aboutsummaryrefslogtreecommitdiffstats
path: root/doc/README.developer
blob: 87b53516ba9b05f902215c16d523bf7ea8cb98b8 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
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
$Revision$
$Date$
$Author$
Tabsize: 4

This file is a HOWTO for Wireshark developers. It describes how to start coding
a Wireshark protocol dissector and the use of some of the important functions
and variables.

This file is compiled to give in depth information on Wireshark.
It is by no means all inclusive and complete. Please feel free to send
remarks and patches to the developer mailing list.

0. Prerequisites.

Before starting to develop a new dissector, a "running" Wireshark build
environment is required - there's no such thing as a standalone "dissector
build toolkit".

How to setup such an environment is platform dependent; detailed information
about these steps can be found in the "Developer's Guide" (available from:
http://www.wireshark.org) and in the INSTALL and README files of the sources
root dir.

0.1. General README files.

You'll find additional information in the following README files:

- README.capture        - the capture engine internals
- README.design         - Wireshark software design - incomplete
- README.developer      - this file
- README.display_filter - Display Filter Engine
- README.idl2wrs        - CORBA IDL converter
- README.packaging      - how to distribute a software package containing WS
- README.regression     - regression testing of WS and TS
- README.stats_tree     - a tree statistics counting specific packets
- README.tapping        - "tap" a dissector to get protocol specific events
- README.xml-output     - how to work with the PDML exported output
- wiretap/README.developer - how to add additional capture file types to
  Wiretap

0.2. Dissector related README files.

You'll find additional dissector related information in the following README
files:

- README.binarytrees    - fast access to large data collections
- README.heuristic      - what are heuristic dissectors and how to write them
- README.malloc         - how to obtain "memory leak free" memory
- README.plugins        - how to "pluginize" a dissector
- README.python         - writing a dissector in PYTHON.
- README.request_response_tracking - how to track req./resp. times and such

0.3 Contributors

James Coe <jammer[AT]cin.net>
Gilbert Ramirez <gram[AT]alumni.rice.edu>
Jeff Foster <jfoste[AT]woodward.com>
Olivier Abad <oabad[AT]cybercable.fr>
Laurent Deniel <laurent.deniel[AT]free.fr>
Gerald Combs <gerald[AT]wireshark.org>
Guy Harris <guy[AT]alum.mit.edu>
Ulf Lamping <ulf.lamping[AT]web.de>

1. Setting up your protocol dissector code.

This section provides skeleton code for a protocol dissector. It also explains
the basic functions needed to enter values in the traffic summary columns,
add to the protocol tree, and work with registered header fields.

1.1 Code style.

1.1.1 Portability.

Wireshark runs on many platforms, and can be compiled with a number of
different compilers; here are some rules for writing code that will work
on multiple platforms.

Don't use C++-style comments (comments beginning with "//" and running
to the end of the line); Wireshark's dissectors are written in C, and
thus run through C rather than C++ compilers, and not all C compilers
support C++-style comments (GCC does, but IBM's C compiler for AIX, for
example, doesn't do so by default).

In general, don't use C99 features since some C compilers used to compile
Wireshark don't support C99 (E.G. Microsoft C).

Don't initialize variables in their declaration with non-constant
values. Not all compilers support this. E.g. don't use
	guint32 i = somearray[2];
use
	guint32 i;
	i = somearray[2];
instead.

Don't use zero-length arrays; not all compilers support them.  If an
array would have no members, just leave it out.

Don't declare variables in the middle of executable code; not all C
compilers support that.  Variables should be declared outside a
function, or at the beginning of a function or compound statement.

Don't use anonymous unions; not all compilers support them.
Example:

	typedef struct foo {
	  guint32 foo;
	  union {
	    guint32 foo_l;
	    guint16 foo_s;
	  } u;  /* have a name here */
	} foo_t;

Don't use "uchar", "u_char", "ushort", "u_short", "uint", "u_int",
"ulong", "u_long" or "boolean"; they aren't defined on all platforms.
If you want an 8-bit unsigned quantity, use "guint8"; if you want an
8-bit character value with the 8th bit not interpreted as a sign bit,
use "guchar"; if you want a 16-bit unsigned quantity, use "guint16";
if you want a 32-bit unsigned quantity, use "guint32"; and if you want
an "int-sized" unsigned quantity, use "guint"; if you want a boolean,
use "gboolean".  Use "%d", "%u", "%x", and "%o" to print those types;
don't use "%ld", "%lu", "%lx", or "%lo", as longs are 64 bits long on
many platforms, but "guint32" is 32 bits long.

Don't use "long" to mean "signed 32-bit integer", and don't use
"unsigned long" to mean "unsigned 32-bit integer"; "long"s are 64 bits
long on many platforms.  Use "gint32" for signed 32-bit integers and use
"guint32" for unsigned 32-bit integers.

Don't use "long" to mean "signed 64-bit integer" and don't use "unsigned
long" to mean "unsigned 64-bit integer"; "long"s are 32 bits long on
many other platforms.  Don't use "long long" or "unsigned long long",
either, as not all platforms support them; use "gint64" or "guint64",
which will be defined as the appropriate types for 64-bit signed and
unsigned integers.

On LLP64 data model systems (notably 64-bit Windows), "int" and "long"
are 32 bits while "size_t" and "ptrdiff_t" are 64 bits. This means that
the following will generate a compiler warning:

	int i;
	i = strlen("hello, sailor");  /* Compiler warning */

Normally, you'd just make "i" a size_t. However, many GLib and Wireshark
functions won't accept a size_t on LLP64:

	size_t i;
	char greeting[] = "hello, sailor";
	guint byte_after_greet;

	i = strlen(greeting);
	byte_after_greet = tvb_get_guint8(tvb, i); /* Compiler warning */

Try to use the appropriate data type when you can. When you can't, you
will have to cast to a compatible data type, e.g.

	size_t i;
	char greeting[] = "hello, sailor";
	guint byte_after_greet;

	i = strlen(greeting);
	byte_after_greet = tvb_get_guint8(tvb, (gint) i); /* OK */

or

	gint i;
	char greeting[] = "hello, sailor";
	guint byte_after_greet;

	i = (gint) strlen(greeting);
	byte_after_greet = tvb_get_guint8(tvb, i); /* OK */

See http://www.unix.org/version2/whatsnew/lp64_wp.html for more
information on the sizes of common types in different data models.

When printing or displaying the values of 64-bit integral data types,
don't use "%lld", "%llu", "%llx", or "%llo" - not all platforms
support "%ll" for printing 64-bit integral data types.  Instead, for
GLib routines, and routines that use them, such as all the routines in
Wireshark that take format arguments, use G_GINT64_MODIFIER, for example:

    proto_tree_add_text(tree, tvb, offset, 8,
			"Sequence Number: %" G_GINT64_MODIFIER "u",
			sequence_number);

When specifying an integral constant that doesn't fit in 32 bits, don't
use "LL" at the end of the constant - not all compilers use "LL" for
that.  Instead, put the constant in a call to the "G_GINT64_CONSTANT()"
macro, e.g.

	G_GINT64_CONSTANT(11644473600U)

rather than

	11644473600ULL

Don't assume that you can scan through a va_list initialized by va_start
more than once without closing it with va_end and re-initalizing it with
va_start.  This applies even if you're not scanning through it yourself,
but are calling a routine that scans through it, such as vfprintf() or
one of the routines in Wireshark that takes a format and a va_list as an
argument.  You must do

	va_start(ap, format);
	call_routine1(xxx, format, ap);
	va_end(ap);
	va_start(ap, format);
	call_routine2(xxx, format, ap);
	va_end(ap);

rather
	va_start(ap, format);
	call_routine1(xxx, format, ap);
	call_routine2(xxx, format, ap);
	va_end(ap);

Don't use a label without a statement following it.  For example,
something such as

	if (...) {

		...

	done:
	}

will not work with all compilers - you have to do

	if (...) {

		...

	done:
		;
	}

with some statement, even if it's a null statement, after the label.

Don't use "bzero()", "bcopy()", or "bcmp()"; instead, use the ANSI C
routines

	"memset()" (with zero as the second argument, so that it sets
	all the bytes to zero);

	"memcpy()" or "memmove()" (note that the first and second
	arguments to "memcpy()" are in the reverse order to the
	arguments to "bcopy()"; note also that "bcopy()" is typically
	guaranteed to work on overlapping memory regions, while
	"memcpy()" isn't, so if you may be copying from one region to a
	region that overlaps it, use "memmove()", not "memcpy()" - but
	"memcpy()" might be faster as a result of not guaranteeing
	correct operation on overlapping memory regions);

	and "memcmp()" (note that "memcmp()" returns 0, 1, or -1, doing
	an ordered comparison, rather than just returning 0 for "equal"
	and 1 for "not equal", as "bcmp()" does).

Not all platforms necessarily have "bzero()"/"bcopy()"/"bcmp()", and
those that do might not declare them in the header file on which they're
declared on your platform.

Don't use "index()" or "rindex()"; instead, use the ANSI C equivalents,
"strchr()" and "strrchr()".  Not all platforms necessarily have
"index()" or "rindex()", and those that do might not declare them in the
header file on which they're declared on your platform.

Don't fetch data from packets by getting a pointer to data in the packet
with "tvb_get_ptr()", casting that pointer to a pointer to a structure,
and dereferencing that pointer.  That pointer won't necessarily be aligned
on the proper boundary, which can cause crashes on some platforms (even
if it doesn't crash on an x86-based PC); furthermore, the data in a
packet is not necessarily in the byte order of the machine on which
Wireshark is running.  Use the tvbuff routines to extract individual
items from the packet, or use "proto_tree_add_item()" and let it extract
the items for you.

Don't use structures that overlay packet data, or into which you copy
packet data; the C programming language does not guarantee any
particular alignment of fields within a structure, and even the
extensions that try to guarantee that are compiler-specific and not
necessarily supported by all compilers used to build Wireshark.  Using
bitfields in those structures is even worse; the order of bitfields
is not guaranteed.

Don't use "ntohs()", "ntohl()", "htons()", or "htonl()"; the header
files required to define or declare them differ between platforms, and
you might be able to get away with not including the appropriate header
file on your platform but that might not work on other platforms.
Instead, use "g_ntohs()", "g_ntohl()", "g_htons()", and "g_htonl()";
those are declared by <glib.h>, and you'll need to include that anyway,
as Wireshark header files that all dissectors must include use stuff from
<glib.h>.

Don't fetch a little-endian value using "tvb_get_ntohs() or
"tvb_get_ntohl()" and then using "g_ntohs()", "g_htons()", "g_ntohl()",
or "g_htonl()" on the resulting value - the g_ routines in question
convert between network byte order (big-endian) and *host* byte order,
not *little-endian* byte order; not all machines on which Wireshark runs
are little-endian, even though PCs are.  Fetch those values using
"tvb_get_letohs()" and "tvb_get_letohl()".

Don't put a comma after the last element of an enum - some compilers may
either warn about it (producing extra noise) or refuse to accept it.

Don't include <unistd.h> without protecting it with

	#ifdef HAVE_UNISTD_H

		...

	#endif

and, if you're including it to get routines such as "open()", "close()",
"read()", and "write()" declared, also include <io.h> if present:

	#ifdef HAVE_IO_H
	#include <io.h>
	#endif

in order to declare the Windows C library routines "_open()",
"_close()", "_read()", and "_write()".  Your file must include <glib.h>
- which many of the Wireshark header files include, so you might not have
to include it explicitly - in order to get "open()", "close()",
"read()", "write()", etc. mapped to "_open()", "_close()", "_read()",
"_write()", etc..

Do not use "open()", "rename()", "mkdir()", "stat()", "unlink()", "remove()",
"fopen()", "freopen()" directly.  Instead use "ws_open()", "ws_rename()",
"ws_mkdir()", "ws_stat()", "ws_unlink()", "ws_remove()", "ws_fopen()",
"ws_freopen()": these wrapper functions change the path and file name from
UTF8 to UTF16 on Windows allowing the functions to work correctly when the
path or file name contain non-ASCII characters.

When opening a file with "ws_fopen()", "ws_freopen()", or "ws_fdopen()", if
the file contains ASCII text, use "r", "w", "a", and so on as the open mode
- but if it contains binary data, use "rb", "wb", and so on.  On
Windows, if a file is opened in a text mode, writing a byte with the
value of octal 12 (newline) to the file causes two bytes, one with the
value octal 15 (carriage return) and one with the value octal 12, to be
written to the file, and causes bytes with the value octal 15 to be
discarded when reading the file (to translate between C's UNIX-style
lines that end with newline and Windows' DEC-style lines that end with
carriage return/line feed).

In addition, that also means that when opening or creating a binary
file, you must use "ws_open()" (with O_CREAT and possibly O_TRUNC if the
file is to be created if it doesn't exist), and OR in the O_BINARY flag.
That flag is not present on most, if not all, UNIX systems, so you must
also do

	#ifndef O_BINARY
	#define O_BINARY	0
	#endif

to properly define it for UNIX (it's not necessary on UNIX).

Don't use forward declarations of static arrays without a specified size
in a fashion such as this:

	static const value_string foo_vals[];

		...

	static const value_string foo_vals[] = {
		{ 0,		"Red" },
		{ 1,		"Green" },
		{ 2,		"Blue" },
		{ 0,		NULL }
	};

as some compilers will reject the first of those statements.  Instead,
initialize the array at the point at which it's first declared, so that
the size is known.

Don't put a comma after the last tuple of an initializer of an array.

For #define names and enum member names, prefix the names with a tag so
as to avoid collisions with other names - this might be more of an issue
on Windows, as it appears to #define names such as DELETE and
OPTIONAL.

Don't use the "numbered argument" feature that many UNIX printf's
implement, e.g.:

	g_snprintf(add_string, 30, " - (%1$d) (0x%1$04x)", value);

as not all UNIX printf's implement it, and Windows printf doesn't appear
to implement it.  Use something like

	g_snprintf(add_string, 30, " - (%d) (0x%04x)", value, value);

instead.

Don't use "variadic macros", such as

	#define DBG(format, args...)	fprintf(stderr, format, ## args)

as not all C compilers support them.  Use macros that take a fixed
number of arguments, such as

	#define DBG0(format)		fprintf(stderr, format)
	#define DBG1(format, arg1)	fprintf(stderr, format, arg1)
	#define DBG2(format, arg1, arg2) fprintf(stderr, format, arg1, arg2)

		...

or something such as

	#define DBG(args)		printf args

Don't use

	case N ... M:

as that's not supported by all compilers.

snprintf() -> g_snprintf()
snprintf() is not available on all platforms, so it's a good idea to use the
g_snprintf() function declared by <glib.h> instead.

tmpnam() -> mkstemp()
tmpnam is insecure and should not be used any more. Wireshark brings its
own mkstemp implementation for use on platforms that lack mkstemp.
Note: mkstemp does not accept NULL as a parameter.

The pointer returned by a call to "tvb_get_ptr()" is not guaranteed to be
aligned on any particular byte boundary; this means that you cannot
safely cast it to any data type other than a pointer to "char",
"unsigned char", "guint8", or other one-byte data types.  You cannot,
for example, safely cast it to a pointer to a structure, and then access
the structure members directly; on some systems, unaligned accesses to
integral data types larger than 1 byte, and floating-point data types,
cause a trap, which will, at best, result in the OS slowly performing an
unaligned access for you, and will, on at least some platforms, cause
the program to be terminated.

Wireshark supports platforms with GLib 2.14[.x]/GTK+ 2.12[.x] or newer.
If a Glib/GTK+ mechanism is available only in Glib/GTK+ versions newer
than 2.14/2.12 then use "#if GLIB_CHECK_VERSION(...)" or "#if
GTK_CHECK_VERSION(...)" to conditionally compile code using that
mechanism.

When different code must be used on UN*X and Win32, use a #if or #ifdef
that tests _WIN32, not WIN32.  Try to write code portably whenever
possible, however; note that there are some routines in Wireshark with
platform-dependent implementations and platform-independent APIs, such
as the routines in epan/filesystem.c, allowing the code that calls it to
be written portably without #ifdefs.

1.1.2 String handling

Do not use functions such as strcat() or strcpy().
A lot of work has been done to remove the existing calls to these functions and
we do not want any new callers of these functions.

Instead use g_snprintf() since that function will if used correctly prevent
buffer overflows for large strings.

When using a buffer to create a string, do not use a buffer stored on the stack.
I.e. do not use a buffer declared as

   char buffer[1024];

instead allocate a buffer dynamically using the string-specific or plain emem
routines (see README.malloc) such as

   emem_strbuf_t *strbuf;
   strbuf = ep_strbuf_new_label("");
   ep_strbuf_append_printf(strbuf, ...

or

   char *buffer=NULL;
   ...
   #define MAX_BUFFER 1024
   buffer=ep_alloc(MAX_BUFFER);
   buffer[0]='\0';
   ...
   g_snprintf(buffer, MAX_BUFFER, ...

This avoids the stack from being corrupted in case there is a bug in your code
that accidentally writes beyond the end of the buffer.


If you write a routine that will create and return a pointer to a filled in
string and if that buffer will not be further processed or appended to after
the routine returns (except being added to the proto tree),
do not preallocate the buffer to fill in and pass as a parameter instead
pass a pointer to a pointer to the function and return a pointer to an
emem allocated buffer that will be automatically freed. (see README.malloc)

I.e. do not write code such as
  static void
  foo_to_str(char *string, ... ){
     <fill in string>
  }
  ...
     char buffer[1024];
     ...
     foo_to_str(buffer, ...
     proto_tree_add_text(... buffer ...

instead write the code as
  static void
  foo_to_str(char **buffer, ...
    #define MAX_BUFFER x
    *buffer=ep_alloc(MAX_BUFFER);
    <fill in *buffer>
  }
  ...
    char *buffer;
    ...
    foo_to_str(&buffer, ...
    proto_tree_add_text(... *buffer ...

Use ep_ allocated buffers. They are very fast and nice. These buffers are all
automatically free()d when the dissection of the current packet ends so you
don't have to worry about free()ing them explicitly in order to not leak memory.
Please read README.malloc.

