1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
|
/*
LZ4 HC - High Compression Mode of LZ4
Copyright (C) 2011-2012, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above
copyright notice, this list of conditions and the following disclaimer
in the documentation and/or other materials provided with the
distribution.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
You can contact the author at :
- LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
- LZ4 source repository : http://code.google.com/p/lz4/
*/
//**************************************
// CPU Feature Detection
//**************************************
// 32 or 64 bits ?
#if (defined(__x86_64__) || defined(__x86_64) || defined(__amd64__) || defined(__amd64) || defined(__ppc64__) || defined(_WIN64) || defined(__LP64__) || defined(_LP64) ) // Detects 64 bits mode
# define LZ4_ARCH64 1
#else
# define LZ4_ARCH64 0
#endif
// Little Endian or Big Endian ?
// Overwrite the #define below if you know your architecture endianess
#if defined (__GLIBC__)
# include <endian.h>
# if (__BYTE_ORDER == __BIG_ENDIAN)
# define LZ4_BIG_ENDIAN 1
# endif
#elif (defined(__BIG_ENDIAN__) || defined(__BIG_ENDIAN) || defined(_BIG_ENDIAN)) && !(defined(__LITTLE_ENDIAN__) || defined(__LITTLE_ENDIAN) || defined(_LITTLE_ENDIAN))
# define LZ4_BIG_ENDIAN 1
#elif defined(__sparc) || defined(__sparc__) \
|| defined(__ppc__) || defined(_POWER) || defined(__powerpc__) || defined(_ARCH_PPC) || defined(__PPC__) || defined(__PPC) || defined(PPC) || defined(__powerpc__) || defined(__powerpc) || defined(powerpc) \
|| defined(__hpux) || defined(__hppa) \
|| defined(_MIPSEB) || defined(__s390__)
# define LZ4_BIG_ENDIAN 1
#else
// Little Endian assumed. PDP Endian and other very rare endian format are unsupported.
#endif
// Unaligned memory access is automatically enabled for "common" CPU, such as x86.
// For others CPU, the compiler will be more cautious, and insert extra code to ensure aligned access is respected
// If you know your target CPU supports unaligned memory access, you want to force this option manually to improve performance
#if defined(__ARM_FEATURE_UNALIGNED)
# define LZ4_FORCE_UNALIGNED_ACCESS 1
#endif
// Define this parameter if your target system or compiler does not support hardware bit count
#if defined(_MSC_VER) && defined(_WIN32_WCE) // Visual Studio for Windows CE does not support Hardware bit count
# define LZ4_FORCE_SW_BITCOUNT
#endif
//**************************************
// Compiler Options
//**************************************
#if __STDC_VERSION__ >= 199901L // C99
/* "restrict" is a known keyword */
#else
# define restrict // Disable restrict
#endif
#ifdef _MSC_VER
# define inline __inline // Visual is not C99, but supports some kind of inline
# define forceinline __forceinline
# include <intrin.h> // For Visual 2005
# if LZ4_ARCH64 // 64-bit
# pragma intrinsic(_BitScanForward64) // For Visual 2005
# pragma intrinsic(_BitScanReverse64) // For Visual 2005
# else
# pragma intrinsic(_BitScanForward) // For Visual 2005
# pragma intrinsic(_BitScanReverse) // For Visual 2005
# endif
#else
