/usr/lib/python3/dist-packages/joblib/test/test_numpy_pickle.py is in python3-joblib 0.10.3+git55-g660fe5d-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 | """Test the numpy pickler as a replacement of the standard pickler."""
from tempfile import mkdtemp
import copy
import shutil
import os
import random
import sys
import re
import tempfile
import io
import warnings
import gzip
import zlib
import bz2
import pickle
import socket
from contextlib import closing
from joblib.test.common import np, with_numpy
from joblib.test.common import with_memory_profiler, memory_used
from joblib.testing import (assert_equal, assert_raises, assert_raises_regex,
SkipTest)
# numpy_pickle is not a drop-in replacement of pickle, as it takes
# filenames instead of open files as arguments.
from joblib import numpy_pickle
from joblib.test import data
from joblib._compat import PY3_OR_LATER
from joblib.numpy_pickle_utils import _IO_BUFFER_SIZE, BinaryZlibFile
from joblib.numpy_pickle_utils import _detect_compressor, _COMPRESSORS
###############################################################################
# Define a list of standard types.
# Borrowed from dill, initial author: Micheal McKerns:
# http://dev.danse.us/trac/pathos/browser/dill/dill_test2.py
typelist = []
# testing types
_none = None
typelist.append(_none)
_type = type
typelist.append(_type)
_bool = bool(1)
typelist.append(_bool)
_int = int(1)
typelist.append(_int)
try:
_long = long(1)
typelist.append(_long)
except NameError:
# long is not defined in python 3
pass
_float = float(1)
typelist.append(_float)
_complex = complex(1)
typelist.append(_complex)
_string = str(1)
typelist.append(_string)
try:
_unicode = unicode(1)
typelist.append(_unicode)
except NameError:
# unicode is not defined in python 3
pass
_tuple = ()
typelist.append(_tuple)
_list = []
typelist.append(_list)
_dict = {}
typelist.append(_dict)
try:
_file = file
typelist.append(_file)
except NameError:
pass # file does not exists in Python 3
try:
_buffer = buffer
typelist.append(_buffer)
except NameError:
# buffer does not exists in Python 3
pass
_builtin = len
typelist.append(_builtin)
def _function(x):
yield x
class _class:
def _method(self):
pass
class _newclass(object):
def _method(self):
pass
typelist.append(_function)
typelist.append(_class)
typelist.append(_newclass) # <type 'type'>
_instance = _class()
typelist.append(_instance)
_object = _newclass()
typelist.append(_object) # <type 'class'>
###############################################################################
# Test fixtures
env = dict()
def setup_module():
""" Test setup.
"""
env['dir'] = mkdtemp()
env['filename'] = os.path.join(env['dir'], 'test.pkl')
print(80 * '_')
print('setup numpy_pickle')
print(80 * '_')
def teardown_module():
""" Test teardown.
"""
shutil.rmtree(env['dir'])
# del env['dir']
# del env['filename']
print(80 * '_')
print('teardown numpy_pickle')
print(80 * '_')
###############################################################################
# Tests
def test_standard_types():
# Test pickling and saving with standard types.
filename = env['filename']
for compress in [0, 1]:
for member in typelist:
# Change the file name to avoid side effects between tests
this_filename = filename + str(random.randint(0, 1000))
numpy_pickle.dump(member, this_filename, compress=compress)
_member = numpy_pickle.load(this_filename)
# We compare the pickled instance to the reloaded one only if it
# can be compared to a copied one
if member == copy.deepcopy(member):
yield assert_equal, member, _member
def test_value_error():
# Test inverting the input arguments to dump
assert_raises(ValueError, numpy_pickle.dump, 'foo', dict())
def test_compress_level_error():
# Verify that passing an invalid compress argument raises an error.
wrong_compress = (-1, 10, 'wrong')
for wrong in wrong_compress:
exception_msg = 'Non valid compress level given: "{0}"'.format(wrong)
assert_raises_regex(ValueError,
exception_msg,
numpy_pickle.dump, 'dummy', 'foo', compress=wrong)
@with_numpy
def test_numpy_persistence():
filename = env['filename']
rnd = np.random.RandomState(0)
a = rnd.random_sample((10, 2))
for compress in (False, True, 0, 3):
