summaryrefslogtreecommitdiffstats
path: root/lib/lz4.c
blob: cee85ec8916a676d6497771720f40e0a5fdf8431 (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
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
/*
   LZ4 - Fast LZ compression algorithm
   Copyright (C) 2011-2017, 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://www.lz4.org
    - LZ4 source repository : https://github.com/lz4/lz4
*/


/*-************************************
*  Tuning parameters
**************************************/
/*
 * LZ4_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()).
 */
#ifndef LZ4_HEAPMODE
#  define LZ4_HEAPMODE 0
#endif

/*
 * ACCELERATION_DEFAULT :
 * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0
 */
#define ACCELERATION_DEFAULT 1


/*-************************************
*  CPU Feature Detection
**************************************/
/* LZ4_FORCE_MEMORY_ACCESS
 * By default, access to unaligned memory is controlled by `memcpy()`, which is safe and portable.
 * Unfortunately, on some target/compiler combinations, the generated assembly is sub-optimal.
 * The below switch allow to select different access method for improved performance.
 * Method 0 (default) : use `memcpy()`. Safe and portable.
 * Method 1 : `__packed` statement. It depends on compiler extension (ie, not portable).
 *            This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`.
 * Method 2 : direct access. This method is portable but violate C standard.
 *            It can generate buggy code on targets which assembly generation depends on alignment.
 *            But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6)
 * See https://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details.
 * Prefer these methods in priority order (0 > 1 > 2)
 */
#ifndef LZ4_FORCE_MEMORY_ACCESS   /* can be defined externally */
#  if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) )
#    define LZ4_FORCE_MEMORY_ACCESS 2
#  elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || defined(__GNUC__)
#    define LZ4_FORCE_MEMORY_ACCESS 1
#  endif
#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



/*-************************************
*  Dependency
**************************************/
#include "lz4.h"
/* see also "memory routines" below */


/*-************************************
*  Compiler Options
**************************************/
#ifdef _MSC_VER    /* Visual Studio */
#  include <intrin.h>
#  pragma warning(disable : 4127)        /* disable: C4127: conditional expression is constant */
#  pragma warning(disable : 4293)        /* disable: C4293: too large shift (32-bits) */
#endif  /* _MSC_VER */

#ifndef LZ4_FORCE_INLINE
#  ifdef _MSC_VER    /* Visual Studio */
#    define LZ4_FORCE_INLINE static __forceinline
#  else
#    if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   /* C99 */
#      ifdef __GNUC__
#        define LZ4_FORCE_INLINE static inline __attribute__((always_inline))
#      else
#        define LZ4_FORCE_INLINE static inline
#      endif
#    else
#      define LZ4_FORCE_INLINE static
#    endif /* __STDC_VERSION__ */
#  endif  /* _MSC_VER */
#endif /* LZ4_FORCE_INLINE */

/* LZ4_FORCE_O2_GCC_PPC64LE and LZ4_FORCE_O2_INLINE_GCC_PPC64LE
 * Gcc on ppc64le generates an unrolled SIMDized loop for LZ4_wildCopy,
 * together with a simple 8-byte copy loop as a fall-back path.
 * However, this optimization hurts the decompression speed by >30%,
 * because the execution does not go to the optimized loop
 * for typical compressible data, and all of the preamble checks
 * before going to the fall-back path become useless overhead.
 * This optimization happens only with the -O3 flag, and -O2 generates
 * a simple 8-byte copy loop.
 * With gcc on ppc64le, all of the LZ4_decompress_* and LZ4_wildCopy
 * functions are annotated with __attribute__((optimize("O2"))),
 * and also LZ4_wildCopy is forcibly inlined, so that the O2 attribute
 * of LZ4_wildCopy does not affect the compression speed.
 */
#if defined(__PPC64__) && defined(__LITTLE_ENDIAN__) && defined(__GNUC__)
#  define LZ4_FORCE_O2_GCC_PPC64LE __attribute__((optimize("O2")))
#  define LZ4_FORCE_O2_INLINE_GCC_PPC64LE __attribute__((optimize("O2"))) LZ4_FORCE_INLINE
#else
#  define LZ4_FORCE_O2_GCC_PPC64LE
#  define LZ4_FORCE_O2_INLINE_GCC_PPC64LE static
#endif

#if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__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 ALLOC(s) malloc(s)
#define ALLOC_AND_ZERO(s) calloc(1,s)
#define FREEMEM        free
#include <string.h>   /* memset, memcpy */
#define MEM_INIT       memset


/*-************************************
*  Basic Types
**************************************/
#if defined(__cplusplus) || (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;
  typedef uintptr_t uptrval;
#else
  typedef unsigned char       BYTE;
  typedef unsigned short      U16;
  typedef unsigned int        U32;
  typedef   signed int        S32;
  typedef unsigned long long  U64;
  typedef size_t              uptrval;   /* generally true, except OpenVMS-64 */
#endif

#if defined(__x86_64__)
  typedef U64    reg_t;   /* 64-bits in x32 mode */
#else
  typedef size_t reg_t;   /* 32-bits in x32 mode */
#endif

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


#if defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==2)
/* lie to the compiler about data alignment; use with caution */

static U16 LZ4_read16(const void* memPtr) { return *(const U16*) memPtr; }
static U32 LZ4_read32(const void* memPtr) { return *(const U32*) memPtr; }
static reg_t LZ4_read_ARCH(const void* memPtr) { return *(const reg_t*) memPtr; }

static void LZ4_write16(void* memPtr, U16 value) { *(U16*)memPtr = value; }
static void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; }

