blob: 8f21280efd6c550ef9db66f259212eada049bec6 [file] [log] [blame]
Guido van Rossum876736c1997-06-03 18:07:49 +00001# Regex test suite and benchmark suite v1.5a2
Guido van Rossum876736c1997-06-03 18:07:49 +00002
3# The 3 possible outcomes for each pattern
4[SUCCEED, FAIL, SYNTAX_ERROR] = range(3)
5
6# Benchmark suite (needs expansion)
7#
8# The benchmark suite does not test correctness, just speed. The
Fred Drake004d5e62000-10-23 17:22:08 +00009# first element of each tuple is the regex pattern; the second is a
Guido van Rossum876736c1997-06-03 18:07:49 +000010# string to match it against. The benchmarking code will embed the
Fred Drake004d5e62000-10-23 17:22:08 +000011# second string inside several sizes of padding, to test how regex
Guido van Rossum876736c1997-06-03 18:07:49 +000012# matching performs on large strings.
13
14benchmarks = [
Fred Drake004d5e62000-10-23 17:22:08 +000015 ('Python', 'Python'), # Simple text literal
16 ('.*Python', 'Python'), # Bad text literal
Guido van Rossum876736c1997-06-03 18:07:49 +000017 ('.*Python.*', 'Python'), # Worse text literal
Fred Drake004d5e62000-10-23 17:22:08 +000018 ('.*\\(Python\\)', 'Python'), # Bad text literal with grouping
Guido van Rossum876736c1997-06-03 18:07:49 +000019
Fred Drake004d5e62000-10-23 17:22:08 +000020 ('(Python\\|Perl\\|Tcl', 'Perl'), # Alternation
21 ('\\(Python\\|Perl\\|Tcl\\)', 'Perl'), # Grouped alternation
22 ('\\(Python\\)\\1', 'PythonPython'), # Backreference
23# ('\\([0a-z][a-z]*,\\)+', 'a5,b7,c9,'), # Disable the fastmap optimization
24 ('\\([a-z][a-z0-9]*,\\)+', 'a5,b7,c9,') # A few sets
Guido van Rossum876736c1997-06-03 18:07:49 +000025]
26
27# Test suite (for verifying correctness)
28#
29# The test suite is a list of 5- or 3-tuples. The 5 parts of a
30# complete tuple are:
31# element 0: a string containing the pattern
32# 1: the string to match against the pattern
33# 2: the expected result (SUCCEED, FAIL, SYNTAX_ERROR)
34# 3: a string that will be eval()'ed to produce a test string.
35# This is an arbitrary Python expression; the available
36# variables are "found" (the whole match), and "g1", "g2", ...
37# up to "g10" contain the contents of each group, or the
38# string 'None' if the group wasn't given a value.
39# 4: The expected result of evaluating the expression.
40# If the two don't match, an error is reported.
41#
42# If the regex isn't expected to work, the latter two elements can be omitted.
