contrib/python-zstandard/tests/test_train_dictionary.py

wireproto: support for pullbundles

Pullbundles are similar to clonebundles, but served as normal inline
bundle streams. They are almost transparent to the client -- the only
visible effect is that the client might get less changes than what it
asked for, i.e. not all requested head revisions are provided.

The client announces support for the necessary retries with the
partial-pull capability. After receiving a partial bundle, it updates
the set of revisions shared with the server and drops all now-known
heads from the request list. It will then rerun getbundle until
no changes are received or all remote heads are present.

Extend badserverext to support per-socket limit, i.e. don't assume that
the same limits should be applied to all sockets.

Differential Revision: https://phab.mercurial-scm.org/D1856

import struct
import sys
import unittest

import zstandard as zstd

from . common import (
    generate_samples,
    make_cffi,
)

if sys.version_info[0] >= 3:
    int_type = int
else:
    int_type = long


@make_cffi
class TestTrainDictionary(unittest.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, generate_samples())
        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)

        self.assertEqual(d.k, 50)
        self.assertEqual(d.d, 16)

@make_cffi
class TestCompressionDict(unittest.TestCase):
    def test_bad_mode(self):
        with self.assertRaisesRegexp(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.assertRaisesRegexp(ValueError, 'must specify one of level or '):
            d.precompute_compress()

        with self.assertRaisesRegexp(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.assertRaisesRegexp(zstd.ZstdError, 'unable to precompute dictionary'):
            d.precompute_compress(level=1)