minor comment changes

This commit is contained in:
Yann Collet 2016-07-24 14:26:11 +02:00
parent 10b9c13d07
commit 7ed5e33b89
3 changed files with 9 additions and 121 deletions

View File

@ -173,16 +173,15 @@ size_t HUF_readStats(BYTE* huffWeight, size_t hwSize, U32* rankStats,
size_t iSize = ip[0];
size_t oSize;
//memset(huffWeight, 0, hwSize); /* is not necessary, even though some analyzer complain ... */
/* memset(huffWeight, 0, hwSize); *//* is not necessary, even though some analyzer complain ... */
if (iSize >= 128) { /* special header */
if (iSize >= 128) { /* special header */
if (iSize >= (242)) { /* RLE */
static U32 l[14] = { 1, 2, 3, 4, 7, 8, 15, 16, 31, 32, 63, 64, 127, 128 };
oSize = l[iSize-242];
memset(huffWeight, 1, hwSize);
iSize = 0;
}
else { /* Incompressible */
} else { /* Incompressible */
oSize = iSize - 127;
iSize = ((oSize+1)/2);
if (iSize+1 > srcSize) return ERROR(srcSize_wrong);

View File

@ -174,7 +174,7 @@ size_t HUF_readCTable (HUF_CElt* CTable, U32 maxSymbolValue, const void* src, si
U32 tableLog = 0;
size_t readSize;
U32 nbSymbols = 0;
//memset(huffWeight, 0, sizeof(huffWeight)); /* is not necessary, even though some analyzer complain ... */
/*memset(huffWeight, 0, sizeof(huffWeight));*/ /* is not necessary, even though some analyzer complain ... */
/* get symbol weights */
readSize = HUF_readStats(huffWeight, HUF_SYMBOLVALUE_MAX+1, rankVal, &nbSymbols, &tableLog, src, srcSize);
@ -193,10 +193,10 @@ size_t HUF_readCTable (HUF_CElt* CTable, U32 maxSymbolValue, const void* src, si
} }
/* fill nbBits */
{ U32 n; for (n=0; n<nbSymbols; n++) {
const U32 w = huffWeight[n];
CTable[n].nbBits = (BYTE)(tableLog + 1 - w);
}}
{ U32 n; for (n=0; n<nbSymbols; n++) {
const U32 w = huffWeight[n];
CTable[n].nbBits = (BYTE)(tableLog + 1 - w);
} }
/* fill val */
{ U16 nbPerRank[HUF_TABLELOG_MAX+1] = {0};
@ -535,7 +535,6 @@ static size_t HUF_compress_internal (
{ size_t const hSize = HUF_writeCTable (op, dstSize, CTable, maxSymbolValue, huffLog);
if (HUF_isError(hSize)) return hSize;
if (hSize + 12 >= srcSize) return 0; /* not useful to try compression */
//static U64 totalHSize = 0; static U32 nbHSize = 0; totalHSize += hSize; nbHSize++; if ((nbHSize & 63) == 1) printf("average : %6.3f \n", (double)totalHSize / nbHSize);
op += hSize;
}

View File

@ -194,117 +194,7 @@ void ZSTD_copyDCtx(ZSTD_DCtx* dstDCtx, const ZSTD_DCtx* srcDCtx)
* Decompression section
***************************************************************/
/* Frame format description
Frame Header - [ Block Header - Block ] - Frame End
1) Frame Header
- 4 bytes - Magic Number : ZSTD_MAGICNUMBER (defined within zstd.h)
- 1 byte - Frame Descriptor
2) Block Header
- 3 bytes, starting with a 2-bits descriptor
Uncompressed, Compressed, Frame End, unused
3) Block
See Block Format Description
4) Frame End
- 3 bytes, compatible with Block Header
*/
/* Frame Header :
1 byte - FrameHeaderDescription :
bit 0-1 : dictID (0, 1, 2 or 4 bytes)
bit 2 : checksumFlag
bit 3 : reserved (must be zero)
bit 4 : reserved (unused, can be any value)
bit 5 : Single Segment (if 1, WindowLog byte is not present)
bit 6-7 : FrameContentFieldSize (0, 2, 4, or 8)
if (SkippedWindowLog && !FrameContentFieldsize) FrameContentFieldsize=1;
Optional : WindowLog (0 or 1 byte)
bit 0-2 : octal Fractional (1/8th)
bit 3-7 : Power of 2, with 0 = 1 KB (up to 2 TB)
Optional : dictID (0, 1, 2 or 4 bytes)
Automatic adaptation
0 : no dictID
1 : 1 - 255
2 : 256 - 65535
4 : all other values
Optional : content size (0, 1, 2, 4 or 8 bytes)
0 : unknown (fcfs==0 and swl==0)
1 : 0-255 bytes (fcfs==0 and swl==1)
2 : 256 - 65535+256 (fcfs==1)
4 : 0 - 4GB-1 (fcfs==2)
8 : 0 - 16EB-1 (fcfs==3)
*/
/* Compressed Block, format description
Block = Literal Section - Sequences Section
Prerequisite : size of (compressed) block, maximum size of regenerated data
1) Literal Section
1.1) Header : 1-5 bytes
flags: 2 bits
00 compressed by Huff0
01 unused
10 is Raw (uncompressed)
11 is Rle
Note : using 01 => Huff0 with precomputed table ?
Note : delta map ? => compressed ?
1.1.1) Huff0-compressed literal block : 3-5 bytes
srcSize < 1 KB => 3 bytes (2-2-10-10) => single stream
srcSize < 1 KB => 3 bytes (2-2-10-10)
srcSize < 16KB => 4 bytes (2-2-14-14)
else => 5 bytes (2-2-18-18)
big endian convention
1.1.2) Raw (uncompressed) literal block header : 1-3 bytes
size : 5 bits: (IS_RAW<<6) + (0<<4) + size
12 bits: (IS_RAW<<6) + (2<<4) + (size>>8)
size&255
20 bits: (IS_RAW<<6) + (3<<4) + (size>>16)
size>>8&255
size&255
1.1.3) Rle (repeated single byte) literal block header : 1-3 bytes
size : 5 bits: (IS_RLE<<6) + (0<<4) + size
12 bits: (IS_RLE<<6) + (2<<4) + (size>>8)
size&255
20 bits: (IS_RLE<<6) + (3<<4) + (size>>16)
size>>8&255
size&255
1.1.4) Huff0-compressed literal block, using precomputed CTables : 3-5 bytes
srcSize < 1 KB => 3 bytes (2-2-10-10) => single stream
srcSize < 1 KB => 3 bytes (2-2-10-10)
srcSize < 16KB => 4 bytes (2-2-14-14)
else => 5 bytes (2-2-18-18)
big endian convention
1- CTable available (stored into workspace ?)
2- Small input (fast heuristic ? Full comparison ? depend on clevel ?)
1.2) Literal block content
1.2.1) Huff0 block, using sizes from header
See Huff0 format
1.2.2) Huff0 block, using prepared table
1.2.3) Raw content
1.2.4) single byte
2) Sequences section
TO DO
*/
/* See compression format details in : zstd_compression_format.md */
/** ZSTD_frameHeaderSize() :
* srcSize must be >= ZSTD_frameHeaderSize_min.