1#!/usr/bin/env python3 2# -*- mode: python -*- 3 4# Re test suite and benchmark suite v1.5 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 17benchmarks = [ 18 19 # test common prefix 20 ('Python|Perl', 'Perl'), # Alternation 21 ('(Python|Perl)', 'Perl'), # Grouped alternation 22 23 ('Python|Perl|Tcl', 'Perl'), # Alternation 24 ('(Python|Perl|Tcl)', 'Perl'), # Grouped alternation 25 26 ('(Python)\\1', 'PythonPython'), # Backreference 27 ('([0a-z][a-z0-9]*,)+', 'a5,b7,c9,'), # Disable the fastmap optimization 28 ('([a-z][a-z0-9]*,)+', 'a5,b7,c9,'), # A few sets 29 30 ('Python', 'Python'), # Simple text literal 31 ('.*Python', 'Python'), # Bad text literal 32 ('.*Python.*', 'Python'), # Worse text literal 33 ('.*(Python)', 'Python'), # Bad text literal with grouping 34 35] 36 37# Test suite (for verifying correctness) 38# 39# The test suite is a list of 5- or 3-tuples. The 5 parts of a 40# complete tuple are: 41# element 0: a string containing the pattern 42# 1: the string to match against the pattern 43# 2: the expected result (SUCCEED, FAIL, SYNTAX_ERROR) 44# 3: a string that will be eval()'ed to produce a test string. 45# This is an arbitrary Python expression; the available 46# variables are "found" (the whole match), and "g1", "g2", ... 47# up to "g99" contain the contents of each group, or the 48# string 'None' if the group wasn't given a value, or the 49# string 'Error' if the group index was out of range; 50# also "groups", the return value of m.group() (a tuple). 51# 4: The expected result of evaluating the expression. 52# If the two don't match, an error is reported. 53# 54# If the regex isn't expected to work, the latter two elements can be omitted. 55 56tests = [ 57 # Test ?P< and ?P= extensions 58 ('(?P<foo_123', '', SYNTAX_ERROR), # Unterminated group identifier 59 ('(?P<1>a)', '', SYNTAX_ERROR), # Begins with a digit 60 ('(?P<!>a)', '', SYNTAX_ERROR), # Begins with an illegal char 61 ('(?P<foo!>a)', '', SYNTAX_ERROR), # Begins with an illegal char 62 63 # Same tests, for the ?P= form 64 ('(?P<foo_123>a)(?P=foo_123', 'aa', SYNTAX_ERROR), 65 ('(?P<foo_123>a)(?P=1)', 'aa', SYNTAX_ERROR), 66 ('(?P<foo_123>a)(?P=!)', 'aa', SYNTAX_ERROR), 67 ('(?P<foo_123>a)(?P=foo_124', 'aa', SYNTAX_ERROR), # Backref to undefined group 68 69 ('(?P<foo_123>a)', 'a', SUCCEED, 'g1', 'a'), 70 ('(?P<foo_123>a)(?P=foo_123)', 'aa', SUCCEED, 'g1', 'a'), 71 72 # Test octal escapes 73 ('\\1', 'a', SYNTAX_ERROR), # Backreference 74 ('[\\1]', '\1', SUCCEED, 'found', '\1'), # Character 75 ('\\09', chr(0) + '9', SUCCEED, 'found', chr(0) + '9'), 76 ('\\141', 'a', SUCCEED, 'found', 'a'), 77 ('(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)\\119', 'abcdefghijklk9', SUCCEED, 'found+"-"+g11', 'abcdefghijklk9-k'), 78 79 # Test \0 is handled everywhere 80 (r'\0', '\0', SUCCEED, 'found', '\0'), 81 (r'[\0a]', '\0', SUCCEED, 'found', '\0'), 82 (r'[a\0]', '\0', SUCCEED, 'found', '\0'), 83 (r'[^a\0]', '\0', FAIL), 84 85 # Test various letter escapes 86 (r'\a[\b]\f\n\r\t\v', '\a\b\f\n\r\t\v', SUCCEED, 'found', '\a\b\f\n\r\t\v'), 87 (r'[\a][\b][\f][\n][\r][\t][\v]', '\a\b\f\n\r\t\v', SUCCEED, 'found', '\a\b\f\n\r\t\v'), 88 # NOTE: not an error under PCRE/PRE: 89 (r'\u', '', SYNTAX_ERROR), # A Perl escape 90 # (r'\c\e\g\h\i\j\k\m\o\p\q\y\z', 'ceghijkmopqyz', SUCCEED, 'found', 'ceghijkmopqyz'), 