ddidderr/zstd-rs
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

initial commit

Browse Source
This commit is contained in:
Danielle Rozenblit
2023-02-09 07:37:37 -08:00
parent dc39409a03
commit 610c8b9e33
385 changed files with 7518 additions and 4039 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/decompress/zstd_decompress.c
+112 -22
View File
@@ -1,5 +1,5 @@
/*
* Copyright (c) Yann Collet, Facebook, Inc.
* Copyright (c) Meta Platforms, Inc. and affiliates.
* All rights reserved.
*
* This source code is licensed under both the BSD-style license (found in the
@@ -59,7 +59,6 @@
#include "../common/mem.h" /* low level memory routines */
#define FSE_STATIC_LINKING_ONLY
#include "../common/fse.h"
#define HUF_STATIC_LINKING_ONLY
#include "../common/huf.h"
#include "../common/xxhash.h" /* XXH64_reset, XXH64_update, XXH64_digest, XXH64 */
#include "../common/zstd_internal.h" /* blockProperties_t */
@@ -244,6 +243,7 @@ static void ZSTD_DCtx_resetParameters(ZSTD_DCtx* dctx)
dctx->outBufferMode = ZSTD_bm_buffered;
dctx->forceIgnoreChecksum = ZSTD_d_validateChecksum;
dctx->refMultipleDDicts = ZSTD_rmd_refSingleDDict;
dctx->disableHufAsm = 0;
}
static void ZSTD_initDCtx_internal(ZSTD_DCtx* dctx)
@@ -782,10 +782,11 @@ static ZSTD_frameSizeInfo ZSTD_findFrameSizeInfo(const void* src, size_t srcSize
ip += 4;
}
frameSizeInfo.nbBlocks = nbBlocks;
frameSizeInfo.compressedSize = (size_t)(ip - ipstart);
frameSizeInfo.decompressedBound = (zfh.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN)
? zfh.frameContentSize
: nbBlocks * zfh.blockSizeMax;
: (unsigned long long)nbBlocks * zfh.blockSizeMax;
return frameSizeInfo;
}
}
@@ -825,6 +826,48 @@ unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize)
return bound;
}
size_t ZSTD_decompressionMargin(void const* src, size_t srcSize)
{
size_t margin = 0;
unsigned maxBlockSize = 0;
/* Iterate over each frame */
while (srcSize > 0) {
ZSTD_frameSizeInfo const frameSizeInfo = ZSTD_findFrameSizeInfo(src, srcSize);
size_t const compressedSize = frameSizeInfo.compressedSize;
unsigned long long const decompressedBound = frameSizeInfo.decompressedBound;
ZSTD_frameHeader zfh;
FORWARD_IF_ERROR(ZSTD_getFrameHeader(&zfh, src, srcSize), "");
if (ZSTD_isError(compressedSize) || decompressedBound == ZSTD_CONTENTSIZE_ERROR)
return ERROR(corruption_detected);
if (zfh.frameType == ZSTD_frame) {
/* Add the frame header to our margin */
margin += zfh.headerSize;
/* Add the checksum to our margin */
margin += zfh.checksumFlag ? 4 : 0;
/* Add 3 bytes per block */
margin += 3 * frameSizeInfo.nbBlocks;
/* Compute the max block size */
maxBlockSize = MAX(maxBlockSize, zfh.blockSizeMax);
} else {
assert(zfh.frameType == ZSTD_skippableFrame);
/* Add the entire skippable frame size to our margin. */
margin += compressedSize;
}
assert(srcSize >= compressedSize);
src = (const BYTE*)src + compressedSize;
srcSize -= compressedSize;
}
/* Add the max block size back to the margin. */
margin += maxBlockSize;
return margin;
}
/*-*************************************************************
* Frame decoding
@@ -850,7 +893,7 @@ static size_t ZSTD_copyRawBlock(void* dst, size_t dstCapacity,
if (srcSize == 0) return 0;
RETURN_ERROR(dstBuffer_null, "");
}
ZSTD_memcpy(dst, src, srcSize);
ZSTD_memmove(dst, src, srcSize);
return srcSize;
}
@@ -928,6 +971,7 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
/* Loop on each block */
while (1) {
BYTE* oBlockEnd = oend;
size_t decodedSize;
blockProperties_t blockProperties;
size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSrcSize, &blockProperties);
@@ -937,16 +981,34 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
remainingSrcSize -= ZSTD_blockHeaderSize;
RETURN_ERROR_IF(cBlockSize > remainingSrcSize, srcSize_wrong, "");
if (ip >= op && ip < oBlockEnd) {
/* We are decompressing in-place. Limit the output pointer so that we
* don't overwrite the block that we are currently reading. This will
* fail decompression if the input & output pointers aren't spaced
* far enough apart.
