summaryrefslogtreecommitdiff
path: root/docs/manual.adoc
blob: 7b498575bb24256d1588d45ed54c266f96e9d5e5 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
= pugixml {version} manual
include::config.adoc[]
:numbered:

[[overview]]
== Overview

[[overview.introduction]]
=== Introduction

http://pugixml.org/[pugixml] is a light-weight C{plus}{plus} XML processing library. It consists of a DOM-like interface with rich traversal/modification capabilities, an extremely fast XML parser which constructs the DOM tree from an XML file/buffer, and an <<xpath,XPath 1.0 implementation>> for complex data-driven tree queries. Full Unicode support is also available, with <<dom.unicode,two Unicode interface variants>> and conversions between different Unicode encodings (which happen automatically during parsing/saving). The library is <<install.portability,extremely portable>> and easy to integrate and use. pugixml is developed and maintained since 2006 and has many users. All code is distributed under the <<overview.license,MIT license>>, making it completely free to use in both open-source and proprietary applications.

pugixml enables very fast, convenient and memory-efficient XML document processing. However, since pugixml has a DOM parser, it can't process XML documents that do not fit in memory; also the parser is a non-validating one, so if you need DTD or XML Schema validation, the library is not for you.

This is the complete manual for pugixml, which describes all features of the library in detail. If you want to start writing code as quickly as possible, you are advised to link:quickstart.html[read the quick start guide first].

NOTE: No documentation is perfect; neither is this one. If you find errors or omissions, please don’t hesitate to https://github.com/zeux/pugixml/issues/new[submit an issue or open a pull request] with a fix.

[[overview.feedback]]
=== Feedback

If you believe you've found a bug in pugixml (bugs include compilation problems (errors/warnings), crashes, performance degradation and incorrect behavior), please file an issue via https://github.com/zeux/pugixml/issues/new[issue submission form]. Be sure to include the relevant information so that the bug can be reproduced: the version of pugixml, compiler version and target architecture, the code that uses pugixml and exhibits the bug, etc.

Feature requests can be reported the same way as bugs, so if you're missing some functionality in pugixml or if the API is rough in some places and you can suggest an improvement, https://github.com/zeux/pugixml/issues/new[file an issue]. However please note that there are many factors when considering API changes (compatibility with previous versions, API redundancy, etc.), so generally features that can be implemented via a small function without pugixml modification are not accepted. However, all rules have exceptions.

If you have a contribution to pugixml, such as build script for some build system/IDE, or a well-designed set of helper functions, or a binding to some language other than C{plus}{plus}, please https://github.com/zeux/pugixml/issues/new[file an issue or open a pull request]. Your contribution has to be distributed under the terms of a license that's compatible with pugixml license; i.e. GPL/LGPL licensed code is not accepted.

If filing an issue is not possible due to privacy or other concerns, you can contact pugixml author by e-mail directly: arseny.kapoulkine@gmail.com.

[[overview.thanks]]
=== Acknowledgments

pugixml could not be developed without the help from many people; some of them are listed in this section. If you've played a part in pugixml development and you can not find yourself on this list, I'm truly sorry; please <<email,send me an e-mail>> so I can fix this.

Thanks to *Kristen Wegner* for pugxml parser, which was used as a basis for pugixml.

Thanks to *Neville Franks* for contributions to pugxml parser.

Thanks to *Artyom Palvelev* for suggesting a lazy gap contraction approach.

Thanks to *Vyacheslav Egorov* for documentation proofreading and fuzz testing.

[[overview.license]]
=== License

The pugixml library is distributed under the MIT license:

....
Copyright (c) 2006-2015 Arseny Kapoulkine

Permission is hereby granted, free of charge, to any person
obtaining a copy of this software and associated documentation
files (the "Software"), to deal in the Software without
restriction, including without limitation the rights to use,
copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the
Software is furnished to do so, subject to the following
conditions:

The above copyright notice and this permission notice shall be
included in all copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
OTHER DEALINGS IN THE SOFTWARE.
....

This means that you can freely use pugixml in your applications, both open-source and proprietary. If you use pugixml in a product, it is sufficient to add an acknowledgment like this to the product distribution:
 
....
This software is based on pugixml library (http://pugixml.org).
pugixml is Copyright (C) 2006-2015 Arseny Kapoulkine.
....

[[install]]
== Installation

[[install.getting]]
=== Getting pugixml

pugixml is distributed in source form. You can either download a source distribution or clone the Git repository.

[[install.getting.source]]
==== Source distributions

You can download the latest source distribution as an archive:

https://github.com/zeux/pugixml/releases/download/v{version}/pugixml-{version}.zip[pugixml-{version}.zip] (Windows line endings)
/
https://github.com/zeux/pugixml/releases/download/v{version}/pugixml-{version}.tar.gz[pugixml-{version}.tar.gz] (Unix line endings)

The distribution contains library source, documentation (the manual you're reading now and the quick start guide) and some code examples. After downloading the distribution, install pugixml by extracting all files from the compressed archive.

If you need an older version, you can download it from the https://github.com/zeux/pugixml/releases[version archive].

[[install.getting.git]]
==== Git repository

The Git repository is located at https://github.com/zeux/pugixml/. There is a Git tag "v\{version\}" for each version; also there is the "latest" tag, which always points to the latest stable release.

For example, to checkout the current version, you can use this command:

[source,bash,subs="attributes"]
----
git clone https://github.com/zeux/pugixml
cd pugixml
git checkout v{version}
----

The repository contains library source, documentation, code examples and full unit test suite.

Use `latest` tag if you want to automatically get new versions. Use other tags if you want to switch to new versions only explicitly. Also please note that the master branch contains the work-in-progress version of the code; while this means that you can get new features and bug fixes from master without waiting for a new release, this also means that occasionally the code can be broken in some configurations.

[[install.getting.subversion]]
==== Subversion repository

You can access the Git repository via Subversion using https://github.com/zeux/pugixml URL. For example, to checkout the current version, you can use this command:

[source,bash,subs="attributes"]
----
svn checkout https://github.com/zeux/pugixml/tags/v{version} pugixml
----

[[install.getting.packages]]
==== Packages

pugixml is available as a package via various package managers. Note that most packages are maintained separately from the main repository so they do not necessarily contain the latest version.

Here's an incomplete list of pugixml packages in various systems:

* Linux (http://packages.ubuntu.com/search?keywords=pugixml[Ubuntu], https://tracker.debian.org/pkg/pugixml[Debian], https://apps.fedoraproject.org/packages/pugixml[Fedora], https://aur.archlinux.org/packages/pugixml/[Arch Linux], other http://pkgs.org/search/pugixml[distributions])
* http://fbsdmon.org/ports/textproc/pugixml[FreeBSD]
* OSX, via http://brewformulas.org/Pugixml[Homebrew]
* Windows, via https://www.nuget.org/packages/pugixml/[NuGet]

[[install.building]]
=== Building pugixml

pugixml is distributed in source form without any pre-built binaries; you have to build them yourself.
 
The complete pugixml source consists of three files - one source file, `pugixml.cpp`, and two header files, `pugixml.hpp` and `pugiconfig.hpp`. `pugixml.hpp` is the primary header which you need to include in order to use pugixml classes/functions; `pugiconfig.hpp` is a supplementary configuration file (see <<install.building.config>>). The rest of this guide assumes that `pugixml.hpp` is either in the current directory or in one of include directories of your projects, so that `#include "pugixml.hpp"` can find the header; however you can also use relative path (i.e. `#include "../libs/pugixml/src/pugixml.hpp"`) or include directory-relative path (i.e. `#include <xml/thirdparty/pugixml/src/pugixml.hpp>`).
 
[[install.building.embed]]
==== Building pugixml as a part of another static library/executable

The easiest way to build pugixml is to compile the source file, `pugixml.cpp`, along with the existing library/executable. This process depends on the method of building your application; for example, if you're using Microsoft Visual Studio footnote:[All trademarks used are properties of their respective owners.], Apple Xcode, Code::Blocks or any other IDE, just add `pugixml.cpp` to one of your projects.

If you're using Microsoft Visual Studio and the project has precompiled headers turned on, you'll see the following error messages:

----
pugixml.cpp(3477) : fatal error C1010: unexpected end of file while looking for precompiled header. Did you forget to add '#include "stdafx.h"' to your source?
----

The correct way to resolve this is to disable precompiled headers for `pugixml.cpp`; you have to set "Create/Use Precompiled Header" option (Properties dialog -> C/C{plus}{plus} -> Precompiled Headers -> Create/Use Precompiled Header) to "Not Using Precompiled Headers". You'll have to do it for all project configurations/platforms (you can select Configuration "All Configurations" and Platform "All Platforms" before editing the option):

[cols="4*a",frame=none]
|===
| image::vs2005_pch1.png[link="images/vs2005_pch1.png"]
| image::vs2005_pch2.png[link="images/vs2005_pch2.png"]
| image::vs2005_pch3.png[link="images/vs2005_pch3.png"]
| image::vs2005_pch4.png[link="images/vs2005_pch4.png"]
|===
 
[[install.building.static]]
==== Building pugixml as a standalone static library
 
It's possible to compile pugixml as a standalone static library. This process depends on the method of building your application; pugixml distribution comes with project files for several popular IDEs/build systems. There are project files for Apple XCode, Code::Blocks, Codelite, Microsoft Visual Studio 2005, 2008, 2010+, and configuration scripts for CMake and premake4. You're welcome to submit project files/build scripts for other software; see <<overview.feedback>>. 

There are two projects for each version of Microsoft Visual Studio: one for dynamically linked CRT, which has a name like `pugixml_vs2008.vcproj`, and another one for statically linked CRT, which has a name like `pugixml_vs2008_static.vcproj`. You should select the version that matches the CRT used in your application; the default option for new projects created by Microsoft Visual Studio is dynamically linked CRT, so unless you changed the defaults, you should use the version with dynamic CRT (i.e. `pugixml_vs2008.vcproj` for Microsoft Visual Studio 2008).

In addition to adding pugixml project to your workspace, you'll have to make sure that your application links with pugixml library. If you're using Microsoft Visual Studio 2005/2008, you can add a dependency from your application project to pugixml one. If you're using Microsoft Visual Studio 2010+, you'll have to add a reference to your application project instead. For other IDEs/systems, consult the relevant documentation.

[cols="4*a",frame=none,options=header]
|===
2+| Microsoft Visual Studio 2005/2008
2+| Microsoft Visual Studio 2010+
| image::vs2005_link1.png[link="images/vs2005_link1.png"]
| image::vs2005_link2.png[link="images/vs2005_link2.png"]
| image::vs2010_link1.png[link="images/vs2010_link1.png"]
| image::vs2010_link2.png[link="images/vs2010_link2.png"]
|===

[[install.building.shared]]
==== Building pugixml as a standalone shared library
 
It's possible to compile pugixml as a standalone shared library. The process is usually similar to the static library approach; however, no preconfigured projects/scripts are included into pugixml distribution, so you'll have to do it yourself. Generally, if you're using GCC-based toolchain, the process does not differ from building any other library as DLL (adding -shared to compilation flags should suffice); if you're using MSVC-based toolchain, you'll have to explicitly mark exported symbols with a declspec attribute. You can do it by defining <<PUGIXML_API,PUGIXML_API>> macro, i.e. via `pugiconfig.hpp`:

[source]
----
#ifdef _DLL
    #define PUGIXML_API __declspec(dllexport)
#else
    #define PUGIXML_API __declspec(dllimport)
#endif
----

CAUTION: If you're using STL-related functions, you should use the shared runtime library to ensure that a single heap is used for STL allocations in your application and in pugixml; in MSVC, this means selecting the 'Multithreaded DLL' or 'Multithreaded Debug DLL' to 'Runtime library' property (`/MD` or `/MDd` linker switch). You should also make sure that your runtime library choice is consistent between different projects.

[[install.building.header]]
==== Using pugixml in header-only mode

[[PUGIXML_HEADER_ONLY]]
It's possible to use pugixml in header-only mode. This means that all source code for pugixml will be included in every translation unit that includes `pugixml.hpp`. This is how most of Boost and STL libraries work.

Note that there are advantages and drawbacks of this approach. Header mode may improve tree traversal/modification performance (because many simple functions will be inlined), if your compiler toolchain does not support link-time optimization, or if you have it turned off (with link-time optimization the performance should be similar to non-header mode). However, since compiler now has to compile pugixml source once for each translation unit that includes it, compilation times may increase noticeably. If you want to use pugixml in header mode but do not need XPath support, you can consider disabling it by using <<PUGIXML_NO_XPATH,PUGIXML_NO_XPATH>> define to improve compilation time.

To enable header-only mode, you have to define `PUGIXML_HEADER_ONLY`. You can either do it in `pugiconfig.hpp`, or provide them via compiler command-line.

Note that it is safe to compile `pugixml.cpp` if `PUGIXML_HEADER_ONLY` is defined - so if you want to i.e. use header-only mode only in Release configuration, you
can include pugixml.cpp in your project (see <<install.building.embed>>), and conditionally enable header-only mode in `pugiconfig.hpp` like this:

[source]
----
#ifndef _DEBUG
    #define PUGIXML_HEADER_ONLY
#endif
----

[[install.building.config]]
==== Additional configuration options

pugixml uses several defines to control the compilation process. There are two ways to define them: either put the needed definitions to `pugiconfig.hpp` (it has some examples that are commented out) or provide them via compiler command-line. Consistency is important: the definitions should match in all source files that include `pugixml.hpp` (including pugixml sources) throughout the application. Adding defines to `pugiconfig.hpp` lets you guarantee this, unless your macro definition is wrapped in preprocessor `#if`/`#ifdef` directive and this directive is not consistent. `pugiconfig.hpp` will never contain anything but comments, which means that when upgrading to a new version, you can safely leave your modified version intact.

[[PUGIXML_WCHAR_MODE]]`PUGIXML_WCHAR_MODE` define toggles between UTF-8 style interface (the in-memory text encoding is assumed to be UTF-8, most functions use `char` as character type) and UTF-16/32 style interface (the in-memory text encoding is assumed to be UTF-16/32, depending on `wchar_t` size, most functions use `wchar_t` as character type). See <<dom.unicode>> for more details.

[[PUGIXML_COMPACT]]`PUGIXML_COMPACT` define activates a different internal representation of document storage that is much more memory efficient for documents with a lot of markup (i.e. nodes and attributes), but is slightly slower to parse and access. For details see <<dom.memory.compact>>.

[[PUGIXML_NO_XPATH]]`PUGIXML_NO_XPATH` define disables XPath. Both XPath interfaces and XPath implementation are excluded from compilation. This option is provided in case you do not need XPath functionality and need to save code space.

[[PUGIXML_NO_STL]]`PUGIXML_NO_STL` define disables use of STL in pugixml. The functions that operate on STL types are no longer present (i.e. load/save via iostream) if this macro is defined. This option is provided in case your target platform does not have a standard-compliant STL implementation.

[[PUGIXML_NO_EXCEPTIONS]]`PUGIXML_NO_EXCEPTIONS` define disables use of exceptions in pugixml. This option is provided in case your target platform does not have exception handling capabilities.

[[PUGIXML_API]]`PUGIXML_API`, [[PUGIXML_CLASS]]`PUGIXML_CLASS` and [[PUGIXML_FUNCTION]]`PUGIXML_FUNCTION` defines let you specify custom attributes (i.e. declspec or calling conventions) for pugixml classes and non-member functions. In absence of `PUGIXML_CLASS` or `PUGIXML_FUNCTION` definitions, `PUGIXML_API` definition is used instead. For example, to specify fixed calling convention, you can define `PUGIXML_FUNCTION` to i.e. `__fastcall`. Another example is DLL import/export attributes in MSVC (see <<install.building.shared>>).

NOTE: In that example `PUGIXML_API` is inconsistent between several source files; this is an exception to the consistency rule.

[[PUGIXML_MEMORY_PAGE_SIZE]]`PUGIXML_MEMORY_PAGE_SIZE`, [[PUGIXML_MEMORY_OUTPUT_STACK]]`PUGIXML_MEMORY_OUTPUT_STACK` and [[PUGIXML_MEMORY_XPATH_PAGE_SIZE]]`PUGIXML_MEMORY_XPATH_PAGE_SIZE` can be used to customize certain important sizes to optimize memory usage for the application-specific patterns. For details see <<dom.memory.tuning>>.

[[PUGIXML_HAS_LONG_LONG]]`PUGIXML_HAS_LONG_LONG` define enables support for `long long` type in pugixml. This define is automatically enabled if your platform is known to have `long long` support (i.e. has C{plus}{plus}11 support or uses a reasonably modern version of a known compiler); if pugixml does not recognize that your platform supports `long long` but in fact it does, you can enable the define manually.
 
[[install.portability]]
=== Portability

pugixml is written in standard-compliant C{plus}{plus} with some compiler-specific workarounds where appropriate. pugixml is compatible with the C{plus}{plus}11 standard, but does not require C{plus}{plus}11 support. Each version is tested with a unit test suite with code coverage exceeding 99%.

pugixml runs on a variety of desktop platforms (including Microsoft Windows, Linux, FreeBSD, Apple MacOSX and Sun Solaris), game consoles (inclusing Microsoft Xbox 360, Microsoft Xbox One, Nintendo Wii, Sony Playstation Portable and Sony Playstation 3) and mobile platforms (including Android, iOS, BlackBerry, Samsung bada and Microsoft Windows CE).

pugixml supports various architectures, such as x86/x86-64, PowerPC, ARM, MIPS and SPARC. In general it should run on any architecture since it does not use architecture-specific code and does not rely on features such as unaligned memory access.

pugixml can be compiled using any C++ compiler; it was tested with all versions of Microsoft Visual C{plus}{plus} from 6.0 up to 2015, GCC from 3.4 up to 5.2, Clang from 3.2 up to 3.7, as well as a variety of other compilers (e.g. Borland C{plus}{plus}, Digital Mars C{plus}{plus}, Intel C{plus}{plus}, Metrowerks CodeWarrior and PathScale). The code is written to avoid compilation warnings even on reasonably high warning levels.

Note that some platforms may have very bare-bones support of C++; in some cases you'll have to use `PUGIXML_NO_STL` and/or `PUGIXML_NO_EXCEPTIONS` to compile without issues. This mostly applies to old game consoles and embedded systems.

[[dom]]
== Document object model

pugixml stores XML data in DOM-like way: the entire XML document (both document structure and element data) is stored in memory as a tree. The tree can be loaded from a character stream (file, string, C{plus}{plus} I/O stream), then traversed with the special API or XPath expressions. The whole tree is mutable: both node structure and node/attribute data can be changed at any time. Finally, the result of document transformations can be saved to a character stream (file, C{plus}{plus} I/O stream or custom transport).

[[dom.tree]]
=== Tree structure

The XML document is represented with a tree data structure. The root of the tree is the document itself, which corresponds to C{plus}{plus} type <<xml_document,xml_document>>. Document has one or more child nodes, which correspond to C{plus}{plus} type <<xml_node,xml_node>>. Nodes have different types; depending on a type, a node can have a collection of child nodes, a collection of attributes, which correspond to C{plus}{plus} type <<xml_attribute,xml_attribute>>, and some additional data (i.e. name).

[[xml_node_type]]
The tree nodes can be of one of the following types (which together form the enumeration `xml_node_type`):

* Document node ([[node_document]]`node_document`) - this is the root of the tree, which consists of several child nodes. This node corresponds to <<xml_document,xml_document>> class; note that <<xml_document,xml_document>> is a sub-class of <<xml_node,xml_node>>, so the entire node interface is also available. However, document node is special in several ways, which are covered below. There can be only one document node in the tree; document node does not have any XML representation.

* Element/tag node ([[node_element]]`node_element`) - this is the most common type of node, which represents XML elements. Element nodes have a name, a collection of attributes and a collection of child nodes (both of which may be empty). The attribute is a simple name/value pair. The example XML representation of element nodes is as follows:
+
----
<node attr="value"><child/></node>
----
+
There are two element nodes here: one has name `"node"`, single attribute `"attr"` and single child `"child"`, another has name `"child"` and does not have any attributes or child nodes.

* Plain character data nodes ([[node_pcdata]]`node_pcdata`) represent plain text in XML. PCDATA nodes have a value, but do not have a name or children/attributes. Note that *plain character data is not a part of the element node but instead has its own node*; an element node can have several child PCDATA nodes. The example XML representation of text nodes is as follows:
+
----
<node> text1 <child/> text2 </node>
----
+
Here `"node"` element has three children, two of which are PCDATA nodes with values `" text1 "` and `" text2 "`.

* Character data nodes ([[node_cdata]]`node_cdata`) represent text in XML that is quoted in a special way. CDATA nodes do not differ from PCDATA nodes except in XML representation - the above text example looks like this with CDATA:
+
----
<node> <![CDATA[text1]]> <child/> <![CDATA[text2]]> </node>
----
+
CDATA nodes make it easy to include non-escaped `<`, `&` and `>` characters in plain text. CDATA value can not contain the character sequence `]]>`, since it is used to determine the end of node contents.

* Comment nodes ([[node_comment]]`node_comment`) represent comments in XML. Comment nodes have a value, but do not have a name or children/attributes. The example XML representation of a comment node is as follows:
+
----
<!-- comment text -->
----
+
Here the comment node has value `"comment text"`. By default comment nodes are treated as non-essential part of XML markup and are not loaded during XML parsing. You can override this behavior with <<parse_comments,parse_comments>> flag.

* Processing instruction node ([[node_pi]]`node_pi`) represent processing instructions (PI) in XML. PI nodes have a name and an optional value, but do not have children/attributes. The example XML representation of a PI node is as follows:
+
----
<?name value?>
----
+
Here the name (also called PI target) is `"name"`, and the value is `"value"`. By default PI nodes are treated as non-essential part of XML markup and are not loaded during XML parsing. You can override this behavior with <<parse_pi,parse_pi>> flag.

* Declaration node ([[node_declaration]]`node_declaration`) represents document declarations in XML. Declaration nodes have a name (`"xml"`) and an optional collection of attributes, but do not have value or children. There can be only one declaration node in a document; moreover, it should be the topmost node (its parent should be the document). The example XML representation of a declaration node is as follows:
+
----
<?xml version="1.0"?>
----
+
Here the node has name `"xml"` and a single attribute with name `"version"` and value `"1.0"`. By default declaration nodes are treated as non-essential part of XML markup and are not loaded during XML parsing. You can override this behavior with <<parse_declaration,parse_declaration>> flag. Also, by default a dummy declaration is output when XML document is saved unless there is already a declaration in the document; you can disable this with <<format_no_declaration,format_no_declaration>> flag.

* Document type declaration node ([[node_doctype]]`node_doctype`) represents document type declarations in XML. Document type declaration nodes have a value, which corresponds to the entire document type contents; no additional nodes are created for inner elements like `<!ENTITY>`. There can be only one document type declaration node in a document; moreover, it should be the topmost node (its parent should be the document). The example XML representation of a document type declaration node is as follows:
+
----
<!DOCTYPE greeting [ <!ELEMENT greeting (#PCDATA)> ]>
----
+
Here the node has value `"greeting [ <!ELEMENT greeting (#PCDATA)> ]"`. By default document type declaration nodes are treated as non-essential part of XML markup and are not loaded during XML parsing. You can override this behavior with <<parse_doctype,parse_doctype>> flag.

Finally, here is a complete example of XML document and the corresponding tree representation (link:samples/tree.xml[]):

[cols="2*a",frame=none]
|===
|
[source,xml]
----
<?xml version="1.0"?>
<mesh name="mesh_root">
    <!-- here is a mesh node -->
    some text
    <![CDATA[someothertext]]>
    some more text
    <node attr1="value1" attr2="value2" />
    <node attr1="value2">
        <innernode/>
    </node>
</mesh>
<?include somedata?>
----
|
image::dom_tree.png[link="images/dom_tree.png"]
|===

[[dom.cpp]]
=== C{plus}{plus} interface

NOTE: All pugixml classes and functions are located in the `pugi` namespace; you have to either use explicit name qualification (i.e. `pugi::xml_node`), or to gain access to relevant symbols via `using` directive (i.e. `using pugi::xml_node;` or `using namespace pugi;`). The namespace will be omitted from all declarations in this documentation hereafter; all code examples will use fully qualified names.

