1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
|
# Copyright (C) 2006, 2007 Canonical Ltd
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
"""Black-box tests for bzr handling non-ascii characters."""
import sys
import os
from bzrlib import osutils, urlutils
import bzrlib
from bzrlib.tests import TestCaseWithTransport, TestSkipped
from bzrlib.trace import mutter, note
class TestNonAscii(TestCaseWithTransport):
"""Test that bzr handles files/committers/etc which are non-ascii."""
def setUp(self):
super(TestNonAscii, self).setUp()
self._orig_email = os.environ.get('BZR_EMAIL', None)
self._orig_encoding = bzrlib.user_encoding
bzrlib.user_encoding = self.encoding
email = self.info['committer'] + ' <joe@foo.com>'
os.environ['BZR_EMAIL'] = email.encode(bzrlib.user_encoding)
self.create_base()
def tearDown(self):
if self._orig_email is not None:
os.environ['BZR_EMAIL'] = self._orig_email
else:
if os.environ.get('BZR_EMAIL', None) is not None:
del os.environ['BZR_EMAIL']
bzrlib.user_encoding = self._orig_encoding
super(TestNonAscii, self).tearDown()
def run_bzr_decode(self, args, encoding=None, fail=False, retcode=None,
working_dir=None):
"""Run bzr and decode the output into a particular encoding.
Returns a string containing the stdout output from bzr.
:param fail: If true, the operation is expected to fail with
a UnicodeError.
"""
if encoding is None:
encoding = bzrlib.user_encoding
try:
out = self.run_bzr(args, output_encoding=encoding, encoding=encoding,
retcode=retcode, working_dir=working_dir)[0]
return out.decode(encoding)
except UnicodeError, e:
if not fail:
raise
else:
# This command, run from the regular command line, will give a
# traceback to the user. That's not really good for a situation
# that can be provoked just by the interaction of their input data
# and locale, as some of these are. What would be better?
if fail:
self.fail("Expected UnicodeError not raised")
def create_base(self):
fs_enc = sys.getfilesystemencoding()
terminal_enc = osutils.get_terminal_encoding()
fname = self.info['filename']
dir_name = self.info['directory']
for thing in [fname, dir_name]:
try:
thing.encode(fs_enc)
except UnicodeEncodeError:
raise TestSkipped(('Unable to represent path %r'
' in filesystem encoding "%s"')
% (thing, fs_enc))
try:
thing.encode(terminal_enc)
except UnicodeEncodeError:
raise TestSkipped(('Unable to represent path %r'
' in terminal encoding "%s"'
' (even though it is valid in'
' filesystem encoding "%s")')
% (thing, terminal_enc, fs_enc))
wt = self.make_branch_and_tree('.')
self.build_tree_contents([('a', 'foo\n')])
wt.add('a')
wt.commit('adding a')
self.build_tree_contents(
[('b', 'non-ascii \xFF\xFF\xFC\xFB\x00 in b\n')])
wt.add('b')
wt.commit(self.info['message'])
self.build_tree_contents([(fname, 'unicode filename\n')])
wt.add(fname)
wt.commit(u'And a unicode file\n')
self.wt = wt
def test_status(self):
self.build_tree_contents(
[(self.info['filename'], 'changed something\n')])
txt = self.run_bzr_decode('status')
self.assertEqual(u'modified:\n %s\n' % (self.info['filename'],), txt)
txt = self.run_bzr_decode('status', encoding='ascii')
expected = u'modified:\n %s\n' % (
self.info['filename'].encode('ascii', 'replace'),)
self.assertEqual(expected, txt)
def test_cat(self):
# bzr cat shouldn't change the contents
# using run_bzr since that doesn't decode
txt = self.run_bzr('cat b')[0]
self.assertEqual('non-ascii \xFF\xFF\xFC\xFB\x00 in b\n', txt)
txt = self.run_bzr(['cat', self.info['filename']])[0]
self.assertEqual('unicode filename\n', txt)
def test_cat_revision(self):
committer = self.info['committer']
txt = self.run_bzr_decode('cat-revision -r 1')
self.failUnless(committer in txt,
'failed to find %r in %r' % (committer, txt))
msg = self.info['message']
txt = self.run_bzr_decode('cat-revision -r 2')
self.failUnless(msg in txt, 'failed to find %r in %r' % (msg, txt))
def test_mkdir(self):
txt = self.run_bzr_decode(['mkdir', self.info['directory']])
self.assertEqual(u'added %s\n' % self.info['directory'], txt)
# The text should be garbled, but the command should succeed
txt = self.run_bzr_decode(['mkdir', self.info['directory'] + '2'],
encoding='ascii')
expected = u'added %s2\n' % (self.info['directory'],)
expected = expected.encode('ascii', 'replace')
self.assertEqual(expected, txt)
def test_relpath(self):
txt = self.run_bzr_decode(['relpath', self.info['filename']])
self.assertEqual(self.info['filename'] + '\n', txt)
self.run_bzr_decode(['relpath', self.info['filename']],
encoding='ascii', fail=True)
def test_inventory(self):
txt = self.run_bzr_decode('inventory')
self.assertEqual(['a', 'b', self.info['filename']],
txt.splitlines())
# inventory should fail if unable to encode
self.run_bzr_decode('inventory', encoding='ascii', fail=True)
# We don't really care about the ids themselves,
# but the command shouldn't fail
txt = self.run_bzr_decode('inventory --show-ids')
def test_revno(self):
# There isn't a lot to test here, since revno should always
# be an integer
self.assertEqual('3\n', self.run_bzr_decode('revno'))
self.assertEqual('3\n', self.run_bzr_decode('revno', encoding='ascii'))
def test_revision_info(self):
self.run_bzr_decode('revision-info -r 1')
