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
|
// ----------------------------------------------------------------------------
// Copyright (C) 2006, 2009 Marcin Kalicinski
//
// Distributed under the Boost Software License, Version 1.0.
// (See accompanying file LICENSE_1_0.txt or copy at
// http://www.boost.org/LICENSE_1_0.txt)
//
// For more information, see www.boost.org
// ----------------------------------------------------------------------------
#ifndef BOOST_PROPERTY_TREE_RAPIDXML_HPP_INCLUDED
#define BOOST_PROPERTY_TREE_RAPIDXML_HPP_INCLUDED
//! \file rapidxml.hpp This file contains rapidxml parser and DOM implementation
#include <cstdlib> // For std::size_t
#include <cassert> // For assert
#include <new> // For placement new
// On MSVC, disable "conditional expression is constant" warning (level 4).
// This warning is almost impossible to avoid with certain types of templated code
#ifdef _MSC_VER
#pragma warning(push)
#pragma warning(disable:4127) // Conditional expression is constant
#endif
///////////////////////////////////////////////////////////////////////////
// BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR
#include <exception> // For std::exception
#define BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR(what, where) throw parse_error(what, where)
namespace boost { namespace property_tree { namespace detail {namespace rapidxml
{
//! Parse error exception.
//! This exception is thrown by the parser when an error occurs.
//! Use what() function to get human-readable error message.
//! Use where() function to get a pointer to position within source text where error was detected.
//! <br><br>
//! If throwing exceptions by the parser is undesirable,
//! it can be disabled by defining RAPIDXML_NO_EXCEPTIONS macro before rapidxml.hpp is included.
//! This will cause the parser to call rapidxml::parse_error_handler() function instead of throwing an exception.
//! This function must be defined by the user.
//! <br><br>
//! This class derives from <code>std::exception</code> class.
class parse_error: public std::exception
{
public:
//! Constructs parse error
parse_error(const char *wa, void *we)
: m_what(wa)
, m_where(we)
{
}
//! Gets human readable description of error.
//! \return Pointer to null terminated description of the error.
virtual const char *what() const throw()
{
return m_what;
}
//! Gets pointer to character data where error happened.
//! Ch should be the same as char type of xml_document that produced the error.
//! \return Pointer to location within the parsed string where error occured.
template<class Ch>
Ch *where() const
{
return reinterpret_cast<Ch *>(m_where);
}
private:
const char *m_what;
void *m_where;
};
}}}}
///////////////////////////////////////////////////////////////////////////
// Pool sizes
#ifndef BOOST_PROPERTY_TREE_RAPIDXML_STATIC_POOL_SIZE
// Size of static memory block of memory_pool.
// Define BOOST_PROPERTY_TREE_RAPIDXML_STATIC_POOL_SIZE before including rapidxml.hpp if you want to override the default value.
// No dynamic memory allocations are performed by memory_pool until static memory is exhausted.
#define BOOST_PROPERTY_TREE_RAPIDXML_STATIC_POOL_SIZE (64 * 1024)
#endif
#ifndef BOOST_PROPERTY_TREE_RAPIDXML_DYNAMIC_POOL_SIZE
// Size of dynamic memory block of memory_pool.
// Define BOOST_PROPERTY_TREE_RAPIDXML_DYNAMIC_POOL_SIZE before including rapidxml.hpp if you want to override the default value.
// After the static block is exhausted, dynamic blocks with approximately this size are allocated by memory_pool.
#define BOOST_PROPERTY_TREE_RAPIDXML_DYNAMIC_POOL_SIZE (64 * 1024)
#endif
#ifndef BOOST_PROPERTY_TREE_RAPIDXML_ALIGNMENT
// Memory allocation alignment.
// Define BOOST_PROPERTY_TREE_RAPIDXML_ALIGNMENT before including rapidxml.hpp if you want to override the default value, which is the size of pointer.
// All memory allocations for nodes, attributes and strings will be aligned to this value.
// This must be a power of 2 and at least 1, otherwise memory_pool will not work.
#define BOOST_PROPERTY_TREE_RAPIDXML_ALIGNMENT sizeof(void *)
#endif
namespace boost { namespace property_tree { namespace detail {namespace rapidxml
{
// Forward declarations
template<class Ch> class xml_node;
template<class Ch> class xml_attribute;
template<class Ch> class xml_document;
//! Enumeration listing all node types produced by the parser.
//! Use xml_node::type() function to query node type.
enum node_type
{
node_document, //!< A document node. Name and value are empty.
node_element, //!< An element node. Name contains element name. Value contains text of first data node.
node_data, //!< A data node. Name is empty. Value contains data text.
node_cdata, //!< A CDATA node. Name is empty. Value contains data text.
node_comment, //!< A comment node. Name is empty. Value contains comment text.
node_declaration, //!< A declaration node. Name and value are empty. Declaration parameters (version, encoding and standalone) are in node attributes.
node_doctype, //!< A DOCTYPE node. Name is empty. Value contains DOCTYPE text.
node_pi //!< A PI node. Name contains target. Value contains instructions.
};
///////////////////////////////////////////////////////////////////////
// Parsing flags
//! Parse flag instructing the parser to not create data nodes.
//! Text of first data node will still be placed in value of parent element, unless rapidxml::parse_no_element_values flag is also specified.
//! Can be combined with other flags by use of | operator.
//! <br><br>
//! See xml_document::parse() function.
const int parse_no_data_nodes = 0x1;
//! Parse flag instructing the parser to not use text of first data node as a value of parent element.
//! Can be combined with other flags by use of | operator.
//! Note that child data nodes of element node take precendence over its value when printing.
//! That is, if element has one or more child data nodes <em>and</em> a value, the value will be ignored.
//! Use rapidxml::parse_no_data_nodes flag to prevent creation of data nodes if you want to manipulate data using values of elements.
//! <br><br>
//! See xml_document::parse() function.
const int parse_no_element_values = 0x2;
//! Parse flag instructing the parser to not place zero terminators after strings in the source text.
//! By default zero terminators are placed, modifying source text.
//! Can be combined with other flags by use of | operator.
//! <br><br>
//! See xml_document::parse() function.
const int parse_no_string_terminators = 0x4;
//! Parse flag instructing the parser to not translate entities in the source text.
//! By default entities are translated, modifying source text.
//! Can be combined with other flags by use of | operator.
//! <br><br>
//! See xml_document::parse() function.
const int parse_no_entity_translation = 0x8;
//! Parse flag instructing the parser to disable UTF-8 handling and assume plain 8 bit characters.
//! By default, UTF-8 handling is enabled.
//! Can be combined with other flags by use of | operator.
//! <br><br>
//! See xml_document::parse() function.
const int parse_no_utf8 = 0x10;
//! Parse flag instructing the parser to create XML declaration node.
//! By default, declaration node is not created.
//! Can be combined with other flags by use of | operator.
//! <br><br>
//! See xml_document::parse() function.
const int parse_declaration_node = 0x20;
//! Parse flag instructing the parser to create comments nodes.
//! By default, comment nodes are not created.
//! Can be combined with other flags by use of | operator.
//! <br><br>
//! See xml_document::parse() function.
const int parse_comment_nodes = 0x40;
//! Parse flag instructing the parser to create DOCTYPE node.
//! By default, doctype node is not created.
//! Although W3C specification allows at most one DOCTYPE node, RapidXml will silently accept documents with more than one.
//! Can be combined with other flags by use of | operator.
//! <br><br>
//! See xml_document::parse() function.
const int parse_doctype_node = 0x80;
//! Parse flag instructing the parser to create PI nodes.
//! By default, PI nodes are not created.
//! Can be combined with other flags by use of | operator.
//! <br><br>
//! See xml_document::parse() function.
const int parse_pi_nodes = 0x100;
//! Parse flag instructing the parser to validate closing tag names.
//! If not set, name inside closing tag is irrelevant to the parser.
//! By default, closing tags are not validated.
//! Can be combined with other flags by use of | operator.
//! <br><br>
//! See xml_document::parse() function.
const int parse_validate_closing_tags = 0x200;
//! Parse flag instructing the parser to trim all leading and trailing whitespace of data nodes.
//! By default, whitespace is not trimmed.
//! This flag does not cause the parser to modify source text.
//! Can be combined with other flags by use of | operator.
//! <br><br>
//! See xml_document::parse() function.
const int parse_trim_whitespace = 0x400;
//! Parse flag instructing the parser to condense all whitespace runs of data nodes to a single space character.
//! Trimming of leading and trailing whitespace of data is controlled by rapidxml::parse_trim_whitespace flag.
//! By default, whitespace is not normalized.
//! If this flag is specified, source text will be modified.
//! Can be combined with other flags by use of | operator.
//! <br><br>
//! See xml_document::parse() function.
const int parse_normalize_whitespace = 0x800;
// Compound flags
//! Parse flags which represent default behaviour of the parser.
//! This is always equal to 0, so that all other flags can be simply ored together.
//! Normally there is no need to inconveniently disable flags by anding with their negated (~) values.
//! This also means that meaning of each flag is a <i>negation</i> of the default setting.
//! For example, if flag name is rapidxml::parse_no_utf8, it means that utf-8 is <i>enabled</i> by default,
//! and using the flag will disable it.
//! <br><br>
//! See xml_document::parse() function.
const int parse_default = 0;
//! A combination of parse flags that forbids any modifications of the source text.
//! This also results in faster parsing. However, note that the following will occur:
//! <ul>
//! <li>names and values of nodes will not be zero terminated, you have to use xml_base::name_size() and xml_base::value_size() functions to determine where name and value ends</li>
//! <li>entities will not be translated</li>
//! <li>whitespace will not be normalized</li>
//! </ul>
//! See xml_document::parse() function.
const int parse_non_destructive = parse_no_string_terminators | parse_no_entity_translation;
//! A combination of parse flags resulting in fastest possible parsing, without sacrificing important data.
