| 1 | n/a | #!/usr/bin/env python3 |
|---|
| 2 | n/a | # -*- mode: python -*- |
|---|
| 3 | n/a | |
|---|
| 4 | n/a | # Re test suite and benchmark suite v1.5 |
|---|
| 5 | n/a | |
|---|
| 6 | n/a | # The 3 possible outcomes for each pattern |
|---|
| 7 | n/a | [SUCCEED, FAIL, SYNTAX_ERROR] = range(3) |
|---|
| 8 | n/a | |
|---|
| 9 | n/a | # Benchmark suite (needs expansion) |
|---|
| 10 | n/a | # |
|---|
| 11 | n/a | # The benchmark suite does not test correctness, just speed. The |
|---|
| 12 | n/a | # first element of each tuple is the regex pattern; the second is a |
|---|
| 13 | n/a | # string to match it against. The benchmarking code will embed the |
|---|
| 14 | n/a | # second string inside several sizes of padding, to test how regex |
|---|
| 15 | n/a | # matching performs on large strings. |
|---|
| 16 | n/a | |
|---|
| 17 | n/a | benchmarks = [ |
|---|
| 18 | n/a | |
|---|
| 19 | n/a | # test common prefix |
|---|
| 20 | n/a | ('Python|Perl', 'Perl'), # Alternation |
|---|
| 21 | n/a | ('(Python|Perl)', 'Perl'), # Grouped alternation |
|---|
| 22 | n/a | |
|---|
| 23 | n/a | ('Python|Perl|Tcl', 'Perl'), # Alternation |
|---|
| 24 | n/a | ('(Python|Perl|Tcl)', 'Perl'), # Grouped alternation |
|---|
| 25 | n/a | |
|---|
| 26 | n/a | ('(Python)\\1', 'PythonPython'), # Backreference |
|---|
| 27 | n/a | ('([0a-z][a-z0-9]*,)+', 'a5,b7,c9,'), # Disable the fastmap optimization |
|---|
| 28 | n/a | ('([a-z][a-z0-9]*,)+', 'a5,b7,c9,'), # A few sets |
|---|
| 29 | n/a | |
|---|
| 30 | n/a | ('Python', 'Python'), # Simple text literal |
|---|
| 31 | n/a | ('.*Python', 'Python'), # Bad text literal |
|---|
| 32 | n/a | ('.*Python.*', 'Python'), # Worse text literal |
|---|
| 33 | n/a | ('.*(Python)', 'Python'), # Bad text literal with grouping |
|---|
| 34 | n/a | |
|---|
| 35 | n/a | ] |
|---|
| 36 | n/a | |
|---|
| 37 | n/a | # Test suite (for verifying correctness) |
|---|
| 38 | n/a | # |
|---|
| 39 | n/a | # The test suite is a list of 5- or 3-tuples. The 5 parts of a |
|---|
| 40 | n/a | # complete tuple are: |
|---|
| 41 | n/a | # element 0: a string containing the pattern |
|---|
| 42 | n/a | # 1: the string to match against the pattern |
|---|
| 43 | n/a | # 2: the expected result (SUCCEED, FAIL, SYNTAX_ERROR) |
|---|
| 44 | n/a | # 3: a string that will be eval()'ed to produce a test string. |
|---|
| 45 | n/a | # This is an arbitrary Python expression; the available |
|---|
| 46 | n/a | # variables are "found" (the whole match), and "g1", "g2", ... |
|---|
| 47 | n/a | # up to "g99" contain the contents of each group, or the |
|---|
| 48 | n/a | # string 'None' if the group wasn't given a value, or the |
|---|
| 49 | n/a | # string 'Error' if the group index was out of range; |
|---|
| 50 | n/a | # also "groups", the return value of m.group() (a tuple). |
|---|
| 51 | n/a | # 4: The expected result of evaluating the expression. |
|---|
| 52 | n/a | # If the two don't match, an error is reported. |
|---|
| 53 | n/a | # |
|---|
| 54 | n/a | # If the regex isn't expected to work, the latter two elements can be omitted. |
|---|
| 55 | n/a | |
|---|
| 56 | n/a | tests = [ |
|---|
| 57 | n/a | # Test ?P< and ?P= extensions |
|---|
| 58 | n/a | ('(?P<foo_123', '', SYNTAX_ERROR), # Unterminated group identifier |
|---|
| 59 | n/a | ('(?P<1>a)', '', SYNTAX_ERROR), # Begins with a digit |
|---|
| 60 | n/a | ('(?P<!>a)', '', SYNTAX_ERROR), # Begins with an illegal char |
|---|
| 61 | n/a | ('(?P<foo!>a)', '', SYNTAX_ERROR), # Begins with an illegal char |
|---|
| 62 | n/a | |
|---|
| 63 | n/a | # Same tests, for the ?P= form |
|---|
| 64 | n/a | ('(?P<foo_123>a)(?P=foo_123', 'aa', SYNTAX_ERROR), |
|---|
| 65 | n/a | ('(?P<foo_123>a)(?P=1)', 'aa', SYNTAX_ERROR), |
|---|
| 66 | n/a | ('(?P<foo_123>a)(?P=!)', 'aa', SYNTAX_ERROR), |
|---|
| 67 | n/a | ('(?P<foo_123>a)(?P=foo_124', 'aa', SYNTAX_ERROR), # Backref to undefined group |
|---|
| 68 | n/a | |
|---|
| 69 | n/a | ('(?P<foo_123>a)', 'a', SUCCEED, 'g1', 'a'), |
|---|
| 70 | n/a | ('(?P<foo_123>a)(?P=foo_123)', 'aa', SUCCEED, 'g1', 'a'), |
|---|
| 71 | n/a | |
|---|
| 72 | n/a | # Test octal escapes |
|---|
| 73 | n/a | ('\\1', 'a', SYNTAX_ERROR), # Backreference |
|---|
| 74 | n/a | ('[\\1]', '\1', SUCCEED, 'found', '\1'), # Character |
|---|
| 75 | n/a | ('\\09', chr(0) + '9', SUCCEED, 'found', chr(0) + '9'), |
|---|
| 76 | n/a | ('\\141', 'a', SUCCEED, 'found', 'a'), |
|---|
| 77 | n/a | ('(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)\\119', 'abcdefghijklk9', SUCCEED, 'found+"-"+g11', 'abcdefghijklk9-k'), |
|---|
| 78 | n/a | |
|---|
| 79 | n/a | # Test \0 is handled everywhere |
|---|
| 80 | n/a | (r'\0', '\0', SUCCEED, 'found', '\0'), |
|---|
| 81 | n/a | (r'[\0a]', '\0', SUCCEED, 'found', '\0'), |
|---|
| 82 | n/a | (r'[a\0]', '\0', SUCCEED, 'found', '\0'), |
|---|
| 83 | n/a | (r'[^a\0]', '\0', FAIL), |
|---|
| 84 | n/a | |
|---|
| 85 | n/a | # Test various letter escapes |
|---|
| 86 | n/a | (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 | n/a | (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 | n/a | # NOTE: not an error under PCRE/PRE: |
|---|
| 89 | n/a | (r'\u', '', SYNTAX_ERROR), # A Perl escape |
|---|
| 90 | n/a | # (r'\c\e\g\h\i\j\k\m\o\p\q\y\z', 'ceghijkmopqyz', SUCCEED, 'found', 'ceghijkmopqyz'), |
|---|
| 91 | n/a | (r'\xff', '\377', SUCCEED, 'found', chr(255)), |
|---|
| 92 | n/a | # new \x semantics |
|---|
| 93 | n/a | (r'\x00ffffffffffffff', '\377', FAIL, 'found', chr(255)), |
|---|
| 94 | n/a | (r'\x00f', '\017', FAIL, 'found', chr(15)), |
|---|
