1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
|
<?xml version="1.0" encoding="iso-8859-1"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
<head>
<title>C++/Parser Mapping Getting Started Guide</title>
<meta name="copyright" content="© 2005-2014 Code Synthesis Tools CC"/>
<meta name="keywords" content="xsd,xml,schema,c++,mapping,data,binding,parser,validation"/>
<meta name="description" content="C++/Parser Mapping Getting Started Guide"/>
<link rel="stylesheet" type="text/css" href="../../../default.css" />
<style type="text/css">
pre {
padding : 0 0 0 0em;
margin : 0em 0em 0em 0;
font-size : 102%
}
body {
min-width: 48em;
}
h1 {
font-weight: bold;
font-size: 200%;
line-height: 1.2em;
}
h2 {
font-weight : bold;
font-size : 150%;
padding-top : 0.8em;
}
h3 {
font-size : 140%;
padding-top : 0.8em;
}
/* Adjust indentation for three levels. */
#container {
max-width: 48em;
}
#content {
padding: 0 0.1em 0 4em;
/*background-color: red;*/
}
#content h1 {
margin-left: -2.06em;
}
#content h2 {
margin-left: -1.33em;
}
/* Title page */
#titlepage {
padding: 2em 0 1em 0;
border-bottom: 1px solid black;
}
#titlepage .title {
font-weight: bold;
font-size: 200%;
text-align: center;
}
#titlepage #first-title {
padding: 1em 0 0.4em 0;
}
#titlepage #second-title {
padding: 0.4em 0 2em 0;
}
/* Lists */
ul.list li {
padding-top : 0.3em;
padding-bottom : 0.3em;
}
ol.steps {
padding-left : 1.8em;
}
ol.steps li {
padding-top : 0.3em;
padding-bottom : 0.3em;
}
div.img {
text-align: center;
padding: 2em 0 2em 0;
}
/* */
dl dt {
padding : 0.8em 0 0 0;
}
/* Built-in table */
#builtin {
margin: 2em 0 2em 0;
border-collapse : collapse;
border : 1px solid;
border-color : #000000;
font-size : 11px;
line-height : 14px;
}
#builtin th, #builtin td {
border: 1px solid;
padding : 0.9em 0.9em 0.7em 0.9em;
}
#builtin th {
background : #cde8f6;
}
#builtin td {
text-align: left;
}
/* XML Schema features table. */
#features {
margin: 2em 0 2em 0;
border-collapse : collapse;
border : 1px solid;
border-color : #000000;
font-size : 11px;
line-height : 14px;
}
#features th, #features td {
border: 1px solid;
padding : 0.6em 0.6em 0.6em 0.6em;
}
#features th {
background : #cde8f6;
}
#features td {
text-align: left;
}
/* TOC */
table.toc {
border-style : none;
border-collapse : separate;
border-spacing : 0;
margin : 0.2em 0 0.2em 0;
padding : 0 0 0 0;
}
table.toc tr {
padding : 0 0 0 0;
margin : 0 0 0 0;
}
table.toc * td, table.toc * th {
border-style : none;
margin : 0 0 0 0;
vertical-align : top;
}
table.toc * th {
font-weight : normal;
padding : 0em 0.1em 0em 0;
text-align : left;
white-space : nowrap;
}
table.toc * table.toc th {
padding-left : 1em;
}
table.toc * td {
padding : 0em 0 0em 0.7em;
text-align : left;
}
</style>
</head>
<body>
<div id="container">
<div id="content">
<div class="noprint">
<div id="titlepage">
<div class="title" id="first-title">C++/Parser Mapping</div>
<div class="title" id="second-title">Getting Started Guide</div>
<p>Copyright © 2005-2014 CODE SYNTHESIS TOOLS CC</p>
<p>Permission is granted to copy, distribute and/or modify this
document under the terms of the
<a href="http://www.codesynthesis.com/licenses/fdl-1.2.txt">GNU Free
Documentation License, version 1.2</a>; with no Invariant Sections,
no Front-Cover Texts and no Back-Cover Texts.
</p>
<p>This document is available in the following formats:
<a href="http://www.codesynthesis.com/projects/xsd/documentation/cxx/parser/guide/index.xhtml">XHTML</a>,
<a href="http://www.codesynthesis.com/projects/xsd/documentation/cxx/parser/guide/cxx-parser-guide.pdf">PDF</a>, and
<a href="http://www.codesynthesis.com/projects/xsd/documentation/cxx/parser/guide/cxx-parser-guide.ps">PostScript</a>.</p>
</div>
<h1>Table of Contents</h1>
<table class="toc">
<tr>
<th></th><td><a href="#0">Preface</a>
<table class="toc">
<tr><th></th><td><a href="#0.1">About This Document</a></td></tr>
<tr><th></th><td><a href="#0.2">More Information</a></td></tr>
</table>
</td>
</tr>
<tr>
<th>1</th><td><a href="#1">Introduction</a>
<table class="toc">
<tr><th>1.1</th><td><a href="#1.1">Mapping Overview</a></td></tr>
<tr><th>1.2</th><td><a href="#1.2">Benefits</a></td></tr>
</table>
</td>
</tr>
<tr>
<th>2</th><td><a href="#2">Hello World Example</a>
<table class="toc">
<tr><th>2.1</th><td><a href="#2.1">Writing XML Document and Schema</a></td></tr>
<tr><th>2.2</th><td><a href="#2.2">Translating Schema to C++</a></td></tr>
<tr><th>2.3</th><td><a href="#2.3">Implementing Application Logic</a></td></tr>
<tr><th>2.4</th><td><a href="#2.4">Compiling and Running</a></td></tr>
</table>
</td>
</tr>
<tr>
<th>3</th><td><a href="#3">Parser Skeletons</a>
<table class="toc">
<tr><th>3.1</th><td><a href="#3.1">Implementing the Gender Parser</a></td></tr>
<tr><th>3.2</th><td><a href="#3.2">Implementing the Person Parser</a></td></tr>
<tr><th>3.3</th><td><a href="#3.3">Implementing the People Parser</a></td></tr>
<tr><th>3.4</th><td><a href="#3.4">Connecting the Parsers Together</a></td></tr>
</table>
</td>
</tr>
<tr>
<th>4</th><td><a href="#4">Type Maps</a>
<table class="toc">
<tr><th>4.1</th><td><a href="#4.1">Object Model</a></td></tr>
<tr><th>4.2</th><td><a href="#4.2">Type Map File Format</a></td></tr>
<tr><th>4.3</th><td><a href="#4.3">Parser Implementations</a></td></tr>
</table>
</td>
</tr>
<tr>
<th>5</th><td><a href="#5">Mapping Configuration</a>
<table class="toc">
<tr><th>5.1</th><td><a href="#5.1">C++ Standard</a></td></tr>
<tr><th>5.2</th><td><a href="#5.2">Character Type and Encoding</a></td></tr>
<tr><th>5.3</th><td><a href="#5.3">Underlying XML Parser</a></td></tr>
<tr><th>5.4</th><td><a href="#5.4">XML Schema Validation</a></td></tr>
<tr><th>5.5</th><td><a href="#5.5">Support for Polymorphism</a></td></tr>
</table>
</td>
</tr>
<tr>
<th>6</th><td><a href="#6">Built-In XML Schema Type Parsers</a>
<table class="toc">
<tr><th>6.1</th><td><a href="#6.1"><code>QName</code> Parser</a></td></tr>
<tr><th>6.2</th><td><a href="#6.2"><code>NMTOKENS</code> and <code>IDREFS</code> Parsers</a></td></tr>
<tr><th>6.3</th><td><a href="#6.3"><code>base64Binary</code> and <code>hexBinary</code> Parsers</a></td></tr>
<tr><th>6.4</th><td><a href="#6.4">Time Zone Representation</a></td></tr>
<tr><th>6.5</th><td><a href="#6.5"><code>date</code> Parser</a></td></tr>
<tr><th>6.6</th><td><a href="#6.6"><code>dateTime</code> Parser</a></td></tr>
<tr><th>6.7</th><td><a href="#6.7"><code>duration</code> Parser</a></td></tr>
<tr><th>6.8</th><td><a href="#6.8"><code>gDay</code> Parser</a></td></tr>
<tr><th>6.9</th><td><a href="#6.9"><code>gMonth</code> Parser</a></td></tr>
<tr><th>6.10</th><td><a href="#6.10"><code>gMonthDay</code> Parser</a></td></tr>
<tr><th>6.11</th><td><a href="#6.11"><code>gYear</code> Parser</a></td></tr>
<tr><th>6.12</th><td><a href="#6.12"><code>gYearMonth</code> Parser</a></td></tr>
<tr><th>6.13</th><td><a href="#6.13"><code>time</code> Parser</a></td></tr>
</table>
</td>
</tr>
<tr>
<th>7</th><td><a href="#7">Document Parser and Error Handling</a>
<table class="toc">
<tr><th>7.1</th><td><a href="#7.1">Xerces-C++ Document Parser</a></td></tr>
<tr><th>7.2</th><td><a href="#7.2">Expat Document Parser</a></td></tr>
<tr><th>7.3</th><td><a href="#7.3">Error Handling</a></td></tr>
</table>
</td>
</tr>
<tr>
<th></th><td><a href="#A">Appendix A — Supported XML Schema Constructs</a></td>
</tr>
</table>
</div>
<h1><a name="0">Preface</a></h1>
<h2><a name="0.1">About This Document</a></h2>
<p>The goal of this document is to provide you with an understanding of
the C++/Parser programming model and allow you to efficiently evaluate
XSD against your project's technical requirements. As such, this
document is intended for C++ developers and software architects
who are looking for an XML processing solution. Prior experience
with XML and C++ is required to understand this document. Basic
understanding of XML Schema is advantageous but not expected
or required.
</p>
<h2><a name="0.2">More Information</a></h2>
<p>Beyond this guide, you may also find the following sources of
information useful:</p>
<ul class="list">
<li><a href="http://www.codesynthesis.com/projects/xsd/documentation/xsd.xhtml">XSD
Compiler Command Line Manual</a></li>
<li>The <code>examples/cxx/parser/</code> directory in the XSD
distribution contains a collection of examples and a README
file with an overview of each example.</li>
<li>The <code>README</code> file in the XSD distribution explains
how to compile the examples on various platforms.</li>
<li>The <a href="http://www.codesynthesis.com/mailman/listinfo/xsd-users">xsd-users</a>
mailing list is the place to ask technical questions about XSD and the C++/Parser mapping.
Furthermore, the <a href="http://www.codesynthesis.com/pipermail/xsd-users/">archives</a>
may already have answers to some of your questions.</li>
</ul>
<!-- Introduction -->
<h1><a name="1">1 Introduction</a></h1>
<p>Welcome to CodeSynthesis XSD and the C++/Parser mapping. XSD is a
cross-platform W3C XML Schema to C++ data binding compiler. C++/Parser
is a W3C XML Schema to C++ mapping that represents an XML vocabulary
as a set of parser skeletons which you can implement to perform XML
processing as required by your application logic.
</p>
<h2><a name="1.1">1.1 Mapping Overview</a></h2>
<p>The C++/Parser mapping provides event-driven, stream-oriented
XML parsing, XML Schema validation, and C++ data binding. It was
specifically designed and optimized for high performance and
small footprint. Based on the static analysis of the schemas, XSD
generates compact, highly-optimized hierarchical state machines
that combine data extraction, validation, and even dispatching
in a single step. As a result, the generated code is typically
2-10 times faster than general-purpose validating XML parsers
while maintaining the lowest static and dynamic memory footprints.
</p>
<p>To speed up application development, the C++/Parser mapping
can be instructed to generate sample parser implementations
and a test driver which can then be filled with the application
logic code. The mapping also provides a wide range of
mechanisms for controlling and customizing the generated code.</p>
<p>The next chapter shows how to create a simple application that uses
the C++/Parser mapping to parse, validate, and extract data from a
simple XML document. The following chapters show how to
use the C++/Parser mapping in more detail.</p>
<h2><a name="1.2">1.2 Benefits</a></h2>
<p>Traditional XML access APIs such as Document Object Model (DOM)
or Simple API for XML (SAX) have a number of drawbacks that
make them less suitable for creating robust and maintainable
XML processing applications. These drawbacks include:
</p>
<ul class="list">
<li>Generic representation of XML in terms of elements, attributes,
and text forces an application developer to write a substantial
amount of bridging code that identifies and transforms pieces
of information encoded in XML to a representation more suitable
for consumption by the application logic.</li>
<li>String-based flow control defers error detection to runtime.
It also reduces code readability and maintainability.</li>
<li>Lack of type safety because the data is represented
as text.</li>
<li>Resulting applications are hard to debug, change, and
maintain.</li>
</ul>
<p>In contrast, statically-typed, vocabulary-specific parser
skeletons produced by the C++/Parser mapping allow you to
operate in your domain terms instead of the generic elements,
attributes, and text. Static typing helps catch errors at
compile-time rather than at run-time. Automatic code generation
frees you for more interesting tasks (such as doing something
useful with the information stored in the XML documents) and
minimizes the effort needed to adapt your applications to
changes in the document structure. To summarize, the C++/Parser
mapping has the following key advantages over generic XML
access APIs:</p>
<ul class="list">
<li><b>Ease of use.</b> The generated code hides all the complexity
associated with recreating the document structure, maintaining the
dispatch state, and converting the data from the text representation
to data types suitable for manipulation by the application logic.
Parser skeletons also provide a convenient mechanism for building
custom in-memory representations.</li>
<li><b>Natural representation.</b> The generated parser skeletons
implement parser callbacks as virtual functions with names
corresponding to elements and attributes in XML. As a result,
you process the XML data using your domain vocabulary instead
of generic elements, attributes, and text.