Despite the fact that there are several node types, there are only three C{plus}{plus} classes representing the tree (`xml_document`, `xml_node`, `xml_attribute`); some operations on `xml_node` are only valid for certain node types. The classes are described below.

[[xml_document]][[xml_document::document_element]]
`xml_document` is the owner of the entire document structure; it is a non-copyable class. The interface of `xml_document` consists of loading functions (see <<loading>>), saving functions (see <<saving>>) and the entire interface of `xml_node`, which allows for document inspection and/or modification. Note that while `xml_document` is a sub-class of `xml_node`, `xml_node` is not a polymorphic type; the inheritance is present only to simplify usage. Alternatively you can use the `document_element` function to get the element node that's the immediate child of the document.

[[xml_document::ctor]][[xml_document::dtor]][[xml_document::reset]]
Default constructor of `xml_document` initializes the document to the tree with only a root node (document node). You can then populate it with data using either tree modification functions or loading functions; all loading functions destroy the previous tree with all occupied memory, which puts existing node/attribute handles for this document to invalid state. If you want to destroy the previous tree, you can use the `xml_document::reset` function; it destroys the tree and replaces it with either an empty one or a copy of the specified document. Destructor of `xml_document` also destroys the tree, thus the lifetime of the document object should exceed the lifetimes of any node/attribute handles that point to the tree.

CAUTION: While technically node/attribute handles can be alive when the tree they're referring to is destroyed, calling any member function for these handles results in undefined behavior. Thus it is recommended to make sure that the document is destroyed only after all references to its nodes/attributes are destroyed.

[[xml_node]][[xml_node::type]]
`xml_node` is the handle to document node; it can point to any node in the document, including the document node itself. There is a common interface for nodes of all types; the actual <<xml_node_type,node type>> can be queried via the `xml_node::type()` method. Note that `xml_node` is only a handle to the actual node, not the node itself - you can have several `xml_node` handles pointing to the same underlying object. Destroying `xml_node` handle does not destroy the node and does not remove it from the tree. The size of `xml_node` is equal to that of a pointer, so it is nothing more than a lightweight wrapper around a pointer; you can safely pass or return `xml_node` objects by value without additional overhead.

[[node_null]]
There is a special value of `xml_node` type, known as null node or empty node (such nodes have type `node_null`). It does not correspond to any node in any document, and thus resembles null pointer. However, all operations are defined on empty nodes; generally the operations don't do anything and return empty nodes/attributes or empty strings as their result (see documentation for specific functions for more detailed information). This is useful for chaining calls; i.e. you can get the grandparent of a node like so: `node.parent().parent()`; if a node is a null node or it does not have a parent, the first `parent()` call returns null node; the second `parent()` call then also returns null node, which makes error handling easier.

[[xml_attribute]]
`xml_attribute` is the handle to an XML attribute; it has the same semantics as `xml_node`, i.e. there can be several `xml_attribute` handles pointing to the same underlying object and there is a special null attribute value, which propagates to function results.

[[xml_attribute::ctor]][[xml_node::ctor]]
Both `xml_node` and `xml_attribute` have the default constructor which initializes them to null objects.

[[xml_attribute::comparison]][[xml_node::comparison]]
`xml_node` and `xml_attribute` try to behave like pointers, that is, they can be compared with other objects of the same type, making it possible to use them as keys in associative containers. All handles to the same underlying object are equal, and any two handles to different underlying objects are not equal. Null handles only compare as equal to themselves. The result of relational comparison can not be reliably determined from the order of nodes in file or in any other way. Do not use relational comparison operators except for search optimization (i.e. associative container keys).

[[xml_attribute::hash_value]][[xml_node::hash_value]]
If you want to use `xml_node` or `xml_attribute` objects as keys in hash-based associative containers, you can use the `hash_value` member functions. They return the hash values that are guaranteed to be the same for all handles to the same underlying object. The hash value for null handles is 0. Note that hash value does not depend on the content of the node, only on the location of the underlying structure in memory - this means that loading the same document twice will likely produce different hash values, and copying the node will not preserve the hash.

[[xml_attribute::unspecified_bool_type]][[xml_node::unspecified_bool_type]][[xml_attribute::empty]][[xml_node::empty]]
Finally handles can be implicitly cast to boolean-like objects, so that you can test if the node/attribute is empty with the following code: `if (node) { ... }` or `if (!node) { ... } else { ... }`. Alternatively you can check if a given `xml_node`/`xml_attribute` handle is null by calling the following methods:

[source]
----
bool xml_attribute::empty() const;
bool xml_node::empty() const;
----

Nodes and attributes do not exist without a document tree, so you can't create them without adding them to some document. Once underlying node/attribute objects are destroyed, the handles to those objects become invalid. While this means that destruction of the entire tree invalidates all node/attribute handles, it also means that destroying a subtree (by calling <<xml_node::remove_child,xml_node::remove_child>>) or removing an attribute invalidates the corresponding handles. There is no way to check handle validity; you have to ensure correctness through external mechanisms.

[[dom.unicode]]
=== Unicode interface

There are two choices of interface and internal representation when configuring pugixml: you can either choose the UTF-8 (also called char) interface or UTF-16/32 (also called wchar_t) one. The choice is controlled via <<PUGIXML_WCHAR_MODE,PUGIXML_WCHAR_MODE>> define; you can set it via `pugiconfig.hpp` or via preprocessor options, as discussed in <<install.building.config>>. If this define is set, the wchar_t interface is used; otherwise (by default) the char interface is used. The exact wide character encoding is assumed to be either UTF-16 or UTF-32 and is determined based on the size of `wchar_t` type.

NOTE: If the size of `wchar_t` is 2, pugixml assumes UTF-16 encoding instead of UCS-2, which means that some characters are represented as two code points.

All tree functions that work with strings work with either C-style null terminated strings or STL strings of the selected character type. For example, node name accessors look like this in char mode:

[source]
----
const char* xml_node::name() const;
bool xml_node::set_name(const char* value);
----

and like this in wchar_t mode:

[source]
----
const wchar_t* xml_node::name() const;
bool xml_node::set_name(const wchar_t* value);
----

[[char_t]][[string_t]]
There is a special type, `pugi::char_t`, that is defined as the character type and depends on the library configuration; it will be also used in the documentation hereafter. There is also a type `pugi::string_t`, which is defined as the STL string of the character type; it corresponds to `std::string` in char mode and to `std::wstring` in wchar_t mode.

In addition to the interface, the internal implementation changes to store XML data as `pugi::char_t`; this means that these two modes have different memory usage characteristics - generally UTF-8 mode is more memory and performance efficient, especially if `sizeof(wchar_t)` is 4. The conversion to `pugi::char_t` upon document loading and from `pugi::char_t` upon document saving happen automatically, which also carries minor performance penalty. The general advice however is to select the character mode based on usage scenario, i.e. if UTF-8 is inconvenient to process and most of your XML data is non-ASCII, wchar_t mode is probably a better choice.

[[as_utf8]][[as_wide]]
There are cases when you'll have to convert string data between UTF-8 and wchar_t encodings; the following helper functions are provided for such purposes:

[source]
----
std::string as_utf8(const wchar_t* str);
std::wstring as_wide(const char* str);
----

Both functions accept a null-terminated string as an argument `str`, and return the converted string. `as_utf8` performs conversion from UTF-16/32 to UTF-8; `as_wide` performs conversion from UTF-8 to UTF-16/32. Invalid UTF sequences are silently discarded upon conversion. `str` has to be a valid string; passing null pointer results in undefined behavior. There are also two overloads with the same semantics which accept a string as an argument:

[source]
----
std::string as_utf8(const std::wstring& str);
std::wstring as_wide(const std::string& str);
----

[NOTE]
====
Most examples in this documentation assume char interface and therefore will not compile with <<PUGIXML_WCHAR_MODE,PUGIXML_WCHAR_MODE>>. This is done to simplify the documentation; usually the only changes you'll have to make is to pass `wchar_t` string literals, i.e. instead of

`xml_node node = doc.child("bookstore").find_child_by_attribute("book", "id", "12345");`

you'll have to use

`xml_node node = doc.child(L"bookstore").find_child_by_attribute(L"book", L"id", L"12345");`
====
 
[[dom.thread]]
=== Thread-safety guarantees

Almost all functions in pugixml have the following thread-safety guarantees:

* it is safe to call free (non-member) functions from multiple threads
* it is safe to perform concurrent read-only accesses to the same tree (all constant member functions do not modify the tree)
* it is safe to perform concurrent read/write accesses, if there is only one read or write access to the single tree at a time

Concurrent modification and traversing of a single tree requires synchronization, for example via reader-writer lock. Modification includes altering document structure and altering individual node/attribute data, i.e. changing names/values.

The only exception is <<set_memory_management_functions,set_memory_management_functions>>; it modifies global variables and as such is not thread-safe. Its usage policy has more restrictions, see <<dom.memory.custom>>.

[[dom.exception]]
=== Exception guarantees

With the exception of XPath, pugixml itself does not throw any exceptions. Additionally, most pugixml functions have a no-throw exception guarantee.

This is not applicable to functions that operate on STL strings or IOstreams; such functions have either strong guarantee (functions that operate on strings) or basic guarantee (functions that operate on streams). Also functions that call user-defined callbacks (i.e. <<xml_node::traverse,xml_node::traverse>> or <<xml_node::find_node,xml_node::find_node>>) do not provide any exception guarantees beyond the ones provided by the callback.

If exception handling is not disabled with <<PUGIXML_NO_EXCEPTIONS,PUGIXML_NO_EXCEPTIONS>> define, XPath functions may throw <<xpath_exception,xpath_exception>> on parsing errors; also, XPath functions may throw `std::bad_alloc` in low memory conditions. Still, XPath functions provide strong exception guarantee.

[[dom.memory]]
=== Memory management

pugixml requests the memory needed for document storage in big chunks, and allocates document data inside those chunks. This section discusses replacing functions used for chunk allocation and internal memory management implementation.

[[dom.memory.custom]]
==== Custom memory allocation/deallocation functions

[[allocation_function]][[deallocation_function]]
All memory for tree structure, tree data and XPath objects is allocated via globally specified functions, which default to malloc/free. You can set your own allocation functions with set_memory_management function. The function interfaces are the same as that of malloc/free:

[source]
----
typedef void* (*allocation_function)(size_t size);
typedef void (*deallocation_function)(void* ptr);
----

[[set_memory_management_functions]][[get_memory_allocation_function]][[get_memory_deallocation_function]]
You can use the following accessor functions to change or get current memory management functions:

[source]
----
void set_memory_management_functions(allocation_function allocate, deallocation_function deallocate);
allocation_function get_memory_allocation_function();
deallocation_function get_memory_deallocation_function();
----

Allocation function is called with the size (in bytes) as an argument and should return a pointer to a memory block with alignment that is suitable for storage of primitive types (usually a maximum of `void*` and `double` types alignment is sufficient) and size that is greater than or equal to the requested one. If the allocation fails, the function has to either return null pointer or to throw an exception.

Deallocation function is called with the pointer that was returned by some call to allocation function; it is never called with a null pointer. If memory management functions are not thread-safe, library thread safety is not guaranteed.

This is a simple example of custom memory management (link:samples/custom_memory_management.cpp[]):

[source,indent=0]
----
include::samples/custom_memory_management.cpp[tags=decl] 
----
[source,indent=0]
----
include::samples/custom_memory_management.cpp[tags=call] 
----

When setting new memory management functions, care must be taken to make sure that there are no live pugixml objects. Otherwise when the objects are destroyed, the new deallocation function will be called with the memory obtained by the old allocation function, resulting in undefined behavior.

[[dom.memory.tuning]]
==== Memory consumption tuning

There are several important buffering optimizations in pugixml that rely on predefined constants. These constants have default values that were tuned for common usage patterns; for some applications, changing these constants might improve memory consumption or increase performance. Changing these constants is not recommended unless their default values result in visible problems.

These constants can be tuned via configuration defines, as discussed in <<install.building.config>>; it is recommended to set them in `pugiconfig.hpp`.

* `PUGIXML_MEMORY_PAGE_SIZE` controls the page size for document memory allocation. Memory for node/attribute objects is allocated in pages of the specified size. The default size is 32 Kb; for some applications the size is too large (i.e. embedded systems with little heap space or applications that keep lots of XML documents in memory). A minimum size of 1 Kb is recommended.

* `PUGIXML_MEMORY_OUTPUT_STACK` controls the cumulative stack space required to output the node. Any output operation (i.e. saving a subtree to file) uses an internal buffering scheme for performance reasons. The default size is 10 Kb; if you're using node output from threads with little stack space, decreasing this value can prevent stack overflows. A minimum size of 1 Kb is recommended.

* `PUGIXML_MEMORY_XPATH_PAGE_SIZE` controls the page size for XPath memory allocation. Memory for XPath query objects as well as internal memory for XPath evaluation is allocated in pages of the specified size. The default size is 4 Kb; if you have a lot of resident XPath query objects, you might need to decrease the size to improve memory consumption. A minimum size of 256 bytes is recommended.

[[dom.memory.internals]]
==== Document memory management internals

Constructing a document object using the default constructor does not result in any allocations; document node is stored inside the <<xml_document,xml_document>> object.

When the document is loaded from file/buffer, unless an inplace loading function is used (see <<loading.memory>>), a complete copy of character stream is made; all names/values of nodes and attributes are allocated in this buffer. This buffer is allocated via a single large allocation and is only freed when document memory is reclaimed (i.e. if the <<xml_document,xml_document>> object is destroyed or if another document is loaded in the same object). Also when loading from file or stream, an additional large allocation may be performed if encoding conversion is required; a temporary buffer is allocated, and it is freed before load function returns.

All additional memory, such as memory for document structure (node/attribute objects) and memory for node/attribute names/values is allocated in pages on the order of 32 Kb; actual objects are allocated inside the pages using a memory management scheme optimized for fast allocation/deallocation of many small objects. Because of the scheme specifics, the pages are only destroyed if all objects inside them are destroyed; also, generally destroying an object does not mean that subsequent object creation will reuse the same memory. This means that it is possible to devise a usage scheme which will lead to higher memory usage than expected; one example is adding a lot of nodes, and them removing all even numbered ones; not a single page is reclaimed in the process. However this is an example specifically crafted to produce unsatisfying behavior; in all practical usage scenarios the memory consumption is less than that of a general-purpose allocator because allocation meta-data is very small in size.

[[dom.memory.compact]]
==== Compact mode

By default nodes and attributes are optimized for efficiency of access. This can cause them to take a significant amount of memory - for documents with a lot of nodes and not a lot of contents (short attribute values/node text), and depending on the pointer size, the document structure can take noticeably more memory than the document itself (e.g. on a 64-bit platform in UTF-8 mode a markup-heavy document with the file size of 2.1 Mb can use 2.1 Mb for document buffer and 8.3 Mb for document structure).

If you are processing big documents or your platform is memory constrained and you're willing to sacrifice a bit of performance for memory, you can compile pugixml with `PUGIXML_COMPACT` define which will activate compact mode. Compact mode uses a different representation of the document structure that assumes locality of reference between nodes and attributes to optimize memory usage. As a result you get significantly smaller node/attribute objects; usually most objects in most documents don't require additional storage, but in the worst case - if assumptions about locality of reference don't hold - additional memory will be allocated to store the extra data required.

The compact storage supports all existing operations - including tree modification - with the same amortized complexity (that is, all basic document manipulations are still O(1) on average). The operations are slightly slower; you can usually expect 10-50% slowdown in terms of processing time unless your processing was memory-bound.

On 32-bit architectures document structure in compact mode is typically reduced by around 2.5x; on 64-bit architectures the ratio is around 5x. Thus for big markup-heavy documents compact mode can make the difference between the processing of a multi-gigabyte document running completely from RAM vs requiring swapping to disk. Even if the document fits into memory, compact storage can use CPU caches more efficiently by taking less space and causing less cache/TLB misses.

[[loading]]
== Loading document

pugixml provides several functions for loading XML data from various places - files, C{plus}{plus} iostreams, memory buffers. All functions use an extremely fast non-validating parser. This parser is not fully W3C conformant - it can load any valid XML document, but does not perform some well-formedness checks. While considerable effort is made to reject invalid XML documents, some validation is not performed for performance reasons. Also some XML transformations (i.e. EOL handling or attribute value normalization) can impact parsing speed and thus can be disabled. However for vast majority of XML documents there is no performance difference between different parsing options. Parsing options also control whether certain XML nodes are parsed; see <<loading.options>> for more information.

XML data is always converted to internal character format (see <<dom.unicode>>) before parsing. pugixml supports all popular Unicode encodings (UTF-8, UTF-16 (big and little endian), UTF-32 (big and little endian); UCS-2 is naturally supported since it's a strict subset of UTF-16) and handles all encoding conversions automatically. Unless explicit encoding is specified, loading functions perform automatic encoding detection based on first few characters of XML data, so in almost all cases you do not have to specify document encoding. Encoding conversion is described in more detail in <<loading.encoding>>.

[[loading.file]]
=== Loading document from file

[[xml_document::load_file]][[xml_document::load_file_wide]]
The most common source of XML data is files; pugixml provides dedicated functions for loading an XML document from file:

[source]
----
xml_parse_result xml_document::load_file(const char* path, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
xml_parse_result xml_document::load_file(const wchar_t* path, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
----
    
These functions accept the file path as its first argument, and also two optional arguments, which specify parsing options (see <<loading.options>>) and input data encoding (see <<loading.encoding>>). The path has the target operating system format, so it can be a relative or absolute one, it should have the delimiters of the target system, it should have the exact case if the target file system is case-sensitive, etc.

File path is passed to the system file opening function as is in case of the first function (which accepts `const char* path`); the second function either uses a special file opening function if it is provided by the runtime library or converts the path to UTF-8 and uses the system file opening function.

`load_file` destroys the existing document tree and then tries to load the new tree from the specified file. The result of the operation is returned in an <<xml_parse_result,xml_parse_result>> object; this object contains the operation status and the related information (i.e. last successfully parsed position in the input file, if parsing fails). See <<loading.errors>> for error handling details.

This is an example of loading XML document from file (link:samples/load_file.cpp[]):

[source,indent=0]
----
include::samples/load_file.cpp[tags=code] 
----

[[loading.memory]]
=== Loading document from memory

[[xml_document::load_buffer]][[xml_document::load_buffer_inplace]][[xml_document::load_buffer_inplace_own]]
Sometimes XML data should be loaded from some other source than a file, i.e. HTTP URL; also you may want to load XML data from file using non-standard functions, i.e. to use your virtual file system facilities or to load XML from GZip-compressed files. All these scenarios require loading document from memory. First you should prepare a contiguous memory block with all XML data; then you have to invoke one of buffer loading functions. These functions will handle the necessary encoding conversions, if any, and then will parse the data into the corresponding XML tree. There are several buffer loading functions, which differ in the behavior and thus in performance/memory usage:

[source]
----
xml_parse_result xml_document::load_buffer(const void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
xml_parse_result xml_document::load_buffer_inplace(void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
xml_parse_result xml_document::load_buffer_inplace_own(void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
----

All functions accept the buffer which is represented by a pointer to XML data, `contents`, and data size in bytes. Also there are two optional arguments, which specify parsing options (see <<loading.options>>) and input data encoding (see <<loading.encoding>>). The buffer does not have to be zero-terminated.

`load_buffer` function works with immutable buffer - it does not ever modify the buffer. Because of this restriction it has to create a private buffer and copy XML data to it before parsing (applying encoding conversions if necessary). This copy operation carries a performance penalty, so inplace functions are provided - `load_buffer_inplace` and `load_buffer_inplace_own` store the document data in the buffer, modifying it in the process. In order for the document to stay valid, you have to make sure that the buffer's lifetime exceeds that of the tree if you're using inplace functions. In addition to that, `load_buffer_inplace` does not assume ownership of the buffer, so you'll have to destroy it yourself; `load_buffer_inplace_own` assumes ownership of the buffer and destroys it once it is not needed. This means that if you're using `load_buffer_inplace_own`, you have to allocate memory with pugixml allocation function (you can get it via <<get_memory_allocation_function,get_memory_allocation_function>>).

The best way from the performance/memory point of view is to load document using `load_buffer_inplace_own`; this function has maximum control of the buffer with XML data so it is able to avoid redundant copies and reduce peak memory usage while parsing. This is the recommended function if you have to load the document from memory and performance is critical.

[[xml_document::load_string]]
There is also a simple helper function for cases when you want to load the XML document from null-terminated character string:

[source]
----
xml_parse_result xml_document::load_string(const char_t* contents, unsigned int options = parse_default);
----

It is equivalent to calling `load_buffer` with `size` being either `strlen(contents)` or `wcslen(contents) * sizeof(wchar_t)`, depending on the character type. This function assumes native encoding for input data, so it does not do any encoding conversion. In general, this function is fine for loading small documents from string literals, but has more overhead and less functionality than the buffer loading functions.

This is an example of loading XML document from memory using different functions (link:samples/load_memory.cpp[]):

[source,indent=0]
----
include::samples/load_memory.cpp[tags=decl] 
----
[source,indent=0]
----
include::samples/load_memory.cpp[tags=load_buffer] 
----
[source,indent=0]
----
include::samples/load_memory.cpp[tags=load_buffer_inplace_begin] 

include::samples/load_memory.cpp[tags=load_buffer_inplace_end] 
----
[source,indent=0]
----
include::samples/load_memory.cpp[tags=load_buffer_inplace_own] 
----
[source,indent=0]
----
include::samples/load_memory.cpp[tags=load_string] 
----

[[loading.stream]]
=== Loading document from C{plus}{plus} IOstreams

[[xml_document::load_stream]]
To enhance interoperability, pugixml provides functions for loading document from any object which implements C{plus}{plus} `std::istream` interface. This allows you to load documents from any standard C{plus}{plus} stream (i.e. file stream) or any third-party compliant implementation (i.e. Boost Iostreams). There are two functions, one works with narrow character streams, another handles wide character ones:

[source]
----
xml_parse_result xml_document::load(std::istream& stream, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
xml_parse_result xml_document::load(std::wistream& stream, unsigned int options = parse_default);
----

`load` with `std::istream` argument loads the document from stream from the current read position to the end, treating the stream contents as a byte stream of the specified encoding (with encoding autodetection as necessary). Thus calling `xml_document::load` on an opened `std::ifstream` object is equivalent to calling `xml_document::load_file`.

`load` with `std::wstream` argument treats the stream contents as a wide character stream (encoding is always <<encoding_wchar,encoding_wchar>>). Because of this, using `load` with wide character streams requires careful (usually platform-specific) stream setup (i.e. using the `imbue` function). Generally use of wide streams is discouraged, however it provides you the ability to load documents from non-Unicode encodings, i.e. you can load Shift-JIS encoded data if you set the correct locale.

This is a simple example of loading XML document from file using streams (link:samples/load_stream.cpp[]); read the sample code for more complex examples involving wide streams and locales:

[source,indent=0]
----
include::samples/load_stream.cpp[tags=code] 
----

[[loading.errors]]
=== Handling parsing errors

[[xml_parse_result]]
All document loading functions return the parsing result via `xml_parse_result` object. It contains parsing status, the offset of last successfully parsed character from the beginning of the source stream, and the encoding of the source stream:

[source]
----
struct xml_parse_result
{
    xml_parse_status status;
    ptrdiff_t offset;
    xml_encoding encoding;

    operator bool() const;
    const char* description() const;
};
----

[[xml_parse_status]][[xml_parse_result::status]]
Parsing status is represented as the `xml_parse_status` enumeration and can be one of the following:

* [[status_ok]]`status_ok` means that no error was encountered during parsing; the source stream represents the valid XML document which was fully parsed and converted to a tree.

