Commit | Line | Data |
---|---|---|
86530b38 AT |
1 | #!/usr/bin/env python |
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 | ||
17 | benchmarks = [ | |
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 | ||
56 | tests = [ | |
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 | (r'\xff', '\377', SUCCEED, 'found', chr(255)), | |
92 | # new \x semantics | |
93 | (r'\x00ffffffffffffff', '\377', FAIL, 'found', chr(255)), | |
94 | (r'\x00f', '\017', FAIL, 'found', chr(15)), | |
95 | (r'\x00fe', '\376', FAIL, 'found', chr(254)), | |
96 | # (r'\x00ffffffffffffff', '\377', SUCCEED, 'found', chr(255)), | |
97 | # (r'\x00f', '\017', SUCCEED, 'found', chr(15)), | |
98 | # (r'\x00fe', '\376', SUCCEED, 'found', chr(254)), | |
99 | ||
100 | (r"^\w+=(\\[\000-\277]|[^\n\\])*", "SRC=eval.c g.c blah blah blah \\\\\n\tapes.c", | |
101 | SUCCEED, 'found', "SRC=eval.c g.c blah blah blah \\\\"), | |
102 | ||
103 | # Test that . only matches \n in DOTALL mode | |
104 | ('a.b', 'acb', SUCCEED, 'found', 'acb'), | |
105 | ('a.b', 'a\nb', FAIL), | |
106 | ('a.*b', 'acc\nccb', FAIL), | |
107 | ('a.{4,5}b', 'acc\nccb', FAIL), | |
108 | ('a.b', 'a\rb', SUCCEED, 'found', 'a\rb'), | |
109 | ('a.b(?s)', 'a\nb', SUCCEED, 'found', 'a\nb'), | |
110 | ('a.*(?s)b', 'acc\nccb', SUCCEED, 'found', 'acc\nccb'), | |
111 | ('(?s)a.{4,5}b', 'acc\nccb', SUCCEED, 'found', 'acc\nccb'), | |
112 | ('(?s)a.b', 'a\nb', SUCCEED, 'found', 'a\nb'), | |
113 | ||
114 | (')', '', SYNTAX_ERROR), # Unmatched right bracket | |
115 | ('', '', SUCCEED, 'found', ''), # Empty pattern | |
116 | ('abc', 'abc', SUCCEED, 'found', 'abc'), | |
117 | ('abc', 'xbc', FAIL), | |
118 | ('abc', 'axc', FAIL), | |
119 | ('abc', 'abx', FAIL), | |
120 | ('abc', 'xabcy', SUCCEED, 'found', 'abc'), | |
121 | ('abc', 'ababc', SUCCEED, 'found', 'abc'), | |
122 | ('ab*c', 'abc', SUCCEED, 'found', 'abc'), | |
123 | ('ab*bc', 'abc', SUCCEED, 'found', 'abc'), | |
124 | ('ab*bc', 'abbc', SUCCEED, 'found', 'abbc'), | |
125 | ('ab*bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), | |
126 | ('ab+bc', 'abbc', SUCCEED, 'found', 'abbc'), | |
127 | ('ab+bc', 'abc', FAIL), | |
128 | ('ab+bc', 'abq', FAIL), | |
129 | ('ab+bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), | |
130 | ('ab?bc', 'abbc', SUCCEED, 'found', 'abbc'), | |
131 | ('ab?bc', 'abc', SUCCEED, 'found', 'abc'), | |
132 | ('ab?bc', 'abbbbc', FAIL), | |
133 | ('ab?c', 'abc', SUCCEED, 'found', 'abc'), | |
134 | ('^abc$', 'abc', SUCCEED, 'found', 'abc'), | |
135 | ('^abc$', 'abcc', FAIL), | |
136 | ('^abc', 'abcc', SUCCEED, 'found', 'abc'), | |
137 | ('^abc$', 'aabc', FAIL), | |
138 | ('abc$', 'aabc', SUCCEED, 'found', 'abc'), | |
139 | ('^', 'abc', SUCCEED, 'found+"-"', '-'), | |
140 | ('$', 'abc', SUCCEED, 'found+"-"', '-'), | |
141 | ('a.c', 'abc', SUCCEED, 'found', 'abc'), | |
142 | ('a.c', 'axc', SUCCEED, 'found', 'axc'), | |
143 | ('a.*c', 'axyzc', SUCCEED, 'found', 'axyzc'), | |
144 | ('a.*c', 'axyzd', FAIL), | |
145 | ('a[bc]d', 'abc', FAIL), | |
146 | ('a[bc]d', 'abd', SUCCEED, 'found', 'abd'), | |
147 | ('a[b-d]e', 'abd', FAIL), | |
148 | ('a[b-d]e', 'ace', SUCCEED, 'found', 'ace'), | |
149 | ('a[b-d]', 'aac', SUCCEED, 'found', 'ac'), | |
150 | ('a[-b]', 'a-', SUCCEED, 'found', 'a-'), | |
151 | ('a[\\-b]', 'a-', SUCCEED, 'found', 'a-'), | |
152 | # NOTE: not an error under PCRE/PRE: | |
153 | # ('a[b-]', 'a-', SYNTAX_ERROR), | |
154 | ('a[]b', '-', SYNTAX_ERROR), | |
155 | ('a[', '-', SYNTAX_ERROR), | |
156 | ('a\\', '-', SYNTAX_ERROR), | |
157 | ('abc)', '-', SYNTAX_ERROR), | |
158 | ('(abc', '-', SYNTAX_ERROR), | |
159 | ('a]', 'a]', SUCCEED, 'found', 'a]'), | |
160 | ('a[]]b', 'a]b', SUCCEED, 'found', 'a]b'), | |
161 | ('a[\]]b', 'a]b', SUCCEED, 'found', 'a]b'), | |
162 | ('a[^bc]d', 'aed', SUCCEED, 'found', 'aed'), | |
163 | ('a[^bc]d', 'abd', FAIL), | |
164 | ('a[^-b]c', 'adc', SUCCEED, 'found', 'adc'), | |
165 | ('a[^-b]c', 'a-c', FAIL), | |
166 | ('a[^]b]c', 'a]c', FAIL), | |
167 | ('a[^]b]c', 'adc', SUCCEED, 'found', 'adc'), | |
168 | ('\\ba\\b', 'a-', SUCCEED, '"-"', '-'), | |
