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
|
/*
* tclUtil.c --
*
* This file contains utility functions that are used by many Tcl
* commands.
*
* Copyright (c) 1987-1993 The Regents of the University of California.
* Copyright (c) 1994-1998 Sun Microsystems, Inc.
* Copyright (c) 2001 by Kevin B. Kenny. All rights reserved.
*
* See the file "license.terms" for information on usage and redistribution of
* this file, and for a DISCLAIMER OF ALL WARRANTIES.
*/
#include "tclInt.h"
#include "tclParse.h"
#include <math.h>
/*
* The absolute pathname of the executable in which this Tcl library is
* running.
*/
static ProcessGlobalValue executableName = {
0, 0, NULL, NULL, NULL, NULL, NULL
};
/*
* The following values are used in the flags arguments of Tcl*Scan*Element
* and Tcl*Convert*Element. The values TCL_DONT_USE_BRACES and
* TCL_DONT_QUOTE_HASH are defined in tcl.h, like so:
*
#define TCL_DONT_USE_BRACES 1
#define TCL_DONT_QUOTE_HASH 8
*
* Those are public flag bits which callers of the public routines
* Tcl_Convert*Element() can use to indicate:
*
* TCL_DONT_USE_BRACES - 1 means the caller is insisting that brace
* quoting not be used when converting the list
* element.
* TCL_DONT_QUOTE_HASH - 1 means the caller insists that a leading hash
* character ('#') should *not* be quoted. This
* is appropriate when the caller can guarantee
* the element is not the first element of a
* list, so [eval] cannot mis-parse the element
* as a comment.
*
* The remaining values which can be carried by the flags of these routines
* are for internal use only. Make sure they do not overlap with the public
* values above.
*
* The Tcl*Scan*Element() routines make a determination which of 4 modes of
* conversion is most appropriate for Tcl*Convert*Element() to perform, and
* sets two bits of the flags value to indicate the mode selected.
*
* CONVERT_NONE The element needs no quoting. Its literal string is
* suitable as is.
* CONVERT_BRACE The conversion should be enclosing the literal string
* in braces.
* CONVERT_ESCAPE The conversion should be using backslashes to escape
* any characters in the string that require it.
* CONVERT_MASK A mask value used to extract the conversion mode from
* the flags argument.
* Also indicates a strange conversion mode where all
* special characters are escaped with backslashes
* *except for braces*. This is a strange and unnecessary
* case, but it's part of the historical way in which
* lists have been formatted in Tcl. To experiment with
* removing this case, set the value of COMPAT to 0.
*
* One last flag value is used only by callers of TclScanElement(). The flag
* value produced by a call to Tcl*Scan*Element() will never leave this bit
* set.
*
* CONVERT_ANY The caller of TclScanElement() declares it can make no
* promise about what public flags will be passed to the
* matching call of TclConvertElement(). As such,
* TclScanElement() has to determine the worst case
* destination buffer length over all possibilities, and
* in other cases this means an overestimate of the
* required size.
*
* For more details, see the comments on the Tcl*Scan*Element and
* Tcl*Convert*Element routines.
*/
#define COMPAT 1
#define CONVERT_NONE 0
#define CONVERT_BRACE 2
#define CONVERT_ESCAPE 4
#define CONVERT_MASK (CONVERT_BRACE | CONVERT_ESCAPE)
#define CONVERT_ANY 16
/*
* The following key is used by Tcl_PrintDouble and TclPrecTraceProc to
* access the precision to be used for double formatting.
*/
static Tcl_ThreadDataKey precisionKey;
/*
* Prototypes for functions defined later in this file.
*/
static void ClearHash(Tcl_HashTable *tablePtr);
static void FreeProcessGlobalValue(ClientData clientData);
static void FreeThreadHash(ClientData clientData);
static Tcl_HashTable * GetThreadHash(Tcl_ThreadDataKey *keyPtr);
static int SetEndOffsetFromAny(Tcl_Interp *interp,
Tcl_Obj *objPtr);
static void UpdateStringOfEndOffset(Tcl_Obj *objPtr);
/*
* The following is the Tcl object type definition for an object that
* represents a list index in the form, "end-offset". It is used as a
* performance optimization in TclGetIntForIndex. The internal rep is an
* integer, so no memory management is required for it.
*/
const Tcl_ObjType tclEndOffsetType = {
"end-offset", /* name */
NULL, /* freeIntRepProc */
NULL, /* dupIntRepProc */
UpdateStringOfEndOffset, /* updateStringProc */
SetEndOffsetFromAny
};
/*
* * STRING REPRESENTATION OF LISTS * * *
*
* The next several routines implement the conversions of strings to and from
* Tcl lists. To understand their operation, the rules of parsing and
* generating the string representation of lists must be known. Here we
* describe them in one place.
*
* A list is made up of zero or more elements. Any string is a list if it is
* made up of alternating substrings of element-separating ASCII whitespace
* and properly formatted elements.
*
* The ASCII characters which can make up the whitespace between list elements
* are:
*
* \u0009 \t TAB
* \u000A \n NEWLINE
* \u000B \v VERTICAL TAB
* \u000C \f FORM FEED
* \u000D \r CARRIAGE RETURN
* \u0020 SPACE
*
* NOTE: differences between this and other places where Tcl defines a role
* for "whitespace".
*
* * Unlike command parsing, here NEWLINE is just another whitespace
* character; its role as a command terminator in a script has no
* importance here.
*
* * Unlike command parsing, the BACKSLASH NEWLINE sequence is not
* considered to be a whitespace character.
*
* * Other Unicode whitespace characters (recognized by [string is space]
* or Tcl_UniCharIsSpace()) do not play any role as element separators
* in Tcl lists.
*
* * The NUL byte ought not appear, as it is not in strings properly
* encoded for Tcl, but if it is present, it is not treated as
* separating whitespace, or a string terminator. It is just another
* character in a list element.
*
* The interpretaton of a formatted substring as a list element follows rules
* similar to the parsing of the words of a command in a Tcl script. Backslash
* substitution plays a key role, and is defined exactly as it is in command
* parsing. The same routine, TclParseBackslash() is used in both command
* parsing and list parsing.
*
* NOTE: This means that if and when backslash substitution rules ever change
* for command parsing, the interpretation of strings as lists also changes.
*
* Backslash substitution replaces an "escape sequence" of one or more
* characters starting with
* \u005c \ BACKSLASH
* with a single character. The one character escape sequent case happens only
* when BACKSLASH is the last character in the string. In all other cases, the
* escape sequence is at least two characters long.
*
* The formatted substrings are interpreted as element values according to the
* following cases:
*
* * If the first character of a formatted substring is
* \u007b { OPEN BRACE
* then the end of the substring is the matching
* \u007d } CLOSE BRACE
* character, where matching is determined by counting nesting levels, and
* not including any brace characters that are contained within a backslash
* escape sequence in the nesting count. Having found the matching brace,
* all characters between the braces are the string value of the element.
* If no matching close brace is found before the end of the string, the
* string is not a Tcl list. If the character following the close brace is
* not an element separating whitespace character, or the end of the string,
* then the string is not a Tcl list.
*
* NOTE: this differs from a brace-quoted word in the parsing of a Tcl
* command only in its treatment of the backslash-newline sequence. In a
* list element, the literal characters in the backslash-newline sequence
* become part of the element value. In a script word, conversion to a
* single SPACE character is done.
*
* NOTE: Most list element values can be represented by a formatted
* substring using brace quoting. The exceptions are any element value that
* includes an unbalanced brace not in a backslash escape sequence, and any
* value that ends with a backslash not itself in a backslash escape
* sequence.
*
* * If the first character of a formatted substring is
* \u0022 " QUOTE
* then the end of the substring is the next QUOTE character, not counting
* any QUOTE characters that are contained within a backslash escape
* sequence. If no next QUOTE is found before the end of the string, the
* string is not a Tcl list. If the character following the closing QUOTE is
* not an element separating whitespace character, or the end of the string,
* then the string is not a Tcl list. Having found the limits of the
* substring, the element value is produced by performing backslash
* substitution on the character sequence between the open and close QUOTEs.
*
* NOTE: Any element value can be represented by this style of formatting,
* given suitable choice of backslash escape sequences.
*
* * All other formatted substrings are terminated by the next element
* separating whitespace character in the string. Having found the limits
* of the substring, the element value is produced by performing backslash
* substitution on it.
*
* NOTE: Any element value can be represented by this style of formatting,
* given suitable choice of backslash escape sequences, with one exception.
* The empty string cannot be represented as a list element without the use
* of either braces or quotes to delimit it.
*
* This collection of parsing rules is implemented in the routine
* TclFindElement().
*
* In order to produce lists that can be parsed by these rules, we need the
* ability to distinguish between characters that are part of a list element
* value from characters providing syntax that define the structure of the
* list. This means that our code that generates lists must at a minimum be
* able to produce escape sequences for the 10 characters identified above
* that have significance to a list parser.
*
* * * CANONICAL LISTS * * * * *
*
* In addition to the basic rules for parsing strings into Tcl lists, there
* are additional properties to be met by the set of list values that are
* generated by Tcl. Such list values are often said to be in "canonical
* form":
*
* * When any canonical list is evaluated as a Tcl script, it is a script of
* either zero commands (an empty list) or exactly one command. The command
* word is exactly the first element of the list, and each argument word is
* exactly one of the following elements of the list. This means that any
* characters that have special meaning during script evaluation need
* special treatment when canonical lists are produced:
*
* * Whitespace between elements may not include NEWLINE.
* * The command terminating character,
* \u003b ; SEMICOLON
* must be BRACEd, QUOTEd, or escaped so that it does not terminate the
* command prematurely.
* * Any of the characters that begin substitutions in scripts,
* \u0024 $ DOLLAR
* \u005b [ OPEN BRACKET
* \u005c \ BACKSLASH
* need to be BRACEd or escaped.
* * In any list where the first character of the first element is
* \u0023 # HASH
* that HASH character must be BRACEd, QUOTEd, or escaped so that it
* does not convert the command into a comment.
* * Any list element that contains the character sequence BACKSLASH
* NEWLINE cannot be formatted with BRACEs. The BACKSLASH character
* must be represented by an escape sequence, and unless QUOTEs are
* used, the NEWLINE must be as well.
*
* * It is also guaranteed that one can use a canonical list as a building
* block of a larger script within command substitution, as in this example:
* set script "puts \[[list $cmd $arg]]"; eval $script
* To support this usage, any appearance of the character
* \u005d ] CLOSE BRACKET
* in a list element must be BRACEd, QUOTEd, or escaped.
*
* * Finally it is guaranteed that enclosing a canonical list in braces
* produces a new value that is also a canonical list. This new list has
* length 1, and its only element is the original canonical list. This same
* guarantee also makes it possible to construct scripts where an argument
* word is given a list value by enclosing the canonical form of that list
* in braces:
* set script "puts {[list $one $two $three]}"; eval $script
* This sort of coding was once fairly common, though it's become more
* idiomatic to see the following instead:
* set script [list puts [list $one $two $three]]; eval $script
* In order to support this guarantee, every canonical list must have
* balance when counting those braces that are not in escape sequences.
*
* Within these constraints, the canonical list generation routines
* TclScanElement() and TclConvertElement() attempt to generate the string for
* any list that is easiest to read. When an element value is itself
* acceptable as the formatted substring, it is usually used (CONVERT_NONE).
* When some quoting or escaping is required, use of BRACEs (CONVERT_BRACE) is
* usually preferred over the use of escape sequences (CONVERT_ESCAPE). There
* are some exceptions to both of these preferences for reasons of code
* simplicity, efficiency, and continuation of historical habits. Canonical
* lists never use the QUOTE formatting to delimit their elements because that
* form of quoting does not nest, which makes construction of nested lists far
* too much trouble. Canonical lists always use only a single SPACE character
* for element-separating whitespace.
*
* * * FUTURE CONSIDERATIONS * * *
*
* When a list element requires quoting or escaping due to a CLOSE BRACKET
* character or an internal QUOTE character, a strange formatting mode is
* recommended. For example, if the value "a{b]c}d" is converted by the usual
* modes:
*
* CONVERT_BRACE: a{b]c}d => {a{b]c}d}
* CONVERT_ESCAPE: a{b]c}d => a\{b\]c\}d
*
* we get perfectly usable formatted list elements. However, this is not what
* Tcl releases have been producing. Instead, we have:
*
* CONVERT_MASK: a{b]c}d => a{b\]c}d
*
* where the CLOSE BRACKET is escaped, but the BRACEs are not. The same effect
* can be seen replacing ] with " in this example. There does not appear to be
* any functional or aesthetic purpose for this strange additional mode. The
* sole purpose I can see for preserving it is to keep generating the same
* formatted lists programmers have become accustomed to, and perhaps written
* tests to expect. That is, compatibility only. The additional code
* complexity required to support this mode is significant. The lines of code
* supporting it are delimited in the routines below with #if COMPAT
* directives. This makes it easy to experiment with eliminating this
* formatting mode simply with "#define COMPAT 0" above. I believe this is
* worth considering.
*
* Another consideration is the treatment of QUOTE characters in list
* elements. TclConvertElement() must have the ability to produce the escape
* sequence \" so that when a list element begins with a QUOTE we do not
* confuse that first character with a QUOTE used as list syntax to define
* list structure. However, that is the only place where QUOTE characters need
* quoting. In this way, handling QUOTE could really be much more like the way
* we handle HASH which also needs quoting and escaping only in particular
* situations. Following up this could increase the set of list elements that
* can use the CONVERT_NONE formatting mode.
*
* More speculative is that the demands of canonical list form require brace
* balance for the list as a whole, while the current implementation achieves
* this by establishing brace balance for every element.
