summaryrefslogtreecommitdiffstats
path: root/lib/lz4.c
blob: e15a022641a131ff069f648c39499e2dd251afc0 (plain)
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
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
/*
   LZ4 - Fast LZ compression algorithm
   Copyright (C) 2011-2015, 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 source repository : https://github.com/Cyan4973/lz4
   - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c
*/


/**************************************
   Tuning parameters
**************************************/
/*
 * HEAPMODE :
 * Select how default compression functions will allocate memory for their hash table,
 * in memory stack (0:default, fastest), or in memory heap (1:requires malloc()).
 */
#define HEAPMODE 0

/*
 * CPU_HAS_EFFICIENT_UNALIGNED_MEMORY_ACCESS :
 * By default, the source code expects the compiler to correctly optimize
 * 4-bytes and 8-bytes read on architectures able to handle it efficiently.
 * This is not always the case. In some circumstances (ARM notably),
 * the compiler will issue cautious code even when target is able to correctly handle unaligned memory accesses.
 *
 * You can force the compiler to use unaligned memory access by uncommenting the line below.
 * One of the below scenarios will happen :
 * 1 - Your target CPU correctly handle unaligned access, and was not well optimized by compiler (good case).
 *     You will witness large performance improvements (+50% and up).
 *     Keep the line uncommented and send a word to upstream (https://groups.google.com/forum/#!forum/lz4c)
 *     The goal is to automatically detect such situations by adding your target CPU within an exception list.
 * 2 - Your target CPU correctly handle unaligned access, and was already already optimized by compiler
 *     No change will be experienced.
 * 3 - Your target CPU inefficiently handle unaligned access.
 *     You will experience a performance loss. Comment back the line.
 * 4 - Your target CPU does not handle unaligned access.
 *     Program will crash.
 * If uncommenting results in better performance (case 1)
 * please report your configuration to upstream (https://groups.google.com/forum/#!forum/lz4c)
 * This way, an automatic detection macro can be added to match your case within later versions of the library.
 */
/* #define CPU_HAS_EFFICIENT_UNALIGNED_MEMORY_ACCESS 1 */


/**************************************
   CPU Feature Detection
**************************************/
/*
 * Automated efficient unaligned memory access detection
 * Based on known hardware architectures
 * This list will be updated thanks to feedbacks
 */
#if defined(CPU_HAS_EFFICIENT_UNALIGNED_MEMORY_ACCESS) \
    || defined(__ARM_FEATURE_UNALIGNED) \
    || defined(__i386__) || defined(__x86_64__) \
    || defined(_M_IX86) || defined(_M_X64) \
    || defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_8__) \
    || (defined(_M_ARM) && (_M_ARM >= 7))
#  define LZ4_UNALIGNED_ACCESS 1
#else
#  define LZ4_UNALIGNED_ACCESS 0
#endif

/*
 * LZ4_FORCE_SW_BITCOUNT
 * 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 defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)   /* C99 */
/* "restrict" is a known keyword */
#else
#  define restrict /* Disable restrict */
#endif

#ifdef _MSC_VER    /* Visual Studio */
#  define FORCE_INLINE static __forceinline
#  include <intrin.h>
#  pragma warning(disable : 4127)        /* disable: C4127: conditional expression is constant */
#  pragma warning(disable : 4293)        /* disable: C4293: too large shift (32-bits) */
#else
#  if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)   /* C99 */
#    ifdef __GNUC__
#      define FORCE_INLINE static inline __attribute__((always_inline))
#    else
#      define FORCE_INLINE static inline
#    endif
#  else
#    define FORCE_INLINE static
#  endif   /* __STDC_VERSION__ */
#endif  /* _MSC_VER */

#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)

#if (GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__)
#  define expect(expr,value)    (__builtin_expect ((expr),(value)) )
#else
#  define expect(expr,value)    (expr)
#endif

#define likely(expr)     expect((expr) != 0, 1)
#define unlikely(expr)   expect((expr) != 0, 0)


/**************************************
   Memory routines
**************************************/
#include <stdlib.h>   /* malloc, calloc, free */
#define ALLOCATOR(n,s) calloc(n,s)
#define FREEMEM        free
#include <string.h>   /* memset, memcpy */
#define MEM_INIT       memset


/**************************************
   Includes
**************************************/
#include "lz4.h"


/**************************************
   Basic Types
**************************************/
#if defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)   /* C99 */
# include <stdint.h>
  typedef  uint8_t BYTE;
  typedef uint16_t U16;
  typedef uint32_t U32;
  typedef  int32_t S32;
  typedef uint64_t U64;
#else
  typedef unsigned char       BYTE;
  typedef unsigned short      U16;
  typedef unsigned int        U32;
  typedef   signed int        S32;
  typedef unsigned long long  U64;
#endif