* [[status_file_not_found]]`status_file_not_found` is only returned by `load_file` function and means that file could not be opened.
* [[status_io_error]]`status_io_error` is returned by `load_file` function and by `load` functions with `std::istream`/`std::wstream` arguments; it means that some I/O error has occurred during reading the file/stream.
* [[status_out_of_memory]]`status_out_of_memory` means that there was not enough memory during some allocation; any allocation failure during parsing results in this error.
* [[status_internal_error]]`status_internal_error` means that something went horribly wrong; currently this error does not occur

* [[status_unrecognized_tag]]`status_unrecognized_tag` means that parsing stopped due to a tag with either an empty name or a name which starts with incorrect character, such as `#`.
* [[status_bad_pi]]`status_bad_pi` means that parsing stopped due to incorrect document declaration/processing instruction
* [[status_bad_comment]]`status_bad_comment`, [[status_bad_cdata]]`status_bad_cdata`, [[status_bad_doctype]]`status_bad_doctype` and [[status_bad_pcdata]]`status_bad_pcdata` mean that parsing stopped due to the invalid construct of the respective type
* [[status_bad_start_element]]`status_bad_start_element` means that parsing stopped because starting tag either had no closing `>` symbol or contained some incorrect symbol
* [[status_bad_attribute]]`status_bad_attribute` means that parsing stopped because there was an incorrect attribute, such as an attribute without value or with value that is not quoted (note that `<node attr=1>` is incorrect in XML)
* [[status_bad_end_element]]`status_bad_end_element` means that parsing stopped because ending tag had incorrect syntax (i.e. extra non-whitespace symbols between tag name and `>`)
* [[status_end_element_mismatch]]`status_end_element_mismatch` means that parsing stopped because the closing tag did not match the opening one (i.e. `<node></nedo>`) or because some tag was not closed at all
* [[status_no_document_element]]`status_no_document_element` means that no element nodes were discovered during parsing; this usually indicates an empty or invalid document

[[xml_parse_result::description]]
`description()` member function can be used to convert parsing status to a string; the returned message is always in English, so you'll have to write your own function if you need a localized string. However please note that the exact messages returned by `description()` function may change from version to version, so any complex status handling should be based on `status` value. Note that `description()` returns a `char` string even in `PUGIXML_WCHAR_MODE`; you'll have to call <<as_wide,as_wide>> to get the `wchar_t` string.

If parsing failed because the source data was not a valid XML, the resulting tree is not destroyed - despite the fact that load function returns error, you can use the part of the tree that was successfully parsed. Obviously, the last element may have an unexpected name/value; for example, if the attribute value does not end with the necessary quotation mark, like in `<node attr="value>some data</node>` example, the value of attribute `attr` will contain the string `value>some data</node>`.

[[xml_parse_result::offset]]
In addition to the status code, parsing result has an `offset` member, which contains the offset of last successfully parsed character if parsing failed because of an error in source data; otherwise `offset` is 0. For parsing efficiency reasons, pugixml does not track the current line during parsing; this offset is in units of <<char_t,pugi::char_t>> (bytes for character mode, wide characters for wide character mode). Many text editors support 'Go To Position' feature - you can use it to locate the exact error position. Alternatively, if you're loading the document from memory, you can display the error chunk along with the error description (see the example code below).

CAUTION: Offset is calculated in the XML buffer in native encoding; if encoding conversion is performed during parsing, offset can not be used to reliably track the error position.

[[xml_parse_result::encoding]]
Parsing result also has an `encoding` member, which can be used to check that the source data encoding was correctly guessed. It is equal to the exact encoding used during parsing (i.e. with the exact endianness); see <<loading.encoding>> for more information.

[[xml_parse_result::bool]]
Parsing result object can be implicitly converted to `bool`; if you do not want to handle parsing errors thoroughly, you can just check the return value of load functions as if it was a `bool`: `if (doc.load_file("file.xml")) { ... } else { ... }`.

This is an example of handling loading errors (link:samples/load_error_handling.cpp[]):

[source,indent=0]
----
include::samples/load_error_handling.cpp[tags=code] 
----

[[loading.options]]
=== Parsing options

All document loading functions accept the optional parameter `options`. This is a bitmask that customizes the parsing process: you can select the node types that are parsed and various transformations that are performed with the XML text. Disabling certain transformations can improve parsing performance for some documents; however, the code for all transformations is very well optimized, and thus the majority of documents won't get any performance benefit. As a rule of thumb, only modify parsing flags if you want to get some nodes in the document that are excluded by default (i.e. declaration or comment nodes).

NOTE: You should use the usual bitwise arithmetics to manipulate the bitmask: to enable a flag, use `mask | flag`; to disable a flag, use `mask & ~flag`.

These flags control the resulting tree contents:

* [[parse_declaration]]`parse_declaration` determines if XML document declaration (node with type <<node_declaration,node_declaration>>) is to be put in DOM tree. If this flag is off, it is not put in the tree, but is still parsed and checked for correctness. This flag is *off* by default.

* [[parse_doctype]]`parse_doctype` determines if XML document type declaration (node with type <<node_doctype,node_doctype>>) is to be put in DOM tree. If this flag is off, it is not put in the tree, but is still parsed and checked for correctness. This flag is *off* by default.

* [[parse_pi]]`parse_pi` determines if processing instructions (nodes with type <<node_pi,node_pi>>) are to be put in DOM tree. If this flag is off, they are not put in the tree, but are still parsed and checked for correctness. Note that `<?xml ...?>` (document declaration) is not considered to be a PI. This flag is *off* by default.

* [[parse_comments]]`parse_comments` determines if comments (nodes with type <<node_comment,node_comment>>) are to be put in DOM tree. If this flag is off, they are not put in the tree, but are still parsed and checked for correctness. This flag is *off* by default.

* [[parse_cdata]]`parse_cdata` determines if CDATA sections (nodes with type <<node_cdata,node_cdata>>) are to be put in DOM tree. If this flag is off, they are not put in the tree, but are still parsed and checked for correctness. This flag is *on* by default.

* [[parse_trim_pcdata]]`parse_trim_pcdata` determines if leading and trailing whitespace characters are to be removed from PCDATA nodes. While for some applications leading/trailing whitespace is significant, often the application only cares about the non-whitespace contents so it's easier to trim whitespace from text during parsing. This flag is *off* by default.

* [[parse_ws_pcdata]]`parse_ws_pcdata` determines if PCDATA nodes (nodes with type <<node_pcdata,node_pcdata>>) that consist only of whitespace characters are to be put in DOM tree. Often whitespace-only data is not significant for the application, and the cost of allocating and storing such nodes (both memory and speed-wise) can be significant. For example, after parsing XML string `<node> <a/> </node>`, `<node>` element will have three children when `parse_ws_pcdata` is set (child with type <<node_pcdata,node_pcdata>> and value `" "`, child with type <<node_element,node_element>> and name `"a"`, and another child with type <<node_pcdata,node_pcdata>> and value `" "`), and only one child when `parse_ws_pcdata` is not set. This flag is *off* by default.

* [[parse_ws_pcdata_single]]`parse_ws_pcdata_single` determines if whitespace-only PCDATA nodes that have no sibling nodes are to be put in DOM tree. In some cases application needs to parse the whitespace-only contents of nodes, i.e. `<node>  </node>`, but is not interested in whitespace markup elsewhere. It is possible to use <<parse_ws_pcdata,parse_ws_pcdata>> flag in this case, but it results in excessive allocations and complicates document processing; this flag can be used to avoid that. As an example, after parsing XML string `<node> <a>  </a> </node>` with `parse_ws_pcdata_single` flag set, `<node>` element will have one child `<a>`, and `<a>` element will have one child with type <<node_pcdata,node_pcdata>> and value `"  "`. This flag has no effect if <<parse_ws_pcdata,parse_ws_pcdata>> is enabled. This flag is *off* by default.

* [[parse_fragment]]`parse_fragment` determines if document should be treated as a fragment of a valid XML. Parsing document as a fragment leads to top-level PCDATA content (i.e. text that is not located inside a node) to be added to a tree, and additionally treats documents without element nodes as valid. This flag is *off* by default.

CAUTION: Using in-place parsing (<<xml_document::load_buffer_inplace,load_buffer_inplace>>) with `parse_fragment` flag may result in the loss of the last character of the buffer if it is a part of PCDATA. Since PCDATA values are null-terminated strings, the only way to resolve this is to provide a null-terminated buffer as an input to `load_buffer_inplace` - i.e. `doc.load_buffer_inplace("test\0", 5, pugi::parse_default | pugi::parse_fragment)`.

These flags control the transformation of tree element contents:

* [[parse_escapes]]`parse_escapes` determines if character and entity references are to be expanded during the parsing process. Character references have the form `&#...;` or `&#x...;` (`...` is Unicode numeric representation of character in either decimal (`&#...;`) or hexadecimal (`&#x...;`) form), entity references are `&amp;lt;`, `&amp;gt;`, `&amp;amp;`, `&amp;apos;` and `&amp;quot;` (note that as pugixml does not handle DTD, the only allowed entities are predefined ones). If character/entity reference can not be expanded, it is left as is, so you can do additional processing later. Reference expansion is performed on attribute values and PCDATA content. This flag is *on* by default.

* [[parse_eol]]`parse_eol` determines if EOL handling (that is, replacing sequences `\r\n` by a single `\n` character, and replacing all standalone `\r` characters by `\n`) is to be performed on input data (that is, comment contents, PCDATA/CDATA contents and attribute values). This flag is *on* by default.

* [[parse_wconv_attribute]]`parse_wconv_attribute` determines if attribute value normalization should be performed for all attributes. This means, that whitespace characters (new line, tab and space) are replaced with space (`' '`). New line characters are always treated as if <<parse_eol,parse_eol>> is set, i.e. `\r\n` is converted to a single space.  This flag is *on* by default.

* [[parse_wnorm_attribute]]`parse_wnorm_attribute` determines if extended attribute value normalization should be performed for all attributes. This means, that after attribute values are normalized as if <<parse_wconv_attribute,parse_wconv_attribute>> was set, leading and trailing space characters are removed, and all sequences of space characters are replaced by a single space character. <<parse_wconv_attribute,parse_wconv_attribute>> has no effect if this flag is on. This flag is *off* by default.

NOTE: `parse_wconv_attribute` option performs transformations that are required by W3C specification for attributes that are declared as CDATA; <<parse_wnorm_attribute,parse_wnorm_attribute>> performs transformations required for NMTOKENS attributes. In the absence of document type declaration all attributes should behave as if they are declared as CDATA, thus <<parse_wconv_attribute,parse_wconv_attribute>> is the default option.

Additionally there are three predefined option masks:

* [[parse_minimal]]`parse_minimal` has all options turned off. This option mask means that pugixml does not add declaration nodes, document type declaration nodes, PI nodes, CDATA sections and comments to the resulting tree and does not perform any conversion for input data, so theoretically it is the fastest mode. However, as mentioned above, in practice <<parse_default,parse_default>> is usually equally fast.

* [[parse_default]]`parse_default` is the default set of flags, i.e. it has all options set to their default values. It includes parsing CDATA sections (comments/PIs are not parsed), performing character and entity reference expansion, replacing whitespace characters with spaces in attribute values and performing EOL handling. Note, that PCDATA sections consisting only of whitespace characters are not parsed (by default) for performance reasons.

* [[parse_full]]`parse_full` is the set of flags which adds nodes of all types to the resulting tree and performs default conversions for input data. It includes parsing CDATA sections, comments, PI nodes, document declaration node and document type declaration node, performing character and entity reference expansion, replacing whitespace characters with spaces in attribute values and performing EOL handling. Note, that PCDATA sections consisting only of whitespace characters are not parsed in this mode.

This is an example of using different parsing options (link:samples/load_options.cpp[]):

[source,indent=0]
----
include::samples/load_options.cpp[tags=code] 
----

[[loading.encoding]]
=== Encodings

[[xml_encoding]]
pugixml supports all popular Unicode encodings (UTF-8, UTF-16 (big and little endian), UTF-32 (big and little endian); UCS-2 is naturally supported since it's a strict subset of UTF-16) and handles all encoding conversions. Most loading functions accept the optional parameter `encoding`. This is a value of enumeration type `xml_encoding`, that can have the following values:

* [[encoding_auto]]`encoding_auto` means that pugixml will try to guess the encoding based on source XML data. The algorithm is a modified version of the one presented in http://www.w3.org/TR/REC-xml/#sec-guessing-no-ext-info[Appendix F.1 of XML recommendation]; it tries to match the first few bytes of input data with the following patterns in strict order:
** If first four bytes match UTF-32 BOM (Byte Order Mark), encoding is assumed to be UTF-32 with the endianness equal to that of BOM;
** If first two bytes match UTF-16 BOM, encoding is assumed to be UTF-16 with the endianness equal to that of BOM;
** If first three bytes match UTF-8 BOM, encoding is assumed to be UTF-8;
** If first four bytes match UTF-32 representation of `<`, encoding is assumed to be UTF-32 with the corresponding endianness;
** If first four bytes match UTF-16 representation of `<?`, encoding is assumed to be UTF-16 with the corresponding endianness;
** If first two bytes match UTF-16 representation of `<`, encoding is assumed to be UTF-16 with the corresponding endianness (this guess may yield incorrect result, but it's better than UTF-8);
** Otherwise encoding is assumed to be UTF-8.

* [[encoding_utf8]]`encoding_utf8` corresponds to UTF-8 encoding as defined in the Unicode standard; UTF-8 sequences with length equal to 5 or 6 are not standard and are rejected.
* [[encoding_utf16_le]]`encoding_utf16_le` corresponds to little-endian UTF-16 encoding as defined in the Unicode standard; surrogate pairs are supported.
* [[encoding_utf16_be]]`encoding_utf16_be` corresponds to big-endian UTF-16 encoding as defined in the Unicode standard; surrogate pairs are supported.
* [[encoding_utf16]]`encoding_utf16` corresponds to UTF-16 encoding as defined in the Unicode standard; the endianness is assumed to be that of the target platform.
* [[encoding_utf32_le]]`encoding_utf32_le` corresponds to little-endian UTF-32 encoding as defined in the Unicode standard.
* [[encoding_utf32_be]]`encoding_utf32_be` corresponds to big-endian UTF-32 encoding as defined in the Unicode standard.
* [[encoding_utf32]]`encoding_utf32` corresponds to UTF-32 encoding as defined in the Unicode standard; the endianness is assumed to be that of the target platform.
* [[encoding_wchar]]`encoding_wchar` corresponds to the encoding of `wchar_t` type; it has the same meaning as either `encoding_utf16` or `encoding_utf32`, depending on `wchar_t` size.
* [[encoding_latin1]]`encoding_latin1` corresponds to ISO-8859-1 encoding (also known as Latin-1).

The algorithm used for `encoding_auto` correctly detects any supported Unicode encoding for all well-formed XML documents (since they start with document declaration) and for all other XML documents that start with `<`; if your XML document does not start with `<` and has encoding that is different from UTF-8, use the specific encoding.

NOTE: The current behavior for Unicode conversion is to skip all invalid UTF sequences during conversion. This behavior should not be relied upon; moreover, in case no encoding conversion is performed, the invalid sequences are not removed, so you'll get them as is in node/attribute contents.

[[loading.w3c]]
=== Conformance to W3C specification

pugixml is not fully W3C conformant - it can load any valid XML document, but does not perform some well-formedness checks. While considerable effort is made to reject invalid XML documents, some validation is not performed because of performance reasons.

There is only one non-conformant behavior when dealing with valid XML documents: pugixml does not use information supplied in document type declaration for parsing. This means that entities declared in DOCTYPE are not expanded, and all attribute/PCDATA values are always processed in a uniform way that depends only on parsing options.

As for rejecting invalid XML documents, there are a number of incompatibilities with W3C specification, including:

* Multiple attributes of the same node can have equal names.
* All non-ASCII characters are treated in the same way as symbols of English alphabet, so some invalid tag names are not rejected.
* Attribute values which contain `<` are not rejected.
* Invalid entity/character references are not rejected and are instead left as is.
* Comment values can contain `--`.
* XML data is not required to begin with document declaration; additionally, document declaration can appear after comments and other nodes.
* Invalid document type declarations are silently ignored in some cases.

[[access]]
== Accessing document data

pugixml features an extensive interface for getting various types of data from the document and for traversing the document. This section provides documentation for all such functions that do not modify the tree except for XPath-related functions; see <<xpath>> for XPath reference. As discussed in <<dom.cpp>>, there are two types of handles to tree data - <<xml_node,xml_node>> and <<xml_attribute,xml_attribute>>. The handles have special null (empty) values which propagate through various functions and thus are useful for writing more concise code; see <<node_null,this description>> for details. The documentation in this section will explicitly state the results of all function in case of null inputs.

[import samples/traverse_base.cpp]

[[access.basic]]
=== Basic traversal functions

[[xml_node::parent]][[xml_node::first_child]][[xml_node::last_child]][[xml_node::next_sibling]][[xml_node::previous_sibling]][[xml_node::first_attribute]][[xml_node::last_attribute]][[xml_attribute::next_attribute]][[xml_attribute::previous_attribute]]
The internal representation of the document is a tree, where each node has a list of child nodes (the order of children corresponds to their order in the XML representation), and additionally element nodes have a list of attributes, which is also ordered. Several functions are provided in order to let you get from one node in the tree to the other. These functions roughly correspond to the internal representation, and thus are usually building blocks for other methods of traversing (i.e. XPath traversals are based on these functions).
 
[source]
----
xml_node xml_node::parent() const;
xml_node xml_node::first_child() const;
xml_node xml_node::last_child() const;
xml_node xml_node::next_sibling() const;
xml_node xml_node::previous_sibling() const;

xml_attribute xml_node::first_attribute() const;
xml_attribute xml_node::last_attribute() const;
xml_attribute xml_attribute::next_attribute() const;
xml_attribute xml_attribute::previous_attribute() const;
----

`parent` function returns the node's parent; all non-null nodes except the document have non-null parent. `first_child` and `last_child` return the first and last child of the node, respectively; note that only document nodes and element nodes can have non-empty child node list. If node has no children, both functions return null nodes. `next_sibling` and `previous_sibling` return the node that's immediately to the right/left of this node in the children list, respectively - for example, in `<a/><b/><c/>`, calling `next_sibling` for a handle that points to `<b/>` results in a handle pointing to `<c/>`, and calling `previous_sibling` results in handle pointing to `<a/>`. If node does not have next/previous sibling (this happens if it is the last/first node in the list, respectively), the functions return null nodes. `first_attribute`, `last_attribute`, `next_attribute` and `previous_attribute` functions behave similarly to the corresponding child node functions and allow to iterate through attribute list in the same way.

NOTE: Because of memory consumption reasons, attributes do not have a link to their parent nodes. Thus there is no `xml_attribute::parent()` function.

Calling any of the functions above on the null handle results in a null handle - i.e. `node.first_child().next_sibling()` returns the second child of `node`, and null handle if `node` is null, has no children at all or if it has only one child node.

With these functions, you can iterate through all child nodes and display all attributes like this (link:samples/traverse_base.cpp[]):

[source,indent=0]
----
include::samples/traverse_base.cpp[tags=basic] 
----

[[access.nodedata]]
=== Getting node data

[[xml_node::name]][[xml_node::value]]
Apart from structural information (parent, child nodes, attributes), nodes can have name and value, both of which are strings. Depending on node type, name or value may be absent. <<node_document,node_document>> nodes do not have a name or value, <<node_element,node_element>> and <<node_declaration,node_declaration>> nodes always have a name but never have a value, <<node_pcdata,node_pcdata>>, <<node_cdata,node_cdata>>, <<node_comment,node_comment>> and <<node_doctype,node_doctype>> nodes never have a name but always have a value (it may be empty though), <<node_pi,node_pi>> nodes always have a name and a value (again, value may be empty). In order to get node's name or value, you can use the following functions:

[source]
----
const char_t* xml_node::name() const;
const char_t* xml_node::value() const;
----

In case node does not have a name or value or if the node handle is null, both functions return empty strings - they never return null pointers.

[[xml_node::child_value]]
It is common to store data as text contents of some node - i.e. `<node><description>This is a node</description></node>`. In this case, `<description>` node does not have a value, but instead has a child of type <<node_pcdata,node_pcdata>> with value `"This is a node"`. pugixml provides several helper functions to parse such data:

[source]
----
const char_t* xml_node::child_value() const;
const char_t* xml_node::child_value(const char_t* name) const;
xml_text xml_node::text() const;
----

`child_value()` returns the value of the first child with type <<node_pcdata,node_pcdata>> or <<node_cdata,node_cdata>>; `child_value(name)` is a simple wrapper for `child(name).child_value()`. For the above example, calling `node.child_value("description")` and `description.child_value()` will both produce string `"This is a node"`. If there is no child with relevant type, or if the handle is null, `child_value` functions return empty string.

`text()` returns a special object that can be used for working with PCDATA contents in more complex cases than just retrieving the value; it is described in <<access.text>> sections.

There is an example of using some of these functions <<code_traverse_base_data,at the end of the next section>>.

[[access.attrdata]]
=== Getting attribute data

[[xml_attribute::name]][[xml_attribute::value]]
All attributes have name and value, both of which are strings (value may be empty). There are two corresponding accessors, like for `xml_node`:

[source]
----
const char_t* xml_attribute::name() const;
const char_t* xml_attribute::value() const;
----

In case the attribute handle is null, both functions return empty strings - they never return null pointers.

[[xml_attribute::as_string]]
If you need a non-empty string if the attribute handle is null (for example, you need to get the option value from XML attribute, but if it is not specified, you need it to default to `"sorted"` instead of `""`), you can use `as_string` accessor:

[source]
----
const char_t* xml_attribute::as_string(const char_t* def = "") const;
----

It returns `def` argument if the attribute handle is null. If you do not specify the argument, the function is equivalent to `value()`.

[[xml_attribute::as_int]][[xml_attribute::as_uint]][[xml_attribute::as_double]][[xml_attribute::as_float]][[xml_attribute::as_bool]][[xml_attribute::as_llong]][[xml_attribute::as_ullong]]
In many cases attribute values have types that are not strings - i.e. an attribute may always contain values that should be treated as integers, despite the fact that they are represented as strings in XML. pugixml provides several accessors that convert attribute value to some other type:
 
[source]
----
int xml_attribute::as_int(int def = 0) const;
unsigned int xml_attribute::as_uint(unsigned int def = 0) const;
double xml_attribute::as_double(double def = 0) const;
float xml_attribute::as_float(float def = 0) const;
bool xml_attribute::as_bool(bool def = false) const;
long long xml_attribute::as_llong(long long def = 0) const;
unsigned long long xml_attribute::as_ullong(unsigned long long def = 0) const;
----

`as_int`, `as_uint`, `as_llong`, `as_ullong`, `as_double` and `as_float` convert attribute values to numbers. If attribute handle is null or attribute value is empty, `def` argument is returned (which is 0 by default). Otherwise, all leading whitespace characters are truncated, and the remaining string is parsed as an integer number in either decimal or hexadecimal form (applicable to `as_int`, `as_uint`, `as_llong` and `as_ullong`; hexadecimal format is used if the number has `0x` or `0X` prefix) or as a floating point number in either decimal or scientific form (`as_double` or `as_float`). Any extra characters are silently discarded, i.e. `as_int` will return `1` for string `"1abc"`.

In case the input string contains a number that is out of the target numeric range, the result is undefined.

CAUTION: Number conversion functions depend on current C locale as set with `setlocale`, so may return unexpected results if the locale is different from `"C"`.