*
* Finally, a reminder that the rules for parsing and formatting lists are
* closely tied together with the rules for parsing and evaluating scripts,
* and will need to evolve in sync.
*/
/*
*----------------------------------------------------------------------
*
* TclMaxListLength --
*
* Given 'bytes' pointing to 'numBytes' bytes, scan through them and
* count the number of whitespace runs that could be list element
* separators. If 'numBytes' is -1, scan to the terminating '\0'. Not a
* full list parser. Typically used to get a quick and dirty overestimate
* of length size in order to allocate space for an actual list parser to
* operate with.
*
* Results:
* Returns the largest number of list elements that could possibly be in
* this string, interpreted as a Tcl list. If 'endPtr' is not NULL,
* writes a pointer to the end of the string scanned there.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
TclMaxListLength(
const char *bytes,
int numBytes,
const char **endPtr)
{
int count = 0;
if ((numBytes == 0) || ((numBytes == -1) && (*bytes == '\0'))) {
/* Empty string case - quick exit */
goto done;
}
/*
* No list element before leading white space.
*/
count += 1 - TclIsSpaceProc(*bytes);
/*
* Count white space runs as potential element separators.
*/
while (numBytes) {
if ((numBytes == -1) && (*bytes == '\0')) {
break;
}
if (TclIsSpaceProc(*bytes)) {
/*
* Space run started; bump count.
*/
count++;
do {
bytes++;
numBytes -= (numBytes != -1);
} while (numBytes && TclIsSpaceProc(*bytes));
if ((numBytes == 0) || ((numBytes == -1) && (*bytes == '\0'))) {
break;
}
/*
* (*bytes) is non-space; return to counting state.
*/
}
bytes++;
numBytes -= (numBytes != -1);
}
/*
* No list element following trailing white space.
*/
count -= TclIsSpaceProc(bytes[-1]);
done:
if (endPtr) {
*endPtr = bytes;
}
return count;
}
/*
*----------------------------------------------------------------------
*
* TclFindElement --
*
* Given a pointer into a Tcl list, locate the first (or next) element in
* the list.
*
* Results:
* The return value is normally TCL_OK, which means that the element was
* successfully located. If TCL_ERROR is returned it means that list
* didn't have proper list structure; the interp's result contains a more
* detailed error message.
*
* If TCL_OK is returned, then *elementPtr will be set to point to the
* first element of list, and *nextPtr will be set to point to the
* character just after any white space following the last character
* that's part of the element. If this is the last argument in the list,
* then *nextPtr will point just after the last character in the list
* (i.e., at the character at list+listLength). If sizePtr is non-NULL,
* *sizePtr is filled in with the number of bytes in the element. If the
* element is in braces, then *elementPtr will point to the character
* after the opening brace and *sizePtr will not include either of the
* braces. If there isn't an element in the list, *sizePtr will be zero,
* and both *elementPtr and *nextPtr will point just after the last
* character in the list. If literalPtr is non-NULL, *literalPtr is set
* to a boolean value indicating whether the substring returned as the
* values of **elementPtr and *sizePtr is the literal value of a list
* element. If not, a call to TclCopyAndCollapse() is needed to produce
* the actual value of the list element. Note: this function does NOT
* collapse backslash sequences, but uses *literalPtr to tell callers
* when it is required for them to do so.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
TclFindElement(
Tcl_Interp *interp, /* Interpreter to use for error reporting. If
* NULL, then no error message is left after
* errors. */
const char *list, /* Points to the first byte of a string
* containing a Tcl list with zero or more
* elements (possibly in braces). */
int listLength, /* Number of bytes in the list's string. */
const char **elementPtr, /* Where to put address of first significant
* character in first element of list. */
const char **nextPtr, /* Fill in with location of character just
* after all white space following end of
* argument (next arg or end of list). */
int *sizePtr, /* If non-zero, fill in with size of
* element. */
int *literalPtr) /* If non-zero, fill in with non-zero/zero to
* indicate that the substring of *sizePtr
* bytes starting at **elementPtr is/is not
* the literal list element and therefore
* does not/does require a call to
* TclCopyAndCollapse() by the caller. */
{
const char *p = list;
const char *elemStart; /* Points to first byte of first element. */
const char *limit; /* Points just after list's last byte. */
int openBraces = 0; /* Brace nesting level during parse. */
int inQuotes = 0;
int size = 0; /* lint. */
int numChars;
int literal = 1;
const char *p2;
/*
* Skim off leading white space and check for an opening brace or quote.
* We treat embedded NULLs in the list as bytes belonging to a list
* element.
*/
limit = (list + listLength);
while ((p < limit) && (TclIsSpaceProc(*p))) {
p++;
}
if (p == limit) { /* no element found */
elemStart = limit;
goto done;
}
if (*p == '{') {
openBraces = 1;
p++;
} else if (*p == '"') {
inQuotes = 1;
p++;
}
elemStart = p;
/*
* Find element's end (a space, close brace, or the end of the string).
*/
while (p < limit) {
switch (*p) {
/*
* Open brace: don't treat specially unless the element is in
* braces. In this case, keep a nesting count.
*/
case '{':
if (openBraces != 0) {
openBraces++;
}
break;
/*
* Close brace: if element is in braces, keep nesting count and
* quit when the last close brace is seen.
*/
case '}':
if (openBraces > 1) {
openBraces--;
} else if (openBraces == 1) {
size = (p - elemStart);
p++;
if ((p >= limit) || TclIsSpaceProc(*p)) {
goto done;
}
/*
* Garbage after the closing brace; return an error.
*/
if (interp != NULL) {
p2 = p;
while ((p2 < limit) && (!TclIsSpaceProc(*p2))
&& (p2 < p+20)) {
p2++;
}
Tcl_SetObjResult(interp, Tcl_ObjPrintf(
"list element in braces followed by \"%.*s\" "
"instead of space", (int) (p2-p), p));
Tcl_SetErrorCode(interp, "TCL", "VALUE", "LIST", "JUNK",
NULL);
}
return TCL_ERROR;
}
break;
/*
* Backslash: skip over everything up to the end of the backslash
* sequence.
*/
case '\\':
if (openBraces == 0) {
/*
* A backslash sequence not within a brace quoted element
* means the value of the element is different from the
* substring we are parsing. A call to TclCopyAndCollapse() is
* needed to produce the element value. Inform the caller.
*/
literal = 0;
}
TclParseBackslash(p, limit - p, &numChars, NULL);
p += (numChars - 1);
break;
/*
* Space: ignore if element is in braces or quotes; otherwise
* terminate element.
*/
case ' ':
case '\f':
case '\n':
case '\r':
case '\t':
case '\v':
if ((openBraces == 0) && !inQuotes) {
size = (p - elemStart);
goto done;
}
break;
/*
* Double-quote: if element is in quotes then terminate it.
*/
case '"':
if (inQuotes) {
size = (p - elemStart);
p++;
if ((p >= limit) || TclIsSpaceProc(*p)) {
goto done;
}
/*
* Garbage after the closing quote; return an error.
*/
if (interp != NULL) {
p2 = p;
while ((p2 < limit) && (!TclIsSpaceProc(*p2))
&& (p2 < p+20)) {
p2++;
}
Tcl_SetObjResult(interp, Tcl_ObjPrintf(
"list element in quotes followed by \"%.*s\" "
"instead of space", (int) (p2-p), p));
Tcl_SetErrorCode(interp, "TCL", "VALUE", "LIST", "JUNK",
NULL);
}
return TCL_ERROR;
}
break;
}
p++;
}
/*
* End of list: terminate element.
*/
if (p == limit) {
if (openBraces != 0) {
if (interp != NULL) {
Tcl_SetObjResult(interp, Tcl_NewStringObj(
"unmatched open brace in list", -1));
Tcl_SetErrorCode(interp, "TCL", "VALUE", "LIST", "BRACE",
NULL);
}
return TCL_ERROR;
} else if (inQuotes) {
if (interp != NULL) {
Tcl_SetObjResult(interp, Tcl_NewStringObj(
"unmatched open quote in list", -1));
Tcl_SetErrorCode(interp, "TCL", "VALUE", "LIST", "QUOTE",
NULL);
}
return TCL_ERROR;
}
size = (p - elemStart);
}
done:
while ((p < limit) && (TclIsSpaceProc(*p))) {
p++;
}
*elementPtr = elemStart;
*nextPtr = p;
if (sizePtr != 0) {
*sizePtr = size;
}
if (literalPtr != 0) {
*literalPtr = literal;
}
return TCL_OK;
}
/*
*----------------------------------------------------------------------
*
* TclCopyAndCollapse --
*
* Copy a string and substitute all backslash escape sequences
*
* Results:
* Count bytes get copied from src to dst. Along the way, backslash
* sequences are substituted in the copy. After scanning count bytes from
* src, a null character is placed at the end of dst. Returns the number
* of bytes that got written to dst.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
TclCopyAndCollapse(
int count, /* Number of byte to copy from src. */
const char *src, /* Copy from here... */
char *dst) /* ... to here. */
{
int newCount = 0;
while (count > 0) {
char c = *src;
if (c == '\\') {
int numRead;
int backslashCount = TclParseBackslash(src, count, &numRead, dst);
dst += backslashCount;
newCount += backslashCount;
src += numRead;
count -= numRead;
} else {
*dst = c;
dst++;
newCount++;
src++;
count--;
}
}
*dst = 0;
return newCount;
}
/*
*----------------------------------------------------------------------
*
* Tcl_SplitList --
*
* Splits a list up into its constituent fields.
*
* Results
* The return value is normally TCL_OK, which means that the list was
* successfully split up. If TCL_ERROR is returned, it means that "list"
* didn't have proper list structure; the interp's result will contain a
* more detailed error message.
*
* *argvPtr will be filled in with the address of an array whose elements
* point to the elements of list, in order. *argcPtr will get filled in
* with the number of valid elements in the array. A single block of
* memory is dynamically allocated to hold both the argv array and a copy
* of the list (with backslashes and braces removed in the standard way).
* The caller must eventually free this memory by calling free() on
* *argvPtr. Note: *argvPtr and *argcPtr are only modified if the
* function returns normally.
*
* Side effects:
* Memory is allocated.
*
*----------------------------------------------------------------------
*/
int
Tcl_SplitList(
Tcl_Interp *interp, /* Interpreter to use for error reporting. If
* NULL, no error message is left. */
const char *list, /* Pointer to string with list structure. */
int *argcPtr, /* Pointer to location to fill in with the
* number of elements in the list. */
const char ***argvPtr) /* Pointer to place to store pointer to array
* of pointers to list elements. */
{
const char **argv, *end, *element;
char *p;
int length, size, i, result, elSize;
/*
* Allocate enough space to work in. A (const char *) for each (possible)
* list element plus one more for terminating NULL, plus as many bytes as
* in the original string value, plus one more for a terminating '\0'.
* Space used to hold element separating white space in the original
* string gets re-purposed to hold '\0' characters in the argv array.
*/
size = TclMaxListLength(list, -1, &end) + 1;
length = end - list;
argv = ckalloc((size * sizeof(char *)) + length + 1);
for (i = 0, p = ((char *) argv) + size*sizeof(char *);
*list != 0; i++) {
const char *prevList = list;
int literal;
result = TclFindElement(interp, list, length, &element, &list,
&elSize, &literal);
length -= (list - prevList);
if (result != TCL_OK) {
ckfree(argv);
return result;
}
if (*element == 0) {
break;
}
if (i >= size) {
ckfree(argv);
if (interp != NULL) {
Tcl_SetObjResult(interp, Tcl_NewStringObj(
"internal error in Tcl_SplitList", -1));
Tcl_SetErrorCode(interp, "TCL", "INTERNAL", "Tcl_SplitList",
NULL);
}
return TCL_ERROR;
}
argv[i] = p;
if (literal) {
memcpy(p, element, (size_t) elSize);
p += elSize;
*p = 0;
p++;
} else {
p += 1 + TclCopyAndCollapse(elSize, element, p);
}
}
argv[i] = NULL;
*argvPtr = argv;
*argcPtr = i;
return TCL_OK;
}
/*
*----------------------------------------------------------------------
*
* Tcl_ScanElement --
*
* This function is a companion function to Tcl_ConvertElement. It scans
* a string to see what needs to be done to it (e.g. add backslashes or
* enclosing braces) to make the string into a valid Tcl list element.
*
* Results:
* The return value is an overestimate of the number of bytes that will
* be needed by Tcl_ConvertElement to produce a valid list element from
* src. The word at *flagPtr is filled in with a value needed by
* Tcl_ConvertElement when doing the actual conversion.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
Tcl_ScanElement(
register const char *src, /* String to convert to list element. */
register int *flagPtr) /* Where to store information to guide
* Tcl_ConvertCountedElement. */
{
return Tcl_ScanCountedElement(src, -1, flagPtr);
}
/*
*----------------------------------------------------------------------
*
* Tcl_ScanCountedElement --
*
* This function is a companion function to Tcl_ConvertCountedElement. It
* scans a string to see what needs to be done to it (e.g. add
* backslashes or enclosing braces) to make the string into a valid Tcl
* list element. If length is -1, then the string is scanned from src up
* to the first null byte.
*
* Results:
* The return value is an overestimate of the number of bytes that will
* be needed by Tcl_ConvertCountedElement to produce a valid list element
* from src. The word at *flagPtr is filled in with a value needed by
* Tcl_ConvertCountedElement when doing the actual conversion.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
Tcl_ScanCountedElement(
const char *src, /* String to convert to Tcl list element. */
int length, /* Number of bytes in src, or -1. */
int *flagPtr) /* Where to store information to guide
* Tcl_ConvertElement. */
{
int flags = CONVERT_ANY;
int numBytes = TclScanElement(src, length, &flags);
*flagPtr = flags;
return numBytes;
}
/*
*----------------------------------------------------------------------
*
* TclScanElement --
*
* This function is a companion function to TclConvertElement. It scans a
* string to see what needs to be done to it (e.g. add backslashes or
* enclosing braces) to make the string into a valid Tcl list element. If
* length is -1, then the string is scanned from src up to the first null
* byte. A NULL value for src is treated as an empty string. The incoming
* value of *flagPtr is a report from the caller what additional flags it
* will pass to TclConvertElement().
