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
|
# Unix SMB/CIFS implementation.
# Copyright © Catalyst
#
# 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 3 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, see <http://www.gnu.org/licenses/>.
from unittest import TestSuite
import os
import random
from samba.tests import TestCase
from samba import compression
TEST_DIR = "testdata/compression"
class BaseCompressionTest(TestCase):
def round_trip(self, data, size_delta=0):
"""Compress, decompress, assert equality with original.
If size_delta is None, no size is given to decompress. This
should fail with the Huffman varient and succeed with plain.
Otherwise size_delta is added to the gven size; if negative,
we'd expect a failure, with plain compression a positive delta
will succeed.
"""
compressed = self.compress(data)
if size_delta is None:
decompressed = self.decompress(compressed)
else:
decomp_size = len(data) + size_delta
decompressed = self.decompress(compressed, decomp_size)
if isinstance(data, str):
data = data.encode()
self.assertEqual(data, decompressed)
return compressed
def decompress_file(self, fn):
decomp_fn = os.path.join(TEST_DIR,
"decompressed",
fn + ".decomp")
comp_fn = os.path.join(TEST_DIR,
self.compressed_dir,
fn + self.compressed_suffix)
with open(decomp_fn, 'rb') as f:
decomp_expected = f.read()
with open(comp_fn, 'rb') as f:
comp = f.read()
decompressed = self.decompress(comp, len(decomp_expected))
self.assertEqual(decomp_expected, decompressed)
class LzxpressPlainCompressionTest(BaseCompressionTest):
compress = compression.plain_compress
decompress = compression.plain_decompress
compressed_dir = "compressed-plain"
compressed_suffix = ".lzplain"
def test_round_trip_aaa_str(self):
s = 'a' * 150000
self.round_trip(s)
def test_round_trip_aaa_bytes(self):
s = b'a' * 150000
self.round_trip(s)
def test_round_trip_aaa_short(self):
s = b'a' * 150000
# this'll fail because the match for 'aaa...' will run
# past the end of the buffer
self.assertRaises(compression.CompressionError,
self.round_trip, s, -1)
def test_round_trip_aaa_long(self):
s = b'a' * 150000
# this *wont* fail because although the data will run out
# before the buffer is full, LZXpress plain does not care
# about that.
try:
self.round_trip(s, 1)
except compression.CompressionError as e:
self.fail(f"failed to decompress with {e}")
def test_round_trip_aaab_short(self):
s = b'a' * 150000 + b'b'
# this will *partially* succeed, because the buffer will fill
# up vat a break in the decompression (not mid-match), and
# lzxpress plain does not mind that. However self.round_trip
# also makes an assertion that the original data equals the
# decompressed result, and it won't because the decompressed
# result is one byte shorter.
self.assertRaises(AssertionError,
self.round_trip, s, -1)
def test_round_trip_aaab_unstated(self):
s = b'a' * 150000 + b'b'
# this will succeed, because with no target size given, we
# guess a large buffer in the python bindings.
try:
self.round_trip(s)
except compression.CompressionError as e:
self.fail(f"failed to decompress with {e}")
def test_round_trip_30mb(self):
s = b'abc' * 10000000
# This will decompress into a string bigger than the python
# bindings are willing to speculatively allocate, so will fail
# to decompress.
with self.assertRaises(compression.CompressionError):
self.round_trip(s, None)
# but it will be fine if we use the length
try:
self.round_trip(s, 0)
except compression.CompressionError as e:
self.fail(f"failed to decompress with {e}")
def test_files(self):
# We don't go through the whole set, which are already tested
# by lib/compression/tests/test_lzxpress_plain.c
for fn in ("slow-33d90a24e70515b14cd0",
"midsummer-nights-dream.txt"):
self.decompress_file(fn)
def test_empty_round_trip(self):
# not symmetrical with Huffman, this doesn't fail
self.round_trip('')
class LzxpressHuffmanCompressionTest(BaseCompressionTest):
compress = compression.huffman_compress
decompress = compression.huffman_decompress
compressed_dir = "compressed-huffman"
compressed_suffix = ".lzhuff"
def test_round_trip_aaa_str(self):
s = 'a' * 150000
self.round_trip(s)
def test_round_trip_aaa_bytes(self):
s = b'a' * 150000
self.round_trip(s)
def test_round_trip_aaa_short(self):
s = b'a' * 150000
# this'll fail because the match for 'aaa...' will run
# past the end of the buffer
self.assertRaises(compression.CompressionError,
self.round_trip, s, -1)
def test_round_trip_aaa_long(self):
s = b'a' * 150000
# this'll fail because the data will run out before the buffer
# is full.
self.assertRaises(compression.CompressionError,
self.round_trip, s, 1)
def test_round_trip_aaab_short(self):
s = b'a' * 150000 + b'b'
# this *could* be allowed to succeed, because even though we
# give it the wrong size, we know the decompression will not
# flow over the end of the buffer, The behaviour here appears
# to be implementation dependent -- the decompressor has the
# option of saying 'whatever' and continuing. We are probably
# stricter than Windows.
self.assertRaises(compression.CompressionError,
self.round_trip, s, -1)
def test_round_trip_aaab_unstated(self):
s = b'a' * 150000 + b'b'
# For the Huffman algorithm, the length is really an essential
# part of the compression data, and the bindings will reject a
# call with out it. This happens at the arument parsing stage,
# so is a TypeError (i.e. wrong type of function), not a
# CompressionError.
self.assertRaises(TypeError,
self.round_trip, s, None)
def test_files(self):
# We don't go through the whole set, which are already tested
# by lib/compression/tests/test_lzx_huffman.c
for fn in ("slow-33d90a24e70515b14cd0",
"midsummer-nights-dream.txt"):
self.decompress_file(fn)
def test_empty_round_trip(self):
with self.assertRaises(compression.CompressionError):
self.round_trip('')
|
