| 1 | n/a | # Regex test suite and benchmark suite v1.5a2 |
|---|
| 2 | n/a | |
|---|
| 3 | n/a | # The 3 possible outcomes for each pattern |
|---|
| 4 | n/a | [SUCCEED, FAIL, SYNTAX_ERROR] = range(3) |
|---|
| 5 | n/a | |
|---|
| 6 | n/a | # Benchmark suite (needs expansion) |
|---|
| 7 | n/a | # |
|---|
| 8 | n/a | # The benchmark suite does not test correctness, just speed. The |
|---|
| 9 | n/a | # first element of each tuple is the regex pattern; the second is a |
|---|
| 10 | n/a | # string to match it against. The benchmarking code will embed the |
|---|
| 11 | n/a | # second string inside several sizes of padding, to test how regex |
|---|
| 12 | n/a | # matching performs on large strings. |
|---|
| 13 | n/a | |
|---|
| 14 | n/a | benchmarks = [ |
|---|
| 15 | n/a | ('Python', 'Python'), # Simple text literal |
|---|
| 16 | n/a | ('.*Python', 'Python'), # Bad text literal |
|---|
| 17 | n/a | ('.*Python.*', 'Python'), # Worse text literal |
|---|
| 18 | n/a | ('.*\\(Python\\)', 'Python'), # Bad text literal with grouping |
|---|
| 19 | n/a | |
|---|
| 20 | n/a | ('(Python\\|Perl\\|Tcl', 'Perl'), # Alternation |
|---|
| 21 | n/a | ('\\(Python\\|Perl\\|Tcl\\)', 'Perl'), # Grouped alternation |
|---|
| 22 | n/a | ('\\(Python\\)\\1', 'PythonPython'), # Backreference |
|---|
| 23 | n/a | # ('\\([0a-z][a-z]*,\\)+', 'a5,b7,c9,'), # Disable the fastmap optimization |
|---|
| 24 | n/a | ('\\([a-z][a-z0-9]*,\\)+', 'a5,b7,c9,') # A few sets |
|---|
| 25 | n/a | ] |
|---|
| 26 | n/a | |
|---|
| 27 | n/a | # Test suite (for verifying correctness) |
|---|
| 28 | n/a | # |
|---|
| 29 | n/a | # The test suite is a list of 5- or 3-tuples. The 5 parts of a |
|---|
| 30 | n/a | # complete tuple are: |
|---|
| 31 | n/a | # element 0: a string containing the pattern |
|---|
| 32 | n/a | # 1: the string to match against the pattern |
|---|
| 33 | n/a | # 2: the expected result (SUCCEED, FAIL, SYNTAX_ERROR) |
|---|
| 34 | n/a | # 3: a string that will be eval()'ed to produce a test string. |
|---|
| 35 | n/a | # This is an arbitrary Python expression; the available |
|---|
| 36 | n/a | # variables are "found" (the whole match), and "g1", "g2", ... |
|---|
| 37 | n/a | # up to "g10" contain the contents of each group, or the |
|---|
| 38 | n/a | # string 'None' if the group wasn't given a value. |
|---|
| 39 | n/a | # 4: The expected result of evaluating the expression. |
|---|
| 40 | n/a | # If the two don't match, an error is reported. |
|---|