`as_bool` converts attribute value to boolean as follows: if attribute handle is null, `def` argument is returned (which is `false` by default). If attribute value is empty, `false` is returned. Otherwise, `true` is returned if the first character is one of `'1', 't', 'T', 'y', 'Y'`. This means that strings like `"true"` and `"yes"` are recognized as `true`, while strings like `"false"` and `"no"` are recognized as `false`. For more complex matching you'll have to write your own function.

NOTE: `as_llong` and `as_ullong` are only available if your platform has reliable support for the `long long` type, including string conversions.

[[code_traverse_base_data]]
This is an example of using these functions, along with node data retrieval ones (link:samples/traverse_base.cpp[]):

[source,indent=0]
----
include::samples/traverse_base.cpp[tags=data] 
----

[[access.contents]]
=== Contents-based traversal functions

[[xml_node::child]][[xml_node::attribute]][[xml_node::next_sibling_name]][[xml_node::previous_sibling_name]]
Since a lot of document traversal consists of finding the node/attribute with the correct name, there are special functions for that purpose:

[source]
----
xml_node xml_node::child(const char_t* name) const;
xml_attribute xml_node::attribute(const char_t* name) const;
xml_node xml_node::next_sibling(const char_t* name) const;
xml_node xml_node::previous_sibling(const char_t* name) const;
----

`child` and `attribute` return the first child/attribute with the specified name; `next_sibling` and `previous_sibling` return the first sibling in the corresponding direction with the specified name. All string comparisons are case-sensitive. In case the node handle is null or there is no node/attribute with the specified name, null handle is returned.

`child` and `next_sibling` functions can be used together to loop through all child nodes with the desired name like this:

[source]
----
for (pugi::xml_node tool = tools.child("Tool"); tool; tool = tool.next_sibling("Tool"))
----

[[xml_node::find_child_by_attribute]]
Occasionally the needed node is specified not by the unique name but instead by the value of some attribute; for example, it is common to have node collections with each node having a unique id: `<group><item id="1"/> <item id="2"/></group>`. There are two functions for finding child nodes based on the attribute values:

[source]
----
xml_node xml_node::find_child_by_attribute(const char_t* name, const char_t* attr_name, const char_t* attr_value) const;
xml_node xml_node::find_child_by_attribute(const char_t* attr_name, const char_t* attr_value) const;
----

The three-argument function returns the first child node with the specified name which has an attribute with the specified name/value; the two-argument function skips the name test for the node, which can be useful for searching in heterogeneous collections. If the node handle is null or if no node is found, null handle is returned. All string comparisons are case-sensitive.

In all of the above functions, all arguments have to be valid strings; passing null pointers results in undefined behavior.

This is an example of using these functions (link:samples/traverse_base.cpp[]):

[source,indent=0]
----
include::samples/traverse_base.cpp[tags=contents] 
----

[[access.rangefor]]
=== Range-based for-loop support

[[xml_node::children]][[xml_node::attributes]]
If your C{plus}{plus} compiler supports range-based for-loop (this is a C{plus}{plus}11 feature, at the time of writing it's supported by Microsoft Visual Studio 2012+, GCC 4.6+ and Clang 3.0+), you can use it to enumerate nodes/attributes. Additional helpers are provided to support this; note that they are also compatible with http://www.boost.org/libs/foreach/[Boost Foreach], and possibly other pre-C{plus}{plus}11 foreach facilities.

[source,subs="+quotes"]
----
_implementation_-_defined_-_type_ xml_node::children() const;
_implementation_-_defined_-_type_ xml_node::children(const char_t* name) const;
_implementation_-_defined_-_type_ xml_node::attributes() const;
----

`children` function allows you to enumerate all child nodes; `children` function with `name` argument allows you to enumerate all child nodes with a specific name; `attributes` function allows you to enumerate all attributes of the node. Note that you can also use node object itself in a range-based for construct, which is equivalent to using `children()`.

This is an example of using these functions (link:samples/traverse_rangefor.cpp[]):

[source,indent=0]
----
include::samples/traverse_rangefor.cpp[tags=code] 
----

[[access.iterators]]
=== Traversing node/attribute lists via iterators

[[xml_node_iterator]][[xml_attribute_iterator]][[xml_node::begin]][[xml_node::end]][[xml_node::attributes_begin]][[xml_node::attributes_end]]
Child node lists and attribute lists are simply double-linked lists; while you can use `previous_sibling`/`next_sibling` and other such functions for iteration, pugixml additionally provides node and attribute iterators, so that you can treat nodes as containers of other nodes or attributes:

[source]
----
class xml_node_iterator;
class xml_attribute_iterator;

typedef xml_node_iterator xml_node::iterator;
iterator xml_node::begin() const;
iterator xml_node::end() const;

typedef xml_attribute_iterator xml_node::attribute_iterator;
attribute_iterator xml_node::attributes_begin() const;
attribute_iterator xml_node::attributes_end() const;
----

`begin` and `attributes_begin` return iterators that point to the first node/attribute, respectively; `end` and `attributes_end` return past-the-end iterator for node/attribute list, respectively - this iterator can't be dereferenced, but decrementing it results in an iterator pointing to the last element in the list (except for empty lists, where decrementing past-the-end iterator results in undefined behavior). Past-the-end iterator is commonly used as a termination value for iteration loops (see sample below). If you want to get an iterator that points to an existing handle, you can construct the iterator with the handle as a single constructor argument, like so: `xml_node_iterator(node)`. For `xml_attribute_iterator`, you'll have to provide both an attribute and its parent node.

`begin` and `end` return equal iterators if called on null node; such iterators can't be dereferenced. `attributes_begin` and `attributes_end` behave the same way. For correct iterator usage this means that child node/attribute collections of null nodes appear to be empty.

Both types of iterators have bidirectional iterator semantics (i.e. they can be incremented and decremented, but efficient random access is not supported) and support all usual iterator operations - comparison, dereference, etc. The iterators are invalidated if the node/attribute objects they're pointing to are removed from the tree; adding nodes/attributes does not invalidate any iterators.

Here is an example of using iterators for document traversal (link:samples/traverse_iter.cpp[]):

[source,indent=0]
----
include::samples/traverse_iter.cpp[tags=code] 
----

CAUTION: Node and attribute iterators are somewhere in the middle between const and non-const iterators. While dereference operation yields a non-constant reference to the object, so that you can use it for tree modification operations, modifying this reference using assignment - i.e. passing iterators to a function like `std::sort` - will not give expected results, as assignment modifies local handle that's stored in the iterator.

[[access.walker]]
=== Recursive traversal with xml_tree_walker

[[xml_tree_walker]]
The methods described above allow traversal of immediate children of some node; if you want to do a deep tree traversal, you'll have to do it via a recursive function or some equivalent method. However, pugixml provides a helper for depth-first traversal of a subtree. In order to use it, you have to implement `xml_tree_walker` interface and to call `traverse` function:

[source]
----
class xml_tree_walker
{
public:
    virtual bool begin(xml_node& node);
    virtual bool for_each(xml_node& node) = 0;
    virtual bool end(xml_node& node);

    int depth() const;
};

bool xml_node::traverse(xml_tree_walker& walker);
----

[[xml_tree_walker::begin]][[xml_tree_walker::for_each]][[xml_tree_walker::end]][[xml_node::traverse]]
The traversal is launched by calling `traverse` function on traversal root and proceeds as follows:

* First, `begin` function is called with traversal root as its argument.
* Then, `for_each` function is called for all nodes in the traversal subtree in depth first order, excluding the traversal root. Node is passed as an argument.
* Finally, `end` function is called with traversal root as its argument.

If `begin`, `end` or any of the `for_each` calls return `false`, the traversal is terminated and `false` is returned as the traversal result; otherwise, the traversal results in `true`. Note that you don't have to override `begin` or `end` functions; their default implementations return `true`.

[[xml_tree_walker::depth]]
You can get the node's depth relative to the traversal root at any point by calling `depth` function. It returns `-1` if called from `begin`/`end`, and returns 0-based depth if called from `for_each` - depth is 0 for all children of the traversal root, 1 for all grandchildren and so on.

This is an example of traversing tree hierarchy with xml_tree_walker (link:samples/traverse_walker.cpp[]):

[source,indent=0]
----
include::samples/traverse_walker.cpp[tags=impl] 
----
[source,indent=0]
----
include::samples/traverse_walker.cpp[tags=traverse] 
----

[[access.predicate]]
=== Searching for nodes/attributes with predicates

[[xml_node::find_attribute]][[xml_node::find_child]][[xml_node::find_node]]
While there are existing functions for getting a node/attribute with known contents, they are often not sufficient for simple queries. As an alternative for manual iteration through nodes/attributes until the needed one is found, you can make a predicate and call one of `find_` functions:

[source]
----
template <typename Predicate> xml_attribute xml_node::find_attribute(Predicate pred) const;
template <typename Predicate> xml_node xml_node::find_child(Predicate pred) const;
template <typename Predicate> xml_node xml_node::find_node(Predicate pred) const;
----

The predicate should be either a plain function or a function object which accepts one argument of type `xml_attribute` (for `find_attribute`) or `xml_node` (for `find_child` and `find_node`), and returns `bool`. The predicate is never called with null handle as an argument.

`find_attribute` function iterates through all attributes of the specified node, and returns the first attribute for which the predicate returned `true`. If the predicate returned `false` for all attributes or if there were no attributes (including the case where the node is null), null attribute is returned.

`find_child` function iterates through all child nodes of the specified node, and returns the first node for which the predicate returned `true`. If the predicate returned `false` for all nodes or if there were no child nodes (including the case where the node is null), null node is returned.

`find_node` function performs a depth-first traversal through the subtree of the specified node (excluding the node itself), and returns the first node for which the predicate returned `true`. If the predicate returned `false` for all nodes or if subtree was empty, null node is returned.

This is an example of using predicate-based functions (link:samples/traverse_predicate.cpp[]):

[source,indent=0]
----
include::samples/traverse_predicate.cpp[tags=decl] 
----
[source,indent=0]
----
include::samples/traverse_predicate.cpp[tags=find] 
----

[[access.text]]
=== Working with text contents

[[xml_text]]
It is common to store data as text contents of some node - i.e. `<node><description>This is a node</description></node>`. In this case, `<description>` node does not have a value, but instead has a child of type <<node_pcdata,node_pcdata>> with value `"This is a node"`. pugixml provides a special class, `xml_text`, to work with such data. Working with text objects to modify data is described in <<modify.text,the documentation for modifying document data>>; this section describes the access interface of `xml_text`.

[[xml_node::text]]
You can get the text object from a node by using `text()` method:
    
[source]
----
xml_text xml_node::text() const;
----

If the node has a type `node_pcdata` or `node_cdata`, then the node itself is used to return data; otherwise, a first child node of type `node_pcdata` or `node_cdata` is used.

[[xml_text::empty]][[xml_text::unspecified_bool_type]]
You can check if the text object is bound to a valid PCDATA/CDATA node by using it as a boolean value, i.e. `if (text) { ... }` or `if (!text) { ... }`. Alternatively you can check it by using the `empty()` method:

[source]
----
bool xml_text::empty() const;
----

[[xml_text::get]]
Given a text object, you can get the contents (i.e. the value of PCDATA/CDATA node) by using the following function:

[source]
----
const char_t* xml_text::get() const;
----

In case text object is empty, the function returns an empty string - it never returns a null pointer.

[[xml_text::as_string]][[xml_text::as_int]][[xml_text::as_uint]][[xml_text::as_double]][[xml_text::as_float]][[xml_text::as_bool]][[xml_text::as_llong]][[xml_text::as_ullong]]
If you need a non-empty string if the text object is empty, or if the text contents is actually a number or a boolean that is stored as a string, you can use the following accessors:

[source]
----
const char_t* xml_text::as_string(const char_t* def = "") const;
int xml_text::as_int(int def = 0) const;
unsigned int xml_text::as_uint(unsigned int def = 0) const;
double xml_text::as_double(double def = 0) const;
float xml_text::as_float(float def = 0) const;
bool xml_text::as_bool(bool def = false) const;
long long xml_text::as_llong(long long def = 0) const;
unsigned long long xml_text::as_ullong(unsigned long long def = 0) const;
----

All of the above functions have the same semantics as similar `xml_attribute` members: they return the default argument if the text object is empty, they convert the text contents to a target type using the same rules and restrictions. You can <<xml_attribute::as_int,refer to documentation for the attribute functions>> for details.

[[xml_text::data]]
`xml_text` is essentially a helper class that operates on `xml_node` values. It is bound to a node of type <<node_pcdata,node_pcdata>> or <<node_cdata,node_cdata>>. You can use the following function to retrieve this node:

[source]
----
xml_node xml_text::data() const;
----

Essentially, assuming `text` is an `xml_text` object, calling `text.get()` is equivalent to calling `text.data().value()`.

This is an example of using `xml_text` object (link:samples/text.cpp[]):

[source,indent=0]
----
include::samples/text.cpp[tags=access] 
----

[[access.misc]]
=== Miscellaneous functions

[[xml_node::root]]
If you need to get the document root of some node, you can use the following function:

[source]
----
xml_node xml_node::root() const;
----

This function returns the node with type <<node_document,node_document>>, which is the root node of the document the node belongs to (unless the node is null, in which case null node is returned).

[[xml_node::path]][[xml_node::first_element_by_path]]
While pugixml supports complex XPath expressions, sometimes a simple path handling facility is needed. There are two functions, for getting node path and for converting path to a node:

[source]
----
string_t xml_node::path(char_t delimiter = '/') const;
xml_node xml_node::first_element_by_path(const char_t* path, char_t delimiter = '/') const;
----

Node paths consist of node names, separated with a delimiter (which is `/` by default); also paths can contain self (`.`) and parent (`..`) pseudo-names, so that this is a valid path: `"../../foo/./bar"`. `path` returns the path to the node from the document root, `first_element_by_path` looks for a node represented by a given path; a path can be an absolute one (absolute paths start with the delimiter), in which case the rest of the path is treated as document root relative, and relative to the given node. For example, in the following document: `<a><b><c/></b></a>`, node `<c/>` has path `"a/b/c"`; calling `first_element_by_path` for document with path `"a/b"` results in node `<b/>`; calling `first_element_by_path` for node `<a/>` with path `"../a/./b/../."` results in node `<a/>`; calling `first_element_by_path` with path `"/a"` results in node `<a/>` for any node.

In case path component is ambiguous (if there are two nodes with given name), the first one is selected; paths are not guaranteed to uniquely identify nodes in a document. If any component of a path is not found, the result of `first_element_by_path` is null node; also `first_element_by_path` returns null node for null nodes, in which case the path does not matter. `path` returns an empty string for null nodes. 

NOTE: `path` function returns the result as STL string, and thus is not available if <<PUGIXML_NO_STL,PUGIXML_NO_STL>> is defined.

[[xml_node::offset_debug]]
pugixml does not record row/column information for nodes upon parsing for efficiency reasons. However, if the node has not changed in a significant way since parsing (the name/value are not changed, and the node itself is the original one, i.e. it was not deleted from the tree and re-added later), it is possible to get the offset from the beginning of XML buffer:

[source]
----
ptrdiff_t xml_node::offset_debug() const;
----

If the offset is not available (this happens if the node is null, was not originally parsed from a stream, or has changed in a significant way), the function returns -1. Otherwise it returns the offset to node's data from the beginning of XML buffer in <<char_t,pugi::char_t>> units. For more information on parsing offsets, see <<xml_parse_result::offset,parsing error handling documentation>>.

[[modify]]
== Modifying document data

The document in pugixml is fully mutable: you can completely change the document structure and modify the data of nodes/attributes. This section provides documentation for the relevant functions. All functions take care of memory management and structural integrity themselves, so they always result in structurally valid tree - however, it is possible to create an invalid XML tree (for example, by adding two attributes with the same name or by setting attribute/node name to empty/invalid string). Tree modification is optimized for performance and for memory consumption, so if you have enough memory you can create documents from scratch with pugixml and later save them to file/stream instead of relying on error-prone manual text writing and without too much overhead.

All member functions that change node/attribute data or structure are non-constant and thus can not be called on constant handles. However, you can easily convert constant handle to non-constant one by simple assignment: `void foo(const pugi::xml_node& n) { pugi::xml_node nc = n; }`, so const-correctness here mainly provides additional documentation.

[import samples/modify_base.cpp]

[[modify.nodedata]]
=== Setting node data

[[xml_node::set_name]][[xml_node::set_value]]
As discussed before, nodes can have name and value, both of which are strings. Depending on node type, name or value may be absent. <<node_document,node_document>> nodes do not have a name or value, <<node_element,node_element>> and <<node_declaration,node_declaration>> nodes always have a name but never have a value, <<node_pcdata,node_pcdata>>, <<node_cdata,node_cdata>>, <<node_comment,node_comment>> and <<node_doctype,node_doctype>> nodes never have a name but always have a value (it may be empty though), <<node_pi,node_pi>> nodes always have a name and a value (again, value may be empty). In order to set node's name or value, you can use the following functions:

[source]
----
bool xml_node::set_name(const char_t* rhs);
bool xml_node::set_value(const char_t* rhs);
----

Both functions try to set the name/value to the specified string, and return the operation result. The operation fails if the node can not have name or value (for instance, when trying to call `set_name` on a <<node_pcdata,node_pcdata>> node), if the node handle is null, or if there is insufficient memory to handle the request. The provided string is copied into document managed memory and can be destroyed after the function returns (for example, you can safely pass stack-allocated buffers to these functions). The name/value content is not verified, so take care to use only valid XML names, or the document may become malformed.

This is an example of setting node name and value (link:samples/modify_base.cpp[]):

[source,indent=0]
----
include::samples/modify_base.cpp[tags=node] 
----

[[modify.attrdata]]
=== Setting attribute data

[[xml_attribute::set_name]][[xml_attribute::set_value]]
All attributes have name and value, both of which are strings (value may be empty). You can set them with the following functions:

[source]
----
bool xml_attribute::set_name(const char_t* rhs);
bool xml_attribute::set_value(const char_t* rhs);
----

Both functions try to set the name/value to the specified string, and return the operation result. The operation fails if the attribute handle is null, or if there is insufficient memory to handle the request. The provided string is copied into document managed memory and can be destroyed after the function returns (for example, you can safely pass stack-allocated buffers to these functions). The name/value content is not verified, so take care to use only valid XML names, or the document may become malformed.

In addition to string functions, several functions are provided for handling attributes with numbers and booleans as values:

[source]
----
bool xml_attribute::set_value(int rhs);
bool xml_attribute::set_value(unsigned int rhs);
bool xml_attribute::set_value(double rhs);
bool xml_attribute::set_value(float rhs);
bool xml_attribute::set_value(bool rhs);
bool xml_attribute::set_value(long long rhs);
bool xml_attribute::set_value(unsigned long long rhs);
----
    
The above functions convert the argument to string and then call the base `set_value` function. Integers are converted to a decimal form, floating-point numbers are converted to either decimal or scientific form, depending on the number magnitude, boolean values are converted to either `"true"` or `"false"`.

CAUTION: Number conversion functions depend on current C locale as set with `setlocale`, so may generate unexpected results if the locale is different from `"C"`.

NOTE: `set_value` overloads with `long long` type are only available if your platform has reliable support for the type, including string conversions.

[[xml_attribute::assign]]

For convenience, all `set_value` functions have the corresponding assignment operators:

[source]
----
xml_attribute& xml_attribute::operator=(const char_t* rhs);
xml_attribute& xml_attribute::operator=(int rhs);
xml_attribute& xml_attribute::operator=(unsigned int rhs);
xml_attribute& xml_attribute::operator=(double rhs);
xml_attribute& xml_attribute::operator=(float rhs);
xml_attribute& xml_attribute::operator=(bool rhs);
xml_attribute& xml_attribute::operator=(long long rhs);
xml_attribute& xml_attribute::operator=(unsigned long long rhs);
----

These operators simply call the right `set_value` function and return the attribute they're called on; the return value of `set_value` is ignored, so errors are ignored.

This is an example of setting attribute name and value (link:samples/modify_base.cpp[]):

[source,indent=0]
----
include::samples/modify_base.cpp[tags=attr] 
----

[[modify.add]]
=== Adding nodes/attributes

[[xml_node::prepend_attribute]][[xml_node::append_attribute]][[xml_node::insert_attribute_after]][[xml_node::insert_attribute_before]][[xml_node::prepend_child]][[xml_node::append_child]][[xml_node::insert_child_after]][[xml_node::insert_child_before]]
Nodes and attributes do not exist without a document tree, so you can't create them without adding them to some document. A node or attribute can be created at the end of node/attribute list or before/after some other node:

[source]
----
xml_attribute xml_node::append_attribute(const char_t* name);
xml_attribute xml_node::prepend_attribute(const char_t* name);
xml_attribute xml_node::insert_attribute_after(const char_t* name, const xml_attribute& attr);
xml_attribute xml_node::insert_attribute_before(const char_t* name, const xml_attribute& attr);

xml_node xml_node::append_child(xml_node_type type = node_element);
xml_node xml_node::prepend_child(xml_node_type type = node_element);
xml_node xml_node::insert_child_after(xml_node_type type, const xml_node& node);
xml_node xml_node::insert_child_before(xml_node_type type, const xml_node& node);

xml_node xml_node::append_child(const char_t* name);
xml_node xml_node::prepend_child(const char_t* name);
xml_node xml_node::insert_child_after(const char_t* name, const xml_node& node);
xml_node xml_node::insert_child_before(const char_t* name, const xml_node& node);
----

`append_attribute` and `append_child` create a new node/attribute at the end of the corresponding list of the node the method is called on; `prepend_attribute` and `prepend_child` create a new node/attribute at the beginning of the list; `insert_attribute_after`, `insert_attribute_before`, `insert_child_after` and `insert_attribute_before` add the node/attribute before or after the specified node/attribute.

Attribute functions create an attribute with the specified name; you can specify the empty name and change the name later if you want to. Node functions with the `type` argument create the node with the specified type; since node type can't be changed, you have to know the desired type beforehand. Also note that not all types can be added as children; see below for clarification. Node functions with the `name` argument create the element node (<<node_element,node_element>>) with the specified name.

All functions return the handle to the created object on success, and null handle on failure. There are several reasons for failure:

* Adding fails if the target node is null;
* Only <<node_element,node_element>> nodes can contain attributes, so attribute adding fails if node is not an element;
* Only <<node_document,node_document>> and <<node_element,node_element>> nodes can contain children, so child node adding fails if the target node is not an element or a document;
* <<node_document,node_document>> and <<node_null,node_null>> nodes can not be inserted as children, so passing <<node_document,node_document>> or <<node_null,node_null>> value as `type` results in operation failure;
* <<node_declaration,node_declaration>> nodes can only be added as children of the document node; attempt to insert declaration node as a child of an element node fails;
* Adding node/attribute results in memory allocation, which may fail;
* Insertion functions fail if the specified node or attribute is null or is not in the target node's children/attribute list.

Even if the operation fails, the document remains in consistent state, but the requested node/attribute is not added.

CAUTION: `attribute()` and `child()` functions do not add attributes or nodes to the tree, so code like `node.attribute("id") = 123;` will not do anything if `node` does not have an attribute with name `"id"`. Make sure you're operating with existing attributes/nodes by adding them if necessary.

This is an example of adding new attributes/nodes to the document (link:samples/modify_add.cpp[]):

[source,indent=0]
----
include::samples/modify_add.cpp[tags=code] 
----

[[modify.remove]]
=== Removing nodes/attributes

[[xml_node::remove_attribute]][[xml_node::remove_child]]
If you do not want your document to contain some node or attribute, you can remove it with one of the following functions:

[source]
----
bool xml_node::remove_attribute(const xml_attribute& a);
bool xml_node::remove_child(const xml_node& n);
----

`remove_attribute` removes the attribute from the attribute list of the node, and returns the operation result. `remove_child` removes the child node with the entire subtree (including all descendant nodes and attributes) from the document, and returns the operation result. Removing fails if one of the following is true:

* The node the function is called on is null;
* The attribute/node to be removed is null;
* The attribute/node to be removed is not in the node's attribute/child list.