//! <br><br>
//! See xml_document::parse() function.
const int parse_fastest = parse_non_destructive | parse_no_data_nodes;
//! A combination of parse flags resulting in largest amount of data being extracted.
//! This usually results in slowest parsing.
//! <br><br>
//! See xml_document::parse() function.
const int parse_full = parse_declaration_node | parse_comment_nodes | parse_doctype_node | parse_pi_nodes | parse_validate_closing_tags;
///////////////////////////////////////////////////////////////////////
// Internals
//! \cond internal
namespace internal
{
// Struct that contains lookup tables for the parser
// It must be a template to allow correct linking (because it has static data members, which are defined in a header file).
template<int Dummy>
struct lookup_tables
{
static const unsigned char lookup_whitespace[256]; // Whitespace table
static const unsigned char lookup_node_name[256]; // Node name table
static const unsigned char lookup_text[256]; // Text table
static const unsigned char lookup_text_pure_no_ws[256]; // Text table
static const unsigned char lookup_text_pure_with_ws[256]; // Text table
static const unsigned char lookup_attribute_name[256]; // Attribute name table
static const unsigned char lookup_attribute_data_1[256]; // Attribute data table with single quote
static const unsigned char lookup_attribute_data_1_pure[256]; // Attribute data table with single quote
static const unsigned char lookup_attribute_data_2[256]; // Attribute data table with double quotes
static const unsigned char lookup_attribute_data_2_pure[256]; // Attribute data table with double quotes
static const unsigned char lookup_digits[256]; // Digits
static const unsigned char lookup_upcase[256]; // To uppercase conversion table for ASCII characters
};
// Find length of the string
template<class Ch>
inline std::size_t measure(const Ch *p)
{
const Ch *tmp = p;
while (*tmp)
++tmp;
return tmp - p;
}
// Compare strings for equality
template<class Ch>
inline bool compare(const Ch *p1, std::size_t size1, const Ch *p2, std::size_t size2, bool case_sensitive)
{
if (size1 != size2)
return false;
if (case_sensitive)
{
for (const Ch *end = p1 + size1; p1 < end; ++p1, ++p2)
if (*p1 != *p2)
return false;
}
else
{
for (const Ch *end = p1 + size1; p1 < end; ++p1, ++p2)
if (lookup_tables<0>::lookup_upcase[static_cast<unsigned char>(*p1)] != lookup_tables<0>::lookup_upcase[static_cast<unsigned char>(*p2)])
return false;
}
return true;
}
template<class Ch>
inline size_t get_index(const Ch c)
{
// If not ASCII char, its sematic is same as plain 'z'
if (c > 255)
{
return 'z';
}
return c;
}
}
//! \endcond
///////////////////////////////////////////////////////////////////////
// Memory pool
//! This class is used by the parser to create new nodes and attributes, without overheads of dynamic memory allocation.
//! In most cases, you will not need to use this class directly.
//! However, if you need to create nodes manually or modify names/values of nodes,
//! you are encouraged to use memory_pool of relevant xml_document to allocate the memory.
//! Not only is this faster than allocating them by using <code>new</code> operator,
//! but also their lifetime will be tied to the lifetime of document,
//! possibly simplyfing memory management.
//! <br><br>
//! Call allocate_node() or allocate_attribute() functions to obtain new nodes or attributes from the pool.
//! You can also call allocate_string() function to allocate strings.
//! Such strings can then be used as names or values of nodes without worrying about their lifetime.
//! Note that there is no <code>free()</code> function -- all allocations are freed at once when clear() function is called,
//! or when the pool is destroyed.
//! <br><br>
//! It is also possible to create a standalone memory_pool, and use it
//! to allocate nodes, whose lifetime will not be tied to any document.
//! <br><br>
//! Pool maintains <code>BOOST_PROPERTY_TREE_RAPIDXML_STATIC_POOL_SIZE</code> bytes of statically allocated memory.
//! Until static memory is exhausted, no dynamic memory allocations are done.
//! When static memory is exhausted, pool allocates additional blocks of memory of size <code>BOOST_PROPERTY_TREE_RAPIDXML_DYNAMIC_POOL_SIZE</code> each,
//! by using global <code>new[]</code> and <code>delete[]</code> operators.
//! This behaviour can be changed by setting custom allocation routines.
//! Use set_allocator() function to set them.
//! <br><br>
//! Allocations for nodes, attributes and strings are aligned at <code>BOOST_PROPERTY_TREE_RAPIDXML_ALIGNMENT</code> bytes.
//! This value defaults to the size of pointer on target architecture.
//! <br><br>
//! To obtain absolutely top performance from the parser,
//! it is important that all nodes are allocated from a single, contiguous block of memory.
//! Otherwise, cache misses when jumping between two (or more) disjoint blocks of memory can slow down parsing quite considerably.
//! If required, you can tweak <code>BOOST_PROPERTY_TREE_RAPIDXML_STATIC_POOL_SIZE</code>, <code>BOOST_PROPERTY_TREE_RAPIDXML_DYNAMIC_POOL_SIZE</code> and <code>BOOST_PROPERTY_TREE_RAPIDXML_ALIGNMENT</code>
//! to obtain best wasted memory to performance compromise.
//! To do it, define their values before rapidxml.hpp file is included.
//! \param Ch Character type of created nodes.
template<class Ch = char>
class memory_pool
{
public:
//! \cond internal
typedef void *(alloc_func)(std::size_t); // Type of user-defined function used to allocate memory
typedef void (free_func)(void *); // Type of user-defined function used to free memory
//! \endcond
//! Constructs empty pool with default allocator functions.
memory_pool()
: m_alloc_func(0)
, m_free_func(0)
{
init();
}
//! Destroys pool and frees all the memory.
//! This causes memory occupied by nodes allocated by the pool to be freed.
//! Nodes allocated from the pool are no longer valid.
~memory_pool()
{
clear();
}
//! Allocates a new node from the pool, and optionally assigns name and value to it.
//! If the allocation request cannot be accomodated, this function will throw <code>std::bad_alloc</code>.
//! If exceptions are disabled by defining RAPIDXML_NO_EXCEPTIONS, this function
//! will call rapidxml::parse_error_handler() function.
//! \param type Type of node to create.
//! \param name Name to assign to the node, or 0 to assign no name.
//! \param value Value to assign to the node, or 0 to assign no value.
//! \param name_size Size of name to assign, or 0 to automatically calculate size from name string.
//! \param value_size Size of value to assign, or 0 to automatically calculate size from value string.
//! \return Pointer to allocated node. This pointer will never be NULL.
xml_node<Ch> *allocate_node(node_type type,
const Ch *name = 0, const Ch *value = 0,
std::size_t name_size = 0, std::size_t value_size = 0)
{
void *memory = allocate_aligned(sizeof(xml_node<Ch>));
xml_node<Ch> *node = new(memory) xml_node<Ch>(type);
if (name)
{
if (name_size > 0)
node->name(name, name_size);
else
node->name(name);
}
if (value)
{
if (value_size > 0)
node->value(value, value_size);
else
node->value(value);
}
return node;
}
//! Allocates a new attribute from the pool, and optionally assigns name and value to it.
//! If the allocation request cannot be accomodated, this function will throw <code>std::bad_alloc</code>.
//! If exceptions are disabled by defining RAPIDXML_NO_EXCEPTIONS, this function
//! will call rapidxml::parse_error_handler() function.
//! \param name Name to assign to the attribute, or 0 to assign no name.
//! \param value Value to assign to the attribute, or 0 to assign no value.
//! \param name_size Size of name to assign, or 0 to automatically calculate size from name string.
//! \param value_size Size of value to assign, or 0 to automatically calculate size from value string.
//! \return Pointer to allocated attribute. This pointer will never be NULL.
xml_attribute<Ch> *allocate_attribute(const Ch *name = 0, const Ch *value = 0,
std::size_t name_size = 0, std::size_t value_size = 0)
{
void *memory = allocate_aligned(sizeof(xml_attribute<Ch>));
xml_attribute<Ch> *attribute = new(memory) xml_attribute<Ch>;
if (name)
{
if (name_size > 0)
attribute->name(name, name_size);
else
attribute->name(name);
}
if (value)
{
if (value_size > 0)
attribute->value(value, value_size);
else
attribute->value(value);
}
return attribute;
}
//! Allocates a char array of given size from the pool, and optionally copies a given string to it.
//! If the allocation request cannot be accomodated, this function will throw <code>std::bad_alloc</code>.
//! If exceptions are disabled by defining RAPIDXML_NO_EXCEPTIONS, this function
//! will call rapidxml::parse_error_handler() function.
//! \param source String to initialize the allocated memory with, or 0 to not initialize it.
//! \param size Number of characters to allocate, or zero to calculate it automatically from source string length; if size is 0, source string must be specified and null terminated.
//! \return Pointer to allocated char array. This pointer will never be NULL.
Ch *allocate_string(const Ch *source = 0, std::size_t size = 0)
{
assert(source || size); // Either source or size (or both) must be specified
if (size == 0)
size = internal::measure(source) + 1;
Ch *result = static_cast<Ch *>(allocate_aligned(size * sizeof(Ch)));
if (source)
for (std::size_t i = 0; i < size; ++i)
result[i] = source[i];
return result;
}
//! Clones an xml_node and its hierarchy of child nodes and attributes.
//! Nodes and attributes are allocated from this memory pool.
//! Names and values are not cloned, they are shared between the clone and the source.
//! Result node can be optionally specified as a second parameter,
//! in which case its contents will be replaced with cloned source node.
//! This is useful when you want to clone entire document.
