Newer
Older
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
XPathMatcher* matcher = fMatcherStack->getMatcherAt(k);
IdentityConstraint* ic = matcher->getIdentityConstraint();
if (ic && (ic->getType() == IdentityConstraint::KEYREF)) {
ValueStore* values = fValueStoreCache->getValueStoreFor(ic, matcher->getInitialDepth());
if (values) { // nothing to do if nothing matched!
values->endDcocumentFragment(fValueStoreCache);
}
matcher->endDocumentFragment();
}
}
fValueStoreCache->endElement();
}
}
// If we have a doc handler, tell it about the end tag
if (fDocHandler)
{
fDocHandler->endElement
(
*topElem->fThisElement
, uriId
, isRoot
, fPrefixBuf.getRawBuffer()
);
}
// If this was the root, then done with content
gotData = !isRoot;
if (gotData) {
// Restore the grammar
fGrammar = fElemStack.getCurrentGrammar();
fGrammarType = fGrammar->getGrammarType();
fValidator->setGrammar(fGrammar);
// Restore the validation flag
fValidate = fElemStack.getValidationFlag();
}
}
// This method handles the high level logic of scanning the DOCType
// declaration. This calls the DTDScanner and kicks off both the scanning of
// the internal subset and the scanning of the external subset, if any.
//
// When we get here the '<!DOCTYPE' part has already been scanned, which is
// what told us that we had a doc type decl to parse.
void SGXMLScanner::scanDocTypeDecl()
{
// Just skips over it
// REVISIT: Should we issue a warning
static const XMLCh doctypeIE[] =
{
chOpenSquare, chCloseAngle, chNull
};
XMLCh nextCh = fReaderMgr.skipUntilIn(doctypeIE);
if (nextCh == chOpenSquare)
fReaderMgr.skipPastChar(chCloseSquare);
fReaderMgr.skipPastChar(chCloseAngle);
}
// This method is called to scan a start tag when we are processing
// namespaces. There are two different versions of this method, one for
// namespace aware processing an done for non-namespace aware processing.
//
// This method is called after we've scanned the < of a start tag. So we
// have to get the element name, then scan the attributes, after which
// we are either going to see >, />, or attributes followed by one of those
// sequences.
bool SGXMLScanner::scanStartTag(bool& gotData)
{
// Assume we will still have data until proven otherwise. It will only
// ever be false if this is the root and its empty.
gotData = true;
// The current position is after the open bracket, so we need to read in
// in the element name.
if (!fReaderMgr.getName(fQNameBuf))
{
emitError(XMLErrs::ExpectedElementName);
fReaderMgr.skipToChar(chOpenAngle);
return false;
}
// See if its the root element
const bool isRoot = fElemStack.isEmpty();
// Skip any whitespace after the name
fReaderMgr.skipPastSpaces();
// First we have to do the rawest attribute scan. We don't do any
// normalization of them at all, since we don't know yet what type they
// might be (since we need the element decl in order to do that.)
bool isEmpty;
unsigned int attCount = rawAttrScan
(
fQNameBuf.getRawBuffer()
, *fRawAttrList
, isEmpty
);
const bool gotAttrs = (attCount != 0);
// save the contentleafname and currentscope before addlevel, for later use
ContentLeafNameTypeVector* cv = 0;
XMLContentModel* cm = 0;
int currentScope = Grammar::TOP_LEVEL_SCOPE;
bool laxThisOne = false;
if (!isRoot) {
SchemaElementDecl* tempElement = (SchemaElementDecl*) fElemStack.topElement()->fThisElement;
SchemaElementDecl::ModelTypes modelType = tempElement->getModelType();
if ((modelType == SchemaElementDecl::Mixed_Simple)
|| (modelType == SchemaElementDecl::Mixed_Complex)
|| (modelType == SchemaElementDecl::Children))
{
cm = tempElement->getContentModel();
cv = cm->getContentLeafNameTypeVector();
currentScope = fElemStack.getCurrentScope();
}
else if (modelType == SchemaElementDecl::Any) {
laxThisOne = true;
}
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
}
// Now, since we might have to update the namespace map for this element,
// but we don't have the element decl yet, we just tell the element stack
// to expand up to get ready.
