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
|
# groupcompress, a bzr plugin providing new compression logic.
# Copyright (C) 2008 Canonical Limited.
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as published
# by the Free Software Foundation.
#
# 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., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
#
"""Tests for group compression."""
import zlib
from bzrlib import tests
from bzrlib.osutils import sha_string
from bzrlib.plugins.groupcompress import errors, groupcompress
from bzrlib.tests import (
TestCaseWithTransport,
multiply_tests,
)
from bzrlib.transport import get_transport
def load_tests(standard_tests, module, loader):
from bzrlib.tests.test_versionedfile import TestVersionedFiles
vf_interface_tests = loader.loadTestsFromTestCase(TestVersionedFiles)
cleanup_pack_group = groupcompress.cleanup_pack_group
make_pack_factory = groupcompress.make_pack_factory
group_scenario = ('groupcompressrabin-nograph', {
'cleanup':cleanup_pack_group,
'factory':make_pack_factory(False, False, 1),
'graph': False,
'key_length':1,
'support_partial_insertion':False,
}
)
scenarios = [group_scenario]
return multiply_tests(vf_interface_tests, scenarios, standard_tests)
class TestGroupCompressor(tests.TestCase):
"""Tests for GroupCompressor"""
def test_empty_delta(self):
compressor = groupcompress.GroupCompressor(True)
self.assertEqual([], compressor.lines)
def test_one_nosha_delta(self):
# diff against NUKK
compressor = groupcompress.GroupCompressor(True)
sha1, end_point, _, _ = compressor.compress(('label',),
'strange\ncommon\n', None)
self.assertEqual(sha_string('strange\ncommon\n'), sha1)
expected_lines = [
'f', '\x0f', 'strange\ncommon\n',
]
self.assertEqual(expected_lines, compressor.lines)
self.assertEqual(sum(map(len, expected_lines)), end_point)
def _chunks_to_repr_lines(self, chunks):
return '\n'.join(map(repr, ''.join(chunks).split('\n')))
def assertEqualDiffEncoded(self, expected, actual):
"""Compare the actual content to the expected content.
:param expected: A group of chunks that we expect to see
:param actual: The measured 'chunks'
We will transform the chunks back into lines, and then run 'repr()'
over them to handle non-ascii characters.
"""
self.assertEqualDiff(self._chunks_to_repr_lines(expected),
self._chunks_to_repr_lines(actual))
def test_two_nosha_delta(self):
compressor = groupcompress.GroupCompressor(True)
sha1_1, _, _, _ = compressor.compress(('label',),
'strange\ncommon long line\nthat needs a 16 byte match\n', None)
expected_lines = list(compressor.lines)
sha1_2, end_point, _, _ = compressor.compress(('newlabel',),
'common long line\nthat needs a 16 byte match\ndifferent\n', None)
self.assertEqual(sha_string('common long line\n'
'that needs a 16 byte match\n'
'different\n'), sha1_2)
expected_lines.extend([
# 'delta', delta length
'd\x10',
# source and target length
'\x36\x36',
# copy the line common
'\x91\x0a\x2c', #copy, offset 0x0a, len 0x2c
# add the line different, and the trailing newline
'\x0adifferent\n', # insert 10 bytes
])
self.assertEqualDiffEncoded(expected_lines, compressor.lines)
self.assertEqual(sum(map(len, expected_lines)), end_point)
def test_three_nosha_delta(self):
# The first interesting test: make a change that should use lines from
# both parents.
compressor = groupcompress.GroupCompressor(True)
sha1_1, end_point, _, _ = compressor.compress(('label',),
'strange\ncommon very very long line\nwith some extra text\n', None)
sha1_2, _, _, _ = compressor.compress(('newlabel',),
'different\nmoredifferent\nand then some more\n', None)
expected_lines = list(compressor.lines)
sha1_3, end_point, _, _ = compressor.compress(('label3',),
'new\ncommon very very long line\nwith some extra text\n'
'different\nmoredifferent\nand then some more\n',
None)
self.assertEqual(
sha_string('new\ncommon very very long line\nwith some extra text\n'
'different\nmoredifferent\nand then some more\n'),
sha1_3)
expected_lines.extend([
# 'delta', delta length
'd\x0c',
# source and target length
'\x67\x5f'
# insert new
'\x03new',
# Copy of first parent 'common' range
'\x91\x09\x31' # copy, offset 0x09, 0x31 bytes
# Copy of second parent 'different' range
'\x91\x3c\x2b' # copy, offset 0x3c, 0x2b bytes
])
self.assertEqualDiffEncoded(expected_lines, compressor.lines)
self.assertEqual(sum(map(len, expected_lines)), end_point)
def test_stats(self):
compressor = groupcompress.GroupCompressor(True)
compressor.compress(('label',), 'strange\ncommon long line\n'
'plus more text\n', None)
compressor.compress(('newlabel',),
'common long line\nplus more text\n'
'different\nmoredifferent\n', None)
compressor.compress(('label3',),
'new\ncommon long line\nplus more text\n'
'\ndifferent\nmoredifferent\n', None)
self.assertAlmostEqual(1.4, compressor.ratio(), 1)
def test_extract_from_compressor(self):
