aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/icu/common/ucnv2022.cpp
blob: 5989c1b405a7895adfb09aba15adeece51e3da75 (plain) (blame)
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
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
*   Copyright (C) 2000-2016, International Business Machines
*   Corporation and others.  All Rights Reserved.
**********************************************************************
*   file name:  ucnv2022.cpp
*   encoding:   UTF-8
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2000feb03
*   created by: Markus W. Scherer
*
*   Change history:
*
*   06/29/2000  helena  Major rewrite of the callback APIs.
*   08/08/2000  Ram     Included support for ISO-2022-JP-2
*                       Changed implementation of toUnicode
*                       function
*   08/21/2000  Ram     Added support for ISO-2022-KR
*   08/29/2000  Ram     Seperated implementation of EBCDIC to
*                       ucnvebdc.c
*   09/20/2000  Ram     Added support for ISO-2022-CN
*                       Added implementations for getNextUChar()
*                       for specific 2022 country variants.
*   10/31/2000  Ram     Implemented offsets logic functions
*/

#include "unicode/utypes.h"

#if !UCONFIG_NO_CONVERSION && !UCONFIG_NO_LEGACY_CONVERSION

#include "unicode/ucnv.h"
#include "unicode/uset.h"
#include "unicode/ucnv_err.h"
#include "unicode/ucnv_cb.h"
#include "unicode/utf16.h"
#include "ucnv_imp.h"
#include "ucnv_bld.h"
#include "ucnv_cnv.h"
#include "ucnvmbcs.h"
#include "cstring.h"
#include "cmemory.h"
#include "uassert.h"

#ifdef U_ENABLE_GENERIC_ISO_2022
/*
 * I am disabling the generic ISO-2022 converter after proposing to do so on
 * the icu mailing list two days ago.
 *
 * Reasons:
 * 1. It does not fully support the ISO-2022/ECMA-35 specification with all of
 *    its designation sequences, single shifts with return to the previous state,
 *    switch-with-no-return to UTF-16BE or similar, etc.
 *    This is unlike the language-specific variants like ISO-2022-JP which
 *    require a much smaller repertoire of ISO-2022 features.
 *    These variants continue to be supported.
 * 2. I believe that no one is really using the generic ISO-2022 converter
 *    but rather always one of the language-specific variants.
 *    Note that ICU's generic ISO-2022 converter has always output one escape
 *    sequence followed by UTF-8 for the whole stream.
 * 3. Switching between subcharsets is extremely slow, because each time
 *    the previous converter is closed and a new one opened,
 *    without any kind of caching, least-recently-used list, etc.
 * 4. The code is currently buggy, and given the above it does not seem
 *    reasonable to spend the time on maintenance.
 * 5. ISO-2022 subcharsets should normally be used with 7-bit byte encodings.
 *    This means, for example, that when ISO-8859-7 is designated, the following
 *    ISO-2022 bytes 00..7f should be interpreted as ISO-8859-7 bytes 80..ff.
 *    The ICU ISO-2022 converter does not handle this - and has no information
 *    about which subconverter would have to be shifted vs. which is designed
 *    for 7-bit ISO-2022.
 *
 * Markus Scherer 2003-dec-03
 */
#endif

#if !UCONFIG_ONLY_HTML_CONVERSION
static const char SHIFT_IN_STR[]  = "\x0F";
// static const char SHIFT_OUT_STR[] = "\x0E";
#endif

#define CR      0x0D
#define LF      0x0A
#define H_TAB   0x09
#define V_TAB   0x0B
#define SPACE   0x20

enum {
    HWKANA_START=0xff61,
    HWKANA_END=0xff9f
};

/*
 * 94-character sets with native byte values A1..FE are encoded in ISO 2022
 * as bytes 21..7E. (Subtract 0x80.)
 * 96-character sets with native byte values A0..FF are encoded in ISO 2022
 * as bytes 20..7F. (Subtract 0x80.)
 * Do not encode C1 control codes with native bytes 80..9F
 * as bytes 00..1F (C0 control codes).
 */
enum {
    GR94_START=0xa1,
    GR94_END=0xfe,
    GR96_START=0xa0,
    GR96_END=0xff
};

/*
 * ISO 2022 control codes must not be converted from Unicode
 * because they would mess up the byte stream.
 * The bit mask 0x0800c000 has bits set at bit positions 0xe, 0xf, 0x1b
 * corresponding to SO, SI, and ESC.
 */
#define IS_2022_CONTROL(c) (((c)<0x20) && (((uint32_t)1<<(c))&0x0800c000)!=0)

/* for ISO-2022-JP and -CN implementations */
typedef enum  {
        /* shared values */
        INVALID_STATE=-1,
        ASCII = 0,

        SS2_STATE=0x10,
        SS3_STATE,

        /* JP */
        ISO8859_1 = 1 ,
        ISO8859_7 = 2 ,
        JISX201  = 3,
        JISX208 = 4,
        JISX212 = 5,
        GB2312  =6,
        KSC5601 =7,
        HWKANA_7BIT=8,    /* Halfwidth Katakana 7 bit */

        /* CN */
        /* the first few enum constants must keep their values because they correspond to myConverterArray[] */
        GB2312_1=1,
        ISO_IR_165=2,
        CNS_11643=3,

        /*
         * these are used in StateEnum and ISO2022State variables,
         * but CNS_11643 must be used to index into myConverterArray[]
         */
        CNS_11643_0=0x20,
        CNS_11643_1,
        CNS_11643_2,
        CNS_11643_3,
        CNS_11643_4,
        CNS_11643_5,
        CNS_11643_6,
        CNS_11643_7
} StateEnum;

/* is the StateEnum charset value for a DBCS charset? */
#if UCONFIG_ONLY_HTML_CONVERSION
#define IS_JP_DBCS(cs) (JISX208==(cs))
#else
#define IS_JP_DBCS(cs) (JISX208<=(cs) && (cs)<=KSC5601)
#endif

#define CSM(cs) ((uint16_t)1<<(cs))

/*
 * Each of these charset masks (with index x) contains a bit for a charset in exact correspondence
 * to whether that charset is used in the corresponding version x of ISO_2022,locale=ja,version=x
 *
 * Note: The converter uses some leniency:
 * - The escape sequence ESC ( I for half-width 7-bit Katakana is recognized in
 *   all versions, not just JIS7 and JIS8.
 * - ICU does not distinguish between different versions of JIS X 0208.
 */
#if UCONFIG_ONLY_HTML_CONVERSION
enum { MAX_JA_VERSION=0 };
#else
enum { MAX_JA_VERSION=4 };
#endif
static const uint16_t jpCharsetMasks[MAX_JA_VERSION+1]={
    CSM(ASCII)|CSM(JISX201)|CSM(JISX208)|CSM(HWKANA_7BIT),
#if !UCONFIG_ONLY_HTML_CONVERSION
    CSM(ASCII)|CSM(JISX201)|CSM(JISX208)|CSM(HWKANA_7BIT)|CSM(JISX212),
    CSM(ASCII)|CSM(JISX201)|CSM(JISX208)|CSM(HWKANA_7BIT)|CSM(JISX212)|CSM(GB2312)|CSM(KSC5601)|CSM(ISO8859_1)|CSM(ISO8859_7),
    CSM(ASCII)|CSM(JISX201)|CSM(JISX208)|CSM(HWKANA_7BIT)|CSM(JISX212)|CSM(GB2312)|CSM(KSC5601)|CSM(ISO8859_1)|CSM(ISO8859_7),
    CSM(ASCII)|CSM(JISX201)|CSM(JISX208)|CSM(HWKANA_7BIT)|CSM(JISX212)|CSM(GB2312)|CSM(KSC5601)|CSM(ISO8859_1)|CSM(ISO8859_7)
#endif
};

typedef enum {
        ASCII1=0,
        LATIN1,
        SBCS,
        DBCS,
        MBCS,
        HWKANA
}Cnv2022Type;

typedef struct ISO2022State {
    int8_t cs[4];       /* charset number for SI (G0)/SO (G1)/SS2 (G2)/SS3 (G3) */
    int8_t g;           /* 0..3 for G0..G3 (SI/SO/SS2/SS3) */
    int8_t prevG;       /* g before single shift (SS2 or SS3) */
} ISO2022State;

#define UCNV_OPTIONS_VERSION_MASK 0xf
#define UCNV_2022_MAX_CONVERTERS 10

typedef struct{
    UConverterSharedData *myConverterArray[UCNV_2022_MAX_CONVERTERS];
    UConverter *currentConverter;
    Cnv2022Type currentType;
    ISO2022State toU2022State, fromU2022State;
    uint32_t key;
    uint32_t version;
#ifdef U_ENABLE_GENERIC_ISO_2022
    UBool isFirstBuffer;
#endif
    UBool isEmptySegment;
    char name[30];
    char locale[3];
}UConverterDataISO2022;

/* Protos */
/* ISO-2022 ----------------------------------------------------------------- */

/*Forward declaration */
U_CFUNC void U_CALLCONV
ucnv_fromUnicode_UTF8(UConverterFromUnicodeArgs * args,
                      UErrorCode * err);
U_CFUNC void U_CALLCONV
ucnv_fromUnicode_UTF8_OFFSETS_LOGIC(UConverterFromUnicodeArgs * args,
                                    UErrorCode * err);

#define ESC_2022 0x1B /*ESC*/

typedef enum
{
        INVALID_2022 = -1, /*Doesn't correspond to a valid iso 2022 escape sequence*/
        VALID_NON_TERMINAL_2022 = 0, /*so far corresponds to a valid iso 2022 escape sequence*/
        VALID_TERMINAL_2022 = 1, /*corresponds to a valid iso 2022 escape sequence*/
        VALID_MAYBE_TERMINAL_2022 = 2 /*so far matches one iso 2022 escape sequence, but by adding more characters might match another escape sequence*/
} UCNV_TableStates_2022;

/*
* The way these state transition arrays work is:
* ex : ESC$B is the sequence for JISX208
*      a) First Iteration: char is ESC
*          i) Get the value of ESC from normalize_esq_chars_2022[] with int value of ESC as index
*             int x = normalize_esq_chars_2022[27] which is equal to 1
*         ii) Search for this value in escSeqStateTable_Key_2022[]
*             value of x is stored at escSeqStateTable_Key_2022[0]
*        iii) Save this index as offset
*         iv) Get state of this sequence from escSeqStateTable_Value_2022[]
*             escSeqStateTable_Value_2022[offset], which is VALID_NON_TERMINAL_2022
*     b) Switch on this state and continue to next char
*          i) Get the value of $ from normalize_esq_chars_2022[] with int value of $ as index
*             which is normalize_esq_chars_2022[36] == 4
*         ii) x is currently 1(from above)
*               x<<=5 -- x is now 32
*               x+=normalize_esq_chars_2022[36]
*               now x is 36
*        iii) Search for this value in escSeqStateTable_Key_2022[]
*             value of x is stored at escSeqStateTable_Key_2022[2], so offset is 2
*         iv) Get state of this sequence from escSeqStateTable_Value_2022[]
*             escSeqStateTable_Value_2022[offset], which is VALID_NON_TERMINAL_2022
*     c) Switch on this state and continue to next char
*        i)  Get the value of B from normalize_esq_chars_2022[] with int value of B as index
*        ii) x is currently 36 (from above)
*            x<<=5 -- x is now 1152
*            x+=normalize_esq_chars_2022[66]
*            now x is 1161
*       iii) Search for this value in escSeqStateTable_Key_2022[]
*            value of x is stored at escSeqStateTable_Key_2022[21], so offset is 21
*        iv) Get state of this sequence from escSeqStateTable_Value_2022[21]
*            escSeqStateTable_Value_2022[offset], which is VALID_TERMINAL_2022
*         v) Get the converter name form escSeqStateTable_Result_2022[21] which is JISX208
*/


/*Below are the 3 arrays depicting a state transition table*/
static const int8_t normalize_esq_chars_2022[256] = {
/*       0      1       2       3       4      5       6        7       8       9           */

         0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,1      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,4      ,7      ,29      ,0
        ,2     ,24     ,26     ,27     ,0      ,3      ,23     ,6      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,5      ,8      ,9      ,10     ,11     ,12
        ,13    ,14     ,15     ,16     ,17     ,18     ,19     ,20     ,25     ,28
        ,0     ,0      ,21     ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,22    ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0      ,0
        ,0     ,0      ,0      ,0      ,0      ,0
};

#ifdef U_ENABLE_GENERIC_ISO_2022
/*
 * When the generic ISO-2022 converter is completely removed, not just disabled
 * per #ifdef, then the following state table and the associated tables that are
 * dimensioned with MAX_STATES_2022 should be trimmed.
 *
 * Especially, VALID_MAYBE_TERMINAL_2022 will not be used any more, and all of
 * the associated escape sequences starting with ESC ( B should be removed.
 * This includes the ones with key values 1097 and all of the ones above 1000000.
 *
 * For the latter, the tables can simply be truncated.
 * For the former, since the tables must be kept parallel, it is probably best
 * to simply duplicate an adjacent table cell, parallel in all tables.
 *
 * It may make sense to restructure the tables, especially by using small search
 * tables for the variants instead of indexing them parallel to the table here.
 */
#endif

#define MAX_STATES_2022 74
static const int32_t escSeqStateTable_Key_2022[MAX_STATES_2022] = {
/*   0           1           2           3           4           5           6           7           8           9           */

     1          ,34         ,36         ,39         ,55         ,57         ,60         ,61         ,1093       ,1096
    ,1097       ,1098       ,1099       ,1100       ,1101       ,1102       ,1103       ,1104       ,1105       ,1106
    ,1109       ,1154       ,1157       ,1160       ,1161       ,1176       ,1178       ,1179       ,1254       ,1257
    ,1768       ,1773       ,1957       ,35105      ,36933      ,36936      ,36937      ,36938      ,36939      ,36940
    ,36942      ,36943      ,36944      ,36945      ,36946      ,36947      ,36948      ,37640      ,37642      ,37644
    ,37646      ,37711      ,37744      ,37745      ,37746      ,37747      ,37748      ,40133      ,40136      ,40138
    ,40139      ,40140      ,40141      ,1123363    ,35947624   ,35947625   ,35947626   ,35947627   ,35947629   ,35947630
    ,35947631   ,35947635   ,35947636   ,35947638
};

#ifdef U_ENABLE_GENERIC_ISO_2022

static const char* const escSeqStateTable_Result_2022[MAX_STATES_2022] = {
 /*  0                      1                        2                      3                   4                   5                        6                      7                       8                       9    */

     nullptr                   ,nullptr                   ,nullptr                   ,nullptr               ,nullptr               ,nullptr                   ,nullptr                   ,nullptr                   ,"latin1"               ,"latin1"
    ,"latin1"               ,"ibm-865"              ,"ibm-865"              ,"ibm-865"          ,"ibm-865"          ,"ibm-865"              ,"ibm-865"              ,"JISX0201"             ,"JISX0201"             ,"latin1"
    ,"latin1"               ,nullptr                   ,"JISX-208"             ,"ibm-5478"         ,"JISX-208"         ,nullptr                   ,nullptr                   ,nullptr                   ,nullptr                   ,"UTF8"
    ,"ISO-8859-1"           ,"ISO-8859-7"           ,"JIS-X-208"            ,nullptr               ,"ibm-955"          ,"ibm-367"              ,"ibm-952"              ,"ibm-949"              ,"JISX-212"             ,"ibm-1383"
    ,"ibm-952"              ,"ibm-964"              ,"ibm-964"              ,"ibm-964"          ,"ibm-964"          ,"ibm-964"              ,"ibm-964"              ,"ibm-5478"         ,"ibm-949"              ,"ISO-IR-165"
    ,"CNS-11643-1992,1"     ,"CNS-11643-1992,2"     ,"CNS-11643-1992,3"     ,"CNS-11643-1992,4" ,"CNS-11643-1992,5" ,"CNS-11643-1992,6"     ,"CNS-11643-1992,7"     ,"UTF16_PlatformEndian" ,"UTF16_PlatformEndian" ,"UTF16_PlatformEndian"
    ,"UTF16_PlatformEndian" ,"UTF16_PlatformEndian" ,"UTF16_PlatformEndian" ,nullptr               ,"latin1"           ,"ibm-912"              ,"ibm-913"              ,"ibm-914"              ,"ibm-813"              ,"ibm-1089"
    ,"ibm-920"              ,"ibm-915"              ,"ibm-915"              ,"latin1"
};

#endif

static const int8_t escSeqStateTable_Value_2022[MAX_STATES_2022] = {
/*          0                           1                         2                             3                           4                           5                               6                        7                          8                           9       */
     VALID_NON_TERMINAL_2022    ,VALID_NON_TERMINAL_2022    ,VALID_NON_TERMINAL_2022    ,VALID_NON_TERMINAL_2022     ,VALID_NON_TERMINAL_2022   ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_NON_TERMINAL_2022    ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022
    ,VALID_MAYBE_TERMINAL_2022  ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022
    ,VALID_TERMINAL_2022        ,VALID_NON_TERMINAL_2022    ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_NON_TERMINAL_2022    ,VALID_NON_TERMINAL_2022    ,VALID_NON_TERMINAL_2022    ,VALID_NON_TERMINAL_2022    ,VALID_TERMINAL_2022
    ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_NON_TERMINAL_2022    ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022
    ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022
    ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022
    ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_NON_TERMINAL_2022    ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022
    ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022        ,VALID_TERMINAL_2022
};

/* Type def for refactoring changeState_2022 code*/
typedef enum{
#ifdef U_ENABLE_GENERIC_ISO_2022
    ISO_2022=0,
#endif
    ISO_2022_JP=1,
#if !UCONFIG_ONLY_HTML_CONVERSION
    ISO_2022_KR=2,
    ISO_2022_CN=3
#endif
} Variant2022;

/*********** ISO 2022 Converter Protos ***********/
static void U_CALLCONV
_ISO2022Open(UConverter *cnv, UConverterLoadArgs *pArgs, UErrorCode *errorCode);

static void U_CALLCONV
 _ISO2022Close(UConverter *converter);

static void U_CALLCONV
_ISO2022Reset(UConverter *converter, UConverterResetChoice choice);

U_CDECL_BEGIN
static const char * U_CALLCONV
_ISO2022getName(const UConverter* cnv);
U_CDECL_END

static void  U_CALLCONV
_ISO_2022_WriteSub(UConverterFromUnicodeArgs *args, int32_t offsetIndex, UErrorCode *err);