Don't use non-ASCII characters in source files; not all compiler
environments will be using the same encoding for non-ASCII characters,
and at least one compiler (Microsoft's Visual C) will, in environments
with double-byte character encodings, such as many Asian environments,
fail if it sees a byte sequence in a source file that doesn't correspond
to a valid character.  This causes source files using either an ISO
8859/n single-byte character encoding or UTF-8 to fail to compile.  Even
if the compiler doesn't fail, there is no guarantee that the compiler,
or a developer's text editor, will interpret the characters the way you
intend them to be interpreted.

1.1.3 Robustness.

Wireshark is not guaranteed to read only network traces that contain correctly-
formed packets. Wireshark is commonly used to track down networking
problems, and the problems might be due to a buggy protocol implementation
sending out bad packets.

Therefore, protocol dissectors not only have to be able to handle
correctly-formed packets without, for example, crashing or looping
infinitely, they also have to be able to handle *incorrectly*-formed
packets without crashing or looping infinitely.

Here are some suggestions for making dissectors more robust in the face
of incorrectly-formed packets:

Do *NOT* use "g_assert()" or "g_assert_not_reached()" in dissectors.
*NO* value in a packet's data should be considered "wrong" in the sense
that it's a problem with the dissector if found; if it cannot do
anything else with a particular value from a packet's data, the
dissector should put into the protocol tree an indication that the
value is invalid, and should return.  The "expert" mechanism should be
used for that purpose.

If there is a case where you are checking not for an invalid data item
in the packet, but for a bug in the dissector (for example, an
assumption being made at a particular point in the code about the
internal state of the dissector), use the DISSECTOR_ASSERT macro for
that purpose; this will put into the protocol tree an indication that
the dissector has a bug in it, and will not crash the application.

If you are allocating a chunk of memory to contain data from a packet,
or to contain information derived from data in a packet, and the size of
the chunk of memory is derived from a size field in the packet, make
sure all the data is present in the packet before allocating the buffer.
Doing so means that:

	1) Wireshark won't leak that chunk of memory if an attempt to
	   fetch data not present in the packet throws an exception.

and

	2) it won't crash trying to allocate an absurdly-large chunk of
	   memory if the size field has a bogus large value.

If you're fetching into such a chunk of memory a string from the buffer,
and the string has a specified size, you can use "tvb_get_*_string()",
which will check whether the entire string is present before allocating
a buffer for the string, and will also put a trailing '\0' at the end of
the buffer.

If you're fetching into such a chunk of memory a 2-byte Unicode string
from the buffer, and the string has a specified size, you can use
"tvb_get_ephemeral_faked_unicode()", which will check whether the entire
string is present before allocating a buffer for the string, and will also
put a trailing '\0' at the end of the buffer.  The resulting string will be
a sequence of single-byte characters; the only Unicode characters that
will be handled correctly are those in the ASCII range.  (Wireshark's
ability to handle non-ASCII strings is limited; it needs to be
improved.)

If you're fetching into such a chunk of memory a sequence of bytes from
the buffer, and the sequence has a specified size, you can use
"tvb_memdup()", which will check whether the entire sequence is present
before allocating a buffer for it.

Otherwise, you can check whether the data is present by using
"tvb_ensure_bytes_exist()" or by getting a pointer to the data by using
"tvb_get_ptr()", although note that there might be problems with using
the pointer from "tvb_get_ptr()" (see the item on this in the
Portability section above, and the next item below).

Note also that you should only fetch string data into a fixed-length
buffer if the code ensures that no more bytes than will fit into the
buffer are fetched ("the protocol ensures" isn't good enough, as
protocol specifications can't ensure only packets that conform to the
specification will be transmitted or that only packets for the protocol
in question will be interpreted as packets for that protocol by
Wireshark).  If there's no maximum length of string data to be fetched,
routines such as "tvb_get_*_string()" are safer, as they allocate a buffer
large enough to hold the string.  (Note that some variants of this call
require you to free the string once you're finished with it.)

If you have gotten a pointer using "tvb_get_ptr()", you must make sure
that you do not refer to any data past the length passed as the last
argument to "tvb_get_ptr()"; while the various "tvb_get" routines
perform bounds checking and throw an exception if you refer to data not
available in the tvbuff, direct references through a pointer gotten from
"tvb_get_ptr()" do not do any bounds checking.

If you have a loop that dissects a sequence of items, each of which has
a length field, with the offset in the tvbuff advanced by the length of
the item, then, if the length field is the total length of the item, and
thus can be zero, you *MUST* check for a zero-length item and abort the
loop if you see one.  Otherwise, a zero-length item could cause the
dissector to loop infinitely.  You should also check that the offset,
after having the length added to it, is greater than the offset before
the length was added to it, if the length field is greater than 24 bits
long, so that, if the length value is *very* large and adding it to the
offset causes an overflow, that overflow is detected.

If you have a

	for (i = {start}; i < {end}; i++)

loop, make sure that the type of the loop index variable is large enough
to hold the maximum {end} value plus 1; otherwise, the loop index
variable can overflow before it ever reaches its maximum value.  In
particular, be very careful when using gint8, guint8, gint16, or guint16
variables as loop indices; you almost always want to use an "int"/"gint"
or "unsigned int"/"guint" as the loop index rather than a shorter type.

If you are fetching a length field from the buffer, corresponding to the
length of a portion of the packet, and subtracting from that length a
value corresponding to the length of, for example, a header in the
packet portion in question, *ALWAYS* check that the value of the length
field is greater than or equal to the length you're subtracting from it,
and report an error in the packet and stop dissecting the packet if it's
less than the length you're subtracting from it.  Otherwise, the
resulting length value will be negative, which will either cause errors
in the dissector or routines called by the dissector, or, if the value
is interpreted as an unsigned integer, will cause the value to be
interpreted as a very large positive value.

Any tvbuff offset that is added to as processing is done on a packet
should be stored in a 32-bit variable, such as an "int"; if you store it
in an 8-bit or 16-bit variable, you run the risk of the variable
overflowing.

sprintf() -> g_snprintf()
Prevent yourself from using the sprintf() function, as it does not test the
length of the given output buffer and might be writing into unintended memory
areas. This function is one of the main causes of security problems like buffer
exploits and many other bugs that are very hard to find. It's much better to
use the g_snprintf() function declared by <glib.h> instead.

You should test your dissector against incorrectly-formed packets.  This
can be done using the randpkt and editcap utilities that come with the
Wireshark distribution.  Testing using randpkt can be done by generating
output at the same layer as your protocol, and forcing Wireshark/TShark
to decode it as your protocol, e.g. if your protocol sits on top of UDP:

    randpkt -c 50000 -t dns randpkt.pcap
    tshark -nVr randpkt.pcap -d udp.port==53,<myproto>

Testing using editcap can be done using preexisting capture files and the
"-E" flag, which introduces errors in a capture file.  E.g.:

    editcap -E 0.03 infile.pcap outfile.pcap
    tshark -nVr outfile.pcap

The script fuzz-test.sh is available to help automate these tests.

1.1.4 Name convention.

Wireshark uses the underscore_convention rather than the InterCapConvention for
function names, so new code should probably use underscores rather than
intercaps for functions and variable names. This is especially important if you
are writing code that will be called from outside your code.  We are just
trying to keep things consistent for other developers.

1.1.5 White space convention.

Avoid using tab expansions different from 8 column widths, as not all
text editors in use by the developers support this. For a detailed
discussion of tabs, spaces, and indentation, see

    http://www.jwz.org/doc/tabs-vs-spaces.html

When creating a new file, you are free to choose an indentation logic.
Most of the files in Wireshark tend to use 2-space or 4-space
indentation. You are encouraged to write a short comment on the
indentation logic at the beginning of this new file, especially if
you're using non-mod-8 tabs.  The tabs-vs-spaces document above provides
examples of Emacs and vi modelines for this purpose.

Please do not leave trailing whitespace (spaces/tabs) on lines.

When editing an existing file, try following the existing indentation
logic and even if it very tempting, never ever use a restyler/reindenter
utility on an existing file.  If you run across wildly varying
indentation styles within the same file, it might be helpful to send a
note to wireshark-dev for guidance.

1.1.6 Compiler warnings

You should write code that is free of compiler warnings. Such warnings will
often indicate questionable code and sometimes even real bugs, so it's best
to avoid warnings at all.

The compiler flags in the Makefiles are set to "treat warnings as errors",
so your code won't even compile when warnings occur.

1.2 Skeleton code.

Wireshark requires certain things when setting up a protocol dissector.
Below is skeleton code for a dissector that you can copy to a file and
fill in.  Your dissector should follow the naming convention of packet-
followed by the abbreviated name for the protocol.  It is recommended
that where possible you keep to the IANA abbreviated name for the
protocol, if there is one, or a commonly-used abbreviation for the
protocol, if any.

Usually, you will put your newly created dissector file into the directory
epan/dissectors, just like all the other packet-....c files already in there.

Also, please add your dissector file to the corresponding makefiles,
described in section "1.9 Editing Makefile.common and CMakeLists.txt
to add your dissector" below.

Dissectors that use the dissector registration to register with a lower level
dissector don't need to define a prototype in the .h file. For other
dissectors the main dissector routine should have a prototype in a header
file whose name is "packet-", followed by the abbreviated name for the
protocol, followed by ".h"; any dissector file that calls your dissector
should be changed to include that file.

You may not need to include all the headers listed in the skeleton
below, and you may need to include additional headers.  For example, the
code inside

	#ifdef HAVE_LIBPCRE

		...

	#endif

is needed only if you are using a function from libpcre, e.g. the
"pcre_compile()" function.

The stdio.h, stdlib.h and string.h header files should be included only as needed.


The "$Id$" in the comment will be updated by Subversion when the file is
checked in.

When creating a new file, it is fine to just write "$Id$" as Subversion will
automatically fill in the identifier at the time the file will be added to the
SVN repository (committed).

------------------------------------Cut here------------------------------------
/* packet-PROTOABBREV.c
 * Routines for PROTONAME dissection
 * Copyright 201x, YOUR_NAME <YOUR_EMAIL_ADDRESS>
 *
 * $Id$
 *
 * Wireshark - Network traffic analyzer
 * By Gerald Combs <gerald@wireshark.org>
 * Copyright 1998 Gerald Combs
 *
 * Copied from WHATEVER_FILE_YOU_USED (where "WHATEVER_FILE_YOU_USED"
 * is a dissector file; if you just copied this from README.developer,
 * don't bother with the "Copied from" - you don't even need to put
 * in a "Copied from" if you copied an existing dissector, especially
 * if the bulk of the code in the new dissector is your code)
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License along
 * with this program; if not, write to the Free Software Foundation, Inc.,
 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 */

#ifdef HAVE_CONFIG_H
# include "config.h"
#endif

#if 0
/* Include only as needed */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#endif

#include <glib.h>

#include <epan/packet.h>
#include <epan/prefs.h>

/* IF PROTO exposes code to other dissectors, then it must be exported
   in a header file. If not, a header file is not needed at all. */
#include "packet-PROTOABBREV.h"

/* Forward declaration we need below (if using proto_reg_handoff...
   as a prefs callback)       */
void proto_reg_handoff_PROTOABBREV(void);

/* Initialize the protocol and registered fields */
static int proto_PROTOABBREV = -1;
static int hf_PROTOABBREV_FIELDABBREV = -1;

/* Global sample preference ("controls" display of numbers) */
static gboolean gPREF_HEX = FALSE;
/* Global sample port pref */
static guint gPORT_PREF = 1234;

/* Initialize the subtree pointers */
static gint ett_PROTOABBREV = -1;

/* Code to actually dissect the packets */
static int
dissect_PROTOABBREV(tvbuff_t *tvb, packet_info *pinfo, proto_tree *tree)
{

/* Set up structures needed to add the protocol subtree and manage it */
	proto_item *ti;
	proto_tree *PROTOABBREV_tree;

/*  First, if at all possible, do some heuristics to check if the packet cannot
 *  possibly belong to your protocol.  This is especially important for
 *  protocols directly on top of TCP or UDP where port collisions are
 *  common place (e.g., even though your protocol uses a well known port,
 *  someone else may set up, for example, a web server on that port which,
 *  if someone analyzed that web server's traffic in Wireshark, would result
 *  in Wireshark handing an HTTP packet to your dissector).  For example:
 */
	/* Check that there's enough data */
	if (tvb_length(tvb) < /* your protocol's smallest packet size */)
		return 0;

	/* Get some values from the packet header, probably using tvb_get_*() */
	if ( /* these values are not possible in PROTONAME */ )
		/*  This packet does not appear to belong to PROTONAME.
		 *  Return 0 to give another dissector a chance to dissect it.
		 */
		return 0;

/* Make entries in Protocol column and Info column on summary display */
	col_set_str(pinfo->cinfo, COL_PROTOCOL, "PROTOABBREV");

/* This field shows up as the "Info" column in the display; you should use
   it, if possible, to summarize what's in the packet, so that a user looking
   at the list of packets can tell what type of packet it is. See section 1.5
   for more information.

   If you are setting the column to a constant string, use "col_set_str()",
   as it's more efficient than the other "col_set_XXX()" calls.

   If you're setting it to a string you've constructed, or will be
   appending to the column later, use "col_add_str()".

   "col_add_fstr()" can be used instead of "col_add_str()"; it takes
   "printf()"-like arguments.  Don't use "col_add_fstr()" with a format
   string of "%s" - just use "col_add_str()" or "col_set_str()", as it's
   more efficient than "col_add_fstr()".

   If you will be fetching any data from the packet before filling in
   the Info column, clear that column first, in case the calls to fetch
   data from the packet throw an exception because they're fetching data
   past the end of the packet, so that the Info column doesn't have data
   left over from the previous dissector; do

	col_clear(pinfo->cinfo, COL_INFO);

   */

	col_set_str(pinfo->cinfo, COL_INFO, "XXX Request");

/* A protocol dissector may be called in 2 different ways - with, or
   without a non-null "tree" argument.

   If the proto_tree argument is null, Wireshark does not need to use
   the protocol tree information from your dissector, and therefore is
   passing the dissector a null "tree" argument so that it doesn't
   need to do work necessary to build the protocol tree.

   In the interest of speed, if "tree" is NULL, avoid building a
   protocol tree and adding stuff to it, or even looking at any packet
   data needed only if you're building the protocol tree, if possible.

   Note, however, that you must fill in column information, create
   conversations, reassemble packets, build any other persistent state
   needed for dissection, and call subdissectors regardless of whether
   "tree" is NULL or not.  This might be inconvenient to do without
   doing most of the dissection work; the routines for adding items to
   the protocol tree can be passed a null protocol tree pointer, in
   which case they'll return a null item pointer, and
   "proto_item_add_subtree()" returns a null tree pointer if passed a
   null item pointer, so, if you're careful not to dereference any null
   tree or item pointers, you can accomplish this by doing all the
   dissection work.  This might not be as efficient as skipping that
   work if you're not building a protocol tree, but if the code would
   have a lot of tests whether "tree" is null if you skipped that work,
   you might still be better off just doing all that work regardless of
   whether "tree" is null or not.

   Note also that there is no guarantee, the first time the dissector is
   called, whether "tree" will be null or not; your dissector must work
   correctly, building or updating whatever state information is
   necessary, in either case. */
	if (tree) {

/* NOTE: The offset and length values in the call to
   "proto_tree_add_item()" define what data bytes to highlight in the hex
   display window when the line in the protocol tree display
   corresponding to that item is selected.

   Supplying a length of -1 is the way to highlight all data from the
   offset to the end of the packet. */

/* create display subtree for the protocol */
		ti = proto_tree_add_item(tree, proto_PROTOABBREV, tvb, 0, -1, ENC_NA);

		PROTOABBREV_tree = proto_item_add_subtree(ti, ett_PROTOABBREV);

/* add an item to the subtree, see section 1.6 for more information */
		proto_tree_add_item(PROTOABBREV_tree,
		    hf_PROTOABBREV_FIELDABBREV, tvb, offset, len, ENC_xxx);


/* Continue adding tree items to process the packet here */


	}

/* If this protocol has a sub-dissector call it here, see section 1.8 */

/* Return the amount of data this dissector was able to dissect */
	return tvb_length(tvb);
}


/* Register the protocol with Wireshark */

/* this format is require because a script is used to build the C function
   that calls all the protocol registration.
*/

void
proto_register_PROTOABBREV(void)
{
	module_t *PROTOABBREV_module;

/* Setup list of header fields  See Section 1.6.1 for details*/
	static hf_register_info hf[] = {
		{ &hf_PROTOABBREV_FIELDABBREV,
			{ "FIELDNAME",           "PROTOABBREV.FIELDABBREV",
			FIELDTYPE, FIELDDISPLAY, FIELDCONVERT, BITMASK,
			"FIELDDESCR", HFILL }
		}
	};

/* Setup protocol subtree array */
	static gint *ett[] = {
		&ett_PROTOABBREV
	};

/* Register the protocol name and description */
	proto_PROTOABBREV = proto_register_protocol("PROTONAME",
	    "PROTOSHORTNAME", "PROTOABBREV");

/* Required function calls to register the header fields and subtrees used */
	proto_register_field_array(proto_PROTOABBREV, hf, array_length(hf));
	proto_register_subtree_array(ett, array_length(ett));

/* Register preferences module (See Section 2.6 for more on preferences) */
/* (Registration of a prefs callback is not required if there are no     */
/*  prefs-dependent registration functions (eg: a port pref).            */
/*  See proto_reg_handoff below.                                         */
/*  If a prefs callback is not needed, use NULL instead of               */
/*  proto_reg_handoff_PROTOABBREV in the following).                     */
	PROTOABBREV_module = prefs_register_protocol(proto_PROTOABBREV,
	    proto_reg_handoff_PROTOABBREV);

/* Register preferences module under preferences subtree.
   Use this function instead of prefs_register_protocol if you want to group
   preferences of several protocols under one preferences subtree.
   Argument subtree identifies grouping tree node name, several subnodes can be
   specified usign slash '/' (e.g. "OSI/X.500" - protocol preferences will be
   accessible under Protocols->OSI->X.500-><PROTOSHORTNAME> preferences node.
*/
  PROTOABBREV_module = prefs_register_protocol_subtree(const char *subtree,
       proto_PROTOABBREV, proto_reg_handoff_PROTOABBREV);

/* Register a sample preference */
	prefs_register_bool_preference(PROTOABBREV_module, "show_hex",
	     "Display numbers in Hex",
	     "Enable to display numerical values in hexadecimal.",
	     &gPREF_HEX);

/* Register a sample port preference   */
	prefs_register_uint_preference(PROTOABBREV_module, "tcp.port", "PROTOABBREV TCP Port",
	     " PROTOABBREV TCP port if other than the default",
	     10, &gPORT_PREF);
}


/* If this dissector uses sub-dissector registration add a registration routine.
   This exact format is required because a script is used to find these
   routines and create the code that calls these routines.