*
* Results:
* The recommended formatting mode for the element is determined and a
* value is written to *flagPtr indicating that recommendation. This
* recommendation is combined with the incoming flag values in *flagPtr
* set by the caller to determine how many bytes will be needed by
* TclConvertElement() in which to write the formatted element following
* the recommendation modified by the flag values. This number of bytes
* is the return value of the routine. In some situations it may be an
* overestimate, but so long as the caller passes the same flags to
* TclConvertElement(), it will be large enough.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
TclScanElement(
const char *src, /* String to convert to Tcl list element. */
int length, /* Number of bytes in src, or -1. */
int *flagPtr) /* Where to store information to guide
* Tcl_ConvertElement. */
{
const char *p = src;
int nestingLevel = 0; /* Brace nesting count */
int forbidNone = 0; /* Do not permit CONVERT_NONE mode. Something
* needs protection or escape. */
int requireEscape = 0; /* Force use of CONVERT_ESCAPE mode. For some
* reason bare or brace-quoted form fails. */
int extra = 0; /* Count of number of extra bytes needed for
* formatted element, assuming we use escape
* sequences in formatting. */
int bytesNeeded; /* Buffer length computed to complete the
* element formatting in the selected mode. */
#if COMPAT
int preferEscape = 0; /* Use preferences to track whether to use */
int preferBrace = 0; /* CONVERT_MASK mode. */
int braceCount = 0; /* Count of all braces '{' '}' seen. */
#endif /* COMPAT */
if ((p == NULL) || (length == 0) || ((*p == '\0') && (length == -1))) {
/*
* Empty string element must be brace quoted.
*/
*flagPtr = CONVERT_BRACE;
return 2;
}
if ((*p == '{') || (*p == '"')) {
/*
* Must escape or protect so leading character of value is not
* misinterpreted as list element delimiting syntax.
*/
forbidNone = 1;
#if COMPAT
preferBrace = 1;
#endif /* COMPAT */
}
while (length) {
if (CHAR_TYPE(*p) != TYPE_NORMAL) {
switch (*p) {
case '{': /* TYPE_BRACE */
#if COMPAT
braceCount++;
#endif /* COMPAT */
extra++; /* Escape '{' => '\{' */
nestingLevel++;
break;
case '}': /* TYPE_BRACE */
#if COMPAT
braceCount++;
#endif /* COMPAT */
extra++; /* Escape '}' => '\}' */
nestingLevel--;
if (nestingLevel < 0) {
/*
* Unbalanced braces! Cannot format with brace quoting.
*/
requireEscape = 1;
}
break;
case ']': /* TYPE_CLOSE_BRACK */
case '"': /* TYPE_SPACE */
#if COMPAT
forbidNone = 1;
extra++; /* Escapes all just prepend a backslash */
preferEscape = 1;
break;
#else
/* FLOW THROUGH */
#endif /* COMPAT */
case '[': /* TYPE_SUBS */
case '$': /* TYPE_SUBS */
case ';': /* TYPE_COMMAND_END */
case ' ': /* TYPE_SPACE */
case '\f': /* TYPE_SPACE */
case '\n': /* TYPE_COMMAND_END */
case '\r': /* TYPE_SPACE */
case '\t': /* TYPE_SPACE */
case '\v': /* TYPE_SPACE */
forbidNone = 1;
extra++; /* Escape sequences all one byte longer. */
#if COMPAT
preferBrace = 1;
#endif /* COMPAT */
break;
case '\\': /* TYPE_SUBS */
extra++; /* Escape '\' => '\\' */
if ((length == 1) || ((length == -1) && (p[1] == '\0'))) {
/*
* Final backslash. Cannot format with brace quoting.
*/
requireEscape = 1;
break;
}
if (p[1] == '\n') {
extra++; /* Escape newline => '\n', one byte longer */
/*
* Backslash newline sequence. Brace quoting not permitted.
*/
requireEscape = 1;
length -= (length > 0);
p++;
break;
}
if ((p[1] == '{') || (p[1] == '}') || (p[1] == '\\')) {
extra++; /* Escape sequences all one byte longer. */
length -= (length > 0);
p++;
}
forbidNone = 1;
#if COMPAT
preferBrace = 1;
#endif /* COMPAT */
break;
case '\0': /* TYPE_SUBS */
if (length == -1) {
goto endOfString;
}
/* TODO: Panic on improper encoding? */
break;
}
}
length -= (length > 0);
p++;
}
endOfString:
if (nestingLevel != 0) {
/*
* Unbalanced braces! Cannot format with brace quoting.
*/
requireEscape = 1;
}
/*
* We need at least as many bytes as are in the element value...
*/
bytesNeeded = p - src;
if (requireEscape) {
/*
* We must use escape sequences. Add all the extra bytes needed to
* have room to create them.
*/
bytesNeeded += extra;
/*
* Make room to escape leading #, if needed.
*/
if ((*src == '#') && !(*flagPtr & TCL_DONT_QUOTE_HASH)) {
bytesNeeded++;
}
*flagPtr = CONVERT_ESCAPE;
goto overflowCheck;
}
if (*flagPtr & CONVERT_ANY) {
/*
* The caller has not let us know what flags it will pass to
* TclConvertElement() so compute the max size we might need for any
* possible choice. Normally the formatting using escape sequences is
* the longer one, and a minimum "extra" value of 2 makes sure we
* don't request too small a buffer in those edge cases where that's
* not true.
*/
if (extra < 2) {
extra = 2;
}
*flagPtr &= ~CONVERT_ANY;
*flagPtr |= TCL_DONT_USE_BRACES;
}
if (forbidNone) {
/*
* We must request some form of quoting of escaping...
*/
#if COMPAT
if (preferEscape && !preferBrace) {
/*
* If we are quoting solely due to ] or internal " characters use
* the CONVERT_MASK mode where we escape all special characters
* except for braces. "extra" counted space needed to escape
* braces too, so substract "braceCount" to get our actual needs.
*/
bytesNeeded += (extra - braceCount);
/* Make room to escape leading #, if needed. */
if ((*src == '#') && !(*flagPtr & TCL_DONT_QUOTE_HASH)) {
bytesNeeded++;
}
/*
* If the caller reports it will direct TclConvertElement() to
* use full escapes on the element, add back the bytes needed to
* escape the braces.
*/
if (*flagPtr & TCL_DONT_USE_BRACES) {
bytesNeeded += braceCount;
}
*flagPtr = CONVERT_MASK;
goto overflowCheck;
}
#endif /* COMPAT */
if (*flagPtr & TCL_DONT_USE_BRACES) {
/*
* If the caller reports it will direct TclConvertElement() to
* use escapes, add the extra bytes needed to have room for them.
*/
bytesNeeded += extra;
/*
* Make room to escape leading #, if needed.
*/
if ((*src == '#') && !(*flagPtr & TCL_DONT_QUOTE_HASH)) {
bytesNeeded++;
}
} else {
/*
* Add 2 bytes for room for the enclosing braces.
*/
bytesNeeded += 2;
}
*flagPtr = CONVERT_BRACE;
goto overflowCheck;
}
/*
* So far, no need to quote or escape anything.
*/
if ((*src == '#') && !(*flagPtr & TCL_DONT_QUOTE_HASH)) {
/*
* If we need to quote a leading #, make room to enclose in braces.
*/
bytesNeeded += 2;
}
*flagPtr = CONVERT_NONE;
overflowCheck:
if (bytesNeeded < 0) {
Tcl_Panic("TclScanElement: string length overflow");
}
return bytesNeeded;
}
/*
*----------------------------------------------------------------------
*
* Tcl_ConvertElement --
*
* This is a companion function to Tcl_ScanElement. Given the information
* produced by Tcl_ScanElement, this function converts a string to a list
* element equal to that string.
*
* Results:
* Information is copied to *dst in the form of a list element identical
* to src (i.e. if Tcl_SplitList is applied to dst it will produce a
* string identical to src). The return value is a count of the number of
* characters copied (not including the terminating NULL character).
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
Tcl_ConvertElement(
register const char *src, /* Source information for list element. */
register char *dst, /* Place to put list-ified element. */
register int flags) /* Flags produced by Tcl_ScanElement. */
{
return Tcl_ConvertCountedElement(src, -1, dst, flags);
}
/*
*----------------------------------------------------------------------
*
* Tcl_ConvertCountedElement --
*
* This is a companion function to Tcl_ScanCountedElement. Given the
* information produced by Tcl_ScanCountedElement, this function converts
* a string to a list element equal to that string.
*
* Results:
* Information is copied to *dst in the form of a list element identical
* to src (i.e. if Tcl_SplitList is applied to dst it will produce a
* string identical to src). The return value is a count of the number of
* characters copied (not including the terminating NULL character).
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
Tcl_ConvertCountedElement(
register const char *src, /* Source information for list element. */
int length, /* Number of bytes in src, or -1. */
char *dst, /* Place to put list-ified element. */
int flags) /* Flags produced by Tcl_ScanElement. */
{
int numBytes = TclConvertElement(src, length, dst, flags);
dst[numBytes] = '\0';
return numBytes;
}
/*
*----------------------------------------------------------------------
*
* TclConvertElement --
*
* This is a companion function to TclScanElement. Given the information
* produced by TclScanElement, this function converts a string to a list
* element equal to that string.
*
* Results:
* Information is copied to *dst in the form of a list element identical
* to src (i.e. if Tcl_SplitList is applied to dst it will produce a
* string identical to src). The return value is a count of the number of
* characters copied (not including the terminating NULL character).
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
TclConvertElement(
register const char *src, /* Source information for list element. */
int length, /* Number of bytes in src, or -1. */
char *dst, /* Place to put list-ified element. */
int flags) /* Flags produced by Tcl_ScanElement. */
{
int conversion = flags & CONVERT_MASK;
char *p = dst;
/*
* Let the caller demand we use escape sequences rather than braces.
*/
if ((flags & TCL_DONT_USE_BRACES) && (conversion & CONVERT_BRACE)) {
conversion = CONVERT_ESCAPE;
}
/*
* No matter what the caller demands, empty string must be braced!
*/
if ((src == NULL) || (length == 0) || (*src == '\0' && length == -1)) {
src = tclEmptyStringRep;
length = 0;
conversion = CONVERT_BRACE;
}
/*
* Escape leading hash as needed and requested.
*/
if ((*src == '#') && !(flags & TCL_DONT_QUOTE_HASH)) {
if (conversion == CONVERT_ESCAPE) {
p[0] = '\\';
p[1] = '#';
p += 2;
src++;
length -= (length > 0);
} else {
conversion = CONVERT_BRACE;
}
}
/*
* No escape or quoting needed. Copy the literal string value.
*/
if (conversion == CONVERT_NONE) {
if (length == -1) {
/* TODO: INT_MAX overflow? */
while (*src) {
*p++ = *src++;
}
return p - dst;
} else {
memcpy(dst, src, length);
return length;
}
}
/*
* Formatted string is original string enclosed in braces.
*/
if (conversion == CONVERT_BRACE) {
*p = '{';
p++;
if (length == -1) {
/* TODO: INT_MAX overflow? */
while (*src) {
*p++ = *src++;
}
} else {
memcpy(p, src, length);
p += length;
}
*p = '}';
p++;
return p - dst;
}
/* conversion == CONVERT_ESCAPE or CONVERT_MASK */
/*
* Formatted string is original string converted to escape sequences.
*/
for ( ; length; src++, length -= (length > 0)) {
switch (*src) {
case ']':
case '[':
case '$':
case ';':
case ' ':
case '\\':
case '"':
*p = '\\';
p++;
break;
case '{':
case '}':
#if COMPAT
if (conversion == CONVERT_ESCAPE)
#endif /* COMPAT */
{
*p = '\\';
p++;
}
break;
case '\f':
*p = '\\';
p++;
*p = 'f';
p++;
continue;
case '\n':
*p = '\\';
p++;
*p = 'n';
p++;
continue;
case '\r':
*p = '\\';
p++;
*p = 'r';
p++;
continue;
case '\t':
*p = '\\';
p++;
*p = 't';
p++;
continue;
case '\v':
*p = '\\';
p++;
*p = 'v';
p++;
continue;
case '\0':
if (length == -1) {
return p - dst;
}
/*
* If we reach this point, there's an embedded NULL in the string
* range being processed, which should not happen when the
* encoding rules for Tcl strings are properly followed. If the
* day ever comes when we stop tolerating such things, this is
* where to put the Tcl_Panic().
*/
break;
}
*p = *src;
p++;
}
return p - dst;
}
/*
*----------------------------------------------------------------------
*
* Tcl_Merge --
*
* Given a collection of strings, merge them together into a single
* string that has proper Tcl list structured (i.e. Tcl_SplitList may be
* used to retrieve strings equal to the original elements, and Tcl_Eval
* will parse the string back into its original elements).
*
* Results:
* The return value is the address of a dynamically-allocated string
* containing the merged list.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
char *
Tcl_Merge(
int argc, /* How many strings to merge. */
const char *const *argv) /* Array of string values. */
{
#define LOCAL_SIZE 20
int localFlags[LOCAL_SIZE], *flagPtr = NULL;
int i, bytesNeeded = 0;
char *result, *dst;
const int maxFlags = UINT_MAX / sizeof(int);
/*
* Handle empty list case first, so logic of the general case can be
* simpler.
