/**
* This method notifies of the start of an entity. The document entity has the pseudo-name of
* "[xml]" the DTD has the pseudo-name of "[dtd]" parameter entity names start with '%'; and
* general entities are just specified by their name.
*
* @param name The name of the entity.
* @param identifier The resource identifier.
* @param encoding The auto-detected IANA encoding name of the entity stream. This value will be
* null in those situations where the entity encoding is not auto-detected (e.g. internal
* entities or a document entity that is parsed from a java.io.Reader).
* @throws XNIException Thrown by handler to signal an error.
*/
public void startEntity(
String name, XMLResourceIdentifier identifier, String encoding, Augmentations augs)
throws XNIException {
// keep track of the entity depth
fEntityDepth++;
// must reset entity scanner
fEntityScanner = fEntityManager.getEntityScanner();
fEntityStore = fEntityManager.getEntityStore();
} // startEntity(String,XMLResourceIdentifier,String)
/**
* @param componentManager The component manager.
* @throws SAXException Throws exception if required features and properties cannot be found.
*/
public void reset(XMLComponentManager componentManager) throws XMLConfigurationException {
fParserSettings = componentManager.getFeature(PARSER_SETTINGS, true);
if (!fParserSettings) {
// parser settings have not been changed
init();
return;
}
// Xerces properties
fSymbolTable = (SymbolTable) componentManager.getProperty(SYMBOL_TABLE);
fErrorReporter = (XMLErrorReporter) componentManager.getProperty(ERROR_REPORTER);
fEntityManager = (XMLEntityManager) componentManager.getProperty(ENTITY_MANAGER);
fSecurityManager = (XMLSecurityManager) componentManager.getProperty(SECURITY_MANAGER);
// this step is extra because we have separated the storage of entity
fEntityStore = fEntityManager.getEntityStore();
// sax features
fValidation = componentManager.getFeature(VALIDATION, false);
fNamespaces = componentManager.getFeature(NAMESPACES, true);
fNotifyCharRefs = componentManager.getFeature(NOTIFY_CHAR_REFS, false);
init();
} // reset(XMLComponentManager)
public void reset(PropertyManager propertyManager) {
init();
// Xerces properties
fSymbolTable =
(SymbolTable)
propertyManager.getProperty(
Constants.XERCES_PROPERTY_PREFIX + Constants.SYMBOL_TABLE_PROPERTY);
fErrorReporter =
(XMLErrorReporter)
propertyManager.getProperty(
Constants.XERCES_PROPERTY_PREFIX + Constants.ERROR_REPORTER_PROPERTY);
fEntityManager = (XMLEntityManager) propertyManager.getProperty(ENTITY_MANAGER);
fEntityStore = fEntityManager.getEntityStore();
fEntityScanner = (XMLEntityScanner) fEntityManager.getEntityScanner();
// fEntityManager.reset();
// DTD preparsing defaults:
fValidation = false;
fNotifyCharRefs = false;
}
/**
* Scans an attribute value and normalizes whitespace converting all whitespace characters to
* space characters.
*
* <p>[10] AttValue ::= '"' ([^<&"] | Reference)* '"' | "'" ([^<&'] | Reference)* "'"
*
* @param value The XMLString to fill in with the value.
* @param nonNormalizedValue The XMLString to fill in with the non-normalized value.
* @param atName The name of the attribute being parsed (for error msgs).
* @param checkEntities true if undeclared entities should be reported as VC violation, false if
* undeclared entities should be reported as WFC violation.
* @param eleName The name of element to which this attribute belongs.
* <p><strong>Note:</strong> This method uses fStringBuffer2, anything in it at the time of
* calling is lost.