unsigned int elemDepth = fElemStack.addLevel();
fElemStack.setValidationFlag(fValidate);
// Check if there is any external schema location specified, and if we are at root,
// go through them first before scanning those specified in the instance document
if (isRoot
&& (fExternalSchemaLocation || fExternalNoNamespaceSchemaLocation)) {
if (fExternalSchemaLocation)
parseSchemaLocation(fExternalSchemaLocation);
if (fExternalNoNamespaceSchemaLocation)
resolveSchemaGrammar(fExternalNoNamespaceSchemaLocation, XMLUni::fgZeroLenString);
}
// Make an initial pass through the list and find any xmlns attributes or
// schema attributes.
if (attCount)
scanRawAttrListforNameSpaces(fRawAttrList, attCount);
// Resolve the qualified name to a URI and name so that we can look up
// the element decl for this element. We have now update the prefix to
// namespace map so we should get the correct element now.
int prefixColonPos = -1;
const XMLCh* qnameRawBuf = fQNameBuf.getRawBuffer();
unsigned int uriId = resolveQName
(
qnameRawBuf
, fPrefixBuf
, ElemStack::Mode_Element
, prefixColonPos
);
//if schema, check if we should lax or skip the validation of this element
bool parentValidation = fValidate;
if (cv) {
QName element(fPrefixBuf.getRawBuffer(), &qnameRawBuf[prefixColonPos + 1], uriId);
// elementDepth will be > 0, as cv is only constructed if element is not
// root.
laxThisOne = laxElementValidation(&element, cv, cm, elemDepth - 1);
}
// Look up the element now in the grammar. This will get us back a
// generic element decl object. We tell him to fault one in if he does
// not find it.
XMLElementDecl* elemDecl = 0;
bool wasAdded = false;
const XMLCh* nameRawBuf = &qnameRawBuf[prefixColonPos + 1];
if (uriId != fEmptyNamespaceId) {
// Check in current grammar before switching if necessary
elemDecl = fGrammar->getElemDecl
(
uriId
, nameRawBuf
, qnameRawBuf
, currentScope
);
if (!elemDecl && (fURIStringPool->getId(fGrammar->getTargetNamespace()) != uriId)) {
// not found, switch to the specified grammar
const XMLCh* uriStr = getURIText(uriId);
if (!switchGrammar(uriStr) && fValidate && !laxThisOne)
{
fValidator->emitError
(
XMLValid::GrammarNotFound
,uriStr
);
}
elemDecl = fGrammar->getElemDecl
(
uriId
, nameRawBuf
, qnameRawBuf
, currentScope
);
}
if (!elemDecl && currentScope != Grammar::TOP_LEVEL_SCOPE) {
// if not found, then it may be a reference, try TOP_LEVEL_SCOPE
elemDecl = fGrammar->getElemDecl
(
uriId
, nameRawBuf
, qnameRawBuf
, Grammar::TOP_LEVEL_SCOPE
);
if(!elemDecl) {
// still not found in specified uri
// try emptyNamesapce see if element should be un-qualified.
elemDecl = fGrammar->getElemDecl
(
fEmptyNamespaceId
, nameRawBuf
, qnameRawBuf
, currentScope
);
if (elemDecl && elemDecl->getCreateReason() != XMLElementDecl::JustFaultIn && fValidate) {
fValidator->emitError
(
XMLValid::ElementNotUnQualified
, elemDecl->getFullName()
);
}
}
}
if (!elemDecl) {
// still not found, fault this in and issue error later
elemDecl = fGrammar->putElemDecl(uriId
, nameRawBuf
, fPrefixBuf.getRawBuffer()
, qnameRawBuf
, currentScope
, true);
wasAdded = true;
}
}
else if (!elemDecl)
{
//the element has no prefix,
//thus it is either a non-qualified element defined in current targetNS
//or an element that is defined in the globalNS
//try unqualifed first
elemDecl = fGrammar->getElemDecl
(
uriId
, nameRawBuf
, qnameRawBuf
, currentScope
);
unsigned orgGrammarUri = fURIStringPool->getId(fGrammar->getTargetNamespace());
if (!elemDecl && orgGrammarUri != fEmptyNamespaceId) {
//not found, switch grammar and try globalNS
if (!switchGrammar(XMLUni::fgZeroLenString) && fValidate && !laxThisOne)
{
fValidator->emitError
(
XMLValid::GrammarNotFound
, XMLUni::fgZeroLenString
);
}
elemDecl = fGrammar->getElemDecl
(
uriId
, nameRawBuf
, qnameRawBuf
, currentScope
);
}
if (!elemDecl && currentScope != Grammar::TOP_LEVEL_SCOPE) {
// if not found, then it may be a reference, try TOP_LEVEL_SCOPE
elemDecl = fGrammar->getElemDecl
(
uriId
, nameRawBuf
, qnameRawBuf
, Grammar::TOP_LEVEL_SCOPE
);
if (!elemDecl && orgGrammarUri != fEmptyNamespaceId) {
// still Not found in specified uri
// go to original Grammar again to see if element needs to be fully qualified.