   If this function is registered as a prefs callback (see prefs_register_protocol
   above) this function is also called by preferences whenever "Apply" is pressed;
   In that case, it should accommodate being called more than once.

   This form of the reg_handoff function is used if if you perform
   registration functions which are dependent upon prefs. See below
   for a simpler form  which can be used if there are no
   prefs-dependent registration functions.
*/
void
proto_reg_handoff_PROTOABBREV(void)
{
	static gboolean initialized = FALSE;
        static dissector_handle_t PROTOABBREV_handle;
        static int currentPort;

	if (!initialized) {

/*  Use new_create_dissector_handle() to indicate that dissect_PROTOABBREV()
 *  returns the number of bytes it dissected (or 0 if it thinks the packet
 *  does not belong to PROTONAME).
 */
		PROTOABBREV_handle = new_create_dissector_handle(dissect_PROTOABBREV,
								 proto_PROTOABBREV);
		initialized = TRUE;
	} else {

 		/*
		  If you perform registration functions which are dependent upon
		  prefs the you should de-register everything which was associated
		  with the previous settings and re-register using the new prefs
		  settings here. In general this means you need to keep track of
		  the PROTOABBREV_handle and the value the preference had at the time
		  you registered.  The PROTOABBREV_handle value and the value of the
		  preference can be saved using local statics in this
		  function (proto_reg_handoff).
		*/

		dissector_delete_uint("tcp.port", currentPort, PROTOABBREV_handle);
	}

	currentPort = gPORT_PREF;

	dissector_add_uint("tcp.port", currentPort, PROTOABBREV_handle);

}

#if 0
/* Simple form of proto_reg_handoff_PROTOABBREV which can be used if there are
   no prefs-dependent registration function calls.
 */

void
proto_reg_handoff_PROTOABBREV(void)
{
	dissector_handle_t PROTOABBREV_handle;

/*  Use new_create_dissector_handle() to indicate that dissect_PROTOABBREV()
 *  returns the number of bytes it dissected (or 0 if it thinks the packet
 *  does not belong to PROTONAME).
 */
	PROTOABBREV_handle = new_create_dissector_handle(dissect_PROTOABBREV,
							 proto_PROTOABBREV);
	dissector_add_uint("PARENT_SUBFIELD", ID_VALUE, PROTOABBREV_handle);
}
#endif


------------------------------------Cut here------------------------------------

1.3 Explanation of needed substitutions in code skeleton.

In the above code block the following strings should be substituted with
your information.

YOUR_NAME	Your name, of course.  You do want credit, don't you?
		It's the only payment you will receive....
YOUR_EMAIL_ADDRESS	Keep those cards and letters coming.
WHATEVER_FILE_YOU_USED	Add this line if you are using another file as a
		starting point.
PROTONAME	The name of the protocol; this is displayed in the
		top-level protocol tree item for that protocol.
PROTOSHORTNAME	An abbreviated name for the protocol; this is displayed
		in the "Preferences" dialog box if your dissector has
		any preferences, in the dialog box of enabled protocols,
		and in the dialog box for filter fields when constructing
		a filter expression.
PROTOABBREV	A name for the protocol for use in filter expressions;
		it shall contain only lower-case letters, digits, and
		hyphens.
FIELDNAME	The displayed name for the header field.
FIELDABBREV	The abbreviated name for the header field. (NO SPACES)
FIELDTYPE	FT_NONE, FT_BOOLEAN, FT_UINT8, FT_UINT16, FT_UINT24,
		FT_UINT32, FT_UINT64, FT_INT8, FT_INT16, FT_INT24, FT_INT32,
		FT_INT64, FT_FLOAT, FT_DOUBLE, FT_ABSOLUTE_TIME,
		FT_RELATIVE_TIME, FT_STRING, FT_STRINGZ, FT_EBCDIC, FT_EUI64
		FT_UINT_STRING,	FT_ETHER, FT_BYTES, FT_UINT_BYTES, FT_IPv4,
		FT_IPv6, FT_IPXNET, FT_FRAMENUM, FT_PROTOCOL, FT_GUID, FT_OID
FIELDDISPLAY	For FT_UINT{8,16,24,32,64} and FT_INT{8,16,24,32,64):

		BASE_DEC, BASE_HEX, BASE_OCT, BASE_DEC_HEX, BASE_HEX_DEC,
		or BASE_CUSTOM, possibly ORed with BASE_RANGE_STRING

		For FT_ABSOLUTE_TIME:

		ABSOLUTE_TIME_LOCAL, ABSOLUTE_TIME_UTC, or
		ABSOLUTE_TIME_DOY_UTC

		For FT_BOOLEAN if BITMASK is non-zero:

		Number of bits in the field containing the FT_BOOLEAN
		bitfield

		For all other types:

		BASE_NONE
FIELDCONVERT	VALS(x), RVALS(x), TFS(x), NULL
BITMASK		Usually 0x0 unless using the TFS(x) field conversion.
FIELDDESCR	A brief description of the field, or NULL. [Please do not use ""].
PARENT_SUBFIELD	Lower level protocol field used for lookup, i.e. "tcp.port"
ID_VALUE	Lower level protocol field value that identifies this protocol
		For example the TCP or UDP port number

If, for example, PROTONAME is "Internet Bogosity Discovery Protocol",
PROTOSHORTNAME would be "IBDP", and PROTOABBREV would be "ibdp".  Try to
conform with IANA names.

1.4 The dissector and the data it receives.


1.4.1 Header file.

This is only needed if the dissector doesn't use self-registration to
register itself with the lower level dissector, or if the protocol dissector
wants/needs to expose code to other subdissectors.

The dissector must be declared exactly as follows in the file
packet-PROTOABBREV.h:

int
dissect_PROTOABBREV(tvbuff_t *tvb, packet_info *pinfo, proto_tree *tree);


1.4.2 Extracting data from packets.

NOTE: See the file /epan/tvbuff.h for more details.

The "tvb" argument to a dissector points to a buffer containing the raw
data to be analyzed by the dissector; for example, for a protocol
running atop UDP, it contains the UDP payload (but not the UDP header,
or any protocol headers above it).  A tvbuffer is an opaque data
structure, the internal data structures are hidden and the data must be
accessed via the tvbuffer accessors.

The accessors are:

Bit accessors for a maximum of 8-bits, 16-bits 32-bits and 64-bits:

guint8 tvb_get_bits8(tvbuff_t *tvb, gint bit_offset, gint no_of_bits);
guint16 tvb_get_bits16(tvbuff_t *tvb, gint bit_offset, gint no_of_bits,gboolean little_endian);
guint32 tvb_get_bits32(tvbuff_t *tvb, gint bit_offset, gint no_of_bits,gboolean little_endian);
guint64 tvb_get_bits64(tvbuff_t *tvb, gint bit_offset, gint no_of_bits,gboolean little_endian);

Single-byte accessor:

guint8  tvb_get_guint8(tvbuff_t*, gint offset);

Network-to-host-order accessors for 16-bit integers (guint16), 24-bit
integers, 32-bit integers (guint32), and 64-bit integers (guint64):

guint16 tvb_get_ntohs(tvbuff_t*, gint offset);
guint32 tvb_get_ntoh24(tvbuff_t*, gint offset);
guint32 tvb_get_ntohl(tvbuff_t*, gint offset);
guint64 tvb_get_ntoh40(tvbuff_t*, gint offset);
guint64 tvb_get_ntoh48(tvbuff_t*, gint offset);
guint64 tvb_get_ntoh56(tvbuff_t*, gint offset);
guint64 tvb_get_ntoh64(tvbuff_t*, gint offset);

Network-to-host-order accessors for single-precision and
double-precision IEEE floating-point numbers:

gfloat tvb_get_ntohieee_float(tvbuff_t*, gint offset);
gdouble tvb_get_ntohieee_double(tvbuff_t*, gint offset);

Little-Endian-to-host-order accessors for 16-bit integers (guint16),
24-bit integers, 32-bit integers (guint32), and 64-bit integers
(guint64):

guint16 tvb_get_letohs(tvbuff_t*, gint offset);
guint32 tvb_get_letoh24(tvbuff_t*, gint offset);
guint32 tvb_get_letohl(tvbuff_t*, gint offset);
guint64 tvb_get_letoh40(tvbuff_t*, gint offset);
guint64 tvb_get_letoh48(tvbuff_t*, gint offset);
guint64 tvb_get_letoh56(tvbuff_t*, gint offset);
guint64 tvb_get_letoh64(tvbuff_t*, gint offset);

Little-Endian-to-host-order accessors for single-precision and
double-precision IEEE floating-point numbers:

gfloat tvb_get_letohieee_float(tvbuff_t*, gint offset);
gdouble tvb_get_letohieee_double(tvbuff_t*, gint offset);

Accessors for IPv4 and IPv6 addresses:

guint32 tvb_get_ipv4(tvbuff_t*, gint offset);
void tvb_get_ipv6(tvbuff_t*, gint offset, struct e_in6_addr *addr);

NOTE: IPv4 addresses are not to be converted to host byte order before
being passed to "proto_tree_add_ipv4()".  You should use "tvb_get_ipv4()"
to fetch them, not "tvb_get_ntohl()" *OR* "tvb_get_letohl()" - don't,
for example, try to use "tvb_get_ntohl()", find that it gives you the
wrong answer on the PC on which you're doing development, and try
"tvb_get_letohl()" instead, as "tvb_get_letohl()" will give the wrong
answer on big-endian machines.

Accessors for GUID:

void tvb_get_ntohguid(tvbuff_t *, gint offset, e_guid_t *guid);
void tvb_get_letohguid(tvbuff_t *, gint offset, e_guid_t *guid);

String accessors:

guint8 *tvb_get_string(tvbuff_t*, gint offset, gint length);
gchar  *tvb_get_unicode_string(tvbuff_t *tvb, const gint offset, gint length, const guint encoding);
guint8 *tvb_get_ephemeral_string(tvbuff_t*, gint offset, gint length);
gchar  *tvb_get_ephemeral_unicode_string(tvbuff_t *tvb, const gint offset, gint length, const guint encoding);
guint8 *tvb_get_seasonal_string(tvbuff_t*, gint offset, gint length);

Returns a null-terminated buffer containing data from the specified
tvbuff, starting at the specified offset, and containing the specified
length worth of characters (the length of the buffer will be length+1,
as it includes a null character to terminate the string).

tvb_get_string() returns a buffer allocated by g_malloc() so you must
g_free() it when you are finished with the string. Failure to g_free() this
buffer will lead to memory leaks.

tvb_get_unicode_string() is a unicode (UTF-16) version of above.  This
is intended for reading UTF-16 unicode strings out of a tvbuff and
returning them as a UTF-8 string for use in Wireshark.  The offset and
returned length pointer are in bytes, not UTF-16 characters.

tvb_get_ephemeral_string() returns a buffer allocated from a special heap
with a lifetime until the next packet is dissected. You do not need to
free() this buffer, it will happen automatically once the next packet is
dissected.

tvb_get_ephemeral_unicode_string() is a unicode (UTF-16) version of above.
This is intended for reading UTF-16 unicode strings out of a tvbuff and
returning them as a UTF-8 string for use in Wireshark.  The offset and
returned length pointer are in bytes, not UTF-16 characters.

tvb_get_seasonal_string() returns a buffer allocated from a special heap
with a lifetime of the current capture session. You do not need to
free() this buffer, it will happen automatically once the a new capture or
file is opened.

guint8 *tvb_get_stringz(tvbuff_t *tvb, gint offset, gint *lengthp);
const guint8 *tvb_get_const stringz(tvbuff_t *tvb, gint offset, gint *lengthp);
guint8 *tvb_get_ephemeral_stringz(tvbuff_t *tvb, gint offset, gint *lengthp);
gchar  *tvb_get_ephemeral_unicode_stringz(tvbuff_t *tvb, const gint offset, gint *lengthp, const guint encoding);
guint8 *tvb_get_seasonal_stringz(tvbuff_t *tvb, gint offset, gint *lengthp);

Returns a null-terminated buffer containing data from the specified tvbuff,
starting at the specified offset, and containing all characters from the
tvbuff up to and including a terminating null character in the tvbuff.
"*lengthp" will be set to the length of the string, including the terminating
null.

tvb_get_stringz() returns a buffer allocated by g_malloc() so you must
g_free() it when you are finished with the string. Failure to g_free() this
buffer will lead to memory leaks.

tvb_get_const_stringz() returns a pointer to the (const) string in the tvbuff.
You do not need to free() this buffer, it will happen automatically once the
next packet is dissected.  This function is slightly more efficient than the
others because it does not allocate memory and copy the string.

tvb_get_ephemeral_stringz() returns a buffer allocated from a special heap
with a lifetime until the next packet is dissected. You do not need to
free() this buffer, it will happen automatically once the next packet is
dissected.

tvb_get_ephemeral_unicode_stringz() is a unicode (UTF-16) version of
above.  This is intended for reading UTF-16 unicode strings out of a tvbuff
and returning them as a UTF-8 string for use in Wireshark.  The offset and
returned length pointer are in bytes, not UTF-16 characters.

tvb_get_seasonal_stringz() returns a buffer allocated from a special heap
with a lifetime of the current capture session. You do not need to
free() this buffer, it will happen automatically once the a new capture or
file is opened.

tvb_fake_unicode() has been superceded by tvb_get_unicode_string(), which
properly handles Unicode (UTF-16) strings by converting them to UTF-8.

tvb_get_ephemeral_faked_unicode() has been superceded by tvb_get_ephemeral_string(), which properly handles Unicode (UTF-16) strings by converting them
to UTF-8.

Byte Array Accessors:

gchar *tvb_bytes_to_str(tvbuff_t *tvb, gint offset, gint len);

Formats a bunch of data from a tvbuff as bytes, returning a pointer
to the string with the data formatted as two hex digits for each byte.
The string pointed to is stored in an "ep_alloc'd" buffer which will be freed
before the next frame is dissected. The formatted string will contain the hex digits
for at most the first 16 bytes of the data. If len is greater than 16 bytes, a
trailing "..." will be added to the string.

gchar *tvb_bytes_to_str_punct(tvbuff_t *tvb, gint offset, gint len, gchar punct);

This function is similar to tvb_bytes_to_str(...) except that 'punct' is inserted
between the hex representation of each byte.

gchar *tvb_bcd_dig_to_ep_str(tvbuff_t *tvb, const gint offset, const gint len, dgt_set_t *dgt, gboolean skip_first);

Given a tvbuff, an offset into the tvbuff, and a length that starts
at that offset (which may be -1 for "all the way to the end of the
tvbuff"), fetch BCD encoded digits from a tvbuff starting from either
the low or high half byte, formating the digits according to an input digit set,
if NUll a default digit set of 0-9 returning "?" for overdecadic digits will be used.
A pointer to the EP allocated string will be returned.
Note: a tvbuff content of 0xf is considered a 'filler' and will end the conversion.

Copying memory:
guint8* tvb_memcpy(tvbuff_t*, guint8* target, gint offset, gint length);

Copies into the specified target the specified length's worth of data
from the specified tvbuff, starting at the specified offset.

guint8* tvb_memdup(tvbuff_t*, gint offset, gint length);
guint8* ep_tvb_memdup(tvbuff_t*, gint offset, gint length);

Returns a buffer, allocated with "g_malloc()", containing the specified
length's worth of data from the specified tvbuff, starting at the
specified offset. The ephemeral variant is freed automatically after the
packet is dissected.

Pointer-retrieval:
/* WARNING! This function is possibly expensive, temporarily allocating
 * another copy of the packet data. Furthermore, it's dangerous because once
 * this pointer is given to the user, there's no guarantee that the user will
 * honor the 'length' and not overstep the boundaries of the buffer.
 */
guint8* tvb_get_ptr(tvbuff_t*, gint offset, gint length);

The reason that tvb_get_ptr() might have to allocate a copy of its data
only occurs with TVBUFF_COMPOSITES, data that spans multiple tvbuffers.
If the user requests a pointer to a range of bytes that span the member
tvbuffs that make up the TVBUFF_COMPOSITE, the data will have to be
copied to another memory region to assure that all the bytes are
contiguous.



1.5 Functions to handle columns in the traffic summary window.

The topmost pane of the main window is a list of the packets in the
capture, possibly filtered by a display filter.

Each line corresponds to a packet, and has one or more columns, as
configured by the user.

Many of the columns are handled by code outside individual dissectors;
most dissectors need only specify the value to put in the "Protocol" and
"Info" columns.

Columns are specified by COL_ values; the COL_ value for the "Protocol"
field, typically giving an abbreviated name for the protocol (but not
the all-lower-case abbreviation used elsewhere) is COL_PROTOCOL, and the
COL_ value for the "Info" field, giving a summary of the contents of the
packet for that protocol, is COL_INFO.

The value for a column can be specified with one of several functions,
all of which take the 'fd' argument to the dissector as their first
argument, and the COL_ value for the column as their second argument.

1.5.1 The col_set_str function.

'col_set_str' takes a string as its third argument, and sets the value
for the column to that value.  It assumes that the pointer passed to it
points to a string constant or a static "const" array, not to a
variable, as it doesn't copy the string, it merely saves the pointer
value; the argument can itself be a variable, as long as it always
points to a string constant or a static "const" array.

It is more efficient than 'col_add_str' or 'col_add_fstr'; however, if
the dissector will be using 'col_append_str' or 'col_append_fstr" to
append more information to the column, the string will have to be copied
anyway, so it's best to use 'col_add_str' rather than 'col_set_str' in
that case.

For example, to set the "Protocol" column
to "PROTOABBREV":

	col_set_str(pinfo->cinfo, COL_PROTOCOL, "PROTOABBREV");


1.5.2 The col_add_str function.

'col_add_str' takes a string as its third argument, and sets the value
for the column to that value.  It takes the same arguments as
'col_set_str', but copies the string, so that if the string is, for
example, an automatic variable that won't remain in scope when the
dissector returns, it's safe to use.