U_CDECL_BEGIN
static UConverter * U_CALLCONV
_ISO_2022_SafeClone(const UConverter *cnv, void *stackBuffer, int32_t *pBufferSize, UErrorCode *status);

U_CDECL_END

#ifdef U_ENABLE_GENERIC_ISO_2022
static void U_CALLCONV
T_UConverter_toUnicode_ISO_2022_OFFSETS_LOGIC(UConverterToUnicodeArgs* args, UErrorCode* err);
#endif

namespace {

/*const UConverterSharedData _ISO2022Data;*/
extern const UConverterSharedData _ISO2022JPData;

#if !UCONFIG_ONLY_HTML_CONVERSION
extern const UConverterSharedData _ISO2022KRData;
extern const UConverterSharedData _ISO2022CNData;
#endif

}  // namespace

/*************** Converter implementations ******************/

/* The purpose of this function is to get around gcc compiler warnings. */
static inline void
fromUWriteUInt8(UConverter *cnv,
                 const char *bytes, int32_t length,
                 uint8_t **target, const char *targetLimit,
                 int32_t **offsets,
                 int32_t sourceIndex,
                 UErrorCode *pErrorCode)
{
    char *targetChars = (char *)*target;
    ucnv_fromUWriteBytes(cnv, bytes, length, &targetChars, targetLimit,
                         offsets, sourceIndex, pErrorCode);
    *target = (uint8_t*)targetChars;

}

static inline void
setInitialStateToUnicodeKR(UConverter* /*converter*/, UConverterDataISO2022 *myConverterData){
    if(myConverterData->version == 1) {
        UConverter *cnv = myConverterData->currentConverter;

        cnv->toUnicodeStatus=0;     /* offset */
        cnv->mode=0;                /* state */
        cnv->toULength=0;           /* byteIndex */
    }
}

static inline void
setInitialStateFromUnicodeKR(UConverter* converter,UConverterDataISO2022 *myConverterData){
   /* in ISO-2022-KR the designator sequence appears only once
    * in a file so we append it only once
    */
    if( converter->charErrorBufferLength==0){

        converter->charErrorBufferLength = 4;
        converter->charErrorBuffer[0] = 0x1b;
        converter->charErrorBuffer[1] = 0x24;
        converter->charErrorBuffer[2] = 0x29;
        converter->charErrorBuffer[3] = 0x43;
    }
    if(myConverterData->version == 1) {
        UConverter *cnv = myConverterData->currentConverter;

        cnv->fromUChar32=0;
        cnv->fromUnicodeStatus=1;   /* prevLength */
    }
}

static void U_CALLCONV
_ISO2022Open(UConverter *cnv, UConverterLoadArgs *pArgs, UErrorCode *errorCode){

    char myLocale[7]={' ',' ',' ',' ',' ',' ', '\0'};

    cnv->extraInfo = uprv_malloc (sizeof (UConverterDataISO2022));
    if(cnv->extraInfo != nullptr) {
        UConverterNamePieces stackPieces;
        UConverterLoadArgs stackArgs=UCNV_LOAD_ARGS_INITIALIZER;
        UConverterDataISO2022 *myConverterData=(UConverterDataISO2022 *) cnv->extraInfo;
        uint32_t version;

        stackArgs.onlyTestIsLoadable = pArgs->onlyTestIsLoadable;

        uprv_memset(myConverterData, 0, sizeof(UConverterDataISO2022));
        myConverterData->currentType = ASCII1;
        cnv->fromUnicodeStatus =false;
        if(pArgs->locale){
            uprv_strncpy(myLocale, pArgs->locale, sizeof(myLocale)-1);
        }
        version = pArgs->options & UCNV_OPTIONS_VERSION_MASK;
        myConverterData->version = version;
        if(myLocale[0]=='j' && (myLocale[1]=='a'|| myLocale[1]=='p') &&
            (myLocale[2]=='_' || myLocale[2]=='\0'))
        {
            /* open the required converters and cache them */
            if(version>MAX_JA_VERSION) {
                // ICU 55 fails to open a converter for an unsupported version.
                // Previously, it fell back to version 0, but that would yield
                // unexpected behavior.
                *errorCode = U_MISSING_RESOURCE_ERROR;
                return;
            }
            if(jpCharsetMasks[version]&CSM(ISO8859_7)) {
                myConverterData->myConverterArray[ISO8859_7] =
                    ucnv_loadSharedData("ISO8859_7", &stackPieces, &stackArgs, errorCode);
            }
            myConverterData->myConverterArray[JISX208] =
                ucnv_loadSharedData("Shift-JIS", &stackPieces, &stackArgs, errorCode);
            if(jpCharsetMasks[version]&CSM(JISX212)) {
                myConverterData->myConverterArray[JISX212] =
                    ucnv_loadSharedData("jisx-212", &stackPieces, &stackArgs, errorCode);
            }
            if(jpCharsetMasks[version]&CSM(GB2312)) {
                myConverterData->myConverterArray[GB2312] =
                    ucnv_loadSharedData("ibm-5478", &stackPieces, &stackArgs, errorCode);   /* gb_2312_80-1 */
            }
            if(jpCharsetMasks[version]&CSM(KSC5601)) {
                myConverterData->myConverterArray[KSC5601] =
                    ucnv_loadSharedData("ksc_5601", &stackPieces, &stackArgs, errorCode);
            }

            /* set the function pointers to appropriate functions */
            cnv->sharedData=(UConverterSharedData*)(&_ISO2022JPData);
            uprv_strcpy(myConverterData->locale,"ja");

            (void)uprv_strcpy(myConverterData->name,"ISO_2022,locale=ja,version=");
            size_t len = uprv_strlen(myConverterData->name);
            myConverterData->name[len]=(char)(myConverterData->version+(int)'0');
            myConverterData->name[len+1]='\0';
        }
#if !UCONFIG_ONLY_HTML_CONVERSION
        else if(myLocale[0]=='k' && (myLocale[1]=='o'|| myLocale[1]=='r') &&
            (myLocale[2]=='_' || myLocale[2]=='\0'))
        {
            if(version>1) {
                // ICU 55 fails to open a converter for an unsupported version.
                // Previously, it fell back to version 0, but that would yield
                // unexpected behavior.
                *errorCode = U_MISSING_RESOURCE_ERROR;
                return;
            }
            const char *cnvName;
            if(version==1) {
                cnvName="icu-internal-25546";
            } else {
                cnvName="ibm-949";
                myConverterData->version=version=0;
            }
            if(pArgs->onlyTestIsLoadable) {
                ucnv_canCreateConverter(cnvName, errorCode);  /* errorCode carries result */
                uprv_free(cnv->extraInfo);
                cnv->extraInfo=nullptr;
                return;
            } else {
                myConverterData->currentConverter=ucnv_open(cnvName, errorCode);
                if (U_FAILURE(*errorCode)) {
                    _ISO2022Close(cnv);
                    return;
                }

                if(version==1) {
                    (void)uprv_strcpy(myConverterData->name,"ISO_2022,locale=ko,version=1");
                    uprv_memcpy(cnv->subChars, myConverterData->currentConverter->subChars, 4);
                    cnv->subCharLen = myConverterData->currentConverter->subCharLen;
                }else{
                    (void)uprv_strcpy(myConverterData->name,"ISO_2022,locale=ko,version=0");
                }

                /* initialize the state variables */
                setInitialStateToUnicodeKR(cnv, myConverterData);
                setInitialStateFromUnicodeKR(cnv, myConverterData);

                /* set the function pointers to appropriate functions */
                cnv->sharedData=(UConverterSharedData*)&_ISO2022KRData;
                uprv_strcpy(myConverterData->locale,"ko");
            }
        }
        else if(((myLocale[0]=='z' && myLocale[1]=='h') || (myLocale[0]=='c'&& myLocale[1]=='n'))&&
            (myLocale[2]=='_' || myLocale[2]=='\0'))
        {
            if(version>2) {
                // ICU 55 fails to open a converter for an unsupported version.
                // Previously, it fell back to version 0, but that would yield
                // unexpected behavior.
                *errorCode = U_MISSING_RESOURCE_ERROR;
                return;
            }

            /* open the required converters and cache them */
            myConverterData->myConverterArray[GB2312_1] =
                ucnv_loadSharedData("ibm-5478", &stackPieces, &stackArgs, errorCode);
            if(version==1) {
                myConverterData->myConverterArray[ISO_IR_165] =
                    ucnv_loadSharedData("iso-ir-165", &stackPieces, &stackArgs, errorCode);
            }
            myConverterData->myConverterArray[CNS_11643] =
                ucnv_loadSharedData("cns-11643-1992", &stackPieces, &stackArgs, errorCode);


            /* set the function pointers to appropriate functions */
            cnv->sharedData=(UConverterSharedData*)&_ISO2022CNData;
            uprv_strcpy(myConverterData->locale,"cn");

            if (version==0){
                myConverterData->version = 0;
                (void)uprv_strcpy(myConverterData->name,"ISO_2022,locale=zh,version=0");
            }else if (version==1){
                myConverterData->version = 1;
                (void)uprv_strcpy(myConverterData->name,"ISO_2022,locale=zh,version=1");
            }else {
                myConverterData->version = 2;
                (void)uprv_strcpy(myConverterData->name,"ISO_2022,locale=zh,version=2");
            }
        }
#endif  // !UCONFIG_ONLY_HTML_CONVERSION
        else{
#ifdef U_ENABLE_GENERIC_ISO_2022
            myConverterData->isFirstBuffer = true;

            /* append the UTF-8 escape sequence */
            cnv->charErrorBufferLength = 3;
            cnv->charErrorBuffer[0] = 0x1b;
            cnv->charErrorBuffer[1] = 0x25;
            cnv->charErrorBuffer[2] = 0x42;

            cnv->sharedData=(UConverterSharedData*)&_ISO2022Data;
            /* initialize the state variables */
            uprv_strcpy(myConverterData->name,"ISO_2022");
#else
            *errorCode = U_MISSING_RESOURCE_ERROR;
            // Was U_UNSUPPORTED_ERROR but changed in ICU 55 to a more standard
            // data loading error code.
            return;
#endif
        }

        cnv->maxBytesPerUChar=cnv->sharedData->staticData->maxBytesPerChar;

        if(U_FAILURE(*errorCode) || pArgs->onlyTestIsLoadable) {
            _ISO2022Close(cnv);
        }
    } else {
        *errorCode = U_MEMORY_ALLOCATION_ERROR;
    }
}


static void U_CALLCONV
_ISO2022Close(UConverter *converter) {
    UConverterDataISO2022* myData =(UConverterDataISO2022 *) (converter->extraInfo);
    UConverterSharedData **array = myData->myConverterArray;
    int32_t i;

    if (converter->extraInfo != nullptr) {
        /*close the array of converter pointers and free the memory*/
        for (i=0; i<UCNV_2022_MAX_CONVERTERS; i++) {
            if(array[i]!=nullptr) {
                ucnv_unloadSharedDataIfReady(array[i]);
            }
        }

        ucnv_close(myData->currentConverter);

        if(!converter->isExtraLocal){
            uprv_free (converter->extraInfo);
            converter->extraInfo = nullptr;
        }
    }
}

static void U_CALLCONV
_ISO2022Reset(UConverter *converter, UConverterResetChoice choice) {
    UConverterDataISO2022 *myConverterData=(UConverterDataISO2022 *) (converter->extraInfo);
    if(choice<=UCNV_RESET_TO_UNICODE) {
        uprv_memset(&myConverterData->toU2022State, 0, sizeof(ISO2022State));
        myConverterData->key = 0;
        myConverterData->isEmptySegment = false;
    }
    if(choice!=UCNV_RESET_TO_UNICODE) {
        uprv_memset(&myConverterData->fromU2022State, 0, sizeof(ISO2022State));
    }
#ifdef U_ENABLE_GENERIC_ISO_2022
    if(myConverterData->locale[0] == 0){
        if(choice<=UCNV_RESET_TO_UNICODE) {
            myConverterData->isFirstBuffer = true;
            myConverterData->key = 0;
            if (converter->mode == UCNV_SO){
                ucnv_close (myConverterData->currentConverter);
                myConverterData->currentConverter=nullptr;
            }
            converter->mode = UCNV_SI;
        }
        if(choice!=UCNV_RESET_TO_UNICODE) {
            /* re-append UTF-8 escape sequence */
            converter->charErrorBufferLength = 3;
            converter->charErrorBuffer[0] = 0x1b;
            converter->charErrorBuffer[1] = 0x28;
            converter->charErrorBuffer[2] = 0x42;
        }
    }
    else
#endif
    {
        /* reset the state variables */
        if(myConverterData->locale[0] == 'k'){
            if(choice<=UCNV_RESET_TO_UNICODE) {
                setInitialStateToUnicodeKR(converter, myConverterData);
            }
            if(choice!=UCNV_RESET_TO_UNICODE) {
                setInitialStateFromUnicodeKR(converter, myConverterData);
            }
        }
    }
}

U_CDECL_BEGIN

static const char * U_CALLCONV
_ISO2022getName(const UConverter* cnv){
    if(cnv->extraInfo){
        UConverterDataISO2022* myData= (UConverterDataISO2022*)cnv->extraInfo;
        return myData->name;
    }
    return nullptr;
}

U_CDECL_END


/*************** to unicode *******************/
/****************************************************************************
 * Recognized escape sequences are
 * <ESC>(B  ASCII
 * <ESC>.A  ISO-8859-1
 * <ESC>.F  ISO-8859-7
 * <ESC>(J  JISX-201
 * <ESC>(I  JISX-201
 * <ESC>$B  JISX-208
 * <ESC>$@  JISX-208
 * <ESC>$(D JISX-212
 * <ESC>$A  GB2312
 * <ESC>$(C KSC5601
 */
static const int8_t nextStateToUnicodeJP[MAX_STATES_2022]= {
/*      0                1               2               3               4               5               6               7               8               9    */
    INVALID_STATE   ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,SS2_STATE      ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE
    ,ASCII          ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,JISX201        ,HWKANA_7BIT    ,JISX201        ,INVALID_STATE
    ,INVALID_STATE  ,INVALID_STATE  ,JISX208        ,GB2312         ,JISX208        ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE
    ,ISO8859_1      ,ISO8859_7      ,JISX208        ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,KSC5601        ,JISX212        ,INVALID_STATE
    ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE
    ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE
    ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE
    ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE
};

#if !UCONFIG_ONLY_HTML_CONVERSION
/*************** to unicode *******************/
static const int8_t nextStateToUnicodeCN[MAX_STATES_2022]= {
/*      0                1               2               3               4               5               6               7               8               9    */
     INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,SS2_STATE      ,SS3_STATE      ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE
    ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE
    ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE
    ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE
    ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,GB2312_1       ,INVALID_STATE  ,ISO_IR_165
    ,CNS_11643_1    ,CNS_11643_2    ,CNS_11643_3    ,CNS_11643_4    ,CNS_11643_5    ,CNS_11643_6    ,CNS_11643_7    ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE
    ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE
    ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE  ,INVALID_STATE
};
#endif


static UCNV_TableStates_2022
getKey_2022(char c,int32_t* key,int32_t* offset){
    int32_t togo;
    int32_t low = 0;
    int32_t hi = MAX_STATES_2022;
    int32_t oldmid=0;

    togo = normalize_esq_chars_2022[(uint8_t)c];
    if(togo == 0) {
        /* not a valid character anywhere in an escape sequence */
        *key = 0;
        *offset = 0;
        return INVALID_2022;
    }
    togo = (*key << 5) + togo;

    while (hi != low)  /*binary search*/{

        int32_t mid = (hi+low) >> 1; /*Finds median*/

        if (mid == oldmid)
            break;

        if (escSeqStateTable_Key_2022[mid] > togo){
            hi = mid;
        }
        else if (escSeqStateTable_Key_2022[mid] < togo){
            low = mid;
        }
        else /*we found it*/{
            *key = togo;
            *offset = mid;
            return (UCNV_TableStates_2022)escSeqStateTable_Value_2022[mid];
        }
        oldmid = mid;

    }

    *key = 0;
    *offset = 0;
    return INVALID_2022;
}

/*runs through a state machine to determine the escape sequence - codepage correspondence
 */
static void
changeState_2022(UConverter* _this,
                const char** source,
                const char* sourceLimit,
                Variant2022 var,
                UErrorCode* err){
    UCNV_TableStates_2022 value;
    UConverterDataISO2022* myData2022 = ((UConverterDataISO2022*)_this->extraInfo);
    uint32_t key = myData2022->key;
    int32_t offset = 0;
    int8_t initialToULength = _this->toULength;
    char c;

    value = VALID_NON_TERMINAL_2022;
    while (*source < sourceLimit) {
        c = *(*source)++;
        _this->toUBytes[_this->toULength++]=(uint8_t)c;
        value = getKey_2022(c,(int32_t *) &key, &offset);

        switch (value){

        case VALID_NON_TERMINAL_2022 :
            /* continue with the loop */
            break;

        case VALID_TERMINAL_2022:
            key = 0;
            goto DONE;

        case INVALID_2022:
            goto DONE;

        case VALID_MAYBE_TERMINAL_2022:
#ifdef U_ENABLE_GENERIC_ISO_2022
            /* ESC ( B is ambiguous only for ISO_2022 itself */
            if(var == ISO_2022) {
                /* discard toUBytes[] for ESC ( B because this sequence is correct and complete */
                _this->toULength = 0;

                /* TODO need to indicate that ESC ( B was seen; if failure, then need to replay from source or from MBCS-style replay */

                /* continue with the loop */
                value = VALID_NON_TERMINAL_2022;
                break;
            } else
#endif
            {
                /* not ISO_2022 itself, finish here */
                value = VALID_TERMINAL_2022;
                key = 0;
                goto DONE;
            }
        }
    }

DONE:
    myData2022->key = key;

    if (value == VALID_NON_TERMINAL_2022) {
        /* indicate that the escape sequence is incomplete: key!=0 */
        return;
    } else if (value == INVALID_2022 ) {
        *err = U_ILLEGAL_ESCAPE_SEQUENCE;
    } else /* value == VALID_TERMINAL_2022 */ {
        switch(var){
#ifdef U_ENABLE_GENERIC_ISO_2022
        case ISO_2022:
        {
            const char *chosenConverterName = escSeqStateTable_Result_2022[offset];
            if(chosenConverterName == nullptr) {
                /* SS2 or SS3 */
                *err = U_UNSUPPORTED_ESCAPE_SEQUENCE;
                _this->toUCallbackReason = UCNV_UNASSIGNED;
                return;
            }