Removing the attribute or node invalidates all handles to the same underlying object, and also invalidates all iterators pointing to the same object. Removing node also invalidates all past-the-end iterators to its attribute or child node list. Be careful to ensure that all such handles and iterators either do not exist or are not used after the attribute/node is removed.

If you want to remove the attribute or child node by its name, two additional helper functions are available:

[source]
----
bool xml_node::remove_attribute(const char_t* name);
bool xml_node::remove_child(const char_t* name);
----

These functions look for the first attribute or child with the specified name, and then remove it, returning the result. If there is no attribute or child with such name, the function returns `false`; if there are two nodes with the given name, only the first node is deleted. If you want to delete all nodes with the specified name, you can use code like this: `while (node.remove_child("tool")) ;`.

This is an example of removing attributes/nodes from the document (link:samples/modify_remove.cpp[]):

[source,indent=0]
----
include::samples/modify_remove.cpp[tags=code] 
----

[[modify.text]]
=== Working with text contents

pugixml provides a special class, `xml_text`, to work with text contents stored as a value of some node, i.e. `<node><description>This is a node</description></node>`. Working with text objects to retrieve data is described in <<access.text,the documentation for accessing document data>>; this section describes the modification interface of `xml_text`.

[[xml_text::set]]
Once you have an `xml_text` object, you can set the text contents using the following function:

[source]
----
bool xml_text::set(const char_t* rhs);
----

This function tries to set the contents to the specified string, and returns the operation result. The operation fails if the text object was retrieved from a node that can not have a value and is not an element node (i.e. it is a <<node_declaration,node_declaration>> node), if the text object is empty, or if there is insufficient memory to handle the request. The provided string is copied into document managed memory and can be destroyed after the function returns (for example, you can safely pass stack-allocated buffers to this function). Note that if the text object was retrieved from an element node, this function creates the PCDATA child node if necessary (i.e. if the element node does not have a PCDATA/CDATA child already).

[[xml_text::set_value]]
In addition to a string function, several functions are provided for handling text with numbers and booleans as contents:

[source]
----
bool xml_text::set(int rhs);
bool xml_text::set(unsigned int rhs);
bool xml_text::set(double rhs);
bool xml_text::set(float rhs);
bool xml_text::set(bool rhs);
bool xml_text::set(long long rhs);
bool xml_text::set(unsigned long long rhs);
----
    
The above functions convert the argument to string and then call the base `set` function. These functions have the same semantics as similar `xml_attribute` functions. You can <<xml_attribute::set_value,refer to documentation for the attribute functions>> for details.

[[xml_text::assign]]

For convenience, all `set` functions have the corresponding assignment operators:

[source]
----
xml_text& xml_text::operator=(const char_t* rhs);
xml_text& xml_text::operator=(int rhs);
xml_text& xml_text::operator=(unsigned int rhs);
xml_text& xml_text::operator=(double rhs);
xml_text& xml_text::operator=(float rhs);
xml_text& xml_text::operator=(bool rhs);
xml_text& xml_text::operator=(long long rhs);
xml_text& xml_text::operator=(unsigned long long rhs);
----

These operators simply call the right `set` function and return the attribute they're called on; the return value of `set` is ignored, so errors are ignored.

This is an example of using `xml_text` object to modify text contents (link:samples/text.cpp[]):

[source,indent=0]
----
include::samples/text.cpp[tags=modify] 
----

[[modify.clone]]
=== Cloning nodes/attributes

[[xml_node::prepend_copy]][[xml_node::append_copy]][[xml_node::insert_copy_after]][[xml_node::insert_copy_before]]
With the help of previously described functions, it is possible to create trees with any contents and structure, including cloning the existing data. However since this is an often needed operation, pugixml provides built-in node/attribute cloning facilities. Since nodes and attributes do not exist without a document tree, you can't create a standalone copy - you have to immediately insert it somewhere in the tree. For this, you can use one of the following functions:

[source]
----
xml_attribute xml_node::append_copy(const xml_attribute& proto);
xml_attribute xml_node::prepend_copy(const xml_attribute& proto);
xml_attribute xml_node::insert_copy_after(const xml_attribute& proto, const xml_attribute& attr);
xml_attribute xml_node::insert_copy_before(const xml_attribute& proto, const xml_attribute& attr);

xml_node xml_node::append_copy(const xml_node& proto);
xml_node xml_node::prepend_copy(const xml_node& proto);
xml_node xml_node::insert_copy_after(const xml_node& proto, const xml_node& node);
xml_node xml_node::insert_copy_before(const xml_node& proto, const xml_node& node);
----

These functions mirror the structure of `append_child`, `prepend_child`, `insert_child_before` and related functions - they take the handle to the prototype object, which is to be cloned, insert a new attribute/node at the appropriate place, and then copy the attribute data or the whole node subtree to the new object. The functions return the handle to the resulting duplicate object, or null handle on failure.

The attribute is copied along with the name and value; the node is copied along with its type, name and value; additionally attribute list and all children are recursively cloned, resulting in the deep subtree clone. The prototype object can be a part of the same document, or a part of any other document.

The failure conditions resemble those of `append_child`, `insert_child_before` and related functions, <<xml_node::append_child,consult their documentation for more information>>. There are additional caveats specific to cloning functions:

* Cloning null handles results in operation failure;
* Node cloning starts with insertion of the node of the same type as that of the prototype; for this reason, cloning functions can not be directly used to clone entire documents, since <<node_document,node_document>> is not a valid insertion type. The example below provides a workaround.
* It is possible to copy a subtree as a child of some node inside this subtree, i.e. `node.append_copy(node.parent().parent());`. This is a valid operation, and it results in a clone of the subtree in the state before cloning started, i.e. no infinite recursion takes place.

This is an example with one possible implementation of include tags in XML (link:samples/include.cpp[]). It illustrates node cloning and usage of other document modification functions:

[source,indent=0]
----
include::samples/include.cpp[tags=code] 
----

[[modify.move]]
=== Moving nodes

[[xml_node::prepend_move]][[xml_node::append_move]][[xml_node::insert_move_after]][[xml_node::insert_move_before]]
Sometimes instead of cloning a node you need to move an existing node to a different position in a tree. This can be accomplished by copying the node and removing the original; however, this is expensive since it results in a lot of extra operations. For moving nodes within the same document tree, you can use of the following functions instead:

[source]
----
xml_node xml_node::append_move(const xml_node& moved);
xml_node xml_node::prepend_move(const xml_node& moved);
xml_node xml_node::insert_move_after(const xml_node& moved, const xml_node& node);
xml_node xml_node::insert_move_before(const xml_node& moved, const xml_node& node);
----

These functions mirror the structure of `append_copy`, `prepend_copy`, `insert_copy_before` and `insert_copy_after` - they take the handle to the moved object and move it to the appropriate place with all attributes and/or child nodes. The functions return the handle to the resulting object (which is the same as the moved object), or null handle on failure.

The failure conditions resemble those of `append_child`, `insert_child_before` and related functions, <<xml_node::append_child,consult their documentation for more information>>. There are additional caveats specific to moving functions:

* Moving null handles results in operation failure;
* Moving is only possible for nodes that belong to the same document; attempting to move nodes between documents will fail.
* `insert_move_after` and `insert_move_before` functions fail if the moved node is the same as the `node` argument (this operation would be a no-op otherwise).
* It is impossible to move a subtree to a child of some node inside this subtree, i.e. `node.append_move(node.parent().parent());` will fail.

[[modify.fragments]]
=== Assembling document from fragments

[[xml_node::append_buffer]]
pugixml provides several ways to assemble an XML document from other XML documents. Assuming there is a set of document fragments, represented as in-memory buffers, the implementation choices are as follows:

* Use a temporary document to parse the data from a string, then clone the nodes to a destination node. For example:
+
[source]
----
bool append_fragment(pugi::xml_node target, const char* buffer, size_t size)
{
    pugi::xml_document doc;
    if (!doc.load_buffer(buffer, size)) return false;

    for (pugi::xml_node child = doc.first_child(); child; child = child.next_sibling())
        target.append_copy(child);
}
----

* Cache the parsing step - instead of keeping in-memory buffers, keep document objects that already contain the parsed fragment:
+
[source]
----
bool append_fragment(pugi::xml_node target, const pugi::xml_document& cached_fragment)
{
    for (pugi::xml_node child = cached_fragment.first_child(); child; child = child.next_sibling())
        target.append_copy(child);
}
----

* Use `xml_node::append_buffer` directly:
+
[source]
----
xml_parse_result xml_node::append_buffer(const void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
----

The first method is more convenient, but slower than the other two. The relative performance of `append_copy` and `append_buffer` depends on the buffer format - usually `append_buffer` is faster if the buffer is in native encoding (UTF-8 or wchar_t, depending on `PUGIXML_WCHAR_MODE`). At the same time it might be less efficient in terms of memory usage - the implementation makes a copy of the provided buffer, and the copy has the same lifetime as the document - the memory used by that copy will be reclaimed after the document is destroyed, but no sooner. Even deleting all nodes in the document, including the appended ones, won't reclaim the memory.

`append_buffer` behaves in the same way as <<xml_document::load_buffer,xml_document::load_buffer>> - the input buffer is a byte buffer, with size in bytes; the buffer is not modified and can be freed after the function returns.

[[status_append_invalid_root]]
Since `append_buffer` needs to append child nodes to the current node, it only works if the current node is either document or element node. Calling `append_buffer` on a node with any other type results in an error with `status_append_invalid_root` status.

[[saving]]
== Saving document

Often after creating a new document or loading the existing one and processing it, it is necessary to save the result back to file. Also it is occasionally useful to output the whole document or a subtree to some stream; use cases include debug printing, serialization via network or other text-oriented medium, etc. pugixml provides several functions to output any subtree of the document to a file, stream or another generic transport interface; these functions allow to customize the output format (see <<saving.options>>), and also perform necessary encoding conversions (see <<saving.encoding>>). This section documents the relevant functionality.

Before writing to the destination the node/attribute data is properly formatted according to the node type; all special XML symbols, such as `<` and `&`, are properly escaped (unless <<format_no_escapes,format_no_escapes>> flag is set). In order to guard against forgotten node/attribute names, empty node/attribute names are printed as `":anonymous"`. For well-formed output, make sure all node and attribute names are set to meaningful values.

CDATA sections with values that contain `"]]>"` are split into several sections as follows: section with value `"pre]]>post"` is written as `<![CDATA[pre]]]]><![CDATA[>post]]>`. While this alters the structure of the document (if you load the document after saving it, there will be two CDATA sections instead of one), this is the only way to escape CDATA contents.

[[saving.file]]
=== Saving document to a file

[[xml_document::save_file]][[xml_document::save_file_wide]]
If you want to save the whole document to a file, you can use one of the following functions:

[source]
----
bool xml_document::save_file(const char* path, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;
bool xml_document::save_file(const wchar_t* path, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;
----

These functions accept file path as its first argument, and also three optional arguments, which specify indentation and other output options (see <<saving.options>>) and output data encoding (see <<saving.encoding>>). The path has the target operating system format, so it can be a relative or absolute one, it should have the delimiters of the target system, it should have the exact case if the target file system is case-sensitive, etc.

File path is passed to the system file opening function as is in case of the first function (which accepts `const char* path`); the second function either uses a special file opening function if it is provided by the runtime library or converts the path to UTF-8 and uses the system file opening function.

[[xml_writer_file]]
`save_file` opens the target file for writing, outputs the requested header (by default a document declaration is output, unless the document already has one), and then saves the document contents. If the file could not be opened, the function returns `false`. Calling `save_file` is equivalent to creating an `xml_writer_file` object with `FILE*` handle as the only constructor argument and then calling `save`; see <<saving.writer>> for writer interface details.

This is a simple example of saving XML document to file (link:samples/save_file.cpp[]):

[source,indent=0]
----
include::samples/save_file.cpp[tags=code] 
----

[[saving.stream]]
=== Saving document to C{plus}{plus} IOstreams

[[xml_document::save_stream]]
To enhance interoperability pugixml provides functions for saving document to any object which implements C{plus}{plus} `std::ostream` interface. This allows you to save documents to any standard C{plus}{plus} stream (i.e. file stream) or any third-party compliant implementation (i.e. Boost Iostreams). Most notably, this allows for easy debug output, since you can use `std::cout` stream as saving target. There are two functions, one works with narrow character streams, another handles wide character ones:

[source]
----
void xml_document::save(std::ostream& stream, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;
void xml_document::save(std::wostream& stream, const char_t* indent = "\t", unsigned int flags = format_default) const;
----

`save` with `std::ostream` argument saves the document to the stream in the same way as `save_file` (i.e. with requested header and with encoding conversions). On the other hand, `save` with `std::wstream` argument saves the document to the wide stream with <<encoding_wchar,encoding_wchar>> encoding.  Because of this, using `save` with wide character streams requires careful (usually platform-specific) stream setup (i.e. using the `imbue` function). Generally use of wide streams is discouraged, however it provides you with the ability to save documents to non-Unicode encodings, i.e. you can save Shift-JIS encoded data if you set the correct locale.

[[xml_writer_stream]]
Calling `save` with stream target is equivalent to creating an `xml_writer_stream` object with stream as the only constructor argument and then calling `save`; see <<saving.writer>> for writer interface details.

This is a simple example of saving XML document to standard output (link:samples/save_stream.cpp[]):

[source,indent=0]
----
include::samples/save_stream.cpp[tags=code] 
----

[[saving.writer]]
=== Saving document via writer interface

[[xml_document::save]][[xml_writer]][[xml_writer::write]]
All of the above saving functions are implemented in terms of writer interface. This is a simple interface with a single function, which is called several times during output process with chunks of document data as input:

[source]
----
class xml_writer
{
public:
    virtual void write(const void* data, size_t size) = 0;
};

void xml_document::save(xml_writer& writer, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;
----

In order to output the document via some custom transport, for example sockets, you should create an object which implements `xml_writer` interface and pass it to `save` function. `xml_writer::write` function is called with a buffer as an input, where `data` points to buffer start, and `size` is equal to the buffer size in bytes. `write` implementation must write the buffer to the transport; it can not save the passed buffer pointer, as the buffer contents will change after `write` returns. The buffer contains the chunk of document data in the desired encoding.

`write` function is called with relatively large blocks (size is usually several kilobytes, except for the last block that may be small), so there is often no need for additional buffering in the implementation.

This is a simple example of custom writer for saving document data to STL string (link:samples/save_custom_writer.cpp[]); read the sample code for more complex examples:

[source,indent=0]
----
include::samples/save_custom_writer.cpp[tags=code] 
----

[[saving.subtree]]
=== Saving a single subtree

[[xml_node::print]][[xml_node::print_stream]]
While the previously described functions save the whole document to the destination, it is easy to save a single subtree. The following functions are provided:

[source]
----
void xml_node::print(std::ostream& os, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto, unsigned int depth = 0) const;
void xml_node::print(std::wostream& os, const char_t* indent = "\t", unsigned int flags = format_default, unsigned int depth = 0) const;
void xml_node::print(xml_writer& writer, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto, unsigned int depth = 0) const;
----

These functions have the same arguments with the same meaning as the corresponding `xml_document::save` functions, and allow you to save the subtree to either a C{plus}{plus} IOstream or to any object that implements `xml_writer` interface.

Saving a subtree differs from saving the whole document: the process behaves as if <<format_write_bom,format_write_bom>> is off, and <<format_no_declaration,format_no_declaration>> is on, even if actual values of the flags are different. This means that BOM is not written to the destination, and document declaration is only written if it is the node itself or is one of node's children. Note that this also holds if you're saving a document; this example (link:samples/save_subtree.cpp[]) illustrates the difference:

[source,indent=0]
----
include::samples/save_subtree.cpp[tags=code] 
----

[[saving.options]]
=== Output options

All saving functions accept the optional parameter `flags`. This is a bitmask that customizes the output format; you can select the way the document nodes are printed and select the needed additional information that is output before the document contents.

NOTE: You should use the usual bitwise arithmetics to manipulate the bitmask: to enable a flag, use `mask | flag`; to disable a flag, use `mask & ~flag`.

These flags control the resulting tree contents:

* [[format_indent]]`format_indent` determines if all nodes should be indented with the indentation string (this is an additional parameter for all saving functions, and is `"\t"` by default). If this flag is on, the indentation string is printed several times before every node, where the amount of indentation depends on the node's depth relative to the output subtree. This flag has no effect if <<format_raw,format_raw>> is enabled. This flag is *on* by default.

* [[format_indent_attributes]]`format_indent_attributes` determines if all attributes should be printed on a new line, indented with the indentation string according to the attribute's depth. This flag implies <<format_indent,format_indent>>. This flag has no effect if <<format_raw,format_raw>> is enabled. This flag is *off* by default.

* [[format_raw]]`format_raw` switches between formatted and raw output. If this flag is on, the nodes are not indented in any way, and also no newlines that are not part of document text are printed. Raw mode can be used for serialization where the result is not intended to be read by humans; also it can be useful if the document was parsed with <<parse_ws_pcdata,parse_ws_pcdata>> flag, to preserve the original document formatting as much as possible. This flag is *off* by default.

* [[format_no_escapes]]`format_no_escapes` disables output escaping for attribute values and PCDATA contents. If this flag is off, special symbols (`"`, `&`, `<`, `>`) and all non-printable characters (those with codepoint values less than 32) are converted to XML escape sequences (i.e. `&amp;amp;`) during output. If this flag is on, no text processing is performed; therefore, output XML can be malformed if output contents contains invalid symbols (i.e. having a stray `<` in the PCDATA will make the output malformed). This flag is *off* by default.

These flags control the additional output information:

* [[format_no_declaration]]`format_no_declaration` disables default node declaration output. By default, if the document is saved via `save` or `save_file` function, and it does not have any document declaration, a default declaration is output before the document contents. Enabling this flag disables this declaration. This flag has no effect in `xml_node::print` functions: they never output the default declaration. This flag is *off* by default.

* [[format_write_bom]]`format_write_bom` enables Byte Order Mark (BOM) output. By default, no BOM is output, so in case of non UTF-8 encodings the resulting document's encoding may not be recognized by some parsers and text editors, if they do not implement sophisticated encoding detection. Enabling this flag adds an encoding-specific BOM to the output. This flag has no effect in `xml_node::print` functions: they never output the BOM. This flag is *off* by default.

* [[format_save_file_text]]`format_save_file_text` changes the file mode when using `save_file` function. By default, file is opened in binary mode, which means that the output file will
contain platform-independent newline `\n` (ASCII 10). If this flag is on, file is opened in text mode, which on some systems changes the newline format (i.e. on Windows you can use this flag to output XML documents with `\r\n` (ASCII 13 10) newlines. This flag is *off* by default.

Additionally, there is one predefined option mask:

* [[format_default]]`format_default` is the default set of flags, i.e. it has all options set to their default values. It sets formatted output with indentation, without BOM and with default node declaration, if necessary.

This is an example that shows the outputs of different output options (link:samples/save_options.cpp[]):

[source,indent=0]
----
include::samples/save_options.cpp[tags=code] 
----

[[saving.encoding]]
=== Encodings

pugixml supports all popular Unicode encodings (UTF-8, UTF-16 (big and little endian), UTF-32 (big and little endian); UCS-2 is naturally supported since it's a strict subset of UTF-16) and handles all encoding conversions during output. The output encoding is set via the `encoding` parameter of saving functions, which is of type `xml_encoding`. The possible values for the encoding are documented in <<loading.encoding>>; the only flag that has a different meaning is `encoding_auto`.

While all other flags set the exact encoding, `encoding_auto` is meant for automatic encoding detection. The automatic detection does not make sense for output encoding, since there is usually nothing to infer the actual encoding from, so here `encoding_auto` means UTF-8 encoding, which is the most popular encoding for XML data storage. This is also the default value of output encoding; specify another value if you do not want UTF-8 encoded output.

Also note that wide stream saving functions do not have `encoding` argument and always assume <<encoding_wchar,encoding_wchar>> encoding.

NOTE: The current behavior for Unicode conversion is to skip all invalid UTF sequences during conversion. This behavior should not be relied upon; if your node/attribute names do not contain any valid UTF sequences, they may be output as if they are empty, which will result in malformed XML document.

[[saving.declaration]]
=== Customizing document declaration

When you are saving the document using `xml_document::save()` or `xml_document::save_file()`, a default XML document declaration is output, if `format_no_declaration` is not specified and if the document does not have a declaration node. However, the default declaration is not customizable. If you want to customize the declaration output, you need to create the declaration node yourself.

NOTE: By default the declaration node is not added to the document during parsing. If you just need to preserve the original declaration node, you have to add the flag <<parse_declaration,parse_declaration>> to the parsing flags; the resulting document will contain the original declaration node, which will be output during saving.

Declaration node is a node with type <<node_declaration,node_declaration>>; it behaves like an element node in that it has attributes with values (but it does not have child nodes). Therefore setting custom version, encoding or standalone declaration involves adding attributes and setting attribute values.

This is an example that shows how to create a custom declaration node (link:samples/save_declaration.cpp[]):

[source,indent=0]
----
include::samples/save_declaration.cpp[tags=code] 
----

[[xpath]]
== XPath

If the task at hand is to select a subset of document nodes that match some criteria, it is possible to code a function using the existing traversal functionality for any practical criteria. However, often either a data-driven approach is desirable, in case the criteria are not predefined and come from a file, or it is inconvenient to use traversal interfaces and a higher-level DSL is required. There is a standard language for XML processing, XPath, that can be useful for these cases. pugixml implements an almost complete subset of XPath 1.0. Because of differences in document object model and some performance implications, there are minor violations of the official specifications, which can be found in <<xpath.w3c>>. The rest of this section describes the interface for XPath functionality. Please note that if you wish to learn to use XPath language, you have to look for other tutorials or manuals; for example, you can read http://www.w3schools.com/xpath/[W3Schools XPath tutorial], http://www.tizag.com/xmlTutorial/xpathtutorial.php[XPath tutorial at tizag.com], and http://www.w3.org/TR/xpath/[the XPath 1.0 specification].

[[xpath.types]]
=== XPath types

[[xpath_value_type]][[xpath_type_number]][[xpath_type_string]][[xpath_type_boolean]][[xpath_type_node_set]][[xpath_type_none]]
Each XPath expression can have one of the following types: boolean, number, string or node set. Boolean type corresponds to `bool` type, number type corresponds to `double` type, string type corresponds to either `std::string` or `std::wstring`, depending on whether <<dom.unicode,wide character interface is enabled>>, and node set corresponds to <<xpath_node_set,xpath_node_set>> type. There is an enumeration, `xpath_value_type`, which can take the values `xpath_type_boolean`, `xpath_type_number`, `xpath_type_string` or `xpath_type_node_set`, accordingly.

[[xpath_node]][[xpath_node::node]][[xpath_node::attribute]][[xpath_node::parent]]
Because an XPath node can be either a node or an attribute, there is a special type, `xpath_node`, which is a discriminated union of these types. A value of this type contains two node handles, one of `xml_node` type, and another one of `xml_attribute` type; at most one of them can be non-null. The accessors to get these handles are available:

[source]
----
xml_node xpath_node::node() const;
xml_attribute xpath_node::attribute() const;
----

XPath nodes can be null, in which case both accessors return null handles.

Note that as per XPath specification, each XPath node has a parent, which can be retrieved via this function:

[source]
----
xml_node xpath_node::parent() const;
----

`parent` function returns the node's parent if the XPath node corresponds to `xml_node` handle (equivalent to `node().parent()`), or the node to which the attribute belongs to, if the XPath node corresponds to `xml_attribute` handle. For null nodes, `parent` returns null handle.

[[xpath_node::unspecified_bool_type]][[xpath_node::comparison]]
Like node and attribute handles, XPath node handles can be implicitly cast to boolean-like object to check if it is a null node, and also can be compared for equality with each other.