# We use 'a.T' to have a non C-contiguous array.
for index, obj in enumerate(((a,), (a.T,), (a, a), [a, a, a])):
# Change the file name to avoid side effects between tests
this_filename = filename + str(random.randint(0, 1000))
filenames = numpy_pickle.dump(obj, this_filename,
compress=compress)
# All is cached in one file
assert len(filenames) == 1
# Check that only one file was created
assert filenames[0] == this_filename
# Check that this file does exist
assert os.path.exists(os.path.join(env['dir'], filenames[0]))
# Unpickle the object
obj_ = numpy_pickle.load(this_filename)
# Check that the items are indeed arrays
for item in obj_:
assert isinstance(item, np.ndarray)
# And finally, check that all the values are equal.
np.testing.assert_array_equal(np.array(obj), np.array(obj_))
# Now test with array subclasses
for obj in (np.matrix(np.zeros(10)),
np.memmap(filename + str(random.randint(0, 1000)) + 'mmap',
mode='w+', shape=4, dtype=np.float)):
this_filename = filename + str(random.randint(0, 1000))
filenames = numpy_pickle.dump(obj, this_filename,
compress=compress)
# All is cached in one file
assert len(filenames) == 1
obj_ = numpy_pickle.load(this_filename)
if (type(obj) is not np.memmap and
hasattr(obj, '__array_prepare__')):
# We don't reconstruct memmaps
assert isinstance(obj_, type(obj))
np.testing.assert_array_equal(obj_, obj)
# Test with an object containing multiple numpy arrays
obj = ComplexTestObject()
filenames = numpy_pickle.dump(obj, this_filename,
compress=compress)
# All is cached in one file
assert len(filenames) == 1
obj_loaded = numpy_pickle.load(this_filename)
assert isinstance(obj_loaded, type(obj))
np.testing.assert_array_equal(obj_loaded.array_float, obj.array_float)
np.testing.assert_array_equal(obj_loaded.array_int, obj.array_int)
np.testing.assert_array_equal(obj_loaded.array_obj, obj.array_obj)
@with_numpy
def test_numpy_persistence_bufferred_array_compression():
big_array = np.ones((_IO_BUFFER_SIZE + 100), dtype=np.uint8)
filename = env['filename'] + str(random.randint(0, 1000))
numpy_pickle.dump(big_array, filename, compress=True)
arr_reloaded = numpy_pickle.load(filename)
np.testing.assert_array_equal(big_array, arr_reloaded)
@with_numpy
def test_memmap_persistence():
rnd = np.random.RandomState(0)
a = rnd.random_sample(10)
filename = env['filename'] + str(random.randint(0, 1000))
numpy_pickle.dump(a, filename)
b = numpy_pickle.load(filename, mmap_mode='r')
assert isinstance(b, np.memmap)
# Test with an object containing multiple numpy arrays
filename = env['filename'] + str(random.randint(0, 1000))
obj = ComplexTestObject()
numpy_pickle.dump(obj, filename)
obj_loaded = numpy_pickle.load(filename, mmap_mode='r')
assert isinstance(obj_loaded, type(obj))
assert isinstance(obj_loaded.array_float, np.memmap)
assert not obj_loaded.array_float.flags.writeable
assert isinstance(obj_loaded.array_int, np.memmap)
assert not obj_loaded.array_int.flags.writeable
# Memory map not allowed for numpy object arrays
assert not isinstance(obj_loaded.array_obj, np.memmap)
np.testing.assert_array_equal(obj_loaded.array_float,
obj.array_float)
np.testing.assert_array_equal(obj_loaded.array_int,
obj.array_int)
np.testing.assert_array_equal(obj_loaded.array_obj,
obj.array_obj)
# Test we can write in memmaped arrays
obj_loaded = numpy_pickle.load(filename, mmap_mode='r+')
assert obj_loaded.array_float.flags.writeable
obj_loaded.array_float[0:10] = 10.0
assert obj_loaded.array_int.flags.writeable
obj_loaded.array_int[0:10] = 10
obj_reloaded = numpy_pickle.load(filename, mmap_mode='r')
np.testing.assert_array_equal(obj_reloaded.array_float,
obj_loaded.array_float)
np.testing.assert_array_equal(obj_reloaded.array_int,
obj_loaded.array_int)
# Test w+ mode is caught and the mode has switched to r+
numpy_pickle.load(filename, mmap_mode='w+')
assert obj_loaded.array_int.flags.writeable
assert obj_loaded.array_int.mode == 'r+'
assert obj_loaded.array_float.flags.writeable
assert obj_loaded.array_float.mode == 'r+'
@with_numpy
def test_memmap_persistence_mixed_dtypes():