            _this->mode = UCNV_SI;
            ucnv_close(myData2022->currentConverter);
            myData2022->currentConverter = myUConverter = ucnv_open(chosenConverterName, err);
            if(U_SUCCESS(*err)) {
                myUConverter->fromCharErrorBehaviour = UCNV_TO_U_CALLBACK_STOP;
                _this->mode = UCNV_SO;
            }
            break;
        }
#endif
        case ISO_2022_JP:
            {
                StateEnum tempState=(StateEnum)nextStateToUnicodeJP[offset];
                switch(tempState) {
                case INVALID_STATE:
                    *err = U_UNSUPPORTED_ESCAPE_SEQUENCE;
                    break;
                case SS2_STATE:
                    if(myData2022->toU2022State.cs[2]!=0) {
                        if(myData2022->toU2022State.g<2) {
                            myData2022->toU2022State.prevG=myData2022->toU2022State.g;
                        }
                        myData2022->toU2022State.g=2;
                    } else {
                        /* illegal to have SS2 before a matching designator */
                        *err = U_ILLEGAL_ESCAPE_SEQUENCE;
                    }
                    break;
                /* case SS3_STATE: not used in ISO-2022-JP-x */
                case ISO8859_1:
                case ISO8859_7:
                    if((jpCharsetMasks[myData2022->version] & CSM(tempState)) == 0) {
                        *err = U_UNSUPPORTED_ESCAPE_SEQUENCE;
                    } else {
                        /* G2 charset for SS2 */
                        myData2022->toU2022State.cs[2]=(int8_t)tempState;
                    }
                    break;
                default:
                    if((jpCharsetMasks[myData2022->version] & CSM(tempState)) == 0) {
                        *err = U_UNSUPPORTED_ESCAPE_SEQUENCE;
                    } else {
                        /* G0 charset */
                        myData2022->toU2022State.cs[0]=(int8_t)tempState;
                    }
                    break;
                }
            }
            break;
#if !UCONFIG_ONLY_HTML_CONVERSION
        case ISO_2022_CN:
            {
                StateEnum tempState=(StateEnum)nextStateToUnicodeCN[offset];
                switch(tempState) {
                case INVALID_STATE:
                    *err = U_UNSUPPORTED_ESCAPE_SEQUENCE;
                    break;
                case SS2_STATE:
                    if(myData2022->toU2022State.cs[2]!=0) {
                        if(myData2022->toU2022State.g<2) {
                            myData2022->toU2022State.prevG=myData2022->toU2022State.g;
                        }
                        myData2022->toU2022State.g=2;
                    } else {
                        /* illegal to have SS2 before a matching designator */
                        *err = U_ILLEGAL_ESCAPE_SEQUENCE;
                    }
                    break;
                case SS3_STATE:
                    if(myData2022->toU2022State.cs[3]!=0) {
                        if(myData2022->toU2022State.g<2) {
                            myData2022->toU2022State.prevG=myData2022->toU2022State.g;
                        }
                        myData2022->toU2022State.g=3;
                    } else {
                        /* illegal to have SS3 before a matching designator */
                        *err = U_ILLEGAL_ESCAPE_SEQUENCE;
                    }
                    break;
                case ISO_IR_165:
                    if(myData2022->version==0) {
                        *err = U_UNSUPPORTED_ESCAPE_SEQUENCE;
                        break;
                    }
                    U_FALLTHROUGH;
                case GB2312_1:
                    U_FALLTHROUGH;
                case CNS_11643_1:
                    myData2022->toU2022State.cs[1]=(int8_t)tempState;
                    break;
                case CNS_11643_2:
                    myData2022->toU2022State.cs[2]=(int8_t)tempState;
                    break;
                default:
                    /* other CNS 11643 planes */
                    if(myData2022->version==0) {
                        *err = U_UNSUPPORTED_ESCAPE_SEQUENCE;
                    } else {
                       myData2022->toU2022State.cs[3]=(int8_t)tempState;
                    }
                    break;
                }
            }
            break;
        case ISO_2022_KR:
            if(offset==0x30){
                /* nothing to be done, just accept this one escape sequence */
            } else {
                *err = U_UNSUPPORTED_ESCAPE_SEQUENCE;
            }
            break;
#endif  // !UCONFIG_ONLY_HTML_CONVERSION

        default:
            *err = U_ILLEGAL_ESCAPE_SEQUENCE;
            break;
        }
    }
    if(U_SUCCESS(*err)) {
        _this->toULength = 0;
    } else if(*err==U_ILLEGAL_ESCAPE_SEQUENCE) {
        if(_this->toULength>1) {
            /*
             * Ticket 5691: consistent illegal sequences:
             * - We include at least the first byte (ESC) in the illegal sequence.
             * - If any of the non-initial bytes could be the start of a character,
             *   we stop the illegal sequence before the first one of those.
             *   In escape sequences, all following bytes are "printable", that is,
             *   unless they are completely illegal (>7f in SBCS, outside 21..7e in DBCS),
             *   they are valid single/lead bytes.
             *   For simplicity, we always only report the initial ESC byte as the
             *   illegal sequence and back out all other bytes we looked at.
             */
            /* Back out some bytes. */
            int8_t backOutDistance=_this->toULength-1;
            int8_t bytesFromThisBuffer=_this->toULength-initialToULength;
            if(backOutDistance<=bytesFromThisBuffer) {
                /* same as initialToULength<=1 */
                *source-=backOutDistance;
            } else {
                /* Back out bytes from the previous buffer: Need to replay them. */
                _this->preToULength=(int8_t)(bytesFromThisBuffer-backOutDistance);
                /* same as -(initialToULength-1) */
                /* preToULength is negative! */
                uprv_memcpy(_this->preToU, _this->toUBytes+1, -_this->preToULength);
                *source-=bytesFromThisBuffer;
            }
            _this->toULength=1;
        }
    } else if(*err==U_UNSUPPORTED_ESCAPE_SEQUENCE) {
        _this->toUCallbackReason = UCNV_UNASSIGNED;
    }
}

#if !UCONFIG_ONLY_HTML_CONVERSION
/*Checks the characters of the buffer against valid 2022 escape sequences
*if the match we return a pointer to the initial start of the sequence otherwise
*we return sourceLimit
*/
/*for 2022 looks ahead in the stream
 *to determine the longest possible convertible
 *data stream
 */
static inline const char*
getEndOfBuffer_2022(const char** source,
                   const char* sourceLimit,
                   UBool /*flush*/){

    const char* mySource = *source;

#ifdef U_ENABLE_GENERIC_ISO_2022
    if (*source >= sourceLimit)
        return sourceLimit;

    do{

        if (*mySource == ESC_2022){
            int8_t i;
            int32_t key = 0;
            int32_t offset;
            UCNV_TableStates_2022 value = VALID_NON_TERMINAL_2022;

            /* Kludge: I could not
            * figure out the reason for validating an escape sequence
            * twice - once here and once in changeState_2022().
            * is it possible to have an ESC character in a ISO2022
            * byte stream which is valid in a code page? Is it legal?
            */
            for (i=0;
            (mySource+i < sourceLimit)&&(value == VALID_NON_TERMINAL_2022);
            i++) {
                value =  getKey_2022(*(mySource+i), &key, &offset);
            }
            if (value > 0 || *mySource==ESC_2022)
                return mySource;

            if ((value == VALID_NON_TERMINAL_2022)&&(!flush) )
                return sourceLimit;
        }
    }while (++mySource < sourceLimit);

    return sourceLimit;
#else
    while(mySource < sourceLimit && *mySource != ESC_2022) {
        ++mySource;
    }
    return mySource;
#endif
}
#endif

/* This inline function replicates code in _MBCSFromUChar32() function in ucnvmbcs.c
 * any future change in _MBCSFromUChar32() function should be reflected here.
 * @return number of bytes in *value; negative number if fallback; 0 if no mapping
 */
static inline int32_t
MBCS_FROM_UCHAR32_ISO2022(UConverterSharedData* sharedData,
                                         UChar32 c,
                                         uint32_t* value,
                                         UBool useFallback,
                                         int outputType)
{
    const int32_t *cx;
    const uint16_t *table;
    uint32_t stage2Entry;
    uint32_t myValue;
    int32_t length;
    const uint8_t *p;
    /*
     * TODO(markus): Use and require new, faster MBCS conversion table structures.
     * Use internal version of ucnv_open() that verifies that the new structures are available,
     * else U_INTERNAL_PROGRAM_ERROR.
     */
    /* BMP-only codepages are stored without stage 1 entries for supplementary code points */
    if(c<0x10000 || (sharedData->mbcs.unicodeMask&UCNV_HAS_SUPPLEMENTARY)) {
        table=sharedData->mbcs.fromUnicodeTable;
        stage2Entry=MBCS_STAGE_2_FROM_U(table, c);
        /* get the bytes and the length for the output */
        if(outputType==MBCS_OUTPUT_2){
            myValue=MBCS_VALUE_2_FROM_STAGE_2(sharedData->mbcs.fromUnicodeBytes, stage2Entry, c);
            if(myValue<=0xff) {
                length=1;
            } else {
                length=2;
            }
        } else /* outputType==MBCS_OUTPUT_3 */ {
            p=MBCS_POINTER_3_FROM_STAGE_2(sharedData->mbcs.fromUnicodeBytes, stage2Entry, c);
            myValue=((uint32_t)*p<<16)|((uint32_t)p[1]<<8)|p[2];
            if(myValue<=0xff) {
                length=1;
            } else if(myValue<=0xffff) {
                length=2;
            } else {
                length=3;
            }
        }
        /* is this code point assigned, or do we use fallbacks? */
        if((stage2Entry&(1<<(16+(c&0xf))))!=0) {
            /* assigned */
            *value=myValue;
            return length;
        } else if(FROM_U_USE_FALLBACK(useFallback, c) && myValue!=0) {
            /*
             * We allow a 0 byte output if the "assigned" bit is set for this entry.
             * There is no way with this data structure for fallback output
             * to be a zero byte.
             */
            *value=myValue;
            return -length;
        }
    }

    cx=sharedData->mbcs.extIndexes;
    if(cx!=nullptr) {
        return ucnv_extSimpleMatchFromU(cx, c, value, useFallback);
    }

    /* unassigned */
    return 0;
}

/* This inline function replicates code in _MBCSSingleFromUChar32() function in ucnvmbcs.c
 * any future change in _MBCSSingleFromUChar32() function should be reflected here.
 * @param retval pointer to output byte
 * @return 1 roundtrip byte  0 no mapping  -1 fallback byte
 */
static inline int32_t
MBCS_SINGLE_FROM_UCHAR32(UConverterSharedData* sharedData,
                                       UChar32 c,
                                       uint32_t* retval,
                                       UBool useFallback)
{
    const uint16_t *table;
    int32_t value;
    /* BMP-only codepages are stored without stage 1 entries for supplementary code points */
    if(c>=0x10000 && !(sharedData->mbcs.unicodeMask&UCNV_HAS_SUPPLEMENTARY)) {
        return 0;
    }
    /* convert the Unicode code point in c into codepage bytes (same as in _MBCSFromUnicodeWithOffsets) */
    table=sharedData->mbcs.fromUnicodeTable;
    /* get the byte for the output */
    value=MBCS_SINGLE_RESULT_FROM_U(table, (uint16_t *)sharedData->mbcs.fromUnicodeBytes, c);
    /* is this code point assigned, or do we use fallbacks? */
    *retval=(uint32_t)(value&0xff);
    if(value>=0xf00) {
        return 1;  /* roundtrip */
    } else if(useFallback ? value>=0x800 : value>=0xc00) {
        return -1;  /* fallback taken */
    } else {
        return 0;  /* no mapping */
    }
}

/*
 * Check that the result is a 2-byte value with each byte in the range A1..FE
 * (strict EUC DBCS) before accepting it and subtracting 0x80 from each byte
 * to move it to the ISO 2022 range 21..7E.
 * Return 0 if out of range.
 */
static inline uint32_t
_2022FromGR94DBCS(uint32_t value) {
    if( (uint16_t)(value - 0xa1a1) <= (0xfefe - 0xa1a1) &&
        (uint8_t)(value - 0xa1) <= (0xfe - 0xa1)
    ) {
        return value - 0x8080;  /* shift down to 21..7e byte range */
    } else {
        return 0;  /* not valid for ISO 2022 */
    }
}

#if 0 /* 5691: Call sites now check for validity. They can just += 0x8080 after that. */
/*
 * This method does the reverse of _2022FromGR94DBCS(). Given the 2022 code point, it returns the
 * 2 byte value that is in the range A1..FE for each byte. Otherwise it returns the 2022 code point
 * unchanged. 
 */
static inline uint32_t
_2022ToGR94DBCS(uint32_t value) {
    uint32_t returnValue = value + 0x8080;
    if( (uint16_t)(returnValue - 0xa1a1) <= (0xfefe - 0xa1a1) &&
        (uint8_t)(returnValue - 0xa1) <= (0xfe - 0xa1)) {
        return returnValue;
    } else {
        return value;
    }
}
#endif

#ifdef U_ENABLE_GENERIC_ISO_2022

/**********************************************************************************
*  ISO-2022 Converter
*
*
*/

static void U_CALLCONV
T_UConverter_toUnicode_ISO_2022_OFFSETS_LOGIC(UConverterToUnicodeArgs* args,
                                                           UErrorCode* err){
    const char* mySourceLimit, *realSourceLimit;
    const char* sourceStart;
    const char16_t* myTargetStart;
    UConverter* saveThis;
    UConverterDataISO2022* myData;
    int8_t length;

    saveThis = args->converter;
    myData=((UConverterDataISO2022*)(saveThis->extraInfo));

    realSourceLimit = args->sourceLimit;
    while (args->source < realSourceLimit) {
        if(myData->key == 0) { /* are we in the middle of an escape sequence? */
            /*Find the end of the buffer e.g : Next Escape Seq | end of Buffer*/
            mySourceLimit = getEndOfBuffer_2022(&(args->source), realSourceLimit, args->flush);

            if(args->source < mySourceLimit) {
                if(myData->currentConverter==nullptr) {
                    myData->currentConverter = ucnv_open("ASCII",err);
                    if(U_FAILURE(*err)){
                        return;
                    }

                    myData->currentConverter->fromCharErrorBehaviour = UCNV_TO_U_CALLBACK_STOP;
                    saveThis->mode = UCNV_SO;
                }

                /* convert to before the ESC or until the end of the buffer */
                myData->isFirstBuffer=false;
                sourceStart = args->source;
                myTargetStart = args->target;
                args->converter = myData->currentConverter;
                ucnv_toUnicode(args->converter,
                    &args->target,
                    args->targetLimit,
                    &args->source,
                    mySourceLimit,
                    args->offsets,
                    (UBool)(args->flush && mySourceLimit == realSourceLimit),
                    err);
                args->converter = saveThis;

                if (*err == U_BUFFER_OVERFLOW_ERROR) {
                    /* move the overflow buffer */
                    length = saveThis->UCharErrorBufferLength = myData->currentConverter->UCharErrorBufferLength;
                    myData->currentConverter->UCharErrorBufferLength = 0;
                    if(length > 0) {
                        uprv_memcpy(saveThis->UCharErrorBuffer,
                                    myData->currentConverter->UCharErrorBuffer,
                                    length*U_SIZEOF_UCHAR);
                    }
                    return;
                }

                /*
                 * At least one of:
                 * -Error while converting
                 * -Done with entire buffer
                 * -Need to write offsets or update the current offset
                 *  (leave that up to the code in ucnv.c)
                 *
                 * or else we just stopped at an ESC byte and continue with changeState_2022()
                 */
                if (U_FAILURE(*err) ||
                    (args->source == realSourceLimit) ||
                    (args->offsets != nullptr && (args->target != myTargetStart || args->source != sourceStart) ||
                    (mySourceLimit < realSourceLimit && myData->currentConverter->toULength > 0))
                ) {
                    /* copy partial or error input for truncated detection and error handling */
                    if(U_FAILURE(*err)) {
                        length = saveThis->invalidCharLength = myData->currentConverter->invalidCharLength;
                        if(length > 0) {
                            uprv_memcpy(saveThis->invalidCharBuffer, myData->currentConverter->invalidCharBuffer, length);
                        }
                    } else {
                        length = saveThis->toULength = myData->currentConverter->toULength;
                        if(length > 0) {
                            uprv_memcpy(saveThis->toUBytes, myData->currentConverter->toUBytes, length);
                            if(args->source < mySourceLimit) {
                                *err = U_TRUNCATED_CHAR_FOUND; /* truncated input before ESC */
                            }
                        }
                    }
                    return;
                }
            }
        }

        sourceStart = args->source;
        changeState_2022(args->converter,
               &(args->source),
               realSourceLimit,
               ISO_2022,
               err);
        if (U_FAILURE(*err) || (args->source != sourceStart && args->offsets != nullptr)) {
            /* let the ucnv.c code update its current offset */
            return;
        }
    }
}

#endif

/*
 * To Unicode Callback helper function
 */
static void
toUnicodeCallback(UConverter *cnv,
                  const uint32_t sourceChar, const uint32_t targetUniChar,
                  UErrorCode* err){
    if(sourceChar>0xff){
        cnv->toUBytes[0] = (uint8_t)(sourceChar>>8);
        cnv->toUBytes[1] = (uint8_t)sourceChar;
        cnv->toULength = 2;
    }
    else{
        cnv->toUBytes[0] =(char) sourceChar;
        cnv->toULength = 1;
    }

    if(targetUniChar == (missingCharMarker-1/*0xfffe*/)){
        *err = U_INVALID_CHAR_FOUND;
    }
    else{
        *err = U_ILLEGAL_CHAR_FOUND;
    }
}

