-b-cd'),
372 ('a[bcd]*dcdcde', 'adcdcde', SUCCEED, 'found', 'adcdcde'),
373 ('a[bcd]+dcdcde', 'adcdcde', FAIL),
374 ('(ab|a)b*c', 'abc', SUCCEED, 'found+"-"+g1', 'abc-ab'),
375 ('((a)(b)c)(d)', 'abcd', SUCCEED, 'g1+"-"+g2+"-"+g3+"-"+g4', 'abc-a-b-d'),
376 ('[a-zA-Z_][a-zA-Z0-9_]*', 'alpha', SUCCEED, 'found', 'alpha'),
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000377 ('^a(bc+|b[eh])g|.h$', 'abh', SUCCEED, 'found+"-"+g1', 'bh-None'),
378 ('(bc+d$|ef*g.|h?i(j|k))', 'effgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000379 ('(bc+d$|ef*g.|h?i(j|k))', 'ij', SUCCEED, 'found+"-"+g1+"-"+g2', 'ij-ij-j'),
380 ('(bc+d$|ef*g.|h?i(j|k))', 'effg', FAIL),
381 ('(bc+d$|ef*g.|h?i(j|k))', 'bcdd', FAIL),
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000382 ('(bc+d$|ef*g.|h?i(j|k))', 'reffgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000383 ('((((((((((a))))))))))', 'a', SUCCEED, 'g10', 'a'),
384 ('((((((((((a))))))))))\\10', 'aa', SUCCEED, 'found', 'aa'),
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000385# Python does not have the same rules for \\41 so this is a syntax error
386# ('((((((((((a))))))))))\\41', 'aa', FAIL),
387# ('((((((((((a))))))))))\\41', 'a!', SUCCEED, 'found', 'a!'),
Guido van Rossum06c0ec91997-07-17 22:36:39 +0000388 ('((((((((((a))))))))))\\41', '', SYNTAX_ERROR),
Guido van Rossum95e80531997-08-13 22:34:14 +0000389 ('(?i)((((((((((a))))))))))\\41', '', SYNTAX_ERROR),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000390 ('(((((((((a)))))))))', 'a', SUCCEED, 'found', 'a'),
391 ('multiple words of text', 'uh-uh', FAIL),
392 ('multiple words', 'multiple words, yeah', SUCCEED, 'found', 'multiple words'),
393 ('(.*)c(.*)', 'abcde', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcde-ab-de'),
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000394 ('\\((.*), (.*)\\)', '(a, b)', SUCCEED, 'g2+"-"+g1', 'b-a'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000395 ('[k]', 'ab', FAIL),
Guido van Rossumdfa67901997-12-08 17:12:06 +0000396# XXX
397# ('abcd', 'abcd', SUCCEED, 'found+"-"+\\found+"-"+\\\\found', 'abcd-$&-\\abcd'),
398# ('a(bc)d', 'abcd', SUCCEED, 'g1+"-"+\\g1+"-"+\\\\g1', 'bc-$1-\\bc'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000399 ('a[-]?c', 'ac', SUCCEED, 'found', 'ac'),
400 ('(abc)\\1', 'abcabc', SUCCEED, 'g1', 'abc'),
401 ('([a-c]*)\\1', 'abcabc', SUCCEED, 'g1', 'abc'),
402 ('(?i)abc', 'ABC', SUCCEED, 'found', 'ABC'),
403 ('(?i)abc', 'XBC', FAIL),
404 ('(?i)abc', 'AXC', FAIL),
405 ('(?i)abc', 'ABX', FAIL),
406 ('(?i)abc', 'XABCY', SUCCEED, 'found', 'ABC'),
407 ('(?i)abc', 'ABABC', SUCCEED, 'found', 'ABC'),
408 ('(?i)ab*c', 'ABC', SUCCEED, 'found', 'ABC'),
409 ('(?i)ab*bc', 'ABC', SUCCEED, 'found', 'ABC'),
410 ('(?i)ab*bc', 'ABBC', SUCCEED, 'found', 'ABBC'),