</li>
<li><b>Concise code.</b> With a separate parser skeleton for each
XML Schema type, the application implementation is
simpler and thus easier to read and understand.</li>
<li><b>Safety.</b> The XML data is delivered to parser callbacks as
statically typed objects. The parser callbacks themselves are virtual
functions. This helps catch programming errors at compile-time
rather than at runtime.</li>
<li><b>Maintainability.</b> Automatic code generation minimizes the
effort needed to adapt the application to changes in the
document structure. With static typing, the C++ compiler
can pin-point the places in the application code that need to be
changed.</li>
<li><b>Efficiency.</b> The generated parser skeletons combine
data extraction, validation, and even dispatching in a single
step. This makes them much more efficient than traditional
architectures with separate stages for validation and data
extraction/dispatch.</li>
</ul>
<!-- Hello World Parser -->
<h1><a name="2">2 Hello World Example</a></h1>
<p>In this chapter we will examine how to parse a very simple XML
document using the XSD-generated C++/Parser skeletons.
The code presented in this chapter is based on the <code>hello</code>
example which can be found in the <code>examples/cxx/parser/</code>
directory of the XSD distribution.</p>
<h2><a name="2.1">2.1 Writing XML Document and Schema</a></h2>
<p>First, we need to get an idea about the structure
of the XML documents we are going to process. Our
<code>hello.xml</code>, for example, could look like this:</p>
<pre class="xml">
<?xml version="1.0"?>
<hello>
<greeting>Hello</greeting>
<name>sun</name>
<name>moon</name>
<name>world</name>
</hello>
</pre>
<p>Then we can write a description of the above XML in the
XML Schema language and save it into <code>hello.xsd</code>:</p>
<pre class="xml">
<?xml version="1.0"?>
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema">
<xs:complexType name="hello">
<xs:sequence>
<xs:element name="greeting" type="xs:string"/>
<xs:element name="name" type="xs:string" maxOccurs="unbounded"/>
</xs:sequence>
</xs:complexType>
<xs:element name="hello" type="hello"/>
</xs:schema>
</pre>
<p>Even if you are not familiar with XML Schema, it
should be easy to connect declarations in <code>hello.xsd</code>
to elements in <code>hello.xml</code>. The <code>hello</code> type
is defined as a sequence of the nested <code>greeting</code> and
<code>name</code> elements. Note that the term sequence in XML
Schema means that elements should appear in a particular order
as opposed to appearing multiple times. The <code>name</code>
element has its <code>maxOccurs</code> property set to
<code>unbounded</code> which means it can appear multiple times
in an XML document. Finally, the globally-defined <code>hello</code>
element prescribes the root element for our vocabulary. For an
easily-approachable introduction to XML Schema refer to
<a href="http://www.w3.org/TR/xmlschema-0/">XML Schema Part 0:
Primer</a>.</p>
<p>The above schema is a specification of our XML vocabulary; it tells
everybody what valid documents of our XML-based language should look
like. The next step is to compile this schema to generate
the object model and parsing functions.</p>
<h2><a name="2.2">2.2 Translating Schema to C++</a></h2>
<p>Now we are ready to translate our <code>hello.xsd</code> to C++ parser
skeletons. To do this we invoke the XSD compiler from a terminal
(UNIX) or a command prompt (Windows):
</p>
<pre class="terminal">
$ xsd cxx-parser --xml-parser expat hello.xsd
</pre>
<p>The <code>--xml-parser</code> option indicates that we want to
use Expat as the underlying XML parser (see <a href="#5.3">Section
5.3, "Underlying XML Parser"</a>). The XSD compiler produces two
C++ files: <code>hello-pskel.hxx</code> and <code>hello-pskel.cxx</code>.
The following code fragment is taken from <code>hello-pskel.hxx</code>;
it should give you an idea about what gets generated:
</p>
<pre class="c++">
class hello_pskel
{
public:
// Parser callbacks. Override them in your implementation.
//
virtual void
pre ();
virtual void
greeting (const std::string&);
virtual void
name (const std::string&);
virtual void
post_hello ();
// Parser construction API.
//
void
greeting_parser (xml_schema::string_pskel&);
void
name_parser (xml_schema::string_pskel&);
void
parsers (xml_schema::string_pskel& /* greeting */,
xml_schema::string_pskel& /* name */);
private:
...
};
</pre>
<p>The first four member functions shown above are called parser
callbacks. You would normally override them in your implementation
of the parser to do something useful. Let's go through all of
them one by one.</p>
<p>The <code>pre()</code> function is an initialization callback. It is
called when a new element of type <code>hello</code> is about
to be parsed. You would normally use this function to allocate a new
instance of the resulting type or clear accumulators that are used
to gather information during parsing. The default implementation
of this function does nothing.</p>
<p>The <code>post_hello()</code> function is a finalization callback. Its
name is constructed by adding the parser skeleton name to the
<code>post_</code> prefix. The finalization callback is called when
parsing of the element is complete and the result, if any, should
be returned. Note that in our case the return type of
<code>post_hello()</code> is <code>void</code> which means there
is nothing to return. More on parser return types later.
</p>
<p>You may be wondering why the finalization callback is called
<code>post_hello()</code> instead of <code>post()</code> just
like <code>pre()</code>. The reason for this is that
finalization callbacks can have different return types and
result in function signature clashes across inheritance
hierarchies. To prevent this the signatures of finalization
callbacks are made unique by adding the type name to their names.</p>
<p>The <code>greeting()</code> and <code>name()</code> functions are
called when the <code>greeting</code> and <code>name</code> elements
have been parsed, respectively. Their arguments are of type
<code>std::string</code> and contain the data extracted from XML.</p>
<p>The last three functions are for connecting parsers to each other.
For example, there is a predefined parser for built-in XML Schema type
<code>string</code> in the XSD runtime. We will be using
it to parse the contents of <code>greeting</code> and
<code>name</code> elements, as shown in the next section.</p>
<h2><a name="2.3">2.3 Implementing Application Logic</a></h2>
<p>At this point we have all the parts we need to do something useful
with the information stored in our XML document. The first step is
to implement the parser:
</p>
<pre class="c++">
#include <iostream>
#include "hello-pskel.hxx"
class hello_pimpl: public hello_pskel
{
public:
virtual void
greeting (const std::string& g)
{
greeting_ = g;
}
virtual void
name (const std::string& n)
{
std::cout << greeting_ << ", " << n << "!" << std::endl;
}
private:
std::string greeting_;
};
</pre>
<p>We left both <code>pre()</code> and <code>post_hello()</code> with the
default implementations; we don't have anything to initialize or
return. The rest is pretty straightforward: we store the greeting
in a member variable and later, when parsing names, use it to
say hello.</p>
<p>An observant reader my ask what happens if the <code>name</code>
element comes before <code>greeting</code>? Don't we need to
make sure <code>greeting_</code> was initialized and report
an error otherwise? The answer is no, we don't have to do
any of this. The <code>hello_pskel</code> parser skeleton
performs validation of XML according to the schema from which
it was generated. As a result, it will check the order
of the <code>greeting</code> and <code>name</code> elements
and report an error if it is violated.</p>
<p>Now it is time to put this parser implementation to work:</p>
<pre class="c++">
using namespace std;
int
main (int argc, char* argv[])
{
try
{
// Construct the parser.
//
xml_schema::string_pimpl string_p;
hello_pimpl hello_p;
hello_p.greeting_parser (string_p);
hello_p.name_parser (string_p);
// Parse the XML instance.
//
xml_schema::document doc_p (hello_p, "hello");
hello_p.pre ();
doc_p.parse (argv[1]);
hello_p.post_hello ();
}
catch (const xml_schema::exception& e)
{
cerr << e << endl;
return 1;
}
}
</pre>
<p>The first part of this code snippet instantiates individual parsers
and assembles them into a complete vocabulary parser.
<code>xml_schema::string_pimpl</code> is an implementation of a parser
for built-in XML Schema type <code>string</code>. It is provided by
the XSD runtime along with parsers for other built-in types (for
more information on the built-in parsers see <a href="#6">Chapter 6,
"Built-In XML Schema Type Parsers"</a>). We use <code>string_pimpl</code>
to parse the <code>greeting</code> and <code>name</code> elements as
indicated by the calls to <code>greeting_parser()</code> and
<code>name_parser()</code>.
</p>
<p>Then we instantiate a document parser (<code>doc_p</code>). The
first argument to its constructor is the parser for
the root element (<code>hello_p</code> in our case). The
second argument is the root element name.
</p>
<p>The final piece is the calls to <code>pre()</code>, <code>parse()</code>,
and <code>post_hello()</code>. The call to <code>parse()</code>
perform the actual XML parsing while the calls to <code>pre()</code> and
<code>post_hello()</code> make sure that the parser for the root
element can perform proper initialization and cleanup.</p>
<p>While our parser implementation and test driver are pretty small and
easy to write by hand, for bigger XML vocabularies it can be a
substantial effort. To help with this task XSD can automatically
generate sample parser implementations and a test driver from your
schemas. You can request the generation of a sample implementation with
empty function bodies by specifying the <code>--generate-noop-impl</code>
option. Or you can generate a sample implementation that prints the
data store in XML by using the <code>--generate-print-impl</code>
option. To request the generation of a test driver you can use the
<code>--generate-test-driver</code> option. For more information
on these options refer to the
<a href="http://www.codesynthesis.com/projects/xsd/documentation/xsd.xhtml">XSD
Compiler Command Line Manual</a>. The <code>'generated'</code> example
in the XSD distribution shows the sample implementation generation
feature in action.</p>
<h2><a name="2.4">2.4 Compiling and Running</a></h2>
<p>After saving all the parts from the previous section in
<code>driver.cxx</code>, we are ready to compile our first
application and run it on the test XML document. On a UNIX
system this can be done with the following commands:
</p>
<pre class="terminal">
$ c++ -I.../libxsd -c driver.cxx hello-pskel.cxx
$ c++ -o driver driver.o hello-pskel.o -lexpat
$ ./driver hello.xml
Hello, sun!
Hello, moon!
Hello, world!
</pre>
<p>Here <code>.../libxsd</code> represents the path to the
<code>libxsd</code> directory in the XSD distribution.
We can also test the error handling. To test XML well-formedness
checking, we can try to parse <code>hello-pskel.hxx</code>:</p>
<pre class="terminal">
$ ./driver hello-pskel.hxx
hello-pskel.hxx:1:0: not well-formed (invalid token)
</pre>
<p>We can also try to parse a valid XML but not from our
vocabulary, for example <code>hello.xsd</code>:</p>
<pre class="terminal">
$ ./driver hello.xsd
hello.xsd:2:0: expected element 'hello' instead of
'http://www.w3.org/2001/XMLSchema#schema'
</pre>
<!-- Chapater 3 -->
<h1><a name="3">3 Parser Skeletons</a></h1>
<p>As we have seen in the previous chapter, the XSD compiler generates
a parser skeleton class for each type defined in XML Schema. In
this chapter we will take a closer look at different functions
that comprise a parser skeleton as well as the way to connect
our implementations of these parser skeletons to create a complete
parser.</p>
<p>In this and subsequent chapters we will use the following schema
that describes a collection of person records. We save it in
<code>people.xsd</code>:</p>
<pre class="xml">
<?xml version="1.0"?>
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema">
<xs:simpleType name="gender">
<xs:restriction base="xs:string">
<xs:enumeration value="male"/>
<xs:enumeration value="female"/>
</xs:restriction>
</xs:simpleType>
<xs:complexType name="person">
<xs:sequence>
<xs:element name="first-name" type="xs:string"/>
<xs:element name="last-name" type="xs:string"/>
<xs:element name="gender" type="gender"/>
<xs:element name="age" type="xs:short"/>
</xs:sequence>
</xs:complexType>
<xs:complexType name="people">
<xs:sequence>
<xs:element name="person" type="person" maxOccurs="unbounded"/>
</xs:sequence>
</xs:complexType>
<xs:element name="people" type="people"/>
</xs:schema>
</pre>
<p>A sample XML instance to go along with this schema is saved
in <code>people.xml</code>:</p>
<pre class="xml">
<?xml version="1.0"?>
<people>
<person>
<first-name>John</first-name>
<last-name>Doe</last-name>
<gender>male</gender>
<age>32</age>
</person>
<person>
<first-name>Jane</first-name>
<last-name>Doe</last-name>
<gender>female</gender>
<age>28</age>
</person>
</people>
</pre>
<p>Compiling <code>people.xsd</code> with the XSD compiler results
in three parser skeletons being generated: <code>gender_pskel</code>,
<code>person_pskel</code>, and <code>people_pskel</code>. We are going
to examine and implement each of them in the subsequent sections.</p>
<h2><a name="3.1">3.1 Implementing the Gender Parser</a></h2>
<p>The generated <code>gender_pskel</code> parser skeleton looks like
this:</p>
<pre class="c++">
class gender_pskel: public virtual xml_schema::string_pskel
{
public:
// Parser callbacks. Override them in your implementation.