/**************************************
   Reading and writing into memory
**************************************/
#define STEPSIZE sizeof(size_t)

static unsigned LZ4_64bits(void) { return sizeof(void*)==8; }

static unsigned LZ4_isLittleEndian(void)
{
    const union { U32 i; BYTE c[4]; } one = { 1 };   /* don't use static : performance detrimental  */
    return one.c[0];
}


static U16 LZ4_readLE16(const void* memPtr)
{
    if ((LZ4_UNALIGNED_ACCESS) && (LZ4_isLittleEndian()))
        return *(U16*)memPtr;
    else
    {
        const BYTE* p = (const BYTE*)memPtr;
        return (U16)((U16)p[0] + (p[1]<<8));
    }
}

static void LZ4_writeLE16(void* memPtr, U16 value)
{
    if ((LZ4_UNALIGNED_ACCESS) && (LZ4_isLittleEndian()))
    {
        *(U16*)memPtr = value;
        return;
    }
    else
    {
        BYTE* p = (BYTE*)memPtr;
        p[0] = (BYTE) value;
        p[1] = (BYTE)(value>>8);
    }
}


static U16 LZ4_read16(const void* memPtr)
{
    if (LZ4_UNALIGNED_ACCESS)
        return *(U16*)memPtr;
    else
    {
        U16 val16;
        memcpy(&val16, memPtr, 2);
        return val16;
    }
}

static U32 LZ4_read32(const void* memPtr)
{
    if (LZ4_UNALIGNED_ACCESS)
        return *(U32*)memPtr;
    else
    {
        U32 val32;
        memcpy(&val32, memPtr, 4);
        return val32;
    }
}

static U64 LZ4_read64(const void* memPtr)
{
    if (LZ4_UNALIGNED_ACCESS)
        return *(U64*)memPtr;
    else
    {
        U64 val64;
        memcpy(&val64, memPtr, 8);
        return val64;
    }
}

static size_t LZ4_read_ARCH(const void* p)
{
    if (LZ4_64bits())
        return (size_t)LZ4_read64(p);
    else
        return (size_t)LZ4_read32(p);
}


static void LZ4_copy4(void* dstPtr, const void* srcPtr)
{
    if (LZ4_UNALIGNED_ACCESS)
    {
        *(U32*)dstPtr = *(U32*)srcPtr;
        return;
    }
    memcpy(dstPtr, srcPtr, 4);
}

static void LZ4_copy8(void* dstPtr, const void* srcPtr)
{
#if GCC_VERSION!=409  /* disabled on GCC 4.9, as it generates invalid opcode (crash) */
    if (LZ4_UNALIGNED_ACCESS)
    {
        if (LZ4_64bits())
            *(U64*)dstPtr = *(U64*)srcPtr;
        else
            ((U32*)dstPtr)[0] = ((U32*)srcPtr)[0],
            ((U32*)dstPtr)[1] = ((U32*)srcPtr)[1];
        return;
    }
#endif
    memcpy(dstPtr, srcPtr, 8);
}

/* customized version of memcpy, which may overwrite up to 7 bytes beyond dstEnd */
static void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd)
{
    BYTE* d = (BYTE*)dstPtr;
    const BYTE* s = (const BYTE*)srcPtr;
    BYTE* e = (BYTE*)dstEnd;
    do { LZ4_copy8(d,s); d+=8; s+=8; } while (d<e);
}


/**************************************
   Common Constants
**************************************/
#define MINMATCH 4

#define COPYLENGTH 8
#define LASTLITERALS 5
#define MFLIMIT (COPYLENGTH+MINMATCH)
static const int LZ4_minLength = (MFLIMIT+1);

#define KB *(1 <<10)
#define MB *(1 <<20)
#define GB *(1U<<30)

#define MAXD_LOG 16
#define MAX_DISTANCE ((1 << MAXD_LOG) - 1)

#define ML_BITS  4
#define ML_MASK  ((1U<<ML_BITS)-1)
#define RUN_BITS (8-ML_BITS)
#define RUN_MASK ((1U<<RUN_BITS)-1)


/**************************************
*  Common Utils
**************************************/
#define LZ4_STATIC_ASSERT(c)    { enum { LZ4_static_assert = 1/(int)(!!(c)) }; }   /* use only *after* variable declarations */


/**************************************
*  Common functions
**************************************/
static unsigned LZ4_NbCommonBytes (register size_t val)
{
    if (LZ4_isLittleEndian())
    {
        if (LZ4_64bits())
        {
#       if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
            unsigned long r = 0;
            _BitScanForward64( &r, (U64)val );
            return (int)(r>>3);
#       elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
            return (__builtin_ctzll((U64)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 & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58];
#       endif
        }
        else /* 32 bits */
        {
#       if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
            unsigned long r;
            _BitScanForward( &r, (U32)val );
            return (int)(r>>3);
#       elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
            return (__builtin_ctz((U32)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
        }
    }
    else   /* Big Endian CPU */
    {
        if (LZ4_64bits())
        {
#       if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
            unsigned long r = 0;
            _BitScanReverse64( &r, val );
            return (unsigned)(r>>3);
#       elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
            return (__builtin_clzll(val) >> 3);
#       else
            unsigned 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 /* 32 bits */
        {
#       if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
            unsigned long r = 0;
            _BitScanReverse( &r, (unsigned long)val );
            return (unsigned)(r>>3);
#       elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
            return (__builtin_clz(val) >> 3);
#       else
            unsigned r;
            if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
            r += (!val);
            return r;
#       endif
        }
    }
}

static unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit)
{
    const BYTE* const pStart = pIn;

    while (likely(pIn<pInLimit-(STEPSIZE-1)))
    {
        size_t diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
        if (!diff) { pIn+=STEPSIZE; pMatch+=STEPSIZE; continue; }
        pIn += LZ4_NbCommonBytes(diff);
        return (unsigned)(pIn - pStart);
    }

    if (LZ4_64bits()) if ((pIn<(pInLimit-3)) && (LZ4_read32(pMatch) == LZ4_read32(pIn))) { pIn+=4; pMatch+=4; }
    if ((pIn<(pInLimit-1)) && (LZ4_read16(pMatch) == LZ4_read16(pIn))) { pIn+=2; pMatch+=2; }
    if ((pIn<pInLimit) && (*pMatch == *pIn)) pIn++;
    return (unsigned)(pIn - pStart);
}


#ifndef LZ4_COMMONDEFS_ONLY
/**************************************
*  Local Constants
**************************************/
#define LZ4_HASHLOG   (LZ4_MEMORY_USAGE-2)
#define HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
#define HASH_SIZE_U32 (1 << LZ4_HASHLOG)       /* required as macro for static allocation */

static const int LZ4_64Klimit = ((64 KB) + (MFLIMIT-1));
static const U32 LZ4_skipTrigger = 6;  /* Increase this value ==> compression run slower on incompressible data */


/**************************************
*  Local Utils
**************************************/
int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; }
int LZ4_compressBound(int isize)  { return LZ4_COMPRESSBOUND(isize); }


/**************************************
*  Local Structures and types
**************************************/
typedef struct {
    U32 hashTable[HASH_SIZE_U32];
    U32 currentOffset;
    U32 initCheck;
    const BYTE* dictionary;
    const BYTE* bufferStart;
    U32 dictSize;
} LZ4_stream_t_internal;

typedef enum { notLimited = 0, limitedOutput = 1 } limitedOutput_directive;
typedef enum { byPtr, byU32, byU16 } tableType_t;

typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive;
typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;

typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
typedef enum { full = 0, partial = 1 } earlyEnd_directive;



/********************************
*  Compression functions
********************************/

static U32 LZ4_hashSequence(U32 sequence, tableType_t const tableType)
{
    if (tableType == byU16)
        return (((sequence) * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1)));
    else
        return (((sequence) * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG));
}

static U32 LZ4_hashPosition(const BYTE* p, tableType_t tableType) { return LZ4_hashSequence(LZ4_read32(p), tableType); }

static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t const tableType, const BYTE* srcBase)
{
    switch (tableType)
    {
    case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = p; return; }
    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); return; }
    case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); return; }
    }
}

static void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
{
    U32 h = LZ4_hashPosition(p, tableType);
    LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase);
}

static const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase)
{
    if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; }
    if (tableType == byU32) { U32* hashTable = (U32*) tableBase; return hashTable[h] + srcBase; }
    { U16* hashTable = (U16*) tableBase; return hashTable[h] + srcBase; }   /* default, to ensure a return */
}

static const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
{
    U32 h = LZ4_hashPosition(p, tableType);
    return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase);
}

static int LZ4_compress_generic(
                 void* ctx,
                 const char* source,
                 char* dest,
                 int inputSize,
                 int maxOutputSize,
                 limitedOutput_directive outputLimited,
                 tableType_t const tableType,
                 dict_directive dict,
                 dictIssue_directive dictIssue)
{
    LZ4_stream_t_internal* const dictPtr = (LZ4_stream_t_internal*)ctx;

    const BYTE* ip = (const BYTE*) source;
    const BYTE* base;
    const BYTE* lowLimit;
    const BYTE* const lowRefLimit = ip - dictPtr->dictSize;
    const BYTE* const dictionary = dictPtr->dictionary;
    const BYTE* const dictEnd = dictionary + dictPtr->dictSize;
    const size_t dictDelta = dictEnd - (const BYTE*)source;
    const BYTE* anchor = (const BYTE*) source;
    const BYTE* const iend = ip + inputSize;
    const BYTE* const mflimit = iend - MFLIMIT;
    const BYTE* const matchlimit = iend - LASTLITERALS;

    BYTE* op = (BYTE*) dest;
    BYTE* const olimit = op + maxOutputSize;

    U32 forwardH;
    size_t refDelta=0;

    /* Init conditions */
    if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0;          /* Unsupported input size, too large (or negative) */
    switch(dict)
    {
    case noDict:
    default:
        base = (const BYTE*)source;
        lowLimit = (const BYTE*)source;
        break;
    case withPrefix64k:
        base = (const BYTE*)source - dictPtr->currentOffset;
        lowLimit = (const BYTE*)source - dictPtr->dictSize;
        break;
    case usingExtDict:
        base = (const BYTE*)source - dictPtr->currentOffset;
        lowLimit = (const BYTE*)source;
        break;
    }
    if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0;   /* Size too large (not within 64K limit) */
    if (inputSize<LZ4_minLength) goto _last_literals;                  /* Input too small, no compression (all literals) */