169 | ('\\ba\\b', '-a', SUCCEED, '"-"', '-'), | |
170 | ('\\ba\\b', '-a-', SUCCEED, '"-"', '-'), | |
171 | ('\\by\\b', 'xy', FAIL), | |
172 | ('\\by\\b', 'yz', FAIL), | |
173 | ('\\by\\b', 'xyz', FAIL), | |
174 | ('x\\b', 'xyz', FAIL), | |
175 | ('x\\B', 'xyz', SUCCEED, '"-"', '-'), | |
176 | ('\\Bz', 'xyz', SUCCEED, '"-"', '-'), | |
177 | ('z\\B', 'xyz', FAIL), | |
178 | ('\\Bx', 'xyz', FAIL), | |
179 | ('\\Ba\\B', 'a-', FAIL, '"-"', '-'), | |
180 | ('\\Ba\\B', '-a', FAIL, '"-"', '-'), | |
181 | ('\\Ba\\B', '-a-', FAIL, '"-"', '-'), | |
182 | ('\\By\\B', 'xy', FAIL), | |
183 | ('\\By\\B', 'yz', FAIL), | |
184 | ('\\By\\b', 'xy', SUCCEED, '"-"', '-'), | |
185 | ('\\by\\B', 'yz', SUCCEED, '"-"', '-'), | |
186 | ('\\By\\B', 'xyz', SUCCEED, '"-"', '-'), | |
187 | ('ab|cd', 'abc', SUCCEED, 'found', 'ab'), | |
188 | ('ab|cd', 'abcd', SUCCEED, 'found', 'ab'), | |
189 | ('()ef', 'def', SUCCEED, 'found+"-"+g1', 'ef-'), | |
190 | ('$b', 'b', FAIL), | |
191 | ('a\\(b', 'a(b', SUCCEED, 'found+"-"+g1', 'a(b-Error'), | |
192 | ('a\\(*b', 'ab', SUCCEED, 'found', 'ab'), | |
193 | ('a\\(*b', 'a((b', SUCCEED, 'found', 'a((b'), | |
194 | ('a\\\\b', 'a\\b', SUCCEED, 'found', 'a\\b'), | |
195 | ('((a))', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'a-a-a'), | |
196 | ('(a)b(c)', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'abc-a-c'), | |
197 | ('a+b+c', 'aabbabc', SUCCEED, 'found', 'abc'), | |
198 | ('(a+|b)*', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), | |
199 | ('(a+|b)+', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), | |
200 | ('(a+|b)?', 'ab', SUCCEED, 'found+"-"+g1', 'a-a'), | |
201 | (')(', '-', SYNTAX_ERROR), | |
202 | ('[^ab]*', 'cde', SUCCEED, 'found', 'cde'), | |
203 | ('abc', '', FAIL), | |
204 | ('a*', '', SUCCEED, 'found', ''), | |
205 | ('a|b|c|d|e', 'e', SUCCEED, 'found', 'e'), | |
206 | ('(a|b|c|d|e)f', 'ef', SUCCEED, 'found+"-"+g1', 'ef-e'), | |
207 | ('abcd*efg', 'abcdefg', SUCCEED, 'found', 'abcdefg'), | |
208 | ('ab*', 'xabyabbbz', SUCCEED, 'found', 'ab'), | |
209 | ('ab*', 'xayabbbz', SUCCEED, 'found', 'a'), | |
210 | ('(ab|cd)e', 'abcde', SUCCEED, 'found+"-"+g1', 'cde-cd'), | |
211 | ('[abhgefdc]ij', 'hij', SUCCEED, 'found', 'hij'), | |
212 | ('^(ab|cd)e', 'abcde', FAIL, 'xg1y', 'xy'), | |
213 | ('(abc|)ef', 'abcdef', SUCCEED, 'found+"-"+g1', 'ef-'), | |
214 | ('(a|b)c*d', 'abcd', SUCCEED, 'found+"-"+g1', 'bcd-b'), | |
215 | ('(ab|ab*)bc', 'abc', SUCCEED, 'found+"-"+g1', 'abc-a'), | |
216 | ('a([bc]*)c*', 'abc', SUCCEED, 'found+"-"+g1', 'abc-bc'), | |
217 | ('a([bc]*)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'), | |
218 | ('a([bc]+)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'), | |
219 | ('a([bc]*)(c+d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-b-cd'), | |
220 | ('a[bcd]*dcdcde', 'adcdcde', SUCCEED, 'found', 'adcdcde'), | |
221 | ('a[bcd]+dcdcde', 'adcdcde', FAIL), | |
222 | ('(ab|a)b*c', 'abc', SUCCEED, 'found+"-"+g1', 'abc-ab'), | |
223 | ('((a)(b)c)(d)', 'abcd', SUCCEED, 'g1+"-"+g2+"-"+g3+"-"+g4', 'abc-a-b-d'), | |
224 | ('[a-zA-Z_][a-zA-Z0-9_]*', 'alpha', SUCCEED, 'found', 'alpha'), | |
225 | ('^a(bc+|b[eh])g|.h$', 'abh', SUCCEED, 'found+"-"+g1', 'bh-None'), | |
226 | ('(bc+d$|ef*g.|h?i(j|k))', 'effgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'), | |
227 | ('(bc+d$|ef*g.|h?i(j|k))', 'ij', SUCCEED, 'found+"-"+g1+"-"+g2', 'ij-ij-j'), | |
228 | ('(bc+d$|ef*g.|h?i(j|k))', 'effg', FAIL), | |
229 | ('(bc+d$|ef*g.|h?i(j|k))', 'bcdd', FAIL), | |
230 | ('(bc+d$|ef*g.|h?i(j|k))', 'reffgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'), | |
231 | ('(((((((((a)))))))))', 'a', SUCCEED, 'found', 'a'), | |
232 | ('multiple words of text', 'uh-uh', FAIL), | |
233 | ('multiple words', 'multiple words, yeah', SUCCEED, 'found', 'multiple words'), | |
234 | ('(.*)c(.*)', 'abcde', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcde-ab-de'), | |
235 | ('\\((.*), (.*)\\)', '(a, b)', SUCCEED, 'g2+"-"+g1', 'b-a'), | |
236 | ('[k]', 'ab', FAIL), | |
237 | ('a[-]?c', 'ac', SUCCEED, 'found', 'ac'), | |