| 95 | n/a | (r'\x00fe', '\376', FAIL, 'found', chr(254)), |
|---|
| 96 | n/a | # (r'\x00ffffffffffffff', '\377', SUCCEED, 'found', chr(255)), |
|---|
| 97 | n/a | # (r'\x00f', '\017', SUCCEED, 'found', chr(15)), |
|---|
| 98 | n/a | # (r'\x00fe', '\376', SUCCEED, 'found', chr(254)), |
|---|
| 99 | n/a | |
|---|
| 100 | n/a | (r"^\w+=(\\[\000-\277]|[^\n\\])*", "SRC=eval.c g.c blah blah blah \\\\\n\tapes.c", |
|---|
| 101 | n/a | SUCCEED, 'found', "SRC=eval.c g.c blah blah blah \\\\"), |
|---|
| 102 | n/a | |
|---|
| 103 | n/a | # Test that . only matches \n in DOTALL mode |
|---|
| 104 | n/a | ('a.b', 'acb', SUCCEED, 'found', 'acb'), |
|---|
| 105 | n/a | ('a.b', 'a\nb', FAIL), |
|---|
| 106 | n/a | ('a.*b', 'acc\nccb', FAIL), |
|---|
| 107 | n/a | ('a.{4,5}b', 'acc\nccb', FAIL), |
|---|
| 108 | n/a | ('a.b', 'a\rb', SUCCEED, 'found', 'a\rb'), |
|---|
| 109 | n/a | ('(?s)a.b', 'a\nb', SUCCEED, 'found', 'a\nb'), |
|---|
| 110 | n/a | ('(?s)a.*b', 'acc\nccb', SUCCEED, 'found', 'acc\nccb'), |
|---|
| 111 | n/a | ('(?s)a.{4,5}b', 'acc\nccb', SUCCEED, 'found', 'acc\nccb'), |
|---|
| 112 | n/a | ('(?s)a.b', 'a\nb', SUCCEED, 'found', 'a\nb'), |
|---|
| 113 | n/a | |
|---|
| 114 | n/a | (')', '', SYNTAX_ERROR), # Unmatched right bracket |
|---|
| 115 | n/a | ('', '', SUCCEED, 'found', ''), # Empty pattern |
|---|
| 116 | n/a | ('abc', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 117 | n/a | ('abc', 'xbc', FAIL), |
|---|
| 118 | n/a | ('abc', 'axc', FAIL), |
|---|
| 119 | n/a | ('abc', 'abx', FAIL), |
|---|
| 120 | n/a | ('abc', 'xabcy', SUCCEED, 'found', 'abc'), |
|---|
| 121 | n/a | ('abc', 'ababc', SUCCEED, 'found', 'abc'), |
|---|
| 122 | n/a | ('ab*c', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 123 | n/a | ('ab*bc', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 124 | n/a | ('ab*bc', 'abbc', SUCCEED, 'found', 'abbc'), |
|---|
| 125 | n/a | ('ab*bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), |
|---|
| 126 | n/a | ('ab+bc', 'abbc', SUCCEED, 'found', 'abbc'), |
|---|
| 127 | n/a | ('ab+bc', 'abc', FAIL), |
|---|
| 128 | n/a | ('ab+bc', 'abq', FAIL), |
|---|
| 129 | n/a | ('ab+bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), |
|---|
| 130 | n/a | ('ab?bc', 'abbc', SUCCEED, 'found', 'abbc'), |
|---|
| 131 | n/a | ('ab?bc', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 132 | n/a | ('ab?bc', 'abbbbc', FAIL), |
|---|
| 133 | n/a | ('ab?c', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 134 | n/a | ('^abc$', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 135 | n/a | ('^abc$', 'abcc', FAIL), |
|---|
| 136 | n/a | ('^abc', 'abcc', SUCCEED, 'found', 'abc'), |
|---|
| 137 | n/a | ('^abc$', 'aabc', FAIL), |
|---|
| 138 | n/a | ('abc$', 'aabc', SUCCEED, 'found', 'abc'), |
|---|
| 139 | n/a | ('^', 'abc', SUCCEED, 'found+"-"', '-'), |
|---|
| 140 | n/a | ('$', 'abc', SUCCEED, 'found+"-"', '-'), |
|---|
| 141 | n/a | ('a.c', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 142 | n/a | ('a.c', 'axc', SUCCEED, 'found', 'axc'), |
|---|
| 143 | n/a | ('a.*c', 'axyzc', SUCCEED, 'found', 'axyzc'), |
|---|
| 144 | n/a | ('a.*c', 'axyzd', FAIL), |
|---|
| 145 | n/a | ('a[bc]d', 'abc', FAIL), |
|---|
| 146 | n/a | ('a[bc]d', 'abd', SUCCEED, 'found', 'abd'), |
|---|
| 147 | n/a | ('a[b-d]e', 'abd', FAIL), |
|---|
| 148 | n/a | ('a[b-d]e', 'ace', SUCCEED, 'found', 'ace'), |
|---|
| 149 | n/a | ('a[b-d]', 'aac', SUCCEED, 'found', 'ac'), |
|---|
| 150 | n/a | ('a[-b]', 'a-', SUCCEED, 'found', 'a-'), |
|---|
| 151 | n/a | ('a[\\-b]', 'a-', SUCCEED, 'found', 'a-'), |
|---|
| 152 | n/a | # NOTE: not an error under PCRE/PRE: |
|---|
| 153 | n/a | # ('a[b-]', 'a-', SYNTAX_ERROR), |
|---|
| 154 | n/a | ('a[]b', '-', SYNTAX_ERROR), |
|---|
| 155 | n/a | ('a[', '-', SYNTAX_ERROR), |
|---|
| 156 | n/a | ('a\\', '-', SYNTAX_ERROR), |
|---|
| 157 | n/a | ('abc)', '-', SYNTAX_ERROR), |
|---|
| 158 | n/a | ('(abc', '-', SYNTAX_ERROR), |
|---|
| 159 | n/a | ('a]', 'a]', SUCCEED, 'found', 'a]'), |
|---|
| 160 | n/a | ('a[]]b', 'a]b', SUCCEED, 'found', 'a]b'), |
|---|
| 161 | n/a | ('a[\\]]b', 'a]b', SUCCEED, 'found', 'a]b'), |
|---|
| 162 | n/a | ('a[^bc]d', 'aed', SUCCEED, 'found', 'aed'), |
|---|
| 163 | n/a | ('a[^bc]d', 'abd', FAIL), |
|---|
| 164 | n/a | ('a[^-b]c', 'adc', SUCCEED, 'found', 'adc'), |
|---|
| 165 | n/a | ('a[^-b]c', 'a-c', FAIL), |
|---|
| 166 | n/a | ('a[^]b]c', 'a]c', FAIL), |
|---|
| 167 | n/a | ('a[^]b]c', 'adc', SUCCEED, 'found', 'adc'), |
|---|
| 168 | n/a | ('\\ba\\b', 'a-', SUCCEED, '"-"', '-'), |
|---|
| 169 | n/a | ('\\ba\\b', '-a', SUCCEED, '"-"', '-'), |
|---|
| 170 | n/a | ('\\ba\\b', '-a-', SUCCEED, '"-"', '-'), |
|---|
| 171 | n/a | ('\\by\\b', 'xy', FAIL), |
|---|
| 172 | n/a | ('\\by\\b', 'yz', FAIL), |
|---|
| 173 | n/a | ('\\by\\b', 'xyz', FAIL), |
|---|
| 174 | n/a | ('x\\b', 'xyz', FAIL), |
|---|
| 175 | n/a | ('x\\B', 'xyz', SUCCEED, '"-"', '-'), |
|---|
| 176 | n/a | ('\\Bz', 'xyz', SUCCEED, '"-"', '-'), |
|---|
| 177 | n/a | ('z\\B', 'xyz', FAIL), |
|---|
| 178 | n/a | ('\\Bx', 'xyz', FAIL), |
|---|
| 179 | n/a | ('\\Ba\\B', 'a-', FAIL, '"-"', '-'), |
|---|
| 180 | n/a | ('\\Ba\\B', '-a', FAIL, '"-"', '-'), |
|---|
| 181 | n/a | ('\\Ba\\B', '-a-', FAIL, '"-"', '-'), |
|---|
| 182 | n/a | ('\\By\\B', 'xy', FAIL), |
|---|
| 183 | n/a | ('\\By\\B', 'yz', FAIL), |
|---|
| 184 | n/a | ('\\By\\b', 'xy', SUCCEED, '"-"', '-'), |
|---|
| 185 | n/a | ('\\by\\B', 'yz', SUCCEED, '"-"', '-'), |
|---|
| 186 | n/a | ('\\By\\B', 'xyz', SUCCEED, '"-"', '-'), |
|---|
| 187 | n/a | ('ab|cd', 'abc', SUCCEED, 'found', 'ab'), |
|---|