//
virtual void
pre ();
virtual void
post_gender ();
};
</pre>
<p>Notice that <code>gender_pskel</code> inherits from
<code>xml_schema::string_skel</code> which is a parser skeleton
for built-in XML Schema type <code>string</code> and is
predefined in the XSD runtime library. This is an example
of the general rule that parser skeletons follow: if a type
in XML Schema inherits from another then there will be an
equivalent inheritance between the corresponding parser
skeleton classes.</p>
<p>The <code>pre()</code> and <code>post_gender()</code> callbacks
should look familiar from the previous chapter. Let's now
implement the parser. Our implementation will simply print
the gender to <code>cout</code>:</p>
<pre class="c++">
class gender_pimpl: public gender_pskel,
public xml_schema::string_pimpl
{
public:
virtual void
post_gender ()
{
std::string s = post_string ();
cout << "gender: " << s << endl;
}
};
</pre>
<p>While the code is quite short, there is a lot going on. First,
notice that we are inheriting from <code>gender_pskel</code> <em>and</em>
from <code>xml_schema::string_pimpl</code>. We've encountered
<code>xml_schema::string_pimpl</code> already; it is an
implementation of the <code>xml_schema::string_pskel</code> parser
skeleton for built-in XML Schema type <code>string</code>.</p>
<p>This is another common theme in the C++/Parser programming model:
reusing implementations of the base parsers in the derived ones with
the C++ mixin idiom. In our case, <code>string_pimpl</code> will
do all the dirty work of extracting the data and we can just get
it at the end with the call to <code>post_string()</code>.</p>
<p>In case you are curious, here is what
<code>xml_schema::string_pskel</code> and
<code>xml_schema::string_pimpl</code> look like:</p>
<pre class="c++">
namespace xml_schema
{
class string_pskel: public simple_content
{
public:
virtual std::string
post_string () = 0;
};
class string_pimpl: public virtual string_pskel
{
public:
virtual void
_pre ();
virtual void
_characters (const xml_schema::ro_string&);
virtual std::string
post_string ();
protected:
std::string str_;
};
}
</pre>
<p>There are three new pieces in this code that we haven't seen yet.
They are the <code>simple_content</code> class as well as
the <code>_pre()</code> and <code>_characters()</code> functions.
The <code>simple_content</code> class is defined in the XSD
runtime and is a base class for all parser skeletons that conform
to the simple content model in XML Schema. Types with the
simple content model cannot have nested elements—only text
and attributes. There is also the <code>complex_content</code>
class which corresponds to the complex content mode (types with
nested elements, for example, <code>person</code> from
<code>people.xsd</code>).</p>
<p>The <code>_pre()</code> function is a parser callback. Remember we
talked about the <code>pre()</code> and <code>post_*()</code> callbacks
in the previous chapter? There are actually two more callbacks
with similar roles: <code>_pre()</code> and <code>_post ()</code>.
As a result, each parser skeleton has four special callbacks:</p>
<pre class="c++">
virtual void
pre ();
virtual void
_pre ();
virtual void
_post ();
virtual void
post_name ();
</pre>
<p><code>pre()</code> and <code>_pre()</code> are initialization
callbacks. They get called in that order before a new instance of the type
is about to be parsed. The difference between <code>pre()</code> and
<code>_pre()</code> is conventional: <code>pre()</code> can
be completely overridden by a derived parser. The derived
parser can also override <code>_pre()</code> but has to always call
the original version. This allows you to partition initialization
into customizable and required parts.</p>
<p>Similarly, <code>_post()</code> and <code>post_name()</code> are
finalization callbacks with exactly the same semantics:
<code>post_name()</code> can be completely overridden by the derived
parser while the original <code>_post()</code> should always be called.
</p>
<p>The final bit we need to discuss in this section is the
<code>_characters()</code> function. As you might have guessed, it
is also a callback. A low-level one that delivers raw character content
for the type being parsed. You will seldom need to use this callback
directly. Using implementations for the built-in parsers provided by
the XSD runtime is usually a simpler and more convenient
alternative.</p>
<p>At this point you might be wondering why some <code>post_*()</code>
callbacks, for example <code>post_string()</code>, return some data
while others, for example <code>post_gender()</code>, have
<code>void</code> as a return type. This is a valid concern
and it will be addressed in the next chapter.</p>
<h2><a name="3.2">3.2 Implementing the Person Parser</a></h2>
<p>The generated <code>person_pskel</code> parser skeleton looks like
this:</p>
<pre class="c++">
class person_pskel: public xml_schema::complex_content
{
public:
// Parser callbacks. Override them in your implementation.
//
virtual void
pre ();
virtual void
first_name (const std::string&);
virtual void
last_name (const std::string&);
virtual void
gender ();
virtual void
age (short);
virtual void
post_person ();
// Parser construction API.
//
void
first_name_parser (xml_schema::string_pskel&);
void
last_name_parser (xml_schema::string_pskel&);
void
gender_parser (gender_pskel&);
void
age_parser (xml_schema::short_pskel&);
void
parsers (xml_schema::string_pskel& /* first-name */,
xml_schema::string_pskel& /* last-name */,
gender_pskel& /* gender */,
xml_schema::short_pskel& /* age */);
};
</pre>
<p>As you can see, we have a parser callback for each of the nested
elements found in the <code>person</code> XML Schema type.
The implementation of this parser is straightforward:</p>
<pre class="c++">
class person_pimpl: public person_pskel
{
public:
virtual void
first_name (const std::string& n)
{
cout << "first: " << f << endl;
}
virtual void
last_name (const std::string& l)
{
cout << "last: " << l << endl;
}
virtual void
age (short a)
{
cout << "age: " << a << endl;
}
};
</pre>
<p>Notice that we didn't override the <code>gender()</code> callback
because all the printing is done by <code>gender_pimpl</code>.</p>
<h2><a name="3.3">3.3 Implementing the People Parser</a></h2>
<p>The generated <code>people_pskel</code> parser skeleton looks like
this:</p>
<pre class="c++">
class people_pskel: public xml_schema::complex_content
{
public:
// Parser callbacks. Override them in your implementation.
//
virtual void
pre ();
virtual void
person ();
virtual void
post_people ();
// Parser construction API.
//
void
person_parser (person_pskel&);
void
parsers (person_pskel& /* person */);
};
</pre>
<p>The <code>person()</code> callback will be called after parsing each
<code>person</code> element. While <code>person_pimpl</code> does
all the printing, one useful thing we can do in this callback is to
print an extra newline after each person record so that our
output is more readable:</p>
<pre class="c++">
class people_pimpl: public people_pskel
{
public:
virtual void
person ()
{
cout << endl;
}
};
</pre>
<p>Now it is time to put everything together.</p>
<h2><a name="3.4">3.4 Connecting the Parsers Together</a></h2>
<p>At this point we have all the individual parsers implemented
and can proceed to assemble them into a complete parser
for our XML vocabulary. The first step is to instantiate
all the individual parsers that we will need:</p>
<pre class="c++">
xml_schema::short_pimpl short_p;
xml_schema::string_pimpl string_p;
gender_pimpl gender_p;
person_pimpl person_p;
people_pimpl people_p;
</pre>
<p>Notice that our schema uses two built-in XML Schema types:
<code>string</code> for the <code>first-name</code> and
<code>last-name</code> elements as well as <code>short</code>
for <code>age</code>. We will use predefined parsers that
come with the XSD runtime to handle these types. The next
step is to connect all the individual parsers. We do this
with the help of functions defined in the parser
skeletons and marked with the "Parser Construction API"
comment. One way to do it is to connect each individual
parser by calling the <code>*_parser()</code> functions:</p>
<pre class="c++">
person_p.first_name_parser (string_p);
person_p.last_name_parser (string_p);
person_p.gender_parser (gender_p);
person_p.age_parser (short_p);
people_p.person_parser (person_p);
</pre>
<p>You might be wondering what happens if you do not provide
a parser by not calling one of the <code>*_parser()</code> functions.
In that case the corresponding XML content will be skipped,
including validation. This is an efficient way to ignore parts
of the document that you are not interested in.</p>
<p>An alternative, shorter, way to connect the parsers is by using
the <code>parsers()</code> functions which connects all the parsers
for a given type at once:</p>
<pre class="c++">
person_p.parsers (string_p, string_p, gender_p, short_p);
people_p.parsers (person_p);
</pre>
<p>The following figure illustrates the resulting connections. Notice
the correspondence between return types of the <code>post_*()</code>
functions and argument types of element callbacks that are connected
by the arrows.</p>
<!-- align=center is needed for html2ps -->
<div class="img" align="center"><img src="figure-1.png"/></div>
<p>The last step is the construction of the document parser and
invocation of the complete parser on our sample XML instance:</p>
<pre class="c++">
xml_schema::document doc_p (people_p, "people");
people_p.pre ();
doc_p.parse ("people.xml");
people_p.post_people ();
</pre>
<p>Let's consider <code>xml_schema::document</code> in
more detail. While the exact definition of this class
varies depending on the underlying parser selected,
here is the common part:</p>
<pre class="c++">
namespace xml_schema
{
class document
{
public:
document (xml_schema::parser_base&,
const std::string& root_element_name,
bool polymorphic = false);
document (xml_schema::parser_base&,
const std::string& root_element_namespace,
const std::string& root_element_name,
bool polymorphic = false);
void
parse (const std::string& file);
void
parse (std::istream&);
...
};
}
</pre>
<p><code>xml_schema::document</code> is a root parser for
the vocabulary. The first argument to its constructors is the
parser for the type of the root element (<code>people_impl</code>
in our case). Because a type parser is only concerned with
the element's content and not with the element's name, we need
to specify the root element's name somewhere. That's
what is passed as the second and third arguments to the
<code>document</code>'s constructors.</p>
<p>There are also two overloaded <code>parse()</code> functions
defined in the <code>document</code> class (there are actually
more but the others are specific to the underlying XML parser).
The first version parses a local file identified by a name. The
second version reads the data from an input stream. For more
information on the <code>xml_schema::document</code> class
refer to <a href="#7">Chapter 7, "Document Parser and Error
Handling"</a>.</p>
<p>Let's now consider a step-by-step list of actions that happen
as we parse through <code>people.xml</code>. The content of
<code>people.xml</code> is repeated below for convenience.</p>
<pre class="xml">
<?xml version="1.0"?>
<people>
<person>
<first-name>John</first-name>
<last-name>Doe</last-name>
<gender>male</gender>
<age>32</age>
</person>
<person>
<first-name>Jane</first-name>
<last-name>Doe</last-name>
<gender>female</gender>
<age>28</age>
</person>
</people>
</pre>
<ol class="steps">
<li><code>people_p.pre()</code> is called from
<code>main()</code>. We did not provide any implementation
for this callback so this call is a no-op.</li>
<li><code>doc_p.parse("people.xml")</code> is called from
<code>main()</code>. The parser opens the file and starts
parsing its content.</li>
<li>The parser encounters the root element. <code>doc_p</code>
verifies that the root element is correct and calls
<code>_pre()</code> on <code>people_p</code> which is also
a no-op. Parsing is now delegated to <code>people_p</code>.</li>
<li>The parser encounters the <code>person</code> element.
<code>people_p</code> determines that <code>person_p</code>
is responsible for parsing this element. <code>pre()</code>
and <code>_pre()</code> callbacks are called on <code>person_p</code>.
Parsing is now delegated to <code>person_p</code>.</li>
<li>The parser encounters the <code>first-name</code> element.
<code>person_p</code> determines that <code>string_p</code>
is responsible for parsing this element. <code>pre()</code>
and <code>_pre()</code> callbacks are called on <code>string_p</code>.
Parsing is now delegated to <code>string_p</code>.</li>
<li>The parser encounters character content consisting of
<code>"John"</code>. The <code>_characters()</code> callback is
called on <code>string_p</code>.</li>
<li>The parser encounters the end of <code>first-name</code>
element. The <code>_post()</code> and <code>post_string()</code>
callbacks are called on <code>string_p</code>. The
<code>first_name()</code> callback is called on <code>person_p</code>
with the return value of <code>post_string()</code>. The
<code>first_name()</code> implementation prints
<code>"first: John"</code> to <code>cout</code>.
Parsing is now returned to <code>person_p</code>.</li>
<li>Steps analogous to 5-7 are performed for the <code>last-name</code>,
<code>gender</code>, and <code>age</code> elements.</li>
<li>The parser encounters the end of <code>person</code>
element. The <code>_post()</code> and <code>post_person()</code>
callbacks are called on <code>person_p</code>. The
<code>person()</code> callback is called on <code>people_p</code>.
The <code>person()</code> implementation prints a new line
to <code>cout</code>. Parsing is now returned to
<code>people_p</code>.</li>
<li>Steps 4-9 are performed for the second <code>person</code>
element.</li>
<li>The parser encounters the end of <code>people</code>
element. The <code>_post()</code> callback is called on
<code>people_p</code>. The <code>doc_p.parse("people.xml")</code>
call returns to <code>main()</code>.</li>
<li><code>people_p.post_people()</code> is called from
<code>main()</code> which is a no-op.</li>
</ol>
<!-- Chpater 4 -->
<h1><a name="4">4 Type Maps</a></h1>
<p>There are many useful things you can do inside parser callbacks as they
are right now. There are, however, times when you want to propagate
some information from one parser to another or to the caller of the
parser. One common task that would greatly benefit from such a
possibility is building a tree-like in-memory object model of the
data stored in XML. During execution, each individual sub-parser
would create a sub-tree and return it to its <em>parent</em> parser
which can then incorporate this sub-tree into the whole tree.</p>
<p>In this chapter we will discuss the mechanisms offered by the
C++/Parser mapping for returning information from individual
parsers and see how to use them to build an object model
of our people vocabulary.</p>
<h2><a name="4.1">4.1 Object Model</a></h2>
<p>An object model for our person record example could
look like this (saved in the <code>people.hxx</code> file):</p>
<pre class="c++">
#include <string>
#include <vector>
enum gender
{
male,
female
};
class person
{
public:
person (const std::string& first,
const std::string& last,
::gender gender,
short age)
: first_ (first), last_ (last),
gender_ (gender), age_ (age)
{
}
const std::string&
first () const
{
return first_;
}
const std::string&
last () const
{
return last_;
}
::gender
gender () const
{
return gender_;
}
short
age () const
{
return age_;
}
private:
std::string first_;
std::string last_;
::gender gender_;
short age_;
};
typedef std::vector<person> people;
</pre>
<p>While it is clear which parser is responsible for which part of
the object model, it is not exactly clear how, for
example, <code>gender_pimpl</code> will deliver <code>gender</code>
to <code>person_pimpl</code>. You might have noticed that
<code>string_pimpl</code> manages to deliver its value to the
<code>first_name()</code> callback of <code>person_pimpl</code>. Let's
see how we can utilize the same mechanism to propagate our
own data.</p>
<p>There is a way to tell the XSD compiler that you want to
exchange data between parsers. More precisely, for each
type defined in XML Schema, you can tell the compiler two things.
