summaryrefslogtreecommitdiffstats
path: root/lib/lz4.c
blob: de0194fed1aa23d184788d664cb7aa434b63d90e (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
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
/*
   LZ4 - Fast LZ compression algorithm
   Copyright (C) 2011-2020, 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

/*
 * LZ4_ACCELERATION_DEFAULT :
 * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0
 */
#define LZ4_ACCELERATION_DEFAULT 1
/*
 * LZ4_ACCELERATION_MAX :
 * Any "acceleration" value higher than this threshold
 * get treated as LZ4_ACCELERATION_MAX instead (fix #876)
 */
#define LZ4_ACCELERATION_MAX 65537


/*-************************************
*  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 WinCE doesn't support Hardware bit count */
#  undef  LZ4_FORCE_SW_BITCOUNT  /* avoid double def */
#  define LZ4_FORCE_SW_BITCOUNT
#endif



/*-************************************
*  Dependency
**************************************/
/*
 * LZ4_SRC_INCLUDED:
 * Amalgamation flag, whether lz4.c is included
 */
#ifndef LZ4_SRC_INCLUDED
#  define LZ4_SRC_INCLUDED 1
#endif

#ifndef LZ4_STATIC_LINKING_ONLY
#define LZ4_STATIC_LINKING_ONLY
#endif

#ifndef LZ4_DISABLE_DEPRECATE_WARNINGS
#define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */
#endif

#define LZ4_STATIC_LINKING_ONLY  /* LZ4_DISTANCE_MAX */
#include "lz4.h"
/* see also "memory routines" below */


/*-************************************
*  Compiler Options
**************************************/
#if defined(_MSC_VER) && (_MSC_VER >= 1400)  /* Visual Studio 2005+ */
#  include <intrin.h>               /* only present in VS2005+ */
#  pragma warning(disable : 4127)   /* disable: C4127: conditional expression is constant */
#  pragma warning(disable : 6237)   /* disable: C6237: conditional expression is always 0 */
#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 and LZ4_FORCE_INLINE
 * gcc on ppc64le generates an unrolled SIMDized loop for LZ4_wildCopy8,
 * 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_wildCopy8
 * functions are annotated with __attribute__((optimize("O2"))),
 * and also LZ4_wildCopy8 is forcibly inlined, so that the O2 attribute
 * of LZ4_wildCopy8 does not affect the compression speed.
 */
#if defined(__PPC64__) && defined(__LITTLE_ENDIAN__) && defined(__GNUC__) && !defined(__clang__)
#  define LZ4_FORCE_O2  __attribute__((optimize("O2")))
#  undef LZ4_FORCE_INLINE
#  define LZ4_FORCE_INLINE  static __inline __attribute__((optimize("O2"),always_inline))
#else
#  define LZ4_FORCE_O2
#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

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

/* Should the alignment test prove unreliable, for some reason,
 * it can be disabled by setting LZ4_ALIGN_TEST to 0 */
#ifndef LZ4_ALIGN_TEST  /* can be externally provided */
# define LZ4_ALIGN_TEST 1
#endif


/*-************************************
*  Memory routines
**************************************/
#ifdef LZ4_USER_MEMORY_FUNCTIONS
/* memory management functions can be customized by user project.
 * Below functions must exist somewhere in the Project
 * and be available at link time */
void* LZ4_malloc(size_t s);
void* LZ4_calloc(size_t n, size_t s);
void  LZ4_free(void* p);
# define ALLOC(s)          LZ4_malloc(s)
# define ALLOC_AND_ZERO(s) LZ4_calloc(1,s)
# define FREEMEM(p)        LZ4_free(p)
#else
# include <stdlib.h>   /* malloc, calloc, free */
# define ALLOC(s)          malloc(s)
# define ALLOC_AND_ZERO(s) calloc(1,s)
# define FREEMEM(p)        free(p)
#endif

#include <string.h>   /* memset, memcpy */
#if !defined(LZ4_memset)
#  define LZ4_memset(p,v,s) memset((p),(v),(s))
#endif
#define MEM_INIT(p,v,s)   LZ4_memset((p),(v),(s))


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

#define WILDCOPYLENGTH 8
#define LASTLITERALS   5   /* see ../doc/lz4_Block_format.md#parsing-restrictions */
#define MFLIMIT       12   /* see ../doc/lz4_Block_format.md#parsing-restrictions */
#define MATCH_SAFEGUARD_DISTANCE  ((2*WILDCOPYLENGTH) - MINMATCH)   /* ensure it's possible to write 2 x wildcopyLength without overflowing output buffer */
#define FASTLOOP_SAFE_DISTANCE 64
static const int LZ4_minLength = (MFLIMIT+1);

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

#define LZ4_DISTANCE_ABSOLUTE_MAX 65535
#if (LZ4_DISTANCE_MAX > LZ4_DISTANCE_ABSOLUTE_MAX)   /* max supported by LZ4 format */
#  error "LZ4_DISTANCE_MAX is too big : must be <= 65535"
#endif

#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 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

static int LZ4_isAligned(const void* ptr, size_t alignment)
{
    return ((size_t)ptr & (alignment -1)) == 0;
}


/*-************************************
*  Types
**************************************/
#include <limits.h>
#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
# if UINT_MAX != 4294967295UL
#   error "LZ4 code (when not C++ or C99) assumes that sizeof(int) == 4"
# endif
  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

typedef enum {
    notLimited = 0,
    limitedOutput = 1,
    fillOutput = 2
} limitedOutput_directive;


/*-************************************
*  Reading and writing into memory
**************************************/

/**
 * LZ4 relies on memcpy with a constant size being inlined. In freestanding
 * environments, the compiler can't assume the implementation of memcpy() is
 * standard compliant, so it can't apply its specialized memcpy() inlining
 * logic. When possible, use __builtin_memcpy() to tell the compiler to analyze
 * memcpy() as if it were standard compliant, so it can inline it in freestanding
 * environments. This is needed when decompressing the Linux Kernel, for example.
 */
#if !defined(LZ4_memcpy)
#  if defined(__GNUC__) && (__GNUC__ >= 4)
#    define LZ4_memcpy(dst, src, size) __builtin_memcpy(dst, src, size)
#  else
#    define LZ4_memcpy(dst, src, size) memcpy(dst, src, size)
#  endif
#endif

#if !defined(LZ4_memmove)
#  if defined(__GNUC__) && (__GNUC__ >= 4)
#    define LZ4_memmove __builtin_memmove
#  else
#    define LZ4_memmove memmove
#  endif
#endif

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)) LZ4_unalign;

static U16 LZ4_read16(const void* ptr) { return ((const LZ4_unalign*)ptr)->u16; }
static U32 LZ4_read32(const void* ptr) { return ((const LZ4_unalign*)ptr)->u32; }
static reg_t LZ4_read_ARCH(const void* ptr) { return ((const LZ4_unalign*)ptr)->uArch; }

static void LZ4_write16(void* memPtr, U16 value) { ((LZ4_unalign*)memPtr)->u16 = value; }
static void LZ4_write32(void* memPtr, U32 value) { ((LZ4_unalign*)memPtr)->u32 = value; }

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

static U16 LZ4_read16(const void* memPtr)
{
    U16 val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val;
}

static U32 LZ4_read32(const void* memPtr)
{
    U32 val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val;
}

static reg_t LZ4_read_ARCH(const void* memPtr)
{
    reg_t val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val;
}

static void LZ4_write16(void* memPtr, U16 value)
{
    LZ4_memcpy(memPtr, &value, sizeof(value));
}

static void LZ4_write32(void* memPtr, U32 value)
{
    LZ4_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_INLINE
void LZ4_wildCopy8(void* dstPtr, const void* srcPtr, void* dstEnd)
{
    BYTE* d = (BYTE*)dstPtr;
    const BYTE* s = (const BYTE*)srcPtr;
    BYTE* const e = (BYTE*)dstEnd;

    do { LZ4_memcpy(d,s,8); d+=8; s+=8; } while (d<e);
}

static const unsigned inc32table[8] = {0, 1, 2,  1,  0,  4, 4, 4};
static const int      dec64table[8] = {0, 0, 0, -1, -4,  1, 2, 3};


#ifndef LZ4_FAST_DEC_LOOP
#  if defined __i386__ || defined _M_IX86 || defined __x86_64__ || defined _M_X64
#    define LZ4_FAST_DEC_LOOP 1
#  elif defined(__aarch64__) && defined(__APPLE__)
#    define LZ4_FAST_DEC_LOOP 1
#  elif defined(__aarch64__) && !defined(__clang__)
     /* On non-Apple aarch64, we disable this optimization for clang because
      * on certain mobile chipsets, performance is reduced with clang. For
      * more information refer to https://github.com/lz4/lz4/pull/707 */
#    define LZ4_FAST_DEC_LOOP 1
#  else
#    define LZ4_FAST_DEC_LOOP 0
#  endif
#endif

