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
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
7753
7754
7755
7756
7757
7758
7759
7760
7761
7762
7763
7764
7765
7766
7767
7768
7769
7770
7771
7772
7773
7774
7775
7776
7777
7778
7779
7780
7781
7782
7783
7784
7785
7786
7787
7788
7789
7790
7791
7792
7793
7794
7795
7796
7797
7798
7799
7800
7801
7802
7803
7804
7805
7806
7807
7808
7809
7810
7811
7812
7813
7814
7815
7816
7817
7818
7819
7820
7821
7822
7823
7824
7825
7826
7827
7828
7829
7830
7831
7832
7833
7834
7835
7836
7837
7838
7839
7840
7841
7842
7843
7844
7845
7846
7847
7848
7849
7850
7851
7852
7853
7854
7855
7856
7857
7858
7859
7860
7861
7862
7863
7864
7865
7866
7867
7868
7869
7870
7871
7872
7873
7874
7875
7876
7877
7878
7879
7880
7881
7882
7883
7884
7885
7886
7887
7888
7889
7890
7891
7892
7893
7894
7895
7896
7897
7898
7899
7900
7901
7902
7903
7904
7905
7906
7907
7908
7909
7910
7911
7912
7913
7914
7915
7916
7917
7918
7919
7920
7921
7922
7923
7924
7925
7926
7927
7928
7929
7930
7931
7932
7933
7934
7935
7936
7937
7938
7939
7940
7941
7942
7943
7944
7945
7946
7947
7948
7949
7950
7951
7952
7953
7954
7955
7956
7957
7958
7959
7960
7961
7962
7963
7964
7965
7966
7967
7968
7969
7970
7971
7972
7973
7974
7975
7976
7977
7978
7979
7980
7981
7982
7983
7984
7985
7986
7987
7988
7989
7990
7991
7992
7993
7994
7995
7996
7997
7998
7999
8000
8001
8002
8003
8004
8005
8006
8007
8008
8009
8010
8011
8012
8013
8014
8015
8016
8017
8018
8019
8020
8021
8022
8023
8024
8025
8026
8027
8028
8029
8030
8031
8032
8033
8034
8035
8036
8037
8038
8039
8040
8041
8042
8043
8044
8045
8046
8047
8048
8049
8050
8051
8052
8053
8054
8055
8056
8057
8058
8059
8060
8061
8062
8063
8064
8065
8066
8067
8068
8069
8070
8071
8072
8073
8074
8075
8076
8077
8078
8079
8080
8081
8082
8083
8084
8085
8086
8087
8088
8089
8090
8091
8092
8093
8094
8095
8096
8097
8098
8099
8100
8101
8102
8103
8104
8105
8106
8107
8108
8109
8110
8111
8112
8113
8114
8115
8116
8117
8118
8119
8120
8121
8122
8123
8124
8125
8126
8127
8128
8129
8130
8131
8132
8133
8134
8135
8136
8137
8138
8139
8140
8141
8142
8143
8144
8145
8146
8147
8148
8149
8150
8151
8152
8153
8154
8155
8156
8157
8158
8159
8160
8161
8162
8163
8164
8165
8166
8167
8168
8169
8170
8171
8172
8173
8174
8175
8176
8177
8178
8179
8180
8181
8182
8183
8184
8185
8186
8187
8188
8189
8190
8191
8192
8193
8194
8195
8196
8197
8198
8199
8200
8201
8202
8203
8204
8205
8206
8207
8208
8209
8210
8211
8212
8213
8214
8215
8216
8217
8218
8219
8220
8221
8222
8223
8224
8225
8226
8227
8228
8229
8230
8231
8232
8233
8234
8235
8236
8237
8238
8239
8240
8241
8242
8243
8244
8245
8246
8247
8248
8249
8250
8251
8252
8253
8254
8255
8256
8257
8258
8259
8260
8261
8262
8263
8264
8265
8266
8267
8268
8269
8270
8271
8272
8273
8274
8275
8276
8277
8278
8279
8280
8281
8282
8283
8284
8285
8286
8287
8288
8289
8290
8291
8292
8293
8294
8295
8296
8297
8298
8299
8300
8301
8302
8303
8304
8305
8306
8307
8308
8309
8310
8311
8312
8313
8314
8315
8316
8317
8318
8319
8320
8321
8322
8323
8324
8325
8326
8327
8328
8329
8330
8331
8332
8333
8334
8335
8336
8337
8338
8339
8340
8341
8342
8343
8344
8345
8346
8347
8348
8349
8350
8351
8352
8353
8354
8355
8356
8357
8358
8359
8360
8361
8362
8363
8364
8365
8366
8367
8368
8369
8370
8371
8372
8373
8374
8375
8376
8377
8378
8379
8380
8381
8382
8383
8384
8385
8386
8387
8388
8389
8390
8391
8392
8393
8394
8395
8396
8397
8398
8399
8400
8401
8402
8403
8404
8405
8406
8407
8408
8409
8410
8411
8412
8413
8414
8415
8416
8417
8418
8419
8420
8421
8422
8423
8424
8425
8426
8427
8428
8429
8430
8431
8432
8433
8434
8435
8436
8437
8438
8439
8440
8441
8442
8443
8444
8445
8446
8447
8448
8449
8450
8451
8452
8453
8454
8455
8456
8457
8458
8459
8460
8461
8462
8463
8464
8465
8466
8467
8468
8469
8470
8471
8472
8473
8474
8475
8476
8477
8478
8479
8480
8481
8482
8483
8484
8485
8486
8487
8488
8489
8490
8491
8492
8493
8494
8495
8496
8497
8498
8499
8500
8501
8502
8503
8504
8505
8506
8507
8508
8509
8510
8511
8512
8513
8514
8515
8516
8517
8518
8519
8520
8521
8522
8523
8524
8525
8526
8527
8528
8529
8530
8531
8532
8533
8534
8535
8536
8537
8538
8539
8540
8541
8542
8543
8544
8545
8546
8547
8548
8549
8550
8551
8552
8553
8554
8555
8556
8557
8558
8559
8560
8561
8562
8563
8564
8565
8566
8567
8568
8569
8570
8571
8572
8573
8574
8575
8576
8577
8578
8579
8580
8581
8582
8583
8584
8585
8586
8587
8588
8589
8590
8591
8592
8593
8594
8595
8596
8597
8598
8599
8600
8601
8602
8603
8604
8605
8606
8607
8608
8609
8610
8611
8612
8613
8614
8615
8616
8617
8618
8619
8620
8621
8622
8623
8624
8625
8626
8627
8628
8629
8630
8631
8632
8633
8634
8635
8636
8637
8638
8639
8640
8641
8642
8643
8644
8645
8646
8647
8648
8649
8650
8651
8652
8653
8654
8655
8656
8657
8658
8659
8660
8661
8662
8663
8664
8665
8666
8667
8668
8669
8670
8671
8672
8673
8674
8675
8676
8677
8678
8679
8680
8681
8682
8683
8684
8685
8686
8687
8688
8689
8690
8691
8692
8693
8694
8695
8696
8697
8698
8699
8700
8701
8702
8703
8704
8705
8706
8707
8708
8709
8710
8711
8712
8713
8714
8715
8716
8717
8718
8719
8720
8721
8722
8723
8724
8725
8726
8727
8728
8729
8730
8731
8732
8733
8734
8735
8736
8737
8738
8739
8740
8741
8742
8743
8744
8745
8746
8747
8748
8749
8750
8751
8752
8753
8754
8755
8756
8757
8758
8759
8760
8761
8762
8763
8764
8765
8766
8767
8768
8769
8770
8771
8772
8773
8774
8775
8776
8777
8778
8779
8780
8781
8782
8783
8784
8785
8786
8787
8788
8789
8790
8791
8792
8793
8794
8795
8796
8797
8798
8799
8800
8801
8802
8803
8804
8805
8806
8807
8808
8809
8810
8811
8812
8813
8814
8815
8816
8817
8818
8819
8820
8821
8822
8823
8824
8825
8826
8827
8828
8829
8830
8831
8832
8833
8834
8835
8836
8837
8838
8839
8840
8841
8842
8843
8844
8845
8846
8847
8848
8849
8850
8851
8852
8853
8854
8855
8856
8857
8858
8859
8860
8861
8862
8863
8864
8865
8866
8867
8868
8869
8870
8871
8872
8873
8874
8875
8876
8877
8878
8879
8880
8881
8882
8883
8884
8885
8886
8887
8888
8889
8890
8891
8892
8893
8894
8895
8896
8897
8898
8899
8900
8901
8902
8903
8904
8905
8906
8907
8908
8909
8910
8911
8912
8913
8914
8915
8916
8917
8918
8919
8920
8921
8922
8923
8924
8925
8926
8927
8928
8929
8930
8931
8932
8933
8934
8935
8936
8937
8938
8939
8940
8941
8942
8943
8944
8945
8946
8947
8948
8949
8950
8951
8952
8953
8954
8955
8956
8957
8958
8959
8960
8961
8962
8963
8964
8965
8966
8967
8968
8969
8970
8971
8972
8973
8974
8975
8976
8977
8978
8979
8980
8981
8982
8983
8984
8985
8986
8987
8988
8989
8990
8991
8992
8993
8994
8995
8996
8997
8998
8999
9000
9001
9002
9003
9004
9005
9006
9007
9008
9009
9010
9011
9012
9013
9014
9015
9016
9017
9018
9019
9020
9021
9022
9023
9024
9025
9026
9027
9028
9029
9030
9031
9032
9033
9034
9035
9036
9037
9038
9039
9040
9041
9042
9043
9044
9045
9046
9047
9048
9049
9050
9051
9052
9053
9054
9055
9056
9057
9058
9059
9060
9061
9062
9063
9064
9065
9066
9067
9068
9069
9070
9071
9072
9073
9074
9075
9076
9077
9078
9079
9080
9081
9082
9083
9084
9085
9086
9087
9088
9089
9090
9091
9092
9093
9094
9095
9096
9097
9098
9099
9100
9101
9102
9103
9104
9105
9106
9107
9108
9109
9110
9111
9112
9113
9114
9115
9116
9117
9118
9119
9120
9121
9122
9123
9124
9125
9126
9127
9128
9129
9130
9131
9132
9133
9134
9135
9136
9137
9138
9139
9140
9141
9142
9143
9144
9145
9146
9147
9148
9149
9150
9151
9152
9153
9154
9155
9156
9157
9158
9159
9160
9161
9162
9163
9164
9165
9166
9167
9168
9169
9170
9171
9172
9173
9174
9175
9176
9177
9178
9179
9180
9181
9182
9183
9184
9185
9186
9187
9188
9189
9190
9191
9192
9193
9194
9195
9196
9197
9198
9199
9200
9201
9202
9203
9204
9205
9206
9207
9208
9209
9210
9211
9212
9213
9214
9215
9216
9217
9218
9219
9220
9221
9222
9223
9224
9225
9226
9227
9228
9229
9230
9231
9232
9233
9234
9235
9236
9237
9238
9239
9240
9241
9242
9243
9244
9245
9246
9247
9248
9249
9250
9251
9252
9253
9254
9255
9256
9257
9258
9259
9260
9261
9262
9263
9264
9265
9266
9267
9268
9269
9270
9271
9272
9273
9274
9275
9276
9277
9278
9279
9280
9281
9282
9283
9284
9285
9286
9287
9288
9289
9290
9291
9292
9293
9294
9295
9296
9297
9298
9299
9300
9301
9302
9303
9304
9305
9306
9307
9308
9309
9310
9311
9312
9313
9314
9315
9316
9317
9318
9319
9320
9321
9322
9323
9324
9325
9326
9327
9328
9329
9330
9331
9332
9333
9334
9335
9336
9337
9338
9339
9340
9341
9342
9343
9344
9345
9346
9347
9348
9349
9350
9351
9352
9353
9354
9355
9356
9357
9358
9359
9360
9361
9362
9363
9364
9365
9366
9367
9368
9369
9370
9371
9372
9373
9374
9375
9376
9377
9378
9379
9380
9381
9382
9383
9384
9385
9386
9387
9388
9389
9390
9391
9392
9393
9394
9395
9396
9397
9398
9399
9400
9401
9402
9403
9404
9405
9406
9407
9408
9409
9410
9411
9412
9413
9414
9415
9416
9417
9418
9419
9420
9421
9422
9423
9424
9425
9426
9427
9428
9429
9430
9431
9432
9433
9434
9435
9436
9437
9438
9439
9440
9441
9442
9443
9444
9445
9446
9447
9448
9449
9450
9451
9452
9453
9454
9455
9456
9457
9458
9459
9460
9461
9462
9463
9464
9465
9466
9467
9468
9469
9470
9471
9472
9473
9474
9475
9476
9477
9478
9479
9480
9481
9482
9483
9484
9485
9486
9487
9488
9489
9490
9491
9492
9493
9494
9495
9496
9497
9498
9499
9500
9501
9502
9503
9504
9505
9506
9507
9508
9509
9510
9511
9512
9513
9514
9515
9516
9517
9518
9519
9520
9521
9522
9523
9524
9525
9526
9527
9528
9529
9530
9531
9532
9533
9534
9535
9536
9537
9538
9539
9540
9541
9542
9543
9544
9545
9546
9547
9548
9549
9550
9551
9552
9553
9554
9555
9556
9557
9558
9559
9560
9561
9562
9563
9564
9565
9566
9567
9568
9569
9570
9571
9572
9573
9574
9575
9576
9577
9578
9579
9580
9581
9582
9583
9584
9585
9586
9587
9588
9589
9590
9591
9592
9593
9594
9595
9596
9597
9598
9599
9600
9601
9602
9603
9604
9605
9606
9607
9608
9609
9610
9611
9612
9613
9614
9615
9616
9617
9618
9619
9620
9621
9622
9623
9624
9625
9626
9627
9628
9629
9630
9631
9632
9633
9634
9635
9636
9637
9638
9639
9640
9641
9642
9643
9644
9645
9646
9647
9648
9649
9650
9651
9652
9653
9654
9655
9656
9657
9658
9659
9660
9661
9662
9663
9664
9665
9666
9667
9668
9669
9670
9671
9672
9673
9674
9675
9676
9677
9678
9679
9680
9681
9682
9683
9684
9685
9686
9687
9688
9689
9690
9691
9692
9693
9694
9695
9696
9697
9698
9699
9700
9701
9702
9703
9704
9705
9706
9707
9708
9709
9710
9711
9712
9713
9714
9715
9716
9717
9718
9719
9720
9721
9722
9723
9724
9725
9726
9727
9728
9729
9730
9731
9732
9733
9734
9735
9736
9737
9738
9739
9740
9741
9742
9743
9744
9745
9746
9747
9748
9749
9750
9751
9752
9753
9754
9755
9756
9757
9758
9759
9760
9761
9762
9763
9764
9765
9766
9767
9768
9769
9770
9771
9772
9773
9774
9775
9776
9777
9778
9779
9780
9781
9782
9783
9784
9785
9786
9787
9788
9789
9790
9791
9792
9793
9794
9795
9796
9797
9798
9799
9800
9801
9802
9803
9804
9805
9806
9807
9808
9809
9810
9811
9812
9813
9814
9815
9816
9817
9818
9819
9820
9821
9822
9823
9824
9825
9826
9827
9828
9829
9830
9831
9832
9833
9834
9835
9836
9837
9838
9839
9840
9841
9842
9843
9844
9845
9846
9847
9848
9849
9850
9851
9852
9853
9854
9855
9856
9857
9858
9859
9860
9861
9862
9863
9864
9865
9866
9867
9868
9869
9870
9871
9872
9873
9874
9875
9876
9877
9878
9879
9880
9881
9882
9883
9884
9885
9886
9887
9888
9889
9890
9891
9892
9893
9894
9895
9896
9897
9898
9899
9900
9901
9902
9903
9904
9905
9906
9907
9908
9909
9910
9911
9912
9913
9914
9915
9916
9917
9918
9919
9920
9921
9922
9923
9924
9925
9926
9927
9928
9929
9930
9931
9932
9933
9934
9935
9936
9937
9938
9939
9940
9941
9942
9943
9944
9945
9946
9947
9948
9949
9950
9951
9952
9953
9954
9955
9956
9957
9958
9959
9960
9961
9962
9963
9964
9965
9966
9967
9968
9969
9970
9971
9972
9973
9974
9975
9976
9977
9978
9979
9980
9981
9982
9983
9984
9985
9986
9987
9988
9989
9990
9991
9992
9993
9994
9995
9996
9997
9998
9999
10000
10001
10002
10003
10004
10005
10006
10007
10008
10009
10010
10011
10012
10013
10014
10015
10016
10017
10018
10019
10020
10021
10022
10023
10024
10025
10026
10027
10028
10029
10030
10031
10032
10033
10034
10035
10036
10037
10038
10039
10040
10041
10042
10043
10044
10045
10046
10047
10048
10049
10050
10051
10052
10053
10054
10055
10056
10057
10058
10059
10060
10061
10062
10063
10064
10065
10066
10067
10068
10069
10070
10071
10072
10073
10074
10075
10076
10077
10078
10079
10080
10081
10082
10083
10084
10085
10086
10087
10088
10089
10090
10091
10092
10093
10094
10095
10096
10097
10098
10099
10100
10101
10102
10103
10104
10105
10106
10107
10108
10109
10110
10111
10112
10113
10114
10115
10116
10117
10118
10119
10120
10121
10122
10123
10124
10125
10126
10127
10128
10129
10130
10131
10132
10133
10134
10135
10136
10137
10138
10139
10140
10141
10142
10143
10144
10145
10146
10147
10148
10149
10150
10151
10152
10153
10154
10155
10156
10157
10158
10159
10160
10161
10162
10163
10164
10165
10166
10167
10168
10169
10170
10171
10172
10173
10174
10175
10176
10177
10178
10179
10180
10181
10182
10183
10184
10185
10186
10187
10188
10189
10190
10191
10192
10193
10194
10195
10196
10197
10198
10199
10200
10201
10202
10203
10204
10205
10206
10207
10208
10209
10210
10211
10212
10213
10214
10215
10216
10217
10218
10219
10220
10221
10222
10223
10224
10225
10226
10227
10228
10229
10230
10231
10232
10233
10234
10235
10236
10237
10238
10239
10240
10241
10242
10243
10244
10245
10246
10247
10248
10249
10250
10251
10252
10253
10254
10255
10256
10257
10258
10259
10260
10261
10262
10263
10264
10265
10266
10267
10268
10269
10270
10271
10272
10273
10274
10275
10276
10277
10278
10279
10280
10281
10282
10283
10284
10285
10286
10287
10288
10289
10290
10291
10292
10293
10294
10295
10296
10297
10298
10299
10300
10301
10302
10303
10304
10305
10306
10307
10308
10309
10310
10311
10312
10313
10314
10315
10316
10317
10318
10319
10320
10321
10322
10323
10324
10325
10326
10327
10328
10329
10330
10331
10332
10333
10334
10335
10336
10337
10338
10339
10340
10341
10342
10343
10344
10345
10346
10347
10348
10349
10350
10351
10352
10353
10354
10355
10356
10357
10358
10359
10360
10361
10362
10363
10364
10365
10366
10367
10368
10369
10370
10371
10372
10373
10374
10375
10376
10377
10378
10379
10380
10381
10382
10383
10384
10385
10386
10387
10388
10389
10390
10391
10392
10393
10394
10395
10396
10397
10398
10399
10400
10401
10402
10403
10404
10405
10406
10407
10408
10409
10410
10411
10412
10413
10414
10415
10416
10417
10418
10419
10420
10421
10422
10423
10424
10425
10426
10427
10428
10429
10430
10431
10432
10433
10434
10435
10436
10437
10438
10439
10440
10441
10442
10443
10444
10445
10446
10447
10448
10449
10450
10451
10452
10453
10454
10455
10456
10457
10458
10459
10460
10461
10462
10463
10464
10465
10466
10467
10468
10469
10470
10471
10472
10473
10474
10475
10476
10477
10478
10479
10480
10481
10482
10483
10484
10485
10486
10487
10488
10489
10490
10491
10492
10493
10494
10495
10496
10497
10498
10499
10500
10501
10502
10503
10504
10505
10506
10507
10508
10509
10510
10511
10512
10513
10514
10515
10516
10517
10518
10519
10520
10521
10522
10523
10524
10525
10526
10527
10528
10529
10530
10531
10532
10533
10534
10535
10536
10537
10538
10539
10540
10541
10542
10543
10544
10545
10546
10547
10548
10549
10550
10551
10552
10553
10554
10555
10556
10557
10558
10559
10560
10561
10562
10563
10564
10565
10566
10567
10568
10569
10570
10571
10572
10573
10574
10575
10576
10577
10578
10579
10580
10581
10582
10583
10584
10585
10586
10587
10588
10589
10590
10591
10592
10593
10594
10595
10596
10597
10598
10599
10600
10601
10602
10603
10604
10605
10606
10607
10608
10609
10610
10611
10612
10613
10614
10615
10616
10617
10618
10619
10620
10621
10622
10623
10624
10625
10626
10627
10628
10629
10630
10631
10632
10633
10634
10635
10636
10637
10638
10639
10640
10641
10642
10643
10644
10645
10646
10647
10648
10649
10650
10651
10652
10653
10654
10655
10656
10657
10658
10659
10660
10661
10662
10663
10664
10665
10666
10667
10668
10669
10670
10671
10672
10673
10674
10675
10676
10677
10678
10679
10680
10681
10682
10683
10684
10685
10686
10687
10688
10689
10690
10691
10692
10693
10694
10695
10696
10697
10698
10699
10700
10701
10702
10703
10704
10705
10706
10707
10708
10709
10710
10711
10712
10713
10714
10715
10716
10717
10718
10719
10720
10721
10722
10723
10724
10725
10726
10727
10728
10729
10730
10731
10732
10733
10734
10735
10736
10737
10738
10739
10740
10741
10742
10743
10744
10745
10746
10747
10748
10749
10750
10751
10752
10753
10754
10755
10756
10757
10758
10759
10760
10761
10762
10763
10764
10765
10766
10767
10768
10769
10770
10771
10772
10773
10774
10775
10776
10777
10778
10779
10780
10781
10782
10783
10784
10785
10786
10787
10788
10789
10790
10791
10792
10793
10794
10795
10796
10797
10798
10799
10800
10801
10802
10803
10804
10805
10806
10807
10808
10809
10810
10811
10812
10813
10814
10815
10816
10817
10818
10819
10820
10821
10822
10823
10824
10825
10826
10827
10828
10829
10830
10831
10832
10833
10834
10835
10836
10837
10838
10839
10840
10841
10842
10843
10844
10845
10846
10847
10848
10849
10850
10851
10852
10853
10854
10855
10856
10857
10858
10859
10860
10861
10862
10863
10864
10865
10866
10867
10868
10869
10870
10871
10872
10873
10874
10875
10876
10877
10878
10879
10880
10881
10882
10883
10884
10885
10886
10887
10888
10889
10890
10891
10892
10893
10894
10895
10896
10897
10898
10899
10900
10901
10902
10903
10904
10905
10906
10907
10908
10909
10910
10911
10912
10913
10914
10915
10916
10917
10918
10919
10920
10921
10922
10923
10924
10925
10926
10927
10928
10929
10930
10931
10932
10933
10934
10935
10936
10937
10938
10939
10940
10941
10942
10943
10944
10945
10946
10947
10948
10949
10950
10951
10952
10953
10954
10955
10956
10957
10958
10959
10960
10961
10962
10963
10964
10965
10966
10967
10968
10969
10970
10971
10972
10973
10974
10975
10976
10977
10978
10979
10980
10981
10982
10983
10984
10985
10986
10987
10988
10989
10990
10991
10992
10993
10994
10995
10996
10997
10998
10999
11000
11001
11002
11003
11004
11005
11006
11007
11008
11009
11010
11011
11012
11013
11014
11015
11016
11017
11018
11019
11020
11021
11022
11023
11024
11025
11026
11027
11028
11029
11030
11031
11032
11033
11034
11035
11036
11037
11038
11039
11040
11041
11042
11043
11044
11045
11046
11047
11048
11049
11050
11051
11052
11053
11054
11055
11056
11057
11058
11059
11060
11061
11062
11063
11064
11065
11066
11067
11068
11069
11070
11071
11072
11073
11074
11075
11076
11077
11078
11079
11080
11081
11082
11083
11084
11085
11086
11087
11088
11089
11090
11091
11092
11093
11094
11095
11096
11097
11098
11099
11100
11101
11102
11103
11104
11105
11106
11107
11108
11109
11110
11111
11112
11113
11114
11115
11116
11117
11118
11119
11120
11121
11122
11123
11124
11125
11126
11127
11128
11129
11130
11131
11132
11133
11134
11135
11136
11137
11138
11139
11140
11141
11142
11143
11144
11145
11146
11147
11148
11149
11150
11151
11152
11153
11154
11155
11156
11157
11158
11159
11160
11161
11162
11163
11164
11165
11166
11167
11168
11169
11170
11171
11172
11173
11174
11175
11176
11177
11178
11179
11180
11181
11182
11183
11184
11185
11186
11187
11188
11189
11190
11191
11192
11193
11194
11195
11196
11197
11198
11199
11200
11201
11202
11203
11204
11205
11206
11207
11208
11209
11210
11211
11212
11213
11214
11215
11216
11217
11218
11219
11220
11221
11222
11223
11224
11225
11226
11227
11228
11229
11230
11231
11232
11233
11234
11235
11236
11237
11238
11239
11240
11241
11242
11243
11244
11245
11246
11247
11248
11249
11250
11251
11252
11253
11254
11255
11256
11257
11258
11259
11260
11261
11262
11263
11264
11265
11266
11267
11268
11269
11270
11271
11272
11273
11274
11275
11276
11277
11278
11279
11280
11281
11282
11283
11284
11285
11286
11287
11288
11289
11290
11291
11292
11293
11294
11295
11296
11297
11298
11299
11300
11301
11302
11303
11304
11305
11306
11307
11308
11309
11310
11311
11312
11313
11314
11315
11316
11317
11318
11319
11320
11321
11322
11323
11324
11325
11326
11327
11328
11329
11330
11331
11332
11333
11334
11335
11336
11337
11338
11339
11340
11341
11342
11343
11344
11345
11346
11347
11348
11349
11350
11351
11352
11353
11354
11355
11356
11357
11358
11359
11360
11361
11362
11363
11364
11365
11366
11367
11368
11369
11370
11371
11372
11373
11374
11375
11376
11377
11378
11379
11380
11381
11382
11383
11384
11385
11386
11387
11388
11389
11390
11391
11392
11393
11394
11395
11396
11397
11398
11399
11400
11401
11402
11403
11404
11405
11406
11407
11408
11409
11410
11411
11412
11413
11414
11415
11416
11417
11418
11419
11420
11421
11422
11423
11424
11425
11426
11427
11428
11429
11430
11431
11432
11433
11434
11435
11436
11437
11438
11439
11440
11441
11442
11443
11444
11445
11446
11447
11448
11449
11450
11451
11452
11453
11454
11455
11456
11457
11458
11459
11460
11461
11462
11463
11464
11465
11466
11467
11468
11469
11470
11471
11472
11473
11474
11475
11476
11477
11478
11479
11480
11481
11482
11483
11484
11485
11486
11487
11488
11489
11490
11491
11492
11493
11494
11495
11496
11497
11498
11499
11500
11501
11502
11503
11504
11505
11506
11507
11508
11509
11510
11511
11512
11513
11514
11515
11516
11517
11518
11519
11520
11521
11522
11523
11524
11525
11526
11527
11528
11529
11530
11531
11532
11533
11534
11535
11536
11537
11538
11539
11540
11541
11542
11543
11544
11545
11546
11547
11548
11549
11550
11551
11552
11553
11554
11555
11556
11557
11558
11559
11560
11561
11562
11563
11564
11565
11566
11567
11568
11569
11570
11571
11572
11573
11574
11575
11576
11577
11578
11579
11580
11581
11582
11583
11584
11585
11586
11587
11588
11589
11590
11591
11592
11593
11594
11595
11596
11597
11598
11599
11600
11601
11602
11603
11604
11605
11606
11607
11608
11609
11610
11611
11612
11613
11614
11615
11616
11617
11618
11619
11620
11621
11622
11623
11624
11625
11626
11627
11628
11629
11630
11631
11632
11633
11634
11635
11636
11637
11638
11639
11640
11641
11642
11643
11644
11645
11646
11647
11648
11649
11650
11651
11652
11653
11654
11655
11656
11657
11658
11659
11660
11661
11662
11663
11664
11665
11666
11667
11668
11669
11670
11671
11672
11673
11674
11675
11676
11677
11678
11679
11680
11681
11682
11683
11684
11685
11686
11687
11688
11689
11690
11691
11692
11693
11694
11695
11696
11697
11698
11699
11700
11701
11702
11703
11704
11705
11706
11707
11708
11709
11710
11711
11712
11713
11714
11715
11716
11717
11718
11719
11720
11721
11722
11723
11724
11725
11726
11727
11728
11729
11730
11731
11732
11733
11734
11735
11736
11737
11738
11739
11740
11741
11742
11743
11744
11745
11746
11747
11748
11749
11750
11751
11752
11753
11754
11755
11756
11757
11758
11759
11760
11761
11762
11763
11764
11765
11766
11767
11768
11769
11770
11771
11772
11773
11774
11775
11776
11777
11778
11779
11780
11781
11782
11783
11784
11785
11786
11787
11788
11789
11790
11791
11792
11793
11794
11795
11796
11797
11798
11799
11800
11801
11802
11803
11804
11805
11806
11807
11808
11809
11810
11811
11812
11813
11814
11815
11816
11817
11818
11819
11820
11821
11822
11823
11824
11825
11826
11827
11828
11829
11830
11831
11832
11833
11834
11835
11836
11837
11838
11839
11840
11841
11842
11843
11844
11845
11846
11847
11848
11849
11850
11851
11852
11853
11854
11855
11856
11857
11858
11859
11860
11861
11862
11863
11864
11865
11866
11867
11868
11869
11870
11871
11872
11873
11874
11875
11876
11877
11878
11879
11880
11881
11882
11883
11884
11885
11886
11887
11888
11889
11890
11891
11892
11893
11894
11895
11896
11897
11898
11899
11900
11901
11902
11903
11904
11905
11906
11907
11908
11909
11910
11911
11912
11913
11914
11915
11916
11917
11918
11919
11920
11921
11922
11923
11924
11925
11926
11927
11928
11929
11930
11931
11932
11933
11934
11935
11936
11937
11938
11939
11940
11941
11942
11943
11944
11945
11946
11947
11948
11949
11950
11951
11952
11953
11954
11955
11956
11957
11958
11959
11960
11961
11962
11963
11964
11965
11966
11967
11968
11969
11970
11971
11972
11973
11974
11975
11976
11977
11978
11979
11980
11981
11982
11983
11984
11985
11986
11987
11988
11989
11990
11991
11992
11993
11994
11995
11996
11997
11998
11999
12000
12001
12002
12003
12004
12005
12006
12007
12008
12009
12010
12011
12012
12013
12014
12015
12016
12017
12018
12019
12020
12021
12022
12023
12024
12025
12026
12027
12028
12029
12030
12031
12032
12033
12034
12035
12036
12037
12038
12039
12040
12041
12042
12043
12044
12045
12046
12047
12048
12049
12050
12051
12052
12053
12054
12055
12056
12057
12058
12059
12060
12061
12062
12063
12064
12065
12066
12067
12068
12069
12070
12071
12072
12073
12074
12075
12076
12077
12078
12079
12080
12081
12082
12083
12084
12085
12086
12087
12088
12089
12090
12091
12092
12093
12094
12095
12096
12097
12098
12099
12100
12101
12102
12103
12104
12105
12106
12107
12108
12109
12110
12111
12112
12113
12114
12115
12116
12117
12118
12119
12120
12121
12122
12123
12124
12125
12126
12127
12128
12129
12130
12131
12132
12133
12134
12135
12136
12137
12138
12139
12140
12141
12142
12143
12144
12145
12146
12147
12148
12149
12150
12151
12152
12153
12154
12155
12156
12157
12158
12159
12160
12161
12162
12163
12164
12165
12166
12167
12168
12169
12170
12171
12172
12173
12174
12175
12176
12177
12178
12179
12180
12181
12182
12183
12184
12185
12186
12187
12188
12189
12190
12191
12192
12193
| | /* Coding system handler (conversion, detection, etc).
Copyright (C) 2001-2020 Free Software Foundation, Inc.
Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
2005, 2006, 2007, 2008, 2009, 2010, 2011
National Institute of Advanced Industrial Science and Technology (AIST)
Registration Number H14PRO021
Copyright (C) 2003
National Institute of Advanced Industrial Science and Technology (AIST)
Registration Number H13PRO009
This file is part of GNU Emacs.
GNU Emacs is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or (at
your option) any later version.
GNU Emacs is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with GNU Emacs. If not, see <https://www.gnu.org/licenses/>. */
/*** TABLE OF CONTENTS ***
0. General comments
1. Preamble
2. Emacs' internal format (emacs-utf-8) handlers
3. UTF-8 handlers
4. UTF-16 handlers
5. Charset-base coding systems handlers
6. emacs-mule (old Emacs' internal format) handlers
7. ISO2022 handlers
8. Shift-JIS and BIG5 handlers
9. CCL handlers
10. C library functions
11. Emacs Lisp library functions
12. Postamble
*/
/*** 0. General comments ***
CODING SYSTEM
A coding system is an object for an encoding mechanism that contains
information about how to convert byte sequences to character
sequences and vice versa. When we say "decode", it means converting
a byte sequence of a specific coding system into a character
sequence that is represented by Emacs' internal coding system
`emacs-utf-8', and when we say "encode", it means converting a
character sequence of emacs-utf-8 to a byte sequence of a specific
coding system.
In Emacs Lisp, a coding system is represented by a Lisp symbol. On
the C level, a coding system is represented by a vector of attributes
stored in the hash table Vcharset_hash_table. The conversion from
coding system symbol to attributes vector is done by looking up
Vcharset_hash_table by the symbol.
Coding systems are classified into the following types depending on
the encoding mechanism. Here's a brief description of the types.
o UTF-8
o UTF-16
o Charset-base coding system
A coding system defined by one or more (coded) character sets.
Decoding and encoding are done by a code converter defined for each
character set.
o Old Emacs internal format (emacs-mule)
The coding system adopted by old versions of Emacs (20 and 21).
o ISO2022-base coding system
The most famous coding system for multiple character sets. X's
Compound Text, various EUCs (Extended Unix Code), and coding systems
used in the Internet communication such as ISO-2022-JP are all
variants of ISO2022.
o SJIS (or Shift-JIS or MS-Kanji-Code)
A coding system to encode character sets: ASCII, JISX0201, and
JISX0208. Widely used for PC's in Japan. Details are described in
section 8.
o BIG5
A coding system to encode character sets: ASCII and Big5. Widely
used for Chinese (mainly in Taiwan and Hong Kong). Details are
described in section 8. In this file, when we write "big5" (all
lowercase), we mean the coding system, and when we write "Big5"
(capitalized), we mean the character set.
o CCL
If a user wants to decode/encode text encoded in a coding system
not listed above, he can supply a decoder and an encoder for it in
CCL (Code Conversion Language) programs. Emacs executes the CCL
program while decoding/encoding.
o Raw-text
A coding system for text containing raw eight-bit data. Emacs
treats each byte of source text as a character (except for
end-of-line conversion).
o No-conversion
Like raw text, but don't do end-of-line conversion.
END-OF-LINE FORMAT
How text end-of-line is encoded depends on operating system. For
instance, Unix's format is just one byte of LF (line-feed) code,
whereas DOS's format is two-byte sequence of `carriage-return' and
`line-feed' codes. Classic Mac OS's format is usually one byte of
`carriage-return'.
Since text character encoding and end-of-line encoding are
independent, any coding system described above can take any format
of end-of-line (except for no-conversion).
STRUCT CODING_SYSTEM
Before using a coding system for code conversion (i.e. decoding and
encoding), we setup a structure of type `struct coding_system'.
This structure keeps various information about a specific code
conversion (e.g. the location of source and destination data).
*/
/* COMMON MACROS */
/*** GENERAL NOTES on `detect_coding_XXX ()' functions ***
These functions check if a byte sequence specified as a source in
CODING conforms to the format of XXX, and update the members of
DETECT_INFO.
Return true if the byte sequence conforms to XXX.
Below is the template of these functions. */
#if 0
static bool
detect_coding_XXX (struct coding_system *coding,
struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source;
const unsigned char *src_end = coding->source + coding->src_bytes;
bool multibytep = coding->src_multibyte;
ptrdiff_t consumed_chars = 0;
int found = 0;
...;
while (1)
{
/* Get one byte from the source. If the source is exhausted, jump
to no_more_source:. */
ONE_MORE_BYTE (c);
if (! __C_conforms_to_XXX___ (c))
break;
if (! __C_strongly_suggests_XXX__ (c))
found = CATEGORY_MASK_XXX;
}
/* The byte sequence is invalid for XXX. */
detect_info->rejected |= CATEGORY_MASK_XXX;
return 0;
no_more_source:
/* The source exhausted successfully. */
detect_info->found |= found;
return 1;
}
#endif
/*** GENERAL NOTES on `decode_coding_XXX ()' functions ***
These functions decode a byte sequence specified as a source by
CODING. The resulting multibyte text goes to a place pointed to by
CODING->charbuf, the length of which should not exceed
CODING->charbuf_size;
These functions set the information of original and decoded texts in
CODING->consumed, CODING->consumed_char, and CODING->charbuf_used.
They also set CODING->result to one of CODING_RESULT_XXX indicating
how the decoding is finished.
Below is the template of these functions. */
#if 0
static void
decode_coding_XXXX (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
/* SRC_BASE remembers the start position in source in each loop.
The loop will be exited when there's not enough source code, or
when there's no room in CHARBUF for a decoded character. */
const unsigned char *src_base;
/* A buffer to produce decoded characters. */
int *charbuf = coding->charbuf + coding->charbuf_used;
int *charbuf_end = coding->charbuf + coding->charbuf_size;
bool multibytep = coding->src_multibyte;
while (1)
{
src_base = src;
if (charbuf < charbuf_end)
/* No more room to produce a decoded character. */
break;
ONE_MORE_BYTE (c);
/* Decode it. */
}
no_more_source:
if (src_base < src_end
&& coding->mode & CODING_MODE_LAST_BLOCK)
/* If the source ends by partial bytes to construct a character,
treat them as eight-bit raw data. */
while (src_base < src_end && charbuf < charbuf_end)
*charbuf++ = *src_base++;
/* Remember how many bytes and characters we consumed. If the
source is multibyte, the bytes and chars are not identical. */
coding->consumed = coding->consumed_char = src_base - coding->source;
/* Remember how many characters we produced. */
coding->charbuf_used = charbuf - coding->charbuf;
}
#endif
/*** GENERAL NOTES on `encode_coding_XXX ()' functions ***
These functions encode SRC_BYTES length text at SOURCE of Emacs'
internal multibyte format by CODING. The resulting byte sequence
goes to a place pointed to by DESTINATION, the length of which
should not exceed DST_BYTES.
These functions set the information of original and encoded texts in
the members produced, produced_char, consumed, and consumed_char of
the structure *CODING. They also set the member result to one of
CODING_RESULT_XXX indicating how the encoding finished.
DST_BYTES zero means that source area and destination area are
overlapped, which means that we can produce an encoded text until it
reaches at the head of not-yet-encoded source text.
Below is a template of these functions. */
#if 0
static void
encode_coding_XXX (struct coding_system *coding)
{
bool multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
int *charbuf_end = charbuf->charbuf + coding->charbuf_used;
unsigned char *dst = coding->destination + coding->produced;
unsigned char *dst_end = coding->destination + coding->dst_bytes;
unsigned char *adjusted_dst_end = dst_end - _MAX_BYTES_PRODUCED_IN_LOOP_;
ptrdiff_t produced_chars = 0;
for (; charbuf < charbuf_end && dst < adjusted_dst_end; charbuf++)
{
int c = *charbuf;
/* Encode C into DST, and increment DST. */
}
label_no_more_destination:
/* How many chars and bytes we produced. */
coding->produced_char += produced_chars;
coding->produced = dst - coding->destination;
}
#endif
\f
/*** 1. Preamble ***/
#include <config.h>
#ifdef HAVE_WCHAR_H
#include <wchar.h>
#endif /* HAVE_WCHAR_H */
#include "lisp.h"
#include "character.h"
#include "buffer.h"
#include "charset.h"
#include "ccl.h"
#include "composite.h"
#include "coding.h"
#include "termhooks.h"
#include "pdumper.h"
Lisp_Object Vcoding_system_hash_table;
/* Coding-systems are handed between Emacs Lisp programs and C internal
routines by the following three variables. */
/* Coding system to be used to encode text for terminal display when
terminal coding system is nil. */
struct coding_system safe_terminal_coding;
/* Two special coding systems. */
static Lisp_Object Vsjis_coding_system;
static Lisp_Object Vbig5_coding_system;
/* ISO2022 section */
#define CODING_ISO_INITIAL(coding, reg) \
(XFIXNUM (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \
coding_attr_iso_initial), \
reg)))
#define CODING_ISO_REQUEST(coding, charset_id) \
(((charset_id) <= (coding)->max_charset_id \
? ((coding)->safe_charsets[charset_id] != 255 \
? (coding)->safe_charsets[charset_id] \
: -1) \
: -1))
#define CODING_ISO_FLAGS(coding) \
((coding)->spec.iso_2022.flags)
#define CODING_ISO_DESIGNATION(coding, reg) \
((coding)->spec.iso_2022.current_designation[reg])
#define CODING_ISO_INVOCATION(coding, plane) \
((coding)->spec.iso_2022.current_invocation[plane])
#define CODING_ISO_SINGLE_SHIFTING(coding) \
((coding)->spec.iso_2022.single_shifting)
#define CODING_ISO_BOL(coding) \
((coding)->spec.iso_2022.bol)
#define CODING_ISO_INVOKED_CHARSET(coding, plane) \
(CODING_ISO_INVOCATION (coding, plane) < 0 ? -1 \
: CODING_ISO_DESIGNATION (coding, CODING_ISO_INVOCATION (coding, plane)))
#define CODING_ISO_CMP_STATUS(coding) \
(&(coding)->spec.iso_2022.cmp_status)
#define CODING_ISO_EXTSEGMENT_LEN(coding) \
((coding)->spec.iso_2022.ctext_extended_segment_len)
#define CODING_ISO_EMBEDDED_UTF_8(coding) \
((coding)->spec.iso_2022.embedded_utf_8)
/* Control characters of ISO2022. */
/* code */ /* function */
#define ISO_CODE_SO 0x0E /* shift-out */
#define ISO_CODE_SI 0x0F /* shift-in */
#define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */
#define ISO_CODE_ESC 0x1B /* escape */
#define ISO_CODE_SS2 0x8E /* single-shift-2 */
#define ISO_CODE_SS3 0x8F /* single-shift-3 */
#define ISO_CODE_CSI 0x9B /* control-sequence-introducer */
/* All code (1-byte) of ISO2022 is classified into one of the
followings. */
enum iso_code_class_type
{
ISO_control_0, /* Control codes in the range
0x00..0x1F and 0x7F, except for the
following 5 codes. */
ISO_shift_out, /* ISO_CODE_SO (0x0E) */
ISO_shift_in, /* ISO_CODE_SI (0x0F) */
ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */
ISO_escape, /* ISO_CODE_ESC (0x1B) */
ISO_control_1, /* Control codes in the range
0x80..0x9F, except for the
following 3 codes. */
ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */
ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */
ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */
ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */
ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */
ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */
ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */
};
/** The macros CODING_ISO_FLAG_XXX defines a flag bit of the
`iso-flags' attribute of an iso2022 coding system. */
/* If set, produce long-form designation sequence (e.g. ESC $ ( A)
instead of the correct short-form sequence (e.g. ESC $ A). */
#define CODING_ISO_FLAG_LONG_FORM 0x0001
/* If set, reset graphic planes and registers at end-of-line to the
initial state. */
#define CODING_ISO_FLAG_RESET_AT_EOL 0x0002
/* If set, reset graphic planes and registers before any control
characters to the initial state. */
#define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004
/* If set, encode by 7-bit environment. */
#define CODING_ISO_FLAG_SEVEN_BITS 0x0008
/* If set, use locking-shift function. */
#define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010
/* If set, use single-shift function. Overwrite
CODING_ISO_FLAG_LOCKING_SHIFT. */
#define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020
/* If set, use designation escape sequence. */
#define CODING_ISO_FLAG_DESIGNATION 0x0040
/* If set, produce revision number sequence. */
#define CODING_ISO_FLAG_REVISION 0x0080
/* If set, produce ISO6429's direction specifying sequence. */
#define CODING_ISO_FLAG_DIRECTION 0x0100
/* If set, assume designation states are reset at beginning of line on
output. */
#define CODING_ISO_FLAG_INIT_AT_BOL 0x0200
/* If set, designation sequence should be placed at beginning of line
on output. */
#define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400
/* If set, do not encode unsafe characters on output. */
#define CODING_ISO_FLAG_SAFE 0x0800
/* If set, extra latin codes (128..159) are accepted as a valid code
on input. */
#define CODING_ISO_FLAG_LATIN_EXTRA 0x1000
#define CODING_ISO_FLAG_COMPOSITION 0x2000
/* #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 */
#define CODING_ISO_FLAG_USE_ROMAN 0x8000
#define CODING_ISO_FLAG_USE_OLDJIS 0x10000
#define CODING_ISO_FLAG_LEVEL_4 0x20000
#define CODING_ISO_FLAG_FULL_SUPPORT 0x100000
/* A character to be produced on output if encoding of the original
character is prohibited by CODING_ISO_FLAG_SAFE. */
#define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?'
/* UTF-8 section */
#define CODING_UTF_8_BOM(coding) \
((coding)->spec.utf_8_bom)
/* UTF-16 section */
#define CODING_UTF_16_BOM(coding) \
((coding)->spec.utf_16.bom)
#define CODING_UTF_16_ENDIAN(coding) \
((coding)->spec.utf_16.endian)
#define CODING_UTF_16_SURROGATE(coding) \
((coding)->spec.utf_16.surrogate)
/* CCL section */
#define CODING_CCL_DECODER(coding) \
AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder)
#define CODING_CCL_ENCODER(coding) \
AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder)
#define CODING_CCL_VALIDS(coding) \
(SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids)))
/* Index for each coding category in `coding_categories' */
enum coding_category
{
coding_category_iso_7,
coding_category_iso_7_tight,
coding_category_iso_8_1,
coding_category_iso_8_2,
coding_category_iso_7_else,
coding_category_iso_8_else,
coding_category_utf_8_auto,
coding_category_utf_8_nosig,
coding_category_utf_8_sig,
coding_category_utf_16_auto,
coding_category_utf_16_be,
coding_category_utf_16_le,
coding_category_utf_16_be_nosig,
coding_category_utf_16_le_nosig,
coding_category_charset,
coding_category_sjis,
coding_category_big5,
coding_category_ccl,
coding_category_emacs_mule,
/* All above are targets of code detection. */
coding_category_raw_text,
coding_category_undecided,
coding_category_max
};
/* Definitions of flag bits used in detect_coding_XXXX. */
#define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7)
#define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight)
#define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1)
#define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2)
#define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else)
#define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else)
#define CATEGORY_MASK_UTF_8_AUTO (1 << coding_category_utf_8_auto)
#define CATEGORY_MASK_UTF_8_NOSIG (1 << coding_category_utf_8_nosig)
#define CATEGORY_MASK_UTF_8_SIG (1 << coding_category_utf_8_sig)
#define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto)
#define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be)
#define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le)
#define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig)
#define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig)
#define CATEGORY_MASK_CHARSET (1 << coding_category_charset)
#define CATEGORY_MASK_SJIS (1 << coding_category_sjis)
#define CATEGORY_MASK_BIG5 (1 << coding_category_big5)
#define CATEGORY_MASK_CCL (1 << coding_category_ccl)
#define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule)
#define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text)
/* This value is returned if detect_coding_mask () find nothing other
than ASCII characters. */
#define CATEGORY_MASK_ANY \
(CATEGORY_MASK_ISO_7 \
| CATEGORY_MASK_ISO_7_TIGHT \
| CATEGORY_MASK_ISO_8_1 \
| CATEGORY_MASK_ISO_8_2 \
| CATEGORY_MASK_ISO_7_ELSE \
| CATEGORY_MASK_ISO_8_ELSE \
| CATEGORY_MASK_UTF_8_AUTO \
| CATEGORY_MASK_UTF_8_NOSIG \
| CATEGORY_MASK_UTF_8_SIG \
| CATEGORY_MASK_UTF_16_AUTO \
| CATEGORY_MASK_UTF_16_BE \
| CATEGORY_MASK_UTF_16_LE \
| CATEGORY_MASK_UTF_16_BE_NOSIG \
| CATEGORY_MASK_UTF_16_LE_NOSIG \
| CATEGORY_MASK_CHARSET \
| CATEGORY_MASK_SJIS \
| CATEGORY_MASK_BIG5 \
| CATEGORY_MASK_CCL \
| CATEGORY_MASK_EMACS_MULE)
#define CATEGORY_MASK_ISO_7BIT \
(CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT)
#define CATEGORY_MASK_ISO_8BIT \
(CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2)
#define CATEGORY_MASK_ISO_ELSE \
(CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE)
#define CATEGORY_MASK_ISO_ESCAPE \
(CATEGORY_MASK_ISO_7 \
| CATEGORY_MASK_ISO_7_TIGHT \
| CATEGORY_MASK_ISO_7_ELSE \
| CATEGORY_MASK_ISO_8_ELSE)
#define CATEGORY_MASK_ISO \
( CATEGORY_MASK_ISO_7BIT \
| CATEGORY_MASK_ISO_8BIT \
| CATEGORY_MASK_ISO_ELSE)
#define CATEGORY_MASK_UTF_16 \
(CATEGORY_MASK_UTF_16_AUTO \
| CATEGORY_MASK_UTF_16_BE \
| CATEGORY_MASK_UTF_16_LE \
| CATEGORY_MASK_UTF_16_BE_NOSIG \
| CATEGORY_MASK_UTF_16_LE_NOSIG)
#define CATEGORY_MASK_UTF_8 \
(CATEGORY_MASK_UTF_8_AUTO \
| CATEGORY_MASK_UTF_8_NOSIG \
| CATEGORY_MASK_UTF_8_SIG)
/* Table of coding categories (Lisp symbols). This variable is for
internal use only. */
static Lisp_Object Vcoding_category_table;
/* Table of coding-categories ordered by priority. */
static enum coding_category coding_priorities[coding_category_max];
/* Nth element is a coding context for the coding system bound to the
Nth coding category. */
static struct coding_system coding_categories[coding_category_max];
/* Encode a flag that can be nil, something else, or t as -1, 0, 1. */
static int
encode_inhibit_flag (Lisp_Object flag)
{
return NILP (flag) ? -1 : EQ (flag, Qt);
}
/* True if the value of ENCODED_FLAG says a flag should be treated as set.
