1 /* 2 * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. 3 * All rights reserved. 4 * 5 * This source code is licensed under both the BSD-style license (found in the 6 * LICENSE file in the root directory of this source tree) and the GPLv2 (found 7 * in the COPYING file in the root directory of this source tree). 8 */ 9 10 #ifndef ZSTD_LDM_H 11 #define ZSTD_LDM_H 12 13 #if defined (__cplusplus) 14 extern "C" { 15 #endif 16 17 #include "zstd_compress_internal.h" /* ldmParams_t, U32 */ 18 #include "zstd.h" /* ZSTD_CCtx, size_t */ 19 20 /*-************************************* 21 * Long distance matching 22 ***************************************/ 23 24 #define ZSTD_LDM_DEFAULT_WINDOW_LOG ZSTD_WINDOWLOG_LIMIT_DEFAULT 25 26 /** 27 * ZSTD_ldm_generateSequences(): 28 * 29 * Generates the sequences using the long distance match finder. 30 * Generates long range matching sequences in `sequences`, which parse a prefix 31 * of the source. `sequences` must be large enough to store every sequence, 32 * which can be checked with `ZSTD_ldm_getMaxNbSeq()`. 33 * @returns 0 or an error code. 34 * 35 * NOTE: The user must have called ZSTD_window_update() for all of the input 36 * they have, even if they pass it to ZSTD_ldm_generateSequences() in chunks. 37 * NOTE: This function returns an error if it runs out of space to store 38 * sequences. 39 */ 40 size_t ZSTD_ldm_generateSequences( 41 ldmState_t* ldms, rawSeqStore_t* sequences, 42 ldmParams_t const* params, void const* src, size_t srcSize); 43 44 /** 45 * ZSTD_ldm_blockCompress(): 46 * 47 * Compresses a block using the predefined sequences, along with a secondary 48 * block compressor. The literals section of every sequence is passed to the 49 * secondary block compressor, and those sequences are interspersed with the 50 * predefined sequences. Returns the length of the last literals. 51 * Updates `rawSeqStore.pos` to indicate how many sequences have been consumed. 52 * `rawSeqStore.seq` may also be updated to split the last sequence between two 53 * blocks. 54 * @return The length of the last literals. 55 * 56 * NOTE: The source must be at most the maximum block size, but the predefined 57 * sequences can be any size, and may be longer than the block. In the case that 58 * they are longer than the block, the last sequences may need to be split into 59 * two. We handle that case correctly, and update `rawSeqStore` appropriately. 60 * NOTE: This function does not return any errors. 61 */ 62 size_t ZSTD_ldm_blockCompress(rawSeqStore_t* rawSeqStore, 63 ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], 64 void const* src, size_t srcSize); 65 66 /** 67 * ZSTD_ldm_skipSequences(): 68 * 69 * Skip past `srcSize` bytes worth of sequences in `rawSeqStore`. 70 * Avoids emitting matches less than `minMatch` bytes. 71 * Must be called for data with is not passed to ZSTD_ldm_blockCompress(). 72 */ 73 void ZSTD_ldm_skipSequences(rawSeqStore_t* rawSeqStore, size_t srcSize, 74 U32 const minMatch); 75 76 77 /** ZSTD_ldm_getTableSize() : 78 * Estimate the space needed for long distance matching tables or 0 if LDM is 79 * disabled. 80 */ 81 size_t ZSTD_ldm_getTableSize(ldmParams_t params); 82 83 /** ZSTD_ldm_getSeqSpace() : 84 * Return an upper bound on the number of sequences that can be produced by 85 * the long distance matcher, or 0 if LDM is disabled. 86 */ 87 size_t ZSTD_ldm_getMaxNbSeq(ldmParams_t params, size_t maxChunkSize); 88 89 /** ZSTD_ldm_adjustParameters() : 90 * If the params->hashRateLog is not set, set it to its default value based on 91 * windowLog and params->hashLog. 92 * 93 * Ensures that params->bucketSizeLog is <= params->hashLog (setting it to 94 * params->hashLog if it is not). 95 * 96 * Ensures that the minMatchLength >= targetLength during optimal parsing. 97 */ 98 void ZSTD_ldm_adjustParameters(ldmParams_t* params, 99 ZSTD_compressionParameters const* cParams); 100 101 #if defined (__cplusplus) 102 } 103 #endif 104 105 #endif /* ZSTD_FAST_H */ 106