blob: 27b92304e0212a7ca11bbb37074c0eb40affb244 [file] [log] [blame]
Guido van Rossum337c6d41997-07-15 18:42:58 +00001#!/usr/bin/env python
2# -*- mode: python -*-
3# $Id$
4
Guido van Rossum8e0ce301997-07-11 19:34:44 +00005# Re test suite and benchmark suite v1.5a2
6
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
50tests = [
Guido van Rossum337c6d41997-07-15 18:42:58 +000051 ('abc', 'abc', SUCCEED, 'found', 'abc'),
52 ('abc', 'xbc', FAIL),
53 ('abc', 'axc', FAIL),
54 ('abc', 'abx', FAIL),
55 ('abc', 'xabcy', SUCCEED, 'found', 'abc'),
56 ('abc', 'ababc', SUCCEED, 'found', 'abc'),
57 ('ab*c', 'abc', SUCCEED, 'found', 'abc'),
58 ('ab*bc', 'abc', SUCCEED, 'found', 'abc'),
59 ('ab*bc', 'abbc', SUCCEED, 'found', 'abbc'),
60 ('ab*bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
61 ('ab+bc', 'abbc', SUCCEED, 'found', 'abbc'),
62 ('ab+bc', 'abc', FAIL),
63 ('ab+bc', 'abq', FAIL),
64 ('ab+bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
65 ('ab?bc', 'abbc', SUCCEED, 'found', 'abbc'),
66 ('ab?bc', 'abc', SUCCEED, 'found', 'abc'),
67 ('ab?bc', 'abbbbc', FAIL),
68 ('ab?c', 'abc', SUCCEED, 'found', 'abc'),
69 ('^abc$', 'abc', SUCCEED, 'found', 'abc'),
70 ('^abc$', 'abcc', FAIL),
71 ('^abc', 'abcc', SUCCEED, 'found', 'abc'),
72 ('^abc$', 'aabc', FAIL),
73 ('abc$', 'aabc', SUCCEED, 'found', 'abc'),
74 ('^', 'abc', SUCCEED, 'found+"-"', '-'),
75 ('$', 'abc', SUCCEED, 'found+"-"', '-'),
76 ('a.c', 'abc', SUCCEED, 'found', 'abc'),
77 ('a.c', 'axc', SUCCEED, 'found', 'axc'),
78 ('a.*c', 'axyzc', SUCCEED, 'found', 'axyzc'),
79 ('a.*c', 'axyzd', FAIL),
80 ('a[bc]d', 'abc', FAIL),
81 ('a[bc]d', 'abd', SUCCEED, 'found', 'abd'),
82 ('a[b-d]e', 'abd', FAIL),
83 ('a[b-d]e', 'ace', SUCCEED, 'found', 'ace'),
84 ('a[b-d]', 'aac', SUCCEED, 'found', 'ac'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +000085 ('a[-b]', 'a-', SUCCEED, 'found', 'a-'),
Guido van Rossum337c6d41997-07-15 18:42:58 +000086 ('a[\\-b]', 'a-', SUCCEED, 'found', 'a-'),
87 ('a[b-]', 'a-', SYNTAX_ERROR),
88 ('a[]b', '-', SYNTAX_ERROR),
89 ('a[', '-', SYNTAX_ERROR),
90 ('a\\', '-', SYNTAX_ERROR),
91 ('abc)', '-', SYNTAX_ERROR),
92 ('(abc', '-', SYNTAX_ERROR),
93 ('a]', 'a]', SUCCEED, 'found', 'a]'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +000094 ('a[]]b', 'a]b', SUCCEED, 'found', 'a]b'),
Guido van Rossum337c6d41997-07-15 18:42:58 +000095 ('a[\]]b', 'a]b', SUCCEED, 'found', 'a]b'),
96 ('a[^bc]d', 'aed', SUCCEED, 'found', 'aed'),
97 ('a[^bc]d', 'abd', FAIL),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +000098 ('a[^-b]c', 'adc', SUCCEED, 'found', 'adc'),
99 ('a[^-b]c', 'a-c', FAIL),
100 ('a[^]b]c', 'a]c', FAIL),
101 ('a[^]b]c', 'adc', SUCCEED, 'found', 'adc'),
Guido van Rossum337c6d41997-07-15 18:42:58 +0000102 ('\\ba\\b', 'a-', SUCCEED, '"-"', '-'),
103 ('\\ba\\b', '-a', SUCCEED, '"-"', '-'),
104 ('\\ba\\b', '-a-', SUCCEED, '"-"', '-'),