43
44tests = [
45('abc', 'abc', SUCCEED,
46 'found', 'abc'),
47('abc', 'xbc', FAIL),
48('abc', 'axc', FAIL),
49('abc', 'abx', FAIL),
50('abc', 'xabcy', SUCCEED,
51 'found', 'abc'),
52('abc', 'ababc', SUCCEED,
53 'found', 'abc'),
54('ab*c', 'abc', SUCCEED,
55 'found', 'abc'),
56('ab*bc', 'abc', SUCCEED,
57 'found', 'abc'),
58('ab*bc', 'abbc', SUCCEED,
59 'found', 'abbc'),
60('ab*bc', 'abbbbc', SUCCEED,
61 'found', 'abbbbc'),
62('ab+bc', 'abbc', SUCCEED,
63 'found', 'abbc'),
64('ab+bc', 'abc', FAIL),
65('ab+bc', 'abq', FAIL),
66('ab+bc', 'abbbbc', SUCCEED,
67 'found', 'abbbbc'),
68('ab?bc', 'abbc', SUCCEED,
69 'found', 'abbc'),
70('ab?bc', 'abc', SUCCEED,
71 'found', 'abc'),
72('ab?bc', 'abbbbc', FAIL),
73('ab?c', 'abc', SUCCEED,
74 'found', 'abc'),
75('^abc$', 'abc', SUCCEED,
76 'found', 'abc'),
77('^abc$', 'abcc', FAIL),
78('^abc', 'abcc', SUCCEED,
79 'found', 'abc'),
80('^abc$', 'aabc', FAIL),
81('abc$', 'aabc', SUCCEED,
82 'found', 'abc'),
83('^', 'abc', SUCCEED,
84 'found+"-"', '-'),
85('$', 'abc', SUCCEED,
86 'found+"-"', '-'),
87('a.c', 'abc', SUCCEED,
88 'found', 'abc'),
89('a.c', 'axc', SUCCEED,
90 'found', 'axc'),
91('a.*c', 'axyzc', SUCCEED,
92 'found', 'axyzc'),
93('a.*c', 'axyzd', FAIL),
94('a[bc]d', 'abc', FAIL),
95('a[bc]d', 'abd', SUCCEED,
96 'found', 'abd'),
97('a[b-d]e', 'abd', FAIL),
98('a[b-d]e', 'ace', SUCCEED,
99 'found', 'ace'),
100('a[b-d]', 'aac', SUCCEED,
101 'found', 'ac'),
102('a[-b]', 'a-', SUCCEED,
103 'found', 'a-'),
104('a[b-]', 'a-', SUCCEED,
105 'found', 'a-'),
106('a[]b', '-', SYNTAX_ERROR),
107('a[', '-', SYNTAX_ERROR),
108('a\\', '-', SYNTAX_ERROR),
109('abc\\)', '-', SYNTAX_ERROR),
110('\\(abc', '-', SYNTAX_ERROR),
111('a]', 'a]', SUCCEED,
112 'found', 'a]'),
113('a[]]b', 'a]b', SUCCEED,
114 'found', 'a]b'),
115('a[^bc]d', 'aed', SUCCEED,
116 'found', 'aed'),
117('a[^bc]d', 'abd', FAIL),
118('a[^-b]c', 'adc', SUCCEED,
119 'found', 'adc'),
120('a[^-b]c', 'a-c', FAIL),
121('a[^]b]c', 'a]c', FAIL),
122('a[^]b]c', 'adc', SUCCEED,
123 'found', 'adc'),
124('\\ba\\b', 'a-', SUCCEED,
125 '"-"', '-'),
126('\\ba\\b', '-a', SUCCEED,
127 '"-"', '-'),
128('\\ba\\b', '-a-', SUCCEED,
129 '"-"', '-'),
130('\\by\\b', 'xy', FAIL),
131('\\by\\b', 'yz', FAIL),
132('\\by\\b', 'xyz', FAIL),
133('ab\\|cd', 'abc', SUCCEED,
134 'found', 'ab'),
135('ab\\|cd', 'abcd', SUCCEED,
136 'found', 'ab'),
137('\\(\\)ef', 'def', SUCCEED,
138 'found+"-"+g1', 'ef-'),
139('$b', 'b', FAIL),
140('a(b', 'a(b', SUCCEED,
141 'found+"-"+g1', 'a(b-None'),
142('a(*b', 'ab', SUCCEED,
143 'found', 'ab'),
144('a(*b', 'a((b', SUCCEED,
145 'found', 'a((b'),
146('a\\\\b', 'a\\b', SUCCEED,