#elif defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==1)

/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */
/* currently only defined for gcc and icc */
typedef union { U16 u16; U32 u32; reg_t uArch; } __attribute__((packed)) unalign;

static U16 LZ4_read16(const void* ptr) { return ((const unalign*)ptr)->u16; }
static U32 LZ4_read32(const void* ptr) { return ((const unalign*)ptr)->u32; }
static reg_t LZ4_read_ARCH(const void* ptr) { return ((const unalign*)ptr)->uArch; }

static void LZ4_write16(void* memPtr, U16 value) { ((unalign*)memPtr)->u16 = value; }
static void LZ4_write32(void* memPtr, U32 value) { ((unalign*)memPtr)->u32 = value; }

#else  /* safe and portable access through memcpy() */

static U16 LZ4_read16(const void* memPtr)
{
    U16 val; memcpy(&val, memPtr, sizeof(val)); return val;
}

static U32 LZ4_read32(const void* memPtr)
{
    U32 val; memcpy(&val, memPtr, sizeof(val)); return val;
}

static reg_t LZ4_read_ARCH(const void* memPtr)
{
    reg_t val; memcpy(&val, memPtr, sizeof(val)); return val;
}

static void LZ4_write16(void* memPtr, U16 value)
{
    memcpy(memPtr, &value, sizeof(value));
}

static void LZ4_write32(void* memPtr, U32 value)
{
    memcpy(memPtr, &value, sizeof(value));
}

#endif /* LZ4_FORCE_MEMORY_ACCESS */


static U16 LZ4_readLE16(const void* memPtr)
{
    if (LZ4_isLittleEndian()) {
        return LZ4_read16(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_isLittleEndian()) {
        LZ4_write16(memPtr, value);
    } else {
        BYTE* p = (BYTE*)memPtr;
        p[0] = (BYTE) value;
        p[1] = (BYTE)(value>>8);
    }
}

/* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */
LZ4_FORCE_O2_INLINE_GCC_PPC64LE
void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd)
{
    BYTE* d = (BYTE*)dstPtr;
    const BYTE* s = (const BYTE*)srcPtr;
    BYTE* const e = (BYTE*)dstEnd;

    do { memcpy(d,s,8); d+=8; s+=8; } while (d<e);
}


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

#define WILDCOPYLENGTH 8
#define LASTLITERALS 5
#define MFLIMIT (WILDCOPYLENGTH+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)


/*-************************************
*  Error detection
**************************************/
#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=1)
#  include <assert.h>
#else
#  ifndef assert
#    define assert(condition) ((void)0)
#  endif
#endif

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

#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2)
#  include <stdio.h>
static int g_debuglog_enable = 1;
#  define DEBUGLOG(l, ...) {                                  \
                if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) {  \
                    fprintf(stderr, __FILE__ ": ");           \
                    fprintf(stderr, __VA_ARGS__);             \
                    fprintf(stderr, " \n");                   \
            }   }
#else
#  define DEBUGLOG(l, ...)      {}    /* disabled */
#endif


/*-************************************
*  Common functions
**************************************/
static unsigned LZ4_NbCommonBytes (reg_t val)
{
    if (LZ4_isLittleEndian()) {
        if (sizeof(val)==8) {
#       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(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !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(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !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 (sizeof(val)==8) {   /* 64-bits */
#       if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
            unsigned long r = 0;
            _BitScanReverse64( &r, val );
            return (unsigned)(r>>3);
#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
            return (__builtin_clzll((U64)val) >> 3);
#       else
            static const U32 by32 = sizeof(val)*4;  /* 32 on 64 bits (goal), 16 on 32 bits.
                Just to avoid some static analyzer complaining about shift by 32 on 32-bits target.
                Note that this code path is never triggered in 32-bits mode. */
            unsigned r;
            if (!(val>>by32)) { r=4; } else { r=0; val>>=by32; }
            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(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
            return (__builtin_clz((U32)val) >> 3);
#       else
            unsigned r;
            if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
            r += (!val);
            return r;
#       endif
        }
    }
}

#define STEPSIZE sizeof(reg_t)
LZ4_FORCE_INLINE
unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit)
{
    const BYTE* const pStart = pIn;

    if (likely(pIn < pInLimit-(STEPSIZE-1))) {
        reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
        if (!diff) {
            pIn+=STEPSIZE; pMatch+=STEPSIZE;
        } else {
            return LZ4_NbCommonBytes(diff);
    }   }

    while (likely(pIn < pInLimit-(STEPSIZE-1))) {
        reg_t const 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 ((STEPSIZE==8) && (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
**************************************/
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 Structures and types
**************************************/
typedef enum { notLimited = 0, limitedOutput = 1 } limitedOutput_directive;
typedef enum { clearedTable = 0, byPtr, byU32, byU16 } tableType_t;