| 188 | n/a | ('ab|cd', 'abcd', SUCCEED, 'found', 'ab'), |
|---|
| 189 | n/a | ('()ef', 'def', SUCCEED, 'found+"-"+g1', 'ef-'), |
|---|
| 190 | n/a | ('$b', 'b', FAIL), |
|---|
| 191 | n/a | ('a\\(b', 'a(b', SUCCEED, 'found+"-"+g1', 'a(b-Error'), |
|---|
| 192 | n/a | ('a\\(*b', 'ab', SUCCEED, 'found', 'ab'), |
|---|
| 193 | n/a | ('a\\(*b', 'a((b', SUCCEED, 'found', 'a((b'), |
|---|
| 194 | n/a | ('a\\\\b', 'a\\b', SUCCEED, 'found', 'a\\b'), |
|---|
| 195 | n/a | ('((a))', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'a-a-a'), |
|---|
| 196 | n/a | ('(a)b(c)', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'abc-a-c'), |
|---|
| 197 | n/a | ('a+b+c', 'aabbabc', SUCCEED, 'found', 'abc'), |
|---|
| 198 | n/a | ('(a+|b)*', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), |
|---|
| 199 | n/a | ('(a+|b)+', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), |
|---|
| 200 | n/a | ('(a+|b)?', 'ab', SUCCEED, 'found+"-"+g1', 'a-a'), |
|---|
| 201 | n/a | (')(', '-', SYNTAX_ERROR), |
|---|
| 202 | n/a | ('[^ab]*', 'cde', SUCCEED, 'found', 'cde'), |
|---|
| 203 | n/a | ('abc', '', FAIL), |
|---|
| 204 | n/a | ('a*', '', SUCCEED, 'found', ''), |
|---|
| 205 | n/a | ('a|b|c|d|e', 'e', SUCCEED, 'found', 'e'), |
|---|
| 206 | n/a | ('(a|b|c|d|e)f', 'ef', SUCCEED, 'found+"-"+g1', 'ef-e'), |
|---|
| 207 | n/a | ('abcd*efg', 'abcdefg', SUCCEED, 'found', 'abcdefg'), |
|---|
| 208 | n/a | ('ab*', 'xabyabbbz', SUCCEED, 'found', 'ab'), |
|---|
| 209 | n/a | ('ab*', 'xayabbbz', SUCCEED, 'found', 'a'), |
|---|
| 210 | n/a | ('(ab|cd)e', 'abcde', SUCCEED, 'found+"-"+g1', 'cde-cd'), |
|---|
| 211 | n/a | ('[abhgefdc]ij', 'hij', SUCCEED, 'found', 'hij'), |
|---|
| 212 | n/a | ('^(ab|cd)e', 'abcde', FAIL, 'xg1y', 'xy'), |
|---|
| 213 | n/a | ('(abc|)ef', 'abcdef', SUCCEED, 'found+"-"+g1', 'ef-'), |
|---|
| 214 | n/a | ('(a|b)c*d', 'abcd', SUCCEED, 'found+"-"+g1', 'bcd-b'), |
|---|
| 215 | n/a | ('(ab|ab*)bc', 'abc', SUCCEED, 'found+"-"+g1', 'abc-a'), |
|---|
| 216 | n/a | ('a([bc]*)c*', 'abc', SUCCEED, 'found+"-"+g1', 'abc-bc'), |
|---|
| 217 | n/a | ('a([bc]*)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'), |
|---|
| 218 | n/a | ('a([bc]+)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'), |
|---|
| 219 | n/a | ('a([bc]*)(c+d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-b-cd'), |
|---|
| 220 | n/a | ('a[bcd]*dcdcde', 'adcdcde', SUCCEED, 'found', 'adcdcde'), |
|---|
| 221 | n/a | ('a[bcd]+dcdcde', 'adcdcde', FAIL), |
|---|
| 222 | n/a | ('(ab|a)b*c', 'abc', SUCCEED, 'found+"-"+g1', 'abc-ab'), |
|---|
| 223 | n/a | ('((a)(b)c)(d)', 'abcd', SUCCEED, 'g1+"-"+g2+"-"+g3+"-"+g4', 'abc-a-b-d'), |
|---|
| 224 | n/a | ('[a-zA-Z_][a-zA-Z0-9_]*', 'alpha', SUCCEED, 'found', 'alpha'), |
|---|
| 225 | n/a | ('^a(bc+|b[eh])g|.h$', 'abh', SUCCEED, 'found+"-"+g1', 'bh-None'), |
|---|
| 226 | n/a | ('(bc+d$|ef*g.|h?i(j|k))', 'effgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'), |
|---|
| 227 | n/a | ('(bc+d$|ef*g.|h?i(j|k))', 'ij', SUCCEED, 'found+"-"+g1+"-"+g2', 'ij-ij-j'), |
|---|
| 228 | n/a | ('(bc+d$|ef*g.|h?i(j|k))', 'effg', FAIL), |
|---|
| 229 | n/a | ('(bc+d$|ef*g.|h?i(j|k))', 'bcdd', FAIL), |
|---|
| 230 | n/a | ('(bc+d$|ef*g.|h?i(j|k))', 'reffgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'), |
|---|
| 231 | n/a | ('(((((((((a)))))))))', 'a', SUCCEED, 'found', 'a'), |
|---|
| 232 | n/a | ('multiple words of text', 'uh-uh', FAIL), |
|---|
| 233 | n/a | ('multiple words', 'multiple words, yeah', SUCCEED, 'found', 'multiple words'), |
|---|
| 234 | n/a | ('(.*)c(.*)', 'abcde', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcde-ab-de'), |
|---|
| 235 | n/a | ('\\((.*), (.*)\\)', '(a, b)', SUCCEED, 'g2+"-"+g1', 'b-a'), |
|---|
| 236 | n/a | ('[k]', 'ab', FAIL), |
|---|
| 237 | n/a | ('a[-]?c', 'ac', SUCCEED, 'found', 'ac'), |
|---|
| 238 | n/a | ('(abc)\\1', 'abcabc', SUCCEED, 'g1', 'abc'), |
|---|
| 239 | n/a | ('([a-c]*)\\1', 'abcabc', SUCCEED, 'g1', 'abc'), |
|---|
| 240 | n/a | ('^(.+)?B', 'AB', SUCCEED, 'g1', 'A'), |
|---|
| 241 | n/a | ('(a+).\\1$', 'aaaaa', SUCCEED, 'found+"-"+g1', 'aaaaa-aa'), |
|---|
| 242 | n/a | ('^(a+).\\1$', 'aaaa', FAIL), |
|---|
| 243 | n/a | ('(abc)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'), |
|---|
| 244 | n/a | ('([a-c]+)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'), |
|---|
| 245 | n/a | ('(a)\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'), |
|---|
| 246 | n/a | ('(a+)\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'), |
|---|
| 247 | n/a | ('(a+)+\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'), |
|---|
| 248 | n/a | ('(a).+\\1', 'aba', SUCCEED, 'found+"-"+g1', 'aba-a'), |
|---|
| 249 | n/a | ('(a)ba*\\1', 'aba', SUCCEED, 'found+"-"+g1', 'aba-a'), |
|---|
| 250 | n/a | ('(aa|a)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'), |
|---|
| 251 | n/a | ('(a|aa)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'), |
|---|
| 252 | n/a | ('(a+)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'), |
|---|
| 253 | n/a | ('([abc]*)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'), |
|---|
| 254 | n/a | ('(a)(b)c|ab', 'ab', SUCCEED, 'found+"-"+g1+"-"+g2', 'ab-None-None'), |
|---|
| 255 | n/a | ('(a)+x', 'aaax', SUCCEED, 'found+"-"+g1', 'aaax-a'), |
|---|
| 256 | n/a | ('([ac])+x', 'aacx', SUCCEED, 'found+"-"+g1', 'aacx-c'), |
|---|
| 257 | n/a | ('([^/]*/)*sub1/', 'd:msgs/tdir/sub1/trial/away.cpp', SUCCEED, 'found+"-"+g1', 'd:msgs/tdir/sub1/-tdir/'), |
|---|
| 258 | n/a | ('([^.]*)\\.([^:]*):[T ]+(.*)', 'track1.title:TBlah blah blah', SUCCEED, 'found+"-"+g1+"-"+g2+"-"+g3', 'track1.title:TBlah blah blah-track1-title-Blah blah blah'), |
