##// END OF EJS Templates
copies-rust: start recording overwrite as they happens...
copies-rust: start recording overwrite as they happens If a revision has information overwriting data from another revision, the overwriting revision is a descendant of the overwritten one. So we could warm the Oracle cache with such information to avoid potential future `is_ancestors` call. This provide us with a large speedup in the most expensive cases: Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev --------------------------------------------------------------------------------------------------------------------------------------------------------------- mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 228985 revs, 41.113063 s, 36.001255 s, -5.111808 s, × 0.8757, 157 µs/rev mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 382065 revs, 27.891612 s, 14.340641 s, -13.550971 s, × 0.5142, 37 µs/rev Full comparison below: Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev --------------------------------------------------------------------------------------------------------------------------------------------------------------- mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 1 revs, 0.000042 s, 0.000042 s, +0.000000 s, × 1.0000, 42 µs/rev mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 6 revs, 0.000114 s, 0.000109 s, -0.000005 s, × 0.9561, 18 µs/rev mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 1032 revs, 0.004934 s, 0.004953 s, +0.000019 s, × 1.0039, 4 µs/rev pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 9 revs, 0.000195 s, 0.000237 s, +0.000042 s, × 1.2154, 26 µs/rev pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 1 revs, 0.000050 s, 0.000050 s, +0.000000 s, × 1.0000, 50 µs/rev pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 7 revs, 0.000113 s, 0.000113 s, +0.000000 s, × 1.0000, 16 µs/rev pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 1 revs, 0.6f1f4a s, 0.6f1f4a s, +0.000000 s, × 1.0000, 322 µs/rev pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 6 revs, 0.010788 s, 0.010702 s, -0.000086 s, × 0.9920, 1783 µs/rev pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 4785 revs, 0.050880 s, 0.050504 s, -0.000376 s, × 0.9926, 10 µs/rev pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 6780 revs, 0.081760 s, 0.080159 s, -0.001601 s, × 0.9804, 11 µs/rev pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 5441 revs, 0.061382 s, 0.060058 s, -0.001324 s, × 0.9784, 11 µs/rev pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 43645 revs, 0.585802 s, 0.536950 s, -0.048852 s, × 0.9166, 12 µs/rev pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 2 revs, 0.012803 s, 0.012868 s, +0.000065 s, × 1.0051, 6434 µs/rev pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 11316 revs, 0.113558 s, 0.112806 s, -0.000752 s, × 0.9934, 9 µs/rev netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 2 revs, 0.000085 s, 0.000084 s, -0.000001 s, × 0.9882, 42 µs/rev netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 2 revs, 0.000106 s, 0.000106 s, +0.000000 s, × 1.0000, 53 µs/rev netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 3 revs, 0.000175 s, 0.000174 s, -0.000001 s, × 0.9943, 58 µs/rev netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 9 revs, 0.000721 s, 0.000726 s, +0.000005 s, × 1.0069, 80 µs/rev netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 1421 revs, 0.010127 s, 0.010105 s, -0.000022 s, × 0.9978, 7 µs/rev netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 1533 revs, 0.015616 s, 0.015748 s, +0.000132 s, × 1.0085, 10 µs/rev netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 5750 revs, 0.061341 s, 0.060357 s, -0.000984 s, × 0.9840, 10 µs/rev netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 66949 revs, 0.542214 s, 0.499356 s, -0.042858 s, × 0.9210, 7 µs/rev mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 2 revs, 0.000089 s, 0.000092 s, +0.000003 s, × 1.0337, 46 µs/rev mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 8 revs, 0.000279 s, 0.000279 s, +0.000000 s, × 1.0000, 34 µs/rev mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 9 revs, 0.000184 s, 0.000186 s, +0.000002 s, × 1.0109, 20 µs/rev mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 7 revs, 0.000661 s, 0.000660 s, -0.000001 s, × 0.9985, 94 µs/rev mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 3 revs, 0.003377 s, 0.003372 s, -0.000005 s, × 0.9985, 1124 µs/rev mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.070508 s, 0.070294 s, -0.000214 s, × 0.9970, 11715 µs/rev mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.006576 s, 0.006545 s, -0.000031 s, × 0.9953, 4 µs/rev mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.004809 s, 0.004998 s, +0.000189 s, × 1.0393, 121 µs/rev mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 7839 revs, 0.064872 