# loading datastructures that have sub-arrays with dtype=object
# should not prevent memmaping on fixed size dtype sub-arrays.
rnd = np.random.RandomState(0)
a = rnd.random_sample(10)
b = np.array([1, 'b'], dtype=object)
construct = (a, b)
filename = env['filename'] + str(random.randint(0, 1000))
numpy_pickle.dump(construct, filename)
a_clone, b_clone = numpy_pickle.load(filename, mmap_mode='r')
# the floating point array has been memory mapped
assert isinstance(a_clone, np.memmap)
# the object-dtype array has been loaded in memory
assert not isinstance(b_clone, np.memmap)
@with_numpy
def test_masked_array_persistence():
# The special-case picker fails, because saving masked_array
# not implemented, but it just delegates to the standard pickler.
rnd = np.random.RandomState(0)
a = rnd.random_sample(10)
a = np.ma.masked_greater(a, 0.5)
filename = env['filename'] + str(random.randint(0, 1000))
numpy_pickle.dump(a, filename)
b = numpy_pickle.load(filename, mmap_mode='r')
assert isinstance(b, np.ma.masked_array)
@with_numpy
def test_compress_mmap_mode_warning():
# Test the warning in case of compress + mmap_mode
rnd = np.random.RandomState(0)
a = rnd.random_sample(10)
this_filename = env['filename'] + str(random.randint(0, 1000))
numpy_pickle.dump(a, this_filename, compress=1)
with warnings.catch_warnings(record=True) as caught_warnings:
warnings.simplefilter("always")
numpy_pickle.load(this_filename, mmap_mode='r+')
assert len(caught_warnings) == 1
for warn in caught_warnings:
assert warn.category == UserWarning
assert (warn.message.args[0] ==
'mmap_mode "%(mmap_mode)s" is not compatible with '
'compressed file %(filename)s. "%(mmap_mode)s" flag will '
'be ignored.' % {'filename': this_filename,
'mmap_mode': 'r+'})
@with_numpy
def test_cache_size_warning():
# Check deprecation warning raised when cache size is not None
filename = env['filename'] + str(random.randint(0, 1000))
rnd = np.random.RandomState(0)
a = rnd.random_sample((10, 2))
for cache_size in (None, 0, 10):
with warnings.catch_warnings(record=True) as caught_warnings:
warnings.simplefilter("always")
numpy_pickle.dump(a, filename, cache_size=cache_size)
expected_nb_warnings = 1 if cache_size is not None else 0
assert len(caught_warnings) == expected_nb_warnings
for warn in caught_warnings:
assert warn.category == DeprecationWarning
assert (warn.message.args[0] ==
"Please do not set 'cache_size' in joblib.dump, this "
"parameter has no effect and will be removed. You "
"used 'cache_size={0}'".format(cache_size))
@with_numpy
@with_memory_profiler
def test_memory_usage():