1.5.3 The col_add_fstr function.

'col_add_fstr' takes a 'printf'-style format string as its third
argument, and 'printf'-style arguments corresponding to '%' format
items in that string as its subsequent arguments.  For example, to set
the "Info" field to "<XXX> request, <N> bytes", where "reqtype" is a
string containing the type of the request in the packet and "n" is an
unsigned integer containing the number of bytes in the request:

	col_add_fstr(pinfo->cinfo, COL_INFO, "%s request, %u bytes",
                     reqtype, n);

Don't use 'col_add_fstr' with a format argument of just "%s" -
'col_add_str', or possibly even 'col_set_str' if the string that matches
the "%s" is a static constant string, will do the same job more
efficiently.


1.5.4 The col_clear function.

If the Info column will be filled with information from the packet, that
means that some data will be fetched from the packet before the Info
column is filled in.  If the packet is so small that the data in
question cannot be fetched, the routines to fetch the data will throw an
exception (see the comment at the beginning about tvbuffers improving
the handling of short packets - the tvbuffers keep track of how much
data is in the packet, and throw an exception on an attempt to fetch
data past the end of the packet, so that the dissector won't process
bogus data), causing the Info column not to be filled in.

This means that the Info column will have data for the previous
protocol, which would be confusing if, for example, the Protocol column
had data for this protocol.

Therefore, before a dissector fetches any data whatsoever from the
packet (unless it's a heuristic dissector fetching data to determine
whether the packet is one that it should dissect, in which case it
should check, before fetching the data, whether there's any data to
fetch; if there isn't, it should return FALSE), it should set the
Protocol column and the Info column.

If the Protocol column will ultimately be set to, for example, a value
containing a protocol version number, with the version number being a
field in the packet, the dissector should, before fetching the version
number field or any other field from the packet, set it to a value
without a version number, using 'col_set_str', and should later set it
to a value with the version number after it's fetched the version
number.

If the Info column will ultimately be set to a value containing
information from the packet, the dissector should, before fetching any
fields from the packet, clear the column using 'col_clear' (which is
more efficient than clearing it by calling 'col_set_str' or
'col_add_str' with a null string), and should later set it to the real
string after it's fetched the data to use when doing that.


1.5.5 The col_append_str function.

Sometimes the value of a column, especially the "Info" column, can't be
conveniently constructed at a single point in the dissection process;
for example, it might contain small bits of information from many of the
fields in the packet.  'col_append_str' takes, as arguments, the same
arguments as 'col_add_str', but the string is appended to the end of the
current value for the column, rather than replacing the value for that
column.  (Note that no blank separates the appended string from the
string to which it is appended; if you want a blank there, you must add
it yourself as part of the string being appended.)


1.5.6 The col_append_fstr function.

'col_append_fstr' is to 'col_add_fstr' as 'col_append_str' is to
'col_add_str' - it takes, as arguments, the same arguments as
'col_add_fstr', but the formatted string is appended to the end of the
current value for the column, rather than replacing the value for that
column.

1.5.7 The col_append_sep_str and col_append_sep_fstr functions.

In specific situations the developer knows that a column's value will be
created in a stepwise manner, where the appended values are listed. Both
'col_append_sep_str' and 'col_append_sep_fstr' functions will add an item
separator between two consecutive items, and will not add the separator at the
beginning of the column. The remainder of the work both functions do is
identical to what 'col_append_str' and 'col_append_fstr' do.

1.5.8 The col_set_fence and col_prepend_fence_fstr functions.

Sometimes a dissector may be called multiple times for different PDUs in the
same frame (for example in the case of SCTP chunk bundling: several upper
layer data packets may be contained in one SCTP packet).  If the upper layer
dissector calls 'col_set_str()' or 'col_clear()' on the Info column when it
begins dissecting each of those PDUs then when the frame is fully dissected
the Info column would contain only the string from the last PDU in the frame.
The 'col_set_fence' function erects a "fence" in the column that prevents
subsequent 'col_...' calls from clearing the data currently in that column.
For example, the SCTP dissector calls 'col_set_fence' on the Info column
after it has called any subdissectors for that chunk so that subdissectors
of any subsequent chunks may only append to the Info column.
'col_prepend_fence_fstr' prepends data before a fence (moving it if
necessary).  It will create a fence at the end of the prepended data if the
fence does not already exist.


1.5.9 The col_set_time function.

The 'col_set_time' function takes an nstime value as its third argument.
This nstime value is a relative value and will be added as such to the
column. The fourth argument is the filtername holding this value. This
way, rightclicking on the column makes it possible to build a filter
based on the time-value.

For example:

	nstime_delta(&ts, &pinfo->fd->abs_ts, &tcpd->ts_first);
  	col_set_time(pinfo->cinfo, COL_REL_CONV_TIME, &ts, "tcp.time_relative");


1.6 Constructing the protocol tree.

The middle pane of the main window, and the topmost pane of a packet
popup window, are constructed from the "protocol tree" for a packet.

The protocol tree, or proto_tree, is a GNode, the N-way tree structure
available within GLIB. Of course the protocol dissectors don't care
what a proto_tree really is; they just pass the proto_tree pointer as an
argument to the routines which allow them to add items and new branches
to the tree.

When a packet is selected in the packet-list pane, or a packet popup
window is created, a new logical protocol tree (proto_tree) is created.
The pointer to the proto_tree (in this case, 'protocol tree'), is passed
to the top-level protocol dissector, and then to all subsequent protocol
dissectors for that packet, and then the GUI tree is drawn via
proto_tree_draw().

The logical proto_tree needs to know detailed information about the protocols
and fields about which information will be collected from the dissection
routines. By strictly defining (or "typing") the data that can be attached to a
proto tree, searching and filtering becomes possible.  This means that for
every protocol and field (which I also call "header fields", since they are
fields in the protocol headers) which might be attached to a tree, some
information is needed.

Every dissector routine will need to register its protocols and fields
with the central protocol routines (in proto.c). At first I thought I
might keep all the protocol and field information about all the
dissectors in one file, but decentralization seemed like a better idea.
That one file would have gotten very large; one small change would have
required a re-compilation of the entire file. Also, by allowing
registration of protocols and fields at run-time, loadable modules of
protocol dissectors (perhaps even user-supplied) is feasible.

To do this, each protocol should have a register routine, which will be
called when Wireshark starts.  The code to call the register routines is
generated automatically; to arrange that a protocol's register routine
be called at startup:

	the file containing a dissector's "register" routine must be
	added to "DISSECTOR_SRC" in "epan/dissectors/Makefile.common"
	(and in "epan/CMakeLists.txt");

	the "register" routine must have a name of the form
	"proto_register_XXX";

	the "register" routine must take no argument, and return no
	value;

	the "register" routine's name must appear in the source file
	either at the beginning of the line, or preceded only by "void "
	at the beginning of the line (that would typically be the
	definition) - other white space shouldn't cause a problem, e.g.:

void proto_register_XXX(void) {

	...

}

and

void
proto_register_XXX( void )
{

	...

}

	and so on should work.

For every protocol or field that a dissector wants to register, a variable of
type int needs to be used to keep track of the protocol. The IDs are
needed for establishing parent/child relationships between protocols and
fields, as well as associating data with a particular field so that it
can be stored in the logical tree and displayed in the GUI protocol
tree.

Some dissectors will need to create branches within their tree to help
organize header fields. These branches should be registered as header
fields. Only true protocols should be registered as protocols. This is
so that a display filter user interface knows how to distinguish
protocols from fields.

A protocol is registered with the name of the protocol and its
abbreviation.

Here is how the frame "protocol" is registered.

        int proto_frame;

        proto_frame = proto_register_protocol (
                /* name */            "Frame",
                /* short name */      "Frame",
                /* abbrev */          "frame" );

A header field is also registered with its name and abbreviation, but
information about its data type is needed. It helps to look at
the header_field_info struct to see what information is expected:

struct header_field_info {
	const char			*name;
	const char			*abbrev;
	enum ftenum			type;
	int				display;
	const void			*strings;
	guint32				bitmask;
	const char			*blurb;
	.....
};

name
----
A string representing the name of the field. This is the name
that will appear in the graphical protocol tree.  It must be a non-empty
string.

abbrev
------
A string with an abbreviation of the field. We concatenate the
abbreviation of the parent protocol with an abbreviation for the field,
using a period as a separator. For example, the "src" field in an IP packet
would have "ip.src" as an abbreviation. It is acceptable to have
multiple levels of periods if, for example, you have fields in your
protocol that are then subdivided into subfields. For example, TRMAC
has multiple error fields, so the abbreviations follow this pattern:
"trmac.errors.iso", "trmac.errors.noniso", etc.

The abbreviation is the identifier used in a display filter.  If it is
an empty string then the field will not be filterable.

type
----
The type of value this field holds. The current field types are:

	FT_NONE			No field type. Used for fields that
				aren't given a value, and that can only
				be tested for presence or absence; a
				field that represents a data structure,
				with a subtree below it containing
				fields for the members of the structure,
				or that represents an array with a
				subtree below it containing fields for
				the members of the array, might be an
				FT_NONE field.
	FT_PROTOCOL		Used for protocols which will be placing
				themselves as top-level items in the
				"Packet Details" pane of the UI.
	FT_BOOLEAN		0 means "false", any other value means
				"true".
	FT_FRAMENUM		A frame number; if this is used, the "Go
				To Corresponding Frame" menu item can
				work on that field.
	FT_UINT8		An 8-bit unsigned integer.
	FT_UINT16		A 16-bit unsigned integer.
	FT_UINT24		A 24-bit unsigned integer.
	FT_UINT32		A 32-bit unsigned integer.
	FT_UINT64		A 64-bit unsigned integer.
	FT_INT8			An 8-bit signed integer.
	FT_INT16		A 16-bit signed integer.
	FT_INT24		A 24-bit signed integer.
	FT_INT32		A 32-bit signed integer.
	FT_INT64		A 64-bit signed integer.
	FT_FLOAT		A single-precision floating point number.
	FT_DOUBLE		A double-precision floating point number.
	FT_ABSOLUTE_TIME	An absolute time from some fixed point in time,
				displayed as the date, followed by the time, as
				hours, minutes, and seconds with 9 digits after
				the decimal point.

				Two absolute time encodings may be specified
				with proto_tree_add_item():

				ENC_TIME_TIMESPEC: Seconds (4 bytes) and
				nanoseconds (4 bytes) of time since January 1,
				1970, midnight UTC.

				ENC_TIME_NTP: NTP timestamps are represented as
				a 64-bit unsigned fixed-point number, in seconds
				relative to 0h on 1 January 1900. The integer
				part is in the first 32 bits and the fraction
				part in the last 32 bits.

				The encoding must be logically ORed with
				ENC_BIG_ENDIAN or ENC_LITTLE_ENDIAN as
				appropriate.
	FT_RELATIVE_TIME	Seconds (4 bytes) and nanoseconds (4 bytes)
				of time relative to an arbitrary time.
				displayed as seconds and 9 digits
				after the decimal point.
	FT_STRING		A string of characters, not necessarily
				NUL-terminated, but possibly NUL-padded.
				This, and the other string-of-characters
				types, are to be used for text strings,
				not raw binary data.
	FT_STRINGZ		A NUL-terminated string of characters.
				The string length is normally the length
				given in the proto_tree_add_item() call.
				However if the length given in the call
				is -1, then the length used is that
				returned by calling tvb_strsize().
	FT_EBCDIC		A string of characters, not necessarily
				NUL-terminated, but possibly NUL-padded.
				The data from the packet is converted from
				EBCDIC to ASCII before displaying to the user.
	FT_UINT_STRING		A counted string of characters, consisting
				of a count (represented as an integral value,
				of width given in the proto_tree_add_item()
				call) followed immediately by that number of
				characters.
	FT_ETHER		A six octet string displayed in
				Ethernet-address format.
	FT_BYTES		A string of bytes with arbitrary values;
				used for raw binary data.
	FT_UINT_BYTES		A counted string of bytes, consisting
				of a count (represented as an integral value,
				of width given in the proto_tree_add_item()
				call) followed immediately by that number of
				arbitrary values; used for raw binary data.
	FT_IPv4			A version 4 IP address (4 bytes) displayed
				in dotted-quad IP address format (4
				decimal numbers separated by dots).
	FT_IPv6			A version 6 IP address (16 bytes) displayed
				in standard IPv6 address format.
	FT_IPXNET		An IPX address displayed in hex as a 6-byte
				network number followed by a 6-byte station
				address.
	FT_GUID			A Globally Unique Identifier
	FT_OID			An ASN.1 Object Identifier
	FT_EUI64		A EUI-64 Address

Some of these field types are still not handled in the display filter
routines, but the most common ones are. The FT_UINT* variables all
represent unsigned integers, and the FT_INT* variables all represent
signed integers; the number on the end represent how many bits are used
to represent the number.

Some constraints are imposed on the header fields depending on the type
(e.g.  FT_BYTES) of the field.  Fields of type FT_ABSOLUTE_TIME must use
'ABSOLUTE_TIME_{LOCAL,UTC,DOY_UTC}, NULL, 0x0' as values for the
'display, 'strings', and 'bitmask' fields, and all other non-integral
types (i.e.. types that are _not_ FT_INT* and FT_UINT*) must use
'BASE_NONE, NULL, 0x0' as values for the 'display', 'strings', 'bitmask'
fields.  The reason is simply that the type itself implictly defines the
nature of 'display', 'strings', 'bitmask'.

display
-------
The display field has a couple of overloaded uses. This is unfortunate,
but since we're using C as an application programming language, this sometimes
makes for cleaner programs. Right now I still think that overloading
this variable was okay.

For integer fields (FT_UINT* and FT_INT*), this variable represents the
base in which you would like the value displayed.  The acceptable bases
are:

	BASE_DEC,
	BASE_HEX,
	BASE_OCT,
	BASE_DEC_HEX,
	BASE_HEX_DEC,
	BASE_CUSTOM

BASE_DEC, BASE_HEX, and BASE_OCT are decimal, hexadecimal, and octal,
respectively. BASE_DEC_HEX and BASE_HEX_DEC display value in two bases
(the 1st representation followed by the 2nd in parenthesis).

BASE_CUSTOM allows one to specify a callback function pointer that will
format the value. The function pointer of the same type as defined by
custom_fmt_func_t in epan/proto.h, specifically:

  void func(gchar *, guint32);

The first argument is a pointer to a buffer of the ITEM_LABEL_LENGTH size
and the second argument is the value to be formatted.

For FT_BOOLEAN fields that are also bitfields (i.e. 'bitmask' is non-zero),
'display' is used to tell the proto_tree how wide the parent bitfield is.
With integers this is not needed since the type of integer itself
(FT_UINT8, FT_UINT16, FT_UINT24, FT_UINT32, etc.) tells the proto_tree how
wide the parent bitfield is.

For FT_ABSOLUTE_TIME fields, 'display' is used to indicate whether the
time is to be displayed as a time in the time zone for the machine on
which Wireshark/TShark is running or as UTC and, for UTC, whether the
date should be displayed as "{monthname}, {month} {day_of_month},
{year}" or as "{year/day_of_year}".

Additionally, BASE_NONE is used for 'display' as a NULL-value. That is, for
non-integers other than FT_ABSOLUTE_TIME fields, and non-bitfield
FT_BOOLEANs, you'll want to use BASE_NONE in the 'display' field.  You may
not use BASE_NONE for integers.

It is possible that in the future we will record the endianness of
integers. If so, it is likely that we'll use a bitmask on the display field
so that integers would be represented as BEND|BASE_DEC or LEND|BASE_HEX.
But that has not happened yet; note that there are protocols for which
no endianness is specified, such as the X11 protocol and the DCE RPC
protocol, so it would not be possible to record the endianness of all
integral fields.

strings
-------
-- value_string
Some integer fields, of type FT_UINT*, need labels to represent the true
value of a field.  You could think of those fields as having an
enumerated data type, rather than an integral data type.

A 'value_string' structure is a way to map values to strings.

	typedef struct _value_string {
		guint32  value;
		gchar   *strptr;
	} value_string;

For fields of that type, you would declare an array of "value_string"s:

	static const value_string valstringname[] = {
		{ INTVAL1, "Descriptive String 1" },
		{ INTVAL2, "Descriptive String 2" },
		{ 0,       NULL }
	};

(the last entry in the array must have a NULL 'strptr' value, to
indicate the end of the array).  The 'strings' field would be set to
'VALS(valstringname)'.

If the field has a numeric rather than an enumerated type, the 'strings'
field would be set to NULL.

-- Extended value strings
You can also use an extended version of the value_string for faster lookups.
It requires a value_string as input.
If all of a contiguous range of values from min to max are present in the array
the value will be used as as a direct index into a value_string array.

If the values in the array are not contiguous (ie: there are "gaps"), but are in assending order
a binary search will be used.

Note: "gaps" in a value_string array can be filled with "empty" entries eg: {value, "Unknown"} so that
direct access to the array is is possible.

The init macro (see below) will perform a check on the value string
the first time it is used to determine which search algorithm fits and fall back to a linear search
if the value_string does not meet the criteria above.

Use this macro to initialise the extended value_string at comile time:

static value_string_ext valstringname_ext = VALUE_STRING_EXT_INIT(valstringname);

Extended value strings can be created at runtime by calling
   value_string_ext_new(<ptr to value_string array>,
                        <total number of entries in the value_string_array>, /* include {0, NULL} entry */
                        <value_string_name>);

For hf[] array FT_(U)INT* fields that need a 'valstringname_ext' struct, the 'strings' field
would be set to '&valstringname_ext)'. Furthermore, 'display' field must be
ORed with 'BASE_EXT_STRING' (e.g. BASE_DEC|BASE_EXT_STRING).


-- Ranges
If the field has a numeric type that might logically fit in ranges of values
one can use a range_string struct.