411 ('(?i)ab*?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'),
412 ('(?i)ab{0,}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'),
413 ('(?i)ab+?bc', 'ABBC', SUCCEED, 'found', 'ABBC'),
414 ('(?i)ab+bc', 'ABC', FAIL),
415 ('(?i)ab+bc', 'ABQ', FAIL),
416 ('(?i)ab{1,}bc', 'ABQ', FAIL),
417 ('(?i)ab+bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'),
418 ('(?i)ab{1,}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'),
419 ('(?i)ab{1,3}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'),
420 ('(?i)ab{3,4}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'),
421 ('(?i)ab{4,5}?bc', 'ABBBBC', FAIL),
422 ('(?i)ab??bc', 'ABBC', SUCCEED, 'found', 'ABBC'),
423 ('(?i)ab??bc', 'ABC', SUCCEED, 'found', 'ABC'),
424 ('(?i)ab{0,1}?bc', 'ABC', SUCCEED, 'found', 'ABC'),
425 ('(?i)ab??bc', 'ABBBBC', FAIL),
426 ('(?i)ab??c', 'ABC', SUCCEED, 'found', 'ABC'),
427 ('(?i)ab{0,1}?c', 'ABC', SUCCEED, 'found', 'ABC'),
428 ('(?i)^abc$', 'ABC', SUCCEED, 'found', 'ABC'),
429 ('(?i)^abc$', 'ABCC', FAIL),
430 ('(?i)^abc', 'ABCC', SUCCEED, 'found', 'ABC'),
431 ('(?i)^abc$', 'AABC', FAIL),
432 ('(?i)abc$', 'AABC', SUCCEED, 'found', 'ABC'),
433 ('(?i)^', 'ABC', SUCCEED, 'found', ''),
434 ('(?i)$', 'ABC', SUCCEED, 'found', ''),
435 ('(?i)a.c', 'ABC', SUCCEED, 'found', 'ABC'),
436 ('(?i)a.c', 'AXC', SUCCEED, 'found', 'AXC'),
437 ('(?i)a.*?c', 'AXYZC', SUCCEED, 'found', 'AXYZC'),
438 ('(?i)a.*c', 'AXYZD', FAIL),
439 ('(?i)a[bc]d', 'ABC', FAIL),
440 ('(?i)a[bc]d', 'ABD', SUCCEED, 'found', 'ABD'),
441 ('(?i)a[b-d]e', 'ABD', FAIL),
442 ('(?i)a[b-d]e', 'ACE', SUCCEED, 'found', 'ACE'),
443 ('(?i)a[b-d]', 'AAC', SUCCEED, 'found', 'AC'),
444 ('(?i)a[-b]', 'A-', SUCCEED, 'found', 'A-'),
445 ('(?i)a[b-]', 'A-', SUCCEED, 'found', 'A-'),
446 ('(?i)a[b-a]', '-', SYNTAX_ERROR),
447 ('(?i)a[]b', '-', SYNTAX_ERROR),
448 ('(?i)a[', '-', SYNTAX_ERROR),
449 ('(?i)a]', 'A]', SUCCEED, 'found', 'A]'),
450 ('(?i)a[]]b', 'A]B', SUCCEED, 'found', 'A]B'),
451 ('(?i)a[^bc]d', 'AED', SUCCEED, 'found', 'AED'),
452 ('(?i)a[^bc]d', 'ABD', FAIL),
453 ('(?i)a[^-b]c', 'ADC', SUCCEED, 'found', 'ADC'),
454 ('(?i)a[^-b]c', 'A-C', FAIL),
455 ('(?i)a[^]b]c', 'A]C', FAIL),
456 ('(?i)a[^]b]c', 'ADC', SUCCEED, 'found', 'ADC'),
457 ('(?i)ab|cd', 'ABC', SUCCEED, 'found', 'AB'),
458 ('(?i)ab|cd', 'ABCD', SUCCEED, 'found', 'AB'),
459 ('(?i)()ef', 'DEF', SUCCEED, 'found+"-"+g1', 'EF-'),
460 ('(?i)*a', '-', SYNTAX_ERROR),
461 ('(?i)(*)b', '-', SYNTAX_ERROR),
462 ('(?i)$b', 'B', FAIL),
463 ('(?i)a\\', '-', SYNTAX_ERROR),
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000464 ('(?i)a\\(b', 'A(B', SUCCEED, 'found+"-"+g1', 'A(B-Error'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000465 ('(?i)a\\(*b', 'AB', SUCCEED, 'found', 'AB'),
466 ('(?i)a\\(*b', 'A((B', SUCCEED, 'found', 'A((B'),
467 ('(?i)a\\\\b', 'A\\B', SUCCEED, 'found', 'A\\B'),