# Verify memory stays within expected bounds.
filename = env['filename']
small_array = np.ones((10, 10))
big_array = np.ones(shape=100 * int(1e6), dtype=np.uint8)
small_matrix = np.matrix(small_array)
big_matrix = np.matrix(big_array)
for compress in (True, False):
for obj in (small_array, big_array, small_matrix, big_matrix):
size = obj.nbytes / 1e6
obj_filename = filename + str(np.random.randint(0, 1000))
mem_used = memory_used(numpy_pickle.dump,
obj, obj_filename, compress=compress)
# The memory used to dump the object shouldn't exceed the buffer
# size used to write array chunks (16MB).
write_buf_size = _IO_BUFFER_SIZE + 16 * 1024 ** 2 / 1e6
assert mem_used <= write_buf_size
mem_used = memory_used(numpy_pickle.load, obj_filename)
# memory used should be less than array size + buffer size used to
# read the array chunk by chunk.
read_buf_size = 32 + _IO_BUFFER_SIZE # MiB
assert mem_used < size + read_buf_size
@with_numpy
def test_compressed_pickle_dump_and_load():
expected_list = [np.arange(5, dtype=np.dtype('<i8')),
np.arange(5, dtype=np.dtype('>i8')),
np.arange(5, dtype=np.dtype('<f8')),
np.arange(5, dtype=np.dtype('>f8')),
np.array([1, 'abc', {'a': 1, 'b': 2}], dtype='O'),
# .tostring actually returns bytes and is a
# compatibility alias for .tobytes which was
# added in 1.9.0
np.arange(256, dtype=np.uint8).tostring(),
# np.matrix is a subclass of np.ndarray, here we want
# to verify this type of object is correctly unpickled
# among versions.
np.matrix([0, 1, 2], dtype=np.dtype('<i8')),
np.matrix([0, 1, 2], dtype=np.dtype('>i8')),
u"C'est l'\xe9t\xe9 !"]
with tempfile.NamedTemporaryFile(suffix='.gz', dir=env['dir']) as f:
fname = f.name
try:
dumped_filenames = numpy_pickle.dump(expected_list, fname, compress=1)
assert len(dumped_filenames) == 1
result_list = numpy_pickle.load(fname)
for result, expected in zip(result_list, expected_list):
if isinstance(expected, np.ndarray):
assert result.dtype == expected.dtype
np.testing.assert_equal(result, expected)
else:
assert result == expected
finally:
os.remove(fname)
def _check_pickle(filename, expected_list):
"""Helper function to test joblib pickle content.
Note: currently only pickles containing an iterable are supported
by this function.
"""
if (not PY3_OR_LATER and (filename.endswith('.xz') or
filename.endswith('.lzma'))):
# lzma is not supported for python versions < 3.3
assert_raises(NotImplementedError, numpy_pickle.load, filename)
return
version_match = re.match(r'.+py(\d)(\d).+', filename)
py_version_used_for_writing = int(version_match.group(1))
py_version_used_for_reading = sys.version_info[0]
py_version_to_default_pickle_protocol = {2: 2, 3: 3}
pickle_reading_protocol = py_version_to_default_pickle_protocol.get(
py_version_used_for_reading, 4)
pickle_writing_protocol = py_version_to_default_pickle_protocol.get(
py_version_used_for_writing, 4)
if pickle_reading_protocol >= pickle_writing_protocol:
try:
with warnings.catch_warnings(record=True) as caught_warnings:
warnings.simplefilter('always')
warnings.filterwarnings(
'ignore', module='numpy',
message='The compiler package is deprecated')
result_list = numpy_pickle.load(filename)
filename_base = os.path.basename(filename)
expected_nb_warnings = 1 if ("_0.9" in filename_base or
"_0.8.4" in filename_base) else 0
assert len(caught_warnings) == expected_nb_warnings
for warn in caught_warnings:
assert warn.category == DeprecationWarning
assert (warn.message.args[0] ==
"The file '{0}' has been generated with a joblib "
"version less than 0.10. Please regenerate this "
"pickle file.".format(filename))
for result, expected in zip(result_list, expected_list):
if isinstance(expected, np.ndarray):
assert result.dtype == expected.dtype
np.testing.assert_equal(result, expected)
else:
assert result == expected
except Exception as exc:
# When trying to read with python 3 a pickle generated
# with python 2 we expect a user-friendly error
if (py_version_used_for_reading == 3 and
py_version_used_for_writing == 2):
assert isinstance(exc, ValueError)
message = ('You may be trying to read with '
'python 3 a joblib pickle generated with python 2.')