238 | ('(abc)\\1', 'abcabc', SUCCEED, 'g1', 'abc'), | |
239 | ('([a-c]*)\\1', 'abcabc', SUCCEED, 'g1', 'abc'), | |
240 | ('^(.+)?B', 'AB', SUCCEED, 'g1', 'A'), | |
241 | ('(a+).\\1$', 'aaaaa', SUCCEED, 'found+"-"+g1', 'aaaaa-aa'), | |
242 | ('^(a+).\\1$', 'aaaa', FAIL), | |
243 | ('(abc)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'), | |
244 | ('([a-c]+)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'), | |
245 | ('(a)\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'), | |
246 | ('(a+)\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'), | |
247 | ('(a+)+\\1', 'aa', SUCCEED, 'found+"-"+g1', 'aa-a'), | |
248 | ('(a).+\\1', 'aba', SUCCEED, 'found+"-"+g1', 'aba-a'), | |
249 | ('(a)ba*\\1', 'aba', SUCCEED, 'found+"-"+g1', 'aba-a'), | |
250 | ('(aa|a)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'), | |
251 | ('(a|aa)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'), | |
252 | ('(a+)a\\1$', 'aaa', SUCCEED, 'found+"-"+g1', 'aaa-a'), | |
253 | ('([abc]*)\\1', 'abcabc', SUCCEED, 'found+"-"+g1', 'abcabc-abc'), | |
254 | ('(a)(b)c|ab', 'ab', SUCCEED, 'found+"-"+g1+"-"+g2', 'ab-None-None'), | |
255 | ('(a)+x', 'aaax', SUCCEED, 'found+"-"+g1', 'aaax-a'), | |
256 | ('([ac])+x', 'aacx', SUCCEED, 'found+"-"+g1', 'aacx-c'), | |
257 | ('([^/]*/)*sub1/', 'd:msgs/tdir/sub1/trial/away.cpp', SUCCEED, 'found+"-"+g1', 'd:msgs/tdir/sub1/-tdir/'), | |
258 | ('([^.]*)\\.([^:]*):[T ]+(.*)', 'track1.title:TBlah blah blah', SUCCEED, 'found+"-"+g1+"-"+g2+"-"+g3', 'track1.title:TBlah blah blah-track1-title-Blah blah blah'), | |
259 | ('([^N]*N)+', 'abNNxyzN', SUCCEED, 'found+"-"+g1', 'abNNxyzN-xyzN'), | |
260 | ('([^N]*N)+', 'abNNxyz', SUCCEED, 'found+"-"+g1', 'abNN-N'), | |
261 | ('([abc]*)x', 'abcx', SUCCEED, 'found+"-"+g1', 'abcx-abc'), | |
262 | ('([abc]*)x', 'abc', FAIL), | |
263 | ('([xyz]*)x', 'abcx', SUCCEED, 'found+"-"+g1', 'x-'), | |
264 | ('(a)+b|aac', 'aac', SUCCEED, 'found+"-"+g1', 'aac-None'), | |
265 | ||
266 | # Test symbolic groups | |
267 | ||
268 | ('(?P<i d>aaa)a', 'aaaa', SYNTAX_ERROR), | |
269 | ('(?P<id>aaa)a', 'aaaa', SUCCEED, 'found+"-"+id', 'aaaa-aaa'), | |
270 | ('(?P<id>aa)(?P=id)', 'aaaa', SUCCEED, 'found+"-"+id', 'aaaa-aa'), | |
271 | ('(?P<id>aa)(?P=xd)', 'aaaa', SYNTAX_ERROR), | |
272 | ||
273 | # Test octal escapes/memory references | |
274 | ||
275 | ('\\1', 'a', SYNTAX_ERROR), | |
276 | ('\\09', chr(0) + '9', SUCCEED, 'found', chr(0) + '9'), | |
277 | ('\\141', 'a', SUCCEED, 'found', 'a'), | |
278 | ('(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)\\119', 'abcdefghijklk9', SUCCEED, 'found+"-"+g11', 'abcdefghijklk9-k'), | |
279 | ||
280 | # All tests from Perl | |
281 | ||
282 | ('abc', 'abc', SUCCEED, 'found', 'abc'), | |
283 | ('abc', 'xbc', FAIL), | |
284 | ('abc', 'axc', FAIL), | |
285 | ('abc', 'abx', FAIL), | |
286 | ('abc', 'xabcy', SUCCEED, 'found', 'abc'), | |
287 | ('abc', 'ababc', SUCCEED, 'found', 'abc'), | |
288 | ('ab*c', 'abc', SUCCEED, 'found', 'abc'), | |
289 | ('ab*bc', 'abc', SUCCEED, 'found', 'abc'), | |
290 | ('ab*bc', 'abbc', SUCCEED, 'found', 'abbc'), | |
291 | ('ab*bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), | |
292 | ('ab{0,}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), | |
293 | ('ab+bc', 'abbc', SUCCEED, 'found', 'abbc'), | |
294 | ('ab+bc', 'abc', FAIL), | |
295 | ('ab+bc', 'abq', FAIL), | |
296 | ('ab{1,}bc', 'abq', FAIL), | |
297 | ('ab+bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), | |
298 | ('ab{1,}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), | |
299 | ('ab{1,3}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), | |
300 | ('ab{3,4}bc', 'abbbbc', SUCCEED, 'found', 'abbbbc'), | |
301 | ('ab{4,5}bc', 'abbbbc', FAIL), | |
302 | ('ab?bc', 'abbc', SUCCEED, 'found', 'abbc'), | |
303 | ('ab?bc', 'abc', SUCCEED, 'found', 'abc'), | |
304 | ('ab{0,1}bc', 'abc', SUCCEED, 'found', 'abc'), | |
305 | ('ab?bc', 'abbbbc', FAIL), | |
306 | ('ab?c', 'abc', SUCCEED, 'found', 'abc'), | |
307 | ('ab{0,1}c', 'abc', SUCCEED, 'found', 'abc'), | |
308 | ('^abc$', 'abc', SUCCEED, 'found', 'abc'), | |