91 # new \x semantics 92 (r'\x00ffffffffffffff', '\377', FAIL, 'found', chr(255)), 93 (r'\x00f', '\017', FAIL, 'found', chr(15)), 94 (r'\x00fe', '\376', FAIL, 'found', chr(254)), 95 # (r'\x00ffffffffffffff', '\377', SUCCEED, 'found', chr(255)), 96 # (r'\x00f', '\017', SUCCEED, 'found', chr(15)), 97 # (r'\x00fe', '\376', SUCCEED, 'found', chr(254)), 98 99 (r"^\w+=(\\[\000-\277]|[^\n\\])*", "SRC=eval.c g.c blah blah blah \\\\\n\tapes.c", 100 SUCCEED, 'found', "SRC=eval.c g.c blah blah blah \\\\"), 101 102 # Test that . only matches \n in DOTALL mode 103 ('a.b', 'acb', SUCCEED, 'found', 'acb'), 104 ('a.b', 'a\nb', FAIL), 105 ('a.*b', 'acc\nccb', FAIL), 106 ('a.{4,5}b', 'acc\nccb', FAIL), 107 ('a.b', 'a\rb', SUCCEED, 'found', 'a\rb'), 108 ('(?s)a.b', 'a\nb', SUCCEED, 'found', 'a\nb'), 109 ('(?s)a.*b', 'acc\nccb', SUCCEED, 'found', 'acc\nccb'), 110 ('(?s)a.{4,5}b', 'acc\nccb', SUCCEED, 'found', 'acc\nccb'), 111 ('(?s)a.b', 'a\rb', SUCCEED, 'found', 'a\rb'), 112 113 (')', '', SYNTAX_ERROR), # Unmatched right bracket 114 ('', '', SUCCEED, 'found', ''), # Empty pattern 115 ('abc', 'abc', SUCCEED, 'found', 'abc'), 116 ('abc', 'xbc', FAIL), 117 ('abc', 'axc', FAIL), 118 ('abc', 'abx', FAIL), 119 ('abc', 'xabcy', SUCCEED, 'found', 'abc'), 120 ('abc', 'ababc', SUCCEED, 'found', 'abc'), 121 ('ab*c', 'abc', SUCCEED, 'found', 'abc'), 122 ('ab*bc', 'abc', SUCCEED, 'found', 'abc'), 123 ('ab*bc', 'abbc', SUCCEED, 'found', 'abbc'), 124 ('ab*bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), 125 ('ab+bc', 'abbc', SUCCEED, 'found', 'abbc'), 126 ('ab+bc', 'abc', FAIL), 127 ('ab+bc', 'abq', FAIL), 128 ('ab+bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), 129 ('ab?bc', 'abbc', SUCCEED, 'found', 'abbc'), 130 ('ab?bc', 'abc', SUCCEED, 'found', 'abc'), 131 ('ab?bc', 'abbbbc', FAIL), 132 ('ab?c', 'abc', SUCCEED, 'found', 'abc'), 133 ('^abc$', 'abc', SUCCEED, 'found', 'abc'), 134 ('^abc$', 'abcc', FAIL), 135 ('^abc', 'abcc', SUCCEED, 'found', 'abc'), 136 ('^abc$', 'aabc', FAIL), 137 ('abc$', 'aabc', SUCCEED, 'found', 'abc'), 138 ('^', 'abc', SUCCEED, 'found+"-"', '-'), 139 ('$', 'abc', SUCCEED, 'found+"-"', '-'), 140 ('a.c', 'abc', SUCCEED, 'found', 'abc'), 141 ('a.c', 'axc', SUCCEED, 'found', 'axc'), 142 ('a.*c', 'axyzc', SUCCEED, 'found', 'axyzc'), 143 ('a.*c', 'axyzd', FAIL), 144 ('a[bc]d', 'abc', FAIL), 145 ('a[bc]d', 'abd', SUCCEED, 'found', 'abd'), 146 ('a[b-d]e', 'abd', FAIL), 147 ('a[b-d]e', 'ace', SUCCEED, 'found', 'ace'), 148 ('a[b-d]', 'aac', SUCCEED, 'found', 'ac'), 149 ('a[-b]', 'a-', SUCCEED, 'found', 'a-'), 150 ('a[\\-b]', 'a-', SUCCEED, 'found', 'a-'), 151 # NOTE: not an error under PCRE/PRE: 152 # ('a[b-]', 'a-', SYNTAX_ERROR), 153 ('a[]b', '-', SYNTAX_ERROR), 154 ('a[', '-', SYNTAX_ERROR), 155 ('a\\', '-', SYNTAX_ERROR), 156 ('abc)', '-', SYNTAX_ERROR), 157 ('(abc', '-', SYNTAX_ERROR), 158 ('a]', 'a]', SUCCEED, 'found', 'a]'), 159 ('a[]]b', 'a]b', SUCCEED, 'found', 'a]b'), 160 ('a[\\]]b', 'a]b', SUCCEED, 'found', 'a]b'), 161 ('a[^bc]d', 'aed', SUCCEED, 'found', 'aed'), 162 ('a[^bc]d', 'abd', FAIL), 163 ('a[^-b]c', 'adc', SUCCEED, 'found', 'adc'), 164 ('a[^-b]c', 'a-c', FAIL), 165 ('a[^]b]c', 'a]c', FAIL), 166 ('a[^]b]c', 'adc', SUCCEED, 'found', 'adc'), 167 ('\\ba\\b', 'a-', SUCCEED, '"-"', '-'), 168 ('\\ba\\b', '-a', SUCCEED, '"-"', '-'), 169 ('\\ba\\b', '-a-', SUCCEED, '"-"', '-'), 170 ('\\by\\b', 'xy', FAIL), 171 ('\\by\\b', 'yz', FAIL), 172 ('\\by\\b', 'xyz', FAIL), 173 ('x\\b', 'xyz', FAIL), 174 ('x\\B', 'xyz', SUCCEED, '"-"', '-'), 175 ('\\Bz', 'xyz', SUCCEED, '"-"', '-'), 176 ('z\\B', 'xyz', FAIL), 177 ('\\Bx', 'xyz', FAIL), 178 ('\\Ba\\B', 'a-', FAIL, '"-"', '-'), 179 ('\\Ba\\B', '-a', FAIL, '"-"', '-'), 180 ('\\Ba\\B', '-a-', FAIL, '"-"', '-'), 181 ('\\By\\B', 'xy', FAIL), 182 ('\\By\\B', 'yz', FAIL), 183 ('\\By\\b', 'xy', SUCCEED, '"-"', '-'), 184 ('\\by\\B', 'yz', SUCCEED, '"-"', '-'), 185 ('\\By\\B', 'xyz', SUCCEED, '"-"', '-'), 186 ('ab|cd', 'abc', SUCCEED, 'found', 'ab'), 187 ('ab|cd', 'abcd', SUCCEED, 'found', 'ab'), 188 ('()ef', 'def', SUCCEED, 'found+"-"+g1', 'ef-'), 189 ('$b', 'b', FAIL), 190 ('a\\(b', 'a(b', SUCCEED, 'found+"-"+g1', 'a(b-Error'), 191 ('a\\(*b', 'ab', SUCCEED, 'found', 'ab'), 192 ('a\\(*b', 'a((b', SUCCEED, 'found', 'a((b'), 193 ('a\\\\b', 'a\\b', SUCCEED, 'found', 'a\\b'), 194 ('((a))', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'a-a-a'), 195 ('(a)b(c)', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'abc-a-c'), 196 ('a+b+c', 'aabbabc', SUCCEED, 'found', 'abc'), 197 ('(a+|b)*', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), 198 ('(a+|b)+', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), 199 ('(a+|b)?', 'ab', SUCCEED, 'found+"-"+g1', 'a-a'), 200 (')(', '-', SYNTAX_ERROR), 201 ('[^ab]*', 'cde', SUCCEED, 'found', 'cde'), 202 ('abc', '', FAIL), 203 ('a*', '', SUCCEED, 'found', ''), 204 ('a|b|c|d|e', 'e', SUCCEED, 'found', 'e'), 205 ('(a|b|c|d|e)f', 'ef', SUCCEED, 'found+"-"+g1', 'ef-e'), 206 ('abcd*efg', 'abcdefg', SUCCEED, 'found', 'abcdefg'), 207 ('ab*', 'xabyabbbz', SUCCEED, 'found', 'ab'), 208 ('ab*', 'xayabbbz', SUCCEED, 'found', 'a'), 209 ('(ab|cd)e', 'abcde', SUCCEED, 'found+"-"+g1', 'cde-cd'), 210 ('[abhgefdc]ij', 'hij', SUCCEED, 'found', 'hij'), 211 ('^(ab|cd)e', 'abcde', FAIL, 'xg1y', 'xy'), 212 ('(abc|)ef', 'abcdef', SUCCEED, 'found+"-"+g1', 'ef-'), 213 ('(a|b)c*d', 'abcd', SUCCEED, 'found+"-"+g1', 'bcd-b'), 214 ('(ab|ab*)bc', 'abc', SUCCEED, 'found+"-"+g1', 'abc-a'), 215 ('a([bc]*)c*', 'abc', SUCCEED, 'found+"-"+g1', 'abc-bc'), 216 ('a([bc]*)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'), 217 ('a([bc]+)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'), 218 ('a([bc]*)(c+d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-b-cd'), 219 ('a[bcd]*dcdcde', 'adcdcde', SUCCEED, 'found', 'adcdcde'), 220 ('a[bcd]+dcdcde', 'adcdcde', FAIL), 221 ('(ab|a)b*c', 'abc', SUCCEED, 'found+"-"+g1', 'abc-ab'), 222 ('((a)(b)c)(d)', 'abcd', SUCCEED, 'g1+"-"+g2+"-"+g3+"-"+g4', 'abc-a-b-d'), 223 ('[a-zA-Z_][a-zA-Z0-9_]*', 'alpha', SUCCEED, 'found', 'alpha'), 224 ('^a(bc+|b[eh])g|.h$', 'abh', SUCCEED, 'found+"-"+g1', 'bh-None'), 225 ('(bc+d$|ef*g.|h?i(j|k))', 'effgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'), 226 ('(bc+d$|ef*g.|h?i(j|k))', 'ij', SUCCEED, 'found+"-"+g1+"-"+g2', 'ij-ij-j'), 227 ('(bc+d$|ef*g.|h?i(j|k))', 'effg', FAIL), 228 ('(bc+d$|ef*g.|h?i(j|k))', 'bcdd', FAIL), 229 ('(bc+d$|ef*g.|h?i(j|k))', 'reffgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'), 230 ('(((((((((a)))))))))', 'a', SUCCEED, 'found', 'a'), 231 ('multiple words of text', 'uh-uh', FAIL), 232 ('multiple words', 'multiple words, yeah', SUCCEED, 'found', 'multiple words'), 233 ('(.