#if LZ4_FAST_DEC_LOOP

LZ4_FORCE_INLINE void
LZ4_memcpy_using_offset_base(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset)
{
    assert(srcPtr + offset == dstPtr);
    if (offset < 8) {
        LZ4_write32(dstPtr, 0);   /* silence an msan warning when offset==0 */
        dstPtr[0] = srcPtr[0];
        dstPtr[1] = srcPtr[1];
        dstPtr[2] = srcPtr[2];
        dstPtr[3] = srcPtr[3];
        srcPtr += inc32table[offset];
        LZ4_memcpy(dstPtr+4, srcPtr, 4);
        srcPtr -= dec64table[offset];
        dstPtr += 8;
    } else {
        LZ4_memcpy(dstPtr, srcPtr, 8);
        dstPtr += 8;
        srcPtr += 8;
    }

    LZ4_wildCopy8(dstPtr, srcPtr, dstEnd);
}

/* customized variant of memcpy, which can overwrite up to 32 bytes beyond dstEnd
 * this version copies two times 16 bytes (instead of one time 32 bytes)
 * because it must be compatible with offsets >= 16. */
LZ4_FORCE_INLINE void
LZ4_wildCopy32(void* dstPtr, const void* srcPtr, void* dstEnd)
{
    BYTE* d = (BYTE*)dstPtr;
    const BYTE* s = (const BYTE*)srcPtr;
    BYTE* const e = (BYTE*)dstEnd;

    do { LZ4_memcpy(d,s,16); LZ4_memcpy(d+16,s+16,16); d+=32; s+=32; } while (d<e);
}

/* LZ4_memcpy_using_offset()  presumes :
 * - dstEnd >= dstPtr + MINMATCH
 * - there is at least 8 bytes available to write after dstEnd */
LZ4_FORCE_INLINE void
LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset)
{
    BYTE v[8];

    assert(dstEnd >= dstPtr + MINMATCH);

    switch(offset) {
    case 1:
        MEM_INIT(v, *srcPtr, 8);
        break;
    case 2:
        LZ4_memcpy(v, srcPtr, 2);
        LZ4_memcpy(&v[2], srcPtr, 2);
        LZ4_memcpy(&v[4], v, 4);
        break;
    case 4:
        LZ4_memcpy(v, srcPtr, 4);
        LZ4_memcpy(&v[4], srcPtr, 4);
        break;
    default:
        LZ4_memcpy_using_offset_base(dstPtr, srcPtr, dstEnd, offset);
        return;
    }

    LZ4_memcpy(dstPtr, v, 8);
    dstPtr += 8;
    while (dstPtr < dstEnd) {
        LZ4_memcpy(dstPtr, v, 8);
        dstPtr += 8;
    }
}
#endif


/*-************************************
*  Common functions
**************************************/
static unsigned LZ4_NbCommonBytes (reg_t val)
{
    assert(val != 0);
    if (LZ4_isLittleEndian()) {
        if (sizeof(val) == 8) {
#       if defined(_MSC_VER) && (_MSC_VER >= 1800) && (defined(_M_AMD64) && !defined(_M_ARM64EC)) && !defined(LZ4_FORCE_SW_BITCOUNT)
/*-*************************************************************************************************
* ARM64EC is a Microsoft-designed ARM64 ABI compatible with AMD64 applications on ARM64 Windows 11.
* The ARM64EC ABI does not support AVX/AVX2/AVX512 instructions, nor their relevant intrinsics
* including _tzcnt_u64. Therefore, we need to neuter the _tzcnt_u64 code path for ARM64EC.
****************************************************************************************************/
#         if defined(__clang__) && (__clang_major__ < 10)
            /* Avoid undefined clang-cl intrinsics issue.
             * See https://github.com/lz4/lz4/pull/1017 for details. */
            return (unsigned)__builtin_ia32_tzcnt_u64(val) >> 3;
#         else
            /* x64 CPUS without BMI support interpret `TZCNT` as `REP BSF` */
            return (unsigned)_tzcnt_u64(val) >> 3;
#         endif
#       elif defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
            unsigned long r = 0;
            _BitScanForward64(&r, (U64)val);
            return (unsigned)r >> 3;
#       elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
                            ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
                                        !defined(LZ4_FORCE_SW_BITCOUNT)
            return (unsigned)__builtin_ctzll((U64)val) >> 3;
#       else
            const U64 m = 0x0101010101010101ULL;
            val ^= val - 1;
            return (unsigned)(((U64)((val & (m - 1)) * m)) >> 56);
#       endif
        } else /* 32 bits */ {
#       if defined(_MSC_VER) && (_MSC_VER >= 1400) && !defined(LZ4_FORCE_SW_BITCOUNT)
            unsigned long r;
            _BitScanForward(&r, (U32)val);
            return (unsigned)r >> 3;
#       elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
                            ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
                        !defined(__TINYC__) && !defined(LZ4_FORCE_SW_BITCOUNT)
            return (unsigned)__builtin_ctz((U32)val) >> 3;
#       else
            const U32 m = 0x01010101;
            return (unsigned)((((val - 1) ^ val) & (m - 1)) * m) >> 24;
#       endif
        }
    } else   /* Big Endian CPU */ {
        if (sizeof(val)==8) {
#       if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
                            ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
                        !defined(__TINYC__) && !defined(LZ4_FORCE_SW_BITCOUNT)
            return (unsigned)__builtin_clzll((U64)val) >> 3;
#       else
#if 1
            /* this method is probably faster,
             * but adds a 128 bytes lookup table */
            static const unsigned char ctz7_tab[128] = {
                7, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
                4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
                5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
                4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
                6, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
                4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
                5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
                4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
            };
            U64 const mask = 0x0101010101010101ULL;
            U64 const t = (((val >> 8) - mask) | val) & mask;
            return ctz7_tab[(t * 0x0080402010080402ULL) >> 57];
#else
            /* this method doesn't consume memory space like the previous one,
             * but it contains several branches,
             * that may end up slowing execution */
            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
#       endif
        } else /* 32 bits */ {
#       if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
                            ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
                                        !defined(LZ4_FORCE_SW_BITCOUNT)
            return (unsigned)__builtin_clz((U32)val) >> 3;
#       else
            val >>= 8;
            val = ((((val + 0x00FFFF00) | 0x00FFFFFF) + val) |
              (val + 0x00FF0000)) >> 24;
            return (unsigned)val ^ 3;
#       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 { 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  : 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;


/*-************************************
*  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(void) { return sizeof(LZ4_stream_t); }


/*-****************************************
*  Internal Definitions, used only in Tests
*******************************************/
#if defined (__cplusplus)
extern "C" {
#endif

int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize);

int LZ4_decompress_safe_forceExtDict(const char* source, char* dest,
                                     int compressedSize, int maxOutputSize,
                                     const void* dictStart, size_t dictSize);
int LZ4_decompress_safe_partial_forceExtDict(const char* source, char* dest,
                                     int compressedSize, int targetOutputSize, int dstCapacity,
                                     const void* dictStart, size_t dictSize);
#if defined (__cplusplus)
}
#endif

/*-******************************
*  Compression functions
********************************/
LZ4_FORCE_INLINE 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));
}

LZ4_FORCE_INLINE U32 LZ4_hash5(U64 sequence, tableType_t const tableType)
{
    const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG;
    if (LZ4_isLittleEndian()) {
        const U64 prime5bytes = 889523592379ULL;
        return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog));
    } else {
        const U64 prime8bytes = 11400714785074694791ULL;
        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);
}

LZ4_FORCE_INLINE void LZ4_clearHash(U32 h, void* tableBase, tableType_t const tableType)
{
    switch (tableType)
    {
    default: /* fallthrough */
    case clearedTable: { /* illegal! */ assert(0); return; }
    case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = NULL; return; }
    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = 0; return; }
    case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = 0; return; }
    }
}

LZ4_FORCE_INLINE void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType)
{
    switch (tableType)
    {
    default: /* fallthrough */
    case clearedTable: /* fallthrough */
    case byPtr: { /* illegal! */ assert(0); return; }
    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = idx; return; }
    case byU16: { U16* hashTable = (U16*) tableBase; assert(idx < 65536); hashTable[h] = (U16)idx; return; }
    }
}

LZ4_FORCE_INLINE 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);
}

/* LZ4_getIndexOnHash() :
 * Index of match position registered in hash table.
 * hash position must be calculated by using base+index, or dictBase+index.
 * Assumption 1 : only valid if tableType == byU32 or byU16.
 * Assumption 2 : h is presumed valid (within limits of hash table)
 */
LZ4_FORCE_INLINE U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_t tableType)
{
    LZ4_STATIC_ASSERT(LZ4_MEMORY_USAGE > 2);
    if (tableType == byU32) {
        const U32* const hashTable = (const U32*) tableBase;
        assert(h < (1U << (LZ4_MEMORY_USAGE-2)));
        return hashTable[h];
    }
    if (tableType == byU16) {
        const U16* const hashTable = (const U16*) tableBase;
        assert(h < (1U << (LZ4_MEMORY_USAGE-1)));
        return hashTable[h];
    }
    assert(0); return 0;  /* forbidden case */
}