*/
protected void scanAttributeValue(
XMLString value,
XMLString nonNormalizedValue,
String atName,
boolean checkEntities,
String eleName)
throws IOException, XNIException {
// quote
int quote = fEntityScanner.peekChar();
if (quote != '\'' && quote != '"') {
reportFatalError("OpenQuoteExpected", new Object[] {eleName, atName});
}
fEntityScanner.scanChar();
int entityDepth = fEntityDepth;
int c = fEntityScanner.scanLiteral(quote, value);
if (DEBUG_ATTR_NORMALIZATION) {
System.out.println("** scanLiteral -> \"" + value.toString() + "\"");
}
fStringBuffer2.clear();
fStringBuffer2.append(value);
normalizeWhitespace(value);
if (DEBUG_ATTR_NORMALIZATION) {
System.out.println("** normalizeWhitespace -> \"" + value.toString() + "\"");
}
if (c != quote) {
fScanningAttribute = true;
fStringBuffer.clear();
do {
fStringBuffer.append(value);
if (DEBUG_ATTR_NORMALIZATION) {
System.out.println("** value2: \"" + fStringBuffer.toString() + "\"");
}
if (c == '&') {
fEntityScanner.skipChar('&');
if (entityDepth == fEntityDepth) {
fStringBuffer2.append('&');
}
if (fEntityScanner.skipChar('#')) {
if (entityDepth == fEntityDepth) {
fStringBuffer2.append('#');
}
int ch = scanCharReferenceValue(fStringBuffer, fStringBuffer2);
if (ch != -1) {
if (DEBUG_ATTR_NORMALIZATION) {
System.out.println("** value3: \"" + fStringBuffer.toString() + "\"");
}
}
} else {
String entityName = fEntityScanner.scanName();
if (entityName == null) {
reportFatalError("NameRequiredInReference", null);
} else if (entityDepth == fEntityDepth) {
fStringBuffer2.append(entityName);
}
if (!fEntityScanner.skipChar(';')) {
reportFatalError("SemicolonRequiredInReference", new Object[] {entityName});
} else if (entityDepth == fEntityDepth) {
fStringBuffer2.append(';');
}
if (entityName == fAmpSymbol) {
fStringBuffer.append('&');
if (DEBUG_ATTR_NORMALIZATION) {
System.out.println("** value5: \"" + fStringBuffer.toString() + "\"");
}
} else if (entityName == fAposSymbol) {
fStringBuffer.append('\'');
if (DEBUG_ATTR_NORMALIZATION) {
System.out.println("** value7: \"" + fStringBuffer.toString() + "\"");
}
} else if (entityName == fLtSymbol) {
fStringBuffer.append('<');
if (DEBUG_ATTR_NORMALIZATION) {
System.out.println("** value9: \"" + fStringBuffer.toString() + "\"");
}
} else if (entityName == fGtSymbol) {
fStringBuffer.append('>');
if (DEBUG_ATTR_NORMALIZATION) {
System.out.println("** valueB: \"" + fStringBuffer.toString() + "\"");
}
} else if (entityName == fQuotSymbol) {
fStringBuffer.append('"');
if (DEBUG_ATTR_NORMALIZATION) {
System.out.println("** valueD: \"" + fStringBuffer.toString() + "\"");
}
} else {
if (fEntityManager.isExternalEntity(entityName)) {
reportFatalError("ReferenceToExternalEntity", new Object[] {entityName});
} else {
if (!fEntityManager.isDeclaredEntity(entityName)) {
// WFC & VC: Entity Declared
if (checkEntities) {
if (fValidation) {
fErrorReporter.reportError(
XMLMessageFormatter.XML_DOMAIN,
"EntityNotDeclared",
new Object[] {entityName},
XMLErrorReporter.SEVERITY_ERROR);
}
} else {
reportFatalError("EntityNotDeclared", new Object[] {entityName});
}
}
fEntityManager.startEntity(entityName, true);
}
}
}
} else if (c == '<') {
reportFatalError("LessthanInAttValue", new Object[] {eleName, atName});
fEntityScanner.scanChar();
if (entityDepth == fEntityDepth) {
fStringBuffer2.append((char) c);
}
} else if (c == '%' || c == ']') {
fEntityScanner.scanChar();
fStringBuffer.append((char) c);
if (entityDepth == fEntityDepth) {
fStringBuffer2.append((char) c);
}
if (DEBUG_ATTR_NORMALIZATION) {
System.out.println("** valueF: \"" + fStringBuffer.toString() + "\"");
}
} else if (c == '\n' || c == '\r') {
fEntityScanner.scanChar();
fStringBuffer.append(' ');
if (entityDepth == fEntityDepth) {
fStringBuffer2.append('\n');
}
} else if (c != -1 && XMLChar.isHighSurrogate(c)) {
fStringBuffer3.clear();
if (scanSurrogates(fStringBuffer3)) {
fStringBuffer.append(fStringBuffer3);
if (entityDepth == fEntityDepth) {
fStringBuffer2.append(fStringBuffer3);
}
if (DEBUG_ATTR_NORMALIZATION) {
System.out.println("** valueI: \"" + fStringBuffer.toString() + "\"");
}
}
} else if (c != -1 && isInvalidLiteral(c)) {
reportFatalError(
"InvalidCharInAttValue", new Object[] {eleName, atName, Integer.toString(c, 16)});
fEntityScanner.scanChar();
if (entityDepth == fEntityDepth) {
fStringBuffer2.append((char) c);
}
}
c = fEntityScanner.scanLiteral(quote, value);
if (entityDepth == fEntityDepth) {
fStringBuffer2.append(value);
}
normalizeWhitespace(value);
} while (c != quote || entityDepth != fEntityDepth);
fStringBuffer.append(value);
if (DEBUG_ATTR_NORMALIZATION) {
System.out.println("** valueN: \"" + fStringBuffer.toString() + "\"");
}
value.setValues(fStringBuffer);
fScanningAttribute = false;
}
nonNormalizedValue.setValues(fStringBuffer2);
// quote
int cquote = fEntityScanner.scanChar();
if (cquote != quote) {
reportFatalError("CloseQuoteExpected", new Object[] {eleName, atName});
}
} // scanAttributeValue()
/**
* Scans a pseudo attribute.