*/
if (argc == 0) {
result = ckalloc(1);
result[0] = '\0';
return result;
}
/*
* Pass 1: estimate space, gather flags.
*/
if (argc <= LOCAL_SIZE) {
flagPtr = localFlags;
} else if (argc > maxFlags) {
/*
* We cannot allocate a large enough flag array to format this list in
* one pass. We could imagine converting this routine to a multi-pass
* implementation, but for sizeof(int) == 4, the limit is a max of
* 2^30 list elements and since each element is at least one byte
* formatted, and requires one byte space between it and the next one,
* that a minimum space requirement of 2^31 bytes, which is already
* INT_MAX. If we tried to format a list of > maxFlags elements, we're
* just going to overflow the size limits on the formatted string
* anyway, so just issue that same panic early.
*/
Tcl_Panic("max size for a Tcl value (%d bytes) exceeded", INT_MAX);
} else {
flagPtr = ckalloc(argc * sizeof(int));
}
for (i = 0; i < argc; i++) {
flagPtr[i] = ( i ? TCL_DONT_QUOTE_HASH : 0 );
bytesNeeded += TclScanElement(argv[i], -1, &flagPtr[i]);
if (bytesNeeded < 0) {
Tcl_Panic("max size for a Tcl value (%d bytes) exceeded", INT_MAX);
}
}
if (bytesNeeded > INT_MAX - argc + 1) {
Tcl_Panic("max size for a Tcl value (%d bytes) exceeded", INT_MAX);
}
bytesNeeded += argc;
/*
* Pass two: copy into the result area.
*/
result = ckalloc(bytesNeeded);
dst = result;
for (i = 0; i < argc; i++) {
flagPtr[i] |= ( i ? TCL_DONT_QUOTE_HASH : 0 );
dst += TclConvertElement(argv[i], -1, dst, flagPtr[i]);
*dst = ' ';
dst++;
}
dst[-1] = 0;
if (flagPtr != localFlags) {
ckfree(flagPtr);
}
return result;
}
/*
*----------------------------------------------------------------------
*
* TclTrimRight --
*
* Takes two counted strings in the Tcl encoding which must both be null
* terminated. Conceptually trims from the right side of the first string
* all characters found in the second string.
*
* Results:
* The number of bytes to be removed from the end of the string.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
TclTrimRight(
const char *bytes, /* String to be trimmed... */
int numBytes, /* ...and its length in bytes */
const char *trim, /* String of trim characters... */
int numTrim) /* ...and its length in bytes */
{
const char *p = bytes + numBytes;
int pInc;
if ((bytes[numBytes] != '\0') || (trim[numTrim] != '\0')) {
Tcl_Panic("TclTrimRight works only on null-terminated strings");
}
/*
* Empty strings -> nothing to do.
*/
if ((numBytes == 0) || (numTrim == 0)) {
return 0;
}
/*
* Outer loop: iterate over string to be trimmed.
*/
do {
Tcl_UniChar ch1;
const char *q = trim;
int bytesLeft = numTrim;
p = Tcl_UtfPrev(p, bytes);
pInc = TclUtfToUniChar(p, &ch1);
/*
* Inner loop: scan trim string for match to current character.
*/
do {
Tcl_UniChar ch2;
int qInc = TclUtfToUniChar(q, &ch2);
if (ch1 == ch2) {
break;
}
q += qInc;
bytesLeft -= qInc;
} while (bytesLeft);
if (bytesLeft == 0) {
/*
* No match; trim task done; *p is last non-trimmed char.
*/
p += pInc;
break;
}
} while (p > bytes);
return numBytes - (p - bytes);
}
/*
*----------------------------------------------------------------------
*
* TclTrimLeft --
*
* Takes two counted strings in the Tcl encoding which must both be null
* terminated. Conceptually trims from the left side of the first string
* all characters found in the second string.
*
* Results:
* The number of bytes to be removed from the start of the string.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
TclTrimLeft(
const char *bytes, /* String to be trimmed... */
int numBytes, /* ...and its length in bytes */
const char *trim, /* String of trim characters... */
int numTrim) /* ...and its length in bytes */
{
const char *p = bytes;
if ((bytes[numBytes] != '\0') || (trim[numTrim] != '\0')) {
Tcl_Panic("TclTrimLeft works only on null-terminated strings");
}
/*
* Empty strings -> nothing to do.
*/
if ((numBytes == 0) || (numTrim == 0)) {
return 0;
}
/*
* Outer loop: iterate over string to be trimmed.
*/
do {
Tcl_UniChar ch1;
int pInc = TclUtfToUniChar(p, &ch1);
const char *q = trim;
int bytesLeft = numTrim;
/*
* Inner loop: scan trim string for match to current character.
*/
do {
Tcl_UniChar ch2;
int qInc = TclUtfToUniChar(q, &ch2);
if (ch1 == ch2) {
break;
}
q += qInc;
bytesLeft -= qInc;
} while (bytesLeft);
if (bytesLeft == 0) {
/*
* No match; trim task done; *p is first non-trimmed char.
*/
break;
}
p += pInc;
numBytes -= pInc;
} while (numBytes);
return p - bytes;
}
/*
*----------------------------------------------------------------------
*
* Tcl_Concat --
*
* Concatenate a set of strings into a single large string.
*
* Results:
* The return value is dynamically-allocated string containing a
* concatenation of all the strings in argv, with spaces between the
* original argv elements.
*
* Side effects:
* Memory is allocated for the result; the caller is responsible for
* freeing the memory.
*
*----------------------------------------------------------------------
*/
/* The whitespace characters trimmed during [concat] operations */
#define CONCAT_WS " \f\v\r\t\n"
#define CONCAT_WS_SIZE (int) (sizeof(CONCAT_WS "") - 1)
char *
Tcl_Concat(
int argc, /* Number of strings to concatenate. */
const char *const *argv) /* Array of strings to concatenate. */
{
int i, needSpace = 0, bytesNeeded = 0;
char *result, *p;
/*
* Dispose of the empty result corner case first to simplify later code.
*/
if (argc == 0) {
result = (char *) ckalloc(1);
result[0] = '\0';
return result;
}
/*
* First allocate the result buffer at the size required.
*/
for (i = 0; i < argc; i++) {
bytesNeeded += strlen(argv[i]);
if (bytesNeeded < 0) {
Tcl_Panic("Tcl_Concat: max size of Tcl value exceeded");
}
}
if (bytesNeeded + argc - 1 < 0) {
/*
* Panic test could be tighter, but not going to bother for this
* legacy routine.
*/
Tcl_Panic("Tcl_Concat: max size of Tcl value exceeded");
}
/*
* All element bytes + (argc - 1) spaces + 1 terminating NULL.
*/
result = ckalloc((unsigned) (bytesNeeded + argc));
for (p = result, i = 0; i < argc; i++) {
int trim, elemLength;
const char *element;
element = argv[i];
elemLength = strlen(argv[i]);
/*
* Trim away the leading whitespace.
*/
trim = TclTrimLeft(element, elemLength, CONCAT_WS, CONCAT_WS_SIZE);
element += trim;
elemLength -= trim;
/*
* Trim away the trailing whitespace. Do not permit trimming to expose
* a final backslash character.
*/
trim = TclTrimRight(element, elemLength, CONCAT_WS, CONCAT_WS_SIZE);
trim -= trim && (element[elemLength - trim - 1] == '\\');
elemLength -= trim;
/*
* If we're left with empty element after trimming, do nothing.
*/
if (elemLength == 0) {
continue;
}
/*
* Append to the result with space if needed.
*/
if (needSpace) {
*p++ = ' ';
}
memcpy(p, element, (size_t) elemLength);
p += elemLength;
needSpace = 1;
}
*p = '\0';
return result;
}
/*
*----------------------------------------------------------------------
*
* Tcl_ConcatObj --
*
* Concatenate the strings from a set of objects into a single string
* object with spaces between the original strings.
*
* Results:
* The return value is a new string object containing a concatenation of
* the strings in objv. Its ref count is zero.
*
* Side effects:
* A new object is created.
*
*----------------------------------------------------------------------
*/
Tcl_Obj *
Tcl_ConcatObj(
int objc, /* Number of objects to concatenate. */
Tcl_Obj *const objv[]) /* Array of objects to concatenate. */
{
int i, elemLength, needSpace = 0, bytesNeeded = 0;
const char *element;
Tcl_Obj *objPtr, *resPtr;
/*
* Check first to see if all the items are of list type or empty. If so,
* we will concat them together as lists, and return a list object. This
* is only valid when the lists are in canonical form.
*/
for (i = 0; i < objc; i++) {
int length;
objPtr = objv[i];
if (TclListObjIsCanonical(objPtr)) {
continue;
}
Tcl_GetStringFromObj(objPtr, &length);
if (length > 0) {
break;
}
}
if (i == objc) {
resPtr = NULL;
for (i = 0; i < objc; i++) {
objPtr = objv[i];
if (objPtr->bytes && objPtr->length == 0) {
continue;
}
if (resPtr) {
Tcl_ListObjAppendList(NULL, resPtr, objPtr);
} else {
resPtr = TclListObjCopy(NULL, objPtr);
}
}
if (!resPtr) {
resPtr = Tcl_NewObj();
}
return resPtr;
}
/*
* Something cannot be determined to be safe, so build the concatenation
* the slow way, using the string representations.
*
* First try to pre-allocate the size required.
*/
for (i = 0; i < objc; i++) {
element = TclGetStringFromObj(objv[i], &elemLength);
bytesNeeded += elemLength;
if (bytesNeeded < 0) {
break;
}
}
/*
* Does not matter if this fails, will simply try later to build up the
* string with each Append reallocating as needed with the usual string
* append algorithm. When that fails it will report the error.
*/
TclNewObj(resPtr);
Tcl_AttemptSetObjLength(resPtr, bytesNeeded + objc - 1);
Tcl_SetObjLength(resPtr, 0);
for (i = 0; i < objc; i++) {
int trim;
element = TclGetStringFromObj(objv[i], &elemLength);
/*
* Trim away the leading whitespace.
*/
trim = TclTrimLeft(element, elemLength, CONCAT_WS, CONCAT_WS_SIZE);
element += trim;
elemLength -= trim;
/*
* Trim away the trailing whitespace. Do not permit trimming to expose
* a final backslash character.
*/
trim = TclTrimRight(element, elemLength, CONCAT_WS, CONCAT_WS_SIZE);
trim -= trim && (element[elemLength - trim - 1] == '\\');
elemLength -= trim;
/*
* If we're left with empty element after trimming, do nothing.
*/
if (elemLength == 0) {
continue;
}
/*
* Append to the result with space if needed.
*/
if (needSpace) {
Tcl_AppendToObj(resPtr, " ", 1);
}
Tcl_AppendToObj(resPtr, element, elemLength);
needSpace = 1;
}
return resPtr;
}
/*
*----------------------------------------------------------------------
*
* Tcl_StringMatch --
*
* See if a particular string matches a particular pattern.
*
* Results:
* The return value is 1 if string matches pattern, and 0 otherwise. The
* matching operation permits the following special characters in the
* pattern: *?\[] (see the manual entry for details on what these mean).
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
Tcl_StringMatch(
const char *str, /* String. */
const char *pattern) /* Pattern, which may contain special
* characters. */
{
return Tcl_StringCaseMatch(str, pattern, 0);
}
/*
*----------------------------------------------------------------------
*
* Tcl_StringCaseMatch --
*
* See if a particular string matches a particular pattern. Allows case
* insensitivity.
*
* Results:
* The return value is 1 if string matches pattern, and 0 otherwise. The
* matching operation permits the following special characters in the
* pattern: *?\[] (see the manual entry for details on what these mean).
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
Tcl_StringCaseMatch(
const char *str, /* String. */
const char *pattern, /* Pattern, which may contain special
* characters. */
int nocase) /* 0 for case sensitive, 1 for insensitive */
{
int p, charLen;
const char *pstart = pattern;
Tcl_UniChar ch1, ch2;
while (1) {
p = *pattern;
/*
* See if we're at the end of both the pattern and the string. If so,
* we succeeded. If we're at the end of the pattern but not at the end
* of the string, we failed.
*/
if (p == '\0') {
return (*str == '\0');
}
if ((*str == '\0') && (p != '*')) {
return 0;
}
/*
* Check for a "*" as the next pattern character. It matches any
* substring. We handle this by calling ourselves recursively for each
* postfix of string, until either we match or we reach the end of the
* string.
*/
if (p == '*') {
/*
* Skip all successive *'s in the pattern
*/
while (*(++pattern) == '*') {}
p = *pattern;
if (p == '\0') {
return 1;
}
/*
* This is a special case optimization for single-byte utf.
*/
if (UCHAR(*pattern) < 0x80) {
ch2 = (Tcl_UniChar)
(nocase ? tolower(UCHAR(*pattern)) : UCHAR(*pattern));
} else {
Tcl_UtfToUniChar(pattern, &ch2);
if (nocase) {
ch2 = Tcl_UniCharToLower(ch2);
}
}
while (1) {
/*
* Optimization for matching - cruise through the string
* quickly if the next char in the pattern isn't a special
* character
*/
if ((p != '[') && (p != '?') && (p != '\\')) {
if (nocase) {
while (*str) {
charLen = TclUtfToUniChar(str, &ch1);
if (ch2==ch1 || ch2==Tcl_UniCharToLower(ch1)) {
break;
}
str += charLen;
}
} else {
/*
* There's no point in trying to make this code
* shorter, as the number of bytes you want to compare
* each time is non-constant.
*/
while (*str) {
charLen = TclUtfToUniChar(str, &ch1);
if (ch2 == ch1) {
break;
}
str += charLen;
}
}
}
if (Tcl_StringCaseMatch(str, pattern, nocase)) {
return 1;
}
if (*str == '\0') {
return 0;
}
str += TclUtfToUniChar(str, &ch1);
}
}
/*
* Check for a "?" as the next pattern character. It matches any
* single character.