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 ((tableType_t)cctx->tableType != clearedTable) {
        assert(inputSize >= 0);
        if ((tableType_t)cctx->tableType != tableType
          || ((tableType == byU16) && cctx->currentOffset + (unsigned)inputSize >= 0xFFFFU)
          || ((tableType == byU32) && cctx->currentOffset > 1 GB)
          || tableType == byPtr
          || inputSize >= 4 KB)
        {
            DEBUGLOG(4, "LZ4_prepareTable: Resetting table in %p", cctx);
            MEM_INIT(cctx->hashTable, 0, LZ4_HASHTABLESIZE);
            cctx->currentOffset = 0;
            cctx->tableType = (U32)clearedTable;
        } else {
            DEBUGLOG(4, "LZ4_prepareTable: Re-use hash table (no reset)");
        }
    }

    /* Adding a gap, so all previous entries are > LZ4_DISTANCE_MAX 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) {
        DEBUGLOG(5, "LZ4_prepareTable: adding 64KB to currentOffset");
        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.
 *  Presumed already validated at this stage:
 *  - source != NULL
 *  - inputSize > 0
 */
LZ4_FORCE_INLINE int LZ4_compress_generic_validated(
                 LZ4_stream_t_internal* const cctx,
                 const char* const source,
                 char* const dest,
                 const int inputSize,
                 int*  inputConsumed, /* only written when outputDirective == fillOutput */
                 const int maxOutputSize,
                 const limitedOutput_directive outputDirective,
                 const tableType_t tableType,
                 const dict_directive dictDirective,
                 const dictIssue_directive dictIssue,
                 const int acceleration)
{
    int result;
    const BYTE* ip = (const BYTE*) source;

    U32 const startIndex = cctx->currentOffset;
    const BYTE* base = (const BYTE*) source - startIndex;
    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 U32 dictDelta = (dictDirective == usingDictCtx) ? startIndex - dictCtx->currentOffset : 0;   /* make indexes in dictCtx comparable with index in current context */

    int const maybe_extMem = (dictDirective == usingExtDict) || (dictDirective == usingDictCtx);
    U32 const prefixIdxLimit = startIndex - dictSize;   /* used when dictDirective == dictSmall */
    const BYTE* const dictEnd = dictionary ? dictionary + dictSize : dictionary;
    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 = (dictionary == NULL) ? NULL :
                           (dictDirective == usingDictCtx) ?
                            dictionary + dictSize - dictCtx->currentOffset :
                            dictionary + dictSize - startIndex;

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

    U32 offset = 0;
    U32 forwardH;

    DEBUGLOG(5, "LZ4_compress_generic_validated: srcSize=%i, tableType=%u", inputSize, tableType);
    assert(ip != NULL);
    /* If init conditions are not met, we don't have to mark stream
     * as having dirty context, since no action was taken yet */
    if (outputDirective == fillOutput && maxOutputSize < 1) { return 0; } /* Impossible to store anything */
    if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) { return 0; }  /* Size too large (not within 64K limit) */
    if (tableType==byPtr) assert(dictDirective==noDict);      /* only supported use case with byPtr */
    assert(acceleration >= 1);

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

    /* 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 = (U32)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 ( ; ; ) {
        const BYTE* match;
        BYTE* token;
        const BYTE* filledIp;

        /* Find a match */
        if (tableType == byPtr) {
            const BYTE* forwardIp = ip;
            int step = 1;
            int 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);
                forwardH = LZ4_hashPosition(forwardIp, tableType);
                LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base);

            } while ( (match+LZ4_DISTANCE_MAX < ip)
                   || (LZ4_read32(match) != LZ4_read32(ip)) );

        } else {   /* byU32, byU16 */

            const BYTE* forwardIp = ip;
            int step = 1;
            int searchMatchNb = acceleration << LZ4_skipTrigger;
            do {
                U32 const h = forwardH;
                U32 const current = (U32)(forwardIp - base);
                U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);
                assert(matchIndex <= current);
                assert(forwardIp - base < (ptrdiff_t)(2 GB - 1));
                ip = forwardIp;
                forwardIp += step;
                step = (searchMatchNb++ >> LZ4_skipTrigger);

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

                if (dictDirective == usingDictCtx) {
                    if (matchIndex < startIndex) {
                        /* there was no match, try the dictionary */
                        assert(tableType == byU32);
                        matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);
                        match = dictBase + matchIndex;
                        matchIndex += dictDelta;   /* make dictCtx index comparable with current context */
                        lowLimit = dictionary;
                    } else {
                        match = base + matchIndex;
                        lowLimit = (const BYTE*)source;
                    }
                } else if (dictDirective == usingExtDict) {
                    if (matchIndex < startIndex) {
                        DEBUGLOG(7, "extDict candidate: matchIndex=%5u  <  startIndex=%5u", matchIndex, startIndex);
                        assert(startIndex - matchIndex >= MINMATCH);
                        assert(dictBase);
                        match = dictBase + matchIndex;
                        lowLimit = dictionary;
                    } else {
                        match = base + matchIndex;
                        lowLimit = (const BYTE*)source;
                    }
                } else {   /* single continuous memory segment */
                    match = base + matchIndex;
                }
                forwardH = LZ4_hashPosition(forwardIp, tableType);
                LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);

                DEBUGLOG(7, "candidate at pos=%u  (offset=%u \n", matchIndex, current - matchIndex);
                if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) { continue; }    /* match outside of valid area */
                assert(matchIndex < current);
                if ( ((tableType != byU16) || (LZ4_DISTANCE_MAX < LZ4_DISTANCE_ABSOLUTE_MAX))
                  && (matchIndex+LZ4_DISTANCE_MAX < current)) {
                    continue;
                } /* too far */
                assert((current - matchIndex) <= LZ4_DISTANCE_MAX);  /* match now expected within distance */

                if (LZ4_read32(match) == LZ4_read32(ip)) {
                    if (maybe_extMem) offset = current - matchIndex;
                    break;   /* match found */
                }

            } while(1);
        }

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

        /* Encode Literals */
        {   unsigned const litLength = (unsigned)(ip - anchor);
            token = op++;
            if ((outputDirective == limitedOutput) &&  /* Check output buffer overflow */
                (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)) ) {
                return 0;   /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
            }
            if ((outputDirective == fillOutput) &&
                (unlikely(op + (litLength+240)/255 /* litlen */ + litLength /* literals */ + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit))) {
                op--;
                goto _last_literals;
            }
            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_wildCopy8(op, anchor, op+litLength);
            op+=litLength;
            DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i",
                        (int)(anchor-(const BYTE*)source), litLength, (int)(ip-(const BYTE*)source));
        }

_next_match:
        /* at this stage, the following variables must be correctly set :
         * - ip : at start of LZ operation
         * - match : at start of previous pattern occurrence; can be within current prefix, or within extDict
         * - offset : if maybe_ext_memSegment==1 (constant)
         * - lowLimit : must be == dictionary to mean "match is within extDict"; must be == source otherwise
         * - token and *token : position to write 4-bits for match length; higher 4-bits for literal length supposed already written
         */

        if ((outputDirective == fillOutput) &&
            (op + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit)) {
            /* the match was too close to the end, rewind and go to last literals */
            op = token;
            goto _last_literals;
        }

        /* Encode Offset */
        if (maybe_extMem) {   /* static test */
            DEBUGLOG(6, "             with offset=%u  (ext if > %i)", offset, (int)(ip - (const BYTE*)source));
            assert(offset <= LZ4_DISTANCE_MAX && offset > 0);
            LZ4_writeLE16(op, (U16)offset); op+=2;
        } else  {
            DEBUGLOG(6, "             with offset=%u  (same segment)", (U32)(ip - match));
            assert(ip-match <= LZ4_DISTANCE_MAX);
            LZ4_writeLE16(op, (U16)(ip - match)); op+=2;
        }