/**
 * This enum distinguishes several different modes of accessing previous
 * content in the stream.
 *
 * - noDict        : There is no preceding content.
 * - withPrefix64k : Table entries up to ctx->dictSize before the current blob
 *                   blob being compressed are valid and refer to the preceding
 *                   content (of length ctx->dictSize), which is available
 *                   contiguously preceding in memory the content currently
 *                   being compressed.
 * - usingExtDict  : Like withPrefix64k, but the preceding content is somewhere
 *                   else in memory, starting at ctx->dictionary with length
 *                   ctx->dictSize.
 * - usingDictCtx  : Like usingExtDict, but everything concerning the preceding
 *                   content is in a separate context, pointed to by
 *                   ctx->dictCtx. ctx->dictionary, ctx->dictSize, and table
 *                   entries in the current context that refer to positions
 *                   preceding the beginning of the current compression are
 *                   ignored. Instead, ctx->dictCtx->dictionary and ctx->dictCtx
 *                   ->dictSize describe the location and size of the preceding
 *                   content, and matches are found by looking in the ctx
 *                   ->dictCtx->hashTable.
 */
typedef enum { noDict = 0, withPrefix64k, usingExtDict, usingDictCtx } 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;


/*-************************************
*  Local Utils
**************************************/
int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; }
const char* LZ4_versionString(void) { return LZ4_VERSION_STRING; }
int LZ4_compressBound(int isize)  { return LZ4_COMPRESSBOUND(isize); }
int LZ4_sizeofState() { return LZ4_STREAMSIZE; }


/*-******************************
*  Compression functions
********************************/
static U32 LZ4_hash4(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_hash5(U64 sequence, tableType_t const tableType)
{
    static const U64 prime5bytes = 889523592379ULL;
    static const U64 prime8bytes = 11400714785074694791ULL;
    const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG;
    if (LZ4_isLittleEndian())
        return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog));
    else
        return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog));
}

LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType)
{
    if ((sizeof(reg_t)==8) && (tableType != byU16)) return LZ4_hash5(LZ4_read_ARCH(p), tableType);
    return LZ4_hash4(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 clearedTable: { /* illegal! */ assert(0); return; }
    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; }
    }
}

LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
{
    U32 const h = LZ4_hashPosition(p, tableType);
    LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase);
}

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

LZ4_FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, const void* tableBase, tableType_t tableType, const BYTE* srcBase)
{
    U32 const h = LZ4_hashPosition(p, tableType);
    return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase);
}

LZ4_FORCE_INLINE void LZ4_prepareTable(
        LZ4_stream_t_internal* const cctx,
        const int inputSize,
        const tableType_t tableType) {
    /* If the table hasn't been used, it's guaranteed to be zeroed out, and is
     * therefore safe to use no matter what mode we're in. Otherwise, we figure
     * out if it's safe to leave as is or whether it needs to be reset.
     */
    if (cctx->tableType != clearedTable) {
        if (cctx->tableType != tableType
          || (tableType == byU16 && cctx->currentOffset + inputSize >= 0xFFFFU)
          || (tableType == byU32 && cctx->currentOffset > 1 GB)
          || tableType == byPtr
          || inputSize >= 4 KB)
        {
            DEBUGLOG(4, "Resetting table in %p", cctx);
            MEM_INIT(cctx->hashTable, 0, LZ4_HASHTABLESIZE);
            cctx->currentOffset = 0;
            cctx->tableType = clearedTable;
        }
    }

    /* Adding a gap, so all previous entries are > MAX_DISTANCE back, is faster
     * than compressing without a gap. However, compressing with
     * currentOffset == 0 is faster still, so we preserve that case.
     */
    if (cctx->currentOffset != 0 && tableType == byU32) {
        cctx->currentOffset += 64 KB;
    }

    /* Finally, clear history */
    cctx->dictCtx = NULL;
    cctx->dictionary = NULL;
    cctx->dictSize = 0;
}

/** LZ4_compress_generic() :
    inlined, to ensure branches are decided at compilation time */
LZ4_FORCE_INLINE int LZ4_compress_generic(
                 LZ4_stream_t_internal* const cctx,
                 const char* const source,
                 char* const dest,
                 const int inputSize,
                 const int maxOutputSize,
                 const limitedOutput_directive outputLimited,
                 const tableType_t tableType,
                 const dict_directive dictDirective,
                 const dictIssue_directive dictIssue,
                 const U32 acceleration)
{
    const BYTE* ip = (const BYTE*) source;

    size_t currentOffset = cctx->currentOffset;
    const BYTE* base = (const BYTE*) source - currentOffset;
    const BYTE* lowLimit;

    const LZ4_stream_t_internal* dictCtx = (const LZ4_stream_t_internal*) cctx->dictCtx;
    const BYTE* const dictionary =
        dictDirective == usingDictCtx ? dictCtx->dictionary : cctx->dictionary;
    const U32 dictSize =
        dictDirective == usingDictCtx ? dictCtx->dictSize : cctx->dictSize;

    const BYTE* const lowRefLimit = (const BYTE*) source - dictSize;
    const BYTE* const dictEnd = dictionary + dictSize;
    const BYTE* anchor = (const BYTE*) source;
    const BYTE* const iend = ip + inputSize;
    const BYTE* const mflimitPlusOne = iend - MFLIMIT + 1;
    const BYTE* const matchlimit = iend - LASTLITERALS;

    /* the dictCtx currentOffset is indexed on the start of the dictionary,
     * while a dictionary in the current context precedes the currentOffset */
    const BYTE* dictBase = dictDirective == usingDictCtx ?
        (const BYTE*) source - dictCtx->currentOffset :
        (const BYTE*) source - dictSize - currentOffset;
    const ptrdiff_t dictDelta = dictionary ? dictEnd - (const BYTE*) source : 0;
    const BYTE* dictLowLimit;

