1
# Copyright (C) 2006-2011 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 (
32
class TestGlobster(TestCase):
34
def assertMatch(self, matchset, glob_prefix=None):
35
for glob, positive, negative in matchset:
37
glob = glob_prefix + glob
38
globster = Globster([glob])
40
self.assertTrue(globster.match(name), repr(
41
u'name "%s" does not match glob "%s" (re=%s)' %
42
(name, glob, globster._regex_patterns[0][0].pattern)))
44
self.assertFalse(globster.match(name), repr(
45
u'name "%s" does match glob "%s" (re=%s)' %
46
(name, glob, globster._regex_patterns[0][0].pattern)))
48
def assertMatchBasenameAndFullpath(self, matchset):
49
# test basename matcher
50
self.assertMatch(matchset)
51
# test fullpath matcher
52
self.assertMatch(matchset, glob_prefix='./')
54
def test_char_group_digit(self):
55
self.assertMatchBasenameAndFullpath([
56
# The definition of digit this uses includes arabic digits from
57
# non-latin scripts (arabic, indic, etc.) but neither roman
58
# numerals nor vulgar fractions. Some characters such as
59
# subscript/superscript digits may or may not match depending on
60
# the Python version used, see: <http://bugs.python.org/issue6561>
62
[u'0', u'5', u'\u0663', u'\u06f9', u'\u0f21'],
63
[u'T', u'q', u' ', u'\u8336', u'.']),
65
[u'T', u'q', u' ', u'\u8336', u'.'],
66
[u'0', u'5', u'\u0663', u'\u06f9', u'\u0f21']),
69
def test_char_group_space(self):
70
self.assertMatchBasenameAndFullpath([
72
[u' ', u'\t', u'\n', u'\xa0', u'\u2000', u'\u2002'],
73
[u'a', u'-', u'\u8336', u'.']),
75
[u'a', u'-', u'\u8336', u'.'],
76
[u' ', u'\t', u'\n', u'\xa0', u'\u2000', u'\u2002']),
79
def test_char_group_alnum(self):
80
self.assertMatchBasenameAndFullpath([
82
[u'a', u'Z', u'\u017e', u'\u8336'],
83
[u':', u'-', u'\u25cf', u'.']),
85
[u':', u'-', u'\u25cf', u'.'],
89
def test_char_group_ascii(self):
90
self.assertMatchBasenameAndFullpath([
92
[u'a', u'Q', u'^', u'.'],
93
[u'\xcc', u'\u8336']),
96
[u'a', u'Q', u'^', u'.']),
99
def test_char_group_blank(self):
100
self.assertMatchBasenameAndFullpath([
103
[u'x', u'y', u'z', u'.']),
105
[u'x', u'y', u'z', u'.'],
109
def test_char_group_cntrl(self):
110
self.assertMatchBasenameAndFullpath([
112
[u'\b', u'\t', '\x7f'],
113
[u'a', u'Q', u'\u8336', u'.']),
115
[u'a', u'Q', u'\u8336', u'.'],
116
[u'\b', u'\t', '\x7f']),
119
def test_char_group_range(self):
120
self.assertMatchBasenameAndFullpath([
129
[u'afoo', u'ABfoo']),
131
[u'fooAbar', u'foo.bar'],
133
(u'[\x20-\x30\u8336]',
134
[u'\040', u'\044', u'\u8336'],
136
(u'[^\x20-\x30\u8336]',
138
[u'\040', u'\044', u'\u8336']),
141
def test_regex(self):
144
[u'a', u'b', u'ccc'],
145
[u'd', u'aa', u'c+', u'-a']),
147
[u'a', u'b', u'ccc'],
148
[u'd', u'aa', u'c+', u'-a']),
149
(u'RE:(?P<a>.)(?P=a)',
151
[u'ab', u'aa', u'aaa']),
152
# test we can handle odd numbers of trailing backslashes
155
[u'a', u'ab', u'aa', u'aaa']),
158
def test_question_mark(self):
161
[u'xfoo', u'bar/xfoo', u'bar/\u8336foo', u'.foo', u'bar/.foo'],
162
[u'bar/foo', u'foo']),
164
[u'fooxbar', u'foo.bar', u'foo\u8336bar', u'qyzzy/foo.bar'],
167
[u'foo/xbar', u'foo/\u8336bar', u'foo/.bar'],
168
[u'foo/bar', u'bar/foo/xbar']),
171
def test_asterisk(self):
174
[u'xx', u'x.x', u'x\u8336..x', u'\u8336/x.x', u'x.y.x'],
175
[u'x/x', u'bar/x/bar/x', u'bax/abaxab']),
177
[u'foo/x', u'foo/bax', u'foo/a.x', u'foo/.x', u'foo/.q.x'],
180
[u'\u8336/x', u'foo/x', u'foo/bax', u'x/a.x', u'.foo/x',
181
u'\u8336/.x', u'foo/.q.x'],
184
[u'foo', u'foo.bar'],
185
[u'.foo', u'foo/bar', u'foo/.bar']),
187
[u'bar', u'foobar', ur'foo\nbar', u'foo.bar', u'foo/bar',
188
u'foo/foobar', u'foo/f.bar', u'.bar', u'foo/.bar'],
192
def test_double_asterisk(self):