468 ('(?i)abc)', '-', SYNTAX_ERROR),
469 ('(?i)(abc', '-', SYNTAX_ERROR),
470 ('(?i)((a))', 'ABC', SUCCEED, 'found+"-"+g1+"-"+g2', 'A-A-A'),
471 ('(?i)(a)b(c)', 'ABC', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABC-A-C'),
472 ('(?i)a+b+c', 'AABBABC', SUCCEED, 'found', 'ABC'),
473 ('(?i)a{1,}b{1,}c', 'AABBABC', SUCCEED, 'found', 'ABC'),
Guido van Rossum06c0ec91997-07-17 22:36:39 +0000474 ('(?i)a**', '-', SYNTAX_ERROR),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000475 ('(?i)a.+?c', 'ABCABC', SUCCEED, 'found', 'ABC'),
476 ('(?i)a.*?c', 'ABCABC', SUCCEED, 'found', 'ABC'),
477 ('(?i)a.{0,5}?c', 'ABCABC', SUCCEED, 'found', 'ABC'),
478 ('(?i)(a+|b)*', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'),
479 ('(?i)(a+|b){0,}', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'),
480 ('(?i)(a+|b)+', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'),
481 ('(?i)(a+|b){1,}', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'),
482 ('(?i)(a+|b)?', 'AB', SUCCEED, 'found+"-"+g1', 'A-A'),
483 ('(?i)(a+|b){0,1}', 'AB', SUCCEED, 'found+"-"+g1', 'A-A'),
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000484 ('(?i)(a+|b){0,1}?', 'AB', SUCCEED, 'found+"-"+g1', '-None'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000485 ('(?i))(', '-', SYNTAX_ERROR),
486 ('(?i)[^ab]*', 'CDE', SUCCEED, 'found', 'CDE'),
487 ('(?i)abc', '', FAIL),
488 ('(?i)a*', '', SUCCEED, 'found', ''),
489 ('(?i)([abc])*d', 'ABBBCD', SUCCEED, 'found+"-"+g1', 'ABBBCD-C'),
490 ('(?i)([abc])*bcd', 'ABCD', SUCCEED, 'found+"-"+g1', 'ABCD-A'),
491 ('(?i)a|b|c|d|e', 'E', SUCCEED, 'found', 'E'),
492 ('(?i)(a|b|c|d|e)f', 'EF', SUCCEED, 'found+"-"+g1', 'EF-E'),
493 ('(?i)abcd*efg', 'ABCDEFG', SUCCEED, 'found', 'ABCDEFG'),
494 ('(?i)ab*', 'XABYABBBZ', SUCCEED, 'found', 'AB'),
495 ('(?i)ab*', 'XAYABBBZ', SUCCEED, 'found', 'A'),
496 ('(?i)(ab|cd)e', 'ABCDE', SUCCEED, 'found+"-"+g1', 'CDE-CD'),
497 ('(?i)[abhgefdc]ij', 'HIJ', SUCCEED, 'found', 'HIJ'),
498 ('(?i)^(ab|cd)e', 'ABCDE', FAIL),
499 ('(?i)(abc|)ef', 'ABCDEF', SUCCEED, 'found+"-"+g1', 'EF-'),
500 ('(?i)(a|b)c*d', 'ABCD', SUCCEED, 'found+"-"+g1', 'BCD-B'),
501 ('(?i)(ab|ab*)bc', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-A'),
502 ('(?i)a([bc]*)c*', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-BC'),
503 ('(?i)a([bc]*)(c*d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-BC-D'),
504 ('(?i)a([bc]+)(c*d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-BC-D'),
505 ('(?i)a([bc]*)(c+d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-B-CD'),
506 ('(?i)a[bcd]*dcdcde', 'ADCDCDE', SUCCEED, 'found', 'ADCDCDE'),
507 ('(?i)a[bcd]+dcdcde', 'ADCDCDE', FAIL),
508 ('(?i)(ab|a)b*c', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-AB'),
509 ('(?i)((a)(b)c)(d)', 'ABCD', SUCCEED, 'g1+"-"+g2+"-"+g3+"-"+g4', 'ABC-A-B-D'),