# Knit fetching will try to reconstruct texts locally which results in
# reading something that is in the compressor stream already.
compressor = groupcompress.GroupCompressor(True)
sha1_1, _, _, _ = compressor.compress(('label',),
'strange\ncommon long line\nthat needs a 16 byte match\n', None)
expected_lines = list(compressor.lines)
sha1_2, end_point, _, _ = compressor.compress(('newlabel',),
'common long line\nthat needs a 16 byte match\ndifferent\n', None)
# get the first out
self.assertEqual(('strange\ncommon long line\n'
'that needs a 16 byte match\n', sha1_1),
compressor.extract(('label',)))
# and the second
self.assertEqual(('common long line\nthat needs a 16 byte match\n'
'different\n', sha1_2),
compressor.extract(('newlabel',)))
class TestBase128Int(tests.TestCase):
def assertEqualEncode(self, bytes, val):
self.assertEqual(bytes, groupcompress.encode_base128_int(val))
def assertEqualDecode(self, val, num_decode, bytes):
self.assertEqual((val, num_decode),
groupcompress.decode_base128_int(bytes))
def test_encode(self):
self.assertEqualEncode('\x01', 1)
self.assertEqualEncode('\x02', 2)
self.assertEqualEncode('\x7f', 127)
self.assertEqualEncode('\x80\x01', 128)
self.assertEqualEncode('\xff\x01', 255)
self.assertEqualEncode('\x80\x02', 256)
self.assertEqualEncode('\xff\xff\xff\xff\x0f', 0xFFFFFFFF)
def test_decode(self):
self.assertEqualDecode(1, 1, '\x01')
self.assertEqualDecode(2, 1, '\x02')
self.assertEqualDecode(127, 1, '\x7f')
self.assertEqualDecode(128, 2, '\x80\x01')
self.assertEqualDecode(255, 2, '\xff\x01')
self.assertEqualDecode(256, 2, '\x80\x02')
self.assertEqualDecode(0xFFFFFFFF, 5, '\xff\xff\xff\xff\x0f')
def test_decode_with_trailing_bytes(self):
self.assertEqualDecode(1, 1, '\x01abcdef')
self.assertEqualDecode(127, 1, '\x7f\x01')
self.assertEqualDecode(128, 2, '\x80\x01abcdef')
self.assertEqualDecode(255, 2, '\xff\x01\xff')
class TestGroupCompressBlock(tests.TestCase):
def test_from_empty_bytes(self):
self.assertRaises(errors.InvalidGroupCompressBlock,
groupcompress.GroupCompressBlock.from_bytes, '')
def test_from_minimal_bytes(self):
block = groupcompress.GroupCompressBlock.from_bytes('gcb1z\n0\n0\n')
self.assertIsInstance(block, groupcompress.GroupCompressBlock)
self.assertEqual({}, block._entries)
def test_from_bytes(self):
z_header_bytes = (
'gcb1z\n' # group compress block v1 plain
'76\n' # Length of zlib bytes
'183\n' # Length of all meta-info
+ zlib.compress(
'key:bing\n'
'sha1:abcdabcdabcdabcdabcdabcdabcdabcdabcdabcd\n'
'type:fulltext\n'
'start:100\n'
'length:100\n'
'\n'
'key:foo\x00bar\n'
'sha1:abcdabcdabcdabcdabcdabcdabcdabcdabcdabcd\n'
'type:fulltext\n'
'start:0\n'
'length:100\n'
'\n'))
block = groupcompress.GroupCompressBlock.from_bytes(
z_header_bytes)
self.assertIs(None, block._content)
self.assertIsInstance(block, groupcompress.GroupCompressBlock)
self.assertEqual([('bing',), ('foo', 'bar')], sorted(block._entries))
bing = block._entries[('bing',)]
self.assertEqual(('bing',), bing.key)
self.assertEqual('fulltext', bing.type)
self.assertEqual('abcd'*10, bing.sha1)
self.assertEqual(100, bing.start)
self.assertEqual(100, bing.length)
foobar = block._entries[('foo', 'bar')]
self.assertEqual(('foo', 'bar'), foobar.key)
self.assertEqual('fulltext', foobar.type)
self.assertEqual('abcd'*10, foobar.sha1)
self.assertEqual(0, foobar.start)
self.assertEqual(100, foobar.length)
def test_add_entry(self):
gcb = groupcompress.GroupCompressBlock()
e = gcb.add_entry(('foo', 'bar'), 'fulltext', 'abcd'*10, 0, 100)
self.assertIsInstance(e, groupcompress.GroupCompressBlockEntry)
self.assertEqual(('foo', 'bar'), e.key)
self.assertEqual('fulltext', e.type)
self.assertEqual('abcd'*10, e.sha1)
self.assertEqual(0, e.start)
self.assertEqual(100, e.length)
def test_to_bytes(self):
gcb = groupcompress.GroupCompressBlock()
gcb.add_entry(('foo', 'bar'), 'fulltext', 'abcd'*10, 0, 100)
gcb.add_entry(('bing',), 'fulltext', 'abcd'*10, 100, 100)
bytes = gcb.to_bytes()
self.assertStartsWith(bytes,
'gcb1z\n' # group compress block v1 zlib
'77\n' # Length of compressed bytes
'183\n' # Length of all meta-info
)
remaining_bytes = bytes[13:]
raw_bytes = zlib.decompress(remaining_bytes)
self.assertEqualDiff('key:bing\n'
'sha1:abcdabcdabcdabcdabcdabcdabcdabcdabcdabcd\n'
'type:fulltext\n'
'start:100\n'
'length:100\n'
'\n'
'key:foo\x00bar\n'
'sha1:abcdabcdabcdabcdabcdabcdabcdabcdabcdabcd\n'
'type:fulltext\n'
'start:0\n'
'length:100\n'
'\n', raw_bytes)
|