309 | ('^abc$', 'abcc', FAIL), | |
310 | ('^abc', 'abcc', SUCCEED, 'found', 'abc'), | |
311 | ('^abc$', 'aabc', FAIL), | |
312 | ('abc$', 'aabc', SUCCEED, 'found', 'abc'), | |
313 | ('^', 'abc', SUCCEED, 'found', ''), | |
314 | ('$', 'abc', SUCCEED, 'found', ''), | |
315 | ('a.c', 'abc', SUCCEED, 'found', 'abc'), | |
316 | ('a.c', 'axc', SUCCEED, 'found', 'axc'), | |
317 | ('a.*c', 'axyzc', SUCCEED, 'found', 'axyzc'), | |
318 | ('a.*c', 'axyzd', FAIL), | |
319 | ('a[bc]d', 'abc', FAIL), | |
320 | ('a[bc]d', 'abd', SUCCEED, 'found', 'abd'), | |
321 | ('a[b-d]e', 'abd', FAIL), | |
322 | ('a[b-d]e', 'ace', SUCCEED, 'found', 'ace'), | |
323 | ('a[b-d]', 'aac', SUCCEED, 'found', 'ac'), | |
324 | ('a[-b]', 'a-', SUCCEED, 'found', 'a-'), | |
325 | ('a[b-]', 'a-', SUCCEED, 'found', 'a-'), | |
326 | ('a[b-a]', '-', SYNTAX_ERROR), | |
327 | ('a[]b', '-', SYNTAX_ERROR), | |
328 | ('a[', '-', SYNTAX_ERROR), | |
329 | ('a]', 'a]', SUCCEED, 'found', 'a]'), | |
330 | ('a[]]b', 'a]b', SUCCEED, 'found', 'a]b'), | |
331 | ('a[^bc]d', 'aed', SUCCEED, 'found', 'aed'), | |
332 | ('a[^bc]d', 'abd', FAIL), | |
333 | ('a[^-b]c', 'adc', SUCCEED, 'found', 'adc'), | |
334 | ('a[^-b]c', 'a-c', FAIL), | |
335 | ('a[^]b]c', 'a]c', FAIL), | |
336 | ('a[^]b]c', 'adc', SUCCEED, 'found', 'adc'), | |
337 | ('ab|cd', 'abc', SUCCEED, 'found', 'ab'), | |
338 | ('ab|cd', 'abcd', SUCCEED, 'found', 'ab'), | |
339 | ('()ef', 'def', SUCCEED, 'found+"-"+g1', 'ef-'), | |
340 | ('*a', '-', SYNTAX_ERROR), | |
341 | ('(*)b', '-', SYNTAX_ERROR), | |
342 | ('$b', 'b', FAIL), | |
343 | ('a\\', '-', SYNTAX_ERROR), | |
344 | ('a\\(b', 'a(b', SUCCEED, 'found+"-"+g1', 'a(b-Error'), | |
345 | ('a\\(*b', 'ab', SUCCEED, 'found', 'ab'), | |
346 | ('a\\(*b', 'a((b', SUCCEED, 'found', 'a((b'), | |
347 | ('a\\\\b', 'a\\b', SUCCEED, 'found', 'a\\b'), | |
348 | ('abc)', '-', SYNTAX_ERROR), | |
349 | ('(abc', '-', SYNTAX_ERROR), | |
350 | ('((a))', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'a-a-a'), | |
351 | ('(a)b(c)', 'abc', SUCCEED, 'found+"-"+g1+"-"+g2', 'abc-a-c'), | |
352 | ('a+b+c', 'aabbabc', SUCCEED, 'found', 'abc'), | |
353 | ('a{1,}b{1,}c', 'aabbabc', SUCCEED, 'found', 'abc'), | |
354 | ('a**', '-', SYNTAX_ERROR), | |
355 | ('a.+?c', 'abcabc', SUCCEED, 'found', 'abc'), | |
356 | ('(a+|b)*', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), | |
357 | ('(a+|b){0,}', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), | |
358 | ('(a+|b)+', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), | |
359 | ('(a+|b){1,}', 'ab', SUCCEED, 'found+"-"+g1', 'ab-b'), | |
360 | ('(a+|b)?', 'ab', SUCCEED, 'found+"-"+g1', 'a-a'), | |
361 | ('(a+|b){0,1}', 'ab', SUCCEED, 'found+"-"+g1', 'a-a'), | |
362 | (')(', '-', SYNTAX_ERROR), | |
363 | ('[^ab]*', 'cde', SUCCEED, 'found', 'cde'), | |
364 | ('abc', '', FAIL), | |
365 | ('a*', '', SUCCEED, 'found', ''), | |
366 | ('([abc])*d', 'abbbcd', SUCCEED, 'found+"-"+g1', 'abbbcd-c'), | |
367 | ('([abc])*bcd', 'abcd', SUCCEED, 'found+"-"+g1', 'abcd-a'), | |
368 | ('a|b|c|d|e', 'e', SUCCEED, 'found', 'e'), | |
369 | ('(a|b|c|d|e)f', 'ef', SUCCEED, 'found+"-"+g1', 'ef-e'), | |
370 | ('abcd*efg', 'abcdefg', SUCCEED, 'found', 'abcdefg'), | |
371 | ('ab*', 'xabyabbbz', SUCCEED, 'found', 'ab'), | |
372 | ('ab*', 'xayabbbz', SUCCEED, 'found', 'a'), | |
373 | ('(ab|cd)e', 'abcde', SUCCEED, 'found+"-"+g1', 'cde-cd'), | |
374 | ('[abhgefdc]ij', 'hij', SUCCEED, 'found', 'hij'), | |
375 | ('^(ab|cd)e', 'abcde', FAIL), | |
376 | ('(abc|)ef', 'abcdef', SUCCEED, 'found+"-"+g1', 'ef-'), | |
377 | ('(a|b)c*d', 'abcd', SUCCEED, 'found+"-"+g1', 'bcd-b'), | |
378 | ('(ab|ab*)bc', 'abc', SUCCEED, 'found+"-"+g1', 'abc-a'), | |
379 | ('a([bc]*)c*', 'abc', SUCCEED, 'found+"-"+g1', 'abc-bc'), | |
380 | ('a([bc]*)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'), | |
381 | ('a([bc]+)(c*d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'), | |
382 | ('a([bc]*)(c+d)', 'abcd', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcd-b-cd'), | |
383 | ('a[bcd]*dcdcde', 'adcdcde', SUCCEED, 'found', 'adcdcde'), | |