1 means yes, -1 means no, 0 means ask the user variable VAR. */
static bool
inhibit_flag (int encoded_flag, bool var)
{
return 0 < encoded_flag + var;
}
#define CODING_GET_INFO(coding, attrs, charset_list) \
do { \
(attrs) = CODING_ID_ATTRS ((coding)->id); \
(charset_list) = CODING_ATTR_CHARSET_LIST (attrs); \
} while (false)
/* True if CODING's destination can be grown. */
static bool
growable_destination (struct coding_system *coding)
{
return STRINGP (coding->dst_object) || BUFFERP (coding->dst_object);
}
/* Safely get one byte from the source text pointed by SRC which ends
at SRC_END, and set C to that byte. If there are not enough bytes
in the source, it jumps to 'no_more_source'. If MULTIBYTEP,
and a multibyte character is found at SRC, set C to the
negative value of the character code. The caller should declare
and set these variables appropriately in advance:
src, src_end, multibytep */
#define ONE_MORE_BYTE(c) \
do { \
if (src == src_end) \
{ \
if (src_base < src) \
record_conversion_result \
(coding, CODING_RESULT_INSUFFICIENT_SRC); \
goto no_more_source; \
} \
c = *src++; \
if (multibytep && (c & 0x80)) \
{ \
if ((c & 0xFE) == 0xC0) \
c = ((c & 1) << 6) | *src++; \
else \
{ \
src--; \
c = - string_char_advance (&src); \
record_conversion_result \
(coding, CODING_RESULT_INVALID_SRC); \
} \
} \
consumed_chars++; \
} while (0)
/* Safely get two bytes from the source text pointed by SRC which ends
at SRC_END, and set C1 and C2 to those bytes while skipping the
heading multibyte characters. If there are not enough bytes in the
source, it jumps to 'no_more_source'. If MULTIBYTEP and
a multibyte character is found for C2, set C2 to the negative value
of the character code. The caller should declare and set these
variables appropriately in advance:
src, src_end, multibytep
It is intended that this macro is used in detect_coding_utf_16. */
#define TWO_MORE_BYTES(c1, c2) \
do { \
do { \
if (src == src_end) \
goto no_more_source; \
c1 = *src++; \
if (multibytep && (c1 & 0x80)) \
{ \
if ((c1 & 0xFE) == 0xC0) \
c1 = ((c1 & 1) << 6) | *src++; \
else \
{ \
src += BYTES_BY_CHAR_HEAD (c1) - 1; \
c1 = -1; \
} \
} \
} while (c1 < 0); \
if (src == src_end) \
goto no_more_source; \
c2 = *src++; \
if (multibytep && (c2 & 0x80)) \
{ \
if ((c2 & 0xFE) == 0xC0) \
c2 = ((c2 & 1) << 6) | *src++; \
else \
c2 = -1; \
} \
} while (0)
/* Store a byte C in the place pointed by DST and increment DST to the
next free point, and increment PRODUCED_CHARS. The caller should
assure that C is 0..127, and declare and set the variable `dst'
appropriately in advance.
*/
#define EMIT_ONE_ASCII_BYTE(c) \
do { \
produced_chars++; \
*dst++ = (c); \
} while (0)
/* Like EMIT_ONE_ASCII_BYTE but store two bytes; C1 and C2. */
#define EMIT_TWO_ASCII_BYTES(c1, c2) \
do { \
produced_chars += 2; \
*dst++ = (c1), *dst++ = (c2); \
} while (0)
/* Store a byte C in the place pointed by DST and increment DST to the
next free point, and increment PRODUCED_CHARS. If MULTIBYTEP,
store in an appropriate multibyte form. The caller should
declare and set the variables `dst' and `multibytep' appropriately
in advance. */
#define EMIT_ONE_BYTE(c) \
do { \
produced_chars++; \
if (multibytep) \
{ \
unsigned ch = (c); \
if (ch >= 0x80) \
ch = BYTE8_TO_CHAR (ch); \
dst += CHAR_STRING (ch, dst); \
} \
else \
*dst++ = (c); \
} while (0)
/* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */
#define EMIT_TWO_BYTES(c1, c2) \
do { \
produced_chars += 2; \
if (multibytep) \
{ \
unsigned ch; \
\
ch = (c1); \
if (ch >= 0x80) \
ch = BYTE8_TO_CHAR (ch); \
dst += CHAR_STRING (ch, dst); \
ch = (c2); \
if (ch >= 0x80) \
ch = BYTE8_TO_CHAR (ch); \
dst += CHAR_STRING (ch, dst); \
} \
else \
{ \
*dst++ = (c1); \
*dst++ = (c2); \
} \
} while (0)
#define EMIT_THREE_BYTES(c1, c2, c3) \
do { \
EMIT_ONE_BYTE (c1); \
EMIT_TWO_BYTES (c2, c3); \
} while (0)
#define EMIT_FOUR_BYTES(c1, c2, c3, c4) \
do { \
EMIT_TWO_BYTES (c1, c2); \
EMIT_TWO_BYTES (c3, c4); \
} while (0)
static void
record_conversion_result (struct coding_system *coding,
enum coding_result_code result)
{
coding->result = result;
switch (result)
{
case CODING_RESULT_INSUFFICIENT_SRC:
Vlast_code_conversion_error = Qinsufficient_source;
break;
case CODING_RESULT_INVALID_SRC:
Vlast_code_conversion_error = Qinvalid_source;
break;
case CODING_RESULT_INTERRUPT:
Vlast_code_conversion_error = Qinterrupted;
break;
case CODING_RESULT_INSUFFICIENT_DST:
/* Don't record this error in Vlast_code_conversion_error
because it happens just temporarily and is resolved when the
whole conversion is finished. */
break;
case CODING_RESULT_SUCCESS:
break;
default:
Vlast_code_conversion_error = intern ("Unknown error");
}
}
/* These wrapper macros are used to preserve validity of pointers into
buffer text across calls to decode_char, encode_char, etc, which
could cause relocation of buffers if it loads a charset map,
because loading a charset map allocates large structures. */
#define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \
do { \
ptrdiff_t offset; \
\
charset_map_loaded = 0; \
c = DECODE_CHAR (charset, code); \
if (charset_map_loaded \
&& (offset = coding_change_source (coding))) \
{ \
src += offset; \
src_base += offset; \
src_end += offset; \
} \
} while (0)
#define CODING_ENCODE_CHAR(coding, dst, dst_end, charset, c, code) \
do { \
ptrdiff_t offset; \
\
charset_map_loaded = 0; \
code = ENCODE_CHAR (charset, c); \
if (charset_map_loaded \
&& (offset = coding_change_destination (coding))) \
{ \
dst += offset; \
dst_end += offset; \
} \
} while (0)
#define CODING_CHAR_CHARSET(coding, dst, dst_end, c, charset_list, code_return, charset) \
do { \
ptrdiff_t offset; \
\
charset_map_loaded = 0; \
charset = char_charset (c, charset_list, code_return); \
if (charset_map_loaded \
&& (offset = coding_change_destination (coding))) \
{ \
dst += offset; \
dst_end += offset; \
} \
} while (0)
#define CODING_CHAR_CHARSET_P(coding, dst, dst_end, c, charset, result) \
do { \
ptrdiff_t offset; \
\
charset_map_loaded = 0; \
result = CHAR_CHARSET_P (c, charset); \
if (charset_map_loaded \
&& (offset = coding_change_destination (coding))) \
{ \
dst += offset; \
dst_end += offset; \
} \
} while (0)
/* If there are at least BYTES length of room at dst, allocate memory
for coding->destination and update dst and dst_end. We don't have
to take care of coding->source which will be relocated. It is
handled by calling coding_set_source in encode_coding. */
#define ASSURE_DESTINATION(bytes) \
do { \
if (dst + (bytes) >= dst_end) \
{ \
ptrdiff_t more_bytes = charbuf_end - charbuf + (bytes); \
\
dst = alloc_destination (coding, more_bytes, dst); \
dst_end = coding->destination + coding->dst_bytes; \
} \
} while (0)
/* Store multibyte form of the character C in P, and advance P to the
end of the multibyte form. This used to be like adding CHAR_STRING
without ever calling MAYBE_UNIFY_CHAR, but nowadays we don't call
MAYBE_UNIFY_CHAR in CHAR_STRING. */
#define CHAR_STRING_ADVANCE_NO_UNIFY(c, p) ((p) += CHAR_STRING (c, p))
/* Return the character code of character whose multibyte form is at
P, and advance P to the end of the multibyte form. This used to be
like string_char_advance without ever calling MAYBE_UNIFY_CHAR, but
nowadays string_char_advance doesn't call MAYBE_UNIFY_CHAR. */
#define STRING_CHAR_ADVANCE_NO_UNIFY(p) string_char_advance (&(p))
/* Set coding->source from coding->src_object. */
static void
coding_set_source (struct coding_system *coding)
{
if (BUFFERP (coding->src_object))
{
struct buffer *buf = XBUFFER (coding->src_object);
if (coding->src_pos < 0)
coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte;
else
coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte);
}
else if (STRINGP (coding->src_object))
{
coding->source = SDATA (coding->src_object) + coding->src_pos_byte;
}
else
{
/* Otherwise, the source is C string and is never relocated
automatically. Thus we don't have to update anything. */
}
}
/* Set coding->source from coding->src_object, and return how many
bytes coding->source was changed. */
static ptrdiff_t
coding_change_source (struct coding_system *coding)
{
const unsigned char *orig = coding->source;
coding_set_source (coding);
return coding->source - orig;
}
/* Set coding->destination from coding->dst_object. */
static void
coding_set_destination (struct coding_system *coding)
{
if (BUFFERP (coding->dst_object))
{
if (BUFFERP (coding->src_object) && coding->src_pos < 0)
{
coding->destination = BEG_ADDR + coding->dst_pos_byte - BEG_BYTE;
coding->dst_bytes = (GAP_END_ADDR
- (coding->src_bytes - coding->consumed)
- coding->destination);
}
else
{
/* We are sure that coding->dst_pos_byte is before the gap
of the buffer. */
coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object))
+ coding->dst_pos_byte - BEG_BYTE);
coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object))
- coding->destination);
}
}
else
{
/* Otherwise, the destination is C string and is never relocated
automatically. Thus we don't have to update anything. */
}
}
/* Set coding->destination from coding->dst_object, and return how
many bytes coding->destination was changed. */
static ptrdiff_t
coding_change_destination (struct coding_system *coding)
{
const unsigned char *orig = coding->destination;
coding_set_destination (coding);
return coding->destination - orig;
}
static void
coding_alloc_by_realloc (struct coding_system *coding, ptrdiff_t bytes)
{
ptrdiff_t newbytes;
if (INT_ADD_WRAPV (coding->dst_bytes, bytes, &newbytes)
|| SIZE_MAX < newbytes)
string_overflow ();
coding->destination = xrealloc (coding->destination, newbytes);
coding->dst_bytes = newbytes;
}
static void
coding_alloc_by_making_gap (struct coding_system *coding,
ptrdiff_t gap_head_used, ptrdiff_t bytes)
{
if (EQ (coding->src_object, coding->dst_object))
{
/* The gap may contain the produced data at the head and not-yet
consumed data at the tail. To preserve those data, we at
first make the gap size to zero, then increase the gap
size. */
ptrdiff_t add = GAP_SIZE;
GPT += gap_head_used, GPT_BYTE += gap_head_used;
GAP_SIZE = 0; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add;
make_gap (bytes);
GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add;
GPT -= gap_head_used, GPT_BYTE -= gap_head_used;
}
else
make_gap_1 (XBUFFER (coding->dst_object), bytes);
}
static unsigned char *
alloc_destination (struct coding_system *coding, ptrdiff_t nbytes,
unsigned char *dst)
{
ptrdiff_t offset = dst - coding->destination;
if (BUFFERP (coding->dst_object))
{
struct buffer *buf = XBUFFER (coding->dst_object);
coding_alloc_by_making_gap (coding, dst - BUF_GPT_ADDR (buf), nbytes);
}
else
coding_alloc_by_realloc (coding, nbytes);
coding_set_destination (coding);
dst = coding->destination + offset;
return dst;
}
/** Macros for annotations. */
/* An annotation data is stored in the array coding->charbuf in this
format:
[ -LENGTH ANNOTATION_MASK NCHARS ... ]
LENGTH is the number of elements in the annotation.
ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK.
NCHARS is the number of characters in the text annotated.
The format of the following elements depend on ANNOTATION_MASK.
In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements
follows:
... NBYTES METHOD [ COMPOSITION-COMPONENTS ... ]
NBYTES is the number of bytes specified in the header part of
old-style emacs-mule encoding, or 0 for the other kind of
composition.
METHOD is one of enum composition_method.
Optional COMPOSITION-COMPONENTS are characters and composition
rules.
In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID
follows.
If ANNOTATION_MASK is 0, this annotation is just a space holder to
recover from an invalid annotation, and should be skipped by
produce_annotation. */
/* Maximum length of the header of annotation data. */
#define MAX_ANNOTATION_LENGTH 5
#define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \
do { \
*(buf)++ = -(len); \
*(buf)++ = (mask); \
*(buf)++ = (nchars); \
coding->annotated = 1; \
} while (0);
#define ADD_COMPOSITION_DATA(buf, nchars, nbytes, method) \
do { \
ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \
*buf++ = nbytes; \
*buf++ = method; \
} while (0)
#define ADD_CHARSET_DATA(buf, nchars, id) \
do { \
ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars); \
*buf++ = id; \
} while (0)
/* Bitmasks for coding->eol_seen. */
#define EOL_SEEN_NONE 0
#define EOL_SEEN_LF 1
#define EOL_SEEN_CR 2
#define EOL_SEEN_CRLF 4
\f
/*** 2. Emacs' internal format (emacs-utf-8) ***/
\f
/*** 3. UTF-8 ***/
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
Return true if a text is encoded in UTF-8. */
#define UTF_8_1_OCTET_P(c) ((c) < 0x80)
#define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80)
#define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0)
#define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0)
#define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0)
#define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8)
#define UTF_8_BOM_1 0xEF
#define UTF_8_BOM_2 0xBB
#define UTF_8_BOM_3 0xBF
/* Unlike the other detect_coding_XXX, this function counts the number
of characters and checks the EOL format. */
static bool
detect_coding_utf_8 (struct coding_system *coding,
struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source, *src_base;
const unsigned char *src_end = coding->source + coding->src_bytes;
bool multibytep = coding->src_multibyte;
ptrdiff_t consumed_chars = 0;
bool bom_found = 0;
ptrdiff_t nchars = coding->head_ascii;
int eol_seen = coding->eol_seen;
detect_info->checked |= CATEGORY_MASK_UTF_8;
/* A coding system of this category is always ASCII compatible. */
src += nchars;
if (src == coding->source /* BOM should be at the head. */
&& src + 3 < src_end /* BOM is 3-byte long. */
&& src[0] == UTF_8_BOM_1
&& src[1] == UTF_8_BOM_2
&& src[2] == UTF_8_BOM_3)
{
bom_found = 1;
src += 3;
nchars++;
}
while (1)
{
int c, c1, c2, c3, c4;
src_base = src;
ONE_MORE_BYTE (c);
if (c < 0 || UTF_8_1_OCTET_P (c))
{
nchars++;
if (c == '\r')
{
if (src < src_end && *src == '\n')
{
eol_seen |= EOL_SEEN_CRLF;
src++;
nchars++;
}
else
eol_seen |= EOL_SEEN_CR;
}
else if (c == '\n')
eol_seen |= EOL_SEEN_LF;
continue;
}
ONE_MORE_BYTE (c1);
if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1))
break;
if (UTF_8_2_OCTET_LEADING_P (c))
{
nchars++;
continue;
}
ONE_MORE_BYTE (c2);
if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2))
break;
if (UTF_8_3_OCTET_LEADING_P (c))
{
nchars++;
continue;
}
ONE_MORE_BYTE (c3);
if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3))
break;
if (UTF_8_4_OCTET_LEADING_P (c))
{
nchars++;
continue;
}
ONE_MORE_BYTE (c4);
if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4))
break;
if (UTF_8_5_OCTET_LEADING_P (c)
/* If we ever need to increase MAX_CHAR, the below may need
to be reviewed. */
&& c < MAX_MULTIBYTE_LEADING_CODE)
{
nchars++;
continue;
}
break;
}
detect_info->rejected |= CATEGORY_MASK_UTF_8;
return 0;
no_more_source:
if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK)
{
detect_info->rejected |= CATEGORY_MASK_UTF_8;
return 0;
}
if (bom_found)
{
/* The first character 0xFFFE doesn't necessarily mean a BOM. */
detect_info->found |= CATEGORY_MASK_UTF_8_AUTO | CATEGORY_MASK_UTF_8_SIG | CATEGORY_MASK_UTF_8_NOSIG;
}
else
{
detect_info->rejected |= CATEGORY_MASK_UTF_8_SIG;
if (nchars < src_end - coding->source)
/* The found characters are less than source bytes, which
means that we found a valid non-ASCII characters. */
detect_info->found |= CATEGORY_MASK_UTF_8_AUTO | CATEGORY_MASK_UTF_8_NOSIG;
}
coding->detected_utf8_bytes = src_base - coding->source;
coding->detected_utf8_chars = nchars;
return 1;
}
static void
decode_coding_utf_8 (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
const unsigned char *src_base;
int *charbuf = coding->charbuf + coding->charbuf_used;
int *charbuf_end = coding->charbuf + coding->charbuf_size;
ptrdiff_t consumed_chars = 0, consumed_chars_base = 0;
bool multibytep = coding->src_multibyte;
enum utf_bom_type bom = CODING_UTF_8_BOM (coding);
bool eol_dos
= !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
int byte_after_cr = -1;
if (bom != utf_without_bom)
{
int c1, c2, c3;
src_base = src;
ONE_MORE_BYTE (c1);
if (! UTF_8_3_OCTET_LEADING_P (c1))
src = src_base;
else
{
ONE_MORE_BYTE (c2);
if (! UTF_8_EXTRA_OCTET_P (c2))
src = src_base;
else
{
ONE_MORE_BYTE (c3);
if (! UTF_8_EXTRA_OCTET_P (c3))
src = src_base;
else
{
if ((c1 != UTF_8_BOM_1)
|| (c2 != UTF_8_BOM_2) || (c3 != UTF_8_BOM_3))
src = src_base;
else
CODING_UTF_8_BOM (coding) = utf_without_bom;
}
}
}
}
CODING_UTF_8_BOM (coding) = utf_without_bom;
while (1)
{
int c, c1, c2, c3, c4, c5;
src_base = src;
consumed_chars_base = consumed_chars;
if (charbuf >= charbuf_end)
{
if (byte_after_cr >= 0)
src_base--;
break;
}
/* In the simple case, rapidly handle ordinary characters */
if (multibytep && ! eol_dos
&& charbuf < charbuf_end - 6 && src < src_end - 6)
{
while (charbuf < charbuf_end - 6 && src < src_end - 6)
{
c1 = *src;
if (c1 & 0x80)
break;
src++;
consumed_chars++;
*charbuf++ = c1;
c1 = *src;
if (c1 & 0x80)
break;
src++;
consumed_chars++;
*charbuf++ = c1;
c1 = *src;
if (c1 & 0x80)
break;
src++;
consumed_chars++;
*charbuf++ = c1;
c1 = *src;
if (c1 & 0x80)
break;
src++;
consumed_chars++;
*charbuf++ = c1;
}
/* If we handled at least one character, restart the main loop. */
if (src != src_base)
continue;
}
if (byte_after_cr >= 0)
c1 = byte_after_cr, byte_after_cr = -1;
else
ONE_MORE_BYTE (c1);
if (c1 < 0)
{
c = - c1;
}
else if (UTF_8_1_OCTET_P (c1))
{
if (eol_dos && c1 == '\r')
ONE_MORE_BYTE (byte_after_cr);
c = c1;
}
else
{
ONE_MORE_BYTE (c2);
if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2))
goto invalid_code;
if (UTF_8_2_OCTET_LEADING_P (c1))
{
c = ((c1 & 0x1F) << 6) | (c2 & 0x3F);
/* Reject overlong sequences here and below. Encoders
producing them are incorrect, they can be misleading,
and they mess up read/write invariance. */
if (c < 128)
goto invalid_code;
}
else
{
ONE_MORE_BYTE (c3);
if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3))
goto invalid_code;
if (UTF_8_3_OCTET_LEADING_P (c1))
{
c = (((c1 & 0xF) << 12)
| ((c2 & 0x3F) << 6) | (c3 & 0x3F));
if (c < 0x800
|| (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */
goto invalid_code;
}
else
{
ONE_MORE_BYTE (c4);
if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4))
goto invalid_code;
if (UTF_8_4_OCTET_LEADING_P (c1))
{
c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12)
| ((c3 & 0x3F) << 6) | (c4 & 0x3F));
if (c < 0x10000)
goto invalid_code;
}
else
{
ONE_MORE_BYTE (c5);
if (c5 < 0 || ! UTF_8_EXTRA_OCTET_P (c5))
goto invalid_code;
if (UTF_8_5_OCTET_LEADING_P (c1))
{
c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18)
| ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6)
| (c5 & 0x3F));
if ((c > MAX_CHAR) || (c < 0x200000))
goto invalid_code;
}
else
goto invalid_code;
}
}
}
}
*charbuf++ = c;
continue;
invalid_code:
src = src_base;
consumed_chars = consumed_chars_base;
ONE_MORE_BYTE (c);
*charbuf++ = ASCII_CHAR_P (c) ? c : BYTE8_TO_CHAR (c);
}
no_more_source:
coding->consumed_char += consumed_chars_base;
coding->consumed = src_base - coding->source;
coding->charbuf_used = charbuf - coding->charbuf;
}
bool
encode_coding_utf_8 (struct coding_system *coding)
{
bool multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
int *charbuf_end = charbuf + coding->charbuf_used;
unsigned char *dst = coding->destination + coding->produced;
unsigned char *dst_end = coding->destination + coding->dst_bytes;
ptrdiff_t produced_chars = 0;
int c;
if (CODING_UTF_8_BOM (coding) == utf_with_bom)
{
ASSURE_DESTINATION (3);
EMIT_THREE_BYTES (UTF_8_BOM_1, UTF_8_BOM_2, UTF_8_BOM_3);
CODING_UTF_8_BOM (coding) = utf_without_bom;
}
if (multibytep)
{
int safe_room = MAX_MULTIBYTE_LENGTH * 2;
while (charbuf < charbuf_end)
{
unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str;
ASSURE_DESTINATION (safe_room);
c = *charbuf++;
if (CHAR_BYTE8_P (c))
{
c = CHAR_TO_BYTE8 (c);
EMIT_ONE_BYTE (c);
}
else
{
CHAR_STRING_ADVANCE_NO_UNIFY (c, pend);
for (p = str; p < pend; p++)
EMIT_ONE_BYTE (*p);
}
}
}
else
{
int safe_room = MAX_MULTIBYTE_LENGTH;
while (charbuf < charbuf_end)
{
ASSURE_DESTINATION (safe_room);
c = *charbuf++;
if (CHAR_BYTE8_P (c))
*dst++ = CHAR_TO_BYTE8 (c);
else
CHAR_STRING_ADVANCE_NO_UNIFY (c, dst);
}
produced_chars = dst - (coding->destination + coding->produced);
}
record_conversion_result (coding, CODING_RESULT_SUCCESS);
coding->produced_char += produced_chars;
coding->produced = dst - coding->destination;
return 0;
}
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
Return true if a text is encoded in one of UTF-16 based coding systems. */
static bool
detect_coding_utf_16 (struct coding_system *coding,
struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source;
const unsigned char *src_end = coding->source + coding->src_bytes;
bool multibytep = coding->src_multibyte;
int c1, c2;
detect_info->checked |= CATEGORY_MASK_UTF_16;
if (coding->mode & CODING_MODE_LAST_BLOCK
&& (coding->src_chars & 1))
{
detect_info->rejected |= CATEGORY_MASK_UTF_16;
return 0;
}
TWO_MORE_BYTES (c1, c2);
if ((c1 == 0xFF) && (c2 == 0xFE))
{
detect_info->found |= (CATEGORY_MASK_UTF_16_LE
| CATEGORY_MASK_UTF_16_AUTO);
detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE
| CATEGORY_MASK_UTF_16_BE_NOSIG
| CATEGORY_MASK_UTF_16_LE_NOSIG);
}
else if ((c1 == 0xFE) && (c2 == 0xFF))
{
detect_info->found |= (CATEGORY_MASK_UTF_16_BE
| CATEGORY_MASK_UTF_16_AUTO);
detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE
| CATEGORY_MASK_UTF_16_BE_NOSIG
| CATEGORY_MASK_UTF_16_LE_NOSIG);
}
else if (c2 < 0)
{
detect_info->rejected |= CATEGORY_MASK_UTF_16;
return 0;
}
else
{
/* We check the dispersion of Eth and Oth bytes where E is even and
O is odd. If both are high, we assume binary data.*/
unsigned char e[256], o[256];
unsigned e_num = 1, o_num = 1;
memset (e, 0, 256);
memset (o, 0, 256);
e[c1] = 1;
o[c2] = 1;
detect_info->rejected |= (CATEGORY_MASK_UTF_16_AUTO
|CATEGORY_MASK_UTF_16_BE
| CATEGORY_MASK_UTF_16_LE);
while ((detect_info->rejected & CATEGORY_MASK_UTF_16)
!= CATEGORY_MASK_UTF_16)
{
TWO_MORE_BYTES (c1, c2);
if (c2 < 0)
break;
if (! e[c1])
{
e[c1] = 1;
e_num++;
if (e_num >= 128)
detect_info->rejected |= CATEGORY_MASK_UTF_16_BE_NOSIG;
}
if (! o[c2])
{
o[c2] = 1;
o_num++;
if (o_num >= 128)
detect_info->rejected |= CATEGORY_MASK_UTF_16_LE_NOSIG;
}
}
return 0;
}
no_more_source:
return 1;
}
static void
decode_coding_utf_16 (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
const unsigned char *src_base;
int *charbuf = coding->charbuf + coding->charbuf_used;
/* We may produces at most 3 chars in one loop. */
int *charbuf_end = coding->charbuf + coding->charbuf_size - 2;
ptrdiff_t consumed_chars = 0, consumed_chars_base = 0;
bool multibytep = coding->src_multibyte;
enum utf_bom_type bom = CODING_UTF_16_BOM (coding);
enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding);
int surrogate = CODING_UTF_16_SURROGATE (coding);
bool eol_dos
= !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
int byte_after_cr1 = -1, byte_after_cr2 = -1;
if (bom == utf_with_bom)
{
int c, c1, c2;
src_base = src;
ONE_MORE_BYTE (c1);
ONE_MORE_BYTE (c2);
c = (c1 << 8) | c2;
if (endian == utf_16_big_endian
? c != 0xFEFF : c != 0xFFFE)
{
/* The first two bytes are not BOM. Treat them as bytes
for a normal character. */
src = src_base;
}
CODING_UTF_16_BOM (coding) = utf_without_bom;
}
else if (bom == utf_detect_bom)
{
/* We have already tried to detect BOM and failed in
detect_coding. */
CODING_UTF_16_BOM (coding) = utf_without_bom;
}
while (1)
{
int c, c1, c2;
src_base = src;
consumed_chars_base = consumed_chars;
if (charbuf >= charbuf_end)
{
if (byte_after_cr1 >= 0)
src_base -= 2;
break;
}
if (byte_after_cr1 >= 0)
c1 = byte_after_cr1, byte_after_cr1 = -1;
else
ONE_MORE_BYTE (c1);
if (c1 < 0)
{
*charbuf++ = -c1;
continue;
}
if (byte_after_cr2 >= 0)
c2 = byte_after_cr2, byte_after_cr2 = -1;
else
ONE_MORE_BYTE (c2);
if (c2 < 0)
{
*charbuf++ = ASCII_CHAR_P (c1) ? c1 : BYTE8_TO_CHAR (c1);
*charbuf++ = -c2;
continue;
}
c = (endian == utf_16_big_endian
? ((c1 << 8) | c2) : ((c2 << 8) | c1));
if (surrogate)
{
if (! UTF_16_LOW_SURROGATE_P (c))
{
if (endian == utf_16_big_endian)
c1 = surrogate >> 8, c2 = surrogate & 0xFF;
else
c1 = surrogate & 0xFF, c2 = surrogate >> 8;
*charbuf++ = c1;
*charbuf++ = c2;
if (UTF_16_HIGH_SURROGATE_P (c))
CODING_UTF_16_SURROGATE (coding) = surrogate = c;
else
*charbuf++ = c;
}
else
{
c = ((surrogate - 0xD800) << 10) | (c - 0xDC00);
CODING_UTF_16_SURROGATE (coding) = surrogate = 0;
*charbuf++ = 0x10000 + c;
}
}
else
{
if (UTF_16_HIGH_SURROGATE_P (c))
CODING_UTF_16_SURROGATE (coding) = surrogate = c;
else
{
if (eol_dos && c == '\r')
{
ONE_MORE_BYTE (byte_after_cr1);
ONE_MORE_BYTE (byte_after_cr2);
}
*charbuf++ = c;
}
}
}
no_more_source:
coding->consumed_char += consumed_chars_base;
coding->consumed = src_base - coding->source;
coding->charbuf_used = charbuf - coding->charbuf;
}
static bool
encode_coding_utf_16 (struct coding_system *coding)
{
bool multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
int *charbuf_end = charbuf + coding->charbuf_used;
unsigned char *dst = coding->destination + coding->produced;
unsigned char *dst_end = coding->destination + coding->dst_bytes;
int safe_room = 8;
enum utf_bom_type bom = CODING_UTF_16_BOM (coding);
bool big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian;
ptrdiff_t produced_chars = 0;
int c;
if (bom != utf_without_bom)
{
ASSURE_DESTINATION (safe_room);
if (big_endian)
EMIT_TWO_BYTES (0xFE, 0xFF);
else
EMIT_TWO_BYTES (0xFF, 0xFE);
CODING_UTF_16_BOM (coding) = utf_without_bom;
}
while (charbuf < charbuf_end)
{
ASSURE_DESTINATION (safe_room);
c = *charbuf++;
if (c > MAX_UNICODE_CHAR)
c = coding->default_char;
if (c < 0x10000)
{
if (big_endian)
EMIT_TWO_BYTES (c >> 8, c & 0xFF);
else
EMIT_TWO_BYTES (c & 0xFF, c >> 8);
}
else
{
int c1, c2;
c -= 0x10000;
c1 = (c >> 10) + 0xD800;
c2 = (c & 0x3FF) + 0xDC00;
if (big_endian)
EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF);
else
EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8);
}
}
record_conversion_result (coding, CODING_RESULT_SUCCESS);
coding->produced = dst - coding->destination;
coding->produced_char += produced_chars;
return 0;
}
\f
/*** 6. Old Emacs' internal format (emacs-mule) ***/
/* Emacs' internal format for representation of multiple character
sets is a kind of multi-byte encoding, i.e. characters are
represented by variable-length sequences of one-byte codes.
ASCII characters and control characters (e.g. `tab', `newline') are
represented by one-byte sequences which are their ASCII codes, in
the range 0x00 through 0x7F.
8-bit characters of the range 0x80..0x9F are represented by
two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit
code + 0x20).
8-bit characters of the range 0xA0..0xFF are represented by
one-byte sequences which are their 8-bit code.
The other characters are represented by a sequence of `base
leading-code', optional `extended leading-code', and one or two
`position-code's. The length of the sequence is determined by the
base leading-code. Leading-code takes the range 0x81 through 0x9D,
whereas extended leading-code and position-code take the range 0xA0
through 0xFF. See `charset.h' for more details about leading-code
and position-code.
--- CODE RANGE of Emacs' internal format ---
character set range
------------- -----
ascii 0x00..0x7F
eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF
eight-bit-graphic 0xA0..0xBF
ELSE 0x81..0x9D + [0xA0..0xFF]+
---------------------------------------------
As this is the internal character representation, the format is
usually not used externally (i.e. in a file or in a data sent to a
process). But, it is possible to have a text externally in this
format (i.e. by encoding by the coding system `emacs-mule').
In that case, a sequence of one-byte codes has a slightly different
form.
At first, all characters in eight-bit-control are represented by
one-byte sequences which are their 8-bit code.
Next, character composition data are represented by the byte
sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ...,
where,
METHOD is 0xF2 plus one of composition method (enum
composition_method),
BYTES is 0xA0 plus a byte length of this composition data,
CHARS is 0xA0 plus a number of characters composed by this
data,
COMPONENTs are characters of multibyte form or composition
rules encoded by two-byte of ASCII codes.
In addition, for backward compatibility, the following formats are
also recognized as composition data on decoding.
0x80 MSEQ ...
0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ
Here,
MSEQ is a multibyte form but in these special format:
ASCII: 0xA0 ASCII_CODE+0x80,
other: LEADING_CODE+0x20 FOLLOWING-BYTE ...,
RULE is a one byte code of the range 0xA0..0xF0 that
represents a composition rule.
*/
char emacs_mule_bytes[256];
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
Return true if a text is encoded in 'emacs-mule'. */
static bool
detect_coding_emacs_mule (struct coding_system *coding,
struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source, *src_base;
const unsigned char *src_end = coding->source + coding->src_bytes;
bool multibytep = coding->src_multibyte;
ptrdiff_t consumed_chars = 0;
int c;
int found = 0;
detect_info->checked |= CATEGORY_MASK_EMACS_MULE;
/* A coding system of this category is always ASCII compatible. */
src += coding->head_ascii;
while (1)
{
src_base = src;
ONE_MORE_BYTE (c);
if (c < 0)
continue;
if (c == 0x80)
{
/* Perhaps the start of composite character. We simply skip
it because analyzing it is too heavy for detecting. But,
at least, we check that the composite character
constitutes of more than 4 bytes. */
const unsigned char *src_start;
repeat:
src_start = src;
do
{
ONE_MORE_BYTE (c);
}
while (c >= 0xA0);
if (src - src_start <= 4)
break;
found = CATEGORY_MASK_EMACS_MULE;
if (c == 0x80)
goto repeat;
}
if (c < 0x80)
{
if (c < 0x20
&& (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO))
break;
}
else
{
int more_bytes = emacs_mule_bytes[c] - 1;
while (more_bytes > 0)
{
ONE_MORE_BYTE (c);
if (c < 0xA0)
{
src--; /* Unread the last byte. */
break;
}
more_bytes--;
}
if (more_bytes != 0)
break;
found = CATEGORY_MASK_EMACS_MULE;
}
}
detect_info->rejected |= CATEGORY_MASK_EMACS_MULE;
return 0;
no_more_source:
if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK)
{
detect_info->rejected |= CATEGORY_MASK_EMACS_MULE;
return 0;
}
detect_info->found |= found;
return 1;
}
/* Parse emacs-mule multibyte sequence at SRC and return the decoded
character. If CMP_STATUS indicates that we must expect MSEQ or
RULE described above, decode it and return the negative value of
the decoded character or rule. If an invalid byte is found, return
-1. If SRC is too short, return -2. */
static int
emacs_mule_char (struct coding_system *coding, const unsigned char *src,
int *nbytes, int *nchars, int *id,
struct composition_status *cmp_status)
{
const unsigned char *src_end = coding->source + coding->src_bytes;
const unsigned char *src_base = src;
bool multibytep = coding->src_multibyte;
int charset_ID;
unsigned code;
int c;
ptrdiff_t consumed_chars = 0;
bool mseq_found = 0;
ONE_MORE_BYTE (c);
if (c < 0)
{
c = -c;
charset_ID = emacs_mule_charset[0];
}
else
{
if (c >= 0xA0)
{
if (cmp_status->state != COMPOSING_NO
&& cmp_status->old_form)
{
if (cmp_status->state == COMPOSING_CHAR)
{
if (c == 0xA0)
{
ONE_MORE_BYTE (c);
c -= 0x80;
if (c < 0)
goto invalid_code;
}
else
c -= 0x20;
mseq_found = 1;
}
else
{
*nbytes = src - src_base;
*nchars = consumed_chars;
return -c;
}
}
else
goto invalid_code;
}
switch (emacs_mule_bytes[c])
{
case 2:
if ((charset_ID = emacs_mule_charset[c]) < 0)
goto invalid_code;
ONE_MORE_BYTE (c);
if (c < 0xA0)
goto invalid_code;
code = c & 0x7F;
break;
case 3:
if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11
|| c == EMACS_MULE_LEADING_CODE_PRIVATE_12)
{
ONE_MORE_BYTE (c);
if (c < 0xA0 || (charset_ID = emacs_mule_charset[c]) < 0)
goto invalid_code;
ONE_MORE_BYTE (c);
if (c < 0xA0)
goto invalid_code;
code = c & 0x7F;
}
else
{
if ((charset_ID = emacs_mule_charset[c]) < 0)
goto invalid_code;
ONE_MORE_BYTE (c);
if (c < 0xA0)
goto invalid_code;
code = (c & 0x7F) << 8;
ONE_MORE_BYTE (c);
if (c < 0xA0)
goto invalid_code;
code |= c & 0x7F;
}
break;
case 4:
ONE_MORE_BYTE (c);
if (c < 0 || (charset_ID = emacs_mule_charset[c]) < 0)
goto invalid_code;
ONE_MORE_BYTE (c);
if (c < 0xA0)
goto invalid_code;
code = (c & 0x7F) << 8;
ONE_MORE_BYTE (c);
if (c < 0xA0)
goto invalid_code;
code |= c & 0x7F;
break;
case 1:
code = c;
charset_ID = ASCII_CHAR_P (code) ? charset_ascii : charset_eight_bit;
break;
default:
emacs_abort ();
}
CODING_DECODE_CHAR (coding, src, src_base, src_end,
CHARSET_FROM_ID (charset_ID), code, c);
if (c < 0)
goto invalid_code;
}
*nbytes = src - src_base;
*nchars = consumed_chars;
if (id)
*id = charset_ID;
return (mseq_found ? -c : c);
no_more_source:
return -2;
invalid_code:
return -1;
}
/* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */
/* Handle these composition sequence ('|': the end of header elements,
BYTES and CHARS >= 0xA0):
(1) relative composition: 0x80 0xF2 BYTES CHARS | CHAR ...
(2) altchar composition: 0x80 0xF4 BYTES CHARS | ALT ... ALT CHAR ...
(3) alt&rule composition: 0x80 0xF5 BYTES CHARS | ALT RULE ... ALT CHAR ...
and these old form:
(4) relative composition: 0x80 | MSEQ ... MSEQ
(5) rulebase composition: 0x80 0xFF | MSEQ MRULE ... MSEQ
When the starter 0x80 and the following header elements are found,
this annotation header is produced.
[ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS NBYTES METHOD ]
NCHARS is CHARS - 0xA0 for (1), (2), (3), and 0 for (4), (5).
NBYTES is BYTES - 0xA0 for (1), (2), (3), and 0 for (4), (5).
Then, upon reading the following elements, these codes are produced
until the composition end is found:
(1) CHAR ... CHAR
(2) ALT ... ALT CHAR ... CHAR
(3) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT CHAR ... CHAR
(4) CHAR ... CHAR
(5) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR
When the composition end is found, LENGTH and NCHARS in the
annotation header is updated as below:
(1) LENGTH: unchanged, NCHARS: unchanged
(2) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged
(3) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged
(4) LENGTH: unchanged, NCHARS: number of CHARs
(5) LENGTH: unchanged, NCHARS: number of CHARs
If an error is found while composing, the annotation header is
changed to the original composition header (plus filler -1s) as
below:
(1),(2),(3) [ 0x80 0xF2+METHOD BYTES CHARS -1 ]
(5) [ 0x80 0xFF -1 -1- -1 ]
and the sequence [ -2 DECODED-RULE ] is changed to the original
byte sequence as below:
o the original byte sequence is B: [ B -1 ]
o the original byte sequence is B1 B2: [ B1 B2 ]
Most of the routines are implemented by macros because many
variables and labels in the caller decode_coding_emacs_mule must be
accessible, and they are usually called just once (thus doesn't
increase the size of compiled object). */
/* Decode a composition rule represented by C as a component of
composition sequence of Emacs 20 style. Set RULE to the decoded
rule. */
#define DECODE_EMACS_MULE_COMPOSITION_RULE_20(c, rule) \
do { \
int gref, nref; \
\
c -= 0xA0; \
if (c < 0 || c >= 81) \
goto invalid_code; \
gref = c / 9, nref = c % 9; \
if (gref == 4) gref = 10; \
if (nref == 4) nref = 10; \
rule = COMPOSITION_ENCODE_RULE (gref, nref); \
} while (0)
/* Decode a composition rule represented by C and the following byte
at SRC as a component of composition sequence of Emacs 21 style.