s, 0.063348 s, -0.001524 s, × 0.9765, 8 µs/rev mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.026142 s, 0.026154 s, +0.000012 s, × 1.0005, 42 µs/rev mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 30263 revs, 0.203956 s, 0.199063 s, -0.004893 s, × 0.9760, 6 µs/rev mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 153721 revs, 1.763853 s, 1.277320 s, -0.486533 s, × 0.7242, 8 µs/rev mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 204976 revs, 2.609761 s, 1.698794 s, -0.910967 s, × 0.6509, 8 µs/rev mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 2 revs, 0.000847 s, 0.000842 s, -0.000005 s, × 0.9941, 421 µs/rev mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 2 revs, 0.000867 s, 0.000865 s, -0.000002 s, × 0.9977, 432 µs/rev mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 4 revs, 0.000161 s, 0.000160 s, -0.000001 s, × 0.9938, 40 µs/rev mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 2 revs, 0.001131 s, 0.001122 s, -0.000009 s, × 0.9920, 561 µs/rev mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 1 revs, 0.033114 s, 0.032743 s, -0.000371 s, × 0.9888, 32743 µs/rev mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.071092 s, 0.071529 s, +0.000437 s, × 1.0061, 11921 µs/rev mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.006554 s, 0.006593 s, +0.000039 s, × 1.0060, 4 µs/rev mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.005160 s, 0.005311 s, +0.000151 s, × 1.0293, 129 µs/rev mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 6657 revs, 0.065063 s, 0.063063 s, -0.002000 s, × 0.9693, 9 µs/rev mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 40314 revs, 0.297118 s, 0.312363 s, +0.015245 s, × 1.0513, 7 µs/rev mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 38690 revs, 0.284002 s, 0.283106 s, -0.000896 s, × 0.9968, 7 µs/rev mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 0.086311 s, 0.083817 s, -0.002494 s, × 0.9711, 9 µs/rev mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.026738 s, 0.026516 s, -0.000222 s, × 0.9917, 43 µs/rev mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 97052 revs, 1.514270 s, 1.304865 s, -0.209405 s, × 0.8617, 13 µs/rev mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 52031 revs, 0.735875 s, 0.681088 s, -0.054787 s, × 0.9255, 13 µs/rev mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 363753 revs, 4.843329 s, 4.454320 s, -0.389009 s, × 0.9197, 12 µs/rev mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 0.591752 s, 0.567913 s, -0.023839 s, × 0.9597, 16 µs/rev mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 362229 revs, 4.760563 s, 4.547043 s, -0.213520 s, × 0.9551, 12 µs/rev mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 359344 revs, 4.751942 s, 4.378579 s, -0.373363 s, × 0.9214, 12 µs/rev mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 192665 revs, 2.605014 s, 1.703622 s, -0.901392 s, × 0.6540, 8 µs/rev mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 228985 revs, 41.113063 s, 36.001255 s, -5.111808 s, × 0.8757, 157 µs/rev mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 382065 revs, 27.891612 s, 14.340641 s, -13.550971 s, × 0.5142, 37 µs/rev Differential Revision: https://phab.mercurial-scm.org/D9497

File last commit:

r44605:5e84a96d default
r46770:fce2f20a default
Show More
test_decompressor_fuzzing.py
593 lines | 18.9 KiB | text/x-python | PythonLexer
import io
import os
import unittest
try:
import hypothesis
import hypothesis.strategies as strategies
except ImportError:
raise unittest.SkipTest("hypothesis not available")
import zstandard as zstd
from .common import (
make_cffi,
NonClosingBytesIO,
random_input_data,
TestCase,
)
@unittest.skipUnless("ZSTD_SLOW_TESTS" in os.environ, "ZSTD_SLOW_TESTS not set")
@make_cffi
class TestDecompressor_stream_reader_fuzzing(TestCase):
@hypothesis.settings(
suppress_health_check=[
hypothesis.HealthCheck.large_base_example,
hypothesis.HealthCheck.too_slow,
]
)
@hypothesis.given(
original=strategies.sampled_from(random_input_data()),
level=strategies.integers(min_value=1, max_value=5),
streaming=strategies.booleans(),
source_read_size=strategies.integers(1, 1048576),
read_sizes=strategies.data(),
)
def test_stream_source_read_variance(
self, original, level, streaming, source_read_size, read_sizes
):
cctx = zstd.ZstdCompressor(level=level)
if streaming:
source = io.BytesIO()
writer = cctx.stream_writer(source)
writer.write(original)
writer.flush(zstd.FLUSH_FRAME)
source.seek(0)
else:
frame = cctx.compress(original)
source = io.BytesIO(frame)
dctx = zstd.ZstdDecompressor()
chunks = []
with dctx.stream_reader(source, read_size=source_read_size) as reader:
while True:
read_size = read_sizes.draw(strategies.integers(-1, 131072))
chunk = reader.read(read_size)
if not chunk and read_size:
break
chunks.append(chunk)
self.assertEqual(b"".join(chunks), original)