First, the return type of the <code>post_*()</code> callback
in the parser skeleton generated for this type. And, second,
the argument type for callbacks corresponding to elements and
attributes of this type. For example, for XML Schema type
<code>gender</code> we can specify the return type for
<code>post_gender()</code> in the <code>gender_pskel</code>
skeleton and the argument type for the <code>gender()</code> callback
in the <code>person_pskel</code> skeleton. As you might have guessed,
the generated code will then pass the return value from the
<code>post_*()</code> callback as an argument to the element or
attribute callback.</p>
<p>The way to tell the XSD compiler about these XML Schema to
C++ mappings is with type map files. Here is a simple type
map for the <code>gender</code> type from the previous paragraph:</p>
<pre class="type-map">
include "people.hxx";
gender ::gender ::gender;
</pre>
<p>The first line indicates that the generated code must include
<code>people.hxx</code> in order to get the definition for the
<code>gender</code> type. The second line specifies that both
argument and return types for the <code>gender</code>
XML Schema type should be the <code>::gender</code> C++ enum
(we use fully-qualified C++ names to avoid name clashes).
The next section will describe the type map format in detail.
We save this type map in <code>people.map</code> and
then translate our schemas with the <code>--type-map</code>
option to let the XSD compiler know about our type map:</p>
<pre class="terminal">
$ xsd cxx-parser --type-map people.map people.xsd
</pre>
<p>If we now look at the generated <code>people-pskel.hxx</code>,
we will see the following changes in the <code>gender_pskel</code> and
<code>person_pskel</code> skeletons:</p>
<pre class="c++">
#include "people.hxx"
class gender_pskel: public virtual xml_schema::string_pskel
{
virtual ::gender
post_gender () = 0;
...
};
class person_pskel: public xml_schema::complex_content
{
virtual void
gender (::gender);
...
};
</pre>
<p>Notice that <code>#include "people.hxx"</code> was added to
the generated header file from the type map to provide the
definition for the <code>gender</code> enum.</p>
<h2><a name="4.2">4.2 Type Map File Format</a></h2>
<p>Type map files are used to define a mapping between XML Schema
and C++ types. The compiler uses this information
to determine return types of <code>post_*()</code>
callbacks in parser skeletons corresponding to XML Schema
types as well as argument types for callbacks corresponding
to elements and attributes of these types.</p>
<p>The compiler has a set of predefined mapping rules that map
the built-in XML Schema types to suitable C++ types (discussed
below) and all other types to <code>void</code>.
By providing your own type maps you can override these predefined
rules. The format of the type map file is presented below:
</p>
<pre class="type-map">
namespace <schema-namespace> [<cxx-namespace>]
{
(include <file-name>;)*
([type] <schema-type> <cxx-ret-type> [<cxx-arg-type>];)*
}
</pre>
<p>Both <code><i><schema-namespace></i></code> and
<code><i><schema-type></i></code> are regex patterns while
<code><i><cxx-namespace></i></code>,
<code><i><cxx-ret-type></i></code>, and
<code><i><cxx-arg-type></i></code> are regex pattern
substitutions. All names can be optionally enclosed in
<code>" "</code>, for example, to include white-spaces.</p>
<p><code><i><schema-namespace></i></code> determines XML
Schema namespace. Optional <code><i><cxx-namespace></i></code>
is prefixed to every C++ type name in this namespace declaration.
<code><i><cxx-ret-type></i></code> is a C++ type name that is
used as a return type for the <code>post_*()</code> callback.
Optional <code><i><cxx-arg-type></i></code> is an argument
type for callbacks corresponding to elements and attributes
of this type. If <code><i><cxx-arg-type></i></code> is not
specified, it defaults to <code><i><cxx-ret-type></i></code>
if <code><i><cxx-ret-type></i></code> ends with <code>*</code> or
<code>&</code> (that is, it is a pointer or a reference) and
<code>const <i><cxx-ret-type></i>&</code>
otherwise.
<code><i><file-name></i></code> is a file name either in the
<code>" "</code> or <code>< ></code> format
and is added with the <code>#include</code> directive to
the generated code.</p>
<p>The <code><b>#</b></code> character starts a comment that ends
with a new line or end of file. To specify a name that contains
<code><b>#</b></code> enclose it in <code><b>" "</b></code>.
For example:</p>
<pre>
namespace http://www.example.com/xmlns/my my
{
include "my.hxx";
# Pass apples by value.
#
apple apple;
# Pass oranges as pointers.
#
orange orange_t*;
}
</pre>
<p>In the example above, for the
<code>http://www.example.com/xmlns/my#orange</code>
XML Schema type, the <code>my::orange_t*</code> C++ type will
be used as both return and argument types.</p>
<p>Several namespace declarations can be specified in a single
file. The namespace declaration can also be completely
omitted to map types in a schema without a namespace. For
instance:</p>
<pre class="type-map">
include "my.hxx";
apple apple;
namespace http://www.example.com/xmlns/my
{
orange "const orange_t*";
}
</pre>
<p>The compiler has a number of predefined mapping rules for
the built-in XML Schema types which can be presented as the
following map files. The string-based XML Schema types are
mapped to either <code>std::string</code> or
<code>std::wstring</code> depending on the character type
selected (see <a href="#5.2"> Section 5.2, "Character Type and
Encoding"</a> for more information). The binary XML Schema
types are mapped to either <code>std::auto_ptr<xml_schema::buffer></code>
or <code>std::unique_ptr<xml_schema::buffer></code>
depending on the C++ standard selected (C++98 or C++11,
respectively; refer to the <code>--std</code> XSD compiler
command line option for details).</p>
<pre class="type-map">
namespace http://www.w3.org/2001/XMLSchema
{
boolean bool bool;
byte "signed char" "signed char";
unsignedByte "unsigned char" "unsigned char";
short short short;
unsignedShort "unsigned short" "unsigned short";
int int int;
unsignedInt "unsigned int" "unsigned int";
long "long long" "long long";
unsignedLong "unsigned long long" "unsigned long long";
integer "long long" "long long";
negativeInteger "long long" "long long";
nonPositiveInteger "long long" "long long";
positiveInteger "unsigned long long" "unsigned long long";
nonNegativeInteger "unsigned long long" "unsigned long long";
float float float;
double double double;
decimal double double;
string std::string;
normalizedString std::string;
token std::string;
Name std::string;
NMTOKEN std::string;
NCName std::string;
ID std::string;
IDREF std::string;
language std::string;
anyURI std::string;
NMTOKENS xml_schema::string_sequence;
IDREFS xml_schema::string_sequence;
QName xml_schema::qname;
base64Binary std::[auto|unique]_ptr<xml_schema::buffer>
std::[auto|unique]_ptr<xml_schema::buffer>;
hexBinary std::[auto|unique]_ptr<xml_schema::buffer>
std::[auto|unique]_ptr<xml_schema::buffer>;
date xml_schema::date;
dateTime xml_schema::date_time;
duration xml_schema::duration;
gDay xml_schema::gday;
gMonth xml_schema::gmonth;
gMonthDay xml_schema::gmonth_day;
gYear xml_schema::gyear;
gYearMonth xml_schema::gyear_month;
time xml_schema::time;
}
</pre>
<p>For more information about the mapping of the built-in XML Schema types
to C++ types refer to <a href="#6">Chapter 6, "Built-In XML Schema Type
Parsers"</a>. The last predefined rule maps anything that wasn't
mapped by previous rules to <code>void</code>:</p>
<pre class="type-map">
namespace .*
{
.* void void;
}
</pre>
<p>When you provide your own type maps with the
<code>--type-map</code> option, they are evaluated first. This
allows you to selectively override any of the predefined rules.
Note also that if you change the mapping
of a built-in XML Schema type then it becomes your responsibility
to provide the corresponding parser skeleton and implementation
in the <code>xml_schema</code> namespace. You can include the
custom definitions into the generated header file using the
<code>--hxx-prologue-*</code> options.</p>
<h2><a name="4.3">4.3 Parser Implementations</a></h2>
<p>With the knowledge from the previous section, we can proceed
with creating a type map that maps types in the <code>people.xsd</code>
schema to our object model classes in
<code>people.hxx</code>. In fact, we already have the beginning
of our type map file in <code>people.map</code>. Let's extend
it with the rest of the types:</p>
<pre class="type-map">
include "people.hxx";
gender ::gender ::gender;
person ::person;
people ::people;
</pre>
<p>There are a few things to note about this type map. We did not
provide the argument types for <code>person</code> and
<code>people</code> because the default constant reference is
exactly what we need. We also did not provide any mappings
for built-in XML Schema types <code>string</code> and
<code>short</code> because they are handled by the predefined
rules and we are happy with the result. Note also that
all C++ types are fully qualified. This is done to avoid
potential name conflicts in the generated code. Now we can
recompile our schema and move on to implementing the parsers:</p>
<pre class="terminal">
$ xsd cxx-parser --xml-parser expat --type-map people.map people.xsd
</pre>
<p>Here is the implementation of our three parsers in full. One
way to save typing when implementing your own parsers is
to open the generated code and copy the signatures of parser
callbacks into your code. Or you could always auto generate the
sample implementations and fill them with your code.</p>
<pre class="c++">
#include "people-pskel.hxx"
class gender_pimpl: public gender_pskel,
public xml_schema::string_pimpl
{
public:
virtual ::gender
post_gender ()
{
return post_string () == "male" ? male : female;
}
};
class person_pimpl: public person_pskel
{
public:
virtual void
first_name (const std::string& f)
{
first_ = f;
}
virtual void
last_name (const std::string& l)
{
last_ = l;
}
virtual void
gender (::gender g)
{
gender_ = g;
}
virtual void
age (short a)
{
age_ = a;
}
virtual ::person
post_person ()
{
return ::person (first_, last_, gender_, age_);
}
private:
std::string first_;
std::string last_;
::gender gender_;
short age_;
};
class people_pimpl: public people_pskel
{
public:
virtual void
person (const ::person& p)
{
people_.push_back (p);
}
virtual ::people
post_people ()
{
::people r;
r.swap (people_);
return r;
}
private:
::people people_;
};
</pre>
<p>This code fragment should look familiar by now. Just note that
all the <code>post_*()</code> callbacks now have return types instead
of <code>void</code>. Here is the implementation of the test
driver for this example:</p>
<pre class="c++">
#include <iostream>
using namespace std;
int
main (int argc, char* argv[])
{
// Construct the parser.
//
xml_schema::short_pimpl short_p;
xml_schema::string_pimpl string_p;
gender_pimpl gender_p;
person_pimpl person_p;
people_pimpl people_p;
person_p.parsers (string_p, string_p, gender_p, short_p);
people_p.parsers (person_p);
// Parse the document to obtain the object model.
//
xml_schema::document doc_p (people_p, "people");
people_p.pre ();
doc_p.parse (argv[1]);
people ppl = people_p.post_people ();
// Print the object model.
//
for (people::iterator i (ppl.begin ()); i != ppl.end (); ++i)
{
cout << "first: " << i->first () << endl
<< "last: " << i->last () << endl
<< "gender: " << (i->gender () == male ? "male" : "female") << endl
<< "age: " << i->age () << endl
<< endl;
}
}
</pre>
<p>The parser creation and assembly part is exactly the same as in
the previous chapter. The parsing part is a bit different:
<code>post_people()</code> now has a return value which is the
complete object model. We store it in the
<code>ppl</code> variable. The last bit of the code simply iterates
over the <code>people</code> vector and prints the information
for each person. We save the last two code fragments to
<code>driver.cxx</code> and proceed to compile and test
our new application:</p>
<pre class="terminal">
$ c++ -I.../libxsd -c driver.cxx people-pskel.cxx
$ c++ -o driver driver.o people-pskel.o -lexpat
$ ./driver people.xml
first: John
last: Doe
gender: male
age: 32
first: Jane
last: Doe
gender: female
age: 28
</pre>
<!-- Mapping Configuration -->
<h1><a name="5">5 Mapping Configuration</a></h1>
<p>The C++/Parser mapping has a number of configuration parameters that
determine the overall properties and behavior of the generated code.
Configuration parameters are specified with the XSD command line
options and include the C++ standard, the character type that is used
by the generated code, the underlying XML parser, whether the XML Schema
validation is performed in the generated code, and support for XML Schema
polymorphism. This chapter describes these configuration
parameters in more detail. For more ways to configure the generated
code refer to the
<a href="http://www.codesynthesis.com/projects/xsd/documentation/xsd.xhtml">XSD
Compiler Command Line Manual</a>.
