Commit | Line | Data |
---|---|---|
86530b38 AT |
1 | import sys |
2 | sys.path = ['.'] + sys.path | |
3 | ||
4 | from test.test_support import verbose, run_unittest | |
5 | import re | |
6 | from sre import Scanner | |
7 | import sys, os, traceback | |
8 | from weakref import proxy | |
9 | ||
10 | # Misc tests from Tim Peters' re.doc | |
11 | ||
12 | # WARNING: Don't change details in these tests if you don't know | |
13 | # what you're doing. Some of these tests were carefuly modeled to | |
14 | # cover most of the code. | |
15 | ||
16 | import unittest | |
17 | ||
18 | class ReTests(unittest.TestCase): | |
19 | ||
20 | def test_weakref(self): | |
21 | s = 'QabbbcR' | |
22 | x = re.compile('ab+c') | |
23 | y = proxy(x) | |
24 | self.assertEqual(x.findall('QabbbcR'), y.findall('QabbbcR')) | |
25 | ||
26 | def test_search_star_plus(self): | |
27 | self.assertEqual(re.search('x*', 'axx').span(0), (0, 0)) | |
28 | self.assertEqual(re.search('x*', 'axx').span(), (0, 0)) | |
29 | self.assertEqual(re.search('x+', 'axx').span(0), (1, 3)) | |
30 | self.assertEqual(re.search('x+', 'axx').span(), (1, 3)) | |
31 | self.assertEqual(re.search('x', 'aaa'), None) | |
32 | self.assertEqual(re.match('a*', 'xxx').span(0), (0, 0)) | |
33 | self.assertEqual(re.match('a*', 'xxx').span(), (0, 0)) | |
34 | self.assertEqual(re.match('x*', 'xxxa').span(0), (0, 3)) | |
35 | self.assertEqual(re.match('x*', 'xxxa').span(), (0, 3)) | |
36 | self.assertEqual(re.match('a+', 'xxx'), None) | |
37 | ||
38 | def bump_num(self, matchobj): | |
39 | int_value = int(matchobj.group(0)) | |
40 | return str(int_value + 1) | |
41 | ||
42 | def test_basic_re_sub(self): | |
43 | self.assertEqual(re.sub("(?i)b+", "x", "bbbb BBBB"), 'x x') | |
44 | self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y'), | |
45 | '9.3 -3 24x100y') | |
46 | self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y', 3), | |
47 | '9.3 -3 23x99y') | |
48 | ||
49 | self.assertEqual(re.sub('.', lambda m: r"\n", 'x'), '\\n') | |
50 | self.assertEqual(re.sub('.', r"\n", 'x'), '\n') | |
51 | ||
52 | s = r"\1\1" | |
53 | self.assertEqual(re.sub('(.)', s, 'x'), 'xx') | |
54 | self.assertEqual(re.sub('(.)', re.escape(s), 'x'), s) | |
55 | self.assertEqual(re.sub('(.)', lambda m: s, 'x'), s) | |
56 | ||
57 | self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<a>', 'xx'), 'xxxx') | |
58 | self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<1>', 'xx'), 'xxxx') | |
59 | self.assertEqual(re.sub('(?P<unk>x)', '\g<unk>\g<unk>', 'xx'), 'xxxx') | |
60 | self.assertEqual(re.sub('(?P<unk>x)', '\g<1>\g<1>', 'xx'), 'xxxx') | |
61 | ||
62 | self.assertEqual(re.sub('a',r'\t\n\v\r\f\a\b\B\Z\a\A\w\W\s\S\d\D','a'), | |
63 | '\t\n\v\r\f\a\b\\B\\Z\a\\A\\w\\W\\s\\S\\d\\D') | |
64 | self.assertEqual(re.sub('a', '\t\n\v\r\f\a', 'a'), '\t\n\v\r\f\a') | |
65 | self.assertEqual(re.sub('a', '\t\n\v\r\f\a', 'a'), | |
66 | (chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7))) | |
67 | ||
68 | self.assertEqual(re.sub('^\s*', 'X', 'test'), 'Xtest') | |
69 | ||
70 | def test_bug_449964(self): | |
71 | # fails for group followed by other escape | |
72 | self.assertEqual(re.sub(r'(?P<unk>x)', '\g<1>\g<1>\\b', 'xx'), | |
73 | 'xx\bxx\b') | |
74 | ||
75 | def test_bug_449000(self): | |
76 | # Test for sub() on escaped characters | |
77 | self.assertEqual(re.sub(r'\r\n', r'\n', 'abc\r\ndef\r\n'), | |
78 | 'abc\ndef\n') | |
79 | self.assertEqual(re.sub('\r\n', r'\n', 'abc\r\ndef\r\n'), | |
80 | 'abc\ndef\n') | |
81 | self.assertEqual(re.sub(r'\r\n', '\n', 'abc\r\ndef\r\n'), | |
82 | 'abc\ndef\n') | |
83 | self.assertEqual(re.sub('\r\n', '\n', 'abc\r\ndef\r\n'), | |
84 | 'abc\ndef\n') | |
85 | ||
86 | def test_sub_template_numeric_escape(self): | |
87 | # bug 776311 and friends | |
88 | self.assertEqual(re.sub('x', r'\0', 'x'), '\0') | |
89 | self.assertEqual(re.sub('x', r'\000', 'x'), '\000') | |
90 | self.assertEqual(re.sub('x', r'\001', 'x'), '\001') | |
91 | self.assertEqual(re.sub('x', r'\008', 'x'), '\0' + '8') | |
92 | self.assertEqual(re.sub('x', r'\009', 'x'), '\0' + '9') | |
93 | self.assertEqual(re.sub('x', r'\111', 'x'), '\111') | |
94 | self.assertEqual(re.sub('x', r'\117', 'x'), '\117') | |