# ifdef __GNUC__
# define forceinline inline __attribute__((always_inline))
# else
# define forceinline inline
# endif
#endif
#ifdef _MSC_VER // Visual Studio
#define lz4_bswap16(x) _byteswap_ushort(x)
#else
#define lz4_bswap16(x) ((unsigned short int) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8)))
#endif
//**************************************
// Includes
//**************************************
#include <stdlib.h> // calloc, free
#include <string.h> // memset, memcpy
#include "lz4hc.h"
#define ALLOCATOR(s) calloc(1,s)
#define FREEMEM free
#define MEM_INIT memset
//**************************************
// Basic Types
//**************************************
#if defined(_MSC_VER) // Visual Studio does not support 'stdint' natively
#define BYTE unsigned __int8
#define U16 unsigned __int16
#define U32 unsigned __int32
#define S32 __int32
#define U64 unsigned __int64
#else
#include <stdint.h>
#define BYTE uint8_t
#define U16 uint16_t
#define U32 uint32_t
#define S32 int32_t
#define U64 uint64_t
#endif
#ifndef LZ4_FORCE_UNALIGNED_ACCESS
#pragma pack(push, 1)
#endif
typedef struct _U16_S { U16 v; } U16_S;
typedef struct _U32_S { U32 v; } U32_S;
typedef struct _U64_S { U64 v; } U64_S;
#ifndef LZ4_FORCE_UNALIGNED_ACCESS
#pragma pack(pop)
#endif
#define A64(x) (((U64_S *)(x))->v)
#define A32(x) (((U32_S *)(x))->v)
#define A16(x) (((U16_S *)(x))->v)
//**************************************
// Constants
//**************************************
#define MINMATCH 4
#define DICTIONARY_LOGSIZE 16
#define MAXD (1<<DICTIONARY_LOGSIZE)
#define MAXD_MASK ((U32)(MAXD - 1))
#define MAX_DISTANCE (MAXD - 1)
#define HASH_LOG (DICTIONARY_LOGSIZE-1)
#define HASHTABLESIZE (1 << HASH_LOG)
#define HASH_MASK (HASHTABLESIZE - 1)
#define MAX_NB_ATTEMPTS 256
#define ML_BITS 4
#define ML_MASK (size_t)((1U<<ML_BITS)-1)
#define RUN_BITS (8-ML_BITS)
#define RUN_MASK ((1U<<RUN_BITS)-1)
#define COPYLENGTH 8
#define LASTLITERALS 5
#define MFLIMIT (COPYLENGTH+MINMATCH)
#define MINLENGTH (MFLIMIT+1)
#define OPTIMAL_ML (int)((ML_MASK-1)+MINMATCH)
//**************************************
// Architecture-specific macros
//**************************************
#if LZ4_ARCH64 // 64-bit
#define STEPSIZE 8
#define LZ4_COPYSTEP(s,d) A64(d) = A64(s); d+=8; s+=8;
#define LZ4_COPYPACKET(s,d) LZ4_COPYSTEP(s,d)
#define UARCH U64
#define AARCH A64
#define HTYPE U32
#define INITBASE(b,s) const BYTE* const b = s
#else // 32-bit
#define STEPSIZE 4
#define LZ4_COPYSTEP(s,d) A32(d) = A32(s); d+=4; s+=4;
#define LZ4_COPYPACKET(s,d) LZ4_COPYSTEP(s,d); LZ4_COPYSTEP(s,d);
#define UARCH U32
#define AARCH A32
#define HTYPE const BYTE*
#define INITBASE(b,s) const int b = 0
#endif
#if defined(LZ4_BIG_ENDIAN)
#define LZ4_READ_LITTLEENDIAN_16(d,s,p) { U16 v = A16(p); v = lz4_bswap16(v); d = (s) - v; }
#define LZ4_WRITE_LITTLEENDIAN_16(p,i) { U16 v = (U16)(i); v = lz4_bswap16(v); A16(p) = v; p+=2; }
#else // Little Endian