const XMLCh* uriStr = getURIText(orgGrammarUri);
if (!switchGrammar(uriStr) && fValidate && !laxThisOne)
{
fValidator->emitError
(
XMLValid::GrammarNotFound
,uriStr
);
}
elemDecl = fGrammar->getElemDecl
(
orgGrammarUri
, nameRawBuf
, qnameRawBuf
, currentScope
);
if (elemDecl && elemDecl->getCreateReason() != XMLElementDecl::JustFaultIn && fValidate) {
fValidator->emitError
(
XMLValid::ElementNotQualified
, elemDecl->getFullName()
);
}
}
}
if (!elemDecl) {
// still not found, fault this in and issue error later
elemDecl = fGrammar->putElemDecl(uriId
, nameRawBuf
, fPrefixBuf.getRawBuffer()
, qnameRawBuf
, currentScope
, true);
wasAdded = true;
}
}
// We do something different here according to whether we found the
// element or not.
if (wasAdded)
{
if (laxThisOne) {
fValidate = false;
fElemStack.setValidationFlag(fValidate);
}
// If validating then emit an error
if (fValidate)
{
// This is to tell the reuse Validator that this element was
// faulted-in, was not an element in the grammar pool originally
elemDecl->setCreateReason(XMLElementDecl::JustFaultIn);
fValidator->emitError
(
XMLValid::ElementNotDefined
, elemDecl->getFullName()
);
}
}
else
{
// If its not marked declared and validating, then emit an error
if (!elemDecl->isDeclared()) {
if (laxThisOne) {
fValidate = false;
fElemStack.setValidationFlag(fValidate);
}
if (fValidate)
{
fValidator->emitError
(
XMLValid::ElementNotDefined
, elemDecl->getFullName()
);
}
}
((SchemaElementDecl*)elemDecl)->setXsiComplexTypeInfo(0);
}
// Now we can update the element stack to set the current element
// decl. We expanded the stack above, but couldn't store the element
// decl because we didn't know it yet.
fElemStack.setElement(elemDecl, fReaderMgr.getCurrentReaderNum());
fElemStack.setCurrentURI(uriId);
if (isRoot)
fRootGrammar = fGrammar;
// Validate the element
if (fValidate)
fValidator->validateElement(elemDecl);
ComplexTypeInfo* typeinfo = ((SchemaElementDecl*)elemDecl)->getComplexTypeInfo();
if (typeinfo) {
currentScope = typeinfo->getScopeDefined();
// switch grammar if the typeinfo has a different grammar (happens when there is xsi:type)
XMLCh* typeName = typeinfo->getTypeName();
const XMLCh poundStr[] = {chPound, chNull};
if (!XMLString::startsWith(typeName, poundStr)) {
const int comma = XMLString::indexOf(typeName, chComma);
if (comma > 0) {
XMLBuffer prefixBuf(comma+1);
prefixBuf.append(typeName, comma);
const XMLCh* uriStr = prefixBuf.getRawBuffer();
if (!switchGrammar(uriStr) && fValidate && !laxThisOne)
{
fValidator->emitError
(
XMLValid::GrammarNotFound
, prefixBuf.getRawBuffer()
);
}
}
}
}
fElemStack.setCurrentScope(currentScope);
// Set element next state
if (elemDepth >= fElemStateSize) {
resizeElemState();
}
fElemState[elemDepth] = 0;
fElemStack.setCurrentGrammar(fGrammar);
// If this is the first element and we are validating, check the root
// element.
if (isRoot)
{
if (fValidate)
{
// Some validators may also want to check the root, call the
// XMLValidator::checkRootElement
if (fValidatorFromUser && !fValidator->checkRootElement(elemDecl->getId()))
fValidator->emitError(XMLValid::RootElemNotLikeDocType);
}
}
else if (parentValidation)
{
// If the element stack is not empty, then add this element as a
// child of the previous top element. If its empty, this is the root
// elem and is not the child of anything.
fElemStack.addChild(elemDecl->getElementName(), true);
}
// Now lets get the fAttrList filled in. This involves faulting in any
// defaulted and fixed attributes and normalizing the values of any that
// we got explicitly.
