1
# Copyright (C) 2006-2010 Canonical Ltd
2
# -*- coding: utf-8 -*-
4
# This program is free software; you can redistribute it and/or modify
5
# it under the terms of the GNU General Public License as published by
6
# the Free Software Foundation; either version 2 of the License, or
7
# (at your option) any later version.
9
# This program is distributed in the hope that it will be useful,
10
# but WITHOUT ANY WARRANTY; without even the implied warranty of
11
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12
# GNU General Public License for more details.
14
# You should have received a copy of the GNU General Public License
15
# along with this program; if not, write to the Free Software
16
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20
from bzrlib import errors
21
from bzrlib.globbing import (
27
from bzrlib.tests import (
33
class TestGlobster(TestCase):
35
def assertMatch(self, matchset, glob_prefix=None):
36
for glob, positive, negative in matchset:
38
glob = glob_prefix + glob
39
globster = Globster([glob])
41
self.failUnless(globster.match(name), repr(
42
u'name "%s" does not match glob "%s" (re=%s)' %
43
(name, glob, globster._regex_patterns[0][0].pattern)))
45
self.failIf(globster.match(name), repr(
46
u'name "%s" does match glob "%s" (re=%s)' %
47
(name, glob, globster._regex_patterns[0][0].pattern)))
49
def assertMatchBasenameAndFullpath(self, matchset):
50
# test basename matcher
51
self.assertMatch(matchset)
52
# test fullpath matcher
53
self.assertMatch(matchset, glob_prefix='./')
55
def test_char_group_digit(self):
56
self.assertMatchBasenameAndFullpath([
57
# The definition of digit this uses includes arabic digits from
58
# non-latin scripts (arabic, indic, etc.) but neither roman
59
# numerals nor vulgar fractions. Some characters such as
60
# subscript/superscript digits may or may not match depending on
61
# the Python version used, see: <http://bugs.python.org/issue6561>
63
[u'0', u'5', u'\u0663', u'\u06f9', u'\u0f21'],
64
[u'T', u'q', u' ', u'\u8336', u'.']),
66
[u'T', u'q', u' ', u'\u8336', u'.'],
67
[u'0', u'5', u'\u0663', u'\u06f9', u'\u0f21']),
70
def test_char_group_space(self):
71
self.assertMatchBasenameAndFullpath([
73
[u' ', u'\t', u'\n', u'\xa0', u'\u2000', u'\u2002'],
74
[u'a', u'-', u'\u8336', u'.']),
76
[u'a', u'-', u'\u8336', u'.'],
77
[u' ', u'\t', u'\n', u'\xa0', u'\u2000', u'\u2002']),
80
def test_char_group_alnum(self):
81
self.assertMatchBasenameAndFullpath([
83
[u'a', u'Z', u'\u017e', u'\u8336'],
84
[u':', u'-', u'\u25cf', u'.']),
86
[u':', u'-', u'\u25cf', u'.'],
90
def test_char_group_ascii(self):
91
self.assertMatchBasenameAndFullpath([
93
[u'a', u'Q', u'^', u'.'],
94
[u'\xcc', u'\u8336']),
97
[u'a', u'Q', u'^', u'.']),
100
def test_char_group_blank(self):
101
self.assertMatchBasenameAndFullpath([
104
[u'x', u'y', u'z', u'.']),
106
[u'x', u'y', u'z', u'.'],
110
def test_char_group_cntrl(self):
111
self.assertMatchBasenameAndFullpath([
113
[u'\b', u'\t', '\x7f'],
114
[u'a', u'Q', u'\u8336', u'.']),
116
[u'a', u'Q', u'\u8336', u'.'],
117
[u'\b', u'\t', '\x7f']),
120
def test_char_group_range(self):
121
self.assertMatchBasenameAndFullpath([
130
[u'afoo', u'ABfoo']),
132
[u'fooAbar', u'foo.bar'],
134
(u'[\x20-\x30\u8336]',
135
[u'\040', u'\044', u'\u8336'],
137
(u'[^\x20-\x30\u8336]',
139
[u'\040', u'\044', u'\u8336']),
142
def test_regex(self):
145
[u'a', u'b', u'ccc'],