# Similar to above except we have a constant read() size.
@hypothesis.settings(
suppress_health_check=[hypothesis.HealthCheck.large_base_example]
)
@hypothesis.given(
original=strategies.sampled_from(random_input_data()),
level=strategies.integers(min_value=1, max_value=5),
streaming=strategies.booleans(),
source_read_size=strategies.integers(1, 1048576),
read_size=strategies.integers(-1, 131072),
)
def test_stream_source_read_size(
self, original, level, streaming, source_read_size, read_size
):
if read_size == 0:
read_size = 1
cctx = zstd.ZstdCompressor(level=level)
if streaming:
source = io.BytesIO()
writer = cctx.stream_writer(source)
writer.write(original)
writer.flush(zstd.FLUSH_FRAME)
source.seek(0)
else:
frame = cctx.compress(original)
source = io.BytesIO(frame)
dctx = zstd.ZstdDecompressor()
chunks = []
reader = dctx.stream_reader(source, read_size=source_read_size)
while True:
chunk = reader.read(read_size)
if not chunk and read_size:
break
chunks.append(chunk)
self.assertEqual(b"".join(chunks), original)
@hypothesis.settings(
suppress_health_check=[
hypothesis.HealthCheck.large_base_example,
hypothesis.HealthCheck.too_slow,
]
)
@hypothesis.given(
original=strategies.sampled_from(random_input_data()),
level=strategies.integers(min_value=1, max_value=5),
streaming=strategies.booleans(),
source_read_size=strategies.integers(1, 1048576),
read_sizes=strategies.data(),
)
def test_buffer_source_read_variance(
self, original, level, streaming, source_read_size, read_sizes
):
cctx = zstd.ZstdCompressor(level=level)
if streaming:
source = io.BytesIO()
writer = cctx.stream_writer(source)
writer.write(original)
writer.flush(zstd.FLUSH_FRAME)
frame = source.getvalue()
else:
frame = cctx.compress(original)
dctx = zstd.ZstdDecompressor()
chunks = []
with dctx.stream_reader(frame, read_size=source_read_size) as reader:
while True:
read_size = read_sizes.draw(strategies.integers(-1, 131072))
chunk = reader.read(read_size)
if not chunk and read_size:
break
chunks.append(chunk)
self.assertEqual(b"".join(chunks), original)