assert message in str(exc)
else:
raise
else:
# Pickle protocol used for writing is too high. We expect a
# "unsupported pickle protocol" error message
try:
numpy_pickle.load(filename)
raise AssertionError('Numpy pickle loading should '
'have raised a ValueError exception')
except ValueError as e:
message = 'unsupported pickle protocol: {0}'.format(
pickle_writing_protocol)
assert message in str(e.args)
@with_numpy
def test_joblib_pickle_across_python_versions():
# We need to be specific about dtypes in particular endianness
# because the pickles can be generated on one architecture and
# the tests run on another one. See
# https://github.com/joblib/joblib/issues/279.
expected_list = [np.arange(5, dtype=np.dtype('<i8')),
np.arange(5, dtype=np.dtype('<f8')),
np.array([1, 'abc', {'a': 1, 'b': 2}], dtype='O'),
# .tostring actually returns bytes and is a
# compatibility alias for .tobytes which was
# added in 1.9.0
np.arange(256, dtype=np.uint8).tostring(),
# np.matrix is a subclass of np.ndarray, here we want
# to verify this type of object is correctly unpickled
# among versions.
np.matrix([0, 1, 2], dtype=np.dtype('<i8')),
u"C'est l'\xe9t\xe9 !"]
# Testing all the compressed and non compressed
# pickles in joblib/test/data. These pickles were generated by
# the joblib/test/data/create_numpy_pickle.py script for the
# relevant python, joblib and numpy versions.
test_data_dir = os.path.dirname(os.path.abspath(data.__file__))
pickle_extensions = ('.pkl', '.gz', '.gzip', '.bz2', '.xz', '.lzma')
pickle_filenames = [os.path.join(test_data_dir, fn)
for fn in os.listdir(test_data_dir)
if any(fn.endswith(ext) for ext in pickle_extensions)]
for fname in pickle_filenames:
_check_pickle(fname, expected_list)
def test_compress_tuple_argument():
compress_tuples = (('zlib', 3),
('gzip', 3))
# Verify the tuple is correctly taken into account.
filename = env['filename'] + str(random.randint(0, 1000))
for compress in compress_tuples:
numpy_pickle.dump("dummy", filename,
compress=compress)
# Verify the file contains the right magic number
with open(filename, 'rb') as f:
assert _detect_compressor(f) == compress[0]
# Verify setting a wrong compress tuple raises a ValueError.
assert_raises_regex(ValueError,
'Compress argument tuple should contain exactly '
'2 elements',
numpy_pickle.dump, "dummy", filename,
compress=('zlib', 3, 'extra'))
# Verify a tuple with a wrong compress method raises a ValueError.
msg = 'Non valid compression method given: "{}"'.format('wrong')
assert_raises_regex(ValueError, msg,
numpy_pickle.dump, "dummy", filename,
compress=('wrong', 3))
# Verify a tuple with a wrong compress level raises a ValueError.
msg = 'Non valid compress level given: "{}"'.format('wrong')
assert_raises_regex(ValueError, msg,
numpy_pickle.dump, "dummy", filename,
compress=('zlib', 'wrong'))
@with_numpy
def test_joblib_compression_formats():
compresslevels = (1, 3, 6)
filename = env['filename'] + str(random.randint(0, 1000))
objects = (np.ones(shape=(100, 100), dtype='f8'),
range(10),
{'a': 1, 2: 'b'}, [], (), {}, 0, 1.0)
for compress in compresslevels:
for cmethod in _COMPRESSORS:
dump_filename = filename + "." + cmethod
for obj in objects:
if not PY3_OR_LATER and cmethod in ('xz', 'lzma'):
# Lzma module only available for python >= 3.3
msg = "{} compression is only available".format(cmethod)
assert_raises_regex(NotImplementedError, msg,
numpy_pickle.dump, obj, dump_filename,
compress=(cmethod, compress))
else:
numpy_pickle.dump(obj, dump_filename,
compress=(cmethod, compress))
# Verify the file contains the right magic number
with open(dump_filename, 'rb') as f:
assert _detect_compressor(f) == cmethod
# Verify the reloaded object is correct
obj_reloaded = numpy_pickle.load(dump_filename)
assert isinstance(obj_reloaded, type(obj))
if isinstance(obj, np.ndarray):
np.testing.assert_array_equal(obj_reloaded, obj)
else:
assert obj_reloaded == obj
os.remove(dump_filename)
def _gzip_file_decompress(source_filename, target_filename):
"""Decompress a gzip file."""