| 41 | n/a | # |
|---|
| 42 | n/a | # If the regex isn't expected to work, the latter two elements can be omitted. |
|---|
| 43 | n/a | |
|---|
| 44 | n/a | tests = [ |
|---|
| 45 | n/a | ('abc', 'abc', SUCCEED, |
|---|
| 46 | n/a | 'found', 'abc'), |
|---|
| 47 | n/a | ('abc', 'xbc', FAIL), |
|---|
| 48 | n/a | ('abc', 'axc', FAIL), |
|---|
| 49 | n/a | ('abc', 'abx', FAIL), |
|---|
| 50 | n/a | ('abc', 'xabcy', SUCCEED, |
|---|
| 51 | n/a | 'found', 'abc'), |
|---|
| 52 | n/a | ('abc', 'ababc', SUCCEED, |
|---|
| 53 | n/a | 'found', 'abc'), |
|---|
| 54 | n/a | ('ab*c', 'abc', SUCCEED, |
|---|
| 55 | n/a | 'found', 'abc'), |
|---|
| 56 | n/a | ('ab*bc', 'abc', SUCCEED, |
|---|
| 57 | n/a | 'found', 'abc'), |
|---|
| 58 | n/a | ('ab*bc', 'abbc', SUCCEED, |
|---|
| 59 | n/a | 'found', 'abbc'), |
|---|
| 60 | n/a | ('ab*bc', 'abbbbc', SUCCEED, |
|---|
| 61 | n/a | 'found', 'abbbbc'), |
|---|
| 62 | n/a | ('ab+bc', 'abbc', SUCCEED, |
|---|
| 63 | n/a | 'found', 'abbc'), |
|---|
| 64 | n/a | ('ab+bc', 'abc', FAIL), |
|---|
| 65 | n/a | ('ab+bc', 'abq', FAIL), |
|---|
| 66 | n/a | ('ab+bc', 'abbbbc', SUCCEED, |
|---|
| 67 | n/a | 'found', 'abbbbc'), |
|---|
| 68 | n/a | ('ab?bc', 'abbc', SUCCEED, |
|---|
| 69 | n/a | 'found', 'abbc'), |
|---|
| 70 | n/a | ('ab?bc', 'abc', SUCCEED, |
|---|
| 71 | n/a | 'found', 'abc'), |
|---|
| 72 | n/a | ('ab?bc', 'abbbbc', FAIL), |
|---|
| 73 | n/a | ('ab?c', 'abc', SUCCEED, |
|---|
| 74 | n/a | 'found', 'abc'), |
|---|
| 75 | n/a | ('^abc$', 'abc', SUCCEED, |
|---|
| 76 | n/a | 'found', 'abc'), |
|---|
| 77 | n/a | ('^abc$', 'abcc', FAIL), |
|---|
| 78 | n/a | ('^abc', 'abcc', SUCCEED, |
|---|
| 79 | n/a | 'found', 'abc'), |
|---|
| 80 | n/a | ('^abc$', 'aabc', FAIL), |
|---|
| 81 | n/a | ('abc$', 'aabc', SUCCEED, |
|---|
| 82 | n/a | 'found', 'abc'), |
|---|
| 83 | n/a | ('^', 'abc', SUCCEED, |
|---|
| 84 | n/a | 'found+"-"', '-'), |
|---|
| 85 | n/a | ('$', 'abc', SUCCEED, |
|---|
| 86 | n/a | 'found+"-"', '-'), |
|---|
| 87 | n/a | ('a.c', 'abc', SUCCEED, |
|---|
| 88 | n/a | 'found', 'abc'), |
|---|
| 89 | n/a | ('a.c', 'axc', SUCCEED, |
|---|
| 90 | n/a | 'found', 'axc'), |
|---|
| 91 | n/a | ('a.*c', 'axyzc', SUCCEED, |
|---|
| 92 | n/a | 'found', 'axyzc'), |
|---|
| 93 | n/a | ('a.*c', 'axyzd', FAIL), |
|---|
| 94 | n/a | ('a[bc]d', 'abc', FAIL), |
|---|
| 95 | n/a | ('a[bc]d', 'abd', SUCCEED, |
|---|
| 96 | n/a | 'found', 'abd'), |
|---|
| 97 | n/a | ('a[b-d]e', 'abd', FAIL), |
|---|