*)c(.*)', 'abcde', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcde-ab-de'), 234 ('\\((.*), (.*)\\)', '(a, b)', SUCCEED, 'g2+"-"+g1', 'b-a'), 235 ('[k]', 'ab', FAIL), 236 ('a[-]?c', 'ac', SUCCEED, 'found', 'ac'), 237 ('(abc)\\1', 'abcabc', SUCCEED, 'g1', 'abc'), 238 ('([a-c]*)\\1', 'abcabc', SUCCEED, 'g1', 'abc'), 239 ('^(.+)?B', 'AB', SUCCEED, 'g1', 'A'), 240 ('(a+).\\1$', 'aaaaa', SUCCEED, 'found+"-"+g1', 'aaaaa-aa'), 241 ('^(a+).\\1$', 'aaaa', FAIL), 242 ('(abc)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'), 243 ('([a-c]+)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'), 244 ('(a)\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'), 245 ('(a+)\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'), 246 ('(a+)+\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'), 247 ('(a).+\\1', 'aba', SUCCEED, 'found+"-"+g1', 'aba-a'), 248 ('(a)ba*\\1', 'aba', SUCCEED, 'found+"-"+g1', 'aba-a'), 249 ('(aa|a)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'), 250 ('(a|aa)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'), 251 ('(a+)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'), 252 ('([abc]*)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'), 253 ('(a)(b)c|ab', 'ab', SUCCEED, 'found+"-"+g1+"-"+g2', 'ab-None-None'), 254 ('(a)+x', 'aaax', SUCCEED, 'found+"-"+g1', 'aaax-a'), 255 ('([ac])+x', 'aacx', SUCCEED, 'found+"-"+g1', 'aacx-c'), 256 ('([^/]*/)*sub1/', 'd:msgs/tdir/sub1/trial/away.cpp', SUCCEED, 'found+"-"+g1', 'd:msgs/tdir/sub1/-tdir/'), 257 ('([^.]*)\\.([^:]*):[T ]+(.*)', 'track1.title:TBlah blah blah', SUCCEED, 'found+"-"+g1+"-"+g2+"-"+g3', 'track1.title:TBlah blah blah-track1-title-Blah blah blah'), 258 ('([^N]*N)+', 'abNNxyzN', SUCCEED, 'found+"-"+g1', 'abNNxyzN-xyzN'), 259 ('([^N]*N)+', 'abNNxyz', SUCCEED, 'found+"-"+g1', 'abNN-N'), 260 ('([abc]*)x', 'abcx', SUCCEED, 'found+"-"+g1', 'abcx-abc'), 261 ('([abc]*)x', 'abc', FAIL), 262 ('([xyz]*)x', 'abcx', SUCCEED, 'found+"-"+g1', 'x-'), 263 ('(a)+b|aac', 'aac', SUCCEED, 'found+"-"+g1', 'aac-None'), 264 265 # Test symbolic groups 266 267 ('(?P<i d>aaa)a', 'aaaa', SYNTAX_ERROR), 268 ('(?P<id>aaa)a', 'aaaa', SUCCEED, 'found+"-"+id', 'aaaa-aaa'), 269 ('(?P<id>aa)(?P=id)', 'aaaa', SUCCEED, 'found+"-"+id', 'aaaa-aa'), 270 ('(?P<id>aa)(?P=xd)', 'aaaa', SYNTAX_ERROR), 271 272 # Test octal escapes/memory references 273 274 ('\\1', 'a', SYNTAX_ERROR), 275 276 # All tests from Perl 277 278 ('ab{0,}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), 279 ('ab{1,}bc', 'abq', FAIL), 280 ('ab{1,}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), 281 ('ab{1,3}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), 282 ('ab{3,4}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), 283 ('ab{4,5}bc', 'abbbbc', FAIL), 284 ('ab{0,1}bc', 'abc', SUCCEED, 'found', 'abc'), 285 ('ab{0,1}c', 'abc', SUCCEED, 'found', 'abc'), 286 ('^', 'abc', SUCCEED, 'found', ''), 287 ('$', 'abc', SUCCEED, 'found', ''), 288 ('a[b-]', 'a-', SUCCEED, 'found', 'a-'), 289 ('a[b-a]', '-', SYNTAX_ERROR), 290 ('*a', '-', SYNTAX_ERROR), 291 ('(*)b', '-', SYNTAX_ERROR), 292 ('a{1,}b{1,}c', 'aabbabc', SUCCEED, 'found', 'abc'), 293 ('a**', '-', SYNTAX_ERROR), 294 ('a.