Set RULE to the decoded rule. */
#define DECODE_EMACS_MULE_COMPOSITION_RULE_21(c, rule) \
do { \
int gref, nref; \
\
gref = c - 0x20; \
if (gref < 0 || gref >= 81) \
goto invalid_code; \
ONE_MORE_BYTE (c); \
nref = c - 0x20; \
if (nref < 0 || nref >= 81) \
goto invalid_code; \
rule = COMPOSITION_ENCODE_RULE (gref, nref); \
} while (0)
/* Start of Emacs 21 style format. The first three bytes at SRC are
(METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is the
byte length of this composition information, CHARS is the number of
characters composed by this composition. */
#define DECODE_EMACS_MULE_21_COMPOSITION() \
do { \
enum composition_method method = c - 0xF2; \
int nbytes, nchars; \
\
ONE_MORE_BYTE (c); \
if (c < 0) \
goto invalid_code; \
nbytes = c - 0xA0; \
if (nbytes < 3 || (method == COMPOSITION_RELATIVE && nbytes != 4)) \
goto invalid_code; \
ONE_MORE_BYTE (c); \
nchars = c - 0xA0; \
if (nchars <= 0 || nchars >= MAX_COMPOSITION_COMPONENTS) \
goto invalid_code; \
cmp_status->old_form = 0; \
cmp_status->method = method; \
if (method == COMPOSITION_RELATIVE) \
cmp_status->state = COMPOSING_CHAR; \
else \
cmp_status->state = COMPOSING_COMPONENT_CHAR; \
cmp_status->length = MAX_ANNOTATION_LENGTH; \
cmp_status->nchars = nchars; \
cmp_status->ncomps = nbytes - 4; \
ADD_COMPOSITION_DATA (charbuf, nchars, nbytes, method); \
} while (0)
/* Start of Emacs 20 style format for relative composition. */
#define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION() \
do { \
cmp_status->old_form = 1; \
cmp_status->method = COMPOSITION_RELATIVE; \
cmp_status->state = COMPOSING_CHAR; \
cmp_status->length = MAX_ANNOTATION_LENGTH; \
cmp_status->nchars = cmp_status->ncomps = 0; \
ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \
} while (0)
/* Start of Emacs 20 style format for rule-base composition. */
#define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION() \
do { \
cmp_status->old_form = 1; \
cmp_status->method = COMPOSITION_WITH_RULE; \
cmp_status->state = COMPOSING_CHAR; \
cmp_status->length = MAX_ANNOTATION_LENGTH; \
cmp_status->nchars = cmp_status->ncomps = 0; \
ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \
} while (0)
#define DECODE_EMACS_MULE_COMPOSITION_START() \
do { \
const unsigned char *current_src = src; \
\
ONE_MORE_BYTE (c); \
if (c < 0) \
goto invalid_code; \
if (c - 0xF2 >= COMPOSITION_RELATIVE \
&& c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) \
DECODE_EMACS_MULE_21_COMPOSITION (); \
else if (c < 0xA0) \
goto invalid_code; \
else if (c < 0xC0) \
{ \
DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (); \
/* Re-read C as a composition component. */ \
src = current_src; \
} \
else if (c == 0xFF) \
DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (); \
else \
goto invalid_code; \
} while (0)
#define EMACS_MULE_COMPOSITION_END() \
do { \
int idx = - cmp_status->length; \
\
if (cmp_status->old_form) \
charbuf[idx + 2] = cmp_status->nchars; \
else if (cmp_status->method > COMPOSITION_RELATIVE) \
charbuf[idx] = charbuf[idx + 2] - cmp_status->length; \
cmp_status->state = COMPOSING_NO; \
} while (0)
static int
emacs_mule_finish_composition (int *charbuf,
struct composition_status *cmp_status)
{
int idx = - cmp_status->length;
int new_chars;
if (cmp_status->old_form && cmp_status->nchars > 0)
{
charbuf[idx + 2] = cmp_status->nchars;
new_chars = 0;
if (cmp_status->method == COMPOSITION_WITH_RULE
&& cmp_status->state == COMPOSING_CHAR)
{
/* The last rule was invalid. */
int rule = charbuf[-1] + 0xA0;
charbuf[-2] = BYTE8_TO_CHAR (rule);
charbuf[-1] = -1;
new_chars = 1;
}
}
else
{
charbuf[idx++] = BYTE8_TO_CHAR (0x80);
if (cmp_status->method == COMPOSITION_WITH_RULE)
{
charbuf[idx++] = BYTE8_TO_CHAR (0xFF);
charbuf[idx++] = -3;
charbuf[idx++] = 0;
new_chars = 1;
}
else
{
int nchars = charbuf[idx + 1] + 0xA0;
int nbytes = charbuf[idx + 2] + 0xA0;
charbuf[idx++] = BYTE8_TO_CHAR (0xF2 + cmp_status->method);
charbuf[idx++] = BYTE8_TO_CHAR (nbytes);
charbuf[idx++] = BYTE8_TO_CHAR (nchars);
charbuf[idx++] = -1;
new_chars = 4;
}
}
cmp_status->state = COMPOSING_NO;
return new_chars;
}
#define EMACS_MULE_MAYBE_FINISH_COMPOSITION() \
do { \
if (cmp_status->state != COMPOSING_NO) \
char_offset += emacs_mule_finish_composition (charbuf, cmp_status); \
} while (0)
static void
decode_coding_emacs_mule (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
const unsigned char *src_base;
int *charbuf = coding->charbuf + coding->charbuf_used;
/* We may produce two annotations (charset and composition) in one
loop and one more charset annotation at the end. */
int *charbuf_end
= coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3)
/* We can produce up to 2 characters in a loop. */
- 1;
ptrdiff_t consumed_chars = 0, consumed_chars_base;
bool multibytep = coding->src_multibyte;
ptrdiff_t char_offset = coding->produced_char;
ptrdiff_t last_offset = char_offset;
int last_id = charset_ascii;
bool eol_dos
= !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
int byte_after_cr = -1;
struct composition_status *cmp_status = &coding->spec.emacs_mule.cmp_status;
if (cmp_status->state != COMPOSING_NO)
{
int i;
if (charbuf_end - charbuf < cmp_status->length)
emacs_abort ();
for (i = 0; i < cmp_status->length; i++)
*charbuf++ = cmp_status->carryover[i];
coding->annotated = 1;
}
while (1)
{
int c;
int id UNINIT;
src_base = src;
consumed_chars_base = consumed_chars;
if (charbuf >= charbuf_end)
{
if (byte_after_cr >= 0)
src_base--;
break;
}
if (byte_after_cr >= 0)
c = byte_after_cr, byte_after_cr = -1;
else
ONE_MORE_BYTE (c);
if (c < 0 || c == 0x80)
{
EMACS_MULE_MAYBE_FINISH_COMPOSITION ();
if (c < 0)
{
*charbuf++ = -c;
char_offset++;
}
else
DECODE_EMACS_MULE_COMPOSITION_START ();
continue;
}
if (c < 0x80)
{
if (eol_dos && c == '\r')
ONE_MORE_BYTE (byte_after_cr);
id = charset_ascii;
if (cmp_status->state != COMPOSING_NO)
{
if (cmp_status->old_form)
EMACS_MULE_MAYBE_FINISH_COMPOSITION ();
else if (cmp_status->state >= COMPOSING_COMPONENT_CHAR)
cmp_status->ncomps--;
}
}
else
{
int nchars UNINIT, nbytes UNINIT;
/* emacs_mule_char can load a charset map from a file, which
allocates a large structure and might cause buffer text
to be relocated as result. Thus, we need to remember the
original pointer to buffer text, and fix up all related
pointers after the call. */
const unsigned char *orig = coding->source;
ptrdiff_t offset;
c = emacs_mule_char (coding, src_base, &nbytes, &nchars, &id,
cmp_status);
offset = coding->source - orig;
if (offset)
{
src += offset;
src_base += offset;
src_end += offset;
}
if (c < 0)
{
if (c == -1)
goto invalid_code;
if (c == -2)
break;
}
src = src_base + nbytes;
consumed_chars = consumed_chars_base + nchars;
if (cmp_status->state >= COMPOSING_COMPONENT_CHAR)
cmp_status->ncomps -= nchars;
}
/* Now if C >= 0, we found a normally encoded character, if C <
0, we found an old-style composition component character or
rule. */
if (cmp_status->state == COMPOSING_NO)
{
if (last_id != id)
{
if (last_id != charset_ascii)
ADD_CHARSET_DATA (charbuf, char_offset - last_offset,
last_id);
last_id = id;
last_offset = char_offset;
}
*charbuf++ = c;
char_offset++;
}
else if (cmp_status->state == COMPOSING_CHAR)
{
if (cmp_status->old_form)
{
if (c >= 0)
{
EMACS_MULE_MAYBE_FINISH_COMPOSITION ();
*charbuf++ = c;
char_offset++;
}
else
{
*charbuf++ = -c;
cmp_status->nchars++;
cmp_status->length++;
if (cmp_status->nchars == MAX_COMPOSITION_COMPONENTS)
EMACS_MULE_COMPOSITION_END ();
else if (cmp_status->method == COMPOSITION_WITH_RULE)
cmp_status->state = COMPOSING_RULE;
}
}
else
{
*charbuf++ = c;
cmp_status->length++;
cmp_status->nchars--;
if (cmp_status->nchars == 0)
EMACS_MULE_COMPOSITION_END ();
}
}
else if (cmp_status->state == COMPOSING_RULE)
{
int rule;
if (c >= 0)
{
EMACS_MULE_COMPOSITION_END ();
*charbuf++ = c;
char_offset++;
}
else
{
c = -c;
DECODE_EMACS_MULE_COMPOSITION_RULE_20 (c, rule);
if (rule < 0)
goto invalid_code;
*charbuf++ = -2;
*charbuf++ = rule;
cmp_status->length += 2;
cmp_status->state = COMPOSING_CHAR;
}
}
else if (cmp_status->state == COMPOSING_COMPONENT_CHAR)
{
*charbuf++ = c;
cmp_status->length++;
if (cmp_status->ncomps == 0)
cmp_status->state = COMPOSING_CHAR;
else if (cmp_status->ncomps > 0)
{
if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS)
cmp_status->state = COMPOSING_COMPONENT_RULE;
}
else
EMACS_MULE_MAYBE_FINISH_COMPOSITION ();
}
else /* COMPOSING_COMPONENT_RULE */
{
int rule;
DECODE_EMACS_MULE_COMPOSITION_RULE_21 (c, rule);
if (rule < 0)
goto invalid_code;
*charbuf++ = -2;
*charbuf++ = rule;
cmp_status->length += 2;
cmp_status->ncomps--;
if (cmp_status->ncomps > 0)
cmp_status->state = COMPOSING_COMPONENT_CHAR;
else
EMACS_MULE_MAYBE_FINISH_COMPOSITION ();
}
continue;
invalid_code:
EMACS_MULE_MAYBE_FINISH_COMPOSITION ();
src = src_base;
consumed_chars = consumed_chars_base;
ONE_MORE_BYTE (c);
*charbuf++ = ASCII_CHAR_P (c) ? c : BYTE8_TO_CHAR (c);
char_offset++;
}
no_more_source:
if (cmp_status->state != COMPOSING_NO)
{
if (coding->mode & CODING_MODE_LAST_BLOCK)
EMACS_MULE_MAYBE_FINISH_COMPOSITION ();
else
{
int i;
charbuf -= cmp_status->length;
for (i = 0; i < cmp_status->length; i++)
cmp_status->carryover[i] = charbuf[i];
}
}
if (last_id != charset_ascii)
ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id);
coding->consumed_char += consumed_chars_base;
coding->consumed = src_base - coding->source;
coding->charbuf_used = charbuf - coding->charbuf;
}
#define EMACS_MULE_LEADING_CODES(id, codes) \
do { \
if (id < 0xA0) \
codes[0] = id, codes[1] = 0; \
else if (id < 0xE0) \
codes[0] = 0x9A, codes[1] = id; \
else if (id < 0xF0) \
codes[0] = 0x9B, codes[1] = id; \
else if (id < 0xF5) \
codes[0] = 0x9C, codes[1] = id; \
else \
codes[0] = 0x9D, codes[1] = id; \
} while (0);
static bool
encode_coding_emacs_mule (struct coding_system *coding)
{
bool multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
int *charbuf_end = charbuf + coding->charbuf_used;
unsigned char *dst = coding->destination + coding->produced;
unsigned char *dst_end = coding->destination + coding->dst_bytes;
int safe_room = 8;
ptrdiff_t produced_chars = 0;
Lisp_Object attrs, charset_list;
int c;
int preferred_charset_id = -1;
CODING_GET_INFO (coding, attrs, charset_list);
if (! EQ (charset_list, Vemacs_mule_charset_list))
{
charset_list = Vemacs_mule_charset_list;
ASET (attrs, coding_attr_charset_list, charset_list);
}
while (charbuf < charbuf_end)
{
ASSURE_DESTINATION (safe_room);
c = *charbuf++;
if (c < 0)
{
/* Handle an annotation. */
switch (*charbuf)
{
case CODING_ANNOTATE_COMPOSITION_MASK:
/* Not yet implemented. */
break;
case CODING_ANNOTATE_CHARSET_MASK:
preferred_charset_id = charbuf[3];
if (preferred_charset_id >= 0
&& NILP (Fmemq (make_fixnum (preferred_charset_id),
charset_list)))
preferred_charset_id = -1;
break;
default:
emacs_abort ();
}
charbuf += -c - 1;
continue;
}
if (ASCII_CHAR_P (c))
EMIT_ONE_ASCII_BYTE (c);
else if (CHAR_BYTE8_P (c))
{
c = CHAR_TO_BYTE8 (c);
EMIT_ONE_BYTE (c);
}
else
{
struct charset *charset;
unsigned code;
int dimension;
int emacs_mule_id;
unsigned char leading_codes[2];
if (preferred_charset_id >= 0)
{
bool result;
charset = CHARSET_FROM_ID (preferred_charset_id);
CODING_CHAR_CHARSET_P (coding, dst, dst_end, c, charset, result);
if (result)
code = ENCODE_CHAR (charset, c);
else
CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list,
&code, charset);
}
else
CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list,
&code, charset);
if (! charset)
{
c = coding->default_char;
if (ASCII_CHAR_P (c))
{
EMIT_ONE_ASCII_BYTE (c);
continue;
}
CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list,
&code, charset);
}
dimension = CHARSET_DIMENSION (charset);
emacs_mule_id = CHARSET_EMACS_MULE_ID (charset);
EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes);
EMIT_ONE_BYTE (leading_codes[0]);
if (leading_codes[1])
EMIT_ONE_BYTE (leading_codes[1]);
if (dimension == 1)
EMIT_ONE_BYTE (code | 0x80);
else
{
code |= 0x8080;
EMIT_ONE_BYTE (code >> 8);
EMIT_ONE_BYTE (code & 0xFF);
}
}
}
record_conversion_result (coding, CODING_RESULT_SUCCESS);
coding->produced_char += produced_chars;
coding->produced = dst - coding->destination;
return 0;
}
\f
/*** 7. ISO2022 handlers ***/
/* The following note describes the coding system ISO2022 briefly.
Since the intention of this note is to help understand the
functions in this file, some parts are NOT ACCURATE or are OVERLY
SIMPLIFIED. For thorough understanding, please refer to the
original document of ISO2022. This is equivalent to the standard
ECMA-35, obtainable from <URL:https://www.ecma.ch/> (*).
ISO2022 provides many mechanisms to encode several character sets
in 7-bit and 8-bit environments. For 7-bit environments, all text
is encoded using bytes less than 128. This may make the encoded
text a little bit longer, but the text passes more easily through
several types of gateway, some of which strip off the MSB (Most
Significant Bit).
There are two kinds of character sets: control character sets and
graphic character sets. The former contain control characters such
as `newline' and `escape' to provide control functions (control
functions are also provided by escape sequences). The latter
contain graphic characters such as 'A' and '-'. Emacs recognizes
two control character sets and many graphic character sets.
Graphic character sets are classified into one of the following
four classes, according to the number of bytes (DIMENSION) and
number of characters in one dimension (CHARS) of the set:
- DIMENSION1_CHARS94
- DIMENSION1_CHARS96
- DIMENSION2_CHARS94
- DIMENSION2_CHARS96
In addition, each character set is assigned an identification tag,
unique for each set, called the "final character" (denoted as <F>
hereafter). The <F> of each character set is decided by ECMA(*)
when it is registered in ISO. The code range of <F> is 0x30..0x7F
(0x30..0x3F are for private use only).
Note (*): ECMA = European Computer Manufacturers Association
Here are examples of graphic character sets [NAME(<F>)]:
o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ...
o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ...
o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ...
o DIMENSION2_CHARS96 -- none for the moment
A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR.
C0 [0x00..0x1F] -- control character plane 0
GL [0x20..0x7F] -- graphic character plane 0
C1 [0x80..0x9F] -- control character plane 1
GR [0xA0..0xFF] -- graphic character plane 1
A control character set is directly designated and invoked to C0 or
C1 by an escape sequence. The most common case is that:
- ISO646's control character set is designated/invoked to C0, and
- ISO6429's control character set is designated/invoked to C1,
and usually these designations/invocations are omitted in encoded
text. In a 7-bit environment, only C0 can be used, and a control
character for C1 is encoded by an appropriate escape sequence to
fit into the environment. All control characters for C1 are
defined to have corresponding escape sequences.
A graphic character set is at first designated to one of four
graphic registers (G0 through G3), then these graphic registers are
invoked to GL or GR. These designations and invocations can be
done independently. The most common case is that G0 is invoked to
GL, G1 is invoked to GR, and ASCII is designated to G0. Usually
these invocations and designations are omitted in encoded text.
In a 7-bit environment, only GL can be used.
When a graphic character set of CHARS94 is invoked to GL, codes
0x20 and 0x7F of the GL area work as control characters SPACE and
DEL respectively, and codes 0xA0 and 0xFF of the GR area should not
be used.
There are two ways of invocation: locking-shift and single-shift.
With locking-shift, the invocation lasts until the next different
invocation, whereas with single-shift, the invocation affects the
following character only and doesn't affect the locking-shift
state. Invocations are done by the following control characters or
escape sequences:
----------------------------------------------------------------------
abbrev function cntrl escape seq description
----------------------------------------------------------------------
SI/LS0 (shift-in) 0x0F none invoke G0 into GL
SO/LS1 (shift-out) 0x0E none invoke G1 into GL
LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL
LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL
LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*)
LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*)
LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*)
SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char
SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char
----------------------------------------------------------------------
(*) These are not used by any known coding system.
Control characters for these functions are defined by macros
ISO_CODE_XXX in `coding.h'.
Designations are done by the following escape sequences:
----------------------------------------------------------------------
escape sequence description
----------------------------------------------------------------------
ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0
ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1
ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2
ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3
ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*)
ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1
ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2
ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3
ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**)
ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1
ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2
ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3
ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*)
ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1
ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2
ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3
----------------------------------------------------------------------
In this list, "DIMENSION1_CHARS94<F>" means a graphic character set
of dimension 1, chars 94, and final character <F>, etc...
Note (*): Although these designations are not allowed in ISO2022,
Emacs accepts them on decoding, and produces them on encoding
CHARS96 character sets in a coding system which is characterized as
7-bit environment, non-locking-shift, and non-single-shift.
Note (**): If <F> is '@', 'A', or 'B', the intermediate character
'(' must be omitted. We refer to this as "short-form" hereafter.
Now you may notice that there are a lot of ways of encoding the
same multilingual text in ISO2022. Actually, there exist many
coding systems such as Compound Text (used in X11's inter client
communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR
(used in Korean Internet), EUC (Extended UNIX Code, used in Asian
localized platforms), and all of these are variants of ISO2022.
In addition to the above, Emacs handles two more kinds of escape
sequences: ISO6429's direction specification and Emacs' private
sequence for specifying character composition.
ISO6429's direction specification takes the following form:
o CSI ']' -- end of the current direction
o CSI '0' ']' -- end of the current direction
o CSI '1' ']' -- start of left-to-right text
o CSI '2' ']' -- start of right-to-left text
The control character CSI (0x9B: control sequence introducer) is
abbreviated to the escape sequence ESC '[' in a 7-bit environment.
Character composition specification takes the following form:
o ESC '0' -- start relative composition
o ESC '1' -- end composition
o ESC '2' -- start rule-base composition (*)
o ESC '3' -- start relative composition with alternate chars (**)
o ESC '4' -- start rule-base composition with alternate chars (**)
Since these are not standard escape sequences of any ISO standard,
the use of them with these meanings is restricted to Emacs only.
(*) This form is used only in Emacs 20.7 and older versions,
but newer versions can safely decode it.
(**) This form is used only in Emacs 21.1 and newer versions,
and older versions can't decode it.
Here's a list of example usages of these composition escape
sequences (categorized by `enum composition_method').
COMPOSITION_RELATIVE:
ESC 0 CHAR [ CHAR ] ESC 1
COMPOSITION_WITH_RULE:
ESC 2 CHAR [ RULE CHAR ] ESC 1
COMPOSITION_WITH_ALTCHARS:
ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1
COMPOSITION_WITH_RULE_ALTCHARS:
ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */
static enum iso_code_class_type iso_code_class[256];
#define SAFE_CHARSET_P(coding, id) \
((id) <= (coding)->max_charset_id \
&& (coding)->safe_charsets[id] != 255)
static void
setup_iso_safe_charsets (Lisp_Object attrs)
{
Lisp_Object charset_list, safe_charsets;
Lisp_Object request;
Lisp_Object reg_usage;
Lisp_Object tail;
EMACS_INT reg94, reg96;
int flags = XFIXNUM (AREF (attrs, coding_attr_iso_flags));
int max_charset_id;
charset_list = CODING_ATTR_CHARSET_LIST (attrs);
if ((flags & CODING_ISO_FLAG_FULL_SUPPORT)
&& ! EQ (charset_list, Viso_2022_charset_list))
{
charset_list = Viso_2022_charset_list;
ASET (attrs, coding_attr_charset_list, charset_list);
ASET (attrs, coding_attr_safe_charsets, Qnil);
}
if (STRINGP (AREF (attrs, coding_attr_safe_charsets)))
return;
max_charset_id = 0;
for (tail = charset_list; CONSP (tail); tail = XCDR (tail))
{
int id = XFIXNUM (XCAR (tail));
if (max_charset_id < id)
max_charset_id = id;
}
safe_charsets = make_uninit_string (max_charset_id + 1);
memset (SDATA (safe_charsets), 255, max_charset_id + 1);
request = AREF (attrs, coding_attr_iso_request);
reg_usage = AREF (attrs, coding_attr_iso_usage);
reg94 = XFIXNUM (XCAR (reg_usage));
reg96 = XFIXNUM (XCDR (reg_usage));
for (tail = charset_list; CONSP (tail); tail = XCDR (tail))
{
Lisp_Object id;
Lisp_Object reg;
struct charset *charset;
id = XCAR (tail);
charset = CHARSET_FROM_ID (XFIXNUM (id));
reg = Fcdr (Fassq (id, request));
if (! NILP (reg))
SSET (safe_charsets, XFIXNUM (id), XFIXNUM (reg));
else if (charset->iso_chars_96)
{
if (reg96 < 4)
SSET (safe_charsets, XFIXNUM (id), reg96);
}
else
{
if (reg94 < 4)
SSET (safe_charsets, XFIXNUM (id), reg94);
}
}
ASET (attrs, coding_attr_safe_charsets, safe_charsets);
}
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
Return true if a text is encoded in one of ISO-2022 based coding
systems. */
static bool
detect_coding_iso_2022 (struct coding_system *coding,
struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source, *src_base = src;
const unsigned char *src_end = coding->source + coding->src_bytes;
bool multibytep = coding->src_multibyte;
bool single_shifting = 0;
int id;
int c, c1;
ptrdiff_t consumed_chars = 0;
int i;
int rejected = 0;
int found = 0;
int composition_count = -1;
detect_info->checked |= CATEGORY_MASK_ISO;
for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++)
{
struct coding_system *this = &(coding_categories[i]);
Lisp_Object attrs, val;
if (this->id < 0)
continue;
attrs = CODING_ID_ATTRS (this->id);
if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT
&& ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Viso_2022_charset_list))
setup_iso_safe_charsets (attrs);
val = CODING_ATTR_SAFE_CHARSETS (attrs);
this->max_charset_id = SCHARS (val) - 1;
this->safe_charsets = SDATA (val);
}
/* A coding system of this category is always ASCII compatible. */
src += coding->head_ascii;
while (rejected != CATEGORY_MASK_ISO)
{
src_base = src;
ONE_MORE_BYTE (c);
switch (c)
{
case ISO_CODE_ESC:
if (inhibit_iso_escape_detection)
break;
single_shifting = 0;
ONE_MORE_BYTE (c);
if (c == 'N' || c == 'O')
{
/* ESC <Fe> for SS2 or SS3. */
single_shifting = 1;
rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT;
}
else if (c == '1')
{
/* End of composition. */
if (composition_count < 0
|| composition_count > MAX_COMPOSITION_COMPONENTS)
/* Invalid */
break;
composition_count = -1;
found |= CATEGORY_MASK_ISO;
}
else if (c >= '0' && c <= '4')
{
/* ESC <Fp> for start/end composition. */
composition_count = 0;
}
else
{
if (c >= '(' && c <= '/')
{
/* Designation sequence for a charset of dimension 1. */
ONE_MORE_BYTE (c1);
if (c1 < ' ' || c1 >= 0x80
|| (id = iso_charset_table[0][c >= ','][c1]) < 0)
{
/* Invalid designation sequence. Just ignore. */
if (c1 >= 0x80)
rejected |= (CATEGORY_MASK_ISO_7BIT
| CATEGORY_MASK_ISO_7_ELSE);
break;
}
}
else if (c == '$')
{
/* Designation sequence for a charset of dimension 2. */
ONE_MORE_BYTE (c);
if (c >= '@' && c <= 'B')
/* Designation for JISX0208.1978, GB2312, or JISX0208. */
id = iso_charset_table[1][0][c];
else if (c >= '(' && c <= '/')
{
ONE_MORE_BYTE (c1);
if (c1 < ' ' || c1 >= 0x80
|| (id = iso_charset_table[1][c >= ','][c1]) < 0)
{
/* Invalid designation sequence. Just ignore. */
if (c1 >= 0x80)
rejected |= (CATEGORY_MASK_ISO_7BIT
| CATEGORY_MASK_ISO_7_ELSE);
break;
}
}
else
{
/* Invalid designation sequence. Just ignore it. */
if (c >= 0x80)
rejected |= (CATEGORY_MASK_ISO_7BIT
| CATEGORY_MASK_ISO_7_ELSE);
break;
}
}
else
{
/* Invalid escape sequence. Just ignore it. */
if (c >= 0x80)
rejected |= (CATEGORY_MASK_ISO_7BIT
| CATEGORY_MASK_ISO_7_ELSE);
break;
}
/* We found a valid designation sequence for CHARSET. */
rejected |= CATEGORY_MASK_ISO_8BIT;
if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7],
id))
found |= CATEGORY_MASK_ISO_7;
else
rejected |= CATEGORY_MASK_ISO_7;
if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight],
id))
found |= CATEGORY_MASK_ISO_7_TIGHT;
else
rejected |= CATEGORY_MASK_ISO_7_TIGHT;
if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else],
id))
found |= CATEGORY_MASK_ISO_7_ELSE;
else
rejected |= CATEGORY_MASK_ISO_7_ELSE;
if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else],
id))
found |= CATEGORY_MASK_ISO_8_ELSE;
else
rejected |= CATEGORY_MASK_ISO_8_ELSE;
}
break;
case ISO_CODE_SO:
case ISO_CODE_SI:
/* Locking shift out/in. */
if (inhibit_iso_escape_detection)
break;
single_shifting = 0;
rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT;
break;
case ISO_CODE_CSI:
/* Control sequence introducer. */
single_shifting = 0;
rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE;
found |= CATEGORY_MASK_ISO_8_ELSE;
goto check_extra_latin;
case ISO_CODE_SS2:
case ISO_CODE_SS3:
/* Single shift. */
if (inhibit_iso_escape_detection)
break;
single_shifting = 0;
rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE;
if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1])
& CODING_ISO_FLAG_SINGLE_SHIFT)
{
found |= CATEGORY_MASK_ISO_8_1;
single_shifting = 1;
}
if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2])
& CODING_ISO_FLAG_SINGLE_SHIFT)
{
found |= CATEGORY_MASK_ISO_8_2;
single_shifting = 1;
}
if (single_shifting)
break;
goto check_extra_latin;
default:
if (c < 0)
continue;
if (c < 0x80)
{
if (composition_count >= 0)
composition_count++;
single_shifting = 0;
break;
}
rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE;
if (c >= 0xA0)
{
found |= CATEGORY_MASK_ISO_8_1;
/* Check the length of succeeding codes of the range
0xA0..0FF. If the byte length is even, we include
CATEGORY_MASK_ISO_8_2 in `found'. We can check this
only when we are not single shifting. */
if (! single_shifting
&& ! (rejected & CATEGORY_MASK_ISO_8_2))
{
ptrdiff_t len = 1;
while (src < src_end)
{
src_base = src;
ONE_MORE_BYTE (c);
if (c < 0xA0)
{
src = src_base;
break;
}
len++;
}
if (len & 1 && src < src_end)
{
rejected |= CATEGORY_MASK_ISO_8_2;
if (composition_count >= 0)
composition_count += len;
}
else
{
found |= CATEGORY_MASK_ISO_8_2;
if (composition_count >= 0)
composition_count += len / 2;
}
}
break;
}
check_extra_latin:
if (! VECTORP (Vlatin_extra_code_table)
|| NILP (AREF (Vlatin_extra_code_table, c)))
{
rejected = CATEGORY_MASK_ISO;
break;
}
if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1])
& CODING_ISO_FLAG_LATIN_EXTRA)
found |= CATEGORY_MASK_ISO_8_1;
else
rejected |= CATEGORY_MASK_ISO_8_1;
rejected |= CATEGORY_MASK_ISO_8_2;
break;
}
}
detect_info->rejected |= CATEGORY_MASK_ISO;
return 0;
no_more_source:
detect_info->rejected |= rejected;
detect_info->found |= (found & ~rejected);
return 1;
}
/* Set designation state into CODING. Set CHARS_96 to -1 if the
escape sequence should be kept. */
#define DECODE_DESIGNATION(reg, dim, chars_96, final) \
do { \
int id, prev; \
\
if (final < '0' || final >= 128 \
|| ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \
|| !SAFE_CHARSET_P (coding, id)) \
{ \
CODING_ISO_DESIGNATION (coding, reg) = -2; \
chars_96 = -1; \
break; \
} \
prev = CODING_ISO_DESIGNATION (coding, reg); \
if (id == charset_jisx0201_roman) \
{ \
if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \
id = charset_ascii; \
} \
else if (id == charset_jisx0208_1978) \
{ \
if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \
id = charset_jisx0208; \
} \
CODING_ISO_DESIGNATION (coding, reg) = id; \
/* If there was an invalid designation to REG previously, and this \
designation is ASCII to REG, we should keep this designation \
sequence. */ \
if (prev == -2 && id == charset_ascii) \
chars_96 = -1; \
} while (0)
/* Handle these composition sequence (ALT: alternate char):
(1) relative composition: ESC 0 CHAR ... ESC 1
(2) rulebase composition: ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1
(3) altchar composition: ESC 3 ALT ... ALT ESC 0 CHAR ... ESC 1
(4) alt&rule composition: ESC 4 ALT RULE ... ALT ESC 0 CHAR ... ESC 1
When the start sequence (ESC 0/2/3/4) is found, this annotation
header is produced.
[ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) 0 METHOD ]
Then, upon reading CHAR or RULE (one or two bytes), these codes are
produced until the end sequence (ESC 1) is found:
(1) CHAR ... CHAR
(2) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR
(3) ALT ... ALT -1 -1 CHAR ... CHAR
(4) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT -1 -1 CHAR ... CHAR
When the end sequence (ESC 1) is found, LENGTH and NCHARS in the
annotation header is updated as below:
(1) LENGTH: unchanged, NCHARS: number of CHARs
(2) LENGTH: unchanged, NCHARS: number of CHARs
(3) LENGTH: += number of ALTs + 2, NCHARS: number of CHARs
(4) LENGTH: += number of ALTs * 3, NCHARS: number of CHARs
If an error is found while composing, the annotation header is
changed to:
[ ESC '0'/'2'/'3'/'4' -2 0 ]
and the sequence [ -2 DECODED-RULE ] is changed to the original
byte sequence as below:
o the original byte sequence is B: [ B -1 ]
o the original byte sequence is B1 B2: [ B1 B2 ]
and the sequence [ -1 -1 ] is changed to the original byte
sequence:
[ ESC '0' ]
*/
/* Decode a composition rule C1 and maybe one more byte from the
source, and set RULE to the encoded composition rule. If the rule
is invalid, goto invalid_code. */
#define DECODE_COMPOSITION_RULE(rule) \
do { \
rule = c1 - 32; \
if (rule < 0) \
goto invalid_code; \
if (rule < 81) /* old format (before ver.21) */ \
{ \
int gref = (rule) / 9; \
int nref = (rule) % 9; \
if (gref == 4) gref = 10; \
if (nref == 4) nref = 10; \
rule = COMPOSITION_ENCODE_RULE (gref, nref); \
} \
else /* new format (after ver.21) */ \
{ \
int b; \
\
ONE_MORE_BYTE (b); \
if (! COMPOSITION_ENCODE_RULE_VALID (rule - 81, b - 32)) \
goto invalid_code; \
rule = COMPOSITION_ENCODE_RULE (rule - 81, b - 32); \
rule += 0x100; /* Distinguish it from the old format. */ \
} \
} while (0)
#define ENCODE_COMPOSITION_RULE(rule) \
do { \
int gref = (rule % 0x100) / 12, nref = (rule % 0x100) % 12; \
\
if (rule < 0x100) /* old format */ \
{ \
if (gref == 10) gref = 4; \
if (nref == 10) nref = 4; \
charbuf[idx] = 32 + gref * 9 + nref; \
charbuf[idx + 1] = -1; \
new_chars++; \
} \
else /* new format */ \
{ \
charbuf[idx] = 32 + 81 + gref; \
charbuf[idx + 1] = 32 + nref; \
new_chars += 2; \
} \
} while (0)
/* Finish the current composition as invalid. */
static int
finish_composition (int *charbuf, struct composition_status *cmp_status)
{
int idx = - cmp_status->length;
int new_chars;
/* Recover the original ESC sequence */
charbuf[idx++] = ISO_CODE_ESC;
charbuf[idx++] = (cmp_status->method == COMPOSITION_RELATIVE ? '0'
: cmp_status->method == COMPOSITION_WITH_RULE ? '2'
: cmp_status->method == COMPOSITION_WITH_ALTCHARS ? '3'
/* cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS */
: '4');
charbuf[idx++] = -2;
charbuf[idx++] = 0;
charbuf[idx++] = -1;
new_chars = cmp_status->nchars;
if (cmp_status->method >= COMPOSITION_WITH_RULE)
for (; idx < 0; idx++)
{
int elt = charbuf[idx];
if (elt == -2)
{
ENCODE_COMPOSITION_RULE (charbuf[idx + 1]);
idx++;
}
else if (elt == -1)
{
charbuf[idx++] = ISO_CODE_ESC;
charbuf[idx] = '0';
new_chars += 2;
}
}
cmp_status->state = COMPOSING_NO;
return new_chars;
}
/* If characters are under composition, finish the composition. */
#define MAYBE_FINISH_COMPOSITION() \
do { \
if (cmp_status->state != COMPOSING_NO) \
char_offset += finish_composition (charbuf, cmp_status); \
} while (0)
/* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4.
ESC 0 : relative composition : ESC 0 CHAR ... ESC 1
ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1
ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1
ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1
Produce this annotation sequence now:
[ -LENGTH(==-4) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) METHOD ]
*/
#define DECODE_COMPOSITION_START(c1) \
do { \
if (c1 == '0' \
&& ((cmp_status->state == COMPOSING_COMPONENT_CHAR \
&& cmp_status->method == COMPOSITION_WITH_ALTCHARS) \
|| (cmp_status->state == COMPOSING_COMPONENT_RULE \
&& cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS))) \
{ \
*charbuf++ = -1; \
*charbuf++= -1; \
cmp_status->state = COMPOSING_CHAR; \
cmp_status->length += 2; \
} \
else \
{ \
MAYBE_FINISH_COMPOSITION (); \
cmp_status->method = (c1 == '0' ? COMPOSITION_RELATIVE \
: c1 == '2' ? COMPOSITION_WITH_RULE \
: c1 == '3' ? COMPOSITION_WITH_ALTCHARS \
: COMPOSITION_WITH_RULE_ALTCHARS); \
cmp_status->state \
= (c1 <= '2' ? COMPOSING_CHAR : COMPOSING_COMPONENT_CHAR); \
ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \
cmp_status->length = MAX_ANNOTATION_LENGTH; \
cmp_status->nchars = cmp_status->ncomps = 0; \
coding->annotated = 1; \
} \
} while (0)
/* Handle composition end sequence ESC 1. */
#define DECODE_COMPOSITION_END() \
do { \
if (cmp_status->nchars == 0 \
|| ((cmp_status->state == COMPOSING_CHAR) \
== (cmp_status->method == COMPOSITION_WITH_RULE))) \
{ \
MAYBE_FINISH_COMPOSITION (); \
goto invalid_code; \
} \
if (cmp_status->method == COMPOSITION_WITH_ALTCHARS) \
charbuf[- cmp_status->length] -= cmp_status->ncomps + 2; \
else if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) \
charbuf[- cmp_status->length] -= cmp_status->ncomps * 3; \
charbuf[- cmp_status->length + 2] = cmp_status->nchars; \
char_offset += cmp_status->nchars; \
cmp_status->state = COMPOSING_NO; \
} while (0)
/* Store a composition rule RULE in charbuf, and update cmp_status. */
#define STORE_COMPOSITION_RULE(rule) \
do { \
*charbuf++ = -2; \
*charbuf++ = rule; \
cmp_status->length += 2; \
cmp_status->state--; \
} while (0)
/* Store a composed char or a component char C in charbuf, and update
cmp_status. */
#define STORE_COMPOSITION_CHAR(c) \
do { \
*charbuf++ = (c); \
cmp_status->length++; \
if (cmp_status->state == COMPOSING_CHAR) \
cmp_status->nchars++; \
else \
cmp_status->ncomps++; \
if (cmp_status->method == COMPOSITION_WITH_RULE \
|| (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS \
&& cmp_status->state == COMPOSING_COMPONENT_CHAR)) \
cmp_status->state++; \
} while (0)
/* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */
static void
decode_coding_iso_2022 (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
const unsigned char *src_base;
int *charbuf = coding->charbuf + coding->charbuf_used;
/* We may produce two annotations (charset and composition) in one
loop and one more charset annotation at the end. */
int *charbuf_end
= coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3);
ptrdiff_t consumed_chars = 0, consumed_chars_base;
bool multibytep = coding->src_multibyte;
/* Charsets invoked to graphic plane 0 and 1 respectively. */
int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0);
int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1);
int charset_id_2, charset_id_3;
struct charset *charset;
int c;
struct composition_status *cmp_status = CODING_ISO_CMP_STATUS (coding);
Lisp_Object attrs = CODING_ID_ATTRS (coding->id);
ptrdiff_t char_offset = coding->produced_char;
ptrdiff_t last_offset = char_offset;
int last_id = charset_ascii;
bool eol_dos
= !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
int byte_after_cr = -1;
int i;
setup_iso_safe_charsets (attrs);
coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs));
if (cmp_status->state != COMPOSING_NO)
{
if (charbuf_end - charbuf < cmp_status->length)
emacs_abort ();
for (i = 0; i < cmp_status->length; i++)
*charbuf++ = cmp_status->carryover[i];
coding->annotated = 1;
}
while (1)
{
int c1, c2, c3;
src_base = src;
consumed_chars_base = consumed_chars;
if (charbuf >= charbuf_end)
{
if (byte_after_cr >= 0)
src_base--;
break;
}
if (byte_after_cr >= 0)
c1 = byte_after_cr, byte_after_cr = -1;
else
ONE_MORE_BYTE (c1);
if (c1 < 0)
goto invalid_code;
if (CODING_ISO_EXTSEGMENT_LEN (coding) > 0)
{
*charbuf++ = ASCII_CHAR_P (c1) ? c1 : BYTE8_TO_CHAR (c1);
char_offset++;
CODING_ISO_EXTSEGMENT_LEN (coding)--;
continue;
}
if (CODING_ISO_EMBEDDED_UTF_8 (coding))
{
if (c1 == ISO_CODE_ESC)
{
if (src + 1 >= src_end)
goto no_more_source;
*charbuf++ = ISO_CODE_ESC;
char_offset++;
if (src[0] == '%' && src[1] == '@')
{
src += 2;
consumed_chars += 2;
char_offset += 2;
/* We are sure charbuf can contain two more chars. */
*charbuf++ = '%';
*charbuf++ = '@';
CODING_ISO_EMBEDDED_UTF_8 (coding) = 0;
}
}
else
{
*charbuf++ = ASCII_CHAR_P (c1) ? c1 : BYTE8_TO_CHAR (c1);
char_offset++;
}
continue;
}
if ((cmp_status->state == COMPOSING_RULE
|| cmp_status->state == COMPOSING_COMPONENT_RULE)
&& c1 != ISO_CODE_ESC)
{
int rule;
DECODE_COMPOSITION_RULE (rule);
STORE_COMPOSITION_RULE (rule);
continue;
}
/* We produce at most one character. */
switch (iso_code_class [c1])
{
case ISO_0x20_or_0x7F:
if (charset_id_0 < 0
|| ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0)))
/* This is SPACE or DEL. */
charset = CHARSET_FROM_ID (charset_ascii);
else
charset = CHARSET_FROM_ID (charset_id_0);
break;
case ISO_graphic_plane_0:
if (charset_id_0 < 0)
charset = CHARSET_FROM_ID (charset_ascii);
else
charset = CHARSET_FROM_ID (charset_id_0);
break;
case ISO_0xA0_or_0xFF:
if (charset_id_1 < 0
|| ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1))
|| CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS)
goto invalid_code;
/* This is a graphic character, we fall down ... */
FALLTHROUGH;
case ISO_graphic_plane_1:
if (charset_id_1 < 0)
goto invalid_code;
charset = CHARSET_FROM_ID (charset_id_1);
break;
case ISO_control_0:
if (eol_dos && c1 == '\r')
ONE_MORE_BYTE (byte_after_cr);
MAYBE_FINISH_COMPOSITION ();
charset = CHARSET_FROM_ID (charset_ascii);
break;
case ISO_control_1:
goto invalid_code;
case ISO_shift_out:
if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)
|| CODING_ISO_DESIGNATION (coding, 1) < 0)
goto invalid_code;
CODING_ISO_INVOCATION (coding, 0) = 1;
charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0);
continue;
case ISO_shift_in:
if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT))
goto invalid_code;
CODING_ISO_INVOCATION (coding, 0) = 0;
charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0);
continue;
case ISO_single_shift_2_7:
if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS))
goto invalid_code;
FALLTHROUGH;
case ISO_single_shift_2:
if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT))
goto invalid_code;
/* SS2 is handled as an escape sequence of ESC 'N' */
c1 = 'N';
goto label_escape_sequence;
case ISO_single_shift_3:
if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT))
goto invalid_code;
/* SS2 is handled as an escape sequence of ESC 'O' */
c1 = 'O';
goto label_escape_sequence;
case ISO_control_sequence_introducer:
/* CSI is handled as an escape sequence of ESC '[' ... */
c1 = '[';
goto label_escape_sequence;
case ISO_escape:
ONE_MORE_BYTE (c1);
label_escape_sequence:
/* Escape sequences handled here are invocation,
designation, direction specification, and character
composition specification. */
switch (c1)
{
case '&': /* revision of following character set */
ONE_MORE_BYTE (c1);
if (!(c1 >= '@' && c1 <= '~'))
goto invalid_code;
ONE_MORE_BYTE (c1);
if (c1 != ISO_CODE_ESC)
goto invalid_code;
ONE_MORE_BYTE (c1);
goto label_escape_sequence;
case '$': /* designation of 2-byte character set */
if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION))
goto invalid_code;
{
int reg, chars96;
ONE_MORE_BYTE (c1);
if (c1 >= '@' && c1 <= 'B')
{ /* designation of JISX0208.1978, GB2312.1980,
or JISX0208.1980 */
reg = 0, chars96 = 0;
}
else if (c1 >= 0x28 && c1 <= 0x2B)
{ /* designation of DIMENSION2_CHARS94 character set */
reg = c1 - 0x28, chars96 = 0;
ONE_MORE_BYTE (c1);
}
else if (c1 >= 0x2C && c1 <= 0x2F)
{ /* designation of DIMENSION2_CHARS96 character set */
reg = c1 - 0x2C, chars96 = 1;
ONE_MORE_BYTE (c1);
}
else
goto invalid_code;
DECODE_DESIGNATION (reg, 2, chars96, c1);
/* We must update these variables now. */
if (reg == 0)
charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0);
else if (reg == 1)
charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1);
if (chars96 < 0)
goto invalid_code;
}
continue;
case 'n': /* invocation of locking-shift-2 */
if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)
|| CODING_ISO_DESIGNATION (coding, 2) < 0)
goto invalid_code;
CODING_ISO_INVOCATION (coding, 0) = 2;
charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0);
continue;
case 'o': /* invocation of locking-shift-3 */
if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)
|| CODING_ISO_DESIGNATION (coding, 3) < 0)
goto invalid_code;
CODING_ISO_INVOCATION (coding, 0) = 3;
charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0);
continue;
case 'N': /* invocation of single-shift-2 */
if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)
|| CODING_ISO_DESIGNATION (coding, 2) < 0)
goto invalid_code;
charset_id_2 = CODING_ISO_DESIGNATION (coding, 2);
if (charset_id_2 < 0)
charset = CHARSET_FROM_ID (charset_ascii);
else
charset = CHARSET_FROM_ID (charset_id_2);
ONE_MORE_BYTE (c1);
if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)
|| (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS)
&& ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LEVEL_4)
? c1 >= 0x80 : c1 < 0x80)))
goto invalid_code;
break;
case 'O': /* invocation of single-shift-3 */
if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)
|| CODING_ISO_DESIGNATION (coding, 3) < 0)
goto invalid_code;
charset_id_3 = CODING_ISO_DESIGNATION (coding, 3);
if (charset_id_3 < 0)
charset = CHARSET_FROM_ID (charset_ascii);
else
charset = CHARSET_FROM_ID (charset_id_3);
ONE_MORE_BYTE (c1);
if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)
|| (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS)
&& ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LEVEL_4)
? c1 >= 0x80 : c1 < 0x80)))
goto invalid_code;
break;
case '0': case '2': case '3': case '4': /* start composition */
if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK))
goto invalid_code;
if (last_id != charset_ascii)
{
ADD_CHARSET_DATA (charbuf, char_offset- last_offset, last_id);
last_id = charset_ascii;
last_offset = char_offset;
}
DECODE_COMPOSITION_START (c1);
continue;
case '1': /* end composition */
if (cmp_status->state == COMPOSING_NO)
goto invalid_code;
DECODE_COMPOSITION_END ();
continue;
case '[': /* specification of direction */
if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION))
goto invalid_code;
/* For the moment, nested direction is not supported.
So, `coding->mode & CODING_MODE_DIRECTION' zero means
left-to-right, and nonzero means right-to-left. */
ONE_MORE_BYTE (c1);
switch (c1)
{
case ']': /* end of the current direction */
coding->mode &= ~CODING_MODE_DIRECTION;
break;
case '0': /* end of the current direction */
case '1': /* start of left-to-right direction */
ONE_MORE_BYTE (c1);
if (c1 == ']')
coding->mode &= ~CODING_MODE_DIRECTION;
else
goto invalid_code;
break;
case '2': /* start of right-to-left direction */
ONE_MORE_BYTE (c1);
if (c1 == ']')
coding->mode |= CODING_MODE_DIRECTION;
else
goto invalid_code;
break;
default:
goto invalid_code;
}
continue;
case '%':
ONE_MORE_BYTE (c1);
if (c1 == '/')
{
/* CTEXT extended segment:
ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES--
We keep these bytes as is for the moment.
They may be decoded by post-read-conversion. */
int dim, M, L;
int size;
ONE_MORE_BYTE (dim);
if (dim < '0' || dim > '4')
goto invalid_code;
ONE_MORE_BYTE (M);
if (M < 128)
goto invalid_code;
ONE_MORE_BYTE (L);
if (L < 128)
goto invalid_code;
size = ((M - 128) * 128) + (L - 128);
if (charbuf + 6 > charbuf_end)
goto break_loop;
*charbuf++ = ISO_CODE_ESC;
*charbuf++ = '%';
*charbuf++ = '/';
*charbuf++ = dim;
*charbuf++ = BYTE8_TO_CHAR (M);
*charbuf++ = BYTE8_TO_CHAR (L);
CODING_ISO_EXTSEGMENT_LEN (coding) = size;
}
else if (c1 == 'G')
{
/* XFree86 extension for embedding UTF-8 in CTEXT:
ESC % G --UTF-8-BYTES-- ESC % @
We keep these bytes as is for the moment.
They may be decoded by post-read-conversion. */
if (charbuf + 3 > charbuf_end)
goto break_loop;
*charbuf++ = ISO_CODE_ESC;
*charbuf++ = '%';
*charbuf++ = 'G';
CODING_ISO_EMBEDDED_UTF_8 (coding) = 1;
}
else
goto invalid_code;
continue;
break;
default:
if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION))
goto invalid_code;
{
int reg, chars96;
if (c1 >= 0x28 && c1 <= 0x2B)
{ /* designation of DIMENSION1_CHARS94 character set */
reg = c1 - 0x28, chars96 = 0;
ONE_MORE_BYTE (c1);
}
else if (c1 >= 0x2C && c1 <= 0x2F)
{ /* designation of DIMENSION1_CHARS96 character set */
reg = c1 - 0x2C, chars96 = 1;
ONE_MORE_BYTE (c1);
}
else
goto invalid_code;
DECODE_DESIGNATION (reg, 1, chars96, c1);
/* We must update these variables now. */
if (reg == 0)
charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0);
else if (reg == 1)
charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1);
if (chars96 < 0)
goto invalid_code;
}
continue;
}
break;
default:
emacs_abort ();
}
if (cmp_status->state == COMPOSING_NO
&& charset->id != charset_ascii
&& last_id != charset->id)
{
if (last_id != charset_ascii)
ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id);
last_id = charset->id;
last_offset = char_offset;
}
/* Now we know CHARSET and 1st position code C1 of a character.
Produce a decoded character while getting 2nd and 3rd
position codes C2, C3 if necessary. */
if (CHARSET_DIMENSION (charset) > 1)
{
ONE_MORE_BYTE (c2);
if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)
|| ((c1 & 0x80) != (c2 & 0x80)))
/* C2 is not in a valid range. */
goto invalid_code;
if (CHARSET_DIMENSION (charset) == 2)
c1 = (c1 << 8) | c2;
else
{
ONE_MORE_BYTE (c3);
if (c3 < 0x20 || (c3 >= 0x80 && c3 < 0xA0)
|| ((c1 & 0x80) != (c3 & 0x80)))
/* C3 is not in a valid range. */
goto invalid_code;
c1 = (c1 << 16) | (c2 << 8) | c2;
}
}
c1 &= 0x7F7F7F;
CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c);
if (c < 0)
{
MAYBE_FINISH_COMPOSITION ();
for (; src_base < src; src_base++, char_offset++)
{
if (ASCII_CHAR_P (*src_base))
*charbuf++ = *src_base;
else
*charbuf++ = BYTE8_TO_CHAR (*src_base);
}
}
else if (cmp_status->state == COMPOSING_NO)
{
*charbuf++ = c;
char_offset++;
}
else if ((cmp_status->state == COMPOSING_CHAR
? cmp_status->nchars
: cmp_status->ncomps)
>= MAX_COMPOSITION_COMPONENTS)
{
/* Too long composition. */
MAYBE_FINISH_COMPOSITION ();
*charbuf++ = c;
char_offset++;
}
else
STORE_COMPOSITION_CHAR (c);
continue;
invalid_code:
MAYBE_FINISH_COMPOSITION ();
src = src_base;
consumed_chars = consumed_chars_base;
ONE_MORE_BYTE (c);
*charbuf++ = c < 0 ? -c : ASCII_CHAR_P (c) ? c : BYTE8_TO_CHAR (c);
char_offset++;
/* Reset the invocation and designation status to the safest
one; i.e. designate ASCII to the graphic register 0, and
invoke that register to the graphic plane 0. This typically
helps the case that a designation sequence for ASCII "ESC (
B" is somehow broken (e.g. broken by a newline). */
CODING_ISO_INVOCATION (coding, 0) = 0;
CODING_ISO_DESIGNATION (coding, 0) = charset_ascii;
charset_id_0 = charset_ascii;
continue;
break_loop:
break;
}
no_more_source:
if (cmp_status->state != COMPOSING_NO)
{
if (coding->mode & CODING_MODE_LAST_BLOCK)
MAYBE_FINISH_COMPOSITION ();
else
{
charbuf -= cmp_status->length;
for (i = 0; i < cmp_status->length; i++)
cmp_status->carryover[i] = charbuf[i];
}
}
else if (last_id != charset_ascii)
ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id);
coding->consumed_char += consumed_chars_base;
coding->consumed = src_base - coding->source;
coding->charbuf_used = charbuf - coding->charbuf;
}
/* ISO2022 encoding stuff. */
/*
It is not enough to say just "ISO2022" on encoding, we have to
specify more details. In Emacs, each coding system of ISO2022
variant has the following specifications:
1. Initial designation to G0 thru G3.
2. Allows short-form designation?
3. ASCII should be designated to G0 before control characters?
4. ASCII should be designated to G0 at end of line?
5. 7-bit environment or 8-bit environment?
6. Use locking-shift?
7. Use Single-shift?
And the following two are only for Japanese:
8. Use ASCII in place of JIS0201-1976-Roman?
9. Use JISX0208-1983 in place of JISX0208-1978?
These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits
defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more
details.