//! \param source Node to clone.
//! \param result Node to put results in, or 0 to automatically allocate result node
//! \return Pointer to cloned node. This pointer will never be NULL.
xml_node<Ch> *clone_node(const xml_node<Ch> *source, xml_node<Ch> *result = 0)
{
// Prepare result node
if (result)
{
result->remove_all_attributes();
result->remove_all_nodes();
result->type(source->type());
}
else
result = allocate_node(source->type());
// Clone name and value
result->name(source->name(), source->name_size());
result->value(source->value(), source->value_size());
// Clone child nodes and attributes
for (xml_node<Ch> *child = source->first_node(); child; child = child->next_sibling())
result->append_node(clone_node(child));
for (xml_attribute<Ch> *attr = source->first_attribute(); attr; attr = attr->next_attribute())
result->append_attribute(allocate_attribute(attr->name(), attr->value(), attr->name_size(), attr->value_size()));
return result;
}
//! Clears the pool.
//! This causes memory occupied by nodes allocated by the pool to be freed.
//! Any nodes or strings allocated from the pool will no longer be valid.
void clear()
{
while (m_begin != m_static_memory)
{
char *previous_begin = reinterpret_cast<header *>(align(m_begin))->previous_begin;
if (m_free_func)
m_free_func(m_begin);
else
delete[] m_begin;
m_begin = previous_begin;
}
init();
}
//! Sets or resets the user-defined memory allocation functions for the pool.
//! This can only be called when no memory is allocated from the pool yet, otherwise results are undefined.
//! Allocation function must not return invalid pointer on failure. It should either throw,
//! stop the program, or use <code>longjmp()</code> function to pass control to other place of program.
//! If it returns invalid pointer, results are undefined.
//! <br><br>
//! User defined allocation functions must have the following forms:
//! <br><code>
//! <br>void *allocate(std::size_t size);
//! <br>void free(void *pointer);
//! </code><br>
//! \param af Allocation function, or 0 to restore default function
//! \param ff Free function, or 0 to restore default function
void set_allocator(alloc_func *af, free_func *ff)
{
assert(m_begin == m_static_memory && m_ptr == align(m_begin)); // Verify that no memory is allocated yet
m_alloc_func = af;
m_free_func = ff;
}
private:
struct header
{
char *previous_begin;
};
void init()
{
m_begin = m_static_memory;
m_ptr = align(m_begin);
m_end = m_static_memory + sizeof(m_static_memory);
}
char *align(char *ptr)
{
std::size_t alignment = ((BOOST_PROPERTY_TREE_RAPIDXML_ALIGNMENT - (std::size_t(ptr) & (BOOST_PROPERTY_TREE_RAPIDXML_ALIGNMENT - 1))) & (BOOST_PROPERTY_TREE_RAPIDXML_ALIGNMENT - 1));
return ptr + alignment;
}
char *allocate_raw(std::size_t size)
{
// Allocate
void *memory;
if (m_alloc_func) // Allocate memory using either user-specified allocation function or global operator new[]
{
memory = m_alloc_func(size);
assert(memory); // Allocator is not allowed to return 0, on failure it must either throw, stop the program or use longjmp
}
else
{
memory = new char[size];
}
return static_cast<char *>(memory);
}
void *allocate_aligned(std::size_t size)
{
// Calculate aligned pointer
char *result = align(m_ptr);
// If not enough memory left in current pool, allocate a new pool
if (result + size > m_end)
{
// Calculate required pool size (may be bigger than BOOST_PROPERTY_TREE_RAPIDXML_DYNAMIC_POOL_SIZE)
std::size_t pool_size = BOOST_PROPERTY_TREE_RAPIDXML_DYNAMIC_POOL_SIZE;
if (pool_size < size)
pool_size = size;
// Allocate
std::size_t alloc_size = sizeof(header) + (2 * BOOST_PROPERTY_TREE_RAPIDXML_ALIGNMENT - 2) + pool_size; // 2 alignments required in worst case: one for header, one for actual allocation
char *raw_memory = allocate_raw(alloc_size);
// Setup new pool in allocated memory
char *pool = align(raw_memory);
header *new_header = reinterpret_cast<header *>(pool);
new_header->previous_begin = m_begin;
m_begin = raw_memory;
m_ptr = pool + sizeof(header);
m_end = raw_memory + alloc_size;
// Calculate aligned pointer again using new pool
result = align(m_ptr);
}
// Update pool and return aligned pointer
m_ptr = result + size;
return result;
}
char *m_begin; // Start of raw memory making up current pool
char *m_ptr; // First free byte in current pool
char *m_end; // One past last available byte in current pool
char m_static_memory[BOOST_PROPERTY_TREE_RAPIDXML_STATIC_POOL_SIZE]; // Static raw memory
alloc_func *m_alloc_func; // Allocator function, or 0 if default is to be used
free_func *m_free_func; // Free function, or 0 if default is to be used
};
///////////////////////////////////////////////////////////////////////////
// XML base
//! Base class for xml_node and xml_attribute implementing common functions:
//! name(), name_size(), value(), value_size() and parent().
//! \param Ch Character type to use
template<class Ch = char>
class xml_base
{
public:
///////////////////////////////////////////////////////////////////////////
// Construction & destruction
// Construct a base with empty name, value and parent
xml_base()
: m_name(0)
, m_value(0)
, m_parent(0)
{
}
///////////////////////////////////////////////////////////////////////////
// Node data access
//! Gets name of the node.
//! Interpretation of name depends on type of node.
//! Note that name will not be zero-terminated if rapidxml::parse_no_string_terminators option was selected during parse.
//! <br><br>
//! Use name_size() function to determine length of the name.
//! \return Name of node, or empty string if node has no name.
Ch *name() const
{
return m_name ? m_name : nullstr();
}
//! Gets size of node name, not including terminator character.
//! This function works correctly irrespective of whether name is or is not zero terminated.
//! \return Size of node name, in characters.
std::size_t name_size() const
{
return m_name ? m_name_size : 0;
}
//! Gets value of node.
//! Interpretation of value depends on type of node.
//! Note that value will not be zero-terminated if rapidxml::parse_no_string_terminators option was selected during parse.
//! <br><br>
//! Use value_size() function to determine length of the value.
//! \return Value of node, or empty string if node has no value.
Ch *value() const
{
return m_value ? m_value : nullstr();
}
//! Gets size of node value, not including terminator character.
//! This function works correctly irrespective of whether value is or is not zero terminated.
//! \return Size of node value, in characters.
std::size_t value_size() const
{
return m_value ? m_value_size : 0;
}
///////////////////////////////////////////////////////////////////////////
// Node modification
//! Sets name of node to a non zero-terminated string.
//! See \ref ownership_of_strings.
//! <br><br>
//! Note that node does not own its name or value, it only stores a pointer to it.
//! It will not delete or otherwise free the pointer on destruction.
//! It is reponsibility of the user to properly manage lifetime of the string.
//! The easiest way to achieve it is to use memory_pool of the document to allocate the string -
//! on destruction of the document the string will be automatically freed.
//! <br><br>
//! Size of name must be specified separately, because name does not have to be zero terminated.
//! Use name(const Ch *) function to have the length automatically calculated (string must be zero terminated).
//! \param n Name of node to set. Does not have to be zero terminated.
//! \param size Size of name, in characters. This does not include zero terminator, if one is present.
void name(const Ch *n, std::size_t size)
{
m_name = const_cast<Ch *>(n);
m_name_size = size;
}
//! Sets name of node to a zero-terminated string.
//! See also \ref ownership_of_strings and xml_node::name(const Ch *, std::size_t).
//! \param n Name of node to set. Must be zero terminated.
void name(const Ch *n)
{
name(n, internal::measure(n));
}
//! Sets value of node to a non zero-terminated string.
//! See \ref ownership_of_strings.
//! <br><br>
//! Note that node does not own its name or value, it only stores a pointer to it.
//! It will not delete or otherwise free the pointer on destruction.
//! It is reponsibility of the user to properly manage lifetime of the string.
//! The easiest way to achieve it is to use memory_pool of the document to allocate the string -
//! on destruction of the document the string will be automatically freed.
//! <br><br>
//! Size of value must be specified separately, because it does not have to be zero terminated.
//! Use value(const Ch *) function to have the length automatically calculated (string must be zero terminated).
//! <br><br>
//! If an element has a child node of type node_data, it will take precedence over element value when printing.
//! If you want to manipulate data of elements using values, use parser flag rapidxml::parse_no_data_nodes to prevent creation of data nodes by the parser.
//! \param val value of node to set. Does not have to be zero terminated.
//! \param size Size of value, in characters. This does not include zero terminator, if one is present.
void value(const Ch *val, std::size_t size)
{
m_value = const_cast<Ch *>(val);
m_value_size = size;
}
//! Sets value of node to a zero-terminated string.
//! See also \ref ownership_of_strings and xml_node::value(const Ch *, std::size_t).
//! \param val Vame of node to set. Must be zero terminated.
void value(const Ch *val)
{
this->value(val, internal::measure(val));
}
///////////////////////////////////////////////////////////////////////////
// Related nodes access
//! Gets node parent.
//! \return Pointer to parent node, or 0 if there is no parent.
xml_node<Ch> *parent() const
{
return m_parent;
}
protected:
// Return empty string
static Ch *nullstr()
{
static Ch zero = Ch('\0');
return &zero;
}
Ch *m_name; // Name of node, or 0 if no name
Ch *m_value; // Value of node, or 0 if no value
std::size_t m_name_size; // Length of node name, or undefined of no name
std::size_t m_value_size; // Length of node value, or undefined if no value
xml_node<Ch> *m_parent; // Pointer to parent node, or 0 if none
};
//! Class representing attribute node of XML document.