384 | ('a[bcd]+dcdcde', 'adcdcde', FAIL), | |
385 | ('(ab|a)b*c', 'abc', SUCCEED, 'found+"-"+g1', 'abc-ab'), | |
386 | ('((a)(b)c)(d)', 'abcd', SUCCEED, 'g1+"-"+g2+"-"+g3+"-"+g4', 'abc-a-b-d'), | |
387 | ('[a-zA-Z_][a-zA-Z0-9_]*', 'alpha', SUCCEED, 'found', 'alpha'), | |
388 | ('^a(bc+|b[eh])g|.h$', 'abh', SUCCEED, 'found+"-"+g1', 'bh-None'), | |
389 | ('(bc+d$|ef*g.|h?i(j|k))', 'effgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'), | |
390 | ('(bc+d$|ef*g.|h?i(j|k))', 'ij', SUCCEED, 'found+"-"+g1+"-"+g2', 'ij-ij-j'), | |
391 | ('(bc+d$|ef*g.|h?i(j|k))', 'effg', FAIL), | |
392 | ('(bc+d$|ef*g.|h?i(j|k))', 'bcdd', FAIL), | |
393 | ('(bc+d$|ef*g.|h?i(j|k))', 'reffgz', SUCCEED, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'), | |
394 | ('((((((((((a))))))))))', 'a', SUCCEED, 'g10', 'a'), | |
395 | ('((((((((((a))))))))))\\10', 'aa', SUCCEED, 'found', 'aa'), | |
396 | # Python does not have the same rules for \\41 so this is a syntax error | |
397 | # ('((((((((((a))))))))))\\41', 'aa', FAIL), | |
398 | # ('((((((((((a))))))))))\\41', 'a!', SUCCEED, 'found', 'a!'), | |
399 | ('((((((((((a))))))))))\\41', '', SYNTAX_ERROR), | |
400 | ('(?i)((((((((((a))))))))))\\41', '', SYNTAX_ERROR), | |
401 | ('(((((((((a)))))))))', 'a', SUCCEED, 'found', 'a'), | |
402 | ('multiple words of text', 'uh-uh', FAIL), | |
403 | ('multiple words', 'multiple words, yeah', SUCCEED, 'found', 'multiple words'), | |
404 | ('(.*)c(.*)', 'abcde', SUCCEED, 'found+"-"+g1+"-"+g2', 'abcde-ab-de'), | |
405 | ('\\((.*), (.*)\\)', '(a, b)', SUCCEED, 'g2+"-"+g1', 'b-a'), | |
406 | ('[k]', 'ab', FAIL), | |
407 | ('a[-]?c', 'ac', SUCCEED, 'found', 'ac'), | |
408 | ('(abc)\\1', 'abcabc', SUCCEED, 'g1', 'abc'), | |
409 | ('([a-c]*)\\1', 'abcabc', SUCCEED, 'g1', 'abc'), | |
410 | ('(?i)abc', 'ABC', SUCCEED, 'found', 'ABC'), | |
411 | ('(?i)abc', 'XBC', FAIL), | |
412 | ('(?i)abc', 'AXC', FAIL), | |
413 | ('(?i)abc', 'ABX', FAIL), | |
414 | ('(?i)abc', 'XABCY', SUCCEED, 'found', 'ABC'), | |
415 | ('(?i)abc', 'ABABC', SUCCEED, 'found', 'ABC'), | |
416 | ('(?i)ab*c', 'ABC', SUCCEED, 'found', 'ABC'), | |
417 | ('(?i)ab*bc', 'ABC', SUCCEED, 'found', 'ABC'), | |
418 | ('(?i)ab*bc', 'ABBC', SUCCEED, 'found', 'ABBC'), | |
419 | ('(?i)ab*?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), | |
420 | ('(?i)ab{0,}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), | |
421 | ('(?i)ab+?bc', 'ABBC', SUCCEED, 'found', 'ABBC'), | |
422 | ('(?i)ab+bc', 'ABC', FAIL), | |
423 | ('(?i)ab+bc', 'ABQ', FAIL), | |
424 | ('(?i)ab{1,}bc', 'ABQ', FAIL), | |
425 | ('(?i)ab+bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), | |
426 | ('(?i)ab{1,}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), | |
427 | ('(?i)ab{1,3}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), | |
428 | ('(?i)ab{3,4}?bc', 'ABBBBC', SUCCEED, 'found', 'ABBBBC'), | |
429 | ('(?i)ab{4,5}?bc', 'ABBBBC', FAIL), | |
430 | ('(?i)ab??bc', 'ABBC', SUCCEED, 'found', 'ABBC'), | |
431 | ('(?i)ab??bc', 'ABC', SUCCEED, 'found', 'ABC'), | |
432 | ('(?i)ab{0,1}?bc', 'ABC', SUCCEED, 'found', 'ABC'), | |
433 | ('(?i)ab??bc', 'ABBBBC', FAIL), | |
434 | ('(?i)ab??c', 'ABC', SUCCEED, 'found', 'ABC'), | |
435 | ('(?i)ab{0,1}?c', 'ABC', SUCCEED, 'found', 'ABC'), | |
436 | ('(?i)^abc$', 'ABC', SUCCEED, 'found', 'ABC'), | |
437 | ('(?i)^abc$', 'ABCC', FAIL), | |
438 | ('(?i)^abc', 'ABCC', SUCCEED, 'found', 'ABC'), | |
439 | ('(?i)^abc$', 'AABC', FAIL), | |
440 | ('(?i)abc$', 'AABC', SUCCEED, 'found', 'ABC'), | |
441 | ('(?i)^', 'ABC', SUCCEED, 'found', ''), | |
442 | ('(?i)$', 'ABC', SUCCEED, 'found', ''), | |
443 | ('(?i)a.c', 'ABC', SUCCEED, 'found', 'ABC'), | |
444 | ('(?i)a.c', 'AXC', SUCCEED, 'found', 'AXC'), | |
445 | ('(?i)a.*?c', 'AXYZC', SUCCEED, 'found', 'AXYZC'), | |
446 | ('(?i)a.*c', 'AXYZD', FAIL), | |
447 | ('(?i)a[bc]d', 'ABC', FAIL), | |
448 | ('(?i)a[bc]d', 'ABD', SUCCEED, 'found', 'ABD'), | |
449 | ('(?i)a[b-d]e', 'ABD', FAIL), | |
450 | ('(?i)a[b-d]e', 'ACE', SUCCEED, 'found', 'ACE'), | |
451 | ('(?i)a[b-d]', 'AAC', SUCCEED, 'found', 'AC'), | |