# Similar to above except we have a constant read() size.
@hypothesis.settings(
suppress_health_check=[hypothesis.HealthCheck.large_base_example]
)
@hypothesis.given(
original=strategies.sampled_from(random_input_data()),
level=strategies.integers(min_value=1, max_value=5),
streaming=strategies.booleans(),
source_read_size=strategies.integers(1, 1048576),
read_size=strategies.integers(-1, 131072),
)
def test_buffer_source_constant_read_size(
self, original, level, streaming, source_read_size, read_size
):
if read_size == 0:
read_size = -1
cctx = zstd.ZstdCompressor(level=level)
if streaming:
source = io.BytesIO()
writer = cctx.stream_writer(source)
writer.write(original)
writer.flush(zstd.FLUSH_FRAME)
frame = source.getvalue()
else:
frame = cctx.compress(original)
dctx = zstd.ZstdDecompressor()
chunks = []
reader = dctx.stream_reader(frame, read_size=source_read_size)
while True:
chunk = reader.read(read_size)
if not chunk and read_size:
break
chunks.append(chunk)
self.assertEqual(b"".join(chunks), original)
@hypothesis.settings(
suppress_health_check=[hypothesis.HealthCheck.large_base_example]
)
@hypothesis.given(
original=strategies.sampled_from(random_input_data()),
level=strategies.integers(min_value=1, max_value=5),
streaming=strategies.booleans(),
source_read_size=strategies.integers(1, 1048576),
)
def test_stream_source_readall(
self, original, level, streaming, source_read_size
):
cctx = zstd.ZstdCompressor(level=level)
if streaming:
source = io.BytesIO()
writer = cctx.stream_writer(source)
writer.write(original)
writer.flush(zstd.FLUSH_FRAME)
source.seek(0)
else:
frame = cctx.compress(original)
source = io.BytesIO(frame)
dctx = zstd.ZstdDecompressor()
data = dctx.stream_reader(source, read_size=source_read_size).readall()
self.assertEqual(data, original)
@hypothesis.settings(
suppress_health_check=[
hypothesis.HealthCheck.large_base_example,
hypothesis.HealthCheck.too_slow,
]
)
@hypothesis.given(
original=strategies.sampled_from(random_input_data()),
level=strategies.integers(min_value=1, max_value=5),
streaming=strategies.booleans(),
source_read_size=strategies.integers(1, 1048576),
read_sizes=strategies.data(),
)
def test_stream_source_read1_variance(
self, original, level, streaming, source_read_size, read_sizes
):
cctx = zstd.ZstdCompressor(level=level)
if streaming:
source = io.BytesIO()
writer = cctx.stream_writer(source)
writer.write(original)
writer.flush(zstd.FLUSH_FRAME)
source.seek(0)
else:
frame = cctx.compress(original)
source = io.BytesIO(frame)
dctx = zstd.ZstdDecompressor()
chunks = []
with dctx.stream_reader(source, read_size=source_read_size) as reader:
while True:
read_size = read_sizes.draw(strategies.integers(-1, 131072))
chunk = reader.read1(read_size)
if not chunk and read_size:
break
chunks.append(chunk)
self.assertEqual(b"".join(chunks), original)
@hypothesis.settings(
suppress_health_check=[
hypothesis.HealthCheck.large_base_example,
hypothesis.HealthCheck.too_slow,
]
)
@hypothesis.given(
original=strategies.sampled_from(random_input_data()),
level=strategies.integers(min_value=1, max_value=5),
streaming=strategies.booleans(),
source_read_size=strategies.integers(1, 1048576),
read_sizes=strategies.data(),
)
def test_stream_source_readinto1_variance(
self, original, level, streaming, source_read_size, read_sizes
):
cctx = zstd.ZstdCompressor(level=level)
if streaming:
source = io.BytesIO()
writer = cctx.stream_writer(source)
writer.write(original)
writer.flush(zstd.FLUSH_FRAME)
source.seek(0)
else:
frame = cctx.compress(original)
source = io.BytesIO(frame)
dctx = zstd.ZstdDecompressor()
chunks = []
with dctx.stream_reader(source, read_size=source_read_size) as reader:
while True:
read_size = read_sizes.draw(strategies.integers(1, 131072))
b = bytearray(read_size)
count = reader.readinto1(b)
if not count:
break
chunks.append(bytes(b[0:count]))