105 ('\\by\\b', 'xy', FAIL),
106 ('\\by\\b', 'yz', FAIL),
107 ('\\by\\b', 'xyz', FAIL),
108 ('ab|cd', 'abc', SUCCEED, 'found', 'ab'),
109 ('ab|cd', 'abcd', SUCCEED, 'found', 'ab'),
110 ('()ef', 'def', SUCCEED, 'found+"-"+g1', 'ef-'),
111 ('$b', 'b', FAIL),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000112 ('a\\(b', 'a(b', SUCCEED, 'found+"-"+g1', 'a(b-Error'),
Guido van Rossum337c6d41997-07-15 18:42:58 +0000113 ('a\\(*b', 'ab', SUCCEED, 'found', 'ab'),
114 ('a\\(*b', 'a((b', SUCCEED, 'found', 'a((b'),
115 ('a\\\\b', 'a\\b', SUCCEED, 'found', 'a\\b'),
116 ('((a))', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'a-a-a'),
117 ('(a)b(c)', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'abc-a-c'),
118 ('a+b+c', 'aabbabc', SUCCEED, 'found', 'abc'),
119 ('(a+|b)*', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'),
120 ('(a+|b)+', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'),
121 ('(a+|b)?', 'ab', SUCCEED, 'found+"-"+g1', 'a-a'),
122 (')(', '-', SYNTAX_ERROR),
123 ('[^ab]*', 'cde', SUCCEED, 'found', 'cde'),
124 ('abc', '', FAIL),
125 ('a*', '', SUCCEED, 'found', ''),
126 ('a|b|c|d|e', 'e', SUCCEED, 'found', 'e'),
127 ('(a|b|c|d|e)f', 'ef', SUCCEED, 'found+"-"+g1', 'ef-e'),
128 ('abcd*efg', 'abcdefg', SUCCEED, 'found', 'abcdefg'),
129 ('ab*', 'xabyabbbz', SUCCEED, 'found', 'ab'),
130 ('ab*', 'xayabbbz', SUCCEED, 'found', 'a'),
131 ('(ab|cd)e', 'abcde', SUCCEED, 'found+"-"+g1', 'cde-cd'),
132 ('[abhgefdc]ij', 'hij', SUCCEED, 'found', 'hij'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000133 ('^(ab|cd)e', 'abcde', FAIL, 'xg1y', 'xy'),
Guido van Rossum337c6d41997-07-15 18:42:58 +0000134 ('(abc|)ef', 'abcdef', SUCCEED, 'found+"-"+g1', 'ef-'),
135 ('(a|b)c*d', 'abcd', SUCCEED, 'found+"-"+g1', 'bcd-b'),
136 ('(ab|ab*)bc', 'abc', SUCCEED, 'found+"-"+g1', 'abc-a'),
137 ('a([bc]*)c*', 'abc', SUCCEED, 'found+"-"+g1', 'abc-bc'),
138 ('a([bc]*)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'),
139 ('a([bc]+)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'),
140 ('a([bc]*)(c+d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-b-cd'),
141 ('a[bcd]*dcdcde', 'adcdcde', SUCCEED, 'found', 'adcdcde'),
142 ('a[bcd]+dcdcde', 'adcdcde', FAIL),
143 ('(ab|a)b*c', 'abc', SUCCEED, 'found+"-"+g1', 'abc-ab'),
144 ('((a)(b)c)(d)', 'abcd', SUCCEED, 'g1+"-"+g2+"-"+g3+"-"+g4', 'abc-a-b-d'),
145 ('[a-zA-Z_][a-zA-Z0-9_]*', 'alpha', SUCCEED, 'found', 'alpha'),
146 ('^a(bc+|b[eh])g|.h$', 'abh', SUCCEED, 'found+"-"+g1', 'bh-None'),
147 ('(bc+d$|ef*g.|h?i(j|k))', 'effgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'),
148 ('(bc+d$|ef*g.|h?i(j|k))', 'ij', SUCCEED, 'found+"-"+g1+"-"+g2', 'ij-ij-j'),
149 ('(bc+d$|ef*g.|h?i(j|k))', 'effg', FAIL),
150 ('(bc+d$|ef*g.|h?i(j|k))', 'bcdd', FAIL),
151 ('(bc+d$|ef*g.|h?i(j|k))', 'reffgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'),