#define LZ4_READ_LITTLEENDIAN_16(d,s,p) { d = (s) - A16(p); }
#define LZ4_WRITE_LITTLEENDIAN_16(p,v) { A16(p) = v; p+=2; }
#endif
//************************************************************
// Local Types
//************************************************************
typedef struct
{
const BYTE* base;
HTYPE hashTable[HASHTABLESIZE];
U16 chainTable[MAXD];
const BYTE* nextToUpdate;
} LZ4HC_Data_Structure;
//**************************************
// Macros
//**************************************
#define LZ4_WILDCOPY(s,d,e) do { LZ4_COPYPACKET(s,d) } while (d<e);
#define LZ4_BLINDCOPY(s,d,l) { BYTE* e=d+l; LZ4_WILDCOPY(s,d,e); d=e; }
#define HASH_FUNCTION(i) (((i) * 2654435761U) >> ((MINMATCH*8)-HASH_LOG))
#define HASH_VALUE(p) HASH_FUNCTION(A32(p))
#define HASH_POINTER(p) (HashTable[HASH_VALUE(p)] + base)
#define DELTANEXT(p) chainTable[(size_t)(p) & MAXD_MASK]
#define GETNEXT(p) ((p) - (size_t)DELTANEXT(p))
//**************************************
// Private functions
//**************************************
#if LZ4_ARCH64
inline static int LZ4_NbCommonBytes (register U64 val)
{
#if defined(LZ4_BIG_ENDIAN)
#if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
unsigned long r = 0;
_BitScanReverse64( &r, val );
return (int)(r>>3);
#elif defined(__GNUC__) && ((__GNUC__ * 100 + __GNUC_MINOR__) >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
return (__builtin_clzll(val) >> 3);
#else
int r;
if (!(val>>32)) { r=4; } else { r=0; val>>=32; }
if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
r += (!val);
return r;
#endif
#else
#if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
unsigned long r = 0;
_BitScanForward64( &r, val );
return (int)(r>>3);
#elif defined(__GNUC__) && ((__GNUC__ * 100 + __GNUC_MINOR__) >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
return (__builtin_ctzll(val) >> 3);
#else
static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, 0, 3, 1, 3, 1, 4, 2, 7, 0, 2, 3, 6, 1, 5, 3, 5, 1, 3, 4, 4, 2, 5, 6, 7, 7, 0, 1, 2, 3, 3, 4, 6, 2, 6, 5, 5, 3, 4, 5, 6, 7, 1, 2, 4, 6, 4, 4, 5, 7, 2, 6, 5, 7, 6, 7, 7 };
return DeBruijnBytePos[((U64)((val & -val) * 0x0218A392CDABBD3F)) >> 58];
#endif
#endif
}
#else
inline static int LZ4_NbCommonBytes (register U32 val)
{
#if defined(LZ4_BIG_ENDIAN)
#if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
unsigned long r;
_BitScanReverse( &r, val );
return (int)(r>>3);
#elif defined(__GNUC__) && ((__GNUC__ * 100 + __GNUC_MINOR__) >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
return (__builtin_clz(val) >> 3);
#else
int r;
if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
r += (!val);
return r;
#endif
#else
#if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
unsigned long r;
_BitScanForward( &r, val );
return (int)(r>>3);
#elif defined(__GNUC__) && ((__GNUC__ * 100 + __GNUC_MINOR__) >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
return (__builtin_ctz(val) >> 3);
#else
static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 };
return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27];