//
// We update the attCount value with the total number of attributes, but
// it goes in with the number of values we got during the raw scan of
// explictly provided attrs above.
attCount = buildAttList(*fRawAttrList, attCount, elemDecl, *fAttrList);
// activate identity constraints
if (fValidate) {
unsigned int count = ((SchemaElementDecl*) elemDecl)->getIdentityConstraintCount();
if (count || fMatcherStack->getMatcherCount()) {
fValueStoreCache->startElement();
fMatcherStack->pushContext();
fValueStoreCache->initValueStoresFor((SchemaElementDecl*) elemDecl, (int) elemDepth);
for (unsigned int i = 0; i < count; i++) {
activateSelectorFor(((SchemaElementDecl*) elemDecl)->getIdentityConstraintAt(i), (int) elemDepth);
}
// call all active identity constraints
count = fMatcherStack->getMatcherCount();
for (unsigned int j = 0; j < count; j++) {
XPathMatcher* matcher = fMatcherStack->getMatcherAt(j);
matcher->startElement(*elemDecl, uriId, fPrefixBuf.getRawBuffer(), *fAttrList, attCount);
}
}
}
// Since the element may have default values, call start tag now regardless if it is empty or not
// If we have a document handler, then tell it about this start tag
if (fDocHandler)
{
fDocHandler->startElement
(
*elemDecl
, uriId
, fPrefixBuf.getRawBuffer()
, *fAttrList
, attCount
, false
, isRoot
);
}
// If empty, validate content right now if we are validating and then
// pop the element stack top. Else, we have to update the current stack
// top's namespace mapping elements.
if (isEmpty)
{
// Pop the element stack back off since it'll never be used now
fElemStack.popTop();
// If validating, then insure that its legal to have no content
if (fValidate)
{
const int res = fValidator->checkContent(elemDecl, 0, 0);
if (res >= 0)
{
fValidator->emitError
(
XMLValid::ElementNotValidForContent
, elemDecl->getFullName()
, elemDecl->getFormattedContentModel()
);
}
// reset xsi:type ComplexTypeInfo
((SchemaElementDecl*)elemDecl)->setXsiComplexTypeInfo(0);
if (!isRoot)
((SchemaElementDecl*)(fElemStack.topElement()->fThisElement))->setXsiComplexTypeInfo(
((SchemaValidator*)fValidator)->getCurrentTypeInfo());
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
// call matchers and de-activate context
int oldCount = fMatcherStack->getMatcherCount();
if (oldCount || ((SchemaElementDecl*) elemDecl)->getIdentityConstraintCount()) {
for (int i = oldCount - 1; i >= 0; i--) {
XPathMatcher* matcher = fMatcherStack->getMatcherAt(i);
matcher->endElement(*elemDecl);
}
if (fMatcherStack->size() > 0) {
fMatcherStack->popContext();
}
// handle everything *but* keyref's.
int newCount = fMatcherStack->getMatcherCount();
for (int j = oldCount - 1; j >= newCount; j--) {
XPathMatcher* matcher = fMatcherStack->getMatcherAt(j);
IdentityConstraint* ic = matcher->getIdentityConstraint();
if (ic && (ic->getType() != IdentityConstraint::KEYREF)) {
matcher->endDocumentFragment();
fValueStoreCache->transplant(ic, matcher->getInitialDepth());
}
else if (!ic) {
matcher->endDocumentFragment();
}
}
// now handle keyref's...
for (int k = oldCount - 1; k >= newCount; k--) {
XPathMatcher* matcher = fMatcherStack->getMatcherAt(k);
IdentityConstraint* ic = matcher->getIdentityConstraint();
if (ic && (ic->getType() == IdentityConstraint::KEYREF)) {
ValueStore* values = fValueStoreCache->getValueStoreFor(ic, matcher->getInitialDepth());
if (values) { // nothing to do if nothing matched!