        /* Encode MatchLength */
        {   unsigned matchCode;

            if ( (dictDirective==usingExtDict || dictDirective==usingDictCtx)
              && (lowLimit==dictionary) /* match within extDict */ ) {
                const BYTE* limit = ip + (dictEnd-match);
                assert(dictEnd > match);
                if (limit > matchlimit) limit = matchlimit;
                matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit);
                ip += (size_t)matchCode + MINMATCH;
                if (ip==limit) {
                    unsigned const more = LZ4_count(limit, (const BYTE*)source, matchlimit);
                    matchCode += more;
                    ip += more;
                }
                DEBUGLOG(6, "             with matchLength=%u starting in extDict", matchCode+MINMATCH);
            } else {
                matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
                ip += (size_t)matchCode + MINMATCH;
                DEBUGLOG(6, "             with matchLength=%u", matchCode+MINMATCH);
            }

            if ((outputDirective) &&    /* Check output buffer overflow */
                (unlikely(op + (1 + LASTLITERALS) + (matchCode+240)/255 > olimit)) ) {
                if (outputDirective == fillOutput) {
                    /* Match description too long : reduce it */
                    U32 newMatchCode = 15 /* in token */ - 1 /* to avoid needing a zero byte */ + ((U32)(olimit - op) - 1 - LASTLITERALS) * 255;
                    ip -= matchCode - newMatchCode;
                    assert(newMatchCode < matchCode);
                    matchCode = newMatchCode;
                    if (unlikely(ip <= filledIp)) {
                        /* We have already filled up to filledIp so if ip ends up less than filledIp
                         * we have positions in the hash table beyond the current position. This is
                         * a problem if we reuse the hash table. So we have to remove these positions
                         * from the hash table.
                         */
                        const BYTE* ptr;
                        DEBUGLOG(5, "Clearing %u positions", (U32)(filledIp - ip));
                        for (ptr = ip; ptr <= filledIp; ++ptr) {
                            U32 const h = LZ4_hashPosition(ptr, tableType);
                            LZ4_clearHash(h, cctx->hashTable, tableType);
                        }
                    }
                } else {
                    assert(outputDirective == limitedOutput);
                    return 0;   /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
                }
            }
            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);
        }
        /* Ensure we have enough space for the last literals. */
        assert(!(outputDirective == fillOutput && op + 1 + LASTLITERALS > olimit));

        anchor = ip;

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

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

        /* Test next position */
        if (tableType == byPtr) {

            match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);
            LZ4_putPosition(ip, cctx->hashTable, tableType, base);
            if ( (match+LZ4_DISTANCE_MAX >= ip)
              && (LZ4_read32(match) == LZ4_read32(ip)) )
            { token=op++; *token=0; goto _next_match; }

        } else {   /* byU32, byU16 */

            U32 const h = LZ4_hashPosition(ip, tableType);
            U32 const current = (U32)(ip-base);
            U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);
            assert(matchIndex < current);
            if (dictDirective == usingDictCtx) {
                if (matchIndex < startIndex) {
                    /* there was no match, try the dictionary */
                    matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);
                    match = dictBase + matchIndex;
                    lowLimit = dictionary;   /* required for match length counter */
                    matchIndex += dictDelta;
                } else {
                    match = base + matchIndex;
                    lowLimit = (const BYTE*)source;  /* required for match length counter */
                }
            } else if (dictDirective==usingExtDict) {
                if (matchIndex < startIndex) {
                    assert(dictBase);
                    match = dictBase + matchIndex;
                    lowLimit = dictionary;   /* required for match length counter */
                } else {
                    match = base + matchIndex;
                    lowLimit = (const BYTE*)source;   /* required for match length counter */
                }
            } else {   /* single memory segment */
                match = base + matchIndex;
            }
            LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
            assert(matchIndex < current);
            if ( ((dictIssue==dictSmall) ? (matchIndex >= prefixIdxLimit) : 1)
              && (((tableType==byU16) && (LZ4_DISTANCE_MAX == LZ4_DISTANCE_ABSOLUTE_MAX)) ? 1 : (matchIndex+LZ4_DISTANCE_MAX >= current))
              && (LZ4_read32(match) == LZ4_read32(ip)) ) {
                token=op++;
                *token=0;
                if (maybe_extMem) offset = current - matchIndex;
                DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i",
                            (int)(anchor-(const BYTE*)source), 0, (int)(ip-(const BYTE*)source));
                goto _next_match;
            }
        }

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

    }

_last_literals:
    /* Encode Last Literals */
    {   size_t lastRun = (size_t)(iend - anchor);
        if ( (outputDirective) &&  /* Check output buffer overflow */
            (op + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > olimit)) {
            if (outputDirective == fillOutput) {
                /* adapt lastRun to fill 'dst' */
                assert(olimit >= op);
                lastRun  = (size_t)(olimit-op) - 1/*token*/;
                lastRun -= (lastRun + 256 - RUN_MASK) / 256;  /*additional length tokens*/
            } else {
                assert(outputDirective == limitedOutput);
                return 0;   /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
            }
        }
        DEBUGLOG(6, "Final literal run : %i literals", (int)lastRun);
        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);
        }
        LZ4_memcpy(op, anchor, lastRun);
        ip = anchor + lastRun;
        op += lastRun;
    }

    if (outputDirective == fillOutput) {
        *inputConsumed = (int) (((const char*)ip)-source);
    }
    result = (int)(((char*)op) - dest);
    assert(result > 0);
    DEBUGLOG(5, "LZ4_compress_generic: compressed %i bytes into %i bytes", inputSize, result);
    return result;
}

/** LZ4_compress_generic() :
 *  inlined, to ensure branches are decided at compilation time;
 *  takes care of src == (NULL, 0)
 *  and forward the rest to LZ4_compress_generic_validated */
LZ4_FORCE_INLINE int LZ4_compress_generic(
                 LZ4_stream_t_internal* const cctx,
                 const char* const src,
                 char* const dst,
                 const int srcSize,
                 int *inputConsumed, /* only written when outputDirective == fillOutput */
                 const int dstCapacity,
                 const limitedOutput_directive outputDirective,
                 const tableType_t tableType,
                 const dict_directive dictDirective,
                 const dictIssue_directive dictIssue,
                 const int acceleration)
{
    DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, dstCapacity=%i",
                srcSize, dstCapacity);

    if ((U32)srcSize > (U32)LZ4_MAX_INPUT_SIZE) { return 0; }  /* Unsupported srcSize, too large (or negative) */
    if (srcSize == 0) {   /* src == NULL supported if srcSize == 0 */
        if (outputDirective != notLimited && dstCapacity <= 0) return 0;  /* no output, can't write anything */
        DEBUGLOG(5, "Generating an empty block");
        assert(outputDirective == notLimited || dstCapacity >= 1);
        assert(dst != NULL);
        dst[0] = 0;
        if (outputDirective == fillOutput) {
            assert (inputConsumed != NULL);
            *inputConsumed = 0;
        }
        return 1;
    }
    assert(src != NULL);

    return LZ4_compress_generic_validated(cctx, src, dst, srcSize,
                inputConsumed, /* only written into if outputDirective == fillOutput */
                dstCapacity, outputDirective,
                tableType, dictDirective, dictIssue, acceleration);
}


int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
{
    LZ4_stream_t_internal* const ctx = & LZ4_initStream(state, sizeof(LZ4_stream_t)) -> internal_donotuse;
    assert(ctx != NULL);
    if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT;
    if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX;
    if (maxOutputSize >= LZ4_compressBound(inputSize)) {
        if (inputSize < LZ4_64Klimit) {
            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, byU16, noDict, noDictIssue, acceleration);
        } else {
            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
        }
    } else {
        if (inputSize < LZ4_64Klimit) {
            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration);
        } else {
            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 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* src, char* dst, int srcSize, int dstCapacity, int acceleration)
{
    LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse;
    if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT;
    if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX;

    if (dstCapacity >= LZ4_compressBound(srcSize)) {
        if (srcSize < LZ4_64Klimit) {
            const tableType_t tableType = byU16;
            LZ4_prepareTable(ctx, srcSize, tableType);
            if (ctx->currentOffset) {
                return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, dictSmall, acceleration);
            } else {
                return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
            }
        } else {
            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
            LZ4_prepareTable(ctx, srcSize, tableType);
            return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
        }
    } else {
        if (srcSize < LZ4_64Klimit) {
            const tableType_t tableType = byU16;
            LZ4_prepareTable(ctx, srcSize, tableType);
            if (ctx->currentOffset) {
                return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, dictSmall, acceleration);
            } else {
                return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration);
            }
        } else {
            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
            LZ4_prepareTable(ctx, srcSize, tableType);
            return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, 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 = (LZ4_stream_t*)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* src, char* dst, int srcSize, int maxOutputSize)
{
    return LZ4_compress_fast(src, dst, srcSize, maxOutputSize, 1);
}


/* Note!: This function leaves the stream in an unclean/broken state!
 * It is not safe to subsequently use the same state with a _fastReset() or
 * _continue() call without resetting it. */
static int LZ4_compress_destSize_extState (LZ4_stream_t* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize)
{
    void* const s = LZ4_initStream(state, sizeof (*state));
    assert(s != NULL); (void)s;

    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_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, byU16, noDict, noDictIssue, 1);
        } else {
            tableType_t const addrMode = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
            return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, addrMode, noDict, noDictIssue, 1);
    }   }
}