*/
/* Produce codes (escape sequence) for designating CHARSET to graphic
register REG at DST, and increment DST. If <final-char> of CHARSET is
'@', 'A', or 'B' and the coding system CODING allows, produce
designation sequence of short-form. */
#define ENCODE_DESIGNATION(charset, reg, coding) \
do { \
unsigned char final_char = CHARSET_ISO_FINAL (charset); \
const char *intermediate_char_94 = "()*+"; \
const char *intermediate_char_96 = ",-./"; \
int revision = -1; \
\
if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \
revision = CHARSET_ISO_REVISION (charset); \
\
if (revision >= 0) \
{ \
EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \
EMIT_ONE_BYTE ('@' + revision); \
} \
EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \
if (CHARSET_DIMENSION (charset) == 1) \
{ \
int b; \
if (! CHARSET_ISO_CHARS_96 (charset)) \
b = intermediate_char_94[reg]; \
else \
b = intermediate_char_96[reg]; \
EMIT_ONE_ASCII_BYTE (b); \
} \
else \
{ \
EMIT_ONE_ASCII_BYTE ('$'); \
if (! CHARSET_ISO_CHARS_96 (charset)) \
{ \
if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \
|| reg != 0 \
|| final_char < '@' || final_char > 'B') \
EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \
} \
else \
EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \
} \
EMIT_ONE_ASCII_BYTE (final_char); \
\
CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \
} while (0)
/* The following two macros produce codes (control character or escape
sequence) for ISO2022 single-shift functions (single-shift-2 and
single-shift-3). */
#define ENCODE_SINGLE_SHIFT_2 \
do { \
if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \
EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \
else \
EMIT_ONE_BYTE (ISO_CODE_SS2); \
CODING_ISO_SINGLE_SHIFTING (coding) = 1; \
} while (0)
#define ENCODE_SINGLE_SHIFT_3 \
do { \
if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \
EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \
else \
EMIT_ONE_BYTE (ISO_CODE_SS3); \
CODING_ISO_SINGLE_SHIFTING (coding) = 1; \
} while (0)
/* The following four macros produce codes (control character or
escape sequence) for ISO2022 locking-shift functions (shift-in,
shift-out, locking-shift-2, and locking-shift-3). */
#define ENCODE_SHIFT_IN \
do { \
EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \
CODING_ISO_INVOCATION (coding, 0) = 0; \
} while (0)
#define ENCODE_SHIFT_OUT \
do { \
EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \
CODING_ISO_INVOCATION (coding, 0) = 1; \
} while (0)
#define ENCODE_LOCKING_SHIFT_2 \
do { \
EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \
CODING_ISO_INVOCATION (coding, 0) = 2; \
} while (0)
#define ENCODE_LOCKING_SHIFT_3 \
do { \
EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \
CODING_ISO_INVOCATION (coding, 0) = 3; \
} while (0)
/* Produce codes for a DIMENSION1 character whose character set is
CHARSET and whose position-code is C1. Designation and invocation
sequences are also produced in advance if necessary. */
#define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \
do { \
int id = CHARSET_ID (charset); \
\
if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \
&& id == charset_ascii) \
{ \
id = charset_jisx0201_roman; \
charset = CHARSET_FROM_ID (id); \
} \
\
if (CODING_ISO_SINGLE_SHIFTING (coding)) \
{ \
if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \
EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \
else \
EMIT_ONE_BYTE (c1 | 0x80); \
CODING_ISO_SINGLE_SHIFTING (coding) = 0; \
break; \
} \
else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \
{ \
EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \
break; \
} \
else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \
{ \
EMIT_ONE_BYTE (c1 | 0x80); \
break; \
} \
else \
/* Since CHARSET is not yet invoked to any graphic planes, we \
must invoke it, or, at first, designate it to some graphic \
register. Then repeat the loop to actually produce the \
character. */ \
dst = encode_invocation_designation (charset, coding, dst, \
&produced_chars); \
} while (1)
/* Produce codes for a DIMENSION2 character whose character set is
CHARSET and whose position-codes are C1 and C2. Designation and
invocation codes are also produced in advance if necessary. */
#define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \
do { \
int id = CHARSET_ID (charset); \
\
if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \
&& id == charset_jisx0208) \
{ \
id = charset_jisx0208_1978; \
charset = CHARSET_FROM_ID (id); \
} \
\
if (CODING_ISO_SINGLE_SHIFTING (coding)) \
{ \
if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \
EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \
else \
EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \
CODING_ISO_SINGLE_SHIFTING (coding) = 0; \
break; \
} \
else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \
{ \
EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \
break; \
} \
else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \
{ \
EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \
break; \
} \
else \
/* Since CHARSET is not yet invoked to any graphic planes, we \
must invoke it, or, at first, designate it to some graphic \
register. Then repeat the loop to actually produce the \
character. */ \
dst = encode_invocation_designation (charset, coding, dst, \
&produced_chars); \
} while (1)
#define ENCODE_ISO_CHARACTER(charset, c) \
do { \
unsigned code; \
CODING_ENCODE_CHAR (coding, dst, dst_end, (charset), (c), code); \
\
if (CHARSET_DIMENSION (charset) == 1) \
ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \
else \
ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \
} while (0)
/* Produce designation and invocation codes at a place pointed by DST
to use CHARSET. The element `spec.iso_2022' of *CODING is updated.
Return new DST. */
static unsigned char *
encode_invocation_designation (struct charset *charset,
struct coding_system *coding,
unsigned char *dst, ptrdiff_t *p_nchars)
{
bool multibytep = coding->dst_multibyte;
ptrdiff_t produced_chars = *p_nchars;
int reg; /* graphic register number */
int id = CHARSET_ID (charset);
/* At first, check designations. */
for (reg = 0; reg < 4; reg++)
if (id == CODING_ISO_DESIGNATION (coding, reg))
break;
if (reg >= 4)
{
/* CHARSET is not yet designated to any graphic registers. */
/* At first check the requested designation. */
reg = CODING_ISO_REQUEST (coding, id);
if (reg < 0)
/* Since CHARSET requests no special designation, designate it
to graphic register 0. */
reg = 0;
ENCODE_DESIGNATION (charset, reg, coding);
}
if (CODING_ISO_INVOCATION (coding, 0) != reg
&& CODING_ISO_INVOCATION (coding, 1) != reg)
{
/* Since the graphic register REG is not invoked to any graphic
planes, invoke it to graphic plane 0. */
switch (reg)
{
case 0: /* graphic register 0 */
ENCODE_SHIFT_IN;
break;
case 1: /* graphic register 1 */
ENCODE_SHIFT_OUT;
break;
case 2: /* graphic register 2 */
if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)
ENCODE_SINGLE_SHIFT_2;
else
ENCODE_LOCKING_SHIFT_2;
break;
case 3: /* graphic register 3 */
if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)
ENCODE_SINGLE_SHIFT_3;
else
ENCODE_LOCKING_SHIFT_3;
break;
default:
break;
}
}
*p_nchars = produced_chars;
return dst;
}
/* Produce codes for designation and invocation to reset the graphic
planes and registers to initial state. */
#define ENCODE_RESET_PLANE_AND_REGISTER() \
do { \
int reg; \
struct charset *charset; \
\
if (CODING_ISO_INVOCATION (coding, 0) != 0) \
ENCODE_SHIFT_IN; \
for (reg = 0; reg < 4; reg++) \
if (CODING_ISO_INITIAL (coding, reg) >= 0 \
&& (CODING_ISO_DESIGNATION (coding, reg) \
!= CODING_ISO_INITIAL (coding, reg))) \
{ \
charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \
ENCODE_DESIGNATION (charset, reg, coding); \
} \
} while (0)
/* Produce designation sequences of charsets in the line started from
CHARBUF to a place pointed by DST, and return the number of
produced bytes. DST should not directly point a buffer text area
which may be relocated by char_charset call.
If the current block ends before any end-of-line, we may fail to
find all the necessary designations. */
static ptrdiff_t
encode_designation_at_bol (struct coding_system *coding,
int *charbuf, int *charbuf_end,
unsigned char *dst)
{
unsigned char *orig = dst;
struct charset *charset;
/* Table of charsets to be designated to each graphic register. */
int r[4];
int c, found = 0, reg;
ptrdiff_t produced_chars = 0;
bool multibytep = coding->dst_multibyte;
Lisp_Object attrs;
Lisp_Object charset_list;
attrs = CODING_ID_ATTRS (coding->id);
charset_list = CODING_ATTR_CHARSET_LIST (attrs);
if (EQ (charset_list, Qiso_2022))
charset_list = Viso_2022_charset_list;
for (reg = 0; reg < 4; reg++)
r[reg] = -1;
while (charbuf < charbuf_end && found < 4)
{
int id;
c = *charbuf++;
if (c == '\n')
break;
charset = char_charset (c, charset_list, NULL);
id = CHARSET_ID (charset);
reg = CODING_ISO_REQUEST (coding, id);
if (reg >= 0 && r[reg] < 0)
{
found++;
r[reg] = id;
}
}
if (found)
{
for (reg = 0; reg < 4; reg++)
if (r[reg] >= 0
&& CODING_ISO_DESIGNATION (coding, reg) != r[reg])
ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding);
}
return dst - orig;
}
/* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */
static bool
encode_coding_iso_2022 (struct coding_system *coding)
{
bool multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
int *charbuf_end = charbuf + coding->charbuf_used;
unsigned char *dst = coding->destination + coding->produced;
unsigned char *dst_end = coding->destination + coding->dst_bytes;
int safe_room = 16;
bool bol_designation
= (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL
&& CODING_ISO_BOL (coding));
ptrdiff_t produced_chars = 0;
Lisp_Object attrs, eol_type, charset_list;
bool ascii_compatible;
int c;
int preferred_charset_id = -1;
CODING_GET_INFO (coding, attrs, charset_list);
eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id);
if (VECTORP (eol_type))
eol_type = Qunix;
setup_iso_safe_charsets (attrs);
/* Charset list may have been changed. */
charset_list = CODING_ATTR_CHARSET_LIST (attrs);
coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs));
ascii_compatible
= (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))
&& ! (CODING_ISO_FLAGS (coding) & (CODING_ISO_FLAG_DESIGNATION
| CODING_ISO_FLAG_LOCKING_SHIFT)));
while (charbuf < charbuf_end)
{
ASSURE_DESTINATION (safe_room);
if (bol_designation)
{
/* We have to produce designation sequences if any now. */
unsigned char desig_buf[16];
ptrdiff_t nbytes;
ptrdiff_t offset;
charset_map_loaded = 0;
nbytes = encode_designation_at_bol (coding, charbuf, charbuf_end,
desig_buf);
if (charset_map_loaded
&& (offset = coding_change_destination (coding)))
{
dst += offset;
dst_end += offset;
}
memcpy (dst, desig_buf, nbytes);
dst += nbytes;
/* We are sure that designation sequences are all ASCII bytes. */
produced_chars += nbytes;
bol_designation = 0;
ASSURE_DESTINATION (safe_room);
}
c = *charbuf++;
if (c < 0)
{
/* Handle an annotation. */
switch (*charbuf)
{
case CODING_ANNOTATE_COMPOSITION_MASK:
/* Not yet implemented. */
break;
case CODING_ANNOTATE_CHARSET_MASK:
preferred_charset_id = charbuf[2];
if (preferred_charset_id >= 0
&& NILP (Fmemq (make_fixnum (preferred_charset_id),
charset_list)))
preferred_charset_id = -1;
break;
default:
emacs_abort ();
}
charbuf += -c - 1;
continue;
}
/* Now encode the character C. */
if (c < 0x20 || c == 0x7F)
{
if (c == '\n'
|| (c == '\r' && EQ (eol_type, Qmac)))
{
if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL)
ENCODE_RESET_PLANE_AND_REGISTER ();
if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL)
{
int i;
for (i = 0; i < 4; i++)
CODING_ISO_DESIGNATION (coding, i)
= CODING_ISO_INITIAL (coding, i);
}
bol_designation = ((CODING_ISO_FLAGS (coding)
& CODING_ISO_FLAG_DESIGNATE_AT_BOL)
!= 0);
}
else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL)
ENCODE_RESET_PLANE_AND_REGISTER ();
EMIT_ONE_ASCII_BYTE (c);
}
else if (ASCII_CHAR_P (c))
{
if (ascii_compatible)
EMIT_ONE_ASCII_BYTE (c);
else
{
struct charset *charset = CHARSET_FROM_ID (charset_ascii);
ENCODE_ISO_CHARACTER (charset, c);
}
}
else if (CHAR_BYTE8_P (c))
{
c = CHAR_TO_BYTE8 (c);
EMIT_ONE_BYTE (c);
}
else
{
struct charset *charset;
if (preferred_charset_id >= 0)
{
bool result;
charset = CHARSET_FROM_ID (preferred_charset_id);
CODING_CHAR_CHARSET_P (coding, dst, dst_end, c, charset, result);
if (! result)
CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list,
NULL, charset);
}
else
CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list,
NULL, charset);
if (!charset)
{
if (coding->mode & CODING_MODE_SAFE_ENCODING)
{
c = CODING_INHIBIT_CHARACTER_SUBSTITUTION;
charset = CHARSET_FROM_ID (charset_ascii);
}
else
{
c = coding->default_char;
CODING_CHAR_CHARSET (coding, dst, dst_end, c,
charset_list, NULL, charset);
}
}
ENCODE_ISO_CHARACTER (charset, c);
}
}
if (coding->mode & CODING_MODE_LAST_BLOCK
&& CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL)
{
ASSURE_DESTINATION (safe_room);
ENCODE_RESET_PLANE_AND_REGISTER ();
}
record_conversion_result (coding, CODING_RESULT_SUCCESS);
CODING_ISO_BOL (coding) = bol_designation;
coding->produced_char += produced_chars;
coding->produced = dst - coding->destination;
return 0;
}
\f
/*** 8,9. SJIS and BIG5 handlers ***/
/* Although SJIS and BIG5 are not ISO's coding system, they are used
quite widely. So, for the moment, Emacs supports them in the bare
C code. But, in the future, they may be supported only by CCL. */
/* SJIS is a coding system encoding three character sets: ASCII, right
half of JISX0201-Kana, and JISX0208. An ASCII character is encoded
as is. A character of charset katakana-jisx0201 is encoded by
"position-code + 0x80". A character of charset japanese-jisx0208
is encoded in 2-byte but two position-codes are divided and shifted
so that it fit in the range below.
--- CODE RANGE of SJIS ---
(character set) (range)
ASCII 0x00 .. 0x7F
KATAKANA-JISX0201 0xA0 .. 0xDF
JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF
(2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC
-------------------------------
*/
/* BIG5 is a coding system encoding two character sets: ASCII and
Big5. An ASCII character is encoded as is. Big5 is a two-byte
character set and is encoded in two-byte.
--- CODE RANGE of BIG5 ---
(character set) (range)
ASCII 0x00 .. 0x7F
Big5 (1st byte) 0xA1 .. 0xFE
(2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE
--------------------------
*/
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
Return true if a text is encoded in SJIS. */
static bool
detect_coding_sjis (struct coding_system *coding,
struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source, *src_base;
const unsigned char *src_end = coding->source + coding->src_bytes;
bool multibytep = coding->src_multibyte;
ptrdiff_t consumed_chars = 0;
int found = 0;
int c;
Lisp_Object attrs, charset_list;
int max_first_byte_of_2_byte_code;
CODING_GET_INFO (coding, attrs, charset_list);
max_first_byte_of_2_byte_code = list_length (charset_list) <= 3 ? 0xEF : 0xFC;
detect_info->checked |= CATEGORY_MASK_SJIS;
/* A coding system of this category is always ASCII compatible. */
src += coding->head_ascii;
while (1)
{
src_base = src;
ONE_MORE_BYTE (c);
if (c < 0x80)
continue;
if ((c >= 0x81 && c <= 0x9F)
|| (c >= 0xE0 && c <= max_first_byte_of_2_byte_code))
{
ONE_MORE_BYTE (c);
if (c < 0x40 || c == 0x7F || c > 0xFC)
break;
found = CATEGORY_MASK_SJIS;
}
else if (c >= 0xA0 && c < 0xE0)
found = CATEGORY_MASK_SJIS;
else
break;
}
detect_info->rejected |= CATEGORY_MASK_SJIS;
return 0;
no_more_source:
if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK)
{
detect_info->rejected |= CATEGORY_MASK_SJIS;
return 0;
}
detect_info->found |= found;
return 1;
}
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
Return true if a text is encoded in BIG5. */
static bool
detect_coding_big5 (struct coding_system *coding,
struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source, *src_base;
const unsigned char *src_end = coding->source + coding->src_bytes;
bool multibytep = coding->src_multibyte;
ptrdiff_t consumed_chars = 0;
int found = 0;
int c;
detect_info->checked |= CATEGORY_MASK_BIG5;
/* A coding system of this category is always ASCII compatible. */
src += coding->head_ascii;
while (1)
{
src_base = src;
ONE_MORE_BYTE (c);
if (c < 0x80)
continue;
if (c >= 0xA1)
{
ONE_MORE_BYTE (c);
if (c < 0x40 || (c >= 0x7F && c <= 0xA0))
return 0;
found = CATEGORY_MASK_BIG5;
}
else
break;
}
detect_info->rejected |= CATEGORY_MASK_BIG5;
return 0;
no_more_source:
if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK)
{
detect_info->rejected |= CATEGORY_MASK_BIG5;
return 0;
}
detect_info->found |= found;
return 1;
}
/* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */
static void
decode_coding_sjis (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
const unsigned char *src_base;
int *charbuf = coding->charbuf + coding->charbuf_used;
/* We may produce one charset annotation in one loop and one more at
the end. */
int *charbuf_end
= coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2);
ptrdiff_t consumed_chars = 0, consumed_chars_base;
bool multibytep = coding->src_multibyte;
struct charset *charset_roman, *charset_kanji, *charset_kana;
struct charset *charset_kanji2;
Lisp_Object attrs, charset_list, val;
ptrdiff_t char_offset = coding->produced_char;
ptrdiff_t last_offset = char_offset;
int last_id = charset_ascii;
bool eol_dos
= !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
int byte_after_cr = -1;
CODING_GET_INFO (coding, attrs, charset_list);
val = charset_list;
charset_roman = CHARSET_FROM_ID (XFIXNUM (XCAR (val))), val = XCDR (val);
charset_kana = CHARSET_FROM_ID (XFIXNUM (XCAR (val))), val = XCDR (val);
charset_kanji = CHARSET_FROM_ID (XFIXNUM (XCAR (val))), val = XCDR (val);
charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XFIXNUM (XCAR (val)));
while (1)
{
int c, c1;
struct charset *charset;
src_base = src;
consumed_chars_base = consumed_chars;
if (charbuf >= charbuf_end)
{
if (byte_after_cr >= 0)
src_base--;
break;
}
if (byte_after_cr >= 0)
c = byte_after_cr, byte_after_cr = -1;
else
ONE_MORE_BYTE (c);
if (c < 0)
goto invalid_code;
if (c < 0x80)
{
if (eol_dos && c == '\r')
ONE_MORE_BYTE (byte_after_cr);
charset = charset_roman;
}
else if (c == 0x80 || c == 0xA0)
goto invalid_code;
else if (c >= 0xA1 && c <= 0xDF)
{
/* SJIS -> JISX0201-Kana */
c &= 0x7F;
charset = charset_kana;
}
else if (c <= 0xEF)
{
/* SJIS -> JISX0208 */
ONE_MORE_BYTE (c1);
if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC)
goto invalid_code;
c = (c << 8) | c1;
SJIS_TO_JIS (c);
charset = charset_kanji;
}
else if (c <= 0xFC && charset_kanji2)
{
/* SJIS -> JISX0213-2 */
ONE_MORE_BYTE (c1);
if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC)
goto invalid_code;
c = (c << 8) | c1;
SJIS_TO_JIS2 (c);
charset = charset_kanji2;
}
else
goto invalid_code;
if (charset->id != charset_ascii
&& last_id != charset->id)
{
if (last_id != charset_ascii)
ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id);
last_id = charset->id;
last_offset = char_offset;
}
CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c);
*charbuf++ = c;
char_offset++;
continue;
invalid_code:
src = src_base;
consumed_chars = consumed_chars_base;
ONE_MORE_BYTE (c);
*charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c);
char_offset++;
}
no_more_source:
if (last_id != charset_ascii)
ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id);
coding->consumed_char += consumed_chars_base;
coding->consumed = src_base - coding->source;
coding->charbuf_used = charbuf - coding->charbuf;
}
static void
decode_coding_big5 (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
const unsigned char *src_base;
int *charbuf = coding->charbuf + coding->charbuf_used;
/* We may produce one charset annotation in one loop and one more at
the end. */
int *charbuf_end
= coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2);
ptrdiff_t consumed_chars = 0, consumed_chars_base;
bool multibytep = coding->src_multibyte;
struct charset *charset_roman, *charset_big5;
Lisp_Object attrs, charset_list, val;
ptrdiff_t char_offset = coding->produced_char;
ptrdiff_t last_offset = char_offset;
int last_id = charset_ascii;
bool eol_dos
= !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
int byte_after_cr = -1;
CODING_GET_INFO (coding, attrs, charset_list);
val = charset_list;
charset_roman = CHARSET_FROM_ID (XFIXNUM (XCAR (val))), val = XCDR (val);
charset_big5 = CHARSET_FROM_ID (XFIXNUM (XCAR (val)));
while (1)
{
int c, c1;
struct charset *charset;
src_base = src;
consumed_chars_base = consumed_chars;
if (charbuf >= charbuf_end)
{
if (byte_after_cr >= 0)
src_base--;
break;
}
if (byte_after_cr >= 0)
c = byte_after_cr, byte_after_cr = -1;
else
ONE_MORE_BYTE (c);
if (c < 0)
goto invalid_code;
if (c < 0x80)
{
if (eol_dos && c == '\r')
ONE_MORE_BYTE (byte_after_cr);
charset = charset_roman;
}
else
{
/* BIG5 -> Big5 */
if (c < 0xA1 || c > 0xFE)
goto invalid_code;
ONE_MORE_BYTE (c1);
if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE)
goto invalid_code;
c = c << 8 | c1;
charset = charset_big5;
}
if (charset->id != charset_ascii
&& last_id != charset->id)
{
if (last_id != charset_ascii)
ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id);
last_id = charset->id;
last_offset = char_offset;
}
CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c);
*charbuf++ = c;
char_offset++;
continue;
invalid_code:
src = src_base;
consumed_chars = consumed_chars_base;
ONE_MORE_BYTE (c);
*charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c);
char_offset++;
}
no_more_source:
if (last_id != charset_ascii)
ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id);
coding->consumed_char += consumed_chars_base;
coding->consumed = src_base - coding->source;
coding->charbuf_used = charbuf - coding->charbuf;
}
/* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions".
This function can encode charsets `ascii', `katakana-jisx0201',
`japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We
are sure that all these charsets are registered as official charset
(i.e. do not have extended leading-codes). Characters of other
charsets are produced without any encoding. */
static bool
encode_coding_sjis (struct coding_system *coding)
{
bool multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
int *charbuf_end = charbuf + coding->charbuf_used;
unsigned char *dst = coding->destination + coding->produced;
unsigned char *dst_end = coding->destination + coding->dst_bytes;
int safe_room = 4;
ptrdiff_t produced_chars = 0;
Lisp_Object attrs, charset_list, val;
bool ascii_compatible;
struct charset *charset_kanji, *charset_kana;
struct charset *charset_kanji2;
int c;
CODING_GET_INFO (coding, attrs, charset_list);
val = XCDR (charset_list);
charset_kana = CHARSET_FROM_ID (XFIXNUM (XCAR (val))), val = XCDR (val);
charset_kanji = CHARSET_FROM_ID (XFIXNUM (XCAR (val))), val = XCDR (val);
charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XFIXNUM (XCAR (val)));
ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs));
while (charbuf < charbuf_end)
{
ASSURE_DESTINATION (safe_room);
c = *charbuf++;
/* Now encode the character C. */
if (ASCII_CHAR_P (c) && ascii_compatible)
EMIT_ONE_ASCII_BYTE (c);
else if (CHAR_BYTE8_P (c))
{
c = CHAR_TO_BYTE8 (c);
EMIT_ONE_BYTE (c);
}
else
{
unsigned code;
struct charset *charset;
CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list,
&code, charset);
if (!charset)
{
if (coding->mode & CODING_MODE_SAFE_ENCODING)
{
code = CODING_INHIBIT_CHARACTER_SUBSTITUTION;
charset = CHARSET_FROM_ID (charset_ascii);
}
else
{
c = coding->default_char;
CODING_CHAR_CHARSET (coding, dst, dst_end, c,
charset_list, &code, charset);
}
}
if (code == CHARSET_INVALID_CODE (charset))
emacs_abort ();
if (charset == charset_kanji)
{
int c1, c2;
JIS_TO_SJIS (code);
c1 = code >> 8, c2 = code & 0xFF;
EMIT_TWO_BYTES (c1, c2);
}
else if (charset == charset_kana)
EMIT_ONE_BYTE (code | 0x80);
else if (charset_kanji2 && charset == charset_kanji2)
{
int c1, c2;
c1 = code >> 8;
if (c1 == 0x21 || (c1 >= 0x23 && c1 <= 0x25)
|| c1 == 0x28
|| (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E)
{
JIS_TO_SJIS2 (code);
c1 = code >> 8, c2 = code & 0xFF;
EMIT_TWO_BYTES (c1, c2);
}
else
EMIT_ONE_ASCII_BYTE (code & 0x7F);
}
else
EMIT_ONE_ASCII_BYTE (code & 0x7F);
}
}
record_conversion_result (coding, CODING_RESULT_SUCCESS);
coding->produced_char += produced_chars;
coding->produced = dst - coding->destination;
return 0;
}
static bool
encode_coding_big5 (struct coding_system *coding)
{
bool multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
int *charbuf_end = charbuf + coding->charbuf_used;
unsigned char *dst = coding->destination + coding->produced;
unsigned char *dst_end = coding->destination + coding->dst_bytes;
int safe_room = 4;
ptrdiff_t produced_chars = 0;
Lisp_Object attrs, charset_list, val;
bool ascii_compatible;
struct charset *charset_big5;
int c;
CODING_GET_INFO (coding, attrs, charset_list);
val = XCDR (charset_list);
charset_big5 = CHARSET_FROM_ID (XFIXNUM (XCAR (val)));
ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs));
while (charbuf < charbuf_end)
{
ASSURE_DESTINATION (safe_room);
c = *charbuf++;
/* Now encode the character C. */
if (ASCII_CHAR_P (c) && ascii_compatible)
EMIT_ONE_ASCII_BYTE (c);
else if (CHAR_BYTE8_P (c))
{
c = CHAR_TO_BYTE8 (c);
EMIT_ONE_BYTE (c);
}
else
{
unsigned code;
struct charset *charset;
CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list,
&code, charset);
if (! charset)
{
if (coding->mode & CODING_MODE_SAFE_ENCODING)
{
code = CODING_INHIBIT_CHARACTER_SUBSTITUTION;
charset = CHARSET_FROM_ID (charset_ascii);
}
else
{
c = coding->default_char;
CODING_CHAR_CHARSET (coding, dst, dst_end, c,
charset_list, &code, charset);
}
}
if (code == CHARSET_INVALID_CODE (charset))
emacs_abort ();
if (charset == charset_big5)
{
int c1, c2;
c1 = code >> 8, c2 = code & 0xFF;
EMIT_TWO_BYTES (c1, c2);
}
else
EMIT_ONE_ASCII_BYTE (code & 0x7F);
}
}
record_conversion_result (coding, CODING_RESULT_SUCCESS);
coding->produced_char += produced_chars;
coding->produced = dst - coding->destination;
return 0;
}
\f
/*** 10. CCL handlers ***/
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
Return true if a text is encoded in a coding system of which
encoder/decoder are written in CCL program. */
static bool
detect_coding_ccl (struct coding_system *coding,
struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source, *src_base;
const unsigned char *src_end = coding->source + coding->src_bytes;
bool multibytep = coding->src_multibyte;
ptrdiff_t consumed_chars = 0;
int found = 0;
unsigned char *valids;
ptrdiff_t head_ascii = coding->head_ascii;
Lisp_Object attrs;
detect_info->checked |= CATEGORY_MASK_CCL;
coding = &coding_categories[coding_category_ccl];
valids = CODING_CCL_VALIDS (coding);
attrs = CODING_ID_ATTRS (coding->id);
if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs)))
src += head_ascii;
while (1)
{
int c;
src_base = src;
ONE_MORE_BYTE (c);
if (c < 0 || ! valids[c])
break;
if ((valids[c] > 1))
found = CATEGORY_MASK_CCL;
}
detect_info->rejected |= CATEGORY_MASK_CCL;
return 0;
no_more_source:
detect_info->found |= found;
return 1;
}
static void
decode_coding_ccl (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
int *charbuf = coding->charbuf + coding->charbuf_used;
int *charbuf_end = coding->charbuf + coding->charbuf_size;
ptrdiff_t consumed_chars = 0;
bool multibytep = coding->src_multibyte;
struct ccl_program *ccl = &coding->spec.ccl->ccl;
int source_charbuf[1024];
int source_byteidx[1025];
Lisp_Object attrs, charset_list;
CODING_GET_INFO (coding, attrs, charset_list);
while (1)
{
const unsigned char *p = src;
ptrdiff_t offset;
int i = 0;
if (multibytep)
{
while (i < 1024 && p < src_end)
{
source_byteidx[i] = p - src;
source_charbuf[i++] = string_char_advance (&p);
}
source_byteidx[i] = p - src;
}
else
while (i < 1024 && p < src_end)
source_charbuf[i++] = *p++;
if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK)
ccl->last_block = true;
/* As ccl_driver calls DECODE_CHAR, buffer may be relocated. */
charset_map_loaded = 0;
ccl_driver (ccl, source_charbuf, charbuf, i, charbuf_end - charbuf,
charset_list);
if (charset_map_loaded
&& (offset = coding_change_source (coding)))
{
p += offset;
src += offset;
src_end += offset;
}
charbuf += ccl->produced;
if (multibytep)
src += source_byteidx[ccl->consumed];
else
src += ccl->consumed;
consumed_chars += ccl->consumed;
if (p == src_end || ccl->status != CCL_STAT_SUSPEND_BY_SRC)
break;
}
switch (ccl->status)
{
case CCL_STAT_SUSPEND_BY_SRC:
record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC);
break;
case CCL_STAT_SUSPEND_BY_DST:
record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST);
break;
case CCL_STAT_QUIT:
case CCL_STAT_INVALID_CMD:
record_conversion_result (coding, CODING_RESULT_INTERRUPT);
break;
default:
record_conversion_result (coding, CODING_RESULT_SUCCESS);
break;
}
coding->consumed_char += consumed_chars;
coding->consumed = src - coding->source;
coding->charbuf_used = charbuf - coding->charbuf;
}
static bool
encode_coding_ccl (struct coding_system *coding)
{
struct ccl_program *ccl = &coding->spec.ccl->ccl;
bool multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
int *charbuf_end = charbuf + coding->charbuf_used;
unsigned char *dst = coding->destination + coding->produced;
unsigned char *dst_end = coding->destination + coding->dst_bytes;
int destination_charbuf[1024];
ptrdiff_t produced_chars = 0;
int i;
Lisp_Object attrs, charset_list;
CODING_GET_INFO (coding, attrs, charset_list);
if (coding->consumed_char == coding->src_chars
&& coding->mode & CODING_MODE_LAST_BLOCK)
ccl->last_block = true;
do
{
ptrdiff_t offset;
/* As ccl_driver calls DECODE_CHAR, buffer may be relocated. */
charset_map_loaded = 0;
ccl_driver (ccl, charbuf, destination_charbuf,
charbuf_end - charbuf, 1024, charset_list);
if (charset_map_loaded
&& (offset = coding_change_destination (coding)))
dst += offset;
if (multibytep)
{
ASSURE_DESTINATION (ccl->produced * 2);
for (i = 0; i < ccl->produced; i++)
EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF);
}
else
{
ASSURE_DESTINATION (ccl->produced);
for (i = 0; i < ccl->produced; i++)
*dst++ = destination_charbuf[i] & 0xFF;
produced_chars += ccl->produced;
}
charbuf += ccl->consumed;
if (ccl->status == CCL_STAT_QUIT
|| ccl->status == CCL_STAT_INVALID_CMD)
break;
}
while (charbuf < charbuf_end);
switch (ccl->status)
{
case CCL_STAT_SUSPEND_BY_SRC:
record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC);
break;
case CCL_STAT_SUSPEND_BY_DST:
record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST);
break;
case CCL_STAT_QUIT:
case CCL_STAT_INVALID_CMD:
record_conversion_result (coding, CODING_RESULT_INTERRUPT);
break;
default:
record_conversion_result (coding, CODING_RESULT_SUCCESS);
break;
}
coding->produced_char += produced_chars;
coding->produced = dst - coding->destination;
return 0;
}
\f
/*** 10, 11. no-conversion handlers ***/
/* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */
static void
decode_coding_raw_text (struct coding_system *coding)
{
bool eol_dos
= !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
coding->chars_at_source = 1;
coding->consumed_char = coding->src_chars;
coding->consumed = coding->src_bytes;
if (eol_dos && coding->source[coding->src_bytes - 1] == '\r')
{
coding->consumed_char--;
coding->consumed--;
record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC);
}
else
record_conversion_result (coding, CODING_RESULT_SUCCESS);
}
static bool
encode_coding_raw_text (struct coding_system *coding)
{
bool multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
int *charbuf_end = coding->charbuf + coding->charbuf_used;
unsigned char *dst = coding->destination + coding->produced;
unsigned char *dst_end = coding->destination + coding->dst_bytes;
ptrdiff_t produced_chars = 0;
int c;
if (multibytep)
{
int safe_room = MAX_MULTIBYTE_LENGTH * 2;
if (coding->src_multibyte)
while (charbuf < charbuf_end)
{
ASSURE_DESTINATION (safe_room);
c = *charbuf++;
if (ASCII_CHAR_P (c))
EMIT_ONE_ASCII_BYTE (c);
else if (CHAR_BYTE8_P (c))
{
c = CHAR_TO_BYTE8 (c);
EMIT_ONE_BYTE (c);
}
else
{
unsigned char str[MAX_MULTIBYTE_LENGTH];
int len = CHAR_STRING (c, str);
for (int i = 0; i < len; i++)
EMIT_ONE_BYTE (str[i]);
}
}
else
while (charbuf < charbuf_end)
{
ASSURE_DESTINATION (safe_room);
c = *charbuf++;
EMIT_ONE_BYTE (c);
}
}
else
{
if (coding->src_multibyte)
{
int safe_room = MAX_MULTIBYTE_LENGTH;
while (charbuf < charbuf_end)
{
ASSURE_DESTINATION (safe_room);
c = *charbuf++;
if (ASCII_CHAR_P (c))
*dst++ = c;
else if (CHAR_BYTE8_P (c))
*dst++ = CHAR_TO_BYTE8 (c);
else
dst += CHAR_STRING (c, dst);
}
}
else
{
ASSURE_DESTINATION (charbuf_end - charbuf);
while (charbuf < charbuf_end && dst < dst_end)
*dst++ = *charbuf++;
}
produced_chars = dst - (coding->destination + coding->produced);
}
record_conversion_result (coding, CODING_RESULT_SUCCESS);
coding->produced_char += produced_chars;
coding->produced = dst - coding->destination;
return 0;
}
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
Return true if a text is encoded in a charset-based coding system. */
static bool
detect_coding_charset (struct coding_system *coding,
struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source, *src_base;
const unsigned char *src_end = coding->source + coding->src_bytes;
bool multibytep = coding->src_multibyte;
ptrdiff_t consumed_chars = 0;
Lisp_Object attrs, valids, name;
int found = 0;
ptrdiff_t head_ascii = coding->head_ascii;
bool check_latin_extra = 0;
detect_info->checked |= CATEGORY_MASK_CHARSET;
coding = &coding_categories[coding_category_charset];
attrs = CODING_ID_ATTRS (coding->id);
valids = AREF (attrs, coding_attr_charset_valids);
name = CODING_ID_NAME (coding->id);
if (strncmp (SSDATA (SYMBOL_NAME (name)),
"iso-8859-", sizeof ("iso-8859-") - 1) == 0
|| strncmp (SSDATA (SYMBOL_NAME (name)),
"iso-latin-", sizeof ("iso-latin-") - 1) == 0)
check_latin_extra = 1;
if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs)))
src += head_ascii;
while (1)
{
int c;
Lisp_Object val;
struct charset *charset;
int dim, idx;
src_base = src;
ONE_MORE_BYTE (c);
if (c < 0)
continue;
val = AREF (valids, c);
if (NILP (val))
break;
if (c >= 0x80)
{
if (c < 0xA0
&& check_latin_extra
&& (!VECTORP (Vlatin_extra_code_table)
|| NILP (AREF (Vlatin_extra_code_table, c))))
break;
found = CATEGORY_MASK_CHARSET;
}
if (FIXNUMP (val))
{
charset = CHARSET_FROM_ID (XFIXNAT (val));
dim = CHARSET_DIMENSION (charset);
for (idx = 1; idx < dim; idx++)
{
if (src == src_end)
goto too_short;
ONE_MORE_BYTE (c);
if (c < charset->code_space[(dim - 1 - idx) * 4]
|| c > charset->code_space[(dim - 1 - idx) * 4 + 1])
break;
}
if (idx < dim)
break;
}
else
{
idx = 1;
for (; CONSP (val); val = XCDR (val))
{
charset = CHARSET_FROM_ID (XFIXNAT (XCAR (val)));
dim = CHARSET_DIMENSION (charset);
while (idx < dim)
{
if (src == src_end)
goto too_short;
ONE_MORE_BYTE (c);
if (c < charset->code_space[(dim - 1 - idx) * 4]
|| c > charset->code_space[(dim - 1 - idx) * 4 + 1])
break;
idx++;
}
if (idx == dim)
{
val = Qnil;
break;
}
}
if (CONSP (val))
break;
}
}
too_short:
detect_info->rejected |= CATEGORY_MASK_CHARSET;
return 0;
no_more_source:
detect_info->found |= found;
return 1;
}
static void
decode_coding_charset (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
const unsigned char *src_base;
int *charbuf = coding->charbuf + coding->charbuf_used;
/* We may produce one charset annotation in one loop and one more at
the end. */
int *charbuf_end
= coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2);
ptrdiff_t consumed_chars = 0, consumed_chars_base;
bool multibytep = coding->src_multibyte;
Lisp_Object attrs = CODING_ID_ATTRS (coding->id);
Lisp_Object valids;
ptrdiff_t char_offset = coding->produced_char;
ptrdiff_t last_offset = char_offset;
int last_id = charset_ascii;
bool eol_dos
= !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
int byte_after_cr = -1;
valids = AREF (attrs, coding_attr_charset_valids);
while (1)
{
int c;
Lisp_Object val;
struct charset *charset;
int dim;
int len = 1;
unsigned code;
src_base = src;
consumed_chars_base = consumed_chars;
if (charbuf >= charbuf_end)
{
if (byte_after_cr >= 0)
src_base--;
break;
}
if (byte_after_cr >= 0)
{
c = byte_after_cr;
byte_after_cr = -1;
}
else
{
ONE_MORE_BYTE (c);
if (eol_dos && c == '\r')
ONE_MORE_BYTE (byte_after_cr);
}
if (c < 0)
goto invalid_code;
code = c;
val = AREF (valids, c);
if (! FIXNUMP (val) && ! CONSP (val))
goto invalid_code;
if (FIXNUMP (val))
{
charset = CHARSET_FROM_ID (XFIXNAT (val));
dim = CHARSET_DIMENSION (charset);
while (len < dim)
{
ONE_MORE_BYTE (c);
code = (code << 8) | c;
len++;
}
CODING_DECODE_CHAR (coding, src, src_base, src_end,
charset, code, c);
}
else
{
/* VAL is a list of charset IDs. It is assured that the
list is sorted by charset dimensions (smaller one
comes first). */
while (CONSP (val))
{
charset = CHARSET_FROM_ID (XFIXNAT (XCAR (val)));
dim = CHARSET_DIMENSION (charset);
while (len < dim)
{
ONE_MORE_BYTE (c);
code = (code << 8) | c;
len++;
}
CODING_DECODE_CHAR (coding, src, src_base,
src_end, charset, code, c);
if (c >= 0)
break;
val = XCDR (val);
}
}
if (c < 0)
goto invalid_code;
if (charset->id != charset_ascii
&& last_id != charset->id)
{
if (last_id != charset_ascii)
ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id);
last_id = charset->id;
last_offset = char_offset;
}
*charbuf++ = c;
char_offset++;
continue;
invalid_code:
src = src_base;
consumed_chars = consumed_chars_base;
ONE_MORE_BYTE (c);
*charbuf++ = c < 0 ? -c : ASCII_CHAR_P (c) ? c : BYTE8_TO_CHAR (c);
char_offset++;
}
no_more_source:
if (last_id != charset_ascii)
ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id);
coding->consumed_char += consumed_chars_base;
coding->consumed = src_base - coding->source;
coding->charbuf_used = charbuf - coding->charbuf;
}
static bool
encode_coding_charset (struct coding_system *coding)
{
bool multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
int *charbuf_end = charbuf + coding->charbuf_used;
unsigned char *dst = coding->destination + coding->produced;
unsigned char *dst_end = coding->destination + coding->dst_bytes;
int safe_room = MAX_MULTIBYTE_LENGTH;
ptrdiff_t produced_chars = 0;
Lisp_Object attrs, charset_list;
bool ascii_compatible;
int c;
CODING_GET_INFO (coding, attrs, charset_list);
ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs));
while (charbuf < charbuf_end)
{
struct charset *charset;
unsigned code;
ASSURE_DESTINATION (safe_room);
c = *charbuf++;
if (ascii_compatible && ASCII_CHAR_P (c))
EMIT_ONE_ASCII_BYTE (c);
else if (CHAR_BYTE8_P (c))
{
c = CHAR_TO_BYTE8 (c);
EMIT_ONE_BYTE (c);
}
else
{
CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list,
&code, charset);
if (charset)
{
if (CHARSET_DIMENSION (charset) == 1)
EMIT_ONE_BYTE (code);
else if (CHARSET_DIMENSION (charset) == 2)
EMIT_TWO_BYTES (code >> 8, code & 0xFF);
else if (CHARSET_DIMENSION (charset) == 3)
EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF);
else
EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF,
(code >> 8) & 0xFF, code & 0xFF);
}
else
{
if (coding->mode & CODING_MODE_SAFE_ENCODING)
c = CODING_INHIBIT_CHARACTER_SUBSTITUTION;
else
c = coding->default_char;
EMIT_ONE_BYTE (c);
}
}
}
record_conversion_result (coding, CODING_RESULT_SUCCESS);
coding->produced_char += produced_chars;
coding->produced = dst - coding->destination;
return 0;
}
\f
/*** 7. C library functions ***/
/* Setup coding context CODING from information about CODING_SYSTEM.
If CODING_SYSTEM is nil, `no-conversion' is assumed. If
CODING_SYSTEM is invalid, signal an error. */
void
setup_coding_system (Lisp_Object coding_system, struct coding_system *coding)
{
Lisp_Object attrs;
Lisp_Object eol_type;
Lisp_Object coding_type;
Lisp_Object val;
if (NILP (coding_system))
coding_system = Qundecided;
CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id);
attrs = CODING_ID_ATTRS (coding->id);
eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id);
coding->mode = 0;
if (VECTORP (eol_type))
coding->common_flags = (CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_DETECTION_MASK);
else if (! EQ (eol_type, Qunix))
coding->common_flags = (CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK);
else
coding->common_flags = 0;
if (! NILP (CODING_ATTR_POST_READ (attrs)))
coding->common_flags |= CODING_REQUIRE_DECODING_MASK;
if (! NILP (CODING_ATTR_PRE_WRITE (attrs)))
coding->common_flags |= CODING_REQUIRE_ENCODING_MASK;
if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs)))
coding->common_flags |= CODING_FOR_UNIBYTE_MASK;
val = CODING_ATTR_SAFE_CHARSETS (attrs);
coding->max_charset_id = SCHARS (val) - 1;
coding->safe_charsets = SDATA (val);
coding->default_char = XFIXNUM (CODING_ATTR_DEFAULT_CHAR (attrs));
coding->carryover_bytes = 0;
coding->raw_destination = 0;
coding_type = CODING_ATTR_TYPE (attrs);
if (EQ (coding_type, Qundecided))
{
coding->detector = NULL;
coding->decoder = decode_coding_raw_text;
coding->encoder = encode_coding_raw_text;
coding->common_flags |= CODING_REQUIRE_DETECTION_MASK;
coding->spec.undecided.inhibit_nbd
= (encode_inhibit_flag
(AREF (attrs, coding_attr_undecided_inhibit_nul_byte_detection)));
coding->spec.undecided.inhibit_ied
= (encode_inhibit_flag
(AREF (attrs, coding_attr_undecided_inhibit_iso_escape_detection)));
coding->spec.undecided.prefer_utf_8
= ! NILP (AREF (attrs, coding_attr_undecided_prefer_utf_8));
}
else if (EQ (coding_type, Qiso_2022))
{
int i;
int flags = XFIXNUM (AREF (attrs, coding_attr_iso_flags));
/* Invoke graphic register 0 to plane 0. */
CODING_ISO_INVOCATION (coding, 0) = 0;
/* Invoke graphic register 1 to plane 1 if we can use 8-bit. */
CODING_ISO_INVOCATION (coding, 1)
= (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1);
/* Setup the initial status of designation. */
for (i = 0; i < 4; i++)
CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i);
/* Not single shifting initially. */
CODING_ISO_SINGLE_SHIFTING (coding) = 0;
/* Beginning of buffer should also be regarded as bol. */
CODING_ISO_BOL (coding) = 1;
coding->detector = detect_coding_iso_2022;
coding->decoder = decode_coding_iso_2022;
coding->encoder = encode_coding_iso_2022;
if (flags & CODING_ISO_FLAG_SAFE)
coding->mode |= CODING_MODE_SAFE_ENCODING;
coding->common_flags
|= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK
| CODING_REQUIRE_FLUSHING_MASK);
if (flags & CODING_ISO_FLAG_COMPOSITION)
coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK;
if (flags & CODING_ISO_FLAG_DESIGNATION)
coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK;
if (flags & CODING_ISO_FLAG_FULL_SUPPORT)
{
setup_iso_safe_charsets (attrs);
val = CODING_ATTR_SAFE_CHARSETS (attrs);
coding->max_charset_id = SCHARS (val) - 1;
coding->safe_charsets = SDATA (val);
}
CODING_ISO_FLAGS (coding) = flags;
CODING_ISO_CMP_STATUS (coding)->state = COMPOSING_NO;
CODING_ISO_CMP_STATUS (coding)->method = COMPOSITION_NO;
CODING_ISO_EXTSEGMENT_LEN (coding) = 0;
CODING_ISO_EMBEDDED_UTF_8 (coding) = 0;
}
else if (EQ (coding_type, Qcharset))
{
coding->detector = detect_coding_charset;
coding->decoder = decode_coding_charset;
coding->encoder = encode_coding_charset;
coding->common_flags
|= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK);
}
else if (EQ (coding_type, Qutf_8))
{
val = AREF (attrs, coding_attr_utf_bom);
CODING_UTF_8_BOM (coding) = (CONSP (val) ? utf_detect_bom
: EQ (val, Qt) ? utf_with_bom
: utf_without_bom);
coding->detector = detect_coding_utf_8;
coding->decoder = decode_coding_utf_8;
coding->encoder = encode_coding_utf_8;
coding->common_flags
|= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK);
if (CODING_UTF_8_BOM (coding) == utf_detect_bom)
coding->common_flags |= CODING_REQUIRE_DETECTION_MASK;
}
else if (EQ (coding_type, Qutf_16))
{
val = AREF (attrs, coding_attr_utf_bom);
CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_detect_bom
: EQ (val, Qt) ? utf_with_bom
: utf_without_bom);
val = AREF (attrs, coding_attr_utf_16_endian);
CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian
: utf_16_little_endian);
CODING_UTF_16_SURROGATE (coding) = 0;
coding->detector = detect_coding_utf_16;
coding->decoder = decode_coding_utf_16;
coding->encoder = encode_coding_utf_16;
coding->common_flags
|= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK);
if (CODING_UTF_16_BOM (coding) == utf_detect_bom)
coding->common_flags |= CODING_REQUIRE_DETECTION_MASK;
}
else if (EQ (coding_type, Qccl))
{
coding->detector = detect_coding_ccl;
coding->decoder = decode_coding_ccl;
coding->encoder = encode_coding_ccl;
coding->common_flags
|= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK
| CODING_REQUIRE_FLUSHING_MASK);
}
else if (EQ (coding_type, Qemacs_mule))
{
coding->detector = detect_coding_emacs_mule;
coding->decoder = decode_coding_emacs_mule;
coding->encoder = encode_coding_emacs_mule;
coding->common_flags
|= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK);
if (! NILP (AREF (attrs, coding_attr_emacs_mule_full))
&& ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list))
{
Lisp_Object tail, safe_charsets;
int max_charset_id = 0;
for (tail = Vemacs_mule_charset_list; CONSP (tail);
tail = XCDR (tail))
if (max_charset_id < XFIXNAT (XCAR (tail)))
max_charset_id = XFIXNAT (XCAR (tail));
safe_charsets = make_uninit_string (max_charset_id + 1);
memset (SDATA (safe_charsets), 255, max_charset_id + 1);
for (tail = Vemacs_mule_charset_list; CONSP (tail);
tail = XCDR (tail))
SSET (safe_charsets, XFIXNAT (XCAR (tail)), 0);
coding->max_charset_id = max_charset_id;
coding->safe_charsets = SDATA (safe_charsets);
}
coding->spec.emacs_mule.cmp_status.state = COMPOSING_NO;
coding->spec.emacs_mule.cmp_status.method = COMPOSITION_NO;
}
else if (EQ (coding_type, Qshift_jis))
{
coding->detector = detect_coding_sjis;
coding->decoder = decode_coding_sjis;
coding->encoder = encode_coding_sjis;
coding->common_flags
|= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK);
}
else if (EQ (coding_type, Qbig5))
{
coding->detector = detect_coding_big5;
coding->decoder = decode_coding_big5;
coding->encoder = encode_coding_big5;
coding->common_flags
|= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK);
}
else /* EQ (coding_type, Qraw_text) */
{
coding->detector = NULL;
coding->decoder = decode_coding_raw_text;
coding->encoder = encode_coding_raw_text;
if (! EQ (eol_type, Qunix))
{
coding->common_flags |= CODING_REQUIRE_DECODING_MASK;
if (! VECTORP (eol_type))
coding->common_flags |= CODING_REQUIRE_ENCODING_MASK;
}
}
return;
}
/* Return a list of charsets supported by CODING. */
Lisp_Object
coding_charset_list (struct coding_system *coding)
{
Lisp_Object attrs, charset_list;
CODING_GET_INFO (coding, attrs, charset_list);
if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022))
{
int flags = XFIXNUM (AREF (attrs, coding_attr_iso_flags));
if (flags & CODING_ISO_FLAG_FULL_SUPPORT)
charset_list = Viso_2022_charset_list;
}
else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule))
{
charset_list = Vemacs_mule_charset_list;
}
return charset_list;
}
/* Return a list of charsets supported by CODING-SYSTEM. */
Lisp_Object
coding_system_charset_list (Lisp_Object coding_system)
{
ptrdiff_t id;
Lisp_Object attrs, charset_list;
CHECK_CODING_SYSTEM_GET_ID (coding_system, id);
attrs = CODING_ID_ATTRS (id);
if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022))
{
int flags = XFIXNUM (AREF (attrs, coding_attr_iso_flags));
if (flags & CODING_ISO_FLAG_FULL_SUPPORT)
charset_list = Viso_2022_charset_list;
else
charset_list = CODING_ATTR_CHARSET_LIST (attrs);
}
else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule))
{
charset_list = Vemacs_mule_charset_list;
}
else
{
charset_list = CODING_ATTR_CHARSET_LIST (attrs);
}
return charset_list;
}
/* Return raw-text or one of its subsidiaries that has the same
eol_type as CODING-SYSTEM. */
Lisp_Object
raw_text_coding_system (Lisp_Object coding_system)
{
Lisp_Object spec, attrs;
Lisp_Object eol_type, raw_text_eol_type;
if (NILP (coding_system))
return Qraw_text;
spec = CODING_SYSTEM_SPEC (coding_system);
attrs = AREF (spec, 0);
if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text))
return coding_system;
eol_type = AREF (spec, 2);
if (VECTORP (eol_type))
return Qraw_text;
spec = CODING_SYSTEM_SPEC (Qraw_text);
raw_text_eol_type = AREF (spec, 2);
return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0)
: EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1)
: AREF (raw_text_eol_type, 2));
}
/* Return true if CODING corresponds to raw-text coding-system. */
bool
raw_text_coding_system_p (struct coding_system *coding)
{
return (coding->decoder == decode_coding_raw_text
&& coding->encoder == encode_coding_raw_text) ? true : false;
}
/* If CODING_SYSTEM doesn't specify end-of-line format, return one of
the subsidiary that has the same eol-spec as PARENT (if it is not
nil and specifies end-of-line format) or the system's setting. */
Lisp_Object
coding_inherit_eol_type (Lisp_Object coding_system, Lisp_Object parent)
{
Lisp_Object spec, eol_type;
if (NILP (coding_system))
coding_system = Qraw_text;
else
CHECK_CODING_SYSTEM (coding_system);
spec = CODING_SYSTEM_SPEC (coding_system);
eol_type = AREF (spec, 2);
if (VECTORP (eol_type))
{
/* Format of end-of-line decided by system.