    /* First Byte */
    LZ4_putPosition(ip, ctx, tableType, base);
    ip++; forwardH = LZ4_hashPosition(ip, tableType);

    /* Main Loop */
    for ( ; ; )
    {
        const BYTE* match;
        BYTE* token;
        {
            const BYTE* forwardIp = ip;
            unsigned step=1;
            unsigned searchMatchNb = (1U << LZ4_skipTrigger);

            /* Find a match */
            do {
                U32 h = forwardH;
                ip = forwardIp;
                forwardIp += step;
                step = searchMatchNb++ >> LZ4_skipTrigger;

                if (unlikely(forwardIp > mflimit)) goto _last_literals;

                match = LZ4_getPositionOnHash(h, ctx, tableType, base);
                if (dict==usingExtDict)
                {
                    if (match<(const BYTE*)source)
                    {
                        refDelta = dictDelta;
                        lowLimit = dictionary;
                    }
                    else
                    {
                        refDelta = 0;
                        lowLimit = (const BYTE*)source;
                    }
                }
                forwardH = LZ4_hashPosition(forwardIp, tableType);
                LZ4_putPositionOnHash(ip, h, ctx, tableType, base);

            } while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0)
                || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
                || (LZ4_read32(match+refDelta) != LZ4_read32(ip)) );
        }

        /* Catch up */
        while ((ip>anchor) && (match+refDelta > lowLimit) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; }

        {
            /* Encode Literal length */
            unsigned litLength = (unsigned)(ip - anchor);
            token = op++;
            if ((outputLimited) && (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)))
                return 0;   /* Check output limit */
            if (litLength>=RUN_MASK)
            {
                int len = (int)litLength-RUN_MASK;
                *token=(RUN_MASK<<ML_BITS);
                for(; len >= 255 ; len-=255) *op++ = 255;
                *op++ = (BYTE)len;
            }
            else *token = (BYTE)(litLength<<ML_BITS);

            /* Copy Literals */
            LZ4_wildCopy(op, anchor, op+litLength);
            op+=litLength;
        }

_next_match:
        /* Encode Offset */
        LZ4_writeLE16(op, (U16)(ip-match)); op+=2;

        /* Encode MatchLength */
        {
            unsigned matchLength;

            if ((dict==usingExtDict) && (lowLimit==dictionary))
            {
                const BYTE* limit;
                match += refDelta;
                limit = ip + (dictEnd-match);
                if (limit > matchlimit) limit = matchlimit;
                matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, limit);
                ip += MINMATCH + matchLength;
                if (ip==limit)
                {
                    unsigned more = LZ4_count(ip, (const BYTE*)source, matchlimit);
                    matchLength += more;
                    ip += more;
                }
            }
            else
            {
                matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
                ip += MINMATCH + matchLength;
            }

            if ((outputLimited) && (unlikely(op + (1 + LASTLITERALS) + (matchLength>>8) > olimit)))
                return 0;    /* Check output limit */
            if (matchLength>=ML_MASK)
            {
                *token += ML_MASK;
                matchLength -= ML_MASK;
                for (; matchLength >= 510 ; matchLength-=510) { *op++ = 255; *op++ = 255; }
                if (matchLength >= 255) { matchLength-=255; *op++ = 255; }
                *op++ = (BYTE)matchLength;
            }
            else *token += (BYTE)(matchLength);
        }

        anchor = ip;

        /* Test end of chunk */
        if (ip > mflimit) break;

        /* Fill table */
        LZ4_putPosition(ip-2, ctx, tableType, base);

        /* Test next position */
        match = LZ4_getPosition(ip, ctx, tableType, base);
        if (dict==usingExtDict)
        {
            if (match<(const BYTE*)source)
            {
                refDelta = dictDelta;
                lowLimit = dictionary;
            }
            else
            {
                refDelta = 0;
                lowLimit = (const BYTE*)source;
            }
        }
        LZ4_putPosition(ip, ctx, tableType, base);
        if ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1)
            && (match+MAX_DISTANCE>=ip)
            && (LZ4_read32(match+refDelta)==LZ4_read32(ip)) )
        { token=op++; *token=0; goto _next_match; }

        /* Prepare next loop */
        forwardH = LZ4_hashPosition(++ip, tableType);
    }

_last_literals:
    /* Encode Last Literals */
    {
        int lastRun = (int)(iend - anchor);
        if ((outputLimited) && (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize))
            return 0;   /* Check output limit */
        if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun >= 255 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; }
        else *op++ = (BYTE)(lastRun<<ML_BITS);
        memcpy(op, anchor, iend - anchor);
        op += iend-anchor;
    }