with closing(gzip.GzipFile(source_filename, "rb")) as fo:
buf = fo.read()
with open(target_filename, "wb") as fo:
fo.write(buf)
def _zlib_file_decompress(source_filename, target_filename):
"""Decompress a zlib file."""
with open(source_filename, 'rb') as fo:
buf = zlib.decompress(fo.read())
with open(target_filename, 'wb') as fo:
fo.write(buf)
def test_load_externally_decompressed_files():
# Test that BinaryZlibFile generates valid gzip and zlib compressed files.
obj = "a string to persist"
filename_raw = env['filename'] + str(random.randint(0, 1000))
compress_list = (('.z', _zlib_file_decompress),
('.gz', _gzip_file_decompress))
for extension, decompress in compress_list:
filename_compressed = filename_raw + extension
# Use automatic extension detection to compress with the right method.
numpy_pickle.dump(obj, filename_compressed)
# Decompress with the corresponding method
decompress(filename_compressed, filename_raw)
# Test that the uncompressed pickle can be loaded and
# that the result is correct.
obj_reloaded = numpy_pickle.load(filename_raw)
assert obj == obj_reloaded
# Do some cleanup
os.remove(filename_raw)
if os.path.exists(filename_compressed):
os.remove(filename_compressed)
def test_compression_using_file_extension():
# test that compression method corresponds to the given filename extension.
extensions_dict = {
# valid compressor extentions
'.z': 'zlib',
'.gz': 'gzip',
'.bz2': 'bz2',
'.lzma': 'lzma',
'.xz': 'xz',
# invalid compressor extensions
'.pkl': 'not-compressed',
'': 'not-compressed'
}
filename = env['filename'] + str(random.randint(0, 1000))
obj = "object to dump"
for ext, cmethod in extensions_dict.items():
dump_fname = filename + ext
if not PY3_OR_LATER and cmethod in ('xz', 'lzma'):
# Lzma module only available for python >= 3.3
msg = "{} compression is only available".format(cmethod)
assert_raises_regex(NotImplementedError, msg,
numpy_pickle.dump, obj, dump_fname)
else:
numpy_pickle.dump(obj, dump_fname)
# Verify the file contains the right magic number
with open(dump_fname, 'rb') as f:
assert _detect_compressor(f) == cmethod
# Verify the reloaded object is correct
obj_reloaded = numpy_pickle.load(dump_fname)
assert isinstance(obj_reloaded, type(obj))
assert obj_reloaded == obj
os.remove(dump_fname)
@with_numpy
def test_file_handle_persistence():
objs = [np.random.random((10, 10)),
"some data",
np.matrix([0, 1, 2])]
fobjs = [bz2.BZ2File, gzip.GzipFile]
if PY3_OR_LATER:
import lzma
fobjs += [lzma.LZMAFile]
filename = env['filename'] + str(random.randint(0, 1000))
for obj in objs:
for fobj in fobjs:
with fobj(filename, 'wb') as f:
numpy_pickle.dump(obj, f)
# using the same decompressor prevents from internally
# decompress again.
with fobj(filename, 'rb') as f:
obj_reloaded = numpy_pickle.load(f)