This is Qunix on Unix and Mac, Qdos on DOS/Windows.
This has an effect only for external encoding (i.e., for output to
file and process), not for in-buffer or Lisp string encoding. */
Lisp_Object system_eol_type = Qunix;
#ifdef DOS_NT
system_eol_type = Qdos;
#endif
Lisp_Object parent_eol_type = system_eol_type;
if (! NILP (parent))
{
CHECK_CODING_SYSTEM (parent);
Lisp_Object parent_spec = CODING_SYSTEM_SPEC (parent);
Lisp_Object pspec_type = AREF (parent_spec, 2);
if (!VECTORP (pspec_type))
parent_eol_type = pspec_type;
}
if (EQ (parent_eol_type, Qunix))
coding_system = AREF (eol_type, 0);
else if (EQ (parent_eol_type, Qdos))
coding_system = AREF (eol_type, 1);
else if (EQ (parent_eol_type, Qmac))
coding_system = AREF (eol_type, 2);
}
return coding_system;
}
/* Check if text-conversion and eol-conversion of CODING_SYSTEM are
decided for writing to a process. If not, complement them, and
return a new coding system. */
Lisp_Object
complement_process_encoding_system (Lisp_Object coding_system)
{
Lisp_Object coding_base = Qnil, eol_base = Qnil;
Lisp_Object spec, attrs;
int i;
for (i = 0; i < 3; i++)
{
if (i == 1)
coding_system = CDR_SAFE (Vdefault_process_coding_system);
else if (i == 2)
coding_system = preferred_coding_system ();
spec = CODING_SYSTEM_SPEC (coding_system);
if (NILP (spec))
continue;
attrs = AREF (spec, 0);
if (NILP (coding_base) && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided))
coding_base = CODING_ATTR_BASE_NAME (attrs);
if (NILP (eol_base) && ! VECTORP (AREF (spec, 2)))
eol_base = coding_system;
if (! NILP (coding_base) && ! NILP (eol_base))
break;
}
if (i > 0)
/* The original CODING_SYSTEM didn't specify text-conversion or
eol-conversion. Be sure that we return a fully complemented
coding system. */
coding_system = coding_inherit_eol_type (coding_base, eol_base);
return coding_system;
}
/* Emacs has a mechanism to automatically detect a coding system if it
is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But,
it's impossible to distinguish some coding systems accurately
because they use the same range of codes. So, at first, coding
systems are categorized into 7, those are:
o coding-category-emacs-mule
The category for a coding system which has the same code range
as Emacs' internal format. Assigned the coding-system (Lisp
symbol) `emacs-mule' by default.
o coding-category-sjis
The category for a coding system which has the same code range
as SJIS. Assigned the coding-system (Lisp
symbol) `japanese-shift-jis' by default.
o coding-category-iso-7
The category for a coding system which has the same code range
as ISO2022 of 7-bit environment. This doesn't use any locking
shift and single shift functions. This can encode/decode all
charsets. Assigned the coding-system (Lisp symbol)
`iso-2022-7bit' by default.
o coding-category-iso-7-tight
Same as coding-category-iso-7 except that this can
encode/decode only the specified charsets.
o coding-category-iso-8-1
The category for a coding system which has the same code range
as ISO2022 of 8-bit environment and graphic plane 1 used only
for DIMENSION1 charset. This doesn't use any locking shift
and single shift functions. Assigned the coding-system (Lisp
symbol) `iso-latin-1' by default.
o coding-category-iso-8-2
The category for a coding system which has the same code range
as ISO2022 of 8-bit environment and graphic plane 1 used only
for DIMENSION2 charset. This doesn't use any locking shift
and single shift functions. Assigned the coding-system (Lisp
symbol) `japanese-iso-8bit' by default.
o coding-category-iso-7-else
The category for a coding system which has the same code range
as ISO2022 of 7-bit environment but uses locking shift or
single shift functions. Assigned the coding-system (Lisp
symbol) `iso-2022-7bit-lock' by default.
o coding-category-iso-8-else
The category for a coding system which has the same code range
as ISO2022 of 8-bit environment but uses locking shift or
single shift functions. Assigned the coding-system (Lisp
symbol) `iso-2022-8bit-ss2' by default.
o coding-category-big5
The category for a coding system which has the same code range
as BIG5. Assigned the coding-system (Lisp symbol)
`cn-big5' by default.
o coding-category-utf-8
The category for a coding system which has the same code range
as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp
symbol) `utf-8' by default.
o coding-category-utf-16-be
The category for a coding system in which a text has an
Unicode signature (cf. Unicode Standard) in the order of BIG
endian at the head. Assigned the coding-system (Lisp symbol)
`utf-16-be' by default.
o coding-category-utf-16-le
The category for a coding system in which a text has an
Unicode signature (cf. Unicode Standard) in the order of
LITTLE endian at the head. Assigned the coding-system (Lisp
symbol) `utf-16-le' by default.
o coding-category-ccl
The category for a coding system of which encoder/decoder is
written in CCL programs. The default value is nil, i.e., no
coding system is assigned.
o coding-category-binary
The category for a coding system not categorized in any of the
above. Assigned the coding-system (Lisp symbol)
`no-conversion' by default.
Each of them is a Lisp symbol and the value is an actual
`coding-system's (this is also a Lisp symbol) assigned by a user.
What Emacs does actually is to detect a category of coding system.
Then, it uses a `coding-system' assigned to it. If Emacs can't
decide only one possible category, it selects a category of the
highest priority. Priorities of categories are also specified by a
user in a Lisp variable `coding-category-list'.
*/
static Lisp_Object adjust_coding_eol_type (struct coding_system *coding,
int eol_seen);
/* Return the number of ASCII characters at the head of the source.
By side effects, set coding->head_ascii and update
coding->eol_seen. The value of coding->eol_seen is "logical or" of
EOL_SEEN_LF, EOL_SEEN_CR, and EOL_SEEN_CRLF, but the value is
reliable only when all the source bytes are ASCII. */
static ptrdiff_t
check_ascii (struct coding_system *coding)
{
const unsigned char *src, *end;
Lisp_Object eol_type = CODING_ID_EOL_TYPE (coding->id);
int eol_seen = coding->eol_seen;
coding_set_source (coding);
src = coding->source;
end = src + coding->src_bytes;
if (inhibit_eol_conversion
|| SYMBOLP (eol_type))
{
/* We don't have to check EOL format. */
while (src < end && !( *src & 0x80))
{
if (*src++ == '\n')
eol_seen |= EOL_SEEN_LF;
}
}
else
{
end--; /* We look ahead one byte for "CR LF". */
while (src < end)
{
int c = *src;
if (c & 0x80)
break;
src++;
if (c == '\r')
{
if (*src == '\n')
{
eol_seen |= EOL_SEEN_CRLF;
src++;
}
else
eol_seen |= EOL_SEEN_CR;
}
else if (c == '\n')
eol_seen |= EOL_SEEN_LF;
}
if (src == end)
{
int c = *src;
/* All bytes but the last one C are ASCII. */
if (! (c & 0x80))
{
if (c == '\r')
eol_seen |= EOL_SEEN_CR;
else if (c == '\n')
eol_seen |= EOL_SEEN_LF;
src++;
}
}
}
coding->head_ascii = src - coding->source;
coding->eol_seen = eol_seen;
return (coding->head_ascii);
}
/* Return the number of characters at the source if all the bytes are
valid UTF-8 (of Unicode range). Otherwise, return -1. By side
effects, update coding->eol_seen. The value of coding->eol_seen is
"logical or" of EOL_SEEN_LF, EOL_SEEN_CR, and EOL_SEEN_CRLF, but
the value is reliable only when all the source bytes are valid
UTF-8. */
static ptrdiff_t
check_utf_8 (struct coding_system *coding)
{
const unsigned char *src, *end;
int eol_seen;
ptrdiff_t nchars = coding->head_ascii;
if (coding->head_ascii < 0)
check_ascii (coding);
else
coding_set_source (coding);
src = coding->source + coding->head_ascii;
/* We look ahead one byte for CR LF. */
end = coding->source + coding->src_bytes - 1;
eol_seen = coding->eol_seen;
while (src < end)
{
int c = *src;
if (UTF_8_1_OCTET_P (*src))
{
src++;
if (c < 0x20)
{
if (c == '\r')
{
if (*src == '\n')
{
eol_seen |= EOL_SEEN_CRLF;
src++;
nchars++;
}
else
eol_seen |= EOL_SEEN_CR;
}
else if (c == '\n')
eol_seen |= EOL_SEEN_LF;
}
}
else if (UTF_8_2_OCTET_LEADING_P (c))
{
if (c < 0xC2 /* overlong sequence */
|| src + 1 >= end
|| ! UTF_8_EXTRA_OCTET_P (src[1]))
return -1;
src += 2;
}
else if (UTF_8_3_OCTET_LEADING_P (c))
{
if (src + 2 >= end
|| ! (UTF_8_EXTRA_OCTET_P (src[1])
&& UTF_8_EXTRA_OCTET_P (src[2])))
return -1;
c = (((c & 0xF) << 12)
| ((src[1] & 0x3F) << 6) | (src[2] & 0x3F));
if (c < 0x800 /* overlong sequence */
|| (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */
return -1;
src += 3;
}
else if (UTF_8_4_OCTET_LEADING_P (c))
{
if (src + 3 >= end
|| ! (UTF_8_EXTRA_OCTET_P (src[1])
&& UTF_8_EXTRA_OCTET_P (src[2])
&& UTF_8_EXTRA_OCTET_P (src[3])))
return -1;
c = (((c & 0x7) << 18) | ((src[1] & 0x3F) << 12)
| ((src[2] & 0x3F) << 6) | (src[3] & 0x3F));
if (c < 0x10000 /* overlong sequence */
|| c >= 0x110000) /* non-Unicode character */
return -1;
src += 4;
}
else
return -1;
nchars++;
}
if (src == end)
{
if (! UTF_8_1_OCTET_P (*src))
return -1;
nchars++;
if (*src == '\r')
eol_seen |= EOL_SEEN_CR;
else if (*src == '\n')
eol_seen |= EOL_SEEN_LF;
}
coding->eol_seen = eol_seen;
return nchars;
}
/* Return whether STRING is a valid UTF-8 string. STRING must be a
unibyte string. */
bool
utf8_string_p (Lisp_Object string)
{
eassert (!STRING_MULTIBYTE (string));
struct coding_system coding;
setup_coding_system (Qutf_8_unix, &coding);
/* We initialize only the fields that check_utf_8 accesses. */
coding.head_ascii = -1;
coding.src_pos = 0;
coding.src_pos_byte = 0;
coding.src_chars = SCHARS (string);
coding.src_bytes = SBYTES (string);
coding.src_object = string;
coding.eol_seen = EOL_SEEN_NONE;
return check_utf_8 (&coding) != -1;
}
/* Like make_string, but always returns a multibyte Lisp string, and
avoids decoding if TEXT is encoded in UTF-8. */
Lisp_Object
make_string_from_utf8 (const char *text, ptrdiff_t nbytes)
{
#if 0
/* This method is on average 2 times slower than if we use
decode_string_utf_8. However, please leave the slower
implementation in the code for now, in case it needs to be reused
in some situations. */
ptrdiff_t chars, bytes;
parse_str_as_multibyte ((const unsigned char *) text, nbytes,
&chars, &bytes);
/* If TEXT is a valid UTF-8 string, we can convert it to a Lisp
string directly. Otherwise, we need to decode it. */
if (chars == nbytes || bytes == nbytes)
return make_specified_string (text, chars, nbytes, true);
else
{
struct coding_system coding;
setup_coding_system (Qutf_8_unix, &coding);
coding.mode |= CODING_MODE_LAST_BLOCK;
coding.source = (const unsigned char *) text;
decode_coding_object (&coding, Qnil, 0, 0, nbytes, nbytes, Qt);
return coding.dst_object;
}
#else
return decode_string_utf_8 (Qnil, text, nbytes, Qnil, false, Qt, Qt);
#endif
}
/* Detect how end-of-line of a text of length SRC_BYTES pointed by
SOURCE is encoded. If CATEGORY is one of
coding_category_utf_16_XXXX, assume that CR and LF are encoded by
two-byte, else they are encoded by one-byte.
Return one of EOL_SEEN_XXX. */
#define MAX_EOL_CHECK_COUNT 3
static int
detect_eol (const unsigned char *source, ptrdiff_t src_bytes,
enum coding_category category)
{
const unsigned char *src = source, *src_end = src + src_bytes;
unsigned char c;
int total = 0;
int eol_seen = EOL_SEEN_NONE;
if ((1 << category) & CATEGORY_MASK_UTF_16)
{
bool msb = category == (coding_category_utf_16_le
| coding_category_utf_16_le_nosig);
bool lsb = !msb;
while (src + 1 < src_end)
{
c = src[lsb];
if (src[msb] == 0 && (c == '\n' || c == '\r'))
{
int this_eol;
if (c == '\n')
this_eol = EOL_SEEN_LF;
else if (src + 3 >= src_end
|| src[msb + 2] != 0
|| src[lsb + 2] != '\n')
this_eol = EOL_SEEN_CR;
else
{
this_eol = EOL_SEEN_CRLF;
src += 2;
}
if (eol_seen == EOL_SEEN_NONE)
/* This is the first end-of-line. */
eol_seen = this_eol;
else if (eol_seen != this_eol)
{
/* The found type is different from what found before.
Allow for stray ^M characters in DOS EOL files. */
if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF)
|| (eol_seen == EOL_SEEN_CRLF
&& this_eol == EOL_SEEN_CR))
eol_seen = EOL_SEEN_CRLF;
else
{
eol_seen = EOL_SEEN_LF;
break;
}
}
if (++total == MAX_EOL_CHECK_COUNT)
break;
}
src += 2;
}
}
else
while (src < src_end)
{
c = *src++;
if (c == '\n' || c == '\r')
{
int this_eol;
if (c == '\n')
this_eol = EOL_SEEN_LF;
else if (src >= src_end || *src != '\n')
this_eol = EOL_SEEN_CR;
else
this_eol = EOL_SEEN_CRLF, src++;
if (eol_seen == EOL_SEEN_NONE)
/* This is the first end-of-line. */
eol_seen = this_eol;
else if (eol_seen != this_eol)
{
/* The found type is different from what found before.
Allow for stray ^M characters in DOS EOL files. */
if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF)
|| (eol_seen == EOL_SEEN_CRLF && this_eol == EOL_SEEN_CR))
eol_seen = EOL_SEEN_CRLF;
else
{
eol_seen = EOL_SEEN_LF;
break;
}
}
if (++total == MAX_EOL_CHECK_COUNT)
break;
}
}
return eol_seen;
}
static Lisp_Object
adjust_coding_eol_type (struct coding_system *coding, int eol_seen)
{
Lisp_Object eol_type;
eol_type = CODING_ID_EOL_TYPE (coding->id);
if (! VECTORP (eol_type))
/* Already adjusted. */
return eol_type;
if (eol_seen & EOL_SEEN_LF)
{
coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0));
eol_type = Qunix;
}
else if (eol_seen & EOL_SEEN_CRLF)
{
coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1));
eol_type = Qdos;
}
else if (eol_seen & EOL_SEEN_CR)
{
coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2));
eol_type = Qmac;
}
return eol_type;
}
/* Detect how a text specified in CODING is encoded. If a coding
system is detected, update fields of CODING by the detected coding
system. */
static void
detect_coding (struct coding_system *coding)
{
const unsigned char *src, *src_end;
unsigned int saved_mode = coding->mode;
Lisp_Object found = Qnil;
Lisp_Object eol_type = CODING_ID_EOL_TYPE (coding->id);
coding->consumed = coding->consumed_char = 0;
coding->produced = coding->produced_char = 0;
coding_set_source (coding);
src_end = coding->source + coding->src_bytes;
coding->eol_seen = EOL_SEEN_NONE;
/* If we have not yet decided the text encoding type, detect it
now. */
if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided))
{
int c, i;
struct coding_detection_info detect_info;
bool nul_byte_found = 0, eight_bit_found = 0;
bool inhibit_nbd = inhibit_flag (coding->spec.undecided.inhibit_nbd,
inhibit_nul_byte_detection);
bool inhibit_ied = inhibit_flag (coding->spec.undecided.inhibit_ied,
inhibit_iso_escape_detection);
bool prefer_utf_8 = coding->spec.undecided.prefer_utf_8;
coding->head_ascii = 0;
detect_info.checked = detect_info.found = detect_info.rejected = 0;
for (src = coding->source; src < src_end; src++)
{
c = *src;
if (c & 0x80)
{
eight_bit_found = 1;
if (nul_byte_found)
break;
}
else if (c < 0x20)
{
if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)
&& ! inhibit_ied
&& ! detect_info.checked)
{
if (detect_coding_iso_2022 (coding, &detect_info))
{
/* We have scanned the whole data. */
if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE))
{
/* We didn't find an 8-bit code. We may
have found a NUL-byte, but it's very
rare that a binary file conforms to
ISO-2022. */
src = src_end;
coding->head_ascii = src - coding->source;
}
detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE;
break;
}
}
else if (! c && !inhibit_nbd)
{
nul_byte_found = 1;
if (eight_bit_found)
break;
}
else if (! disable_ascii_optimization
&& ! inhibit_eol_conversion)
{
if (c == '\r')
{
if (src < src_end && src[1] == '\n')
{
coding->eol_seen |= EOL_SEEN_CRLF;
src++;
if (! eight_bit_found)
coding->head_ascii++;
}
else
coding->eol_seen |= EOL_SEEN_CR;
}
else if (c == '\n')
{
coding->eol_seen |= EOL_SEEN_LF;
}
}
if (! eight_bit_found)
coding->head_ascii++;
}
else if (! eight_bit_found)
coding->head_ascii++;
}
if (nul_byte_found || eight_bit_found
|| coding->head_ascii < coding->src_bytes
|| detect_info.found)
{
enum coding_category category;
struct coding_system *this;
if (coding->head_ascii == coding->src_bytes)
/* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */
for (i = 0; i < coding_category_raw_text; i++)
{
category = coding_priorities[i];
this = coding_categories + category;
if (detect_info.found & (1 << category))
break;
}
else
{
if (nul_byte_found)
{
detect_info.checked |= ~CATEGORY_MASK_UTF_16;
detect_info.rejected |= ~CATEGORY_MASK_UTF_16;
}
else if (prefer_utf_8
&& detect_coding_utf_8 (coding, &detect_info))
{
detect_info.checked |= ~CATEGORY_MASK_UTF_8;
detect_info.rejected |= ~CATEGORY_MASK_UTF_8;
}
for (i = 0; i < coding_category_raw_text; i++)
{
category = coding_priorities[i];
this = coding_categories + category;
/* Some of this->detector (e.g. detect_coding_sjis)
require this information. */
coding->id = this->id;
if (this->id < 0)
{
/* No coding system of this category is defined. */
detect_info.rejected |= (1 << category);
}
else if (category >= coding_category_raw_text)
continue;
else if (detect_info.checked & (1 << category))
{
if (detect_info.found & (1 << category))
break;
}
else if ((*(this->detector)) (coding, &detect_info)
&& detect_info.found & (1 << category))
break;
}
}
if (i < coding_category_raw_text)
{
if (category == coding_category_utf_8_auto)
{
Lisp_Object coding_systems;
coding_systems = AREF (CODING_ID_ATTRS (this->id),
coding_attr_utf_bom);
if (CONSP (coding_systems))
{
if (detect_info.found & CATEGORY_MASK_UTF_8_SIG)
found = XCAR (coding_systems);
else
found = XCDR (coding_systems);
}
else
found = CODING_ID_NAME (this->id);
}
else if (category == coding_category_utf_16_auto)
{
Lisp_Object coding_systems;
coding_systems = AREF (CODING_ID_ATTRS (this->id),
coding_attr_utf_bom);
if (CONSP (coding_systems))
{
if (detect_info.found & CATEGORY_MASK_UTF_16_LE)
found = XCAR (coding_systems);
else if (detect_info.found & CATEGORY_MASK_UTF_16_BE)
found = XCDR (coding_systems);
}
else
found = CODING_ID_NAME (this->id);
}
else
found = CODING_ID_NAME (this->id);
}
else if (nul_byte_found)
found = Qno_conversion;
else if ((detect_info.rejected & CATEGORY_MASK_ANY)
== CATEGORY_MASK_ANY)
found = Qraw_text;
else if (detect_info.rejected)
for (i = 0; i < coding_category_raw_text; i++)
if (! (detect_info.rejected & (1 << coding_priorities[i])))
{
this = coding_categories + coding_priorities[i];
found = CODING_ID_NAME (this->id);
break;
}
}
}
else if (XFIXNUM (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id)))
== coding_category_utf_8_auto)
{
Lisp_Object coding_systems;
struct coding_detection_info detect_info;
coding_systems
= AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom);
detect_info.found = detect_info.rejected = 0;
if (check_ascii (coding) == coding->src_bytes)
{
if (CONSP (coding_systems))
found = XCDR (coding_systems);
}
else
{
if (CONSP (coding_systems)
&& detect_coding_utf_8 (coding, &detect_info))
{
if (detect_info.found & CATEGORY_MASK_UTF_8_SIG)
found = XCAR (coding_systems);
else
found = XCDR (coding_systems);
}
}
}
else if (XFIXNUM (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id)))
== coding_category_utf_16_auto)
{
Lisp_Object coding_systems;
struct coding_detection_info detect_info;
coding_systems
= AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom);
detect_info.found = detect_info.rejected = 0;
coding->head_ascii = 0;
if (CONSP (coding_systems)
&& detect_coding_utf_16 (coding, &detect_info))
{
if (detect_info.found & CATEGORY_MASK_UTF_16_LE)
found = XCAR (coding_systems);
else if (detect_info.found & CATEGORY_MASK_UTF_16_BE)
found = XCDR (coding_systems);
}
}
if (! NILP (found))
{
int specified_eol = (VECTORP (eol_type) ? EOL_SEEN_NONE
: EQ (eol_type, Qdos) ? EOL_SEEN_CRLF
: EQ (eol_type, Qmac) ? EOL_SEEN_CR
: EOL_SEEN_LF);
setup_coding_system (found, coding);
if (specified_eol != EOL_SEEN_NONE)
adjust_coding_eol_type (coding, specified_eol);
}
coding->mode = saved_mode;
}
static void
decode_eol (struct coding_system *coding)
{
Lisp_Object eol_type;
unsigned char *p, *pbeg, *pend;
eol_type = CODING_ID_EOL_TYPE (coding->id);
if (EQ (eol_type, Qunix) || inhibit_eol_conversion)
return;
if (NILP (coding->dst_object))
pbeg = coding->destination;
else
pbeg = BYTE_POS_ADDR (coding->dst_pos_byte);
pend = pbeg + coding->produced;
if (VECTORP (eol_type))
{
int eol_seen = EOL_SEEN_NONE;
for (p = pbeg; p < pend; p++)
{
if (*p == '\n')
eol_seen |= EOL_SEEN_LF;
else if (*p == '\r')
{
if (p + 1 < pend && *(p + 1) == '\n')
{
eol_seen |= EOL_SEEN_CRLF;
p++;
}
else
eol_seen |= EOL_SEEN_CR;
}
}
/* Handle DOS-style EOLs in a file with stray ^M characters. */
if ((eol_seen & EOL_SEEN_CRLF) != 0
&& (eol_seen & EOL_SEEN_CR) != 0
&& (eol_seen & EOL_SEEN_LF) == 0)
eol_seen = EOL_SEEN_CRLF;
else if (eol_seen != EOL_SEEN_NONE
&& eol_seen != EOL_SEEN_LF
&& eol_seen != EOL_SEEN_CRLF
&& eol_seen != EOL_SEEN_CR)
eol_seen = EOL_SEEN_LF;
if (eol_seen != EOL_SEEN_NONE)
eol_type = adjust_coding_eol_type (coding, eol_seen);
}
if (EQ (eol_type, Qmac))
{
for (p = pbeg; p < pend; p++)
if (*p == '\r')
*p = '\n';
}
else if (EQ (eol_type, Qdos))
{
ptrdiff_t n = 0;
ptrdiff_t pos = coding->dst_pos;
ptrdiff_t pos_byte = coding->dst_pos_byte;
ptrdiff_t pos_end = pos_byte + coding->produced - 1;
/* This assertion is here instead of code, now deleted, that
handled the NILP case, which no longer happens with the
current codebase. */
eassert (!NILP (coding->dst_object));
while (pos_byte < pos_end)
{
int incr;
p = BYTE_POS_ADDR (pos_byte);
if (coding->dst_multibyte)
incr = BYTES_BY_CHAR_HEAD (*p);
else
incr = 1;
if (*p == '\r' && p[1] == '\n')
{
del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0);
n++;
pos_end--;
}
pos++;
pos_byte += incr;
}
coding->produced -= n;
coding->produced_char -= n;
}
}
/* MAX_LOOKUP's maximum value. MAX_LOOKUP is an int and so cannot
exceed INT_MAX. Also, MAX_LOOKUP is multiplied by sizeof (int) for
alloca, so it cannot exceed MAX_ALLOCA / sizeof (int). */
enum { MAX_LOOKUP_MAX = min (INT_MAX, MAX_ALLOCA / sizeof (int)) };
/* Return a translation table (or list of them) from coding system
attribute vector ATTRS for encoding (if ENCODEP) or decoding (if
not ENCODEP). */
static Lisp_Object
get_translation_table (Lisp_Object attrs, bool encodep, int *max_lookup)
{
Lisp_Object standard, translation_table;
Lisp_Object val;
if (NILP (Venable_character_translation))
{
if (max_lookup)
*max_lookup = 0;
return Qnil;
}
if (encodep)
translation_table = CODING_ATTR_ENCODE_TBL (attrs),
standard = Vstandard_translation_table_for_encode;
else
translation_table = CODING_ATTR_DECODE_TBL (attrs),
standard = Vstandard_translation_table_for_decode;
if (NILP (translation_table))
translation_table = standard;
else
{
if (SYMBOLP (translation_table))
translation_table = Fget (translation_table, Qtranslation_table);
else if (CONSP (translation_table))
{
translation_table = Fcopy_sequence (translation_table);
for (val = translation_table; CONSP (val); val = XCDR (val))
if (SYMBOLP (XCAR (val)))
XSETCAR (val, Fget (XCAR (val), Qtranslation_table));
}
if (CHAR_TABLE_P (standard))
{
if (CONSP (translation_table))
translation_table = nconc2 (translation_table, list1 (standard));
else
translation_table = list2 (translation_table, standard);
}
}
if (max_lookup)
{
*max_lookup = 1;
if (CHAR_TABLE_P (translation_table)
&& CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table)) > 1)
{
val = XCHAR_TABLE (translation_table)->extras[1];
if (FIXNATP (val) && *max_lookup < XFIXNAT (val))
*max_lookup = min (XFIXNAT (val), MAX_LOOKUP_MAX);
}
else if (CONSP (translation_table))
{
Lisp_Object tail;
for (tail = translation_table; CONSP (tail); tail = XCDR (tail))
if (CHAR_TABLE_P (XCAR (tail))
&& CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1)
{
Lisp_Object tailval = XCHAR_TABLE (XCAR (tail))->extras[1];
if (FIXNATP (tailval) && *max_lookup < XFIXNAT (tailval))
*max_lookup = min (XFIXNAT (tailval), MAX_LOOKUP_MAX);
}
}
}
return translation_table;
}
#define LOOKUP_TRANSLATION_TABLE(table, c, trans) \
do { \
trans = Qnil; \
if (CHAR_TABLE_P (table)) \
{ \
trans = CHAR_TABLE_REF (table, c); \
if (CHARACTERP (trans)) \
c = XFIXNAT (trans), trans = Qnil; \
} \
else if (CONSP (table)) \
{ \
Lisp_Object tail; \
\
for (tail = table; CONSP (tail); tail = XCDR (tail)) \
if (CHAR_TABLE_P (XCAR (tail))) \
{ \
trans = CHAR_TABLE_REF (XCAR (tail), c); \
if (CHARACTERP (trans)) \
c = XFIXNAT (trans), trans = Qnil; \
else if (! NILP (trans)) \
break; \
} \
} \
} while (0)
/* Return a translation of character(s) at BUF according to TRANS.
TRANS is TO-CHAR, [TO-CHAR ...], or ((FROM . TO) ...) where FROM =
[FROM-CHAR ...], TO is TO-CHAR or [TO-CHAR ...]. The return value
is TO-CHAR or [TO-CHAR ...] if a translation is found, Qnil if not
found, or Qt if BUF is too short to lookup characters in FROM. As
a side effect, if a translation is found, *NCHARS is set to the
number of characters being translated. */
static Lisp_Object
get_translation (Lisp_Object trans, int *buf, int *buf_end, ptrdiff_t *nchars)
{
if (FIXNUMP (trans) || VECTORP (trans))
{
*nchars = 1;
return trans;
}
for (; CONSP (trans); trans = XCDR (trans))
{
Lisp_Object val = XCAR (trans);
Lisp_Object from = XCAR (val);
ptrdiff_t len = ASIZE (from);
ptrdiff_t i;
for (i = 0; i < len; i++)
{
if (buf + i == buf_end)
return Qt;
if (XFIXNUM (AREF (from, i)) != buf[i])
break;
}
if (i == len)
{
*nchars = len;
return XCDR (val);
}
}
return Qnil;
}
static int
produce_chars (struct coding_system *coding, Lisp_Object translation_table,
bool last_block)
{
unsigned char *dst = coding->destination + coding->produced;
unsigned char *dst_end = coding->destination + coding->dst_bytes;
ptrdiff_t produced;
ptrdiff_t produced_chars = 0;
int carryover = 0;
if (! coding->chars_at_source)
{
/* Source characters are in coding->charbuf. */
int *buf = coding->charbuf;
int *buf_end = buf + coding->charbuf_used;
if (EQ (coding->src_object, coding->dst_object)
&& ! NILP (coding->dst_object))
{
eassert (growable_destination (coding));
coding_set_source (coding);
dst_end = ((unsigned char *) coding->source) + coding->consumed;
}
while (buf < buf_end)
{
int c = *buf;
ptrdiff_t i;
if (c >= 0)
{
ptrdiff_t from_nchars = 1, to_nchars = 1;
Lisp_Object trans = Qnil;
LOOKUP_TRANSLATION_TABLE (translation_table, c, trans);
if (! NILP (trans))
{
trans = get_translation (trans, buf, buf_end, &from_nchars);
if (FIXNUMP (trans))
c = XFIXNUM (trans);
else if (VECTORP (trans))
{
to_nchars = ASIZE (trans);
c = XFIXNUM (AREF (trans, 0));
}
else if (EQ (trans, Qt) && ! last_block)
break;
}
if ((dst_end - dst) / MAX_MULTIBYTE_LENGTH < to_nchars)
{
eassert (growable_destination (coding));
ptrdiff_t dst_size;
if (INT_MULTIPLY_WRAPV (to_nchars, MAX_MULTIBYTE_LENGTH,
&dst_size)
|| INT_ADD_WRAPV (buf_end - buf, dst_size, &dst_size))
memory_full (SIZE_MAX);
dst = alloc_destination (coding, dst_size, dst);
if (EQ (coding->src_object, coding->dst_object))
{
coding_set_source (coding);
dst_end = (((unsigned char *) coding->source)
+ coding->consumed);
}
else
dst_end = coding->destination + coding->dst_bytes;
}
for (i = 0; i < to_nchars; i++)
{
if (i > 0)
c = XFIXNUM (AREF (trans, i));
if (coding->dst_multibyte
|| ! CHAR_BYTE8_P (c))
CHAR_STRING_ADVANCE_NO_UNIFY (c, dst);
else
*dst++ = CHAR_TO_BYTE8 (c);
}
produced_chars += to_nchars;
buf += from_nchars;
}
else
/* This is an annotation datum. (-C) is the length. */
buf += -c;
}
carryover = buf_end - buf;
}
else
{
/* Source characters are at coding->source. */
const unsigned char *src = coding->source;
const unsigned char *src_end = src + coding->consumed;
if (EQ (coding->dst_object, coding->src_object))
{
eassert (growable_destination (coding));
dst_end = (unsigned char *) src;
}
if (coding->src_multibyte != coding->dst_multibyte)
{
if (coding->src_multibyte)
{
bool multibytep = 1;
ptrdiff_t consumed_chars = 0;
while (1)
{
const unsigned char *src_base = src;
int c;
ONE_MORE_BYTE (c);
if (dst == dst_end)
{
eassert (growable_destination (coding));
if (EQ (coding->src_object, coding->dst_object))
dst_end = (unsigned char *) src;
if (dst == dst_end)
{
ptrdiff_t offset = src - coding->source;
dst = alloc_destination (coding, src_end - src + 1,
dst);
dst_end = coding->destination + coding->dst_bytes;
coding_set_source (coding);
src = coding->source + offset;
src_end = coding->source + coding->consumed;
if (EQ (coding->src_object, coding->dst_object))
dst_end = (unsigned char *) src;
}
}
*dst++ = c;
produced_chars++;
}
no_more_source:
;
}
else
while (src < src_end)
{
bool multibytep = 1;
int c = *src++;
if (dst >= dst_end - 1)
{
eassert (growable_destination (coding));
if (EQ (coding->src_object, coding->dst_object))
dst_end = (unsigned char *) src;
if (dst >= dst_end - 1)
{
ptrdiff_t offset = src - coding->source;
ptrdiff_t more_bytes;
if (EQ (coding->src_object, coding->dst_object))
more_bytes = ((src_end - src) / 2) + 2;
else
more_bytes = src_end - src + 2;
dst = alloc_destination (coding, more_bytes, dst);
dst_end = coding->destination + coding->dst_bytes;
coding_set_source (coding);
src = coding->source + offset;
src_end = coding->source + coding->consumed;
if (EQ (coding->src_object, coding->dst_object))
dst_end = (unsigned char *) src;
}
}
EMIT_ONE_BYTE (c);
}
}
else
{
if (!EQ (coding->src_object, coding->dst_object))
{
ptrdiff_t require = coding->src_bytes - coding->dst_bytes;
if (require > 0)
{
ptrdiff_t offset = src - coding->source;
dst = alloc_destination (coding, require, dst);
coding_set_source (coding);
src = coding->source + offset;
src_end = coding->source + coding->consumed;
}
}
produced_chars = coding->consumed_char;
while (src < src_end)
*dst++ = *src++;
}
}
produced = dst - (coding->destination + coding->produced);
if (BUFFERP (coding->dst_object) && produced_chars > 0)
insert_from_gap (produced_chars, produced, 0);
coding->produced += produced;
coding->produced_char += produced_chars;
return carryover;
}
/* Compose text in CODING->object according to the annotation data at
CHARBUF. CHARBUF is an array:
[ -LENGTH ANNOTATION_MASK NCHARS NBYTES METHOD [ COMPONENTS... ] ]
*/
static void
produce_composition (struct coding_system *coding, int *charbuf, ptrdiff_t pos)
{
int len;
ptrdiff_t to;
enum composition_method method;
Lisp_Object components;
len = -charbuf[0] - MAX_ANNOTATION_LENGTH;
to = pos + charbuf[2];
method = (enum composition_method) (charbuf[4]);
if (method == COMPOSITION_RELATIVE)
components = Qnil;
else
{
Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1];
int i, j;
if (method == COMPOSITION_WITH_RULE)
len = charbuf[2] * 3 - 2;
charbuf += MAX_ANNOTATION_LENGTH;
/* charbuf = [ CHRA ... CHAR] or [ CHAR -2 RULE ... CHAR ] */
for (i = j = 0; i < len && charbuf[i] != -1; i++, j++)
{
if (charbuf[i] >= 0)
args[j] = make_fixnum (charbuf[i]);
else
{
i++;
args[j] = make_fixnum (charbuf[i] % 0x100);
}
}
components = (i == j ? Fstring (j, args) : Fvector (j, args));
}
compose_text (pos, to, components, Qnil, coding->dst_object);
}
/* Put `charset' property on text in CODING->object according to
the annotation data at CHARBUF. CHARBUF is an array:
[ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ]
*/
static void
produce_charset (struct coding_system *coding, int *charbuf, ptrdiff_t pos)
{
ptrdiff_t from = pos - charbuf[2];
struct charset *charset = CHARSET_FROM_ID (charbuf[3]);
Fput_text_property (make_fixnum (from), make_fixnum (pos),
Qcharset, CHARSET_NAME (charset),
coding->dst_object);
}
#define MAX_CHARBUF_SIZE 0x4000
/* How many units decoding functions expect in coding->charbuf at
most. Currently, decode_coding_emacs_mule expects the following
size, and that is the largest value. */
#define MAX_CHARBUF_EXTRA_SIZE ((MAX_ANNOTATION_LENGTH * 3) + 1)
#define ALLOC_CONVERSION_WORK_AREA(coding, size) \
do { \
ptrdiff_t units = min ((size) + MAX_CHARBUF_EXTRA_SIZE, \
MAX_CHARBUF_SIZE); \
coding->charbuf = SAFE_ALLOCA (units * sizeof (int)); \
coding->charbuf_size = units; \
} while (0)
static void
produce_annotation (struct coding_system *coding, ptrdiff_t pos)
{
int *charbuf = coding->charbuf;
int *charbuf_end = charbuf + coding->charbuf_used;
if (NILP (coding->dst_object))
return;
while (charbuf < charbuf_end)
{
if (*charbuf >= 0)
pos++, charbuf++;
else
{
int len = -*charbuf;
if (len > 2)
switch (charbuf[1])
{
case CODING_ANNOTATE_COMPOSITION_MASK:
produce_composition (coding, charbuf, pos);
break;
case CODING_ANNOTATE_CHARSET_MASK:
produce_charset (coding, charbuf, pos);
break;
default:
break;
}
charbuf += len;
}
}
}
/* Decode the data at CODING->src_object into CODING->dst_object.
CODING->src_object is a buffer, a string, or nil.
CODING->dst_object is a buffer.
If CODING->src_object is a buffer, it must be the current buffer.
In this case, if CODING->src_pos is positive, it is a position of
the source text in the buffer, otherwise, the source text is in the
gap area of the buffer, and CODING->src_pos specifies the offset of
the text from the end of the gap (and GPT must be equal to PT).
When the text is taken from the gap, it can't be at the beginning
of the gap because the new decoded text is progressively accumulated
at the beginning of the gap before it gets inserted at PT (this way,
as the output grows, the input shrinks, so we only need to allocate
enough space for `max(IN, OUT)` instead of `IN + OUT`).
If CODING->src_object is a string, CODING->src_pos is an index to
that string.
If CODING->src_object is nil, CODING->source must already point to
the non-relocatable memory area. In this case, CODING->src_pos is
an offset from CODING->source.
The decoded data is inserted at the current point of the buffer
CODING->dst_object.
*/
static void
decode_coding (struct coding_system *coding)
{
Lisp_Object attrs;
Lisp_Object undo_list;
Lisp_Object translation_table;
struct ccl_spec cclspec;
int carryover;
int i;
USE_SAFE_ALLOCA;
if (BUFFERP (coding->src_object)
&& coding->src_pos > 0
&& coding->src_pos < GPT
&& coding->src_pos + coding->src_chars > GPT)
move_gap_both (coding->src_pos, coding->src_pos_byte);
undo_list = Qt;
if (BUFFERP (coding->dst_object))
{
set_buffer_internal (XBUFFER (coding->dst_object));
if (GPT != PT)
move_gap_both (PT, PT_BYTE);
/* We must disable undo_list in order to record the whole insert
transaction via record_insert at the end. But doing so also
disables the recording of the first change to the undo_list.
Therefore we check for first change here and record it via
record_first_change if needed. */
if (MODIFF <= SAVE_MODIFF)
record_first_change ();
undo_list = BVAR (current_buffer, undo_list);
bset_undo_list (current_buffer, Qt);
}
coding->consumed = coding->consumed_char = 0;
coding->produced = coding->produced_char = 0;
coding->chars_at_source = 0;
record_conversion_result (coding, CODING_RESULT_SUCCESS);
ALLOC_CONVERSION_WORK_AREA (coding, coding->src_bytes);
attrs = CODING_ID_ATTRS (coding->id);
translation_table = get_translation_table (attrs, 0, NULL);
carryover = 0;
if (coding->decoder == decode_coding_ccl)
{
coding->spec.ccl = &cclspec;
setup_ccl_program (&cclspec.ccl, CODING_CCL_DECODER (coding));
}
do
{
ptrdiff_t pos = coding->dst_pos + coding->produced_char;
coding_set_source (coding);
coding->annotated = 0;
coding->charbuf_used = carryover;
(*(coding->decoder)) (coding);
coding_set_destination (coding);
carryover = produce_chars (coding, translation_table, 0);
if (coding->annotated)
produce_annotation (coding, pos);
for (i = 0; i < carryover; i++)
coding->charbuf[i]
= coding->charbuf[coding->charbuf_used - carryover + i];
}
while (coding->result == CODING_RESULT_INSUFFICIENT_DST
|| (coding->consumed < coding->src_bytes
&& (coding->result == CODING_RESULT_SUCCESS
|| coding->result == CODING_RESULT_INVALID_SRC)));
if (carryover > 0)
{
coding_set_destination (coding);
coding->charbuf_used = carryover;
produce_chars (coding, translation_table, 1);
}
coding->carryover_bytes = 0;
if (coding->consumed < coding->src_bytes)
{
ptrdiff_t nbytes = coding->src_bytes - coding->consumed;
const unsigned char *src;
coding_set_source (coding);
coding_set_destination (coding);
src = coding->source + coding->consumed;
if (coding->mode & CODING_MODE_LAST_BLOCK)
{
/* Flush out unprocessed data as binary chars. We are sure
that the number of data is less than the size of
coding->charbuf. */
coding->charbuf_used = 0;
coding->chars_at_source = 0;
while (nbytes-- > 0)
{
int c;
/* Copy raw bytes in their 2-byte forms from multibyte
text as single characters. */
if (coding->src_multibyte
&& CHAR_BYTE8_HEAD_P (*src) && nbytes > 0)
{
c = string_char_advance (&src);
nbytes--;
}
else
{
c = *src++;
if (c & 0x80)
c = BYTE8_TO_CHAR (c);
}
coding->charbuf[coding->charbuf_used++] = c;
}
produce_chars (coding, Qnil, 1);
}
else
{
/* Record unprocessed bytes in coding->carryover. We are
sure that the number of data is less than the size of
coding->carryover. */
unsigned char *p = coding->carryover;
if (nbytes > sizeof coding->carryover)
nbytes = sizeof coding->carryover;
coding->carryover_bytes = nbytes;
while (nbytes-- > 0)
*p++ = *src++;
}
coding->consumed = coding->src_bytes;
}
if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix)
&& !inhibit_eol_conversion)
decode_eol (coding);
if (BUFFERP (coding->dst_object))
{
bset_undo_list (current_buffer, undo_list);
record_insert (coding->dst_pos, coding->produced_char);
}
SAFE_FREE ();
}
/* Extract an annotation datum from a composition starting at POS and
ending before LIMIT of CODING->src_object (buffer or string), store
the data in BUF, set *STOP to a starting position of the next
composition (if any) or to LIMIT, and return the address of the
next element of BUF.
If such an annotation is not found, set *STOP to a starting
position of a composition after POS (if any) or to LIMIT, and
return BUF. */
static int *
handle_composition_annotation (ptrdiff_t pos, ptrdiff_t limit,
struct coding_system *coding, int *buf,
ptrdiff_t *stop)
{
ptrdiff_t start, end;
Lisp_Object prop;
if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object)
|| end > limit)
*stop = limit;
else if (start > pos)
*stop = start;
else
{
if (start == pos)
{
/* We found a composition. Store the corresponding
annotation data in BUF. */
int *head = buf;
enum composition_method method = composition_method (prop);
int nchars = COMPOSITION_LENGTH (prop);
ADD_COMPOSITION_DATA (buf, nchars, 0, method);
if (method != COMPOSITION_RELATIVE)
{
Lisp_Object components;
ptrdiff_t i, len, i_byte;
components = COMPOSITION_COMPONENTS (prop);
if (VECTORP (components))
{
len = ASIZE (components);
for (i = 0; i < len; i++)
*buf++ = XFIXNUM (AREF (components, i));
}
else if (STRINGP (components))
{
len = SCHARS (components);
i = i_byte = 0;
while (i < len)
*buf++ = fetch_string_char_advance (components,
&i, &i_byte);
}
else if (FIXNUMP (components))
{
len = 1;
*buf++ = XFIXNUM (components);
}
else if (CONSP (components))
{
for (len = 0; CONSP (components);
len++, components = XCDR (components))
*buf++ = XFIXNUM (XCAR (components));
}
else
emacs_abort ();
*head -= len;
}
}
if (find_composition (end, limit, &start, &end, &prop,
coding->src_object)
&& end <= limit)
*stop = start;
else
*stop = limit;
}
return buf;
}
/* Extract an annotation datum from a text property `charset' at POS of
CODING->src_object (buffer of string), store the data in BUF, set
*STOP to the position where the value of `charset' property changes
(limiting by LIMIT), and return the address of the next element of
BUF.