452 | ('(?i)a[-b]', 'A-', SUCCEED, 'found', 'A-'), | |
453 | ('(?i)a[b-]', 'A-', SUCCEED, 'found', 'A-'), | |
454 | ('(?i)a[b-a]', '-', SYNTAX_ERROR), | |
455 | ('(?i)a[]b', '-', SYNTAX_ERROR), | |
456 | ('(?i)a[', '-', SYNTAX_ERROR), | |
457 | ('(?i)a]', 'A]', SUCCEED, 'found', 'A]'), | |
458 | ('(?i)a[]]b', 'A]B', SUCCEED, 'found', 'A]B'), | |
459 | ('(?i)a[^bc]d', 'AED', SUCCEED, 'found', 'AED'), | |
460 | ('(?i)a[^bc]d', 'ABD', FAIL), | |
461 | ('(?i)a[^-b]c', 'ADC', SUCCEED, 'found', 'ADC'), | |
462 | ('(?i)a[^-b]c', 'A-C', FAIL), | |
463 | ('(?i)a[^]b]c', 'A]C', FAIL), | |
464 | ('(?i)a[^]b]c', 'ADC', SUCCEED, 'found', 'ADC'), | |
465 | ('(?i)ab|cd', 'ABC', SUCCEED, 'found', 'AB'), | |
466 | ('(?i)ab|cd', 'ABCD', SUCCEED, 'found', 'AB'), | |
467 | ('(?i)()ef', 'DEF', SUCCEED, 'found+"-"+g1', 'EF-'), | |
468 | ('(?i)*a', '-', SYNTAX_ERROR), | |
469 | ('(?i)(*)b', '-', SYNTAX_ERROR), | |
470 | ('(?i)$b', 'B', FAIL), | |
471 | ('(?i)a\\', '-', SYNTAX_ERROR), | |
472 | ('(?i)a\\(b', 'A(B', SUCCEED, 'found+"-"+g1', 'A(B-Error'), | |
473 | ('(?i)a\\(*b', 'AB', SUCCEED, 'found', 'AB'), | |
474 | ('(?i)a\\(*b', 'A((B', SUCCEED, 'found', 'A((B'), | |
475 | ('(?i)a\\\\b', 'A\\B', SUCCEED, 'found', 'A\\B'), | |
476 | ('(?i)abc)', '-', SYNTAX_ERROR), | |
477 | ('(?i)(abc', '-', SYNTAX_ERROR), | |
478 | ('(?i)((a))', 'ABC', SUCCEED, 'found+"-"+g1+"-"+g2', 'A-A-A'), | |
479 | ('(?i)(a)b(c)', 'ABC', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABC-A-C'), | |
480 | ('(?i)a+b+c', 'AABBABC', SUCCEED, 'found', 'ABC'), | |
481 | ('(?i)a{1,}b{1,}c', 'AABBABC', SUCCEED, 'found', 'ABC'), | |
482 | ('(?i)a**', '-', SYNTAX_ERROR), | |
483 | ('(?i)a.+?c', 'ABCABC', SUCCEED, 'found', 'ABC'), | |
484 | ('(?i)a.*?c', 'ABCABC', SUCCEED, 'found', 'ABC'), | |
485 | ('(?i)a.{0,5}?c', 'ABCABC', SUCCEED, 'found', 'ABC'), | |
486 | ('(?i)(a+|b)*', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'), | |
487 | ('(?i)(a+|b){0,}', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'), | |
488 | ('(?i)(a+|b)+', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'), | |
489 | ('(?i)(a+|b){1,}', 'AB', SUCCEED, 'found+"-"+g1', 'AB-B'), | |
490 | ('(?i)(a+|b)?', 'AB', SUCCEED, 'found+"-"+g1', 'A-A'), | |
491 | ('(?i)(a+|b){0,1}', 'AB', SUCCEED, 'found+"-"+g1', 'A-A'), | |
492 | ('(?i)(a+|b){0,1}?', 'AB', SUCCEED, 'found+"-"+g1', '-None'), | |
493 | ('(?i))(', '-', SYNTAX_ERROR), | |
494 | ('(?i)[^ab]*', 'CDE', SUCCEED, 'found', 'CDE'), | |
495 | ('(?i)abc', '', FAIL), | |
496 | ('(?i)a*', '', SUCCEED, 'found', ''), | |
497 | ('(?i)([abc])*d', 'ABBBCD', SUCCEED, 'found+"-"+g1', 'ABBBCD-C'), | |
498 | ('(?i)([abc])*bcd', 'ABCD', SUCCEED, 'found+"-"+g1', 'ABCD-A'), | |
499 | ('(?i)a|b|c|d|e', 'E', SUCCEED, 'found', 'E'), | |
500 | ('(?i)(a|b|c|d|e)f', 'EF', SUCCEED, 'found+"-"+g1', 'EF-E'), | |
501 | ('(?i)abcd*efg', 'ABCDEFG', SUCCEED, 'found', 'ABCDEFG'), | |
502 | ('(?i)ab*', 'XABYABBBZ', SUCCEED, 'found', 'AB'), | |
503 | ('(?i)ab*', 'XAYABBBZ', SUCCEED, 'found', 'A'), | |
504 | ('(?i)(ab|cd)e', 'ABCDE', SUCCEED, 'found+"-"+g1', 'CDE-CD'), | |
505 | ('(?i)[abhgefdc]ij', 'HIJ', SUCCEED, 'found', 'HIJ'), | |
506 | ('(?i)^(ab|cd)e', 'ABCDE', FAIL), | |
507 | ('(?i)(abc|)ef', 'ABCDEF', SUCCEED, 'found+"-"+g1', 'EF-'), | |
508 | ('(?i)(a|b)c*d', 'ABCD', SUCCEED, 'found+"-"+g1', 'BCD-B'), | |
509 | ('(?i)(ab|ab*)bc', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-A'), | |
510 | ('(?i)a([bc]*)c*', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-BC'), | |
511 | ('(?i)a([bc]*)(c*d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-BC-D'), | |
512 | ('(?i)a([bc]+)(c*d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-BC-D'), | |
513 | ('(?i)a([bc]*)(c+d)', 'ABCD', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCD-B-CD'), | |
514 | ('(?i)a[bcd]*dcdcde', 'ADCDCDE', SUCCEED, 'found', 'ADCDCDE'), | |
515 | ('(?i)a[bcd]+dcdcde', 'ADCDCDE', FAIL), | |
516 | ('(?i)(ab|a)b*c', 'ABC', SUCCEED, 'found+"-"+g1', 'ABC-AB'), | |
517 | ('(?i)((a)(b)c)(d)', 'ABCD', SUCCEED, 'g1+"-"+g2+"-"+g3+"-"+g4', 'ABC-A-B-D'), | |
