Mercurial > public > mercurial-scm > hg

comparison contrib/python-zstandard/c-ext/compressionparams.c @ 40121:73fef626dae3

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
zstandard: vendor python-zstandard 0.10.1 This was just released. The upstream source distribution from PyPI was extracted. Unwanted files were removed. The clang-format ignore list was updated to reflect the new source of files. setup.py was updated to pass a new argument to python-zstandard's function for returning an Extension instance. Upstream had to change to use relative paths because Python 3.7's packaging doesn't seem to like absolute paths when defining sources, includes, etc. The default relative path calculation is relative to setup_zstd.py which is different from the directory of Mercurial's setup.py. The project contains a vendored copy of zstandard 1.3.6. The old version was 1.3.4. The API should be backwards compatible and nothing in core should need adjusted. However, there is a new "chunker" API that we may find useful in places where we want to emit compressed chunks of a fixed size. There are a pair of bug fixes in 0.10.0 with regards to compressobj() and decompressobj() when block flushing is used. I actually found these bugs when introducing these APIs in Mercurial! But existing Mercurial code is not affected because we don't perform block flushing. # no-check-commit because 3rd party code has different style guidelines Differential Revision: https://phab.mercurial-scm.org/D4911
author Gregory Szorc <gregory.szorc@gmail.com>
date Mon, 08 Oct 2018 16:27:40 -0700
parents b1fb341d8a61
children 675775c33ab6
comparison
equal deleted inserted replaced
40120:89742f1fa6cb 40121:73fef626dae3
37 TRY_SET_PARAMETER(params, ZSTD_p_checksumFlag, obj->checksumFlag); 37 TRY_SET_PARAMETER(params, ZSTD_p_checksumFlag, obj->checksumFlag);
38 TRY_SET_PARAMETER(params, ZSTD_p_dictIDFlag, obj->dictIDFlag); 38 TRY_SET_PARAMETER(params, ZSTD_p_dictIDFlag, obj->dictIDFlag);
39 TRY_SET_PARAMETER(params, ZSTD_p_nbWorkers, obj->threads); 39 TRY_SET_PARAMETER(params, ZSTD_p_nbWorkers, obj->threads);
40 TRY_SET_PARAMETER(params, ZSTD_p_jobSize, obj->jobSize); 40 TRY_SET_PARAMETER(params, ZSTD_p_jobSize, obj->jobSize);
41 TRY_SET_PARAMETER(params, ZSTD_p_overlapSizeLog, obj->overlapSizeLog); 41 TRY_SET_PARAMETER(params, ZSTD_p_overlapSizeLog, obj->overlapSizeLog);
42 TRY_SET_PARAMETER(params, ZSTD_p_compressLiterals, obj->compressLiterals);
43 TRY_SET_PARAMETER(params, ZSTD_p_forceMaxWindow, obj->forceMaxWindow); 42 TRY_SET_PARAMETER(params, ZSTD_p_forceMaxWindow, obj->forceMaxWindow);
44 TRY_SET_PARAMETER(params, ZSTD_p_enableLongDistanceMatching, obj->enableLongDistanceMatching); 43 TRY_SET_PARAMETER(params, ZSTD_p_enableLongDistanceMatching, obj->enableLongDistanceMatching);
45 TRY_SET_PARAMETER(params, ZSTD_p_ldmHashLog, obj->ldmHashLog); 44 TRY_SET_PARAMETER(params, ZSTD_p_ldmHashLog, obj->ldmHashLog);
46 TRY_SET_PARAMETER(params, ZSTD_p_ldmMinMatch, obj->ldmMinMatch); 45 TRY_SET_PARAMETER(params, ZSTD_p_ldmMinMatch, obj->ldmMinMatch);
47 TRY_SET_PARAMETER(params, ZSTD_p_ldmBucketSizeLog, obj->ldmBucketSizeLog); 46 TRY_SET_PARAMETER(params, ZSTD_p_ldmBucketSizeLog, obj->ldmBucketSizeLog);
86 "ldm_hash_log", 85 "ldm_hash_log",
87 "ldm_min_match", 86 "ldm_min_match",
88 "ldm_bucket_size_log", 87 "ldm_bucket_size_log",
89 "ldm_hash_every_log", 88 "ldm_hash_every_log",
90 "threads", 89 "threads",
91 "compress_literals",
92 NULL 90 NULL
93 }; 91 };
94 92
95 unsigned format = 0; 93 unsigned format = 0;
96 int compressionLevel = 0; 94 int compressionLevel = 0;
112 unsigned ldmMinMatch = 0; 110 unsigned ldmMinMatch = 0;
113 unsigned ldmBucketSizeLog = 0; 111 unsigned ldmBucketSizeLog = 0;
114 unsigned ldmHashEveryLog = 0; 112 unsigned ldmHashEveryLog = 0;
115 int threads = 0; 113 int threads = 0;
116 114
117 /* Setting value 0 has the effect of disabling. So we use -1 as a default
118 * to detect whether to set. Then we automatically derive the expected value
119 * based on the level, just like zstandard does itself. */
120 int compressLiterals = -1;
121
122 if (!PyArg_ParseTupleAndKeywords(args, kwargs, 115 if (!PyArg_ParseTupleAndKeywords(args, kwargs,