Thus a 'range_string' structure is a way to map ranges to strings.

        typedef struct _range_string {
                guint32        value_min;
                guint32        value_max;
                const gchar   *strptr;
        } range_string;

For fields of that type, you would declare an array of "range_string"s:

	static const range_string rvalstringname[] = {
		{ INTVAL_MIN1, INTVALMAX1, "Descriptive String 1" },
		{ INTVAL_MIN2, INTVALMAX2, "Descriptive String 2" },
		{ 0,           0,          NULL                   }
	};

If INTVAL_MIN equals INTVAL_MAX for a given entry the range_string
behavior collapses to the one of value_string.
For FT_(U)INT* fields that need a 'range_string' struct, the 'strings' field
would be set to 'RVALS(rvalstringname)'. Furthermore, 'display' field must be
ORed with 'BASE_RANGE_STRING' (e.g. BASE_DEC|BASE_RANGE_STRING).

-- Booleans
FT_BOOLEANs have a default map of 0 = "False", 1 (or anything else) = "True".
Sometimes it is useful to change the labels for boolean values (e.g.,
to "Yes"/"No", "Fast"/"Slow", etc.).  For these mappings, a struct called
true_false_string is used.

	typedef struct true_false_string {
		char	*true_string;
		char	*false_string;
	} true_false_string;

For Boolean fields for which "False" and "True" aren't the desired
labels, you would declare a "true_false_string"s:

	static const true_false_string boolstringname = {
		"String for True",
		"String for False"
	};

Its two fields are pointers to the string representing truth, and the
string representing falsehood.  For FT_BOOLEAN fields that need a
'true_false_string' struct, the 'strings' field would be set to
'TFS(&boolstringname)'.

If the Boolean field is to be displayed as "False" or "True", the
'strings' field would be set to NULL.

Wireshark predefines a whole range of ready made "true_false_string"s
in tfs.h, included via packet.h.

bitmask
-------
If the field is a bitfield, then the bitmask is the mask which will
leave only the bits needed to make the field when ANDed with a value.
The proto_tree routines will calculate 'bitshift' automatically
from 'bitmask', by finding the rightmost set bit in the bitmask.
This shift is applied before applying string mapping functions or
filtering.
If the field is not a bitfield, then bitmask should be set to 0.

blurb
-----
This is a string giving a proper description of the field.  It should be
at least one grammatically complete sentence, or NULL in which case the
name field is used. (Please do not use "").
It is meant to provide a more detailed description of the field than the
name alone provides. This information will be used in the man page, and
in a future GUI display-filter creation tool. We might also add tooltips
to the labels in the GUI protocol tree, in which case the blurb would
be used as the tooltip text.


1.6.1 Field Registration.

Protocol registration is handled by creating an instance of the
header_field_info struct (or an array of such structs), and
calling the registration function along with the registration ID of
the protocol that is the parent of the fields. Here is a complete example:

	static int proto_eg = -1;
	static int hf_field_a = -1;
	static int hf_field_b = -1;

	static hf_register_info hf[] = {

		{ &hf_field_a,
		{ "Field A",	"proto.field_a", FT_UINT8, BASE_HEX, NULL,
			0xf0, "Field A represents Apples", HFILL }},

		{ &hf_field_b,
		{ "Field B",	"proto.field_b", FT_UINT16, BASE_DEC, VALS(vs),
			0x0, "Field B represents Bananas", HFILL }}
	};

	proto_eg = proto_register_protocol("Example Protocol",
	    "PROTO", "proto");
	proto_register_field_array(proto_eg, hf, array_length(hf));

Be sure that your array of hf_register_info structs is declared 'static',
since the proto_register_field_array() function does not create a copy
of the information in the array... it uses that static copy of the
information that the compiler created inside your array. Here's the
layout of the hf_register_info struct:

typedef struct hf_register_info {
	int			*p_id;	/* pointer to parent variable */
	header_field_info	hfinfo;
} hf_register_info;

Also be sure to use the handy array_length() macro found in packet.h
to have the compiler compute the array length for you at compile time.

If you don't have any fields to register, do *NOT* create a zero-length
"hf" array; not all compilers used to compile Wireshark support them.
Just omit the "hf" array, and the "proto_register_field_array()" call,
entirely.

It is OK to have header fields with a different format be registered with
the same abbreviation. For instance, the following is valid:

	static hf_register_info hf[] = {

		{ &hf_field_8bit, /* 8-bit version of proto.field */
		{ "Field (8 bit)", "proto.field", FT_UINT8, BASE_DEC, NULL,
			0x00, "Field represents FOO", HFILL }},

		{ &hf_field_32bit, /* 32-bit version of proto.field */
		{ "Field (32 bit)", "proto.field", FT_UINT32, BASE_DEC, NULL,
			0x00, "Field represents FOO", HFILL }}
	};

This way a filter expression can match a header field, irrespective of the
representation of it in the specific protocol context. This is interesting
for protocols with variable-width header fields.

The HFILL macro at the end of the struct will set reasonable default values
for internally used fields.

1.6.2 Adding Items and Values to the Protocol Tree.

A protocol item is added to an existing protocol tree with one of a
handful of proto_XXX_DO_YYY() functions.

Remember that it only makes sense to add items to a protocol tree if its
proto_tree pointer is not null. Should you add an item to a NULL tree, then
the proto_XXX_DO_YYY() function will immediately return. The cost of this
function call can be avoided by checking for the tree pointer.

Subtrees can be made with the proto_item_add_subtree() function:

	item = proto_tree_add_item(....);
	new_tree = proto_item_add_subtree(item, tree_type);

This will add a subtree under the item in question; a subtree can be
created under an item made by any of the "proto_tree_add_XXX" functions,
so that the tree can be given an arbitrary depth.

Subtree types are integers, assigned by
"proto_register_subtree_array()".  To register subtree types, pass an
array of pointers to "gint" variables to hold the subtree type values to
"proto_register_subtree_array()":

	static gint ett_eg = -1;
	static gint ett_field_a = -1;

	static gint *ett[] = {
		&ett_eg,
		&ett_field_a
	};

	proto_register_subtree_array(ett, array_length(ett));

in your "register" routine, just as you register the protocol and the
fields for that protocol.

The ett_ variables identify particular type of subtree so that if you expand
one of them, Wireshark keeps track of that and, when you click on
another packet, it automatically opens all subtrees of that type.
If you close one of them, all subtrees of that type will be closed when
you move to another packet.

There are several functions that the programmer can use to add either
protocol or field labels to the proto_tree:

	proto_item*
	proto_tree_add_item(tree, id, tvb, start, length, encoding);

	proto_item*
	proto_tree_add_none_format(tree, id, tvb, start, length, format, ...);

	proto_item*
	proto_tree_add_protocol_format(tree, id, tvb, start, length,
		format, ...);

	proto_item *
	proto_tree_add_bytes(tree, id, tvb, start, length, start_ptr);

	proto_item *
	proto_tree_add_bytes_format(tree, id, tvb, start, length, start_ptr,
		format, ...);

	proto_item *
	proto_tree_add_bytes_format_value(tree, id, tvb, start, length,
		start_ptr, format, ...);

	proto_item *
	proto_tree_add_time(tree, id, tvb, start, length, value_ptr);

	proto_item *
	proto_tree_add_time_format(tree, id, tvb, start, length, value_ptr,
		format, ...);

	proto_item *
	proto_tree_add_time_format_value(tree, id, tvb, start, length,
		value_ptr, format, ...);

	proto_item *
	proto_tree_add_ipxnet(tree, id, tvb, start, length, value);

	proto_item *
	proto_tree_add_ipxnet_format(tree, id, tvb, start, length, value,
		format, ...);

	proto_item *
	proto_tree_add_ipxnet_format_value(tree, id, tvb, start, length,
		value, format, ...);

	proto_item *
	proto_tree_add_ipv4(tree, id, tvb, start, length, value);

	proto_item *
	proto_tree_add_ipv4_format(tree, id, tvb, start, length, value,
		format, ...);

	proto_item *
	proto_tree_add_ipv4_format_value(tree, id, tvb, start, length,
		value, format, ...);

	proto_item *
	proto_tree_add_ipv6(tree, id, tvb, start, length, value_ptr);

	proto_item *
	proto_tree_add_ipv6_format(tree, id, tvb, start, length, value_ptr,
		format, ...);

	proto_item *
	proto_tree_add_ipv6_format_value(tree, id, tvb, start, length,
		value_ptr, format, ...);

	proto_item *
	proto_tree_add_ether(tree, id, tvb, start, length, value_ptr);

	proto_item *
	proto_tree_add_ether_format(tree, id, tvb, start, length, value_ptr,
		format, ...);

	proto_item *
	proto_tree_add_ether_format_value(tree, id, tvb, start, length,
		value_ptr, format, ...);

	proto_item *
	proto_tree_add_string(tree, id, tvb, start, length, value_ptr);

	proto_item *
	proto_tree_add_string_format(tree, id, tvb, start, length, value_ptr,
		format, ...);

	proto_item *
	proto_tree_add_string_format_value(tree, id, tvb, start, length,
		value_ptr, format, ...);

	proto_item *
	proto_tree_add_boolean(tree, id, tvb, start, length, value);

	proto_item *
	proto_tree_add_boolean_format(tree, id, tvb, start, length, value,
		format, ...);

	proto_item *
	proto_tree_add_boolean_format_value(tree, id, tvb, start, length,
		value, format, ...);

	proto_item *
	proto_tree_add_float(tree, id, tvb, start, length, value);

	proto_item *
	proto_tree_add_float_format(tree, id, tvb, start, length, value,
		format, ...);

	proto_item *
	proto_tree_add_float_format_value(tree, id, tvb, start, length,
		value, format, ...);

	proto_item *
	proto_tree_add_double(tree, id, tvb, start, length, value);

	proto_item *
	proto_tree_add_double_format(tree, id, tvb, start, length, value,
		format, ...);

	proto_item *
	proto_tree_add_double_format_value(tree, id, tvb, start, length,
		value, format, ...);

	proto_item *
	proto_tree_add_uint(tree, id, tvb, start, length, value);

	proto_item *
	proto_tree_add_uint_format(tree, id, tvb, start, length, value,
		format, ...);

	proto_item *
	proto_tree_add_uint_format_value(tree, id, tvb, start, length,
		value, format, ...);

	proto_item *
	proto_tree_add_uint64(tree, id, tvb, start, length, value);

	proto_item *
	proto_tree_add_uint64_format(tree, id, tvb, start, length, value,
		format, ...);

	proto_item *
	proto_tree_add_uint64_format_value(tree, id, tvb, start, length,
		value, format, ...);

	proto_item *
	proto_tree_add_int(tree, id, tvb, start, length, value);

	proto_item *
	proto_tree_add_int_format(tree, id, tvb, start, length, value,
		format, ...);

	proto_item *
	proto_tree_add_int_format_value(tree, id, tvb, start, length,
		value, format, ...);

	proto_item *
	proto_tree_add_int64(tree, id, tvb, start, length, value);

	proto_item *
	proto_tree_add_int64_format(tree, id, tvb, start, length, value,
		format, ...);

	proto_item *
	proto_tree_add_int64_format_value(tree, id, tvb, start, length,
		value, format, ...);

	proto_item*
	proto_tree_add_text(tree, tvb, start, length, format, ...);

	proto_item*
	proto_tree_add_text_valist(tree, tvb, start, length, format, ap);

	proto_item *
	proto_tree_add_guid(tree, id, tvb, start, length, value_ptr);

	proto_item *
	proto_tree_add_guid_format(tree, id, tvb, start, length, value_ptr,
		format, ...);

	proto_item *
	proto_tree_add_guid_format_value(tree, id, tvb, start, length,
		value_ptr, format, ...);

	proto_item *
	proto_tree_add_oid(tree, id, tvb, start, length, value_ptr);

	proto_item *
	proto_tree_add_oid_format(tree, id, tvb, start, length, value_ptr,
		format, ...);

	proto_item *
	proto_tree_add_eui64(tree, id, tvb, start, length, value);

	proto_item *
	proto_tree_add_eui64_format(tree, id, tvb, start, length, value,
		format, ...);

	proto_item *
	proto_tree_add_eui64_format_value(tree, id, tvb, start, length,
		value, format, ...);

	proto_item *
	proto_tree_add_oid_format_value(tree, id, tvb, start, length,
		value_ptr, format, ...);

	proto_item*
	proto_tree_add_bits_item(tree, id, tvb, bit_offset, no_of_bits,
		little_endian);

	proto_item *
	proto_tree_add_bits_ret_val(tree, id, tvb, bit_offset, no_of_bits,
		return_value, little_endian);

	proto_item *
	proto_tree_add_bitmask(tree, tvb, start, header, ett, fields,
		little_endian);

	proto_item *
	proto_tree_add_bitmask_text(tree, tvb, offset, len, name, fallback,
		ett, fields, little_endian, flags);

The 'tree' argument is the tree to which the item is to be added.  The
'tvb' argument is the tvbuff from which the item's value is being
extracted; the 'start' argument is the offset from the beginning of that
tvbuff of the item being added, and the 'length' argument is the length,
in bytes, of the item, bit_offset is the offset in bits and no_of_bits
is the length in bits.

The length of some items cannot be determined until the item has been
dissected; to add such an item, add it with a length of -1, and, when the
dissection is complete, set the length with 'proto_item_set_len()':

	void
	proto_item_set_len(ti, length);

The "ti" argument is the value returned by the call that added the item
to the tree, and the "length" argument is the length of the item.

proto_tree_add_item()
---------------------
proto_tree_add_item is used when you wish to do no special formatting.
The item added to the GUI tree will contain the name (as passed in the
proto_register_*() function) and a value.  The value will be fetched
from the tvbuff by proto_tree_add_item(), based on the type of the field
and, for integral and Boolean fields, the byte order of the value; the
byte order, for items for which that's relevant, is specified by the
'encoding' argument, which is ENC_LITTLE_ENDIAN if the value is
little-endian and ENC_BIG_ENDIAN if it is big-endian.  If the byte order
is not relevant, use ENC_NA (Not Applicable).  In the future, other
elements of the encoding, such as the character encoding for
character strings, might be supported.

Now that definitions of fields have detailed information about bitfield
fields, you can use proto_tree_add_item() with no extra processing to
add bitfield values to your tree.  Here's an example.  Take the Format
Identifier (FID) field in the Transmission Header (TH) portion of the SNA
protocol.  The FID is the high nibble of the first byte of the TH.  The
FID would be registered like this:

	name		= "Format Identifier"
	abbrev		= "sna.th.fid"
	type		= FT_UINT8
	display		= BASE_HEX
	strings		= sna_th_fid_vals
	bitmask		= 0xf0

The bitmask contains the value which would leave only the FID if bitwise-ANDed
against the parent field, the first byte of the TH.

The code to add the FID to the tree would be;

	proto_tree_add_item(bf_tree, hf_sna_th_fid, tvb, offset, 1,
	    ENC_BIG_ENDIAN);

The definition of the field already has the information about bitmasking
and bitshifting, so it does the work of masking and shifting for us!
This also means that you no longer have to create value_string structs
with the values bitshifted.  The value_string for FID looks like this,
even though the FID value is actually contained in the high nibble.
(You'd expect the values to be 0x0, 0x10, 0x20, etc.)

/* Format Identifier */
static const value_string sna_th_fid_vals[] = {
	{ 0x0,	"SNA device <--> Non-SNA Device" },
	{ 0x1,	"Subarea Node <--> Subarea Node" },
	{ 0x2,	"Subarea Node <--> PU2" },
	{ 0x3,	"Subarea Node or SNA host <--> Subarea Node" },
	{ 0x4,	"?" },
	{ 0x5,	"?" },
	{ 0xf,	"Adjacent Subarea Nodes" },
	{ 0,	NULL }
};

The final implication of this is that display filters work the way you'd
naturally expect them to. You'd type "sna.th.fid == 0xf" to find Adjacent
Subarea Nodes. The user does not have to shift the value of the FID to
the high nibble of the byte ("sna.th.fid == 0xf0") as was necessary
in the past.

proto_tree_add_protocol_format()
--------------------------------
proto_tree_add_protocol_format is used to add the top-level item for the
protocol when the dissector routine wants complete control over how the
field and value will be represented on the GUI tree.  The ID value for
the protocol is passed in as the "id" argument; the rest of the
arguments are a "printf"-style format and any arguments for that format.
The caller must include the name of the protocol in the format; it is
not added automatically as in proto_tree_add_item().

proto_tree_add_none_format()
----------------------------
proto_tree_add_none_format is used to add an item of type FT_NONE.
The caller must include the name of the field in the format; it is
not added automatically as in proto_tree_add_item().

proto_tree_add_bytes()
proto_tree_add_time()
proto_tree_add_ipxnet()
proto_tree_add_ipv4()
proto_tree_add_ipv6()
proto_tree_add_ether()
proto_tree_add_string()
proto_tree_add_boolean()
proto_tree_add_float()
proto_tree_add_double()
proto_tree_add_uint()
proto_tree_add_uint64()
proto_tree_add_int()
proto_tree_add_int64()
proto_tree_add_guid()
proto_tree_add_oid()
proto_tree_add_eui64()
------------------------
These routines are used to add items to the protocol tree if either:

	the value of the item to be added isn't just extracted from the
	packet data, but is computed from data in the packet;

	the value was fetched into a variable.

The 'value' argument has the value to be added to the tree.

NOTE: in all cases where the 'value' argument is a pointer, a copy is
made of the object pointed to; if you have dynamically allocated a
buffer for the object, that buffer will not be freed when the protocol
tree is freed - you must free the buffer yourself when you don't need it
any more.

For proto_tree_add_bytes(), the 'value_ptr' argument is a pointer to a
sequence of bytes.

For proto_tree_add_bytes_format() and proto_tree_add_bytes_format_value(), the
'value_ptr' argument is a pointer to a sequence of bytes or NULL if the bytes
should be taken from the given TVB using the given offset and length.

For proto_tree_add_time(), the 'value_ptr' argument is a pointer to an
"nstime_t", which is a structure containing the time to be added; it has
'secs' and 'nsecs' members, giving the integral part and the fractional
part of a time in units of seconds, with 'nsecs' being the number of
nanoseconds.  For absolute times, "secs" is a UNIX-style seconds since
January 1, 1970, 00:00:00 GMT value.

For proto_tree_add_ipxnet(), the 'value' argument is a 32-bit IPX
network address.

For proto_tree_add_ipv4(), the 'value' argument is a 32-bit IPv4
address, in network byte order.

For proto_tree_add_ipv6(), the 'value_ptr' argument is a pointer to a
128-bit IPv6 address.