518 | ('(?i)[a-zA-Z_][a-zA-Z0-9_]*', 'ALPHA', SUCCEED, 'found', 'ALPHA'), | |
519 | ('(?i)^a(bc+|b[eh])g|.h$', 'ABH', SUCCEED, 'found+"-"+g1', 'BH-None'), | |
520 | ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'EFFGZ', SUCCEED, 'found+"-"+g1+"-"+g2', 'EFFGZ-EFFGZ-None'), | |
521 | ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'IJ', SUCCEED, 'found+"-"+g1+"-"+g2', 'IJ-IJ-J'), | |
522 | ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'EFFG', FAIL), | |
523 | ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'BCDD', FAIL), | |
524 | ('(?i)(bc+d$|ef*g.|h?i(j|k))', 'REFFGZ', SUCCEED, 'found+"-"+g1+"-"+g2', 'EFFGZ-EFFGZ-None'), | |
525 | ('(?i)((((((((((a))))))))))', 'A', SUCCEED, 'g10', 'A'), | |
526 | ('(?i)((((((((((a))))))))))\\10', 'AA', SUCCEED, 'found', 'AA'), | |
527 | #('(?i)((((((((((a))))))))))\\41', 'AA', FAIL), | |
528 | #('(?i)((((((((((a))))))))))\\41', 'A!', SUCCEED, 'found', 'A!'), | |
529 | ('(?i)(((((((((a)))))))))', 'A', SUCCEED, 'found', 'A'), | |
530 | ('(?i)(?:(?:(?:(?:(?:(?:(?:(?:(?:(a))))))))))', 'A', SUCCEED, 'g1', 'A'), | |
531 | ('(?i)(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))', 'C', SUCCEED, 'g1', 'C'), | |
532 | ('(?i)multiple words of text', 'UH-UH', FAIL), | |
533 | ('(?i)multiple words', 'MULTIPLE WORDS, YEAH', SUCCEED, 'found', 'MULTIPLE WORDS'), | |
534 | ('(?i)(.*)c(.*)', 'ABCDE', SUCCEED, 'found+"-"+g1+"-"+g2', 'ABCDE-AB-DE'), | |
535 | ('(?i)\\((.*), (.*)\\)', '(A, B)', SUCCEED, 'g2+"-"+g1', 'B-A'), | |
536 | ('(?i)[k]', 'AB', FAIL), | |
537 | # ('(?i)abcd', 'ABCD', SUCCEED, 'found+"-"+\\found+"-"+\\\\found', 'ABCD-$&-\\ABCD'), | |
538 | # ('(?i)a(bc)d', 'ABCD', SUCCEED, 'g1+"-"+\\g1+"-"+\\\\g1', 'BC-$1-\\BC'), | |
539 | ('(?i)a[-]?c', 'AC', SUCCEED, 'found', 'AC'), | |
540 | ('(?i)(abc)\\1', 'ABCABC', SUCCEED, 'g1', 'ABC'), | |
541 | ('(?i)([a-c]*)\\1', 'ABCABC', SUCCEED, 'g1', 'ABC'), | |
542 | ('a(?!b).', 'abad', SUCCEED, 'found', 'ad'), | |
543 | ('a(?=d).', 'abad', SUCCEED, 'found', 'ad'), | |
544 | ('a(?=c|d).', 'abad', SUCCEED, 'found', 'ad'), | |
545 | ('a(?:b|c|d)(.)', 'ace', SUCCEED, 'g1', 'e'), | |
546 | ('a(?:b|c|d)*(.)', 'ace', SUCCEED, 'g1', 'e'), | |
547 | ('a(?:b|c|d)+?(.)', 'ace', SUCCEED, 'g1', 'e'), | |
548 | ('a(?:b|(c|e){1,2}?|d)+?(.)', 'ace', SUCCEED, 'g1 + g2', 'ce'), | |
549 | ('^(.+)?B', 'AB', SUCCEED, 'g1', 'A'), | |
550 | ||
551 | # lookbehind: split by : but not if it is escaped by -. | |
552 | ('(?<!-):(.*?)(?<!-):', 'a:bc-:de:f', SUCCEED, 'g1', 'bc-:de' ), | |
553 | # escaping with \ as we know it | |
554 | ('(?<!\\\):(.*?)(?<!\\\):', 'a:bc\\:de:f', SUCCEED, 'g1', 'bc\\:de' ), | |
555 | # terminating with ' and escaping with ? as in edifact | |
556 | ("(?<!\\?)'(.*?)(?<!\\?)'", "a'bc?'de'f", SUCCEED, 'g1', "bc?'de" ), | |
557 | ||
558 | # Comments using the (?#...) syntax | |
559 | ||
560 | ('w(?# comment', 'w', SYNTAX_ERROR), | |
561 | ('w(?# comment 1)xy(?# comment 2)z', 'wxyz', SUCCEED, 'found', 'wxyz'), | |
562 | ||
563 | # Check odd placement of embedded pattern modifiers | |
564 | ||
565 | # not an error under PCRE/PRE: | |
566 | ('w(?i)', 'W', SUCCEED, 'found', 'W'), | |
567 | # ('w(?i)', 'W', SYNTAX_ERROR), | |
568 | ||
569 | # Comments using the x embedded pattern modifier | |
570 | ||
571 | ("""(?x)w# comment 1 | |
572 | x y | |
573 | # comment 2 | |
574 | z""", 'wxyz', SUCCEED, 'found', 'wxyz'), | |
575 | ||
576 | # using the m embedded pattern modifier | |
577 | ||
578 | ('^abc', """jkl | |
579 | abc | |
580 | xyz""", FAIL), | |
581 | ('(?m)^abc', """jkl | |
582 | abc | |
583 | xyz""", SUCCEED, 'found', 'abc'), | |
584 | ||
585 | ('(?m)abc$', """jkl | |
586 | xyzabc | |
587 | 123""", SUCCEED, 'found', 'abc'), | |
588 | ||
589 | # using the s embedded pattern modifier | |
590 | ||
591 | ('a.b', 'a\nb', FAIL), | |
592 | ('(?s)a.b', 'a\nb', SUCCEED, 'found', 'a\nb'), | |
593 | ||
594 | # test \w, etc. both inside and outside character classes | |
595 | ||
596 | ('\\w+', '--ab_cd0123--', SUCCEED, 'found', 'ab_cd0123'), | |