#endif
#endif
}
#endif
inline static int LZ4HC_Init (LZ4HC_Data_Structure* hc4, const BYTE* base)
{
MEM_INIT((void*)hc4->hashTable, 0, sizeof(hc4->hashTable));
MEM_INIT(hc4->chainTable, 0xFF, sizeof(hc4->chainTable));
hc4->nextToUpdate = base + LZ4_ARCH64;
hc4->base = base;
return 1;
}
inline static void* LZ4HC_Create (const BYTE* base)
{
void* hc4 = ALLOCATOR(sizeof(LZ4HC_Data_Structure));
LZ4HC_Init ((LZ4HC_Data_Structure*)hc4, base);
return hc4;
}
inline static int LZ4HC_Free (void** LZ4HC_Data)
{
FREEMEM(*LZ4HC_Data);
*LZ4HC_Data = NULL;
return (1);
}
// Update chains up to ip (excluded)
forceinline static void LZ4HC_Insert (LZ4HC_Data_Structure* hc4, const BYTE* ip)
{
U16* chainTable = hc4->chainTable;
HTYPE* HashTable = hc4->hashTable;
INITBASE(base,hc4->base);
while(hc4->nextToUpdate < ip)
{
const BYTE* p = hc4->nextToUpdate;
size_t delta = (p) - HASH_POINTER(p);
if (delta>MAX_DISTANCE) delta = MAX_DISTANCE;
DELTANEXT(p) = (U16)delta;
HashTable[HASH_VALUE(p)] = (p) - base;
hc4->nextToUpdate++;
}
}
forceinline static size_t LZ4HC_CommonLength (const BYTE* p1, const BYTE* p2, const BYTE* const matchlimit)
{
const BYTE* p1t = p1;
while (p1t<matchlimit-(STEPSIZE-1))
{
UARCH diff = AARCH(p2) ^ AARCH(p1t);
if (!diff) { p1t+=STEPSIZE; p2+=STEPSIZE; continue; }
p1t += LZ4_NbCommonBytes(diff);
return (p1t - p1);
}
if (LZ4_ARCH64) if ((p1t<(matchlimit-3)) && (A32(p2) == A32(p1t))) { p1t+=4; p2+=4; }
if ((p1t<(matchlimit-1)) && (A16(p2) == A16(p1t))) { p1t+=2; p2+=2; }
if ((p1t<matchlimit) && (*p2 == *p1t)) p1t++;
return (p1t - p1);
}
forceinline static int LZ4HC_InsertAndFindBestMatch (LZ4HC_Data_Structure* hc4, const BYTE* ip, const BYTE* const matchlimit, const BYTE** matchpos)
{
U16* const chainTable = hc4->chainTable;
HTYPE* const HashTable = hc4->hashTable;
const BYTE* ref;
INITBASE(base,hc4->base);
int nbAttempts=MAX_NB_ATTEMPTS;
size_t ml=0;
// HC4 match finder
LZ4HC_Insert(hc4, ip);
ref = HASH_POINTER(ip);
#if 1
if (ref >= ip-4) // potential repetition
{
if (A32(ref) == A32(ip)) // confirmed
{
const U16 delta = (U16)(ip-ref);
const BYTE* ptr = ip;
const BYTE* end;
ml = LZ4HC_CommonLength(ip+MINMATCH, ref+MINMATCH, matchlimit) + MINMATCH;
end = ip + ml - (MINMATCH-1);
while(ptr < end-delta)
{
DELTANEXT(ptr) = delta; // Pre-Load
ptr++;
}
do
{
DELTANEXT(ptr) = delta;
HashTable[HASH_VALUE(ptr)] = (ptr) - base; // Head of chain
ptr++;
} while(ptr < end);
hc4->nextToUpdate = end;
*matchpos = ref;
}
ref = GETNEXT(ref);
}
#endif
while ((ref >= ip-MAX_DISTANCE) && (ref >= hc4->base) && (nbAttempts))
{
nbAttempts--;
if (*(ref+ml) == *(ip+ml))
if (A32(ref) == A32(ip))
{
size_t mlt = LZ4HC_CommonLength(ip+MINMATCH, ref+MINMATCH, matchlimit) + MINMATCH;
if (mlt > ml) { ml = mlt; *matchpos = ref; }
}
ref = GETNEXT(ref);
}
return (int)ml;
}
forceinline static int LZ4HC_InsertAndGetWiderMatch (LZ4HC_Data_Structure* hc4, const BYTE* ip, const BYTE* startLimit, const BYTE* matchlimit, int longest, const BYTE** matchpos, const BYTE** startpos)
{
U16* const chainTable = hc4->chainTable;