95 | ||
96 | self.assertEqual(re.sub('x', r'\1111', 'x'), '\1111') | |
97 | self.assertEqual(re.sub('x', r'\1111', 'x'), '\111' + '1') | |
98 | ||
99 | self.assertEqual(re.sub('x', r'\00', 'x'), '\x00') | |
100 | self.assertEqual(re.sub('x', r'\07', 'x'), '\x07') | |
101 | self.assertEqual(re.sub('x', r'\08', 'x'), '\0' + '8') | |
102 | self.assertEqual(re.sub('x', r'\09', 'x'), '\0' + '9') | |
103 | self.assertEqual(re.sub('x', r'\0a', 'x'), '\0' + 'a') | |
104 | ||
105 | self.assertEqual(re.sub('x', r'\400', 'x'), '\0') | |
106 | self.assertEqual(re.sub('x', r'\777', 'x'), '\377') | |
107 | ||
108 | self.assertRaises(re.error, re.sub, 'x', r'\1', 'x') | |
109 | self.assertRaises(re.error, re.sub, 'x', r'\8', 'x') | |
110 | self.assertRaises(re.error, re.sub, 'x', r'\9', 'x') | |
111 | self.assertRaises(re.error, re.sub, 'x', r'\11', 'x') | |
112 | self.assertRaises(re.error, re.sub, 'x', r'\18', 'x') | |
113 | self.assertRaises(re.error, re.sub, 'x', r'\1a', 'x') | |
114 | self.assertRaises(re.error, re.sub, 'x', r'\90', 'x') | |
115 | self.assertRaises(re.error, re.sub, 'x', r'\99', 'x') | |
116 | self.assertRaises(re.error, re.sub, 'x', r'\118', 'x') # r'\11' + '8' | |
117 | self.assertRaises(re.error, re.sub, 'x', r'\11a', 'x') | |
118 | self.assertRaises(re.error, re.sub, 'x', r'\181', 'x') # r'\18' + '1' | |
119 | self.assertRaises(re.error, re.sub, 'x', r'\800', 'x') # r'\80' + '0' | |
120 | ||
121 | # in python2.3 (etc), these loop endlessly in sre_parser.py | |
122 | self.assertEqual(re.sub('(((((((((((x)))))))))))', r'\11', 'x'), 'x') | |
123 | self.assertEqual(re.sub('((((((((((y))))))))))(.)', r'\118', 'xyz'), | |
124 | 'xz8') | |
125 | self.assertEqual(re.sub('((((((((((y))))))))))(.)', r'\11a', 'xyz'), | |
126 | 'xza') | |
127 | ||
128 | def test_qualified_re_sub(self): | |
129 | self.assertEqual(re.sub('a', 'b', 'aaaaa'), 'bbbbb') | |
130 | self.assertEqual(re.sub('a', 'b', 'aaaaa', 1), 'baaaa') | |
131 | ||
132 | def test_bug_114660(self): | |
133 | self.assertEqual(re.sub(r'(\S)\s+(\S)', r'\1 \2', 'hello there'), | |
134 | 'hello there') | |
135 | ||
136 | def test_bug_462270(self): | |
137 | # Test for empty sub() behaviour, see SF bug #462270 | |
138 | self.assertEqual(re.sub('x*', '-', 'abxd'), '-a-b-d-') | |
139 | self.assertEqual(re.sub('x+', '-', 'abxd'), 'ab-d') | |
140 | ||
141 | def test_symbolic_refs(self): | |
142 | self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<a', 'xx') | |
143 | self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<', 'xx') | |
144 | self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g', 'xx') | |
145 | self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<a a>', 'xx') | |
146 | self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<1a1>', 'xx') | |
147 | self.assertRaises(IndexError, re.sub, '(?P<a>x)', '\g<ab>', 'xx') | |
148 | self.assertRaises(re.error, re.sub, '(?P<a>x)|(?P<b>y)', '\g<b>', 'xx') | |
149 | self.assertRaises(re.error, re.sub, '(?P<a>x)|(?P<b>y)', '\\2', 'xx') | |
150 | self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<-1>', 'xx') | |
151 | ||
152 | def test_re_subn(self): | |
153 | self.assertEqual(re.subn("(?i)b+", "x", "bbbb BBBB"), ('x x', 2)) | |
154 | self.assertEqual(re.subn("b+", "x", "bbbb BBBB"), ('x BBBB', 1)) | |
155 | self.assertEqual(re.subn("b+", "x", "xyz"), ('xyz', 0)) | |
156 | self.assertEqual(re.subn("b*", "x", "xyz"), ('xxxyxzx', 4)) | |
157 | self.assertEqual(re.subn("b*", "x", "xyz", 2), ('xxxyz', 2)) | |
158 | ||
159 | def test_re_split(self): | |
160 | self.assertEqual(re.split(":", ":a:b::c"), ['', 'a', 'b', '', 'c']) | |
161 | self.assertEqual(re.split(":*", ":a:b::c"), ['', 'a', 'b', 'c']) | |
162 | self.assertEqual(re.split("(:*)", ":a:b::c"), | |
163 | ['', ':', 'a', ':', 'b', '::', 'c']) | |
164 | self.assertEqual(re.split("(?::*)", ":a:b::c"), ['', 'a', 'b', 'c']) | |
165 | self.assertEqual(re.split("(:)*", ":a:b::c"), | |
166 | ['', ':', 'a', ':', 'b', ':', 'c']) | |
167 | self.assertEqual(re.split("([b:]+)", ":a:b::c"), | |
168 | ['', ':', 'a', ':b::', 'c']) | |
169 | self.assertEqual(re.split("(b)|(:+)", ":a:b::c"), | |
170 | ['', None, ':', 'a', None, ':', '', 'b', None, '', | |