123 "|IiIIIIIIIIIIIIIIIIIIii:CompressionParameters", 116 "|IiIIIIIIIIIIIIIIIIIIi:CompressionParameters",
124 kwlist, &format, &compressionLevel, &windowLog, &hashLog, &chainLog, 117 kwlist, &format, &compressionLevel, &windowLog, &hashLog, &chainLog,
125 &searchLog, &minMatch, &targetLength, &compressionStrategy, 118 &searchLog, &minMatch, &targetLength, &compressionStrategy,
126 &contentSizeFlag, &checksumFlag, &dictIDFlag, &jobSize, &overlapSizeLog, 119 &contentSizeFlag, &checksumFlag, &dictIDFlag, &jobSize, &overlapSizeLog,
127 &forceMaxWindow, &enableLDM, &ldmHashLog, &ldmMinMatch, &ldmBucketSizeLog, 120 &forceMaxWindow, &enableLDM, &ldmHashLog, &ldmMinMatch, &ldmBucketSizeLog,
128 &ldmHashEveryLog, &threads, &compressLiterals)) { 121 &ldmHashEveryLog, &threads)) {
129 return -1; 122 return -1;
130 } 123 }
131 124
132 if (threads < 0) { 125 if (threads < 0) {
133 threads = cpu_count(); 126 threads = cpu_count();
134 }
135
136 if (compressLiterals < 0) {
137 compressLiterals = compressionLevel >= 0;
138 } 127 }
139 128
140 self->format = format; 129 self->format = format;
141 self->compressionLevel = compressionLevel; 130 self->compressionLevel = compressionLevel;
142 self->windowLog = windowLog; 131 self->windowLog = windowLog;
150 self->checksumFlag = checksumFlag; 139 self->checksumFlag = checksumFlag;
151 self->dictIDFlag = dictIDFlag; 140 self->dictIDFlag = dictIDFlag;
152 self->threads = threads; 141 self->threads = threads;
153 self->jobSize = jobSize; 142 self->jobSize = jobSize;
154 self->overlapSizeLog = overlapSizeLog; 143 self->overlapSizeLog = overlapSizeLog;
155 self->compressLiterals = compressLiterals;
156 self->forceMaxWindow = forceMaxWindow; 144 self->forceMaxWindow = forceMaxWindow;
157 self->enableLongDistanceMatching = enableLDM; 145 self->enableLongDistanceMatching = enableLDM;
158 self->ldmHashLog = ldmHashLog; 146 self->ldmHashLog = ldmHashLog;
159 self->ldmMinMatch = ldmMinMatch; 147 self->ldmMinMatch = ldmMinMatch;
160 self->ldmBucketSizeLog = ldmBucketSizeLog; 148 self->ldmBucketSizeLog = ldmBucketSizeLog;
294 val = PyLong_FromUnsignedLong(params.strategy); 282 val = PyLong_FromUnsignedLong(params.strategy);
295 if (!val) { 283 if (!val) {
296 goto cleanup; 284 goto cleanup;
297 } 285 }
298 PyDict_SetItemString(kwargs, "compression_strategy", val); 286 PyDict_SetItemString(kwargs, "compression_strategy", val);
299 Py_DECREF(val);
300 }
301
302 val = PyDict_GetItemString(kwargs, "compress_literals");
303 if (!val) {
304 val = PyLong_FromLong(level >= 0 ? 1 : 0);
305 if (!val) {
306 goto cleanup;
307 }
308 PyDict_SetItemString(kwargs, "compress_literals", val);
309 Py_DECREF(val); 287 Py_DECREF(val);
310 } 288 }
311 289
312 result = PyObject_New(ZstdCompressionParametersObject, &ZstdCompressionParametersType); 290 result = PyObject_New(ZstdCompressionParametersObject, &ZstdCompressionParametersType);
313 if (!result) { 291 if (!result) {
418 offsetof(ZstdCompressionParametersObject, jobSize), READONLY, 396 offsetof(ZstdCompressionParametersObject, jobSize), READONLY,
419 "size of compression job when using multiple threads" }, 397 "size of compression job when using multiple threads" },
420 { "overlap_size_log", T_UINT, 398 { "overlap_size_log", T_UINT,
421 offsetof(ZstdCompressionParametersObject, overlapSizeLog), READONLY, 399 offsetof(ZstdCompressionParametersObject, overlapSizeLog), READONLY,
422 "Size of previous input reloaded at the beginning of each job" }, 400 "Size of previous input reloaded at the beginning of each job" },
423 { "compress_literals", T_UINT,
424 offsetof(ZstdCompressionParametersObject, compressLiterals), READONLY,
425 "whether Huffman compression of literals is in use" },
426 { "force_max_window", T_UINT, 401 { "force_max_window", T_UINT,
427 offsetof(ZstdCompressionParametersObject, forceMaxWindow), READONLY, 402 offsetof(ZstdCompressionParametersObject, forceMaxWindow), READONLY,
428 "force back references to remain smaller than window size" }, 403 "force back references to remain smaller than window size" },
429 { "enable_ldm", T_UINT, 404 { "enable_ldm", T_UINT,
430 offsetof(ZstdCompressionParametersObject, enableLongDistanceMatching), READONLY, 405 offsetof(ZstdCompressionParametersObject, enableLongDistanceMatching), READONLY,