# TODO: jam 20060105 If we support revisions with non-ascii characters,
# this should be strict and fail.
self.run_bzr_decode('revision-info -r 1', encoding='ascii')
def test_mv(self):
fname1 = self.info['filename']
fname2 = self.info['filename'] + '2'
dirname = self.info['directory']
# fname1 already exists
self.run_bzr_decode(['mv', 'a', fname1], fail=True)
txt = self.run_bzr_decode(['mv', 'a', fname2])
self.assertEqual(u'a => %s\n' % fname2, txt)
self.failIfExists('a')
self.failUnlessExists(fname2)
# After 'mv' we need to re-open the working tree
self.wt = self.wt.bzrdir.open_workingtree()
self.wt.commit('renamed to non-ascii')
os.mkdir(dirname)
self.wt.add(dirname)
txt = self.run_bzr_decode(['mv', fname1, fname2, dirname])
self.assertEqual([u'%s => %s/%s' % (fname1, dirname, fname1),
u'%s => %s/%s' % (fname2, dirname, fname2)]
, txt.splitlines())
# The rename should still succeed
newpath = u'%s/%s' % (dirname, fname2)
txt = self.run_bzr_decode(['mv', newpath, 'a'], encoding='ascii')
self.failUnlessExists('a')
self.assertEqual(newpath.encode('ascii', 'replace') + ' => a\n', txt)
def test_branch(self):
# We should be able to branch into a directory that
# has a unicode name, even if we can't display the name
self.run_bzr_decode(['branch', u'.', self.info['directory']])
self.run_bzr_decode(['branch', u'.', self.info['directory'] + '2'],
encoding='ascii')
def test_pull(self):
# Make sure we can pull from paths that can't be encoded
dirname1 = self.info['directory']
dirname2 = self.info['directory'] + '2'
url1 = urlutils.local_path_to_url(dirname1)
url2 = urlutils.local_path_to_url(dirname2)
out_bzrdir = self.wt.bzrdir.sprout(url1)
out_bzrdir.sprout(url2)
self.build_tree_contents(
[(osutils.pathjoin(dirname1, "a"), 'different text\n')])
self.wt.commit('mod a')
txt = self.run_bzr_decode('pull', working_dir=dirname2)
expected = osutils.pathjoin(osutils.getcwd(), dirname1)
self.assertEqual(u'Using saved location: %s/\n'
'No revisions to pull.\n' % (expected,), txt)
self.build_tree_contents(
[(osutils.pathjoin(dirname1, 'a'), 'and yet more\n')])
self.wt.commit(u'modifying a by ' + self.info['committer'])
# We should be able to pull, even if our encoding is bad
self.run_bzr_decode('pull --verbose', encoding='ascii',
working_dir=dirname2)
def test_push(self):