//! Each attribute has name and value strings, which are available through name() and value() functions (inherited from xml_base).
//! Note that after parse, both name and value of attribute will point to interior of source text used for parsing.
//! Thus, this text must persist in memory for the lifetime of attribute.
//! \param Ch Character type to use.
template<class Ch = char>
class xml_attribute: public xml_base<Ch>
{
friend class xml_node<Ch>;
public:
///////////////////////////////////////////////////////////////////////////
// Construction & destruction
//! Constructs an empty attribute with the specified type.
//! Consider using memory_pool of appropriate xml_document if allocating attributes manually.
xml_attribute()
{
}
///////////////////////////////////////////////////////////////////////////
// Related nodes access
//! Gets document of which attribute is a child.
//! \return Pointer to document that contains this attribute, or 0 if there is no parent document.
xml_document<Ch> *document() const
{
if (xml_node<Ch> *node = this->parent())
{
while (node->parent())
node = node->parent();
return node->type() == node_document ? static_cast<xml_document<Ch> *>(node) : 0;
}
else
return 0;
}
//! Gets previous attribute, optionally matching attribute name.
//! \param n Name of attribute to find, or 0 to return previous attribute regardless of its name; this string doesn't have to be zero-terminated if nsize is non-zero
//! \param nsize Size of name, in characters, or 0 to have size calculated automatically from string
//! \param case_sensitive Should name comparison be case-sensitive; non case-sensitive comparison works properly only for ASCII characters
//! \return Pointer to found attribute, or 0 if not found.
xml_attribute<Ch> *previous_attribute(const Ch *n = 0, std::size_t nsize = 0, bool case_sensitive = true) const
{
if (n)
{
if (nsize == 0)
nsize = internal::measure(n);
for (xml_attribute<Ch> *attribute = m_prev_attribute; attribute; attribute = attribute->m_prev_attribute)
if (internal::compare(attribute->name(), attribute->name_size(), n, nsize, case_sensitive))
return attribute;
return 0;
}
else
return this->m_parent ? m_prev_attribute : 0;
}
//! Gets next attribute, optionally matching attribute name.
//! \param n Name of attribute to find, or 0 to return next attribute regardless of its name; this string doesn't have to be zero-terminated if nsize is non-zero
//! \param nsize Size of name, in characters, or 0 to have size calculated automatically from string
//! \param case_sensitive Should name comparison be case-sensitive; non case-sensitive comparison works properly only for ASCII characters
//! \return Pointer to found attribute, or 0 if not found.
xml_attribute<Ch> *next_attribute(const Ch *n = 0, std::size_t nsize = 0, bool case_sensitive = true) const
{
if (n)
{
if (nsize == 0)
nsize = internal::measure(n);
for (xml_attribute<Ch> *attribute = m_next_attribute; attribute; attribute = attribute->m_next_attribute)
if (internal::compare(attribute->name(), attribute->name_size(), n, nsize, case_sensitive))
return attribute;
return 0;
}
else
return this->m_parent ? m_next_attribute : 0;
}
private:
xml_attribute<Ch> *m_prev_attribute; // Pointer to previous sibling of attribute, or 0 if none; only valid if parent is non-zero
xml_attribute<Ch> *m_next_attribute; // Pointer to next sibling of attribute, or 0 if none; only valid if parent is non-zero
};
///////////////////////////////////////////////////////////////////////////
// XML node
//! Class representing a node of XML document.
//! Each node may have associated name and value strings, which are available through name() and value() functions.
//! Interpretation of name and value depends on type of the node.
//! Type of node can be determined by using type() function.
//! <br><br>
//! Note that after parse, both name and value of node, if any, will point interior of source text used for parsing.
//! Thus, this text must persist in the memory for the lifetime of node.
//! \param Ch Character type to use.
template<class Ch = char>
class xml_node: public xml_base<Ch>
{
public:
///////////////////////////////////////////////////////////////////////////
// Construction & destruction
//! Constructs an empty node with the specified type.
//! Consider using memory_pool of appropriate document to allocate nodes manually.
//! \param t Type of node to construct.
xml_node(node_type t)
: m_type(t)
, m_first_node(0)
, m_first_attribute(0)
{
}
///////////////////////////////////////////////////////////////////////////
// Node data access
//! Gets type of node.
//! \return Type of node.
node_type type() const
{
return m_type;
}
///////////////////////////////////////////////////////////////////////////
// Related nodes access
//! Gets document of which node is a child.
//! \return Pointer to document that contains this node, or 0 if there is no parent document.
xml_document<Ch> *document() const
{
xml_node<Ch> *node = const_cast<xml_node<Ch> *>(this);
while (node->parent())
node = node->parent();
return node->type() == node_document ? static_cast<xml_document<Ch> *>(node) : 0;
}
//! Gets first child node, optionally matching node name.
//! \param n Name of child to find, or 0 to return first child regardless of its name; this string doesn't have to be zero-terminated if nsize is non-zero
//! \param nsize Size of name, in characters, or 0 to have size calculated automatically from string
//! \param case_sensitive Should name comparison be case-sensitive; non case-sensitive comparison works properly only for ASCII characters
//! \return Pointer to found child, or 0 if not found.
xml_node<Ch> *first_node(const Ch *n = 0, std::size_t nsize = 0, bool case_sensitive = true) const
{
if (n)
{
if (nsize == 0)
nsize = internal::measure(n);
for (xml_node<Ch> *child = m_first_node; child; child = child->next_sibling())
if (internal::compare(child->name(), child->name_size(), n, nsize, case_sensitive))
return child;
return 0;
}
else
return m_first_node;
}
//! Gets last child node, optionally matching node name.
//! Behaviour is undefined if node has no children.
//! Use first_node() to test if node has children.
//! \param n Name of child to find, or 0 to return last child regardless of its name; this string doesn't have to be zero-terminated if nsize is non-zero
//! \param nsize Size of name, in characters, or 0 to have size calculated automatically from string
//! \param case_sensitive Should name comparison be case-sensitive; non case-sensitive comparison works properly only for ASCII characters
//! \return Pointer to found child, or 0 if not found.
xml_node<Ch> *last_node(const Ch *n = 0, std::size_t nsize = 0, bool case_sensitive = true) const
{
assert(m_first_node); // Cannot query for last child if node has no children
if (n)
{
if (nsize == 0)
nsize = internal::measure(n);
for (xml_node<Ch> *child = m_last_node; child; child = child->previous_sibling())
if (internal::compare(child->name(), child->name_size(), n, nsize, case_sensitive))
return child;
return 0;
}
else
return m_last_node;
}
//! Gets previous sibling node, optionally matching node name.
//! Behaviour is undefined if node has no parent.
//! Use parent() to test if node has a parent.
//! \param n Name of sibling to find, or 0 to return previous sibling regardless of its name; this string doesn't have to be zero-terminated if nsize is non-zero
//! \param nsize Size of name, in characters, or 0 to have size calculated automatically from string
//! \param case_sensitive Should name comparison be case-sensitive; non case-sensitive comparison works properly only for ASCII characters
//! \return Pointer to found sibling, or 0 if not found.
xml_node<Ch> *previous_sibling(const Ch *n = 0, std::size_t nsize = 0, bool case_sensitive = true) const
{
assert(this->m_parent); // Cannot query for siblings if node has no parent
if (n)
{
if (nsize == 0)
nsize = internal::measure(n);
for (xml_node<Ch> *sibling = m_prev_sibling; sibling; sibling = sibling->m_prev_sibling)
if (internal::compare(sibling->name(), sibling->name_size(), n, nsize, case_sensitive))
return sibling;
return 0;
}
else
return m_prev_sibling;
}
//! Gets next sibling node, optionally matching node name.
//! Behaviour is undefined if node has no parent.
//! Use parent() to test if node has a parent.
//! \param n Name of sibling to find, or 0 to return next sibling regardless of its name; this string doesn't have to be zero-terminated if nsize is non-zero
//! \param nsize Size of name, in characters, or 0 to have size calculated automatically from string
//! \param case_sensitive Should name comparison be case-sensitive; non case-sensitive comparison works properly only for ASCII characters
//! \return Pointer to found sibling, or 0 if not found.
xml_node<Ch> *next_sibling(const Ch *n = 0, std::size_t nsize = 0, bool case_sensitive = true) const
{
assert(this->m_parent); // Cannot query for siblings if node has no parent
if (n)
{
if (nsize == 0)
nsize = internal::measure(n);
for (xml_node<Ch> *sibling = m_next_sibling; sibling; sibling = sibling->m_next_sibling)
if (internal::compare(sibling->name(), sibling->name_size(), n, nsize, case_sensitive))
return sibling;
return 0;
}
else
return m_next_sibling;
}
//! Gets first attribute of node, optionally matching attribute name.
//! \param n Name of attribute to find, or 0 to return first attribute regardless of its name; this string doesn't have to be zero-terminated if nsize is non-zero
//! \param nsize Size of name, in characters, or 0 to have size calculated automatically from string
//! \param case_sensitive Should name comparison be case-sensitive; non case-sensitive comparison works properly only for ASCII characters
//! \return Pointer to found attribute, or 0 if not found.
xml_attribute<Ch> *first_attribute(const Ch *n = 0, std::size_t nsize = 0, bool case_sensitive = true) const
{
if (n)
{
if (nsize == 0)
nsize = internal::measure(n);
for (xml_attribute<Ch> *attribute = m_first_attribute; attribute; attribute = attribute->m_next_attribute)
if (internal::compare(attribute->name(), attribute->name_size(), n, nsize, case_sensitive))
return attribute;
return 0;
}
else
return m_first_attribute;
}
//! Gets last attribute of node, optionally matching attribute name.