If the property value is nil, set *STOP to the position where the
property value is non-nil (limiting by LIMIT), and return BUF. */
static int *
handle_charset_annotation (ptrdiff_t pos, ptrdiff_t limit,
struct coding_system *coding, int *buf,
ptrdiff_t *stop)
{
Lisp_Object val, next;
int id;
val = Fget_text_property (make_fixnum (pos), Qcharset, coding->src_object);
if (! NILP (val) && CHARSETP (val))
id = XFIXNUM (CHARSET_SYMBOL_ID (val));
else
id = -1;
ADD_CHARSET_DATA (buf, 0, id);
next = Fnext_single_property_change (make_fixnum (pos), Qcharset,
coding->src_object,
make_fixnum (limit));
*stop = XFIXNUM (next);
return buf;
}
static void
consume_chars (struct coding_system *coding, Lisp_Object translation_table,
int max_lookup)
{
int *buf = coding->charbuf;
int *buf_end = coding->charbuf + coding->charbuf_size;
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
ptrdiff_t pos = coding->src_pos + coding->consumed_char;
ptrdiff_t end_pos = coding->src_pos + coding->src_chars;
bool multibytep = coding->src_multibyte;
Lisp_Object eol_type;
int c;
ptrdiff_t stop, stop_composition, stop_charset;
int *lookup_buf = NULL;
if (! NILP (translation_table))
lookup_buf = alloca (sizeof (int) * max_lookup);
eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id);
if (VECTORP (eol_type))
eol_type = Qunix;
/* Note: composition handling is not yet implemented. */
coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK;
if (NILP (coding->src_object))
stop = stop_composition = stop_charset = end_pos;
else
{
if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)
stop = stop_composition = pos;
else
stop = stop_composition = end_pos;
if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK)
stop = stop_charset = pos;
else
stop_charset = end_pos;
}
/* Compensate for CRLF and conversion. */
buf_end -= 1 + MAX_ANNOTATION_LENGTH;
while (buf < buf_end)
{
Lisp_Object trans;
if (pos == stop)
{
if (pos == end_pos)
break;
if (pos == stop_composition)
buf = handle_composition_annotation (pos, end_pos, coding,
buf, &stop_composition);
if (pos == stop_charset)
buf = handle_charset_annotation (pos, end_pos, coding,
buf, &stop_charset);
stop = (stop_composition < stop_charset
? stop_composition : stop_charset);
}
if (! multibytep)
{
if (coding->encoder == encode_coding_raw_text
|| coding->encoder == encode_coding_ccl)
c = *src++, pos++;
else
{
int bytes = multibyte_length (src, src_end, true, true);
if (0 < bytes)
c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos += bytes;
else
c = BYTE8_TO_CHAR (*src), src++, pos++;
}
}
else
c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos++;
if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY))
c = '\n';
if (! EQ (eol_type, Qunix))
{
if (c == '\n')
{
if (EQ (eol_type, Qdos))
*buf++ = '\r';
else
c = '\r';
}
}
trans = Qnil;
LOOKUP_TRANSLATION_TABLE (translation_table, c, trans);
if (NILP (trans))
*buf++ = c;
else
{
ptrdiff_t from_nchars = 1, to_nchars = 1;
int *lookup_buf_end;
const unsigned char *p = src;
int i;
lookup_buf[0] = c;
for (i = 1; i < max_lookup && p < src_end; i++)
lookup_buf[i] = string_char_advance (&p);
lookup_buf_end = lookup_buf + i;
trans = get_translation (trans, lookup_buf, lookup_buf_end,
&from_nchars);
if (FIXNUMP (trans))
c = XFIXNUM (trans);
else if (VECTORP (trans))
{
to_nchars = ASIZE (trans);
if (buf_end - buf < to_nchars)
break;
c = XFIXNUM (AREF (trans, 0));
}
else
break;
*buf++ = c;
for (i = 1; i < to_nchars; i++)
*buf++ = XFIXNUM (AREF (trans, i));
for (i = 1; i < from_nchars; i++, pos++)
src += multibyte_length (src, NULL, false, true);
}
}
coding->consumed = src - coding->source;
coding->consumed_char = pos - coding->src_pos;
coding->charbuf_used = buf - coding->charbuf;
coding->chars_at_source = 0;
}
/* Encode the text at CODING->src_object into CODING->dst_object.
CODING->src_object is a buffer or a string.
CODING->dst_object is a buffer or nil.
If CODING->src_object is a buffer, it must be the current buffer.
In this case, if CODING->src_pos is positive, it is a position of
the source text in the buffer, otherwise. the source text is in the
gap area of the buffer, and coding->src_pos specifies the offset of
the text from GPT (which must be the same as PT). If this is the
same buffer as CODING->dst_object, CODING->src_pos must be
negative and CODING should not have `pre-write-conversion'.
If CODING->src_object is a string, CODING should not have
`pre-write-conversion'.
If CODING->dst_object is a buffer, the encoded data is inserted at
the current point of that buffer.
If CODING->dst_object is nil, the encoded data is placed at the
memory area specified by CODING->destination. */
static void
encode_coding (struct coding_system *coding)
{
Lisp_Object attrs;
Lisp_Object translation_table;
int max_lookup;
struct ccl_spec cclspec;
USE_SAFE_ALLOCA;
attrs = CODING_ID_ATTRS (coding->id);
if (coding->encoder == encode_coding_raw_text)
translation_table = Qnil, max_lookup = 0;
else
translation_table = get_translation_table (attrs, 1, &max_lookup);
if (BUFFERP (coding->dst_object))
{
set_buffer_internal (XBUFFER (coding->dst_object));
coding->dst_multibyte
= ! NILP (BVAR (current_buffer, enable_multibyte_characters));
}
coding->consumed = coding->consumed_char = 0;
coding->produced = coding->produced_char = 0;
record_conversion_result (coding, CODING_RESULT_SUCCESS);
ALLOC_CONVERSION_WORK_AREA (coding, coding->src_chars);
if (coding->encoder == encode_coding_ccl)
{
coding->spec.ccl = &cclspec;
setup_ccl_program (&cclspec.ccl, CODING_CCL_ENCODER (coding));
}
do {
coding_set_source (coding);
consume_chars (coding, translation_table, max_lookup);
coding_set_destination (coding);
(*(coding->encoder)) (coding);
} while (coding->consumed_char < coding->src_chars);
if (BUFFERP (coding->dst_object) && coding->produced_char > 0)
insert_from_gap (coding->produced_char, coding->produced, 0);
SAFE_FREE ();
}
/* Code-conversion operations use internal buffers. There's a single
reusable buffer, which is created the first time it is needed, and
then never killed. When this reusable buffer is being used, the
reused_workbuf_in_use flag is set. If we need another conversion
buffer while the reusable one is in use (e.g., if code-conversion
is reentered when another code-conversion is in progress), we
create temporary buffers using the name of the reusable buffer as
the base name, see code_conversion_save below. These temporary
buffers are killed when the code-conversion operations that use
them return, see code_conversion_restore below. */
/* A string that serves as name of the reusable work buffer, and as base
name of temporary work buffers used for code-conversion operations. */
Lisp_Object Vcode_conversion_workbuf_name;
/* The reusable working buffer, created once and never killed. */
static Lisp_Object Vcode_conversion_reused_workbuf;
/* True iff Vcode_conversion_reused_workbuf is already in use. */
static bool reused_workbuf_in_use;
static void
code_conversion_restore (Lisp_Object arg)
{
Lisp_Object current, workbuf;
current = XCAR (arg);
workbuf = XCDR (arg);
if (! NILP (workbuf))
{
if (EQ (workbuf, Vcode_conversion_reused_workbuf))
reused_workbuf_in_use = 0;
else
Fkill_buffer (workbuf);
}
set_buffer_internal (XBUFFER (current));
}
Lisp_Object
code_conversion_save (bool with_work_buf, bool multibyte)
{
Lisp_Object workbuf = Qnil;
if (with_work_buf)
{
if (reused_workbuf_in_use)
{
Lisp_Object name
= Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil);
workbuf = Fget_buffer_create (name);
}
else
{
if (NILP (Fbuffer_live_p (Vcode_conversion_reused_workbuf)))
Vcode_conversion_reused_workbuf
= Fget_buffer_create (Vcode_conversion_workbuf_name);
workbuf = Vcode_conversion_reused_workbuf;
}
}
record_unwind_protect (code_conversion_restore,
Fcons (Fcurrent_buffer (), workbuf));
if (!NILP (workbuf))
{
struct buffer *current = current_buffer;
set_buffer_internal (XBUFFER (workbuf));
/* We can't allow modification hooks to run in the work buffer. For
instance, directory_files_internal assumes that file decoding
doesn't compile new regexps. */
Fset (Fmake_local_variable (Qinhibit_modification_hooks), Qt);
Ferase_buffer ();
bset_undo_list (current_buffer, Qt);
bset_enable_multibyte_characters (current_buffer, multibyte ? Qt : Qnil);
if (EQ (workbuf, Vcode_conversion_reused_workbuf))
reused_workbuf_in_use = 1;
set_buffer_internal (current);
}
return workbuf;
}
static void
coding_restore_undo_list (Lisp_Object arg)
{
Lisp_Object undo_list = XCAR (arg);
struct buffer *buf = XBUFFER (XCDR (arg));
bset_undo_list (buf, undo_list);
}
/* Decode the *last* BYTES of the gap and insert them at point. */
void
decode_coding_gap (struct coding_system *coding, ptrdiff_t bytes)
{
ptrdiff_t count = SPECPDL_INDEX ();
Lisp_Object attrs;
eassert (GPT_BYTE == PT_BYTE);
coding->src_object = Fcurrent_buffer ();
coding->src_chars = bytes;
coding->src_bytes = bytes;
coding->src_pos = -bytes;
coding->src_pos_byte = -bytes;
coding->src_multibyte = false;
coding->dst_object = coding->src_object;
coding->dst_pos = PT;
coding->dst_pos_byte = PT_BYTE;
eassert (coding->dst_multibyte
== !NILP (BVAR (current_buffer, enable_multibyte_characters)));
coding->head_ascii = -1;
coding->detected_utf8_bytes = coding->detected_utf8_chars = -1;
coding->eol_seen = EOL_SEEN_NONE;
if (CODING_REQUIRE_DETECTION (coding))
detect_coding (coding);
attrs = CODING_ID_ATTRS (coding->id);
if (! disable_ascii_optimization
&& ! coding->src_multibyte
&& ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))
&& NILP (CODING_ATTR_POST_READ (attrs))
&& NILP (get_translation_table (attrs, 0, NULL)))
{
ptrdiff_t chars = coding->head_ascii;
if (chars < 0)
chars = check_ascii (coding);
if (chars != bytes)
{
/* There exists a non-ASCII byte. */
if (EQ (CODING_ATTR_TYPE (attrs), Qutf_8)
&& coding->detected_utf8_bytes == coding->src_bytes)
{
if (coding->detected_utf8_chars >= 0)
chars = coding->detected_utf8_chars;
else
chars = check_utf_8 (coding);
if (CODING_UTF_8_BOM (coding) != utf_without_bom
&& coding->head_ascii == 0
&& coding->source[0] == UTF_8_BOM_1
&& coding->source[1] == UTF_8_BOM_2
&& coding->source[2] == UTF_8_BOM_3)
{
chars--;
bytes -= 3;
coding->src_bytes -= 3;
}
}
else
chars = -1;
}
if (chars >= 0)
{
Lisp_Object eol_type;
eol_type = CODING_ID_EOL_TYPE (coding->id);
if (VECTORP (eol_type))
{
if (coding->eol_seen != EOL_SEEN_NONE)
eol_type = adjust_coding_eol_type (coding, coding->eol_seen);
}
if (EQ (eol_type, Qmac))
{
unsigned char *src_end = GAP_END_ADDR;
unsigned char *src = src_end - coding->src_bytes;
while (src < src_end)
{
if (*src++ == '\r')
src[-1] = '\n';
}
}
else if (EQ (eol_type, Qdos))
{
unsigned char *src = GAP_END_ADDR;
unsigned char *src_beg = src - coding->src_bytes;
unsigned char *dst = src;
ptrdiff_t diff;
while (src_beg < src)
{
*--dst = *--src;
if (*src == '\n' && src > src_beg && src[-1] == '\r')
src--;
}
diff = dst - src;
bytes -= diff;
chars -= diff;
}
coding->produced = bytes;
coding->produced_char = chars;
insert_from_gap (chars, bytes, 1);
return;
}
}
code_conversion_save (0, 0);
coding->mode |= CODING_MODE_LAST_BLOCK;
current_buffer->text->inhibit_shrinking = 1;
decode_coding (coding);
current_buffer->text->inhibit_shrinking = 0;
if (! NILP (CODING_ATTR_POST_READ (attrs)))
{
ptrdiff_t prev_Z = Z, prev_Z_BYTE = Z_BYTE;
Lisp_Object val;
Lisp_Object undo_list = BVAR (current_buffer, undo_list);
record_unwind_protect (coding_restore_undo_list,
Fcons (undo_list, Fcurrent_buffer ()));
bset_undo_list (current_buffer, Qt);
TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte);
val = call1 (CODING_ATTR_POST_READ (attrs),
make_fixnum (coding->produced_char));
CHECK_FIXNAT (val);
coding->produced_char += Z - prev_Z;
coding->produced += Z_BYTE - prev_Z_BYTE;
}
unbind_to (count, Qnil);
}
/* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in
SRC_OBJECT into DST_OBJECT by coding context CODING.
SRC_OBJECT is a buffer, a string, or Qnil.
If it is a buffer, the text is at point of the buffer. FROM and TO
are positions in the buffer.
If it is a string, the text is at the beginning of the string.
FROM and TO are indices to the string.
If it is nil, the text is at coding->source. FROM and TO are
indices to coding->source.
DST_OBJECT is a buffer, Qt, or Qnil.
If it is a buffer, the decoded text is inserted at point of the
buffer. If the buffer is the same as SRC_OBJECT, the source text
is deleted.
If it is Qt, a string is made from the decoded text, and
set in CODING->dst_object.
If it is Qnil, the decoded text is stored at CODING->destination.
The caller must allocate CODING->dst_bytes bytes at
CODING->destination by xmalloc. If the decoded text is longer than
CODING->dst_bytes, CODING->destination is relocated by xrealloc.
*/
void
decode_coding_object (struct coding_system *coding,
Lisp_Object src_object,
ptrdiff_t from, ptrdiff_t from_byte,
ptrdiff_t to, ptrdiff_t to_byte,
Lisp_Object dst_object)
{
ptrdiff_t count = SPECPDL_INDEX ();
unsigned char *destination UNINIT;
ptrdiff_t dst_bytes UNINIT;
ptrdiff_t chars = to - from;
ptrdiff_t bytes = to_byte - from_byte;
Lisp_Object attrs;
ptrdiff_t saved_pt = -1, saved_pt_byte UNINIT;
bool need_marker_adjustment = 0;
Lisp_Object old_deactivate_mark;
old_deactivate_mark = Vdeactivate_mark;
if (NILP (dst_object))
{
destination = coding->destination;
dst_bytes = coding->dst_bytes;
}
coding->src_object = src_object;
coding->src_chars = chars;
coding->src_bytes = bytes;
coding->src_multibyte = chars < bytes;
if (STRINGP (src_object))
{
coding->src_pos = from;
coding->src_pos_byte = from_byte;
}
else if (BUFFERP (src_object))
{
set_buffer_internal (XBUFFER (src_object));
if (from != GPT)
move_gap_both (from, from_byte);
if (EQ (src_object, dst_object))
{
struct Lisp_Marker *tail;
for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next)
{
tail->need_adjustment
= tail->charpos == (tail->insertion_type ? from : to);
need_marker_adjustment |= tail->need_adjustment;
}
saved_pt = PT, saved_pt_byte = PT_BYTE;
TEMP_SET_PT_BOTH (from, from_byte);
current_buffer->text->inhibit_shrinking = 1;
del_range_both (from, from_byte, to, to_byte, 1);
coding->src_pos = -chars;
coding->src_pos_byte = -bytes;
}
else
{
coding->src_pos = from;
coding->src_pos_byte = from_byte;
}
}
if (CODING_REQUIRE_DETECTION (coding))
detect_coding (coding);
attrs = CODING_ID_ATTRS (coding->id);
if (EQ (dst_object, Qt)
|| (! NILP (CODING_ATTR_POST_READ (attrs))
&& NILP (dst_object)))
{
coding->dst_multibyte = !CODING_FOR_UNIBYTE (coding);
coding->dst_object = code_conversion_save (1, coding->dst_multibyte);
coding->dst_pos = BEG;
coding->dst_pos_byte = BEG_BYTE;
}
else if (BUFFERP (dst_object))
{
code_conversion_save (0, 0);
coding->dst_object = dst_object;
coding->dst_pos = BUF_PT (XBUFFER (dst_object));
coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object));
coding->dst_multibyte
= ! NILP (BVAR (XBUFFER (dst_object), enable_multibyte_characters));
}
else
{
code_conversion_save (0, 0);
coding->dst_object = Qnil;
/* Most callers presume this will return a multibyte result, and they
won't use `binary' or `raw-text' anyway, so let's not worry about
CODING_FOR_UNIBYTE. */
coding->dst_multibyte = 1;
}
decode_coding (coding);
if (BUFFERP (coding->dst_object))
set_buffer_internal (XBUFFER (coding->dst_object));
if (! NILP (CODING_ATTR_POST_READ (attrs)))
{
ptrdiff_t prev_Z = Z, prev_Z_BYTE = Z_BYTE;
Lisp_Object val;
Lisp_Object undo_list = BVAR (current_buffer, undo_list);
ptrdiff_t count1 = SPECPDL_INDEX ();
record_unwind_protect (coding_restore_undo_list,
Fcons (undo_list, Fcurrent_buffer ()));
bset_undo_list (current_buffer, Qt);
TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte);
val = safe_call1 (CODING_ATTR_POST_READ (attrs),
make_fixnum (coding->produced_char));
CHECK_FIXNAT (val);
coding->produced_char += Z - prev_Z;
coding->produced += Z_BYTE - prev_Z_BYTE;
unbind_to (count1, Qnil);
}
if (EQ (dst_object, Qt))
{
coding->dst_object = Fbuffer_string ();
}
else if (NILP (dst_object) && BUFFERP (coding->dst_object))
{
set_buffer_internal (XBUFFER (coding->dst_object));
if (dst_bytes < coding->produced)
{
eassert (coding->produced > 0);
destination = xrealloc (destination, coding->produced);
if (BEGV < GPT && GPT < BEGV + coding->produced_char)
move_gap_both (BEGV, BEGV_BYTE);
memcpy (destination, BEGV_ADDR, coding->produced);
coding->destination = destination;
}
}
if (saved_pt >= 0)
{
/* This is the case of:
(BUFFERP (src_object) && EQ (src_object, dst_object))
As we have moved PT while replacing the original buffer
contents, we must recover it now. */
set_buffer_internal (XBUFFER (src_object));
current_buffer->text->inhibit_shrinking = 0;
if (saved_pt < from)
TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte);
else if (saved_pt < from + chars)
TEMP_SET_PT_BOTH (from, from_byte);
else if (! NILP (BVAR (current_buffer, enable_multibyte_characters)))
TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars),
saved_pt_byte + (coding->produced - bytes));
else
TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes),
saved_pt_byte + (coding->produced - bytes));
if (need_marker_adjustment)
{
struct Lisp_Marker *tail;
for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next)
if (tail->need_adjustment)
{
tail->need_adjustment = 0;
if (tail->insertion_type)
{
tail->bytepos = from_byte;
tail->charpos = from;
}
else
{
tail->bytepos = from_byte + coding->produced;
tail->charpos
= (NILP (BVAR (current_buffer, enable_multibyte_characters))
? tail->bytepos : from + coding->produced_char);
}
}
}
}
Vdeactivate_mark = old_deactivate_mark;
unbind_to (count, coding->dst_object);
}
void
encode_coding_object (struct coding_system *coding,
Lisp_Object src_object,
ptrdiff_t from, ptrdiff_t from_byte,
ptrdiff_t to, ptrdiff_t to_byte,
Lisp_Object dst_object)
{
ptrdiff_t count = SPECPDL_INDEX ();
ptrdiff_t chars = to - from;
ptrdiff_t bytes = to_byte - from_byte;
Lisp_Object attrs;
ptrdiff_t saved_pt = -1, saved_pt_byte;
bool need_marker_adjustment = 0;
bool kill_src_buffer = 0;
Lisp_Object old_deactivate_mark;
old_deactivate_mark = Vdeactivate_mark;
coding->src_object = src_object;
coding->src_chars = chars;
coding->src_bytes = bytes;
coding->src_multibyte = chars < bytes;
attrs = CODING_ID_ATTRS (coding->id);
if (EQ (src_object, dst_object))
{
struct Lisp_Marker *tail;
for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next)
{
tail->need_adjustment
= tail->charpos == (tail->insertion_type ? from : to);
need_marker_adjustment |= tail->need_adjustment;
}
}
if (! NILP (CODING_ATTR_PRE_WRITE (attrs)))
{
coding->src_object = code_conversion_save (1, coding->src_multibyte);
set_buffer_internal (XBUFFER (coding->src_object));
if (STRINGP (src_object))
insert_from_string (src_object, from, from_byte, chars, bytes, 0);
else if (BUFFERP (src_object))
insert_from_buffer (XBUFFER (src_object), from, chars, 0);
else
insert_1_both ((char *) coding->source + from, chars, bytes, 0, 0, 0);
if (EQ (src_object, dst_object))
{
set_buffer_internal (XBUFFER (src_object));
saved_pt = PT, saved_pt_byte = PT_BYTE;
del_range_both (from, from_byte, to, to_byte, 1);
set_buffer_internal (XBUFFER (coding->src_object));
}
safe_call2 (CODING_ATTR_PRE_WRITE (attrs),
make_fixnum (BEG), make_fixnum (Z));
if (XBUFFER (coding->src_object) != current_buffer)
kill_src_buffer = 1;
coding->src_object = Fcurrent_buffer ();
if (BEG != GPT)
move_gap_both (BEG, BEG_BYTE);
coding->src_chars = Z - BEG;
coding->src_bytes = Z_BYTE - BEG_BYTE;
coding->src_pos = BEG;
coding->src_pos_byte = BEG_BYTE;
coding->src_multibyte = Z < Z_BYTE;
}
else if (STRINGP (src_object))
{
code_conversion_save (0, 0);
coding->src_pos = from;
coding->src_pos_byte = from_byte;
}
else if (BUFFERP (src_object))
{
code_conversion_save (0, 0);
set_buffer_internal (XBUFFER (src_object));
if (EQ (src_object, dst_object))
{
saved_pt = PT, saved_pt_byte = PT_BYTE;
coding->src_object = del_range_1 (from, to, 1, 1);
coding->src_pos = 0;
coding->src_pos_byte = 0;
}
else
{
if (from < GPT && to >= GPT)
move_gap_both (from, from_byte);
coding->src_pos = from;
coding->src_pos_byte = from_byte;
}
}
else
{
code_conversion_save (0, 0);
coding->src_pos = from;
coding->src_pos_byte = from_byte;
}
if (BUFFERP (dst_object))
{
coding->dst_object = dst_object;
if (EQ (src_object, dst_object))
{
coding->dst_pos = from;
coding->dst_pos_byte = from_byte;
}
else
{
struct buffer *current = current_buffer;
set_buffer_temp (XBUFFER (dst_object));
coding->dst_pos = PT;
coding->dst_pos_byte = PT_BYTE;
move_gap_both (coding->dst_pos, coding->dst_pos_byte);
set_buffer_temp (current);
}
coding->dst_multibyte
= ! NILP (BVAR (XBUFFER (dst_object), enable_multibyte_characters));
}
else if (EQ (dst_object, Qt))
{
ptrdiff_t dst_bytes = max (1, coding->src_chars);
coding->dst_object = Qnil;
coding->destination = xmalloc (dst_bytes);
coding->dst_bytes = dst_bytes;
coding->dst_multibyte = 0;
}
else
{
coding->dst_object = Qnil;
coding->dst_multibyte = 0;
}
encode_coding (coding);
if (EQ (dst_object, Qt))
{
if (BUFFERP (coding->dst_object))
coding->dst_object = Fbuffer_string ();
else if (coding->raw_destination)
/* This is used to avoid creating huge Lisp string.
NOTE: caller who sets `raw_destination' is also
responsible for freeing `destination' buffer. */
coding->dst_object = Qnil;
else
{
coding->dst_object
= make_unibyte_string ((char *) coding->destination,
coding->produced);
xfree (coding->destination);
}
}
if (saved_pt >= 0)
{
/* This is the case of:
(BUFFERP (src_object) && EQ (src_object, dst_object))
As we have moved PT while replacing the original buffer
contents, we must recover it now. */
set_buffer_internal (XBUFFER (src_object));
if (saved_pt < from)
TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte);
else if (saved_pt < from + chars)
TEMP_SET_PT_BOTH (from, from_byte);
else if (! NILP (BVAR (current_buffer, enable_multibyte_characters)))
TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars),
saved_pt_byte + (coding->produced - bytes));
else
TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes),
saved_pt_byte + (coding->produced - bytes));
if (need_marker_adjustment)
{
struct Lisp_Marker *tail;
for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next)
if (tail->need_adjustment)
{
tail->need_adjustment = 0;
if (tail->insertion_type)
{
tail->bytepos = from_byte;
tail->charpos = from;
}
else
{
tail->bytepos = from_byte + coding->produced;
tail->charpos
= (NILP (BVAR (current_buffer, enable_multibyte_characters))
? tail->bytepos : from + coding->produced_char);
}
}
}
}
if (kill_src_buffer)
Fkill_buffer (coding->src_object);
Vdeactivate_mark = old_deactivate_mark;
unbind_to (count, Qnil);
}
Lisp_Object
preferred_coding_system (void)
{
int id = coding_categories[coding_priorities[0]].id;
return CODING_ID_NAME (id);
}
#if defined (WINDOWSNT) || defined (CYGWIN)
Lisp_Object
from_unicode (Lisp_Object str)
{
CHECK_STRING (str);
if (!STRING_MULTIBYTE (str) &&
SBYTES (str) & 1)
{
str = Fsubstring (str, make_fixnum (0), make_fixnum (-1));
}
return code_convert_string_norecord (str, Qutf_16le, 0);
}
Lisp_Object
from_unicode_buffer (const wchar_t *wstr)
{
/* We get one of the two final NUL bytes for free. */
ptrdiff_t len = 1 + sizeof (wchar_t) * wcslen (wstr);
AUTO_STRING_WITH_LEN (str, (char *) wstr, len);
return from_unicode (str);
}
wchar_t *
to_unicode (Lisp_Object str, Lisp_Object *buf)
{
*buf = code_convert_string_norecord (str, Qutf_16le, 1);
/* We need to make another copy (in addition to the one made by
code_convert_string_norecord) to ensure that the final string is
_doubly_ zero terminated --- that is, that the string is
terminated by two zero bytes and one utf-16le NUL character.
Because strings are already terminated with a single zero byte,
we just add one additional zero. */
str = make_uninit_string (SBYTES (*buf) + 1);
memcpy (SDATA (str), SDATA (*buf), SBYTES (*buf));
SDATA (str) [SBYTES (*buf)] = '\0';
*buf = str;
return WCSDATA (*buf);
}
#endif /* WINDOWSNT || CYGWIN */
\f
/*** 8. Emacs Lisp library functions ***/
DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0,
doc: /* Return t if OBJECT is nil or a coding-system.
See the documentation of `define-coding-system' for information
about coding-system objects. */)
(Lisp_Object object)
{
if (NILP (object)
|| CODING_SYSTEM_ID (object) >= 0)
return Qt;
if (! SYMBOLP (object)
|| NILP (Fget (object, Qcoding_system_define_form)))
return Qnil;
return Qt;
}
DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system,
Sread_non_nil_coding_system, 1, 1, 0,
doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */)
(Lisp_Object prompt)
{
Lisp_Object val;
do
{
val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil,
Qt, Qnil, Qcoding_system_history, Qnil, Qnil);
}
while (SCHARS (val) == 0);
return (Fintern (val, Qnil));
}
DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0,
doc: /* Read a coding system from the minibuffer, prompting with string PROMPT.
If the user enters null input, return second argument DEFAULT-CODING-SYSTEM.
Ignores case when completing coding systems (all Emacs coding systems
are lower-case). */)
(Lisp_Object prompt, Lisp_Object default_coding_system)
{
Lisp_Object val;
ptrdiff_t count = SPECPDL_INDEX ();
if (SYMBOLP (default_coding_system))
default_coding_system = SYMBOL_NAME (default_coding_system);
specbind (Qcompletion_ignore_case, Qt);
val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil,
Qt, Qnil, Qcoding_system_history,
default_coding_system, Qnil);
val = unbind_to (count, val);
return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil));
}
DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system,
1, 1, 0,
doc: /* Check validity of CODING-SYSTEM.
If valid, return CODING-SYSTEM, else signal a `coding-system-error' error.
It is valid if it is nil or a symbol defined as a coding system by the
function `define-coding-system'. */)
(Lisp_Object coding_system)
{
Lisp_Object define_form;
define_form = Fget (coding_system, Qcoding_system_define_form);
if (! NILP (define_form))
{
Fput (coding_system, Qcoding_system_define_form, Qnil);
safe_eval (define_form);
}
if (!NILP (Fcoding_system_p (coding_system)))
return coding_system;
xsignal1 (Qcoding_system_error, coding_system);
}
\f
/* Detect how the bytes at SRC of length SRC_BYTES are encoded. If
HIGHEST, return the coding system of the highest
priority among the detected coding systems. Otherwise return a
list of detected coding systems sorted by their priorities. If
MULTIBYTEP, it is assumed that the bytes are in correct
multibyte form but contains only ASCII and eight-bit chars.
Otherwise, the bytes are raw bytes.
CODING-SYSTEM controls the detection as below:
If it is nil, detect both text-format and eol-format. If the
text-format part of CODING-SYSTEM is already specified
(e.g. `iso-latin-1'), detect only eol-format. If the eol-format
part of CODING-SYSTEM is already specified (e.g. `undecided-unix'),
detect only text-format. */
Lisp_Object
detect_coding_system (const unsigned char *src,
ptrdiff_t src_chars, ptrdiff_t src_bytes,
bool highest, bool multibytep,
Lisp_Object coding_system)
{
const unsigned char *src_end = src + src_bytes;
Lisp_Object attrs, eol_type;
Lisp_Object val = Qnil;
struct coding_system coding;
ptrdiff_t id;
struct coding_detection_info detect_info;
enum coding_category base_category;
bool nul_byte_found = 0, eight_bit_found = 0;
if (NILP (coding_system))
coding_system = Qundecided;
setup_coding_system (coding_system, &coding);
attrs = CODING_ID_ATTRS (coding.id);
eol_type = CODING_ID_EOL_TYPE (coding.id);
coding_system = CODING_ATTR_BASE_NAME (attrs);
coding.source = src;
coding.src_chars = src_chars;
coding.src_bytes = src_bytes;
coding.src_multibyte = multibytep;
coding.consumed = 0;
coding.mode |= CODING_MODE_LAST_BLOCK;
coding.head_ascii = 0;
detect_info.checked = detect_info.found = detect_info.rejected = 0;
/* At first, detect text-format if necessary. */
base_category = XFIXNUM (CODING_ATTR_CATEGORY (attrs));
if (base_category == coding_category_undecided)
{
enum coding_category category UNINIT;
struct coding_system *this UNINIT;
int c, i;
bool inhibit_nbd = inhibit_flag (coding.spec.undecided.inhibit_nbd,
inhibit_nul_byte_detection);
bool inhibit_ied = inhibit_flag (coding.spec.undecided.inhibit_ied,
inhibit_iso_escape_detection);
bool prefer_utf_8 = coding.spec.undecided.prefer_utf_8;
/* Skip all ASCII bytes except for a few ISO2022 controls. */
for (; src < src_end; src++)
{
c = *src;
if (c & 0x80)
{
eight_bit_found = 1;
if (nul_byte_found)
break;
}
else if (c < 0x20)
{
if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)
&& ! inhibit_ied
&& ! detect_info.checked)
{
if (detect_coding_iso_2022 (&coding, &detect_info))
{
/* We have scanned the whole data. */
if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE))
{
/* We didn't find an 8-bit code. We may
have found a NUL-byte, but it's very
rare that a binary file confirm to
ISO-2022. */
src = src_end;
coding.head_ascii = src - coding.source;
}
detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE;
break;
}
}
else if (! c && !inhibit_nbd)
{
nul_byte_found = 1;
if (eight_bit_found)
break;
}
if (! eight_bit_found)
coding.head_ascii++;
}
else if (! eight_bit_found)
coding.head_ascii++;
}
if (nul_byte_found || eight_bit_found
|| coding.head_ascii < coding.src_bytes
|| detect_info.found)
{
if (coding.head_ascii == coding.src_bytes)
/* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */
for (i = 0; i < coding_category_raw_text; i++)
{
category = coding_priorities[i];
this = coding_categories + category;
if (detect_info.found & (1 << category))
break;
}
else
{
if (nul_byte_found)
{
detect_info.checked |= ~CATEGORY_MASK_UTF_16;
detect_info.rejected |= ~CATEGORY_MASK_UTF_16;
}
else if (prefer_utf_8
&& detect_coding_utf_8 (&coding, &detect_info))
{
detect_info.checked |= ~CATEGORY_MASK_UTF_8;
detect_info.rejected |= ~CATEGORY_MASK_UTF_8;
}
for (i = 0; i < coding_category_raw_text; i++)
{
category = coding_priorities[i];
this = coding_categories + category;
if (this->id < 0)
{
/* No coding system of this category is defined. */
detect_info.rejected |= (1 << category);
}
else if (category >= coding_category_raw_text)
continue;
else if (detect_info.checked & (1 << category))
{
if (highest
&& (detect_info.found & (1 << category)))
break;
}
else if ((*(this->detector)) (&coding, &detect_info)
&& highest
&& (detect_info.found & (1 << category)))
{
if (category == coding_category_utf_16_auto)
{
if (detect_info.found & CATEGORY_MASK_UTF_16_LE)
category = coding_category_utf_16_le;
else
category = coding_category_utf_16_be;
}
break;
}
}
}
}
if ((detect_info.rejected & CATEGORY_MASK_ANY) == CATEGORY_MASK_ANY
|| nul_byte_found)
{
detect_info.found = CATEGORY_MASK_RAW_TEXT;
id = CODING_SYSTEM_ID (Qno_conversion);
val = list1i (id);
}
else if (! detect_info.rejected && ! detect_info.found)
{
detect_info.found = CATEGORY_MASK_ANY;
id = coding_categories[coding_category_undecided].id;
val = list1i (id);
}
else if (highest)
{
if (detect_info.found)
{
detect_info.found = 1 << category;
val = list1i (this->id);
}
else
for (i = 0; i < coding_category_raw_text; i++)
if (! (detect_info.rejected & (1 << coding_priorities[i])))
{
detect_info.found = 1 << coding_priorities[i];
id = coding_categories[coding_priorities[i]].id;
val = list1i (id);
break;
}
}
else
{
int mask = detect_info.rejected | detect_info.found;
int found = 0;
for (i = coding_category_raw_text - 1; i >= 0; i--)
{
category = coding_priorities[i];
if (! (mask & (1 << category)))
{
found |= 1 << category;
id = coding_categories[category].id;
if (id >= 0)
val = list1i (id);
}
}
for (i = coding_category_raw_text - 1; i >= 0; i--)
{
category = coding_priorities[i];
if (detect_info.found & (1 << category))
{
id = coding_categories[category].id;
val = Fcons (make_fixnum (id), val);
}
}
detect_info.found |= found;
}
}
else if (base_category == coding_category_utf_8_auto)
{
if (detect_coding_utf_8 (&coding, &detect_info))
{
struct coding_system *this;
if (detect_info.found & CATEGORY_MASK_UTF_8_SIG)
this = coding_categories + coding_category_utf_8_sig;
else
this = coding_categories + coding_category_utf_8_nosig;
val = list1i (this->id);
}
}
else if (base_category == coding_category_utf_16_auto)
{
if (detect_coding_utf_16 (&coding, &detect_info))
{
struct coding_system *this;
if (detect_info.found & CATEGORY_MASK_UTF_16_LE)
this = coding_categories + coding_category_utf_16_le;
else if (detect_info.found & CATEGORY_MASK_UTF_16_BE)
this = coding_categories + coding_category_utf_16_be;
else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG)
this = coding_categories + coding_category_utf_16_be_nosig;
else
this = coding_categories + coding_category_utf_16_le_nosig;
val = list1i (this->id);
}
}
else
{
detect_info.found = 1 << XFIXNUM (CODING_ATTR_CATEGORY (attrs));
val = list1i (coding.id);
}
/* Then, detect eol-format if necessary. */
{
int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol = -1;
Lisp_Object tail;
if (VECTORP (eol_type))
{
if (detect_info.found & ~CATEGORY_MASK_UTF_16)
{
if (nul_byte_found)
normal_eol = EOL_SEEN_LF;
else
normal_eol = detect_eol (coding.source, src_bytes,
coding_category_raw_text);
}
if (detect_info.found & (CATEGORY_MASK_UTF_16_BE
| CATEGORY_MASK_UTF_16_BE_NOSIG))
utf_16_be_eol = detect_eol (coding.source, src_bytes,
coding_category_utf_16_be);
if (detect_info.found & (CATEGORY_MASK_UTF_16_LE
| CATEGORY_MASK_UTF_16_LE_NOSIG))
utf_16_le_eol = detect_eol (coding.source, src_bytes,
coding_category_utf_16_le);
}
else
{
if (EQ (eol_type, Qunix))
normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF;
else if (EQ (eol_type, Qdos))
normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF;
else
normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR;
}
for (tail = val; CONSP (tail); tail = XCDR (tail))
{
enum coding_category category;
int this_eol;
id = XFIXNUM (XCAR (tail));
attrs = CODING_ID_ATTRS (id);
category = XFIXNUM (CODING_ATTR_CATEGORY (attrs));
eol_type = CODING_ID_EOL_TYPE (id);
if (VECTORP (eol_type))
{
if (category == coding_category_utf_16_be
|| category == coding_category_utf_16_be_nosig)
this_eol = utf_16_be_eol;
else if (category == coding_category_utf_16_le
|| category == coding_category_utf_16_le_nosig)
this_eol = utf_16_le_eol;
else
this_eol = normal_eol;
if (this_eol == EOL_SEEN_LF)
XSETCAR (tail, AREF (eol_type, 0));
else if (this_eol == EOL_SEEN_CRLF)
XSETCAR (tail, AREF (eol_type, 1));
else if (this_eol == EOL_SEEN_CR)
XSETCAR (tail, AREF (eol_type, 2));
else
XSETCAR (tail, CODING_ID_NAME (id));
}
else
XSETCAR (tail, CODING_ID_NAME (id));
}
}
return (highest ? (CONSP (val) ? XCAR (val) : Qnil) : val);
}
DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region,
2, 3, 0,
doc: /* Detect coding system of the text in the region between START and END.
Return a list of possible coding systems ordered by priority.
The coding systems to try and their priorities follows what
the function `coding-system-priority-list' (which see) returns.
If only ASCII characters are found (except for such ISO-2022 control
characters as ESC), it returns a list of single element `undecided'
or its subsidiary coding system according to a detected end-of-line
format.
If optional argument HIGHEST is non-nil, return the coding system of
highest priority. */)
(Lisp_Object start, Lisp_Object end, Lisp_Object highest)
{
ptrdiff_t from, to;
ptrdiff_t from_byte, to_byte;
validate_region (&start, &end);
from = XFIXNUM (start), to = XFIXNUM (end);
from_byte = CHAR_TO_BYTE (from);
to_byte = CHAR_TO_BYTE (to);
if (from < GPT && to >= GPT)
move_gap_both (to, to_byte);
return detect_coding_system (BYTE_POS_ADDR (from_byte),
to - from, to_byte - from_byte,
!NILP (highest),
!NILP (BVAR (current_buffer
, enable_multibyte_characters)),
Qnil);
}
DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string,
1, 2, 0,
doc: /* Detect coding system of the text in STRING.
Return a list of possible coding systems ordered by priority.
The coding systems to try and their priorities follows what
the function `coding-system-priority-list' (which see) returns.
If only ASCII characters are found (except for such ISO-2022 control
characters as ESC), it returns a list of single element `undecided'
or its subsidiary coding system according to a detected end-of-line
format.
If optional argument HIGHEST is non-nil, return the coding system of
highest priority. */)
(Lisp_Object string, Lisp_Object highest)
{
CHECK_STRING (string);
return detect_coding_system (SDATA (string),
SCHARS (string), SBYTES (string),
!NILP (highest), STRING_MULTIBYTE (string),
Qnil);
}
static bool
char_encodable_p (int c, Lisp_Object attrs)
{
Lisp_Object tail;
struct charset *charset;
Lisp_Object translation_table;
translation_table = CODING_ATTR_TRANS_TBL (attrs);
if (! NILP (translation_table))
c = translate_char (translation_table, c);
for (tail = CODING_ATTR_CHARSET_LIST (attrs);
CONSP (tail); tail = XCDR (tail))
{
charset = CHARSET_FROM_ID (XFIXNUM (XCAR (tail)));
if (CHAR_CHARSET_P (c, charset))
break;
}
return (! NILP (tail));
}
/* Return a list of coding systems that safely encode the text between
START and END. If EXCLUDE is non-nil, it is a list of coding
systems not to check. The returned list doesn't contain any such
coding systems. In any case, if the text contains only ASCII or is
unibyte, return t. */
DEFUN ("find-coding-systems-region-internal",
Ffind_coding_systems_region_internal,
Sfind_coding_systems_region_internal, 2, 3, 0,
doc: /* Internal use only. */)
(Lisp_Object start, Lisp_Object end, Lisp_Object exclude)
{
Lisp_Object coding_attrs_list, safe_codings;
ptrdiff_t start_byte, end_byte;
const unsigned char *p, *pbeg, *pend;
int c;
Lisp_Object tail, elt, work_table;
if (STRINGP (start))
{
if (!STRING_MULTIBYTE (start)
|| SCHARS (start) == SBYTES (start))
return Qt;
start_byte = 0;
end_byte = SBYTES (start);
}
else
{
EMACS_INT s = fix_position (start);
EMACS_INT e = fix_position (end);
if (! (BEG <= s && s <= e && e <= Z))
args_out_of_range (start, end);
if (NILP (BVAR (current_buffer, enable_multibyte_characters)))
return Qt;
start_byte = CHAR_TO_BYTE (s);
end_byte = CHAR_TO_BYTE (e);
if (e - s == end_byte - start_byte)
return Qt;
if (s < GPT && GPT < e)
{
if (GPT - s < e - GPT)
move_gap_both (s, start_byte);
else
move_gap_both (e, end_byte);
}
}
coding_attrs_list = Qnil;
for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail))
if (NILP (exclude)
|| NILP (Fmemq (XCAR (tail), exclude)))
{
Lisp_Object attrs;
attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0);
if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)))
{
ASET (attrs, coding_attr_trans_tbl,
get_translation_table (attrs, 1, NULL));
coding_attrs_list = Fcons (attrs, coding_attrs_list);
}
}
if (STRINGP (start))
p = pbeg = SDATA (start);
else
p = pbeg = BYTE_POS_ADDR (start_byte);
pend = p + (end_byte - start_byte);
while (p < pend && ASCII_CHAR_P (*p)) p++;
while (p < pend && ASCII_CHAR_P (*(pend - 1))) pend--;
work_table = Fmake_char_table (Qnil, Qnil);
while (p < pend)
{
if (ASCII_CHAR_P (*p))
p++;
else
{
c = string_char_advance (&p);
if (!NILP (char_table_ref (work_table, c)))
/* This character was already checked. Ignore it. */
continue;
charset_map_loaded = 0;
for (tail = coding_attrs_list; CONSP (tail);)
{
elt = XCAR (tail);
if (NILP (elt))
tail = XCDR (tail);
else if (char_encodable_p (c, elt))
tail = XCDR (tail);
else if (CONSP (XCDR (tail)))
{
XSETCAR (tail, XCAR (XCDR (tail)));
XSETCDR (tail, XCDR (XCDR (tail)));
}
else
{
XSETCAR (tail, Qnil);
tail = XCDR (tail);
}
}
if (charset_map_loaded)
{
ptrdiff_t p_offset = p - pbeg, pend_offset = pend - pbeg;
if (STRINGP (start))
pbeg = SDATA (start);
else
pbeg = BYTE_POS_ADDR (start_byte);
p = pbeg + p_offset;
pend = pbeg + pend_offset;
}
char_table_set (work_table, c, Qt);
}
}
safe_codings = list2 (Qraw_text, Qno_conversion);
for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail))
if (! NILP (XCAR (tail)))
safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings);
return safe_codings;
}
DEFUN ("unencodable-char-position", Funencodable_char_position,
Sunencodable_char_position, 3, 5, 0,
doc: /* Return position of first un-encodable character in a region.
START and END specify the region and CODING-SYSTEM specifies the
encoding to check. Return nil if CODING-SYSTEM does encode the region.
If optional 4th argument COUNT is non-nil, it specifies at most how
many un-encodable characters to search. In this case, the value is a
list of positions.
If optional 5th argument STRING is non-nil, it is a string to search
for un-encodable characters. In that case, START and END are indexes
to the string and treated as in `substring'. */)
(Lisp_Object start, Lisp_Object end, Lisp_Object coding_system,
Lisp_Object count, Lisp_Object string)
{
EMACS_INT n;
struct coding_system coding;
Lisp_Object attrs, charset_list, translation_table;
Lisp_Object positions;
ptrdiff_t from, to;
const unsigned char *p, *stop, *pend;
bool ascii_compatible;
setup_coding_system (Fcheck_coding_system (coding_system), &coding);
attrs = CODING_ID_ATTRS (coding.id);
if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text))
return Qnil;
ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs));
charset_list = CODING_ATTR_CHARSET_LIST (attrs);
translation_table = get_translation_table (attrs, 1, NULL);
if (NILP (string))
{
validate_region (&start, &end);
from = XFIXNUM (start);
to = XFIXNUM (end);
if (NILP (BVAR (current_buffer, enable_multibyte_characters))
|| (ascii_compatible
&& (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from)))))
return Qnil;
p = CHAR_POS_ADDR (from);
pend = CHAR_POS_ADDR (to);
if (from < GPT && to >= GPT)
stop = GPT_ADDR;
else
stop = pend;
}
else
{
CHECK_STRING (string);
validate_subarray (string, start, end, SCHARS (string), &from, &to);
if (! STRING_MULTIBYTE (string))
return Qnil;
p = SDATA (string) + string_char_to_byte (string, from);
stop = pend = SDATA (string) + string_char_to_byte (string, to);
if (ascii_compatible && (to - from) == (pend - p))
return Qnil;
}
if (NILP (count))
n = 1;
else
{
CHECK_FIXNAT (count);
n = XFIXNUM (count);
}
positions = Qnil;
charset_map_loaded = 0;
while (1)
{
int c;
if (ascii_compatible)
while (p < stop && ASCII_CHAR_P (*p))
p++, from++;
if (p >= stop)
{
if (p >= pend)
break;
stop = pend;
p = GAP_END_ADDR;
}
c = string_char_advance (&p);
if (! (ASCII_CHAR_P (c) && ascii_compatible)
&& ! char_charset (translate_char (translation_table, c),
charset_list, NULL))
{
positions = Fcons (make_fixnum (from), positions);
n--;
if (n == 0)
break;
}
from++;
if (charset_map_loaded && NILP (string))
{
p = CHAR_POS_ADDR (from);
pend = CHAR_POS_ADDR (to);
if (from < GPT && to >= GPT)
stop = GPT_ADDR;
else
stop = pend;
charset_map_loaded = 0;
}
}
return (NILP (count) ? Fcar (positions) : Fnreverse (positions));
}
DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region,
Scheck_coding_systems_region, 3, 3, 0,
doc: /* Check if text between START and END is encodable by CODING-SYSTEM-LIST.
START and END are buffer positions specifying the region.
CODING-SYSTEM-LIST is a list of coding systems to check.
If all coding systems in CODING-SYSTEM-LIST can encode the region, the
function returns nil.
If some of the coding systems cannot encode the whole region, value is
an alist, each element of which has the form (CODING-SYSTEM POS1 POS2 ...),
which means that CODING-SYSTEM cannot encode the text at buffer positions
POS1, POS2, ...
START may be a string. In that case, check if the string is
encodable, and the value contains character indices into the string
instead of buffer positions. END is ignored in this case.
