|
5718
|
1
|
|
|
2 # Regex test suite and benchmark suite v1.5a2
|
|
|
3 # Due to the use of r"aw" strings, this file will
|
|
|
4 # only work with Python 1.5 or higher.
|
|
|
5
|
|
|
6 # The 3 possible outcomes for each pattern
|
|
|
7 [SUCCEED, FAIL, SYNTAX_ERROR] = range(3)
|
|
|
8
|
|
|
9 # Benchmark suite (needs expansion)
|
|
|
10 #
|
|
|
11 # The benchmark suite does not test correctness, just speed. The
|
|
|
12 # first element of each tuple is the regex pattern; the second is a
|
|
|
13 # string to match it against. The benchmarking code will embed the
|
|
|
14 # second string inside several sizes of padding, to test how regex
|
|
|
15 # matching performs on large strings.
|
|
|
16
|
|
|
17 benchmarks = [
|
|
|
18 ('Python', 'Python'), # Simple text literal
|
|
|
19 ('.*Python', 'Python'), # Bad text literal
|
|
|
20 ('.*Python.*', 'Python'), # Worse text literal
|
|
|
21 ('.*\\(Python\\)', 'Python'), # Bad text literal with grouping
|
|
|
22
|
|
|
23 ('(Python\\|Perl\\|Tcl', 'Perl'), # Alternation
|
|
|
24 ('\\(Python\\|Perl\\|Tcl\\)', 'Perl'), # Grouped alternation
|
|
|
25 ('\\(Python\\)\\1', 'PythonPython'), # Backreference
|
|
|
26 # ('\\([0a-z][a-z]*,\\)+', 'a5,b7,c9,'), # Disable the fastmap optimization
|
|
|
27 ('\\([a-z][a-z0-9]*,\\)+', 'a5,b7,c9,') # A few sets
|
|
|
28 ]
|
|
|
29
|
|
|
30 # Test suite (for verifying correctness)
|
|
|
31 #
|
|
|
32 # The test suite is a list of 5- or 3-tuples. The 5 parts of a
|
|
|
33 # complete tuple are:
|
|
|
34 # element 0: a string containing the pattern
|
|
|
35 # 1: the string to match against the pattern
|
|
|
36 # 2: the expected result (SUCCEED, FAIL, SYNTAX_ERROR)
|
|
|
37 # 3: a string that will be eval()'ed to produce a test string.
|
|
|
38 # This is an arbitrary Python expression; the available
|
|
|
39 # variables are "found" (the whole match), and "g1", "g2", ...
|
|
|
40 # up to "g10" contain the contents of each group, or the
|
|
|
41 # string 'None' if the group wasn't given a value.
|
|
|
42 # 4: The expected result of evaluating the expression.
|
|
|
43 # If the two don't match, an error is reported.
|
|
|
44 #
|
|
|
45 # If the regex isn't expected to work, the latter two elements can be omitted.