+?c', 'abcabc', SUCCEED, 'found', 'abc'), 295 ('(a+|b){0,}', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), 296 ('(a+|b){1,}', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), 297 ('(a+|b){0,1}', 'ab', SUCCEED, 'found+"-"+g1', 'a-a'), 298 ('([abc])*d', 'abbbcd', SUCCEED, 'found+"-"+g1', 'abbbcd-c'), 299 ('([abc])*bcd', 'abcd', SUCCEED, 'found+"-"+g1', 'abcd-a'), 300 ('^(ab|cd)e', 'abcde', FAIL), 301 ('((((((((((a))))))))))', 'a', SUCCEED, 'g10', 'a'), 302 ('((((((((((a))))))))))\\10', 'aa', SUCCEED, 'found', 'aa'), 303# Python does not have the same rules for \\41 so this is a syntax error 304# ('((((((((((a))))))))))\\41', 'aa', FAIL), 305# ('((((((((((a))))))))))\\41', 'a!', SUCCEED, 'found', 'a!'), 306 ('((((((((((a))))))))))\\41', '', SYNTAX_ERROR), 307 ('(?i)((((((((((a))))))))))\\41', '', SYNTAX_ERROR), 308 ('(?i)abc', 'ABC', SUCCEED, 'found', 'ABC'), 309 ('(?i)abc', 'XBC', FAIL), 310 ('(?i)abc', 'AXC', FAIL), 311 ('(?i)abc', 'ABX', FAIL), 312 ('(?i)abc', 'XABCY', SUCCEED, 'found', 'ABC'), 313 ('(?i)abc', 'ABABC', SUCCEED, 'found', 'ABC'), 314 ('(?i)ab*c', 'ABC', SUCCEED, 'found', 'ABC'), 315 ('(?i)ab*bc', 'ABC', SUCCEED, 'found', 'ABC'), 316 ('(?i)ab*bc', 'ABBC', SUCCEED, 'found', 'ABBC'), 317 ('(?i)ab*?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), 318 ('(?i)ab{0,}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), 319 ('(?i)ab+?bc', 'ABBC', SUCCEED, 'found', 'ABBC'), 320 ('(?i)ab+bc', 'ABC', FAIL), 321 ('(?i)ab+bc', 'ABQ', FAIL), 322 ('(?i)ab{1,}bc', 'ABQ', FAIL), 323 ('(?i)ab+bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), 324 ('(?i)ab{1,}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), 325 ('(?i)ab{1,3}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), 326 ('(?i)ab{3,4}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), 327 ('(?i)ab{4,5}?bc', 'ABBBBC', FAIL), 328 ('(?i)ab??bc', 'ABBC', SUCCEED, 'found', 'ABBC'), 329 ('(?i)ab??bc', 'ABC', SUCCEED, 'found', 'ABC'), 330 ('(?i)ab{0,1}?bc', 'ABC', SUCCEED, 'found', 'ABC'), 331 ('(?i)ab??bc', 'ABBBBC', FAIL), 332 ('(?i)ab??c', 'ABC', SUCCEED, 'found', 'ABC'), 333 ('(?i)ab{0,1}?c', 'ABC', SUCCEED, 'found', 'ABC'), 334 ('(?i)^abc$', 'ABC', SUCCEED, 'found', 'ABC'), 335 ('(?i)^abc$', 'ABCC', FAIL), 336 ('(?i)^abc', 'ABCC', SUCCEED, 'found', 'ABC'), 337 ('(?i)^abc$', 'AABC', FAIL), 338 ('(?i)abc$', 'AABC', SUCCEED, 'found', 'ABC'), 339 ('(?i)^', 'ABC', SUCCEED, 'found', ''), 340 ('(?i)$', 'ABC', SUCCEED, 'found', ''), 341 ('(?i)a.c', 'ABC', SUCCEED, 'found', 'ABC'), 342 ('(?i)a.c', 'AXC', SUCCEED, 'found', 'AXC'), 343 ('(?i)a.*?c', 'AXYZC', SUCCEED, 'found', 'AXYZC'), 344 ('(?i)a.*c', 'AXYZD', FAIL), 345 ('(?i)a[bc]d', 'ABC', FAIL), 346 ('(?i)a[bc]d', 'ABD', SUCCEED, 'found', 'ABD'), 347 ('(?i)a[b-d]e', 'ABD', FAIL), 348 ('(?i)a[b-d]e', 'ACE', SUCCEED, 'found', 'ACE'), 349 ('(?i)a[b-d]', 'AAC', SUCCEED, 'found', 'AC'), 350 ('(?i)a[-b]', 'A-', SUCCEED, 'found', 'A-'), 351 ('(?i)a[b-]', 'A-', SUCCEED, 'found', 'A-'), 352 ('(?i)a[b-a]', '-', SYNTAX_ERROR), 353 ('(?i)a[]b', '-', SYNTAX_ERROR), 354 ('(?i)a[', '-', SYNTAX_ERROR), 355 ('(?i)a]', 'A]', SUCCEED, 'found', 'A]'), 356 ('(?i)a[]]b', 'A]B', SUCCEED, 'found', 'A]B'), 357 ('(?i)a[^bc]d', 'AED', SUCCEED, 'found', 'AED'), 358 ('(?i)a[^bc]d', 'ABD', FAIL), 359 ('(?i)a[^-b]c', 'ADC', SUCCEED, 'found', 'ADC'), 360 ('(?i)a[^-b]c', 'A-C', FAIL), 361 ('(?i)a[^]b]c', 'A]C', FAIL), 362 ('(?i)a[^]b]c', 'ADC', SUCCEED, 'found', 'ADC'), 363 ('(?i)ab|cd', 'ABC', SUCCEED, 