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

    U32 forwardH;

    /* Init conditions */
    if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0;   /* Unsupported inputSize, too large (or negative) */

    lowLimit = (const BYTE*)source - (dictDirective == withPrefix64k ? dictSize : 0);
    dictLowLimit = dictionary ? dictionary : lowLimit;

    if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0;   /* Size too large (not within 64K limit) */

    /* Update context state */
    if (dictDirective == usingDictCtx) {
        /* Subsequent linked blocks can't use the dictionary. */
        /* Instead, they use the block we just compressed. */
        cctx->dictCtx = NULL;
        cctx->dictSize = (U32)inputSize;
    } else {
        cctx->dictSize += (U32)inputSize;
    }
    cctx->currentOffset += (U32)inputSize;
    cctx->tableType = tableType;

    if (inputSize<LZ4_minLength) goto _last_literals;                  /* Input too small, no compression (all literals) */

    /* First Byte */
    LZ4_putPosition(ip, cctx->hashTable, tableType, base);
    ip++; forwardH = LZ4_hashPosition(ip, tableType);

    /* Main Loop */
    for ( ; ; ) {
        ptrdiff_t refDelta = 0;
        const BYTE* match;
        BYTE* token;

        /* Find a match */
        {   const BYTE* forwardIp = ip;
            unsigned step = 1;
            unsigned searchMatchNb = acceleration << LZ4_skipTrigger;
            do {
                U32 const h = forwardH;
                ip = forwardIp;
                forwardIp += step;
                step = (searchMatchNb++ >> LZ4_skipTrigger);

                if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals;
                assert(ip < mflimitPlusOne);

                match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base);
                if (dictDirective == usingDictCtx) {
                    if (match < (const BYTE*)source) {
                        /* there was no match, try the dictionary */
                        match = LZ4_getPosition(ip, dictCtx->hashTable, byU32, dictBase);
                        refDelta = dictDelta;
                        lowLimit = dictLowLimit;
                    } else {
                        refDelta = 0;
                        lowLimit = (const BYTE*)source;
                    }
                } else if (dictDirective==usingExtDict) {
                    if (match < (const BYTE*)source) {
                        refDelta = dictDelta;
                        lowLimit = dictLowLimit;
                    } else {
                        refDelta = 0;
                        lowLimit = (const BYTE*)source;
                }   }
                forwardH = LZ4_hashPosition(forwardIp, tableType);
                LZ4_putPositionOnHash(ip, h, cctx->hashTable, 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 Literals */
        {   unsigned const litLength = (unsigned)(ip - anchor);
            token = op++;
            if ((outputLimited) &&  /* Check output buffer overflow */
                (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)))
                return 0;
            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 matchCode;

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

            if ( outputLimited &&    /* Check output buffer overflow */
                (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) )
                return 0;
            if (matchCode >= ML_MASK) {
                *token += ML_MASK;
                matchCode -= ML_MASK;
                LZ4_write32(op, 0xFFFFFFFF);
                while (matchCode >= 4*255) {
                    op+=4;
                    LZ4_write32(op, 0xFFFFFFFF);
                    matchCode -= 4*255;
                }
                op += matchCode / 255;
                *op++ = (BYTE)(matchCode % 255);
            } else
                *token += (BYTE)(matchCode);
        }

        anchor = ip;

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

        /* Fill table */
        LZ4_putPosition(ip-2, cctx->hashTable, tableType, base);

        /* Test next position */
        match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);
        if (dictDirective == usingDictCtx) {
            if (match < (const BYTE*)source) {
                /* there was no match, try the dictionary */
                match = LZ4_getPosition(ip, dictCtx->hashTable, byU32, dictBase);
                refDelta = dictDelta;
                lowLimit = dictLowLimit;
            } else {
                refDelta = 0;
                lowLimit = (const BYTE*)source;
            }
        } else if (dictDirective==usingExtDict) {
            if (match < (const BYTE*)source) {
                refDelta = dictDelta;
                lowLimit = dictLowLimit;
            } else {
                refDelta = 0;
                lowLimit = (const BYTE*)source;
        }   }
        LZ4_putPosition(ip, cctx->hashTable, 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 */
    {   size_t const lastRun = (size_t)(iend - anchor);
        if ( (outputLimited) &&  /* Check output buffer overflow */
            ((op - (BYTE*)dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) )
            return 0;
        if (lastRun >= RUN_MASK) {
            size_t accumulator = lastRun - RUN_MASK;
            *op++ = RUN_MASK << ML_BITS;
            for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
            *op++ = (BYTE) accumulator;
        } else {
            *op++ = (BYTE)(lastRun<<ML_BITS);
        }
        memcpy(op, anchor, lastRun);
        op += lastRun;
    }

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


int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
{
    LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse;
    if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
    LZ4_resetStream((LZ4_stream_t*)state);
    if (maxOutputSize >= LZ4_compressBound(inputSize)) {
        if (inputSize < LZ4_64Klimit) {
            return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue, acceleration);
        } else {
            const tableType_t tableType = (sizeof(void*)==8) ? byU32 : byPtr;
            return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
        }
    } else {
        if (inputSize < LZ4_64Klimit) {;
            return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration);
        } else {
            const tableType_t tableType = (sizeof(void*)==8) ? byU32 : byPtr;
            return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration);
        }
    }
}

