1
# Copyright (C) 2006 Canonical Ltd
3
# This program is free software; you can redistribute it and/or modify
4
# it under the terms of the GNU General Public License as published by
5
# the Free Software Foundation; either version 2 of the License, or
6
# (at your option) any later version.
8
# This program is distributed in the hope that it will be useful,
9
# but WITHOUT ANY WARRANTY; without even the implied warranty of
10
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
# GNU General Public License for more details.
13
# You should have received a copy of the GNU General Public License
14
# along with this program; if not, write to the Free Software
15
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
17
"""Tests for bzrlib/generate_ids.py"""
27
class TestFileIds(tests.TestCase):
28
"""Test functions which generate file ids"""
30
def assertGenFileId(self, regex, filename):
31
"""gen_file_id should create a file id matching the regex.
33
The file id should be ascii, and should be an 8-bit string
35
file_id = generate_ids.gen_file_id(filename)
36
self.assertContainsRe(file_id, '^'+regex+'$')
37
# It should be a utf8 file_id, not a unicode one
38
self.assertIsInstance(file_id, str)
39
# gen_file_id should always return ascii file ids.
40
file_id.decode('ascii')
42
def test_gen_file_id(self):
43
gen_file_id = generate_ids.gen_file_id
45
# We try to use the filename if possible
46
self.assertStartsWith(gen_file_id('bar'), 'bar-')
48
# but we squash capitalization, and remove non word characters
49
self.assertStartsWith(gen_file_id('Mwoo oof\t m'), 'mwoooofm-')
51
# We also remove leading '.' characters to prevent hidden file-ids
52
self.assertStartsWith(gen_file_id('..gam.py'), 'gam.py-')
53
self.assertStartsWith(gen_file_id('..Mwoo oof\t m'), 'mwoooofm-')
55
# we remove unicode characters, and still don't end up with a
57
self.assertStartsWith(gen_file_id(u'\xe5\xb5.txt'), 'txt-')
59
# Our current method of generating unique ids adds 33 characters
60
# plus an serial number (log10(N) characters)
61
# to the end of the filename. We now restrict the filename portion to
62
# be <= 20 characters, so the maximum length should now be approx < 60
64
# Test both case squashing and length restriction
65
fid = gen_file_id('A'*50 + '.txt')
66
self.assertStartsWith(fid, 'a'*20 + '-')
67
self.failUnless(len(fid) < 60)
69
# restricting length happens after the other actions, so
70
# we preserve as much as possible
71
fid = gen_file_id('\xe5\xb5..aBcd\tefGhijKLMnop\tqrstuvwxyz')
72
self.assertStartsWith(fid, 'abcdefghijklmnopqrst-')
73
self.failUnless(len(fid) < 60)
75
def test_file_ids_are_ascii(self):
76
tail = r'-\d{14}-[a-z0-9]{16}-\d+'
77
self.assertGenFileId('foo' + tail, 'foo')
78
self.assertGenFileId('foo' + tail, u'foo')
79
self.assertGenFileId('bar' + tail, u'bar')
80
self.assertGenFileId('br' + tail, u'b\xe5r')
82
def test__next_id_suffix_sets_suffix(self):
83
generate_ids._gen_file_id_suffix = None
84
generate_ids._next_id_suffix()
85
self.assertNotEqual(None, generate_ids._gen_file_id_suffix)
87
def test__next_id_suffix_increments(self):
88
generate_ids._gen_file_id_suffix = "foo-"
89
generate_ids._gen_file_id_serial = 1
91
self.assertEqual("foo-2", generate_ids._next_id_suffix())
92
self.assertEqual("foo-3", generate_ids._next_id_suffix())
93
self.assertEqual("foo-4", generate_ids._next_id_suffix())