'found', 'AB'), 364 ('(?i)ab|cd', 'ABCD', SUCCEED, 'found', 'AB'), 365 ('(?i)()ef', 'DEF', SUCCEED, 'found+"-"+g1', 'EF-'), 366 ('(?i)*a', '-', SYNTAX_ERROR), 367 ('(?i)(*)b', '-', SYNTAX_ERROR), 368 ('(?i)$b', 'B', FAIL), 369 ('(?i)a\\', '-', SYNTAX_ERROR), 370 ('(?i)a\\(b', 'A(B', SUCCEED, 'found+"-"+g1', 'A(B-Error'), 371 ('(?i)a\\(*b', 'AB', SUCCEED, 'found', 'AB'), 372 ('(?i)a\\(*b', 'A((B', SUCCEED, 'found', 'A((B'), 373 ('(?i)a\\\\b', 'A\\B', SUCCEED, 'found', 'A\\B'), 374 ('(?i)abc)', '-', SYNTAX_ERROR), 375 ('(?i)(abc', '-', SYNTAX_ERROR), 376 ('(?i)((a))', 'ABC', SUCCEED, 'found+"-"+g1+"-"+g2', 'A-A-A'), 377 ('(?i)(a)b(c)', 'ABC', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABC-A-C'), 378 ('(?i)a+b+c', 'AABBABC', SUCCEED, 'found', 'ABC'), 379 ('(?i)a{1,}b{1,}c', 'AABBABC', SUCCEED, 'found', 'ABC'), 380 ('(?i)a**', '-', SYNTAX_ERROR), 381 ('(?i)a.+?c', 'ABCABC', SUCCEED, 'found', 'ABC'), 382 ('(?i)a.*?c', 'ABCABC', SUCCEED, 'found', 'ABC'), 383 ('(?i)a.{0,5}?c', 'ABCABC', SUCCEED, 'found', 'ABC'), 384 ('(?i)(a+|b)*', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'), 385 ('(?i)(a+|b){0,}', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'), 386 ('(?i)(a+|b)+', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'), 387 ('(?i)(a+|b){1,}', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'), 388 ('(?i)(a+|b)?', 'AB', SUCCEED, 'found+"-"+g1', 'A-A'), 389 ('(?i)(a+|b){0,1}', 'AB', SUCCEED, 'found+"-"+g1', 'A-A'), 390 ('(?i)(a+|b){0,1}?', 'AB', SUCCEED, 'found+"-"+g1', '-None'), 391 ('(?i))(', '-', SYNTAX_ERROR), 392 ('(?i)[^ab]*', 'CDE', SUCCEED, 'found', 'CDE'), 393 ('(?i)abc', '', FAIL), 394 ('(?i)a*', '', SUCCEED, 'found', ''), 395 ('(?i)([abc])*d', 'ABBBCD', SUCCEED, 'found+"-"+g1', 'ABBBCD-C'), 396 ('(?i)([abc])*bcd', 'ABCD', SUCCEED, 'found+"-"+g1', 'ABCD-A'), 397 ('(?i)a|b|c|d|e', 'E', SUCCEED, 'found', 'E'), 398 ('(?i)(a|b|c|d|e)f', 'EF', SUCCEED, 'found+"-"+g1', 'EF-E'), 399 ('(?i)abcd*efg', 'ABCDEFG', SUCCEED, 'found', 'ABCDEFG'), 400 ('(?i)ab*', 'XABYABBBZ', SUCCEED, 'found', 'AB'), 401 ('(?i)ab*', 'XAYABBBZ', SUCCEED, 'found', 'A'), 402 ('(?i)(ab|cd)e', 'ABCDE', SUCCEED, 'found+"-"+g1', 'CDE-CD'), 403 ('(?i)[abhgefdc]ij', 'HIJ', SUCCEED, 'found', 'HIJ'), 404 ('(?i)^(ab|cd)e', 'ABCDE', FAIL), 405 ('(?i)(abc|)ef', 'ABCDEF', SUCCEED, 'found+"-"+g1', 'EF-'), 406 ('(?i)(a|b)c*d', 'ABCD', SUCCEED, 'found+"-"+g1', 'BCD-B'), 407 ('(?i)(ab|ab*)bc', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-A'), 408 ('(?i)a([bc]*)c*', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-BC'), 409 ('(?i)a([bc]*)(c*d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-BC-D'), 410 ('(?i)a([bc]+)(c*d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-BC-D'), 411 ('(?i)a([bc]*)(c+d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-B-CD'), 412 ('(?i)a[bcd]*dcdcde', 'ADCDCDE', SUCCEED, 'found', 'ADCDCDE'), 413 ('(?i)a[bcd]+dcdcde', 'ADCDCDE', FAIL), 414 ('(?i)(ab|a)b*c', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-AB'), 415 ('(?i)((a)(b)c)(d)', 'ABCD', SUCCEED, 'g1+"-"+g2+"-"+g3+"-"+g4', 'ABC-A-B-D'), 416 ('(?i)[a-zA-Z_][a-zA-Z0-9_]*', 'ALPHA', SUCCEED, 'found', 'ALPHA'), 417 ('(?i)^a(bc+|b[eh])g|.h$', 'ABH', SUCCEED, 'found+"-"+g1', 'BH-None'), 418 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'EFFGZ', SUCCEED, 'found+"-"+g1+"-"+g2', 