/**************************************ISO-2022-JP*************************************************/

/************************************** IMPORTANT **************************************************
* The UConverter_fromUnicode_ISO2022_JP converter does not use ucnv_fromUnicode() functions for SBCS,DBCS and
* MBCS; instead, the values are obtained directly by calling _MBCSFromUChar32().
* The converter iterates over each Unicode codepoint
* to obtain the equivalent codepoints from the codepages supported. Since the source buffer is
* processed one char at a time it would make sense to reduce the extra processing a canned converter
* would do as far as possible.
*
* If the implementation of these macros or structure of sharedData struct change in the future, make
* sure that ISO-2022 is also changed.
***************************************************************************************************
*/

/***************************************************************************************************
* Rules for ISO-2022-jp encoding
* (i)   Escape sequences must be fully contained within a line they should not
*       span new lines or CRs
* (ii)  If the last character on a line is represented by two bytes then an ASCII or
*       JIS-Roman character escape sequence should follow before the line terminates
* (iii) If the first character on the line is represented by two bytes then a two
*       byte character escape sequence should precede it
* (iv)  If no escape sequence is encountered then the characters are ASCII
* (v)   Latin(ISO-8859-1) and Greek(ISO-8859-7) characters must be designated to G2,
*       and invoked with SS2 (ESC N).
* (vi)  If there is any G0 designation in text, there must be a switch to
*       ASCII or to JIS X 0201-Roman before a space character (but not
*       necessarily before "ESC 4/14 2/0" or "ESC N ' '") or control
*       characters such as tab or CRLF.
* (vi)  Supported encodings:
*          ASCII, JISX201, JISX208, JISX212, GB2312, KSC5601, ISO-8859-1,ISO-8859-7
*
*  source : RFC-1554
*
*          JISX201, JISX208,JISX212 : new .cnv data files created
*          KSC5601 : alias to ibm-949 mapping table
*          GB2312 : alias to ibm-1386 mapping table
*          ISO-8859-1 : Algorithmic implemented as LATIN1 case
*          ISO-8859-7 : alias to ibm-9409 mapping table
*/

/* preference order of JP charsets */
static const StateEnum jpCharsetPref[]={
    ASCII,
    JISX201,
    ISO8859_1,
    JISX208,
    ISO8859_7,
    JISX212,
    GB2312,
    KSC5601,
    HWKANA_7BIT
};

/*
 * The escape sequences must be in order of the enum constants like JISX201  = 3,
 * not in order of jpCharsetPref[]!
 */
static const char escSeqChars[][6] ={
    "\x1B\x28\x42",         /* <ESC>(B  ASCII       */
    "\x1B\x2E\x41",         /* <ESC>.A  ISO-8859-1  */
    "\x1B\x2E\x46",         /* <ESC>.F  ISO-8859-7  */
    "\x1B\x28\x4A",         /* <ESC>(J  JISX-201    */
    "\x1B\x24\x42",         /* <ESC>$B  JISX-208    */
    "\x1B\x24\x28\x44",     /* <ESC>$(D JISX-212    */
    "\x1B\x24\x41",         /* <ESC>$A  GB2312      */
    "\x1B\x24\x28\x43",     /* <ESC>$(C KSC5601     */
    "\x1B\x28\x49"          /* <ESC>(I  HWKANA_7BIT */

};
static  const int8_t escSeqCharsLen[] ={
    3, /* length of <ESC>(B  ASCII       */
    3, /* length of <ESC>.A  ISO-8859-1  */
    3, /* length of <ESC>.F  ISO-8859-7  */
    3, /* length of <ESC>(J  JISX-201    */
    3, /* length of <ESC>$B  JISX-208    */
    4, /* length of <ESC>$(D JISX-212    */
    3, /* length of <ESC>$A  GB2312      */
    4, /* length of <ESC>$(C KSC5601     */
    3  /* length of <ESC>(I  HWKANA_7BIT */
};

/*
* The iteration over various code pages works this way:
* i)   Get the currentState from myConverterData->currentState
* ii)  Check if the character is mapped to a valid character in the currentState
*      Yes ->  a) set the initIterState to currentState
*       b) remain in this state until an invalid character is found
*      No  ->  a) go to the next code page and find the character
* iii) Before changing the state increment the current state check if the current state
*      is equal to the intitIteration state
*      Yes ->  A character that cannot be represented in any of the supported encodings
*       break and return a U_INVALID_CHARACTER error
*      No  ->  Continue and find the character in next code page
*
*
* TODO: Implement a priority technique where the users are allowed to set the priority of code pages
*/

/* Map 00..7F to Unicode according to JIS X 0201. */
static inline uint32_t
jisx201ToU(uint32_t value) {
    if(value < 0x5c) {
        return value;
    } else if(value == 0x5c) {
        return 0xa5;
    } else if(value == 0x7e) {
        return 0x203e;
    } else /* value <= 0x7f */ {
        return value;
    }
}

/* Map Unicode to 00..7F according to JIS X 0201. Return U+FFFE if unmappable. */
static inline uint32_t
jisx201FromU(uint32_t value) {
    if(value<=0x7f) {
        if(value!=0x5c && value!=0x7e) {
            return value;
        }
    } else if(value==0xa5) {
        return 0x5c;
    } else if(value==0x203e) {
        return 0x7e;
    }
    return 0xfffe;
}

/*
 * Take a valid Shift-JIS byte pair, check that it is in the range corresponding
 * to JIS X 0208, and convert it to a pair of 21..7E bytes.
 * Return 0 if the byte pair is out of range.
 */
static inline uint32_t
_2022FromSJIS(uint32_t value) {
    uint8_t trail;

    if(value > 0xEFFC) {
        return 0;  /* beyond JIS X 0208 */
    }

    trail = (uint8_t)value;

    value &= 0xff00;  /* lead byte */
    if(value <= 0x9f00) {
        value -= 0x7000;
    } else /* 0xe000 <= value <= 0xef00 */ {
        value -= 0xb000;
    }
    value <<= 1;

    if(trail <= 0x9e) {
        value -= 0x100;
        if(trail <= 0x7e) {
            value |= trail - 0x1f;
        } else {
            value |= trail - 0x20;
        }
    } else /* trail <= 0xfc */ {
        value |= trail - 0x7e;
    }
    return value;
}

/*
 * Convert a pair of JIS X 0208 21..7E bytes to Shift-JIS.
 * If either byte is outside 21..7E make sure that the result is not valid
 * for Shift-JIS so that the converter catches it.
 * Some invalid byte values already turn into equally invalid Shift-JIS
 * byte values and need not be tested explicitly.
 */
static inline void
_2022ToSJIS(uint8_t c1, uint8_t c2, char bytes[2]) {
    if(c1&1) {
        ++c1;
        if(c2 <= 0x5f) {
            c2 += 0x1f;
        } else if(c2 <= 0x7e) {
            c2 += 0x20;
        } else {
            c2 = 0;  /* invalid */
        }
    } else {
        if((uint8_t)(c2-0x21) <= ((0x7e)-0x21)) {
            c2 += 0x7e;
        } else {
            c2 = 0;  /* invalid */
        }
    }
    c1 >>= 1;
    if(c1 <= 0x2f) {
        c1 += 0x70;
    } else if(c1 <= 0x3f) {
        c1 += 0xb0;
    } else {
        c1 = 0;  /* invalid */
    }
    bytes[0] = (char)c1;
    bytes[1] = (char)c2;
}

/*
 * JIS X 0208 has fallbacks from Unicode half-width Katakana to full-width (DBCS)
 * Katakana.
 * Now that we use a Shift-JIS table for JIS X 0208 we need to hardcode these fallbacks
 * because Shift-JIS roundtrips half-width Katakana to single bytes.
 * These were the only fallbacks in ICU's jisx-208.ucm file.
 */
static const uint16_t hwkana_fb[HWKANA_END - HWKANA_START + 1] = {
    0x2123,  /* U+FF61 */
    0x2156,
    0x2157,
    0x2122,
    0x2126,
    0x2572,
    0x2521,
    0x2523,
    0x2525,
    0x2527,
    0x2529,
    0x2563,
    0x2565,
    0x2567,
    0x2543,
    0x213C,  /* U+FF70 */
    0x2522,
    0x2524,
    0x2526,
    0x2528,
    0x252A,
    0x252B,
    0x252D,
    0x252F,
    0x2531,
    0x2533,
    0x2535,
    0x2537,
    0x2539,
    0x253B,
    0x253D,
    0x253F,  /* U+FF80 */
    0x2541,
    0x2544,
    0x2546,
    0x2548,
    0x254A,
    0x254B,
    0x254C,
    0x254D,
    0x254E,
    0x254F,
    0x2552,
    0x2555,
    0x2558,
    0x255B,
    0x255E,
    0x255F,  /* U+FF90 */
    0x2560,
    0x2561,
    0x2562,
    0x2564,
    0x2566,
    0x2568,
    0x2569,
    0x256A,
    0x256B,
    0x256C,
    0x256D,
    0x256F,
    0x2573,
    0x212B,
    0x212C   /* U+FF9F */
};

static void U_CALLCONV
UConverter_fromUnicode_ISO_2022_JP_OFFSETS_LOGIC(UConverterFromUnicodeArgs* args, UErrorCode* err) {
    UConverter *cnv = args->converter;
    UConverterDataISO2022 *converterData;
    ISO2022State *pFromU2022State;
    uint8_t *target = (uint8_t *) args->target;
    const uint8_t *targetLimit = (const uint8_t *) args->targetLimit;
    const char16_t* source = args->source;
    const char16_t* sourceLimit = args->sourceLimit;
    int32_t* offsets = args->offsets;
    UChar32 sourceChar;
    char buffer[8];
    int32_t len, outLen;
    int8_t choices[10];
    int32_t choiceCount;
    uint32_t targetValue = 0;
    UBool useFallback;

    int32_t i;
    int8_t cs, g;

    /* set up the state */
    converterData     = (UConverterDataISO2022*)cnv->extraInfo;
    pFromU2022State   = &converterData->fromU2022State;

    choiceCount = 0;

    /* check if the last codepoint of previous buffer was a lead surrogate*/
    if((sourceChar = cnv->fromUChar32)!=0 && target< targetLimit) {
        goto getTrail;
    }

    while(source < sourceLimit) {
        if(target < targetLimit) {

            sourceChar  = *(source++);
            /*check if the char is a First surrogate*/
            if(U16_IS_SURROGATE(sourceChar)) {
                if(U16_IS_SURROGATE_LEAD(sourceChar)) {
getTrail:
                    /*look ahead to find the trail surrogate*/
                    if(source < sourceLimit) {
                        /* test the following code unit */
                        char16_t trail=(char16_t) *source;
                        if(U16_IS_TRAIL(trail)) {
                            source++;
                            sourceChar=U16_GET_SUPPLEMENTARY(sourceChar, trail);
                            cnv->fromUChar32=0x00;
                            /* convert this supplementary code point */
                            /* exit this condition tree */
                        } else {
                            /* this is an unmatched lead code unit (1st surrogate) */
                            /* callback(illegal) */
                            *err=U_ILLEGAL_CHAR_FOUND;
                            cnv->fromUChar32=sourceChar;
                            break;
                        }
                    } else {
                        /* no more input */
                        cnv->fromUChar32=sourceChar;
                        break;
                    }
                } else {
                    /* this is an unmatched trail code unit (2nd surrogate) */
                    /* callback(illegal) */
                    *err=U_ILLEGAL_CHAR_FOUND;
                    cnv->fromUChar32=sourceChar;
                    break;
                }
            }

            /* do not convert SO/SI/ESC */
            if(IS_2022_CONTROL(sourceChar)) {
                /* callback(illegal) */
                *err=U_ILLEGAL_CHAR_FOUND;
                cnv->fromUChar32=sourceChar;
                break;
            }

            /* do the conversion */

            if(choiceCount == 0) {
                uint16_t csm;

                /*
                 * The csm variable keeps track of which charsets are allowed
                 * and not used yet while building the choices[].
                 */
                csm = jpCharsetMasks[converterData->version];
                choiceCount = 0;

                /* JIS7/8: try single-byte half-width Katakana before JISX208 */
                if(converterData->version == 3 || converterData->version == 4) {
                    choices[choiceCount++] = (int8_t)HWKANA_7BIT;
                }
                /* Do not try single-byte half-width Katakana for other versions. */
                csm &= ~CSM(HWKANA_7BIT);

                /* try the current G0 charset */
                choices[choiceCount++] = cs = pFromU2022State->cs[0];
                csm &= ~CSM(cs);

                /* try the current G2 charset */
                if((cs = pFromU2022State->cs[2]) != 0) {
                    choices[choiceCount++] = cs;
                    csm &= ~CSM(cs);
                }

                /* try all the other possible charsets */
                for(i = 0; i < UPRV_LENGTHOF(jpCharsetPref); ++i) {
                    cs = (int8_t)jpCharsetPref[i];
                    if(CSM(cs) & csm) {
                        choices[choiceCount++] = cs;
                        csm &= ~CSM(cs);
                    }
                }
            }

            cs = g = 0;
            /*
             * len==0: no mapping found yet
             * len<0: found a fallback result: continue looking for a roundtrip but no further fallbacks
             * len>0: found a roundtrip result, done
             */
            len = 0;
            /*
             * We will turn off useFallback after finding a fallback,
             * but we still get fallbacks from PUA code points as usual.
             * Therefore, we will also need to check that we don't overwrite
             * an early fallback with a later one.
             */
            useFallback = cnv->useFallback;

            for(i = 0; i < choiceCount && len <= 0; ++i) {
                uint32_t value;
                int32_t len2;
                int8_t cs0 = choices[i];
                switch(cs0) {
                case ASCII:
                    if(sourceChar <= 0x7f) {
                        targetValue = (uint32_t)sourceChar;
                        len = 1;
                        cs = cs0;
                        g = 0;
                    }
                    break;
                case ISO8859_1:
                    if(GR96_START <= sourceChar && sourceChar <= GR96_END) {
                        targetValue = (uint32_t)sourceChar - 0x80;
                        len = 1;
                        cs = cs0;
                        g = 2;
                    }
                    break;
                case HWKANA_7BIT:
                    if((uint32_t)(sourceChar - HWKANA_START) <= (HWKANA_END - HWKANA_START)) {
                        if(converterData->version==3) {
                            /* JIS7: use G1 (SO) */
                            /* Shift U+FF61..U+FF9F to bytes 21..5F. */
                            targetValue = (uint32_t)(sourceChar - (HWKANA_START - 0x21));
                            len = 1;
                            pFromU2022State->cs[1] = cs = cs0; /* do not output an escape sequence */
                            g = 1;
                        } else if(converterData->version==4) {
                            /* JIS8: use 8-bit bytes with any single-byte charset, see escape sequence output below */
                            /* Shift U+FF61..U+FF9F to bytes A1..DF. */
                            targetValue = (uint32_t)(sourceChar - (HWKANA_START - 0xa1));
                            len = 1;

                            cs = pFromU2022State->cs[0];
                            if(IS_JP_DBCS(cs)) {
                                /* switch from a DBCS charset to JISX201 */
                                cs = (int8_t)JISX201;
                            }
                            /* else stay in the current G0 charset */
                            g = 0;
                        }
                        /* else do not use HWKANA_7BIT with other versions */
                    }
                    break;
                case JISX201:
                    /* G0 SBCS */
                    value = jisx201FromU(sourceChar);
                    if(value <= 0x7f) {
                        targetValue = value;
                        len = 1;
                        cs = cs0;
                        g = 0;
                        useFallback = false;
                    }
                    break;
                case JISX208:
                    /* G0 DBCS from Shift-JIS table */
                    len2 = MBCS_FROM_UCHAR32_ISO2022(
                                converterData->myConverterArray[cs0],
                                sourceChar, &value,
                                useFallback, MBCS_OUTPUT_2);
                    if(len2 == 2 || (len2 == -2 && len == 0)) {  /* only accept DBCS: abs(len)==2 */
                        value = _2022FromSJIS(value);
                        if(value != 0) {
                            targetValue = value;
                            len = len2;
                            cs = cs0;
                            g = 0;
                            useFallback = false;
                        }
                    } else if(len == 0 && useFallback &&
                              (uint32_t)(sourceChar - HWKANA_START) <= (HWKANA_END - HWKANA_START)) {
                        targetValue = hwkana_fb[sourceChar - HWKANA_START];
                        len = -2;
                        cs = cs0;
                        g = 0;
                        useFallback = false;
                    }
                    break;
                case ISO8859_7:
                    /* G0 SBCS forced to 7-bit output */
                    len2 = MBCS_SINGLE_FROM_UCHAR32(
                                converterData->myConverterArray[cs0],
                                sourceChar, &value,
                                useFallback);
                    if(len2 != 0 && !(len2 < 0 && len != 0) && GR96_START <= value && value <= GR96_END) {
                        targetValue = value - 0x80;
                        len = len2;
                        cs = cs0;
                        g = 2;
                        useFallback = false;
                    }
                    break;
                default:
                    /* G0 DBCS */
                    len2 = MBCS_FROM_UCHAR32_ISO2022(
                                converterData->myConverterArray[cs0],
                                sourceChar, &value,
                                useFallback, MBCS_OUTPUT_2);
                    if(len2 == 2 || (len2 == -2 && len == 0)) {  /* only accept DBCS: abs(len)==2 */
                        if(cs0 == KSC5601) {
                            /*
                             * Check for valid bytes for the encoding scheme.
                             * This is necessary because the sub-converter (windows-949)
                             * has a broader encoding scheme than is valid for 2022.
                             */
                            value = _2022FromGR94DBCS(value);
                            if(value == 0) {
                                break;
                            }
                        }
                        targetValue = value;
                        len = len2;
                        cs = cs0;
                        g = 0;
                        useFallback = false;
                    }
                    break;
                }
            }

            if(len != 0) {
                if(len < 0) {
                    len = -len;  /* fallback */
                }
                outLen = 0; /* count output bytes */

                /* write SI if necessary (only for JIS7) */
                if(pFromU2022State->g == 1 && g == 0) {
                    buffer[outLen++] = UCNV_SI;
                    pFromU2022State->g = 0;
                }

                /* write the designation sequence if necessary */
                if(cs != pFromU2022State->cs[g]) {
                    int32_t escLen = escSeqCharsLen[cs];
                    uprv_memcpy(buffer + outLen, escSeqChars[cs], escLen);
                    outLen += escLen;
                    pFromU2022State->cs[g] = cs;

                    /* invalidate the choices[] */
                    choiceCount = 0;
                }