//! \param n Name of attribute to find, or 0 to return last attribute regardless of its name; this string doesn't have to be zero-terminated if nsize is non-zero
//! \param nsize Size of name, in characters, or 0 to have size calculated automatically from string
//! \param case_sensitive Should name comparison be case-sensitive; non case-sensitive comparison works properly only for ASCII characters
//! \return Pointer to found attribute, or 0 if not found.
xml_attribute<Ch> *last_attribute(const Ch *n = 0, std::size_t nsize = 0, bool case_sensitive = true) const
{
if (n)
{
if (nsize == 0)
nsize = internal::measure(n);
for (xml_attribute<Ch> *attribute = m_last_attribute; attribute; attribute = attribute->m_prev_attribute)
if (internal::compare(attribute->name(), attribute->name_size(), n, nsize, case_sensitive))
return attribute;
return 0;
}
else
return m_first_attribute ? m_last_attribute : 0;
}
///////////////////////////////////////////////////////////////////////////
// Node modification
//! Sets type of node.
//! \param t Type of node to set.
void type(node_type t)
{
m_type = t;
}
///////////////////////////////////////////////////////////////////////////
// Node manipulation
//! Prepends a new child node.
//! The prepended child becomes the first child, and all existing children are moved one position back.
//! \param child Node to prepend.
void prepend_node(xml_node<Ch> *child)
{
assert(child && !child->parent() && child->type() != node_document);
if (first_node())
{
child->m_next_sibling = m_first_node;
m_first_node->m_prev_sibling = child;
}
else
{
child->m_next_sibling = 0;
m_last_node = child;
}
m_first_node = child;
child->m_parent = this;
child->m_prev_sibling = 0;
}
//! Appends a new child node.
//! The appended child becomes the last child.
//! \param child Node to append.
void append_node(xml_node<Ch> *child)
{
assert(child && !child->parent() && child->type() != node_document);
if (first_node())
{
child->m_prev_sibling = m_last_node;
m_last_node->m_next_sibling = child;
}
else
{
child->m_prev_sibling = 0;
m_first_node = child;
}
m_last_node = child;
child->m_parent = this;
child->m_next_sibling = 0;
}
//! Inserts a new child node at specified place inside the node.
//! All children after and including the specified node are moved one position back.
//! \param where Place where to insert the child, or 0 to insert at the back.
//! \param child Node to insert.
void insert_node(xml_node<Ch> *where, xml_node<Ch> *child)
{
assert(!where || where->parent() == this);
assert(child && !child->parent() && child->type() != node_document);
if (where == m_first_node)
prepend_node(child);
else if (where == 0)
append_node(child);
else
{
child->m_prev_sibling = where->m_prev_sibling;
child->m_next_sibling = where;
where->m_prev_sibling->m_next_sibling = child;
where->m_prev_sibling = child;
child->m_parent = this;
}
}
//! Removes first child node.
//! If node has no children, behaviour is undefined.
//! Use first_node() to test if node has children.
void remove_first_node()
{
assert(first_node());
xml_node<Ch> *child = m_first_node;
m_first_node = child->m_next_sibling;
if (child->m_next_sibling)
child->m_next_sibling->m_prev_sibling = 0;
else
m_last_node = 0;
child->m_parent = 0;
}
//! Removes last child of the node.
//! If node has no children, behaviour is undefined.
//! Use first_node() to test if node has children.
void remove_last_node()
{
assert(first_node());
xml_node<Ch> *child = m_last_node;
if (child->m_prev_sibling)
{
m_last_node = child->m_prev_sibling;
child->m_prev_sibling->m_next_sibling = 0;
}
else
m_first_node = 0;
child->m_parent = 0;
}
//! Removes specified child from the node
// \param where Pointer to child to be removed.
void remove_node(xml_node<Ch> *where)
{
assert(where && where->parent() == this);
assert(first_node());
if (where == m_first_node)
remove_first_node();
else if (where == m_last_node)
remove_last_node();
else
{
where->m_prev_sibling->m_next_sibling = where->m_next_sibling;
where->m_next_sibling->m_prev_sibling = where->m_prev_sibling;
where->m_parent = 0;
}
}
//! Removes all child nodes (but not attributes).
void remove_all_nodes()
{
for (xml_node<Ch> *node = first_node(); node; node = node->m_next_sibling)
node->m_parent = 0;
m_first_node = 0;
}
//! Prepends a new attribute to the node.
//! \param attribute Attribute to prepend.
void prepend_attribute(xml_attribute<Ch> *attribute)
{
assert(attribute && !attribute->parent());
if (first_attribute())
{
attribute->m_next_attribute = m_first_attribute;
m_first_attribute->m_prev_attribute = attribute;
}
else
{
attribute->m_next_attribute = 0;
m_last_attribute = attribute;
}
m_first_attribute = attribute;
attribute->m_parent = this;
attribute->m_prev_attribute = 0;
}
//! Appends a new attribute to the node.
//! \param attribute Attribute to append.
void append_attribute(xml_attribute<Ch> *attribute)
{
assert(attribute && !attribute->parent());
if (first_attribute())
{
attribute->m_prev_attribute = m_last_attribute;
m_last_attribute->m_next_attribute = attribute;
}
else
{
attribute->m_prev_attribute = 0;
m_first_attribute = attribute;
}
m_last_attribute = attribute;
attribute->m_parent = this;
attribute->m_next_attribute = 0;
}
//! Inserts a new attribute at specified place inside the node.
//! All attributes after and including the specified attribute are moved one position back.
//! \param where Place where to insert the attribute, or 0 to insert at the back.
//! \param attribute Attribute to insert.
void insert_attribute(xml_attribute<Ch> *where, xml_attribute<Ch> *attribute)
{
assert(!where || where->parent() == this);
assert(attribute && !attribute->parent());
if (where == m_first_attribute)
prepend_attribute(attribute);
else if (where == 0)
append_attribute(attribute);
else
{
attribute->m_prev_attribute = where->m_prev_attribute;
attribute->m_next_attribute = where;
where->m_prev_attribute->m_next_attribute = attribute;
where->m_prev_attribute = attribute;
attribute->m_parent = this;
}
}
//! Removes first attribute of the node.
//! If node has no attributes, behaviour is undefined.
//! Use first_attribute() to test if node has attributes.
void remove_first_attribute()
{
assert(first_attribute());
xml_attribute<Ch> *attribute = m_first_attribute;
if (attribute->m_next_attribute)
{
attribute->m_next_attribute->m_prev_attribute = 0;
}
else
m_last_attribute = 0;
attribute->m_parent = 0;
m_first_attribute = attribute->m_next_attribute;
}
//! Removes last attribute of the node.
//! If node has no attributes, behaviour is undefined.
//! Use first_attribute() to test if node has attributes.
void remove_last_attribute()
{
assert(first_attribute());
xml_attribute<Ch> *attribute = m_last_attribute;
if (attribute->m_prev_attribute)
{
attribute->m_prev_attribute->m_next_attribute = 0;
m_last_attribute = attribute->m_prev_attribute;
}
else
m_first_attribute = 0;
attribute->m_parent = 0;
}
//! Removes specified attribute from node.
//! \param where Pointer to attribute to be removed.
void remove_attribute(xml_attribute<Ch> *where)
{
assert(first_attribute() && where->parent() == this);
if (where == m_first_attribute)
remove_first_attribute();
else if (where == m_last_attribute)
remove_last_attribute();
else
{
where->m_prev_attribute->m_next_attribute = where->m_next_attribute;
where->m_next_attribute->m_prev_attribute = where->m_prev_attribute;
where->m_parent = 0;
}
}
//! Removes all attributes of node.
void remove_all_attributes()
{
for (xml_attribute<Ch> *attribute = first_attribute(); attribute; attribute = attribute->m_next_attribute)
attribute->m_parent = 0;
m_first_attribute = 0;
}
private:
///////////////////////////////////////////////////////////////////////////
// Restrictions
// No copying
xml_node(const xml_node &);
void operator =(const xml_node &);
///////////////////////////////////////////////////////////////////////////
// Data members
// Note that some of the pointers below have UNDEFINED values if certain other pointers are 0.
// This is required for maximum performance, as it allows the parser to omit initialization of
// unneded/redundant values.
//
// The rules are as follows:
// 1. first_node and first_attribute contain valid pointers, or 0 if node has no children/attributes respectively
// 2. last_node and last_attribute are valid only if node has at least one child/attribute respectively, otherwise they contain garbage
// 3. prev_sibling and next_sibling are valid only if node has a parent, otherwise they contain garbage
node_type m_type; // Type of node; always valid
xml_node<Ch> *m_first_node; // Pointer to first child node, or 0 if none; always valid
xml_node<Ch> *m_last_node; // Pointer to last child node, or 0 if none; this value is only valid if m_first_node is non-zero
xml_attribute<Ch> *m_first_attribute; // Pointer to first attribute of node, or 0 if none; always valid
xml_attribute<Ch> *m_last_attribute; // Pointer to last attribute of node, or 0 if none; this value is only valid if m_first_attribute is non-zero
xml_node<Ch> *m_prev_sibling; // Pointer to previous sibling of node, or 0 if none; this value is only valid if m_parent is non-zero
xml_node<Ch> *m_next_sibling; // Pointer to next sibling of node, or 0 if none; this value is only valid if m_parent is non-zero
};
///////////////////////////////////////////////////////////////////////////
// XML document
//! This class represents root of the DOM hierarchy.
//! It is also an xml_node and a memory_pool through public inheritance.
//! Use parse() function to build a DOM tree from a zero-terminated XML text string.
//! parse() function allocates memory for nodes and attributes by using functions of xml_document,
//! which are inherited from memory_pool.
//! To access root node of the document, use the document itself, as if it was an xml_node.