|
|
|
46
|
|
|
47 tests = [
|
|
|
48 ('abc', 'abc', SUCCEED,
|
|
|
49 'found', 'abc'),
|
|
|
50 ('abc', 'xbc', FAIL),
|
|
|
51 ('abc', 'axc', FAIL),
|
|
|
52 ('abc', 'abx', FAIL),
|
|
|
53 ('abc', 'xabcy', SUCCEED,
|
|
|
54 'found', 'abc'),
|
|
|
55 ('abc', 'ababc', SUCCEED,
|
|
|
56 'found', 'abc'),
|
|
|
57 ('ab*c', 'abc', SUCCEED,
|
|
|
58 'found', 'abc'),
|
|
|
59 ('ab*bc', 'abc', SUCCEED,
|
|
|
60 'found', 'abc'),
|
|
|
61 ('ab*bc', 'abbc', SUCCEED,
|
|
|
62 'found', 'abbc'),
|
|
|
63 ('ab*bc', 'abbbbc', SUCCEED,
|
|
|
64 'found', 'abbbbc'),
|
|
|
65 ('ab+bc', 'abbc', SUCCEED,
|
|
|
66 'found', 'abbc'),
|
|
|
67 ('ab+bc', 'abc', FAIL),
|
|
|
68 ('ab+bc', 'abq', FAIL),
|
|
|
69 ('ab+bc', 'abbbbc', SUCCEED,
|
|
|
70 'found', 'abbbbc'),
|
|
|
71 ('ab?bc', 'abbc', SUCCEED,
|
|
|
72 'found', 'abbc'),
|
|
|
73 ('ab?bc', 'abc', SUCCEED,
|
|
|
74 'found', 'abc'),
|
|
|
75 ('ab?bc', 'abbbbc', FAIL),
|
|
|
76 ('ab?c', 'abc', SUCCEED,
|
|
|
77 'found', 'abc'),
|
|
|
78 ('^abc$', 'abc', SUCCEED,
|
|
|
79 'found', 'abc'),
|
|
|
80 ('^abc$', 'abcc', FAIL),
|
|
|
81 ('^abc', 'abcc', SUCCEED,
|
|
|
82 'found', 'abc'),
|
|
|
83 ('^abc$', 'aabc', FAIL),
|
|
|
84 ('abc$', 'aabc', SUCCEED,
|
|
|
85 'found', 'abc'),
|
|
|
86 ('^', 'abc', SUCCEED,
|
|
|
87 'found+"-"', '-'),
|
|
|
88 ('$', 'abc', SUCCEED,
|
|
|
89 'found+"-"', '-'),
|
|
|
90 ('a.c', 'abc', SUCCEED,
|
|
|
91 'found', 'abc'),
|
|
|
92 ('a.c', 'axc', SUCCEED,
|
|
|
93 'found', 'axc'),
|
|
|
94 ('a.*c', 'axyzc', SUCCEED,
|
|
|
95 'found', 'axyzc'),
|
|
|
96 ('a.*c', 'axyzd', FAIL),
|
|
|
97 ('a[bc]d', 'abc', FAIL),
|
|
|
98 ('a[bc]d', 'abd', SUCCEED,
|
|
|
99 'found', 'abd'),
|
|
|
100 ('a[b-d]e', 'abd', FAIL),
|
|
|
101 ('a[b-d]e', 'ace', SUCCEED,
|
|
|
102 'found', 'ace'),
|
|
|
103 ('a[b-d]', 'aac', SUCCEED,
|
|
|
104 'found', 'ac'),
|
|
|
105 ('a[-b]', 'a-', SUCCEED,
|
|
|
106 'found', 'a-'),
|
|
|
107 ('a[b-]', 'a-', SUCCEED,
|
|
|
108 'found', 'a-'),
|
|
|
109 ('a[]b', '-', SYNTAX_ERROR),
|
|
|
110 ('a[', '-', SYNTAX_ERROR),
|
|
|
111 ('a\\', '-', SYNTAX_ERROR),
|
|
|
112 ('abc\\)', '-', SYNTAX_ERROR),
|
|
|
113 ('\\(abc', '-', SYNTAX_ERROR),
|
|
|
114 ('a]', 'a]', SUCCEED,
|
|
|
115 'found', 'a]'),
|
|
|
116 ('a[]]b', 'a]b', SUCCEED,
|
|
|
117 'found', 'a]b'),
|
|
|
118 ('a[^bc]d', 'aed', SUCCEED,