                /* write the shift sequence if necessary */
                if(g != pFromU2022State->g) {
                    switch(g) {
                    /* case 0 handled before writing escapes */
                    case 1:
                        buffer[outLen++] = UCNV_SO;
                        pFromU2022State->g = 1;
                        break;
                    default: /* case 2 */
                        buffer[outLen++] = 0x1b;
                        buffer[outLen++] = 0x4e;
                        break;
                    /* no case 3: no SS3 in ISO-2022-JP-x */
                    }
                }

                /* write the output bytes */
                if(len == 1) {
                    buffer[outLen++] = (char)targetValue;
                } else /* len == 2 */ {
                    buffer[outLen++] = (char)(targetValue >> 8);
                    buffer[outLen++] = (char)targetValue;
                }
            } else {
                /*
                 * if we cannot find the character after checking all codepages
                 * then this is an error
                 */
                *err = U_INVALID_CHAR_FOUND;
                cnv->fromUChar32=sourceChar;
                break;
            }

            if(sourceChar == CR || sourceChar == LF) {
                /* reset the G2 state at the end of a line (conversion got us into ASCII or JISX201 already) */
                pFromU2022State->cs[2] = 0;
                choiceCount = 0;
            }

            /* output outLen>0 bytes in buffer[] */
            if(outLen == 1) {
                *target++ = buffer[0];
                if(offsets) {
                    *offsets++ = (int32_t)(source - args->source - 1); /* -1: known to be ASCII */
                }
            } else if(outLen == 2 && (target + 2) <= targetLimit) {
                *target++ = buffer[0];
                *target++ = buffer[1];
                if(offsets) {
                    int32_t sourceIndex = (int32_t)(source - args->source - U16_LENGTH(sourceChar));
                    *offsets++ = sourceIndex;
                    *offsets++ = sourceIndex;
                }
            } else {
                fromUWriteUInt8(
                    cnv,
                    buffer, outLen,
                    &target, (const char *)targetLimit,
                    &offsets, (int32_t)(source - args->source - U16_LENGTH(sourceChar)),
                    err);
                if(U_FAILURE(*err)) {
                    break;
                }
            }
        } /* end if(myTargetIndex<myTargetLength) */
        else{
            *err =U_BUFFER_OVERFLOW_ERROR;
            break;
        }

    }/* end while(mySourceIndex<mySourceLength) */

    /*
     * the end of the input stream and detection of truncated input
     * are handled by the framework, but for ISO-2022-JP conversion
     * we need to be in ASCII mode at the very end
     *
     * conditions:
     *   successful
     *   in SO mode or not in ASCII mode
     *   end of input and no truncated input
     */
    if( U_SUCCESS(*err) &&
        (pFromU2022State->g!=0 || pFromU2022State->cs[0]!=ASCII) &&
        args->flush && source>=sourceLimit && cnv->fromUChar32==0
    ) {
        int32_t sourceIndex;

        outLen = 0;

        if(pFromU2022State->g != 0) {
            buffer[outLen++] = UCNV_SI;
            pFromU2022State->g = 0;
        }

        if(pFromU2022State->cs[0] != ASCII) {
            int32_t escLen = escSeqCharsLen[ASCII];
            uprv_memcpy(buffer + outLen, escSeqChars[ASCII], escLen);
            outLen += escLen;
            pFromU2022State->cs[0] = (int8_t)ASCII;
        }

        /* get the source index of the last input character */
        /*
         * TODO this would be simpler and more reliable if we used a pair
         * of sourceIndex/prevSourceIndex like in ucnvmbcs.c
         * so that we could simply use the prevSourceIndex here;
         * this code gives an incorrect result for the rare case of an unmatched
         * trail surrogate that is alone in the last buffer of the text stream
         */
        sourceIndex=(int32_t)(source-args->source);
        if(sourceIndex>0) {
            --sourceIndex;
            if( U16_IS_TRAIL(args->source[sourceIndex]) &&
                (sourceIndex==0 || U16_IS_LEAD(args->source[sourceIndex-1]))
            ) {
                --sourceIndex;
            }
        } else {
            sourceIndex=-1;
        }

        fromUWriteUInt8(
            cnv,
            buffer, outLen,
            &target, (const char *)targetLimit,
            &offsets, sourceIndex,
            err);
    }

    /*save the state and return */
    args->source = source;
    args->target = (char*)target;
}

/*************** to unicode *******************/

static void U_CALLCONV
UConverter_toUnicode_ISO_2022_JP_OFFSETS_LOGIC(UConverterToUnicodeArgs *args,
                                               UErrorCode* err){
    char tempBuf[2];
    const char *mySource = (char *) args->source;
    char16_t *myTarget = args->target;
    const char *mySourceLimit = args->sourceLimit;
    uint32_t targetUniChar = 0x0000;
    uint32_t mySourceChar = 0x0000;
    uint32_t tmpSourceChar = 0x0000;
    UConverterDataISO2022* myData;
    ISO2022State *pToU2022State;
    StateEnum cs;

    myData=(UConverterDataISO2022*)(args->converter->extraInfo);
    pToU2022State = &myData->toU2022State;

    if(myData->key != 0) {
        /* continue with a partial escape sequence */
        goto escape;
    } else if(args->converter->toULength == 1 && mySource < mySourceLimit && myTarget < args->targetLimit) {
        /* continue with a partial double-byte character */
        mySourceChar = args->converter->toUBytes[0];
        args->converter->toULength = 0;
        cs = (StateEnum)pToU2022State->cs[pToU2022State->g];
        targetUniChar = missingCharMarker;
        goto getTrailByte;
    }

    while(mySource < mySourceLimit){

        targetUniChar =missingCharMarker;

        if(myTarget < args->targetLimit){

            mySourceChar= (unsigned char) *mySource++;

            switch(mySourceChar) {
            case UCNV_SI:
                if(myData->version==3) {
                    pToU2022State->g=0;
                    continue;
                } else {
                    /* only JIS7 uses SI/SO, not ISO-2022-JP-x */
                    myData->isEmptySegment = false;	/* reset this, we have a different error */
                    break;
                }

            case UCNV_SO:
                if(myData->version==3) {
                    /* JIS7: switch to G1 half-width Katakana */
                    pToU2022State->cs[1] = (int8_t)HWKANA_7BIT;
                    pToU2022State->g=1;
                    continue;
                } else {
                    /* only JIS7 uses SI/SO, not ISO-2022-JP-x */
                    myData->isEmptySegment = false;	/* reset this, we have a different error */
                    break;
                }

            case ESC_2022:
                mySource--;
escape:
                {
                    const char * mySourceBefore = mySource;
                    int8_t toULengthBefore = args->converter->toULength;

                    changeState_2022(args->converter,&(mySource),
                        mySourceLimit, ISO_2022_JP,err);

                    /* If in ISO-2022-JP only and we successfully completed an escape sequence, but previous segment was empty, create an error */
                    if(myData->version==0 && myData->key==0 && U_SUCCESS(*err) && myData->isEmptySegment) {
                        *err = U_ILLEGAL_ESCAPE_SEQUENCE;
                        args->converter->toUCallbackReason = UCNV_IRREGULAR;
                        args->converter->toULength = (int8_t)(toULengthBefore + (mySource - mySourceBefore));
                    }
                }

                /* invalid or illegal escape sequence */
                if(U_FAILURE(*err)){
                    args->target = myTarget;
                    args->source = mySource;
                    myData->isEmptySegment = false;	/* Reset to avoid future spurious errors */
                    return;
                }
                /* If we successfully completed an escape sequence, we begin a new segment, empty so far */
                if(myData->key==0) {
                    myData->isEmptySegment = true;
                }
                continue;

            /* ISO-2022-JP does not use single-byte (C1) SS2 and SS3 */

            case CR:
            case LF:
                /* automatically reset to single-byte mode */
                if((StateEnum)pToU2022State->cs[0] != ASCII && (StateEnum)pToU2022State->cs[0] != JISX201) {
                    pToU2022State->cs[0] = (int8_t)ASCII;
                }
                pToU2022State->cs[2] = 0;
                pToU2022State->g = 0;
                U_FALLTHROUGH;
            default:
                /* convert one or two bytes */
                myData->isEmptySegment = false;
                cs = (StateEnum)pToU2022State->cs[pToU2022State->g];
                if( (uint8_t)(mySourceChar - 0xa1) <= (0xdf - 0xa1) && myData->version==4 &&
                    !IS_JP_DBCS(cs)
                ) {
                    /* 8-bit halfwidth katakana in any single-byte mode for JIS8 */
                    targetUniChar = mySourceChar + (HWKANA_START - 0xa1);

                    /* return from a single-shift state to the previous one */
                    if(pToU2022State->g >= 2) {
                        pToU2022State->g=pToU2022State->prevG;
                    }
                } else switch(cs) {
                case ASCII:
                    if(mySourceChar <= 0x7f) {
                        targetUniChar = mySourceChar;
                    }
                    break;
                case ISO8859_1:
                    if(mySourceChar <= 0x7f) {
                        targetUniChar = mySourceChar + 0x80;
                    }
                    /* return from a single-shift state to the previous one */
                    pToU2022State->g=pToU2022State->prevG;
                    break;
                case ISO8859_7:
                    if(mySourceChar <= 0x7f) {
                        /* convert mySourceChar+0x80 to use a normal 8-bit table */
                        targetUniChar =
                            _MBCS_SINGLE_SIMPLE_GET_NEXT_BMP(
                                myData->myConverterArray[cs],
                                mySourceChar + 0x80);
                    }
                    /* return from a single-shift state to the previous one */
                    pToU2022State->g=pToU2022State->prevG;
                    break;
                case JISX201:
                    if(mySourceChar <= 0x7f) {
                        targetUniChar = jisx201ToU(mySourceChar);
                    }
                    break;
                case HWKANA_7BIT:
                    if((uint8_t)(mySourceChar - 0x21) <= (0x5f - 0x21)) {
                        /* 7-bit halfwidth Katakana */
                        targetUniChar = mySourceChar + (HWKANA_START - 0x21);
                    }
                    break;
                default:
                    /* G0 DBCS */
                    if(mySource < mySourceLimit) {
                        int leadIsOk, trailIsOk;
                        uint8_t trailByte;
getTrailByte:
                        trailByte = (uint8_t)*mySource;
                        /*
                         * Ticket 5691: consistent illegal sequences:
                         * - We include at least the first byte in the illegal sequence.
                         * - If any of the non-initial bytes could be the start of a character,
                         *   we stop the illegal sequence before the first one of those.
                         *
                         * In ISO-2022 DBCS, if the second byte is in the 21..7e range or is
                         * an ESC/SO/SI, we report only the first byte as the illegal sequence.
                         * Otherwise we convert or report the pair of bytes.
                         */
                        leadIsOk = (uint8_t)(mySourceChar - 0x21) <= (0x7e - 0x21);
                        trailIsOk = (uint8_t)(trailByte - 0x21) <= (0x7e - 0x21);
                        if (leadIsOk && trailIsOk) {
                            ++mySource;
                            tmpSourceChar = (mySourceChar << 8) | trailByte;
                            if(cs == JISX208) {
                                _2022ToSJIS((uint8_t)mySourceChar, trailByte, tempBuf);
                                mySourceChar = tmpSourceChar;
                            } else {
                                /* Copy before we modify tmpSourceChar so toUnicodeCallback() sees the correct bytes. */
                                mySourceChar = tmpSourceChar;
                                if (cs == KSC5601) {
                                    tmpSourceChar += 0x8080;  /* = _2022ToGR94DBCS(tmpSourceChar) */
                                }
                                tempBuf[0] = (char)(tmpSourceChar >> 8);
                                tempBuf[1] = (char)(tmpSourceChar);
                            }
                            targetUniChar = ucnv_MBCSSimpleGetNextUChar(myData->myConverterArray[cs], tempBuf, 2, false);
                        } else if (!(trailIsOk || IS_2022_CONTROL(trailByte))) {
                            /* report a pair of illegal bytes if the second byte is not a DBCS starter */
                            ++mySource;
                            /* add another bit so that the code below writes 2 bytes in case of error */
                            mySourceChar = 0x10000 | (mySourceChar << 8) | trailByte;
                        }
                    } else {
                        args->converter->toUBytes[0] = (uint8_t)mySourceChar;
                        args->converter->toULength = 1;
                        goto endloop;
                    }
                }  /* End of inner switch */
                break;
            }  /* End of outer switch */
            if(targetUniChar < (missingCharMarker-1/*0xfffe*/)){
                if(args->offsets){
                    args->offsets[myTarget - args->target] = (int32_t)(mySource - args->source - (mySourceChar <= 0xff ? 1 : 2));
                }
                *(myTarget++)=(char16_t)targetUniChar;
            }
            else if(targetUniChar > missingCharMarker){
                /* disassemble the surrogate pair and write to output*/
                targetUniChar-=0x0010000;
                *myTarget = (char16_t)(0xd800+(char16_t)(targetUniChar>>10));
                if(args->offsets){
                    args->offsets[myTarget - args->target] = (int32_t)(mySource - args->source - (mySourceChar <= 0xff ? 1 : 2));
                }
                ++myTarget;
                if(myTarget< args->targetLimit){
                    *myTarget = (char16_t)(0xdc00+(char16_t)(targetUniChar&0x3ff));
                    if(args->offsets){
                        args->offsets[myTarget - args->target] = (int32_t)(mySource - args->source - (mySourceChar <= 0xff ? 1 : 2));
                    }
                    ++myTarget;
                }else{
                    args->converter->UCharErrorBuffer[args->converter->UCharErrorBufferLength++]=
                                    (char16_t)(0xdc00+(char16_t)(targetUniChar&0x3ff));
                }

            }
            else{
                /* Call the callback function*/
                toUnicodeCallback(args->converter,mySourceChar,targetUniChar,err);
                break;
            }
        }
        else{    /* goes with "if(myTarget < args->targetLimit)"  way up near top of function */
            *err =U_BUFFER_OVERFLOW_ERROR;
            break;
        }
    }
endloop:
    args->target = myTarget;
    args->source = mySource;
}


#if !UCONFIG_ONLY_HTML_CONVERSION
/***************************************************************
*   Rules for ISO-2022-KR encoding
*   i) The KSC5601 designator sequence should appear only once in a file,
*      at the beginning of a line before any KSC5601 characters. This usually
*      means that it appears by itself on the first line of the file
*  ii) There are only 2 shifting sequences SO to shift into double byte mode
*      and SI to shift into single byte mode
*/
static void U_CALLCONV
UConverter_fromUnicode_ISO_2022_KR_OFFSETS_LOGIC_IBM(UConverterFromUnicodeArgs* args, UErrorCode* err){

    UConverter* saveConv = args->converter;
    UConverterDataISO2022 *myConverterData=(UConverterDataISO2022*)saveConv->extraInfo;
    args->converter=myConverterData->currentConverter;

    myConverterData->currentConverter->fromUChar32 = saveConv->fromUChar32;
    ucnv_MBCSFromUnicodeWithOffsets(args,err);
    saveConv->fromUChar32 = myConverterData->currentConverter->fromUChar32;

    if(*err == U_BUFFER_OVERFLOW_ERROR) {
        if(myConverterData->currentConverter->charErrorBufferLength > 0) {
            uprv_memcpy(
                saveConv->charErrorBuffer,
                myConverterData->currentConverter->charErrorBuffer,
                myConverterData->currentConverter->charErrorBufferLength);
        }
        saveConv->charErrorBufferLength = myConverterData->currentConverter->charErrorBufferLength;
        myConverterData->currentConverter->charErrorBufferLength = 0;
    }
    args->converter=saveConv;
}

static void U_CALLCONV
UConverter_fromUnicode_ISO_2022_KR_OFFSETS_LOGIC(UConverterFromUnicodeArgs* args, UErrorCode* err){

    const char16_t *source = args->source;
    const char16_t *sourceLimit = args->sourceLimit;
    unsigned char *target = (unsigned char *) args->target;
    unsigned char *targetLimit = (unsigned char *) args->targetLimit;
    int32_t* offsets = args->offsets;
    uint32_t targetByteUnit = 0x0000;
    UChar32 sourceChar = 0x0000;
    UBool isTargetByteDBCS;
    UBool oldIsTargetByteDBCS;
    UConverterDataISO2022 *converterData;
    UConverterSharedData* sharedData;
    UBool useFallback;
    int32_t length =0;

    converterData=(UConverterDataISO2022*)args->converter->extraInfo;
    /* if the version is 1 then the user is requesting
     * conversion with ibm-25546 pass the arguments to
     * MBCS converter and return
     */
    if(converterData->version==1){
        UConverter_fromUnicode_ISO_2022_KR_OFFSETS_LOGIC_IBM(args,err);
        return;
    }

    /* initialize data */
    sharedData = converterData->currentConverter->sharedData;
    useFallback = args->converter->useFallback;
    isTargetByteDBCS=(UBool)args->converter->fromUnicodeStatus;
    oldIsTargetByteDBCS = isTargetByteDBCS;

    isTargetByteDBCS   = (UBool) args->converter->fromUnicodeStatus;
    if((sourceChar = args->converter->fromUChar32)!=0 && target <targetLimit) {
        goto getTrail;
    }
    while(source < sourceLimit){

        targetByteUnit = missingCharMarker;

        if(target < (unsigned char*) args->targetLimit){
            sourceChar = *source++;

            /* do not convert SO/SI/ESC */
            if(IS_2022_CONTROL(sourceChar)) {
                /* callback(illegal) */
                *err=U_ILLEGAL_CHAR_FOUND;
                args->converter->fromUChar32=sourceChar;
                break;
            }

            length = MBCS_FROM_UCHAR32_ISO2022(sharedData,sourceChar,&targetByteUnit,useFallback,MBCS_OUTPUT_2);
            if(length < 0) {
                length = -length;  /* fallback */
            }
            /* only DBCS or SBCS characters are expected*/
            /* DB characters with high bit set to 1 are expected */
            if( length > 2 || length==0 ||
                (length == 1 && targetByteUnit > 0x7f) ||
                (length == 2 &&
                    ((uint16_t)(targetByteUnit - 0xa1a1) > (0xfefe - 0xa1a1) ||
                    (uint8_t)(targetByteUnit - 0xa1) > (0xfe - 0xa1)))
            ) {
                targetByteUnit=missingCharMarker;
            }
            if (targetByteUnit != missingCharMarker){

                oldIsTargetByteDBCS = isTargetByteDBCS;
                isTargetByteDBCS = (UBool)(targetByteUnit>0x00FF);
                  /* append the shift sequence */
                if (oldIsTargetByteDBCS != isTargetByteDBCS ){

                    if (isTargetByteDBCS)
                        *target++ = UCNV_SO;
                    else
                        *target++ = UCNV_SI;
                    if(offsets)
                        *(offsets++) = (int32_t)(source - args->source-1);
                }
                /* write the targetUniChar  to target */
                if(targetByteUnit <= 0x00FF){
                    if( target < targetLimit){
                        *(target++) = (unsigned char) targetByteUnit;
                        if(offsets){
                            *(offsets++) = (int32_t)(source - args->source-1);
                        }