'EFFGZ-EFFGZ-None'), 419 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'IJ', SUCCEED, 'found+"-"+g1+"-"+g2', 'IJ-IJ-J'), 420 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'EFFG', FAIL), 421 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'BCDD', FAIL), 422 ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'REFFGZ', SUCCEED, 'found+"-"+g1+"-"+g2', 'EFFGZ-EFFGZ-None'), 423 ('(?i)((((((((((a))))))))))', 'A', SUCCEED, 'g10', 'A'), 424 ('(?i)((((((((((a))))))))))\\10', 'AA', SUCCEED, 'found', 'AA'), 425 #('(?i)((((((((((a))))))))))\\41', 'AA', FAIL), 426 #('(?i)((((((((((a))))))))))\\41', 'A!', SUCCEED, 'found', 'A!'), 427 ('(?i)(((((((((a)))))))))', 'A', SUCCEED, 'found', 'A'), 428 ('(?i)(?:(?:(?:(?:(?:(?:(?:(?:(?:(a))))))))))', 'A', SUCCEED, 'g1', 'A'), 429 ('(?i)(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))', 'C', SUCCEED, 'g1', 'C'), 430 ('(?i)multiple words of text', 'UH-UH', FAIL), 431 ('(?i)multiple words', 'MULTIPLE WORDS, YEAH', SUCCEED, 'found', 'MULTIPLE WORDS'), 432 ('(?i)(.*)c(.*)', 'ABCDE', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCDE-AB-DE'), 433 ('(?i)\\((.*), (.*)\\)', '(A, B)', SUCCEED, 'g2+"-"+g1', 'B-A'), 434 ('(?i)[k]', 'AB', FAIL), 435# ('(?i)abcd', 'ABCD', SUCCEED, 'found+"-"+\\found+"-"+\\\\found', 'ABCD-$&-\\ABCD'), 436# ('(?i)a(bc)d', 'ABCD', SUCCEED, 'g1+"-"+\\g1+"-"+\\\\g1', 'BC-$1-\\BC'), 437 ('(?i)a[-]?c', 'AC', SUCCEED, 'found', 'AC'), 438 ('(?i)(abc)\\1', 'ABCABC', SUCCEED, 'g1', 'ABC'), 439 ('(?i)([a-c]*)\\1', 'ABCABC', SUCCEED, 'g1', 'ABC'), 440 ('a(?!b).', 'abad', SUCCEED, 'found', 'ad'), 441 ('a(?=d).', 'abad', SUCCEED, 'found', 'ad'), 442 ('a(?=c|d).', 'abad', SUCCEED, 'found', 'ad'), 443 ('a(?:b|c|d)(.)', 'ace', SUCCEED, 'g1', 'e'), 444 ('a(?:b|c|d)*(.)', 'ace', SUCCEED, 'g1', 'e'), 445 ('a(?:b|c|d)+?(.)', 'ace', SUCCEED, 'g1', 'e'), 446 ('a(?:b|(c|e){1,2}?|d)+?(.)', 'ace', SUCCEED, 'g1 + g2', 'ce'), 447 448 # lookbehind: split by : but not if it is escaped by -. 449 ('(?<!-):(.*?)(?<!-):', 'a:bc-:de:f', SUCCEED, 'g1', 'bc-:de' ), 450 # escaping with \ as we know it 451 ('(?<!\\\\):(.*?)(?<!\\\\):', 'a:bc\\:de:f', SUCCEED, 'g1', 'bc\\:de' ), 452 # terminating with ' and escaping with ? as in edifact 453 ("(?<!\\?)'(.*?)(?<!\\?)'", "a'bc?'de'f", SUCCEED, 'g1', "bc?'de" ), 454 455 # Comments using the (?#...) syntax 456 457 ('w(?# comment', 'w', SYNTAX_ERROR), 458 ('w(?# comment 1)xy(?# comment 2)z', 'wxyz', SUCCEED, 'found', 'wxyz'), 459 460 # Check odd placement of embedded pattern modifiers 461 462 # not an error under PCRE/PRE: 463 ('(?i)w', 'W', SUCCEED, 'found', 'W'), 464 # ('w(?i)', 'W', SYNTAX_ERROR), 465 466 # Comments using the x embedded pattern modifier 467 468 ("""(?x)w# comment 1 469 x y 470 # comment 2 471 z""", 'wxyz', SUCCEED, 'found', 'wxyz'), 472 473 # using the m embedded pattern modifier 474 475 ('^abc', """jkl 476abc 477xyz""", FAIL), 478 ('(?m)^abc', """jkl 479abc 480xyz""", SUCCEED, 'found', 'abc'), 481 482 ('(?m)abc$', """jkl 483xyzabc 484123""", SUCCEED, 'found', 'abc'), 485 486 487 488 # test \w, etc. both inside and outside character classes 489 490 ('\\w+', '--ab_cd0123--', SUCCEED, 'found', 'ab_cd0123'), 491 ('[\\w]+', '--ab_cd0123--', SUCCEED, 'found', 'ab_cd0123'), 492 ('\\D+', '1234abc5678', SUCCEED, 'found', 'abc'), 493 ('[\\D]+', '1234abc5678', SUCCEED, 