|---|
| 259 | n/a | ('([^N]*N)+', 'abNNxyzN', SUCCEED, 'found+"-"+g1', 'abNNxyzN-xyzN'), |
|---|
| 260 | n/a | ('([^N]*N)+', 'abNNxyz', SUCCEED, 'found+"-"+g1', 'abNN-N'), |
|---|
| 261 | n/a | ('([abc]*)x', 'abcx', SUCCEED, 'found+"-"+g1', 'abcx-abc'), |
|---|
| 262 | n/a | ('([abc]*)x', 'abc', FAIL), |
|---|
| 263 | n/a | ('([xyz]*)x', 'abcx', SUCCEED, 'found+"-"+g1', 'x-'), |
|---|
| 264 | n/a | ('(a)+b|aac', 'aac', SUCCEED, 'found+"-"+g1', 'aac-None'), |
|---|
| 265 | n/a | |
|---|
| 266 | n/a | # Test symbolic groups |
|---|
| 267 | n/a | |
|---|
| 268 | n/a | ('(?P<i d>aaa)a', 'aaaa', SYNTAX_ERROR), |
|---|
| 269 | n/a | ('(?P<id>aaa)a', 'aaaa', SUCCEED, 'found+"-"+id', 'aaaa-aaa'), |
|---|
| 270 | n/a | ('(?P<id>aa)(?P=id)', 'aaaa', SUCCEED, 'found+"-"+id', 'aaaa-aa'), |
|---|
| 271 | n/a | ('(?P<id>aa)(?P=xd)', 'aaaa', SYNTAX_ERROR), |
|---|
| 272 | n/a | |
|---|
| 273 | n/a | # Test octal escapes/memory references |
|---|
| 274 | n/a | |
|---|
| 275 | n/a | ('\\1', 'a', SYNTAX_ERROR), |
|---|
| 276 | n/a | ('\\09', chr(0) + '9', SUCCEED, 'found', chr(0) + '9'), |
|---|
| 277 | n/a | ('\\141', 'a', SUCCEED, 'found', 'a'), |
|---|
| 278 | n/a | ('(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)\\119', 'abcdefghijklk9', SUCCEED, 'found+"-"+g11', 'abcdefghijklk9-k'), |
|---|
| 279 | n/a | |
|---|
| 280 | n/a | # All tests from Perl |
|---|
| 281 | n/a | |
|---|
| 282 | n/a | ('abc', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 283 | n/a | ('abc', 'xbc', FAIL), |
|---|
| 284 | n/a | ('abc', 'axc', FAIL), |
|---|
| 285 | n/a | ('abc', 'abx', FAIL), |
|---|
| 286 | n/a | ('abc', 'xabcy', SUCCEED, 'found', 'abc'), |
|---|
| 287 | n/a | ('abc', 'ababc', SUCCEED, 'found', 'abc'), |
|---|
| 288 | n/a | ('ab*c', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 289 | n/a | ('ab*bc', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 290 | n/a | ('ab*bc', 'abbc', SUCCEED, 'found', 'abbc'), |
|---|
| 291 | n/a | ('ab*bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), |
|---|
| 292 | n/a | ('ab{0,}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), |
|---|
| 293 | n/a | ('ab+bc', 'abbc', SUCCEED, 'found', 'abbc'), |
|---|
| 294 | n/a | ('ab+bc', 'abc', FAIL), |
|---|
| 295 | n/a | ('ab+bc', 'abq', FAIL), |
|---|
| 296 | n/a | ('ab{1,}bc', 'abq', FAIL), |
|---|
| 297 | n/a | ('ab+bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), |
|---|
| 298 | n/a | ('ab{1,}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), |
|---|
| 299 | n/a | ('ab{1,3}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), |
|---|
| 300 | n/a | ('ab{3,4}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), |
|---|
| 301 | n/a | ('ab{4,5}bc', 'abbbbc', FAIL), |
|---|
| 302 | n/a | ('ab?bc', 'abbc', SUCCEED, 'found', 'abbc'), |
|---|
| 303 | n/a | ('ab?bc', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 304 | n/a | ('ab{0,1}bc', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 305 | n/a | ('ab?bc', 'abbbbc', FAIL), |
|---|
| 306 | n/a | ('ab?c', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 307 | n/a | ('ab{0,1}c', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 308 | n/a | ('^abc$', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 309 | n/a | ('^abc$', 'abcc', FAIL), |
|---|
| 310 | n/a | ('^abc', 'abcc', SUCCEED, 'found', 'abc'), |
|---|
| 311 | n/a | ('^abc$', 'aabc', FAIL), |
|---|
| 312 | n/a | ('abc$', 'aabc', SUCCEED, 'found', 'abc'), |
|---|
| 313 | n/a | ('^', 'abc', SUCCEED, 'found', ''), |
|---|
| 314 | n/a | ('$', 'abc', SUCCEED, 'found', ''), |
|---|
| 315 | n/a | ('a.c', 'abc', SUCCEED, 'found', 'abc'), |
|---|
| 316 | n/a | ('a.c', 'axc', SUCCEED, 'found', 'axc'), |
|---|
| 317 | n/a | ('a.*c', 'axyzc', SUCCEED, 'found', 'axyzc'), |
|---|
| 318 | n/a | ('a.*c', 'axyzd', FAIL), |
|---|
| 319 | n/a | ('a[bc]d', 'abc', FAIL), |
|---|
| 320 | n/a | ('a[bc]d', 'abd', SUCCEED, 'found', 'abd'), |
|---|
| 321 | n/a | ('a[b-d]e', 'abd', FAIL), |
|---|
| 322 | n/a | ('a[b-d]e', 'ace', SUCCEED, 'found', 'ace'), |
|---|
| 323 | n/a | ('a[b-d]', 'aac', SUCCEED, 'found', 'ac'), |
|---|
| 324 | n/a | ('a[-b]', 'a-', SUCCEED, 'found', 'a-'), |
|---|
| 325 | n/a | ('a[b-]', 'a-', SUCCEED, 'found', 'a-'), |
|---|
| 326 | n/a | ('a[b-a]', '-', SYNTAX_ERROR), |
|---|
| 327 | n/a | ('a[]b', '-', SYNTAX_ERROR), |
|---|
| 328 | n/a | ('a[', '-', SYNTAX_ERROR), |
|---|
| 329 | n/a | ('a]', 'a]', SUCCEED, 'found', 'a]'), |
|---|
| 330 | n/a | ('a[]]b', 'a]b', SUCCEED, 'found', 'a]b'), |
|---|
| 331 | n/a | ('a[^bc]d', 'aed', SUCCEED, 'found', 'aed'), |
|---|
| 332 | n/a | ('a[^bc]d', 'abd', FAIL), |
|---|
| 333 | n/a | ('a[^-b]c', 'adc', SUCCEED, 'found', 'adc'), |
|---|
| 334 | n/a | ('a[^-b]c', 'a-c', FAIL), |
|---|
| 335 | n/a | ('a[^]b]c', 'a]c', FAIL), |
|---|
| 336 | n/a | ('a[^]b]c', 'adc', SUCCEED, 'found', 'adc'), |
|---|
| 337 | n/a | ('ab|cd', 'abc', SUCCEED, 'found', 'ab'), |
|---|
| 338 | n/a | ('ab|cd', 'abcd', SUCCEED, 'found', 'ab'), |
|---|
| 339 | n/a | ('()ef', 'def', SUCCEED, 'found+"-"+g1', 'ef-'), |
|---|
| 340 | n/a | ('*a', '-', SYNTAX_ERROR), |
|---|
| 341 | n/a | ('(*)b', '-', SYNTAX_ERROR), |
|---|
| 342 | n/a | ('$b', 'b', FAIL), |
|---|
| 343 | n/a | ('a\\', '-', SYNTAX_ERROR), |
|---|
| 344 | n/a | ('a\\(b', 'a(b', SUCCEED, 'found+"-"+g1', 'a(b-Error'), |
|---|
| 345 | n/a | ('a\\(*b', 'ab', SUCCEED, 'found', 'ab'), |
|---|
| 346 | n/a | ('a\\(*b', 'a((b', SUCCEED, 'found', 'a((b'), |
|---|
| 347 | n/a | ('a\\\\b', 'a\\b', SUCCEED, 'found', 'a\\b'), |