# TODO: Test push to an SFTP location
# Make sure we can pull from paths that can't be encoded
# TODO: jam 20060427 For drastically improving performance, we probably
# could create a local repository, so it wouldn't have to copy
# the files around as much.
dirname = self.info['directory']
self.run_bzr_decode(['push', dirname])
self.build_tree_contents([('a', 'adding more text\n')])
self.wt.commit('added some stuff')
# TODO: check the output text is properly encoded
self.run_bzr_decode('push')
self.build_tree_contents(
[('a', 'and a bit more: \n%s\n' % (dirname.encode('utf-8'),))])
self.wt.commit('Added some ' + dirname)
self.run_bzr_decode('push --verbose', encoding='ascii')
self.run_bzr_decode(['push', '--verbose', dirname + '2'])
self.run_bzr_decode(['push', '--verbose', dirname + '3'],
encoding='ascii')
self.run_bzr_decode(['push', '--verbose', '--create-prefix',
dirname + '4/' + dirname + '5'])
self.run_bzr_decode(['push', '--verbose', '--create-prefix',
dirname + '6/' + dirname + '7'], encoding='ascii')
def test_renames(self):
fname = self.info['filename'] + '2'
self.wt.rename_one('a', fname)
txt = self.run_bzr_decode('renames')
self.assertEqual(u'a => %s\n' % fname, txt)
self.run_bzr_decode('renames', fail=True, encoding='ascii')
def test_remove(self):
fname = self.info['filename']
txt = self.run_bzr_decode(['remove', fname], encoding='ascii')
def test_remove_verbose(self):
fname = self.info['filename']
txt = self.run_bzr_decode(['remove', '--verbose', fname],
encoding='ascii')
def test_file_id(self):
fname = self.info['filename']
txt = self.run_bzr_decode(['file-id', fname])
# TODO: jam 20060106 We don't support non-ascii file ids yet,
# so there is nothing which would fail in ascii encoding
# This *should* be retcode=3
txt = self.run_bzr_decode(['file-id', fname], encoding='ascii')
def test_file_path(self):
# Create a directory structure
fname = self.info['filename']
dirname = self.info['directory']
self.build_tree_contents([
('base/', ),
(osutils.pathjoin('base', '%s/' % (dirname,)), )])
self.wt.add('base')
self.wt.add('base/'+dirname)
path = osutils.pathjoin('base', dirname, fname)
self.wt.rename_one(fname, path)
self.wt.commit('moving things around')
txt = self.run_bzr_decode(['file-path', path])
# TODO: jam 20060106 We don't support non-ascii file ids yet,
# so there is nothing which would fail in ascii encoding
# This *should* be retcode=3
txt = self.run_bzr_decode(['file-path', path], encoding='ascii')
def test_revision_history(self):
# TODO: jam 20060106 We don't support non-ascii revision ids yet,
# so there is nothing which would fail in ascii encoding
txt = self.run_bzr_decode('revision-history')
def test_ancestry(self):
# TODO: jam 20060106 We don't support non-ascii revision ids yet,
# so there is nothing which would fail in ascii encoding
txt = self.run_bzr_decode('ancestry')
def test_diff(self):
# TODO: jam 20060106 diff is a difficult one to test, because it
# shouldn't encode the file contents, but it needs some sort
# of encoding for the paths, etc which are displayed.
self.build_tree_contents([(self.info['filename'], 'newline\n')])
txt = self.run_bzr('diff', retcode=1)[0]
def test_deleted(self):
fname = self.info['filename']
os.remove(fname)
self.wt.remove(fname)
txt = self.run_bzr_decode('deleted')
self.assertEqual(fname+'\n', txt)
txt = self.run_bzr_decode('deleted --show-ids')
self.failUnless(txt.startswith(fname))
# Deleted should fail if cannot decode
# Because it is giving the exact paths
# which might be used by a front end
self.run_bzr_decode('deleted', encoding='ascii', fail=True)
def test_modified(self):
fname = self.info['filename']
self.build_tree_contents([(fname, 'modified\n')])
txt = self.run_bzr_decode('modified')
self.assertEqual('"'+fname+'"'+'\n', txt)
self.run_bzr_decode('modified', encoding='ascii', fail=True)
def test_added(self):
fname = self.info['filename'] + '2'
self.build_tree_contents([(fname, 'added\n')])
self.wt.add(fname)
txt = self.run_bzr_decode('added')
self.assertEqual('"'+fname+'"'+'\n', txt)
self.run_bzr_decode('added', encoding='ascii', fail=True)
def test_root(self):
dirname = self.info['directory']