510 ('(?i)[a-zA-Z_][a-zA-Z0-9_]*', 'ALPHA', SUCCEED, 'found', 'ALPHA'),
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000511 ('(?i)^a(bc+|b[eh])g|.h$', 'ABH', SUCCEED, 'found+"-"+g1', 'BH-None'),
512 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'EFFGZ', SUCCEED, 'found+"-"+g1+"-"+g2', 'EFFGZ-EFFGZ-None'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000513 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'IJ', SUCCEED, 'found+"-"+g1+"-"+g2', 'IJ-IJ-J'),
514 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'EFFG', FAIL),
515 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'BCDD', FAIL),
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000516 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'REFFGZ', SUCCEED, 'found+"-"+g1+"-"+g2', 'EFFGZ-EFFGZ-None'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000517 ('(?i)((((((((((a))))))))))', 'A', SUCCEED, 'g10', 'A'),
518 ('(?i)((((((((((a))))))))))\\10', 'AA', SUCCEED, 'found', 'AA'),
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000519 #('(?i)((((((((((a))))))))))\\41', 'AA', FAIL),
520 #('(?i)((((((((((a))))))))))\\41', 'A!', SUCCEED, 'found', 'A!'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000521 ('(?i)(((((((((a)))))))))', 'A', SUCCEED, 'found', 'A'),
522 ('(?i)(?:(?:(?:(?:(?:(?:(?:(?:(?:(a))))))))))', 'A', SUCCEED, 'g1', 'A'),
523 ('(?i)(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))', 'C', SUCCEED, 'g1', 'C'),
524 ('(?i)multiple words of text', 'UH-UH', FAIL),
525 ('(?i)multiple words', 'MULTIPLE WORDS, YEAH', SUCCEED, 'found', 'MULTIPLE WORDS'),
526 ('(?i)(.*)c(.*)', 'ABCDE', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCDE-AB-DE'),
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000527 ('(?i)\\((.*), (.*)\\)', '(A, B)', SUCCEED, 'g2+"-"+g1', 'B-A'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000528 ('(?i)[k]', 'AB', FAIL),
Guido van Rossumdfa67901997-12-08 17:12:06 +0000529# ('(?i)abcd', 'ABCD', SUCCEED, 'found+"-"+\\found+"-"+\\\\found', 'ABCD-$&-\\ABCD'),
530# ('(?i)a(bc)d', 'ABCD', SUCCEED, 'g1+"-"+\\g1+"-"+\\\\g1', 'BC-$1-\\BC'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000531 ('(?i)a[-]?c', 'AC', SUCCEED, 'found', 'AC'),
532 ('(?i)(abc)\\1', 'ABCABC', SUCCEED, 'g1', 'ABC'),
533 ('(?i)([a-c]*)\\1', 'ABCABC', SUCCEED, 'g1', 'ABC'),
Guido van Rossumdfa67901997-12-08 17:12:06 +0000534 ('a(?!b).', 'abad', SUCCEED, 'found', 'ad'),
535 ('a(?=d).', 'abad', SUCCEED, 'found', 'ad'),
536 ('a(?=c|d).', 'abad', SUCCEED, 'found', 'ad'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000537 ('a(?:b|c|d)(.)', 'ace', SUCCEED, 'g1', 'e'),
538 ('a(?:b|c|d)*(.)', 'ace', SUCCEED, 'g1', 'e'),
539 ('a(?:b|c|d)+?(.)', 'ace', SUCCEED, 'g1', 'e'),