171 | None, '::', 'c']) | |
172 | self.assertEqual(re.split("(?:b)|(?::+)", ":a:b::c"), | |
173 | ['', 'a', '', '', 'c']) | |
174 | ||
175 | def test_qualified_re_split(self): | |
176 | self.assertEqual(re.split(":", ":a:b::c", 2), ['', 'a', 'b::c']) | |
177 | self.assertEqual(re.split(':', 'a:b:c:d', 2), ['a', 'b', 'c:d']) | |
178 | self.assertEqual(re.split("(:)", ":a:b::c", 2), | |
179 | ['', ':', 'a', ':', 'b::c']) | |
180 | self.assertEqual(re.split("(:*)", ":a:b::c", 2), | |
181 | ['', ':', 'a', ':', 'b::c']) | |
182 | ||
183 | def test_re_findall(self): | |
184 | self.assertEqual(re.findall(":+", "abc"), []) | |
185 | self.assertEqual(re.findall(":+", "a:b::c:::d"), [":", "::", ":::"]) | |
186 | self.assertEqual(re.findall("(:+)", "a:b::c:::d"), [":", "::", ":::"]) | |
187 | self.assertEqual(re.findall("(:)(:*)", "a:b::c:::d"), [(":", ""), | |
188 | (":", ":"), | |
189 | (":", "::")]) | |
190 | ||
191 | def test_bug_117612(self): | |
192 | self.assertEqual(re.findall(r"(a|(b))", "aba"), | |
193 | [("a", ""),("b", "b"),("a", "")]) | |
194 | ||
195 | def test_re_match(self): | |
196 | self.assertEqual(re.match('a', 'a').groups(), ()) | |
197 | self.assertEqual(re.match('(a)', 'a').groups(), ('a',)) | |
198 | self.assertEqual(re.match(r'(a)', 'a').group(0), 'a') | |
199 | self.assertEqual(re.match(r'(a)', 'a').group(1), 'a') | |
200 | self.assertEqual(re.match(r'(a)', 'a').group(1, 1), ('a', 'a')) | |
201 | ||
202 | pat = re.compile('((a)|(b))(c)?') | |
203 | self.assertEqual(pat.match('a').groups(), ('a', 'a', None, None)) | |
204 | self.assertEqual(pat.match('b').groups(), ('b', None, 'b', None)) | |
205 | self.assertEqual(pat.match('ac').groups(), ('a', 'a', None, 'c')) | |
206 | self.assertEqual(pat.match('bc').groups(), ('b', None, 'b', 'c')) | |
207 | self.assertEqual(pat.match('bc').groups(""), ('b', "", 'b', 'c')) | |
208 | ||
209 | # A single group | |
210 | m = re.match('(a)', 'a') | |
211 | self.assertEqual(m.group(0), 'a') | |
212 | self.assertEqual(m.group(0), 'a') | |
213 | self.assertEqual(m.group(1), 'a') | |
214 | self.assertEqual(m.group(1, 1), ('a', 'a')) | |
215 | ||
216 | pat = re.compile('(?:(?P<a1>a)|(?P<b2>b))(?P<c3>c)?') | |
217 | self.assertEqual(pat.match('a').group(1, 2, 3), ('a', None, None)) | |
218 | self.assertEqual(pat.match('b').group('a1', 'b2', 'c3'), | |
219 | (None, 'b', None)) | |
220 | self.assertEqual(pat.match('ac').group(1, 'b2', 3), ('a', None, 'c')) | |
221 | ||
222 | def test_re_groupref_exists(self): | |
223 | self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a)').groups(), | |
224 | ('(', 'a')) | |
225 | self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', 'a').groups(), | |
226 | (None, 'a')) | |
227 | self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', 'a)'), None) | |
228 | self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a'), None) | |
229 | self.assertEqual(re.match('^(?:(a)|c)((?(1)b|d))$', 'ab').groups(), | |
230 | ('a', 'b')) | |
231 | self.assertEqual(re.match('^(?:(a)|c)((?(1)b|d))$', 'cd').groups(), | |
232 | (None, 'd')) | |
233 | self.assertEqual(re.match('^(?:(a)|c)((?(1)|d))$', 'cd').groups(), | |
234 | (None, 'd')) | |
235 | self.assertEqual(re.match('^(?:(a)|c)((?(1)|d))$', 'a').groups(), | |
236 | ('a', '')) | |
237 | ||
238 | # Tests for bug #1177831: exercise groups other than the first group | |
239 | p = re.compile('(?P<g1>a)(?P<g2>b)?((?(g2)c|d))') | |
240 | self.assertEqual(p.match('abc').groups(), | |
241 | ('a', 'b', 'c')) | |
242 | self.assertEqual(p.match('ad').groups(), | |
243 | ('a', None, 'd')) | |
244 | self.assertEqual(p.match('abd'), None) | |
245 | self.assertEqual(p.match('ac'), None) | |
246 | ||
247 | ||
248 | def test_re_groupref(self): | |
249 | self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', '|a|').groups(), | |
250 | ('|', 'a')) | |
251 | self.assertEqual(re.match(r'^(\|)?([^()]+)\1?$', 'a').groups(), | |
252 | (None, 'a')) | |
253 | self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', 'a|'), None) | |
254 | self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', '|a'), None) | |
255 | self.assertEqual(re.match(r'^(?:(a)|c)(\1)$', 'aa').groups(), | |