*/
if (p == '?') {
pattern++;
str += TclUtfToUniChar(str, &ch1);
continue;
}
/*
* Check for a "[" as the next pattern character. It is followed by a
* list of characters that are acceptable, or by a range (two
* characters separated by "-").
*/
if (p == '[') {
Tcl_UniChar startChar, endChar;
pattern++;
if (UCHAR(*str) < 0x80) {
ch1 = (Tcl_UniChar)
(nocase ? tolower(UCHAR(*str)) : UCHAR(*str));
str++;
} else {
str += Tcl_UtfToUniChar(str, &ch1);
if (nocase) {
ch1 = Tcl_UniCharToLower(ch1);
}
}
while (1) {
if ((*pattern == ']') || (*pattern == '\0')) {
return 0;
}
if (UCHAR(*pattern) < 0x80) {
startChar = (Tcl_UniChar) (nocase
? tolower(UCHAR(*pattern)) : UCHAR(*pattern));
pattern++;
} else {
pattern += Tcl_UtfToUniChar(pattern, &startChar);
if (nocase) {
startChar = Tcl_UniCharToLower(startChar);
}
}
if (*pattern == '-') {
pattern++;
if (*pattern == '\0') {
return 0;
}
if (UCHAR(*pattern) < 0x80) {
endChar = (Tcl_UniChar) (nocase
? tolower(UCHAR(*pattern)) : UCHAR(*pattern));
pattern++;
} else {
pattern += Tcl_UtfToUniChar(pattern, &endChar);
if (nocase) {
endChar = Tcl_UniCharToLower(endChar);
}
}
if (((startChar <= ch1) && (ch1 <= endChar))
|| ((endChar <= ch1) && (ch1 <= startChar))) {
/*
* Matches ranges of form [a-z] or [z-a].
*/
break;
}
} else if (startChar == ch1) {
break;
}
}
while (*pattern != ']') {
if (*pattern == '\0') {
pattern = Tcl_UtfPrev(pattern, pstart);
break;
}
pattern++;
}
pattern++;
continue;
}
/*
* If the next pattern character is '\', just strip off the '\' so we
* do exact matching on the character that follows.
*/
if (p == '\\') {
pattern++;
if (*pattern == '\0') {
return 0;
}
}
/*
* There's no special character. Just make sure that the next bytes of
* each string match.
*/
str += TclUtfToUniChar(str, &ch1);
pattern += TclUtfToUniChar(pattern, &ch2);
if (nocase) {
if (Tcl_UniCharToLower(ch1) != Tcl_UniCharToLower(ch2)) {
return 0;
}
} else if (ch1 != ch2) {
return 0;
}
}
}
/*
*----------------------------------------------------------------------
*
* TclByteArrayMatch --
*
* See if a particular string matches a particular pattern. Does not
* allow for case insensitivity.
* Parallels tclUtf.c:TclUniCharMatch, adjusted for char* and sans nocase.
*
* Results:
* The return value is 1 if string matches pattern, and 0 otherwise. The
* matching operation permits the following special characters in the
* pattern: *?\[] (see the manual entry for details on what these mean).
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
TclByteArrayMatch(
const unsigned char *string,/* String. */
int strLen, /* Length of String */
const unsigned char *pattern,
/* Pattern, which may contain special
* characters. */
int ptnLen, /* Length of Pattern */
int flags)
{
const unsigned char *stringEnd, *patternEnd;
unsigned char p;
stringEnd = string + strLen;
patternEnd = pattern + ptnLen;
while (1) {
/*
* See if we're at the end of both the pattern and the string. If so,
* we succeeded. If we're at the end of the pattern but not at the end
* of the string, we failed.
*/
if (pattern == patternEnd) {
return (string == stringEnd);
}
p = *pattern;
if ((string == stringEnd) && (p != '*')) {
return 0;
}
/*
* Check for a "*" as the next pattern character. It matches any
* substring. We handle this by skipping all the characters up to the
* next matching one in the pattern, and then calling ourselves
* recursively for each postfix of string, until either we match or we
* reach the end of the string.
*/
if (p == '*') {
/*
* Skip all successive *'s in the pattern.
*/
while ((++pattern < patternEnd) && (*pattern == '*')) {
/* empty body */
}
if (pattern == patternEnd) {
return 1;
}
p = *pattern;
while (1) {
/*
* Optimization for matching - cruise through the string
* quickly if the next char in the pattern isn't a special
* character.
*/
if ((p != '[') && (p != '?') && (p != '\\')) {
while ((string < stringEnd) && (p != *string)) {
string++;
}
}
if (TclByteArrayMatch(string, stringEnd - string,
pattern, patternEnd - pattern, 0)) {
return 1;
}
if (string == stringEnd) {
return 0;
}
string++;
}
}
/*
* Check for a "?" as the next pattern character. It matches any
* single character.
*/
if (p == '?') {
pattern++;
string++;
continue;
}
/*
* Check for a "[" as the next pattern character. It is followed by a
* list of characters that are acceptable, or by a range (two
* characters separated by "-").
*/
if (p == '[') {
unsigned char ch1, startChar, endChar;
pattern++;
ch1 = *string;
string++;
while (1) {
if ((*pattern == ']') || (pattern == patternEnd)) {
return 0;
}
startChar = *pattern;
pattern++;
if (*pattern == '-') {
pattern++;
if (pattern == patternEnd) {
return 0;
}
endChar = *pattern;
pattern++;
if (((startChar <= ch1) && (ch1 <= endChar))
|| ((endChar <= ch1) && (ch1 <= startChar))) {
/*
* Matches ranges of form [a-z] or [z-a].
*/
break;
}
} else if (startChar == ch1) {
break;
}
}
while (*pattern != ']') {
if (pattern == patternEnd) {
pattern--;
break;
}
pattern++;
}
pattern++;
continue;
}
/*
* If the next pattern character is '\', just strip off the '\' so we
* do exact matching on the character that follows.
*/
if (p == '\\') {
if (++pattern == patternEnd) {
return 0;
}
}
/*
* There's no special character. Just make sure that the next bytes of
* each string match.
*/
if (*string != *pattern) {
return 0;
}
string++;
pattern++;
}
}
/*
*----------------------------------------------------------------------
*
* TclStringMatchObj --
*
* See if a particular string matches a particular pattern. Allows case
* insensitivity. This is the generic multi-type handler for the various
* matching algorithms.
*
* Results:
* The return value is 1 if string matches pattern, and 0 otherwise. The
* matching operation permits the following special characters in the
* pattern: *?\[] (see the manual entry for details on what these mean).
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
TclStringMatchObj(
Tcl_Obj *strObj, /* string object. */
Tcl_Obj *ptnObj, /* pattern object. */
int flags) /* Only TCL_MATCH_NOCASE should be passed, or
* 0. */
{
int match, length, plen;
/*
* Promote based on the type of incoming object.
* XXX: Currently doesn't take advantage of exact-ness that
* XXX: TclReToGlob tells us about
trivial = nocase ? 0 : TclMatchIsTrivial(TclGetString(ptnObj));
*/
if ((strObj->typePtr == &tclStringType) || (strObj->typePtr == NULL)) {
Tcl_UniChar *udata, *uptn;
udata = Tcl_GetUnicodeFromObj(strObj, &length);
uptn = Tcl_GetUnicodeFromObj(ptnObj, &plen);
match = TclUniCharMatch(udata, length, uptn, plen, flags);
} else if (TclIsPureByteArray(strObj) && !flags) {
unsigned char *data, *ptn;
data = Tcl_GetByteArrayFromObj(strObj, &length);
ptn = Tcl_GetByteArrayFromObj(ptnObj, &plen);
match = TclByteArrayMatch(data, length, ptn, plen, 0);
} else {
match = Tcl_StringCaseMatch(TclGetString(strObj),
TclGetString(ptnObj), flags);
}
return match;
}
/*
*----------------------------------------------------------------------
*
* Tcl_DStringInit --
*
* Initializes a dynamic string, discarding any previous contents of the
* string (Tcl_DStringFree should have been called already if the dynamic
* string was previously in use).
*
* Results:
* None.
*
* Side effects:
* The dynamic string is initialized to be empty.
*
*----------------------------------------------------------------------
*/
void
Tcl_DStringInit(
Tcl_DString *dsPtr) /* Pointer to structure for dynamic string. */
{
dsPtr->string = dsPtr->staticSpace;
dsPtr->length = 0;
dsPtr->spaceAvl = TCL_DSTRING_STATIC_SIZE;
dsPtr->staticSpace[0] = '\0';
}
/*
*----------------------------------------------------------------------
*
* Tcl_DStringAppend --
*
* Append more bytes to the current value of a dynamic string.
*
* Results:
* The return value is a pointer to the dynamic string's new value.
*
* Side effects:
* Length bytes from "bytes" (or all of "bytes" if length is less than
* zero) are added to the current value of the string. Memory gets
* reallocated if needed to accomodate the string's new size.
*
*----------------------------------------------------------------------
*/
char *
Tcl_DStringAppend(
Tcl_DString *dsPtr, /* Structure describing dynamic string. */
const char *bytes, /* String to append. If length is -1 then this
* must be null-terminated. */
int length) /* Number of bytes from "bytes" to append. If
* < 0, then append all of bytes, up to null
* at end. */
{
int newSize;
if (length < 0) {
length = strlen(bytes);
}
newSize = length + dsPtr->length;
/*
* Allocate a larger buffer for the string if the current one isn't large
* enough. Allocate extra space in the new buffer so that there will be
* room to grow before we have to allocate again.
*/
if (newSize >= dsPtr->spaceAvl) {
dsPtr->spaceAvl = newSize * 2;
if (dsPtr->string == dsPtr->staticSpace) {
char *newString = ckalloc(dsPtr->spaceAvl);
memcpy(newString, dsPtr->string, (size_t) dsPtr->length);
dsPtr->string = newString;
} else {
dsPtr->string = ckrealloc(dsPtr->string, dsPtr->spaceAvl);
}
}
/*
* Copy the new string into the buffer at the end of the old one.
*/
memcpy(dsPtr->string + dsPtr->length, bytes, length);
dsPtr->length += length;
dsPtr->string[dsPtr->length] = '\0';
return dsPtr->string;
}
/*
*----------------------------------------------------------------------
*
* TclDStringAppendObj, TclDStringAppendDString --
*
* Simple wrappers round Tcl_DStringAppend that make it easier to append
* from particular sources of strings.
*
*----------------------------------------------------------------------
*/
char *
TclDStringAppendObj(
Tcl_DString *dsPtr,
Tcl_Obj *objPtr)
{
int length;
char *bytes = Tcl_GetStringFromObj(objPtr, &length);
return Tcl_DStringAppend(dsPtr, bytes, length);
}
char *
TclDStringAppendDString(
Tcl_DString *dsPtr,
Tcl_DString *toAppendPtr)
{
return Tcl_DStringAppend(dsPtr, Tcl_DStringValue(toAppendPtr),
Tcl_DStringLength(toAppendPtr));
}
/*
*----------------------------------------------------------------------
*
* Tcl_DStringAppendElement --
*
* Append a list element to the current value of a dynamic string.
*
* Results:
* The return value is a pointer to the dynamic string's new value.
*
* Side effects:
* String is reformatted as a list element and added to the current value
* of the string. Memory gets reallocated if needed to accomodate the
* string's new size.
*
*----------------------------------------------------------------------
*/
char *
Tcl_DStringAppendElement(
Tcl_DString *dsPtr, /* Structure describing dynamic string. */
const char *element) /* String to append. Must be
* null-terminated. */
{
char *dst = dsPtr->string + dsPtr->length;
int needSpace = TclNeedSpace(dsPtr->string, dst);
int flags = needSpace ? TCL_DONT_QUOTE_HASH : 0;
int newSize = dsPtr->length + needSpace
+ TclScanElement(element, -1, &flags);
/*
* Allocate a larger buffer for the string if the current one isn't large
* enough. Allocate extra space in the new buffer so that there will be
* room to grow before we have to allocate again. SPECIAL NOTE: must use
* memcpy, not strcpy, to copy the string to a larger buffer, since there
* may be embedded NULLs in the string in some cases.
*/
if (newSize >= dsPtr->spaceAvl) {
dsPtr->spaceAvl = newSize * 2;
if (dsPtr->string == dsPtr->staticSpace) {
char *newString = ckalloc(dsPtr->spaceAvl);
memcpy(newString, dsPtr->string, (size_t) dsPtr->length);
dsPtr->string = newString;
} else {
dsPtr->string = ckrealloc(dsPtr->string, dsPtr->spaceAvl);
}
dst = dsPtr->string + dsPtr->length;
}
/*
* Convert the new string to a list element and copy it into the buffer at
* the end, with a space, if needed.
*/
if (needSpace) {
*dst = ' ';
dst++;
dsPtr->length++;
/*
* If we need a space to separate this element from preceding stuff,
* then this element will not lead a list, and need not have it's
* leading '#' quoted.
*/
flags |= TCL_DONT_QUOTE_HASH;
}
dsPtr->length += TclConvertElement(element, -1, dst, flags);
dsPtr->string[dsPtr->length] = '\0';
return dsPtr->string;
}
/*
*----------------------------------------------------------------------
*
* Tcl_DStringSetLength --
*
* Change the length of a dynamic string. This can cause the string to
* either grow or shrink, depending on the value of length.
*
* Results:
* None.
*
* Side effects:
* The length of dsPtr is changed to length and a null byte is stored at
* that position in the string. If length is larger than the space
* allocated for dsPtr, then a panic occurs.