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* const lz4s = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));
    LZ4_STATIC_ASSERT(sizeof(LZ4_stream_t) >= sizeof(LZ4_stream_t_internal));
    DEBUGLOG(4, "LZ4_createStream %p", lz4s);
    if (lz4s == NULL) return NULL;
    LZ4_initStream(lz4s, sizeof(*lz4s));
    return lz4s;
}

static size_t LZ4_stream_t_alignment(void)
{
#if LZ4_ALIGN_TEST
    typedef struct { char c; LZ4_stream_t t; } t_a;
    return sizeof(t_a) - sizeof(LZ4_stream_t);
#else
    return 1;  /* effectively disabled */
#endif
}

LZ4_stream_t* LZ4_initStream (void* buffer, size_t size)
{
    DEBUGLOG(5, "LZ4_initStream");
    if (buffer == NULL) { return NULL; }
    if (size < sizeof(LZ4_stream_t)) { return NULL; }
    if (!LZ4_isAligned(buffer, LZ4_stream_t_alignment())) return NULL;
    MEM_INIT(buffer, 0, sizeof(LZ4_stream_t_internal));
    return (LZ4_stream_t*)buffer;
}

/* resetStream is now deprecated,
 * prefer initStream() which is more general */
void LZ4_resetStream (LZ4_stream_t* LZ4_stream)
{
    DEBUGLOG(5, "LZ4_resetStream (ctx:%p)", LZ4_stream);
    MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t_internal));
}

void LZ4_resetStream_fast(LZ4_stream_t* 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 (%i bytes from %p into %p)", dictSize, dictionary, LZ4_dict);

    /* It's necessary to reset the context,
     * and not just continue it with prepareTable()
     * to avoid any risk of generating overflowing matchIndex
     * when compressing using this dictionary */
    LZ4_resetStream(LZ4_dict);

    /* We always increment the offset by 64 KB, since, if the dict is longer,
     * we truncate it to the last 64k, and if it's shorter, we still want to
     * advance by a whole window length so we can provide the guarantee that
     * there are only valid offsets in the window, which allows an optimization
     * in LZ4_compress_fast_continue() where it uses noDictIssue even when the
     * dictionary isn't a full 64k. */
    dict->currentOffset += 64 KB;

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

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

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

    return (int)dict->dictSize;
}

void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream)
{
    const LZ4_stream_t_internal* dictCtx = (dictionaryStream == NULL) ? NULL :
        &(dictionaryStream->internal_donotuse);

    DEBUGLOG(4, "LZ4_attach_dictionary (%p, %p, size %u)",
             workingStream, dictionaryStream,
             dictCtx != NULL ? dictCtx->dictSize : 0);

    if (dictCtx != NULL) {
        /* 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 (workingStream->internal_donotuse.currentOffset == 0) {
            workingStream->internal_donotuse.currentOffset = 64 KB;
        }

        /* Don't actually attach an empty dictionary.
         */
        if (dictCtx->dictSize == 0) {
            dictCtx = NULL;
        }
    }
    workingStream->internal_donotuse.dictCtx = dictCtx;
}


static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, int nextSize)
{
    assert(nextSize >= 0);
    if (LZ4_dict->currentOffset + (unsigned)nextSize > 0x80000000) {   /* potential ptrdiff_t overflow (32-bits mode) */
        /* 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");
        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* const streamPtr = &LZ4_stream->internal_donotuse;
    const char* dictEnd = streamPtr->dictSize ? (const char*)streamPtr->dictionary + streamPtr->dictSize : NULL;

    DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i, dictSize=%u)", inputSize, streamPtr->dictSize);

    LZ4_renormDictT(streamPtr, inputSize);   /* fix index overflow */
    if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT;
    if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX;

    /* invalidate tiny dictionaries */
    if ( (streamPtr->dictSize < 4)     /* tiny dictionary : not enough for a hash */
      && (dictEnd != source)           /* prefix mode */
      && (inputSize > 0)               /* tolerance : don't lose history, in case next invocation would use prefix mode */
      && (streamPtr->dictCtx == NULL)  /* usingDictCtx */
      ) {
        DEBUGLOG(5, "LZ4_compress_fast_continue: dictSize(%u) at addr:%p is too small", streamPtr->dictSize, streamPtr->dictionary);
        /* remove dictionary existence from history, to employ faster prefix mode */
        streamPtr->dictSize = 0;
        streamPtr->dictionary = (const BYTE*)source;
        dictEnd = source;
    }

    /* Check overlapping input/dictionary space */
    {   const char* const sourceEnd = source + inputSize;
        if ((sourceEnd > (const char*)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 = (const BYTE*)dictEnd - streamPtr->dictSize;
        }
    }

    /* prefix mode : source data follows dictionary */
    if (dictEnd == source) {
        if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
            return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, dictSmall, acceleration);
        else
            return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, 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 into one table.
                 */
                LZ4_memcpy(streamPtr, streamPtr->dictCtx, sizeof(*streamPtr));
                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
            } else {
                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingDictCtx, noDictIssue, acceleration);
            }
        } else {  /* small data <= 4 KB */
            if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) {
                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, dictSmall, acceleration);
            } else {
                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
            }
        }
        streamPtr->dictionary = (const BYTE*)source;
        streamPtr->dictSize = (U32)inputSize;
        return result;
    }
}


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

    LZ4_renormDictT(streamPtr, srcSize);

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

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

    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 : no need to call LZ4_loadDict() afterwards, dictionary is immediately usable,
 *         one can therefore call LZ4_compress_fast_continue() right after.
 * @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;

    DEBUGLOG(5, "LZ4_saveDict : dictSize=%i, safeBuffer=%p", dictSize, safeBuffer);

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

    if (safeBuffer == NULL) assert(dictSize == 0);
    if (dictSize > 0) {
        const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize;
        assert(dict->dictionary);
        LZ4_memmove(safeBuffer, previousDictEnd - dictSize, (size_t)dictSize);
    }

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

    return dictSize;
}



/*-*******************************
 *  Decompression functions
 ********************************/

typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive;

#undef MIN
#define MIN(a,b)    ( (a) < (b) ? (a) : (b) )


/* variant for decompress_unsafe()
 * does not know end of input
 * presumes input is well formed
 * note : will consume at least one byte */
size_t read_long_length_no_check(const BYTE** pp)
{
    size_t b, l = 0;
    do { b = **pp; (*pp)++; l += b; } while (b==255);
    DEBUGLOG(6, "read_long_length_no_check: +length=%zu using %zu input bytes", l, l/255 + 1)
    return l;
}

/* core decoder variant for LZ4_decompress_fast*()
 * for legacy support only : these entry points are deprecated.
 * - Presumes input is correctly formed (no defense vs malformed inputs)
 * - Does not know input size (presume input buffer is "large enough")
 * - Decompress a full block (only)
 * @return : nb of bytes read from input.
 * Note : this variant is not optimized for speed, just for maintenance.
 *        the goal is to remove support of decompress_fast*() variants by v2.0
**/
LZ4_FORCE_INLINE int
LZ4_decompress_unsafe_generic(
                 const BYTE* const istart,
                 BYTE* const ostart,
                 int decompressedSize,

                 size_t prefixSize,
                 const BYTE* const dictStart,  /* only if dict==usingExtDict */
                 const size_t dictSize         /* note: =0 if dictStart==NULL */
                 )
{
    const BYTE* ip = istart;
    BYTE* op = (BYTE*)ostart;
    BYTE* const oend = ostart + decompressedSize;
    const BYTE* const prefixStart = ostart - prefixSize;

    DEBUGLOG(5, "LZ4_decompress_unsafe_generic");
    if (dictStart == NULL) assert(dictSize == 0);

    while (1) {
        /* start new sequence */
        unsigned token = *ip++;

        /* literals */
        {   size_t ll = token >> ML_BITS;
            if (ll==15) {
                /* long literal length */
                ll += read_long_length_no_check(&ip);
            }
            if ((size_t)(oend-op) < ll) return -1; /* output buffer overflow */
            LZ4_memmove(op, ip, ll); /* support in-place decompression */
            op += ll;
            ip += ll;
            if ((size_t)(oend-op) < MFLIMIT) {
                if (op==oend) break;  /* end of block */
                DEBUGLOG(5, "invalid: literals end at distance %zi from end of block", oend-op);
                /* incorrect end of block :
                 * last match must start at least MFLIMIT==12 bytes before end of output block */
                return -1;
        }   }

        /* match */
        {   size_t ml = token & 15;
            size_t const offset = LZ4_readLE16(ip);
            ip+=2;

            if (ml==15) {
                /* long literal length */
                ml += read_long_length_no_check(&ip);
            }
            ml += MINMATCH;

            if ((size_t)(oend-op) < ml) return -1; /* output buffer overflow */

            {   const BYTE* match = op - offset;

                /* out of range */
                if (offset > (size_t)(op - prefixStart) + dictSize) {
                    DEBUGLOG(6, "offset out of range");
                    return -1;
                }