152 ('(((((((((a)))))))))', 'a', SUCCEED, 'found', 'a'),
153 ('multiple words of text', 'uh-uh', FAIL),
154 ('multiple words', 'multiple words, yeah', SUCCEED, 'found', 'multiple words'),
155 ('(.*)c(.*)', 'abcde', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcde-ab-de'),
156 ('\\((.*), (.*)\\)', '(a, b)', SUCCEED, 'g2+"-"+g1', 'b-a'),
157 ('[k]', 'ab', FAIL),
158 ('a[-]?c', 'ac', SUCCEED, 'found', 'ac'),
159 ('(abc)\\1', 'abcabc', SUCCEED, 'g1', 'abc'),
160 ('([a-c]*)\\1', 'abcabc', SUCCEED, 'g1', 'abc'),
161 ('^(.+)?B', 'AB', SUCCEED, 'g1', 'A'),
162 ('(a+).\\1$', 'aaaaa', SUCCEED, 'found+"-"+g1', 'aaaaa-aa'),
163 ('^(a+).\\1$', 'aaaa', FAIL),
164 ('(abc)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'),
165 ('([a-c]+)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'),
166 ('(a)\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'),
167 ('(a+)\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'),
168 ('(a+)+\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'),
169 ('(a).+\\1', 'aba', SUCCEED, 'found+"-"+g1', 'aba-a'),
170 ('(a)ba*\\1', 'aba', SUCCEED, 'found+"-"+g1', 'aba-a'),
171 ('(aa|a)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'),
172 ('(a|aa)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'),
173 ('(a+)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'),
174 ('([abc]*)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'),
175 ('(a)(b)c|ab', 'ab', SUCCEED, 'found+"-"+g1+"-"+g2', 'ab-None-None'),
176 ('(a)+x', 'aaax', SUCCEED, 'found+"-"+g1', 'aaax-a'),
177 ('([ac])+x', 'aacx', SUCCEED, 'found+"-"+g1', 'aacx-c'),
178 ('([^/]*/)*sub1/', 'd:msgs/tdir/sub1/trial/away.cpp', SUCCEED, 'found+"-"+g1', 'd:msgs/tdir/sub1/-tdir/'),
179 ('([^.]*)\\.([^:]*):[T ]+(.*)', 'track1.title:TBlah blah blah', SUCCEED, 'found+"-"+g1+"-"+g2+"-"+g3', 'track1.title:TBlah blah blah-track1-title-Blah blah blah'),
180 ('([^N]*N)+', 'abNNxyzN', SUCCEED, 'found+"-"+g1', 'abNNxyzN-xyzN'),
181 ('([^N]*N)+', 'abNNxyz', SUCCEED, 'found+"-"+g1', 'abNN-N'),
182 ('([abc]*)x', 'abcx', SUCCEED, 'found+"-"+g1', 'abcx-abc'),
183 ('([abc]*)x', 'abc', FAIL),
184 ('([xyz]*)x', 'abcx', SUCCEED, 'found+"-"+g1', 'x-'),
185 ('(a)+b|aac', 'aac', SUCCEED, 'found+"-"+g1', 'aac-None'),
186
187 # Test symbolic groups
188
189 ('(?P<i d>aaa)a', 'aaaa', SYNTAX_ERROR),
190 ('(?P<id>aaa)a', 'aaaa', SUCCEED, 'found+"-"+id', 'aaaa-aaa'),
191 ('(?P<id>aa)(?P=id)', 'aaaa', SUCCEED, 'found+"-"+id', 'aaaa-aa'),
192 ('(?P<id>aa)(?P=xd)', 'aaaa', SYNTAX_ERROR),
193
194 # Test octal escapes/memory references
195
196 ('\\1', 'a', SYNTAX_ERROR),
197 ('\\09', chr(0) + '9', SUCCEED, 'found', chr(0) + '9'),
198 ('\\141', 'a', SUCCEED, 'found', 'a'),
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000199 ('(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 +0000200
Guido van Rossum16bd0ff1997-07-15 18:45:20 +0000201 # All tests from Perl
202