If the current buffer (or START if it is a string) is unibyte, the value
is nil. */)
(Lisp_Object start, Lisp_Object end, Lisp_Object coding_system_list)
{
Lisp_Object list;
ptrdiff_t start_byte, end_byte;
ptrdiff_t pos;
const unsigned char *p, *pbeg, *pend;
int c;
Lisp_Object tail, elt, attrs;
if (STRINGP (start))
{
if (!STRING_MULTIBYTE (start)
|| SCHARS (start) == SBYTES (start))
return Qnil;
start_byte = 0;
end_byte = SBYTES (start);
pos = 0;
}
else
{
EMACS_INT s = fix_position (start);
EMACS_INT e = fix_position (end);
if (! (BEG <= s && s <= e && e <= Z))
args_out_of_range (start, end);
if (NILP (BVAR (current_buffer, enable_multibyte_characters)))
return Qnil;
start_byte = CHAR_TO_BYTE (s);
end_byte = CHAR_TO_BYTE (e);
if (e - s == end_byte - start_byte)
return Qnil;
if (s < GPT && GPT < e)
{
if (GPT - s < e - GPT)
move_gap_both (s, start_byte);
else
move_gap_both (e, end_byte);
}
pos = s;
}
list = Qnil;
for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail))
{
elt = XCAR (tail);
Lisp_Object spec = CODING_SYSTEM_SPEC (elt);
if (!VECTORP (spec))
xsignal1 (Qcoding_system_error, elt);
attrs = AREF (spec, 0);
ASET (attrs, coding_attr_trans_tbl,
get_translation_table (attrs, 1, NULL));
list = Fcons (list2 (elt, attrs), list);
}
if (STRINGP (start))
p = pbeg = SDATA (start);
else
p = pbeg = BYTE_POS_ADDR (start_byte);
pend = p + (end_byte - start_byte);
while (p < pend && ASCII_CHAR_P (*p)) p++, pos++;
while (p < pend && ASCII_CHAR_P (*(pend - 1))) pend--;
while (p < pend)
{
if (ASCII_CHAR_P (*p))
p++;
else
{
c = string_char_advance (&p);
charset_map_loaded = 0;
for (tail = list; CONSP (tail); tail = XCDR (tail))
{
elt = XCDR (XCAR (tail));
if (! char_encodable_p (c, XCAR (elt)))
XSETCDR (elt, Fcons (make_fixnum (pos), XCDR (elt)));
}
if (charset_map_loaded)
{
ptrdiff_t p_offset = p - pbeg, pend_offset = pend - pbeg;
if (STRINGP (start))
pbeg = SDATA (start);
else
pbeg = BYTE_POS_ADDR (start_byte);
p = pbeg + p_offset;
pend = pbeg + pend_offset;
}
}
pos++;
}
tail = list;
list = Qnil;
for (; CONSP (tail); tail = XCDR (tail))
{
elt = XCAR (tail);
if (CONSP (XCDR (XCDR (elt))))
list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))),
list);
}
return list;
}
static Lisp_Object
code_convert_region (Lisp_Object start, Lisp_Object end,
Lisp_Object coding_system, Lisp_Object dst_object,
bool encodep, bool norecord)
{
struct coding_system coding;
ptrdiff_t from, from_byte, to, to_byte;
Lisp_Object src_object;
if (NILP (coding_system))
coding_system = Qno_conversion;
else
CHECK_CODING_SYSTEM (coding_system);
src_object = Fcurrent_buffer ();
if (NILP (dst_object))
dst_object = src_object;
else if (! EQ (dst_object, Qt))
CHECK_BUFFER (dst_object);
validate_region (&start, &end);
from = XFIXNAT (start);
from_byte = CHAR_TO_BYTE (from);
to = XFIXNAT (end);
to_byte = CHAR_TO_BYTE (to);
setup_coding_system (coding_system, &coding);
coding.mode |= CODING_MODE_LAST_BLOCK;
if (BUFFERP (dst_object) && !EQ (dst_object, src_object))
{
struct buffer *buf = XBUFFER (dst_object);
ptrdiff_t buf_pt = BUF_PT (buf);
invalidate_buffer_caches (buf, buf_pt, buf_pt);
}
if (encodep)
encode_coding_object (&coding, src_object, from, from_byte, to, to_byte,
dst_object);
else
decode_coding_object (&coding, src_object, from, from_byte, to, to_byte,
dst_object);
if (! norecord)
Vlast_coding_system_used = CODING_ID_NAME (coding.id);
return (BUFFERP (dst_object)
? make_fixnum (coding.produced_char)
: coding.dst_object);
}
DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region,
3, 4, "r\nzCoding system: ",
doc: /* Decode the current region from the specified coding system.
What's meant by \"decoding\" is transforming bytes into text
(characters). If, for instance, you have a region that contains data
that represents the two bytes #xc2 #xa9, after calling this function
with the utf-8 coding system, the region will contain the single
character ?\\N{COPYRIGHT SIGN}.
When called from a program, takes four arguments:
START, END, CODING-SYSTEM, and DESTINATION.
START and END are buffer positions.
Optional 4th arguments DESTINATION specifies where the decoded text goes.
If nil, the region between START and END is replaced by the decoded text.
If buffer, the decoded text is inserted in that buffer after point (point
does not move). If that buffer is unibyte, it receives the individual
bytes of the internal representation of the decoded text.
In those cases, the length of the decoded text is returned.
If DESTINATION is t, the decoded text is returned.
This function sets `last-coding-system-used' to the precise coding system
used (which may be different from CODING-SYSTEM if CODING-SYSTEM is
not fully specified.) */)
(Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination)
{
return code_convert_region (start, end, coding_system, destination, 0, 0);
}
DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region,
3, 4, "r\nzCoding system: ",
doc: /* Encode the current region by specified coding system.
What's meant by \"encoding\" is transforming textual data (characters)
into bytes. If, for instance, you have a region that contains the
single character ?\\N{COPYRIGHT SIGN}, after calling this function with
the utf-8 coding system, the data in the region will represent the two
bytes #xc2 #xa9.
When called from a program, takes four arguments:
START, END, CODING-SYSTEM and DESTINATION.
START and END are buffer positions.
Optional 4th argument DESTINATION specifies where the encoded text goes.
If nil, the region between START and END is replaced by the encoded text.
If buffer, the encoded text is inserted in that buffer after point (point
does not move).
In those cases, the length of the encoded text is returned.
If DESTINATION is t, the encoded text is returned.
This function sets `last-coding-system-used' to the precise coding system
used (which may be different from CODING-SYSTEM if CODING-SYSTEM is
not fully specified.) */)
(Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination)
{
return code_convert_region (start, end, coding_system, destination, 1, 0);
}
/* Whether STRING only contains chars in the 0..127 range. */
static bool
string_ascii_p (Lisp_Object string)
{
ptrdiff_t nbytes = SBYTES (string);
for (ptrdiff_t i = 0; i < nbytes; i++)
if (SREF (string, i) > 127)
return false;
return true;
}
Lisp_Object
code_convert_string (Lisp_Object string, Lisp_Object coding_system,
Lisp_Object dst_object, bool encodep, bool nocopy,
bool norecord)
{
struct coding_system coding;
ptrdiff_t chars, bytes;
CHECK_STRING (string);
if (NILP (coding_system))
{
if (! norecord)
Vlast_coding_system_used = Qno_conversion;
if (NILP (dst_object))
return nocopy ? string : Fcopy_sequence (string);
}
if (NILP (coding_system))
coding_system = Qno_conversion;
else
CHECK_CODING_SYSTEM (coding_system);
if (NILP (dst_object))
dst_object = Qt;
else if (! EQ (dst_object, Qt))
CHECK_BUFFER (dst_object);
setup_coding_system (coding_system, &coding);
coding.mode |= CODING_MODE_LAST_BLOCK;
chars = SCHARS (string);
bytes = SBYTES (string);
if (EQ (dst_object, Qt))
{
/* Fast path for ASCII-only input and an ASCII-compatible coding:
act as identity if no EOL conversion is needed. */
Lisp_Object attrs = CODING_ID_ATTRS (coding.id);
if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))
&& (STRING_MULTIBYTE (string)
? (chars == bytes) : string_ascii_p (string))
&& (EQ (CODING_ID_EOL_TYPE (coding.id), Qunix)
|| inhibit_eol_conversion
|| ! memchr (SDATA (string), encodep ? '\n' : '\r', bytes)))
{
if (! norecord)
Vlast_coding_system_used = coding_system;
return (nocopy
? string
: (encodep
? make_unibyte_string (SSDATA (string), bytes)
: make_multibyte_string (SSDATA (string), bytes, bytes)));
}
}
else if (BUFFERP (dst_object))
{
struct buffer *buf = XBUFFER (dst_object);
ptrdiff_t buf_pt = BUF_PT (buf);
invalidate_buffer_caches (buf, buf_pt, buf_pt);
}
if (encodep)
encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object);
else
decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object);
if (! norecord)
Vlast_coding_system_used = CODING_ID_NAME (coding.id);
return (BUFFERP (dst_object)
? make_fixnum (coding.produced_char)
: coding.dst_object);
}
/* Encode or decode STRING according to CODING_SYSTEM.
Do not set Vlast_coding_system_used. */
Lisp_Object
code_convert_string_norecord (Lisp_Object string, Lisp_Object coding_system,
bool encodep)
{
return code_convert_string (string, coding_system, Qt, encodep, 0, 1);
}
/* Return the gap address of BUFFER. If the gap size is less than
NBYTES, enlarge the gap in advance. */
static unsigned char *
get_buffer_gap_address (Lisp_Object buffer, ptrdiff_t nbytes)
{
struct buffer *buf = XBUFFER (buffer);
if (BUF_GPT (buf) != BUF_PT (buf))
{
struct buffer *oldb = current_buffer;
current_buffer = buf;
move_gap_both (PT, PT_BYTE);
current_buffer = oldb;
}
if (BUF_GAP_SIZE (buf) < nbytes)
make_gap_1 (buf, nbytes);
return BUF_GPT_ADDR (buf);
}
/* Return a pointer to the byte sequence for C, and its byte length in
LEN. This function is used to get a byte sequence for HANDLE_8_BIT
and HANDLE_OVER_UNI arguments of encode_string_utf_8 and
decode_string_utf_8 when those arguments are given by
characters. */
static unsigned char *
get_char_bytes (int c, int *len)
{
/* Use two caches, since encode/decode_string_utf_8 are called
repeatedly with the same values for HANDLE_8_BIT and
HANDLE_OVER_UNI arguments. */
static int chars[2];
static unsigned char bytes[2][6];
static int nbytes[2];
static int last_index;
if (chars[last_index] == c)
{
*len = nbytes[last_index];
return bytes[last_index];
}
if (chars[1 - last_index] == c)
{
*len = nbytes[1 - last_index];
return bytes[1 - last_index];
}
last_index = 1 - last_index;
chars[last_index] = c;
*len = nbytes[last_index] = CHAR_STRING (c, bytes[last_index]);
return bytes[last_index];
}
/* Encode STRING by the coding system utf-8-unix.
This function is optimized for speed when the input string is
already a valid sequence of Unicode codepoints in the internal
representation, i.e. there are neither 8-bit raw bytes nor
characters beyond the Unicode range in the string's contents.
Ignore any :pre-write-conversion and :encode-translation-table
properties.
Assume that arguments have values as described below.
The validity must be enforced and ensured by the caller.
STRING is a multibyte string or an ASCII-only unibyte string.
BUFFER is a unibyte buffer or Qnil.
If BUFFER is a unibyte buffer, insert the encoded result
after point of the buffer, and return the number of
inserted characters. The caller should have made BUFFER ready for
modifying in advance (e.g., by calling invalidate_buffer_caches).
If BUFFER is nil, return a unibyte string from the encoded result.
If NOCOPY is non-zero, and if STRING contains only Unicode
characters (i.e., the encoding does not change the byte sequence),
return STRING even if it is multibyte. WARNING: This will return a
_multibyte_ string, something that callers might not expect, especially
if STRING is not pure-ASCII; only use NOCOPY non-zero if the caller
will only use the byte sequence of the encoded result accessed by
SDATA or SSDATA, and the original STRING will _not_ be modified after
the encoding. When in doubt, always pass NOCOPY as zero. You _have_
been warned!
HANDLE-8-BIT and HANDLE-OVER-UNI specify how to handle a non-Unicode
character in STRING. The former is for an eight-bit character (represented
by a 2-byte overlong sequence in a multibyte STRING). The latter is
for a codepoint beyond the end of the Unicode range (a character whose
code is greater than the maximum Unicode character 0x10FFFF, represented
by a 4 or 5-byte sequence in a multibyte STRING).
If these two arguments are unibyte strings (typically
"\357\277\275", the UTF-8 sequence for the Unicode REPLACEMENT
CHARACTER #xFFFD), encode a non-Unicode character into that
unibyte sequence.
If the two arguments are characters, encode a non-Unicode
character as the respective argument characters.
If they are Qignored, skip a non-Unicode character.
If HANDLE-8-BIT is Qt, encode eight-bit characters into single bytes
of the same value, like the usual Emacs encoding does.
If HANDLE-OVER-UNI is Qt, encode characters beyond the Unicode
range into the same 4 or 5-byte sequence as used by Emacs
internally, like the usual Emacs encoding does.
If the two arguments are Qnil, return Qnil if STRING has a
non-Unicode character. This allows the caller to signal an error
if such input strings are not allowed. */
Lisp_Object
encode_string_utf_8 (Lisp_Object string, Lisp_Object buffer,
bool nocopy, Lisp_Object handle_8_bit,
Lisp_Object handle_over_uni)
{
ptrdiff_t nchars = SCHARS (string), nbytes = SBYTES (string);
if (NILP (buffer) && nchars == nbytes && nocopy)
/* STRING contains only ASCII characters. */
return string;
ptrdiff_t num_8_bit = 0; /* number of eight-bit chars in STRING */
/* The following two vars are counted only if handle_over_uni is not Qt. */
ptrdiff_t num_over_4 = 0; /* number of 4-byte non-Unicode chars in STRING */
ptrdiff_t num_over_5 = 0; /* number of 5-byte non-Unicode chars in STRING */
ptrdiff_t outbytes; /* number of bytes of decoding result */
unsigned char *p = SDATA (string);
unsigned char *pend = p + nbytes;
unsigned char *src = NULL, *dst = NULL;
unsigned char *replace_8_bit = NULL, *replace_over_uni = NULL;
int replace_8_bit_len = 0, replace_over_uni_len = 0;
Lisp_Object val; /* the return value */
/* Scan bytes in STRING twice. The first scan is to count non-Unicode
characters, and the second scan is to encode STRING. If the
encoding is trivial (no need of changing the byte sequence),
the second scan is avoided. */
for (int scan_count = 0; scan_count < 2; scan_count++)
{
while (p < pend)
{
if (nchars == pend - p)
/* There is no multibyte character remaining. */
break;
int c = *p;
int len = BYTES_BY_CHAR_HEAD (c);
nchars--;
if (len == 1
|| len == 3
|| (len == 2 ? ! CHAR_BYTE8_HEAD_P (c)
: (EQ (handle_over_uni, Qt)
|| (len == 4
&& STRING_CHAR (p) <= MAX_UNICODE_CHAR))))
{
p += len;
continue;
}
/* A character to change the byte sequence on encoding was
found. A rare case. */
if (len == 2)
{
/* Handle an eight-bit character by handle_8_bit. */
if (scan_count == 0)
{
if (NILP (handle_8_bit))
return Qnil;
num_8_bit++;
}
else
{
if (src < p)
{
memcpy (dst, src, p - src);
dst += p - src;
}
if (replace_8_bit_len > 0)
{
memcpy (dst, replace_8_bit, replace_8_bit_len);
dst += replace_8_bit_len;
}
else if (EQ (handle_8_bit, Qt))
{
int char8 = STRING_CHAR (p);
*dst++ = CHAR_TO_BYTE8 (char8);
}
}
}
else /* len == 4 or 5 */
{
/* Handle an over-unicode character by handle_over_uni. */
if (scan_count == 0)
{
if (NILP (handle_over_uni))
return Qnil;
if (len == 4)
num_over_4++;
else
num_over_5++;
}
else
{
if (src < p)
{
memcpy (dst, src, p - src);
dst += p - src;
}
if (replace_over_uni_len > 0)
{
memcpy (dst, replace_over_uni, replace_over_uni_len);
dst += replace_over_uni_len;
}
}
}
p += len;
src = p;
}
if (scan_count == 0)
{
/* End of the first scan. */
outbytes = nbytes;
if (num_8_bit == 0
&& (num_over_4 + num_over_5 == 0 || EQ (handle_over_uni, Qt)))
{
/* We can break the loop because there is no need of
changing the byte sequence. This is the typical
case. */
scan_count = 1;
}
else
{
/* Prepare for handling non-Unicode characters during
the next scan. */
if (num_8_bit > 0)
{
if (CHARACTERP (handle_8_bit))
replace_8_bit = get_char_bytes (XFIXNUM (handle_8_bit),
&replace_8_bit_len);
else if (STRINGP (handle_8_bit))
{
replace_8_bit = SDATA (handle_8_bit);
replace_8_bit_len = SBYTES (handle_8_bit);
}
if (replace_8_bit)
outbytes += (replace_8_bit_len - 2) * num_8_bit;
else if (EQ (handle_8_bit, Qignored))
outbytes -= 2 * num_8_bit;
else if (EQ (handle_8_bit, Qt))
outbytes -= num_8_bit;
else
return Qnil;
}
if (num_over_4 + num_over_5 > 0)
{
if (CHARACTERP (handle_over_uni))
replace_over_uni = get_char_bytes (XFIXNUM (handle_over_uni),
&replace_over_uni_len);
else if (STRINGP (handle_over_uni))
{
replace_over_uni = SDATA (handle_over_uni);
replace_over_uni_len = SBYTES (handle_over_uni);
}
if (num_over_4 > 0)
{
if (replace_over_uni)
outbytes += (replace_over_uni_len - 4) * num_over_4;
else if (EQ (handle_over_uni, Qignored))
outbytes -= 4 * num_over_4;
else if (! EQ (handle_over_uni, Qt))
return Qnil;
}
if (num_over_5 > 0)
{
if (replace_over_uni)
outbytes += (replace_over_uni_len - 5) * num_over_5;
else if (EQ (handle_over_uni, Qignored))
outbytes -= 5 * num_over_5;
else if (! EQ (handle_over_uni, Qt))
return Qnil;
}
}
}
/* Prepare return value and space to store the encoded bytes. */
if (BUFFERP (buffer))
{
val = make_fixnum (outbytes);
dst = get_buffer_gap_address (buffer, nbytes);
}
else
{
if (nocopy && (num_8_bit + num_over_4 + num_over_5) == 0)
return string;
val = make_uninit_string (outbytes);
dst = SDATA (val);
}
p = src = SDATA (string);
}
}
if (src < pend)
memcpy (dst, src, pend - src);
if (BUFFERP (buffer))
{
struct buffer *oldb = current_buffer;
current_buffer = XBUFFER (buffer);
insert_from_gap (outbytes, outbytes, false);
current_buffer = oldb;
}
return val;
}
/* Decode input string by the coding system utf-8-unix.
This function is optimized for speed when the input string is
already a valid UTF-8 sequence, i.e. there are neither 8-bit raw
bytes nor any UTF-8 sequences longer than 4 bytes in the string's
contents.
Ignore any :post-read-conversion and :decode-translation-table
properties.
Assume that arguments have values as described below.
The validity must be enforced and ensured by the caller.
STRING is a unibyte string, an ASCII-only multibyte string, or Qnil.
If STRING is Qnil, the input is a C string pointed by STR whose
length in bytes is in STR_LEN.
BUFFER is a multibyte buffer or Qnil.
If BUFFER is a multibyte buffer, insert the decoding result of
Unicode characters after point of the buffer, and return the number
of inserted characters. The caller should have made BUFFER ready
for modifying in advance (e.g., by calling invalidate_buffer_caches).
If BUFFER is Qnil, return a multibyte string from the decoded result.
NOCOPY non-zero means it is OK to return the input STRING if it
contains only ASCII characters or only valid UTF-8 sequences of 2
to 4 bytes. WARNING: This will return a _unibyte_ string, something
that callers might not expect, especially if STRING is not
pure-ASCII; only use NOCOPY non-zero if the caller will only use
the byte sequence of the decoded result accessed via SDATA or
SSDATA, and if the original STRING will _not_ be modified after the
decoding. When in doubt, always pass NOCOPY as zero. You _have_
been warned!
If STRING is Qnil, and the original string is passed via STR, NOCOPY
is ignored.
HANDLE-8-BIT and HANDLE-OVER-UNI specify how to handle a invalid
byte sequence. The former is for a 1-byte invalid sequence that
violates the fundamental UTF-8 encoding rules. The latter is for a
4 or 5-byte overlong sequences that Emacs internally uses to
represent characters beyond the Unicode range (characters whose
codepoints are greater than #x10FFFF). Note that this function does
not in general treat such overlong UTF-8 sequences as invalid.
If these two arguments are strings (typically a 1-char string of
the Unicode REPLACEMENT CHARACTER #xFFFD), decode an invalid byte
sequence into that string. They must be multibyte strings if they
contain a non-ASCII character.
If the two arguments are characters, decode an invalid byte
sequence into the corresponding multibyte representation of the
respective character.
If they are Qignored, skip an invalid byte sequence without
producing anything in the decoded string.
If HANDLE-8-BIT is Qt, decode a 1-byte invalid sequence into the
corresponding eight-bit multibyte representation, like the usual
Emacs decoding does.
If HANDLE-OVER-UNI is Qt, decode a 4 or 5-byte overlong sequence
that follows Emacs' internal representation for a character beyond
Unicode range into the corresponding character, like the usual
Emacs decoding does.
If the two arguments are Qnil, return Qnil if the input string has
raw bytes or overlong sequences. This allows the caller to signal
an error if such inputs are not allowed. */
Lisp_Object
decode_string_utf_8 (Lisp_Object string, const char *str, ptrdiff_t str_len,
Lisp_Object buffer, bool nocopy,
Lisp_Object handle_8_bit, Lisp_Object handle_over_uni)
{
/* This is like BYTES_BY_CHAR_HEAD, but it is assured that C >= 0x80
and it returns 0 for an invalid sequence. */
#define UTF_8_SEQUENCE_LENGTH(c) \
((c) < 0xC2 ? 0 \
: (c) < 0xE0 ? 2 \
: (c) < 0xF0 ? 3 \
: (c) < 0xF8 ? 4 \
: (c) == 0xF8 ? 5 \
: 0)
ptrdiff_t nbytes = STRINGP (string) ? SBYTES (string) : str_len;
unsigned char *p = STRINGP (string) ? SDATA (string) : (unsigned char *) str;
unsigned char *str_orig = p;
unsigned char *pend = p + nbytes;
ptrdiff_t num_8_bit = 0; /* number of invalid 1-byte sequences */
ptrdiff_t num_over_4 = 0; /* number of invalid 4-byte sequences */
ptrdiff_t num_over_5 = 0; /* number of invalid 5-byte sequences */
ptrdiff_t outbytes = nbytes; /* number of decoded bytes */
ptrdiff_t outchars = 0; /* number of decoded characters */
unsigned char *src = NULL, *dst = NULL;
bool change_byte_sequence = false;
/* Scan input bytes twice. The first scan is to count invalid
sequences, and the second scan is to decode input. If the
decoding is trivial (no need of changing the byte sequence),
the second scan is avoided. */
while (p < pend)
{
src = p;
/* Try short cut for an ASCII-only case. */
while (p < pend && *p < 0x80) p++;
outchars += (p - src);
if (p == pend)
break;
int c = *p;
outchars++;
int len = UTF_8_SEQUENCE_LENGTH (c);
/* len == 0, 2, 3, 4, 5. */
if (UTF_8_EXTRA_OCTET_P (p[1])
&& (len == 2
|| (UTF_8_EXTRA_OCTET_P (p[2])
&& (len == 3
|| (UTF_8_EXTRA_OCTET_P (p[3])
&& len == 4
&& STRING_CHAR (p) <= MAX_UNICODE_CHAR)))))
{
p += len;
continue;
}
/* A sequence to change on decoding was found. A rare case. */
if (len == 0)
{
if (NILP (handle_8_bit))
return Qnil;
num_8_bit++;
len = 1;
}
else /* len == 4 or 5 */
{
if (NILP (handle_over_uni))
return Qnil;
if (len == 4)
num_over_4++;
else
num_over_5++;
}
change_byte_sequence = true;
p += len;
}
Lisp_Object val; /* the return value */
if (! change_byte_sequence
&& NILP (buffer))
{
if (nocopy && STRINGP (string))
return string;
val = make_uninit_multibyte_string (outchars, outbytes);
memcpy (SDATA (val), str_orig, pend - str_orig);
return val;
}
/* Count the number of resulting chars and bytes. */
unsigned char *replace_8_bit = NULL, *replace_over_uni = NULL;
int replace_8_bit_len = 0, replace_over_uni_len = 0;
if (change_byte_sequence)
{
if (num_8_bit > 0)
{
if (CHARACTERP (handle_8_bit))
replace_8_bit = get_char_bytes (XFIXNUM (handle_8_bit),
&replace_8_bit_len);
else if (STRINGP (handle_8_bit))
{
replace_8_bit = SDATA (handle_8_bit);
replace_8_bit_len = SBYTES (handle_8_bit);
}
if (replace_8_bit)
outbytes += (replace_8_bit_len - 1) * num_8_bit;
else if (EQ (handle_8_bit, Qignored))
{
outbytes -= num_8_bit;
outchars -= num_8_bit;
}
else /* EQ (handle_8_bit, Qt)) */
outbytes += num_8_bit;
}
else if (num_over_4 + num_over_5 > 0)
{
if (CHARACTERP (handle_over_uni))
replace_over_uni = get_char_bytes (XFIXNUM (handle_over_uni),
&replace_over_uni_len);
else if (STRINGP (handle_over_uni))
{
replace_over_uni = SDATA (handle_over_uni);
replace_over_uni_len = SBYTES (handle_over_uni);
}
if (num_over_4 > 0)
{
if (replace_over_uni)
outbytes += (replace_over_uni_len - 4) * num_over_4;
else if (EQ (handle_over_uni, Qignored))
{
outbytes -= 4 * num_over_4;
outchars -= num_over_4;
}
}
if (num_over_5 > 0)
{
if (replace_over_uni)
outbytes += (replace_over_uni_len - 5) * num_over_5;
else if (EQ (handle_over_uni, Qignored))
{
outbytes -= 5 * num_over_5;
outchars -= num_over_5;
}
}
}
}
/* Prepare return value and space to store the decoded bytes. */
if (BUFFERP (buffer))
{
val = make_fixnum (outchars);
dst = get_buffer_gap_address (buffer, outbytes);
}
else
{
if (nocopy && (num_8_bit + num_over_4 + num_over_5) == 0
&& STRINGP (string))
return string;
val = make_uninit_multibyte_string (outchars, outbytes);
dst = SDATA (val);
}
src = str_orig;
if (change_byte_sequence)
{
p = src;
while (p < pend)
{
/* Try short cut for an ASCII-only case. */
/* while (p < pend && *p < 0x80) p++; */
/* if (p == pend) */
/* break; */
int c = *p;
if (c < 0x80)
{
p++;
continue;
}
int len = UTF_8_SEQUENCE_LENGTH (c);
if (len > 1)
{
int mlen;
for (mlen = 1; mlen < len && UTF_8_EXTRA_OCTET_P (p[mlen]);
mlen++);
if (mlen == len
&& (len <= 3
|| (len == 4 && STRING_CHAR (p) <= MAX_UNICODE_CHAR)
|| EQ (handle_over_uni, Qt)))
{
p += len;
continue;
}
}
if (src < p)
{
memcpy (dst, src, p - src);
dst += p - src;
}
if (len == 0)
{
if (replace_8_bit)
{
memcpy (dst, replace_8_bit, replace_8_bit_len);
dst += replace_8_bit_len;
}
else if (EQ (handle_8_bit, Qt))
{
dst += BYTE8_STRING (c, dst);
}
len = 1;
}
else /* len == 4 or 5 */
{
/* Handle p[0]... by handle_over_uni. */
if (replace_over_uni)
{
memcpy (dst, replace_over_uni, replace_over_uni_len);
dst += replace_over_uni_len;
}
}
p += len;
src = p;
}
}
if (src < pend)
memcpy (dst, src, pend - src);
if (BUFFERP (buffer))
{
struct buffer *oldb = current_buffer;
current_buffer = XBUFFER (buffer);
insert_from_gap (outchars, outbytes, false);
current_buffer = oldb;
}
return val;
}
/* #define ENABLE_UTF_8_CONVERTER_TEST */
#ifdef ENABLE_UTF_8_CONVERTER_TEST
/* These functions are useful for testing and benchmarking
encode_string_utf_8 and decode_string_utf_8. */
/* ENCODE_METHOD specifies which internal decoder to use.
If it is Qnil, use encode_string_utf_8.
Otherwise, use code_convert_string.
COUNT, if integer, specifies how many times to call those functions
with the same arguments (for benchmarking). */
DEFUN ("internal-encode-string-utf-8", Finternal_encode_string_utf_8,
Sinternal_encode_string_utf_8, 7, 7, 0,
doc: /* Internal use only.*/)
(Lisp_Object string, Lisp_Object buffer, Lisp_Object nocopy,
Lisp_Object handle_8_bit, Lisp_Object handle_over_uni,
Lisp_Object encode_method, Lisp_Object count)
{
int repeat_count;
Lisp_Object val;
/* Check arguments. Return Qnil when an argument is invalid. */
if (! STRINGP (string))
return Qnil;
if (! NILP (buffer)
&& (! BUFFERP (buffer)
|| ! NILP (BVAR (XBUFFER (buffer), enable_multibyte_characters))))
return Qnil;
if (! NILP (handle_8_bit) && ! EQ (handle_8_bit, Qt)
&& ! EQ (handle_8_bit, Qignored)
&& ! CHARACTERP (handle_8_bit)
&& (! STRINGP (handle_8_bit) || STRING_MULTIBYTE (handle_8_bit)))
return Qnil;
if (! NILP (handle_over_uni) && ! EQ (handle_over_uni, Qt)
&& ! EQ (handle_over_uni, Qignored)
&& ! CHARACTERP (handle_over_uni)
&& (! STRINGP (handle_over_uni) || STRING_MULTIBYTE (handle_over_uni)))
return Qnil;
CHECK_FIXNUM (count);
repeat_count = XFIXNUM (count);
val = Qnil;
/* Run an encoder according to ENCODE_METHOD. */
if (NILP (encode_method))
{
for (int i = 0; i < repeat_count; i++)
val = encode_string_utf_8 (string, buffer, ! NILP (nocopy),
handle_8_bit, handle_over_uni);
}
else
{
for (int i = 0; i < repeat_count; i++)
val = code_convert_string (string, Qutf_8_unix, Qnil, true,
! NILP (nocopy), true);
}
return val;
}
/* DECODE_METHOD specifies which internal decoder to use.
If it is Qnil, use decode_string_utf_8.
If it is Qt, use code_convert_string.
Otherwise, use make_string_from_utf8.
COUNT, if integer, specifies how many times to call those functions
with the same arguments (for benchmarking). */
DEFUN ("internal-decode-string-utf-8", Finternal_decode_string_utf_8,
Sinternal_decode_string_utf_8, 7, 7, 0,
doc: /* Internal use only.*/)
(Lisp_Object string, Lisp_Object buffer, Lisp_Object nocopy,
Lisp_Object handle_8_bit, Lisp_Object handle_over_uni,
Lisp_Object decode_method, Lisp_Object count)
{
int repeat_count;
Lisp_Object val;
/* Check arguments. Return Qnil when an argument is invalid. */
if (! STRINGP (string))
return Qnil;
if (! NILP (buffer)
&& (! BUFFERP (buffer)
|| NILP (BVAR (XBUFFER (buffer), enable_multibyte_characters))))
return Qnil;
if (! NILP (handle_8_bit) && ! EQ (handle_8_bit, Qt)
&& ! EQ (handle_8_bit, Qignored)
&& ! CHARACTERP (handle_8_bit)
&& (! STRINGP (handle_8_bit) || ! STRING_MULTIBYTE (handle_8_bit)))
return Qnil;
if (! NILP (handle_over_uni) && ! EQ (handle_over_uni, Qt)
&& ! EQ (handle_over_uni, Qignored)
&& ! CHARACTERP (handle_over_uni)
&& (! STRINGP (handle_over_uni) || ! STRING_MULTIBYTE (handle_over_uni)))
return Qnil;
CHECK_FIXNUM (count);
repeat_count = XFIXNUM (count);
val = Qnil;
/* Run a decoder according to DECODE_METHOD. */
if (NILP (decode_method))
{
for (int i = 0; i < repeat_count; i++)
val = decode_string_utf_8 (string, buffer, ! NILP (nocopy),
handle_8_bit, handle_over_uni);
}
else if (EQ (decode_method, Qt))
{
if (! BUFFERP (buffer))
buffer = Qt;
for (int i = 0; i < repeat_count; i++)
val = code_convert_string (string, Qutf_8_unix, buffer, false,
! NILP (nocopy), true);
}
else if (! NILP (decode_method))
{
for (int i = 0; i < repeat_count; i++)
val = make_string_from_utf8 ((char *) SDATA (string), SBYTES (string));
}
return val;
}
#endif /* ENABLE_UTF_8_CONVERTER_TEST */
/* Encode or decode STRING using CODING_SYSTEM, with the possibility of
returning STRING itself if it equals the result.
Do not set Vlast_coding_system_used. */
static Lisp_Object
convert_string_nocopy (Lisp_Object string, Lisp_Object coding_system,
bool encodep)
{
return code_convert_string (string, coding_system, Qt, encodep, 1, 1);
}
/* Encode or decode a file name, to or from a unibyte string suitable
for passing to C library functions. */
Lisp_Object
decode_file_name (Lisp_Object fname)
{
#ifdef WINDOWSNT
/* The w32 build pretends to use UTF-8 for file-name encoding, and
converts the file names either to UTF-16LE or to the system ANSI
codepage internally, depending on the underlying OS; see w32.c. */
if (! NILP (Fcoding_system_p (Qutf_8)))
return convert_string_nocopy (fname, Qutf_8, 0);
return fname;
#else /* !WINDOWSNT */
if (! NILP (Vfile_name_coding_system))
return convert_string_nocopy (fname, Vfile_name_coding_system, 0);
else if (! NILP (Vdefault_file_name_coding_system))
return convert_string_nocopy (fname, Vdefault_file_name_coding_system, 0);
else
return fname;
#endif
}
Lisp_Object
encode_file_name (Lisp_Object fname)
{
/* This is especially important during bootstrap and dumping, when
file-name encoding is not yet known, and therefore any non-ASCII
file names are unibyte strings, and could only be thrashed if we
try to encode them. */
if (!STRING_MULTIBYTE (fname))
return fname;
#ifdef WINDOWSNT
/* The w32 build pretends to use UTF-8 for file-name encoding, and
converts the file names either to UTF-16LE or to the system ANSI
codepage internally, depending on the underlying OS; see w32.c. */
if (! NILP (Fcoding_system_p (Qutf_8)))
return convert_string_nocopy (fname, Qutf_8, 1);
return fname;
#else /* !WINDOWSNT */
if (! NILP (Vfile_name_coding_system))
return convert_string_nocopy (fname, Vfile_name_coding_system, 1);
else if (! NILP (Vdefault_file_name_coding_system))
return convert_string_nocopy (fname, Vdefault_file_name_coding_system, 1);
else
return fname;
#endif
}
DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string,
2, 4, 0,
doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result.
Optional third arg NOCOPY non-nil means it is OK to return STRING itself
if the decoding operation is trivial.
Optional fourth arg BUFFER non-nil means that the decoded text is
inserted in that buffer after point (point does not move). In this
case, the return value is the length of the decoded text. If that
buffer is unibyte, it receives the individual bytes of the internal
representation of the decoded text.
This function sets `last-coding-system-used' to the precise coding system
used (which may be different from CODING-SYSTEM if CODING-SYSTEM is
not fully specified.) The function does not change the match data. */)
(Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer)
{
return code_convert_string (string, coding_system, buffer,
0, ! NILP (nocopy), 0);
}
DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string,
2, 4, 0,
doc: /* Encode STRING to CODING-SYSTEM, and return the result.
Optional third arg NOCOPY non-nil means it is OK to return STRING
itself if the encoding operation is trivial.
Optional fourth arg BUFFER non-nil means that the encoded text is
inserted in that buffer after point (point does not move). In this
case, the return value is the length of the encoded text.
This function sets `last-coding-system-used' to the precise coding system
used (which may be different from CODING-SYSTEM if CODING-SYSTEM is
not fully specified.) The function does not change the match data. */)
(Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer)
{
return code_convert_string (string, coding_system, buffer,
1, ! NILP (nocopy), 0);
}
\f
DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0,
doc: /* Decode a Japanese character which has CODE in shift_jis encoding.
Return the corresponding character. */)
(Lisp_Object code)
{
Lisp_Object spec, attrs, val;
struct charset *charset_roman, *charset_kanji, *charset_kana, *charset;
EMACS_INT ch;
int c;
CHECK_FIXNAT (code);
ch = XFIXNAT (code);
CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec);
attrs = AREF (spec, 0);
if (ASCII_CHAR_P (ch)
&& ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)))
return code;
val = CODING_ATTR_CHARSET_LIST (attrs);
charset_roman = CHARSET_FROM_ID (XFIXNUM (XCAR (val))), val = XCDR (val);
charset_kana = CHARSET_FROM_ID (XFIXNUM (XCAR (val))), val = XCDR (val);
charset_kanji = CHARSET_FROM_ID (XFIXNUM (XCAR (val)));
if (ch <= 0x7F)
{
c = ch;
charset = charset_roman;
}
else if (ch >= 0xA0 && ch < 0xDF)
{
c = ch - 0x80;
charset = charset_kana;
}
else
{
EMACS_INT c1 = ch >> 8;
int c2 = ch & 0xFF;
if (c1 < 0x81 || (c1 > 0x9F && c1 < 0xE0) || c1 > 0xEF
|| c2 < 0x40 || c2 == 0x7F || c2 > 0xFC)
error ("Invalid code: %"pI"d", ch);
c = ch;
SJIS_TO_JIS (c);
charset = charset_kanji;
}
c = DECODE_CHAR (charset, c);
if (c < 0)
error ("Invalid code: %"pI"d", ch);
return make_fixnum (c);
}
DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0,
doc: /* Encode a Japanese character CH to shift_jis encoding.
Return the corresponding code in SJIS. */)
(Lisp_Object ch)
{
Lisp_Object spec, attrs, charset_list;
int c;
struct charset *charset;
unsigned code;
CHECK_CHARACTER (ch);
c = XFIXNAT (ch);
CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec);
attrs = AREF (spec, 0);
if (ASCII_CHAR_P (c)
&& ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)))
return ch;
charset_list = CODING_ATTR_CHARSET_LIST (attrs);
charset = char_charset (c, charset_list, &code);
if (code == CHARSET_INVALID_CODE (charset))
error ("Can't encode by shift_jis encoding: %c", c);
JIS_TO_SJIS (code);
return make_fixnum (code);
}
DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0,
doc: /* Decode a Big5 character which has CODE in BIG5 coding system.
Return the corresponding character. */)
(Lisp_Object code)
{
Lisp_Object spec, attrs, val;
struct charset *charset_roman, *charset_big5, *charset;
EMACS_INT ch;
int c;
CHECK_FIXNAT (code);
ch = XFIXNAT (code);
CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec);
attrs = AREF (spec, 0);
if (ASCII_CHAR_P (ch)
&& ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)))
return code;
val = CODING_ATTR_CHARSET_LIST (attrs);
charset_roman = CHARSET_FROM_ID (XFIXNUM (XCAR (val))), val = XCDR (val);
charset_big5 = CHARSET_FROM_ID (XFIXNUM (XCAR (val)));
if (ch <= 0x7F)
{
c = ch;
charset = charset_roman;
}
else
{
EMACS_INT b1 = ch >> 8;
int b2 = ch & 0x7F;
if (b1 < 0xA1 || b1 > 0xFE
|| b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE)
error ("Invalid code: %"pI"d", ch);
c = ch;
charset = charset_big5;
}
c = DECODE_CHAR (charset, c);
if (c < 0)
error ("Invalid code: %"pI"d", ch);
return make_fixnum (c);
}
DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0,
doc: /* Encode the Big5 character CH to BIG5 coding system.
Return the corresponding character code in Big5. */)
(Lisp_Object ch)
{
Lisp_Object spec, attrs, charset_list;
struct charset *charset;
int c;
unsigned code;
CHECK_CHARACTER (ch);
c = XFIXNAT (ch);
CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec);
attrs = AREF (spec, 0);
if (ASCII_CHAR_P (c)
&& ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)))
return ch;
charset_list = CODING_ATTR_CHARSET_LIST (attrs);
charset = char_charset (c, charset_list, &code);
if (code == CHARSET_INVALID_CODE (charset))
error ("Can't encode by Big5 encoding: %c", c);
return make_fixnum (code);
}
\f
DEFUN ("set-terminal-coding-system-internal", Fset_terminal_coding_system_internal,
Sset_terminal_coding_system_internal, 1, 2, 0,
doc: /* Internal use only. */)
(Lisp_Object coding_system, Lisp_Object terminal)
{
struct terminal *term = decode_live_terminal (terminal);
struct coding_system *terminal_coding = TERMINAL_TERMINAL_CODING (term);
CHECK_SYMBOL (coding_system);
setup_coding_system (Fcheck_coding_system (coding_system), terminal_coding);
/* We had better not send unsafe characters to terminal. */
terminal_coding->mode |= CODING_MODE_SAFE_ENCODING;
/* Character composition should be disabled. */
terminal_coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK;
terminal_coding->src_multibyte = 1;
terminal_coding->dst_multibyte = 0;
tset_charset_list
(term, (terminal_coding->common_flags & CODING_REQUIRE_ENCODING_MASK
? coding_charset_list (terminal_coding)
: list1i (charset_ascii)));
return Qnil;
}
DEFUN ("set-safe-terminal-coding-system-internal",
Fset_safe_terminal_coding_system_internal,
Sset_safe_terminal_coding_system_internal, 1, 1, 0,
doc: /* Internal use only. */)
(Lisp_Object coding_system)
{
CHECK_SYMBOL (coding_system);
setup_coding_system (Fcheck_coding_system (coding_system),
&safe_terminal_coding);
/* Character composition should be disabled. */
safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK;
safe_terminal_coding.src_multibyte = 1;
safe_terminal_coding.dst_multibyte = 0;
return Qnil;
}
DEFUN ("terminal-coding-system", Fterminal_coding_system,
Sterminal_coding_system, 0, 1, 0,
doc: /* Return coding system specified for terminal output on the given terminal.
TERMINAL may be a terminal object, a frame, or nil for the selected
frame's terminal device. */)
(Lisp_Object terminal)
{
struct coding_system *terminal_coding
= TERMINAL_TERMINAL_CODING (decode_live_terminal (terminal));
Lisp_Object coding_system = CODING_ID_NAME (terminal_coding->id);
/* For backward compatibility, return nil if it is `undecided'. */
return (! EQ (coding_system, Qundecided) ? coding_system : Qnil);
}
DEFUN ("set-keyboard-coding-system-internal", Fset_keyboard_coding_system_internal,
Sset_keyboard_coding_system_internal, 1, 2, 0,
doc: /* Internal use only. */)
(Lisp_Object coding_system, Lisp_Object terminal)
{
struct terminal *t = decode_live_terminal (terminal);
CHECK_SYMBOL (coding_system);
if (NILP (coding_system))
coding_system = Qno_conversion;
else
Fcheck_coding_system (coding_system);
setup_coding_system (coding_system, TERMINAL_KEYBOARD_CODING (t));
/* Character composition should be disabled. */
TERMINAL_KEYBOARD_CODING (t)->common_flags
&= ~CODING_ANNOTATE_COMPOSITION_MASK;
return Qnil;
}
DEFUN ("keyboard-coding-system",
Fkeyboard_coding_system, Skeyboard_coding_system, 0, 1, 0,
doc: /* Return coding system specified for decoding keyboard input. */)
(Lisp_Object terminal)
{
return CODING_ID_NAME (TERMINAL_KEYBOARD_CODING
(decode_live_terminal (terminal))->id);
}
\f
DEFUN ("find-operation-coding-system", Ffind_operation_coding_system,
Sfind_operation_coding_system, 1, MANY, 0,
doc: /* Choose a coding system for an operation based on the target name.
The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM).
DECODING-SYSTEM is the coding system to use for decoding
\(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system
for encoding (in case OPERATION does encoding).
The first argument OPERATION specifies an I/O primitive:
For file I/O, `insert-file-contents' or `write-region'.
For process I/O, `call-process', `call-process-region', or `start-process'.
For network I/O, `open-network-stream'.
The remaining arguments should be the same arguments that were passed
to the primitive. Depending on which primitive, one of those arguments
is selected as the TARGET. For example, if OPERATION does file I/O,
whichever argument specifies the file name is TARGET.
TARGET has a meaning which depends on OPERATION:
For file I/O, TARGET is a file name (except for the special case below).
For process I/O, TARGET is a process name.
For network I/O, TARGET is a service name or a port number.
This function looks up what is specified for TARGET in
`file-coding-system-alist', `process-coding-system-alist',
or `network-coding-system-alist' depending on OPERATION.
They may specify a coding system, a cons of coding systems,
or a function symbol to call.
In the last case, we call the function with one argument,
which is a list of all the arguments given to this function.
If the function can't decide a coding system, it can return
`undecided' so that the normal code-detection is performed.
If OPERATION is `insert-file-contents', the argument corresponding to
TARGET may be a cons (FILENAME . BUFFER). In that case, FILENAME is a
file name to look up, and BUFFER is a buffer that contains the file's
contents (not yet decoded). If `file-coding-system-alist' specifies a
function to call for FILENAME, that function should examine the
contents of BUFFER instead of reading the file.
usage: (find-operation-coding-system OPERATION ARGUMENTS...) */)
(ptrdiff_t nargs, Lisp_Object *args)
{
Lisp_Object operation, target_idx, target, val;
register Lisp_Object chain;
if (nargs < 2)
error ("Too few arguments");
operation = args[0];
if (!SYMBOLP (operation)
|| (target_idx = Fget (operation, Qtarget_idx), !FIXNATP (target_idx)))
error ("Invalid first argument");
if (nargs <= 1 + XFIXNAT (target_idx))
error ("Too few arguments for operation `%s'",
SDATA (SYMBOL_NAME (operation)));
target = args[XFIXNAT (target_idx) + 1];
if (!(STRINGP (target)
|| (EQ (operation, Qinsert_file_contents) && CONSP (target)
&& STRINGP (XCAR (target)) && BUFFERP (XCDR (target)))
|| (EQ (operation, Qopen_network_stream)
&& (FIXNUMP (target) || EQ (target, Qt)))))
error ("Invalid argument %"pI"d of operation `%s'",
XFIXNAT (target_idx) + 1, SDATA (SYMBOL_NAME (operation)));
if (CONSP (target))
target = XCAR (target);
chain = ((EQ (operation, Qinsert_file_contents)
|| EQ (operation, Qwrite_region))
? Vfile_coding_system_alist
: (EQ (operation, Qopen_network_stream)
? Vnetwork_coding_system_alist
: Vprocess_coding_system_alist));
if (NILP (chain))
return Qnil;
for (; CONSP (chain); chain = XCDR (chain))
{
Lisp_Object elt;
elt = XCAR (chain);
if (CONSP (elt)
&& ((STRINGP (target)
&& STRINGP (XCAR (elt))
&& fast_string_match (XCAR (elt), target) >= 0)
|| (FIXNUMP (target) && EQ (target, XCAR (elt)))))
{
val = XCDR (elt);
/* Here, if VAL is both a valid coding system and a valid
function symbol, we return VAL as a coding system. */
if (CONSP (val))
return val;
if (! SYMBOLP (val))
return Qnil;
if (! NILP (Fcoding_system_p (val)))
return Fcons (val, val);
if (! NILP (Ffboundp (val)))
{
/* We use call1 rather than safe_call1
so as to get bug reports about functions called here
which don't handle the current interface. */
val = call1 (val, Flist (nargs, args));
if (CONSP (val))
return val;
if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val)))
return Fcons (val, val);
}
return Qnil;
}
}
return Qnil;
}
DEFUN ("set-coding-system-priority", Fset_coding_system_priority,
Sset_coding_system_priority, 0, MANY, 0,
doc: /* Assign higher priority to the coding systems given as arguments.
If multiple coding systems belong to the same category,
all but the first one are ignored.
usage: (set-coding-system-priority &rest coding-systems) */)
(ptrdiff_t nargs, Lisp_Object *args)
{
ptrdiff_t i, j;
bool changed[coding_category_max];
enum coding_category priorities[coding_category_max];
memset (changed, 0, sizeof changed);
for (i = j = 0; i < nargs; i++)
{
enum coding_category category;
Lisp_Object spec, attrs;
CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec);
attrs = AREF (spec, 0);
category = XFIXNUM (CODING_ATTR_CATEGORY (attrs));
if (changed[category])
/* Ignore this coding system because a coding system of the
same category already had a higher priority. */
continue;
changed[category] = 1;
priorities[j++] = category;
if (coding_categories[category].id >= 0
&& ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id)))
setup_coding_system (args[i], &coding_categories[category]);
Fset (AREF (Vcoding_category_table, category), args[i]);
}
/* Now we have decided top J priorities. Reflect the order of the
original priorities to the remaining priorities. */
for (i = j, j = 0; i < coding_category_max; i++, j++)
{
while (j < coding_category_max
&& changed[coding_priorities[j]])
j++;
if (j == coding_category_max)
emacs_abort ();
priorities[i] = coding_priorities[j];
}
memcpy (coding_priorities, priorities, sizeof priorities);
/* Update `coding-category-list'. */
Vcoding_category_list = Qnil;
for (i = coding_category_max; i-- > 0; )
Vcoding_category_list
= Fcons (AREF (Vcoding_category_table, priorities[i]),
Vcoding_category_list);
return Qnil;
}
DEFUN ("coding-system-priority-list", Fcoding_system_priority_list,
Scoding_system_priority_list, 0, 1, 0,
doc: /* Return a list of coding systems ordered by their priorities.