256 | ('a', 'a')) | |
257 | self.assertEqual(re.match(r'^(?:(a)|c)(\1)?$', 'c').groups(), | |
258 | (None, None)) | |
259 | ||
260 | def test_groupdict(self): | |
261 | self.assertEqual(re.match('(?P<first>first) (?P<second>second)', | |
262 | 'first second').groupdict(), | |
263 | {'first':'first', 'second':'second'}) | |
264 | ||
265 | def test_expand(self): | |
266 | self.assertEqual(re.match("(?P<first>first) (?P<second>second)", | |
267 | "first second") | |
268 | .expand(r"\2 \1 \g<second> \g<first>"), | |
269 | "second first second first") | |
270 | ||
271 | def test_repeat_minmax(self): | |
272 | self.assertEqual(re.match("^(\w){1}$", "abc"), None) | |
273 | self.assertEqual(re.match("^(\w){1}?$", "abc"), None) | |
274 | self.assertEqual(re.match("^(\w){1,2}$", "abc"), None) | |
275 | self.assertEqual(re.match("^(\w){1,2}?$", "abc"), None) | |
276 | ||
277 | self.assertEqual(re.match("^(\w){3}$", "abc").group(1), "c") | |
278 | self.assertEqual(re.match("^(\w){1,3}$", "abc").group(1), "c") | |
279 | self.assertEqual(re.match("^(\w){1,4}$", "abc").group(1), "c") | |
280 | self.assertEqual(re.match("^(\w){3,4}?$", "abc").group(1), "c") | |
281 | self.assertEqual(re.match("^(\w){3}?$", "abc").group(1), "c") | |
282 | self.assertEqual(re.match("^(\w){1,3}?$", "abc").group(1), "c") | |
283 | self.assertEqual(re.match("^(\w){1,4}?$", "abc").group(1), "c") | |
284 | self.assertEqual(re.match("^(\w){3,4}?$", "abc").group(1), "c") | |
285 | ||
286 | self.assertEqual(re.match("^x{1}$", "xxx"), None) | |
287 | self.assertEqual(re.match("^x{1}?$", "xxx"), None) | |
288 | self.assertEqual(re.match("^x{1,2}$", "xxx"), None) | |
289 | self.assertEqual(re.match("^x{1,2}?$", "xxx"), None) | |
290 | ||
291 | self.assertNotEqual(re.match("^x{3}$", "xxx"), None) | |
292 | self.assertNotEqual(re.match("^x{1,3}$", "xxx"), None) | |
293 | self.assertNotEqual(re.match("^x{1,4}$", "xxx"), None) | |
294 | self.assertNotEqual(re.match("^x{3,4}?$", "xxx"), None) | |
295 | self.assertNotEqual(re.match("^x{3}?$", "xxx"), None) | |
296 | self.assertNotEqual(re.match("^x{1,3}?$", "xxx"), None) | |
297 | self.assertNotEqual(re.match("^x{1,4}?$", "xxx"), None) | |
298 | self.assertNotEqual(re.match("^x{3,4}?$", "xxx"), None) | |
299 | ||
300 | self.assertEqual(re.match("^x{}$", "xxx"), None) | |
301 | self.assertNotEqual(re.match("^x{}$", "x{}"), None) | |
302 | ||
303 | def test_getattr(self): | |
304 | self.assertEqual(re.match("(a)", "a").pos, 0) | |
305 | self.assertEqual(re.match("(a)", "a").endpos, 1) | |
306 | self.assertEqual(re.match("(a)", "a").string, "a") | |
307 | self.assertEqual(re.match("(a)", "a").regs, ((0, 1), (0, 1))) | |
308 | self.assertNotEqual(re.match("(a)", "a").re, None) | |
309 | ||
310 | def test_special_escapes(self): | |
311 | self.assertEqual(re.search(r"\b(b.)\b", | |
312 | "abcd abc bcd bx").group(1), "bx") | |
313 | self.assertEqual(re.search(r"\B(b.)\B", | |
314 | "abc bcd bc abxd").group(1), "bx") | |
315 | self.assertEqual(re.search(r"\b(b.)\b", | |
316 | "abcd abc bcd bx", re.LOCALE).group(1), "bx") | |
317 | self.assertEqual(re.search(r"\B(b.)\B", | |
318 | "abc bcd bc abxd", re.LOCALE).group(1), "bx") | |
319 | self.assertEqual(re.search(r"\b(b.)\b", | |
320 | "abcd abc bcd bx", re.UNICODE).group(1), "bx") | |
321 | self.assertEqual(re.search(r"\B(b.)\B", | |
322 | "abc bcd bc abxd", re.UNICODE).group(1), "bx") | |
323 | self.assertEqual(re.search(r"^abc$", "\nabc\n", re.M).group(0), "abc") | |
324 | self.assertEqual(re.search(r"^\Aabc\Z$", "abc", re.M).group(0), "abc") | |
325 | self.assertEqual(re.search(r"^\Aabc\Z$", "\nabc\n", re.M), None) | |
326 | self.assertEqual(re.search(r"\b(b.)\b", | |
327 | u"abcd abc bcd bx").group(1), "bx") | |
328 | self.assertEqual(re.search(r"\B(b.)\B", | |
329 | u"abc bcd bc abxd").group(1), "bx") | |
330 | self.assertEqual(re.search(r"^abc$", u"\nabc\n", re.M).group(0), "abc") | |
331 | self.assertEqual(re.search(r"^\Aabc\Z$", u"abc", re.M).group(0), "abc") | |
332 | self.assertEqual(re.search(r"^\Aabc\Z$", u"\nabc\n", re.M), None) | |
333 | self.assertEqual(re.search(r"\d\D\w\W\s\S", | |
334 | "1aa! a").group(0), "1aa! a") | |
335 | self.assertEqual(re.search(r"\d\D\w\W\s\S", | |
