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

fixed #304

Browse Source 
Pathological samples may result in literal section being incompressible.
This case is now detected,
and literal distribution is replaced by one that can be written into the dictionary.
This commit is contained in:
Yann Collet
2018-01-11 11:16:32 -08:00
parent 218e9fe0fc
commit e8093dde09
4 changed files with 38 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/dictBuilder/zdict.c
+25 -7
View File
@@ -666,6 +666,18 @@ static void ZDICT_insertSortCount(offsetCount_t table[ZSTD_REP_NUM+1], U32 val,
}
}
/* ZDICT_flatLit() :
* rewrite `countLit` to contain a mostly flat but still compressible distribution of literals.
* necessary to avoid generating a non-compressible distribution that HUF_writeCTable() cannot encode.
*/
static void ZDICT_flatLit(U32* countLit)
{
int u;
for (u=1; u<256; u++) countLit[u] = 2;
countLit[0] = 4;
countLit[253] = 1;
countLit[254] = 1;
}
#define OFFCODE_MAX 30 /* only applicable to first block */
static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize,
@@ -730,14 +742,20 @@ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize,
pos += fileSizes[u];
}
/* analyze */
errorCode = HUF_buildCTable (hufTable, countLit, 255, huffLog);
if (HUF_isError(errorCode)) {
eSize = ERROR(GENERIC);
DISPLAYLEVEL(1, " HUF_buildCTable error \n");
goto _cleanup;
/* analyze, build stats, starting with literals */
{ size_t maxNbBits = HUF_buildCTable (hufTable, countLit, 255, huffLog);
if (HUF_isError(maxNbBits)) {
eSize = ERROR(GENERIC);
DISPLAYLEVEL(1, " HUF_buildCTable error \n");
goto _cleanup;
}
if (maxNbBits==8) { /* not compressible : will fail on HUF_writeCTable() */
ZDICT_flatLit(countLit); /* replace distribution by a fake "mostly flat but still compressible" distribution, that HUF_writeCTable() can encode */
maxNbBits = HUF_buildCTable (hufTable, countLit, 255, huffLog);
assert(maxNbBits==9);
}
huffLog = (U32)maxNbBits;
}
huffLog = (U32)errorCode;
/* looking for most common first offsets */
{ U32 offset;