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000540 ('a(?:b|(c|e){1,2}?|d)+?(.)', 'ace', SUCCEED, 'g1 + g2', 'ce'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000541 ('^(.+)?B', 'AB', SUCCEED, 'g1', 'A'),
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000542
543 # Comments using the (?#...) syntax
544
545 ('w(?# comment', 'w', SYNTAX_ERROR),
546 ('w(?# comment 1)xy(?# comment 2)z', 'wxyz', SUCCEED, 'found', 'wxyz'),
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000547
Guido van Rossum06c0ec91997-07-17 22:36:39 +0000548 # Check odd placement of embedded pattern modifiers
549
550 ('w(?i)', 'W', SYNTAX_ERROR),
551
552 # Comments using the x embedded pattern modifier
553
554 ("""(?x)w# comment 1
555 x y
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000556 # comment 2
557 z""", 'wxyz', SUCCEED, 'found', 'wxyz'),
558
559 # using the m embedded pattern modifier
560
561 ('^abc', """jkl
562abc
563xyz""", FAIL),
564 ('(?m)^abc', """jkl
565abc
566xyz""", SUCCEED, 'found', 'abc'),
567
Guido van Rossum06c0ec91997-07-17 22:36:39 +0000568 ('(?m)abc$', """jkl
569xyzabc
570123""", SUCCEED, 'found', 'abc'),
571
Guido van Rossuma0e4c1b1997-07-17 14:52:48 +0000572 # using the s embedded pattern modifier
573
574 ('a.b', 'a\nb', FAIL),
575 ('(?s)a.b', 'a\nb', SUCCEED, 'found', 'a\nb'),
Guido van Rossum06c0ec91997-07-17 22:36:39 +0000576
Guido van Rossum95e80531997-08-13 22:34:14 +0000577 # test \w, etc. both inside and outside character classes
Guido van Rossum06c0ec91997-07-17 22:36:39 +0000578
579 ('\\w+', '--ab_cd0123--', SUCCEED, 'found', 'ab_cd0123'),
Guido van Rossum95e80531997-08-13 22:34:14 +0000580 ('[\\w]+', '--ab_cd0123--', SUCCEED, 'found', 'ab_cd0123'),
Guido van Rossum06c0ec91997-07-17 22:36:39 +0000581 ('\\D+', '1234abc5678', SUCCEED, 'found', 'abc'),
Guido van Rossum95e80531997-08-13 22:34:14 +0000582 ('[\\D]+', '1234abc5678', SUCCEED, 'found', 'abc'),
Guido van Rossum06c0ec91997-07-17 22:36:39 +0000583 ('[\\da-fA-F]+', '123abc', SUCCEED, 'found', '123abc'),
584 ('[\\d-x]', '-', SYNTAX_ERROR),
Guido van Rossum95e80531997-08-13 22:34:14 +0000585 (r'([\s]*)([\S]*)([\s]*)', ' testing!1972', SUCCEED, 'g3+g2+g1', 'testing!1972 '),
586 (r'(\s*)(\S*)(\s*)', ' testing!1972', SUCCEED, 'g3+g2+g1', 'testing!1972 '),
587
588 (r'\xff', '\377', SUCCEED, 'found', chr(255)),
589 (r'\x00ff', '\377', SUCCEED, 'found', chr(255)),
590 (r'\t\n\v\r\f\a\g', '\t\n\v\r\f\ag', SUCCEED, 'found', '\t\n\v\r\f\ag'),
591 ('\t\n\v\r\f\a\g', '\t\n\v\r\f\ag', SUCCEED, 'found', '\t\n\v\r\f\ag'),
592 (r'\t\n\v\r\f\a', '\t\n\v\r\f\a', SUCCEED, 'found', chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7)),
Guido van Rossumdfa67901997-12-08 17:12:06 +0000593 (r'[\t][\n][\v][\r][\f][\b]', '\t\n\v\r\f\b', SUCCEED, 'found', '\t\n\v\r\f\b'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000594]