147 'found', 'a\\b'),
148('\\(\\(a\\)\\)', 'abc', SUCCEED,
149 'found+"-"+g1+"-"+g2', 'a-a-a'),
150('\\(a\\)b\\(c\\)', 'abc', SUCCEED,
151 'found+"-"+g1+"-"+g2', 'abc-a-c'),
152('a+b+c', 'aabbabc', SUCCEED,
153 'found', 'abc'),
154('\\(a+\\|b\\)*', 'ab', SUCCEED,
155 'found+"-"+g1', 'ab-b'),
156('\\(a+\\|b\\)+', 'ab', SUCCEED,
157 'found+"-"+g1', 'ab-b'),
158('\\(a+\\|b\\)?', 'ab', SUCCEED,
159 'found+"-"+g1', 'a-a'),
160('\\)\\(', '-', SYNTAX_ERROR),
161('[^ab]*', 'cde', SUCCEED,
162 'found', 'cde'),
163('abc', '', FAIL),
164('a*', '', SUCCEED,
165 'found', ''),
166('a\\|b\\|c\\|d\\|e', 'e', SUCCEED,
167 'found', 'e'),
168('\\(a\\|b\\|c\\|d\\|e\\)f', 'ef', SUCCEED,
169 'found+"-"+g1', 'ef-e'),
170('abcd*efg', 'abcdefg', SUCCEED,
171 'found', 'abcdefg'),
172('ab*', 'xabyabbbz', SUCCEED,
173 'found', 'ab'),
174('ab*', 'xayabbbz', SUCCEED,
175 'found', 'a'),
176('\\(ab\\|cd\\)e', 'abcde', SUCCEED,
177 'found+"-"+g1', 'cde-cd'),
178('[abhgefdc]ij', 'hij', SUCCEED,
179 'found', 'hij'),
180('^\\(ab\\|cd\\)e', 'abcde', FAIL,
181 'xg1y', 'xy'),
182('\\(abc\\|\\)ef', 'abcdef', SUCCEED,
183 'found+"-"+g1', 'ef-'),
184('\\(a\\|b\\)c*d', 'abcd', SUCCEED,
185 'found+"-"+g1', 'bcd-b'),
186('\\(ab\\|ab*\\)bc', 'abc', SUCCEED,
187 'found+"-"+g1', 'abc-a'),
188('a\\([bc]*\\)c*', 'abc', SUCCEED,
189 'found+"-"+g1', 'abc-bc'),
190('a\\([bc]*\\)\\(c*d\\)', 'abcd', SUCCEED,
191 'found+"-"+g1+"-"+g2', 'abcd-bc-d'),
192('a\\([bc]+\\)\\(c*d\\)', 'abcd', SUCCEED,
193 'found+"-"+g1+"-"+g2', 'abcd-bc-d'),
194('a\\([bc]*\\)\\(c+d\\)', 'abcd', SUCCEED,
195 'found+"-"+g1+"-"+g2', 'abcd-b-cd'),
196('a[bcd]*dcdcde', 'adcdcde', SUCCEED,
197 'found', 'adcdcde'),
198('a[bcd]+dcdcde', 'adcdcde', FAIL),
199('\\(ab\\|a\\)b*c', 'abc', SUCCEED,
200 'found+"-"+g1', 'abc-ab'),
201('\\(\\(a\\)\\(b\\)c\\)\\(d\\)', 'abcd', SUCCEED,
202 'g1+"-"+g2+"-"+g3+"-"+g4', 'abc-a-b-d'),
203('[a-zA-Z_][a-zA-Z0-9_]*', 'alpha', SUCCEED,
204 'found', 'alpha'),
205('^a\\(bc+\\|b[eh]\\)g\\|.h$', 'abh', SUCCEED,
206 'found+"-"+g1', 'bh-None'),
207('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'effgz', SUCCEED,
208 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'),
209('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'ij', SUCCEED,
210 'found+"-"+g1+"-"+g2', 'ij-ij-j'),
211('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'effg', FAIL),
212('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'bcdd', FAIL),
213('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'reffgz', SUCCEED,
214 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'),
215('\\(\\(\\(\\(\\(\\(\\(\\(\\(a\\)\\)\\)\\)\\)\\)\\)\\)\\)', 'a', SUCCEED,