336 | "1aa! a", re.LOCALE).group(0), "1aa! a") | |
337 | self.assertEqual(re.search(r"\d\D\w\W\s\S", | |
338 | "1aa! a", re.UNICODE).group(0), "1aa! a") | |
339 | ||
340 | def test_ignore_case(self): | |
341 | self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC") | |
342 | self.assertEqual(re.match("abc", u"ABC", re.I).group(0), "ABC") | |
343 | ||
344 | def test_bigcharset(self): | |
345 | self.assertEqual(re.match(u"([\u2222\u2223])", | |
346 | u"\u2222").group(1), u"\u2222") | |
347 | self.assertEqual(re.match(u"([\u2222\u2223])", | |
348 | u"\u2222", re.UNICODE).group(1), u"\u2222") | |
349 | ||
350 | def test_anyall(self): | |
351 | self.assertEqual(re.match("a.b", "a\nb", re.DOTALL).group(0), | |
352 | "a\nb") | |
353 | self.assertEqual(re.match("a.*b", "a\n\nb", re.DOTALL).group(0), | |
354 | "a\n\nb") | |
355 | ||
356 | def test_non_consuming(self): | |
357 | self.assertEqual(re.match("(a(?=\s[^a]))", "a b").group(1), "a") | |
358 | self.assertEqual(re.match("(a(?=\s[^a]*))", "a b").group(1), "a") | |
359 | self.assertEqual(re.match("(a(?=\s[abc]))", "a b").group(1), "a") | |
360 | self.assertEqual(re.match("(a(?=\s[abc]*))", "a bc").group(1), "a") | |
361 | self.assertEqual(re.match(r"(a)(?=\s\1)", "a a").group(1), "a") | |
362 | self.assertEqual(re.match(r"(a)(?=\s\1*)", "a aa").group(1), "a") | |
363 | self.assertEqual(re.match(r"(a)(?=\s(abc|a))", "a a").group(1), "a") | |
364 | ||
365 | self.assertEqual(re.match(r"(a(?!\s[^a]))", "a a").group(1), "a") | |
366 | self.assertEqual(re.match(r"(a(?!\s[abc]))", "a d").group(1), "a") | |
367 | self.assertEqual(re.match(r"(a)(?!\s\1)", "a b").group(1), "a") | |
368 | self.assertEqual(re.match(r"(a)(?!\s(abc|a))", "a b").group(1), "a") | |
369 | ||
370 | def test_ignore_case(self): | |
371 | self.assertEqual(re.match(r"(a\s[^a])", "a b", re.I).group(1), "a b") | |
372 | self.assertEqual(re.match(r"(a\s[^a]*)", "a bb", re.I).group(1), "a bb") | |
373 | self.assertEqual(re.match(r"(a\s[abc])", "a b", re.I).group(1), "a b") | |
374 | self.assertEqual(re.match(r"(a\s[abc]*)", "a bb", re.I).group(1), "a bb") | |
375 | self.assertEqual(re.match(r"((a)\s\2)", "a a", re.I).group(1), "a a") | |
376 | self.assertEqual(re.match(r"((a)\s\2*)", "a aa", re.I).group(1), "a aa") | |
377 | self.assertEqual(re.match(r"((a)\s(abc|a))", "a a", re.I).group(1), "a a") | |
378 | self.assertEqual(re.match(r"((a)\s(abc|a)*)", "a aa", re.I).group(1), "a aa") | |
379 | ||
380 | def test_category(self): | |
381 | self.assertEqual(re.match(r"(\s)", " ").group(1), " ") | |
382 | ||
383 | def test_getlower(self): | |
384 | import _sre | |
385 | self.assertEqual(_sre.getlower(ord('A'), 0), ord('a')) | |
386 | self.assertEqual(_sre.getlower(ord('A'), re.LOCALE), ord('a')) | |
387 | self.assertEqual(_sre.getlower(ord('A'), re.UNICODE), ord('a')) | |
388 | ||
389 | self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC") | |
390 | self.assertEqual(re.match("abc", u"ABC", re.I).group(0), "ABC") | |
391 | ||
392 | def test_not_literal(self): | |
393 | self.assertEqual(re.search("\s([^a])", " b").group(1), "b") | |
394 | self.assertEqual(re.search("\s([^a]*)", " bb").group(1), "bb") | |
395 | ||
396 | def test_search_coverage(self): | |
397 | self.assertEqual(re.search("\s(b)", " b").group(1), "b") | |
398 | self.assertEqual(re.search("a\s", "a ").group(0), "a ") | |
399 | ||
400 | def test_re_escape(self): | |
401 | p="" | |
402 | for i in range(0, 256): | |
403 | p = p + chr(i) | |
404 | self.assertEqual(re.match(re.escape(chr(i)), chr(i)) is not None, | |
405 | True) | |
406 | self.assertEqual(re.match(re.escape(chr(i)), chr(i)).span(), (0,1)) | |
407 | ||
408 | pat=re.compile(re.escape(p)) | |
409 | self.assertEqual(pat.match(p) is not None, True) | |
410 | self.assertEqual(pat.match(p).span(), (0,256)) | |
411 | ||
412 | def test_pickling(self): | |
413 | import pickle | |
414 | self.pickle_test(pickle) | |
415 | import cPickle | |
416 | self.pickle_test(cPickle) | |
417 | ||
418 | def pickle_test(self, pickle): | |
419 | oldpat = re.compile('a(?:b|(c|e){1,2}?|d)+?(.)') | |
420 | s = pickle.dumps(oldpat) | |
421 | newpat = pickle.loads(s) | |