|
|
|
119 'found', 'aed'),
|
|
|
120 ('a[^bc]d', 'abd', FAIL),
|
|
|
121 ('a[^-b]c', 'adc', SUCCEED,
|
|
|
122 'found', 'adc'),
|
|
|
123 ('a[^-b]c', 'a-c', FAIL),
|
|
|
124 ('a[^]b]c', 'a]c', FAIL),
|
|
|
125 ('a[^]b]c', 'adc', SUCCEED,
|
|
|
126 'found', 'adc'),
|
|
|
127 ('\\ba\\b', 'a-', SUCCEED,
|
|
|
128 '"-"', '-'),
|
|
|
129 ('\\ba\\b', '-a', SUCCEED,
|
|
|
130 '"-"', '-'),
|
|
|
131 ('\\ba\\b', '-a-', SUCCEED,
|
|
|
132 '"-"', '-'),
|
|
|
133 ('\\by\\b', 'xy', FAIL),
|
|
|
134 ('\\by\\b', 'yz', FAIL),
|
|
|
135 ('\\by\\b', 'xyz', FAIL),
|
|
|
136 ('ab\\|cd', 'abc', SUCCEED,
|
|
|
137 'found', 'ab'),
|
|
|
138 ('ab\\|cd', 'abcd', SUCCEED,
|
|
|
139 'found', 'ab'),
|
|
|
140 ('\\(\\)ef', 'def', SUCCEED,
|
|
|
141 'found+"-"+g1', 'ef-'),
|
|
|
142 ('$b', 'b', FAIL),
|
|
|
143 ('a(b', 'a(b', SUCCEED,
|
|
|
144 'found+"-"+g1', 'a(b-None'),
|
|
|
145 ('a(*b', 'ab', SUCCEED,
|
|
|
146 'found', 'ab'),
|
|
|
147 ('a(*b', 'a((b', SUCCEED,
|
|
|
148 'found', 'a((b'),
|
|
|
149 ('a\\\\b', 'a\\b', SUCCEED,
|
|
|
150 'found', 'a\\b'),
|
|
|
151 ('\\(\\(a\\)\\)', 'abc', SUCCEED,
|
|
|
152 'found+"-"+g1+"-"+g2', 'a-a-a'),
|
|
|
153 ('\\(a\\)b\\(c\\)', 'abc', SUCCEED,
|
|
|
154 'found+"-"+g1+"-"+g2', 'abc-a-c'),
|
|
|
155 ('a+b+c', 'aabbabc', SUCCEED,
|
|
|
156 'found', 'abc'),
|
|
|
157 ('\\(a+\\|b\\)*', 'ab', SUCCEED,
|
|
|
158 'found+"-"+g1', 'ab-b'),
|
|
|
159 ('\\(a+\\|b\\)+', 'ab', SUCCEED,
|
|
|
160 'found+"-"+g1', 'ab-b'),
|
|
|
161 ('\\(a+\\|b\\)?', 'ab', SUCCEED,
|
|
|
162 'found+"-"+g1', 'a-a'),
|
|
|
163 ('\\)\\(', '-', SYNTAX_ERROR),
|
|
|
164 ('[^ab]*', 'cde', SUCCEED,
|
|
|
165 'found', 'cde'),
|
|
|
166 ('abc', '', FAIL),
|
|
|
167 ('a*', '', SUCCEED,
|
|
|
168 'found', ''),
|
|
|
169 ('a\\|b\\|c\\|d\\|e', 'e', SUCCEED,
|
|
|
170 'found', 'e'),
|
|
|
171 ('\\(a\\|b\\|c\\|d\\|e\\)f', 'ef', SUCCEED,
|
|
|
172 'found+"-"+g1', 'ef-e'),
|
|
|
173 ('abcd*efg', 'abcdefg', SUCCEED,
|
|
|
174 'found', 'abcdefg'),
|
|
|
175 ('ab*', 'xabyabbbz', SUCCEED,
|
|
|
176 'found', 'ab'),
|
|
|
177 ('ab*', 'xayabbbz', SUCCEED,
|
|
|
178 'found', 'a'),
|
|
|
179 ('\\(ab\\|cd\\)e', 'abcde', SUCCEED,
|
|
|
180 'found+"-"+g1', 'cde-cd'),
|
|
|
181 ('[abhgefdc]ij', 'hij', SUCCEED,
|
|
|
182 'found', 'hij'),
|
|
|
183 ('^\\(ab\\|cd\\)e', 'abcde', FAIL,
|
|
|