    /* End */
    return (int) (((char*)op)-dest);
}


int LZ4_compress(const char* source, char* dest, int inputSize)
{
#if (HEAPMODE)
    void* ctx = ALLOCATOR(LZ4_STREAMSIZE_U64, 8);   /* Aligned on 8-bytes boundaries */
#else
    U64 ctx[LZ4_STREAMSIZE_U64] = {0};      /* Ensure data is aligned on 8-bytes boundaries */
#endif
    int result;

    if (inputSize < LZ4_64Klimit)
        result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue);
    else
        result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, 0, notLimited, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue);

#if (HEAPMODE)
    FREEMEM(ctx);
#endif
    return result;
}

int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize)
{
#if (HEAPMODE)
    void* ctx = ALLOCATOR(LZ4_STREAMSIZE_U64, 8);   /* Aligned on 8-bytes boundaries */
#else
    U64 ctx[LZ4_STREAMSIZE_U64] = {0};      /* Ensure data is aligned on 8-bytes boundaries */
#endif
    int result;

    if (inputSize < LZ4_64Klimit)
        result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue);
    else
        result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limitedOutput, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue);

#if (HEAPMODE)
    FREEMEM(ctx);
#endif
    return result;
}


/*****************************************
*  Experimental : Streaming functions
*****************************************/

/*
 * LZ4_initStream
 * Use this function once, to init a newly allocated LZ4_stream_t structure
 * Return : 1 if OK, 0 if error
 */
void LZ4_resetStream (LZ4_stream_t* LZ4_stream)
{
    MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t));
}

LZ4_stream_t* LZ4_createStream(void)
{
    LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOCATOR(8, LZ4_STREAMSIZE_U64);
    LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal));    /* A compilation error here means LZ4_STREAMSIZE is not large enough */
    LZ4_resetStream(lz4s);
    return lz4s;
}

int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
{
    FREEMEM(LZ4_stream);
    return (0);
}


int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
{
    LZ4_stream_t_internal* dict = (LZ4_stream_t_internal*) LZ4_dict;
    const BYTE* p = (const BYTE*)dictionary;
    const BYTE* const dictEnd = p + dictSize;
    const BYTE* base;

    if (dict->initCheck) LZ4_resetStream(LZ4_dict);                         /* Uninitialized structure detected */

    if (dictSize < MINMATCH)
    {
        dict->dictionary = NULL;
        dict->dictSize = 0;
        return 0;
    }

    if (p <= dictEnd - 64 KB) p = dictEnd - 64 KB;
    base = p - dict->currentOffset;
    dict->dictionary = p;
    dict->dictSize = (U32)(dictEnd - p);
    dict->currentOffset += dict->dictSize;

    while (p <= dictEnd-MINMATCH)
    {
        LZ4_putPosition(p, dict, byU32, base);
        p+=3;
    }

    return dict->dictSize;
}


static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src)
{
    if ((LZ4_dict->currentOffset > 0x80000000) ||
        ((size_t)LZ4_dict->currentOffset > (size_t)src))   /* address space overflow */
    {
        /* rescale hash table */
        U32 delta = LZ4_dict->currentOffset - 64 KB;
        const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize;
        int i;
        for (i=0; i<HASH_SIZE_U32; i++)
        {
            if (LZ4_dict->hashTable[i] < delta) LZ4_dict->hashTable[i]=0;
            else LZ4_dict->hashTable[i] -= delta;
        }
        LZ4_dict->currentOffset = 64 KB;
        if (LZ4_dict->dictSize > 64 KB) LZ4_dict->dictSize = 64 KB;
        LZ4_dict->dictionary = dictEnd - LZ4_dict->dictSize;
    }
}


FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* source, char* dest, int inputSize,
                                                int maxOutputSize, limitedOutput_directive limit)
{
    LZ4_stream_t_internal* streamPtr = (LZ4_stream_t_internal*)LZ4_stream;
    const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;

    const BYTE* smallest = (const BYTE*) source;
    if (streamPtr->initCheck) return 0;   /* Uninitialized structure detected */
    if ((streamPtr->dictSize>0) && (smallest>dictEnd)) smallest = dictEnd;
    LZ4_renormDictT(streamPtr, smallest);

    /* Check overlapping input/dictionary space */
    {
        const BYTE* sourceEnd = (const BYTE*) source + inputSize;
        if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd))
        {
            streamPtr->dictSize = (U32)(dictEnd - sourceEnd);
            if (streamPtr->dictSize > 64 KB) streamPtr->dictSize = 64 KB;
            if (streamPtr->dictSize < 4) streamPtr->dictSize = 0;
            streamPtr->dictionary = dictEnd - streamPtr->dictSize;
        }
    }

    /* prefix mode : source data follows dictionary */
    if (dictEnd == (const BYTE*)source)
    {
        int result;
        if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
            result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, withPrefix64k, dictSmall);
        else
            result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, withPrefix64k, noDictIssue);
        streamPtr->dictSize += (U32)inputSize;
        streamPtr->currentOffset += (U32)inputSize;
        return result;
    }

    /* external dictionary mode */
    {
        int result;
        if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
            result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, usingExtDict, dictSmall);
        else
            result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, usingExtDict, noDictIssue);
        streamPtr->dictionary = (const BYTE*)source;
        streamPtr->dictSize = (U32)inputSize;
        streamPtr->currentOffset += (U32)inputSize;
        return result;
    }
}

int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize)
{
    return LZ4_compress_continue_generic(LZ4_stream, source, dest, inputSize, 0, notLimited);
}

int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize)
{
    return LZ4_compress_continue_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput);
}