                /* check special case : extDict */
                if (offset > (size_t)(op - prefixStart)) {
                    /* extDict scenario */
                    const BYTE* const dictEnd = dictStart + dictSize;
                    const BYTE* extMatch = dictEnd - (offset - (size_t)(op-prefixStart));
                    size_t const extml = (size_t)(dictEnd - extMatch);
                    if (extml > ml) {
                        /* match entirely within extDict */
                        LZ4_memmove(op, extMatch, ml);
                        op += ml;
                        ml = 0;
                    } else {
                        /* match split between extDict & prefix */
                        LZ4_memmove(op, extMatch, extml);
                        op += extml;
                        ml -= extml;
                    }
                    match = prefixStart;
                }

                /* match copy - slow variant, supporting overlap copy */
                {   size_t u;
                    for (u=0; u<ml; u++) {
                        op[u] = match[u];
            }   }   }
            op += ml;
            if ((size_t)(oend-op) < LASTLITERALS) {
                DEBUGLOG(5, "invalid: match ends at distance %zi from end of block", oend-op);
                /* incorrect end of block :
                 * last match must stop at least LASTLITERALS==5 bytes before end of output block */
                return -1;
            }
        } /* match */
    } /* main loop */
    return (int)(ip - istart);
}


/* Read the variable-length literal or match length.
 *
 * @ip : input pointer
 * @ilimit : position after which if length is not decoded, the input is necessarily corrupted.
 * @initial_check - check ip >= ipmax before start of loop.  Returns initial_error if so.
 * @error (output) - error code.  Must be set to 0 before call.
**/
typedef size_t Rvl_t;
static const Rvl_t rvl_error = (Rvl_t)(-1);
LZ4_FORCE_INLINE Rvl_t
read_variable_length(const BYTE** ip, const BYTE* ilimit,
                     int initial_check)
{
    Rvl_t s, length = 0;
    assert(ip != NULL);
    assert(*ip !=  NULL);
    assert(ilimit != NULL);
    if (initial_check && unlikely((*ip) >= ilimit)) {    /* read limit reached */
        return rvl_error;
    }
    do {
        s = **ip;
        (*ip)++;
        length += s;
        if (unlikely((*ip) > ilimit)) {    /* read limit reached */
            return rvl_error;
        }
        /* accumulator overflow detection (32-bit mode only) */
        if ((sizeof(length)<8) && unlikely(length > ((Rvl_t)(-1)/2)) ) {
            return rvl_error;
        }
    } while (s==255);

    return length;
}

/*! 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_INLINE int
LZ4_decompress_generic(
                 const char* const src,
                 char* const dst,
                 int srcSize,
                 int outputSize,         /* If endOnInput==endOnInputSize, this value is `dstCapacity` */

                 earlyEnd_directive partialDecoding,  /* full, partial */
                 dict_directive 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 */
                 )
{
    if ((src == NULL) || (outputSize < 0)) { return -1; }

    {   const BYTE* ip = (const BYTE*) src;
        const BYTE* const iend = ip + srcSize;

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

        const BYTE* const dictEnd = (dictStart == NULL) ? NULL : dictStart + dictSize;

        const int checkOffset = (dictSize < (int)(64 KB));


        /* Set up the "end" pointers for the shortcut. */
        const BYTE* const shortiend = iend - 14 /*maxLL*/ - 2 /*offset*/;
        const BYTE* const shortoend = oend - 14 /*maxLL*/ - 18 /*maxML*/;

        const BYTE* match;
        size_t offset;
        unsigned token;
        size_t length;


        DEBUGLOG(5, "LZ4_decompress_generic (srcSize:%i, dstSize:%i)", srcSize, outputSize);

        /* Special cases */
        assert(lowPrefix <= op);
        if (unlikely(outputSize==0)) {
            /* Empty output buffer */
            if (partialDecoding) return 0;
            return ((srcSize==1) && (*ip==0)) ? 0 : -1;
        }
        if (unlikely(srcSize==0)) { return -1; }

    /* LZ4_FAST_DEC_LOOP:
     * designed for modern OoO performance cpus,
     * where copying reliably 32-bytes is preferable to an unpredictable branch.
     * note : fast loop may show a regression for some client arm chips. */
#if LZ4_FAST_DEC_LOOP
        if ((oend - op) < FASTLOOP_SAFE_DISTANCE) {
            DEBUGLOG(6, "skip fast decode loop");
            goto safe_decode;
        }

        /* Fast loop : decode sequences as long as output < oend-FASTLOOP_SAFE_DISTANCE */
        while (1) {
            /* Main fastloop assertion: We can always wildcopy FASTLOOP_SAFE_DISTANCE */
            assert(oend - op >= FASTLOOP_SAFE_DISTANCE);
            assert(ip < iend);
            token = *ip++;
            length = token >> ML_BITS;  /* literal length */

            /* decode literal length */
            if (length == RUN_MASK) {
                size_t const addl = read_variable_length(&ip, iend-RUN_MASK, 1);
                if (addl == rvl_error) { goto _output_error; }
                length += addl;
                if (unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */
                if (unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */

                /* copy literals */
                cpy = op+length;
                LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
                if ((cpy>oend-32) || (ip+length>iend-32)) { goto safe_literal_copy; }
                LZ4_wildCopy32(op, ip, cpy);
                ip += length; op = cpy;
            } else {
                cpy = op+length;
                DEBUGLOG(7, "copy %u bytes in a 16-bytes stripe", (unsigned)length);
                /* We don't need to check oend, since we check it once for each loop below */
                if (ip > iend-(16 + 1/*max lit + offset + nextToken*/)) { goto safe_literal_copy; }
                /* Literals can only be <= 14, but hope compilers optimize better when copy by a register size */
                LZ4_memcpy(op, ip, 16);
                ip += length; op = cpy;
            }

            /* get offset */
            offset = LZ4_readLE16(ip); ip+=2;
            match = op - offset;
            assert(match <= op);  /* overflow check */

            /* get matchlength */
            length = token & ML_MASK;

            if (length == ML_MASK) {
                size_t const addl = read_variable_length(&ip, iend - LASTLITERALS + 1, 0);
                if (addl == rvl_error) { goto _output_error; }
                length += addl;
                length += MINMATCH;
                if (unlikely((uptrval)(op)+length<(uptrval)op)) { goto _output_error; } /* overflow detection */
                if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */
                if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) {
                    goto safe_match_copy;
                }
            } else {
                length += MINMATCH;
                if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) {
                    goto safe_match_copy;
                }

                /* Fastpath check: skip LZ4_wildCopy32 when true */
                if ((dict == withPrefix64k) || (match >= lowPrefix)) {
                    if (offset >= 8) {
                        assert(match >= lowPrefix);
                        assert(match <= op);
                        assert(op + 18 <= oend);

                        LZ4_memcpy(op, match, 8);
                        LZ4_memcpy(op+8, match+8, 8);
                        LZ4_memcpy(op+16, match+16, 2);
                        op += length;
                        continue;
            }   }   }

            if (checkOffset && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */
            /* match starting within external dictionary */
            if ((dict==usingExtDict) && (match < lowPrefix)) {
                assert(dictEnd != NULL);
                if (unlikely(op+length > oend-LASTLITERALS)) {
                    if (partialDecoding) {
                        DEBUGLOG(7, "partialDecoding: dictionary match, close to dstEnd");
                        length = MIN(length, (size_t)(oend-op));
                    } else {
                        goto _output_error;  /* end-of-block condition violated */
                }   }

                if (length <= (size_t)(lowPrefix-match)) {
                    /* match fits entirely within external dictionary : just copy */
                    LZ4_memmove(op, dictEnd - (lowPrefix-match), length);
                    op += length;
                } else {
                    /* match stretches into both external dictionary and current block */
                    size_t const copySize = (size_t)(lowPrefix - match);
                    size_t const restSize = length - copySize;
                    LZ4_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 {
                        LZ4_memcpy(op, lowPrefix, restSize);
                        op += restSize;
                }   }
                continue;
            }

            /* copy match within block */
            cpy = op + length;

            assert((op <= oend) && (oend-op >= 32));
            if (unlikely(offset<16)) {
                LZ4_memcpy_using_offset(op, match, cpy, offset);
            } else {
                LZ4_wildCopy32(op, match, cpy);
            }

            op = cpy;   /* wildcopy correction */
        }
    safe_decode:
#endif

        /* Main Loop : decode remaining sequences where output < FASTLOOP_SAFE_DISTANCE */
        while (1) {
            assert(ip < iend);
            token = *ip++;
            length = token >> ML_BITS;  /* literal length */

            /* A two-stage shortcut for the most common case:
             * 1) If the literal length is 0..14, and there is enough space,
             * enter the shortcut and copy 16 bytes on behalf of the literals
             * (in the fast mode, only 8 bytes can be safely copied this way).
             * 2) Further if the match length is 4..18, copy 18 bytes in a similar
             * manner; but we ensure that there's enough space in the output for
             * those 18 bytes earlier, upon entering the shortcut (in other words,
             * there is a combined check for both stages).
             */
            if ( (length != RUN_MASK)
                /* strictly "less than" on input, to re-enter the loop with at least one byte */
              && likely((ip < shortiend) & (op <= shortoend)) ) {
                /* Copy the literals */
                LZ4_memcpy(op, ip, 16);
                op += length; ip += length;