| 98 | n/a | ('a[b-d]e', 'ace', SUCCEED, |
|---|
| 99 | n/a | 'found', 'ace'), |
|---|
| 100 | n/a | ('a[b-d]', 'aac', SUCCEED, |
|---|
| 101 | n/a | 'found', 'ac'), |
|---|
| 102 | n/a | ('a[-b]', 'a-', SUCCEED, |
|---|
| 103 | n/a | 'found', 'a-'), |
|---|
| 104 | n/a | ('a[b-]', 'a-', SUCCEED, |
|---|
| 105 | n/a | 'found', 'a-'), |
|---|
| 106 | n/a | ('a[]b', '-', SYNTAX_ERROR), |
|---|
| 107 | n/a | ('a[', '-', SYNTAX_ERROR), |
|---|
| 108 | n/a | ('a\\', '-', SYNTAX_ERROR), |
|---|
| 109 | n/a | ('abc\\)', '-', SYNTAX_ERROR), |
|---|
| 110 | n/a | ('\\(abc', '-', SYNTAX_ERROR), |
|---|
| 111 | n/a | ('a]', 'a]', SUCCEED, |
|---|
| 112 | n/a | 'found', 'a]'), |
|---|
| 113 | n/a | ('a[]]b', 'a]b', SUCCEED, |
|---|
| 114 | n/a | 'found', 'a]b'), |
|---|
| 115 | n/a | ('a[^bc]d', 'aed', SUCCEED, |
|---|
| 116 | n/a | 'found', 'aed'), |
|---|
| 117 | n/a | ('a[^bc]d', 'abd', FAIL), |
|---|
| 118 | n/a | ('a[^-b]c', 'adc', SUCCEED, |
|---|
| 119 | n/a | 'found', 'adc'), |
|---|
| 120 | n/a | ('a[^-b]c', 'a-c', FAIL), |
|---|
| 121 | n/a | ('a[^]b]c', 'a]c', FAIL), |
|---|
| 122 | n/a | ('a[^]b]c', 'adc', SUCCEED, |
|---|
| 123 | n/a | 'found', 'adc'), |
|---|
| 124 | n/a | ('\\ba\\b', 'a-', SUCCEED, |
|---|
| 125 | n/a | '"-"', '-'), |
|---|
| 126 | n/a | ('\\ba\\b', '-a', SUCCEED, |
|---|
| 127 | n/a | '"-"', '-'), |
|---|
| 128 | n/a | ('\\ba\\b', '-a-', SUCCEED, |
|---|
| 129 | n/a | '"-"', '-'), |
|---|
| 130 | n/a | ('\\by\\b', 'xy', FAIL), |
|---|
| 131 | n/a | ('\\by\\b', 'yz', FAIL), |
|---|
| 132 | n/a | ('\\by\\b', 'xyz', FAIL), |
|---|
| 133 | n/a | ('ab\\|cd', 'abc', SUCCEED, |
|---|
| 134 | n/a | 'found', 'ab'), |
|---|
| 135 | n/a | ('ab\\|cd', 'abcd', SUCCEED, |
|---|
| 136 | n/a | 'found', 'ab'), |
|---|
| 137 | n/a | ('\\(\\)ef', 'def', SUCCEED, |
|---|
| 138 | n/a | 'found+"-"+g1', 'ef-'), |
|---|
| 139 | n/a | ('$b', 'b', FAIL), |
|---|
| 140 | n/a | ('a(b', 'a(b', SUCCEED, |
|---|
| 141 | n/a | 'found+"-"+g1', 'a(b-None'), |
|---|
| 142 | n/a | ('a(*b', 'ab', SUCCEED, |
|---|
| 143 | n/a | 'found', 'ab'), |
|---|
| 144 | n/a | ('a(*b', 'a((b', SUCCEED, |
|---|
| 145 | n/a | 'found', 'a((b'), |
|---|
| 146 | n/a | ('a\\\\b', 'a\\b', SUCCEED, |
|---|
| 147 | n/a | 'found', 'a\\b'), |
|---|
| 148 | n/a | ('\\(\\(a\\)\\)', 'abc', SUCCEED, |
|---|
| 149 | n/a | 'found+"-"+g1+"-"+g2', 'a-a-a'), |
|---|
| 150 | n/a | ('\\(a\\)b\\(c\\)', 'abc', SUCCEED, |
|---|
| 151 | n/a | 'found+"-"+g1+"-"+g2', 'abc-a-c'), |
|---|
| 152 | n/a | ('a+b+c', 'aabbabc', SUCCEED, |