url = urlutils.local_path_to_url(dirname)
self.run_bzr_decode('root')
self.wt.bzrdir.sprout(url)
txt = self.run_bzr_decode('root', working_dir=dirname)
self.failUnless(txt.endswith(dirname+'\n'))
txt = self.run_bzr_decode('root', encoding='ascii', fail=True,
working_dir=dirname)
def test_log(self):
fname = self.info['filename']
txt = self.run_bzr_decode('log')
self.assertNotEqual(-1, txt.find(self.info['committer']))
self.assertNotEqual(-1, txt.find(self.info['message']))
txt = self.run_bzr_decode('log --verbose')
self.assertNotEqual(-1, txt.find(fname))
# Make sure log doesn't fail even if we can't write out
txt = self.run_bzr_decode('log --verbose', encoding='ascii')
self.assertEqual(-1, txt.find(fname))
self.assertNotEqual(-1, txt.find(fname.encode('ascii', 'replace')))
def test_touching_revisions(self):
fname = self.info['filename']
txt = self.run_bzr_decode(['touching-revisions', fname])
self.assertEqual(u' 3 added %s\n' % (fname,), txt)
fname2 = self.info['filename'] + '2'
self.wt.rename_one(fname, fname2)
self.wt.commit(u'Renamed %s => %s' % (fname, fname2))
txt = self.run_bzr_decode(['touching-revisions', fname2])
expected_txt = (u' 3 added %s\n'
u' 4 renamed %s => %s\n'
% (fname, fname, fname2))
self.assertEqual(expected_txt, txt)
self.run_bzr_decode(['touching-revisions', fname2], encoding='ascii',
fail=True)
def test_ls(self):
txt = self.run_bzr_decode('ls')
self.assertEqual(sorted(['a', 'b', self.info['filename']]),
sorted(txt.splitlines()))
txt = self.run_bzr_decode('ls --null')
self.assertEqual(sorted(['', 'a', 'b', self.info['filename']]),
sorted(txt.split('\0')))
txt = self.run_bzr_decode('ls', encoding='ascii', fail=True)
txt = self.run_bzr_decode('ls --null', encoding='ascii', fail=True)
def test_unknowns(self):
fname = self.info['filename'] + '2'
self.build_tree_contents([(fname, 'unknown\n')])
# TODO: jam 20060112 bzr unknowns is the only one which
# quotes paths do we really want it to?
# awilkins 20080521 added and modified do it now as well
txt = self.run_bzr_decode('unknowns')
self.assertEqual(u'"%s"\n' % (fname,), txt)
self.run_bzr_decode('unknowns', encoding='ascii', fail=True)
def test_ignore(self):
fname2 = self.info['filename'] + '2.txt'
self.build_tree_contents([(fname2, 'ignored\n')])
def check_unknowns(expected):
self.assertEqual(expected, list(self.wt.unknowns()))
check_unknowns([fname2])
self.run_bzr_decode(['ignore', './' + fname2])
check_unknowns([])
fname3 = self.info['filename'] + '3.txt'
self.build_tree_contents([(fname3, 'unknown 3\n')])
check_unknowns([fname3])
# Ignore should not care what the encoding is
# (right now it doesn't print anything)
self.run_bzr_decode(['ignore', fname3], encoding='ascii')
check_unknowns([])
# Now try a wildcard match
fname4 = self.info['filename'] + '4.txt'
self.build_tree_contents([(fname4, 'unknown 4\n')])
self.run_bzr_decode('ignore *.txt')
check_unknowns([])
# and a different wildcard that matches everything
os.remove('.bzrignore')
self.run_bzr_decode(['ignore', self.info['filename'] + '*'])
check_unknowns([])
def test_missing(self):
# create empty tree as reference for missing
self.make_branch_and_tree('empty-tree')
msg = self.info['message']
txt = self.run_bzr_decode('missing empty-tree')
self.assertNotEqual(-1, txt.find(self.info['committer']))
self.assertNotEqual(-1, txt.find(msg))
# Make sure missing doesn't fail even if we can't write out
txt = self.run_bzr_decode('missing empty-tree', encoding='ascii')
self.assertEqual(-1, txt.find(msg))
self.assertNotEqual(-1, txt.find(msg.encode('ascii', 'replace')))
def test_info(self):
self.run_bzr_decode(['branch', u'.', self.info['directory']])
self.run_bzr_decode(['info', self.info['directory']])
self.run_bzr_decode(['info', self.info['directory']],
encoding='ascii')
def test_ignored(self):
fname = self.info['filename'] + '1.txt'
self.build_tree_contents([(fname, 'ignored\n')])
self.run_bzr(['ignore', fname])
txt = self.run_bzr_decode(['ignored'])
self.assertEqual(txt, '%-50s %s\n' % (fname, fname))
txt = self.run_bzr_decode(['ignored'], encoding='ascii')
fname = fname.encode('ascii', 'replace')
self.assertEqual(txt, '%-50s %s\n' % (fname, fname))
|