194
# expected uses of double asterisk
196
[u'foo/x', u'foo/bar/x'],
197
[u'foox', u'foo/bax', u'foo/.x', u'foo/bar/bax']),
199
[u'bar', u'foo/bar'],
200
[u'foobar', u'foo.bar', u'foo/foobar', u'foo/f.bar',
201
u'.bar', u'foo/.bar']),
202
# check that we ignore extra *s, so *** is treated like ** not *.
204
[u'foo/x', u'foo/bar/x'],
205
[u'foox', u'foo/bax', u'foo/.x', u'foo/bar/bax']),
207
[u'bar', u'foo/bar'],
208
[u'foobar', u'foo.bar', u'foo/foobar', u'foo/f.bar',
209
u'.bar', u'foo/.bar']),
210
# the remaining tests check that ** is interpreted as *
211
# unless it is a whole path component
213
[u'x\u8336/x', u'x/x'],
214
[u'xx', u'x.x', u'bar/x/bar/x', u'x.y.x', u'x/y/x']),
216
[u'xx', u'x.x', u'x\u8336..x', u'foo/x.x', u'x.y.x'],
217
[u'bar/x/bar/x', u'xfoo/bar/x', u'x/x', u'bax/abaxab']),
219
[u'foo/x', u'foo/bax', u'foo/a.x', u'foo/.x', u'foo/.q.x'],
222
[u'foo', u'foo.bar'],
223
[u'.foo', u'foo/bar', u'foo/.bar']),
225
[u'bar', u'foobar', ur'foo\nbar', u'foo.bar', u'foo/bar',
226
u'foo/foobar', u'foo/f.bar', u'.bar', u'foo/.bar'],
230
def test_leading_dot_slash(self):
234
[u'\u8336/foo', u'barfoo', u'x/y/foo']),
237
[u'foo/bar', u'foo/.bar', u'x/foo/y']),
240
def test_backslash(self):
244
[u'\u8336/foo', u'barfoo', u'x/y/foo']),
247
[u'foo/bar', u'foo/.bar', u'x/foo/y']),
249
[u'foo/x', u'foo/bar/x'],
250
[u'foox', u'foo/bax', u'foo/.x', u'foo/bar/bax']),
253
def test_trailing_slash(self):
257
[u'\u8336/foo', u'barfoo', u'x/y/foo']),
260
[u'foo/', u'\u8336/foo', u'barfoo', u'x/y/foo']),
263
def test_leading_asterisk_dot(self):
266
[u'foo/bar/baz.x', u'\u8336/Q.x', u'foo.y.x', u'.foo.x',
267
u'bar/.foo.x', u'.x',],
270
[u'foo/b.bar', u'foo/a.b.bar', u'foo/.bar'],
273
[u'foo.py.~1~', u'.foo.py.~1~'],
277
def test_end_anchor(self):
287
def test_mixed_globs(self):
288
"""tests handling of combinations of path type matches.
290
The types being extension, basename and full path.
292
patterns = [ u'*.foo', u'.*.swp', u'./*.png']
293
globster = Globster(patterns)
294
self.assertEqual(u'*.foo', globster.match('bar.foo'))
295
self.assertEqual(u'./*.png', globster.match('foo.png'))
296
self.assertEqual(None, globster.match('foo/bar.png'))
297
self.assertEqual(u'.*.swp', globster.match('foo/.bar.py.swp'))
299
def test_large_globset(self):
300
"""tests that the globster can handle a large set of patterns.