[[xpath_node::ctor]]
You can also create XPath nodes with one of the three constructors: the default constructor, the constructor that takes node argument, and the constructor that takes attribute and node arguments (in which case the attribute must belong to the attribute list of the node). The constructor from `xml_node` is implicit, so you can usually pass `xml_node` to functions that expect `xpath_node`. Apart from that you usually don't need to create your own XPath node objects, since they are returned to you via selection functions.

[[xpath_node_set]]
XPath expressions operate not on single nodes, but instead on node sets. A node set is a collection of nodes, which can be optionally ordered in either a forward document order or a reverse one. Document order is defined in XPath specification; an XPath node is before another node in document order if it appears before it in XML representation of the corresponding document.

[[xpath_node_set::const_iterator]][[xpath_node_set::begin]][[xpath_node_set::end]]
Node sets are represented by `xpath_node_set` object, which has an interface that resembles one of sequential random-access containers. It has an iterator type along with usual begin/past-the-end iterator accessors:

[source]
----
typedef const xpath_node* xpath_node_set::const_iterator;
const_iterator xpath_node_set::begin() const;
const_iterator xpath_node_set::end() const;
----

[[xpath_node_set::index]][[xpath_node_set::size]][[xpath_node_set::empty]]
And it also can be iterated via indices, just like `std::vector`:

[source]
----
const xpath_node& xpath_node_set::operator[](size_t index) const;
size_t xpath_node_set::size() const;
bool xpath_node_set::empty() const;
----

All of the above operations have the same semantics as that of `std::vector`: the iterators are random-access, all of the above operations are constant time, and accessing the element at index that is greater or equal than the set size results in undefined behavior. You can use both iterator-based and index-based access for iteration, however the iterator-based one can be faster.

[[xpath_node_set::type]][[xpath_node_set::type_unsorted]][[xpath_node_set::type_sorted]][[xpath_node_set::type_sorted_reverse]][[xpath_node_set::sort]]
The order of iteration depends on the order of nodes inside the set; the order can be queried via the following function:

[source]
----
enum xpath_node_set::type_t {type_unsorted, type_sorted, type_sorted_reverse};
type_t xpath_node_set::type() const;
----

`type` function returns the current order of nodes; `type_sorted` means that the nodes are in forward document order, `type_sorted_reverse` means that the nodes are in reverse document order, and `type_unsorted` means that neither order is guaranteed (nodes can accidentally be in a sorted order even if `type()` returns `type_unsorted`). If you require a specific order of iteration, you can change it via `sort` function:

[source]
----
void xpath_node_set::sort(bool reverse = false);
----

Calling `sort` sorts the nodes in either forward or reverse document order, depending on the argument; after this call `type()` will return `type_sorted` or `type_sorted_reverse`.

[[xpath_node_set::first]]
Often the actual iteration is not needed; instead, only the first element in document order is required. For this, a special accessor is provided:

[source]
----
xpath_node xpath_node_set::first() const;
----

This function returns the first node in forward document order from the set, or null node if the set is empty. Note that while the result of the node does not depend on the order of nodes in the set (i.e. on the result of `type()`), the complexity does - if the set is sorted, the complexity is constant, otherwise it is linear in the number of elements or worse.

[[xpath_node_set::ctor]]
While in the majority of cases the node set is returned by XPath functions, sometimes there is a need to manually construct a node set. For such cases, a constructor is provided which takes an iterator range (`const_iterator` is a typedef for `const xpath_node*`), and an optional type:

[source]
----
xpath_node_set::xpath_node_set(const_iterator begin, const_iterator end, type_t type = type_unsorted);
----

The constructor copies the specified range and sets the specified type. The objects in the range are not checked in any way; you'll have to ensure that the range contains no duplicates, and that the objects are sorted according to the `type` parameter. Otherwise XPath operations with this set may produce unexpected results.

[[xpath.select]]
=== Selecting nodes via XPath expression

[[xml_node::select_node]][[xml_node::select_nodes]]
If you want to select nodes that match some XPath expression, you can do it with the following functions:

[source]
----
xpath_node xml_node::select_node(const char_t* query, xpath_variable_set* variables = 0) const;
xpath_node_set xml_node::select_nodes(const char_t* query, xpath_variable_set* variables = 0) const;
----

`select_nodes` function compiles the expression and then executes it with the node as a context node, and returns the resulting node set. `select_node` returns only the first node in document order from the result, and is equivalent to calling `select_nodes(query).first()`. If the XPath expression does not match anything, or the node handle is null, `select_nodes` returns an empty set, and `select_node` returns null XPath node.

If exception handling is not disabled, both functions throw <<xpath_exception,xpath_exception>> if the query can not be compiled or if it returns a value with type other than node set; see <<xpath.errors>> for details.

[[xml_node::select_node_precomp]][[xml_node::select_nodes_precomp]]
While compiling expressions is fast, the compilation time can introduce a significant overhead if the same expression is used many times on small subtrees. If you're doing many similar queries, consider compiling them into query objects (see <<xpath.query>> for further reference). Once you get a compiled query object, you can pass it to select functions instead of an expression string:

[source]
----
xpath_node xml_node::select_node(const xpath_query& query) const;
xpath_node_set xml_node::select_nodes(const xpath_query& query) const;
----

If exception handling is not disabled, both functions throw <<xpath_exception,xpath_exception>> if the query returns a value with type other than node set.

This is an example of selecting nodes using XPath expressions (link:samples/xpath_select.cpp[]):

[source,indent=0]
----
include::samples/xpath_select.cpp[tags=code] 
----

[[xpath.query]]
=== Using query objects

[[xpath_query]]
When you call `select_nodes` with an expression string as an argument, a query object is created behind the scenes. A query object represents a compiled XPath expression. Query objects can be needed in the following circumstances:

* You can precompile expressions to query objects to save compilation time if it becomes an issue;
* You can use query objects to evaluate XPath expressions which result in booleans, numbers or strings;
* You can get the type of expression value via query object.

Query objects correspond to `xpath_query` type. They are immutable and non-copyable: they are bound to the expression at creation time and can not be cloned. If you want to put query objects in a container, either allocate them on heap via `new` operator and store pointers to `xpath_query` in the container, or use a C++11 compiler (query objects are movable in C++11).

[[xpath_query::ctor]]
You can create a query object with the constructor that takes XPath expression as an argument:

[source]
----
explicit xpath_query::xpath_query(const char_t* query, xpath_variable_set* variables = 0);
----

[[xpath_query::return_type]]
The expression is compiled and the compiled representation is stored in the new query object. If compilation fails, <<xpath_exception,xpath_exception>> is thrown if exception handling is not disabled (see <<xpath.errors>> for details). After the query is created, you can query the type of the evaluation result using the following function:

[source]
----
xpath_value_type xpath_query::return_type() const;
----

[[xpath_query::evaluate_boolean]][[xpath_query::evaluate_number]][[xpath_query::evaluate_string]][[xpath_query::evaluate_node_set]][[xpath_query::evaluate_node]]
You can evaluate the query using one of the following functions:

[source]
----
bool xpath_query::evaluate_boolean(const xpath_node& n) const;
double xpath_query::evaluate_number(const xpath_node& n) const;
string_t xpath_query::evaluate_string(const xpath_node& n) const;
xpath_node_set xpath_query::evaluate_node_set(const xpath_node& n) const;
xpath_node xpath_query::evaluate_node(const xpath_node& n) const;
----

All functions take the context node as an argument, compute the expression and return the result, converted to the requested type. According to XPath specification, value of any type can be converted to boolean, number or string value, but no type other than node set can be converted to node set. Because of this, `evaluate_boolean`, `evaluate_number` and `evaluate_string` always return a result, but `evaluate_node_set` and `evaluate_node` result in an error if the return type is not node set (see <<xpath.errors>>).

NOTE: Calling `node.select_nodes("query")` is equivalent to calling `xpath_query("query").evaluate_node_set(node)`. Calling `node.select_node("query")` is equivalent to calling `xpath_query("query").evaluate_node(node)`.

[[xpath_query::evaluate_string_buffer]]
Note that `evaluate_string` function returns the STL string; as such, it's not available in <<PUGIXML_NO_STL,PUGIXML_NO_STL>> mode and also usually allocates memory. There is another string evaluation function:

[source]
----
size_t xpath_query::evaluate_string(char_t* buffer, size_t capacity, const xpath_node& n) const;
----

This function evaluates the string, and then writes the result to `buffer` (but at most `capacity` characters); then it returns the full size of the result in characters, including the terminating zero. If `capacity` is not 0, the resulting buffer is always zero-terminated. You can use this function as follows: 

* First call the function with `buffer = 0` and `capacity = 0`; then allocate the returned amount of characters, and call the function again, passing the allocated storage and the amount of characters;
* First call the function with small buffer and buffer capacity; then, if the result is larger than the capacity, the output has been trimmed, so allocate a larger buffer and call the function again.

This is an example of using query objects (link:samples/xpath_query.cpp[]):

[source,indent=0]
----
include::samples/xpath_query.cpp[tags=code] 
----

[[xpath.variables]]
=== Using variables

XPath queries may contain references to variables; this is useful if you want to use queries that depend on some dynamic parameter without manually preparing the complete query string, or if you want to reuse the same query object for similar queries.

Variable references have the form `$name`; in order to use them, you have to provide a variable set, which includes all variables present in the query with correct types. This set is passed to `xpath_query` constructor or to `select_nodes`/`select_node` functions:

[source]
----
explicit xpath_query::xpath_query(const char_t* query, xpath_variable_set* variables = 0);
xpath_node xml_node::select_node(const char_t* query, xpath_variable_set* variables = 0) const;
xpath_node_set xml_node::select_nodes(const char_t* query, xpath_variable_set* variables = 0) const;
----

If you're using query objects, you can change the variable values before `evaluate`/`select` calls to change the query behavior.

NOTE: The variable set pointer is stored in the query object; you have to ensure that the lifetime of the set exceeds that of query object.

[[xpath_variable_set]]
Variable sets correspond to `xpath_variable_set` type, which is essentially a variable container.

[[xpath_variable_set::add]]
You can add new variables with the following function:

[source]
----
xpath_variable* xpath_variable_set::add(const char_t* name, xpath_value_type type);
----

The function tries to add a new variable with the specified name and type; if the variable with such name does not exist in the set, the function adds a new variable and returns the variable handle; if there is already a variable with the specified name, the function returns the variable handle if variable has the specified type. Otherwise the function returns null pointer; it also returns null pointer on allocation failure.

New variables are assigned the default value which depends on the type: `0` for numbers, `false` for booleans, empty string for strings and empty set for node sets.

[[xpath_variable_set::get]]
You can get the existing variables with the following functions:

[source]
----
xpath_variable* xpath_variable_set::get(const char_t* name);
const xpath_variable* xpath_variable_set::get(const char_t* name) const;
----

The functions return the variable handle, or null pointer if the variable with the specified name is not found.

[[xpath_variable_set::set]]
Additionally, there are the helper functions for setting the variable value by name; they try to add the variable with the corresponding type, if it does not exist, and to set the value. If the variable with the same name but with different type is already present, they return `false`; they also return `false` on allocation failure. Note that these functions do not perform any type conversions.

[source]
----
bool xpath_variable_set::set(const char_t* name, bool value);
bool xpath_variable_set::set(const char_t* name, double value);
bool xpath_variable_set::set(const char_t* name, const char_t* value);
bool xpath_variable_set::set(const char_t* name, const xpath_node_set& value);
----

The variable values are copied to the internal variable storage, so you can modify or destroy them after the functions return.

[[xpath_variable]]
If setting variables by name is not efficient enough, or if you have to inspect variable information or get variable values, you can use variable handles. A variable corresponds to the `xpath_variable` type, and a variable handle is simply a pointer to `xpath_variable`.

[[xpath_variable::type]][[xpath_variable::name]]
In order to get variable information, you can use one of the following functions:

[source]
----
const char_t* xpath_variable::name() const;
xpath_value_type xpath_variable::type() const;
----

Note that each variable has a distinct type which is specified upon variable creation and can not be changed later.

[[xpath_variable::get_boolean]][[xpath_variable::get_number]][[xpath_variable::get_string]][[xpath_variable::get_node_set]]
In order to get variable value, you should use one of the following functions, depending on the variable type:

[source]
----
bool xpath_variable::get_boolean() const;
double xpath_variable::get_number() const;
const char_t* xpath_variable::get_string() const;
const xpath_node_set& xpath_variable::get_node_set() const;
----

These functions return the value of the variable. Note that no type conversions are performed; if the type mismatch occurs, a dummy value is returned (`false` for booleans, `NaN` for numbers, empty string for strings and empty set for node sets).

[[xpath_variable::set]]
In order to set variable value, you should use one of the following functions, depending on the variable type:

[source]
----
bool xpath_variable::set(bool value);
bool xpath_variable::set(double value);
bool xpath_variable::set(const char_t* value);
bool xpath_variable::set(const xpath_node_set& value);
----

These functions modify the variable value. Note that no type conversions are performed; if the type mismatch occurs, the functions return `false`; they also return `false` on allocation failure. The variable values are copied to the internal variable storage, so you can modify or destroy them after the functions return.

This is an example of using variables in XPath queries (link:samples/xpath_variables.cpp[]):

[source,indent=0]
----
include::samples/xpath_variables.cpp[tags=code] 
----

[[xpath.errors]]
=== Error handling

There are two different mechanisms for error handling in XPath implementation; the mechanism used depends on whether exception support is disabled (this is controlled with <<PUGIXML_NO_EXCEPTIONS,PUGIXML_NO_EXCEPTIONS>> define).

[[xpath_exception]][[xpath_exception::result]][[xpath_exception::what]]
By default, XPath functions throw `xpath_exception` object in case of errors; additionally, in the event any memory allocation fails, an `std::bad_alloc` exception is thrown. Also `xpath_exception` is thrown if the query is evaluated to a node set, but the return type is not node set. If the query constructor succeeds (i.e. no exception is thrown), the query object is valid. Otherwise you can get the error details via one of the following functions:

[source]
----
virtual const char* xpath_exception::what() const throw();
const xpath_parse_result& xpath_exception::result() const;
----

[[xpath_query::unspecified_bool_type]][[xpath_query::result]]
If exceptions are disabled, then in the event of parsing failure the query is initialized to invalid state; you can test if the query object is valid by using it in a boolean expression: `if (query) { ... }`. Additionally, you can get parsing result via the result() accessor:

[source]
----
const xpath_parse_result& xpath_query::result() const;
----
    
Without exceptions, evaluating invalid query results in `false`, empty string, `NaN` or an empty node set, depending on the type; evaluating a query as a node set results in an empty node set if the return type is not node set.

[[xpath_parse_result]]
The information about parsing result is returned via `xpath_parse_result` object. It contains parsing status and the offset of last successfully parsed character from the beginning of the source stream:

[source]
----
struct xpath_parse_result
{
    const char* error;
    ptrdiff_t offset;

    operator bool() const;
    const char* description() const;
};
----

[[xpath_parse_result::error]]
Parsing result is represented as the error message; it is either a null pointer, in case there is no error, or the error message in the form of ASCII zero-terminated string.

[[xpath_parse_result::description]]
`description()` member function can be used to get the error message; it never returns the null pointer, so you can safely use `description()` even if query parsing succeeded. Note that `description()` returns a `char` string even in `PUGIXML_WCHAR_MODE`; you'll have to call <<as_wide,as_wide>> to get the `wchar_t` string.

[[xpath_parse_result::offset]]
In addition to the error message, parsing result has an `offset` member, which contains the offset of last successfully parsed character. This offset is in units of <<char_t,pugi::char_t>> (bytes for character mode, wide characters for wide character mode).

[[xpath_parse_result::bool]]
Parsing result object can be implicitly converted to `bool` like this: `if (result) { ... } else { ... }`.

This is an example of XPath error handling (link:samples/xpath_error.cpp[]):

[source,indent=0]
----
include::samples/xpath_error.cpp[tags=code] 
----

[[xpath.w3c]]
=== Conformance to W3C specification

Because of the differences in document object models, performance considerations and implementation complexity, pugixml does not provide a fully conformant XPath 1.0 implementation. This is the current list of incompatibilities:

* Consecutive text nodes sharing the same parent are not merged, i.e. in `<node>text1 <![CDATA[data]]> text2</node>` node should have one text node child, but instead has three.
* Since the document type declaration is not used for parsing, `id()` function always returns an empty node set.
* Namespace nodes are not supported (affects `namespace::` axis).
* Name tests are performed on QNames in XML document instead of expanded names; for `<foo xmlns:ns1='uri' xmlns:ns2='uri'><ns1:child/><ns2:child/></foo>`, query `foo/ns1:*` will return only the first child, not both of them. Compliant XPath implementations can return both nodes if the user provides appropriate namespace declarations.
* String functions consider a character to be either a single `char` value or a single `wchar_t` value, depending on the library configuration; this means that some string functions are not fully Unicode-aware. This affects `substring()`, `string-length()` and `translate()` functions.

[[changes]]
== Changelog

:!numbered:

[[v1.7]]
=== v1.7 ^2015-10-19^

Major release, featuring performance and memory improvements along with some new features. Changes:

* Compact mode:
    . Introduced a new tree storage mode that takes significantly less memory (2-5x smaller DOM) at some performance cost.
    . The mode can be enabled using `PUGIXML_COMPACT` define.

* New integer parsing/formatting implementation:
	. Functions that convert from and to integers (e.g. `as_int`/`set_value`) do not rely on CRT any more.
	. New implementation is 3-5x faster and is always correct wrt overflow or underflow. This is a behavior change - where previously `as_uint()` would return UINT_MAX on a value "-1", it now returns 0.

* New features:
	. XPath objects (`xpath_query`, `xpath_node_set`, `xpath_variable_set`) are now movable if your compiler supports C++11. Additionally, `xpath_variable_set` is copyable.
	. Added `format_indent_attributes` that makes the resulting XML friendlier to line diff/merge tools.
	. Added a variant of `xml_node::attribute` function with a hint that can improve lookup performance.
	. Custom allocation functions are now allowed (but not required) to throw instead of returning a null pointer.

* Bug fixes:
	. Fix Clang 3.7 crashes in out-of-memory cases (C++ DR 1748)
	. Fix XPath crashes on SPARC64 (and other 32-bit architectures where doubles have to be aligned to 8 bytes)
	. Fix xpath_node_set assignment to provide strong exception guarantee
	. Fix saving for custom xml_writer implementations that can throw from write()

[[v1.6]]
=== v1.6 ^2015-04-10^

Maintenance release. Changes:

* Specification changes:
    . Attribute/text values now use more digits when printing floating point numbers to guarantee round-tripping.
    . Text nodes no longer get extra surrounding whitespace when pretty-printing nodes with mixed contents

* Bug fixes:
    . Fixed translate and normalize-space XPath functions to no longer return internal NUL characters
    . Fixed buffer overrun on malformed comments inside DOCTYPE sections
    . DOCTYPE parsing can no longer run out of stack space on malformed inputs (XML parsing is now using bounded stack space)
    . Adjusted processing instruction output to avoid malformed documents if the PI value contains `?>`

[[v1.5]]
=== v1.5 ^2014-11-27^

Major release, featuring a lot of performance improvements and some new features.

* Specification changes:
    . `xml_document::load(const char_t*)` was renamed to `load_string`; the old method is still available and will be deprecated in a future release
    . `xml_node::select_single_node` was renamed to `select_node`; the old method is still available and will be deprecated in a future release.

* New features:
    . Added `xml_node::append_move` and other functions for moving nodes within a document
    . Added `xpath_query::evaluate_node` for evaluating queries with a single node as a result

* Performance improvements:
    . Optimized XML parsing (10-40% faster with clang/gcc, up to 10% faster with MSVC)
    . Optimized memory consumption when copying nodes in the same document (string contents is now shared)
    . Optimized node copying (10% faster for cross-document copies, 3x faster for inter-document copies; also it now consumes a constant amount of stack space)
    . Optimized node output (60% faster; also it now consumes a constant amount of stack space)
    . Optimized XPath allocation (query evaluation now results in fewer temporary allocations)
    . Optimized XPath sorting (node set sorting is 2-3x faster in some cases)
    . Optimized XPath evaluation (XPathMark suite is 100x faster; some commonly used queries are 3-4x faster)

* Compatibility improvements:
    . Fixed `xml_node::offset_debug` for corner cases
    . Fixed undefined behavior while calling memcpy in some cases
    . Fixed MSVC 2015 compilation warnings
    . Fixed `contrib/foreach.hpp` for Boost 1.56.0

* Bug fixes
    . Adjusted comment output to avoid malformed documents if the comment value contains `--`
    . Fix XPath sorting for documents that were constructed using append_buffer
    . Fix `load_file` for wide-character paths with non-ASCII characters in MinGW with C{plus}{plus}11 mode enabled

[[v1.4]]
=== v1.4 ^2014-02-27^

Major release, featuring various new features, bug fixes and compatibility improvements.

* Specification changes:
    . Documents without element nodes are now rejected with `status_no_document_element` error, unless `parse_fragment` option is used

* New features:
    . Added XML fragment parsing (`parse_fragment` flag)
    . Added PCDATA whitespace trimming (`parse_trim_pcdata` flag)
    . Added long long support for `xml_attribute` and `xml_text` (`as_llong`, `as_ullong` and `set_value`/`set` overloads)
    . Added hexadecimal integer parsing support for `as_int`/`as_uint`/`as_llong`/`as_ullong`
    . Added `xml_node::append_buffer` to improve performance of assembling documents from fragments
    . `xml_named_node_iterator` is now bidirectional
    . Reduced XPath stack consumption during compilation and evaluation (useful for embedded systems)

* Compatibility improvements:
    . Improved support for platforms without wchar_t support
    . Fixed several false positives in clang static analysis
    . Fixed several compilation warnings for various GCC versions

* Bug fixes:
    . Fixed undefined pointer arithmetic in XPath implementation
    . Fixed non-seekable iostream support for certain stream types, i.e. Boost `file_source` with pipe input
    . Fixed `xpath_query::return_type` for some expressions
    . Fixed dllexport issues with `xml_named_node_iterator`
    . Fixed `find_child_by_attribute` assertion for attributes with null name/value

[[v1.2]]
=== v1.2 ^2012-05-01^

Major release, featuring header-only mode, various interface enhancements (i.e. PCDATA manipulation and C{plus}{plus}11 iteration), many other features and compatibility improvements.

* New features:
    . Added `xml_text` helper class for working with PCDATA/CDATA contents of an element node
    . Added optional header-only mode (controlled by `PUGIXML_HEADER_ONLY` define)
    . Added `xml_node::children()` and `xml_node::attributes()` for C{plus}{plus}11 ranged for loop or `BOOST_FOREACH`
    . Added support for Latin-1 (ISO-8859-1) encoding conversion during loading and saving
    . Added custom default values for `xml_attribute::as_*` (they are returned if the attribute does not exist)
    . Added `parse_ws_pcdata_single` flag for preserving whitespace-only PCDATA in case it's the only child
    . Added `format_save_file_text` for `xml_document::save_file` to open files as text instead of binary (changes newlines on Windows)
    . Added `format_no_escapes` flag to disable special symbol escaping (complements `~parse_escapes`)
    . Added support for loading document from streams that do not support seeking
    . Added `PUGIXML_MEMORY_*` constants for tweaking allocation behavior (useful for embedded systems)
    . Added `PUGIXML_VERSION` preprocessor define

* Compatibility improvements:
    . Parser does not require setjmp support (improves compatibility with some embedded platforms, enables `/clr:pure` compilation)
    . STL forward declarations are no longer used (fixes SunCC/RWSTL compilation, fixes clang compilation in C{plus}{plus}11 mode)
    . Fixed AirPlay SDK, Android, Windows Mobile (WinCE) and C{plus}{plus}/CLI compilation
    . Fixed several compilation warnings for various GCC versions, Intel C{plus}{plus} compiler and Clang

* Bug fixes:
    . Fixed unsafe bool conversion to avoid problems on C{plus}{plus}/CLI
    . Iterator dereference operator is const now (fixes Boost `filter_iterator` support)
    . `xml_document::save_file` now checks for file I/O errors during saving

[[v1.0]]
=== v1.0 ^2010-11-01^

Major release, featuring many XPath enhancements, wide character filename support, miscellaneous performance improvements, bug fixes and more.