|---|
| 153 | n/a | 'found', 'abc'), |
|---|
| 154 | n/a | ('\\(a+\\|b\\)*', 'ab', SUCCEED, |
|---|
| 155 | n/a | 'found+"-"+g1', 'ab-b'), |
|---|
| 156 | n/a | ('\\(a+\\|b\\)+', 'ab', SUCCEED, |
|---|
| 157 | n/a | 'found+"-"+g1', 'ab-b'), |
|---|
| 158 | n/a | ('\\(a+\\|b\\)?', 'ab', SUCCEED, |
|---|
| 159 | n/a | 'found+"-"+g1', 'a-a'), |
|---|
| 160 | n/a | ('\\)\\(', '-', SYNTAX_ERROR), |
|---|
| 161 | n/a | ('[^ab]*', 'cde', SUCCEED, |
|---|
| 162 | n/a | 'found', 'cde'), |
|---|
| 163 | n/a | ('abc', '', FAIL), |
|---|
| 164 | n/a | ('a*', '', SUCCEED, |
|---|
| 165 | n/a | 'found', ''), |
|---|
| 166 | n/a | ('a\\|b\\|c\\|d\\|e', 'e', SUCCEED, |
|---|
| 167 | n/a | 'found', 'e'), |
|---|
| 168 | n/a | ('\\(a\\|b\\|c\\|d\\|e\\)f', 'ef', SUCCEED, |
|---|
| 169 | n/a | 'found+"-"+g1', 'ef-e'), |
|---|
| 170 | n/a | ('abcd*efg', 'abcdefg', SUCCEED, |
|---|
| 171 | n/a | 'found', 'abcdefg'), |
|---|
| 172 | n/a | ('ab*', 'xabyabbbz', SUCCEED, |
|---|
| 173 | n/a | 'found', 'ab'), |
|---|
| 174 | n/a | ('ab*', 'xayabbbz', SUCCEED, |
|---|
| 175 | n/a | 'found', 'a'), |
|---|
| 176 | n/a | ('\\(ab\\|cd\\)e', 'abcde', SUCCEED, |
|---|
| 177 | n/a | 'found+"-"+g1', 'cde-cd'), |
|---|
| 178 | n/a | ('[abhgefdc]ij', 'hij', SUCCEED, |
|---|
| 179 | n/a | 'found', 'hij'), |
|---|
| 180 | n/a | ('^\\(ab\\|cd\\)e', 'abcde', FAIL, |
|---|
| 181 | n/a | 'xg1y', 'xy'), |
|---|
| 182 | n/a | ('\\(abc\\|\\)ef', 'abcdef', SUCCEED, |
|---|
| 183 | n/a | 'found+"-"+g1', 'ef-'), |
|---|
| 184 | n/a | ('\\(a\\|b\\)c*d', 'abcd', SUCCEED, |
|---|
| 185 | n/a | 'found+"-"+g1', 'bcd-b'), |
|---|
| 186 | n/a | ('\\(ab\\|ab*\\)bc', 'abc', SUCCEED, |
|---|
| 187 | n/a | 'found+"-"+g1', 'abc-a'), |
|---|
| 188 | n/a | ('a\\([bc]*\\)c*', 'abc', SUCCEED, |
|---|
| 189 | n/a | 'found+"-"+g1', 'abc-bc'), |
|---|
| 190 | n/a | ('a\\([bc]*\\)\\(c*d\\)', 'abcd', SUCCEED, |
|---|
| 191 | n/a | 'found+"-"+g1+"-"+g2', 'abcd-bc-d'), |
|---|
| 192 | n/a | ('a\\([bc]+\\)\\(c*d\\)', 'abcd', SUCCEED, |
|---|
| 193 | n/a | 'found+"-"+g1+"-"+g2', 'abcd-bc-d'), |
|---|
| 194 | n/a | ('a\\([bc]*\\)\\(c+d\\)', 'abcd', SUCCEED, |
|---|
| 195 | n/a | 'found+"-"+g1+"-"+g2', 'abcd-b-cd'), |
|---|
| 196 | n/a | ('a[bcd]*dcdcde', 'adcdcde', SUCCEED, |
|---|
| 197 | n/a | 'found', 'adcdcde'), |
|---|
| 198 | n/a | ('a[bcd]+dcdcde', 'adcdcde', FAIL), |
|---|
| 199 | n/a | ('\\(ab\\|a\\)b*c', 'abc', SUCCEED, |
|---|
| 200 | n/a | 'found+"-"+g1', 'abc-ab'), |
|---|