*
* This is important to set, even when the pointers are far enough
* apart, because ZSTD_decompressBlock_internal() can decide to store
* literals in the output buffer, after the block it is decompressing.
* Since we don't want anything to overwrite our input, we have to tell
* ZSTD_decompressBlock_internal to never write past ip.
*
* See ZSTD_allocateLiteralsBuffer() for reference.
*/
oBlockEnd = op + (ip - op);
}
switch(blockProperties.blockType)
{
case bt_compressed:
decodedSize = ZSTD_decompressBlock_internal(dctx, op, (size_t)(oend-op), ip, cBlockSize, /* frame */ 1, not_streaming);
decodedSize = ZSTD_decompressBlock_internal(dctx, op, (size_t)(oBlockEnd-op), ip, cBlockSize, /* frame */ 1, not_streaming);
break;
case bt_raw :
/* Use oend instead of oBlockEnd because this function is safe to overlap. It uses memmove. */
decodedSize = ZSTD_copyRawBlock(op, (size_t)(oend-op), ip, cBlockSize);
break;
case bt_rle :
decodedSize = ZSTD_setRleBlock(op, (size_t)(oend-op), *ip, blockProperties.origSize);
decodedSize = ZSTD_setRleBlock(op, (size_t)(oBlockEnd-op), *ip, blockProperties.origSize);
break;
case bt_reserved :
default:
@@ -981,6 +1043,7 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
}
ZSTD_DCtx_trace_end(dctx, (U64)(op-ostart), (U64)(ip-istart), /* streaming */ 0);
/* Allow caller to get size read */
DEBUGLOG(4, "ZSTD_decompressFrame: decompressed frame of size %zi, consuming %zi bytes of input", op-ostart, ip - (const BYTE*)*srcPtr);
*srcPtr = ip;
*srcSizePtr = remainingSrcSize;
return (size_t)(op-ostart);
@@ -1375,11 +1438,11 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
/* in minimal huffman, we always use X1 variants */
size_t const hSize = HUF_readDTableX1_wksp(entropy->hufTable,
dictPtr, dictEnd - dictPtr,
workspace, workspaceSize);
workspace, workspaceSize, /* flags */ 0);
#else
size_t const hSize = HUF_readDTableX2_wksp(entropy->hufTable,
dictPtr, (size_t)(dictEnd - dictPtr),
workspace, workspaceSize);
workspace, workspaceSize, /* flags */ 0);
#endif
RETURN_ERROR_IF(HUF_isError(hSize), dictionary_corrupted, "");
dictPtr += hSize;
@@ -1549,7 +1612,7 @@ unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize)
* ZSTD_getFrameHeader(), which will provide a more precise error code. */
unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize)
{
ZSTD_frameHeader zfp = { 0, 0, 0, ZSTD_frame, 0, 0, 0 };
ZSTD_frameHeader zfp = { 0, 0, 0, ZSTD_frame, 0, 0, 0, 0, 0 };
size_t const hError = ZSTD_getFrameHeader(&zfp, src, srcSize);
if (ZSTD_isError(hError)) return 0;
return zfp.dictID;
@@ -1656,7 +1719,9 @@ size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t di
size_t ZSTD_initDStream(ZSTD_DStream* zds)
{
DEBUGLOG(4, "ZSTD_initDStream");
return ZSTD_initDStream_usingDDict(zds, NULL);
FORWARD_IF_ERROR(ZSTD_DCtx_reset(zds, ZSTD_reset_session_only), "");
FORWARD_IF_ERROR(ZSTD_DCtx_refDDict(zds, NULL), "");
return ZSTD_startingInputLength(zds->format);
}
/* ZSTD_initDStream_usingDDict() :
@@ -1664,6 +1729,7 @@ size_t ZSTD_initDStream(ZSTD_DStream* zds)
* this function cannot fail */
size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* dctx, const ZSTD_DDict* ddict)
{
DEBUGLOG(4, "ZSTD_initDStream_usingDDict");
FORWARD_IF_ERROR( ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only) , "");
FORWARD_IF_ERROR( ZSTD_DCtx_refDDict(dctx, ddict) , "");
return ZSTD_startingInputLength(dctx->format);
@@ -1674,6 +1740,7 @@ size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* dctx, const ZSTD_DDict* ddict)
* this function cannot fail */
size_t ZSTD_resetDStream(ZSTD_DStream* dctx)
{
DEBUGLOG(4, "ZSTD_resetDStream");
FORWARD_IF_ERROR(ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only), "");
return ZSTD_startingInputLength(dctx->format);
}
@@ -1745,6 +1812,11 @@ ZSTD_bounds ZSTD_dParam_getBounds(ZSTD_dParameter dParam)
