##// END OF EJS Templates
rust-node: binary Node ID and conversion utilities...
rust-node: binary Node ID and conversion utilities The choice of type makes sure that a `Node` has the exact wanted size. We'll use a different type for prefixes. Added dependency: hexadecimal conversion relies on the `hex` crate. The fact that sooner or later Mercurial is going to need to change its hash sizes has been taken strongly in consideration: - the hash length is a constant, but that is not directly exposed to callers. Changing the value of that constant is the only thing to do to change the hash length (even in unit tests) - the code could be adapted to support several sizes of hashes, if that turned out to be useful. To that effect, only the size of a given `Node` is exposed in the public API. - callers not involved in initial computation, I/O and FFI are able to operate without a priori assumptions on the hash size. The traits `FromHex` and `ToHex` have not been directly implemented, so that the doc-comments explaining these restrictions would stay really visible in `cargo doc` Differential Revision: https://phab.mercurial-scm.org/D7788

File last commit:

r44446:de783805 default
r44601:7f86426f default
Show More
test_train_dictionary.py
92 lines | 2.7 KiB | text/x-python | PythonLexer
import struct
import sys
import unittest
import zstandard as zstd
from .common import (
generate_samples,
make_cffi,
random_input_data,
TestCase,
)
if sys.version_info[0] >= 3:
int_type = int
else:
int_type = long
@make_cffi
class TestTrainDictionary(TestCase):
def test_no_args(self):
with self.assertRaises(TypeError):
zstd.train_dictionary()
def test_bad_args(self):
with self.assertRaises(TypeError):
zstd.train_dictionary(8192, u"foo")
with self.assertRaises(ValueError):
zstd.train_dictionary(8192, [u"foo"])
def test_no_params(self):
d = zstd.train_dictionary(8192, random_input_data())
self.assertIsInstance(d.dict_id(), int_type)
# The dictionary ID may be different across platforms.
expected = b"\x37\xa4\x30\xec" + struct.pack("<I", d.dict_id())
data = d.as_bytes()
self.assertEqual(data[0:8], expected)
def test_basic(self):
d = zstd.train_dictionary(8192, generate_samples(), k=64, d=16)
self.assertIsInstance(d.dict_id(), int_type)
data = d.as_bytes()
self.assertEqual(data[0:4], b"\x37\xa4\x30\xec")
self.assertEqual(d.k, 64)
self.assertEqual(d.d, 16)
def test_set_dict_id(self):
d = zstd.train_dictionary(8192, generate_samples(), k=64, d=16, dict_id=42)
self.assertEqual(d.dict_id(), 42)
def test_optimize(self):
d = zstd.train_dictionary(8192, generate_samples(), threads=-1, steps=1, d=16)
# This varies by platform.
self.assertIn(d.k, (50, 2000))
self.assertEqual(d.d, 16)
@make_cffi
class TestCompressionDict(TestCase):
def test_bad_mode(self):
with self.assertRaisesRegex(ValueError, "invalid dictionary load mode"):
zstd.ZstdCompressionDict(b"foo", dict_type=42)
def test_bad_precompute_compress(self):
d = zstd.train_dictionary(8192, generate_samples(), k=64, d=16)
with self.assertRaisesRegex(ValueError, "must specify one of level or "):
d.precompute_compress()
with self.assertRaisesRegex(ValueError, "must only specify one of level or "):
d.precompute_compress(
level=3, compression_params=zstd.CompressionParameters()
)
def test_precompute_compress_rawcontent(self):
d = zstd.ZstdCompressionDict(
b"dictcontent" * 64, dict_type=zstd.DICT_TYPE_RAWCONTENT
)
d.precompute_compress(level=1)
d = zstd.ZstdCompressionDict(
b"dictcontent" * 64, dict_type=zstd.DICT_TYPE_FULLDICT
)
with self.assertRaisesRegex(zstd.ZstdError, "unable to precompute dictionary"):
d.precompute_compress(level=1)