203 ('abc', 'abc', SUCCEED, 'found', 'abc'),
204 ('abc', 'xbc', FAIL),
205 ('abc', 'axc', FAIL),
206 ('abc', 'abx', FAIL),
207 ('abc', 'xabcy', SUCCEED, 'found', 'abc'),
208 ('abc', 'ababc', SUCCEED, 'found', 'abc'),
209 ('ab*c', 'abc', SUCCEED, 'found', 'abc'),
210 ('ab*bc', 'abc', SUCCEED, 'found', 'abc'),
211 ('ab*bc', 'abbc', SUCCEED, 'found', 'abbc'),
212 ('ab*bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
213 ('ab{0,}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
214 ('ab+bc', 'abbc', SUCCEED, 'found', 'abbc'),
215 ('ab+bc', 'abc', FAIL),
216 ('ab+bc', 'abq', FAIL),
217 ('ab{1,}bc', 'abq', FAIL),
218 ('ab+bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
219 ('ab{1,}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
220 ('ab{1,3}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
221 ('ab{3,4}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'),
222 ('ab{4,5}bc', 'abbbbc', FAIL),
223 ('ab?bc', 'abbc', SUCCEED, 'found', 'abbc'),
224 ('ab?bc', 'abc', SUCCEED, 'found', 'abc'),
225 ('ab{0,1}bc', 'abc', SUCCEED, 'found', 'abc'),
226 ('ab?bc', 'abbbbc', FAIL),
227 ('ab?c', 'abc', SUCCEED, 'found', 'abc'),
228 ('ab{0,1}c', 'abc', SUCCEED, 'found', 'abc'),
229 ('^abc$', 'abc', SUCCEED, 'found', 'abc'),
230 ('^abc$', 'abcc', FAIL),
231 ('^abc', 'abcc', SUCCEED, 'found', 'abc'),
232 ('^abc$', 'aabc', FAIL),
233 ('abc$', 'aabc', SUCCEED, 'found', 'abc'),
234 ('^', 'abc', SUCCEED, 'found', ''),
235 ('$', 'abc', SUCCEED, 'found', ''),
236 ('a.c', 'abc', SUCCEED, 'found', 'abc'),
237 ('a.c', 'axc', SUCCEED, 'found', 'axc'),
238 ('a.*c', 'axyzc', SUCCEED, 'found', 'axyzc'),
239 ('a.*c', 'axyzd', FAIL),
240 ('a[bc]d', 'abc', FAIL),
241 ('a[bc]d', 'abd', SUCCEED, 'found', 'abd'),
242 ('a[b-d]e', 'abd', FAIL),
243 ('a[b-d]e', 'ace', SUCCEED, 'found', 'ace'),
244 ('a[b-d]', 'aac', SUCCEED, 'found', 'ac'),
245 ('a[-b]', 'a-', SUCCEED, 'found', 'a-'),
246 ('a[b-]', 'a-', SUCCEED, 'found', 'a-'),
247 ('a[b-a]', '-', SYNTAX_ERROR),
248 ('a[]b', '-', SYNTAX_ERROR),
249 ('a[', '-', SYNTAX_ERROR),
250 ('a]', 'a]', SUCCEED, 'found', 'a]'),
251 ('a[]]b', 'a]b', SUCCEED, 'found', 'a]b'),
252 ('a[^bc]d', 'aed', SUCCEED, 'found', 'aed'),
253 ('a[^bc]d', 'abd', FAIL),
254 ('a[^-b]c', 'adc', SUCCEED, 'found', 'adc'),
255 ('a[^-b]c', 'a-c', FAIL),
256 ('a[^]b]c', 'a]c', FAIL),
257 ('a[^]b]c', 'adc', SUCCEED, 'found', 'adc'),
258 ('ab|cd', 'abc', SUCCEED, 'found', 'ab'),
259 ('ab|cd', 'abcd', SUCCEED, 'found', 'ab'),
260 ('()ef', 'def', SUCCEED, 'found+"-"+g1', 'ef-'),
261 ('*a', '-', SYNTAX_ERROR),
262 ('(*)b', '-', SYNTAX_ERROR),
263 ('$b', 'b', FAIL),
264 ('a\\', '-', SYNTAX_ERROR),
265 ('a\\(b', 'a(b', SUCCEED, 'found+"-"+g1', 'a(b-'),
266 ('a\\(*b', 'ab', SUCCEED, 'found', 'ab'),
267 ('a\\(*b', 'a((b', SUCCEED, 'found', 'a((b'),
268 ('a\\\\b', 'a\\b', SUCCEED, 'found', 'a\\b'),
269 ('abc)', '-', SYNTAX_ERROR),
270 ('(abc', '-', SYNTAX_ERROR),