/**
 * LZ4_compress_fast_extState_fastReset() :
 * A variant of LZ4_compress_fast_extState().
 *
 * Using this variant avoids an expensive initialization step. It is only safe
 * to call if the state buffer is known to be correctly initialized already
 * (see comment in lz4.h on LZ4_resetStream_fast() for a definition of
 * "correctly initialized").
 */
int LZ4_compress_fast_extState_fastReset(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
{
    LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse;
    if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;

    if (maxOutputSize >= LZ4_compressBound(inputSize)) {
        if (inputSize < LZ4_64Klimit) {
            const tableType_t tableType = byU16;
            LZ4_prepareTable(ctx, inputSize, tableType);
            if (ctx->currentOffset) {
                return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, tableType, noDict, dictSmall, acceleration);
            } else {
                return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
            }
        } else {
            const tableType_t tableType = (sizeof(void*)==8) ? byU32 : byPtr;
            LZ4_prepareTable(ctx, inputSize, tableType);
            return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
        }
    } else {
        if (inputSize < LZ4_64Klimit) {
            const tableType_t tableType = byU16;
            LZ4_prepareTable(ctx, inputSize, tableType);
            if (ctx->currentOffset) {
                return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, noDict, dictSmall, acceleration);
            } else {
                return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration);
            }
        } else {
            const tableType_t tableType = (sizeof(void*)==8) ? byU32 : byPtr;
            LZ4_prepareTable(ctx, inputSize, tableType);
            return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration);
        }
    }
}


int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
{
    int result;
#if (LZ4_HEAPMODE)
    LZ4_stream_t* ctxPtr = ALLOC(sizeof(LZ4_stream_t));   /* malloc-calloc always properly aligned */
    if (ctxPtr == NULL) return 0;
#else
    LZ4_stream_t ctx;
    LZ4_stream_t* const ctxPtr = &ctx;
#endif
    result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration);

#if (LZ4_HEAPMODE)
    FREEMEM(ctxPtr);
#endif
    return result;
}


int LZ4_compress_default(const char* source, char* dest, int inputSize, int maxOutputSize)
{
    return LZ4_compress_fast(source, dest, inputSize, maxOutputSize, 1);
}


/* hidden debug function */
/* strangely enough, gcc generates faster code when this function is uncommented, even if unused */
int LZ4_compress_fast_force(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
{
    LZ4_stream_t ctx;
    LZ4_resetStream(&ctx);

    if (inputSize < LZ4_64Klimit)
        return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, byU16,                        noDict, noDictIssue, acceleration);
    else
        return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, sizeof(void*)==8 ? byU32 : byPtr, noDict, noDictIssue, acceleration);
}


/*-******************************
*  *_destSize() variant
********************************/

static int LZ4_compress_destSize_generic(
                       LZ4_stream_t_internal* const ctx,
                 const char* const src,
                       char* const dst,
                       int*  const srcSizePtr,
                 const int targetDstSize,
                 const tableType_t tableType)
{
    const BYTE* ip = (const BYTE*) src;
    const BYTE* base = (const BYTE*) src;
    const BYTE* lowLimit = (const BYTE*) src;
    const BYTE* anchor = ip;
    const BYTE* const iend = ip + *srcSizePtr;
    const BYTE* const mflimit = iend - MFLIMIT;
    const BYTE* const matchlimit = iend - LASTLITERALS;

    BYTE* op = (BYTE*) dst;
    BYTE* const oend = op + targetDstSize;
    BYTE* const oMaxLit = op + targetDstSize - 2 /* offset */ - 8 /* because 8+MINMATCH==MFLIMIT */ - 1 /* token */;
    BYTE* const oMaxMatch = op + targetDstSize - (LASTLITERALS + 1 /* token */);
    BYTE* const oMaxSeq = oMaxLit - 1 /* token */;

    U32 forwardH;


    /* Init conditions */
    if (targetDstSize < 1) return 0;                                     /* Impossible to store anything */
    if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) return 0;            /* Unsupported input size, too large (or negative) */
    if ((tableType == byU16) && (*srcSizePtr>=LZ4_64Klimit)) return 0;   /* Size too large (not within 64K limit) */
    if (*srcSizePtr<LZ4_minLength) goto _last_literals;                  /* Input too small, no compression (all literals) */

    /* First Byte */
    *srcSizePtr = 0;
    LZ4_putPosition(ip, ctx->hashTable, tableType, base);
    ip++; forwardH = LZ4_hashPosition(ip, tableType);

    /* Main Loop */
    for ( ; ; ) {
        const BYTE* match;
        BYTE* token;

        /* Find a match */
        {   const BYTE* forwardIp = ip;
            unsigned step = 1;
            unsigned searchMatchNb = 1 << LZ4_skipTrigger;

            do {
                U32 h = forwardH;
                ip = forwardIp;
                forwardIp += step;
                step = (searchMatchNb++ >> LZ4_skipTrigger);

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

                match = LZ4_getPositionOnHash(h, ctx->hashTable, tableType, base);
                forwardH = LZ4_hashPosition(forwardIp, tableType);
                LZ4_putPositionOnHash(ip, h, ctx->hashTable, tableType, base);