*
*----------------------------------------------------------------------
*/
void
Tcl_DStringSetLength(
Tcl_DString *dsPtr, /* Structure describing dynamic string. */
int length) /* New length for dynamic string. */
{
int newsize;
if (length < 0) {
length = 0;
}
if (length >= dsPtr->spaceAvl) {
/*
* There are two interesting cases here. In the first case, the user
* may be trying to allocate a large buffer of a specific size. It
* would be wasteful to overallocate that buffer, so we just allocate
* enough for the requested size plus the trailing null byte. In the
* second case, we are growing the buffer incrementally, so we need
* behavior similar to Tcl_DStringAppend. The requested length will
* usually be a small delta above the current spaceAvl, so we'll end
* up doubling the old size. This won't grow the buffer quite as
* quickly, but it should be close enough.
*/
newsize = dsPtr->spaceAvl * 2;
if (length < newsize) {
dsPtr->spaceAvl = newsize;
} else {
dsPtr->spaceAvl = length + 1;
}
if (dsPtr->string == dsPtr->staticSpace) {
char *newString = ckalloc(dsPtr->spaceAvl);
memcpy(newString, dsPtr->string, (size_t) dsPtr->length);
dsPtr->string = newString;
} else {
dsPtr->string = ckrealloc(dsPtr->string, dsPtr->spaceAvl);
}
}
dsPtr->length = length;
dsPtr->string[length] = 0;
}
/*
*----------------------------------------------------------------------
*
* Tcl_DStringFree --
*
* Frees up any memory allocated for the dynamic string and reinitializes
* the string to an empty state.
*
* Results:
* None.
*
* Side effects:
* The previous contents of the dynamic string are lost, and the new
* value is an empty string.
*
*----------------------------------------------------------------------
*/
void
Tcl_DStringFree(
Tcl_DString *dsPtr) /* Structure describing dynamic string. */
{
if (dsPtr->string != dsPtr->staticSpace) {
ckfree(dsPtr->string);
}
dsPtr->string = dsPtr->staticSpace;
dsPtr->length = 0;
dsPtr->spaceAvl = TCL_DSTRING_STATIC_SIZE;
dsPtr->staticSpace[0] = '\0';
}
/*
*----------------------------------------------------------------------
*
* Tcl_DStringResult --
*
* This function moves the value of a dynamic string into an interpreter
* as its string result. Afterwards, the dynamic string is reset to an
* empty string.
*
* Results:
* None.
*
* Side effects:
* The string is "moved" to interp's result, and any existing string
* result for interp is freed. dsPtr is reinitialized to an empty string.
*
*----------------------------------------------------------------------
*/
void
Tcl_DStringResult(
Tcl_Interp *interp, /* Interpreter whose result is to be reset. */
Tcl_DString *dsPtr) /* Dynamic string that is to become the
* result of interp. */
{
Tcl_ResetResult(interp);
Tcl_SetObjResult(interp, TclDStringToObj(dsPtr));
}
/*
*----------------------------------------------------------------------
*
* Tcl_DStringGetResult --
*
* This function moves an interpreter's result into a dynamic string.
*
* Results:
* None.
*
* Side effects:
* The interpreter's string result is cleared, and the previous contents
* of dsPtr are freed.
*
* If the string result is empty, the object result is moved to the
* string result, then the object result is reset.
*
*----------------------------------------------------------------------
*/
void
Tcl_DStringGetResult(
Tcl_Interp *interp, /* Interpreter whose result is to be reset. */
Tcl_DString *dsPtr) /* Dynamic string that is to become the result
* of interp. */
{
Interp *iPtr = (Interp *) interp;
if (dsPtr->string != dsPtr->staticSpace) {
ckfree(dsPtr->string);
}
/*
* Do more efficient transfer when we know the result is a Tcl_Obj. When
* there's no st`ring result, we only have to deal with two cases:
*
* 1. When the string rep is the empty string, when we don't copy but
* instead use the staticSpace in the DString to hold an empty string.
* 2. When the string rep is not there or there's a real string rep, when
* we use Tcl_GetString to fetch (or generate) the string rep - which
* we know to have been allocated with ckalloc() - and use it to
* populate the DString space. Then, we free the internal rep. and set
* the object's string representation back to the canonical empty
* string.
*/
if (!iPtr->result[0] && iPtr->objResultPtr
&& !Tcl_IsShared(iPtr->objResultPtr)) {
if (iPtr->objResultPtr->bytes == tclEmptyStringRep) {
dsPtr->string = dsPtr->staticSpace;
dsPtr->string[0] = 0;
dsPtr->length = 0;
dsPtr->spaceAvl = TCL_DSTRING_STATIC_SIZE;
} else {
dsPtr->string = Tcl_GetString(iPtr->objResultPtr);
dsPtr->length = iPtr->objResultPtr->length;
dsPtr->spaceAvl = dsPtr->length + 1;
TclFreeIntRep(iPtr->objResultPtr);
iPtr->objResultPtr->bytes = tclEmptyStringRep;
iPtr->objResultPtr->length = 0;
}
return;
}
/*
* If the string result is empty, move the object result to the string
* result, then reset the object result.
*/
(void) Tcl_GetStringResult(interp);
dsPtr->length = strlen(iPtr->result);
if (iPtr->freeProc != NULL) {
if (iPtr->freeProc == TCL_DYNAMIC) {
dsPtr->string = iPtr->result;
dsPtr->spaceAvl = dsPtr->length+1;
} else {
dsPtr->string = ckalloc(dsPtr->length+1);
memcpy(dsPtr->string, iPtr->result, (unsigned) dsPtr->length+1);
iPtr->freeProc(iPtr->result);
}
dsPtr->spaceAvl = dsPtr->length+1;
iPtr->freeProc = NULL;
} else {
if (dsPtr->length < TCL_DSTRING_STATIC_SIZE) {
dsPtr->string = dsPtr->staticSpace;
dsPtr->spaceAvl = TCL_DSTRING_STATIC_SIZE;
} else {
dsPtr->string = ckalloc(dsPtr->length+1);
dsPtr->spaceAvl = dsPtr->length + 1;
}
memcpy(dsPtr->string, iPtr->result, (unsigned) dsPtr->length+1);
}
iPtr->result = iPtr->resultSpace;
iPtr->resultSpace[0] = 0;
}
/*
*----------------------------------------------------------------------
*
* TclDStringToObj --
*
* This function moves a dynamic string's contents to a new Tcl_Obj. Be
* aware that this function does *not* check that the encoding of the
* contents of the dynamic string is correct; this is the caller's
* responsibility to enforce.
*
* Results:
* The newly-allocated untyped (i.e., typePtr==NULL) Tcl_Obj with a
* reference count of zero.
*
* Side effects:
* The string is "moved" to the object. dsPtr is reinitialized to an
* empty string; it does not need to be Tcl_DStringFree'd after this if
* not used further.
*
*----------------------------------------------------------------------
*/
Tcl_Obj *
TclDStringToObj(
Tcl_DString *dsPtr)
{
Tcl_Obj *result;
if (dsPtr->length == 0) {
TclNewObj(result);
} else if (dsPtr->string == dsPtr->staticSpace) {
/*
* Static buffer, so must copy.
*/
TclNewStringObj(result, dsPtr->string, dsPtr->length);
} else {
/*
* Dynamic buffer, so transfer ownership and reset.
*/
TclNewObj(result);
result->bytes = dsPtr->string;
result->length = dsPtr->length;
}
/*
* Re-establish the DString as empty with no buffer allocated.
*/
dsPtr->string = dsPtr->staticSpace;
dsPtr->spaceAvl = TCL_DSTRING_STATIC_SIZE;
dsPtr->length = 0;
dsPtr->staticSpace[0] = '\0';
return result;
}
/*
*----------------------------------------------------------------------
*
* Tcl_DStringStartSublist --
*
* This function adds the necessary information to a dynamic string
* (e.g. " {") to start a sublist. Future element appends will be in the
* sublist rather than the main list.
*
* Results:
* None.
*
* Side effects:
* Characters get added to the dynamic string.
*
*----------------------------------------------------------------------
*/
void
Tcl_DStringStartSublist(
Tcl_DString *dsPtr) /* Dynamic string. */
{
if (TclNeedSpace(dsPtr->string, dsPtr->string + dsPtr->length)) {
TclDStringAppendLiteral(dsPtr, " {");
} else {
TclDStringAppendLiteral(dsPtr, "{");
}
}
/*
*----------------------------------------------------------------------
*
* Tcl_DStringEndSublist --
*
* This function adds the necessary characters to a dynamic string to end
* a sublist (e.g. "}"). Future element appends will be in the enclosing
* (sub)list rather than the current sublist.
*
* Results:
* None.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
void
Tcl_DStringEndSublist(
Tcl_DString *dsPtr) /* Dynamic string. */
{
TclDStringAppendLiteral(dsPtr, "}");
}
/*
*----------------------------------------------------------------------
*
* Tcl_PrintDouble --
*
* Given a floating-point value, this function converts it to an ASCII
* string using.
*
* Results:
* The ASCII equivalent of "value" is written at "dst". It is written
* using the current precision, and it is guaranteed to contain a decimal
* point or exponent, so that it looks like a floating-point value and
* not an integer.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
void
Tcl_PrintDouble(
Tcl_Interp *interp, /* Interpreter whose tcl_precision variable
* used to be used to control printing. It's
* ignored now. */
double value, /* Value to print as string. */
char *dst) /* Where to store converted value; must have
* at least TCL_DOUBLE_SPACE characters. */
{
char *p, c;
int exponent;
int signum;
char *digits;
char *end;
int *precisionPtr = Tcl_GetThreadData(&precisionKey, (int) sizeof(int));
/*
* Handle NaN.
*/
if (TclIsNaN(value)) {
TclFormatNaN(value, dst);
return;
}
/*
* Handle infinities.
*/
if (TclIsInfinite(value)) {
/*
* Remember to copy the terminating NUL too.
*/
if (value < 0) {
memcpy(dst, "-Inf", 5);
} else {
memcpy(dst, "Inf", 4);
}
return;
}
/*
* Ordinary (normal and denormal) values.
*/
if (*precisionPtr == 0) {
digits = TclDoubleDigits(value, -1, TCL_DD_SHORTEST,
&exponent, &signum, &end);
} else {
/*
* There are at least two possible interpretations for tcl_precision.
*
* The first is, "choose the decimal representation having
* $tcl_precision digits of significance that is nearest to the given
* number, breaking ties by rounding to even, and then trimming
* trailing zeros." This gives the greatest possible precision in the
* decimal string, but offers the anomaly that [expr 0.1] will be
* "0.10000000000000001".
*
* The second is "choose the decimal representation having at most
* $tcl_precision digits of significance that is nearest to the given
* number. If no such representation converts exactly to the given
* number, choose the one that is closest, breaking ties by rounding
* to even. If more than one such representation converts exactly to
* the given number, choose the shortest, breaking ties in favour of
* the nearest, breaking remaining ties in favour of the one ending in
* an even digit."
*
* Tcl 8.4 implements the first of these, which gives rise to
* anomalies in formatting:
*
* % expr 0.1
* 0.10000000000000001
* % expr 0.01
* 0.01
* % expr 1e-7
* 9.9999999999999995e-08
*
* For human readability, it appears better to choose the second rule,
* and let [expr 0.1] return 0.1. But for 8.4 compatibility, we prefer
* the first (the recommended zero value for tcl_precision avoids the
* problem entirely).
*
* Uncomment TCL_DD_SHORTEN_FLAG in the next call to prefer the method
* that allows floating point values to be shortened if it can be done
* without loss of precision.
*/
digits = TclDoubleDigits(value, *precisionPtr,
TCL_DD_E_FORMAT /* | TCL_DD_SHORTEN_FLAG */,
&exponent, &signum, &end);
}
if (signum) {
*dst++ = '-';
}
p = digits;
if (exponent < -4 || exponent > 16) {
/*
* E format for numbers < 1e-3 or >= 1e17.
*/
*dst++ = *p++;
c = *p;
if (c != '\0') {
*dst++ = '.';
while (c != '\0') {
*dst++ = c;
c = *++p;
}
}
/*
* Tcl 8.4 appears to format with at least a two-digit exponent;
* preserve that behaviour when tcl_precision != 0
*/
if (*precisionPtr == 0) {
sprintf(dst, "e%+d", exponent);
} else {
sprintf(dst, "e%+03d", exponent);
}
} else {
/*
* F format for others.
*/
if (exponent < 0) {
*dst++ = '0';
}
c = *p;
while (exponent-- >= 0) {
if (c != '\0') {
*dst++ = c;
c = *++p;
} else {
*dst++ = '0';
}
}
*dst++ = '.';
if (c == '\0') {
*dst++ = '0';
} else {
while (++exponent < -1) {
*dst++ = '0';
}
while (c != '\0') {
*dst++ = c;
c = *++p;
}
}
*dst++ = '\0';
}
ckfree(digits);
}
/*
*----------------------------------------------------------------------
*
* TclPrecTraceProc --
*
* This function is invoked whenever the variable "tcl_precision" is
* written.
*
* Results:
* Returns NULL if all went well, or an error message if the new value
* for the variable doesn't make sense.
*
* Side effects:
* If the new value doesn't make sense then this function undoes the
* effect of the variable modification. Otherwise it modifies the format
* string that's used by Tcl_PrintDouble.
*
*----------------------------------------------------------------------
*/
/* ARGSUSED */
char *
TclPrecTraceProc(
ClientData clientData, /* Not used. */
Tcl_Interp *interp, /* Interpreter containing variable. */
const char *name1, /* Name of variable. */
const char *name2, /* Second part of variable name. */
int flags) /* Information about what happened. */
{
Tcl_Obj *value;
int prec;
int *precisionPtr = Tcl_GetThreadData(&precisionKey, (int) sizeof(int));
/*
* If the variable is unset, then recreate the trace.
