annotate contrib/python-zstandard/zstd/dictBuilder/cover.h @ 40121:73fef626dae3

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

#include <stdio.h>  /* fprintf */
#include <stdlib.h> /* malloc, free, qsort */
#include <string.h> /* memset */
#include <time.h>   /* clock */
#include "mem.h" /* read */
#include "pool.h"
#include "threading.h"
#include "zstd_internal.h" /* includes zstd.h */
#ifndef ZDICT_STATIC_LINKING_ONLY
#define ZDICT_STATIC_LINKING_ONLY
#endif
#include "zdict.h"

/**
 * COVER_best_t is used for two purposes:
 * 1. Synchronizing threads.
 * 2. Saving the best parameters and dictionary.
 *
 * All of the methods except COVER_best_init() are thread safe if zstd is
 * compiled with multithreaded support.
 */
typedef struct COVER_best_s {
  ZSTD_pthread_mutex_t mutex;
  ZSTD_pthread_cond_t cond;
  size_t liveJobs;
  void *dict;
  size_t dictSize;
  ZDICT_cover_params_t parameters;
  size_t compressedSize;
} COVER_best_t;

/**
 * A segment is a range in the source as well as the score of the segment.
 */
typedef struct {
  U32 begin;
  U32 end;
  U32 score;
} COVER_segment_t;

/**
 *  Checks total compressed size of a dictionary
 */
size_t COVER_checkTotalCompressedSize(const ZDICT_cover_params_t parameters,
                                      const size_t *samplesSizes, const BYTE *samples,
                                      size_t *offsets,
                                      size_t nbTrainSamples, size_t nbSamples,
                                      BYTE *const dict, size_t dictBufferCapacity);

/**
 * Returns the sum of the sample sizes.
 */
size_t COVER_sum(const size_t *samplesSizes, unsigned nbSamples) ;

/**
 * Initialize the `COVER_best_t`.
 */
void COVER_best_init(COVER_best_t *best);

/**
 * Wait until liveJobs == 0.
 */
void COVER_best_wait(COVER_best_t *best);

/**
 * Call COVER_best_wait() and then destroy the COVER_best_t.
 */
void COVER_best_destroy(COVER_best_t *best);

/**
 * Called when a thread is about to be launched.
 * Increments liveJobs.
 */
void COVER_best_start(COVER_best_t *best);

/**
 * Called when a thread finishes executing, both on error or success.
 * Decrements liveJobs and signals any waiting threads if liveJobs == 0.
 * If this dictionary is the best so far save it and its parameters.
 */
void COVER_best_finish(COVER_best_t *best, size_t compressedSize,
                       ZDICT_cover_params_t parameters, void *dict,
                       size_t dictSize);