values->endDcocumentFragment(fValueStoreCache);
}
matcher->endDocumentFragment();
}
}
fValueStoreCache->endElement();
}
}
// If we have a doc handler, tell it about the end tag
if (fDocHandler)
{
fDocHandler->endElement
(
*elemDecl
, uriId
, isRoot
, fPrefixBuf.getRawBuffer()
);
}
// If the elem stack is empty, then it was an empty root
if (isRoot)
gotData = false;
else
{
// Restore the grammar
fGrammar = fElemStack.getCurrentGrammar();
fGrammarType = fGrammar->getGrammarType();
fValidator->setGrammar(fGrammar);
// Restore the validation flag
fValidate = fElemStack.getValidationFlag();
}
}
return true;
}
unsigned int
SGXMLScanner::resolveQName(const XMLCh* const qName
, XMLBuffer& prefixBuf
, const short mode
, int& prefixColonPos)
{
// Lets split out the qName into a URI and name buffer first. The URI
// can be empty.
prefixColonPos = XMLString::indexOf(qName, chColon);
if (prefixColonPos == -1)
{
// Its all name with no prefix, so put the whole thing into the name
// buffer. Then map the empty string to a URI, since the empty string
// represents the default namespace. This will either return some
// explicit URI which the default namespace is mapped to, or the
// the default global namespace.
bool unknown = false;
prefixBuf.reset();
return fElemStack.mapPrefixToURI(XMLUni::fgZeroLenString, (ElemStack::MapModes) mode, unknown);
}
else
{
// Copy the chars up to but not including the colon into the prefix
// buffer.
prefixBuf.set(qName, prefixColonPos);
// Watch for the special namespace prefixes. We always map these to
// special URIs. 'xml' gets mapped to the official URI that its defined
// to map to by the NS spec. xmlns gets mapped to a special place holder
// URI that we define (so that it maps to something checkable.)
const XMLCh* prefixRawBuf = prefixBuf.getRawBuffer();
if (XMLString::equals(prefixRawBuf, XMLUni::fgXMLNSString)) {
// if this is an element, it is an error to have xmlns as prefix
if (mode == ElemStack::Mode_Element)
emitError(XMLErrs::NoXMLNSAsElementPrefix, qName);
return fXMLNSNamespaceId;
}
else if (XMLString::equals(prefixRawBuf, XMLUni::fgXMLString)) {
return fXMLNamespaceId;
}
else
{
bool unknown = false;
unsigned int uriId = fElemStack.mapPrefixToURI(prefixRawBuf, (ElemStack::MapModes) mode, unknown);
if (unknown)
emitError(XMLErrs::UnknownPrefix, prefixRawBuf);
return uriId;
}
}
}
// ---------------------------------------------------------------------------
// SGXMLScanner: IC activation methos
// ---------------------------------------------------------------------------
void SGXMLScanner::activateSelectorFor(IdentityConstraint* const ic, const int initialDepth) {
IC_Selector* selector = ic->getSelector();
if (!selector)
return;
XPathMatcher* matcher = selector->createMatcher(fFieldActivator, initialDepth);
fMatcherStack->addMatcher(matcher);
matcher->startDocumentFragment();
}
// ---------------------------------------------------------------------------
// SGXMLScanner: Grammar preparsing
// ---------------------------------------------------------------------------
Grammar* SGXMLScanner::loadGrammar(const InputSource& src
, const short grammarType
, const bool toCache)
{
try
{
fGrammarResolver->cacheGrammarFromParse(false);
fGrammarResolver->useCachedGrammarInParse(false);
fRootGrammar = 0;
if (fValScheme == Val_Auto) {
fValidate = true;
}
// Reset some status flags
fInException = false;
fStandalone = false;
fErrorCount = 0;
fHasNoDTD = true;
fSeeXsi = false;
if (grammarType == Grammar::SchemaGrammarType) {
return loadXMLSchemaGrammar(src, toCache);
}
// Reset the reader manager to close all files, sockets, etc...
fReaderMgr.reset();
}
// NOTE:
//
// In all of the error processing below, the emitError() call MUST come
// before the flush of the reader mgr, or it will fail because it tries
// to find out the position in the XML source of the error.