*/
if (flags & TCL_TRACE_UNSETS) {
if ((flags & TCL_TRACE_DESTROYED) && !Tcl_InterpDeleted(interp)) {
Tcl_TraceVar2(interp, name1, name2,
TCL_GLOBAL_ONLY|TCL_TRACE_READS|TCL_TRACE_WRITES
|TCL_TRACE_UNSETS, TclPrecTraceProc, clientData);
}
return NULL;
}
/*
* When the variable is read, reset its value from our shared value. This
* is needed in case the variable was modified in some other interpreter
* so that this interpreter's value is out of date.
*/
if (flags & TCL_TRACE_READS) {
Tcl_SetVar2Ex(interp, name1, name2, Tcl_NewIntObj(*precisionPtr),
flags & TCL_GLOBAL_ONLY);
return NULL;
}
/*
* The variable is being written. Check the new value and disallow it if
* it isn't reasonable or if this is a safe interpreter (we don't want
* safe interpreters messing up the precision of other interpreters).
*/
if (Tcl_IsSafe(interp)) {
return (char *) "can't modify precision from a safe interpreter";
}
value = Tcl_GetVar2Ex(interp, name1, name2, flags & TCL_GLOBAL_ONLY);
if (value == NULL
|| Tcl_GetIntFromObj(NULL, value, &prec) != TCL_OK
|| prec < 0 || prec > TCL_MAX_PREC) {
return (char *) "improper value for precision";
}
*precisionPtr = prec;
return NULL;
}
/*
*----------------------------------------------------------------------
*
* TclNeedSpace --
*
* This function checks to see whether it is appropriate to add a space
* before appending a new list element to an existing string.
*
* Results:
* The return value is 1 if a space is appropriate, 0 otherwise.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
TclNeedSpace(
const char *start, /* First character in string. */
const char *end) /* End of string (place where space will be
* added, if appropriate). */
{
/*
* A space is needed unless either:
* (a) we're at the start of the string, or
*/
if (end == start) {
return 0;
}
/*
* (b) we're at the start of a nested list-element, quoted with an open
* curly brace; we can be nested arbitrarily deep, so long as the
* first curly brace starts an element, so backtrack over open curly
* braces that are trailing characters of the string; and
*/
end = Tcl_UtfPrev(end, start);
while (*end == '{') {
if (end == start) {
return 0;
}
end = Tcl_UtfPrev(end, start);
}
/*
* (c) the trailing character of the string is already a list-element
* separator (according to TclFindElement); that is, one of these
* characters:
* \u0009 \t TAB
* \u000A \n NEWLINE
* \u000B \v VERTICAL TAB
* \u000C \f FORM FEED
* \u000D \r CARRIAGE RETURN
* \u0020 SPACE
* with the condition that the penultimate character is not a
* backslash.
*/
if (*end > 0x20) {
/*
* Performance tweak. All ASCII spaces are <= 0x20. So get a quick
* answer for most characters before comparing against all spaces in
* the switch below.
*
* NOTE: Remove this if other Unicode spaces ever get accepted as
* list-element separators.
*/
return 1;
}
switch (*end) {
case ' ':
case '\t':
case '\n':
case '\r':
case '\v':
case '\f':
if ((end == start) || (end[-1] != '\\')) {
return 0;
}
}
return 1;
}
/*
*----------------------------------------------------------------------
*
* TclFormatInt --
*
* This procedure formats an integer into a sequence of decimal digit
* characters in a buffer. If the integer is negative, a minus sign is
* inserted at the start of the buffer. A null character is inserted at
* the end of the formatted characters. It is the caller's responsibility
* to ensure that enough storage is available. This procedure has the
* effect of sprintf(buffer, "%ld", n) but is faster as proven in
* benchmarks. This is key to UpdateStringOfInt, which is a common path
* for a lot of code (e.g. int-indexed arrays).
*
* Results:
* An integer representing the number of characters formatted, not
* including the terminating \0.
*
* Side effects:
* The formatted characters are written into the storage pointer to by
* the "buffer" argument.
*
*----------------------------------------------------------------------
*/
int
TclFormatInt(
char *buffer, /* Points to the storage into which the
* formatted characters are written. */
long n) /* The integer to format. */
{
long intVal;
int i;
int numFormatted, j;
const char *digits = "0123456789";
/*
* Check first whether "n" is zero.
*/
if (n == 0) {
buffer[0] = '0';
buffer[1] = 0;
return 1;
}
/*
* Check whether "n" is the maximum negative value. This is -2^(m-1) for
* an m-bit word, and has no positive equivalent; negating it produces the
* same value.
*/
intVal = -n; /* [Bug 3390638] Workaround for*/
if (n == -n || intVal == n) { /* broken compiler optimizers. */
return sprintf(buffer, "%ld", n);
}
/*
* Generate the characters of the result backwards in the buffer.
*/
intVal = (n < 0? -n : n);
i = 0;
buffer[0] = '\0';
do {
i++;
buffer[i] = digits[intVal % 10];
intVal = intVal/10;
} while (intVal > 0);
if (n < 0) {
i++;
buffer[i] = '-';
}
numFormatted = i;
/*
* Now reverse the characters.
*/
for (j = 0; j < i; j++, i--) {
char tmp = buffer[i];
buffer[i] = buffer[j];
buffer[j] = tmp;
}
return numFormatted;
}
/*
*----------------------------------------------------------------------
*
* TclGetIntForIndex --
*
* This function returns an integer corresponding to the list index held
* in a Tcl object. The Tcl object's value is expected to be in the
* format integer([+-]integer)? or the format end([+-]integer)?.
*
* Results:
* The return value is normally TCL_OK, which means that the index was
* successfully stored into the location referenced by "indexPtr". If the
* Tcl object referenced by "objPtr" has the value "end", the value
* stored is "endValue". If "objPtr"s values is not of one of the
* expected formats, TCL_ERROR is returned and, if "interp" is non-NULL,
* an error message is left in the interpreter's result object.
*
* Side effects:
* The object referenced by "objPtr" might be converted to an integer,
* wide integer, or end-based-index object.
*
*----------------------------------------------------------------------
*/
int
TclGetIntForIndex(
Tcl_Interp *interp, /* Interpreter to use for error reporting. If
* NULL, then no error message is left after
* errors. */
Tcl_Obj *objPtr, /* Points to an object containing either "end"
* or an integer. */
int endValue, /* The value to be stored at "indexPtr" if
* "objPtr" holds "end". */
int *indexPtr) /* Location filled in with an integer
* representing an index. */
{
int length;
char *opPtr;
const char *bytes;
if (TclGetIntFromObj(NULL, objPtr, indexPtr) == TCL_OK) {
return TCL_OK;
}
if (SetEndOffsetFromAny(NULL, objPtr) == TCL_OK) {
/*
* If the object is already an offset from the end of the list, or can
* be converted to one, use it.
*/
*indexPtr = endValue + objPtr->internalRep.longValue;
return TCL_OK;
}
bytes = TclGetStringFromObj(objPtr, &length);
/*
* Leading whitespace is acceptable in an index.
*/
while (length && TclIsSpaceProc(*bytes)) {
bytes++;
length--;
}
if (TclParseNumber(NULL, NULL, NULL, bytes, length, (const char **)&opPtr,
TCL_PARSE_INTEGER_ONLY | TCL_PARSE_NO_WHITESPACE) == TCL_OK) {
int code, first, second;
char savedOp = *opPtr;
if ((savedOp != '+') && (savedOp != '-')) {
goto parseError;
}
if (TclIsSpaceProc(opPtr[1])) {
goto parseError;
}
*opPtr = '\0';
code = Tcl_GetInt(interp, bytes, &first);
*opPtr = savedOp;
if (code == TCL_ERROR) {
goto parseError;
}
if (TCL_ERROR == Tcl_GetInt(interp, opPtr+1, &second)) {
goto parseError;
}
if (savedOp == '+') {
*indexPtr = first + second;
} else {
*indexPtr = first - second;
}
return TCL_OK;
}
/*
* Report a parse error.
*/
parseError:
if (interp != NULL) {
bytes = Tcl_GetString(objPtr);
Tcl_SetObjResult(interp, Tcl_ObjPrintf(
"bad index \"%s\": must be integer?[+-]integer? or"
" end?[+-]integer?", bytes));
if (!strncmp(bytes, "end-", 4)) {
bytes += 4;
}
Tcl_SetErrorCode(interp, "TCL", "VALUE", "INDEX", NULL);
}
return TCL_ERROR;
}
/*
*----------------------------------------------------------------------
*
* UpdateStringOfEndOffset --
*
* Update the string rep of a Tcl object holding an "end-offset"
* expression.
*
* Results:
* None.
*
* Side effects:
* Stores a valid string in the object's string rep.
*
* This function does NOT free any earlier string rep. If it is called on an
* object that already has a valid string rep, it will leak memory.
*
*----------------------------------------------------------------------
*/
static void
UpdateStringOfEndOffset(
register Tcl_Obj *objPtr)
{
char buffer[TCL_INTEGER_SPACE + 5];
register int len;
memcpy(buffer, "end", 4);
len = sizeof("end") - 1;
if (objPtr->internalRep.longValue != 0) {
buffer[len++] = '-';
len += TclFormatInt(buffer+len, -(objPtr->internalRep.longValue));
}
objPtr->bytes = ckalloc((unsigned) len+1);
memcpy(objPtr->bytes, buffer, (unsigned) len+1);
objPtr->length = len;
}
/*
*----------------------------------------------------------------------
*
* SetEndOffsetFromAny --
*
* Look for a string of the form "end[+-]offset" and convert it to an
* internal representation holding the offset.
*
* Results:
* Returns TCL_OK if ok, TCL_ERROR if the string was badly formed.
*
* Side effects:
* If interp is not NULL, stores an error message in the interpreter
* result.
*
*----------------------------------------------------------------------
*/
static int
SetEndOffsetFromAny(
Tcl_Interp *interp, /* Tcl interpreter or NULL */
Tcl_Obj *objPtr) /* Pointer to the object to parse */
{
int offset; /* Offset in the "end-offset" expression */
register const char *bytes; /* String rep of the object */
int length; /* Length of the object's string rep */
/*
* If it's already the right type, we're fine.
*/
if (objPtr->typePtr == &tclEndOffsetType) {
return TCL_OK;
}
/*
* Check for a string rep of the right form.
*/
bytes = TclGetStringFromObj(objPtr, &length);
if ((*bytes != 'e') || (strncmp(bytes, "end",
(size_t)((length > 3) ? 3 : length)) != 0)) {
if (interp != NULL) {
Tcl_SetObjResult(interp, Tcl_ObjPrintf(
"bad index \"%s\": must be end?[+-]integer?", bytes));
Tcl_SetErrorCode(interp, "TCL", "VALUE", "INDEX", NULL);
}
return TCL_ERROR;
}
/*
* Convert the string rep.
*/
if (length <= 3) {
offset = 0;
} else if ((length > 4) && ((bytes[3] == '-') || (bytes[3] == '+'))) {
/*
* This is our limited string expression evaluator. Pass everything
* after "end-" to Tcl_GetInt, then reverse for offset.
*/
if (TclIsSpaceProc(bytes[4])) {
goto badIndexFormat;
}
if (Tcl_GetInt(interp, bytes+4, &offset) != TCL_OK) {
return TCL_ERROR;
}
if (bytes[3] == '-') {
offset = -offset;
}
} else {
/*
* Conversion failed. Report the error.
*/
badIndexFormat:
if (interp != NULL) {
Tcl_SetObjResult(interp, Tcl_ObjPrintf(
"bad index \"%s\": must be end?[+-]integer?", bytes));
Tcl_SetErrorCode(interp, "TCL", "VALUE", "INDEX", NULL);
}
return TCL_ERROR;
}
/*
* The conversion succeeded. Free the old internal rep and set the new
* one.
*/
TclFreeIntRep(objPtr);
objPtr->internalRep.longValue = offset;
objPtr->typePtr = &tclEndOffsetType;
return TCL_OK;
}
/*
*----------------------------------------------------------------------
*
* ClearHash --
*
* Remove all the entries in the hash table *tablePtr.
*
*----------------------------------------------------------------------
*/
static void
ClearHash(
Tcl_HashTable *tablePtr)
{
Tcl_HashSearch search;
Tcl_HashEntry *hPtr;
for (hPtr = Tcl_FirstHashEntry(tablePtr, &search); hPtr != NULL;
hPtr = Tcl_NextHashEntry(&search)) {
Tcl_Obj *objPtr = Tcl_GetHashValue(hPtr);
Tcl_DecrRefCount(objPtr);
Tcl_DeleteHashEntry(hPtr);
}
}
/*
*----------------------------------------------------------------------
*
* GetThreadHash --
*
* Get a thread-specific (Tcl_HashTable *) associated with a thread data
* key.
*
* Results:
* The Tcl_HashTable * corresponding to *keyPtr.
*
* Side effects:
* The first call on a keyPtr in each thread creates a new Tcl_HashTable,
* and registers a thread exit handler to dispose of it.
*
*----------------------------------------------------------------------
*/
static Tcl_HashTable *
GetThreadHash(
Tcl_ThreadDataKey *keyPtr)
{
Tcl_HashTable **tablePtrPtr =
Tcl_GetThreadData(keyPtr, sizeof(Tcl_HashTable *));
if (NULL == *tablePtrPtr) {
*tablePtrPtr = ckalloc(sizeof(Tcl_HashTable));
Tcl_CreateThreadExitHandler(FreeThreadHash, *tablePtrPtr);
Tcl_InitHashTable(*tablePtrPtr, TCL_ONE_WORD_KEYS);
}
return *tablePtrPtr;
}
/*
*----------------------------------------------------------------------
*
* FreeThreadHash --
*
* Thread exit handler used by GetThreadHash to dispose of a thread hash
* table.