216 'found', 'a'),
217('multiple words of text', 'uh-uh', FAIL),
218('multiple words', 'multiple words, yeah', SUCCEED,
219 'found', 'multiple words'),
220('\\(.*\\)c\\(.*\\)', 'abcde', SUCCEED,
221 'found+"-"+g1+"-"+g2', 'abcde-ab-de'),
222('(\\(.*\\), \\(.*\\))', '(a, b)', SUCCEED,
223 'g2+"-"+g1', 'b-a'),
224('[k]', 'ab', FAIL),
225('a[-]?c', 'ac', SUCCEED,
226 'found', 'ac'),
227('\\(abc\\)\\1', 'abcabc', SUCCEED,
228 'g1', 'abc'),
229('\\([a-c]*\\)\\1', 'abcabc', SUCCEED,
230 'g1', 'abc'),
231('^\\(.+\\)?B', 'AB', SUCCEED,
232 'g1', 'A'),
233('\\(a+\\).\\1$', 'aaaaa', SUCCEED,
234 'found+"-"+g1', 'aaaaa-aa'),
235('^\\(a+\\).\\1$', 'aaaa', FAIL),
236('\\(abc\\)\\1', 'abcabc', SUCCEED,
237 'found+"-"+g1', 'abcabc-abc'),
238('\\([a-c]+\\)\\1', 'abcabc', SUCCEED,
239 'found+"-"+g1', 'abcabc-abc'),
240('\\(a\\)\\1', 'aa', SUCCEED,
241 'found+"-"+g1', 'aa-a'),
242('\\(a+\\)\\1', 'aa', SUCCEED,
243 'found+"-"+g1', 'aa-a'),
244('\\(a+\\)+\\1', 'aa', SUCCEED,
245 'found+"-"+g1', 'aa-a'),
246('\\(a\\).+\\1', 'aba', SUCCEED,
247 'found+"-"+g1', 'aba-a'),
248('\\(a\\)ba*\\1', 'aba', SUCCEED,
249 'found+"-"+g1', 'aba-a'),
250('\\(aa\\|a\\)a\\1$', 'aaa', SUCCEED,
251 'found+"-"+g1', 'aaa-a'),
252('\\(a\\|aa\\)a\\1$', 'aaa', SUCCEED,
253 'found+"-"+g1', 'aaa-a'),
254('\\(a+\\)a\\1$', 'aaa', SUCCEED,
255 'found+"-"+g1', 'aaa-a'),
256('\\([abc]*\\)\\1', 'abcabc', SUCCEED,
257 'found+"-"+g1', 'abcabc-abc'),
258('\\(a\\)\\(b\\)c\\|ab', 'ab', SUCCEED,
259 'found+"-"+g1+"-"+g2', 'ab-None-None'),
260('\\(a\\)+x', 'aaax', SUCCEED,
261 'found+"-"+g1', 'aaax-a'),
262('\\([ac]\\)+x', 'aacx', SUCCEED,
263 'found+"-"+g1', 'aacx-c'),
264('\\([^/]*/\\)*sub1/', 'd:msgs/tdir/sub1/trial/away.cpp', SUCCEED,
265 'found+"-"+g1', 'd:msgs/tdir/sub1/-tdir/'),
266('\\([^.]*\\)\\.\\([^:]*\\):[T ]+\\(.*\\)', 'track1.title:TBlah blah blah', SUCCEED,
267 'found+"-"+g1+"-"+g2+"-"+g3', 'track1.title:TBlah blah blah-track1-title-Blah blah blah'),
268('\\([^N]*N\\)+', 'abNNxyzN', SUCCEED,
269 'found+"-"+g1', 'abNNxyzN-xyzN'),
270('\\([^N]*N\\)+', 'abNNxyz', SUCCEED,
271 'found+"-"+g1', 'abNN-N'),
272('\\([abc]*\\)x', 'abcx', SUCCEED,
273 'found+"-"+g1', 'abcx-abc'),
274('\\([abc]*\\)x', 'abc', FAIL),
275('\\([xyz]*\\)x', 'abcx', SUCCEED,
276 'found+"-"+g1', 'x-'),
277('\\(a\\)+b\\|aac', 'aac', SUCCEED,
Guido van Rossum95e80531997-08-13 22:34:14 +0000278 'found+"-"+g1', 'aac-None'),
279('\<a', 'a', SUCCEED, 'found', 'a'),
280('\<a', '!', FAIL),
281('a\<b', 'ab', FAIL),
282('a\>', 'ab', FAIL),
283('a\>', 'a!', SUCCEED, 'found', 'a'),
284('a\>', 'a', SUCCEED, 'found', 'a'),
Guido van Rossum876736c1997-06-03 18:07:49 +0000285]