*
* @param scanningTextDecl True if scanning this pseudo-attribute for a TextDecl; false if
* scanning XMLDecl. This flag is needed to report the correct type of error.
* @param value The string to fill in with the attribute value.
* @return The name of the attribute
* <p><strong>Note:</strong> This method uses fStringBuffer2, anything in it at the time of
* calling is lost.
*/
public String scanPseudoAttribute(boolean scanningTextDecl, XMLString value)
throws IOException, XNIException {
// REVISIT: This method is used for generic scanning of
// pseudo attributes, but since there are only three such
// attributes: version, encoding, and standalone there are
// for performant ways of scanning them. Every decl must
// have a version, and in TextDecls this version must
// be followed by an encoding declaration. Also the
// methods we invoke on the scanners allow non-ASCII
// characters to be parsed in the decls, but since
// we don't even know what the actual encoding of the
// document is until we scan the encoding declaration
// you cannot reliably read any characters outside
// of the ASCII range here. -- mrglavas
String name = fEntityScanner.scanName();
XMLEntityManager.print(fEntityManager.getCurrentEntity());
if (name == null) {
reportFatalError("PseudoAttrNameExpected", null);
}
fEntityScanner.skipDeclSpaces();
if (!fEntityScanner.skipChar('=')) {
reportFatalError(
scanningTextDecl ? "EqRequiredInTextDecl" : "EqRequiredInXMLDecl", new Object[] {name});
}
fEntityScanner.skipDeclSpaces();
int quote = fEntityScanner.peekChar();
if (quote != '\'' && quote != '"') {
reportFatalError(
scanningTextDecl ? "QuoteRequiredInTextDecl" : "QuoteRequiredInXMLDecl",
new Object[] {name});
}
fEntityScanner.scanChar();
int c = fEntityScanner.scanLiteral(quote, value);
if (c != quote) {
fStringBuffer2.clear();
do {
fStringBuffer2.append(value);
if (c != -1) {
if (c == '&' || c == '%' || c == '<' || c == ']') {
fStringBuffer2.append((char) fEntityScanner.scanChar());
}
// REVISIT: Even if you could reliably read non-ASCII chars
// why bother scanning for surrogates here? Only ASCII chars
// match the productions in XMLDecls and TextDecls. -- mrglavas
else if (XMLChar.isHighSurrogate(c)) {
scanSurrogates(fStringBuffer2);
} else if (isInvalidLiteral(c)) {
String key = scanningTextDecl ? "InvalidCharInTextDecl" : "InvalidCharInXMLDecl";
reportFatalError(key, new Object[] {Integer.toString(c, 16)});
fEntityScanner.scanChar();
}
}
c = fEntityScanner.scanLiteral(quote, value);
} while (c != quote);
fStringBuffer2.append(value);
value.setValues(fStringBuffer2);
}
if (!fEntityScanner.skipChar(quote)) {
reportFatalError(
scanningTextDecl ? "CloseQuoteMissingInTextDecl" : "CloseQuoteMissingInXMLDecl",
new Object[] {name});
}
// return
return name;
} // scanPseudoAttribute(XMLString):String
/**
* Scans an XML or text declaration.