* XPath:
    . XPath implementation is moved to `pugixml.cpp` (which is the only source file now); use `PUGIXML_NO_XPATH` if you want to disable XPath to reduce code size
    . XPath is now supported without exceptions (`PUGIXML_NO_EXCEPTIONS`); the error handling mechanism depends on the presence of exception support
    . XPath is now supported without STL (`PUGIXML_NO_STL`)
    . Introduced variable support
    . Introduced new `xpath_query::evaluate_string`, which works without STL
    . Introduced new `xpath_node_set` constructor (from an iterator range)
    . Evaluation function now accept attribute context nodes
    . All internal allocations use custom allocation functions
    . Improved error reporting; now a last parsed offset is returned together with the parsing error

* Bug fixes:
    . Fixed memory leak for loading from streams with stream exceptions turned on
    . Fixed custom deallocation function calling with null pointer in one case
    . Fixed missing attributes for iterator category functions; all functions/classes can now be DLL-exported
    . Worked around Digital Mars compiler bug, which lead to minor read overfetches in several functions
    . `load_file` now works with 2+ Gb files in MSVC/MinGW
    . XPath: fixed memory leaks for incorrect queries
    . XPath: fixed `xpath_node()` attribute constructor with empty attribute argument
    . XPath: fixed `lang()` function for non-ASCII arguments

* Specification changes:
    . CDATA nodes containing `]]>` are printed as several nodes; while this changes the internal structure, this is the only way to escape CDATA contents
    . Memory allocation errors during parsing now preserve last parsed offset (to give an idea about parsing progress)
    . If an element node has the only child, and it is of CDATA type, then the extra indentation is omitted (previously this behavior only held for PCDATA children)

* Additional functionality:
    . Added `xml_parse_result` default constructor
    . Added `xml_document::load_file` and `xml_document::save_file` with wide character paths
    . Added `as_utf8` and `as_wide` overloads for `std::wstring`/`std::string` arguments
    . Added DOCTYPE node type (`node_doctype`) and a special parse flag, `parse_doctype`, to add such nodes to the document during parsing
    . Added `parse_full` parse flag mask, which extends `parse_default` with all node type parsing flags except `parse_ws_pcdata`
    . Added `xml_node::hash_value()` and `xml_attribute::hash_value()` functions for use in hash-based containers
    . Added `internal_object()` and additional constructor for both `xml_node` and `xml_attribute` for easier marshalling (useful for language bindings)
    . Added `xml_document::document_element()` function
    . Added `xml_node::prepend_attribute`, `xml_node::prepend_child` and `xml_node::prepend_copy` functions
    . Added `xml_node::append_child`, `xml_node::prepend_child`, `xml_node::insert_child_before` and `xml_node::insert_child_after` overloads for element nodes (with name instead of type)
    . Added `xml_document::reset()` function

* Performance improvements:
    . `xml_node::root()` and `xml_node::offset_debug()` are now O(1) instead of O(logN)
    . Minor parsing optimizations
    . Minor memory optimization for strings in DOM tree (`set_name`/`set_value`)
    . Memory optimization for string memory reclaiming in DOM tree (`set_name`/`set_value` now reallocate the buffer if memory waste is too big)
    . XPath: optimized document order sorting
    . XPath: optimized child/attribute axis step
    . XPath: optimized number-to-string conversions in MSVC
    . XPath: optimized concat for many arguments
    . XPath: optimized evaluation allocation mechanism: constant and document strings are not heap-allocated
    . XPath: optimized evaluation allocation mechanism: all temporaries' allocations use fast stack-like allocator

* Compatibility:
    . Removed wildcard functions (`xml_node::child_w`, `xml_node::attribute_w`, etc.)
    . Removed `xml_node::all_elements_by_name`
    . Removed `xpath_type_t` enumeration; use `xpath_value_type` instead
    . Removed `format_write_bom_utf8` enumeration; use `format_write_bom` instead
    . Removed `xml_document::precompute_document_order`, `xml_attribute::document_order` and `xml_node::document_order` functions; document order sort optimization is now automatic
    . Removed `xml_document::parse` functions and `transfer_ownership` struct; use `xml_document::load_buffer_inplace` and `xml_document::load_buffer_inplace_own` instead
    . Removed `as_utf16` function; use `as_wide` instead

[[v0.9]]
=== v0.9 ^2010-07-01^

Major release, featuring extended and improved Unicode support, miscellaneous performance improvements, bug fixes and more.

* Major Unicode improvements:
    . Introduced encoding support (automatic/manual encoding detection on load, manual encoding selection on save, conversion from/to UTF8, UTF16 LE/BE, UTF32 LE/BE)
    . Introduced `wchar_t` mode (you can set `PUGIXML_WCHAR_MODE` define to switch pugixml internal encoding from UTF8 to `wchar_t`; all functions are switched to their Unicode variants)
    . Load/save functions now support wide streams

* Bug fixes:
    . Fixed document corruption on failed parsing bug
    . XPath string/number conversion improvements (increased precision, fixed crash for huge numbers)
    . Improved DOCTYPE parsing: now parser recognizes all well-formed DOCTYPE declarations
    . Fixed `xml_attribute::as_uint()` for large numbers (i.e. 2^32^-1)
    . Fixed `xml_node::first_element_by_path` for path components that are prefixes of node names, but are not exactly equal to them.

* Specification changes:
    . `parse()` API changed to `load_buffer`/`load_buffer_inplace`/`load_buffer_inplace_own`; `load_buffer` APIs do not require zero-terminated strings.
    . Renamed `as_utf16` to `as_wide`
    . Changed `xml_node::offset_debug` return type and `xml_parse_result::offset` type to `ptrdiff_t`
    . Nodes/attributes with empty names are now printed as `:anonymous`

* Performance improvements:
    . Optimized document parsing and saving
    . Changed internal memory management: internal allocator is used for both metadata and name/value data; allocated pages are deleted if all allocations from them are deleted
    . Optimized memory consumption: `sizeof(xml_node_struct)` reduced from 40 bytes to 32 bytes on x86
    . Optimized debug mode parsing/saving by order of magnitude

* Miscellaneous:
    . All STL includes except `<exception>` in `pugixml.hpp` are replaced with forward declarations
    . `xml_node::remove_child` and `xml_node::remove_attribute` now return the operation result

* Compatibility:
    . `parse()` and `as_utf16` are left for compatibility (these functions are deprecated and will be removed in version 1.0)
    . Wildcard functions, `document_order`/`precompute_document_order` functions, `all_elements_by_name` function and `format_write_bom_utf8` flag are deprecated and will be removed in version 1.0
    . `xpath_type_t` enumeration was renamed to `xpath_value_type`; `xpath_type_t` is deprecated and will be removed in version 1.0

[[v0.5]]
=== v0.5 ^2009-11-08^

Major bugfix release. Changes:

* XPath bugfixes:
    . Fixed `translate()`, `lang()` and `concat()` functions (infinite loops/crashes)
    . Fixed compilation of queries with empty literal strings (`""`)
    . Fixed axis tests: they never add empty nodes/attributes to the resulting node set now
    . Fixed string-value evaluation for node-set (the result excluded some text descendants)
    . Fixed `self::` axis (it behaved like `ancestor-or-self::`)
    . Fixed `following::` and `preceding::` axes (they included descendent and ancestor nodes, respectively)
    . Minor fix for `namespace-uri()` function (namespace declaration scope includes the parent element of namespace declaration attribute)
    . Some incorrect queries are no longer parsed now (i.e. `foo: *`)
    . Fixed `text()`/etc. node test parsing bug (i.e. `foo[text()]` failed to compile)
    . Fixed root step (`/`) - it now selects empty node set if query is evaluated on empty node
    . Fixed string to number conversion (`"123 "` converted to NaN, `"123 .456"` converted to 123.456 - now the results are 123 and NaN, respectively)
    . Node set copying now preserves sorted type; leads to better performance on some queries

* Miscellaneous bugfixes:
    . Fixed `xml_node::offset_debug` for PI nodes
    . Added empty attribute checks to `xml_node::remove_attribute`
    . Fixed `node_pi` and `node_declaration` copying
    . Const-correctness fixes

* Specification changes:
    . `xpath_node::select_nodes()` and related functions now throw exception if expression return type is not node set (instead of assertion)
    . `xml_node::traverse()` now sets depth to -1 for both `begin()` and `end()` callbacks (was 0 at `begin()` and -1 at `end()`)
    . In case of non-raw node printing a newline is output after PCDATA inside nodes if the PCDATA has siblings
    . UTF8 -> `wchar_t` conversion now considers 5-byte UTF8-like sequences as invalid

* New features:
    . Added `xpath_node_set::operator[]` for index-based iteration
    . Added `xpath_query::return_type()`
    . Added getter accessors for memory-management functions

[[v0.42]]
=== v0.42 ^2009-09-17^

Maintenance release. Changes:

* Bug fixes:
    . Fixed deallocation in case of custom allocation functions or if `delete[]` / `free` are incompatible
    . XPath parser fixed for incorrect queries (i.e. incorrect XPath queries should now always fail to compile)
    . Const-correctness fixes for `find_child_by_attribute`
    . Improved compatibility (miscellaneous warning fixes, fixed `<cstring>` include dependency for GCC)
    . Fixed iterator begin/end and print function to work correctly for empty nodes

* New features:
    . Added `PUGIXML_API`/`PUGIXML_CLASS`/`PUGIXML_FUNCTION` configuration macros to control class/function attributes
    . Added `xml_attribute::set_value` overloads for different types

[[v0.41]]
=== v0.41 ^2009-02-08^

Maintenance release. Changes:

* Bug fixes:
    . Fixed bug with node printing (occasionally some content was not written to output stream)

[[v0.4]]
=== v0.4 ^2009-01-18^

Changes:

* Bug fixes:
    . Documentation fix in samples for `parse()` with manual lifetime control
    . Fixed document order sorting in XPath (it caused wrong order of nodes after `xpath_node_set::sort` and wrong results of some XPath queries)

* Node printing changes:
    . Single quotes are no longer escaped when printing nodes
    . Symbols in second half of ASCII table are no longer escaped when printing nodes; because of this, `format_utf8` flag is deleted as it's no longer needed and `format_write_bom` is renamed to `format_write_bom_utf8`.
    . Reworked node printing - now it works via `xml_writer` interface; implementations for `FILE*` and `std::ostream` are available. As a side-effect, `xml_document::save_file` now works without STL.

* New features:
    . Added unsigned integer support for attributes (`xml_attribute::as_uint`, `xml_attribute::operator=`)
    . Now document declaration (`<?xml ...?>`) is parsed as node with type `node_declaration` when `parse_declaration` flag is specified (access to encoding/version is performed as if they were attributes, i.e. `doc.child("xml").attribute("version").as_float()`); corresponding flags for node printing were also added
    . Added support for custom memory management (see `set_memory_management_functions` for details)
    . Implemented node/attribute copying (see `xml_node::insert_copy_*` and `xml_node::append_copy` for details)
    . Added `find_child_by_attribute` and `find_child_by_attribute_w` to simplify parsing code in some cases (i.e. COLLADA files)
    . Added file offset information querying for debugging purposes (now you're able to determine exact location of any `xml_node` in parsed file, see `xml_node::offset_debug` for details)
    . Improved error handling for parsing - now `load()`, `load_file()` and `parse()` return `xml_parse_result`, which contains error code and last parsed offset; this does not break old interface as `xml_parse_result` can be implicitly casted to `bool`.

[[v0.34]]
=== v0.34 ^2007-10-31^

Maintenance release. Changes:

* Bug fixes:
    . Fixed bug with loading from text-mode iostreams
    . Fixed leak when `transfer_ownership` is true and parsing is failing
    . Fixed bug in saving (`\r` and `\n` are now escaped in attribute values)
    . Renamed `free()` to `destroy()` - some macro conflicts were reported

* New features:
    . Improved compatibility (supported Digital Mars C{plus}{plus}, MSVC 6, CodeWarrior 8, PGI C{plus}{plus}, Comeau, supported PS3 and XBox360)
    . `PUGIXML_NO_EXCEPTION` flag for platforms without exception handling

[[v0.3]]
=== v0.3 ^2007-02-21^

Refactored, reworked and improved version. Changes:

* Interface:
    . Added XPath
    . Added tree modification functions
    . Added no STL compilation mode
    . Added saving document to file
    . Refactored parsing flags
    . Removed `xml_parser` class in favor of `xml_document`
    . Added transfer ownership parsing mode
    . Modified the way `xml_tree_walker` works
    . Iterators are now non-constant

* Implementation:
    . Support of several compilers and platforms
    . Refactored and sped up parsing core
    . Improved standard compliancy
    . Added XPath implementation
    . Fixed several bugs

[[v0.2]]
=== v0.2 ^2006-11-06^

First public release. Changes:

* Bug fixes:
    . Fixed `child_value()` (for empty nodes)
    . Fixed `xml_parser_impl` warning at W4

* New features:
    . Introduced `child_value(name)` and `child_value_w(name)`
    . `parse_eol_pcdata` and `parse_eol_attribute` flags + `parse_minimal` optimizations
    . Optimizations of `strconv_t`

[[v0.1]]
=== v0.1 ^2006-07-15^

First private release for testing purposes

:numbered:

[[apiref]]
== API Reference

This is the reference for all macros, types, enumerations, classes and functions in pugixml. Each symbol is a link that leads to the relevant section of the manual.

[[apiref.macros]]
=== Macros

[source,subs="+macros"]
----
#define +++<a href="#PUGIXML_WCHAR_MODE">PUGIXML_WCHAR_MODE</a>+++
#define +++<a href="#PUGIXML_COMPACT">PUGIXML_COMPACT</a>+++
#define +++<a href="#PUGIXML_NO_XPATH">PUGIXML_NO_XPATH</a>+++
#define +++<a href="#PUGIXML_NO_STL">PUGIXML_NO_STL</a>+++
#define +++<a href="#PUGIXML_NO_EXCEPTIONS">PUGIXML_NO_EXCEPTIONS</a>+++
#define +++<a href="#PUGIXML_API">PUGIXML_API</a>+++
#define +++<a href="#PUGIXML_CLASS">PUGIXML_CLASS</a>+++
#define +++<a href="#PUGIXML_FUNCTION">PUGIXML_FUNCTION</a>+++
#define +++<a href="#PUGIXML_MEMORY_PAGE_SIZE">PUGIXML_MEMORY_PAGE_SIZE</a>+++
#define +++<a href="#PUGIXML_MEMORY_OUTPUT_STACK">PUGIXML_MEMORY_OUTPUT_STACK</a>+++
#define +++<a href="#PUGIXML_MEMORY_XPATH_PAGE_SIZE">PUGIXML_MEMORY_XPATH_PAGE_SIZE</a>+++
#define +++<a href="#PUGIXML_HEADER_ONLY">PUGIXML_HEADER_ONLY</a>+++
#define +++<a href="#PUGIXML_HAS_LONG_LONG">PUGIXML_HAS_LONG_LONG</a>+++
----

[[apiref.types]]
=== Types

[source,subs="+macros"]
----
typedef configuration-defined-type +++<a href="#char_t">char_t</a>+++;
typedef configuration-defined-type +++<a href="#string_t">string_t</a>+++;
typedef void* (*+++<a href="#allocation_function">allocation_function</a>+++)(size_t size);
typedef void (*+++<a href="#deallocation_function">deallocation_function</a>+++)(void* ptr);
----

[[apiref.enums]]
=== Enumerations

[source,subs="+macros"]
----
enum +++<a href="#xml_node_type">xml_node_type</a>+++
    +++<a href="#node_null">node_null</a>+++
    +++<a href="#node_document">node_document</a>+++
    +++<a href="#node_element">node_element</a>+++
    +++<a href="#node_pcdata">node_pcdata</a>+++
    +++<a href="#node_cdata">node_cdata</a>+++
    +++<a href="#node_comment">node_comment</a>+++
    +++<a href="#node_pi">node_pi</a>+++
    +++<a href="#node_declaration">node_declaration</a>+++
    +++<a href="#node_doctype">node_doctype</a>+++

enum +++<a href="#xml_parse_status">xml_parse_status</a>+++
    +++<a href="#status_ok">status_ok</a>+++
    +++<a href="#status_file_not_found">status_file_not_found</a>+++
    +++<a href="#status_io_error">status_io_error</a>+++
    +++<a href="#status_out_of_memory">status_out_of_memory</a>+++
    +++<a href="#status_internal_error">status_internal_error</a>+++
    +++<a href="#status_unrecognized_tag">status_unrecognized_tag</a>+++
    +++<a href="#status_bad_pi">status_bad_pi</a>+++
    +++<a href="#status_bad_comment">status_bad_comment</a>+++
    +++<a href="#status_bad_cdata">status_bad_cdata</a>+++
    +++<a href="#status_bad_doctype">status_bad_doctype</a>+++
    +++<a href="#status_bad_pcdata">status_bad_pcdata</a>+++
    +++<a href="#status_bad_start_element">status_bad_start_element</a>+++
    +++<a href="#status_bad_attribute">status_bad_attribute</a>+++
    +++<a href="#status_bad_end_element">status_bad_end_element</a>+++
    +++<a href="#status_end_element_mismatch">status_end_element_mismatch</a>+++
    +++<a href="#status_append_invalid_root">status_append_invalid_root</a>+++
    +++<a href="#status_no_document_element">status_no_document_element</a>+++

enum +++<a href="#xml_encoding">xml_encoding</a>+++
    +++<a href="#encoding_auto">encoding_auto</a>+++
    +++<a href="#encoding_utf8">encoding_utf8</a>+++
    +++<a href="#encoding_utf16_le">encoding_utf16_le</a>+++
    +++<a href="#encoding_utf16_be">encoding_utf16_be</a>+++
    +++<a href="#encoding_utf16">encoding_utf16</a>+++
    +++<a href="#encoding_utf32_le">encoding_utf32_le</a>+++
    +++<a href="#encoding_utf32_be">encoding_utf32_be</a>+++
    +++<a href="#encoding_utf32">encoding_utf32</a>+++
    +++<a href="#encoding_wchar">encoding_wchar</a>+++
    +++<a href="#encoding_latin1">encoding_latin1</a>+++

enum +++<a href="#xpath_value_type">xpath_value_type</a>+++
    +++<a href="#xpath_type_none">xpath_type_none</a>+++
    +++<a href="#xpath_type_node_set">xpath_type_node_set</a>+++
    +++<a href="#xpath_type_number">xpath_type_number</a>+++
    +++<a href="#xpath_type_string">xpath_type_string</a>+++
    +++<a href="#xpath_type_boolean">xpath_type_boolean</a>+++
----

[[apiref.constants]]
=== Constants

[source,subs="+macros"]
----
// Formatting options bit flags:
const unsigned int +++<a href="#format_default">format_default</a>+++
const unsigned int +++<a href="#format_indent">format_indent</a>+++
const unsigned int +++<a href="#format_indent_attributes">format_indent_attributes</a>+++
const unsigned int +++<a href="#format_no_declaration">format_no_declaration</a>+++
const unsigned int +++<a href="#format_no_escapes">format_no_escapes</a>+++
const unsigned int +++<a href="#format_raw">format_raw</a>+++
const unsigned int +++<a href="#format_save_file_text">format_save_file_text</a>+++
const unsigned int +++<a href="#format_write_bom">format_write_bom</a>+++

// Parsing options bit flags:
const unsigned int +++<a href="#parse_cdata">parse_cdata</a>+++
const unsigned int +++<a href="#parse_comments">parse_comments</a>+++
const unsigned int +++<a href="#parse_declaration">parse_declaration</a>+++
const unsigned int +++<a href="#parse_default">parse_default</a>+++
const unsigned int +++<a href="#parse_doctype">parse_doctype</a>+++
const unsigned int +++<a href="#parse_eol">parse_eol</a>+++
const unsigned int +++<a href="#parse_escapes">parse_escapes</a>+++
const unsigned int +++<a href="#parse_fragment">parse_fragment</a>+++
const unsigned int +++<a href="#parse_full">parse_full</a>+++
const unsigned int +++<a href="#parse_minimal">parse_minimal</a>+++
const unsigned int +++<a href="#parse_pi">parse_pi</a>+++
const unsigned int +++<a href="#parse_trim_pcdata">parse_trim_pcdata</a>+++
const unsigned int +++<a href="#parse_ws_pcdata">parse_ws_pcdata</a>+++
const unsigned int +++<a href="#parse_ws_pcdata_single">parse_ws_pcdata_single</a>+++
const unsigned int +++<a href="#parse_wconv_attribute">parse_wconv_attribute</a>+++
const unsigned int +++<a href="#parse_wnorm_attribute">parse_wnorm_attribute</a>+++
----
        
[[apiref.classes]]
=== Classes

[source,subs="+macros"]
----
+++<span class="tok-k">class</span> <a href="#xml_attribute">xml_attribute</a>+++
    +++<a href="#xml_attribute::ctor">xml_attribute</a>+++();

    bool +++<a href="#xml_attribute::empty">empty</a>+++() const;
    operator +++<a href="#xml_attribute::unspecified_bool_type">unspecified_bool_type</a>+++() const;

    bool +++<a href="#xml_attribute::comparison">operator==</a>+++(const xml_attribute& r) const;
    bool +++<a href="#xml_attribute::comparison">operator!=</a>+++(const xml_attribute& r) const;
    bool +++<a href="#xml_attribute::comparison">operator&lt;</a>+++(const xml_attribute& r) const;
    bool +++<a href="#xml_attribute::comparison">operator&gt;</a>+++(const xml_attribute& r) const;
    bool +++<a href="#xml_attribute::comparison">operator&lt;=</a>+++(const xml_attribute& r) const;
    bool +++<a href="#xml_attribute::comparison">operator&gt;=</a>+++(const xml_attribute& r) const;

    size_t +++<a href="#xml_attribute::hash_value">hash_value</a>+++() const;

    xml_attribute +++<a href="#xml_attribute::next_attribute">next_attribute</a>+++() const;
    xml_attribute +++<a href="#xml_attribute::previous_attribute">previous_attribute</a>+++() const;

    const char_t* +++<a href="#xml_attribute::name">name</a>+++() const;
    const char_t* +++<a href="#xml_attribute::value">value</a>+++() const;

    const char_t* +++<a href="#xml_attribute::as_string">as_string</a>+++(const char_t* def = "") const;
    int +++<a href="#xml_attribute::as_int">as_int</a>+++(int def = 0) const;
    unsigned int +++<a href="#xml_attribute::as_uint">as_uint</a>+++(unsigned int def = 0) const;
    double +++<a href="#xml_attribute::as_double">as_double</a>+++(double def = 0) const;
    float +++<a href="#xml_attribute::as_float">as_float</a>+++(float def = 0) const;
    bool +++<a href="#xml_attribute::as_bool">as_bool</a>+++(bool def = false) const;
    long long +++<a href="#xml_attribute::as_llong">as_llong</a>+++(long long def = 0) const;
    unsigned long long +++<a href="#xml_attribute::as_ullong">as_ullong</a>+++(unsigned long long def = 0) const;

    bool +++<a href="#xml_attribute::set_name">set_name</a>+++(const char_t* rhs);
    bool +++<a href="#xml_attribute::set_value">set_value</a>+++(const char_t* rhs);
    bool +++<a href="#xml_attribute::set_value">set_value</a>+++(int rhs);
    bool +++<a href="#xml_attribute::set_value">set_value</a>+++(unsigned int rhs);
    bool +++<a href="#xml_attribute::set_value">set_value</a>+++(double rhs);
    bool +++<a href="#xml_attribute::set_value">set_value</a>+++(float rhs);
    bool +++<a href="#xml_attribute::set_value">set_value</a>+++(bool rhs);
    bool +++<a href="#xml_attribute::set_value">set_value</a>+++(long long rhs);
    bool +++<a href="#xml_attribute::set_value">set_value</a>+++(unsigned long long rhs);

    xml_attribute& +++<a href="#xml_attribute::assign">operator=</a>+++(const char_t* rhs);
    xml_attribute& +++<a href="#xml_attribute::assign">operator=</a>+++(int rhs);
    xml_attribute& +++<a href="#xml_attribute::assign">operator=</a>+++(unsigned int rhs);
    xml_attribute& +++<a href="#xml_attribute::assign">operator=</a>+++(double rhs);
    xml_attribute& +++<a href="#xml_attribute::assign">operator=</a>+++(float rhs);
    xml_attribute& +++<a href="#xml_attribute::assign">operator=</a>+++(bool rhs);
    xml_attribute& +++<a href="#xml_attribute::assign">operator=</a>+++(long long rhs);
    xml_attribute& +++<a href="#xml_attribute::assign">operator=</a>+++(unsnigned long long rhs);