HTYPE* const HashTable = hc4->hashTable;
INITBASE(base,hc4->base);
const BYTE* ref;
int nbAttempts = MAX_NB_ATTEMPTS;
int delta = (int)(ip-startLimit);
// First Match
LZ4HC_Insert(hc4, ip);
ref = HASH_POINTER(ip);
while ((ref >= ip-MAX_DISTANCE) && (ref >= hc4->base) && (nbAttempts))
{
nbAttempts--;
if (*(startLimit + longest) == *(ref - delta + longest))
if (A32(ref) == A32(ip))
{
#if 1
const BYTE* reft = ref+MINMATCH;
const BYTE* ipt = ip+MINMATCH;
const BYTE* startt = ip;
while (ipt<matchlimit-(STEPSIZE-1))
{
UARCH diff = AARCH(reft) ^ AARCH(ipt);
if (!diff) { ipt+=STEPSIZE; reft+=STEPSIZE; continue; }
ipt += LZ4_NbCommonBytes(diff);
goto _endCount;
}
if (LZ4_ARCH64) if ((ipt<(matchlimit-3)) && (A32(reft) == A32(ipt))) { ipt+=4; reft+=4; }
if ((ipt<(matchlimit-1)) && (A16(reft) == A16(ipt))) { ipt+=2; reft+=2; }
if ((ipt<matchlimit) && (*reft == *ipt)) ipt++;
_endCount:
reft = ref;
#else
// Easier for code maintenance, but unfortunately slower too
const BYTE* startt = ip;
const BYTE* reft = ref;
const BYTE* ipt = ip + MINMATCH + LZ4HC_CommonLength(ip+MINMATCH, ref+MINMATCH, matchlimit);
#endif
while ((startt>startLimit) && (reft > hc4->base) && (startt[-1] == reft[-1])) {startt--; reft--;}
if ((ipt-startt) > longest)
{
longest = (int)(ipt-startt);
*matchpos = reft;
*startpos = startt;
}
}
ref = GETNEXT(ref);
}
return longest;
}
forceinline static int LZ4_encodeSequence(const BYTE** ip, BYTE** op, const BYTE** anchor, int ml, const BYTE* ref)
{
int length, len;
BYTE* token;
// Encode Literal length
length = (int)(*ip - *anchor);
token = (*op)++;
if (length>=(int)RUN_MASK) { *token=(RUN_MASK<<ML_BITS); len = length-RUN_MASK; for(; len > 254 ; len-=255) *(*op)++ = 255; *(*op)++ = (BYTE)len; }
else *token = (length<<ML_BITS);
// Copy Literals
LZ4_BLINDCOPY(*anchor, *op, length);
// Encode Offset
LZ4_WRITE_LITTLEENDIAN_16(*op,(U16)(*ip-ref));
// Encode MatchLength
len = (int)(ml-MINMATCH);
if (len>=(int)ML_MASK) { *token+=ML_MASK; len-=ML_MASK; for(; len > 509 ; len-=510) { *(*op)++ = 255; *(*op)++ = 255; } if (len > 254) { len-=255; *(*op)++ = 255; } *(*op)++ = (BYTE)len; }
else *token += len;
// Prepare next loop
*ip += ml;
*anchor = *ip;
return 0;
}
//****************************
// Compression CODE
//****************************
int LZ4_compressHCCtx(LZ4HC_Data_Structure* ctx,
const char* source,
char* dest,
int isize)
{
const BYTE* ip = (const BYTE*) source;
const BYTE* anchor = ip;
const BYTE* const iend = ip + isize;
const BYTE* const mflimit = iend - MFLIMIT;
const BYTE* const matchlimit = (iend - LASTLITERALS);
BYTE* op = (BYTE*) dest;
int ml, ml2, ml3, ml0;
const BYTE* ref=NULL;
const BYTE* start2=NULL;
const BYTE* ref2=NULL;
const BYTE* start3=NULL;
const BYTE* ref3=NULL;
const BYTE* start0;
const BYTE* ref0;
ip++;
// Main Loop
while (ip < mflimit)
{
ml = LZ4HC_InsertAndFindBestMatch (ctx, ip, matchlimit, (&ref));
if (!ml) { ip++; continue; }
// saved, in case we would skip too much
start0 = ip;
ref0 = ref;
ml0 = ml;
_Search2:
if (ip+ml < mflimit)