/* Hidden debug function, to force separate dictionary mode */
int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int inputSize)
{
    LZ4_stream_t_internal* streamPtr = (LZ4_stream_t_internal*)LZ4_dict;
    int result;
    const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;

    const BYTE* smallest = dictEnd;
    if (smallest > (const BYTE*) source) smallest = (const BYTE*) source;
    LZ4_renormDictT((LZ4_stream_t_internal*)LZ4_dict, smallest);

    result = LZ4_compress_generic(LZ4_dict, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue);

    streamPtr->dictionary = (const BYTE*)source;
    streamPtr->dictSize = (U32)inputSize;
    streamPtr->currentOffset += (U32)inputSize;

    return result;
}


int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
{
    LZ4_stream_t_internal* dict = (LZ4_stream_t_internal*) LZ4_dict;
    const BYTE* previousDictEnd = dict->dictionary + dict->dictSize;

    if ((U32)dictSize > 64 KB) dictSize = 64 KB;   /* useless to define a dictionary > 64 KB */
    if ((U32)dictSize > dict->dictSize) dictSize = dict->dictSize;

    memmove(safeBuffer, previousDictEnd - dictSize, dictSize);

    dict->dictionary = (const BYTE*)safeBuffer;
    dict->dictSize = (U32)dictSize;

    return dictSize;
}



/*******************************
*  Decompression functions
*******************************/
/*
 * This generic decompression function cover all use cases.
 * It shall be instantiated several times, using different sets of directives
 * Note that it is essential this generic function is really inlined,
 * in order to remove useless branches during compilation optimization.
 */
FORCE_INLINE int LZ4_decompress_generic(
                 const char* const source,
                 char* const dest,
                 int inputSize,
                 int outputSize,         /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */

                 int endOnInput,         /* endOnOutputSize, endOnInputSize */
                 int partialDecoding,    /* full, partial */
                 int targetOutputSize,   /* only used if partialDecoding==partial */
                 int dict,               /* noDict, withPrefix64k, usingExtDict */
                 const BYTE* const lowPrefix,  /* == dest if dict == noDict */
                 const BYTE* const dictStart,  /* only if dict==usingExtDict */
                 const size_t dictSize         /* note : = 0 if noDict */
                 )
{
    /* Local Variables */
    const BYTE* restrict ip = (const BYTE*) source;
    const BYTE* const iend = ip + inputSize;

    BYTE* op = (BYTE*) dest;
    BYTE* const oend = op + outputSize;
    BYTE* cpy;
    BYTE* oexit = op + targetOutputSize;
    const BYTE* const lowLimit = lowPrefix - dictSize;

    const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize;
    const size_t dec32table[] = {4, 1, 2, 1, 4, 4, 4, 4};
    const size_t dec64table[] = {0, 0, 0, (size_t)-1, 0, 1, 2, 3};

    const int safeDecode = (endOnInput==endOnInputSize);
    const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB)));


    /* Special cases */
    if ((partialDecoding) && (oexit> oend-MFLIMIT)) oexit = oend-MFLIMIT;                         /* targetOutputSize too high => decode everything */
    if ((endOnInput) && (unlikely(outputSize==0))) return ((inputSize==1) && (*ip==0)) ? 0 : -1;  /* Empty output buffer */
    if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1);


    /* Main Loop */
    while (1)
    {
        unsigned token;
        size_t length;
        const BYTE* match;

        /* get literal length */
        token = *ip++;
        if ((length=(token>>ML_BITS)) == RUN_MASK)
        {
            unsigned s;
            do
            {
                s = *ip++;
                length += s;
            }
            while (likely((endOnInput)?ip<iend-RUN_MASK:1) && (s==255));
            if ((safeDecode) && unlikely((size_t)(op+length)<(size_t)(op))) goto _output_error;   /* overflow detection */
            if ((safeDecode) && unlikely((size_t)(ip+length)<(size_t)(ip))) goto _output_error;   /* overflow detection */
        }

        /* copy literals */
        cpy = op+length;
        if (((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) )
            || ((!endOnInput) && (cpy>oend-COPYLENGTH)))
        {
            if (partialDecoding)
            {
                if (cpy > oend) goto _output_error;                           /* Error : write attempt beyond end of output buffer */
                if ((endOnInput) && (ip+length > iend)) goto _output_error;   /* Error : read attempt beyond end of input buffer */
            }
            else
            {
                if ((!endOnInput) && (cpy != oend)) goto _output_error;       /* Error : block decoding must stop exactly there */
                if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error;   /* Error : input must be consumed */
            }
            memcpy(op, ip, length);
            ip += length;
            op += length;
            break;     /* Necessarily EOF, due to parsing restrictions */
        }
        LZ4_wildCopy(op, ip, cpy);
        ip += length; op = cpy;