//! \param Ch Character type to use.
template<class Ch = char>
class xml_document: public xml_node<Ch>, public memory_pool<Ch>
{
public:
//! Constructs empty XML document
xml_document()
: xml_node<Ch>(node_document)
{
}
//! Parses zero-terminated XML string according to given flags.
//! Passed string will be modified by the parser, unless rapidxml::parse_non_destructive flag is used.
//! The string must persist for the lifetime of the document.
//! In case of error, rapidxml::parse_error exception will be thrown.
//! <br><br>
//! If you want to parse contents of a file, you must first load the file into the memory, and pass pointer to its beginning.
//! Make sure that data is zero-terminated.
//! <br><br>
//! Document can be parsed into multiple times.
//! Each new call to parse removes previous nodes and attributes (if any), but does not clear memory pool.
//! \param text XML data to parse; pointer is non-const to denote fact that this data may be modified by the parser.
template<int Flags>
void parse(Ch *text)
{
assert(text);
// Remove current contents
this->remove_all_nodes();
this->remove_all_attributes();
// Parse BOM, if any
parse_bom<Flags>(text);
// Parse children
while (1)
{
// Skip whitespace before node
skip<whitespace_pred, Flags>(text);
if (*text == 0)
break;
// Parse and append new child
if (*text == Ch('<'))
{
++text; // Skip '<'
if (xml_node<Ch> *node = parse_node<Flags>(text))
this->append_node(node);
}
else
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("expected <", text);
}
}
//! Clears the document by deleting all nodes and clearing the memory pool.
//! All nodes owned by document pool are destroyed.
void clear()
{
this->remove_all_nodes();
this->remove_all_attributes();
memory_pool<Ch>::clear();
}
private:
///////////////////////////////////////////////////////////////////////
// Internal character utility functions
// Detect whitespace character
struct whitespace_pred
{
static unsigned char test(Ch ch)
{
return internal::lookup_tables<0>::lookup_whitespace[internal::get_index(ch)];
}
};
// Detect node name character
struct node_name_pred
{
static unsigned char test(Ch ch)
{
return internal::lookup_tables<0>::lookup_node_name[internal::get_index(ch)];
}
};
// Detect attribute name character
struct attribute_name_pred
{
static unsigned char test(Ch ch)
{
return internal::lookup_tables<0>::lookup_attribute_name[internal::get_index(ch)];
}
};
// Detect text character (PCDATA)
struct text_pred
{
static unsigned char test(Ch ch)
{
return internal::lookup_tables<0>::lookup_text[internal::get_index(ch)];
}
};
// Detect text character (PCDATA) that does not require processing
struct text_pure_no_ws_pred
{
static unsigned char test(Ch ch)
{
return internal::lookup_tables<0>::lookup_text_pure_no_ws[internal::get_index(ch)];
}
};
// Detect text character (PCDATA) that does not require processing
struct text_pure_with_ws_pred
{
static unsigned char test(Ch ch)
{
return internal::lookup_tables<0>::lookup_text_pure_with_ws[internal::get_index(ch)];
}
};
// Detect attribute value character
template<Ch Quote>
struct attribute_value_pred
{
static unsigned char test(Ch ch)
{
if (Quote == Ch('\''))
return internal::lookup_tables<0>::lookup_attribute_data_1[internal::get_index(ch)];
if (Quote == Ch('\"'))
return internal::lookup_tables<0>::lookup_attribute_data_2[internal::get_index(ch)];
return 0; // Should never be executed, to avoid warnings on Comeau
}
};
// Detect attribute value character
template<Ch Quote>
struct attribute_value_pure_pred
{
static unsigned char test(Ch ch)
{
if (Quote == Ch('\''))
return internal::lookup_tables<0>::lookup_attribute_data_1_pure[internal::get_index(ch)];
if (Quote == Ch('\"'))
return internal::lookup_tables<0>::lookup_attribute_data_2_pure[internal::get_index(ch)];
return 0; // Should never be executed, to avoid warnings on Comeau
}
};
// Insert coded character, using UTF8 or 8-bit ASCII
template<int Flags>
static void insert_coded_character(Ch *&text, unsigned long code)
{
if (Flags & parse_no_utf8)
{
// Insert 8-bit ASCII character
// Todo: possibly verify that code is less than 256 and use replacement char otherwise?
text[0] = static_cast<unsigned char>(code);
text += 1;
}
else
{
// Insert UTF8 sequence
if (code < 0x80) // 1 byte sequence
{
text[0] = static_cast<unsigned char>(code);
text += 1;
}
else if (code < 0x800) // 2 byte sequence
{
text[1] = static_cast<unsigned char>((code | 0x80) & 0xBF); code >>= 6;
text[0] = static_cast<unsigned char>(code | 0xC0);
text += 2;
}
else if (code < 0x10000) // 3 byte sequence
{
text[2] = static_cast<unsigned char>((code | 0x80) & 0xBF); code >>= 6;
text[1] = static_cast<unsigned char>((code | 0x80) & 0xBF); code >>= 6;
text[0] = static_cast<unsigned char>(code | 0xE0);
text += 3;
}
else if (code < 0x110000) // 4 byte sequence
{
text[3] = static_cast<unsigned char>((code | 0x80) & 0xBF); code >>= 6;
text[2] = static_cast<unsigned char>((code | 0x80) & 0xBF); code >>= 6;
text[1] = static_cast<unsigned char>((code | 0x80) & 0xBF); code >>= 6;
text[0] = static_cast<unsigned char>(code | 0xF0);
text += 4;
}
else // Invalid, only codes up to 0x10FFFF are allowed in Unicode
{
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("invalid numeric character entity", text);
}
}
}
// Skip characters until predicate evaluates to true
template<class StopPred, int Flags>
static void skip(Ch *&text)
{
Ch *tmp = text;
while (StopPred::test(*tmp))
++tmp;
text = tmp;
}
// Skip characters until predicate evaluates to true while doing the following:
// - replacing XML character entity references with proper characters (' & " < > &#...;)
// - condensing whitespace sequences to single space character
template<class StopPred, class StopPredPure, int Flags>
static Ch *skip_and_expand_character_refs(Ch *&text)
{
// If entity translation, whitespace condense and whitespace trimming is disabled, use plain skip
if (Flags & parse_no_entity_translation &&
!(Flags & parse_normalize_whitespace) &&
!(Flags & parse_trim_whitespace))
{
skip<StopPred, Flags>(text);
return text;
}
// Use simple skip until first modification is detected
skip<StopPredPure, Flags>(text);
// Use translation skip
Ch *src = text;
Ch *dest = src;
while (StopPred::test(*src))
{
// If entity translation is enabled
if (!(Flags & parse_no_entity_translation))
{
// Test if replacement is needed
if (src[0] == Ch('&'))
{
switch (src[1])
{
// & '
case Ch('a'):
if (src[2] == Ch('m') && src[3] == Ch('p') && src[4] == Ch(';'))
{
*dest = Ch('&');
++dest;
src += 5;
continue;
}
if (src[2] == Ch('p') && src[3] == Ch('o') && src[4] == Ch('s') && src[5] == Ch(';'))
{
*dest = Ch('\'');
++dest;
src += 6;
continue;
}
break;
// "
case Ch('q'):
if (src[2] == Ch('u') && src[3] == Ch('o') && src[4] == Ch('t') && src[5] == Ch(';'))
{
*dest = Ch('"');
++dest;
src += 6;
continue;
}
break;
// >
case Ch('g'):
if (src[2] == Ch('t') && src[3] == Ch(';'))
{
*dest = Ch('>');
++dest;
src += 4;
continue;
}
break;
// <
case Ch('l'):
if (src[2] == Ch('t') && src[3] == Ch(';'))
{
*dest = Ch('<');
++dest;
src += 4;
continue;
}
break;
// &#...; - assumes ASCII
case Ch('#'):
if (src[2] == Ch('x'))
{
unsigned long code = 0;
src += 3; // Skip &#x
while (1)
{
unsigned char digit = internal::lookup_tables<0>::lookup_digits[static_cast<unsigned char>(*src)];
if (digit == 0xFF)
break;
code = code * 16 + digit;
++src;
}
insert_coded_character<Flags>(dest, code); // Put character in output
}
else
{
unsigned long code = 0;
src += 2; // Skip &#
while (1)
{
unsigned char digit = internal::lookup_tables<0>::lookup_digits[static_cast<unsigned char>(*src)];
if (digit == 0xFF)
break;
code = code * 10 + digit;
++src;
}
insert_coded_character<Flags>(dest, code); // Put character in output
}
if (*src == Ch(';'))
++src;
else
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("expected ;", src);
continue;
// Something else
default:
// Ignore, just copy '&' verbatim
break;
}
}
}
// If whitespace condensing is enabled
if (Flags & parse_normalize_whitespace)
{
// Test if condensing is needed
if (whitespace_pred::test(*src))
{
*dest = Ch(' '); ++dest; // Put single space in dest
++src; // Skip first whitespace char
// Skip remaining whitespace chars
while (whitespace_pred::test(*src))
++src;
continue;
}
}
// No replacement, only copy character
*dest++ = *src++;
}
// Return new end
text = src;
return dest;
}
///////////////////////////////////////////////////////////////////////
// Internal parsing functions
// Parse BOM, if any
template<int Flags>
void parse_bom(Ch *&text)
{
// UTF-8?
if (static_cast<unsigned char>(text[0]) == 0xEF &&
static_cast<unsigned char>(text[1]) == 0xBB &&
static_cast<unsigned char>(text[2]) == 0xBF)
{
text += 3; // Skip utf-8 bom
}
}
// Parse XML declaration (<?xml...)