422 | self.assertEqual(oldpat, newpat) | |
423 | ||
424 | def test_constants(self): | |
425 | self.assertEqual(re.I, re.IGNORECASE) | |
426 | self.assertEqual(re.L, re.LOCALE) | |
427 | self.assertEqual(re.M, re.MULTILINE) | |
428 | self.assertEqual(re.S, re.DOTALL) | |
429 | self.assertEqual(re.X, re.VERBOSE) | |
430 | ||
431 | def test_flags(self): | |
432 | for flag in [re.I, re.M, re.X, re.S, re.L]: | |
433 | self.assertNotEqual(re.compile('^pattern$', flag), None) | |
434 | ||
435 | def test_sre_character_literals(self): | |
436 | for i in [0, 8, 16, 32, 64, 127, 128, 255]: | |
437 | self.assertNotEqual(re.match(r"\%03o" % i, chr(i)), None) | |
438 | self.assertNotEqual(re.match(r"\%03o0" % i, chr(i)+"0"), None) | |
439 | self.assertNotEqual(re.match(r"\%03o8" % i, chr(i)+"8"), None) | |
440 | self.assertNotEqual(re.match(r"\x%02x" % i, chr(i)), None) | |
441 | self.assertNotEqual(re.match(r"\x%02x0" % i, chr(i)+"0"), None) | |
442 | self.assertNotEqual(re.match(r"\x%02xz" % i, chr(i)+"z"), None) | |
443 | self.assertRaises(re.error, re.match, "\911", "") | |
444 | ||
445 | def test_sre_character_class_literals(self): | |
446 | for i in [0, 8, 16, 32, 64, 127, 128, 255]: | |
447 | self.assertNotEqual(re.match(r"[\%03o]" % i, chr(i)), None) | |
448 | self.assertNotEqual(re.match(r"[\%03o0]" % i, chr(i)), None) | |
449 | self.assertNotEqual(re.match(r"[\%03o8]" % i, chr(i)), None) | |
450 | self.assertNotEqual(re.match(r"[\x%02x]" % i, chr(i)), None) | |
451 | self.assertNotEqual(re.match(r"[\x%02x0]" % i, chr(i)), None) | |
452 | self.assertNotEqual(re.match(r"[\x%02xz]" % i, chr(i)), None) | |
453 | self.assertRaises(re.error, re.match, "[\911]", "") | |
454 | ||
455 | def test_bug_113254(self): | |
456 | self.assertEqual(re.match(r'(a)|(b)', 'b').start(1), -1) | |
457 | self.assertEqual(re.match(r'(a)|(b)', 'b').end(1), -1) | |
458 | self.assertEqual(re.match(r'(a)|(b)', 'b').span(1), (-1, -1)) | |
459 | ||
460 | def test_bug_527371(self): | |
461 | # bug described in patches 527371/672491 | |
462 | self.assertEqual(re.match(r'(a)?a','a').lastindex, None) | |
463 | self.assertEqual(re.match(r'(a)(b)?b','ab').lastindex, 1) | |
464 | self.assertEqual(re.match(r'(?P<a>a)(?P<b>b)?b','ab').lastgroup, 'a') | |
465 | self.assertEqual(re.match("(?P<a>a(b))", "ab").lastgroup, 'a') | |
466 | self.assertEqual(re.match("((a))", "a").lastindex, 1) | |
467 | ||
468 | def test_bug_545855(self): | |
469 | # bug 545855 -- This pattern failed to cause a compile error as it | |
470 | # should, instead provoking a TypeError. | |
471 | self.assertRaises(re.error, re.compile, 'foo[a-') | |
472 | ||
473 | def test_bug_418626(self): | |
474 | # bugs 418626 at al. -- Testing Greg Chapman's addition of op code | |
475 | # SRE_OP_MIN_REPEAT_ONE for eliminating recursion on simple uses of | |
476 | # pattern '*?' on a long string. | |
477 | self.assertEqual(re.match('.*?c', 10000*'ab'+'cd').end(0), 20001) | |
478 | self.assertEqual(re.match('.*?cd', 5000*'ab'+'c'+5000*'ab'+'cde').end(0), | |
479 | 20003) | |
480 | self.assertEqual(re.match('.*?cd', 20000*'abc'+'de').end(0), 60001) | |
481 | # non-simple '*?' still used to hit the recursion limit, before the | |
482 | # non-recursive scheme was implemented. | |
483 | self.assertEqual(re.search('(a|b)*?c', 10000*'ab'+'cd').end(0), 20001) | |
484 | ||
485 | def test_bug_612074(self): | |
486 | pat=u"["+re.escape(u"\u2039")+u"]" | |
487 | self.assertEqual(re.compile(pat) and 1, 1) | |
488 | ||
489 | def test_stack_overflow(self): | |
490 | # nasty cases that used to overflow the straightforward recursive | |
491 | # implementation of repeated groups. | |
492 | self.assertEqual(re.match('(x)*', 50000*'x').group(1), 'x') | |
493 | self.assertEqual(re.match('(x)*y', 50000*'x'+'y').group(1), 'x') | |
494 | self.assertEqual(re.match('(x)*?y', 50000*'x'+'y').group(1), 'x') | |
495 | ||
496 | def test_scanner(self): | |
497 | def s_ident(scanner, token): return token | |
498 | def s_operator(scanner, token): return "op%s" % token | |
499 | def s_float(scanner, token): return float(token) | |
500 | def s_int(scanner, token): return int(token) | |
501 | ||
502 | scanner = Scanner([ | |
503 | (r"[a-zA-Z_]\w*", s_ident), | |
