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
|
# Copyright (c) 2013-2016, Freja Nordsiek
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# 1. Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
#
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
# HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
import os
import os.path
import random
import h5py
import hdf5storage
from asserts import *
from make_randoms import *
random.seed()
filename = 'data.mat'
def check_read_filters(filters):
# Read out the filter arguments.
filts = {'compression': 'gzip',
'shuffle': True,
'fletcher32': True,
'gzip_level': 7}
for k, v in filters.items():
filts[k] = v
if filts['compression'] == 'gzip':
filts['compression_opts'] = filts['gzip_level']
del filts['gzip_level']
# Make some random data.
dims = random.randint(1, 4)
data = random_numpy(shape=random_numpy_shape(dims,
max_array_axis_length),
dtype=random.choice(tuple(
set(dtypes) - set(['U']))))
# Make a random name.
name = random_name()
# Write the data to the proper file with the given name with the
# provided filters and read it backt. The file needs to be deleted
# before and after to keep junk from building up.
if os.path.exists(filename):
os.remove(filename)
try:
with h5py.File(filename, mode='w') as f:
f.create_dataset(name, data=data, chunks=True, **filts)
out = hdf5storage.read(path=name, filename=filename,
matlab_compatible=False)
except:
raise
finally:
if os.path.exists(filename):
os.remove(filename)
# Compare
assert_equal(out, data)
def check_write_filters(filters):
# Read out the filter arguments.
filts = {'compression': 'gzip',
'shuffle': True,
'fletcher32': True,
'gzip_level': 7}
for k, v in filters.items():
filts[k] = v
# Make some random data. The dtype must be restricted so that it can
# be read back reliably.
dims = random.randint(1, 4)
dts = tuple(set(dtypes) - set(['U', 'S', 'bool', 'complex64', \
'complex128']))
data = random_numpy(shape=random_numpy_shape(dims,
max_array_axis_length),
dtype=random.choice(dts))
# Make a random name.
name = random_name()
# Write the data to the proper file with the given name with the
# provided filters and read it backt. The file needs to be deleted
# before and after to keep junk from building up.
if os.path.exists(filename):
os.remove(filename)
try:
hdf5storage.write(data, path=name, filename=filename, \
store_python_metadata=False, matlab_compatible=False, \
compress=True, compress_size_threshold=0, \
compression_algorithm=filts['compression'], \
gzip_compression_level=filts['gzip_level'], \
shuffle_filter=filts['shuffle'], \
compressed_fletcher32_filter=filts['fletcher32'])
with h5py.File(filename, mode='r') as f:
d = f[name]
fletcher32 = d.fletcher32
shuffle = d.shuffle
compression = d.compression
gzip_level = d.compression_opts
out = d[...]
except:
raise
finally:
if os.path.exists(filename):
os.remove(filename)
# Check the filters
assert fletcher32 == filts['fletcher32']
assert shuffle == filts['shuffle']
assert compression == filts['compression']
if filts['compression'] == 'gzip':
assert gzip_level == filts['gzip_level']
# Compare
assert_equal(out, data)
def check_uncompressed_write_filters(method,
uncompressed_fletcher32_filter,
filters):
# Read out the filter arguments.
filts = {'compression': 'gzip',
'shuffle': True,
'fletcher32': True,
'gzip_level': 7}
for k, v in filters.items():
filts[k] = v
# Make some random data. The dtype must be restricted so that it can
# be read back reliably.
dims = random.randint(1, 4)
dts = tuple(set(dtypes) - set(['U', 'S', 'bool', 'complex64', \
'complex128']))
data = random_numpy(shape=random_numpy_shape(dims,
max_array_axis_length),
dtype=random.choice(dts))
# Make a random name.
name = random_name()
# Make the options to disable compression by the method specified,
# which is either that it is outright disabled or that the data is
# smaller than the compression threshold.
if method == 'compression_disabled':
opts = {'compress': False, 'compress_size_threshold': 0}
else:
opts = {'compress': True,
'compress_size_threshold': data.nbytes + 1}
# Write the data to the proper file with the given name with the
# provided filters and read it backt. The file needs to be deleted
# before and after to keep junk from building up.
if os.path.exists(filename):
os.remove(filename)
try:
hdf5storage.write(data, path=name, filename=filename, \
store_python_metadata=False, matlab_compatible=False, \
compression_algorithm=filts['compression'], \
gzip_compression_level=filts['gzip_level'], \
shuffle_filter=filts['shuffle'], \
compressed_fletcher32_filter=filts['fletcher32'], \
uncompressed_fletcher32_filter= \
uncompressed_fletcher32_filter, \
**opts)
with h5py.File(filename, mode='r') as f:
d = f[name]
fletcher32 = d.fletcher32
shuffle = d.shuffle
compression = d.compression
gzip_level = d.compression_opts
out = d[...]
except:
raise
finally:
if os.path.exists(filename):
os.remove(filename)
# Check the filters
assert compression == None
assert shuffle == False
assert fletcher32 == uncompressed_fletcher32_filter
# Compare
assert_equal(out, data)
def test_read_filtered_data():
for compression in ('gzip', 'lzf'):
for shuffle in (True, False):
for fletcher32 in (True, False):
if compression != 'gzip':
filters = {'compression': compression,
'shuffle': shuffle,
'fletcher32': fletcher32}
check_read_filters(filters)
else:
for level in range(10):
filters = {'compression': compression,
'shuffle': shuffle,
'fletcher32': fletcher32,
'gzip_level': level}
check_read_filters(filters)
def test_write_filtered_data():
for compression in ('gzip', 'lzf'):
for shuffle in (True, False):
for fletcher32 in (True, False):
if compression != 'gzip':
filters = {'compression': compression,
'shuffle': shuffle,
'fletcher32': fletcher32}
check_read_filters(filters)
else:
for level in range(10):
filters = {'compression': compression,
'shuffle': shuffle,
'fletcher32': fletcher32,
'gzip_level': level}
check_write_filters(filters)
def test_uncompressed_write_filtered_data():
for method in ('compression_disabled', 'data_too_small'):
for uncompressed_fletcher32_filter in (True, False):
for compression in ('gzip', 'lzf'):
for shuffle in (True, False):
for fletcher32 in (True, False):
if compression != 'gzip':
filters = {'compression': compression,
'shuffle': shuffle,
'fletcher32': fletcher32}
check_read_filters(filters)
else:
for level in range(10):
filters = {'compression': compression,
'shuffle': shuffle,
'fletcher32': fletcher32,
'gzip_level': level}
check_uncompressed_write_filters(method, uncompressed_fletcher32_filter, filters)
|