For proto_tree_add_ether(), the 'value_ptr' argument is a pointer to a
48-bit MAC address.

For proto_tree_add_string(), the 'value_ptr' argument is a pointer to a
text string.

For proto_tree_add_boolean(), the 'value' argument is a 32-bit integer.
It is masked and shifted as defined by the field info after which zero
means "false", and non-zero means "true".

For proto_tree_add_float(), the 'value' argument is a 'float' in the
host's floating-point format.

For proto_tree_add_double(), the 'value' argument is a 'double' in the
host's floating-point format.

For proto_tree_add_uint(), the 'value' argument is a 32-bit unsigned
integer value, in host byte order.  (This routine cannot be used to add
64-bit integers.)

For proto_tree_add_uint64(), the 'value' argument is a 64-bit unsigned
integer value, in host byte order.

For proto_tree_add_int(), the 'value' argument is a 32-bit signed
integer value, in host byte order.  (This routine cannot be used to add
64-bit integers.)

For proto_tree_add_int64(), the 'value' argument is a 64-bit signed
integer value, in host byte order.

For proto_tree_add_guid(), the 'value_ptr' argument is a pointer to an
e_guid_t structure.

For proto_tree_add_oid(), the 'value_ptr' argument is a pointer to an
ASN.1 Object Identifier.

For proto_tree_add_eui64(), the 'value' argument is a 64-bit integer 
value

proto_tree_add_bytes_format()
proto_tree_add_time_format()
proto_tree_add_ipxnet_format()
proto_tree_add_ipv4_format()
proto_tree_add_ipv6_format()
proto_tree_add_ether_format()
proto_tree_add_string_format()
proto_tree_add_boolean_format()
proto_tree_add_float_format()
proto_tree_add_double_format()
proto_tree_add_uint_format()
proto_tree_add_uint64_format()
proto_tree_add_int_format()
proto_tree_add_int64_format()
proto_tree_add_guid_format()
proto_tree_add_oid_format()
proto_tree_add_eui64_format()
----------------------------
These routines are used to add items to the protocol tree when the
dissector routine wants complete control over how the field and value
will be represented on the GUI tree.  The argument giving the value is
the same as the corresponding proto_tree_add_XXX() function; the rest of
the arguments are a "printf"-style format and any arguments for that
format.  The caller must include the name of the field in the format; it
is not added automatically as in the proto_tree_add_XXX() functions.

proto_tree_add_bytes_format_value()
proto_tree_add_time_format_value()
proto_tree_add_ipxnet_format_value()
proto_tree_add_ipv4_format_value()
proto_tree_add_ipv6_format_value()
proto_tree_add_ether_format_value()
proto_tree_add_string_format_value()
proto_tree_add_boolean_format_value()
proto_tree_add_float_format_value()
proto_tree_add_double_format_value()
proto_tree_add_uint_format_value()
proto_tree_add_uint64_format_value()
proto_tree_add_int_format_value()
proto_tree_add_int64_format_value()
proto_tree_add_guid_format_value()
proto_tree_add_oid_format_value()
proto_tree_add_eui64_format_value()
------------------------------------

These routines are used to add items to the protocol tree when the
dissector routine wants complete control over how the value will be
represented on the GUI tree.  The argument giving the value is the same
as the corresponding proto_tree_add_XXX() function; the rest of the
arguments are a "printf"-style format and any arguments for that format.
With these routines, unlike the proto_tree_add_XXX_format() routines,
the name of the field is added automatically as in the
proto_tree_add_XXX() functions; only the value is added with the format.

proto_tree_add_text()
---------------------
proto_tree_add_text() is used to add a label to the GUI tree.  It will
contain no value, so it is not searchable in the display filter process.
This function was needed in the transition from the old-style proto_tree
to this new-style proto_tree so that Wireshark would still decode all
protocols w/o being able to filter on all protocols and fields.
Otherwise we would have had to cripple Wireshark's functionality while we
converted all the old-style proto_tree calls to the new-style proto_tree
calls.  In other words, you should not use this in new code unless you've got
a specific reason (see below).

This can also be used for items with subtrees, which may not have values
themselves - the items in the subtree are the ones with values.

For a subtree, the label on the subtree might reflect some of the items
in the subtree.  This means the label can't be set until at least some
of the items in the subtree have been dissected.  To do this, use
'proto_item_set_text()' or 'proto_item_append_text()':

	void
	proto_item_set_text(proto_item *ti, ...);

	void
	proto_item_append_text(proto_item *ti, ...);

'proto_item_set_text()' takes as an argument the value returned by
'proto_tree_add_text()', a 'printf'-style format string, and a set of
arguments corresponding to '%' format items in that string, and replaces
the text for the item created by 'proto_tree_add_text()' with the result
of applying the arguments to the format string.

'proto_item_append_text()' is similar, but it appends to the text for
the item the result of applying the arguments to the format string.

For example, early in the dissection, one might do:

	ti = proto_tree_add_text(tree, tvb, offset, length, <label>);

and later do

	proto_item_set_text(ti, "%s: %s", type, value);

after the "type" and "value" fields have been extracted and dissected.
<label> would be a label giving what information about the subtree is
available without dissecting any of the data in the subtree.

Note that an exception might be thrown when trying to extract the values of
the items used to set the label, if not all the bytes of the item are
available.  Thus, one should create the item with text that is as
meaningful as possible, and set it or append additional information to
it as the values needed to supply that information are extracted.

proto_tree_add_text_valist()
----------------------------
This is like proto_tree_add_text(), but takes, as the last argument, a
'va_list'; it is used to allow routines that take a printf-like
variable-length list of arguments to add a text item to the protocol
tree.

proto_tree_add_bits_item()
--------------------------
Adds a number of bits to the protocol tree which does not have to be byte
aligned. The offset and length is in bits.
Output format:

..10 1010 10.. .... "value" (formatted as FT_ indicates).

proto_tree_add_bits_ret_val()
-----------------------------
Works in the same way but also returns the value of the read bits.

proto_tree_add_bitmask() and proto_tree_add_bitmask_text()
----------------------------------------------------------
This function provides an easy to use and convenient helper function
to manage many types of common bitmasks that occur in protocols.

This function will dissect a 1/2/3/4 byte large bitmask into its individual
fields.
header is an integer type and must be of type FT_[U]INT{8|16|24|32} and
represents the entire width of the bitmask.

'header' and 'ett' are the hf fields and ett field respectively to create an
expansion that covers the 1-4 bytes of the bitmask.

'fields' is a NULL terminated array of pointers to hf fields representing
the individual subfields of the bitmask. These fields must either be integers
of the same byte width as 'header' or of the type FT_BOOLEAN.
Each of the entries in 'fields' will be dissected as an item under the
'header' expansion and also IF the field is a boolean and IF it is set to 1,
then the name of that boolean field will be printed on the 'header' expansion
line.  For integer type subfields that have a value_string defined, the
matched string from that value_string will be printed on the expansion line
as well.

Example: (from the SCSI dissector)
	static int hf_scsi_inq_peripheral        = -1;
	static int hf_scsi_inq_qualifier         = -1;
	static int hf_scsi_inq_devtype           = -1;
	...
	static gint ett_scsi_inq_peripheral = -1;
	...
	static const int *peripheal_fields[] = {
		&hf_scsi_inq_qualifier,
		&hf_scsi_inq_devtype,
		NULL
	};
	...
	/* Qualifier and DeviceType */
	proto_tree_add_bitmask(tree, tvb, offset, hf_scsi_inq_peripheral,
		ett_scsi_inq_peripheral, peripheal_fields, FALSE);
	offset+=1;
	...
        { &hf_scsi_inq_peripheral,
          {"Peripheral", "scsi.inquiry.preipheral", FT_UINT8, BASE_HEX,
           NULL, 0, NULL, HFILL}},
        { &hf_scsi_inq_qualifier,
          {"Qualifier", "scsi.inquiry.qualifier", FT_UINT8, BASE_HEX,
           VALS (scsi_qualifier_val), 0xE0, NULL, HFILL}},
        { &hf_scsi_inq_devtype,
          {"Device Type", "scsi.inquiry.devtype", FT_UINT8, BASE_HEX,
           VALS (scsi_devtype_val), SCSI_DEV_BITS, NULL, HFILL}},
	...

Which provides very pretty dissection of this one byte bitmask.

    Peripheral: 0x05, Qualifier: Device type is connected to logical unit, Device Type: CD-ROM
        000. .... = Qualifier: Device type is connected to logical unit (0x00)
        ...0 0101 = Device Type: CD-ROM (0x05)

The proto_tree_add_bitmask_text() function is an extended version of
the proto_tree_add_bitmask() function. In addition, it allows to:
- Provide a leading text (e.g. "Flags: ") that will appear before
  the comma-separated list of field values
- Provide a fallback text (e.g. "None") that will be appended if
  no fields warranted a change to the top-level title.
- Using flags, specify which fields will affect the top-level title.

There are the following flags defined:

  BMT_NO_APPEND - the title is taken "as-is" from the 'name' argument.
  BMT_NO_INT - only boolean flags are added to the title.
  BMT_NO_FALSE - boolean flags are only added to the title if they are set.
  BMT_NO_TFS - only add flag name to the title, do not use true_false_string

The proto_tree_add_bitmask() behavior can be obtained by providing
both 'name' and 'fallback' arguments as NULL, and a flags of
(BMT_NO_FALSE|BMT_NO_TFS).

PROTO_ITEM_SET_GENERATED()
--------------------------
PROTO_ITEM_SET_GENERATED is used to mark fields as not being read from the
captured data directly, but inferred from one or more values.

One of the primary uses of this is the presentation of verification of
checksums. Every IP packet has a checksum line, which can present the result
of the checksum verification, if enabled in the preferences. The result is
presented as a subtree, where the result is enclosed in square brackets
indicating a generated field.

  Header checksum: 0x3d42 [correct]
    [Good: True]
    [Bad: False]

PROTO_ITEM_SET_HIDDEN()
-----------------------
PROTO_ITEM_SET_HIDDEN is used to hide fields, which have already been added
to the tree, from being visible in the displayed tree.

NOTE that creating hidden fields is actually quite a bad idea from a UI design
perspective because the user (someone who did not write nor has ever seen the
code) has no way of knowing that hidden fields are there to be filtered on
thus defeating the whole purpose of putting them there.  A Better Way might
be to add the fields (that might otherwise be hidden) to a subtree where they
won't be seen unless the user opens the subtree--but they can be found if the
user wants.

One use for hidden fields (which would be better implemented using visible
fields in a subtree) follows: The caller may want a value to be
included in a tree so that the packet can be filtered on this field, but
the representation of that field in the tree is not appropriate.  An
example is the token-ring routing information field (RIF).  The best way
to show the RIF in a GUI is by a sequence of ring and bridge numbers.
Rings are 3-digit hex numbers, and bridges are single hex digits:

	RIF: 001-A-013-9-C0F-B-555

In the case of RIF, the programmer should use a field with no value and
use proto_tree_add_none_format() to build the above representation. The
programmer can then add the ring and bridge values, one-by-one, with
proto_tree_add_item() and hide them with PROTO_ITEM_SET_HIDDEN() so that the
user can then filter on or search for a particular ring or bridge. Here's a
skeleton of how the programmer might code this.

	char *rif;
	rif = create_rif_string(...);

	proto_tree_add_none_format(tree, hf_tr_rif_label, ..., "RIF: %s", rif);

	for(i = 0; i < num_rings; i++) {
		proto_item *pi;

		pi = proto_tree_add_item(tree, hf_tr_rif_ring, ...,
		    ENC_BIG_ENDIAN);
		PROTO_ITEM_SET_HIDDEN(pi);
	}
	for(i = 0; i < num_rings - 1; i++) {
		proto_item *pi;

		pi = proto_tree_add_item(tree, hf_tr_rif_bridge, ...,
		    ENC_BIG_ENDIAN);
		PROTO_ITEM_SET_HIDDEN(pi);
	}

The logical tree has these items:

	hf_tr_rif_label, text="RIF: 001-A-013-9-C0F-B-555", value = NONE
	hf_tr_rif_ring,  hidden, value=0x001
	hf_tr_rif_bridge, hidden, value=0xA
	hf_tr_rif_ring,  hidden, value=0x013
	hf_tr_rif_bridge, hidden, value=0x9
	hf_tr_rif_ring,  hidden, value=0xC0F
	hf_tr_rif_bridge, hidden, value=0xB
	hf_tr_rif_ring,  hidden, value=0x555

GUI or print code will not display the hidden fields, but a display
filter or "packet grep" routine will still see the values. The possible
filter is then possible:

	tr.rif_ring eq 0x013

PROTO_ITEM_SET_URL
------------------
PROTO_ITEM_SET_URL is used to mark fields as containing a URL. This can only
be done with fields of type FT_STRING(Z). If these fields are presented they
are underlined, as could be done in a browser. These fields are sensitive to
clicks as well, launching the configured browser with this URL as parameter.

1.7 Utility routines.

1.7.1 match_strval, match_strval_ext, val_to_str and val_to_str_ext.

A dissector may need to convert a value to a string, using a
'value_string' structure, by hand, rather than by declaring a field with
an associated 'value_string' structure; this might be used, for example,
to generate a COL_INFO line for a frame.

'match_strval()' will do that:

	gchar*
	match_strval(guint32 val, const value_string *vs)

It will look up the value 'val' in the 'value_string' table pointed to
by 'vs', and return either the corresponding string, or NULL if the
value could not be found in the table.  Note that, unless 'val' is
guaranteed to be a value in the 'value_string' table ("guaranteed" as in
"the code has already checked that it's one of those values" or "the
table handles all possible values of the size of 'val'", not "the
protocol spec says it has to be" - protocol specs do not prevent invalid
packets from being put onto a network or into a purported packet capture
file), you must check whether 'match_strval()' returns NULL, and arrange
that its return value not be dereferenced if it's NULL. 'val_to_str()'
can be used to generate a string for values not found in the table:

	gchar*
	val_to_str(guint32 val, const value_string *vs, const char *fmt)

If the value 'val' is found in the 'value_string' table pointed to by
'vs', 'val_to_str' will return the corresponding string; otherwise, it
will use 'fmt' as an 'sprintf'-style format, with 'val' as an argument,
to generate a string, and will return a pointer to that string.
You can use it in a call to generate a COL_INFO line for a frame such as

	col_add_fstr(COL_INFO, ", %s", val_to_str(val, table, "Unknown %d"));

The match_strval_ext and val_to_str_ext functions are "extended" versions
of match_strval and val_to_str. They should be used for large value-string
arrays which contain many entries. They implement value to string conversions
which will do either a direct access or a binary search of the
value string array if possible. See "Extended Value Strings" under
section  1.6 "Constructing the protocol tree" for more information.

See epan/value_string.h for detailed information on the various value_string
functions.


1.7.2 match_strrval and rval_to_str.

A dissector may need to convert a range of values to a string, using a
'range_string' structure.

'match_strrval()' will do that:

	gchar*
	match_strrval(guint32 val, const range_string *rs)

It will look up the value 'val' in the 'range_string' table pointed to
by 'rs', and return either the corresponding string, or NULL if the
value could not be found in the table. Please note that its base
behavior is inherited from match_strval().

'rval_to_str()' can be used to generate a string for values not found in
the table:

	gchar*
	rval_to_str(guint32 val, const range_string *rs, const char *fmt)

If the value 'val' is found in the 'range_string' table pointed to by
'rs', 'rval_to_str' will return the corresponding string; otherwise, it
will use 'fmt' as an 'sprintf'-style format, with 'val' as an argument,
to generate a string, and will return a pointer to that string. Please
note that its base behavior is inherited from match_strval().

1.8 Calling Other Dissectors.

As each dissector completes its portion of the protocol analysis, it
is expected to create a new tvbuff of type TVBUFF_SUBSET which
contains the payload portion of the protocol (that is, the bytes
that are relevant to the next dissector).

The syntax for creating a new TVBUFF_SUBSET is:

next_tvb = tvb_new_subset(tvb, offset, length, reported_length)

Where:
	tvb is the tvbuff that the dissector has been working on. It
	can be a tvbuff of any type.

	next_tvb is the new TVBUFF_SUBSET.

	offset is the byte offset of 'tvb' at which the new tvbuff
	should start.  The first byte is the 0th byte.

	length is the number of bytes in the new TVBUFF_SUBSET. A length
	argument of -1 says to use as many bytes as are available in
	'tvb'.

	reported_length is the number of bytes that the current protocol
	says should be in the payload. A reported_length of -1 says that
	the protocol doesn't say anything about the size of its payload.


An example from packet-ipx.c -

void
dissect_ipx(tvbuff_t *tvb, packet_info *pinfo, proto_tree *tree)
{
        tvbuff_t        *next_tvb;
        int             reported_length, available_length;


        /* Make the next tvbuff */

/* IPX does have a length value in the header, so calculate report_length */
   Set this to -1 if there isn't any length information in the protocol
*/
        reported_length = ipx_length - IPX_HEADER_LEN;

/* Calculate the available data in the packet,
   set this to -1 to use all the data in the tv_buffer
*/
        available_length = tvb_length(tvb) - IPX_HEADER_LEN;

/* Create the tvbuffer for the next dissector */
        next_tvb = tvb_new_subset(tvb, IPX_HEADER_LEN,
                        MIN(available_length, reported_length),
                        reported_length);

/* call the next dissector */
	dissector_next( next_tvb, pinfo, tree);


1.9 Editing Makefile.common and CMakeLists.txt to add your dissector.

To arrange that your dissector will be built as part of Wireshark, you
must add the name of the source file for your dissector to the
'DISSECTOR_SRC' macro in the 'Makefile.common' file in the 'epan/dissectors'
directory.  (Note that this is for modern versions of UNIX, so there
is no 14-character limitation on file names, and for modern versions of
Windows, so there is no 8.3-character limitation on file names.)

If your dissector also has its own header file or files, you must add
them to the 'DISSECTOR_INCLUDES' macro in the 'Makefile.common' file in
the 'epan/dissectors' directory, so that it's included when release source
tarballs are built (otherwise, the source in the release tarballs won't
compile).