|---|
| 348 | n/a | ('abc)', '-', SYNTAX_ERROR), |
|---|
| 349 | n/a | ('(abc', '-', SYNTAX_ERROR), |
|---|
| 350 | n/a | ('((a))', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'a-a-a'), |
|---|
| 351 | n/a | ('(a)b(c)', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'abc-a-c'), |
|---|
| 352 | n/a | ('a+b+c', 'aabbabc', SUCCEED, 'found', 'abc'), |
|---|
| 353 | n/a | ('a{1,}b{1,}c', 'aabbabc', SUCCEED, 'found', 'abc'), |
|---|
| 354 | n/a | ('a**', '-', SYNTAX_ERROR), |
|---|
| 355 | n/a | ('a.+?c', 'abcabc', SUCCEED, 'found', 'abc'), |
|---|
| 356 | n/a | ('(a+|b)*', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), |
|---|
| 357 | n/a | ('(a+|b){0,}', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), |
|---|
| 358 | n/a | ('(a+|b)+', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), |
|---|
| 359 | n/a | ('(a+|b){1,}', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), |
|---|
| 360 | n/a | ('(a+|b)?', 'ab', SUCCEED, 'found+"-"+g1', 'a-a'), |
|---|
| 361 | n/a | ('(a+|b){0,1}', 'ab', SUCCEED, 'found+"-"+g1', 'a-a'), |
|---|
| 362 | n/a | (')(', '-', SYNTAX_ERROR), |
|---|
| 363 | n/a | ('[^ab]*', 'cde', SUCCEED, 'found', 'cde'), |
|---|
| 364 | n/a | ('abc', '', FAIL), |
|---|
| 365 | n/a | ('a*', '', SUCCEED, 'found', ''), |
|---|
| 366 | n/a | ('([abc])*d', 'abbbcd', SUCCEED, 'found+"-"+g1', 'abbbcd-c'), |
|---|
| 367 | n/a | ('([abc])*bcd', 'abcd', SUCCEED, 'found+"-"+g1', 'abcd-a'), |
|---|
| 368 | n/a | ('a|b|c|d|e', 'e', SUCCEED, 'found', 'e'), |
|---|
| 369 | n/a | ('(a|b|c|d|e)f', 'ef', SUCCEED, 'found+"-"+g1', 'ef-e'), |
|---|
| 370 | n/a | ('abcd*efg', 'abcdefg', SUCCEED, 'found', 'abcdefg'), |
|---|
| 371 | n/a | ('ab*', 'xabyabbbz', SUCCEED, 'found', 'ab'), |
|---|
| 372 | n/a | ('ab*', 'xayabbbz', SUCCEED, 'found', 'a'), |
|---|
| 373 | n/a | ('(ab|cd)e', 'abcde', SUCCEED, 'found+"-"+g1', 'cde-cd'), |
|---|
| 374 | n/a | ('[abhgefdc]ij', 'hij', SUCCEED, 'found', 'hij'), |
|---|
| 375 | n/a | ('^(ab|cd)e', 'abcde', FAIL), |
|---|
| 376 | n/a | ('(abc|)ef', 'abcdef', SUCCEED, 'found+"-"+g1', 'ef-'), |
|---|
| 377 | n/a | ('(a|b)c*d', 'abcd', SUCCEED, 'found+"-"+g1', 'bcd-b'), |
|---|
| 378 | n/a | ('(ab|ab*)bc', 'abc', SUCCEED, 'found+"-"+g1', 'abc-a'), |
|---|
| 379 | n/a | ('a([bc]*)c*', 'abc', SUCCEED, 'found+"-"+g1', 'abc-bc'), |
|---|
| 380 | n/a | ('a([bc]*)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'), |
|---|
| 381 | n/a | ('a([bc]+)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'), |
|---|
| 382 | n/a | ('a([bc]*)(c+d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-b-cd'), |
|---|
| 383 | n/a | ('a[bcd]*dcdcde', 'adcdcde', SUCCEED, 'found', 'adcdcde'), |
|---|
| 384 | n/a | ('a[bcd]+dcdcde', 'adcdcde', FAIL), |
|---|
| 385 | n/a | ('(ab|a)b*c', 'abc', SUCCEED, 'found+"-"+g1', 'abc-ab'), |
|---|
| 386 | n/a | ('((a)(b)c)(d)', 'abcd', SUCCEED, 'g1+"-"+g2+"-"+g3+"-"+g4', 'abc-a-b-d'), |
|---|
| 387 | n/a | ('[a-zA-Z_][a-zA-Z0-9_]*', 'alpha', SUCCEED, 'found', 'alpha'), |
|---|
| 388 | n/a | ('^a(bc+|b[eh])g|.h$', 'abh', SUCCEED, 'found+"-"+g1', 'bh-None'), |
|---|
| 389 | n/a | ('(bc+d$|ef*g.|h?i(j|k))', 'effgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'), |
|---|
| 390 | n/a | ('(bc+d$|ef*g.|h?i(j|k))', 'ij', SUCCEED, 'found+"-"+g1+"-"+g2', 'ij-ij-j'), |
|---|
| 391 | n/a | ('(bc+d$|ef*g.|h?i(j|k))', 'effg', FAIL), |
|---|
| 392 | n/a | ('(bc+d$|ef*g.|h?i(j|k))', 'bcdd', FAIL), |
|---|
| 393 | n/a | ('(bc+d$|ef*g.|h?i(j|k))', 'reffgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'), |
|---|
| 394 | n/a | ('((((((((((a))))))))))', 'a', SUCCEED, 'g10', 'a'), |
|---|
| 395 | n/a | ('((((((((((a))))))))))\\10', 'aa', SUCCEED, 'found', 'aa'), |
|---|
| 396 | n/a | # Python does not have the same rules for \\41 so this is a syntax error |
|---|
| 397 | n/a | # ('((((((((((a))))))))))\\41', 'aa', FAIL), |
|---|
| 398 | n/a | # ('((((((((((a))))))))))\\41', 'a!', SUCCEED, 'found', 'a!'), |
|---|
| 399 | n/a | ('((((((((((a))))))))))\\41', '', SYNTAX_ERROR), |
|---|
| 400 | n/a | ('(?i)((((((((((a))))))))))\\41', '', SYNTAX_ERROR), |
|---|
| 401 | n/a | ('(((((((((a)))))))))', 'a', SUCCEED, 'found', 'a'), |
|---|
| 402 | n/a | ('multiple words of text', 'uh-uh', FAIL), |
|---|
| 403 | n/a | ('multiple words', 'multiple words, yeah', SUCCEED, 'found', 'multiple words'), |
|---|
| 404 | n/a | ('(.*)c(.*)', 'abcde', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcde-ab-de'), |
|---|
| 405 | n/a | ('\\((.*), (.*)\\)', '(a, b)', SUCCEED, 'g2+"-"+g1', 'b-a'), |
|---|
| 406 | n/a | ('[k]', 'ab', FAIL), |
|---|
| 407 | n/a | ('a[-]?c', 'ac', SUCCEED, 'found', 'ac'), |
|---|
| 408 | n/a | ('(abc)\\1', 'abcabc', SUCCEED, 'g1', 'abc'), |
|---|
| 409 | n/a | ('([a-c]*)\\1', 'abcabc', SUCCEED, 'g1', 'abc'), |
|---|
| 410 | n/a | ('(?i)abc', 'ABC', SUCCEED, 'found', 'ABC'), |
|---|
| 411 | n/a | ('(?i)abc', 'XBC', FAIL), |
|---|
| 412 | n/a | ('(?i)abc', 'AXC', FAIL), |
|---|
| 413 | n/a | ('(?i)abc', 'ABX', FAIL), |
|---|
| 414 | n/a | ('(?i)abc', 'XABCY', SUCCEED, 'found', 'ABC'), |
|---|
| 415 | n/a | ('(?i)abc', 'ABABC', SUCCEED, 'found', 'ABC'), |
|---|
| 416 | n/a | ('(?i)ab*c', 'ABC', SUCCEED, 'found', 'ABC'), |
|---|
| 417 | n/a | ('(?i)ab*bc', 'ABC', SUCCEED, 'found', 'ABC'), |
|---|
| 418 | n/a | ('(?i)ab*bc', 'ABBC', SUCCEED, 'found', 'ABBC'), |
|---|
| 419 | n/a | ('(?i)ab*?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), |
|---|
| 420 | n/a | ('(?i)ab{0,}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), |
|---|
| 421 | n/a | ('(?i)ab+?bc', 'ABBC', SUCCEED, 'found', 'ABBC'), |