271 ('((a))', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'a-a-a'),
272 ('(a)b(c)', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'abc-a-c'),
273 ('a+b+c', 'aabbabc', SUCCEED, 'found', 'abc'),
274 ('a{1,}b{1,}c', 'aabbabc', SUCCEED, 'found', 'abc'),
275 #('a**', '-', SYNTAX_ERROR),
276 ('a.+?c', 'abcabc', SUCCEED, 'found', 'abc'),
277 ('(a+|b)*', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'),
278 ('(a+|b){0,}', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'),
279 ('(a+|b)+', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'),
280 ('(a+|b){1,}', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'),
281 ('(a+|b)?', 'ab', SUCCEED, 'found+"-"+g1', 'a-a'),
282 ('(a+|b){0,1}', 'ab', SUCCEED, 'found+"-"+g1', 'a-a'),
283 (')(', '-', SYNTAX_ERROR),
284 ('[^ab]*', 'cde', SUCCEED, 'found', 'cde'),
285 ('abc', '', FAIL),
286 ('a*', '', SUCCEED, 'found', ''),
287 ('([abc])*d', 'abbbcd', SUCCEED, 'found+"-"+g1', 'abbbcd-c'),
288 ('([abc])*bcd', 'abcd', SUCCEED, 'found+"-"+g1', 'abcd-a'),
289 ('a|b|c|d|e', 'e', SUCCEED, 'found', 'e'),
290 ('(a|b|c|d|e)f', 'ef', SUCCEED, 'found+"-"+g1', 'ef-e'),
291 ('abcd*efg', 'abcdefg', SUCCEED, 'found', 'abcdefg'),
292 ('ab*', 'xabyabbbz', SUCCEED, 'found', 'ab'),
293 ('ab*', 'xayabbbz', SUCCEED, 'found', 'a'),
294 ('(ab|cd)e', 'abcde', SUCCEED, 'found+"-"+g1', 'cde-cd'),
295 ('[abhgefdc]ij', 'hij', SUCCEED, 'found', 'hij'),
296 ('^(ab|cd)e', 'abcde', FAIL),
297 ('(abc|)ef', 'abcdef', SUCCEED, 'found+"-"+g1', 'ef-'),
298 ('(a|b)c*d', 'abcd', SUCCEED, 'found+"-"+g1', 'bcd-b'),
299 ('(ab|ab*)bc', 'abc', SUCCEED, 'found+"-"+g1', 'abc-a'),
300 ('a([bc]*)c*', 'abc', SUCCEED, 'found+"-"+g1', 'abc-bc'),
301 ('a([bc]*)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'),
302 ('a([bc]+)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'),
303 ('a([bc]*)(c+d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-b-cd'),
304 ('a[bcd]*dcdcde', 'adcdcde', SUCCEED, 'found', 'adcdcde'),
305 ('a[bcd]+dcdcde', 'adcdcde', FAIL),
306 ('(ab|a)b*c', 'abc', SUCCEED, 'found+"-"+g1', 'abc-ab'),
307 ('((a)(b)c)(d)', 'abcd', SUCCEED, 'g1+"-"+g2+"-"+g3+"-"+g4', 'abc-a-b-d'),
308 ('[a-zA-Z_][a-zA-Z0-9_]*', 'alpha', SUCCEED, 'found', 'alpha'),
309 ('^a(bc+|b[eh])g|.h$', 'abh', SUCCEED, 'found+"-"+g1', 'bh-'),
310 ('(bc+d$|ef*g.|h?i(j|k))', 'effgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-'),
311 ('(bc+d$|ef*g.|h?i(j|k))', 'ij', SUCCEED, 'found+"-"+g1+"-"+g2', 'ij-ij-j'),
312 ('(bc+d$|ef*g.|h?i(j|k))', 'effg', FAIL),
313 ('(bc+d$|ef*g.|h?i(j|k))', 'bcdd', FAIL),
314 ('(bc+d$|ef*g.|h?i(j|k))', 'reffgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-'),
315 ('((((((((((a))))))))))', 'a', SUCCEED, 'g10', 'a'),
316 ('((((((((((a))))))))))\\10', 'aa', SUCCEED, 'found', 'aa'),
317 ('((((((((((a))))))))))\\41', 'aa', FAIL),
318 ('((((((((((a))))))))))\\41', 'a!', SUCCEED, 'found', 'a!'),