self.assertEqual(b"".join(chunks), original)
@hypothesis.settings(
suppress_health_check=[
hypothesis.HealthCheck.large_base_example,
hypothesis.HealthCheck.too_slow,
]
)
@hypothesis.given(
original=strategies.sampled_from(random_input_data()),
level=strategies.integers(min_value=1, max_value=5),
source_read_size=strategies.integers(1, 1048576),
seek_amounts=strategies.data(),
read_sizes=strategies.data(),
)
def test_relative_seeks(
self, original, level, source_read_size, seek_amounts, read_sizes
):
cctx = zstd.ZstdCompressor(level=level)
frame = cctx.compress(original)
dctx = zstd.ZstdDecompressor()
with dctx.stream_reader(frame, read_size=source_read_size) as reader:
while True:
amount = seek_amounts.draw(strategies.integers(0, 16384))
reader.seek(amount, os.SEEK_CUR)
offset = reader.tell()
read_amount = read_sizes.draw(strategies.integers(1, 16384))
chunk = reader.read(read_amount)
if not chunk:
break
self.assertEqual(original[offset : offset + len(chunk)], chunk)
@hypothesis.settings(
suppress_health_check=[
hypothesis.HealthCheck.large_base_example,
hypothesis.HealthCheck.too_slow,
]
)
@hypothesis.given(
originals=strategies.data(),
frame_count=strategies.integers(min_value=2, max_value=10),
level=strategies.integers(min_value=1, max_value=5),
source_read_size=strategies.integers(1, 1048576),
read_sizes=strategies.data(),
)
def test_multiple_frames(
self, originals, frame_count, level, source_read_size, read_sizes
):
cctx = zstd.ZstdCompressor(level=level)
source = io.BytesIO()
buffer = io.BytesIO()
writer = cctx.stream_writer(buffer)
for i in range(frame_count):
data = originals.draw(strategies.sampled_from(random_input_data()))
source.write(data)
writer.write(data)
writer.flush(zstd.FLUSH_FRAME)
dctx = zstd.ZstdDecompressor()
buffer.seek(0)
reader = dctx.stream_reader(
buffer, read_size=source_read_size, read_across_frames=True
)
chunks = []
while True:
read_amount = read_sizes.draw(strategies.integers(-1, 16384))
chunk = reader.read(read_amount)
if not chunk and read_amount:
break
chunks.append(chunk)
self.assertEqual(source.getvalue(), b"".join(chunks))
@unittest.skipUnless("ZSTD_SLOW_TESTS" in os.environ, "ZSTD_SLOW_TESTS not set")
@make_cffi
class TestDecompressor_stream_writer_fuzzing(TestCase):
@hypothesis.settings(
suppress_health_check=[
hypothesis.HealthCheck.large_base_example,
hypothesis.HealthCheck.too_slow,
]
)
@hypothesis.given(
original=strategies.sampled_from(random_input_data()),
level=strategies.integers(min_value=1, max_value=5),
write_size=strategies.integers(min_value=1, max_value=8192),
input_sizes=strategies.data(),
)
def test_write_size_variance(
self, original, level, write_size, input_sizes
):
cctx = zstd.ZstdCompressor(level=level)
frame = cctx.compress(original)
dctx = zstd.ZstdDecompressor()
source = io.BytesIO(frame)
dest = NonClosingBytesIO()
with dctx.stream_writer(dest, write_size=write_size) as decompressor:
while True:
input_size = input_sizes.draw(strategies.integers(1, 4096))
chunk = source.read(input_size)
if not chunk:
break
decompressor.write(chunk)
self.assertEqual(dest.getvalue(), original)
@unittest.skipUnless("ZSTD_SLOW_TESTS" in os.environ, "ZSTD_SLOW_TESTS not set")
@make_cffi
class TestDecompressor_copy_stream_fuzzing(TestCase):
@hypothesis.settings(
suppress_health_check=[
hypothesis.HealthCheck.large_base_example,
hypothesis.HealthCheck.too_slow,
]
)
@hypothesis.given(
original=strategies.sampled_from(random_input_data()),
level=strategies.integers(min_value=1, max_value=5),
read_size=strategies.integers(min_value=1, max_value=8192),
write_size=strategies.integers(min_value=1, max_value=8192),
)
def test_read_write_size_variance(
self, original, level, read_size, write_size
):
cctx = zstd.ZstdCompressor(level=level)
frame = cctx.compress(original)
source = io.BytesIO(frame)
dest = io.BytesIO()
dctx = zstd.ZstdDecompressor()