+++<span class="tok-k">class</span> <a href="#xml_node">xml_node</a>+++
    +++<a href="#xml_node::ctor">xml_node</a>+++();

    bool +++<a href="#xml_node::empty">empty</a>+++() const;
    operator +++<a href="#xml_node::unspecified_bool_type">unspecified_bool_type</a>+++() const;

    bool +++<a href="#xml_node::comparison">operator==</a>+++(const xml_node& r) const;
    bool +++<a href="#xml_node::comparison">operator!=</a>+++(const xml_node& r) const;
    bool +++<a href="#xml_node::comparison">operator&lt;</a>+++(const xml_node& r) const;
    bool +++<a href="#xml_node::comparison">operator&gt;</a>+++(const xml_node& r) const;
    bool +++<a href="#xml_node::comparison">operator&lt;=</a>+++(const xml_node& r) const;
    bool +++<a href="#xml_node::comparison">operator&gt;=</a>+++(const xml_node& r) const;

    size_t +++<a href="#xml_node::hash_value">hash_value</a>+++() const;

    xml_node_type +++<a href="#xml_node::type">type</a>+++() const;

    const char_t* +++<a href="#xml_node::name">name</a>+++() const;
    const char_t* +++<a href="#xml_node::value">value</a>+++() const;

    xml_node +++<a href="#xml_node::parent">parent</a>+++() const;
    xml_node +++<a href="#xml_node::first_child">first_child</a>+++() const;
    xml_node +++<a href="#xml_node::last_child">last_child</a>+++() const;
    xml_node +++<a href="#xml_node::next_sibling">next_sibling</a>+++() const;
    xml_node +++<a href="#xml_node::previous_sibling">previous_sibling</a>+++() const;

    xml_attribute +++<a href="#xml_node::first_attribute">first_attribute</a>+++() const;
    xml_attribute +++<a href="#xml_node::last_attribute">last_attribute</a>+++() const;

    implementation-defined-type +++<a href="#xml_node::children">children</a>+++() const;
    implementation-defined-type +++<a href="#xml_node::children">children</a>+++(const char_t* name) const;
    implementation-defined-type +++<a href="#xml_node::attributes">attributes</a>+++() const;

    xml_node +++<a href="#xml_node::child">child</a>+++(const char_t* name) const;
    xml_attribute +++<a href="#xml_node::attribute">attribute</a>+++(const char_t* name) const;
    xml_node +++<a href="#xml_node::next_sibling_name">next_sibling</a>+++(const char_t* name) const;
    xml_node +++<a href="#xml_node::previous_sibling_name">previous_sibling</a>+++(const char_t* name) const;
    xml_node +++<a href="#xml_node::find_child_by_attribute">find_child_by_attribute</a>+++(const char_t* name, const char_t* attr_name, const char_t* attr_value) const;
    xml_node +++<a href="#xml_node::find_child_by_attribute">find_child_by_attribute</a>+++(const char_t* attr_name, const char_t* attr_value) const;

    const char_t* +++<a href="#xml_node::child_value">child_value</a>+++() const;
    const char_t* +++<a href="#xml_node::child_value">child_value</a>+++(const char_t* name) const;
    xml_text +++<a href="#xml_node::text">text</a>+++() const;

    typedef xml_node_iterator +++<a href="#xml_node_iterator">iterator</a>+++;
    iterator +++<a href="#xml_node::begin">begin</a>+++() const;
    iterator +++<a href="#xml_node::end">end</a>+++() const;

    typedef xml_attribute_iterator +++<a href="#xml_attribute_iterator">attribute_iterator</a>+++;
    attribute_iterator +++<a href="#xml_node::attributes_begin">attributes_begin</a>+++() const;
    attribute_iterator +++<a href="#xml_node::attributes_end">attributes_end</a>+++() const;

    bool +++<a href="#xml_node::traverse">traverse</a>+++(xml_tree_walker& walker);

    template <typename Predicate> xml_attribute +++<a href="#xml_node::find_attribute">find_attribute</a>+++(Predicate pred) const;
    template <typename Predicate> xml_node +++<a href="#xml_node::find_child">find_child</a>+++(Predicate pred) const;
    template <typename Predicate> xml_node +++<a href="#xml_node::find_node">find_node</a>+++(Predicate pred) const;

    string_t +++<a href="#xml_node::path">path</a>+++(char_t delimiter = '/') const;
    xml_node +++<a href="#xml_node::first_element_by_path">xml_node::first_element_by_path</a>+++(const char_t* path, char_t delimiter = '/') const;
    xml_node +++<a href="#xml_node::root">root</a>+++() const;
    ptrdiff_t +++<a href="#xml_node::offset_debug">offset_debug</a>+++() const;

    bool +++<a href="#xml_node::set_name">set_name</a>+++(const char_t* rhs);
    bool +++<a href="#xml_node::set_value">set_value</a>+++(const char_t* rhs);

    xml_attribute +++<a href="#xml_node::append_attribute">append_attribute</a>+++(const char_t* name);
    xml_attribute +++<a href="#xml_node::prepend_attribute">prepend_attribute</a>+++(const char_t* name);
    xml_attribute +++<a href="#xml_node::insert_attribute_after">insert_attribute_after</a>+++(const char_t* name, const xml_attribute& attr);
    xml_attribute +++<a href="#xml_node::insert_attribute_before">insert_attribute_before</a>+++(const char_t* name, const xml_attribute& attr);

    xml_node +++<a href="#xml_node::append_child">append_child</a>+++(xml_node_type type = node_element);
    xml_node +++<a href="#xml_node::prepend_child">prepend_child</a>+++(xml_node_type type = node_element);
    xml_node +++<a href="#xml_node::insert_child_after">insert_child_after</a>+++(xml_node_type type, const xml_node& node);
    xml_node +++<a href="#xml_node::insert_child_before">insert_child_before</a>+++(xml_node_type type, const xml_node& node);

    xml_node +++<a href="#xml_node::append_child">append_child</a>+++(const char_t* name);
    xml_node +++<a href="#xml_node::prepend_child">prepend_child</a>+++(const char_t* name);
    xml_node +++<a href="#xml_node::insert_child_after">insert_child_after</a>+++(const char_t* name, const xml_node& node);
    xml_node +++<a href="#xml_node::insert_child_before">insert_child_before</a>+++(const char_t* name, const xml_node& node);

    xml_attribute +++<a href="#xml_node::append_copy">append_copy</a>+++(const xml_attribute& proto);
    xml_attribute +++<a href="#xml_node::prepend_copy">prepend_copy</a>+++(const xml_attribute& proto);
    xml_attribute +++<a href="#xml_node::insert_copy_after">insert_copy_after</a>+++(const xml_attribute& proto, const xml_attribute& attr);
    xml_attribute +++<a href="#xml_node::insert_copy_before">insert_copy_before</a>+++(const xml_attribute& proto, const xml_attribute& attr);

    xml_node +++<a href="#xml_node::append_copy">append_copy</a>+++(const xml_node& proto);
    xml_node +++<a href="#xml_node::prepend_copy">prepend_copy</a>+++(const xml_node& proto);
    xml_node +++<a href="#xml_node::insert_copy_after">insert_copy_after</a>+++(const xml_node& proto, const xml_node& node);
    xml_node +++<a href="#xml_node::insert_copy_before">insert_copy_before</a>+++(const xml_node& proto, const xml_node& node);

    xml_node +++<a href="#xml_node::append_move">append_move</a>+++(const xml_node& moved);
    xml_node +++<a href="#xml_node::prepend_move">prepend_move</a>+++(const xml_node& moved);
    xml_node +++<a href="#xml_node::insert_move_after">insert_move_after</a>+++(const xml_node& moved, const xml_node& node);
    xml_node +++<a href="#xml_node::insert_move_before">insert_move_before</a>+++(const xml_node& moved, const xml_node& node);

    bool +++<a href="#xml_node::remove_attribute">remove_attribute</a>+++(const xml_attribute& a);
    bool +++<a href="#xml_node::remove_attribute">remove_attribute</a>+++(const char_t* name);
    bool +++<a href="#xml_node::remove_child">remove_child</a>+++(const xml_node& n);
    bool +++<a href="#xml_node::remove_child">remove_child</a>+++(const char_t* name);

    xml_parse_result +++<a href="#xml_node::append_buffer">append_buffer</a>+++(const void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);

    void +++<a href="#xml_node::print">print</a>+++(xml_writer& writer, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto, unsigned int depth = 0) const;
    void +++<a href="#xml_node::print_stream">print</a>+++(std::ostream& os, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto, unsigned int depth = 0) const;
    void +++<a href="#xml_node::print_stream">print</a>+++(std::wostream& os, const char_t* indent = "\t", unsigned int flags = format_default, unsigned int depth = 0) const;

    xpath_node +++<a href="#xml_node::select_node">select_node</a>+++(const char_t* query, xpath_variable_set* variables = 0) const;
    xpath_node +++<a href="#xml_node::select_node_precomp">select_node</a>+++(const xpath_query& query) const;
    xpath_node_set +++<a href="#xml_node::select_nodes">select_nodes</a>+++(const char_t* query, xpath_variable_set* variables = 0) const;
    xpath_node_set +++<a href="#xml_node::select_nodes_precomp">select_nodes</a>+++(const xpath_query& query) const;

+++<span class="tok-k">class</span> <a href="#xml_document">xml_document</a>+++
    +++<a href="#xml_document::ctor">xml_document</a>+++();
    ~+++<a href="#xml_document::dtor">xml_document</a>+++();

    void +++<a href="#xml_document::reset">reset</a>+++();
    void +++<a href="#xml_document::reset">reset</a>+++(const xml_document& proto);

    xml_parse_result +++<a href="#xml_document::load_stream">load</a>+++(std::istream& stream, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
    xml_parse_result +++<a href="#xml_document::load_stream">load</a>+++(std::wistream& stream, unsigned int options = parse_default);

    xml_parse_result +++<a href="#xml_document::load_string">load_string</a>+++(const char_t* contents, unsigned int options = parse_default);

    xml_parse_result +++<a href="#xml_document::load_file">load_file</a>+++(const char* path, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
    xml_parse_result +++<a href="#xml_document::load_file_wide">load_file</a>+++(const wchar_t* path, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);

    xml_parse_result +++<a href="#xml_document::load_buffer">load_buffer</a>+++(const void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
    xml_parse_result +++<a href="#xml_document::load_buffer_inplace">load_buffer_inplace</a>+++(void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);
    xml_parse_result +++<a href="#xml_document::load_buffer_inplace_own">load_buffer_inplace_own</a>+++(void* contents, size_t size, unsigned int options = parse_default, xml_encoding encoding = encoding_auto);

    bool +++<a href="#xml_document::save_file">save_file</a>+++(const char* path, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;
    bool +++<a href="#xml_document::save_file_wide">save_file</a>+++(const wchar_t* path, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;

    void +++<a href="#xml_document::save_stream">save</a>+++(std::ostream& stream, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;
    void +++<a href="#xml_document::save_stream">save</a>+++(std::wostream& stream, const char_t* indent = "\t", unsigned int flags = format_default) const;

    void +++<a href="#xml_document::save">save</a>+++(xml_writer& writer, const char_t* indent = "\t", unsigned int flags = format_default, xml_encoding encoding = encoding_auto) const;

    xml_node +++<a href="#xml_document::document_element">document_element</a>+++() const;

+++<span class="tok-k">struct</span> <a href="#xml_parse_result">xml_parse_result</a>+++
    xml_parse_status +++<a href="#xml_parse_result::status">status</a>+++;
    ptrdiff_t +++<a href="#xml_parse_result::offset">offset</a>+++;
    xml_encoding +++<a href="#xml_parse_result::encoding">encoding</a>+++;

    operator +++<a href="#xml_parse_result::bool">bool</a>+++() const;
    const char* +++<a href="#xml_parse_result::description">description</a>+++() const;

+++<span class="tok-k">class</span> <a href="#xml_node_iterator">xml_node_iterator</a>+++
+++<span class="tok-k">class</span> <a href="#xml_attribute_iterator">xml_attribute_iterator</a>+++

+++<span class="tok-k">class</span> <a href="#xml_tree_walker">xml_tree_walker</a>+++
    virtual bool +++<a href="#xml_tree_walker::begin">begin</a>+++(xml_node& node);
    virtual bool +++<a href="#xml_tree_walker::for_each">for_each</a>+++(xml_node& node) = 0;
    virtual bool +++<a href="#xml_tree_walker::end">end</a>+++(xml_node& node);

    int +++<a href="#xml_tree_walker::depth">depth</a>+++() const;

+++<span class="tok-k">class</span> <a href="#xml_text">xml_text</a>+++
    bool +++<a href="#xml_text::empty">empty</a>+++() const;
    operator +++<a href="#xml_text::unspecified_bool_type">xml_text::unspecified_bool_type</a>+++() const;

    const char_t* +++<a href="#xml_text::get">xml_text::get</a>+++() const;

    const char_t* +++<a href="#xml_text::as_string">as_string</a>+++(const char_t* def = "") const;
    int +++<a href="#xml_text::as_int">as_int</a>+++(int def = 0) const;
    unsigned int +++<a href="#xml_text::as_uint">as_uint</a>+++(unsigned int def = 0) const;
    double +++<a href="#xml_text::as_double">as_double</a>+++(double def = 0) const;
    float +++<a href="#xml_text::as_float">as_float</a>+++(float def = 0) const;
    bool +++<a href="#xml_text::as_bool">as_bool</a>+++(bool def = false) const;
    long long +++<a href="#xml_text::as_llong">as_llong</a>+++(long long def = 0) const;
    unsigned long long +++<a href="#xml_text::as_ullong">as_ullong</a>+++(unsigned long long def = 0) const;

    bool +++<a href="#xml_text::set">set</a>+++(const char_t* rhs);

    bool +++<a href="#xml_text::set">set</a>+++(int rhs);
    bool +++<a href="#xml_text::set">set</a>+++(unsigned int rhs);
    bool +++<a href="#xml_text::set">set</a>+++(double rhs);
    bool +++<a href="#xml_text::set">set</a>+++(float rhs);
    bool +++<a href="#xml_text::set">set</a>+++(bool rhs);
    bool +++<a href="#xml_text::set">set</a>+++(long long rhs);
    bool +++<a href="#xml_text::set">set</a>+++(unsigned long long rhs);

    xml_text& +++<a href="#xml_text::assign">operator=</a>+++(const char_t* rhs);
    xml_text& +++<a href="#xml_text::assign">operator=</a>+++(int rhs);
    xml_text& +++<a href="#xml_text::assign">operator=</a>+++(unsigned int rhs);
    xml_text& +++<a href="#xml_text::assign">operator=</a>+++(double rhs);
    xml_text& +++<a href="#xml_text::assign">operator=</a>+++(float rhs);
    xml_text& +++<a href="#xml_text::assign">operator=</a>+++(bool rhs);
    xml_text& +++<a href="#xml_text::assign">operator=</a>+++(long long rhs);
    xml_text& +++<a href="#xml_text::assign">operator=</a>+++(unsigned long long rhs);

    xml_node +++<a href="#xml_text::data">data</a>+++() const;

+++<span class="tok-k">class</span> <a href="#xml_writer">xml_writer</a>+++
    virtual void +++<a href="#xml_writer::write">write</a>+++(const void* data, size_t size) = 0;

+++<span class="tok-k">class</span> <a href="#xml_writer_file">xml_writer_file</a>+++: public xml_writer
    +++<a href="#xml_writer_file">xml_writer_file</a>+++(void* file);

+++<span class="tok-k">class</span> <a href="#xml_writer_stream">xml_writer_stream</a>+++: public xml_writer
    +++<a href="#xml_writer_stream">xml_writer_stream</a>+++(std::ostream& stream);
    +++<a href="#xml_writer_stream">xml_writer_stream</a>+++(std::wostream& stream);

+++<span class="tok-k">struct</span> <a href="#xpath_parse_result">xpath_parse_result</a>+++
    const char* +++<a href="#xpath_parse_result::error">error</a>+++;
    ptrdiff_t +++<a href="#xpath_parse_result::offset">offset</a>+++;

    operator +++<a href="#xpath_parse_result::bool">bool</a>+++() const;
    const char* +++<a href="#xpath_parse_result::description">description</a>+++() const;

+++<span class="tok-k">class</span> <a href="#xpath_query">xpath_query</a>+++
    explicit +++<a href="#xpath_query::ctor">xpath_query</a>+++(const char_t* query, xpath_variable_set* variables = 0);

    bool +++<a href="#xpath_query::evaluate_boolean">evaluate_boolean</a>+++(const xpath_node& n) const;
    double +++<a href="#xpath_query::evaluate_number">evaluate_number</a>+++(const xpath_node& n) const;
    string_t +++<a href="#xpath_query::evaluate_string">evaluate_string</a>+++(const xpath_node& n) const;
    size_t +++<a href="#xpath_query::evaluate_string_buffer">evaluate_string</a>+++(char_t* buffer, size_t capacity, const xpath_node& n) const;
    xpath_node_set +++<a href="#xpath_query::evaluate_node_set">evaluate_node_set</a>+++(const xpath_node& n) const;
    xpath_node +++<a href="#xpath_query::evaluate_node">evaluate_node</a>+++(const xpath_node& n) const;

    xpath_value_type +++<a href="#xpath_query::return_type">return_type</a>+++() const;

    const xpath_parse_result& +++<a href="#xpath_query::result">result</a>+++() const;
    operator +++<a href="#xpath_query::unspecified_bool_type">unspecified_bool_type</a>+++() const;

+++<span class="tok-k">class</span> <a href="#xpath_exception">xpath_exception</a>+++: public std::exception
    virtual const char* +++<a href="#xpath_exception::what">what</a>+++() const throw();

    const xpath_parse_result& +++<a href="#xpath_exception::result">result</a>+++() const;

+++<span class="tok-k">class</span> <a href="#xpath_node">xpath_node</a>+++
    +++<a href="#xpath_node::ctor">xpath_node</a>+++();
    +++<a href="#xpath_node::ctor">xpath_node</a>+++(const xml_node& node);
    +++<a href="#xpath_node::ctor">xpath_node</a>+++(const xml_attribute& attribute, const xml_node& parent);

    xml_node +++<a href="#xpath_node::node">node</a>+++() const;
    xml_attribute +++<a href="#xpath_node::attribute">attribute</a>+++() const;
    xml_node +++<a href="#xpath_node::parent">parent</a>+++() const;

    operator +++<a href="#xpath_node::unspecified_bool_type">unspecified_bool_type</a>+++() const;
    bool +++<a href="#xpath_node::comparison">operator==</a>+++(const xpath_node& n) const;
    bool +++<a href="#xpath_node::comparison">operator!=</a>+++(const xpath_node& n) const;

+++<span class="tok-k">class</span> <a href="#xpath_node_set">xpath_node_set</a>+++
    +++<a href="#xpath_node_set::ctor">xpath_node_set</a>+++();
    +++<a href="#xpath_node_set::ctor">xpath_node_set</a>+++(const_iterator begin, const_iterator end, type_t type = type_unsorted);

    typedef const xpath_node* +++<a href="#xpath_node_set::const_iterator">const_iterator</a>+++;
    const_iterator +++<a href="#xpath_node_set::begin">begin</a>+++() const;
    const_iterator +++<a href="#xpath_node_set::end">end</a>+++() const;

    const xpath_node& +++<a href="#xpath_node_set::index">operator[</a>+++](size_t index) const;
    size_t +++<a href="#xpath_node_set::size">size</a>+++() const;
    bool +++<a href="#xpath_node_set::empty">empty</a>+++() const;

    xpath_node +++<a href="#xpath_node_set::first">first</a>+++() const;

    enum type_t {+++<a href="#xpath_node_set::type_unsorted">type_unsorted</a>+++, +++<a href="#xpath_node_set::type_sorted">type_sorted</a>+++, +++<a href="#xpath_node_set::type_sorted_reverse">type_sorted_reverse</a>+++};
    type_t +++<a href="#xpath_node_set::type">type</a>+++() const;
    void +++<a href="#xpath_node_set::sort">sort</a>+++(bool reverse = false);

+++<span class="tok-k">class</span> <a href="#xpath_variable">xpath_variable</a>+++
    const char_t* +++<a href="#xpath_variable::name">name</a>+++() const;
    xpath_value_type +++<a href="#xpath_variable::type">type</a>+++() const;

    bool +++<a href="#xpath_variable::get_boolean">get_boolean</a>+++() const;
    double +++<a href="#xpath_variable::get_number">get_number</a>+++() const;
    const char_t* +++<a href="#xpath_variable::get_string">get_string</a>+++() const;
    const xpath_node_set& +++<a href="#xpath_variable::get_node_set">get_node_set</a>+++() const;

    bool +++<a href="#xpath_variable::set">set</a>+++(bool value);
    bool +++<a href="#xpath_variable::set">set</a>+++(double value);
    bool +++<a href="#xpath_variable::set">set</a>+++(const char_t* value);
    bool +++<a href="#xpath_variable::set">set</a>+++(const xpath_node_set& value);

+++<span class="tok-k">class</span> <a href="#xpath_variable_set">xpath_variable_set</a>+++
    xpath_variable* +++<a href="#xpath_variable_set::add">add</a>+++(const char_t* name, xpath_value_type type);

    bool +++<a href="#xpath_variable_set::set">set</a>+++(const char_t* name, bool value);
    bool +++<a href="#xpath_variable_set::set">set</a>+++(const char_t* name, double value);
    bool +++<a href="#xpath_variable_set::set">set</a>+++(const char_t* name, const char_t* value);
    bool +++<a href="#xpath_variable_set::set">set</a>+++(const char_t* name, const xpath_node_set& value);

    xpath_variable* +++<a href="#xpath_variable_set::get">get</a>+++(const char_t* name);
    const xpath_variable* +++<a href="#xpath_variable_set::get">get</a>+++(const char_t* name) const;
----

[[apiref.functions]]
=== Functions

[source,subs="+macros"]
----
std::string +++<a href="#as_utf8">as_utf8</a>+++(const wchar_t* str);
std::string +++<a href="#as_utf8">as_utf8</a>+++(const std::wstring& str);
std::wstring +++<a href="#as_wide">as_wide</a>+++(const char* str);
std::wstring +++<a href="#as_wide">as_wide</a>+++(const std::string& str);
void +++<a href="#set_memory_management_functions">set_memory_management_functions</a>+++(allocation_function allocate, deallocation_function deallocate);
allocation_function +++<a href="#get_memory_allocation_function">get_memory_allocation_function</a>+++();
deallocation_function +++<a href="#get_memory_deallocation_function">get_memory_deallocation_function</a>+++();
----