'found', 'abc'), 494 ('[\\da-fA-F]+', '123abc', SUCCEED, 'found', '123abc'), 495 # not an error under PCRE/PRE: 496 # ('[\\d-x]', '-', SYNTAX_ERROR), 497 (r'([\s]*)([\S]*)([\s]*)', ' testing!1972', SUCCEED, 'g3+g2+g1', 'testing!1972 '), 498 (r'(\s*)(\S*)(\s*)', ' testing!1972', SUCCEED, 'g3+g2+g1', 'testing!1972 '), 499 500 (r'\xff', '\377', SUCCEED, 'found', chr(255)), 501 # new \x semantics 502 (r'\x00ff', '\377', FAIL), 503 # (r'\x00ff', '\377', SUCCEED, 'found', chr(255)), 504 (r'\t\n\v\r\f\a', '\t\n\v\r\f\a', SUCCEED, 'found', '\t\n\v\r\f\a'), 505 ('\t\n\v\r\f\a', '\t\n\v\r\f\a', SUCCEED, 'found', '\t\n\v\r\f\a'), 506 (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)), 507 (r'[\t][\n][\v][\r][\f][\b]', '\t\n\v\r\f\b', SUCCEED, 'found', '\t\n\v\r\f\b'), 508 509 # 510 # post-1.5.2 additions 511 512 # xmllib problem 513 (r'(([a-z]+):)?([a-z]+)$', 'smil', SUCCEED, 'g1+"-"+g2+"-"+g3', 'None-None-smil'), 514 # bug 110866: reference to undefined group 515 (r'((.)\1+)', '', SYNTAX_ERROR), 516 # bug 111869: search (PRE/PCRE fails on this one, SRE doesn't) 517 (r'.*d', 'abc\nabd', SUCCEED, 'found', 'abd'), 518 # bug 112468: various expected syntax errors 519 (r'(', '', SYNTAX_ERROR), 520 (r'[\41]', '!', SUCCEED, 'found', '!'), 521 # bug 114033: nothing to repeat 522 (r'(x?)?', 'x', SUCCEED, 'found', 'x'), 523 # bug 115040: rescan if flags are modified inside pattern 524 (r'(?x) foo ', 'foo', SUCCEED, 'found', 'foo'), 525 # bug 115618: negative lookahead 526 (r'(?<!abc)(d.f)', 'abcdefdof', SUCCEED, 'found', 'dof'), 527 # bug 116251: character class bug 528 (r'[\w-]+', 'laser_beam', SUCCEED, 'found', 'laser_beam'), 529 # bug 123769+127259: non-greedy backtracking bug 530 (r'.*?\S *:', 'xx:', SUCCEED, 'found', 'xx:'), 531 (r'a[ ]*?\ (\d+).*', 'a 10', SUCCEED, 'found', 'a 10'), 532 (r'a[ ]*?\ (\d+).*', 'a 10', SUCCEED, 'found', 'a 10'), 533 # bug 127259: \Z shouldn't depend on multiline mode 534 (r'(?ms).*?x\s*\Z(.*)','xx\nx\n', SUCCEED, 'g1', ''), 535 # bug 128899: uppercase literals under the ignorecase flag 536 (r'(?i)M+', 'MMM', SUCCEED, 'found', 'MMM'), 537 (r'(?i)m+', 'MMM', SUCCEED, 'found', 'MMM'), 538 (r'(?i)[M]+', 'MMM', SUCCEED, 'found', 'MMM'), 539 (r'(?i)[m]+', 'MMM', SUCCEED, 'found', 'MMM'), 540 # bug 130748: ^* should be an error (nothing to repeat) 541 (r'^*', '', SYNTAX_ERROR), 542 # bug 133283: minimizing repeat problem 543 (r'"(?:\\"|[^"])*?"', r'"\""', SUCCEED, 'found', r'"\""'), 544 # bug 477728: minimizing repeat problem 545 (r'^.*?$', 'one\ntwo\nthree\n', FAIL), 546 # bug 483789: minimizing repeat problem 547 (r'a[^>]*?b', 'a>b', FAIL), 548 # bug 490573: minimizing repeat problem 549 (r'^a*?$', 'foo', FAIL), 550 # bug 470582: nested groups problem 551 (r'^((a)c)?(ab)$', 'ab', SUCCEED, 'g1+"-"+g2+"-"+g3', 'None-None-ab'), 552 # another minimizing repeat problem (capturing groups in assertions) 553 ('^([ab]*?)(?=(b)?)c', 'abc', SUCCEED, 'g1+"-"+g2', 'ab-None'), 554 ('^([ab]*?)(?!(b))c', 'abc', SUCCEED, 'g1+"-"+g2', 'ab-None'), 555 ('^([ab]*?)(?<!(a))c', 'abc', SUCCEED, 'g1+"-"+g2', 'ab-None'), 556] 557 558u = '\N{LATIN CAPITAL LETTER A WITH DIAERESIS}' 559tests.extend([ 560 # bug 410271: \b broken under locales 561 (r'\b.\b', 'a', SUCCEED, 'found', 'a'), 562 (r'(?u)\b.\b', u, SUCCEED, 'found', u), 563 (r'(?u)\w', u, SUCCEED, 'found', u), 564]) 565