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

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

        /* Encode Literal length */
        {   unsigned litLength = (unsigned)(ip - anchor);
            token = op++;
            if (op + ((litLength+240)/255) + litLength > oMaxLit) {
                /* Not enough space for a last match */
                op--;
                goto _last_literals;
            }
            if (litLength>=RUN_MASK) {
                unsigned len = 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 */
        {   size_t matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);

            if (op + ((matchLength+240)/255) > oMaxMatch) {
                /* Match description too long : reduce it */
                matchLength = (15-1) + (oMaxMatch-op) * 255;
            }
            ip += MINMATCH + matchLength;

            if (matchLength>=ML_MASK) {
                *token += ML_MASK;
                matchLength -= ML_MASK;
                while (matchLength >= 255) { matchLength-=255; *op++ = 255; }
                *op++ = (BYTE)matchLength;
            }
            else *token += (BYTE)(matchLength);
        }

        anchor = ip;

        /* Test end of block */
        if (ip > mflimit) break;
        if (op > oMaxSeq) break;

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

        /* Test next position */
        match = LZ4_getPosition(ip, ctx->hashTable, tableType, base);
        LZ4_putPosition(ip, ctx->hashTable, tableType, base);
        if ( (match+MAX_DISTANCE>=ip)
            && (LZ4_read32(match)==LZ4_read32(ip)) )
        { token=op++; *token=0; goto _next_match; }

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

_last_literals:
    /* Encode Last Literals */
    {   size_t lastRunSize = (size_t)(iend - anchor);
        if (op + 1 /* token */ + ((lastRunSize+240)/255) /* litLength */ + lastRunSize /* literals */ > oend) {
            /* adapt lastRunSize to fill 'dst' */
            lastRunSize  = (oend-op) - 1;
            lastRunSize -= (lastRunSize+240)/255;
        }
        ip = anchor + lastRunSize;

        if (lastRunSize >= RUN_MASK) {
            size_t accumulator = lastRunSize - RUN_MASK;
            *op++ = RUN_MASK << ML_BITS;
            for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
            *op++ = (BYTE) accumulator;
        } else {
            *op++ = (BYTE)(lastRunSize<<ML_BITS);
        }
        memcpy(op, anchor, lastRunSize);
        op += lastRunSize;
    }

    /* End */
    *srcSizePtr = (int) (((const char*)ip)-src);
    return (int) (((char*)op)-dst);
}


static int LZ4_compress_destSize_extState (LZ4_stream_t* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize)
{
    LZ4_resetStream(state);

    if (targetDstSize >= LZ4_compressBound(*srcSizePtr)) {  /* compression success is guaranteed */
        return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, 1);
    } else {
        if (*srcSizePtr < LZ4_64Klimit)
            return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, byU16);
        else
            return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, sizeof(void*)==8 ? byU32 : byPtr);
    }
}


int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize)
{
#if (LZ4_HEAPMODE)
    LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));   /* malloc-calloc always properly aligned */
    if (ctx == NULL) return 0;
#else
    LZ4_stream_t ctxBody;
    LZ4_stream_t* ctx = &ctxBody;
#endif

    int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize);

#if (LZ4_HEAPMODE)
    FREEMEM(ctx);
#endif
    return result;
}



/*-******************************
*  Streaming functions
********************************/

LZ4_stream_t* LZ4_createStream(void)
{
    LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));
    LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal));    /* A compilation error here means LZ4_STREAMSIZE is not large enough */
    DEBUGLOG(4, "LZ4_createStream %p", lz4s);
    if (lz4s == NULL) return NULL;
    LZ4_resetStream(lz4s);
    return lz4s;
}

void LZ4_resetStream (LZ4_stream_t* LZ4_stream)
{
    DEBUGLOG(5, "LZ4_resetStream %p", LZ4_stream);
    MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t));
}

void LZ4_resetStream_fast(LZ4_stream_t* const ctx) {
    LZ4_prepareTable(&(ctx->internal_donotuse), 0, byU32);
}

int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
{
    if (!LZ4_stream) return 0;   /* support free on NULL */
    DEBUGLOG(5, "LZ4_freeStream %p", LZ4_stream);
    FREEMEM(LZ4_stream);
    return (0);
}


#define HASH_UNIT sizeof(reg_t)
int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
{
    LZ4_stream_t_internal* dict = &LZ4_dict->internal_donotuse;
    const tableType_t tableType = byU32;
    const BYTE* p = (const BYTE*)dictionary;
    const BYTE* const dictEnd = p + dictSize;
    const BYTE* base;

    DEBUGLOG(4, "LZ4_loadDict %p", LZ4_dict);

    LZ4_prepareTable(dict, 0, tableType);

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

    if (dictSize < (int)HASH_UNIT) {
        return 0;
    }

    while (p <= dictEnd-HASH_UNIT) {
        LZ4_putPosition(p, dict->hashTable, tableType, base);
        p+=3;
    }

    return dict->dictSize;
}

void LZ4_attach_dictionary(LZ4_stream_t *working_stream, const LZ4_stream_t *dictionary_stream) {
    working_stream->internal_donotuse.dictCtx = dictionary_stream != NULL ? &(dictionary_stream->internal_donotuse) : NULL;
}


static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src)
{
    if ((LZ4_dict->currentOffset > 0x80000000) ||
        ((uptrval)LZ4_dict->currentOffset > (uptrval)src)) {   /* address space overflow */
        /* rescale hash table */
        U32 const delta = LZ4_dict->currentOffset - 64 KB;
        const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize;
        int i;
        DEBUGLOG(4, "LZ4_renormDictT %p", LZ4_dict);
        for (i=0; i<LZ4_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;
    }
}


int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
{
    const tableType_t tableType = byU32;
    LZ4_stream_t_internal* streamPtr = &LZ4_stream->internal_donotuse;
    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);
    if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;