                    }else{
                        args->converter->charErrorBuffer[args->converter->charErrorBufferLength++] = (unsigned char) (targetByteUnit);
                        *err = U_BUFFER_OVERFLOW_ERROR;
                    }
                }else{
                    if(target < targetLimit){
                        *(target++) =(unsigned char) ((targetByteUnit>>8) -0x80);
                        if(offsets){
                            *(offsets++) = (int32_t)(source - args->source-1);
                        }
                        if(target < targetLimit){
                            *(target++) =(unsigned char) (targetByteUnit -0x80);
                            if(offsets){
                                *(offsets++) = (int32_t)(source - args->source-1);
                            }
                        }else{
                            args->converter->charErrorBuffer[args->converter->charErrorBufferLength++] = (unsigned char) (targetByteUnit -0x80);
                            *err = U_BUFFER_OVERFLOW_ERROR;
                        }
                    }else{
                        args->converter->charErrorBuffer[args->converter->charErrorBufferLength++] = (unsigned char) ((targetByteUnit>>8) -0x80);
                        args->converter->charErrorBuffer[args->converter->charErrorBufferLength++] = (unsigned char) (targetByteUnit-0x80);
                        *err = U_BUFFER_OVERFLOW_ERROR;
                    }
                }

            }
            else{
                /* oops.. the code point is unassingned
                 * set the error and reason
                 */

                /*check if the char is a First surrogate*/
                if(U16_IS_SURROGATE(sourceChar)) {
                    if(U16_IS_SURROGATE_LEAD(sourceChar)) {
getTrail:
                        /*look ahead to find the trail surrogate*/
                        if(source <  sourceLimit) {
                            /* test the following code unit */
                            char16_t trail=(char16_t) *source;
                            if(U16_IS_TRAIL(trail)) {
                                source++;
                                sourceChar=U16_GET_SUPPLEMENTARY(sourceChar, trail);
                                *err = U_INVALID_CHAR_FOUND;
                                /* convert this surrogate code point */
                                /* exit this condition tree */
                            } else {
                                /* this is an unmatched lead code unit (1st surrogate) */
                                /* callback(illegal) */
                                *err=U_ILLEGAL_CHAR_FOUND;
                            }
                        } else {
                            /* no more input */
                            *err = U_ZERO_ERROR;
                        }
                    } else {
                        /* this is an unmatched trail code unit (2nd surrogate) */
                        /* callback(illegal) */
                        *err=U_ILLEGAL_CHAR_FOUND;
                    }
                } else {
                    /* callback(unassigned) for a BMP code point */
                    *err = U_INVALID_CHAR_FOUND;
                }

                args->converter->fromUChar32=sourceChar;
                break;
            }
        } /* end if(myTargetIndex<myTargetLength) */
        else{
            *err =U_BUFFER_OVERFLOW_ERROR;
            break;
        }

    }/* end while(mySourceIndex<mySourceLength) */

    /*
     * the end of the input stream and detection of truncated input
     * are handled by the framework, but for ISO-2022-KR conversion
     * we need to be in ASCII mode at the very end
     *
     * conditions:
     *   successful
     *   not in ASCII mode
     *   end of input and no truncated input
     */
    if( U_SUCCESS(*err) &&
        isTargetByteDBCS &&
        args->flush && source>=sourceLimit && args->converter->fromUChar32==0
    ) {
        int32_t sourceIndex;

        /* we are switching to ASCII */
        isTargetByteDBCS=false;

        /* get the source index of the last input character */
        /*
         * TODO this would be simpler and more reliable if we used a pair
         * of sourceIndex/prevSourceIndex like in ucnvmbcs.c
         * so that we could simply use the prevSourceIndex here;
         * this code gives an incorrect result for the rare case of an unmatched
         * trail surrogate that is alone in the last buffer of the text stream
         */
        sourceIndex=(int32_t)(source-args->source);
        if(sourceIndex>0) {
            --sourceIndex;
            if( U16_IS_TRAIL(args->source[sourceIndex]) &&
                (sourceIndex==0 || U16_IS_LEAD(args->source[sourceIndex-1]))
            ) {
                --sourceIndex;
            }
        } else {
            sourceIndex=-1;
        }

        fromUWriteUInt8(
            args->converter,
            SHIFT_IN_STR, 1,
            &target, (const char *)targetLimit,
            &offsets, sourceIndex,
            err);
    }

    /*save the state and return */
    args->source = source;
    args->target = (char*)target;
    args->converter->fromUnicodeStatus = (uint32_t)isTargetByteDBCS;
}

/************************ To Unicode ***************************************/

static void U_CALLCONV
UConverter_toUnicode_ISO_2022_KR_OFFSETS_LOGIC_IBM(UConverterToUnicodeArgs *args,
                                                            UErrorCode* err){
    char const* sourceStart;
    UConverterDataISO2022* myData=(UConverterDataISO2022*)(args->converter->extraInfo);

    UConverterToUnicodeArgs subArgs;
    int32_t minArgsSize;

    /* set up the subconverter arguments */
    if(args->size<sizeof(UConverterToUnicodeArgs)) {
        minArgsSize = args->size;
    } else {
        minArgsSize = (int32_t)sizeof(UConverterToUnicodeArgs);
    }

    uprv_memcpy(&subArgs, args, minArgsSize);
    subArgs.size = (uint16_t)minArgsSize;
    subArgs.converter = myData->currentConverter;

    /* remember the original start of the input for offsets */
    sourceStart = args->source;

    if(myData->key != 0) {
        /* continue with a partial escape sequence */
        goto escape;
    }

    while(U_SUCCESS(*err) && args->source < args->sourceLimit) {
        /*Find the end of the buffer e.g : Next Escape Seq | end of Buffer*/
        subArgs.source = args->source;
        subArgs.sourceLimit = getEndOfBuffer_2022(&(args->source), args->sourceLimit, args->flush);
        if(subArgs.source != subArgs.sourceLimit) {
            /*
             * get the current partial byte sequence
             *
             * it needs to be moved between the public and the subconverter
             * so that the conversion framework, which only sees the public
             * converter, can handle truncated and illegal input etc.
             */
            if(args->converter->toULength > 0) {
                uprv_memcpy(subArgs.converter->toUBytes, args->converter->toUBytes, args->converter->toULength);
            }
            subArgs.converter->toULength = args->converter->toULength;

            /*
             * Convert up to the end of the input, or to before the next escape character.
             * Does not handle conversion extensions because the preToU[] state etc.
             * is not copied.
             */
            ucnv_MBCSToUnicodeWithOffsets(&subArgs, err);

            if(args->offsets != nullptr && sourceStart != args->source) {
                /* update offsets to base them on the actual start of the input */
                int32_t *offsets = args->offsets;
                char16_t *target = args->target;
                int32_t delta = (int32_t)(args->source - sourceStart);
                while(target < subArgs.target) {
                    if(*offsets >= 0) {
                        *offsets += delta;
                    }
                    ++offsets;
                    ++target;
                }
            }
            args->source = subArgs.source;
            args->target = subArgs.target;
            args->offsets = subArgs.offsets;

            /* copy input/error/overflow buffers */
            if(subArgs.converter->toULength > 0) {
                uprv_memcpy(args->converter->toUBytes, subArgs.converter->toUBytes, subArgs.converter->toULength);
            }
            args->converter->toULength = subArgs.converter->toULength;

            if(*err == U_BUFFER_OVERFLOW_ERROR) {
                if(subArgs.converter->UCharErrorBufferLength > 0) {
                    uprv_memcpy(args->converter->UCharErrorBuffer, subArgs.converter->UCharErrorBuffer,
                                subArgs.converter->UCharErrorBufferLength);
                }
                args->converter->UCharErrorBufferLength=subArgs.converter->UCharErrorBufferLength;
                subArgs.converter->UCharErrorBufferLength = 0;
            }
        }

        if (U_FAILURE(*err) || (args->source == args->sourceLimit)) {
            return;
        }

escape:
        changeState_2022(args->converter,
               &(args->source),
               args->sourceLimit,
               ISO_2022_KR,
               err);
    }
}

static void U_CALLCONV
UConverter_toUnicode_ISO_2022_KR_OFFSETS_LOGIC(UConverterToUnicodeArgs *args,
                                                            UErrorCode* err){
    char tempBuf[2];
    const char *mySource = ( char *) args->source;
    char16_t *myTarget = args->target;
    const char *mySourceLimit = args->sourceLimit;
    UChar32 targetUniChar = 0x0000;
    char16_t mySourceChar = 0x0000;
    UConverterDataISO2022* myData;
    UConverterSharedData* sharedData ;
    UBool useFallback;

    myData=(UConverterDataISO2022*)(args->converter->extraInfo);
    if(myData->version==1){
        UConverter_toUnicode_ISO_2022_KR_OFFSETS_LOGIC_IBM(args,err);
        return;
    }

    /* initialize state */
    sharedData = myData->currentConverter->sharedData;
    useFallback = args->converter->useFallback;

    if(myData->key != 0) {
        /* continue with a partial escape sequence */
        goto escape;
    } else if(args->converter->toULength == 1 && mySource < mySourceLimit && myTarget < args->targetLimit) {
        /* continue with a partial double-byte character */
        mySourceChar = args->converter->toUBytes[0];
        args->converter->toULength = 0;
        goto getTrailByte;
    }

    while(mySource< mySourceLimit){

        if(myTarget < args->targetLimit){

            mySourceChar= (unsigned char) *mySource++;

            if(mySourceChar==UCNV_SI){
                myData->toU2022State.g = 0;
                if (myData->isEmptySegment) {
                    myData->isEmptySegment = false;	/* we are handling it, reset to avoid future spurious errors */
                    *err = U_ILLEGAL_ESCAPE_SEQUENCE;
                    args->converter->toUCallbackReason = UCNV_IRREGULAR;
                    args->converter->toUBytes[0] = (uint8_t)mySourceChar;
                    args->converter->toULength = 1;
                    args->target = myTarget;
                    args->source = mySource;
                    return;
                }
                /*consume the source */
                continue;
            }else if(mySourceChar==UCNV_SO){
                myData->toU2022State.g = 1;
                myData->isEmptySegment = true;	/* Begin a new segment, empty so far */
                /*consume the source */
                continue;
            }else if(mySourceChar==ESC_2022){
                mySource--;
escape:
                myData->isEmptySegment = false;	/* Any invalid ESC sequences will be detected separately, so just reset this */
                changeState_2022(args->converter,&(mySource),
                                mySourceLimit, ISO_2022_KR, err);
                if(U_FAILURE(*err)){
                    args->target = myTarget;
                    args->source = mySource;
                    return;
                }
                continue;
            }

            myData->isEmptySegment = false;	/* Any invalid char errors will be detected separately, so just reset this */
            if(myData->toU2022State.g == 1) {
                if(mySource < mySourceLimit) {
                    int leadIsOk, trailIsOk;
                    uint8_t trailByte;
getTrailByte:
                    targetUniChar = missingCharMarker;
                    trailByte = (uint8_t)*mySource;
                    /*
                     * Ticket 5691: consistent illegal sequences:
                     * - We include at least the first byte in the illegal sequence.
                     * - If any of the non-initial bytes could be the start of a character,
                     *   we stop the illegal sequence before the first one of those.
                     *
                     * In ISO-2022 DBCS, if the second byte is in the 21..7e range or is
                     * an ESC/SO/SI, we report only the first byte as the illegal sequence.
                     * Otherwise we convert or report the pair of bytes.
                     */
                    leadIsOk = (uint8_t)(mySourceChar - 0x21) <= (0x7e - 0x21);
                    trailIsOk = (uint8_t)(trailByte - 0x21) <= (0x7e - 0x21);
                    if (leadIsOk && trailIsOk) {
                        ++mySource;
                        tempBuf[0] = (char)(mySourceChar + 0x80);
                        tempBuf[1] = (char)(trailByte + 0x80);
                        targetUniChar = ucnv_MBCSSimpleGetNextUChar(sharedData, tempBuf, 2, useFallback);
                        mySourceChar = (mySourceChar << 8) | trailByte;
                    } else if (!(trailIsOk || IS_2022_CONTROL(trailByte))) {
                        /* report a pair of illegal bytes if the second byte is not a DBCS starter */
                        ++mySource;
                        /* add another bit so that the code below writes 2 bytes in case of error */
                        mySourceChar = static_cast<char16_t>(0x10000 | (mySourceChar << 8) | trailByte);
                    }
                } else {
                    args->converter->toUBytes[0] = (uint8_t)mySourceChar;
                    args->converter->toULength = 1;
                    break;
                }
            }
            else if(mySourceChar <= 0x7f) {
                targetUniChar = ucnv_MBCSSimpleGetNextUChar(sharedData, mySource - 1, 1, useFallback);
            } else {
                targetUniChar = 0xffff;
            }
            if(targetUniChar < 0xfffe){
                if(args->offsets) {
                    args->offsets[myTarget - args->target] = (int32_t)(mySource - args->source - (mySourceChar <= 0xff ? 1 : 2));
                }
                *(myTarget++)=(char16_t)targetUniChar;
            }
            else {
                /* Call the callback function*/
                toUnicodeCallback(args->converter,mySourceChar,targetUniChar,err);
                break;
            }
        }
        else{
            *err =U_BUFFER_OVERFLOW_ERROR;
            break;
        }
    }
    args->target = myTarget;
    args->source = mySource;
}

/*************************** END ISO2022-KR *********************************/

/*************************** ISO-2022-CN *********************************
*
* Rules for ISO-2022-CN Encoding:
* i)   The designator sequence must appear once on a line before any instance
*      of character set it designates.
* ii)  If two lines contain characters from the same character set, both lines
*      must include the designator sequence.
* iii) Once the designator sequence is known, a shifting sequence has to be found
*      to invoke the  shifting
* iv)  All lines start in ASCII and end in ASCII.
* v)   Four shifting sequences are employed for this purpose:
*
*      Sequcence   ASCII Eq    Charsets
*      ----------  -------    ---------
*      SI           <SI>        US-ASCII
*      SO           <SO>        CNS-11643-1992 Plane 1, GB2312, ISO-IR-165
*      SS2          <ESC>N      CNS-11643-1992 Plane 2
*      SS3          <ESC>O      CNS-11643-1992 Planes 3-7
*
* vi)
*      SOdesignator  : ESC "$" ")" finalchar_for_SO
*      SS2designator : ESC "$" "*" finalchar_for_SS2
*      SS3designator : ESC "$" "+" finalchar_for_SS3
*
*      ESC $ ) A       Indicates the bytes following SO are Chinese
*       characters as defined in GB 2312-80, until
*       another SOdesignation appears
*
*
*      ESC $ ) E       Indicates the bytes following SO are as defined
*       in ISO-IR-165 (for details, see section 2.1),
*       until another SOdesignation appears
*
*      ESC $ ) G       Indicates the bytes following SO are as defined
*       in CNS 11643-plane-1, until another
*       SOdesignation appears
*
*      ESC $ * H       Indicates the two bytes immediately following
*       SS2 is a Chinese character as defined in CNS
*       11643-plane-2, until another SS2designation
*       appears
*       (Meaning <ESC>N must precede every 2 byte
*        sequence.)
*
*      ESC $ + I       Indicates the immediate two bytes following SS3
*       is a Chinese character as defined in CNS
*       11643-plane-3, until another SS3designation
*       appears
*       (Meaning <ESC>O must precede every 2 byte
*        sequence.)
*
*      ESC $ + J       Indicates the immediate two bytes following SS3
*       is a Chinese character as defined in CNS
*       11643-plane-4, until another SS3designation
*       appears
*       (In English: <ESC>O must precede every 2 byte
*        sequence.)
*
*      ESC $ + K       Indicates the immediate two bytes following SS3
*       is a Chinese character as defined in CNS
*       11643-plane-5, until another SS3designation
*       appears
*
*      ESC $ + L       Indicates the immediate two bytes following SS3
*       is a Chinese character as defined in CNS
*       11643-plane-6, until another SS3designation
*       appears
*
*      ESC $ + M       Indicates the immediate two bytes following SS3
*       is a Chinese character as defined in CNS
*       11643-plane-7, until another SS3designation
*       appears
*
*       As in ISO-2022-CN, each line starts in ASCII, and ends in ASCII, and
*       has its own designation information before any Chinese characters
*       appear
*
*/

/* The following are defined this way to make the strings truly readonly */
static const char GB_2312_80_STR[] = "\x1B\x24\x29\x41";
static const char ISO_IR_165_STR[] = "\x1B\x24\x29\x45";
static const char CNS_11643_1992_Plane_1_STR[] = "\x1B\x24\x29\x47";
static const char CNS_11643_1992_Plane_2_STR[] = "\x1B\x24\x2A\x48";
static const char CNS_11643_1992_Plane_3_STR[] = "\x1B\x24\x2B\x49";
static const char CNS_11643_1992_Plane_4_STR[] = "\x1B\x24\x2B\x4A";
static const char CNS_11643_1992_Plane_5_STR[] = "\x1B\x24\x2B\x4B";
static const char CNS_11643_1992_Plane_6_STR[] = "\x1B\x24\x2B\x4C";
static const char CNS_11643_1992_Plane_7_STR[] = "\x1B\x24\x2B\x4D";