template<int Flags>
xml_node<Ch> *parse_xml_declaration(Ch *&text)
{
// If parsing of declaration is disabled
if (!(Flags & parse_declaration_node))
{
// Skip until end of declaration
while (text[0] != Ch('?') || text[1] != Ch('>'))
{
if (!text[0])
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("unexpected end of data", text);
++text;
}
text += 2; // Skip '?>'
return 0;
}
// Create declaration
xml_node<Ch> *declaration = this->allocate_node(node_declaration);
// Skip whitespace before attributes or ?>
skip<whitespace_pred, Flags>(text);
// Parse declaration attributes
parse_node_attributes<Flags>(text, declaration);
// Skip ?>
if (text[0] != Ch('?') || text[1] != Ch('>'))
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("expected ?>", text);
text += 2;
return declaration;
}
// Parse XML comment (<!--...)
template<int Flags>
xml_node<Ch> *parse_comment(Ch *&text)
{
// If parsing of comments is disabled
if (!(Flags & parse_comment_nodes))
{
// Skip until end of comment
while (text[0] != Ch('-') || text[1] != Ch('-') || text[2] != Ch('>'))
{
if (!text[0])
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("unexpected end of data", text);
++text;
}
text += 3; // Skip '-->'
return 0; // Do not produce comment node
}
// Remember value start
Ch *val = text;
// Skip until end of comment
while (text[0] != Ch('-') || text[1] != Ch('-') || text[2] != Ch('>'))
{
if (!text[0])
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("unexpected end of data", text);
++text;
}
// Create comment node
xml_node<Ch> *comment = this->allocate_node(node_comment);
comment->value(val, text - val);
// Place zero terminator after comment value
if (!(Flags & parse_no_string_terminators))
*text = Ch('\0');
text += 3; // Skip '-->'
return comment;
}
// Parse DOCTYPE
template<int Flags>
xml_node<Ch> *parse_doctype(Ch *&text)
{
// Remember value start
Ch *val = text;
// Skip to >
while (*text != Ch('>'))
{
// Determine character type
switch (*text)
{
// If '[' encountered, scan for matching ending ']' using naive algorithm with depth
// This works for all W3C test files except for 2 most wicked
case Ch('['):
{
++text; // Skip '['
int depth = 1;
while (depth > 0)
{
switch (*text)
{
case Ch('['): ++depth; break;
case Ch(']'): --depth; break;
case 0: BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("unexpected end of data", text);
default: break;
}
++text;
}
break;
}
// Error on end of text
case Ch('\0'):
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("unexpected end of data", text);
// Other character, skip it
default:
++text;
}
}
// If DOCTYPE nodes enabled
if (Flags & parse_doctype_node)
{
// Create a new doctype node
xml_node<Ch> *doctype = this->allocate_node(node_doctype);
doctype->value(val, text - val);
// Place zero terminator after value
if (!(Flags & parse_no_string_terminators))
*text = Ch('\0');
text += 1; // skip '>'
return doctype;
}
else
{
text += 1; // skip '>'
return 0;
}
}
// Parse PI
template<int Flags>
xml_node<Ch> *parse_pi(Ch *&text)
{
// If creation of PI nodes is enabled
if (Flags & parse_pi_nodes)
{
// Create pi node
xml_node<Ch> *pi = this->allocate_node(node_pi);
// Extract PI target name
Ch *n = text;
skip<node_name_pred, Flags>(text);
if (text == n)
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("expected PI target", text);
pi->name(n, text - n);
// Skip whitespace between pi target and pi
skip<whitespace_pred, Flags>(text);
// Remember start of pi
Ch *val = text;
// Skip to '?>'
while (text[0] != Ch('?') || text[1] != Ch('>'))
{
if (*text == Ch('\0'))
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("unexpected end of data", text);
++text;
}
// Set pi value (verbatim, no entity expansion or whitespace normalization)
pi->value(val, text - val);
// Place zero terminator after name and value
if (!(Flags & parse_no_string_terminators))
{
pi->name()[pi->name_size()] = Ch('\0');
pi->value()[pi->value_size()] = Ch('\0');
}
text += 2; // Skip '?>'
return pi;
}
else
{
// Skip to '?>'
while (text[0] != Ch('?') || text[1] != Ch('>'))
{
if (*text == Ch('\0'))
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("unexpected end of data", text);
++text;
}
text += 2; // Skip '?>'
return 0;
}
}
// Parse and append data
// Return character that ends data.
// This is necessary because this character might have been overwritten by a terminating 0
template<int Flags>
Ch parse_and_append_data(xml_node<Ch> *node, Ch *&text, Ch *contents_start)
{
// Backup to contents start if whitespace trimming is disabled
if (!(Flags & parse_trim_whitespace))
text = contents_start;
// Skip until end of data
Ch *val = text, *end;
if (Flags & parse_normalize_whitespace)
end = skip_and_expand_character_refs<text_pred, text_pure_with_ws_pred, Flags>(text);
else
end = skip_and_expand_character_refs<text_pred, text_pure_no_ws_pred, Flags>(text);
// Trim trailing whitespace if flag is set; leading was already trimmed by whitespace skip after >
if (Flags & parse_trim_whitespace)
{
if (Flags & parse_normalize_whitespace)
{
// Whitespace is already condensed to single space characters by skipping function, so just trim 1 char off the end
if (*(end - 1) == Ch(' '))
--end;
}
else
{
// Backup until non-whitespace character is found
while (whitespace_pred::test(*(end - 1)))
--end;
}
}
// If characters are still left between end and value (this test is only necessary if normalization is enabled)
// Create new data node
if (!(Flags & parse_no_data_nodes))
{
xml_node<Ch> *data = this->allocate_node(node_data);
data->value(val, end - val);
node->append_node(data);
}
// Add data to parent node if no data exists yet
if (!(Flags & parse_no_element_values))
if (*node->value() == Ch('\0'))
node->value(val, end - val);
// Place zero terminator after value
if (!(Flags & parse_no_string_terminators))
{
Ch ch = *text;
*end = Ch('\0');
return ch; // Return character that ends data; this is required because zero terminator overwritten it
}
// Return character that ends data
return *text;
}
// Parse CDATA
template<int Flags>
xml_node<Ch> *parse_cdata(Ch *&text)
{
// If CDATA is disabled
if (Flags & parse_no_data_nodes)
{
// Skip until end of cdata
while (text[0] != Ch(']') || text[1] != Ch(']') || text[2] != Ch('>'))
{
if (!text[0])
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("unexpected end of data", text);
++text;
}
text += 3; // Skip ]]>
return 0; // Do not produce CDATA node
}
// Skip until end of cdata
Ch *val = text;
while (text[0] != Ch(']') || text[1] != Ch(']') || text[2] != Ch('>'))
{
if (!text[0])
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("unexpected end of data", text);
++text;
}
// Create new cdata node
xml_node<Ch> *cdata = this->allocate_node(node_cdata);
cdata->value(val, text - val);
// Place zero terminator after value
if (!(Flags & parse_no_string_terminators))
*text = Ch('\0');
text += 3; // Skip ]]>
return cdata;
}
// Parse element node
template<int Flags>
xml_node<Ch> *parse_element(Ch *&text)
{
// Create element node
xml_node<Ch> *element = this->allocate_node(node_element);
// Extract element name
Ch *n = text;
skip<node_name_pred, Flags>(text);
if (text == n)
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("expected element name", text);
element->name(n, text - n);
// Skip whitespace between element name and attributes or >
skip<whitespace_pred, Flags>(text);
// Parse attributes, if any
parse_node_attributes<Flags>(text, element);
// Determine ending type
if (*text == Ch('>'))
{
++text;
parse_node_contents<Flags>(text, element);
}
else if (*text == Ch('/'))
{
++text;
if (*text != Ch('>'))
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("expected >", text);
++text;
}
else
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("expected >", text);
// Place zero terminator after name
if (!(Flags & parse_no_string_terminators))
element->name()[element->name_size()] = Ch('\0');
// Return parsed element
return element;
}
// Determine node type, and parse it
template<int Flags>
xml_node<Ch> *parse_node(Ch *&text)
{
// Parse proper node type
switch (text[0])
{
// <...
default:
// Parse and append element node
return parse_element<Flags>(text);
// <?...
case Ch('?'):
++text; // Skip ?
if ((text[0] == Ch('x') || text[0] == Ch('X')) &&
(text[1] == Ch('m') || text[1] == Ch('M')) &&
(text[2] == Ch('l') || text[2] == Ch('L')) &&
whitespace_pred::test(text[3]))
{
// '<?xml ' - xml declaration
text += 4; // Skip 'xml '
return parse_xml_declaration<Flags>(text);
}
else
{
// Parse PI
return parse_pi<Flags>(text);
}
// <!...
case Ch('!'):
// Parse proper subset of <! node
switch (text[1])
{
// <!-
case Ch('-'):
if (text[2] == Ch('-'))
{
// '<!--' - xml comment
text += 3; // Skip '!--'
return parse_comment<Flags>(text);
}
break;
// <![
case Ch('['):
if (text[2] == Ch('C') && text[3] == Ch('D') && text[4] == Ch('A') &&
text[5] == Ch('T') && text[6] == Ch('A') && text[7] == Ch('['))
{
// '<![CDATA[' - cdata
text += 8; // Skip '![CDATA['
return parse_cdata<Flags>(text);
}
break;
// <!D
case Ch('D'):
if (text[2] == Ch('O') && text[3] == Ch('C') && text[4] == Ch('T') &&
text[5] == Ch('Y') && text[6] == Ch('P') && text[7] == Ch('E') &&
whitespace_pred::test(text[8]))
{
// '<!DOCTYPE ' - doctype
text += 9; // skip '!DOCTYPE '
return parse_doctype<Flags>(text);
}
break;
default: break;
} // switch
// Attempt to skip other, unrecognized node types starting with <!