catch(const XMLErrs::Codes)
{
// This is a 'first fatal error' type exit, so reset and fall through
fReaderMgr.reset();
}
catch(const XMLValid::Codes)
{
// This is a 'first fatal error' type exit, so reset and fall through
fReaderMgr.reset();
}
catch(const XMLException& excToCatch)
{
// Emit the error and catch any user exception thrown from here. Make
// sure in all cases we flush the reader manager.
fInException = true;
try
{
if (excToCatch.getErrorType() == XMLErrorReporter::ErrType_Warning)
emitError
(
XMLErrs::DisplayErrorMessage
, excToCatch.getMessage()
);
else if (excToCatch.getErrorType() >= XMLErrorReporter::ErrType_Fatal)
emitError
(
XMLErrs::XMLException_Fatal
, excToCatch.getType()
, excToCatch.getMessage()
);
else
emitError
(
XMLErrs::XMLException_Error
, excToCatch.getType()
, excToCatch.getMessage()
);
}
catch(...)
{
// Flush the reader manager and rethrow user's error
fReaderMgr.reset();
throw;
}
// If it returned, then reset the reader manager and fall through
fReaderMgr.reset();
}
catch(...)
{
// Reset and rethrow
fReaderMgr.reset();
throw;
}
return 0;
}
// ---------------------------------------------------------------------------
// SGXMLScanner: Private helper methods
// ---------------------------------------------------------------------------
// This method handles the common initialization, to avoid having to do
// it redundantly in multiple constructors.
void SGXMLScanner::commonInit()
{
// Create the element state array
fElemState = new unsigned int[fElemStateSize];
// And we need one for the raw attribute scan. This just stores key/
// value string pairs (prior to any processing.)
fRawAttrList = new RefVectorOf<KVStringPair>(32);
// Create dummy schema grammar
fSchemaGrammar = new SchemaGrammar();
// Create the Validator and init them
fSchemaValidator = new SchemaValidator();
initValidator(fSchemaValidator);
// Create IdentityConstraint info
fMatcherStack = new XPathMatcherStack();
fValueStoreCache = new ValueStoreCache();
fFieldActivator = new FieldActivator(fValueStoreCache, fMatcherStack);
fValueStoreCache->setScanner(this);
// Add the default entity entries for the character refs that must always
// be present.
fEntityTable = new ValueHashTableOf<XMLCh>(11);
fEntityTable->put((void*) XMLUni::fgAmp, chAmpersand);
fEntityTable->put((void*) XMLUni::fgLT, chOpenAngle);
fEntityTable->put((void*) XMLUni::fgGT, chCloseAngle);
fEntityTable->put((void*) XMLUni::fgQuot, chDoubleQuote);
fEntityTable->put((void*) XMLUni::fgApos, chSingleQuote);
}
void SGXMLScanner::cleanUp()
{
delete [] fElemState;
delete fSchemaGrammar;
delete fEntityTable;
delete fRawAttrList;
delete fSchemaValidator;
delete fFieldActivator;
delete fMatcherStack;
delete fValueStoreCache;
}
void SGXMLScanner::resizeElemState() {
unsigned int newSize = fElemStateSize * 2;
unsigned int* newElemState = new unsigned int[newSize];
// Copy the existing values
unsigned int index = 0;
for (; index < fElemStateSize; index++)
newElemState[index] = fElemState[index];
for (; index < newSize; index++)
newElemState[index] = 0;
// Delete the old array and udpate our members
delete [] fElemState;
fElemState = newElemState;
fElemStateSize = newSize;
}
// This method is called from scanStartTag() to build up the list of
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
// XMLAttr objects that will be passed out in the start tag callout. We
// get the key/value pairs from the raw scan of explicitly provided attrs,
// which have not been normalized. And we get the element declaration from
// which we will get any defaulted or fixed attribute defs and add those
// in as well.
unsigned int
SGXMLScanner::buildAttList(const RefVectorOf<KVStringPair>& providedAttrs
, const unsigned int attCount
, XMLElementDecl* elemDecl
, RefVectorOf<XMLAttr>& toFill)
{
// Ask the element to clear the 'provided' flag on all of the att defs
// that it owns, and to return us a boolean indicating whether it has
// any defs.
const bool hasDefs = elemDecl->resetDefs();
// If there are no expliclitily provided attributes and there are no
// defined attributes for the element, the we don't have anything to do.