/********************** ISO2022-CN Data **************************/
static const char* const escSeqCharsCN[10] ={
        SHIFT_IN_STR,                   /* 0 ASCII */
        GB_2312_80_STR,                 /* 1 GB2312_1 */
        ISO_IR_165_STR,                 /* 2 ISO_IR_165 */
        CNS_11643_1992_Plane_1_STR,
        CNS_11643_1992_Plane_2_STR,
        CNS_11643_1992_Plane_3_STR,
        CNS_11643_1992_Plane_4_STR,
        CNS_11643_1992_Plane_5_STR,
        CNS_11643_1992_Plane_6_STR,
        CNS_11643_1992_Plane_7_STR
};

static void U_CALLCONV
UConverter_fromUnicode_ISO_2022_CN_OFFSETS_LOGIC(UConverterFromUnicodeArgs* args, UErrorCode* err){
    UConverter *cnv = args->converter;
    UConverterDataISO2022 *converterData;
    ISO2022State *pFromU2022State;
    uint8_t *target = (uint8_t *) args->target;
    const uint8_t *targetLimit = (const uint8_t *) args->targetLimit;
    const char16_t* source = args->source;
    const char16_t* sourceLimit = args->sourceLimit;
    int32_t* offsets = args->offsets;
    UChar32 sourceChar;
    char buffer[8];
    int32_t len;
    int8_t choices[3];
    int32_t choiceCount;
    uint32_t targetValue = 0;
    UBool useFallback;

    /* set up the state */
    converterData     = (UConverterDataISO2022*)cnv->extraInfo;
    pFromU2022State   = &converterData->fromU2022State;

    choiceCount = 0;

    /* check if the last codepoint of previous buffer was a lead surrogate*/
    if((sourceChar = cnv->fromUChar32)!=0 && target< targetLimit) {
        goto getTrail;
    }

    while( source < sourceLimit){
        if(target < targetLimit){

            sourceChar  = *(source++);
            /*check if the char is a First surrogate*/
             if(U16_IS_SURROGATE(sourceChar)) {
                if(U16_IS_SURROGATE_LEAD(sourceChar)) {
getTrail:
                    /*look ahead to find the trail surrogate*/
                    if(source < sourceLimit) {
                        /* test the following code unit */
                        char16_t trail=(char16_t) *source;
                        if(U16_IS_TRAIL(trail)) {
                            source++;
                            sourceChar=U16_GET_SUPPLEMENTARY(sourceChar, trail);
                            cnv->fromUChar32=0x00;
                            /* convert this supplementary code point */
                            /* exit this condition tree */
                        } else {
                            /* this is an unmatched lead code unit (1st surrogate) */
                            /* callback(illegal) */
                            *err=U_ILLEGAL_CHAR_FOUND;
                            cnv->fromUChar32=sourceChar;
                            break;
                        }
                    } else {
                        /* no more input */
                        cnv->fromUChar32=sourceChar;
                        break;
                    }
                } else {
                    /* this is an unmatched trail code unit (2nd surrogate) */
                    /* callback(illegal) */
                    *err=U_ILLEGAL_CHAR_FOUND;
                    cnv->fromUChar32=sourceChar;
                    break;
                }
            }

            /* do the conversion */
            if(sourceChar <= 0x007f ){
                /* do not convert SO/SI/ESC */
                if(IS_2022_CONTROL(sourceChar)) {
                    /* callback(illegal) */
                    *err=U_ILLEGAL_CHAR_FOUND;
                    cnv->fromUChar32=sourceChar;
                    break;
                }

                /* US-ASCII */
                if(pFromU2022State->g == 0) {
                    buffer[0] = (char)sourceChar;
                    len = 1;
                } else {
                    buffer[0] = UCNV_SI;
                    buffer[1] = (char)sourceChar;
                    len = 2;
                    pFromU2022State->g = 0;
                    choiceCount = 0;
                }
                if(sourceChar == CR || sourceChar == LF) {
                    /* reset the state at the end of a line */
                    uprv_memset(pFromU2022State, 0, sizeof(ISO2022State));
                    choiceCount = 0;
                }
            }
            else{
                /* convert U+0080..U+10ffff */
                int32_t i;
                int8_t cs, g;

                if(choiceCount == 0) {
                    /* try the current SO/G1 converter first */
                    choices[0] = pFromU2022State->cs[1];

                    /* default to GB2312_1 if none is designated yet */
                    if(choices[0] == 0) {
                        choices[0] = GB2312_1;
                    }

                    if(converterData->version == 0) {
                        /* ISO-2022-CN */

                        /* try the other SO/G1 converter; a CNS_11643_1 lookup may result in any plane */
                        if(choices[0] == GB2312_1) {
                            choices[1] = (int8_t)CNS_11643_1;
                        } else {
                            choices[1] = (int8_t)GB2312_1;
                        }

                        choiceCount = 2;
                    } else if (converterData->version == 1) {
                        /* ISO-2022-CN-EXT */

                        /* try one of the other converters */
                        switch(choices[0]) {
                        case GB2312_1:
                            choices[1] = (int8_t)CNS_11643_1;
                            choices[2] = (int8_t)ISO_IR_165;
                            break;
                        case ISO_IR_165:
                            choices[1] = (int8_t)GB2312_1;
                            choices[2] = (int8_t)CNS_11643_1;
                            break;
                        default: /* CNS_11643_x */
                            choices[1] = (int8_t)GB2312_1;
                            choices[2] = (int8_t)ISO_IR_165;
                            break;
                        }

                        choiceCount = 3;
                    } else {
                        choices[0] = (int8_t)CNS_11643_1;
                        choices[1] = (int8_t)GB2312_1;
                    }
                }

                cs = g = 0;
                /*
                 * len==0: no mapping found yet
                 * len<0: found a fallback result: continue looking for a roundtrip but no further fallbacks
                 * len>0: found a roundtrip result, done
                 */
                len = 0;
                /*
                 * We will turn off useFallback after finding a fallback,
                 * but we still get fallbacks from PUA code points as usual.
                 * Therefore, we will also need to check that we don't overwrite
                 * an early fallback with a later one.
                 */
                useFallback = cnv->useFallback;

                for(i = 0; i < choiceCount && len <= 0; ++i) {
                    int8_t cs0 = choices[i];
                    if(cs0 > 0) {
                        uint32_t value;
                        int32_t len2;
                        if(cs0 >= CNS_11643_0) {
                            len2 = MBCS_FROM_UCHAR32_ISO2022(
                                        converterData->myConverterArray[CNS_11643],
                                        sourceChar,
                                        &value,
                                        useFallback,
                                        MBCS_OUTPUT_3);
                            if(len2 == 3 || (len2 == -3 && len == 0)) {
                                targetValue = value;
                                cs = (int8_t)(CNS_11643_0 + (value >> 16) - 0x80);
                                if(len2 >= 0) {
                                    len = 2;
                                } else {
                                    len = -2;
                                    useFallback = false;
                                }
                                if(cs == CNS_11643_1) {
                                    g = 1;
                                } else if(cs == CNS_11643_2) {
                                    g = 2;
                                } else /* plane 3..7 */ if(converterData->version == 1) {
                                    g = 3;
                                } else {
                                    /* ISO-2022-CN (without -EXT) does not support plane 3..7 */
                                    len = 0;
                                }
                            }
                        } else {
                            /* GB2312_1 or ISO-IR-165 */
                            U_ASSERT(cs0<UCNV_2022_MAX_CONVERTERS);
                            len2 = MBCS_FROM_UCHAR32_ISO2022(
                                        converterData->myConverterArray[cs0],
                                        sourceChar,
                                        &value,
                                        useFallback,
                                        MBCS_OUTPUT_2);
                            if(len2 == 2 || (len2 == -2 && len == 0)) {
                                targetValue = value;
                                len = len2;
                                cs = cs0;
                                g = 1;
                                useFallback = false;
                            }
                        }
                    }
                }

                if(len != 0) {
                    len = 0; /* count output bytes; it must have been abs(len) == 2 */

                    /* write the designation sequence if necessary */
                    if(cs != pFromU2022State->cs[g]) {
                        if(cs < CNS_11643) {
                            uprv_memcpy(buffer, escSeqCharsCN[cs], 4);
                        } else {
                            U_ASSERT(cs >= CNS_11643_1);
                            uprv_memcpy(buffer, escSeqCharsCN[CNS_11643 + (cs - CNS_11643_1)], 4);
                        }
                        len = 4;
                        pFromU2022State->cs[g] = cs;
                        if(g == 1) {
                            /* changing the SO/G1 charset invalidates the choices[] */
                            choiceCount = 0;
                        }
                    }

                    /* write the shift sequence if necessary */
                    if(g != pFromU2022State->g) {
                        switch(g) {
                        case 1:
                            buffer[len++] = UCNV_SO;

                            /* set the new state only if it is the locking shift SO/G1, not for SS2 or SS3 */
                            pFromU2022State->g = 1;
                            break;
                        case 2:
                            buffer[len++] = 0x1b;
                            buffer[len++] = 0x4e;
                            break;
                        default: /* case 3 */
                            buffer[len++] = 0x1b;
                            buffer[len++] = 0x4f;
                            break;
                        }
                    }

                    /* write the two output bytes */
                    buffer[len++] = (char)(targetValue >> 8);
                    buffer[len++] = (char)targetValue;
                } else {
                    /* if we cannot find the character after checking all codepages
                     * then this is an error
                     */
                    *err = U_INVALID_CHAR_FOUND;
                    cnv->fromUChar32=sourceChar;
                    break;
                }
            }

            /* output len>0 bytes in buffer[] */
            if(len == 1) {
                *target++ = buffer[0];
                if(offsets) {
                    *offsets++ = (int32_t)(source - args->source - 1); /* -1: known to be ASCII */
                }
            } else if(len == 2 && (target + 2) <= targetLimit) {
                *target++ = buffer[0];
                *target++ = buffer[1];
                if(offsets) {
                    int32_t sourceIndex = (int32_t)(source - args->source - U16_LENGTH(sourceChar));
                    *offsets++ = sourceIndex;
                    *offsets++ = sourceIndex;
                }
            } else {
                fromUWriteUInt8(
                    cnv,
                    buffer, len,
                    &target, (const char *)targetLimit,
                    &offsets, (int32_t)(source - args->source - U16_LENGTH(sourceChar)),
                    err);
                if(U_FAILURE(*err)) {
                    break;
                }
            }
        } /* end if(myTargetIndex<myTargetLength) */
        else{
            *err =U_BUFFER_OVERFLOW_ERROR;
            break;
        }

    }/* end while(mySourceIndex<mySourceLength) */

    /*
     * the end of the input stream and detection of truncated input
     * are handled by the framework, but for ISO-2022-CN conversion
     * we need to be in ASCII mode at the very end
     *
     * conditions:
     *   successful
     *   not in ASCII mode
     *   end of input and no truncated input
     */
    if( U_SUCCESS(*err) &&
        pFromU2022State->g!=0 &&
        args->flush && source>=sourceLimit && cnv->fromUChar32==0
    ) {
        int32_t sourceIndex;

        /* we are switching to ASCII */
        pFromU2022State->g=0;

        /* get the source index of the last input character */
        /*
         * TODO this would be simpler and more reliable if we used a pair
         * of sourceIndex/prevSourceIndex like in ucnvmbcs.c
         * so that we could simply use the prevSourceIndex here;
         * this code gives an incorrect result for the rare case of an unmatched
         * trail surrogate that is alone in the last buffer of the text stream
         */
        sourceIndex=(int32_t)(source-args->source);
        if(sourceIndex>0) {
            --sourceIndex;
            if( U16_IS_TRAIL(args->source[sourceIndex]) &&
                (sourceIndex==0 || U16_IS_LEAD(args->source[sourceIndex-1]))
            ) {
                --sourceIndex;
            }
        } else {
            sourceIndex=-1;
        }

        fromUWriteUInt8(
            cnv,
            SHIFT_IN_STR, 1,
            &target, (const char *)targetLimit,
            &offsets, sourceIndex,
            err);
    }

    /*save the state and return */
    args->source = source;
    args->target = (char*)target;
}


static void U_CALLCONV
UConverter_toUnicode_ISO_2022_CN_OFFSETS_LOGIC(UConverterToUnicodeArgs *args,
                                               UErrorCode* err){
    char tempBuf[3];
    const char *mySource = (char *) args->source;
    char16_t *myTarget = args->target;
    const char *mySourceLimit = args->sourceLimit;
    uint32_t targetUniChar = 0x0000;
    uint32_t mySourceChar = 0x0000;
    UConverterDataISO2022* myData;
    ISO2022State *pToU2022State;

    myData=(UConverterDataISO2022*)(args->converter->extraInfo);
    pToU2022State = &myData->toU2022State;

    if(myData->key != 0) {
        /* continue with a partial escape sequence */
        goto escape;
    } else if(args->converter->toULength == 1 && mySource < mySourceLimit && myTarget < args->targetLimit) {
        /* continue with a partial double-byte character */
        mySourceChar = args->converter->toUBytes[0];
        args->converter->toULength = 0;
        targetUniChar = missingCharMarker;
        goto getTrailByte;
    }

    while(mySource < mySourceLimit){

        targetUniChar =missingCharMarker;

        if(myTarget < args->targetLimit){

            mySourceChar= (unsigned char) *mySource++;

            switch(mySourceChar){
            case UCNV_SI:
                pToU2022State->g=0;
                if (myData->isEmptySegment) {
                    myData->isEmptySegment = false;	/* we are handling it, reset to avoid future spurious errors */
                    *err = U_ILLEGAL_ESCAPE_SEQUENCE;
                    args->converter->toUCallbackReason = UCNV_IRREGULAR;
                    args->converter->toUBytes[0] = static_cast<uint8_t>(mySourceChar);
                    args->converter->toULength = 1;
                    args->target = myTarget;
                    args->source = mySource;
                    return;
                }
                continue;

            case UCNV_SO:
                if(pToU2022State->cs[1] != 0) {
                    pToU2022State->g=1;
                    myData->isEmptySegment = true;	/* Begin a new segment, empty so far */
                    continue;
                } else {
                    /* illegal to have SO before a matching designator */
                    myData->isEmptySegment = false;	/* Handling a different error, reset this to avoid future spurious errs */
                    break;
                }

            case ESC_2022:
                mySource--;
escape:
                {
                    const char * mySourceBefore = mySource;
                    int8_t toULengthBefore = args->converter->toULength;

                    changeState_2022(args->converter,&(mySource),
                        mySourceLimit, ISO_2022_CN,err);

                    /* After SO there must be at least one character before a designator (designator error handled separately) */
                    if(myData->key==0 && U_SUCCESS(*err) && myData->isEmptySegment) {
                        *err = U_ILLEGAL_ESCAPE_SEQUENCE;
                        args->converter->toUCallbackReason = UCNV_IRREGULAR;
                        args->converter->toULength = (int8_t)(toULengthBefore + (mySource - mySourceBefore));
                    }
                }

                /* invalid or illegal escape sequence */
                if(U_FAILURE(*err)){
                    args->target = myTarget;
                    args->source = mySource;
                    myData->isEmptySegment = false;	/* Reset to avoid future spurious errors */
                    return;
                }
                continue;

            /* ISO-2022-CN does not use single-byte (C1) SS2 and SS3 */

            case CR:
            case LF:
                uprv_memset(pToU2022State, 0, sizeof(ISO2022State));
                U_FALLTHROUGH;
            default:
                /* convert one or two bytes */
                myData->isEmptySegment = false;
                if(pToU2022State->g != 0) {
                    if(mySource < mySourceLimit) {
                        UConverterSharedData *cnv;
                        StateEnum tempState;
                        int32_t tempBufLen;
                        int leadIsOk, trailIsOk;
                        uint8_t trailByte;
getTrailByte:
                        trailByte = (uint8_t)*mySource;
                        /*
                         * Ticket 5691: consistent illegal sequences:
                         * - We include at least the first byte in the illegal sequence.
                         * - If any of the non-initial bytes could be the start of a character,
                         *   we stop the illegal sequence before the first one of those.
                         *
                         * In ISO-2022 DBCS, if the second byte is in the 21..7e range or is
                         * an ESC/SO/SI, we report only the first byte as the illegal sequence.
                         * Otherwise we convert or report the pair of bytes.
                         */
                        leadIsOk = (uint8_t)(mySourceChar - 0x21) <= (0x7e - 0x21);
                        trailIsOk = (uint8_t)(trailByte - 0x21) <= (0x7e - 0x21);
                        if (leadIsOk && trailIsOk) {
                            ++mySource;
                            tempState = (StateEnum)pToU2022State->cs[pToU2022State->g];
                            if(tempState >= CNS_11643_0) {
                                cnv = myData->myConverterArray[CNS_11643];
                                tempBuf[0] = (char) (0x80+(tempState-CNS_11643_0));
                                tempBuf[1] = (char) (mySourceChar);
                                tempBuf[2] = (char) trailByte;
                                tempBufLen = 3;

                            }else{
                                U_ASSERT(tempState<UCNV_2022_MAX_CONVERTERS);
                                cnv = myData->myConverterArray[tempState];
                                tempBuf[0] = (char) (mySourceChar);
                                tempBuf[1] = (char) trailByte;
                                tempBufLen = 2;
                            }
                            targetUniChar = ucnv_MBCSSimpleGetNextUChar(cnv, tempBuf, tempBufLen, false);
                            mySourceChar = (mySourceChar << 8) | trailByte;
                        } else if (!(trailIsOk || IS_2022_CONTROL(trailByte))) {
                            /* report a pair of illegal bytes if the second byte is not a DBCS starter */
                            ++mySource;
                            /* add another bit so that the code below writes 2 bytes in case of error */
                            mySourceChar = 0x10000 | (mySourceChar << 8) | trailByte;
                        }
                        if(pToU2022State->g>=2) {
                            /* return from a single-shift state to the previous one */
                            pToU2022State->g=pToU2022State->prevG;
                        }
                    } else {
                        args->converter->toUBytes[0] = (uint8_t)mySourceChar;
                        args->converter->toULength = 1;
                        goto endloop;
                    }
                }
                else{
                    if(mySourceChar <= 0x7f) {
                        targetUniChar = (char16_t) mySourceChar;
                    }
                }
                break;
            }
            if(targetUniChar < (missingCharMarker-1/*0xfffe*/)){
                if(args->offsets){
                    args->offsets[myTarget - args->target] = (int32_t)(mySource - args->source - (mySourceChar <= 0xff ? 1 : 2));
                }
                *(myTarget++)=(char16_t)targetUniChar;
            }
            else if(targetUniChar > missingCharMarker){
                /* disassemble the surrogate pair and write to output*/
                targetUniChar-=0x0010000;
                *myTarget = (char16_t)(0xd800+(char16_t)(targetUniChar>>10));
                if(args->offsets){
                    args->offsets[myTarget - args->target] = (int32_t)(mySource - args->source - (mySourceChar <= 0xff ? 1 : 2));
                }
                ++myTarget;
                if(myTarget< args->targetLimit){
                    *myTarget = (char16_t)(0xdc00+(char16_t)(targetUniChar&0x3ff));
                    if(args->offsets){
                        args->offsets[myTarget - args->target] = (int32_t)(mySource - args->source - (mySourceChar <= 0xff ? 1 : 2));
                    }
                    ++myTarget;
                }else{
                    args->converter->UCharErrorBuffer[args->converter->UCharErrorBufferLength++]=
                                    (char16_t)(0xdc00+(char16_t)(targetUniChar&0x3ff));
                }