# when needed, the correct decompressor should be used when
# passing a raw file handle.
with open(filename, 'rb') as f:
obj_reloaded_2 = numpy_pickle.load(f)
if isinstance(obj, np.ndarray):
np.testing.assert_array_equal(obj_reloaded, obj)
np.testing.assert_array_equal(obj_reloaded_2, obj)
else:
assert obj_reloaded == obj
assert obj_reloaded_2 == obj
os.remove(filename)
@with_numpy
def test_in_memory_persistence():
objs = [np.random.random((10, 10)),
"some data",
np.matrix([0, 1, 2])]
for obj in objs:
f = io.BytesIO()
numpy_pickle.dump(obj, f)
obj_reloaded = numpy_pickle.load(f)
if isinstance(obj, np.ndarray):
np.testing.assert_array_equal(obj_reloaded, obj)
else:
assert obj_reloaded == obj
@with_numpy
def test_file_handle_persistence_mmap():
obj = np.random.random((10, 10))
filename = env['filename'] + str(random.randint(0, 1000))
with open(filename, 'wb') as f:
numpy_pickle.dump(obj, f)
with open(filename, 'rb') as f:
obj_reloaded = numpy_pickle.load(f, mmap_mode='r+')
np.testing.assert_array_equal(obj_reloaded, obj)
@with_numpy
def test_file_handle_persistence_compressed_mmap():
obj = np.random.random((10, 10))
filename = env['filename'] + str(random.randint(0, 1000))
with open(filename, 'wb') as f:
numpy_pickle.dump(obj, f, compress=('gzip', 3))
with closing(gzip.GzipFile(filename, 'rb')) as f:
with warnings.catch_warnings(record=True) as caught_warnings:
warnings.simplefilter("always")
numpy_pickle.load(f, mmap_mode='r+')
assert len(caught_warnings) == 1
for warn in caught_warnings:
assert warn.category == UserWarning
assert (warn.message.args[0] ==
'"%(fileobj)r" is not a raw file, mmap_mode '
'"%(mmap_mode)s" flag will be ignored.'
% {'fileobj': f, 'mmap_mode': 'r+'})
@with_numpy
def test_file_handle_persistence_in_memory_mmap():
obj = np.random.random((10, 10))
buf = io.BytesIO()
numpy_pickle.dump(obj, buf)
with warnings.catch_warnings(record=True) as caught_warnings:
warnings.simplefilter("always")
numpy_pickle.load(buf, mmap_mode='r+')
assert len(caught_warnings) == 1
for warn in caught_warnings:
assert warn.category == UserWarning
assert (warn.message.args[0] ==
'In memory persistence is not compatible with '
'mmap_mode "%(mmap_mode)s" flag passed. mmap_mode '
'option will be ignored.' % {'mmap_mode': 'r+'})
def test_binary_zlibfile():
filename = env['filename'] + str(random.randint(0, 1000))
# Test bad compression levels
for bad_value in (-1, 10, 15, 'a', (), {}):
assert_raises(ValueError, BinaryZlibFile, filename, 'wb',
compresslevel=bad_value)
# Test invalid modes
for bad_mode in ('a', 'x', 'r', 'w', 1, 2):
assert_raises(ValueError, BinaryZlibFile, filename, bad_mode)
# Test wrong filename type (not a string or a file)
for bad_file in (1, (), {}):
assert_raises(TypeError, BinaryZlibFile, bad_file, 'rb')
for d in (b'a little data as bytes.',
# More bytes
10000 * "{}"
.format(random.randint(0, 1000) * 1000).encode('latin-1')):
# Regular cases
for compress_level in (1, 3, 9):
with open(filename, 'wb') as f:
with BinaryZlibFile(f, 'wb',
compresslevel=compress_level) as fz:
assert fz.writable()
fz.write(d)
assert fz.fileno() == f.fileno()
assert_raises(io.UnsupportedOperation, fz._check_can_read)
assert_raises(io.UnsupportedOperation, fz._check_can_seek)
assert fz.closed
assert_raises(ValueError, fz._check_not_closed)
with open(filename, 'rb') as f:
with BinaryZlibFile(f) as fz:
assert fz.readable()
if PY3_OR_LATER:
assert fz.seekable()
assert fz.fileno() == f.fileno()