                /* The second stage: prepare for match copying, decode full info.
                 * If it doesn't work out, the info won't be wasted. */
                length = token & ML_MASK; /* match length */
                offset = LZ4_readLE16(ip); ip += 2;
                match = op - offset;
                assert(match <= op); /* check overflow */

                /* Do not deal with overlapping matches. */
                if ( (length != ML_MASK)
                  && (offset >= 8)
                  && (dict==withPrefix64k || match >= lowPrefix) ) {
                    /* Copy the match. */
                    LZ4_memcpy(op + 0, match + 0, 8);
                    LZ4_memcpy(op + 8, match + 8, 8);
                    LZ4_memcpy(op +16, match +16, 2);
                    op += length + MINMATCH;
                    /* Both stages worked, load the next token. */
                    continue;
                }

                /* The second stage didn't work out, but the info is ready.
                 * Propel it right to the point of match copying. */
                goto _copy_match;
            }

            /* decode literal length */
            if (length == RUN_MASK) {
                size_t const addl = read_variable_length(&ip, iend-RUN_MASK, 1);
                if (addl == rvl_error) { goto _output_error; }
                length += addl;
                if (unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */
                if (unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
            }

            /* copy literals */
            cpy = op+length;
#if LZ4_FAST_DEC_LOOP
        safe_literal_copy:
#endif
            LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
            if ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) {
                /* We've either hit the input parsing restriction or the output parsing restriction.
                 * In the normal scenario, decoding a full block, it must be the last sequence,
                 * otherwise it's an error (invalid input or dimensions).
                 * In partialDecoding scenario, it's necessary to ensure there is no buffer overflow.
                 */
                if (partialDecoding) {
                    /* Since we are partial decoding we may be in this block because of the output parsing
                     * restriction, which is not valid since the output buffer is allowed to be undersized.
                     */
                    DEBUGLOG(7, "partialDecoding: copying literals, close to input or output end")
                    DEBUGLOG(7, "partialDecoding: literal length = %u", (unsigned)length);
                    DEBUGLOG(7, "partialDecoding: remaining space in dstBuffer : %i", (int)(oend - op));
                    DEBUGLOG(7, "partialDecoding: remaining space in srcBuffer : %i", (int)(iend - ip));
                    /* Finishing in the middle of a literals segment,
                     * due to lack of input.
                     */
                    if (ip+length > iend) {
                        length = (size_t)(iend-ip);
                        cpy = op + length;
                    }
                    /* Finishing in the middle of a literals segment,
                     * due to lack of output space.
                     */
                    if (cpy > oend) {
                        cpy = oend;
                        assert(op<=oend);
                        length = (size_t)(oend-op);
                    }
                } else {
                     /* We must be on the last sequence (or invalid) because of the parsing limitations
                      * so check that we exactly consume the input and don't overrun the output buffer.
                      */
                    if ((ip+length != iend) || (cpy > oend)) {
                        DEBUGLOG(6, "should have been last run of literals")
                        DEBUGLOG(6, "ip(%p) + length(%i) = %p != iend (%p)", ip, (int)length, ip+length, iend);
                        DEBUGLOG(6, "or cpy(%p) > oend(%p)", cpy, oend);
                        goto _output_error;
                    }
                }
                LZ4_memmove(op, ip, length);  /* supports overlapping memory regions, for in-place decompression scenarios */
                ip += length;
                op += length;
                /* Necessarily EOF when !partialDecoding.
                 * When partialDecoding, it is EOF if we've either
                 * filled the output buffer or
                 * can't proceed with reading an offset for following match.
                 */
                if (!partialDecoding || (cpy == oend) || (ip >= (iend-2))) {
                    break;
                }
            } else {
                LZ4_wildCopy8(op, ip, cpy);   /* can overwrite up to 8 bytes beyond cpy */
                ip += length; op = cpy;
            }

            /* get offset */
            offset = LZ4_readLE16(ip); ip+=2;
            match = op - offset;

            /* get matchlength */
            length = token & ML_MASK;

    _copy_match:
            if (length == ML_MASK) {
                size_t const addl = read_variable_length(&ip, iend - LASTLITERALS + 1, 0);
                if (addl == rvl_error) { goto _output_error; }
                length += addl;
                if (unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error;   /* overflow detection */
            }
            length += MINMATCH;

#if LZ4_FAST_DEC_LOOP
        safe_match_copy:
#endif
            if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error;   /* Error : offset outside buffers */
            /* match starting within external dictionary */
            if ((dict==usingExtDict) && (match < lowPrefix)) {
                assert(dictEnd != NULL);
                if (unlikely(op+length > oend-LASTLITERALS)) {
                    if (partialDecoding) length = MIN(length, (size_t)(oend-op));
                    else goto _output_error;   /* doesn't respect parsing restriction */
                }

                if (length <= (size_t)(lowPrefix-match)) {
                    /* match fits entirely within external dictionary : just copy */
                    LZ4_memmove(op, dictEnd - (lowPrefix-match), length);
                    op += length;
                } else {
                    /* match stretches into both external dictionary and current block */
                    size_t const copySize = (size_t)(lowPrefix - match);
                    size_t const restSize = length - copySize;
                    LZ4_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 {
                        LZ4_memcpy(op, lowPrefix, restSize);
                        op += restSize;
                }   }
                continue;
            }
            assert(match >= lowPrefix);

            /* copy match within block */
            cpy = op + length;

            /* partialDecoding : may end anywhere within the block */
            assert(op<=oend);
            if (partialDecoding && (cpy > oend-MATCH_SAFEGUARD_DISTANCE)) {
                size_t const mlen = MIN(length, (size_t)(oend-op));
                const BYTE* const matchEnd = match + mlen;
                BYTE* const copyEnd = op + mlen;
                if (matchEnd > op) {   /* overlap copy */
                    while (op < copyEnd) { *op++ = *match++; }
                } else {
                    LZ4_memcpy(op, match, mlen);
                }
                op = copyEnd;
                if (op == oend) { break; }
                continue;
            }

            if (unlikely(offset<8)) {
                LZ4_write32(op, 0);   /* silence msan warning when offset==0 */
                op[0] = match[0];
                op[1] = match[1];
                op[2] = match[2];
                op[3] = match[3];
                match += inc32table[offset];
                LZ4_memcpy(op+4, match, 4);
                match -= dec64table[offset];
            } else {
                LZ4_memcpy(op, match, 8);
                match += 8;
            }
            op += 8;

            if (unlikely(cpy > oend-MATCH_SAFEGUARD_DISTANCE)) {
                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_wildCopy8(op, match, oCopyLimit);
                    match += oCopyLimit - op;
                    op = oCopyLimit;
                }
                while (op < cpy) { *op++ = *match++; }
            } else {
                LZ4_memcpy(op, match, 8);
                if (length > 16)  { LZ4_wildCopy8(op+8, match+8, cpy); }
            }
            op = cpy;   /* wildcopy correction */
        }

        /* end of decoding */
        DEBUGLOG(5, "decoded %i bytes", (int) (((char*)op)-dst));
        return (int) (((char*)op)-dst);     /* Nb of output bytes decoded */

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


/*===== Instantiate the API decoding functions. =====*/

LZ4_FORCE_O2
int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize)
{
    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize,
                                  decode_full_block, noDict,
                                  (BYTE*)dest, NULL, 0);
}

LZ4_FORCE_O2
int LZ4_decompress_safe_partial(const char* src, char* dst, int compressedSize, int targetOutputSize, int dstCapacity)
{
    dstCapacity = MIN(targetOutputSize, dstCapacity);
    return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity,
                                  partial_decode,
                                  noDict, (BYTE*)dst, NULL, 0);
}

LZ4_FORCE_O2
int LZ4_decompress_fast(const char* source, char* dest, int originalSize)
{
    DEBUGLOG(5, "LZ4_decompress_fast");
    return LZ4_decompress_unsafe_generic(
                (const BYTE*)source, (BYTE*)dest, originalSize,
                0, NULL, 0);
}

/*===== Instantiate a few more decoding cases, used more than once. =====*/

LZ4_FORCE_O2 /* Exported, an obsolete API function. */
int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize)
{
    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
                                  decode_full_block, withPrefix64k,
                                  (BYTE*)dest - 64 KB, NULL, 0);
}

LZ4_FORCE_O2
static int LZ4_decompress_safe_partial_withPrefix64k(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity)
{
    dstCapacity = MIN(targetOutputSize, dstCapacity);
    return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity,
                                  partial_decode, withPrefix64k,
                                  (BYTE*)dest - 64 KB, NULL, 0);
}