</p>
<h2><a name="5.1">5.1 C++ Standard</a></h2>
<p>The C++/Parser mapping provides support for ISO/IEC C++ 1998/2003 (C++98)
and ISO/IEC C++ 2011 (C++11). To select the C++ standard for the
generated code we use the <code>--std</code> XSD compiler command
line option. While the majority of the examples in this guide use
C++98, support for the new functionality and library components
introduced in C++11 are discussed throughout the document.</p>
<h2><a name="5.2">5.2 Character Type and Encoding</a></h2>
<p>The C++/Parser mapping has built-in support for two character types:
<code>char</code> and <code>wchar_t</code>. You can select the
character type with the <code>--char-type</code> command line
option. The default character type is <code>char</code>. The
string-based built-in XML Schema types are returned as either
<code>std::string</code> or <code>std::wstring</code> depending
on the character type selected.</p>
<p>Another aspect of the mapping that depends on the character type
is character encoding. For the <code>char</code> character type
the default encoding is UTF-8. Other supported encodings are
ISO-8859-1, Xerces-C++ Local Code Page (LPC), as well as
custom encodings. You can select which encoding should be used
in the object model with the <code>--char-encoding</code> command
line option.</p>
<p>For the <code>wchar_t</code> character type the encoding is
automatically selected between UTF-16 and UTF-32/UCS-4 depending
on the size of the <code>wchar_t</code> type. On some platforms
(for example, Windows with Visual C++ and AIX with IBM XL C++)
<code>wchar_t</code> is 2 bytes long. For these platforms the
encoding is UTF-16. On other platforms <code>wchar_t</code> is 4 bytes
long and UTF-32/UCS-4 is used.</p>
<p>Note also that the character encoding that is used in the object model
is independent of the encodings used in input and output XML. In fact,
all three (object mode, input XML, and output XML) can have different
encodings.</p>
<h2><a name="5.3">5.3 Underlying XML Parser</a></h2>
<p>The C++/Parser mapping can be used with either Xerces-C++ or Expat
as the underlying XML parser. You can select the XML parser with
the <code>--xml-parser</code> command line option. Valid values
for this option are <code>xerces</code> and <code>expat</code>.
The default XML parser is Xerces-C++.</p>
<p>The generated code is identical for both parsers except for the
<code>xml_schema::document</code> class in which some of the
<code>parse()</code> functions are parser-specific as described
in <a href="#7">Chapter 7, "Document Parser and Error Handling"</a>.</p>
<h2><a name="5.4">5.4 XML Schema Validation</a></h2>
<p>The C++/Parser mapping provides support for validating a
commonly-used subset of W3C XML Schema in the generated code.
For the list of supported XML Schema constructs refer to
<a href="#A">Appendix A, "Supported XML Schema Constructs"</a>.</p>
<p>By default validation in the generated code is disabled if
the underlying XML parser is validating (Xerces-C++) and
enabled otherwise (Expat). See <a href="#5.3">Section 5.3,
"Underlying XML Parser"</a> for more information about
the underlying XML parser. You can override the default
behavior with the <code>--generate-validation</code>
and <code>--suppress-validation</code> command line options.</p>
<h2><a name="5.5">5.5 Support for Polymorphism</a></h2>
<p>By default the XSD compiler generates non-polymorphic code. If your
vocabulary uses XML Schema polymorphism in the form of <code>xsi:type</code>
and/or substitution groups, then you will need to compile your schemas
with the <code>--generate-polymorphic</code> option to produce
polymorphism-aware code as well as pass <code>true</code> as the last
argument to the <code>xml_schema::document</code>'s constructors.</p>
<p>When using the polymorphism-aware generated code, you can specify
several parsers for a single element by passing a parser map
instead of an individual parser to the parser connection function
for the element. One of the parsers will then be looked up and used
depending on the <code>xsi:type</code> attribute value or an element
name from a substitution group. Consider the following schema as an
example:</p>
<pre class="xml">
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema">
<xs:complexType name="person">
<xs:sequence>
<xs:element name="name" type="xs:string"/>
</xs:sequence>
</xs:complexType>
<!-- substitution group root -->
<xs:element name="person" type="person"/>
<xs:complexType name="superman">
<xs:complexContent>
<xs:extension base="person">
<xs:attribute name="can-fly" type="xs:boolean"/>
</xs:extension>
</xs:complexContent>
</xs:complexType>
<xs:element name="superman"
type="superman"
substitutionGroup="person"/>
<xs:complexType name="batman">
<xs:complexContent>
<xs:extension base="superman">
<xs:attribute name="wing-span" type="xs:unsignedInt"/>
</xs:extension>
</xs:complexContent>
</xs:complexType>
<xs:element name="batman"
type="batman"
substitutionGroup="superman"/>
<xs:complexType name="supermen">
<xs:sequence>
<xs:element ref="person" maxOccurs="unbounded"/>
</xs:sequence>
</xs:complexType>
<xs:element name="supermen" type="supermen"/>
</xs:schema>
</pre>
<p>Conforming XML documents can use the <code>superman</code>
and <code>batman</code> types in place of the <code>person</code>
type either by specifying the type with the <code>xsi:type</code>
attributes or by using the elements from the substitution
group, for instance:</p>
<pre class="xml">
<supermen xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<person>
<name>John Doe</name>
</person>
<superman can-fly="false">
<name>James "007" Bond</name>
</superman>
<superman can-fly="true" wing-span="10" xsi:type="batman">
<name>Bruce Wayne</name>
</superman>
</supermen>
</pre>
<p>To print the data stored in such XML documents we can implement
the parsers as follows:</p>
<pre class="c++">
class person_pimpl: public virtual person_pskel
{
public:
virtual void
pre ()
{
cout << "starting to parse person" << endl;
}
virtual void
name (const std::string& v)
{
cout << "name: " << v << endl;
}
virtual void
post_person ()
{
cout << "finished parsing person" << endl;
}
};
class superman_pimpl: public virtual superman_pskel,
public person_pimpl
{
public:
virtual void
pre ()
{
cout << "starting to parse superman" << endl;
}
virtual void
can_fly (bool v)
{
cout << "can-fly: " << v << endl;
}
virtual void
post_person ()
{
post_superman ();
}
virtual void
post_superman ()
{
cout << "finished parsing superman" << endl
}
};
class batman_pimpl: public virtual batman_pskel,
public superman_pimpl
{
public:
virtual void
pre ()
{
cout << "starting to parse batman" << endl;
}
virtual void
wing_span (unsigned int v)
{
cout << "wing-span: " << v << endl;
}
virtual void
post_superman ()
{
post_batman ();
}
virtual void
post_batman ()
{
cout << "finished parsing batman" << endl;
}
};
</pre>
<p>Note that because the derived type parsers (<code>superman_pskel</code>
and <code>batman_pskel</code>) are called via the <code>person_pskel</code>
interface, we have to override the <code>post_person()</code>
virtual function in <code>superman_pimpl</code> to call
<code>post_superman()</code> and the <code>post_superman()</code>
virtual function in <code>batman_pimpl</code> to call
<code>post_batman()</code>.</p>
<p>The following code fragment shows how to connect the parsers together.
Notice that for the <code>person</code> element in the <code>supermen_p</code>
parser we specify a parser map instead of a specific parser and we pass
<code>true</code> as the last argument to the document parser constructor
to indicate that we are parsing potentially-polymorphic XML documents:</p>
<pre class="c++">
int
main (int argc, char* argv[])
{
// Construct the parser.
//
xml_schema::string_pimpl string_p;
xml_schema::boolean_pimpl boolean_p;
xml_schema::unsigned_int_pimpl unsigned_int_p;
person_pimpl person_p;
superman_pimpl superman_p;
batman_pimpl batman_p;
xml_schema::parser_map_impl person_map;
supermen_pimpl supermen_p;
person_p.parsers (string_p);
superman_p.parsers (string_p, boolean_p);
batman_p.parsers (string_p, boolean_p, unsigned_int_p);
// Here we are specifying a parser map which containes several
// parsers that can be used to parse the person element.
//
person_map.insert (person_p);
person_map.insert (superman_p);
person_map.insert (batman_p);
supermen_p.person_parser (person_map);
// Parse the XML document. The last argument to the document's
// constructor indicates that we are parsing polymorphic XML
// documents.
//
xml_schema::document doc_p (supermen_p, "supermen", true);
supermen_p.pre ();
doc_p.parse (argv[1]);
supermen_p.post_supermen ();
}
</pre>
<p>When polymorphism-aware code is generated, each element's
<code>*_parser()</code> function is overloaded to also accept
an object of the <code>xml_schema::parser_map</code> type.
For example, the <code>supermen_pskel</code> class from the
above example looks like this:</p>
<pre class="c++">
class supermen_pskel: public xml_schema::parser_complex_content
{
public:
...
// Parser construction API.
//
void
parsers (person_pskel&);
// Individual element parsers.
//
void
person_parser (person_pskel&);
void
person_parser (const xml_schema::parser_map&);
...
};
</pre>
<p>Note that you can specify both the individual (static) parser and
the parser map. The individual parser will be used when the static
element type and the dynamic type of the object being parsed are
the same. This is the case, for example, when there is no
<code>xsi:type</code> attribute and the element hasn't been
substituted. Because the individual parser for an element is
cached and no map lookup is necessary, it makes sense to specify
both the individual parser and the parser map when most of the
objects being parsed are of the static type and optimal
performance is important. The following code fragment shows
how to change the above example to set both the individual
parser and the parser map:</p>
<pre class="c++">
int
main (int argc, char* argv[])
{
...
person_map.insert (superman_p);
person_map.insert (batman_p);
supermen_p.person_parser (person_p);
supermen_p.person_parser (person_map);
...
}
</pre>
<p>The <code>xml_schema::parser_map</code> interface and the
<code>xml_schema::parser_map_impl</code> default implementation
are presented below:</p>
<pre class="c++">
namespace xml_schema
{
class parser_map
{
public:
virtual parser_base*
find (const ro_string* type) const = 0;
};
class parser_map_impl: public parser_map
{
public:
void
insert (parser_base&);
virtual parser_base*
find (const ro_string* type) const;
private:
parser_map_impl (const parser_map_impl&);
parser_map_impl&
operator= (const parser_map_impl&);
...
};
}
</pre>
<p>The <code>type</code> argument in the <code>find()</code> virtual
function is the type name and namespace from the xsi:type attribute
(the namespace prefix is resolved to the actual XML namespace)
or the type of an element from the substitution group in the form
<code>"<name> <namespace>"</code> with the space and the
namespace part absent if the type does not have a namespace.
You can obtain a parser's dynamic type in the same format
using the <code>_dynamic_type()</code> function. The static
type can be obtained by calling the static <code>_static_type()</code>
function, for example <code>person_pskel::_static_type()</code>.
Both functions return a C string (<code>const char*</code> or
<code>const wchar_t*</code>, depending on the character type
used) which is valid for as long as the application is running.
The following example shows how we can implement our own parser
map using <code>std::map</code>:</p>
<pre class="c++">
#include <map>
#include <string>
class parser_map: public xml_schema::parser_map
{
public:
void
insert (xml_schema::parser_base& p)
{
map_[p._dynamic_type ()] = &p;
}
virtual xml_schema::parser_base*
find (const xml_schema::ro_string* type) const
{
map::const_iterator i = map_.find (type);
return i != map_.end () ? i->second : 0;
}
private:
typedef std::map<std::string, xml_schema::parser_base*> map;
map map_;
};
</pre>
<p>Most of code presented in this section is taken from the
<code>polymorphism</code> example which can be found in the
<code>examples/cxx/parser/</code> directory of the XSD distribution.