| 201 | n/a | ('\\(\\(a\\)\\(b\\)c\\)\\(d\\)', 'abcd', SUCCEED, |
|---|
| 202 | n/a | 'g1+"-"+g2+"-"+g3+"-"+g4', 'abc-a-b-d'), |
|---|
| 203 | n/a | ('[a-zA-Z_][a-zA-Z0-9_]*', 'alpha', SUCCEED, |
|---|
| 204 | n/a | 'found', 'alpha'), |
|---|
| 205 | n/a | ('^a\\(bc+\\|b[eh]\\)g\\|.h$', 'abh', SUCCEED, |
|---|
| 206 | n/a | 'found+"-"+g1', 'bh-None'), |
|---|
| 207 | n/a | ('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'effgz', SUCCEED, |
|---|
| 208 | n/a | 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'), |
|---|
| 209 | n/a | ('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'ij', SUCCEED, |
|---|
| 210 | n/a | 'found+"-"+g1+"-"+g2', 'ij-ij-j'), |
|---|
| 211 | n/a | ('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'effg', FAIL), |
|---|
| 212 | n/a | ('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'bcdd', FAIL), |
|---|
| 213 | n/a | ('\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'reffgz', SUCCEED, |
|---|
| 214 | n/a | 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'), |
|---|
| 215 | n/a | ('\\(\\(\\(\\(\\(\\(\\(\\(\\(a\\)\\)\\)\\)\\)\\)\\)\\)\\)', 'a', SUCCEED, |
|---|
| 216 | n/a | 'found', 'a'), |
|---|
| 217 | n/a | ('multiple words of text', 'uh-uh', FAIL), |
|---|
| 218 | n/a | ('multiple words', 'multiple words, yeah', SUCCEED, |
|---|
| 219 | n/a | 'found', 'multiple words'), |
|---|
| 220 | n/a | ('\\(.*\\)c\\(.*\\)', 'abcde', SUCCEED, |
|---|
| 221 | n/a | 'found+"-"+g1+"-"+g2', 'abcde-ab-de'), |
|---|
| 222 | n/a | ('(\\(.*\\), \\(.*\\))', '(a, b)', SUCCEED, |
|---|
| 223 | n/a | 'g2+"-"+g1', 'b-a'), |
|---|
| 224 | n/a | ('[k]', 'ab', FAIL), |
|---|
| 225 | n/a | ('a[-]?c', 'ac', SUCCEED, |
|---|
| 226 | n/a | 'found', 'ac'), |
|---|
| 227 | n/a | ('\\(abc\\)\\1', 'abcabc', SUCCEED, |
|---|
| 228 | n/a | 'g1', 'abc'), |
|---|
| 229 | n/a | ('\\([a-c]*\\)\\1', 'abcabc', SUCCEED, |
|---|
| 230 | n/a | 'g1', 'abc'), |
|---|
| 231 | n/a | ('^\\(.+\\)?B', 'AB', SUCCEED, |
|---|
| 232 | n/a | 'g1', 'A'), |
|---|
| 233 | n/a | ('\\(a+\\).\\1$', 'aaaaa', SUCCEED, |
|---|
| 234 | n/a | 'found+"-"+g1', 'aaaaa-aa'), |
|---|
| 235 | n/a | ('^\\(a+\\).\\1$', 'aaaa', FAIL), |
|---|
| 236 | n/a | ('\\(abc\\)\\1', 'abcabc', SUCCEED, |
|---|
| 237 | n/a | 'found+"-"+g1', 'abcabc-abc'), |
|---|
| 238 | n/a | ('\\([a-c]+\\)\\1', 'abcabc', SUCCEED, |
|---|
| 239 | n/a | 'found+"-"+g1', 'abcabc-abc'), |
|---|
| 240 | n/a | ('\\(a\\)\\1', 'aa', SUCCEED, |
|---|
| 241 | n/a | 'found+"-"+g1', 'aa-a'), |