146
[u'd', u'aa', u'c+', u'-a']),
148
[u'a', u'b', u'ccc'],
149
[u'd', u'aa', u'c+', u'-a']),
150
(u'RE:(?P<a>.)(?P=a)',
152
[u'ab', u'aa', u'aaa']),
153
# test we can handle odd numbers of trailing backslashes
156
[u'a', u'ab', u'aa', u'aaa']),
159
def test_question_mark(self):
162
[u'xfoo', u'bar/xfoo', u'bar/\u8336foo', u'.foo', u'bar/.foo'],
163
[u'bar/foo', u'foo']),
165
[u'fooxbar', u'foo.bar', u'foo\u8336bar', u'qyzzy/foo.bar'],
168
[u'foo/xbar', u'foo/\u8336bar', u'foo/.bar'],
169
[u'foo/bar', u'bar/foo/xbar']),
172
def test_asterisk(self):
175
[u'xx', u'x.x', u'x\u8336..x', u'\u8336/x.x', u'x.y.x'],
176
[u'x/x', u'bar/x/bar/x', u'bax/abaxab']),
178
[u'foo/x', u'foo/bax', u'foo/a.x', u'foo/.x', u'foo/.q.x'],
181
[u'\u8336/x', u'foo/x', u'foo/bax', u'x/a.x', u'.foo/x',
182
u'\u8336/.x', u'foo/.q.x'],
185
[u'foo', u'foo.bar'],
186
[u'.foo', u'foo/bar', u'foo/.bar']),
188
[u'bar', u'foobar', ur'foo\nbar', u'foo.bar', u'foo/bar',
189
u'foo/foobar', u'foo/f.bar', u'.bar', u'foo/.bar'],
193
def test_double_asterisk(self):
195
# expected uses of double asterisk
197
[u'foo/x', u'foo/bar/x'],
198
[u'foox', u'foo/bax', u'foo/.x', u'foo/bar/bax']),
200
[u'bar', u'foo/bar'],
201
[u'foobar', u'foo.bar', u'foo/foobar', u'foo/f.bar',
202
u'.bar', u'foo/.bar']),
203
# check that we ignore extra *s, so *** is treated like ** not *.
205
[u'foo/x', u'foo/bar/x'],
206
[u'foox', u'foo/bax', u'foo/.x', u'foo/bar/bax']),
208
[u'bar', u'foo/bar'],
209
[u'foobar', u'foo.bar', u'foo/foobar', u'foo/f.bar',
210
u'.bar', u'foo/.bar']),
211
# the remaining tests check that ** is interpreted as *
212
# unless it is a whole path component
214
[u'x\u8336/x', u'x/x'],
215
[u'xx', u'x.x', u'bar/x/bar/x', u'x.y.x', u'x/y/x']),
217
[u'xx', u'x.x', u'x\u8336..x', u'foo/x.x', u'x.y.x'],
218
[u'bar/x/bar/x', u'xfoo/bar/x', u'x/x', u'bax/abaxab']),
220
[u'foo/x', u'foo/bax', u'foo/a.x', u'foo/.x', u'foo/.q.x'],
223
[u'foo', u'foo.bar'],
224
[u'.foo', u'foo/bar', u'foo/.bar']),
226
[u'bar', u'foobar', ur'foo\nbar', u'foo.bar', u'foo/bar',
227
u'foo/foobar', u'foo/f.bar', u'.bar', u'foo/.bar'],
231
def test_leading_dot_slash(self):
235
[u'\u8336/foo', u'barfoo', u'x/y/foo']),
238
[u'foo/bar', u'foo/.bar', u'x/foo/y']),
241
def test_backslash(self):
245
[u'\u8336/foo', u'barfoo', u'x/y/foo']),
248
[u'foo/bar', u'foo/.bar', u'x/foo/y']),
250
[u'foo/x', u'foo/bar/x'],
251
[u'foox', u'foo/bax', u'foo/.x', u'foo/bar/bax']),
254
def test_trailing_slash(self):
258
[u'\u8336/foo', u'barfoo', u'x/y/foo']),
261
[u'foo/', u'\u8336/foo', u'barfoo', u'x/y/foo']),
264
def test_leading_asterisk_dot(self):
267
[u'foo/bar/baz.x', u'\u8336/Q.x', u'foo.y.x', u'.foo.x',
268
u'bar/.foo.x', u'.x',],
271
[u'foo/b.bar', u'foo/a.b.bar', u'foo/.bar'],
274
[u'foo.py.~1~', u'.foo.py.~1~'],
278
def test_end_anchor(self):
288
def test_mixed_globs(self):
289
"""tests handling of combinations of path type matches.
291
The types being extension, basename and full path.
293
patterns = [ u'*.foo', u'.*.swp', u'./*.png']
294
globster = Globster(patterns)
295
self.assertEqual(u'*.foo', globster.match('bar.foo'))
296
self.assertEqual(u'./*.png', globster.match('foo.png'))
297
self.assertEqual(None, globster.match('foo/bar.png'))
298
self.assertEqual(u'.*.swp', globster.match('foo/.bar.py.swp'))
300
def test_large_globset(self):
301
"""tests that the globster can handle a large set of patterns.