Handling of <code>xsi:type</code> and substitution groups when used
on root elements requires a number of special actions as shown in
the <code>polyroot</code> example.</p>
<!-- Built-in XML Schema Type Parsers -->
<h1><a name="6">6 Built-In XML Schema Type Parsers</a></h1>
<p>The XSD runtime provides parser implementations for all built-in
XML Schema types as summarized in the following table. Declarations
for these types are automatically included into each generated
header file. As a result you don't need to include any headers
to gain access to these parser implementations. Note that some
parsers return either <code>std::string</code> or
<code>std::wstring</code> depending on the character type selected.</p>
<!-- border="1" is necessary for html2ps -->
<table id="builtin" border="1">
<tr>
<th>XML Schema type</th>
<th>Parser implementation in the <code>xml_schema</code> namespace</th>
<th>Parser return type</th>
</tr>
<tr>
<th colspan="3">anyType and anySimpleType types</th>
</tr>
<tr>
<td><code>anyType</code></td>
<td><code>any_type_pimpl</code></td>
<td><code>void</code></td>
</tr>
<tr>
<td><code>anySimpleType</code></td>
<td><code>any_simple_type_pimpl</code></td>
<td><code>void</code></td>
</tr>
<tr>
<th colspan="3">fixed-length integral types</th>
</tr>
<!-- 8-bit -->
<tr>
<td><code>byte</code></td>
<td><code>byte_pimpl</code></td>
<td><code>signed char</code></td>
</tr>
<tr>
<td><code>unsignedByte</code></td>
<td><code>unsigned_byte_pimpl</code></td>
<td><code>unsigned char</code></td>
</tr>
<!-- 16-bit -->
<tr>
<td><code>short</code></td>
<td><code>short_pimpl</code></td>
<td><code>short</code></td>
</tr>
<tr>
<td><code>unsignedShort</code></td>
<td><code>unsigned_short_pimpl</code></td>
<td><code>unsigned short</code></td>
</tr>
<!-- 32-bit -->
<tr>
<td><code>int</code></td>
<td><code>int_pimpl</code></td>
<td><code>int</code></td>
</tr>
<tr>
<td><code>unsignedInt</code></td>
<td><code>unsigned_int_pimpl</code></td>
<td><code>unsigned int</code></td>
</tr>
<!-- 64-bit -->
<tr>
<td><code>long</code></td>
<td><code>long_pimpl</code></td>
<td><code>long long</code></td>
</tr>
<tr>
<td><code>unsignedLong</code></td>
<td><code>unsigned_long_pimpl</code></td>
<td><code>unsigned long long</code></td>
</tr>
<tr>
<th colspan="3">arbitrary-length integral types</th>
</tr>
<tr>
<td><code>integer</code></td>
<td><code>integer_pimpl</code></td>
<td><code>long long</code></td>
</tr>
<tr>
<td><code>nonPositiveInteger</code></td>
<td><code>non_positive_integer_pimpl</code></td>
<td><code>long long</code></td>
</tr>
<tr>
<td><code>nonNegativeInteger</code></td>
<td><code>non_negative_integer_pimpl</code></td>
<td><code>unsigned long long</code></td>
</tr>
<tr>
<td><code>positiveInteger</code></td>
<td><code>positive_integer_pimpl</code></td>
<td><code>unsigned long long</code></td>
</tr>
<tr>
<td><code>negativeInteger</code></td>
<td><code>negative_integer_pimpl</code></td>
<td><code>long long</code></td>
</tr>
<tr>
<th colspan="3">boolean types</th>
</tr>
<tr>
<td><code>boolean</code></td>
<td><code>boolean_pimpl</code></td>
<td><code>bool</code></td>
</tr>
<tr>
<th colspan="3">fixed-precision floating-point types</th>
</tr>
<tr>
<td><code>float</code></td>
<td><code>float_pimpl</code></td>
<td><code>float</code></td>
</tr>
<tr>
<td><code>double</code></td>
<td><code>double_pimpl</code></td>
<td><code>double</code></td>
</tr>
<tr>
<th colspan="3">arbitrary-precision floating-point types</th>
</tr>
<tr>
<td><code>decimal</code></td>
<td><code>decimal_pimpl</code></td>
<td><code>double</code></td>
</tr>
<tr>
<th colspan="3">string-based types</th>
</tr>
<tr>
<td><code>string</code></td>
<td><code>string_pimpl</code></td>
<td><code>std::string</code> or <code>std::wstring</code></td>
</tr>
<tr>
<td><code>normalizedString</code></td>
<td><code>normalized_string_pimpl</code></td>
<td><code>std::string</code> or <code>std::wstring</code></td>
</tr>
<tr>
<td><code>token</code></td>
<td><code>token_pimpl</code></td>
<td><code>std::string</code> or <code>std::wstring</code></td>
</tr>
<tr>
<td><code>Name</code></td>
<td><code>name_pimpl</code></td>
<td><code>std::string</code> or <code>std::wstring</code></td>
</tr>
<tr>
<td><code>NMTOKEN</code></td>
<td><code>nmtoken_pimpl</code></td>
<td><code>std::string</code> or <code>std::wstring</code></td>
</tr>
<tr>
<td><code>NCName</code></td>
<td><code>ncname_pimpl</code></td>
<td><code>std::string</code> or <code>std::wstring</code></td>
</tr>
<tr>
<td><code>language</code></td>
<td><code>language_pimpl</code></td>
<td><code>std::string</code> or <code>std::wstring</code></td>
</tr>
<tr>
<th colspan="3">qualified name</th>
</tr>
<tr>
<td><code>QName</code></td>
<td><code>qname_pimpl</code></td>
<td><code>xml_schema::qname</code><br/><a href="#6.1">Section 6.1,
"<code>QName</code> Parser"</a></td>
</tr>
<tr>
<th colspan="3">ID/IDREF types</th>
</tr>
<tr>
<td><code>ID</code></td>
<td><code>id_pimpl</code></td>
<td><code>std::string</code> or <code>std::wstring</code></td>
</tr>
<tr>
<td><code>IDREF</code></td>
<td><code>idref_pimpl</code></td>
<td><code>std::string</code> or <code>std::wstring</code></td>
</tr>
<tr>
<th colspan="3">list types</th>
</tr>
<tr>
<td><code>NMTOKENS</code></td>
<td><code>nmtokens_pimpl</code></td>
<td><code>xml_schema::string_sequence</code><br/><a href="#6.2">Section
6.2, "<code>NMTOKENS</code> and <code>IDREFS</code> Parsers"</a></td>
</tr>
<tr>
<td><code>IDREFS</code></td>
<td><code>idrefs_pimpl</code></td>
<td><code>xml_schema::string_sequence</code><br/><a href="#6.2">Section
6.2, "<code>NMTOKENS</code> and <code>IDREFS</code> Parsers"</a></td>
</tr>
<tr>
<th colspan="3">URI types</th>
</tr>
<tr>
<td><code>anyURI</code></td>
<td><code>uri_pimpl</code></td>
<td><code>std::string</code> or <code>std::wstring</code></td>
</tr>
<tr>
<th colspan="3">binary types</th>
</tr>
<tr>
<td><code>base64Binary</code></td>
<td><code>base64_binary_pimpl</code></td>
<td><code>std::[auto|unique]_ptr< xml_schema::buffer></code><br/>
<a href="#6.3">Section 6.3, "<code>base64Binary</code> and
<code>hexBinary</code> Parsers"</a></td>
</tr>
<tr>
<td><code>hexBinary</code></td>
<td><code>hex_binary_pimpl</code></td>
<td><code>std::[auto|unique]_ptr< xml_schema::buffer></code><br/>
<a href="#6.3">Section 6.3, "<code>base64Binary</code> and
<code>hexBinary</code> Parsers"</a></td>
</tr>
<tr>
<th colspan="3">date/time types</th>
</tr>
<tr>
<td><code>date</code></td>
<td><code>date_pimpl</code></td>
<td><code>xml_schema::date</code><br/><a href="#6.5">Section 6.5,
"<code>date</code> Parser"</a></td>
</tr>
<tr>
<td><code>dateTime</code></td>
<td><code>date_time_pimpl</code></td>
<td><code>xml_schema::date_time</code><br/><a href="#6.6">Section 6.6,
"<code>dateTime</code> Parser"</a></td>
</tr>
<tr>
<td><code>duration</code></td>
<td><code>duration_pimpl</code></td>
<td><code>xml_schema::duration</code><br/><a href="#6.7">Section 6.7,
"<code>duration</code> Parser"</a></td>
</tr>
<tr>
<td><code>gDay</code></td>
<td><code>gday_pimpl</code></td>
<td><code>xml_schema::gday</code><br/><a href="#6.8">Section 6.8,
"<code>gDay</code> Parser"</a></td>
</tr>
<tr>
<td><code>gMonth</code></td>
<td><code>gmonth_pimpl</code></td>
<td><code>xml_schema::gmonth</code><br/><a href="#6.9">Section 6.9,
"<code>gMonth</code> Parser"</a></td>
</tr>
<tr>
<td><code>gMonthDay</code></td>
<td><code>gmonth_day_pimpl</code></td>
<td><code>xml_schema::gmonth_day</code><br/><a href="#6.10">Section 6.10,
"<code>gMonthDay</code> Parser"</a></td>
</tr>
<tr>
<td><code>gYear</code></td>
<td><code>gyear_pimpl</code></td>
<td><code>xml_schema::gyear</code><br/><a href="#6.11">Section 6.11,
"<code>gYear</code> Parser"</a></td>
</tr>
<tr>
<td><code>gYearMonth</code></td>
<td><code>gyear_month_pimpl</code></td>
<td><code>xml_schema::gyear_month</code><br/><a href="#6.12">Section
6.12, "<code>gYearMonth</code> Parser"</a></td>
</tr>
<tr>
<td><code>time</code></td>
<td><code>time_pimpl</code></td>
<td><code>xml_schema::time</code><br/><a href="#6.13">Section 6.13,
"<code>time</code> Parser"</a></td>
</tr>
</table>
<h2><a name="6.1">6.1 <code>QName</code> Parser</a></h2>
<p>The return type of the <code>qname_pimpl</code> parser implementation
is <code>xml_schema::qname</code> which represents an XML qualified
name. Its interface is presented below.
Note that the <code>std::string</code> type in the interface becomes
<code>std::wstring</code> if the selected character type is
<code>wchar_t</code>.</p>
<pre class="c++">
namespace xml_schema
{
class qname
{
public:
explicit
qname (const std::string& name);
qname (const std::string& prefix, const std::string& name);
const std::string&
prefix () const;
void
prefix (const std::string&);
const std::string&
name () const;
void
name (const std::string&);
};
bool
operator== (const qname&, const qname&);
bool
operator!= (const qname&, const qname&);
}
</pre>
<h2><a name="6.2">6.2 <code>NMTOKENS</code> and <code>IDREFS</code> Parsers</a></h2>
<p>The return type of the <code>nmtokens_pimpl</code> and
<code>idrefs_pimpl</code> parser implementations is
<code>xml_schema::string_sequence</code> which represents a
sequence of strings. Its interface is presented below.
Note that the <code>std::string</code> type in the interface becomes
<code>std::wstring</code> if the selected character type is
<code>wchar_t</code>.</p>
<pre class="c++">
namespace xml_schema
{
class string_sequence: public std::vector<std::string>
{
public:
string_sequence ();
explicit
string_sequence (std::vector<std::string>::size_type n,
const std::string& x = std::string ());
template <typename I>
string_sequence (const I& begin, const I& end);
};
bool
operator== (const string_sequence&, const string_sequence&);
bool
operator!= (const string_sequence&, const string_sequence&);
}
</pre>
<h2><a name="6.3">6.3 <code>base64Binary</code> and <code>hexBinary</code> Parsers</a></h2>
<p>The return type of the <code>base64_binary_pimpl</code> and
<code>hex_binary_pimpl</code> parser implementations is either
<code>std::auto_ptr<xml_schema::buffer></code> (C++98) or
<code>std::unique_ptr<xml_schema::buffer></code> (C++11),
depending on the C++ standard selected (<code>--std</code> XSD
compiler option). The <code>xml_schema::buffer</code> type
represents a binary buffer and its interface is presented below.</p>
<pre class="c++">
namespace xml_schema
{
class buffer
{
public:
typedef std::size_t size_t;
class bounds {}; // Out of bounds exception.
public:
explicit
buffer (size_t size = 0);
buffer (size_t size, size_t capacity);
buffer (const void* data, size_t size);
buffer (const void* data, size_t size, size_t capacity);
buffer (void* data,
size_t size,
size_t capacity,
bool assume_ownership);
public:
buffer (const buffer&);
buffer&
operator= (const buffer&);
void
swap (buffer&);
public:
size_t
capacity () const;
bool
capacity (size_t);
public:
size_t
size () const;
bool
size (size_t);
public:
const char*
data () const;
char*
data ();
const char*
begin () const;
char*
begin ();
const char*
end () const;
char*
end ();
};
bool
operator== (const buffer&, const buffer&);
bool
operator!= (const buffer&, const buffer&);
}
</pre>
<p>If the <code>assume_ownership</code> argument to the constructor
is <code>true</code>, the instance assumes the ownership of the
memory block pointed to by the <code>data</code> argument and will
eventually release it by calling <code>operator delete()</code>. The
<code>capacity()</code> and <code>size()</code> modifier functions
return <code>true</code> if the underlying buffer has moved.
</p>
<p>The <code>bounds</code> exception is thrown if the constructor
arguments violate the <code>(size <= capacity)</code>
constraint.</p>
<h2><a name="6.4">6.4 Time Zone Representation</a></h2>
<p>The <code>date</code>, <code>dateTime</code>, <code>gDay</code>,
<code>gMonth</code>, <code>gMonthDay</code>, <code>gYear</code>,
<code>gYearMonth</code>, and <code>time</code> XML Schema built-in
types all include an optional time zone component. The following
<code>xml_schema::time_zone</code> base class is used to represent
this information:</p>
<pre class="c++">
namespace xml_schema
{
class time_zone
{
public:
time_zone ();
time_zone (short hours, short minutes);
bool
zone_present () const;
void
zone_reset ();
short
zone_hours () const;
void
zone_hours (short);
short
zone_minutes () const;
void
zone_minutes (short);
};
bool
operator== (const time_zone&, const time_zone&);
bool
operator!= (const time_zone&, const time_zone&);
}
</pre>
<p>The <code>zone_present()</code> accessor function returns <code>true</code>
if the time zone is specified. The <code>zone_reset()</code> modifier
function resets the time zone object to the <em>not specified</em>
state. If the time zone offset is negative then both hours and
minutes components are represented as negative integers.</p>
<h2><a name="6.5">6.5 <code>date</code> Parser</a></h2>
<p>The return type of the <code>date_pimpl</code> parser implementation
is <code>xml_schema::date</code> which represents a year, a day, and a month
with an optional time zone. Its interface is presented below.
For more information on the base <code>xml_schema::time_zone</code>
class refer to <a href="#6.4">Section 6.4, "Time Zone
Representation"</a>.</p>
<pre class="c++">
namespace xml_schema
{
class date
{
public:
date (int year, unsigned short month, unsigned short day);
date (int year, unsigned short month, unsigned short day,
short zone_hours, short zone_minutes);
int
year () const;
void
year (int);
unsigned short
month () const;
void
month (unsigned short);
unsigned short
day () const;
void
day (unsigned short);
};
bool
operator== (const date&, const date&);
bool
operator!= (const date&, const date&);
}
</pre>
<h2><a name="6.6">6.6 <code>dateTime</code> Parser</a></h2>
<p>The return type of the <code>date_time_pimpl</code> parser implementation
is <code>xml_schema::date_time</code> which represents a year, a month, a day,
hours, minutes, and seconds with an optional time zone. Its interface
is presented below.