|---|
| 242 | n/a | ('\\(a+\\)\\1', 'aa', SUCCEED, |
|---|
| 243 | n/a | 'found+"-"+g1', 'aa-a'), |
|---|
| 244 | n/a | ('\\(a+\\)+\\1', 'aa', SUCCEED, |
|---|
| 245 | n/a | 'found+"-"+g1', 'aa-a'), |
|---|
| 246 | n/a | ('\\(a\\).+\\1', 'aba', SUCCEED, |
|---|
| 247 | n/a | 'found+"-"+g1', 'aba-a'), |
|---|
| 248 | n/a | ('\\(a\\)ba*\\1', 'aba', SUCCEED, |
|---|
| 249 | n/a | 'found+"-"+g1', 'aba-a'), |
|---|
| 250 | n/a | ('\\(aa\\|a\\)a\\1$', 'aaa', SUCCEED, |
|---|
| 251 | n/a | 'found+"-"+g1', 'aaa-a'), |
|---|
| 252 | n/a | ('\\(a\\|aa\\)a\\1$', 'aaa', SUCCEED, |
|---|
| 253 | n/a | 'found+"-"+g1', 'aaa-a'), |
|---|
| 254 | n/a | ('\\(a+\\)a\\1$', 'aaa', SUCCEED, |
|---|
| 255 | n/a | 'found+"-"+g1', 'aaa-a'), |
|---|
| 256 | n/a | ('\\([abc]*\\)\\1', 'abcabc', SUCCEED, |
|---|
| 257 | n/a | 'found+"-"+g1', 'abcabc-abc'), |
|---|
| 258 | n/a | ('\\(a\\)\\(b\\)c\\|ab', 'ab', SUCCEED, |
|---|
| 259 | n/a | 'found+"-"+g1+"-"+g2', 'ab-None-None'), |
|---|
| 260 | n/a | ('\\(a\\)+x', 'aaax', SUCCEED, |
|---|
| 261 | n/a | 'found+"-"+g1', 'aaax-a'), |
|---|
| 262 | n/a | ('\\([ac]\\)+x', 'aacx', SUCCEED, |
|---|
| 263 | n/a | 'found+"-"+g1', 'aacx-c'), |
|---|
| 264 | n/a | ('\\([^/]*/\\)*sub1/', 'd:msgs/tdir/sub1/trial/away.cpp', SUCCEED, |
|---|
| 265 | n/a | 'found+"-"+g1', 'd:msgs/tdir/sub1/-tdir/'), |
|---|
| 266 | n/a | ('\\([^.]*\\)\\.\\([^:]*\\):[T ]+\\(.*\\)', 'track1.title:TBlah blah blah', SUCCEED, |
|---|
| 267 | n/a | 'found+"-"+g1+"-"+g2+"-"+g3', 'track1.title:TBlah blah blah-track1-title-Blah blah blah'), |
|---|
| 268 | n/a | ('\\([^N]*N\\)+', 'abNNxyzN', SUCCEED, |
|---|
| 269 | n/a | 'found+"-"+g1', 'abNNxyzN-xyzN'), |
|---|
| 270 | n/a | ('\\([^N]*N\\)+', 'abNNxyz', SUCCEED, |
|---|
| 271 | n/a | 'found+"-"+g1', 'abNN-N'), |
|---|
| 272 | n/a | ('\\([abc]*\\)x', 'abcx', SUCCEED, |
|---|
| 273 | n/a | 'found+"-"+g1', 'abcx-abc'), |
|---|
| 274 | n/a | ('\\([abc]*\\)x', 'abc', FAIL), |
|---|
| 275 | n/a | ('\\([xyz]*\\)x', 'abcx', SUCCEED, |
|---|
| 276 | n/a | 'found+"-"+g1', 'x-'), |
|---|
| 277 | n/a | ('\\(a\\)+b\\|aac', 'aac', SUCCEED, |
|---|
| 278 | n/a | 'found+"-"+g1', 'aac-None'), |
|---|
| 279 | n/a | ('\<a', 'a', SUCCEED, 'found', 'a'), |
|---|
| 280 | n/a | ('\<a', '!', FAIL), |
|---|
| 281 | n/a | ('a\<b', 'ab', FAIL), |
|---|
| 282 | n/a | ('a\>', 'ab', FAIL), |
|---|
| 283 | n/a | ('a\>', 'a!', SUCCEED, 'found', 'a'), |
|---|
| 284 | n/a | ('a\>', 'a', SUCCEED, 'found', 'a'), |
|---|
| 285 | n/a | ] |
|---|