94
self.assertEqual("foo-5", generate_ids._next_id_suffix())
95
self.assertEqual("foo-6", generate_ids._next_id_suffix())
96
self.assertEqual("foo-7", generate_ids._next_id_suffix())
97
self.assertEqual("foo-8", generate_ids._next_id_suffix())
98
self.assertEqual("foo-9", generate_ids._next_id_suffix())
99
self.assertEqual("foo-10", generate_ids._next_id_suffix())
101
# Reset so that all future ids generated in the test suite
102
# don't end in 'foo-XXX'
103
generate_ids._gen_file_id_suffix = None
104
generate_ids._gen_file_id_serial = 0
106
def test_gen_root_id(self):
107
# Mostly just make sure gen_root_id() exists
108
root_id = generate_ids.gen_root_id()
109
self.assertStartsWith(root_id, 'tree_root-')
112
class TestGenRevisionId(tests.TestCase):
113
"""Test generating revision ids"""
115
def assertMatchesRe(self, regex, text):
116
"""Make sure text is matched by the regex given"""
117
if re.match(regex, text) is None:
118
self.fail('Pattern %s did not match text %s' % (regex, text))
120
def assertGenRevisionId(self, regex, username, timestamp=None):
121
"""gen_revision_id should create a revision id matching the regex"""
122
revision_id = generate_ids.gen_revision_id(username, timestamp)
123
self.assertMatchesRe(regex, revision_id)
124
# It should be a utf8 revision_id, not a unicode one
125
self.assertIsInstance(revision_id, str)
126
# gen_revision_id should always return ascii revision ids.
127
revision_id.decode('ascii')
129
def test_timestamp(self):
130
"""passing a timestamp should cause it to be used"""
131
self.assertGenRevisionId(r'user@host-\d{14}-[a-z0-9]{16}', 'user@host')
132
self.assertGenRevisionId('user@host-20061102205056-[a-z0-9]{16}',
133
'user@host', 1162500656.688)
134
self.assertGenRevisionId(r'user@host-20061102205024-[a-z0-9]{16}',
135
'user@host', 1162500624.000)
137
def test_gen_revision_id_email(self):
138
"""gen_revision_id uses email address if present"""
139
regex = r'user\+joe_bar@foo-bar\.com-\d{14}-[a-z0-9]{16}'
140
self.assertGenRevisionId(regex,'user+joe_bar@foo-bar.com')
141
self.assertGenRevisionId(regex, '<user+joe_bar@foo-bar.com>')
142
self.assertGenRevisionId(regex, 'Joe Bar <user+joe_bar@foo-bar.com>')
143
self.assertGenRevisionId(regex, 'Joe Bar <user+Joe_Bar@Foo-Bar.com>')
144
self.assertGenRevisionId(regex, u'Joe B\xe5r <user+Joe_Bar@Foo-Bar.com>')
146
def test_gen_revision_id_user(self):
147
"""If there is no email, fall back to the whole username"""
148
tail = r'-\d{14}-[a-z0-9]{16}'
149
self.assertGenRevisionId('joe_bar' + tail, 'Joe Bar')
150
self.assertGenRevisionId('joebar' + tail, 'joebar')
151
self.assertGenRevisionId('joe_br' + tail, u'Joe B\xe5r')
152
self.assertGenRevisionId(r'joe_br_user\+joe_bar_foo-bar.com' + tail,
153
u'Joe B\xe5r <user+Joe_Bar_Foo-Bar.com>')
155
def test_revision_ids_are_ascii(self):
156
"""gen_revision_id should always return an ascii revision id."""
157
tail = r'-\d{14}-[a-z0-9]{16}'
158
self.assertGenRevisionId('joe_bar' + tail, 'Joe Bar')
159
self.assertGenRevisionId('joe_bar' + tail, u'Joe Bar')
160
self.assertGenRevisionId('joe@foo' + tail, u'Joe Bar <joe@foo>')
161
# We cheat a little with this one, because email-addresses shouldn't
162
# contain non-ascii characters, but generate_ids should strip them
164
self.assertGenRevisionId('joe@f' + tail, u'Joe Bar <joe@f\xb6>')
added
removed
bzrlib/tests/test_generate_ids.py