For more information on the base <code>xml_schema::time_zone</code>
class refer to <a href="#6.4">Section 6.4, "Time Zone
Representation"</a>.</p>
<pre class="c++">
namespace xml_schema
{
class date_time
{
public:
date_time (int year, unsigned short month, unsigned short day,
unsigned short hours, unsigned short minutes,
double seconds);
date_time (int year, unsigned short month, unsigned short day,
unsigned short hours, unsigned short minutes,
double seconds, short zone_hours, short zone_minutes);
int
year () const;
void
year (int);
unsigned short
month () const;
void
month (unsigned short);
unsigned short
day () const;
void
day (unsigned short);
unsigned short
hours () const;
void
hours (unsigned short);
unsigned short
minutes () const;
void
minutes (unsigned short);
double
seconds () const;
void
seconds (double);
};
bool
operator== (const date_time&, const date_time&);
bool
operator!= (const date_time&, const date_time&);
}
</pre>
<h2><a name="6.7">6.7 <code>duration</code> Parser</a></h2>
<p>The return type of the <code>duration_pimpl</code> parser implementation
is <code>xml_schema::duration</code> which represents a potentially
negative duration in the form of years, months, days, hours, minutes,
and seconds. Its interface is presented below.</p>
<pre class="c++">
namespace xml_schema
{
class duration
{
public:
duration (bool negative,
unsigned int years, unsigned int months, unsigned int days,
unsigned int hours, unsigned int minutes, double seconds);
bool
negative () const;
void
negative (bool);
unsigned int
years () const;
void
years (unsigned int);
unsigned int
months () const;
void
months (unsigned int);
unsigned int
days () const;
void
days (unsigned int);
unsigned int
hours () const;
void
hours (unsigned int);
unsigned int
minutes () const;
void
minutes (unsigned int);
double
seconds () const;
void
seconds (double);
};
bool
operator== (const duration&, const duration&);
bool
operator!= (const duration&, const duration&);
}
</pre>
<h2><a name="6.8">6.8 <code>gDay</code> Parser</a></h2>
<p>The return type of the <code>gday_pimpl</code> parser implementation
is <code>xml_schema::gday</code> which represents a day of the month with
an optional time zone. Its interface is presented below.
For more information on the base <code>xml_schema::time_zone</code>
class refer to <a href="#6.4">Section 6.4, "Time Zone
Representation"</a>.</p>
<pre class="c++">
namespace xml_schema
{
class gday
{
public:
explicit
gday (unsigned short day);
gday (unsigned short day, short zone_hours, short zone_minutes);
unsigned short
day () const;
void
day (unsigned short);
};
bool
operator== (const gday&, const gday&);
bool
operator!= (const gday&, const gday&);
}
</pre>
<h2><a name="6.9">6.9 <code>gMonth</code> Parser</a></h2>
<p>The return type of the <code>gmonth_pimpl</code> parser implementation
is <code>xml_schema::gmonth</code> which represents a month of the year
with an optional time zone. Its interface is presented below.
For more information on the base <code>xml_schema::time_zone</code>
class refer to <a href="#6.4">Section 6.4, "Time Zone
Representation"</a>.</p>
<pre class="c++">
namespace xml_schema
{
class gmonth
{
public:
explicit
gmonth (unsigned short month);
gmonth (unsigned short month, short zone_hours, short zone_minutes);
unsigned short
month () const;
void
month (unsigned short);
};
bool
operator== (const gmonth&, const gmonth&);
bool
operator!= (const gmonth&, const gmonth&);
}
</pre>
<h2><a name="6.10">6.10 <code>gMonthDay</code> Parser</a></h2>
<p>The return type of the <code>gmonth_day_pimpl</code> parser implementation
is <code>xml_schema::gmonth_day</code> which represents a day and a month
of the year with an optional time zone. Its interface is presented below.
For more information on the base <code>xml_schema::time_zone</code>
class refer to <a href="#6.4">Section 6.4, "Time Zone
Representation"</a>.</p>
<pre class="c++">
namespace xml_schema
{
class gmonth_day
{
public:
gmonth_day (unsigned short month, unsigned short day);
gmonth_day (unsigned short month, unsigned short day,
short zone_hours, short zone_minutes);
unsigned short
month () const;
void
month (unsigned short);
unsigned short
day () const;
void
day (unsigned short);
};
bool
operator== (const gmonth_day&, const gmonth_day&);
bool
operator!= (const gmonth_day&, const gmonth_day&);
}
</pre>
<h2><a name="6.11">6.11 <code>gYear</code> Parser</a></h2>
<p>The return type of the <code>gyear_pimpl</code> parser implementation
is <code>xml_schema::gyear</code> which represents a year with
an optional time zone. Its interface is presented below.
For more information on the base <code>xml_schema::time_zone</code>
class refer to <a href="#6.4">Section 6.4, "Time Zone
Representation"</a>.</p>
<pre class="c++">
namespace xml_schema
{
class gyear
{
public:
explicit
gyear (int year);
gyear (int year, short zone_hours, short zone_minutes);
int
year () const;
void
year (int);
};
bool
operator== (const gyear&, const gyear&);
bool
operator!= (const gyear&, const gyear&);
}
</pre>
<h2><a name="6.12">6.12 <code>gYearMonth</code> Parser</a></h2>
<p>The return type of the <code>gyear_month_pimpl</code> parser implementation
is <code>xml_schema::gyear_month</code> which represents a year and a month
with an optional time zone. Its interface is presented below.
For more information on the base <code>xml_schema::time_zone</code>
class refer to <a href="#6.4">Section 6.4, "Time Zone
Representation"</a>.</p>
<pre class="c++">
namespace xml_schema
{
class gyear_month
{
public:
gyear_month (int year, unsigned short month);
gyear_month (int year, unsigned short month,
short zone_hours, short zone_minutes);
int
year () const;
void
year (int);
unsigned short
month () const;
void
month (unsigned short);
};
bool
operator== (const gyear_month&, const gyear_month&);
bool
operator!= (const gyear_month&, const gyear_month&);
}
</pre>
<h2><a name="6.13">6.13 <code>time</code> Parser</a></h2>
<p>The return type of the <code>time_pimpl</code> parser implementation
is <code>xml_schema::time</code> which represents hours, minutes,
and seconds with an optional time zone. Its interface is presented below.
For more information on the base <code>xml_schema::time_zone</code>
class refer to <a href="#6.4">Section 6.4, "Time Zone
Representation"</a>.</p>
<pre class="c++">
namespace xml_schema
{
class time
{
public:
time (unsigned short hours, unsigned short minutes, double seconds);
time (unsigned short hours, unsigned short minutes, double seconds,
short zone_hours, short zone_minutes);
unsigned short
hours () const;
void
hours (unsigned short);
unsigned short
minutes () const;
void
minutes (unsigned short);
double
seconds () const;
void
seconds (double);
};
bool
operator== (const time&, const time&);
bool
operator!= (const time&, const time&);
}
</pre>
<!-- Error Handling -->
<h1><a name="7">7 Document Parser and Error Handling</a></h1>
<p>In this chapter we will discuss the <code>xml_schema::document</code>
type as well as the error handling mechanisms provided by the mapping
in more detail. As mentioned in <a href="#3.4">Section 3.4,
"Connecting the Parsers Together"</a>, the interface of
<code>xml_schema::document</code> depends on the underlying XML
parser selected (<a href="#5.3">Section 5.3, "Underlying XML
Parser"</a>). The following sections describe the
<code>document</code> type interface for Xerces-C++ and
Expat as underlying parsers.</p>
<h2><a name="7.1">7.1 Xerces-C++ Document Parser</a></h2>
<p>When Xerces-C++ is used as the underlying XML parser, the
<code>document</code> type has the following interface. Note that
if the character type is <code>wchar_t</code>, then the string type
in the interface becomes <code>std::wstring</code>
(see <a href="#5.2">Section 5.2, "Character Type and Encoding"</a>).</p>
<pre class="c++">
namespace xml_schema
{
class parser_base;
class error_handler;
class flags
{
public:
// Do not validate XML documents with the Xerces-C++ validator.
//
static const unsigned long dont_validate;
// Do not initialize the Xerces-C++ runtime.
//
static const unsigned long dont_initialize;
// Disable handling of subsequent imports for the same namespace
// in Xerces-C++ 3.1.0 and later.
//
static const unsigned long no_multiple_imports;
};
class properties
{
public:
// Add a location for a schema with a target namespace.
//
void
schema_location (const std::string& namespace_,
const std::string& location);
// Add a location for a schema without a target namespace.
//
void
no_namespace_schema_location (const std::string& location);
};
class document
{
public:
document (parser_base& root,
const std::string& root_element_name,
bool polymorphic = false);
document (parser_base& root,
const std::string& root_element_namespace,
const std::string& root_element_name,
bool polymorphic = false);
public:
// Parse URI or a local file.
//
void
parse (const std::string& uri,
flags = 0,
const properties& = properties ());
// Parse URI or a local file with a user-provided error_handler
// object.
//
void
parse (const std::string& uri,
error_handler&,
flags = 0,
const properties& = properties ());
// Parse URI or a local file with a user-provided ErrorHandler
// object. Note that you must initialize the Xerces-C++ runtime
// before calling this function.
//
void
parse (const std::string& uri,
xercesc::ErrorHandler&,
flags = 0,
const properties& = properties ());
// Parse URI or a local file using a user-provided SAX2XMLReader
// object. Note that you must initialize the Xerces-C++ runtime
// before calling this function.
//
void
parse (const std::string& uri,
xercesc::SAX2XMLReader&,
flags = 0,
const properties& = properties ());
public:
// Parse std::istream.
//
void
parse (std::istream&,
flags = 0,
const properties& = properties ());
// Parse std::istream with a user-provided error_handler object.
//
void
parse (std::istream&,
error_handler&,
flags = 0,
const properties& = properties ());
// Parse std::istream with a user-provided ErrorHandler object.
// Note that you must initialize the Xerces-C++ runtime before
// calling this function.
//
void
parse (std::istream&,
xercesc::ErrorHandler&,
flags = 0,
const properties& = properties ());
// Parse std::istream using a user-provided SAX2XMLReader object.
// Note that you must initialize the Xerces-C++ runtime before
// calling this function.
//
void
parse (std::istream&,
xercesc::SAX2XMLReader&,
flags = 0,
const properties& = properties ());
public:
// Parse std::istream with a system id.
//
void
parse (std::istream&,
const std::string& system_id,
flags = 0,
const properties& = properties ());
// Parse std::istream with a system id and a user-provided
// error_handler object.
//
void
parse (std::istream&,
const std::string& system_id,
error_handler&,
flags = 0,
const properties& = properties ());
// Parse std::istream with a system id and a user-provided
// ErrorHandler object. Note that you must initialize the
// Xerces-C++ runtime before calling this function.
//
void
parse (std::istream&,
const std::string& system_id,
xercesc::ErrorHandler&,
flags = 0,
const properties& = properties ());
// Parse std::istream with a system id using a user-provided
// SAX2XMLReader object. Note that you must initialize the
// Xerces-C++ runtime before calling this function.
//
void
parse (std::istream&,
const std::string& system_id,
xercesc::SAX2XMLReader&,
flags = 0,
const properties& = properties ());
public:
// Parse std::istream with system and public ids.
//
void
parse (std::istream&,
const std::string& system_id,
const std::string& public_id,
flags = 0,
const properties& = properties ());
// Parse std::istream with system and public ids and a user-provided
// error_handler object.
//
void
parse (std::istream&,
const std::string& system_id,
const std::string& public_id,
error_handler&,
flags = 0,
const properties& = properties ());
// Parse std::istream with system and public ids and a user-provided
// ErrorHandler object. Note that you must initialize the Xerces-C++
// runtime before calling this function.
//
void
parse (std::istream&,
const std::string& system_id,
const std::string& public_id,
xercesc::ErrorHandler&,
flags = 0,
const properties& = properties ());
// Parse std::istream with system and public ids using a user-
// provided SAX2XMLReader object. Note that you must initialize
// the Xerces-C++ runtime before calling this function.
//
void
parse (std::istream&,
const std::string& system_id,
const std::string& public_id,
xercesc::SAX2XMLReader&,
flags = 0,
const properties& = properties ());
public:
// Parse InputSource. Note that you must initialize the Xerces-C++
// runtime before calling this function.
//
void
parse (const xercesc::InputSource&,
flags = 0,
const properties& = properties ());
// Parse InputSource with a user-provided error_handler object.
// Note that you must initialize the Xerces-C++ runtime before
// calling this function.
//
void
parse (const xercesc::InputSource&,
error_handler&,
flags = 0,
const properties& = properties ());
// Parse InputSource with a user-provided ErrorHandler object.
// Note that you must initialize the Xerces-C++ runtime before
// calling this function.
//
void
parse (const xercesc::InputSource&,
xercesc::ErrorHandler&,
flags = 0,
const properties& = properties ());
// Parse InputSource using a user-provided SAX2XMLReader object.
// Note that you must initialize the Xerces-C++ runtime before
// calling this function.
//
void
parse (const xercesc::InputSource&,
xercesc::SAX2XMLReader&,
flags = 0,
const properties& = properties ());
};
}
</pre>
<p>The <code>document</code> class is a root parser for
the vocabulary. The first argument to its constructors is the
parser for the type of the root element. The <code>parser_base</code>
class is the base type for all parser skeletons. The second and
third arguments to the <code>document</code>'s constructors are
the root element's name and namespace. The last argument,
<code>polymorphic</code>, specifies whether the XML documents
being parsed use polymorphism. For more information on support
for XML Schema polymorphism in the C++/Parser mapping refer
to <a href="#5.5">Section 5.5, "Support for Polymorphism"</a>.</p>
<p>The rest of the <code>document</code> interface consists of overloaded
<code>parse()</code> functions. The last two arguments in each of these
functions are <code>flags</code> and <code>properties</code>. The
<code>flags</code> argument allows you to modify the default behavior
of the parsing functions. The <code>properties</code> argument allows
you to override the schema location attributes specified in XML
documents. Note that the schema location paths are relative to an
XML document unless they are complete URIs. For example if you want
to use a local schema file then you will need to use a URI in the
form <code>file:///absolute/path/to/your/schema</code>.</p>
<p>A number of overloaded <code>parse()</code> functions have the
<code>system_id</code> and <code>public_id</code> arguments. The
system id is a <em>system</em> identifier of the resources being
parsed (for example, URI or a full file path). The public id is a
<em>public</em> identifier of the resource (for example, an
application-specific name or a relative file path). The system id
is used to resolve relative paths (for example, schema paths). In
diagnostics messages the public id is used if it is available.