302
Large is defined as more than supported by python regex groups,
304
This test assumes the globs are broken into regexs containing 99
307
patterns = [ u'*.%03d' % i for i in xrange(0,300) ]
308
globster = Globster(patterns)
309
# test the fence posts
310
for x in (0,98,99,197,198,296,297,299):
311
filename = u'foo.%03d' % x
312
self.assertEqual(patterns[x],globster.match(filename))
313
self.assertEqual(None,globster.match('foobar.300'))
315
def test_bad_pattern(self):
316
"""Ensure that globster handles bad patterns cleanly."""
317
patterns = [u'RE:[', u'/home/foo', u'RE:*.cpp']
318
g = Globster(patterns)
319
e = self.assertRaises(errors.InvalidPattern, g.match, 'filename')
320
self.assertContainsRe(e.msg,
321
"File.*ignore.*contains error.*RE:\[.*RE:\*\.cpp", flags=re.DOTALL)
324
class TestExceptionGlobster(TestCase):
326
def test_exclusion_patterns(self):
327
"""test that exception patterns are not matched"""
328
patterns = [ u'*', u'!./local', u'!./local/**/*', u'!RE:\.z.*',u'!!./.zcompdump' ]
329
globster = ExceptionGlobster(patterns)
330
self.assertEqual(u'*', globster.match('tmp/foo.txt'))
331
self.assertEqual(None, globster.match('local'))
332
self.assertEqual(None, globster.match('local/bin/wombat'))
333
self.assertEqual(None, globster.match('.zshrc'))
334
self.assertEqual(None, globster.match('.zfunctions/fiddle/flam'))
335
self.assertEqual(u'!!./.zcompdump', globster.match('.zcompdump'))
337
def test_exclusion_order(self):
338
"""test that ordering of exclusion patterns does not matter"""
339
patterns = [ u'static/**/*.html', u'!static/**/versionable.html']
340
globster = ExceptionGlobster(patterns)
341
self.assertEqual(u'static/**/*.html', globster.match('static/foo.html'))
342
self.assertEqual(None, globster.match('static/versionable.html'))
343
self.assertEqual(None, globster.match('static/bar/versionable.html'))
344
globster = ExceptionGlobster(reversed(patterns))
345
self.assertEqual(u'static/**/*.html', globster.match('static/foo.html'))
346
self.assertEqual(None, globster.match('static/versionable.html'))
347
self.assertEqual(None, globster.match('static/bar/versionable.html'))
349
class TestOrderedGlobster(TestCase):
351
def test_ordered_globs(self):
352
"""test that the first match in a list is the one found"""
353
patterns = [ u'*.foo', u'bar.*']
354
globster = _OrderedGlobster(patterns)
355
self.assertEqual(u'*.foo', globster.match('bar.foo'))
356
self.assertEqual(None, globster.match('foo.bar'))
357
globster = _OrderedGlobster(reversed(patterns))
358
self.assertEqual(u'bar.*', globster.match('bar.foo'))
359
self.assertEqual(None, globster.match('foo.bar'))
362
class TestNormalizePattern(TestCase):
364
def test_backslashes(self):
365
"""tests that backslashes are converted to forward slashes, multiple
366
backslashes are collapsed to single forward slashes and trailing
367
backslashes are removed"""
368
self.assertEqual(u'/', normalize_pattern(u'\\'))
369
self.assertEqual(u'/', normalize_pattern(u'\\\\'))
370
self.assertEqual(u'/foo/bar', normalize_pattern(u'\\foo\\bar'))
371
self.assertEqual(u'foo/bar', normalize_pattern(u'foo\\bar\\'))
372
self.assertEqual(u'/foo/bar', normalize_pattern(u'\\\\foo\\\\bar\\\\'))
374
def test_forward_slashes(self):
375
"""tests that multiple foward slashes are collapsed to single forward
376
slashes and trailing forward slashes are removed"""
377
self.assertEqual(u'/', normalize_pattern(u'/'))
378
self.assertEqual(u'/', normalize_pattern(u'//'))
379
self.assertEqual(u'/foo/bar', normalize_pattern(u'/foo/bar'))
380
self.assertEqual(u'foo/bar', normalize_pattern(u'foo/bar/'))
381
self.assertEqual(u'/foo/bar', normalize_pattern(u'//foo//bar//'))
383
def test_mixed_slashes(self):
384
"""tests that multiple mixed slashes are collapsed to single forward
385
slashes and trailing mixed slashes are removed"""
386
self.assertEqual(u'/foo/bar', normalize_pattern(u'\\/\\foo//\\///bar/\\\\/'))
added
removed
bzrlib/tests/test_globbing.py