504 | (r"\d+\.\d*", s_float), | |
505 | (r"\d+", s_int), | |
506 | (r"=|\+|-|\*|/", s_operator), | |
507 | (r"\s+", None), | |
508 | ]) | |
509 | ||
510 | self.assertNotEqual(scanner.scanner.scanner("").pattern, None) | |
511 | ||
512 | self.assertEqual(scanner.scan("sum = 3*foo + 312.50 + bar"), | |
513 | (['sum', 'op=', 3, 'op*', 'foo', 'op+', 312.5, | |
514 | 'op+', 'bar'], '')) | |
515 | ||
516 | def test_bug_448951(self): | |
517 | # bug 448951 (similar to 429357, but with single char match) | |
518 | # (Also test greedy matches.) | |
519 | for op in '','?','*': | |
520 | self.assertEqual(re.match(r'((.%s):)?z'%op, 'z').groups(), | |
521 | (None, None)) | |
522 | self.assertEqual(re.match(r'((.%s):)?z'%op, 'a:z').groups(), | |
523 | ('a:', 'a')) | |
524 | ||
525 | def test_bug_725106(self): | |
526 | # capturing groups in alternatives in repeats | |
527 | self.assertEqual(re.match('^((a)|b)*', 'abc').groups(), | |
528 | ('b', 'a')) | |
529 | self.assertEqual(re.match('^(([ab])|c)*', 'abc').groups(), | |
530 | ('c', 'b')) | |
531 | self.assertEqual(re.match('^((d)|[ab])*', 'abc').groups(), | |
532 | ('b', None)) | |
533 | self.assertEqual(re.match('^((a)c|[ab])*', 'abc').groups(), | |
534 | ('b', None)) | |
535 | self.assertEqual(re.match('^((a)|b)*?c', 'abc').groups(), | |
536 | ('b', 'a')) | |
537 | self.assertEqual(re.match('^(([ab])|c)*?d', 'abcd').groups(), | |
538 | ('c', 'b')) | |
539 | self.assertEqual(re.match('^((d)|[ab])*?c', 'abc').groups(), | |
540 | ('b', None)) | |
541 | self.assertEqual(re.match('^((a)c|[ab])*?c', 'abc').groups(), | |
542 | ('b', None)) | |
543 | ||
544 | def test_bug_725149(self): | |
545 | # mark_stack_base restoring before restoring marks | |
546 | self.assertEqual(re.match('(a)(?:(?=(b)*)c)*', 'abb').groups(), | |
547 | ('a', None)) | |
548 | self.assertEqual(re.match('(a)((?!(b)*))*', 'abb').groups(), | |
549 | ('a', None, None)) | |
550 | ||
551 | def test_bug_764548(self): | |
552 | # bug 764548, re.compile() barfs on str/unicode subclasses | |
553 | try: | |
554 | unicode | |
555 | except NameError: | |
556 | return # no problem if we have no unicode | |
557 | class my_unicode(unicode): pass | |
558 | pat = re.compile(my_unicode("abc")) | |
559 | self.assertEqual(pat.match("xyz"), None) | |
560 | ||
561 | def test_finditer(self): | |
562 | iter = re.finditer(r":+", "a:b::c:::d") | |
563 | self.assertEqual([item.group(0) for item in iter], | |
564 | [":", "::", ":::"]) | |
565 | ||
566 | def test_bug_926075(self): | |
567 | try: | |
568 | unicode | |
569 | except NameError: | |
570 | return # no problem if we have no unicode | |
571 | self.assert_(re.compile('bug_926075') is not | |
572 | re.compile(eval("u'bug_926075'"))) | |
573 | ||
574 | def test_bug_931848(self): | |
575 | try: | |
576 | unicode | |
577 | except NameError: | |
578 | pass | |
579 | pattern = eval('u"[\u002E\u3002\uFF0E\uFF61]"') | |
580 | self.assertEqual(re.compile(pattern).split("a.b.c"), | |
581 | ['a','b','c']) | |
582 | ||
583 | def test_bug_581080(self): | |
584 | iter = re.finditer(r"\s", "a b") | |
585 | self.assertEqual(iter.next().span(), (1,2)) | |
586 | self.assertRaises(StopIteration, iter.next) | |
587 | ||
588 | scanner = re.compile(r"\s").scanner("a b") | |
589 | self.assertEqual(scanner.search().span(), (1, 2)) | |
590 | self.assertEqual(scanner.search(), None) | |
591 | ||
592 | def test_bug_817234(self): | |
593 | iter = re.finditer(r".*", "asdf") | |
594 | self.assertEqual(iter.next().span(), (0, 4)) | |
595 | self.assertEqual(iter.next().span(), (4, 4)) | |
596 | self.assertRaises(StopIteration, iter.next) | |
597 | ||
598 | ||
599 | def run_re_tests(): | |
600 | from test.re_tests import benchmarks, tests, SUCCEED, FAIL, SYNTAX_ERROR | |
601 | if verbose: | |
602 | print 'Running re_tests test suite' | |
603 | else: | |
604 | # To save time, only run the first and last 10 tests | |
605 | #tests = tests[:10] + tests[-10:] | |
606 | pass | |
607 | ||
608 | for t in tests: | |
609 | sys.stdout.flush() | |
610 | pattern = s = outcome = repl = expected = None | |
611 | if len(t) == 5: | |
612 | pattern, s, outcome, repl, expected = t | |
613 | elif len(t) == 3: | |