303
Large is defined as more than supported by python regex groups,
305
This test assumes the globs are broken into regexs containing 99
308
patterns = [ u'*.%03d' % i for i in xrange(0,300) ]
309
globster = Globster(patterns)
310
# test the fence posts
311
for x in (0,98,99,197,198,296,297,299):
312
filename = u'foo.%03d' % x
313
self.assertEqual(patterns[x],globster.match(filename))
314
self.assertEqual(None,globster.match('foobar.300'))
316
def test_bad_pattern(self):
317
"""Ensure that globster handles bad patterns cleanly."""
318
patterns = [u'RE:[', u'/home/foo', u'RE:*.cpp']
319
g = Globster(patterns)
320
e = self.assertRaises(errors.InvalidPattern, g.match, 'filename')
321
self.assertContainsRe(e.msg,
322
"File.*ignore.*contains error.*RE:\[.*RE:\*\.cpp", flags=re.DOTALL)
325
class TestExceptionGlobster(TestCase):
327
def test_exclusion_patterns(self):
328
"""test that exception patterns are not matched"""
329
patterns = [ u'*', u'!./local', u'!./local/**/*', u'!RE:\.z.*',u'!!./.zcompdump' ]
330
globster = ExceptionGlobster(patterns)
331
self.assertEqual(u'*', globster.match('tmp/foo.txt'))
332
self.assertEqual(None, globster.match('local'))
333
self.assertEqual(None, globster.match('local/bin/wombat'))
334
self.assertEqual(None, globster.match('.zshrc'))
335
self.assertEqual(None, globster.match('.zfunctions/fiddle/flam'))
336
self.assertEqual(u'!!./.zcompdump', globster.match('.zcompdump'))
338
def test_exclusion_order(self):
339
"""test that ordering of exclusion patterns does not matter"""
340
patterns = [ u'static/**/*.html', u'!static/**/versionable.html']
341
globster = ExceptionGlobster(patterns)
342
self.assertEqual(u'static/**/*.html', globster.match('static/foo.html'))
343
self.assertEqual(None, globster.match('static/versionable.html'))
344
self.assertEqual(None, globster.match('static/bar/versionable.html'))
345
globster = ExceptionGlobster(reversed(patterns))
346
self.assertEqual(u'static/**/*.html', globster.match('static/foo.html'))
347
self.assertEqual(None, globster.match('static/versionable.html'))
348
self.assertEqual(None, globster.match('static/bar/versionable.html'))
350
class TestOrderedGlobster(TestCase):
352
def test_ordered_globs(self):
353
"""test that the first match in a list is the one found"""
354
patterns = [ u'*.foo', u'bar.*']
355
globster = _OrderedGlobster(patterns)
356
self.assertEqual(u'*.foo', globster.match('bar.foo'))
357
self.assertEqual(None, globster.match('foo.bar'))
358
globster = _OrderedGlobster(reversed(patterns))
359
self.assertEqual(u'bar.*', globster.match('bar.foo'))
360
self.assertEqual(None, globster.match('foo.bar'))
363
class TestNormalizePattern(TestCase):
365
def test_backslashes(self):
366
"""tests that backslashes are converted to forward slashes, multiple
367
backslashes are collapsed to single forward slashes and trailing
368
backslashes are removed"""
369
self.assertEqual(u'/', normalize_pattern(u'\\'))
370
self.assertEqual(u'/', normalize_pattern(u'\\\\'))
371
self.assertEqual(u'/foo/bar', normalize_pattern(u'\\foo\\bar'))
372
self.assertEqual(u'foo/bar', normalize_pattern(u'foo\\bar\\'))
373
self.assertEqual(u'/foo/bar', normalize_pattern(u'\\\\foo\\\\bar\\\\'))
375
def test_forward_slashes(self):
376
"""tests that multiple foward slashes are collapsed to single forward
377
slashes and trailing forward slashes are removed"""
378
self.assertEqual(u'/', normalize_pattern(u'/'))
379
self.assertEqual(u'/', normalize_pattern(u'//'))
380
self.assertEqual(u'/foo/bar', normalize_pattern(u'/foo/bar'))
381
self.assertEqual(u'foo/bar', normalize_pattern(u'foo/bar/'))
382
self.assertEqual(u'/foo/bar', normalize_pattern(u'//foo//bar//'))
384
def test_mixed_slashes(self):
385
"""tests that multiple mixed slashes are collapsed to single forward
386
slashes and trailing mixed slashes are removed"""
387
self.assertEqual(u'/foo/bar', normalize_pattern(u'\\/\\foo//\\///bar/\\\\/'))
added
removed
bzrlib/tests/test_globbing.py