184 'xg1y', 'xy'),
|
|
|
185 ('\\(abc\\|\\)ef', 'abcdef', SUCCEED,
|
|
|
186 'found+"-"+g1', 'ef-'),
|
|
|
187 ('\\(a\\|b\\)c*d', 'abcd', SUCCEED,
|
|
|
188 'found+"-"+g1', 'bcd-b'),
|
|
|
189 ('\\(ab\\|ab*\\)bc', 'abc', SUCCEED,
|
|
|
190 'found+"-"+g1', 'abc-a'),
|
|
|
191 ('a\\([bc]*\\)c*', 'abc', SUCCEED,
|
|
|
192 'found+"-"+g1', 'abc-bc'),
|
|
|
193 ('a\\([bc]*\\)\\(c*d\\)', 'abcd', SUCCEED,
|
|
|
194 'found+"-"+g1+"-"+g2', 'abcd-bc-d'),
|
|
|
195 ('a\\([bc]+\\)\\(c*d\\)', 'abcd', SUCCEED,
|
|
|
196 'found+"-"+g1+"-"+g2', 'abcd-bc-d'),
|
|
|
197 ('a\\([bc]*\\)\\(c+d\\)', 'abcd', SUCCEED,
|
|
|
198 'found+"-"+g1+"-"+g2', 'abcd-b-cd'),
|
|
|
199 ('a[bcd]*dcdcde', 'adcdcde', SUCCEED,
|
|
|
200 'found', 'adcdcde'),
|
|
|
201 ('a[bcd]+dcdcde', 'adcdcde', FAIL),
|
|
|
202 ('\\(ab\\|a\\)b*c', 'abc', SUCCEED,
|
|
|
203 'found+"-"+g1', 'abc-ab'),
|
|
|
204 ('\\(\\(a\\)\\(b\\)c\\)\\(d\\)', 'abcd', SUCCEED,
|
|
|
205 'g1+"-"+g2+"-"+g3+"-"+g4', 'abc-a-b-d'),
|
|
|
206 ('[a-zA-Z_][a-zA-Z0-9_]*', 'alpha', SUCCEED,
|
|
|
207 'found', 'alpha'),
|
|
|
208 ('^a\\(bc+\\|b[eh]\\)g\\|.h$', 'abh', SUCCEED,
|
|
|
209 'found+"-"+g1', 'bh-None'),
|
|
|
210 ('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'effgz', SUCCEED,
|
|
|
211 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'),
|
|
|
212 ('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'ij', SUCCEED,
|
|
|
213 'found+"-"+g1+"-"+g2', 'ij-ij-j'),
|
|
|
214 ('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'effg', FAIL),
|
|
|
215 ('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'bcdd', FAIL),
|
|
|
216 ('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'reffgz', SUCCEED,
|
|
|
217 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'),
|
|
|
218 ('\\(\\(\\(\\(\\(\\(\\(\\(\\(a\\)\\)\\)\\)\\)\\)\\)\\)\\)', 'a', SUCCEED,
|
|
|
219 'found', 'a'),
|
|
|
220 ('multiple words of text', 'uh-uh', FAIL),
|
|
|
221 ('multiple words', 'multiple words, yeah', SUCCEED,
|
|
|
222 'found', 'multiple words'),
|
|
|
223 ('\\(.*\\)c\\(.*\\)', 'abcde', SUCCEED,
|
|
|
224 'found+"-"+g1+"-"+g2', 'abcde-ab-de'),
|
|
|
225 ('(\\(.*\\), \\(.*\\))', '(a, b)', SUCCEED,
|
|
|
226 'g2+"-"+g1', 'b-a'),
|
|
|
227 ('[k]', 'ab', FAIL),
|
|
|
228 ('a[-]?c', 'ac', SUCCEED,
|
|
|
229 'found', 'ac'),
|
|
|