614 | pattern, s, outcome = t | |
615 | else: | |
616 | raise ValueError, ('Test tuples should have 3 or 5 fields', t) | |
617 | ||
618 | try: | |
619 | obj = re.compile(pattern) | |
620 | except re.error: | |
621 | if outcome == SYNTAX_ERROR: pass # Expected a syntax error | |
622 | else: | |
623 | print '=== Syntax error:', t | |
624 | except KeyboardInterrupt: raise KeyboardInterrupt | |
625 | except: | |
626 | print '*** Unexpected error ***', t | |
627 | if verbose: | |
628 | traceback.print_exc(file=sys.stdout) | |
629 | else: | |
630 | try: | |
631 | result = obj.search(s) | |
632 | except re.error, msg: | |
633 | print '=== Unexpected exception', t, repr(msg) | |
634 | if outcome == SYNTAX_ERROR: | |
635 | # This should have been a syntax error; forget it. | |
636 | pass | |
637 | elif outcome == FAIL: | |
638 | if result is None: pass # No match, as expected | |
639 | else: print '=== Succeeded incorrectly', t | |
640 | elif outcome == SUCCEED: | |
641 | if result is not None: | |
642 | # Matched, as expected, so now we compute the | |
643 | # result string and compare it to our expected result. | |
644 | start, end = result.span(0) | |
645 | vardict={'found': result.group(0), | |
646 | 'groups': result.group(), | |
647 | 'flags': result.re.flags} | |
648 | for i in range(1, 100): | |
649 | try: | |
650 | gi = result.group(i) | |
651 | # Special hack because else the string concat fails: | |
652 | if gi is None: | |
653 | gi = "None" | |
654 | except IndexError: | |
655 | gi = "Error" | |
656 | vardict['g%d' % i] = gi | |
657 | for i in result.re.groupindex.keys(): | |
658 | try: | |
659 | gi = result.group(i) | |
660 | if gi is None: | |
661 | gi = "None" | |
662 | except IndexError: | |
663 | gi = "Error" | |
664 | vardict[i] = gi | |
665 | repl = eval(repl, vardict) | |
666 | if repl != expected: | |
667 | print '=== grouping error', t, | |
668 | print repr(repl) + ' should be ' + repr(expected) | |
669 | else: | |
670 | print '=== Failed incorrectly', t | |
671 | ||
672 | # Try the match on a unicode string, and check that it | |
673 | # still succeeds. | |
674 | try: | |
675 | result = obj.search(unicode(s, "latin-1")) | |
676 | if result is None: | |
677 | print '=== Fails on unicode match', t | |
678 | except NameError: | |
679 | continue # 1.5.2 | |
680 | except TypeError: | |
681 | continue # unicode test case | |
682 | ||
683 | # Try the match on a unicode pattern, and check that it | |
684 | # still succeeds. | |
685 | obj=re.compile(unicode(pattern, "latin-1")) | |
686 | result = obj.search(s) | |
687 | if result is None: | |
688 | print '=== Fails on unicode pattern match', t | |
689 | ||
690 | # Try the match with the search area limited to the extent | |
691 | # of the match and see if it still succeeds. \B will | |
692 | # break (because it won't match at the end or start of a | |
693 | # string), so we'll ignore patterns that feature it. | |
694 | ||
695 | if pattern[:2] != '\\B' and pattern[-2:] != '\\B' \ | |
696 | and result is not None: | |
697 | obj = re.compile(pattern) | |
698 | result = obj.search(s, result.start(0), result.end(0) + 1) | |
699 | if result is None: | |
700 | print '=== Failed on range-limited match', t | |
701 | ||
702 | # Try the match with IGNORECASE enabled, and check that it | |
703 | # still succeeds. | |
704 | obj = re.compile(pattern, re.IGNORECASE) | |
705 | result = obj.search(s) | |
706 | if result is None: | |
707 | print '=== Fails on case-insensitive match', t | |
708 | ||
709 | # Try the match with LOCALE enabled, and check that it | |
710 | # still succeeds. | |
711 | obj = re.compile(pattern, re.LOCALE) | |
712 | result = obj.search(s) | |
713 | if result is None: | |
714 | print '=== Fails on locale-sensitive match', t | |
715 | ||
716 | # Try the match with UNICODE locale enabled, and check | |
717 | # that it still succeeds. | |
718 | obj = re.compile(pattern, re.UNICODE) | |
719 | result = obj.search(s) | |
720 | if result is None: | |
721 | print '=== Fails on unicode-sensitive match', t | |
722 | ||
723 | def test_main(): | |
724 | run_unittest(ReTests) | |
725 | run_re_tests() | |
726 | ||
727 | if __name__ == "__main__": | |
728 | test_main() |