319 ('(((((((((a)))))))))', 'a', SUCCEED, 'found', 'a'),
320 ('multiple words of text', 'uh-uh', FAIL),
321 ('multiple words', 'multiple words, yeah', SUCCEED, 'found', 'multiple words'),
322 ('(.*)c(.*)', 'abcde', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcde-ab-de'),
323 ('\\((.*), (.*)\\)', '(a, b)', SUCCEED, '(g2, g1)', '(b, a)'),
324 ('[k]', 'ab', FAIL),
325 ##('abcd', 'abcd', SUCCEED, 'found+"-"+\\found+"-"+\\\\found', 'abcd-$&-\\abcd'),
326 ##('a(bc)d', 'abcd', SUCCEED, 'g1+"-"+\\g1+"-"+\\\\g1', 'bc-$1-\\bc'),
327 ('a[-]?c', 'ac', SUCCEED, 'found', 'ac'),
328 ('(abc)\\1', 'abcabc', SUCCEED, 'g1', 'abc'),
329 ('([a-c]*)\\1', 'abcabc', SUCCEED, 'g1', 'abc'),
330 ('(?i)abc', 'ABC', SUCCEED, 'found', 'ABC'),
331 ('(?i)abc', 'XBC', FAIL),
332 ('(?i)abc', 'AXC', FAIL),
333 ('(?i)abc', 'ABX', FAIL),
334 ('(?i)abc', 'XABCY', SUCCEED, 'found', 'ABC'),
335 ('(?i)abc', 'ABABC', SUCCEED, 'found', 'ABC'),
336 ('(?i)ab*c', 'ABC', SUCCEED, 'found', 'ABC'),
337 ('(?i)ab*bc', 'ABC', SUCCEED, 'found', 'ABC'),
338 ('(?i)ab*bc', 'ABBC', SUCCEED, 'found', 'ABBC'),
339 ('(?i)ab*?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'),
340 ('(?i)ab{0,}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'),
341 ('(?i)ab+?bc', 'ABBC', SUCCEED, 'found', 'ABBC'),
342 ('(?i)ab+bc', 'ABC', FAIL),
343 ('(?i)ab+bc', 'ABQ', FAIL),
344 ('(?i)ab{1,}bc', 'ABQ', FAIL),
345 ('(?i)ab+bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'),
346 ('(?i)ab{1,}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'),
347 ('(?i)ab{1,3}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'),
348 ('(?i)ab{3,4}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'),
349 ('(?i)ab{4,5}?bc', 'ABBBBC', FAIL),
350 ('(?i)ab??bc', 'ABBC', SUCCEED, 'found', 'ABBC'),
351 ('(?i)ab??bc', 'ABC', SUCCEED, 'found', 'ABC'),
352 ('(?i)ab{0,1}?bc', 'ABC', SUCCEED, 'found', 'ABC'),
353 ('(?i)ab??bc', 'ABBBBC', FAIL),
354 ('(?i)ab??c', 'ABC', SUCCEED, 'found', 'ABC'),
355 ('(?i)ab{0,1}?c', 'ABC', SUCCEED, 'found', 'ABC'),
356 ('(?i)^abc$', 'ABC', SUCCEED, 'found', 'ABC'),
357 ('(?i)^abc$', 'ABCC', FAIL),
358 ('(?i)^abc', 'ABCC', SUCCEED, 'found', 'ABC'),
359 ('(?i)^abc$', 'AABC', FAIL),
360 ('(?i)abc$', 'AABC', SUCCEED, 'found', 'ABC'),
361 ('(?i)^', 'ABC', SUCCEED, 'found', ''),
362 ('(?i)$', 'ABC', SUCCEED, 'found', ''),
363 ('(?i)a.c', 'ABC', SUCCEED, 'found', 'ABC'),
364 ('(?i)a.c', 'AXC', SUCCEED, 'found', 'AXC'),
365 ('(?i)a.*?c', 'AXYZC', SUCCEED, 'found', 'AXYZC'),
366 ('(?i)a.*c', 'AXYZD', FAIL),
367 ('(?i)a[bc]d', 'ABC', FAIL),
368 ('(?i)a[bc]d', 'ABD', SUCCEED, 'found', 'ABD'),
369 ('(?i)a[b-d]e', 'ABD', FAIL),
370 ('(?i)a[b-d]e', 'ACE', SUCCEED, 'found', 'ACE'),
371 ('(?i)a[b-d]', 'AAC', SUCCEED, 'found', 'AC'),
372 ('(?i)a[-b]', 'A-', SUCCEED, 'found', 'A-'),
373 ('(?i)a[b-]', 'A-', SUCCEED, 'found', 'A-'),
374 ('(?i)a[b-a]', '-', SYNTAX_ERROR),