bounds.lowerBound = (int)ZSTD_rmd_refSingleDDict;
bounds.upperBound = (int)ZSTD_rmd_refMultipleDDicts;
return bounds;
case ZSTD_d_disableHuffmanAssembly:
bounds.lowerBound = 0;
bounds.upperBound = 1;
return bounds;
default:;
}
bounds.error = ERROR(parameter_unsupported);
@@ -1785,6 +1857,9 @@ size_t ZSTD_DCtx_getParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int* value
case ZSTD_d_refMultipleDDicts:
*value = (int)dctx->refMultipleDDicts;
return 0;
case ZSTD_d_disableHuffmanAssembly:
*value = (int)dctx->disableHufAsm;
return 0;
default:;
}
RETURN_ERROR(parameter_unsupported, "");
@@ -1818,6 +1893,10 @@ size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter dParam, int value
}
dctx->refMultipleDDicts = (ZSTD_refMultipleDDicts_e)value;
return 0;
case ZSTD_d_disableHuffmanAssembly:
CHECK_DBOUNDS(ZSTD_d_disableHuffmanAssembly, value);
dctx->disableHufAsm = value != 0;
return 0;
default:;
}
RETURN_ERROR(parameter_unsupported, "");
@@ -2058,6 +2137,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, (size_t)(oend-op), istart, cSize, ZSTD_getDDict(zds));
if (ZSTD_isError(decompressedSize)) return decompressedSize;
DEBUGLOG(4, "shortcut to single-pass ZSTD_decompress_usingDDict()")
assert(istart != NULL);
ip = istart + cSize;
op = op ? op + decompressedSize : op; /* can occur if frameContentSize = 0 (empty frame) */
zds->expected = 0;
@@ -2143,6 +2223,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
}
if ((size_t)(iend-ip) >= neededInSize) { /* decode directly from src */
FORWARD_IF_ERROR(ZSTD_decompressContinueStream(zds, &op, oend, ip, neededInSize), "");
assert(ip != NULL);
ip += neededInSize;
/* Function modifies the stage so we must break */
break;
@@ -2157,7 +2238,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
int const isSkipFrame = ZSTD_isSkipFrame(zds);
size_t loadedSize;
/* At this point we shouldn't be decompressing a block that we can stream. */
assert(neededInSize == ZSTD_nextSrcSizeToDecompressWithInputSize(zds, iend - ip));
assert(neededInSize == ZSTD_nextSrcSizeToDecompressWithInputSize(zds, (size_t)(iend - ip)));
if (isSkipFrame) {
loadedSize = MIN(toLoad, (size_t)(iend-ip));
} else {
@@ -2166,8 +2247,11 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
"should never happen");
loadedSize = ZSTD_limitCopy(zds->inBuff + zds->inPos, toLoad, ip, (size_t)(iend-ip));
}
ip += loadedSize;
zds->inPos += loadedSize;
if (loadedSize != 0) {
/* ip may be NULL */
ip += loadedSize;
zds->inPos += loadedSize;
}
if (loadedSize < toLoad) { someMoreWork = 0; break; } /* not enough input, wait for more */
/* decode loaded input */
@@ -2214,8 +2298,8 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
if ((ip==istart) && (op==ostart)) { /* no forward progress */
zds->noForwardProgress ++;
if (zds->noForwardProgress >= ZSTD_NO_FORWARD_PROGRESS_MAX) {
RETURN_ERROR_IF(op==oend, dstSize_tooSmall, "");
RETURN_ERROR_IF(ip==iend, srcSize_wrong, "");
RETURN_ERROR_IF(op==oend, noForwardProgress_destFull, "");
RETURN_ERROR_IF(ip==iend, noForwardProgress_inputEmpty, "");
assert(0);
}
} else {
@@ -2252,11 +2336,17 @@ size_t ZSTD_decompressStream_simpleArgs (
void* dst, size_t dstCapacity, size_t* dstPos,
const void* src, size_t srcSize, size_t* srcPos)
{
ZSTD_outBuffer output = { dst, dstCapacity, *dstPos };
ZSTD_inBuffer input = { src, srcSize, *srcPos };
/* ZSTD_compress_generic() will check validity of dstPos and srcPos */
size_t const cErr = ZSTD_decompressStream(dctx, &output, &input);
*dstPos = output.pos;
*srcPos = input.pos;
return cErr;
ZSTD_outBuffer output;
ZSTD_inBuffer input;
output.dst = dst;
output.size = dstCapacity;
output.pos = *dstPos;
input.src = src;
input.size = srcSize;
input.pos = *srcPos;
{ size_t const cErr = ZSTD_decompressStream(dctx, &output, &input);
*dstPos = output.pos;
*srcPos = input.pos;
return cErr;
}
}