The list contains a subset of coding systems; i.e. coding systems
assigned to each coding category (see `coding-category-list').
HIGHESTP non-nil means just return the highest priority one. */)
(Lisp_Object highestp)
{
int i;
Lisp_Object val;
for (i = 0, val = Qnil; i < coding_category_max; i++)
{
enum coding_category category = coding_priorities[i];
int id = coding_categories[category].id;
Lisp_Object attrs;
if (id < 0)
continue;
attrs = CODING_ID_ATTRS (id);
if (! NILP (highestp))
return CODING_ATTR_BASE_NAME (attrs);
val = Fcons (CODING_ATTR_BASE_NAME (attrs), val);
}
return Fnreverse (val);
}
static const char *const suffixes[] = { "-unix", "-dos", "-mac" };
static Lisp_Object
make_subsidiaries (Lisp_Object base)
{
Lisp_Object subsidiaries;
ptrdiff_t base_name_len = SBYTES (SYMBOL_NAME (base));
USE_SAFE_ALLOCA;
char *buf = SAFE_ALLOCA (base_name_len + 6);
int i;
memcpy (buf, SDATA (SYMBOL_NAME (base)), base_name_len);
subsidiaries = make_uninit_vector (3);
for (i = 0; i < 3; i++)
{
strcpy (buf + base_name_len, suffixes[i]);
ASET (subsidiaries, i, intern (buf));
}
SAFE_FREE ();
return subsidiaries;
}
DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal,
Sdefine_coding_system_internal, coding_arg_max, MANY, 0,
doc: /* For internal use only.
usage: (define-coding-system-internal ...) */)
(ptrdiff_t nargs, Lisp_Object *args)
{
enum coding_category category;
int max_charset_id = 0;
if (nargs < coding_arg_max)
goto short_args;
Lisp_Object attrs = make_nil_vector (coding_attr_last_index);
Lisp_Object name = args[coding_arg_name];
CHECK_SYMBOL (name);
ASET (attrs, coding_attr_base_name, name);
Lisp_Object val = args[coding_arg_mnemonic];
if (! STRINGP (val))
CHECK_CHARACTER (val);
ASET (attrs, coding_attr_mnemonic, val);
Lisp_Object coding_type = args[coding_arg_coding_type];
CHECK_SYMBOL (coding_type);
ASET (attrs, coding_attr_type, coding_type);
Lisp_Object charset_list = args[coding_arg_charset_list];
if (SYMBOLP (charset_list))
{
if (EQ (charset_list, Qiso_2022))
{
if (! EQ (coding_type, Qiso_2022))
error ("Invalid charset-list");
charset_list = Viso_2022_charset_list;
}
else if (EQ (charset_list, Qemacs_mule))
{
if (! EQ (coding_type, Qemacs_mule))
error ("Invalid charset-list");
charset_list = Vemacs_mule_charset_list;
}
for (Lisp_Object tail = charset_list; CONSP (tail); tail = XCDR (tail))
{
if (! RANGED_FIXNUMP (0, XCAR (tail), INT_MAX - 1))
error ("Invalid charset-list");
if (max_charset_id < XFIXNAT (XCAR (tail)))
max_charset_id = XFIXNAT (XCAR (tail));
}
}
else
{
charset_list = Fcopy_sequence (charset_list);
for (Lisp_Object tail = charset_list; CONSP (tail); tail = XCDR (tail))
{
struct charset *charset;
val = XCAR (tail);
CHECK_CHARSET_GET_CHARSET (val, charset);
if (EQ (coding_type, Qiso_2022)
? CHARSET_ISO_FINAL (charset) < 0
: EQ (coding_type, Qemacs_mule)
? CHARSET_EMACS_MULE_ID (charset) < 0
: 0)
error ("Can't handle charset `%s'",
SDATA (SYMBOL_NAME (CHARSET_NAME (charset))));
XSETCAR (tail, make_fixnum (charset->id));
if (max_charset_id < charset->id)
max_charset_id = charset->id;
}
}
ASET (attrs, coding_attr_charset_list, charset_list);
Lisp_Object safe_charsets = make_uninit_string (max_charset_id + 1);
memset (SDATA (safe_charsets), 255, max_charset_id + 1);
for (Lisp_Object tail = charset_list; CONSP (tail); tail = XCDR (tail))
SSET (safe_charsets, XFIXNAT (XCAR (tail)), 0);
ASET (attrs, coding_attr_safe_charsets, safe_charsets);
ASET (attrs, coding_attr_ascii_compat, args[coding_arg_ascii_compatible_p]);
val = args[coding_arg_decode_translation_table];
if (! CHAR_TABLE_P (val) && ! CONSP (val))
CHECK_SYMBOL (val);
ASET (attrs, coding_attr_decode_tbl, val);
val = args[coding_arg_encode_translation_table];
if (! CHAR_TABLE_P (val) && ! CONSP (val))
CHECK_SYMBOL (val);
ASET (attrs, coding_attr_encode_tbl, val);
val = args[coding_arg_post_read_conversion];
CHECK_SYMBOL (val);
ASET (attrs, coding_attr_post_read, val);
val = args[coding_arg_pre_write_conversion];
CHECK_SYMBOL (val);
ASET (attrs, coding_attr_pre_write, val);
val = args[coding_arg_default_char];
if (NILP (val))
ASET (attrs, coding_attr_default_char, make_fixnum (' '));
else
{
CHECK_CHARACTER (val);
ASET (attrs, coding_attr_default_char, val);
}
val = args[coding_arg_for_unibyte];
ASET (attrs, coding_attr_for_unibyte, NILP (val) ? Qnil : Qt);
val = args[coding_arg_plist];
CHECK_LIST (val);
ASET (attrs, coding_attr_plist, val);
if (EQ (coding_type, Qcharset))
{
/* Generate a lisp vector of 256 elements. Each element is nil,
integer, or a list of charset IDs.
If Nth element is nil, the byte code N is invalid in this
coding system.
If Nth element is a number NUM, N is the first byte of a
charset whose ID is NUM.
If Nth element is a list of charset IDs, N is the first byte
of one of them. The list is sorted by dimensions of the
charsets. A charset of smaller dimension comes first. */
val = make_nil_vector (256);
for (Lisp_Object tail = charset_list; CONSP (tail); tail = XCDR (tail))
{
struct charset *charset = CHARSET_FROM_ID (XFIXNAT (XCAR (tail)));
int dim = CHARSET_DIMENSION (charset);
int idx = (dim - 1) * 4;
if (CHARSET_ASCII_COMPATIBLE_P (charset))
ASET (attrs, coding_attr_ascii_compat, Qt);
for (int i = charset->code_space[idx];
i <= charset->code_space[idx + 1]; i++)
{
Lisp_Object tmp, tmp2;
int dim2;
tmp = AREF (val, i);
if (NILP (tmp))
tmp = XCAR (tail);
else if (FIXNATP (tmp))
{
dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFIXNAT (tmp)));
if (dim < dim2)
tmp = list2 (XCAR (tail), tmp);
else
tmp = list2 (tmp, XCAR (tail));
}
else
{
for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2))
{
dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFIXNAT (XCAR (tmp2))));
if (dim < dim2)
break;
}
if (NILP (tmp2))
tmp = nconc2 (tmp, list1 (XCAR (tail)));
else
{
XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2)));
XSETCAR (tmp2, XCAR (tail));
}
}
ASET (val, i, tmp);
}
}
ASET (attrs, coding_attr_charset_valids, val);
category = coding_category_charset;
}
else if (EQ (coding_type, Qccl))
{
Lisp_Object valids;
if (nargs < coding_arg_ccl_max)
goto short_args;
val = args[coding_arg_ccl_decoder];
CHECK_CCL_PROGRAM (val);
if (VECTORP (val))
val = Fcopy_sequence (val);
ASET (attrs, coding_attr_ccl_decoder, val);
val = args[coding_arg_ccl_encoder];
CHECK_CCL_PROGRAM (val);
if (VECTORP (val))
val = Fcopy_sequence (val);
ASET (attrs, coding_attr_ccl_encoder, val);
val = args[coding_arg_ccl_valids];
valids = Fmake_string (make_fixnum (256), make_fixnum (0), Qnil);
for (Lisp_Object tail = val; CONSP (tail); tail = XCDR (tail))
{
int from, to;
val = XCAR (tail);
if (FIXNUMP (val))
{
if (! (0 <= XFIXNUM (val) && XFIXNUM (val) <= 255))
args_out_of_range_3 (val, make_fixnum (0), make_fixnum (255));
from = to = XFIXNUM (val);
}
else
{
CHECK_CONS (val);
from = check_integer_range (XCAR (val), 0, 255);
to = check_integer_range (XCDR (val), from, 255);
}
for (int i = from; i <= to; i++)
SSET (valids, i, 1);
}
ASET (attrs, coding_attr_ccl_valids, valids);
category = coding_category_ccl;
}
else if (EQ (coding_type, Qutf_16))
{
Lisp_Object bom, endian;
ASET (attrs, coding_attr_ascii_compat, Qnil);
if (nargs < coding_arg_utf16_max)
goto short_args;
bom = args[coding_arg_utf16_bom];
if (! NILP (bom) && ! EQ (bom, Qt))
{
CHECK_CONS (bom);
val = XCAR (bom);
CHECK_CODING_SYSTEM (val);
val = XCDR (bom);
CHECK_CODING_SYSTEM (val);
}
ASET (attrs, coding_attr_utf_bom, bom);
endian = args[coding_arg_utf16_endian];
CHECK_SYMBOL (endian);
if (NILP (endian))
endian = Qbig;
else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle))
error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian)));
ASET (attrs, coding_attr_utf_16_endian, endian);
category = (CONSP (bom)
? coding_category_utf_16_auto
: NILP (bom)
? (EQ (endian, Qbig)
? coding_category_utf_16_be_nosig
: coding_category_utf_16_le_nosig)
: (EQ (endian, Qbig)
? coding_category_utf_16_be
: coding_category_utf_16_le));
}
else if (EQ (coding_type, Qiso_2022))
{
Lisp_Object initial, reg_usage, request, flags;
if (nargs < coding_arg_iso2022_max)
goto short_args;
initial = Fcopy_sequence (args[coding_arg_iso2022_initial]);
CHECK_VECTOR (initial);
for (int i = 0; i < 4; i++)
{
val = AREF (initial, i);
if (! NILP (val))
{
struct charset *charset;
CHECK_CHARSET_GET_CHARSET (val, charset);
ASET (initial, i, make_fixnum (CHARSET_ID (charset)));
if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset))
ASET (attrs, coding_attr_ascii_compat, Qt);
}
else
ASET (initial, i, make_fixnum (-1));
}
reg_usage = args[coding_arg_iso2022_reg_usage];
CHECK_CONS (reg_usage);
CHECK_FIXNUM (XCAR (reg_usage));
CHECK_FIXNUM (XCDR (reg_usage));
request = Fcopy_sequence (args[coding_arg_iso2022_request]);
for (Lisp_Object tail = request; CONSP (tail); tail = XCDR (tail))
{
int id;
val = XCAR (tail);
CHECK_CONS (val);
CHECK_CHARSET_GET_ID (XCAR (val), id);
check_integer_range (XCDR (val), 0, 3);
XSETCAR (val, make_fixnum (id));
}
flags = args[coding_arg_iso2022_flags];
CHECK_FIXNAT (flags);
int i = XFIXNUM (flags) & INT_MAX;
if (EQ (args[coding_arg_charset_list], Qiso_2022))
i |= CODING_ISO_FLAG_FULL_SUPPORT;
flags = make_fixnum (i);
ASET (attrs, coding_attr_iso_initial, initial);
ASET (attrs, coding_attr_iso_usage, reg_usage);
ASET (attrs, coding_attr_iso_request, request);
ASET (attrs, coding_attr_iso_flags, flags);
setup_iso_safe_charsets (attrs);
if (i & CODING_ISO_FLAG_SEVEN_BITS)
category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT
| CODING_ISO_FLAG_SINGLE_SHIFT))
? coding_category_iso_7_else
: EQ (args[coding_arg_charset_list], Qiso_2022)
? coding_category_iso_7
: coding_category_iso_7_tight);
else
{
int id = XFIXNUM (AREF (initial, 1));
category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT)
|| EQ (args[coding_arg_charset_list], Qiso_2022)
|| id < 0)
? coding_category_iso_8_else
: (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1)
? coding_category_iso_8_1
: coding_category_iso_8_2);
}
if (category != coding_category_iso_8_1
&& category != coding_category_iso_8_2)
ASET (attrs, coding_attr_ascii_compat, Qnil);
}
else if (EQ (coding_type, Qemacs_mule))
{
if (EQ (args[coding_arg_charset_list], Qemacs_mule))
ASET (attrs, coding_attr_emacs_mule_full, Qt);
ASET (attrs, coding_attr_ascii_compat, Qt);
category = coding_category_emacs_mule;
}
else if (EQ (coding_type, Qshift_jis))
{
ptrdiff_t charset_list_len = list_length (charset_list);
if (charset_list_len != 3 && charset_list_len != 4)
error ("There should be three or four charsets");
struct charset *charset = CHARSET_FROM_ID (XFIXNUM (XCAR (charset_list)));
if (CHARSET_DIMENSION (charset) != 1)
error ("Dimension of charset %s is not one",
SDATA (SYMBOL_NAME (CHARSET_NAME (charset))));
if (CHARSET_ASCII_COMPATIBLE_P (charset))
ASET (attrs, coding_attr_ascii_compat, Qt);
charset_list = XCDR (charset_list);
charset = CHARSET_FROM_ID (XFIXNUM (XCAR (charset_list)));
if (CHARSET_DIMENSION (charset) != 1)
error ("Dimension of charset %s is not one",
SDATA (SYMBOL_NAME (CHARSET_NAME (charset))));
charset_list = XCDR (charset_list);
charset = CHARSET_FROM_ID (XFIXNUM (XCAR (charset_list)));
if (CHARSET_DIMENSION (charset) != 2)
error ("Dimension of charset %s is not two",
SDATA (SYMBOL_NAME (CHARSET_NAME (charset))));
charset_list = XCDR (charset_list);
if (! NILP (charset_list))
{
charset = CHARSET_FROM_ID (XFIXNUM (XCAR (charset_list)));
if (CHARSET_DIMENSION (charset) != 2)
error ("Dimension of charset %s is not two",
SDATA (SYMBOL_NAME (CHARSET_NAME (charset))));
}
category = coding_category_sjis;
Vsjis_coding_system = name;
}
else if (EQ (coding_type, Qbig5))
{
struct charset *charset;
if (list_length (charset_list) != 2)
error ("There should be just two charsets");
charset = CHARSET_FROM_ID (XFIXNUM (XCAR (charset_list)));
if (CHARSET_DIMENSION (charset) != 1)
error ("Dimension of charset %s is not one",
SDATA (SYMBOL_NAME (CHARSET_NAME (charset))));
if (CHARSET_ASCII_COMPATIBLE_P (charset))
ASET (attrs, coding_attr_ascii_compat, Qt);
charset_list = XCDR (charset_list);
charset = CHARSET_FROM_ID (XFIXNUM (XCAR (charset_list)));
if (CHARSET_DIMENSION (charset) != 2)
error ("Dimension of charset %s is not two",
SDATA (SYMBOL_NAME (CHARSET_NAME (charset))));
category = coding_category_big5;
Vbig5_coding_system = name;
}
else if (EQ (coding_type, Qraw_text))
{
category = coding_category_raw_text;
ASET (attrs, coding_attr_ascii_compat, Qt);
}
else if (EQ (coding_type, Qutf_8))
{
Lisp_Object bom;
if (nargs < coding_arg_utf8_max)
goto short_args;
bom = args[coding_arg_utf8_bom];
if (! NILP (bom) && ! EQ (bom, Qt))
{
CHECK_CONS (bom);
val = XCAR (bom);
CHECK_CODING_SYSTEM (val);
val = XCDR (bom);
CHECK_CODING_SYSTEM (val);
}
ASET (attrs, coding_attr_utf_bom, bom);
if (NILP (bom))
ASET (attrs, coding_attr_ascii_compat, Qt);
category = (CONSP (bom) ? coding_category_utf_8_auto
: NILP (bom) ? coding_category_utf_8_nosig
: coding_category_utf_8_sig);
}
else if (EQ (coding_type, Qundecided))
{
if (nargs < coding_arg_undecided_max)
goto short_args;
ASET (attrs, coding_attr_undecided_inhibit_nul_byte_detection,
args[coding_arg_undecided_inhibit_nul_byte_detection]);
ASET (attrs, coding_attr_undecided_inhibit_iso_escape_detection,
args[coding_arg_undecided_inhibit_iso_escape_detection]);
ASET (attrs, coding_attr_undecided_prefer_utf_8,
args[coding_arg_undecided_prefer_utf_8]);
category = coding_category_undecided;
}
else
error ("Invalid coding system type: %s",
SDATA (SYMBOL_NAME (coding_type)));
ASET (attrs, coding_attr_category, make_fixnum (category));
ASET (attrs, coding_attr_plist,
Fcons (QCcategory,
Fcons (AREF (Vcoding_category_table, category),
CODING_ATTR_PLIST (attrs))));
ASET (attrs, coding_attr_plist,
Fcons (QCascii_compatible_p,
Fcons (CODING_ATTR_ASCII_COMPAT (attrs),
CODING_ATTR_PLIST (attrs))));
Lisp_Object eol_type = args[coding_arg_eol_type];
if (! NILP (eol_type)
&& ! EQ (eol_type, Qunix)
&& ! EQ (eol_type, Qdos)
&& ! EQ (eol_type, Qmac))
error ("Invalid eol-type");
Lisp_Object aliases = list1 (name);
if (NILP (eol_type))
{
eol_type = make_subsidiaries (name);
for (int i = 0; i < 3; i++)
{
Lisp_Object this_spec, this_name, this_aliases, this_eol_type;
this_name = AREF (eol_type, i);
this_aliases = list1 (this_name);
this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac);
this_spec = make_uninit_vector (3);
ASET (this_spec, 0, attrs);
ASET (this_spec, 1, this_aliases);
ASET (this_spec, 2, this_eol_type);
Fputhash (this_name, this_spec, Vcoding_system_hash_table);
Vcoding_system_list = Fcons (this_name, Vcoding_system_list);
val = Fassoc (Fsymbol_name (this_name), Vcoding_system_alist, Qnil);
if (NILP (val))
Vcoding_system_alist
= Fcons (Fcons (Fsymbol_name (this_name), Qnil),
Vcoding_system_alist);
}
}
Lisp_Object spec_vec = make_uninit_vector (3);
ASET (spec_vec, 0, attrs);
ASET (spec_vec, 1, aliases);
ASET (spec_vec, 2, eol_type);
Fputhash (name, spec_vec, Vcoding_system_hash_table);
Vcoding_system_list = Fcons (name, Vcoding_system_list);
val = Fassoc (Fsymbol_name (name), Vcoding_system_alist, Qnil);
if (NILP (val))
Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil),
Vcoding_system_alist);
int id = coding_categories[category].id;
if (id < 0 || EQ (name, CODING_ID_NAME (id)))
setup_coding_system (name, &coding_categories[category]);
return Qnil;
short_args:
Fsignal (Qwrong_number_of_arguments,
Fcons (intern ("define-coding-system-internal"),
make_fixnum (nargs)));
}
DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put,
3, 3, 0,
doc: /* Change value in CODING-SYSTEM's property list PROP to VAL. */)
(Lisp_Object coding_system, Lisp_Object prop, Lisp_Object val)
{
Lisp_Object spec, attrs;
CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec);
attrs = AREF (spec, 0);
if (EQ (prop, QCmnemonic))
{
if (! STRINGP (val))
CHECK_CHARACTER (val);
ASET (attrs, coding_attr_mnemonic, val);
}
else if (EQ (prop, QCdefault_char))
{
if (NILP (val))
val = make_fixnum (' ');
else
CHECK_CHARACTER (val);
ASET (attrs, coding_attr_default_char, val);
}
else if (EQ (prop, QCdecode_translation_table))
{
if (! CHAR_TABLE_P (val) && ! CONSP (val))
CHECK_SYMBOL (val);
ASET (attrs, coding_attr_decode_tbl, val);
}
else if (EQ (prop, QCencode_translation_table))
{
if (! CHAR_TABLE_P (val) && ! CONSP (val))
CHECK_SYMBOL (val);
ASET (attrs, coding_attr_encode_tbl, val);
}
else if (EQ (prop, QCpost_read_conversion))
{
CHECK_SYMBOL (val);
ASET (attrs, coding_attr_post_read, val);
}
else if (EQ (prop, QCpre_write_conversion))
{
CHECK_SYMBOL (val);
ASET (attrs, coding_attr_pre_write, val);
}
else if (EQ (prop, QCascii_compatible_p))
{
ASET (attrs, coding_attr_ascii_compat, val);
}
ASET (attrs, coding_attr_plist,
Fplist_put (CODING_ATTR_PLIST (attrs), prop, val));
return val;
}
DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias,
Sdefine_coding_system_alias, 2, 2, 0,
doc: /* Define ALIAS as an alias for CODING-SYSTEM. */)
(Lisp_Object alias, Lisp_Object coding_system)
{
Lisp_Object spec, aliases, eol_type, val;
CHECK_SYMBOL (alias);
CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec);
aliases = AREF (spec, 1);
/* ALIASES should be a list of length more than zero, and the first
element is a base coding system. Append ALIAS at the tail of the
list. */
while (!NILP (XCDR (aliases)))
aliases = XCDR (aliases);
XSETCDR (aliases, list1 (alias));
eol_type = AREF (spec, 2);
if (VECTORP (eol_type))
{
Lisp_Object subsidiaries;
int i;
subsidiaries = make_subsidiaries (alias);
for (i = 0; i < 3; i++)
Fdefine_coding_system_alias (AREF (subsidiaries, i),
AREF (eol_type, i));
}
Fputhash (alias, spec, Vcoding_system_hash_table);
Vcoding_system_list = Fcons (alias, Vcoding_system_list);
val = Fassoc (Fsymbol_name (alias), Vcoding_system_alist, Qnil);
if (NILP (val))
Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil),
Vcoding_system_alist);
return Qnil;
}
DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base,
1, 1, 0,
doc: /* Return the base of CODING-SYSTEM.
Any alias or subsidiary coding system is not a base coding system. */)
(Lisp_Object coding_system)
{
Lisp_Object spec, attrs;
if (NILP (coding_system))
return (Qno_conversion);
CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec);
attrs = AREF (spec, 0);
return CODING_ATTR_BASE_NAME (attrs);
}
DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist,
1, 1, 0,
doc: /* Return the property list of CODING-SYSTEM. */)
(Lisp_Object coding_system)
{
Lisp_Object spec, attrs;
if (NILP (coding_system))
coding_system = Qno_conversion;
CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec);
attrs = AREF (spec, 0);
return CODING_ATTR_PLIST (attrs);
}
DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases,
1, 1, 0,
doc: /* Return the list of aliases of CODING-SYSTEM. */)
(Lisp_Object coding_system)
{
Lisp_Object spec;
if (NILP (coding_system))
coding_system = Qno_conversion;
CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec);
return AREF (spec, 1);
}
DEFUN ("coding-system-eol-type", Fcoding_system_eol_type,
Scoding_system_eol_type, 1, 1, 0,
doc: /* Return eol-type of CODING-SYSTEM.
An eol-type is an integer 0, 1, 2, or a vector of coding systems.
Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF,
and CR respectively.
A vector value indicates that a format of end-of-line should be
detected automatically. Nth element of the vector is the subsidiary
coding system whose eol-type is N. */)
(Lisp_Object coding_system)
{
Lisp_Object spec, eol_type;
int n;
if (NILP (coding_system))
coding_system = Qno_conversion;
if (! CODING_SYSTEM_P (coding_system))
return Qnil;
spec = CODING_SYSTEM_SPEC (coding_system);
eol_type = AREF (spec, 2);
if (VECTORP (eol_type))
return Fcopy_sequence (eol_type);
n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2;
return make_fixnum (n);
}
\f
/*** 9. Post-amble ***/
void
init_coding_once (void)
{
int i;
for (i = 0; i < coding_category_max; i++)
{
coding_categories[i].id = -1;
coding_priorities[i] = i;
}
PDUMPER_REMEMBER_SCALAR (coding_categories);
PDUMPER_REMEMBER_SCALAR (coding_priorities);
/* ISO2022 specific initialize routine. */
for (i = 0; i < 0x20; i++)
iso_code_class[i] = ISO_control_0;
for (i = 0x21; i < 0x7F; i++)
iso_code_class[i] = ISO_graphic_plane_0;
for (i = 0x80; i < 0xA0; i++)
iso_code_class[i] = ISO_control_1;
for (i = 0xA1; i < 0xFF; i++)
iso_code_class[i] = ISO_graphic_plane_1;
iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F;
iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF;
iso_code_class[ISO_CODE_SO] = ISO_shift_out;
iso_code_class[ISO_CODE_SI] = ISO_shift_in;
iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7;
iso_code_class[ISO_CODE_ESC] = ISO_escape;
iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2;
iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3;
iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer;
PDUMPER_REMEMBER_SCALAR (iso_code_class);
for (i = 0; i < 256; i++)
{
emacs_mule_bytes[i] = 1;
}
emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3;
emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3;
emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4;
emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4;
PDUMPER_REMEMBER_SCALAR (emacs_mule_bytes);
}
static void reset_coding_after_pdumper_load (void);
void
syms_of_coding (void)
{
staticpro (&Vcoding_system_hash_table);
Vcoding_system_hash_table = CALLN (Fmake_hash_table, QCtest, Qeq);
staticpro (&Vsjis_coding_system);
Vsjis_coding_system = Qnil;
staticpro (&Vbig5_coding_system);
Vbig5_coding_system = Qnil;
staticpro (&Vcode_conversion_reused_workbuf);
Vcode_conversion_reused_workbuf = Qnil;
staticpro (&Vcode_conversion_workbuf_name);
Vcode_conversion_workbuf_name = build_pure_c_string (" *code-conversion-work*");
reused_workbuf_in_use = 0;
PDUMPER_REMEMBER_SCALAR (reused_workbuf_in_use);
DEFSYM (Qcharset, "charset");
DEFSYM (Qtarget_idx, "target-idx");
DEFSYM (Qcoding_system_history, "coding-system-history");
Fset (Qcoding_system_history, Qnil);
/* Target FILENAME is the first argument. */
Fput (Qinsert_file_contents, Qtarget_idx, make_fixnum (0));
/* Target FILENAME is the third argument. */
Fput (Qwrite_region, Qtarget_idx, make_fixnum (2));
DEFSYM (Qcall_process, "call-process");
/* Target PROGRAM is the first argument. */
Fput (Qcall_process, Qtarget_idx, make_fixnum (0));
DEFSYM (Qcall_process_region, "call-process-region");
/* Target PROGRAM is the third argument. */
Fput (Qcall_process_region, Qtarget_idx, make_fixnum (2));
DEFSYM (Qstart_process, "start-process");
/* Target PROGRAM is the third argument. */
Fput (Qstart_process, Qtarget_idx, make_fixnum (2));
DEFSYM (Qopen_network_stream, "open-network-stream");
/* Target SERVICE is the fourth argument. */
Fput (Qopen_network_stream, Qtarget_idx, make_fixnum (3));
DEFSYM (Qunix, "unix");
DEFSYM (Qdos, "dos");
DEFSYM (Qmac, "mac");
DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system");
DEFSYM (Qundecided, "undecided");
DEFSYM (Qno_conversion, "no-conversion");
DEFSYM (Qraw_text, "raw-text");
DEFSYM (Qus_ascii, "us-ascii");
DEFSYM (Qiso_2022, "iso-2022");
DEFSYM (Qutf_8, "utf-8");
DEFSYM (Qutf_8_unix, "utf-8-unix");
DEFSYM (Qutf_8_emacs, "utf-8-emacs");
#if defined (WINDOWSNT) || defined (CYGWIN)
/* No, not utf-16-le: that one has a BOM. */
DEFSYM (Qutf_16le, "utf-16le");
#endif
DEFSYM (Qutf_16, "utf-16");
DEFSYM (Qbig, "big");
DEFSYM (Qlittle, "little");
DEFSYM (Qshift_jis, "shift-jis");
DEFSYM (Qbig5, "big5");
DEFSYM (Qcoding_system_p, "coding-system-p");
/* Error signaled when there's a problem with detecting a coding system. */
DEFSYM (Qcoding_system_error, "coding-system-error");
Fput (Qcoding_system_error, Qerror_conditions,
pure_list (Qcoding_system_error, Qerror));
Fput (Qcoding_system_error, Qerror_message,
build_pure_c_string ("Invalid coding system"));
DEFSYM (Qtranslation_table, "translation-table");
Fput (Qtranslation_table, Qchar_table_extra_slots, make_fixnum (2));
DEFSYM (Qtranslation_table_id, "translation-table-id");
/* Coding system emacs-mule and raw-text are for converting only
end-of-line format. */
DEFSYM (Qemacs_mule, "emacs-mule");
DEFSYM (QCcategory, ":category");
DEFSYM (QCmnemonic, ":mnemonic");
DEFSYM (QCdefault_char, ":default-char");
DEFSYM (QCdecode_translation_table, ":decode-translation-table");
DEFSYM (QCencode_translation_table, ":encode-translation-table");
DEFSYM (QCpost_read_conversion, ":post-read-conversion");
DEFSYM (QCpre_write_conversion, ":pre-write-conversion");
DEFSYM (QCascii_compatible_p, ":ascii-compatible-p");
Vcoding_category_table = make_nil_vector (coding_category_max);
staticpro (&Vcoding_category_table);
/* Followings are target of code detection. */
ASET (Vcoding_category_table, coding_category_iso_7,
intern_c_string ("coding-category-iso-7"));
ASET (Vcoding_category_table, coding_category_iso_7_tight,
intern_c_string ("coding-category-iso-7-tight"));
ASET (Vcoding_category_table, coding_category_iso_8_1,
intern_c_string ("coding-category-iso-8-1"));
ASET (Vcoding_category_table, coding_category_iso_8_2,
intern_c_string ("coding-category-iso-8-2"));
ASET (Vcoding_category_table, coding_category_iso_7_else,
intern_c_string ("coding-category-iso-7-else"));
ASET (Vcoding_category_table, coding_category_iso_8_else,
intern_c_string ("coding-category-iso-8-else"));
ASET (Vcoding_category_table, coding_category_utf_8_auto,
intern_c_string ("coding-category-utf-8-auto"));
ASET (Vcoding_category_table, coding_category_utf_8_nosig,
intern_c_string ("coding-category-utf-8"));
ASET (Vcoding_category_table, coding_category_utf_8_sig,
intern_c_string ("coding-category-utf-8-sig"));
ASET (Vcoding_category_table, coding_category_utf_16_be,
intern_c_string ("coding-category-utf-16-be"));
ASET (Vcoding_category_table, coding_category_utf_16_auto,
intern_c_string ("coding-category-utf-16-auto"));
ASET (Vcoding_category_table, coding_category_utf_16_le,
intern_c_string ("coding-category-utf-16-le"));
ASET (Vcoding_category_table, coding_category_utf_16_be_nosig,
intern_c_string ("coding-category-utf-16-be-nosig"));
ASET (Vcoding_category_table, coding_category_utf_16_le_nosig,
intern_c_string ("coding-category-utf-16-le-nosig"));
ASET (Vcoding_category_table, coding_category_charset,
intern_c_string ("coding-category-charset"));
ASET (Vcoding_category_table, coding_category_sjis,
intern_c_string ("coding-category-sjis"));
ASET (Vcoding_category_table, coding_category_big5,
intern_c_string ("coding-category-big5"));
ASET (Vcoding_category_table, coding_category_ccl,
intern_c_string ("coding-category-ccl"));
ASET (Vcoding_category_table, coding_category_emacs_mule,
intern_c_string ("coding-category-emacs-mule"));
/* Followings are NOT target of code detection. */
ASET (Vcoding_category_table, coding_category_raw_text,
intern_c_string ("coding-category-raw-text"));
ASET (Vcoding_category_table, coding_category_undecided,
intern_c_string ("coding-category-undecided"));
DEFSYM (Qinsufficient_source, "insufficient-source");
DEFSYM (Qinvalid_source, "invalid-source");
DEFSYM (Qinterrupted, "interrupted");
/* If a symbol has this property, evaluate the value to define the
symbol as a coding system. */
DEFSYM (Qcoding_system_define_form, "coding-system-define-form");
DEFSYM (Qignored, "ignored");
DEFSYM (Qutf_8_string_p, "utf-8-string-p");
defsubr (&Scoding_system_p);
defsubr (&Sread_coding_system);
defsubr (&Sread_non_nil_coding_system);
defsubr (&Scheck_coding_system);
defsubr (&Sdetect_coding_region);
defsubr (&Sdetect_coding_string);
defsubr (&Sfind_coding_systems_region_internal);
defsubr (&Sunencodable_char_position);
defsubr (&Scheck_coding_systems_region);
defsubr (&Sdecode_coding_region);
defsubr (&Sencode_coding_region);
defsubr (&Sdecode_coding_string);
defsubr (&Sencode_coding_string);
#ifdef ENABLE_UTF_8_CONVERTER_TEST
defsubr (&Sinternal_encode_string_utf_8);
defsubr (&Sinternal_decode_string_utf_8);
#endif /* ENABLE_UTF_8_CONVERTER_TEST */
defsubr (&Sdecode_sjis_char);
defsubr (&Sencode_sjis_char);
defsubr (&Sdecode_big5_char);
defsubr (&Sencode_big5_char);
defsubr (&Sset_terminal_coding_system_internal);
defsubr (&Sset_safe_terminal_coding_system_internal);
defsubr (&Sterminal_coding_system);
defsubr (&Sset_keyboard_coding_system_internal);
defsubr (&Skeyboard_coding_system);
defsubr (&Sfind_operation_coding_system);
defsubr (&Sset_coding_system_priority);
defsubr (&Sdefine_coding_system_internal);
defsubr (&Sdefine_coding_system_alias);
defsubr (&Scoding_system_put);
defsubr (&Scoding_system_base);
defsubr (&Scoding_system_plist);
defsubr (&Scoding_system_aliases);
defsubr (&Scoding_system_eol_type);
defsubr (&Scoding_system_priority_list);
DEFVAR_LISP ("coding-system-list", Vcoding_system_list,
doc: /* List of coding systems.
Do not alter the value of this variable manually. This variable should be
updated by the functions `define-coding-system' and
`define-coding-system-alias'. */);
Vcoding_system_list = Qnil;
DEFVAR_LISP ("coding-system-alist", Vcoding_system_alist,
doc: /* Alist of coding system names.
Each element is one element list of coding system name.
This variable is given to `completing-read' as COLLECTION argument.
Do not alter the value of this variable manually. This variable should be
updated by the functions `make-coding-system' and
`define-coding-system-alias'. */);
Vcoding_system_alist = Qnil;
DEFVAR_LISP ("coding-category-list", Vcoding_category_list,
doc: /* List of coding-categories (symbols) ordered by priority.
On detecting a coding system, Emacs tries code detection algorithms
associated with each coding-category one by one in this order. When
one algorithm agrees with a byte sequence of source text, the coding
system bound to the corresponding coding-category is selected.
Don't modify this variable directly, but use `set-coding-system-priority'. */);
{
int i;
Vcoding_category_list = Qnil;
for (i = coding_category_max - 1; i >= 0; i--)
Vcoding_category_list
= Fcons (AREF (Vcoding_category_table, i),
Vcoding_category_list);
}
DEFVAR_LISP ("coding-system-for-read", Vcoding_system_for_read,
doc: /* Specify the coding system for read operations.
It is useful to bind this variable with `let', but do not set it globally.
If the value is a coding system, it is used for decoding on read operation.
If not, an appropriate element is used from one of the coding system alists.
There are three such tables: `file-coding-system-alist',
`process-coding-system-alist', and `network-coding-system-alist'. */);
Vcoding_system_for_read = Qnil;
DEFVAR_LISP ("coding-system-for-write", Vcoding_system_for_write,
doc: /* Specify the coding system for write operations.
Programs bind this variable with `let', but you should not set it globally.
If the value is a coding system, it is used for encoding of output,
when writing it to a file and when sending it to a file or subprocess.
If this does not specify a coding system, an appropriate element
is used from one of the coding system alists.
There are three such tables: `file-coding-system-alist',
`process-coding-system-alist', and `network-coding-system-alist'.
For output to files, if the above procedure does not specify a coding system,
the value of `buffer-file-coding-system' is used. */);
Vcoding_system_for_write = Qnil;
DEFVAR_LISP ("last-coding-system-used", Vlast_coding_system_used,
doc: /*
Coding system used in the latest file or process I/O. */);
Vlast_coding_system_used = Qnil;
DEFVAR_LISP ("last-code-conversion-error", Vlast_code_conversion_error,
doc: /*
Error status of the last code conversion.
When an error was detected in the last code conversion, this variable
is set to one of the following symbols.
`insufficient-source'
`inconsistent-eol'
`invalid-source'
`interrupted'
`insufficient-memory'
When no error was detected, the value doesn't change. So, to check
the error status of a code conversion by this variable, you must
explicitly set this variable to nil before performing code
conversion. */);
Vlast_code_conversion_error = Qnil;
DEFVAR_BOOL ("inhibit-eol-conversion", inhibit_eol_conversion,
doc: /*
Non-nil means always inhibit code conversion of end-of-line format.
See info node `Coding Systems' and info node `Text and Binary' concerning
such conversion. */);
inhibit_eol_conversion = 0;
DEFVAR_BOOL ("inherit-process-coding-system", inherit_process_coding_system,
doc: /*
Non-nil means process buffer inherits coding system of process output.
Bind it to t if the process output is to be treated as if it were a file
read from some filesystem. */);
inherit_process_coding_system = 0;
DEFVAR_LISP ("file-coding-system-alist", Vfile_coding_system_alist,
doc: /*
Alist to decide a coding system to use for a file I/O operation.
The format is ((PATTERN . VAL) ...),
where PATTERN is a regular expression matching a file name,
VAL is a coding system, a cons of coding systems, or a function symbol.
If VAL is a coding system, it is used for both decoding and encoding
the file contents.
If VAL is a cons of coding systems, the car part is used for decoding,
and the cdr part is used for encoding.
If VAL is a function symbol, the function must return a coding system
or a cons of coding systems which are used as above. The function is
called with an argument that is a list of the arguments with which
`find-operation-coding-system' was called. If the function can't decide
a coding system, it can return `undecided' so that the normal
code-detection is performed.
See also the function `find-operation-coding-system'
and the variable `auto-coding-alist'. */);
Vfile_coding_system_alist = Qnil;
DEFVAR_LISP ("process-coding-system-alist", Vprocess_coding_system_alist,
doc: /*
Alist to decide a coding system to use for a process I/O operation.
The format is ((PATTERN . VAL) ...),
where PATTERN is a regular expression matching a program name,
VAL is a coding system, a cons of coding systems, or a function symbol.
If VAL is a coding system, it is used for both decoding what received
from the program and encoding what sent to the program.
If VAL is a cons of coding systems, the car part is used for decoding,
and the cdr part is used for encoding.
If VAL is a function symbol, the function must return a coding system
or a cons of coding systems which are used as above.
See also the function `find-operation-coding-system'. */);
Vprocess_coding_system_alist = Qnil;
DEFVAR_LISP ("network-coding-system-alist", Vnetwork_coding_system_alist,
doc: /*
Alist to decide a coding system to use for a network I/O operation.
The format is ((PATTERN . VAL) ...),
where PATTERN is a regular expression matching a network service name
or is a port number to connect to,
VAL is a coding system, a cons of coding systems, or a function symbol.
If VAL is a coding system, it is used for both decoding what received
from the network stream and encoding what sent to the network stream.
If VAL is a cons of coding systems, the car part is used for decoding,
and the cdr part is used for encoding.
If VAL is a function symbol, the function must return a coding system
or a cons of coding systems which are used as above.
See also the function `find-operation-coding-system'. */);
Vnetwork_coding_system_alist = Qnil;
DEFVAR_LISP ("locale-coding-system", Vlocale_coding_system,
doc: /* Coding system to use with system messages.
Also used for decoding keyboard input on X Window system, and for
encoding standard output and error streams. */);
Vlocale_coding_system = Qnil;
/* The eol mnemonics are reset in startup.el system-dependently. */
DEFVAR_LISP ("eol-mnemonic-unix", eol_mnemonic_unix,
doc: /*
String displayed in mode line for UNIX-like (LF) end-of-line format. */);
eol_mnemonic_unix = build_pure_c_string (":");
DEFVAR_LISP ("eol-mnemonic-dos", eol_mnemonic_dos,
doc: /*
String displayed in mode line for DOS-like (CRLF) end-of-line format. */);
eol_mnemonic_dos = build_pure_c_string ("\\");
DEFVAR_LISP ("eol-mnemonic-mac", eol_mnemonic_mac,
doc: /*
String displayed in mode line for MAC-like (CR) end-of-line format. */);
eol_mnemonic_mac = build_pure_c_string ("/");
DEFVAR_LISP ("eol-mnemonic-undecided", eol_mnemonic_undecided,
doc: /*
String displayed in mode line when end-of-line format is not yet determined. */);
eol_mnemonic_undecided = build_pure_c_string (":");
DEFVAR_LISP ("enable-character-translation", Venable_character_translation,
doc: /*
Non-nil enables character translation while encoding and decoding. */);
Venable_character_translation = Qt;
DEFVAR_LISP ("standard-translation-table-for-decode",
Vstandard_translation_table_for_decode,
doc: /* Table for translating characters while decoding. */);
Vstandard_translation_table_for_decode = Qnil;
DEFVAR_LISP ("standard-translation-table-for-encode",
Vstandard_translation_table_for_encode,
doc: /* Table for translating characters while encoding. */);
Vstandard_translation_table_for_encode = Qnil;
DEFVAR_LISP ("charset-revision-table", Vcharset_revision_table,
doc: /* Alist of charsets vs revision numbers.
While encoding, if a charset (car part of an element) is found,
designate it with the escape sequence identifying revision (cdr part
of the element). */);
Vcharset_revision_table = Qnil;
DEFVAR_LISP ("default-process-coding-system",
Vdefault_process_coding_system,
doc: /* Cons of coding systems used for process I/O by default.
The car part is used for decoding a process output,
the cdr part is used for encoding a text to be sent to a process. */);
Vdefault_process_coding_system = Qnil;
DEFVAR_LISP ("latin-extra-code-table", Vlatin_extra_code_table,
doc: /*
Table of extra Latin codes in the range 128..159 (inclusive).
This is a vector of length 256.
If Nth element is non-nil, the existence of code N in a file
\(or output of subprocess) doesn't prevent it to be detected as
a coding system of ISO 2022 variant which has a flag
`accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file
or reading output of a subprocess.
Only 128th through 159th elements have a meaning. */);
Vlatin_extra_code_table = make_nil_vector (256);
DEFVAR_LISP ("select-safe-coding-system-function",
Vselect_safe_coding_system_function,
doc: /*
Function to call to select safe coding system for encoding a text.
If set, this function is called to force a user to select a proper
coding system which can encode the text in the case that a default
coding system used in each operation can't encode the text. The
function should take care that the buffer is not modified while
the coding system is being selected.
The default value is `select-safe-coding-system' (which see). */);
Vselect_safe_coding_system_function = Qnil;
DEFVAR_BOOL ("coding-system-require-warning",
coding_system_require_warning,
doc: /* Internal use only.
If non-nil, on writing a file, `select-safe-coding-system-function' is
called even if `coding-system-for-write' is non-nil. The command
`universal-coding-system-argument' binds this variable to t temporarily. */);
coding_system_require_warning = 0;
DEFVAR_BOOL ("inhibit-iso-escape-detection",
inhibit_iso_escape_detection,
doc: /*
If non-nil, Emacs ignores ISO-2022 escape sequences during code detection.
When Emacs reads text, it tries to detect how the text is encoded.
This code detection is sensitive to escape sequences. If Emacs sees
a valid ISO-2022 escape sequence, it assumes the text is encoded in one
of the ISO2022 encodings, and decodes text by the corresponding coding
system (e.g. `iso-2022-7bit').
However, there may be a case that you want to read escape sequences in
a file as is. In such a case, you can set this variable to non-nil.
Then the code detection will ignore any escape sequences, and no text is
detected as encoded in some ISO-2022 encoding. The result is that all
escape sequences become visible in a buffer.
The default value is nil, and it is strongly recommended not to change
it. That is because many Emacs Lisp source files that contain
non-ASCII characters are encoded by the coding system `iso-2022-7bit'
in Emacs's distribution, and they won't be decoded correctly on
reading if you suppress escape sequence detection.
The other way to read escape sequences in a file without decoding is
to explicitly specify some coding system that doesn't use ISO-2022
escape sequence (e.g., `latin-1') on reading by \\[universal-coding-system-argument]. */);
inhibit_iso_escape_detection = 0;
DEFVAR_BOOL ("inhibit-nul-byte-detection",
inhibit_nul_byte_detection,
doc: /* If non-nil, Emacs ignores NUL bytes on code detection.
By default, Emacs treats it as binary data, and does not attempt to
decode it. The effect is as if you specified `no-conversion' for
reading that text.
Set this to non-nil when a regular text happens to include NUL bytes.
Examples are Index nodes of Info files and NUL-byte delimited output
from GNU Find and GNU Grep. Emacs will then ignore the NUL bytes and
decode text as usual. */);
inhibit_nul_byte_detection = 0;
DEFVAR_BOOL ("disable-ascii-optimization", disable_ascii_optimization,
doc: /* If non-nil, Emacs does not optimize code decoder for ASCII files.
Internal use only. Remove after the experimental optimizer becomes stable. */);
disable_ascii_optimization = 0;
DEFVAR_LISP ("translation-table-for-input", Vtranslation_table_for_input,
doc: /* Char table for translating self-inserting characters.
This is applied to the result of input methods, not their input.
See also `keyboard-translate-table'.
Use of this variable for character code unification was rendered
obsolete in Emacs 23.1 and later, since Unicode is now the basis of
internal character representation. */);
Vtranslation_table_for_input = Qnil;
Lisp_Object args[coding_arg_undecided_max];
memclear (args, sizeof args);
Lisp_Object plist[] =
{
QCname,
args[coding_arg_name] = Qno_conversion,
QCmnemonic,
args[coding_arg_mnemonic] = make_fixnum ('='),
intern_c_string (":coding-type"),
args[coding_arg_coding_type] = Qraw_text,
QCascii_compatible_p,
args[coding_arg_ascii_compatible_p] = Qt,
QCdefault_char,
args[coding_arg_default_char] = make_fixnum (0),
intern_c_string (":for-unibyte"),
args[coding_arg_for_unibyte] = Qt,
intern_c_string (":docstring"),
(build_pure_c_string
("Do no conversion.\n"
"\n"
"When you visit a file with this coding, the file is read into a\n"
"unibyte buffer as is, thus each byte of a file is treated as a\n"
"character.")),
intern_c_string (":eol-type"),
args[coding_arg_eol_type] = Qunix,
};
args[coding_arg_plist] = CALLMANY (Flist, plist);
Fdefine_coding_system_internal (coding_arg_max, args);
plist[1] = args[coding_arg_name] = Qundecided;
plist[3] = args[coding_arg_mnemonic] = make_fixnum ('-');
plist[5] = args[coding_arg_coding_type] = Qundecided;
/* This is already set.
plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */
plist[8] = intern_c_string (":charset-list");
plist[9] = args[coding_arg_charset_list] = list1 (Qascii);
plist[11] = args[coding_arg_for_unibyte] = Qnil;
plist[13] = build_pure_c_string ("No conversion on encoding, "
"automatic conversion on decoding.");
plist[15] = args[coding_arg_eol_type] = Qnil;
args[coding_arg_plist] = CALLMANY (Flist, plist);
args[coding_arg_undecided_inhibit_nul_byte_detection] = make_fixnum (0);
args[coding_arg_undecided_inhibit_iso_escape_detection] = make_fixnum (0);
Fdefine_coding_system_internal (coding_arg_undecided_max, args);
setup_coding_system (Qno_conversion, &safe_terminal_coding);
for (int i = 0; i < coding_category_max; i++)
Fset (AREF (Vcoding_category_table, i), Qno_conversion);
pdumper_do_now_and_after_load (reset_coding_after_pdumper_load);
}
static void
reset_coding_after_pdumper_load (void)
{
if (!dumped_with_pdumper_p ())
return;
for (struct coding_system *this = &coding_categories[0];
this < &coding_categories[coding_category_max];
++this)
{
int id = this->id;
if (id >= 0)
{
/* Need to rebuild the coding system object because we
persisted it as a scalar and it's full of gunk that's now
invalid. */
memset (this, 0, sizeof (*this));
setup_coding_system (CODING_ID_NAME (id), this);
}
}
/* In temacs the below is done by mule-conf.el, because we need to
define us-ascii first. But in dumped Emacs us-ascii is restored
by the above loop, and mule-conf.el will not be loaded, so we set
it up now; otherwise safe_terminal_coding will remain zeroed. */
Fset_safe_terminal_coding_system_internal (Qus_ascii);
}
|