230 ('\\(abc\\)\\1', 'abcabc', SUCCEED,
|
|
|
231 'g1', 'abc'),
|
|
|
232 ('\\([a-c]*\\)\\1', 'abcabc', SUCCEED,
|
|
|
233 'g1', 'abc'),
|
|
|
234 ('^\\(.+\\)?B', 'AB', SUCCEED,
|
|
|
235 'g1', 'A'),
|
|
|
236 ('\\(a+\\).\\1$', 'aaaaa', SUCCEED,
|
|
|
237 'found+"-"+g1', 'aaaaa-aa'),
|
|
|
238 ('^\\(a+\\).\\1$', 'aaaa', FAIL),
|
|
|
239 ('\\(abc\\)\\1', 'abcabc', SUCCEED,
|
|
|
240 'found+"-"+g1', 'abcabc-abc'),
|
|
|
241 ('\\([a-c]+\\)\\1', 'abcabc', SUCCEED,
|
|
|
242 'found+"-"+g1', 'abcabc-abc'),
|
|
|
243 ('\\(a\\)\\1', 'aa', SUCCEED,
|
|
|
244 'found+"-"+g1', 'aa-a'),
|
|
|
245 ('\\(a+\\)\\1', 'aa', SUCCEED,
|
|
|
246 'found+"-"+g1', 'aa-a'),
|
|
|
247 ('\\(a+\\)+\\1', 'aa', SUCCEED,
|
|
|
248 'found+"-"+g1', 'aa-a'),
|
|
|
249 ('\\(a\\).+\\1', 'aba', SUCCEED,
|
|
|
250 'found+"-"+g1', 'aba-a'),
|
|
|
251 ('\\(a\\)ba*\\1', 'aba', SUCCEED,
|
|
|
252 'found+"-"+g1', 'aba-a'),
|
|
|
253 ('\\(aa\\|a\\)a\\1$', 'aaa', SUCCEED,
|
|
|
254 'found+"-"+g1', 'aaa-a'),
|
|
|
255 ('\\(a\\|aa\\)a\\1$', 'aaa', SUCCEED,
|
|
|
256 'found+"-"+g1', 'aaa-a'),
|
|
|
257 ('\\(a+\\)a\\1$', 'aaa', SUCCEED,
|
|
|
258 'found+"-"+g1', 'aaa-a'),
|
|
|
259 ('\\([abc]*\\)\\1', 'abcabc', SUCCEED,
|
|
|
260 'found+"-"+g1', 'abcabc-abc'),
|
|
|
261 ('\\(a\\)\\(b\\)c\\|ab', 'ab', SUCCEED,
|
|
|
262 'found+"-"+g1+"-"+g2', 'ab-None-None'),
|
|
|
263 ('\\(a\\)+x', 'aaax', SUCCEED,
|
|
|
264 'found+"-"+g1', 'aaax-a'),
|
|
|
265 ('\\([ac]\\)+x', 'aacx', SUCCEED,
|
|
|
266 'found+"-"+g1', 'aacx-c'),
|
|
|
267 ('\\([^/]*/\\)*sub1/', 'd:msgs/tdir/sub1/trial/away.cpp', SUCCEED,
|
|
|
268 'found+"-"+g1', 'd:msgs/tdir/sub1/-tdir/'),
|
|
|
269 ('\\([^.]*\\)\\.\\([^:]*\\):[T ]+\\(.*\\)', 'track1.title:TBlah blah blah', SUCCEED,
|
|
|
270 'found+"-"+g1+"-"+g2+"-"+g3', 'track1.title:TBlah blah blah-track1-title-Blah blah blah'),
|
|
|
271 ('\\([^N]*N\\)+', 'abNNxyzN', SUCCEED,
|
|
|
272 'found+"-"+g1', 'abNNxyzN-xyzN'),
|
|
|
273 ('\\([^N]*N\\)+', 'abNNxyz', SUCCEED,
|
|
|
274 'found+"-"+g1', 'abNN-N'),
|
|
|
275 ('\\([abc]*\\)x', 'abcx', SUCCEED,
|
|
|
276 'found+"-"+g1', 'abcx-abc'),
|
|
|
277 ('\\([abc]*\\)x', 'abc', FAIL),
|
|
|
278 ('\\([xyz]*\\)x', 'abcx', SUCCEED,
|
|
|
279 'found+"-"+g1', 'x-'),
|
|
|
280 ('\\(a\\)+b\\|aac', 'aac', SUCCEED,
|
|
|
281 'found+"-"+g1', 'aac-None')
|
|
|
282 ]
|
|
|
283
|