In addition to the above, you should add your dissector source file name
to the DISSECTOR_SRC section of epan/CMakeLists.txt


1.10 Using the SVN source code tree.

  See <http://www.wireshark.org/develop.html>

1.11 Submitting code for your new dissector.

  - VERIFY that your dissector code does not use prohibited or deprecated APIs
    as follows:
    perl <wireshark_root>/tools/checkAPIs.pl <source-filename(s)>

  - TEST YOUR DISSECTOR BEFORE SUBMITTING IT.
    Use fuzz-test.sh and/or randpkt against your dissector.  These are
    described at <http://wiki.wireshark.org/FuzzTesting>.

  - Subscribe to <mailto:wireshark-dev[AT]wireshark.org> by sending an email to
    <mailto:wireshark-dev-request[AT]wireshark.org?body="help"> or visiting
    <http://www.wireshark.org/lists/>.

  - 'svn add' all the files of your new dissector.

  - 'svn diff' the workspace and save the result to a file.

  - Edit the diff file - remove any changes unrelated to your new dissector,
    e.g. changes in config.nmake

  - Submit a bug report to the Wireshark bug database, found at
    <http://bugs.wireshark.org>, qualified as an enhancement and attach your
    diff file there. Set the review request flag to '?' so it will pop up in
    the patch review list.

  - Create a Wiki page on the protocol at <http://wiki.wireshark.org>.
    A template is provided so it is easy to setup in a consistent style.
      See: <http://wiki.wireshark.org/HowToEdit>
      and  <http://wiki.wireshark.org/ProtocolReference>

  - If possible, add sample capture files to the sample captures page at
    <http://wiki.wireshark.org/SampleCaptures>.  These files are used by
    the automated build system for fuzz testing.

  - If you find that you are contributing a lot to wireshark on an ongoing
    basis you can request to become a committer which will allow you to
    commit files to subversion directly.

2. Advanced dissector topics.

2.1 Introduction.

Some of the advanced features are being worked on constantly. When using them
it is wise to check the relevant header and source files for additional details.

2.2 Following "conversations".

In wireshark a conversation is defined as a series of data packets between two
address:port combinations.  A conversation is not sensitive to the direction of
the packet.  The same conversation will be returned for a packet bound from
ServerA:1000 to ClientA:2000 and the packet from ClientA:2000 to ServerA:1000.

2.2.1 Conversation Routines

There are six routines that you will use to work with a conversation:
conversation_new, find_conversation, conversation_add_proto_data,
conversation_get_proto_data, conversation_delete_proto_data,
and conversation_set_dissector.


2.2.1.1 The conversation_init function.

This is an internal routine for the conversation code.  As such you
will not have to call this routine.  Just be aware that this routine is
called at the start of each capture and before the packets are filtered
with a display filter.  The routine will destroy all stored
conversations.  This routine does NOT clean up any data pointers that are
passed in the conversation_add_proto_data 'data' variable.  You are
responsible for this clean up if you pass a malloc'ed pointer
in this variable.

See item 2.2.1.5 for more information about use of the 'data' pointer.


2.2.1.2 The conversation_new function.

This routine will create a new conversation based upon two address/port
pairs.  If you want to associate with the conversation a pointer to a
private data structure you must use the conversation_add_proto_data
function.  The ptype variable is used to differentiate between
conversations over different protocols, i.e. TCP and UDP.  The options
variable is used to define a conversation that will accept any destination
address and/or port.  Set options = 0 if the destination port and address
are know when conversation_new is called.  See section 2.4 for more
information on usage of the options parameter.

The conversation_new prototype:
	conversation_t *conversation_new(guint32 setup_frame, address *addr1,
	    address *addr2, port_type ptype, guint32 port1, guint32 port2,
	    guint options);

Where:
	guint32 setup_frame = The lowest numbered frame for this conversation
	address* addr1 	    = first data packet address
	address* addr2 	    = second data packet address
	port_type ptype     = port type, this is defined in packet.h
	guint32 port1	    = first data packet port
	guint32 port2	    = second data packet port
	guint options	    = conversation options, NO_ADDR2 and/or NO_PORT2

setup_frame indicates the first frame for this conversation, and is used to
distinguish multiple conversations with the same addr1/port1 and addr2/port2
pair that occur within the same capture session.

"addr1" and "port1" are the first address/port pair; "addr2" and "port2"
are the second address/port pair.  A conversation doesn't have source
and destination address/port pairs - packets in a conversation go in
both directions - so "addr1"/"port1" may be the source or destination
address/port pair; "addr2"/"port2" would be the other pair.

If NO_ADDR2 is specified, the conversation is set up so that a
conversation lookup will match only the "addr1" address; if NO_PORT2 is
specified, the conversation is set up so that a conversation lookup will
match only the "port1" port; if both are specified, i.e.
NO_ADDR2|NO_PORT2, the conversation is set up so that the lookup will
match only the "addr1"/"port1" address/port pair.  This can be used if a
packet indicates that, later in the capture, a conversation will be
created using certain addresses and ports, in the case where the packet
doesn't specify the addresses and ports of both sides.

2.2.1.3 The find_conversation function.

Call this routine to look up a conversation.  If no conversation is found,
the routine will return a NULL value.

The find_conversation prototype:

	conversation_t *find_conversation(guint32 frame_num, address *addr_a,
	    address *addr_b, port_type ptype, guint32 port_a, guint32 port_b,
	    guint options);

Where:
	guint32 frame_num = a frame number to match
	address* addr_a = first address
	address* addr_b = second address
	port_type ptype = port type
	guint32 port_a	= first data packet port
	guint32 port_b	= second data packet port
	guint options	= conversation options, NO_ADDR_B and/or NO_PORT_B

frame_num is a frame number to match. The conversation returned is where
	(frame_num >= conversation->setup_frame
	&& frame_num < conversation->next->setup_frame)
Suppose there are a total of 3 conversations (A, B, and C) that match
addr_a/port_a and addr_b/port_b, where the setup_frame used in
conversation_new() for A, B and C are 10, 50, and 100 respectively. The
frame_num passed in find_conversation is compared to the setup_frame of each
conversation. So if (frame_num >= 10 && frame_num < 50), conversation A is
returned. If (frame_num >= 50 && frame_num < 100), conversation B is returned.
If (frame_num >= 100) conversation C is returned.

"addr_a" and "port_a" are the first address/port pair; "addr_b" and
"port_b" are the second address/port pair.  Again, as a conversation
doesn't have source and destination address/port pairs, so
"addr_a"/"port_a" may be the source or destination address/port pair;
"addr_b"/"port_b" would be the other pair.  The search will match the
"a" address/port pair against both the "1" and "2" address/port pairs,
and match the "b" address/port pair against both the "2" and "1"
address/port pairs; you don't have to worry about which side the "a" or
"b" pairs correspond to.

If the NO_ADDR_B flag was specified to "find_conversation()", the
"addr_b" address will be treated as matching any "wildcarded" address;
if the NO_PORT_B flag was specified, the "port_b" port will be treated
as matching any "wildcarded" port.  If both flags are specified, i.e.
NO_ADDR_B|NO_PORT_B, the "addr_b" address will be treated as matching
any "wildcarded" address and the "port_b" port will be treated as
matching any "wildcarded" port.


2.2.1.4 The find_or_create_conversation function.

This convenience function will create find an existing conversation (by calling
find_conversation()) and, if a conversation does not already exist, create a
new conversation by calling conversation_new().

The find_or_create_conversation prototype:

	extern conversation_t *find_or_create_conversation(packet_info *pinfo);

Where:
	packet_info *pinfo = the packet_info structure

The frame number and the addresses necessary for find_conversation() and
conversation_new() are taken from the pinfo structure (as is commonly done)
and no 'options' are used.


2.2.1.5 The conversation_add_proto_data function.

Once you have created a conversation with conversation_new, you can
associate data with it using this function.

The conversation_add_proto_data prototype:

	void conversation_add_proto_data(conversation_t *conv, int proto,
		void *proto_data);

Where:
	conversation_t *conv = the conversation in question
	int proto	     = registered protocol number
	void *data	     = dissector data structure

"conversation" is the value returned by conversation_new.  "proto" is a
unique protocol number created with proto_register_protocol.  Protocols
are typically registered in the proto_register_XXXX section of your
dissector.  "data" is a pointer to the data you wish to associate with the
conversation.  "data" usually points to "se_alloc'd" memory; the
memory will be automatically freed each time a new dissection begins
and thus need not be managed (freed) by the dissector.
Using the protocol number allows several dissectors to
associate data with a given conversation.


2.2.1.6 The conversation_get_proto_data function.

After you have located a conversation with find_conversation, you can use
this function to retrieve any data associated with it.

The conversation_get_proto_data prototype:

	void *conversation_get_proto_data(conversation_t *conv, int proto);

Where:
	conversation_t *conv = the conversation in question
	int proto	     = registered protocol number

"conversation" is the conversation created with conversation_new.  "proto"
is a unique protocol number created with proto_register_protocol,
typically in the proto_register_XXXX portion of a dissector.  The function
returns a pointer to the data requested, or NULL if no data was found.


2.2.1.7 The conversation_delete_proto_data function.

After you are finished with a conversation, you can remove your association
with this function.  Please note that ONLY the conversation entry is
removed.  If you have allocated any memory for your data (other than with se_alloc),
 you must free it as well.

The conversation_delete_proto_data prototype:

	void conversation_delete_proto_data(conversation_t *conv, int proto);

Where:
	conversation_t *conv = the conversation in question
	int proto	     = registered protocol number

"conversation" is the conversation created with conversation_new.  "proto"
is a unique protocol number created with proto_register_protocol,
typically in the proto_register_XXXX portion of a dissector.

2.2.1.8 The conversation_set_dissector function

This function sets the protocol dissector to be invoked whenever
conversation parameters (addresses, port_types, ports, etc) are matched
during the dissection of a packet.

The conversation_set_dissector prototype:

        void conversation_set_dissector(conversation_t *conversation, const dissector_handle_t handle);

Where:
	conversation_t *conv = the conversation in question
        const dissector_handle_t handle = the dissector handle.


2.2.2 Using timestamps relative to the conversation

There is a framework to calculate timestamps relative to the start of the
conversation. First of all the timestamp of the first packet that has been
seen in the conversation must be kept in the protocol data to be able
to calculate the timestamp of the current packet relative to the start
of the conversation. The timestamp of the last packet that was seen in the
conversation should also be kept in the protocol data. This way the
delta time between the current packet and the previous packet in the
conversation can be calculated.

So add the following items to the struct that is used for the protocol data:

  nstime_t	ts_first;
  nstime_t	ts_prev;

The ts_prev value should only be set during the first run through the
packets (ie pinfo->fd->flags.visited is false).

Next step is to use the per-packet information (described in section 2.5)
to keep the calculated delta timestamp, as it can only be calculated
on the first run through the packets. This is because a packet can be
selected in random order once the whole file has been read.

After calculating the conversation timestamps, it is time to put them in
the appropriate columns with the function 'col_set_time' (described in
section 1.5.9). There are two columns for conversation timestamps:

COL_REL_CONV_TIME,  /* Relative time to beginning of conversation */
COL_DELTA_CONV_TIME,/* Delta time to last frame in conversation */

Last but not least, there MUST be a preference in each dissector that
uses conversation timestamps that makes it possible to enable and
disable the calculation of conversation timestamps. The main argument
for this is that a higher level conversation is able to overwrite
the values of lowel level conversations in these two columns. Being
able to actively select which protocols may overwrite the conversation
timestamp columns gives the user the power to control these columns.
(A second reason is that conversation timestamps use the per-packet
data structure which uses additional memory, which should be avoided
if these timestamps are not needed)

Have a look at the differences to packet-tcp.[ch] in SVN 22966 and
SVN 23058 to see the implementation of conversation timestamps for
the tcp-dissector.


2.2.3 The example conversation code using se_alloc'd memory.

For a conversation between two IP addresses and ports you can use this as an
example.  This example uses se_alloc() to allocate memory and stores the data
pointer in the conversation 'data' variable.

/************************ Global values ************************/

/* define your structure here */
typedef struct {

} my_entry_t;

/* Registered protocol number */
static int my_proto = -1;

/********************* in the dissector routine *********************/

/* the local variables in the dissector */

conversation_t *conversation;
my_entry_t *data_ptr;


/* look up the conversation */

conversation = find_conversation(pinfo->fd->num, &pinfo->src, &pinfo->dst,
	pinfo->ptype, pinfo->srcport, pinfo->destport, 0);

/* if conversation found get the data pointer that you stored */
if (conversation)
    data_ptr = (my_entry_t*)conversation_get_proto_data(conversation, my_proto);
else {

    /* new conversation create local data structure */

    data_ptr = se_alloc(sizeof(my_entry_t));

    /*** add your code here to setup the new data structure ***/

    /* create the conversation with your data pointer  */

    conversation = conversation_new(pinfo->fd->num,  &pinfo->src, &pinfo->dst, pinfo->ptype,
	    pinfo->srcport, pinfo->destport, 0);
    conversation_add_proto_data(conversation, my_proto, (void *)data_ptr);
}

/* at this point the conversation data is ready */

/***************** in the protocol register routine *****************/

my_proto = proto_register_protocol("My Protocol", "My Protocol", "my_proto");


2.2.4 An example conversation code that starts at a specific frame number.

Sometimes a dissector has determined that a new conversation is needed that
starts at a specific frame number, when a capture session encompasses multiple
conversation that reuse the same src/dest ip/port pairs. You can use the
conversation->setup_frame returned by find_conversation with
pinfo->fd->num to determine whether or not there already exists a conversation
that starts at the specific frame number.

/* in the dissector routine */

	conversation = find_conversation(pinfo->fd->num, &pinfo->src, &pinfo->dst,
	    pinfo->ptype, pinfo->srcport, pinfo->destport, 0);
	if (conversation == NULL || (conversation->setup_frame != pinfo->fd->num)) {
		/* It's not part of any conversation or the returned
		 * conversation->setup_frame doesn't match the current frame
		 * create a new one.
		 */
		conversation = conversation_new(pinfo->fd->num, &pinfo->src,
		    &pinfo->dst, pinfo->ptype, pinfo->srcport, pinfo->destport,
		    NULL, 0);
	}


2.2.5 The example conversation code using conversation index field.

Sometimes the conversation isn't enough to define a unique data storage
value for the network traffic.  For example if you are storing information
about requests carried in a conversation, the request may have an
identifier that is used to  define the request. In this case the
conversation and the identifier are required to find the data storage
pointer.  You can use the conversation data structure index value to
uniquely define the conversation.

See packet-afs.c for an example of how to use the conversation index.  In
this dissector multiple requests are sent in the same conversation.  To store
information for each request the dissector has an internal hash table based
upon the conversation index and values inside the request packets.


        /* in the dissector routine */

        /* to find a request value, first lookup conversation to get index */
        /* then used the conversation index, and request data to find data */
        /* in the local hash table */

	conversation = find_or_create_conversation(pinfo);

	request_key.conversation = conversation->index;
	request_key.service = pntohs(&rxh->serviceId);
	request_key.callnumber = pntohl(&rxh->callNumber);

	request_val = (struct afs_request_val *)g_hash_table_lookup(
		afs_request_hash, &request_key);

	/* only allocate a new hash element when it's a request */
	opcode = 0;
	if (!request_val && !reply)
	{
		new_request_key = se_alloc(sizeof(struct afs_request_key));
		*new_request_key = request_key;

		request_val = se_alloc(sizeof(struct afs_request_val));
		request_val -> opcode = pntohl(&afsh->opcode);
		opcode = request_val->opcode;

		g_hash_table_insert(afs_request_hash, new_request_key,
			request_val);
	}



2.3 Dynamic conversation dissector registration.


NOTE:   This sections assumes that all information is available to
	create a complete conversation, source port/address and
	destination port/address.  If either the destination port or
	address is know, see section 2.4 Dynamic server port dissector
	registration.

For protocols that negotiate a secondary port connection, for example
packet-msproxy.c, a conversation can install a dissector to handle
the secondary protocol dissection.  After the conversation is created
for the negotiated ports use the conversation_set_dissector to define
the dissection routine.
Before we create these conversations or assign a dissector to them we should
first check that the conversation does not already exist and if it exists
whether it is registered to our protocol or not.
We should do this because it is uncommon but it does happen that multiple
different protocols can use the same socketpair during different stages of
an application cycle. By keeping track of the frame number a conversation
was started in wireshark can still tell these different protocols apart.

The second argument to conversation_set_dissector is a dissector handle,
which is created with a call to create_dissector_handle or
register_dissector.

create_dissector_handle takes as arguments a pointer to the dissector
function and a protocol ID as returned by proto_register_protocol;
register_dissector takes as arguments a string giving a name for the
dissector, a pointer to the dissector function, and a protocol ID.

The protocol ID is the ID for the protocol dissected by the function.
The function will not be called if the protocol has been disabled by the
user; instead, the data for the protocol will be dissected as raw data.

An example -

/* the handle for the dynamic dissector *
static dissector_handle_t sub_dissector_handle;

/* prototype for the dynamic dissector */
static void sub_dissector(tvbuff_t *tvb, packet_info *pinfo,
                proto_tree *tree);

/* in the main protocol dissector, where the next dissector is setup */

/* if conversation has a data field, create it and load structure */

/* First check if a conversation already exists for this
	socketpair
*/
	conversation = find_conversation(pinfo->fd->num,
				&pinfo->src, &pinfo->dst, protocol,
				src_port, dst_port,  0);

/* If there is no such conversation, or if there is one but for
   someone else's protocol then we just create a new conversation
   and assign our protocol to it.
*/
	if ( (conversation == NULL) ||
	     (conversation->dissector_handle != sub_dissector_handle) ) {
            new_conv_info = se_alloc(sizeof(struct _new_conv_info));
            new_conv_info->data1 = value1;

/* create the conversation for the dynamic port */
	    conversation = conversation_new(pinfo->fd->num,
	        &pinfo->src, &pinfo->dst, protocol,
	        src_port, dst_port, new_conv_info, 0);

/* set the dissector for the new conversation */
	    conversation_set_dissector(conversation, sub_dissector_handle);
	}
		...

void
proto_register_PROTOABBREV(void)
{
	...

	sub_dissector_handle = create_dissector_handle(sub_dissector,
	    proto);

	...
}

2.4 Dynamic server port dissector registration.

NOTE: While this example used both NO_ADDR2 and NO_PORT2 to create a
conversation with only one port and address set, this isn't a
requirement.  Either the second port or the second address can be set
when the conversation is created.