assert fz.read() == d
assert_raises(io.UnsupportedOperation,
fz._check_can_write)
if PY3_OR_LATER:
# io.BufferedIOBase doesn't have seekable() method in
# python 2
assert fz.seekable()
fz.seek(0)
assert fz.tell() == 0
assert fz.closed
os.remove(filename)
# Test with a filename as input
with BinaryZlibFile(filename, 'wb',
compresslevel=compress_level) as fz:
assert fz.writable()
fz.write(d)
with BinaryZlibFile(filename, 'rb') as fz:
assert fz.read() == d
assert fz.seekable()
# Test without context manager
fz = BinaryZlibFile(filename, 'wb', compresslevel=compress_level)
assert fz.writable()
fz.write(d)
fz.close()
fz = BinaryZlibFile(filename, 'rb')
assert fz.read() == d
fz.close()
###############################################################################
# Test dumping array subclasses
if np is not None:
class SubArray(np.ndarray):
def __reduce__(self):
return _load_sub_array, (np.asarray(self), )
def _load_sub_array(arr):
d = SubArray(arr.shape)
d[:] = arr
return d
class ComplexTestObject:
"""A complex object containing numpy arrays as attributes."""
def __init__(self):
self.array_float = np.arange(100, dtype='float64')
self.array_int = np.ones(100, dtype='int32')
self.array_obj = np.array(['a', 10, 20.0], dtype='object')
@with_numpy
def test_numpy_subclass():
filename = env['filename']
a = SubArray((10,))
numpy_pickle.dump(a, filename)
c = numpy_pickle.load(filename)
assert isinstance(c, SubArray)
np.testing.assert_array_equal(c, a)
def test_pathlib():
try:
from pathlib import Path
except ImportError:
pass
else:
filename = env['filename']
value = 123
numpy_pickle.dump(value, Path(filename))
assert numpy_pickle.load(filename) == value
numpy_pickle.dump(value, filename)
assert numpy_pickle.load(Path(filename)) == value
@with_numpy
def test_non_contiguous_array_pickling():
filename = env['filename'] + str(random.randint(0, 1000))
for array in [ # Array that triggers a contiguousness issue with nditer,
# see https://github.com/joblib/joblib/pull/352 and see
# https://github.com/joblib/joblib/pull/353
np.asfortranarray([[1, 2], [3, 4]])[1:],
# Non contiguous array with works fine with nditer
np.ones((10, 50, 20), order='F')[:, :1, :]]:
assert not array.flags.c_contiguous
assert not array.flags.f_contiguous
numpy_pickle.dump(array, filename)
array_reloaded = numpy_pickle.load(filename)
np.testing.assert_array_equal(array_reloaded, array)
os.remove(filename)
@with_numpy
def test_pickle_highest_protocol():
# ensure persistence of a numpy array is valid even when using
# the pickle HIGHEST_PROTOCOL.
# see https://github.com/joblib/joblib/issues/362
filename = env['filename'] + str(random.randint(0, 1000))
test_array = np.zeros(10)
numpy_pickle.dump(test_array, filename, protocol=pickle.HIGHEST_PROTOCOL)
array_reloaded = numpy_pickle.load(filename)
np.testing.assert_array_equal(array_reloaded, test_array)
@with_numpy
def test_pickle_in_socket():
# test that joblib can pickle in sockets
if not PY3_OR_LATER:
raise SkipTest("Cannot peek or seek in socket in python 2.")
test_array = np.arange(10)
_ADDR = ("localhost", 12345)
listener = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
listener.bind(_ADDR)
listener.listen(1)
client = socket.create_connection(_ADDR)
server, client_addr = listener.accept()
with server.makefile("wb") as sf:
numpy_pickle.dump(test_array, sf)
with client.makefile("rb") as cf:
array_reloaded = numpy_pickle.load(cf)
np.testing.assert_array_equal(array_reloaded, test_array)
|