        /* get offset */
        match = cpy - LZ4_readLE16(ip); ip+=2;
        if ((checkOffset) && (unlikely(match < lowLimit))) goto _output_error;   /* Error : offset outside destination buffer */

        /* get matchlength */
        length = token & ML_MASK;
        if (length == ML_MASK)
        {
            unsigned s;
            do
            {
                if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error;
                s = *ip++;
                length += s;
            } while (s==255);
            if ((safeDecode) && unlikely((size_t)(op+length)<(size_t)op)) goto _output_error;   /* overflow detection */
        }
        length += MINMATCH;

        /* check external dictionary */
        if ((dict==usingExtDict) && (match < lowPrefix))
        {
            if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error;   /* doesn't respect parsing restriction */

            if (length <= (size_t)(lowPrefix-match))
            {
                /* match can be copied as a single segment from external dictionary */
                match = dictEnd - (lowPrefix-match);
                memcpy(op, match, length);
                op += length;
            }
            else
            {
                /* match encompass external dictionary and current segment */
                size_t copySize = (size_t)(lowPrefix-match);
                memcpy(op, dictEnd - copySize, copySize);
                op += copySize;
                copySize = length - copySize;
                if (copySize > (size_t)(op-lowPrefix))   /* overlap within current segment */
                {
                    BYTE* const endOfMatch = op + copySize;
                    const BYTE* copyFrom = lowPrefix;
                    while (op < endOfMatch) *op++ = *copyFrom++;
                }
                else
                {
                    memcpy(op, lowPrefix, copySize);
                    op += copySize;
                }
            }
            continue;
        }

        /* copy repeated sequence */
        cpy = op + length;
        if (unlikely((op-match)<8))
        {
            const size_t dec64 = dec64table[op-match];
            op[0] = match[0];
            op[1] = match[1];
            op[2] = match[2];
            op[3] = match[3];
            match += dec32table[op-match];
            LZ4_copy4(op+4, match);
            op += 8; match -= dec64;
        } else { LZ4_copy8(op, match); op+=8; match+=8; }

        if (unlikely(cpy>oend-12))
        {
            if (cpy > oend-LASTLITERALS) goto _output_error;    /* Error : last LASTLITERALS bytes must be literals */
            if (op < oend-8)
            {
                LZ4_wildCopy(op, match, oend-8);
                match += (oend-8) - op;
                op = oend-8;
            }
            while (op<cpy) *op++ = *match++;
        }
        else
            LZ4_wildCopy(op, match, cpy);
        op=cpy;   /* correction */
    }

    /* end of decoding */
    if (endOnInput)
       return (int) (((char*)op)-dest);     /* Nb of output bytes decoded */
    else
       return (int) (((char*)ip)-source);   /* Nb of input bytes read */

    /* Overflow error detected */
_output_error:
    return (int) (-(((char*)ip)-source))-1;
}


int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize)
{
    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, (BYTE*)dest, NULL, 0);
}

int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize)
{
    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, (BYTE*)dest, NULL, 0);
}

int LZ4_decompress_fast(const char* source, char* dest, int originalSize)
{
    return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)(dest - 64 KB), NULL, 64 KB);
}


/* streaming decompression functions */

typedef struct
{
    BYTE* externalDict;
    size_t extDictSize;
    BYTE* prefixEnd;
    size_t prefixSize;
} LZ4_streamDecode_t_internal;

/*
 * If you prefer dynamic allocation methods,
 * LZ4_createStreamDecode()
 * provides a pointer (void*) towards an initialized LZ4_streamDecode_t structure.
 */
LZ4_streamDecode_t* LZ4_createStreamDecode(void)
{
    LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOCATOR(1, sizeof(LZ4_streamDecode_t));
    return lz4s;
}

int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
{
    FREEMEM(LZ4_stream);
    return 0;
}

/*
 * LZ4_setStreamDecode
 * Use this function to instruct where to find the dictionary
 * This function is not necessary if previous data is still available where it was decoded.
 * Loading a size of 0 is allowed (same effect as no dictionary).
 * Return : 1 if OK, 0 if error
 */
int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize)
{
    LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode;
    lz4sd->prefixSize = (size_t) dictSize;
    lz4sd->prefixEnd = (BYTE*) dictionary + dictSize;
    lz4sd->externalDict = NULL;
    lz4sd->extDictSize  = 0;
    return 1;
}