For protocols that define a server address and port for a secondary
protocol, a conversation can be used to link a protocol dissector to
the server port and address.  The key is to create the new
conversation with the second address and port set to the "accept
any" values.

Some server applications can use the same port for different protocols during
different stages of a transaction. For example it might initially use SNMP
to perform some discovery and later switch to use TFTP using the same port.
In order to handle this properly we must first check whether such a
conversation already exists or not and if it exists we also check whether the
registered dissector_handle for that conversation is "our" dissector or not.
If not we create a new conversation on top of the previous one and set this new
conversation to use our protocol.
Since wireshark keeps track of the frame number where a conversation started
wireshark will still be able to keep the packets apart even though they do use
the same socketpair.
		(See packet-tftp.c and packet-snmp.c for examples of this)

There are two support routines that will allow the second port and/or
address to be set later.

conversation_set_port2( conversation_t *conv, guint32 port);
conversation_set_addr2( conversation_t *conv, address addr);

These routines will change the second address or port for the
conversation.  So, the server port conversation will be converted into a
more complete conversation definition.  Don't use these routines if you
want to create a conversation between the server and client and retain the
server port definition, you must create a new conversation.


An example -

/* the handle for the dynamic dissector *
static dissector_handle_t sub_dissector_handle;

	...

/* in the main protocol dissector, where the next dissector is setup */

/* if conversation has a data field, create it and load structure */

        new_conv_info = se_alloc(sizeof(struct _new_conv_info));
        new_conv_info->data1 = value1;

/* create the conversation for the dynamic server address and port 	*/
/* NOTE: The second address and port values don't matter because the	*/
/* NO_ADDR2 and NO_PORT2 options are set. 				*/

/* First check if a conversation already exists for this
	IP/protocol/port
*/
	conversation = find_conversation(pinfo->fd->num,
				&server_src_addr, 0, protocol,
				server_src_port, 0, NO_ADDR2 | NO_PORT_B);
/* If there is no such conversation, or if there is one but for
   someone else's protocol then we just create a new conversation
   and assign our protocol to it.
*/
	if ( (conversation == NULL) ||
	     (conversation->dissector_handle != sub_dissector_handle) ) {
	    conversation = conversation_new(pinfo->fd->num,
	    &server_src_addr, 0, protocol,
	    server_src_port, 0, new_conv_info, NO_ADDR2 | NO_PORT2);

/* set the dissector for the new conversation */
	    conversation_set_dissector(conversation, sub_dissector_handle);
	}

2.5 Per-packet information.

Information can be stored for each data packet that is processed by the
dissector.  The information is added with the p_add_proto_data function and
retrieved with the p_get_proto_data function.  The data pointers passed into
the p_add_proto_data are not managed by the proto_data routines. If you use
malloc or any other dynamic memory allocation scheme, you must release the
data when it isn't required.

void
p_add_proto_data(frame_data *fd, int proto, void *proto_data)
void *
p_get_proto_data(frame_data *fd, int proto)

Where:
	fd         - The fd pointer in the pinfo structure, pinfo->fd
	proto      - Protocol id returned by the proto_register_protocol call
	             during initialization
	proto_data - pointer to the dissector data.


2.6 User Preferences.

If the dissector has user options, there is support for adding these preferences
to a configuration dialog.

You must register the module with the preferences routine with -

       module_t *prefs_register_protocol(proto_id, void (*apply_cb)(void))
       or
       module_t *prefs_register_protocol_subtree(const char *subtree, int id,
              void (*apply_cb)(void));


Where: proto_id   - the value returned by "proto_register_protocol()" when
                    the protocol was registered.
       apply_cb   - Callback routine that is called when preferences are
                    applied. It may be NULL, which inhibits the callback.
       subtree    - grouping preferences tree node name (several protocols can
                    be grouped under one preferences subtree)

Then you can register the fields that can be configured by the user with these
routines -

	/* Register a preference with an unsigned integral value. */
	void prefs_register_uint_preference(module_t *module, const char *name,
	    const char *title, const char *description, guint base, guint *var);

	/* Register a preference with an Boolean value. */
	void prefs_register_bool_preference(module_t *module, const char *name,
	    const char *title, const char *description, gboolean *var);

	/* Register a preference with an enumerated value. */
	void prefs_register_enum_preference(module_t *module, const char *name,
	    const char *title, const char *description, gint *var,
	    const enum_val_t *enumvals, gboolean radio_buttons)

	/* Register a preference with a character-string value. */
	void prefs_register_string_preference(module_t *module, const char *name,
	    const char *title, const char *description, char **var)

	/* Register a preference with a range of unsigned integers (e.g.,
	 * "1-20,30-40").
	 */
	void prefs_register_range_preference(module_t *module, const char *name,
	    const char *title, const char *description, range_t *var,
	    guint32 max_value)

Where: module - Returned by the prefs_register_protocol routine
	 name     - This is appended to the name of the protocol, with a
		    "." between them, to construct a name that identifies
		    the field in the preference file; the name itself
		    should not include the protocol name, as the name in
		    the preference file will already have it. Make sure that
		    only lower-case ASCII letters, numbers, underscores and
		    dots appear in the preference name.
	 title    - Field title in the preferences dialog
	 description - Comments added to the preference file above the
		       preference value and shown as tooltip in the GUI, or NULL
	 var	  - pointer to the storage location that is updated when the
		    field is changed in the preference dialog box.  Note that
		    with string preferences the given pointer is overwritten
		    with a pointer to a new copy of the string during the
		    preference registration.  The passed-in string may be
		    freed, but you must keep another pointer to the string
		    in order to free it.
	 base	  - Base that the unsigned integer is expected to be in,
		    see strtoul(3).
	 enumvals - an array of enum_val_t structures.  This must be
		    NULL-terminated; the members of that structure are:

			a short name, to be used with the "-o" flag - it
			should not contain spaces or upper-case letters,
			so that it's easier to put in a command line;

			a description, which is used in the GUI (and
			which, for compatibility reasons, is currently
			what's written to the preferences file) - it can
			contain spaces, capital letters, punctuation,
			etc.;

			the numerical value corresponding to that name
			and description
	 radio_buttons - TRUE if the field is to be displayed in the
			 preferences dialog as a set of radio buttons,
			 FALSE if it is to be displayed as an option
			 menu
	 max_value - The maximum allowed value for a range (0 is the minimum).

An example from packet-beep.c -

  proto_beep = proto_register_protocol("Blocks Extensible Exchange Protocol",
				       "BEEP", "beep");

	...

  /* Register our configuration options for BEEP, particularly our port */

  beep_module = prefs_register_protocol(proto_beep, proto_reg_handoff_beep);

  prefs_register_uint_preference(beep_module, "tcp.port", "BEEP TCP Port",
				 "Set the port for BEEP messages (if other"
				 " than the default of 10288)",
				 10, &global_beep_tcp_port);

  prefs_register_bool_preference(beep_module, "strict_header_terminator",
				 "BEEP Header Requires CRLF",
				 "Specifies that BEEP requires CRLF as a "
				 "terminator, and not just CR or LF",
				 &global_beep_strict_term);

This will create preferences "beep.tcp.port" and
"beep.strict_header_terminator", the first of which is an unsigned
integer and the second of which is a Boolean.

Note that a warning will pop up if you've saved such preference to the
preference file and you subsequently take the code out. The way to make
a preference obsolete is to register it as such:

/* Register a preference that used to be supported but no longer is. */
	void prefs_register_obsolete_preference(module_t *module,
	    const char *name);

2.7 Reassembly/desegmentation for protocols running atop TCP.

There are two main ways of reassembling a Protocol Data Unit (PDU) which
spans across multiple TCP segments.  The first approach is simpler, but
assumes you are running atop of TCP when this occurs (but your dissector
might run atop of UDP, too, for example), and that your PDUs consist of a
fixed amount of data that includes enough information to determine the PDU
length, possibly followed by additional data.  The second method is more
generic but requires more code and is less efficient.

2.7.1 Using tcp_dissect_pdus().

For the first method, you register two different dissection methods, one
for the TCP case, and one for the other cases.  It is a good idea to
also have a dissect_PROTO_common function which will parse the generic
content that you can find in all PDUs which is called from
dissect_PROTO_tcp when the reassembly is complete and from
dissect_PROTO_udp (or dissect_PROTO_other).

To register the distinct dissector functions, consider the following
example, stolen from packet-dns.c:

	dissector_handle_t dns_udp_handle;
	dissector_handle_t dns_tcp_handle;
	dissector_handle_t mdns_udp_handle;

	dns_udp_handle = create_dissector_handle(dissect_dns_udp,
	    proto_dns);
	dns_tcp_handle = create_dissector_handle(dissect_dns_tcp,
	    proto_dns);
	mdns_udp_handle = create_dissector_handle(dissect_mdns_udp,
	    proto_dns);

	dissector_add_uint("udp.port", UDP_PORT_DNS, dns_udp_handle);
	dissector_add_uint("tcp.port", TCP_PORT_DNS, dns_tcp_handle);
	dissector_add_uint("udp.port", UDP_PORT_MDNS, mdns_udp_handle);
	dissector_add_uint("tcp.port", TCP_PORT_MDNS, dns_tcp_handle);

The dissect_dns_udp function does very little work and calls
dissect_dns_common, while dissect_dns_tcp calls tcp_dissect_pdus with a
reference to a callback which will be called with reassembled data:

	static void
	dissect_dns_tcp(tvbuff_t *tvb, packet_info *pinfo, proto_tree *tree)
	{
		tcp_dissect_pdus(tvb, pinfo, tree, dns_desegment, 2,
		    get_dns_pdu_len, dissect_dns_tcp_pdu);
	}

(The dissect_dns_tcp_pdu function acts similarly to dissect_dns_udp.)
The arguments to tcp_dissect_pdus are:

	the tvbuff pointer, packet_info pointer, and proto_tree pointer
	passed to the dissector;

	a gboolean flag indicating whether desegmentation is enabled for
	your protocol;

	the number of bytes of PDU data required to determine the length
	of the PDU;

	a routine that takes as arguments a packet_info pointer, a tvbuff
	pointer and an offset value representing the offset into the tvbuff
	at which a PDU begins and should return - *without* throwing an
	exception (it is guaranteed that the number of bytes specified by the
	previous argument to tcp_dissect_pdus is available, but more data
	might not be available, so don't refer to any data past that) - the
	total length of the PDU, in bytes;

	a routine that's passed a tvbuff pointer, packet_info pointer,
	and proto_tree pointer, with the tvbuff containing a
	possibly-reassembled PDU, and that should dissect that PDU.

2.7.2 Modifying the pinfo struct.

The second reassembly mode is preferred when the dissector cannot determine
how many bytes it will need to read in order to determine the size of a PDU.
It may also be useful if your dissector needs to support reassembly from
protocols other than TCP.

Your dissect_PROTO will initially be passed a tvbuff containing the payload of
the first packet. It should dissect as much data as it can, noting that it may
contain more than one complete PDU. If the end of the provided tvbuff coincides
with the end of a PDU then all is well and your dissector can just return as
normal. (If it is a new-style dissector, it should return the number of bytes
successfully processed.)

If the dissector discovers that the end of the tvbuff does /not/ coincide with
the end of a PDU, (ie, there is half of a PDU at the end of the tvbuff), it can
indicate this to the parent dissector, by updating the pinfo struct. The
desegment_offset field is the offset in the tvbuff at which the dissector will
continue processing when next called.  The desegment_len field should contain
the estimated number of additional bytes required for completing the PDU.  Next
time your dissect_PROTO is called, it will be passed a tvbuff composed of the
end of the data from the previous tvbuff together with desegment_len more bytes.

If the dissector cannot tell how many more bytes it will need, it should set
desegment_len=DESEGMENT_ONE_MORE_SEGMENT; it will then be called again as soon
as any more data becomes available. Dissectors should set the desegment_len to a
reasonable value when possible rather than always setting
DESEGMENT_ONE_MORE_SEGMENT as it will generally be more efficient. Also, you
*must not* set desegment_len=1 in this case, in the hope that you can change
your mind later: once you return a positive value from desegment_len, your PDU
boundary is set in stone.

static hf_register_info hf[] = {
    {&hf_cstring,
     {"C String", "c.string", FT_STRING, BASE_NONE, NULL, 0x0,
      NULL, HFILL}
     }
   };

/**
*   Dissect a buffer containing C strings.
*
*   @param  tvb     The buffer to dissect.
*   @param  pinfo   Packet Info.
*   @param  tree    The protocol tree.
**/
static void dissect_cstr(tvbuff_t * tvb, packet_info * pinfo, proto_tree * tree)
{
    guint offset = 0;
    while(offset < tvb_reported_length(tvb)) {
        gint available = tvb_reported_length_remaining(tvb, offset);
        gint len = tvb_strnlen(tvb, offset, available);

        if( -1 == len ) {
            /* we ran out of data: ask for more */
            pinfo->desegment_offset = offset;
            pinfo->desegment_len = DESEGMENT_ONE_MORE_SEGMENT;
            return;
        }

        col_set_str(pinfo->cinfo, COL_INFO, "C String");

        len += 1; /* Add one for the '\0' */

        if (tree) {
            proto_tree_add_item(tree, hf_cstring, tvb, offset, len,
				ENC_NA);
        }
        offset += (guint)len;
    }

    /* if we get here, then the end of the tvb coincided with the end of a
       string. Happy days. */
}

This simple dissector will repeatedly return DESEGMENT_ONE_MORE_SEGMENT
requesting more data until the tvbuff contains a complete C string. The C string
will then be added to the protocol tree. Note that there may be more
than one complete C string in the tvbuff, so the dissection is done in a
loop.

2.8 ptvcursors.

The ptvcursor API allows a simpler approach to writing dissectors for
simple protocols. The ptvcursor API works best for protocols whose fields
are static and whose format does not depend on the value of other fields.
However, even if only a portion of your protocol is statically defined,
then that portion could make use of ptvcursors.

The ptvcursor API lets you extract data from a tvbuff, and add it to a
protocol tree in one step. It also keeps track of the position in the
tvbuff so that you can extract data again without having to compute any
offsets --- hence the "cursor" name of the API.

The three steps for a simple protocol are:
    1. Create a new ptvcursor with ptvcursor_new()
    2. Add fields with multiple calls of ptvcursor_add()
    3. Delete the ptvcursor with ptvcursor_free()

ptvcursor offers the possibility to add subtrees in the tree as well. It can be
done in very simple steps :
    1. Create a new subtree with ptvcursor_push_subtree(). The old subtree is
       pushed in a stack and the new subtree will be used by ptvcursor.
    2. Add fields with multiple calls of ptvcursor_add(). The fields will be
       added in the new subtree created at the previous step.
    3. Pop the previous subtree with ptvcursor_pop_subtree(). The previous
       subtree is again used by ptvcursor.
Note that at the end of the parsing of a packet you must have popped each
subtree you pushed. If it's not the case, the dissector will generate an error.

To use the ptvcursor API, include the "ptvcursor.h" file. The PGM dissector
is an example of how to use it. You don't need to look at it as a guide;
instead, the API description here should be good enough.

2.8.1 ptvcursor API.

ptvcursor_t*
ptvcursor_new(proto_tree* tree, tvbuff_t* tvb, gint offset)
    This creates a new ptvcursor_t object for iterating over a tvbuff.
You must call this and use this ptvcursor_t object so you can use the
ptvcursor API.

proto_item*
ptvcursor_add(ptvcursor_t* ptvc, int hf, gint length, const guint encoding)
    This will extract 'length' bytes from the tvbuff and place it in
the proto_tree as field 'hf', which is a registered header_field. The
pointer to the proto_item that is created is passed back to you. Internally,
the ptvcursor advances its cursor so the next call to ptvcursor_add
starts where this call finished. The 'encoding' parameter is relevant for
certain type of fields (See above under proto_tree_add_item()).

proto_item*
ptvcursor_add_no_advance(ptvcursor_t* ptvc, int hf, gint length, const guint encoding)
    Like ptvcursor_add, but does not advance the internal cursor.

void
ptvcursor_advance(ptvcursor_t* ptvc, gint length)
    Advances the internal cursor without adding anything to the proto_tree.

void
ptvcursor_free(ptvcursor_t* ptvc)
    Frees the memory associated with the ptvcursor. You must call this
after your dissection with the ptvcursor API is completed.


proto_tree*
ptvcursor_push_subtree(ptvcursor_t* ptvc, proto_item* it, gint ett_subtree)
    Pushes the current subtree in the tree stack of the cursor, creates a new
one and sets this one as the working tree.

void
ptvcursor_pop_subtree(ptvcursor_t* ptvc);
    Pops a subtree in the tree stack of the cursor

proto_tree*
ptvcursor_add_with_subtree(ptvcursor_t* ptvc, int hfindex, gint length,
			    const guint encoding, gint ett_subtree);
    Adds an item to the tree and creates a subtree.
If the length is unknown, length may be defined as SUBTREE_UNDEFINED_LENGTH.
In this case, at the next pop, the item length will be equal to the advancement
of the cursor since the creation of the subtree.

proto_tree*
ptvcursor_add_text_with_subtree(ptvcursor_t* ptvc, gint length,
				gint ett_subtree, const char* format, ...);
    Add a text node to the tree and create a subtree.
If the length is unknown, length may be defined as SUBTREE_UNDEFINED_LENGTH.
In this case, at the next pop, the item length will be equal to the advancement
of the cursor since the creation of the subtree.

2.8.2 Miscellaneous functions.

tvbuff_t*
ptvcursor_tvbuff(ptvcursor_t* ptvc)
    Returns the tvbuff associated with the ptvcursor.

gint
ptvcursor_current_offset(ptvcursor_t* ptvc)
    Returns the current offset.

proto_tree*
ptvcursor_tree(ptvcursor_t* ptvc)
    Returns the proto_tree associated with the ptvcursor.

void
ptvcursor_set_tree(ptvcursor_t* ptvc, proto_tree *tree)
    Sets a new proto_tree for the ptvcursor.

proto_tree*
ptvcursor_set_subtree(ptvcursor_t* ptvc, proto_item* it, gint ett_subtree);
    Creates a subtree and adds it to the cursor as the working tree but does
not save the old working tree.