|---|
| 422 | n/a | ('(?i)ab+bc', 'ABC', FAIL), |
|---|
| 423 | n/a | ('(?i)ab+bc', 'ABQ', FAIL), |
|---|
| 424 | n/a | ('(?i)ab{1,}bc', 'ABQ', FAIL), |
|---|
| 425 | n/a | ('(?i)ab+bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), |
|---|
| 426 | n/a | ('(?i)ab{1,}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), |
|---|
| 427 | n/a | ('(?i)ab{1,3}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), |
|---|
| 428 | n/a | ('(?i)ab{3,4}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), |
|---|
| 429 | n/a | ('(?i)ab{4,5}?bc', 'ABBBBC', FAIL), |
|---|
| 430 | n/a | ('(?i)ab??bc', 'ABBC', SUCCEED, 'found', 'ABBC'), |
|---|
| 431 | n/a | ('(?i)ab??bc', 'ABC', SUCCEED, 'found', 'ABC'), |
|---|
| 432 | n/a | ('(?i)ab{0,1}?bc', 'ABC', SUCCEED, 'found', 'ABC'), |
|---|
| 433 | n/a | ('(?i)ab??bc', 'ABBBBC', FAIL), |
|---|
| 434 | n/a | ('(?i)ab??c', 'ABC', SUCCEED, 'found', 'ABC'), |
|---|
| 435 | n/a | ('(?i)ab{0,1}?c', 'ABC', SUCCEED, 'found', 'ABC'), |
|---|
| 436 | n/a | ('(?i)^abc$', 'ABC', SUCCEED, 'found', 'ABC'), |
|---|
| 437 | n/a | ('(?i)^abc$', 'ABCC', FAIL), |
|---|
| 438 | n/a | ('(?i)^abc', 'ABCC', SUCCEED, 'found', 'ABC'), |
|---|
| 439 | n/a | ('(?i)^abc$', 'AABC', FAIL), |
|---|
| 440 | n/a | ('(?i)abc$', 'AABC', SUCCEED, 'found', 'ABC'), |
|---|
| 441 | n/a | ('(?i)^', 'ABC', SUCCEED, 'found', ''), |
|---|
| 442 | n/a | ('(?i)$', 'ABC', SUCCEED, 'found', ''), |
|---|
| 443 | n/a | ('(?i)a.c', 'ABC', SUCCEED, 'found', 'ABC'), |
|---|
| 444 | n/a | ('(?i)a.c', 'AXC', SUCCEED, 'found', 'AXC'), |
|---|
| 445 | n/a | ('(?i)a.*?c', 'AXYZC', SUCCEED, 'found', 'AXYZC'), |
|---|
| 446 | n/a | ('(?i)a.*c', 'AXYZD', FAIL), |
|---|
| 447 | n/a | ('(?i)a[bc]d', 'ABC', FAIL), |
|---|
| 448 | n/a | ('(?i)a[bc]d', 'ABD', SUCCEED, 'found', 'ABD'), |
|---|
| 449 | n/a | ('(?i)a[b-d]e', 'ABD', FAIL), |
|---|
| 450 | n/a | ('(?i)a[b-d]e', 'ACE', SUCCEED, 'found', 'ACE'), |
|---|
| 451 | n/a | ('(?i)a[b-d]', 'AAC', SUCCEED, 'found', 'AC'), |
|---|
| 452 | n/a | ('(?i)a[-b]', 'A-', SUCCEED, 'found', 'A-'), |
|---|
| 453 | n/a | ('(?i)a[b-]', 'A-', SUCCEED, 'found', 'A-'), |
|---|
| 454 | n/a | ('(?i)a[b-a]', '-', SYNTAX_ERROR), |
|---|
| 455 | n/a | ('(?i)a[]b', '-', SYNTAX_ERROR), |
|---|
| 456 | n/a | ('(?i)a[', '-', SYNTAX_ERROR), |
|---|
| 457 | n/a | ('(?i)a]', 'A]', SUCCEED, 'found', 'A]'), |
|---|
| 458 | n/a | ('(?i)a[]]b', 'A]B', SUCCEED, 'found', 'A]B'), |
|---|
| 459 | n/a | ('(?i)a[^bc]d', 'AED', SUCCEED, 'found', 'AED'), |
|---|
| 460 | n/a | ('(?i)a[^bc]d', 'ABD', FAIL), |
|---|
| 461 | n/a | ('(?i)a[^-b]c', 'ADC', SUCCEED, 'found', 'ADC'), |
|---|
| 462 | n/a | ('(?i)a[^-b]c', 'A-C', FAIL), |
|---|
| 463 | n/a | ('(?i)a[^]b]c', 'A]C', FAIL), |
|---|
| 464 | n/a | ('(?i)a[^]b]c', 'ADC', SUCCEED, 'found', 'ADC'), |
|---|
| 465 | n/a | ('(?i)ab|cd', 'ABC', SUCCEED, 'found', 'AB'), |
|---|
| 466 | n/a | ('(?i)ab|cd', 'ABCD', SUCCEED, 'found', 'AB'), |
|---|
| 467 | n/a | ('(?i)()ef', 'DEF', SUCCEED, 'found+"-"+g1', 'EF-'), |
|---|
| 468 | n/a | ('(?i)*a', '-', SYNTAX_ERROR), |
|---|
| 469 | n/a | ('(?i)(*)b', '-', SYNTAX_ERROR), |
|---|
| 470 | n/a | ('(?i)$b', 'B', FAIL), |
|---|
| 471 | n/a | ('(?i)a\\', '-', SYNTAX_ERROR), |
|---|
| 472 | n/a | ('(?i)a\\(b', 'A(B', SUCCEED, 'found+"-"+g1', 'A(B-Error'), |
|---|
| 473 | n/a | ('(?i)a\\(*b', 'AB', SUCCEED, 'found', 'AB'), |
|---|
| 474 | n/a | ('(?i)a\\(*b', 'A((B', SUCCEED, 'found', 'A((B'), |
|---|
| 475 | n/a | ('(?i)a\\\\b', 'A\\B', SUCCEED, 'found', 'A\\B'), |
|---|
| 476 | n/a | ('(?i)abc)', '-', SYNTAX_ERROR), |
|---|
| 477 | n/a | ('(?i)(abc', '-', SYNTAX_ERROR), |
|---|
| 478 | n/a | ('(?i)((a))', 'ABC', SUCCEED, 'found+"-"+g1+"-"+g2', 'A-A-A'), |
|---|
| 479 | n/a | ('(?i)(a)b(c)', 'ABC', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABC-A-C'), |
|---|
| 480 | n/a | ('(?i)a+b+c', 'AABBABC', SUCCEED, 'found', 'ABC'), |
|---|
| 481 | n/a | ('(?i)a{1,}b{1,}c', 'AABBABC', SUCCEED, 'found', 'ABC'), |
|---|
| 482 | n/a | ('(?i)a**', '-', SYNTAX_ERROR), |
|---|
| 483 | n/a | ('(?i)a.+?c', 'ABCABC', SUCCEED, 'found', 'ABC'), |
|---|
| 484 | n/a | ('(?i)a.*?c', 'ABCABC', SUCCEED, 'found', 'ABC'), |
|---|
| 485 | n/a | ('(?i)a.{0,5}?c', 'ABCABC', SUCCEED, 'found', 'ABC'), |
|---|
| 486 | n/a | ('(?i)(a+|b)*', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'), |
|---|
| 487 | n/a | ('(?i)(a+|b){0,}', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'), |
|---|
| 488 | n/a | ('(?i)(a+|b)+', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'), |
|---|
| 489 | n/a | ('(?i)(a+|b){1,}', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'), |
|---|
| 490 | n/a | ('(?i)(a+|b)?', 'AB', SUCCEED, 'found+"-"+g1', 'A-A'), |
|---|
| 491 | n/a | ('(?i)(a+|b){0,1}', 'AB', SUCCEED, 'found+"-"+g1', 'A-A'), |
|---|
| 492 | n/a | ('(?i)(a+|b){0,1}?', 'AB', SUCCEED, 'found+"-"+g1', '-None'), |
|---|
| 493 | n/a | ('(?i))(', '-', SYNTAX_ERROR), |
|---|
| 494 | n/a | ('(?i)[^ab]*', 'CDE', SUCCEED, 'found', 'CDE'), |
|---|
| 495 | n/a | ('(?i)abc', '', FAIL), |
|---|
| 496 | n/a | ('(?i)a*', '', SUCCEED, 'found', ''), |
|---|
| 497 | n/a | ('(?i)([abc])*d', 'ABBBCD', SUCCEED, 'found+"-"+g1', 'ABBBCD-C'), |
|---|
| 498 | n/a | ('(?i)([abc])*bcd', 'ABCD', SUCCEED, 'found+"-"+g1', 'ABCD-A'), |
|---|
| 499 | n/a | ('(?i)a|b|c|d|e', 'E', SUCCEED, 'found', 'E'), |
|---|
| 500 | n/a | ('(?i)(a|b|c|d|e)f', 'EF', SUCCEED, 'found+"-"+g1', 'EF-E'), |
|---|
| 501 | n/a | ('(?i)abcd*efg', 'ABCDEFG', SUCCEED, 'found', 'ABCDEFG'), |
|---|
| 502 | n/a | ('(?i)ab*', 'XABYABBBZ', SUCCEED, 'found', 'AB'), |