375 ('(?i)a[]b', '-', SYNTAX_ERROR),
376 ('(?i)a[', '-', SYNTAX_ERROR),
377 ('(?i)a]', 'A]', SUCCEED, 'found', 'A]'),
378 ('(?i)a[]]b', 'A]B', SUCCEED, 'found', 'A]B'),
379 ('(?i)a[^bc]d', 'AED', SUCCEED, 'found', 'AED'),
380 ('(?i)a[^bc]d', 'ABD', FAIL),
381 ('(?i)a[^-b]c', 'ADC', SUCCEED, 'found', 'ADC'),
382 ('(?i)a[^-b]c', 'A-C', FAIL),
383 ('(?i)a[^]b]c', 'A]C', FAIL),
384 ('(?i)a[^]b]c', 'ADC', SUCCEED, 'found', 'ADC'),
385 ('(?i)ab|cd', 'ABC', SUCCEED, 'found', 'AB'),
386 ('(?i)ab|cd', 'ABCD', SUCCEED, 'found', 'AB'),
387 ('(?i)()ef', 'DEF', SUCCEED, 'found+"-"+g1', 'EF-'),
388 ('(?i)*a', '-', SYNTAX_ERROR),
389 ('(?i)(*)b', '-', SYNTAX_ERROR),
390 ('(?i)$b', 'B', FAIL),
391 ('(?i)a\\', '-', SYNTAX_ERROR),
392 ('(?i)a\\(b', 'A(B', SUCCEED, 'found+"-"+g1', 'A(B-'),
393 ('(?i)a\\(*b', 'AB', SUCCEED, 'found', 'AB'),
394 ('(?i)a\\(*b', 'A((B', SUCCEED, 'found', 'A((B'),
395 ('(?i)a\\\\b', 'A\\B', SUCCEED, 'found', 'A\\B'),
396 ('(?i)abc)', '-', SYNTAX_ERROR),
397 ('(?i)(abc', '-', SYNTAX_ERROR),
398 ('(?i)((a))', 'ABC', SUCCEED, 'found+"-"+g1+"-"+g2', 'A-A-A'),
399 ('(?i)(a)b(c)', 'ABC', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABC-A-C'),
400 ('(?i)a+b+c', 'AABBABC', SUCCEED, 'found', 'ABC'),
401 ('(?i)a{1,}b{1,}c', 'AABBABC', SUCCEED, 'found', 'ABC'),
402 #('(?i)a**', '-', SYNTAX_ERROR),
403 ('(?i)a.+?c', 'ABCABC', SUCCEED, 'found', 'ABC'),
404 ('(?i)a.*?c', 'ABCABC', SUCCEED, 'found', 'ABC'),
405 ('(?i)a.{0,5}?c', 'ABCABC', SUCCEED, 'found', 'ABC'),
406 ('(?i)(a+|b)*', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'),
407 ('(?i)(a+|b){0,}', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'),
408 ('(?i)(a+|b)+', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'),
409 ('(?i)(a+|b){1,}', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'),
410 ('(?i)(a+|b)?', 'AB', SUCCEED, 'found+"-"+g1', 'A-A'),
411 ('(?i)(a+|b){0,1}', 'AB', SUCCEED, 'found+"-"+g1', 'A-A'),
412 ('(?i)(a+|b){0,1}?', 'AB', SUCCEED, 'found+"-"+g1', '-'),
413 ('(?i))(', '-', SYNTAX_ERROR),
414 ('(?i)[^ab]*', 'CDE', SUCCEED, 'found', 'CDE'),
415 ('(?i)abc', '', FAIL),
416 ('(?i)a*', '', SUCCEED, 'found', ''),
417 ('(?i)([abc])*d', 'ABBBCD', SUCCEED, 'found+"-"+g1', 'ABBBCD-C'),
418 ('(?i)([abc])*bcd', 'ABCD', SUCCEED, 'found+"-"+g1', 'ABCD-A'),
419 ('(?i)a|b|c|d|e', 'E', SUCCEED, 'found', 'E'),
420 ('(?i)(a|b|c|d|e)f', 'EF', SUCCEED, 'found+"-"+g1', 'EF-E'),
421 ('(?i)abcd*efg', 'ABCDEFG', SUCCEED, 'found', 'ABCDEFG'),
422 ('(?i)ab*', 'XABYABBBZ', SUCCEED, 'found', 'AB'),
423 ('(?i)ab*', 'XAYABBBZ', SUCCEED, 'found', 'A'),
424 ('(?i)(ab|cd)e', 'ABCDE', SUCCEED, 'found+"-"+g1', 'CDE-CD'),
425 ('(?i)[abhgefdc]ij', 'HIJ', SUCCEED, 'found', 'HIJ'),
426 ('(?i)^(ab|cd)e', 'ABCDE', FAIL),
427 ('(?i)(abc|)ef', 'ABCDEF', SUCCEED, 'found+"-"+g1', 'EF-'),
428 ('(?i)(a|b)c*d', 'ABCD', SUCCEED, 'found+"-"+g1', 'BCD-B'),