// So just return zero in this case.
if (!hasDefs && !attCount)
return 0;
// Keep up with how many attrs we end up with total
unsigned int retCount = 0;
// And get the current size of the output vector. This lets us use
// existing elements until we fill it, then start adding new ones.
const unsigned int curAttListSize = toFill.size();
// We need a buffer into which raw scanned attribute values will be
// normalized.
XMLBufBid bbNormal(&fBufMgr);
XMLBuffer& normBuf = bbNormal.getBuffer();
// Loop through our explicitly provided attributes, which are in the raw
// scanned form, and build up XMLAttr objects.
unsigned int index;
for (index = 0; index < attCount; index++)
{
const KVStringPair* curPair = providedAttrs.elementAt(index);
// We have to split the name into its prefix and name parts. Then
// we map the prefix to its URI.
const XMLCh* const namePtr = curPair->getKey();
ArrayJanitor<XMLCh> janName(0);
// use a stack-based buffer when possible.
XMLCh tempBuffer[100];
const int colonInd = XMLString::indexOf(namePtr, chColon);
const XMLCh* prefPtr = XMLUni::fgZeroLenString;
const XMLCh* suffPtr = XMLUni::fgZeroLenString;
if (colonInd != -1)
{
// We have to split the string, so make a copy.
if (XMLString::stringLen(namePtr) < sizeof(tempBuffer) / sizeof(tempBuffer[0]))
{
XMLString::copyString(tempBuffer, namePtr);
tempBuffer[colonInd] = chNull;
prefPtr = tempBuffer;
}
else
{
janName.reset(XMLString::replicate(namePtr));
janName[colonInd] = chNull;
prefPtr = janName.get();
}
suffPtr = prefPtr + colonInd + 1;
}
else
{
// No colon, so we just have a name with no prefix
suffPtr = namePtr;
}
// Map the prefix to a URI id. We tell him that we are mapping an
// attr prefix, so any xmlns attrs at this level will not affect it.
const unsigned int uriId = resolvePrefix(prefPtr, ElemStack::Mode_Attribute);
// If the uri comes back as the xmlns or xml URI or its just a name
// and that name is 'xmlns', then we handle it specially. So set a
// boolean flag that lets us quickly below know which we are dealing
// with.
const bool isNSAttr = (uriId == fXMLNSNamespaceId)
|| (uriId == fXMLNamespaceId)
|| XMLString::equals(suffPtr, XMLUni::fgXMLNSString)
|| XMLString::equals(getURIText(uriId), SchemaSymbols::fgURI_XSI);
// If its not a special case namespace attr of some sort, then we
// do normal checking and processing.
XMLAttDef::AttTypes attType;
if (!isNSAttr)
{
// Some checking for attribute wild card first (for schema)
bool laxThisOne = false;
bool skipThisOne = false;
XMLAttDef* attDefForWildCard = 0;
XMLAttDef* attDef = 0;
if (fGrammarType == Grammar::SchemaGrammarType) {
//retrieve the att def
attDef = ((SchemaElementDecl*)elemDecl)->getAttDef(suffPtr, uriId);
// if not found or faulted in - check for a matching wildcard attribute
// if no matching wildcard attribute, check (un)qualifed cases and flag
// appropriate errors
if (!attDef || (attDef->getCreateReason() == XMLAttDef::JustFaultIn)) {
SchemaAttDef* attWildCard = ((SchemaElementDecl*)elemDecl)->getAttWildCard();
if (attWildCard) {
//if schema, see if we should lax or skip the validation of this attribute
if (anyAttributeValidation(attWildCard, uriId, skipThisOne, laxThisOne)) {
SchemaGrammar* sGrammar = (SchemaGrammar*) fGrammarResolver->getGrammar(getURIText(uriId));
if (sGrammar && sGrammar->getGrammarType() == Grammar::SchemaGrammarType) {
RefHashTableOf<XMLAttDef>* attRegistry = sGrammar->getAttributeDeclRegistry();
if (attRegistry) {
attDefForWildCard = attRegistry->get(suffPtr);
}
}
}
}
else {
// not found, see if the attDef should be qualified or not
if (uriId == fEmptyNamespaceId) {
attDef = ((SchemaElementDecl*)elemDecl)->getAttDef(suffPtr, fURIStringPool->getId(fGrammar->getTargetNamespace()));
if (fValidate
&& attDef
&& attDef->getCreateReason() != XMLAttDef::JustFaultIn) {
// the attribute should be qualified
fValidator->emitError
(