++text; // Skip !
while (*text != Ch('>'))
{
if (*text == 0)
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("unexpected end of data", text);
++text;
}
++text; // Skip '>'
return 0; // No node recognized
}
}
// Parse contents of the node - children, data etc.
template<int Flags>
void parse_node_contents(Ch *&text, xml_node<Ch> *node)
{
// For all children and text
while (1)
{
// Skip whitespace between > and node contents
Ch *contents_start = text; // Store start of node contents before whitespace is skipped
if (Flags & parse_trim_whitespace)
skip<whitespace_pred, Flags>(text);
Ch next_char = *text;
// After data nodes, instead of continuing the loop, control jumps here.
// This is because zero termination inside parse_and_append_data() function
// would wreak havoc with the above code.
// Also, skipping whitespace after data nodes is unnecessary.
after_data_node:
// Determine what comes next: node closing, child node, data node, or 0?
switch (next_char)
{
// Node closing or child node
case Ch('<'):
if (text[1] == Ch('/'))
{
// Node closing
text += 2; // Skip '</'
if (Flags & parse_validate_closing_tags)
{
// Skip and validate closing tag name
Ch *closing_name = text;
skip<node_name_pred, Flags>(text);
if (!internal::compare(node->name(), node->name_size(), closing_name, text - closing_name, true))
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("invalid closing tag name", text);
}
else
{
// No validation, just skip name
skip<node_name_pred, Flags>(text);
}
// Skip remaining whitespace after node name
skip<whitespace_pred, Flags>(text);
if (*text != Ch('>'))
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("expected >", text);
++text; // Skip '>'
return; // Node closed, finished parsing contents
}
else
{
// Child node
++text; // Skip '<'
if (xml_node<Ch> *child = parse_node<Flags>(text))
node->append_node(child);
}
break;
// End of data - error
case Ch('\0'):
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("unexpected end of data", text);
// Data node
default:
next_char = parse_and_append_data<Flags>(node, text, contents_start);
goto after_data_node; // Bypass regular processing after data nodes
}
}
}
// Parse XML attributes of the node
template<int Flags>
void parse_node_attributes(Ch *&text, xml_node<Ch> *node)
{
// For all attributes
while (attribute_name_pred::test(*text))
{
// Extract attribute name
Ch *n = text;
++text; // Skip first character of attribute name
skip<attribute_name_pred, Flags>(text);
if (text == n)
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("expected attribute name", n);
// Create new attribute
xml_attribute<Ch> *attribute = this->allocate_attribute();
attribute->name(n, text - n);
node->append_attribute(attribute);
// Skip whitespace after attribute name
skip<whitespace_pred, Flags>(text);
// Skip =
if (*text != Ch('='))
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("expected =", text);
++text;
// Add terminating zero after name
if (!(Flags & parse_no_string_terminators))
attribute->name()[attribute->name_size()] = 0;
// Skip whitespace after =
skip<whitespace_pred, Flags>(text);
// Skip quote and remember if it was ' or "
Ch quote = *text;
if (quote != Ch('\'') && quote != Ch('"'))
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("expected ' or \"", text);
++text;
// Extract attribute value and expand char refs in it
Ch *val = text, *end;
const int AttFlags = Flags & ~parse_normalize_whitespace; // No whitespace normalization in attributes
if (quote == Ch('\''))
end = skip_and_expand_character_refs<attribute_value_pred<Ch('\'')>, attribute_value_pure_pred<Ch('\'')>, AttFlags>(text);
else
end = skip_and_expand_character_refs<attribute_value_pred<Ch('"')>, attribute_value_pure_pred<Ch('"')>, AttFlags>(text);
// Set attribute value
attribute->value(val, end - val);
// Make sure that end quote is present
if (*text != quote)
BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR("expected ' or \"", text);
++text; // Skip quote
// Add terminating zero after value
if (!(Flags & parse_no_string_terminators))
attribute->value()[attribute->value_size()] = 0;
// Skip whitespace after attribute value
skip<whitespace_pred, Flags>(text);
}
}
};
//! \cond internal
namespace internal
{
// Whitespace (space \n \r \t)
template<int Dummy>
const unsigned char lookup_tables<Dummy>::lookup_whitespace[256] =
{
// 0 1 2 3 4 5 6 7 8 9 A B C D E F
0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, // 0
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 1
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 2
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 3
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 4
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 5
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 6
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 7
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 8
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 9
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // A
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // B
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // C
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // D
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // E
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 // F
};
// Node name (anything but space \n \r \t / > ? \0)
template<int Dummy>
const unsigned char lookup_tables<Dummy>::lookup_node_name[256] =
{
// 0 1 2 3 4 5 6 7 8 9 A B C D E F
0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, // 0
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 1
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, // 2
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, // 3
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 4
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 5
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 6
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 7
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 8
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 9
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // A
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // B
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // C
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // D
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // E
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 // F
};
// Text (i.e. PCDATA) (anything but < \0)
template<int Dummy>
const unsigned char lookup_tables<Dummy>::lookup_text[256] =
{
// 0 1 2 3 4 5 6 7 8 9 A B C D E F
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 1
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 2
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, // 3
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 4
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 5
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 6
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 7
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 8
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 9
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // A
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // B
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // C
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // D
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // E
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 // F
};
// Text (i.e. PCDATA) that does not require processing when ws normalization is disabled
// (anything but < \0 &)
template<int Dummy>
const unsigned char lookup_tables<Dummy>::lookup_text_pure_no_ws[256] =
{
// 0 1 2 3 4 5 6 7 8 9 A B C D E F
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 1
1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 2
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, // 3
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 4
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 5
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 6
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 7
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 8
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 9
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // A
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // B
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // C
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // D
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // E
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 // F
};
// Text (i.e. PCDATA) that does not require processing when ws normalizationis is enabled
// (anything but < \0 & space \n \r \t)
template<int Dummy>
const unsigned char lookup_tables<Dummy>::lookup_text_pure_with_ws[256] =
{
// 0 1 2 3 4 5 6 7 8 9 A B C D E F
0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, // 0
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 1
0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 2
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, // 3
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 4
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 5
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 6
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 7
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 8
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 9
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // A
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // B
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // C
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // D
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // E
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 // F
};
// Attribute name (anything but space \n \r \t / < > = ? ! \0)
template<int Dummy>
const unsigned char lookup_tables<Dummy>::lookup_attribute_name[256] =
{
// 0 1 2 3 4 5 6 7 8 9 A B C D E F
0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, // 0
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 1
0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, // 2
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, // 3
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 4
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 5
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 6
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 7
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 8
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 9
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // A
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // B
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // C
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // D
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // E
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 // F
};
// Attribute data with single quote (anything but ' \0)
template<int Dummy>
const unsigned char lookup_tables<Dummy>::lookup_attribute_data_1[256] =
{
// 0 1 2 3 4 5 6 7 8 9 A B C D E F
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 1
1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, // 2
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 3
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 4
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 5
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 6
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 7
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 8
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 9
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // A
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // B
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // C
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // D
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // E
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 // F
};
// Attribute data with single quote that does not require processing (anything but ' \0 &)
template<int Dummy>
const unsigned char lookup_tables<Dummy>::lookup_attribute_data_1_pure[256] =
{
// 0 1 2 3 4 5 6 7 8 9 A B C D E F
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 1
1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, // 2
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 3
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 4
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 5
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 6
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 7
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 8
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 9
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // A
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // B
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // C
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // D
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // E
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 // F
};
// Attribute data with double quote (anything but " \0)
template<int Dummy>
const unsigned char lookup_tables<Dummy>::lookup_attribute_data_2[256] =
{
// 0 1 2 3 4 5 6 7 8 9 A B C D E F
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 1
1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 2
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 3
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 4
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 5
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 6
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 7
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 8
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 9
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // A
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // B
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // C
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // D
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // E
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 // F
};
// Attribute data with double quote that does not require processing (anything but " \0 &)
template<int Dummy>
const unsigned char lookup_tables<Dummy>::lookup_attribute_data_2_pure[256] =
{
// 0 1 2 3 4 5 6 7 8 9 A B C D E F
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 1
1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 2
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 3
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 4
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 5
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 6
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 7
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 8
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 9
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // A
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // B
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // C
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // D
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // E
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 // F
};
// Digits (dec and hex, 255 denotes end of numeric character reference)
template<int Dummy>
const unsigned char lookup_tables<Dummy>::lookup_digits[256] =
{
// 0 1 2 3 4 5 6 7 8 9 A B C D E F
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255, // 0
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255, // 1
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255, // 2
0, 1, 2, 3, 4, 5, 6, 7, 8, 9,255,255,255,255,255,255, // 3
255, 10, 11, 12, 13, 14, 15,255,255,255,255,255,255,255,255,255, // 4
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255, // 5
255, 10, 11, 12, 13, 14, 15,255,255,255,255,255,255,255,255,255, // 6
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255, // 7
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255, // 8
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255, // 9
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255, // A
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255, // B
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255, // C
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255, // D
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255, // E
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255 // F
};
// Upper case conversion
template<int Dummy>
const unsigned char lookup_tables<Dummy>::lookup_upcase[256] =
{
// 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, A B C D E F
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, // 0
16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, // 1
32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, // 2
48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, // 3
64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, // 4
80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, // 5
96, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, // 6
80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 123,124,125,126,127, // 7
128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143, // 8
144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159, // 9
160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175, // A
176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191, // B
192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207, // C
208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223, // D
224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239, // E
240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255 // F
};
}
//! \endcond
}}}}
// Undefine internal macros
#undef BOOST_PROPERTY_TREE_RAPIDXML_PARSE_ERROR
// On MSVC, restore warnings state
#ifdef _MSC_VER
#pragma warning(pop)
#endif
#endif
|