ml2 = LZ4HC_InsertAndGetWiderMatch(ctx, ip + ml - 2, ip + 1, matchlimit, ml, &ref2, &start2);
else ml2 = ml;
if (ml2 == ml) // No better match
{
LZ4_encodeSequence(&ip, &op, &anchor, ml, ref);
continue;
}
if (start0 < ip)
{
if (start2 < ip + ml0) // empirical
{
ip = start0;
ref = ref0;
ml = ml0;
}
}
// Here, start0==ip
if ((start2 - ip) < 3) // First Match too small : removed
{
ml = ml2;
ip = start2;
ref =ref2;
goto _Search2;
}
_Search3:
// Currently we have :
// ml2 > ml1, and
// ip1+3 <= ip2 (usually < ip1+ml1)
if ((start2 - ip) < OPTIMAL_ML)
{
int correction;
int new_ml = ml;
if (new_ml > OPTIMAL_ML) new_ml = OPTIMAL_ML;
if (ip+new_ml > start2 + ml2 - MINMATCH) new_ml = (int)(start2 - ip) + ml2 - MINMATCH;
correction = new_ml - (int)(start2 - ip);
if (correction > 0)
{
start2 += correction;
ref2 += correction;
ml2 -= correction;
}
}
// Now, we have start2 = ip+new_ml, with new_ml = min(ml, OPTIMAL_ML=18)
if (start2 + ml2 < mflimit)
ml3 = LZ4HC_InsertAndGetWiderMatch(ctx, start2 + ml2 - 3, start2, matchlimit, ml2, &ref3, &start3);
else ml3 = ml2;
if (ml3 == ml2) // No better match : 2 sequences to encode
{
// ip & ref are known; Now for ml
if (start2 < ip+ml) ml = (int)(start2 - ip);
// Now, encode 2 sequences
LZ4_encodeSequence(&ip, &op, &anchor, ml, ref);
ip = start2;
LZ4_encodeSequence(&ip, &op, &anchor, ml2, ref2);
continue;
}
if (start3 < ip+ml+3) // Not enough space for match 2 : remove it
{
if (start3 >= (ip+ml)) // can write Seq1 immediately ==> Seq2 is removed, so Seq3 becomes Seq1
{
if (start2 < ip+ml)
{
int correction = (int)(ip+ml - start2);
start2 += correction;
ref2 += correction;
ml2 -= correction;
if (ml2 < MINMATCH)
{
start2 = start3;
ref2 = ref3;
ml2 = ml3;
}
}
LZ4_encodeSequence(&ip, &op, &anchor, ml, ref);
ip = start3;
ref = ref3;
ml = ml3;
start0 = start2;
ref0 = ref2;
ml0 = ml2;
goto _Search2;
}
start2 = start3;
ref2 = ref3;
ml2 = ml3;
goto _Search3;
}
// OK, now we have 3 ascending matches; let's write at least the first one
// ip & ref are known; Now for ml
if (start2 < ip+ml)
{
if ((start2 - ip) < (int)ML_MASK)
{
int correction;
if (ml > OPTIMAL_ML) ml = OPTIMAL_ML;
if (ip + ml > start2 + ml2 - MINMATCH) ml = (int)(start2 - ip) + ml2 - MINMATCH;
correction = ml - (int)(start2 - ip);
if (correction > 0)
{
start2 += correction;
ref2 += correction;
ml2 -= correction;
}
}
else
{
ml = (int)(start2 - ip);
}
}
LZ4_encodeSequence(&ip, &op, &anchor, ml, ref);
ip = start2;
ref = ref2;
ml = ml2;
start2 = start3;
ref2 = ref3;
ml2 = ml3;
goto _Search3;
}
// Encode Last Literals
{
int lastRun = (int)(iend - anchor);
if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun > 254 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; }
else *op++ = (lastRun<<ML_BITS);
memcpy(op, anchor, iend - anchor);
op += iend-anchor;
}
// End
return (int) (((char*)op)-dest);
}
int LZ4_compressHC(const char* source,
char* dest,
int isize)
{
void* ctx = LZ4HC_Create((const BYTE*)source);
int result = LZ4_compressHCCtx(ctx, source, dest, isize);
LZ4HC_Free (&ctx);
return result;
}
|