    /* 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) {
        if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
            return LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, withPrefix64k, dictSmall, acceleration);
        else
            return LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, withPrefix64k, noDictIssue, acceleration);
    }

    /* external dictionary mode */
    {   int result;
        if (streamPtr->dictCtx) {
            /* We depend here on the fact that dictCtx'es (produced by
             * LZ4_loadDict) guarantee that their tables contain no references
             * to offsets between dictCtx->currentOffset - 64 KB and
             * dictCtx->currentOffset - dictCtx->dictSize. This makes it safe
             * to use noDictIssue even when the dict isn't a full 64 KB.
             */
            if (inputSize > 4 KB) {
                /* For compressing large blobs, it is faster to pay the setup
                 * cost to copy the dictionary's tables into the active context,
                 * so that the compression loop is only looking in one table.
                 */
                memcpy(streamPtr, streamPtr->dictCtx, sizeof(LZ4_stream_t));
                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
            } else {
                /* If the current offset is zero, we will never look in the
                 * external dictionary context, since there is no value a table
                 * entry can take that indicate a miss. In that case, we need
                 * to bump the offset to something non-zero.
                 */
                if (streamPtr->currentOffset == 0) {
                    streamPtr->currentOffset = 64 KB;
                }
                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, usingDictCtx, noDictIssue, acceleration);
            }
        } else {
            if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) {
                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, usingExtDict, dictSmall, acceleration);
            } else {
                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
            }
        }
        streamPtr->dictionary = (const BYTE*)source;
        streamPtr->dictSize = (U32)inputSize;
        return result;
    }
}


/* Hidden debug function, to force external dictionary mode */
int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int inputSize)
{
    LZ4_stream_t_internal* streamPtr = &LZ4_dict->internal_donotuse;
    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(streamPtr, smallest);

    if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) {
        result = LZ4_compress_generic(streamPtr, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, dictSmall, 1);
    } else {
        result = LZ4_compress_generic(streamPtr, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1);
    }

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

    return result;
}


/*! LZ4_saveDict() :
 *  If previously compressed data block is not guaranteed to remain available at its memory location,
 *  save it into a safer place (char* safeBuffer).
 *  Note : you don't need to call LZ4_loadDict() afterwards,
 *         dictionary is immediately usable, you can therefore call LZ4_compress_fast_continue().
 *  Return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error.
 */
int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
{
    LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse;
    const BYTE* const 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
*******************************/
/*! LZ4_decompress_generic() :
 *  This generic decompression function covers all use cases.
 *  It shall be instantiated several times, using different sets of directives.
 *  Note that it is important for performance that this function really get inlined,
 *  in order to remove useless branches during compilation optimization.
 */
LZ4_FORCE_O2_GCC_PPC64LE
LZ4_FORCE_INLINE int LZ4_decompress_generic(
                 const char* const src,
                 char* const dst,
                 int srcSize,
                 int outputSize,         /* If endOnInput==endOnInputSize, this value is `dstCapacity` */

                 int endOnInput,         /* endOnOutputSize, endOnInputSize */
                 int partialDecoding,    /* full, partial */
                 int targetOutputSize,   /* only used if partialDecoding==partial */
                 int dict,               /* noDict, withPrefix64k, usingExtDict */
                 const BYTE* const lowPrefix,  /* always <= dst, == dst when no prefix */
                 const BYTE* const dictStart,  /* only if dict==usingExtDict */
                 const size_t dictSize         /* note : = 0 if noDict */
                 )
{
    const BYTE* ip = (const BYTE*) src;
    const BYTE* const iend = ip + srcSize;

    BYTE* op = (BYTE*) dst;
    BYTE* const oend = op + outputSize;
    BYTE* cpy;
    BYTE* oexit = op + targetOutputSize;

    const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize;
    const unsigned inc32table[8] = {0, 1, 2,  1,  0,  4, 4, 4};
    const int      dec64table[8] = {0, 0, 0, -1, -4,  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 => just decode everything */
    if ((endOnInput) && (unlikely(outputSize==0))) return ((srcSize==1) && (*ip==0)) ? 0 : -1;  /* Empty output buffer */
    if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1);

    /* Main Loop : decode sequences */
    while (1) {
        size_t length;
        const BYTE* match;
        size_t offset;

        unsigned const token = *ip++;