/* Another obsolete API function, paired with the previous one. */
int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize)
{
    return LZ4_decompress_unsafe_generic(
                (const BYTE*)source, (BYTE*)dest, originalSize,
                64 KB, NULL, 0);
}

LZ4_FORCE_O2
static int LZ4_decompress_safe_withSmallPrefix(const char* source, char* dest, int compressedSize, int maxOutputSize,
                                               size_t prefixSize)
{
    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
                                  decode_full_block, noDict,
                                  (BYTE*)dest-prefixSize, NULL, 0);
}

LZ4_FORCE_O2
static int LZ4_decompress_safe_partial_withSmallPrefix(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity,
                                               size_t prefixSize)
{
    dstCapacity = MIN(targetOutputSize, dstCapacity);
    return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity,
                                  partial_decode, noDict,
                                  (BYTE*)dest-prefixSize, NULL, 0);
}

LZ4_FORCE_O2
int LZ4_decompress_safe_forceExtDict(const char* source, char* dest,
                                     int compressedSize, int maxOutputSize,
                                     const void* dictStart, size_t dictSize)
{
    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
                                  decode_full_block, usingExtDict,
                                  (BYTE*)dest, (const BYTE*)dictStart, dictSize);
}

LZ4_FORCE_O2
int LZ4_decompress_safe_partial_forceExtDict(const char* source, char* dest,
                                     int compressedSize, int targetOutputSize, int dstCapacity,
                                     const void* dictStart, size_t dictSize)
{
    dstCapacity = MIN(targetOutputSize, dstCapacity);
    return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity,
                                  partial_decode, usingExtDict,
                                  (BYTE*)dest, (const BYTE*)dictStart, dictSize);
}

LZ4_FORCE_O2
static int LZ4_decompress_fast_extDict(const char* source, char* dest, int originalSize,
                                       const void* dictStart, size_t dictSize)
{
    return LZ4_decompress_unsafe_generic(
                (const BYTE*)source, (BYTE*)dest, originalSize,
                0, (const BYTE*)dictStart, dictSize);
}

/* The "double dictionary" mode, for use with e.g. ring buffers: the first part
 * of the dictionary is passed as prefix, and the second via dictStart + dictSize.
 * These routines are used only once, in LZ4_decompress_*_continue().
 */
LZ4_FORCE_INLINE
int LZ4_decompress_safe_doubleDict(const char* source, char* dest, int compressedSize, int maxOutputSize,
                                   size_t prefixSize, const void* dictStart, size_t dictSize)
{
    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
                                  decode_full_block, usingExtDict,
                                  (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize);
}

/*===== streaming decompression functions =====*/

LZ4_streamDecode_t* LZ4_createStreamDecode(void)
{
    LZ4_STATIC_ASSERT(sizeof(LZ4_streamDecode_t) >= sizeof(LZ4_streamDecode_t_internal));
    return (LZ4_streamDecode_t*) ALLOC_AND_ZERO(sizeof(LZ4_streamDecode_t));
}

int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
{
    if (LZ4_stream == NULL) { 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;
    if (dictSize) {
        assert(dictionary != NULL);
        lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize;
    } else {
        lz4sd->prefixEnd = (const BYTE*) dictionary;
    }
    lz4sd->externalDict = NULL;
    lz4sd->extDictSize  = 0;
    return 1;
}

/*! LZ4_decoderRingBufferSize() :
 *  when setting a ring buffer for streaming decompression (optional scenario),
 *  provides the minimum size of this ring buffer
 *  to be compatible with any source respecting maxBlockSize condition.
 *  Note : in a ring buffer scenario,
 *  blocks are presumed decompressed next to each other.
 *  When not enough space remains for next block (remainingSize < maxBlockSize),
 *  decoding resumes from beginning of ring buffer.
 * @return : minimum ring buffer size,
 *           or 0 if there is an error (invalid maxBlockSize).
 */
int LZ4_decoderRingBufferSize(int maxBlockSize)
{
    if (maxBlockSize < 0) return 0;
    if (maxBlockSize > LZ4_MAX_INPUT_SIZE) return 0;
    if (maxBlockSize < 16) maxBlockSize = 16;
    return LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize);
}

/*
*_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
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->prefixSize == 0) {
        /* The first call, no dictionary yet. */
        assert(lz4sd->extDictSize == 0);
        result = LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize);
        if (result <= 0) return result;
        lz4sd->prefixSize = (size_t)result;
        lz4sd->prefixEnd = (BYTE*)dest + result;
    } else if (lz4sd->prefixEnd == (BYTE*)dest) {
        /* They're rolling the current segment. */
        if (lz4sd->prefixSize >= 64 KB - 1)
            result = LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize);
        else if (lz4sd->extDictSize == 0)
            result = LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize,
                                                         lz4sd->prefixSize);
        else
            result = LZ4_decompress_safe_doubleDict(source, dest, compressedSize, maxOutputSize,
                                                    lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
        if (result <= 0) return result;
        lz4sd->prefixSize += (size_t)result;
        lz4sd->prefixEnd  += result;
    } else {
        /* The buffer wraps around, or they're switching to another buffer. */
        lz4sd->extDictSize = lz4sd->prefixSize;
        lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
        result = LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize,
                                                  lz4sd->externalDict, lz4sd->extDictSize);
        if (result <= 0) return result;
        lz4sd->prefixSize = (size_t)result;
        lz4sd->prefixEnd  = (BYTE*)dest + result;
    }

    return result;
}

LZ4_FORCE_O2 int
LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode,
                        const char* source, char* dest, int originalSize)
{
    LZ4_streamDecode_t_internal* const lz4sd =
        (assert(LZ4_streamDecode!=NULL), &LZ4_streamDecode->internal_donotuse);
    int result;

    DEBUGLOG(5, "LZ4_decompress_fast_continue (toDecodeSize=%i)", originalSize);
    assert(originalSize >= 0);

    if (lz4sd->prefixSize == 0) {
        DEBUGLOG(5, "first invocation : no prefix nor extDict");
        assert(lz4sd->extDictSize == 0);
        result = LZ4_decompress_fast(source, dest, originalSize);
        if (result <= 0) return result;
        lz4sd->prefixSize = (size_t)originalSize;
        lz4sd->prefixEnd = (BYTE*)dest + originalSize;
    } else if (lz4sd->prefixEnd == (BYTE*)dest) {
        DEBUGLOG(5, "continue using existing prefix");
        result = LZ4_decompress_unsafe_generic(
                        (const BYTE*)source, (BYTE*)dest, originalSize,
                        lz4sd->prefixSize,
                        lz4sd->externalDict, lz4sd->extDictSize);
        if (result <= 0) return result;
        lz4sd->prefixSize += (size_t)originalSize;
        lz4sd->prefixEnd  += originalSize;
    } else {
        DEBUGLOG(5, "prefix becomes extDict");
        lz4sd->extDictSize = lz4sd->prefixSize;
        lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
        result = LZ4_decompress_fast_extDict(source, dest, originalSize,
                                             lz4sd->externalDict, lz4sd->extDictSize);
        if (result <= 0) return result;
        lz4sd->prefixSize = (size_t)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
*/

int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
{
    if (dictSize==0)
        return LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize);
    if (dictStart+dictSize == dest) {
        if (dictSize >= 64 KB - 1) {
            return LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize);
        }
        assert(dictSize >= 0);
        return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, (size_t)dictSize);
    }
    assert(dictSize >= 0);
    return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, (size_t)dictSize);
}

int LZ4_decompress_safe_partial_usingDict(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity, const char* dictStart, int dictSize)
{
    if (dictSize==0)
        return LZ4_decompress_safe_partial(source, dest, compressedSize, targetOutputSize, dstCapacity);
    if (dictStart+dictSize == dest) {
        if (dictSize >= 64 KB - 1) {
            return LZ4_decompress_safe_partial_withPrefix64k(source, dest, compressedSize, targetOutputSize, dstCapacity);
        }
        assert(dictSize >= 0);
        return LZ4_decompress_safe_partial_withSmallPrefix(source, dest, compressedSize, targetOutputSize, dstCapacity, (size_t)dictSize);
    }
    assert(dictSize >= 0);
    return LZ4_decompress_safe_partial_forceExtDict(source, dest, compressedSize, targetOutputSize, dstCapacity, dictStart, (size_t)dictSize);
}

int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize)
{
    if (dictSize==0 || dictStart+dictSize == dest)
        return LZ4_decompress_unsafe_generic(
                        (const BYTE*)source, (BYTE*)dest, originalSize,
                        (size_t)dictSize, NULL, 0);
    assert(dictSize >= 0);
    return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, (size_t)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* src, char* dest, int srcSize)
{
    return LZ4_compress_default(src, dest, srcSize, LZ4_compressBound(srcSize));
}
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 dstCapacity)
{
    return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, dstCapacity, 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 decompression functions 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(void) { return sizeof(LZ4_stream_t); }

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;
}

#endif   /* LZ4_COMMONDEFS_ONLY */