|---|
| 503 | n/a | ('(?i)ab*', 'XAYABBBZ', SUCCEED, 'found', 'A'), |
|---|
| 504 | n/a | ('(?i)(ab|cd)e', 'ABCDE', SUCCEED, 'found+"-"+g1', 'CDE-CD'), |
|---|
| 505 | n/a | ('(?i)[abhgefdc]ij', 'HIJ', SUCCEED, 'found', 'HIJ'), |
|---|
| 506 | n/a | ('(?i)^(ab|cd)e', 'ABCDE', FAIL), |
|---|
| 507 | n/a | ('(?i)(abc|)ef', 'ABCDEF', SUCCEED, 'found+"-"+g1', 'EF-'), |
|---|
| 508 | n/a | ('(?i)(a|b)c*d', 'ABCD', SUCCEED, 'found+"-"+g1', 'BCD-B'), |
|---|
| 509 | n/a | ('(?i)(ab|ab*)bc', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-A'), |
|---|
| 510 | n/a | ('(?i)a([bc]*)c*', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-BC'), |
|---|
| 511 | n/a | ('(?i)a([bc]*)(c*d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-BC-D'), |
|---|
| 512 | n/a | ('(?i)a([bc]+)(c*d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-BC-D'), |
|---|
| 513 | n/a | ('(?i)a([bc]*)(c+d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-B-CD'), |
|---|
| 514 | n/a | ('(?i)a[bcd]*dcdcde', 'ADCDCDE', SUCCEED, 'found', 'ADCDCDE'), |
|---|
| 515 | n/a | ('(?i)a[bcd]+dcdcde', 'ADCDCDE', FAIL), |
|---|
| 516 | n/a | ('(?i)(ab|a)b*c', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-AB'), |
|---|
| 517 | n/a | ('(?i)((a)(b)c)(d)', 'ABCD', SUCCEED, 'g1+"-"+g2+"-"+g3+"-"+g4', 'ABC-A-B-D'), |
|---|
| 518 | n/a | ('(?i)[a-zA-Z_][a-zA-Z0-9_]*', 'ALPHA', SUCCEED, 'found', 'ALPHA'), |
|---|
| 519 | n/a | ('(?i)^a(bc+|b[eh])g|.h$', 'ABH', SUCCEED, 'found+"-"+g1', 'BH-None'), |
|---|
| 520 | n/a | ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'EFFGZ', SUCCEED, 'found+"-"+g1+"-"+g2', 'EFFGZ-EFFGZ-None'), |
|---|
| 521 | n/a | ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'IJ', SUCCEED, 'found+"-"+g1+"-"+g2', 'IJ-IJ-J'), |
|---|
| 522 | n/a | ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'EFFG', FAIL), |
|---|
| 523 | n/a | ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'BCDD', FAIL), |
|---|
| 524 | n/a | ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'REFFGZ', SUCCEED, 'found+"-"+g1+"-"+g2', 'EFFGZ-EFFGZ-None'), |
|---|
| 525 | n/a | ('(?i)((((((((((a))))))))))', 'A', SUCCEED, 'g10', 'A'), |
|---|
| 526 | n/a | ('(?i)((((((((((a))))))))))\\10', 'AA', SUCCEED, 'found', 'AA'), |
|---|
| 527 | n/a | #('(?i)((((((((((a))))))))))\\41', 'AA', FAIL), |
|---|
| 528 | n/a | #('(?i)((((((((((a))))))))))\\41', 'A!', SUCCEED, 'found', 'A!'), |
|---|
| 529 | n/a | ('(?i)(((((((((a)))))))))', 'A', SUCCEED, 'found', 'A'), |
|---|
| 530 | n/a | ('(?i)(?:(?:(?:(?:(?:(?:(?:(?:(?:(a))))))))))', 'A', SUCCEED, 'g1', 'A'), |
|---|
| 531 | n/a | ('(?i)(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))', 'C', SUCCEED, 'g1', 'C'), |
|---|
| 532 | n/a | ('(?i)multiple words of text', 'UH-UH', FAIL), |
|---|
| 533 | n/a | ('(?i)multiple words', 'MULTIPLE WORDS, YEAH', SUCCEED, 'found', 'MULTIPLE WORDS'), |
|---|
| 534 | n/a | ('(?i)(.*)c(.*)', 'ABCDE', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCDE-AB-DE'), |
|---|
| 535 | n/a | ('(?i)\\((.*), (.*)\\)', '(A, B)', SUCCEED, 'g2+"-"+g1', 'B-A'), |
|---|
| 536 | n/a | ('(?i)[k]', 'AB', FAIL), |
|---|
| 537 | n/a | # ('(?i)abcd', 'ABCD', SUCCEED, 'found+"-"+\\found+"-"+\\\\found', 'ABCD-$&-\\ABCD'), |
|---|
| 538 | n/a | # ('(?i)a(bc)d', 'ABCD', SUCCEED, 'g1+"-"+\\g1+"-"+\\\\g1', 'BC-$1-\\BC'), |
|---|
| 539 | n/a | ('(?i)a[-]?c', 'AC', SUCCEED, 'found', 'AC'), |
|---|
| 540 | n/a | ('(?i)(abc)\\1', 'ABCABC', SUCCEED, 'g1', 'ABC'), |
|---|
| 541 | n/a | ('(?i)([a-c]*)\\1', 'ABCABC', SUCCEED, 'g1', 'ABC'), |
|---|
| 542 | n/a | ('a(?!b).', 'abad', SUCCEED, 'found', 'ad'), |
|---|
| 543 | n/a | ('a(?=d).', 'abad', SUCCEED, 'found', 'ad'), |
|---|
| 544 | n/a | ('a(?=c|d).', 'abad', SUCCEED, 'found', 'ad'), |
|---|
| 545 | n/a | ('a(?:b|c|d)(.)', 'ace', SUCCEED, 'g1', 'e'), |
|---|
| 546 | n/a | ('a(?:b|c|d)*(.)', 'ace', SUCCEED, 'g1', 'e'), |
|---|
| 547 | n/a | ('a(?:b|c|d)+?(.)', 'ace', SUCCEED, 'g1', 'e'), |
|---|
| 548 | n/a | ('a(?:b|(c|e){1,2}?|d)+?(.)', 'ace', SUCCEED, 'g1 + g2', 'ce'), |
|---|
| 549 | n/a | ('^(.+)?B', 'AB', SUCCEED, 'g1', 'A'), |
|---|
| 550 | n/a | |
|---|
| 551 | n/a | # lookbehind: split by : but not if it is escaped by -. |
|---|
| 552 | n/a | ('(?<!-):(.*?)(?<!-):', 'a:bc-:de:f', SUCCEED, 'g1', 'bc-:de' ), |
|---|
| 553 | n/a | # escaping with \ as we know it |
|---|
| 554 | n/a | ('(?<!\\\\):(.*?)(?<!\\\\):', 'a:bc\\:de:f', SUCCEED, 'g1', 'bc\\:de' ), |
|---|
| 555 | n/a | # terminating with ' and escaping with ? as in edifact |
|---|
| 556 | n/a | ("(?<!\\?)'(.*?)(?<!\\?)'", "a'bc?'de'f", SUCCEED, 'g1', "bc?'de" ), |
|---|
| 557 | n/a | |
|---|
| 558 | n/a | # Comments using the (?#...) syntax |
|---|
| 559 | n/a | |
|---|
| 560 | n/a | ('w(?# comment', 'w', SYNTAX_ERROR), |
|---|
| 561 | n/a | ('w(?# comment 1)xy(?# comment 2)z', 'wxyz', SUCCEED, 'found', 'wxyz'), |
|---|
| 562 | n/a | |
|---|
| 563 | n/a | # Check odd placement of embedded pattern modifiers |
|---|
| 564 | n/a | |
|---|
| 565 | n/a | # not an error under PCRE/PRE: |
|---|
| 566 | n/a | ('(?i)w', 'W', SUCCEED, 'found', 'W'), |
|---|
| 567 | n/a | # ('w(?i)', 'W', SYNTAX_ERROR), |
|---|
| 568 | n/a | |
|---|
| 569 | n/a | # Comments using the x embedded pattern modifier |
|---|
| 570 | n/a | |
|---|
| 571 | n/a | ("""(?x)w# comment 1 |
|---|
| 572 | n/a | x y |
|---|
| 573 | n/a | # comment 2 |
|---|
| 574 | n/a | z""", 'wxyz', SUCCEED, 'found', 'wxyz'), |
|---|
| 575 | n/a | |
|---|
| 576 | n/a | # using the m embedded pattern modifier |
|---|
| 577 | n/a | |
|---|
| 578 | n/a | ('^abc', """jkl |
|---|