Otherwise the system id is used.</p>
<p>The error handling mechanisms employed by the <code>document</code>
parser are described in <a href="#7.3">Section 7.3, "Error
Handling"</a>.</p>
<h2><a name="7.2">7.2 Expat Document Parser</a></h2>
<p>When Expat is used as the underlying XML parser, the
<code>document</code> type has the following interface. Note that
if the character type is <code>wchar_t</code>, then the string type
in the interface becomes <code>std::wstring</code>
(see <a href="#5.2">Section 5.2, "Character Type and Encoding"</a>).</p>
<pre class="c++">
namespace xml_schema
{
class parser_base;
class error_handler;
class document
{
public:
document (parser_base&,
const std::string& root_element_name,
bool polymorphic = false);
document (parser_base&,
const std::string& root_element_namespace,
const std::string& root_element_name,
bool polymorphic = false);
public:
// Parse a local file. The file is accessed with std::ifstream
// in binary mode. The std::ios_base::failure exception is used
// to report io errors (badbit and failbit).
void
parse (const std::string& file);
// Parse a local file with a user-provided error_handler
// object. The file is accessed with std::ifstream in binary
// mode. The std::ios_base::failure exception is used to report
// io errors (badbit and failbit).
//
void
parse (const std::string& file, error_handler&);
public:
// Parse std::istream.
//
void
parse (std::istream&);
// Parse std::istream with a user-provided error_handler object.
//
void
parse (std::istream&, error_handler&);
// Parse std::istream with a system id.
//
void
parse (std::istream&, const std::string& system_id);
// Parse std::istream with a system id and a user-provided
// error_handler object.
//
void
parse (std::istream&,
const std::string& system_id,
error_handler&);
// Parse std::istream with system and public ids.
//
void
parse (std::istream&,
const std::string& system_id,
const std::string& public_id);
// Parse std::istream with system and public ids and a user-provided
// error_handler object.
//
void
parse (std::istream&,
const std::string& system_id,
const std::string& public_id,
error_handler&);
public:
// Parse a chunk of input. You can call these functions multiple
// times with the last call having the last argument true.
//
void
parse (const void* data, std::size_t size, bool last);
void
parse (const void* data, std::size_t size, bool last,
error_handler&);
void
parse (const void* data, std::size_t size, bool last,
const std::string& system_id);
void
parse (const void* data, std::size_t size, bool last,
const std::string& system_id,
error_handler&);
void
parse (const void* data, std::size_t size, bool last,
const std::string& system_id,
const std::string& public_id);
void
parse (const void* data, std::size_t size, bool last,
const std::string& system_id,
const std::string& public_id,
error_handler&);
public:
// Low-level Expat-specific parsing API.
//
void
parse_begin (XML_Parser);
void
parse_begin (XML_Parser, const std::string& public_id);
void
parse_begin (XML_Parser, error_handler&);
void
parse_begin (XML_Parser,
const std::string& public_id,
error_handler&);
void
parse_end ();
};
}
</pre>
<p>The <code>document</code> class is a root parser for
the vocabulary. The first argument to its constructors is the
parser for the type of the root element. The <code>parser_base</code>
class is the base type for all parser skeletons. The second and
third arguments to the <code>document</code>'s constructors are
the root element's name and namespace. The last argument,
<code>polymorphic</code>, specifies whether the XML documents
being parsed use polymorphism. For more information on support
for XML Schema polymorphism in the C++/Parser mapping refer
to <a href="#5.5">Section 5.5, "Support for Polymorphism"</a>.</p>
<p>A number of overloaded <code>parse()</code> functions have the
<code>system_id</code> and <code>public_id</code> arguments. The
system id is a <em>system</em> identifier of the resources being
parsed (for example, URI or a full file path). The public id is a
<em>public</em> identifier of the resource (for example, an
application-specific name or a relative file path). The system id
is used to resolve relative paths. In diagnostics messages the
public id is used if it is available. Otherwise the system id
is used.</p>
<p>The <code>parse_begin()</code> and <code>parse_end()</code> functions
present a low-level, Expat-specific parsing API for maximum control.
A typical use-case would look like this (pseudo-code):</p>
<pre class="c++">
xxx_pimpl root_p;
document doc_p (root_p, "root");
root_p.pre ();
doc_p.parse_begin (xml_parser, "file.xml");
while (more_data_to_parse)
{
// Call XML_Parse or XML_ParseBuffer.
if (status == XML_STATUS_ERROR)
break;
}
// Call parse_end even in case of an error to translate
// XML and Schema errors to exceptions or error_handler
// calls.
//
doc.parse_end ();
result_type result (root_p.post_xxx ());
</pre>
<p>Note that if your vocabulary uses XML namespaces, the
<code>XML_ParserCreateNS()</code> functions should be used to create
the XML parser. Space (<code>XML_Char (' ')</code>) should be used
as a separator (the second argument to <code>XML_ParserCreateNS()</code>).
</p>
<p>The error handling mechanisms employed by the <code>document</code>
parser are described in <a href="#7.3">Section 7.3, "Error
Handling"</a>.</p>
<h2><a name="7.3">7.3 Error Handling</a></h2>
<p>There are three categories of errors that can result from running
a parser on an XML document: System, XML, and Application.
The System category contains memory allocation and file/stream
operation errors. The XML category covers XML parsing and
well-formedness checking as well as XML Schema validation errors.
Finally, the Application category is for application logic errors
that you may want to propagate from parser implementations to the
caller of the parser.
</p>
<p>The System errors are mapped to the standard exceptions. The
out of memory condition is indicated by throwing an instance
of <code>std::bad_alloc</code>. The stream operation errors
are reported either by throwing an instance of
<code>std::ios_base::failure</code> if exceptions are enabled
or by setting the stream state.</p>
<p>Note that if you are parsing <code>std::istream</code> on
which exceptions are not enabled, then you will need to
check the stream state before calling the <code>post()</code>
callback, as shown in the following example:</p>
<pre class="c++">
int
main (int argc, char* argv[])
{
...
std::ifstream ifs (argv[1]);
if (ifs.fail ())
{
cerr << argv[1] << ": unable to open" << endl;
return 1;
}
root_p.pre ();
doc_p.parse (ifs);
if (ifs.fail ())
{
cerr << argv[1] << ": io failure" << endl;
return 1;
}
result_type result (root_p.post_xxx ());
}
</pre>
<p>The above example can be rewritten to use exceptions
as shown below:</p>
<pre class="c++">
int
main (int argc, char* argv[])
{
try
{
...
std::ifstream ifs;
ifs.exceptions (std::ifstream::badbit | std::ifstream::failbit);
ifs.open (argv[1]);
root_p.pre ();
doc_p.parse (ifs);
result_type result (root_p.post_xxx ());
}
catch (const std::ifstream::failure&)
{
cerr << argv[1] << ": unable to open or io failure" << endl;
return 1;
}
}
</pre>
<p>For reporting application errors from parsing callbacks, you
can throw any exceptions of your choice. They are propagated to
the caller of the parser without any alterations.</p>
<p>The XML errors can be reported either by throwing the
<code>xml_schema::parsing</code> exception or by a callback
to the <code>xml_schema::error_handler</code> object (and
<code>xercesc::ErrorHandler</code> object in case of Xerces-C++).</p>
<p>The <code>xml_schema::parsing</code> exception contains
a list of warnings and errors that were accumulated during
parsing. Note that this exception is thrown only if there
was an error. This makes it impossible to obtain warnings
from an otherwise successful parsing using this mechanism.
The following listing shows the definition of
<code>xml_schema::parsing</code> exception. Note that if the
character type is <code>wchar_t</code>, then the string type
and output stream type in the definition become
<code>std::wstring</code> and <code>std::wostream</code>,
respectively (see <a href="#5.2">Section 5.2, "Character Type
and Encoding"</a>).</p>
<pre class="c++">
namespace xml_schema
{
class exception: public std::exception
{
protected:
virtual void
print (std::ostream&) const = 0;
};
inline std::ostream&
operator<< (std::ostream& os, const exception& e)
{
e.print (os);
return os;
}
class severity
{
public:
enum value
{
warning,
error
};
};
class error
{
public:
error (xml_schema::severity,
const std::string& id,
unsigned long line,
unsigned long column,
const std::string& message);
xml_schema::severity
severity () const;
const std::string&
id () const;
unsigned long
line () const;
unsigned long
column () const;
const std::string&
message () const;
};
std::ostream&
operator<< (std::ostream&, const error&);
class diagnostics: public std::vector<error>
{
};
std::ostream&
operator<< (std::ostream&, const diagnostics&);
class parsing: public exception
{
public:
parsing ();
parsing (const xml_schema::diagnostics&);
const xml_schema::diagnostics&
diagnostics () const;
virtual const char*
what () const throw ();
protected:
virtual void
print (std::ostream&) const;
};
}
</pre>
<p>The following example shows how we can catch and print this
exception. The code will print diagnostics messages one per line
in case of an error.</p>
<pre class="c++">
int
main (int argc, char* argv[])
{
try
{
// Parse.
}
catch (const xml_schema::parsing& e)
{
cerr << e << endl;
return 1;
}
}
</pre>
<p>With the <code>error_handler</code> approach the diagnostics
messages are delivered as parsing progresses. The following
listing presents the definition of the <code>error_handler</code>
interface. Note that if the character type is <code>wchar_t</code>,
then the string type in the interface becomes <code>std::wstring</code>
(see <a href="#5.2">Section 5.2, "Character Type and Encoding"</a>).</p>
<pre class="c++">
namespace xml_schema
{
class error_handler
{
public:
class severity
{
public:
enum value
{
warning,
error,
fatal
};
};
virtual bool
handle (const std::string& id,
unsigned long line,
unsigned long column,
severity,
const std::string& message) = 0;
};
}
</pre>
<p>The return value of the <code>handle()</code> function indicates whether
parsing should continue if possible. The error with the fatal severity
level terminates the parsing process regardless of the returned value.
At the end of the parsing process with an error that was reported via
the <code>error_handler</code> object, an empty
<code>xml_schema::parsing</code> exception is thrown to indicate
the failure to the caller. You can alter this behavior by throwing
your own exception from the <code>handle()</code> function.</p>
<!-- Appendix A -->
<h1><a name="A">Appendix A — Supported XML Schema Constructs</a></h1>
<p>The C++/Parser mapping supports validation of the following W3C XML
Schema constructs in the generated code.</p>
<!-- border="1" is necessary for html2ps -->
<table id="features" border="1">
<tr><th>Construct</th><th>Notes</th></tr>
<tr><th colspan="2">Structure</th></tr>
<tr><td>element</td><td></td></tr>
<tr><td>attribute</td><td></td></tr>
<tr><td>any</td><td></td></tr>
<tr><td>anyAttribute</td><td></td></tr>
<tr><td>all</td><td></td></tr>
<tr><td>sequence</td><td></td></tr>
<tr><td>choice</td><td></td></tr>
<tr><td>complex type, empty content</td><td></td></tr>
<tr><td>complex type, mixed content</td><td></td></tr>
<tr><td>complex type, simple content extension</td><td></td></tr>
<tr><td>complex type, simple content restriction</td>
<td>Simple type facets are not validated.</td></tr>
<tr><td>complex type, complex content extension</td><td></td></tr>
<tr><td>complex type, complex content restriction</td><td></td></tr>
<tr><td>list</td><td></td></tr>
<tr><th colspan="2">Datatypes</th></tr>
<tr><td>byte</td><td></td></tr>
<tr><td>unsignedByte</td><td></td></tr>
<tr><td>short</td><td></td></tr>
<tr><td>unsignedShort</td><td></td></tr>
<tr><td>int</td><td></td></tr>
<tr><td>unsignedInt</td><td></td></tr>
<tr><td>long</td><td></td></tr>
<tr><td>unsignedLong</td><td></td></tr>
<tr><td>integer</td><td></td></tr>
<tr><td>nonPositiveInteger</td><td></td></tr>
<tr><td>nonNegativeInteger</td><td></td></tr>
<tr><td>positiveInteger</td><td></td></tr>
<tr><td>negativeInteger</td><td></td></tr>
<tr><td>boolean</td><td></td></tr>
<tr><td>float</td><td></td></tr>
<tr><td>double</td><td></td></tr>
<tr><td>decimal</td><td></td></tr>
<tr><td>string</td><td></td></tr>
<tr><td>normalizedString</td><td></td></tr>
<tr><td>token</td><td></td></tr>
<tr><td>Name</td><td></td></tr>
<tr><td>NMTOKEN</td><td></td></tr>
<tr><td>NCName</td><td></td></tr>
<tr><td>language</td><td></td></tr>
<tr><td>anyURI</td><td></td></tr>
<tr><td>ID</td><td>Identity constraint is not enforced.</td></tr>
<tr><td>IDREF</td><td>Identity constraint is not enforced.</td></tr>
<tr><td>NMTOKENS</td><td></td></tr>
<tr><td>IDREFS</td><td>Identity constraint is not enforced.</td></tr>
<tr><td>QName</td><td></td></tr>
<tr><td>base64Binary</td><td></td></tr>
<tr><td>hexBinary</td><td></td></tr>
<tr><td>date</td><td></td></tr>
<tr><td>dateTime</td><td></td></tr>
<tr><td>duration</td><td></td></tr>
<tr><td>gDay</td><td></td></tr>
<tr><td>gMonth</td><td></td></tr>
<tr><td>gMonthDay</td><td></td></tr>
<tr><td>gYear</td><td></td></tr>
<tr><td>gYearMonth</td><td></td></tr>
<tr><td>time</td><td></td></tr>
</table>
</div>
</div>
</body>
</html>
|