            }
            else{
                /* Call the callback function*/
                toUnicodeCallback(args->converter,mySourceChar,targetUniChar,err);
                break;
            }
        }
        else{
            *err =U_BUFFER_OVERFLOW_ERROR;
            break;
        }
    }
endloop:
    args->target = myTarget;
    args->source = mySource;
}
#endif /* #if !UCONFIG_ONLY_HTML_CONVERSION */

static void U_CALLCONV
_ISO_2022_WriteSub(UConverterFromUnicodeArgs *args, int32_t offsetIndex, UErrorCode *err) {
    UConverter *cnv = args->converter;
    UConverterDataISO2022 *myConverterData=(UConverterDataISO2022 *) cnv->extraInfo;
    ISO2022State *pFromU2022State=&myConverterData->fromU2022State;
    char *p, *subchar;
    char buffer[8];
    int32_t length;

    subchar=(char *)cnv->subChars;
    length=cnv->subCharLen; /* assume length==1 for most variants */

    p = buffer;
    switch(myConverterData->locale[0]){
    case 'j':
        {
            int8_t cs;

            if(pFromU2022State->g == 1) {
                /* JIS7: switch from G1 to G0 */
                pFromU2022State->g = 0;
                *p++ = UCNV_SI;
            }

            cs = pFromU2022State->cs[0];
            if(cs != ASCII && cs != JISX201) {
                /* not in ASCII or JIS X 0201: switch to ASCII */
                pFromU2022State->cs[0] = (int8_t)ASCII;
                *p++ = '\x1b';
                *p++ = '\x28';
                *p++ = '\x42';
            }

            *p++ = subchar[0];
            break;
        }
    case 'c':
        if(pFromU2022State->g != 0) {
            /* not in ASCII mode: switch to ASCII */
            pFromU2022State->g = 0;
            *p++ = UCNV_SI;
        }
        *p++ = subchar[0];
        break;
    case 'k':
        if(myConverterData->version == 0) {
            if(length == 1) {
                if(args->converter->fromUnicodeStatus) {
                    /* in DBCS mode: switch to SBCS */
                    args->converter->fromUnicodeStatus = 0;
                    *p++ = UCNV_SI;
                }
                *p++ = subchar[0];
            } else /* length == 2*/ {
                if(!args->converter->fromUnicodeStatus) {
                    /* in SBCS mode: switch to DBCS */
                    args->converter->fromUnicodeStatus = 1;
                    *p++ = UCNV_SO;
                }
                *p++ = subchar[0];
                *p++ = subchar[1];
            }
            break;
        } else {
            /* save the subconverter's substitution string */
            uint8_t *currentSubChars = myConverterData->currentConverter->subChars;
            int8_t currentSubCharLen = myConverterData->currentConverter->subCharLen;

            /* set our substitution string into the subconverter */
            myConverterData->currentConverter->subChars = (uint8_t *)subchar;
            myConverterData->currentConverter->subCharLen = (int8_t)length;

            /* let the subconverter write the subchar, set/retrieve fromUChar32 state */
            args->converter = myConverterData->currentConverter;
            myConverterData->currentConverter->fromUChar32 = cnv->fromUChar32;
            ucnv_cbFromUWriteSub(args, 0, err);
            cnv->fromUChar32 = myConverterData->currentConverter->fromUChar32;
            args->converter = cnv;

            /* restore the subconverter's substitution string */
            myConverterData->currentConverter->subChars = currentSubChars;
            myConverterData->currentConverter->subCharLen = currentSubCharLen;

            if(*err == U_BUFFER_OVERFLOW_ERROR) {
                if(myConverterData->currentConverter->charErrorBufferLength > 0) {
                    uprv_memcpy(
                        cnv->charErrorBuffer,
                        myConverterData->currentConverter->charErrorBuffer,
                        myConverterData->currentConverter->charErrorBufferLength);
                }
                cnv->charErrorBufferLength = myConverterData->currentConverter->charErrorBufferLength;
                myConverterData->currentConverter->charErrorBufferLength = 0;
            }
            return;
        }
    default:
        /* not expected */
        break;
    }
    ucnv_cbFromUWriteBytes(args,
                           buffer, (int32_t)(p - buffer),
                           offsetIndex, err);
}

/*
 * Structure for cloning an ISO 2022 converter into a single memory block.
 */
struct cloneStruct
{
    UConverter cnv;
    UConverter currentConverter;
    UConverterDataISO2022 mydata;
};


U_CDECL_BEGIN

static UConverter * U_CALLCONV
_ISO_2022_SafeClone(
            const UConverter *cnv,
            void *stackBuffer,
            int32_t *pBufferSize,
            UErrorCode *status)
{
    struct cloneStruct * localClone;
    UConverterDataISO2022 *cnvData;
    int32_t i, size;

    if (U_FAILURE(*status)){
        return nullptr;
    }

    if (*pBufferSize == 0) { /* 'preflighting' request - set needed size into *pBufferSize */
        *pBufferSize = (int32_t)sizeof(struct cloneStruct);
        return nullptr;
    }

    cnvData = (UConverterDataISO2022 *)cnv->extraInfo;
    localClone = (struct cloneStruct *)stackBuffer;

    /* ucnv.c/ucnv_safeClone() copied the main UConverter already */

    uprv_memcpy(&localClone->mydata, cnvData, sizeof(UConverterDataISO2022));
    localClone->cnv.extraInfo = &localClone->mydata; /* set pointer to extra data */
    localClone->cnv.isExtraLocal = true;

    /* share the subconverters */

    if(cnvData->currentConverter != nullptr) {
        size = (int32_t)sizeof(UConverter);
        localClone->mydata.currentConverter =
            ucnv_safeClone(cnvData->currentConverter,
                            &localClone->currentConverter,
                            &size, status);
        if(U_FAILURE(*status)) {
            return nullptr;
        }
    }

    for(i=0; i<UCNV_2022_MAX_CONVERTERS; ++i) {
        if(cnvData->myConverterArray[i] != nullptr) {
            ucnv_incrementRefCount(cnvData->myConverterArray[i]);
        }
    }

    return &localClone->cnv;
}

U_CDECL_END

static void U_CALLCONV
_ISO_2022_GetUnicodeSet(const UConverter *cnv,
                    const USetAdder *sa,
                    UConverterUnicodeSet which,
                    UErrorCode *pErrorCode)
{
    int32_t i;
    UConverterDataISO2022* cnvData;

    if (U_FAILURE(*pErrorCode)) {
        return;
    }
#ifdef U_ENABLE_GENERIC_ISO_2022
    if (cnv->sharedData == &_ISO2022Data) {
        /* We use UTF-8 in this case */
        sa->addRange(sa->set, 0, 0xd7FF);
        sa->addRange(sa->set, 0xE000, 0x10FFFF);
        return;
    }
#endif

    cnvData = (UConverterDataISO2022*)cnv->extraInfo;

    /* open a set and initialize it with code points that are algorithmically round-tripped */
    switch(cnvData->locale[0]){
    case 'j':
        /* include JIS X 0201 which is hardcoded */
        sa->add(sa->set, 0xa5);
        sa->add(sa->set, 0x203e);
        if(jpCharsetMasks[cnvData->version]&CSM(ISO8859_1)) {
            /* include Latin-1 for some variants of JP */
            sa->addRange(sa->set, 0, 0xff);
        } else {
            /* include ASCII for JP */
            sa->addRange(sa->set, 0, 0x7f);
        }
        if(cnvData->version==3 || cnvData->version==4 || which==UCNV_ROUNDTRIP_AND_FALLBACK_SET) {
            /*
             * Do not test (jpCharsetMasks[cnvData->version]&CSM(HWKANA_7BIT))!=0
             * because the bit is on for all JP versions although only versions 3 & 4 (JIS7 & JIS8)
             * use half-width Katakana.
             * This is because all ISO-2022-JP variants are lenient in that they accept (in toUnicode)
             * half-width Katakana via the ESC ( I sequence.
             * However, we only emit (fromUnicode) half-width Katakana according to the
             * definition of each variant.
             *
             * When including fallbacks,
             * we need to include half-width Katakana Unicode code points for all JP variants because
             * JIS X 0208 has hardcoded fallbacks for them (which map to full-width Katakana).
             */
            /* include half-width Katakana for JP */
            sa->addRange(sa->set, HWKANA_START, HWKANA_END);
        }
        break;
#if !UCONFIG_ONLY_HTML_CONVERSION
    case 'c':
    case 'z':
        /* include ASCII for CN */
        sa->addRange(sa->set, 0, 0x7f);
        break;
    case 'k':
        /* there is only one converter for KR, and it is not in the myConverterArray[] */
        cnvData->currentConverter->sharedData->impl->getUnicodeSet(
                cnvData->currentConverter, sa, which, pErrorCode);
        /* the loop over myConverterArray[] will simply not find another converter */
        break;
#endif
    default:
        break;
    }

#if 0  /* Replaced by ucnv_MBCSGetFilteredUnicodeSetForUnicode() until we implement ucnv_getUnicodeSet() with reverse fallbacks. */
            if( (cnvData->locale[0]=='c' || cnvData->locale[0]=='z') &&
                cnvData->version==0 && i==CNS_11643
            ) {
                /* special handling for non-EXT ISO-2022-CN: add only code points for CNS planes 1 and 2 */
                ucnv_MBCSGetUnicodeSetForBytes(
                        cnvData->myConverterArray[i],
                        sa, UCNV_ROUNDTRIP_SET,
                        0, 0x81, 0x82,
                        pErrorCode);
            }
#endif

    for (i=0; i<UCNV_2022_MAX_CONVERTERS; i++) {
        UConverterSetFilter filter;
        if(cnvData->myConverterArray[i]!=nullptr) {
            if(cnvData->locale[0]=='j' && i==JISX208) {
                /*
                 * Only add code points that map to Shift-JIS codes
                 * corresponding to JIS X 0208.
                 */
                filter=UCNV_SET_FILTER_SJIS;
#if !UCONFIG_ONLY_HTML_CONVERSION
            } else if( (cnvData->locale[0]=='c' || cnvData->locale[0]=='z') &&
                       cnvData->version==0 && i==CNS_11643) {
                /*
                 * Version-specific for CN:
                 * CN version 0 does not map CNS planes 3..7 although
                 * they are all available in the CNS conversion table;
                 * CN version 1 (-EXT) does map them all.
                 * The two versions create different Unicode sets.
                 */
                filter=UCNV_SET_FILTER_2022_CN;
            } else if(i==KSC5601) {
                /*
                 * Some of the KSC 5601 tables (convrtrs.txt has this aliases on multiple tables)
                 * are broader than GR94.
                 */
                filter=UCNV_SET_FILTER_GR94DBCS;
#endif
            } else {
                filter=UCNV_SET_FILTER_NONE;
            }
            ucnv_MBCSGetFilteredUnicodeSetForUnicode(cnvData->myConverterArray[i], sa, which, filter, pErrorCode);
        }
    }

    /*
     * ISO 2022 converters must not convert SO/SI/ESC despite what
     * sub-converters do by themselves.
     * Remove these characters from the set.
     */
    sa->remove(sa->set, 0x0e);
    sa->remove(sa->set, 0x0f);
    sa->remove(sa->set, 0x1b);

    /* ISO 2022 converters do not convert C1 controls either */
    sa->removeRange(sa->set, 0x80, 0x9f);
}

static const UConverterImpl _ISO2022Impl={
    UCNV_ISO_2022,

    nullptr,
    nullptr,

    _ISO2022Open,
    _ISO2022Close,
    _ISO2022Reset,

#ifdef U_ENABLE_GENERIC_ISO_2022
    T_UConverter_toUnicode_ISO_2022_OFFSETS_LOGIC,
    T_UConverter_toUnicode_ISO_2022_OFFSETS_LOGIC,
    ucnv_fromUnicode_UTF8,
    ucnv_fromUnicode_UTF8_OFFSETS_LOGIC,
#else
    nullptr,
    nullptr,
    nullptr,
    nullptr,
#endif
    nullptr,

    nullptr,
    _ISO2022getName,
    _ISO_2022_WriteSub,
    _ISO_2022_SafeClone,
    _ISO_2022_GetUnicodeSet,

    nullptr,
    nullptr
};
static const UConverterStaticData _ISO2022StaticData={
    sizeof(UConverterStaticData),
    "ISO_2022",
    2022,
    UCNV_IBM,
    UCNV_ISO_2022,
    1,
    3, /* max 3 bytes per char16_t from UTF-8 (4 bytes from surrogate _pair_) */
    { 0x1a, 0, 0, 0 },
    1,
    false,
    false,
    0,
    0,
    { 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 } /* reserved */
};
const UConverterSharedData _ISO2022Data=
        UCNV_IMMUTABLE_SHARED_DATA_INITIALIZER(&_ISO2022StaticData, &_ISO2022Impl);

/*************JP****************/
static const UConverterImpl _ISO2022JPImpl={
    UCNV_ISO_2022,

    nullptr,
    nullptr,

    _ISO2022Open,
    _ISO2022Close,
    _ISO2022Reset,

    UConverter_toUnicode_ISO_2022_JP_OFFSETS_LOGIC,
    UConverter_toUnicode_ISO_2022_JP_OFFSETS_LOGIC,
    UConverter_fromUnicode_ISO_2022_JP_OFFSETS_LOGIC,
    UConverter_fromUnicode_ISO_2022_JP_OFFSETS_LOGIC,
    nullptr,

    nullptr,
    _ISO2022getName,
    _ISO_2022_WriteSub,
    _ISO_2022_SafeClone,
    _ISO_2022_GetUnicodeSet,

    nullptr,
    nullptr
};
static const UConverterStaticData _ISO2022JPStaticData={
    sizeof(UConverterStaticData),
    "ISO_2022_JP",
    0,
    UCNV_IBM,
    UCNV_ISO_2022,
    1,
    6, /* max 6 bytes per char16_t: 4-byte escape sequence + DBCS */
    { 0x1a, 0, 0, 0 },
    1,
    false,
    false,
    0,
    0,
    { 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 } /* reserved */
};

namespace {

const UConverterSharedData _ISO2022JPData=
        UCNV_IMMUTABLE_SHARED_DATA_INITIALIZER(&_ISO2022JPStaticData, &_ISO2022JPImpl);

}  // namespace

#if !UCONFIG_ONLY_HTML_CONVERSION
/************* KR ***************/
static const UConverterImpl _ISO2022KRImpl={
    UCNV_ISO_2022,

    nullptr,
    nullptr,

    _ISO2022Open,
    _ISO2022Close,
    _ISO2022Reset,

    UConverter_toUnicode_ISO_2022_KR_OFFSETS_LOGIC,
    UConverter_toUnicode_ISO_2022_KR_OFFSETS_LOGIC,
    UConverter_fromUnicode_ISO_2022_KR_OFFSETS_LOGIC,
    UConverter_fromUnicode_ISO_2022_KR_OFFSETS_LOGIC,
    nullptr,

    nullptr,
    _ISO2022getName,
    _ISO_2022_WriteSub,
    _ISO_2022_SafeClone,
    _ISO_2022_GetUnicodeSet,

    nullptr,
    nullptr
};
static const UConverterStaticData _ISO2022KRStaticData={
    sizeof(UConverterStaticData),
    "ISO_2022_KR",
    0,
    UCNV_IBM,
    UCNV_ISO_2022,
    1,
    8, /* max 8 bytes per char16_t */
    { 0x1a, 0, 0, 0 },
    1,
    false,
    false,
    0,
    0,
    { 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 } /* reserved */
};

namespace {

const UConverterSharedData _ISO2022KRData=
        UCNV_IMMUTABLE_SHARED_DATA_INITIALIZER(&_ISO2022KRStaticData, &_ISO2022KRImpl);

}  // namespace

/*************** CN ***************/
static const UConverterImpl _ISO2022CNImpl={

    UCNV_ISO_2022,

    nullptr,
    nullptr,

    _ISO2022Open,
    _ISO2022Close,
    _ISO2022Reset,

    UConverter_toUnicode_ISO_2022_CN_OFFSETS_LOGIC,
    UConverter_toUnicode_ISO_2022_CN_OFFSETS_LOGIC,
    UConverter_fromUnicode_ISO_2022_CN_OFFSETS_LOGIC,
    UConverter_fromUnicode_ISO_2022_CN_OFFSETS_LOGIC,
    nullptr,

    nullptr,
    _ISO2022getName,
    _ISO_2022_WriteSub,
    _ISO_2022_SafeClone,
    _ISO_2022_GetUnicodeSet,

    nullptr,
    nullptr
};
static const UConverterStaticData _ISO2022CNStaticData={
    sizeof(UConverterStaticData),
    "ISO_2022_CN",
    0,
    UCNV_IBM,
    UCNV_ISO_2022,
    1,
    8, /* max 8 bytes per char16_t: 4-byte CNS designator + 2 bytes for SS2/SS3 + DBCS */
    { 0x1a, 0, 0, 0 },
    1,
    false,
    false,
    0,
    0,
    { 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 } /* reserved */
};

namespace {

const UConverterSharedData _ISO2022CNData=
        UCNV_IMMUTABLE_SHARED_DATA_INITIALIZER(&_ISO2022CNStaticData, &_ISO2022CNImpl);

}  // namespace
#endif /* #if !UCONFIG_ONLY_HTML_CONVERSION */

#endif /* #if !UCONFIG_NO_LEGACY_CONVERSION */