429 ('(?i)(ab|ab*)bc', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-A'),
430 ('(?i)a([bc]*)c*', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-BC'),
431 ('(?i)a([bc]*)(c*d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-BC-D'),
432 ('(?i)a([bc]+)(c*d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-BC-D'),
433 ('(?i)a([bc]*)(c+d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-B-CD'),
434 ('(?i)a[bcd]*dcdcde', 'ADCDCDE', SUCCEED, 'found', 'ADCDCDE'),
435 ('(?i)a[bcd]+dcdcde', 'ADCDCDE', FAIL),
436 ('(?i)(ab|a)b*c', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-AB'),
437 ('(?i)((a)(b)c)(d)', 'ABCD', SUCCEED, 'g1+"-"+g2+"-"+g3+"-"+g4', 'ABC-A-B-D'),
438 ('(?i)[a-zA-Z_][a-zA-Z0-9_]*', 'ALPHA', SUCCEED, 'found', 'ALPHA'),
439 ('(?i)^a(bc+|b[eh])g|.h$', 'ABH', SUCCEED, 'found+"-"+g1', 'BH-'),
440 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'EFFGZ', SUCCEED, 'found+"-"+g1+"-"+g2', 'EFFGZ-EFFGZ-'),
441 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'IJ', SUCCEED, 'found+"-"+g1+"-"+g2', 'IJ-IJ-J'),
442 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'EFFG', FAIL),
443 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'BCDD', FAIL),
444 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'REFFGZ', SUCCEED, 'found+"-"+g1+"-"+g2', 'EFFGZ-EFFGZ-'),
445 ('(?i)((((((((((a))))))))))', 'A', SUCCEED, 'g10', 'A'),
446 ('(?i)((((((((((a))))))))))\\10', 'AA', SUCCEED, 'found', 'AA'),
447 ('(?i)((((((((((a))))))))))\\41', 'AA', FAIL),
448 ('(?i)((((((((((a))))))))))\\41', 'A!', SUCCEED, 'found', 'A!'),
449 ('(?i)(((((((((a)))))))))', 'A', SUCCEED, 'found', 'A'),
450 ('(?i)(?:(?:(?:(?:(?:(?:(?:(?:(?:(a))))))))))', 'A', SUCCEED, 'g1', 'A'),
451 ('(?i)(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))', 'C', SUCCEED, 'g1', 'C'),
452 ('(?i)multiple words of text', 'UH-UH', FAIL),
453 ('(?i)multiple words', 'MULTIPLE WORDS, YEAH', SUCCEED, 'found', 'MULTIPLE WORDS'),
454 ('(?i)(.*)c(.*)', 'ABCDE', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCDE-AB-DE'),
455 ('(?i)\\((.*), (.*)\\)', '(A, B)', SUCCEED, '(g2, g1)', '(B, A)'),
456 ('(?i)[k]', 'AB', FAIL),
457 ##('(?i)abcd', 'ABCD', SUCCEED, 'found+"-"+\\found+"-"+\\\\found', 'ABCD-$&-\\ABCD'),
458 ##('(?i)a(bc)d', 'ABCD', SUCCEED, 'g1+"-"+\\g1+"-"+\\\\g1', 'BC-$1-\\BC'),
459 ('(?i)a[-]?c', 'AC', SUCCEED, 'found', 'AC'),
460 ('(?i)(abc)\\1', 'ABCABC', SUCCEED, 'g1', 'ABC'),
461 ('(?i)([a-c]*)\\1', 'ABCABC', SUCCEED, 'g1', 'ABC'),
462 ('a(?!b).', 'abad', SUCCEED, 'found', 'ad'),
463 ('a(?=d).', 'abad', SUCCEED, 'found', 'ad'),
464 ('a(?=c|d).', 'abad', SUCCEED, 'found', 'ad'),
465 ('a(?:b|c|d)(.)', 'ace', SUCCEED, 'g1', 'e'),
466 ('a(?:b|c|d)*(.)', 'ace', SUCCEED, 'g1', 'e'),
467 ('a(?:b|c|d)+?(.)', 'ace', SUCCEED, 'g1', 'e'),
468 ('a(?:b|(c|e){1,2}?|d)+?(.)', 'ace', SUCCEED, 'g1g2', 'ce'),
469 ('^(.+)?B', 'AB', SUCCEED, 'g1', 'A'),
470]