dctx.copy_stream(
source, dest, read_size=read_size, write_size=write_size
)
self.assertEqual(dest.getvalue(), original)
@unittest.skipUnless("ZSTD_SLOW_TESTS" in os.environ, "ZSTD_SLOW_TESTS not set")
@make_cffi
class TestDecompressor_decompressobj_fuzzing(TestCase):
@hypothesis.settings(
suppress_health_check=[
hypothesis.HealthCheck.large_base_example,
hypothesis.HealthCheck.too_slow,
]
)
@hypothesis.given(
original=strategies.sampled_from(random_input_data()),
level=strategies.integers(min_value=1, max_value=5),
chunk_sizes=strategies.data(),
)
def test_random_input_sizes(self, original, level, chunk_sizes):
cctx = zstd.ZstdCompressor(level=level)
frame = cctx.compress(original)
source = io.BytesIO(frame)
dctx = zstd.ZstdDecompressor()
dobj = dctx.decompressobj()
chunks = []
while True:
chunk_size = chunk_sizes.draw(strategies.integers(1, 4096))
chunk = source.read(chunk_size)
if not chunk:
break
chunks.append(dobj.decompress(chunk))
self.assertEqual(b"".join(chunks), original)
@hypothesis.settings(
suppress_health_check=[
hypothesis.HealthCheck.large_base_example,
hypothesis.HealthCheck.too_slow,
]
)
@hypothesis.given(
original=strategies.sampled_from(random_input_data()),
level=strategies.integers(min_value=1, max_value=5),
write_size=strategies.integers(
min_value=1,
max_value=4 * zstd.DECOMPRESSION_RECOMMENDED_OUTPUT_SIZE,
),
chunk_sizes=strategies.data(),
)
def test_random_output_sizes(
self, original, level, write_size, chunk_sizes
):
cctx = zstd.ZstdCompressor(level=level)
frame = cctx.compress(original)
source = io.BytesIO(frame)
dctx = zstd.ZstdDecompressor()
dobj = dctx.decompressobj(write_size=write_size)
chunks = []
while True:
chunk_size = chunk_sizes.draw(strategies.integers(1, 4096))
chunk = source.read(chunk_size)
if not chunk:
break
chunks.append(dobj.decompress(chunk))
self.assertEqual(b"".join(chunks), original)
@unittest.skipUnless("ZSTD_SLOW_TESTS" in os.environ, "ZSTD_SLOW_TESTS not set")
@make_cffi
class TestDecompressor_read_to_iter_fuzzing(TestCase):
@hypothesis.given(
original=strategies.sampled_from(random_input_data()),
level=strategies.integers(min_value=1, max_value=5),
read_size=strategies.integers(min_value=1, max_value=4096),
write_size=strategies.integers(min_value=1, max_value=4096),
)
def test_read_write_size_variance(
self, original, level, read_size, write_size
):
cctx = zstd.ZstdCompressor(level=level)
frame = cctx.compress(original)
source = io.BytesIO(frame)
dctx = zstd.ZstdDecompressor()
chunks = list(
dctx.read_to_iter(
source, read_size=read_size, write_size=write_size
)
)
self.assertEqual(b"".join(chunks), original)
@unittest.skipUnless("ZSTD_SLOW_TESTS" in os.environ, "ZSTD_SLOW_TESTS not set")
class TestDecompressor_multi_decompress_to_buffer_fuzzing(TestCase):
@hypothesis.given(
original=strategies.lists(
strategies.sampled_from(random_input_data()),
min_size=1,
max_size=1024,
),
threads=strategies.integers(min_value=1, max_value=8),
use_dict=strategies.booleans(),
)
def test_data_equivalence(self, original, threads, use_dict):
kwargs = {}
if use_dict:
kwargs["dict_data"] = zstd.ZstdCompressionDict(original[0])
cctx = zstd.ZstdCompressor(
level=1, write_content_size=True, write_checksum=True, **kwargs
)
if not hasattr(cctx, "multi_compress_to_buffer"):
self.skipTest("multi_compress_to_buffer not available")
frames_buffer = cctx.multi_compress_to_buffer(original, threads=-1)
dctx = zstd.ZstdDecompressor(**kwargs)
result = dctx.multi_decompress_to_buffer(frames_buffer)
self.assertEqual(len(result), len(original))
for i, frame in enumerate(result):
self.assertEqual(frame.tobytes(), original[i])
frames_list = [f.tobytes() for f in frames_buffer]
result = dctx.multi_decompress_to_buffer(frames_list)
self.assertEqual(len(result), len(original))
for i, frame in enumerate(result):
self.assertEqual(frame.tobytes(), original[i])