        /* shortcut for common case :
         * in most circumstances, we expect to decode small matches (<= 18 bytes) separated by few literals (<= 14 bytes).
         * this shortcut was tested on x86 and x64, where it improves decoding speed.
         * it has not yet been benchmarked on ARM, Power, mips, etc. */
        if (((ip + 14 /*maxLL*/ + 2 /*offset*/ <= iend)
          & (op + 14 /*maxLL*/ + 18 /*maxML*/ <= oend))
          & ((token < (15<<ML_BITS)) & ((token & ML_MASK) != 15)) ) {
            size_t const ll = token >> ML_BITS;
            size_t const off = LZ4_readLE16(ip+ll);
            const BYTE* const matchPtr = op + ll - off;  /* pointer underflow risk ? */
            if ((off >= 8) /* do not deal with overlapping matches */ & (matchPtr >= lowPrefix)) {
                size_t const ml = (token & ML_MASK) + MINMATCH;
                memcpy(op, ip, 16); op += ll; ip += ll + 2 /*offset*/;
                memcpy(op + 0, matchPtr + 0, 8);
                memcpy(op + 8, matchPtr + 8, 8);
                memcpy(op +16, matchPtr +16, 2);
                op += ml;
                continue;
            }
        }

        /* decode literal length */
        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((uptrval)(op)+length<(uptrval)(op))) goto _output_error;   /* overflow detection */
            if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(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-WILDCOPYLENGTH)) )
        {
            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 */
        offset = LZ4_readLE16(ip); ip+=2;
        match = op - offset;
        if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error;   /* Error : offset outside buffers */
        LZ4_write32(op, (U32)offset);   /* costs ~1%; silence an msan warning when offset==0 */

        /* get matchlength */
        length = token & ML_MASK;
        if (length == ML_MASK) {
            unsigned s;
            do {
                s = *ip++;
                if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error;
                length += s;
            } while (s==255);
            if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)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 */
                memmove(op, dictEnd - (lowPrefix-match), length);
                op += length;
            } else {
                /* match encompass external dictionary and current block */
                size_t const copySize = (size_t)(lowPrefix-match);
                size_t const restSize = length - copySize;
                memcpy(op, dictEnd - copySize, copySize);
                op += copySize;
                if (restSize > (size_t)(op-lowPrefix)) {  /* overlap copy */
                    BYTE* const endOfMatch = op + restSize;
                    const BYTE* copyFrom = lowPrefix;
                    while (op < endOfMatch) *op++ = *copyFrom++;
                } else {
                    memcpy(op, lowPrefix, restSize);
                    op += restSize;
            }   }
            continue;
        }

        /* copy match within block */
        cpy = op + length;
        if (unlikely(offset<8)) {
            op[0] = match[0];
            op[1] = match[1];
            op[2] = match[2];
            op[3] = match[3];
            match += inc32table[offset];
            memcpy(op+4, match, 4);
            match -= dec64table[offset];
        } else { memcpy(op, match, 8); match+=8; }
        op += 8;

        if (unlikely(cpy>oend-12)) {
            BYTE* const oCopyLimit = oend-(WILDCOPYLENGTH-1);
            if (cpy > oend-LASTLITERALS) goto _output_error;    /* Error : last LASTLITERALS bytes must be literals (uncompressed) */
            if (op < oCopyLimit) {
                LZ4_wildCopy(op, match, oCopyLimit);
                match += oCopyLimit - op;
                op = oCopyLimit;
            }
            while (op<cpy) *op++ = *match++;
        } else {
            memcpy(op, match, 8);
            if (length>16) LZ4_wildCopy(op+8, match+8, cpy);
        }
        op = cpy;   /* correction */
    }

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

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


LZ4_FORCE_O2_GCC_PPC64LE
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);
}

LZ4_FORCE_O2_GCC_PPC64LE
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);
}

LZ4_FORCE_O2_GCC_PPC64LE
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 =====*/

LZ4_streamDecode_t* LZ4_createStreamDecode(void)
{
    LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOC_AND_ZERO(sizeof(LZ4_streamDecode_t));
    return lz4s;
}

int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
{
    if (!LZ4_stream) return 0;   /* support free on NULL */
    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->internal_donotuse;
    lz4sd->prefixSize = (size_t) dictSize;
    lz4sd->prefixEnd = (const 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()
*/
LZ4_FORCE_O2_GCC_PPC64LE
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->internal_donotuse;
    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;
}

LZ4_FORCE_O2_GCC_PPC64LE
int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize)
{
    LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
    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 = lz4sd->prefixEnd - 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
*/

LZ4_FORCE_O2_GCC_PPC64LE
LZ4_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, (const BYTE*)dictStart, dictSize);
}

LZ4_FORCE_O2_GCC_PPC64LE
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);
}

LZ4_FORCE_O2_GCC_PPC64LE
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 */
LZ4_FORCE_O2_GCC_PPC64LE
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, (const BYTE*)dictStart, dictSize);
}


/*=*************************************************
*  Obsolete Functions
***************************************************/
/* obsolete compression functions */
int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) { return LZ4_compress_default(source, dest, inputSize, maxOutputSize); }
int LZ4_compress(const char* source, char* dest, int inputSize) { return LZ4_compress_default(source, dest, inputSize, LZ4_compressBound(inputSize)); }
int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1); }
int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1); }
int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, maxDstSize, 1); }
int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize) { return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1); }

/*
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; }

int LZ4_resetStreamState(void* state, char* inputBuffer)
{
    (void)inputBuffer;
    LZ4_resetStream((LZ4_stream_t*)state);
    return 0;
}

void* LZ4_create (char* inputBuffer)
{
    (void)inputBuffer;
    return LZ4_createStream();
}

char* LZ4_slideInputBuffer (void* state)
{
    /* avoid const char * -> char * conversion warning */
    return (char *)(uptrval)((LZ4_stream_t*)state)->internal_donotuse.dictionary;
}

/* 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 */