/*
*_continue() :
    These decoding functions allow decompression of multiple blocks in "streaming" mode.
    Previously decoded blocks must still be available at the memory position where they were decoded.
    If it's not possible, save the relevant part of decoded data into a safe buffer,
    and indicate where it stands using LZ4_setStreamDecode()
*/
int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize)
{
    LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode;
    int result;

    if (lz4sd->prefixEnd == (BYTE*)dest)
    {
        result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
                                        endOnInputSize, full, 0,
                                        usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
        if (result <= 0) return result;
        lz4sd->prefixSize += result;
        lz4sd->prefixEnd  += result;
    }
    else
    {
        lz4sd->extDictSize = lz4sd->prefixSize;
        lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
        result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
                                        endOnInputSize, full, 0,
                                        usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize);
        if (result <= 0) return result;
        lz4sd->prefixSize = result;
        lz4sd->prefixEnd  = (BYTE*)dest + result;
    }

    return result;
}

int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize)
{
    LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode;
    int result;

    if (lz4sd->prefixEnd == (BYTE*)dest)
    {
        result = LZ4_decompress_generic(source, dest, 0, originalSize,
                                        endOnOutputSize, full, 0,
                                        usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
        if (result <= 0) return result;
        lz4sd->prefixSize += originalSize;
        lz4sd->prefixEnd  += originalSize;
    }
    else
    {
        lz4sd->extDictSize = lz4sd->prefixSize;
        lz4sd->externalDict = (BYTE*)dest - lz4sd->extDictSize;
        result = LZ4_decompress_generic(source, dest, 0, originalSize,
                                        endOnOutputSize, full, 0,
                                        usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize);
        if (result <= 0) return result;
        lz4sd->prefixSize = originalSize;
        lz4sd->prefixEnd  = (BYTE*)dest + originalSize;
    }

    return result;
}


/*
Advanced decoding functions :
*_usingDict() :
    These decoding functions work the same as "_continue" ones,
    the dictionary must be explicitly provided within parameters
*/

FORCE_INLINE int LZ4_decompress_usingDict_generic(const char* source, char* dest, int compressedSize, int maxOutputSize, int safe, const char* dictStart, int dictSize)
{
    if (dictSize==0)
        return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest, NULL, 0);
    if (dictStart+dictSize == dest)
    {
        if (dictSize >= (int)(64 KB - 1))
            return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, withPrefix64k, (BYTE*)dest-64 KB, NULL, 0);
        return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest-dictSize, NULL, 0);
    }
    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, usingExtDict, (BYTE*)dest, (BYTE*)dictStart, dictSize);
}

int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
{
    return LZ4_decompress_usingDict_generic(source, dest, compressedSize, maxOutputSize, 1, dictStart, dictSize);
}

int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize)
{
    return LZ4_decompress_usingDict_generic(source, dest, 0, originalSize, 0, dictStart, dictSize);
}

/* debug function */
int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
{
    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, (BYTE*)dest, (BYTE*)dictStart, dictSize);
}


/***************************************************
*  Obsolete Functions
***************************************************/
/*
These function names are deprecated and should no longer be used.
They are only provided here for compatibility with older user programs.
- LZ4_uncompress is totally equivalent to LZ4_decompress_fast
- LZ4_uncompress_unknownOutputSize is totally equivalent to LZ4_decompress_safe
*/
int LZ4_uncompress (const char* source, char* dest, int outputSize) { return LZ4_decompress_fast(source, dest, outputSize); }
int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) { return LZ4_decompress_safe(source, dest, isize, maxOutputSize); }


/* Obsolete Streaming functions */

int LZ4_sizeofStreamState() { return LZ4_STREAMSIZE; }

static void LZ4_init(LZ4_stream_t_internal* lz4ds, const BYTE* base)
{
    MEM_INIT(lz4ds, 0, LZ4_STREAMSIZE);
    lz4ds->bufferStart = base;
}

int LZ4_resetStreamState(void* state, const char* inputBuffer)
{
    if ((((size_t)state) & 3) != 0) return 1;   /* Error : pointer is not aligned on 4-bytes boundary */
    LZ4_init((LZ4_stream_t_internal*)state, (const BYTE*)inputBuffer);
    return 0;
}

void* LZ4_create (const char* inputBuffer)
{
    void* lz4ds = ALLOCATOR(8, LZ4_STREAMSIZE_U64);
    LZ4_init ((LZ4_stream_t_internal*)lz4ds, (const BYTE*)inputBuffer);
    return lz4ds;
}

char* LZ4_slideInputBuffer (void* LZ4_Data)
{
    LZ4_stream_t_internal* ctx = (LZ4_stream_t_internal*)LZ4_Data;
    int dictSize = LZ4_saveDict((LZ4_stream_t*)ctx, (char*)ctx->bufferStart, 64 KB);
    return (char*)(ctx->bufferStart + dictSize);
}

/*  Obsolete compresson functions using User-allocated state */

int LZ4_sizeofState() { return LZ4_STREAMSIZE; }

int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize)
{
    if (((size_t)(state)&3) != 0) return 0;   /* Error : state is not aligned on 4-bytes boundary */
    MEM_INIT(state, 0, LZ4_STREAMSIZE);

    if (inputSize < LZ4_64Klimit)
        return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue);
    else
        return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue);
}

int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize)
{
    if (((size_t)(state)&3) != 0) return 0;   /* Error : state is not aligned on 4-bytes boundary */
    MEM_INIT(state, 0, LZ4_STREAMSIZE);

    if (inputSize < LZ4_64Klimit)
        return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue);
    else
        return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue);
}

/* Obsolete streaming decompression functions */

int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize)
{
    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB);
}

int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize)
{
    return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB);
}

#endif   /* LZ4_COMMONDEFS_ONLY */