*
* Side effects:
* Frees a Tcl_HashTable.
*
*----------------------------------------------------------------------
*/
static void
FreeThreadHash(
ClientData clientData)
{
Tcl_HashTable *tablePtr = clientData;
ClearHash(tablePtr);
Tcl_DeleteHashTable(tablePtr);
ckfree(tablePtr);
}
/*
*----------------------------------------------------------------------
*
* FreeProcessGlobalValue --
*
* Exit handler used by Tcl(Set|Get)ProcessGlobalValue to cleanup a
* ProcessGlobalValue at exit.
*
*----------------------------------------------------------------------
*/
static void
FreeProcessGlobalValue(
ClientData clientData)
{
ProcessGlobalValue *pgvPtr = clientData;
pgvPtr->epoch++;
pgvPtr->numBytes = 0;
ckfree(pgvPtr->value);
pgvPtr->value = NULL;
if (pgvPtr->encoding) {
Tcl_FreeEncoding(pgvPtr->encoding);
pgvPtr->encoding = NULL;
}
Tcl_MutexFinalize(&pgvPtr->mutex);
}
/*
*----------------------------------------------------------------------
*
* TclSetProcessGlobalValue --
*
* Utility routine to set a global value shared by all threads in the
* process while keeping a thread-local copy as well.
*
*----------------------------------------------------------------------
*/
void
TclSetProcessGlobalValue(
ProcessGlobalValue *pgvPtr,
Tcl_Obj *newValue,
Tcl_Encoding encoding)
{
const char *bytes;
Tcl_HashTable *cacheMap;
Tcl_HashEntry *hPtr;
int dummy;
Tcl_MutexLock(&pgvPtr->mutex);
/*
* Fill the global string value.
*/
pgvPtr->epoch++;
if (NULL != pgvPtr->value) {
ckfree(pgvPtr->value);
} else {
Tcl_CreateExitHandler(FreeProcessGlobalValue, pgvPtr);
}
bytes = Tcl_GetStringFromObj(newValue, &pgvPtr->numBytes);
pgvPtr->value = ckalloc(pgvPtr->numBytes + 1);
memcpy(pgvPtr->value, bytes, (unsigned) pgvPtr->numBytes + 1);
if (pgvPtr->encoding) {
Tcl_FreeEncoding(pgvPtr->encoding);
}
pgvPtr->encoding = encoding;
/*
* Fill the local thread copy directly with the Tcl_Obj value to avoid
* loss of the intrep. Increment newValue refCount early to handle case
* where we set a PGV to itself.
*/
Tcl_IncrRefCount(newValue);
cacheMap = GetThreadHash(&pgvPtr->key);
ClearHash(cacheMap);
hPtr = Tcl_CreateHashEntry(cacheMap, INT2PTR(pgvPtr->epoch), &dummy);
Tcl_SetHashValue(hPtr, newValue);
Tcl_MutexUnlock(&pgvPtr->mutex);
}
/*
*----------------------------------------------------------------------
*
* TclGetProcessGlobalValue --
*
* Retrieve a global value shared among all threads of the process,
* preferring a thread-local copy as long as it remains valid.
*
* Results:
* Returns a (Tcl_Obj *) that holds a copy of the global value.
*
*----------------------------------------------------------------------
*/
Tcl_Obj *
TclGetProcessGlobalValue(
ProcessGlobalValue *pgvPtr)
{
Tcl_Obj *value = NULL;
Tcl_HashTable *cacheMap;
Tcl_HashEntry *hPtr;
int epoch = pgvPtr->epoch;
if (pgvPtr->encoding) {
Tcl_Encoding current = Tcl_GetEncoding(NULL, NULL);
if (pgvPtr->encoding != current) {
/*
* The system encoding has changed since the master string value
* was saved. Convert the master value to be based on the new
* system encoding.
*/
Tcl_DString native, newValue;
Tcl_MutexLock(&pgvPtr->mutex);
pgvPtr->epoch++;
epoch = pgvPtr->epoch;
Tcl_UtfToExternalDString(pgvPtr->encoding, pgvPtr->value,
pgvPtr->numBytes, &native);
Tcl_ExternalToUtfDString(current, Tcl_DStringValue(&native),
Tcl_DStringLength(&native), &newValue);
Tcl_DStringFree(&native);
ckfree(pgvPtr->value);
pgvPtr->value = ckalloc(Tcl_DStringLength(&newValue) + 1);
memcpy(pgvPtr->value, Tcl_DStringValue(&newValue),
(size_t) Tcl_DStringLength(&newValue) + 1);
Tcl_DStringFree(&newValue);
Tcl_FreeEncoding(pgvPtr->encoding);
pgvPtr->encoding = current;
Tcl_MutexUnlock(&pgvPtr->mutex);
} else {
Tcl_FreeEncoding(current);
}
}
cacheMap = GetThreadHash(&pgvPtr->key);
hPtr = Tcl_FindHashEntry(cacheMap, (char *) INT2PTR(epoch));
if (NULL == hPtr) {
int dummy;
/*
* No cache for the current epoch - must be a new one.
*
* First, clear the cacheMap, as anything in it must refer to some
* expired epoch.
*/
ClearHash(cacheMap);
/*
* If no thread has set the shared value, call the initializer.
*/
Tcl_MutexLock(&pgvPtr->mutex);
if ((NULL == pgvPtr->value) && (pgvPtr->proc)) {
pgvPtr->epoch++;
pgvPtr->proc(&pgvPtr->value,&pgvPtr->numBytes,&pgvPtr->encoding);
if (pgvPtr->value == NULL) {
Tcl_Panic("PGV Initializer did not initialize");
}
Tcl_CreateExitHandler(FreeProcessGlobalValue, pgvPtr);
}
/*
* Store a copy of the shared value in our epoch-indexed cache.
*/
value = Tcl_NewStringObj(pgvPtr->value, pgvPtr->numBytes);
hPtr = Tcl_CreateHashEntry(cacheMap,
INT2PTR(pgvPtr->epoch), &dummy);
Tcl_MutexUnlock(&pgvPtr->mutex);
Tcl_SetHashValue(hPtr, value);
Tcl_IncrRefCount(value);
}
return Tcl_GetHashValue(hPtr);
}
/*
*----------------------------------------------------------------------
*
* TclSetObjNameOfExecutable --
*
* This function stores the absolute pathname of the executable file
* (normally as computed by TclpFindExecutable).
*
* Results:
* None.
*
* Side effects:
* Stores the executable name.
*
*----------------------------------------------------------------------
*/
void
TclSetObjNameOfExecutable(
Tcl_Obj *name,
Tcl_Encoding encoding)
{
TclSetProcessGlobalValue(&executableName, name, encoding);
}
/*
*----------------------------------------------------------------------
*
* TclGetObjNameOfExecutable --
*
* This function retrieves the absolute pathname of the application in
* which the Tcl library is running, usually as previously stored by
* TclpFindExecutable(). This function call is the C API equivalent to
* the "info nameofexecutable" command.
*
* Results:
* A pointer to an "fsPath" Tcl_Obj, or to an empty Tcl_Obj if the
* pathname of the application is unknown.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
Tcl_Obj *
TclGetObjNameOfExecutable(void)
{
return TclGetProcessGlobalValue(&executableName);
}
/*
*----------------------------------------------------------------------
*
* Tcl_GetNameOfExecutable --
*
* This function retrieves the absolute pathname of the application in
* which the Tcl library is running, and returns it in string form.
*
* The returned string belongs to Tcl and should be copied if the caller
* plans to keep it, to guard against it becoming invalid.
*
* Results:
* A pointer to the internal string or NULL if the internal full path
* name has not been computed or unknown.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
const char *
Tcl_GetNameOfExecutable(void)
{
int numBytes;
const char *bytes =
Tcl_GetStringFromObj(TclGetObjNameOfExecutable(), &numBytes);
if (numBytes == 0) {
return NULL;
}
return bytes;
}
/*
*----------------------------------------------------------------------
*
* TclGetPlatform --
*
* This is a kludge that allows the test library to get access the
* internal tclPlatform variable.
*
* Results:
* Returns a pointer to the tclPlatform variable.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
TclPlatformType *
TclGetPlatform(void)
{
return &tclPlatform;
}
/*
*----------------------------------------------------------------------
*
* TclReToGlob --
*
* Attempt to convert a regular expression to an equivalent glob pattern.
*
* Results:
* Returns TCL_OK on success, TCL_ERROR on failure. If interp is not
* NULL, an error message is placed in the result. On success, the
* DString will contain an exact equivalent glob pattern. The caller is
* responsible for calling Tcl_DStringFree on success. If exactPtr is not
* NULL, it will be 1 if an exact match qualifies.
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
TclReToGlob(
Tcl_Interp *interp,
const char *reStr,
int reStrLen,
Tcl_DString *dsPtr,
int *exactPtr)
{
int anchorLeft, anchorRight, lastIsStar, numStars;
char *dsStr, *dsStrStart;
const char *msg, *p, *strEnd, *code;
strEnd = reStr + reStrLen;
Tcl_DStringInit(dsPtr);
/*
* "***=xxx" == "*xxx*", watch for glob-sensitive chars.
*/
if ((reStrLen >= 4) && (memcmp("***=", reStr, 4) == 0)) {
/*
* At most, the glob pattern has length 2*reStrLen + 2 to backslash
* escape every character and have * at each end.
*/
Tcl_DStringSetLength(dsPtr, reStrLen + 2);
dsStr = dsStrStart = Tcl_DStringValue(dsPtr);
*dsStr++ = '*';
for (p = reStr + 4; p < strEnd; p++) {
switch (*p) {
case '\\': case '*': case '[': case ']': case '?':
/* Only add \ where necessary for glob */
*dsStr++ = '\\';
/* fall through */
default:
*dsStr++ = *p;
break;
}
}
*dsStr++ = '*';
Tcl_DStringSetLength(dsPtr, dsStr - dsStrStart);
if (exactPtr) {
*exactPtr = 0;
}
return TCL_OK;
}
/*
* At most, the glob pattern has length reStrLen + 2 to account for
* possible * at each end.
*/
Tcl_DStringSetLength(dsPtr, reStrLen + 2);
dsStr = dsStrStart = Tcl_DStringValue(dsPtr);
/*
* Check for anchored REs (ie ^foo$), so we can use string equal if
* possible. Do not alter the start of str so we can free it correctly.
*
* Keep track of the last char being an unescaped star to prevent multiple
* instances. Simpler than checking that the last star may be escaped.
*/
msg = NULL;
code = NULL;
p = reStr;
anchorRight = 0;
lastIsStar = 0;
numStars = 0;
if (*p == '^') {
anchorLeft = 1;
p++;
} else {
anchorLeft = 0;
*dsStr++ = '*';
lastIsStar = 1;
}
for ( ; p < strEnd; p++) {
switch (*p) {
case '\\':
p++;
switch (*p) {
case 'a':
*dsStr++ = '\a';
break;
case 'b':
*dsStr++ = '\b';
break;
case 'f':
*dsStr++ = '\f';
break;
case 'n':
*dsStr++ = '\n';
break;
case 'r':
*dsStr++ = '\r';
break;
case 't':
*dsStr++ = '\t';
break;
case 'v':
*dsStr++ = '\v';
break;
case 'B': case '\\':
*dsStr++ = '\\';
*dsStr++ = '\\';
anchorLeft = 0; /* prevent exact match */
break;
case '*': case '[': case ']': case '?':
/* Only add \ where necessary for glob */
*dsStr++ = '\\';
anchorLeft = 0; /* prevent exact match */
/* fall through */
case '{': case '}': case '(': case ')': case '+':
case '.': case '|': case '^': case '$':
*dsStr++ = *p;
break;
default:
msg = "invalid escape sequence";
code = "BADESCAPE";
goto invalidGlob;
}
break;
case '.':
anchorLeft = 0; /* prevent exact match */
if (p+1 < strEnd) {
if (p[1] == '*') {
p++;
if (!lastIsStar) {
*dsStr++ = '*';
lastIsStar = 1;
numStars++;
}
continue;
} else if (p[1] == '+') {
p++;
*dsStr++ = '?';
*dsStr++ = '*';
lastIsStar = 1;
numStars++;
continue;
}
}
*dsStr++ = '?';
break;
case '$':
if (p+1 != strEnd) {
msg = "$ not anchor";
code = "NONANCHOR";
goto invalidGlob;
}
anchorRight = 1;
break;
case '*': case '+': case '?': case '|': case '^':
case '{': case '}': case '(': case ')': case '[': case ']':
msg = "unhandled RE special char";
code = "UNHANDLED";
goto invalidGlob;
default:
*dsStr++ = *p;
break;
}
lastIsStar = 0;
}
if (numStars > 1) {
/*
* Heuristic: if >1 non-anchoring *, the risk is large that glob
* matching is slower than the RE engine, so report invalid.
*/
msg = "excessive recursive glob backtrack potential";
code = "OVERCOMPLEX";
goto invalidGlob;
}
if (!anchorRight && !lastIsStar) {
*dsStr++ = '*';
}
Tcl_DStringSetLength(dsPtr, dsStr - dsStrStart);
if (exactPtr) {
*exactPtr = (anchorLeft && anchorRight);
}
return TCL_OK;
invalidGlob:
if (interp != NULL) {
Tcl_SetObjResult(interp, Tcl_NewStringObj(msg, -1));
Tcl_SetErrorCode(interp, "TCL", "RE2GLOB", code, NULL);
}
Tcl_DStringFree(dsPtr);
return TCL_ERROR;
}
/*
* Local Variables:
* mode: c
* c-basic-offset: 4
* fill-column: 78
* End:
*/
|