597 | ('[\\w]+', '--ab_cd0123--', SUCCEED, 'found', 'ab_cd0123'), | |
598 | ('\\D+', '1234abc5678', SUCCEED, 'found', 'abc'), | |
599 | ('[\\D]+', '1234abc5678', SUCCEED, 'found', 'abc'), | |
600 | ('[\\da-fA-F]+', '123abc', SUCCEED, 'found', '123abc'), | |
601 | # not an error under PCRE/PRE: | |
602 | # ('[\\d-x]', '-', SYNTAX_ERROR), | |
603 | (r'([\s]*)([\S]*)([\s]*)', ' testing!1972', SUCCEED, 'g3+g2+g1', 'testing!1972 '), | |
604 | (r'(\s*)(\S*)(\s*)', ' testing!1972', SUCCEED, 'g3+g2+g1', 'testing!1972 '), | |
605 | ||
606 | (r'\xff', '\377', SUCCEED, 'found', chr(255)), | |
607 | # new \x semantics | |
608 | (r'\x00ff', '\377', FAIL), | |
609 | # (r'\x00ff', '\377', SUCCEED, 'found', chr(255)), | |
610 | (r'\t\n\v\r\f\a\g', '\t\n\v\r\f\ag', SUCCEED, 'found', '\t\n\v\r\f\ag'), | |
611 | ('\t\n\v\r\f\a\g', '\t\n\v\r\f\ag', SUCCEED, 'found', '\t\n\v\r\f\ag'), | |
612 | (r'\t\n\v\r\f\a', '\t\n\v\r\f\a', SUCCEED, 'found', chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7)), | |
613 | (r'[\t][\n][\v][\r][\f][\b]', '\t\n\v\r\f\b', SUCCEED, 'found', '\t\n\v\r\f\b'), | |
614 | ||
615 | # | |
616 | # post-1.5.2 additions | |
617 | ||
618 | # xmllib problem | |
619 | (r'(([a-z]+):)?([a-z]+)$', 'smil', SUCCEED, 'g1+"-"+g2+"-"+g3', 'None-None-smil'), | |
620 | # bug 110866: reference to undefined group | |
621 | (r'((.)\1+)', '', SYNTAX_ERROR), | |
622 | # bug 111869: search (PRE/PCRE fails on this one, SRE doesn't) | |
623 | (r'.*d', 'abc\nabd', SUCCEED, 'found', 'abd'), | |
624 | # bug 112468: various expected syntax errors | |
625 | (r'(', '', SYNTAX_ERROR), | |
626 | (r'[\41]', '!', SUCCEED, 'found', '!'), | |
627 | # bug 114033: nothing to repeat | |
628 | (r'(x?)?', 'x', SUCCEED, 'found', 'x'), | |
629 | # bug 115040: rescan if flags are modified inside pattern | |
630 | (r' (?x)foo ', 'foo', SUCCEED, 'found', 'foo'), | |
631 | # bug 115618: negative lookahead | |
632 | (r'(?<!abc)(d.f)', 'abcdefdof', SUCCEED, 'found', 'dof'), | |
633 | # bug 116251: character class bug | |
634 | (r'[\w-]+', 'laser_beam', SUCCEED, 'found', 'laser_beam'), | |
635 | # bug 123769+127259: non-greedy backtracking bug | |
636 | (r'.*?\S *:', 'xx:', SUCCEED, 'found', 'xx:'), | |
637 | (r'a[ ]*?\ (\d+).*', 'a 10', SUCCEED, 'found', 'a 10'), | |
638 | (r'a[ ]*?\ (\d+).*', 'a 10', SUCCEED, 'found', 'a 10'), | |
639 | # bug 127259: \Z shouldn't depend on multiline mode | |
640 | (r'(?ms).*?x\s*\Z(.*)','xx\nx\n', SUCCEED, 'g1', ''), | |
641 | # bug 128899: uppercase literals under the ignorecase flag | |
642 | (r'(?i)M+', 'MMM', SUCCEED, 'found', 'MMM'), | |
643 | (r'(?i)m+', 'MMM', SUCCEED, 'found', 'MMM'), | |
644 | (r'(?i)[M]+', 'MMM', SUCCEED, 'found', 'MMM'), | |
645 | (r'(?i)[m]+', 'MMM', SUCCEED, 'found', 'MMM'), | |
646 | # bug 130748: ^* should be an error (nothing to repeat) | |
647 | (r'^*', '', SYNTAX_ERROR), | |
648 | # bug 133283: minimizing repeat problem | |
649 | (r'"(?:\\"|[^"])*?"', r'"\""', SUCCEED, 'found', r'"\""'), | |
650 | # bug 477728: minimizing repeat problem | |
651 | (r'^.*?$', 'one\ntwo\nthree\n', FAIL), | |
652 | # bug 483789: minimizing repeat problem | |
653 | (r'a[^>]*?b', 'a>b', FAIL), | |
654 | # bug 490573: minimizing repeat problem | |
655 | (r'^a*?$', 'foo', FAIL), | |
656 | # bug 470582: nested groups problem | |
657 | (r'^((a)c)?(ab)$', 'ab', SUCCEED, 'g1+"-"+g2+"-"+g3', 'None-None-ab'), | |
658 | # another minimizing repeat problem (capturing groups in assertions) | |
659 | ('^([ab]*?)(?=(b)?)c', 'abc', SUCCEED, 'g1+"-"+g2', 'ab-None'), | |
660 | ('^([ab]*?)(?!(b))c', 'abc', SUCCEED, 'g1+"-"+g2', 'ab-None'), | |
661 | ('^([ab]*?)(?<!(a))c', 'abc', SUCCEED, 'g1+"-"+g2', 'ab-None'), | |
662 | ] | |
663 | ||
664 | try: | |
665 | u = eval("u'\N{LATIN CAPITAL LETTER A WITH DIAERESIS}'") | |
666 | except SyntaxError: | |
667 | pass | |
668 | else: | |
669 | tests.extend([ | |
670 | # bug 410271: \b broken under locales | |
671 | (r'\b.\b', 'a', SUCCEED, 'found', 'a'), | |
672 | (r'(?u)\b.\b', u, SUCCEED, 'found', u), | |
673 | (r'(?u)\w', u, SUCCEED, 'found', u), | |
674 | ]) |