| 579 | n/a | abc |
|---|
| 580 | n/a | xyz""", FAIL), |
|---|
| 581 | n/a | ('(?m)^abc', """jkl |
|---|
| 582 | n/a | abc |
|---|
| 583 | n/a | xyz""", SUCCEED, 'found', 'abc'), |
|---|
| 584 | n/a | |
|---|
| 585 | n/a | ('(?m)abc$', """jkl |
|---|
| 586 | n/a | xyzabc |
|---|
| 587 | n/a | 123""", SUCCEED, 'found', 'abc'), |
|---|
| 588 | n/a | |
|---|
| 589 | n/a | # using the s embedded pattern modifier |
|---|
| 590 | n/a | |
|---|
| 591 | n/a | ('a.b', 'a\nb', FAIL), |
|---|
| 592 | n/a | ('(?s)a.b', 'a\nb', SUCCEED, 'found', 'a\nb'), |
|---|
| 593 | n/a | |
|---|
| 594 | n/a | # test \w, etc. both inside and outside character classes |
|---|
| 595 | n/a | |
|---|
| 596 | n/a | ('\\w+', '--ab_cd0123--', SUCCEED, 'found', 'ab_cd0123'), |
|---|
| 597 | n/a | ('[\\w]+', '--ab_cd0123--', SUCCEED, 'found', 'ab_cd0123'), |
|---|
| 598 | n/a | ('\\D+', '1234abc5678', SUCCEED, 'found', 'abc'), |
|---|
| 599 | n/a | ('[\\D]+', '1234abc5678', SUCCEED, 'found', 'abc'), |
|---|
| 600 | n/a | ('[\\da-fA-F]+', '123abc', SUCCEED, 'found', '123abc'), |
|---|
| 601 | n/a | # not an error under PCRE/PRE: |
|---|
| 602 | n/a | # ('[\\d-x]', '-', SYNTAX_ERROR), |
|---|
| 603 | n/a | (r'([\s]*)([\S]*)([\s]*)', ' testing!1972', SUCCEED, 'g3+g2+g1', 'testing!1972 '), |
|---|
| 604 | n/a | (r'(\s*)(\S*)(\s*)', ' testing!1972', SUCCEED, 'g3+g2+g1', 'testing!1972 '), |
|---|
| 605 | n/a | |
|---|
| 606 | n/a | (r'\xff', '\377', SUCCEED, 'found', chr(255)), |
|---|
| 607 | n/a | # new \x semantics |
|---|
| 608 | n/a | (r'\x00ff', '\377', FAIL), |
|---|
| 609 | n/a | # (r'\x00ff', '\377', SUCCEED, 'found', chr(255)), |
|---|
| 610 | n/a | (r'\t\n\v\r\f\a', '\t\n\v\r\f\a', SUCCEED, 'found', '\t\n\v\r\f\a'), |
|---|
| 611 | n/a | ('\t\n\v\r\f\a', '\t\n\v\r\f\a', SUCCEED, 'found', '\t\n\v\r\f\a'), |
|---|
| 612 | n/a | (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)), |
|---|
| 613 | n/a | (r'[\t][\n][\v][\r][\f][\b]', '\t\n\v\r\f\b', SUCCEED, 'found', '\t\n\v\r\f\b'), |
|---|
| 614 | n/a | |
|---|
| 615 | n/a | # |
|---|
| 616 | n/a | # post-1.5.2 additions |
|---|
| 617 | n/a | |
|---|
| 618 | n/a | # xmllib problem |
|---|
| 619 | n/a | (r'(([a-z]+):)?([a-z]+)$', 'smil', SUCCEED, 'g1+"-"+g2+"-"+g3', 'None-None-smil'), |
|---|
| 620 | n/a | # bug 110866: reference to undefined group |
|---|
| 621 | n/a | (r'((.)\1+)', '', SYNTAX_ERROR), |
|---|
| 622 | n/a | # bug 111869: search (PRE/PCRE fails on this one, SRE doesn't) |
|---|
| 623 | n/a | (r'.*d', 'abc\nabd', SUCCEED, 'found', 'abd'), |
|---|
| 624 | n/a | # bug 112468: various expected syntax errors |
|---|
| 625 | n/a | (r'(', '', SYNTAX_ERROR), |
|---|
| 626 | n/a | (r'[\41]', '!', SUCCEED, 'found', '!'), |
|---|
| 627 | n/a | # bug 114033: nothing to repeat |
|---|
| 628 | n/a | (r'(x?)?', 'x', SUCCEED, 'found', 'x'), |
|---|
| 629 | n/a | # bug 115040: rescan if flags are modified inside pattern |
|---|
| 630 | n/a | (r'(?x) foo ', 'foo', SUCCEED, 'found', 'foo'), |
|---|
| 631 | n/a | # bug 115618: negative lookahead |
|---|
| 632 | n/a | (r'(?<!abc)(d.f)', 'abcdefdof', SUCCEED, 'found', 'dof'), |
|---|
| 633 | n/a | # bug 116251: character class bug |
|---|
| 634 | n/a | (r'[\w-]+', 'laser_beam', SUCCEED, 'found', 'laser_beam'), |
|---|
| 635 | n/a | # bug 123769+127259: non-greedy backtracking bug |
|---|
| 636 | n/a | (r'.*?\S *:', 'xx:', SUCCEED, 'found', 'xx:'), |
|---|
| 637 | n/a | (r'a[ ]*?\ (\d+).*', 'a 10', SUCCEED, 'found', 'a 10'), |
|---|
| 638 | n/a | (r'a[ ]*?\ (\d+).*', 'a 10', SUCCEED, 'found', 'a 10'), |
|---|
| 639 | n/a | # bug 127259: \Z shouldn't depend on multiline mode |
|---|
| 640 | n/a | (r'(?ms).*?x\s*\Z(.*)','xx\nx\n', SUCCEED, 'g1', ''), |
|---|
| 641 | n/a | # bug 128899: uppercase literals under the ignorecase flag |
|---|
| 642 | n/a | (r'(?i)M+', 'MMM', SUCCEED, 'found', 'MMM'), |
|---|
| 643 | n/a | (r'(?i)m+', 'MMM', SUCCEED, 'found', 'MMM'), |
|---|
| 644 | n/a | (r'(?i)[M]+', 'MMM', SUCCEED, 'found', 'MMM'), |
|---|
| 645 | n/a | (r'(?i)[m]+', 'MMM', SUCCEED, 'found', 'MMM'), |
|---|
| 646 | n/a | # bug 130748: ^* should be an error (nothing to repeat) |
|---|
| 647 | n/a | (r'^*', '', SYNTAX_ERROR), |
|---|
| 648 | n/a | # bug 133283: minimizing repeat problem |
|---|
| 649 | n/a | (r'"(?:\\"|[^"])*?"', r'"\""', SUCCEED, 'found', r'"\""'), |
|---|
| 650 | n/a | # bug 477728: minimizing repeat problem |
|---|
| 651 | n/a | (r'^.*?$', 'one\ntwo\nthree\n', FAIL), |
|---|
| 652 | n/a | # bug 483789: minimizing repeat problem |
|---|
| 653 | n/a | (r'a[^>]*?b', 'a>b', FAIL), |
|---|
| 654 | n/a | # bug 490573: minimizing repeat problem |
|---|
| 655 | n/a | (r'^a*?$', 'foo', FAIL), |
|---|
| 656 | n/a | # bug 470582: nested groups problem |
|---|
| 657 | n/a | (r'^((a)c)?(ab)$', 'ab', SUCCEED, 'g1+"-"+g2+"-"+g3', 'None-None-ab'), |
|---|
| 658 | n/a | # another minimizing repeat problem (capturing groups in assertions) |
|---|
| 659 | n/a | ('^([ab]*?)(?=(b)?)c', 'abc', SUCCEED, 'g1+"-"+g2', 'ab-None'), |
|---|
| 660 | n/a | ('^([ab]*?)(?!(b))c', 'abc', SUCCEED, 'g1+"-"+g2', 'ab-None'), |
|---|
| 661 | n/a | ('^([ab]*?)(?<!(a))c', 'abc', SUCCEED, 'g1+"-"+g2', 'ab-None'), |
|---|
| 662 | n/a | ] |
|---|
| 663 | n/a | |
|---|
| 664 | n/a | u = '\N{LATIN CAPITAL LETTER A WITH DIAERESIS}' |
|---|
| 665 | n/a | tests.extend([ |
|---|
| 666 | n/a | # bug 410271: \b broken under locales |
|---|
| 667 | n/a | (r'\b.\b', 'a', SUCCEED, 'found', 'a'), |
|---|
| 668 | n/a | (r'(?u)\b.\b', u, SUCCEED, 'found', u), |
|---|
| 669 | n/a | (r'(?u)\w', u, SUCCEED, 'found', u), |
|---|
| 670 | n/a | ]) |
|---|