*
* <p>
*
* <pre>
* [23] XMLDecl ::= '<?xml' VersionInfo EncodingDecl? SDDecl? S? '?>'
* [24] VersionInfo ::= S 'version' Eq (' VersionNum ' | " VersionNum ")
* [80] EncodingDecl ::= S 'encoding' Eq ('"' EncName '"' | "'" EncName "'" )
* [81] EncName ::= [A-Za-z] ([A-Za-z0-9._] | '-')*
* [32] SDDecl ::= S 'standalone' Eq (("'" ('yes' | 'no') "'")
* | ('"' ('yes' | 'no') '"'))
*
* [77] TextDecl ::= '<?xml' VersionInfo? EncodingDecl S? '?>'
* </pre>
*
* @param scanningTextDecl True if a text declaration is to be scanned instead of an XML
* declaration.
* @param pseudoAttributeValues An array of size 3 to return the version, encoding and standalone
* pseudo attribute values (in that order).
* <p><strong>Note:</strong> This method uses fString, anything in it at the time of calling
* is lost.
*/
protected void scanXMLDeclOrTextDecl(boolean scanningTextDecl, String[] pseudoAttributeValues)
throws IOException, XNIException {
// pseudo-attribute values
String version = null;
String encoding = null;
String standalone = null;
// scan pseudo-attributes
final int STATE_VERSION = 0;
final int STATE_ENCODING = 1;
final int STATE_STANDALONE = 2;
final int STATE_DONE = 3;
int state = STATE_VERSION;
boolean dataFoundForTarget = false;
boolean sawSpace = fEntityScanner.skipDeclSpaces();
// since pseudoattributes are *not* attributes,
// their quotes don't need to be preserved in external parameter entities.
// the XMLEntityScanner#scanLiteral method will continue to
// emit -1 in such cases when it finds a quote; this is
// fine for other methods that parse scanned entities,
// but not for the scanning of pseudoattributes. So,
// temporarily, we must mark the current entity as not being "literal"
XMLEntityManager.ScannedEntity currEnt = fEntityManager.getCurrentEntity();
boolean currLiteral = currEnt.literal;
currEnt.literal = false;
while (fEntityScanner.peekChar() != '?') {
dataFoundForTarget = true;
String name = scanPseudoAttribute(scanningTextDecl, fString);
switch (state) {
case STATE_VERSION:
{
if (name == fVersionSymbol) {
if (!sawSpace) {
reportFatalError(
scanningTextDecl
? "SpaceRequiredBeforeVersionInTextDecl"
: "SpaceRequiredBeforeVersionInXMLDecl",
null);
}
version = fString.toString();
state = STATE_ENCODING;
if (!versionSupported(version)) {
reportFatalError(getVersionNotSupportedKey(), new Object[] {version});
}
} else if (name == fEncodingSymbol) {
if (!scanningTextDecl) {
reportFatalError("VersionInfoRequired", null);
}
if (!sawSpace) {
reportFatalError(
scanningTextDecl
? "SpaceRequiredBeforeEncodingInTextDecl"
: "SpaceRequiredBeforeEncodingInXMLDecl",
null);
}
encoding = fString.toString();
state = scanningTextDecl ? STATE_DONE : STATE_STANDALONE;
} else {
if (scanningTextDecl) {
reportFatalError("EncodingDeclRequired", null);
} else {
reportFatalError("VersionInfoRequired", null);
}
}
break;
}
case STATE_ENCODING:
{
if (name == fEncodingSymbol) {
if (!sawSpace) {
reportFatalError(
scanningTextDecl
? "SpaceRequiredBeforeEncodingInTextDecl"
: "SpaceRequiredBeforeEncodingInXMLDecl",
null);
}
encoding = fString.toString();
state = scanningTextDecl ? STATE_DONE : STATE_STANDALONE;
// TODO: check encoding name; set encoding on
// entity scanner
} else if (!scanningTextDecl && name == fStandaloneSymbol) {
if (!sawSpace) {
reportFatalError("SpaceRequiredBeforeStandalone", null);
}
standalone = fString.toString();
state = STATE_DONE;
if (!standalone.equals("yes") && !standalone.equals("no")) {
reportFatalError("SDDeclInvalid", new Object[] {standalone});
}
} else {
reportFatalError("EncodingDeclRequired", null);
}
break;
}
case STATE_STANDALONE:
{
if (name == fStandaloneSymbol) {
if (!sawSpace) {
reportFatalError("SpaceRequiredBeforeStandalone", null);
}
standalone = fString.toString();
state = STATE_DONE;
if (!standalone.equals("yes") && !standalone.equals("no")) {
reportFatalError("SDDeclInvalid", new Object[] {standalone});
}
} else {
reportFatalError("EncodingDeclRequired", null);
}
break;
}
default:
{
reportFatalError("NoMorePseudoAttributes", null);
}
}
sawSpace = fEntityScanner.skipDeclSpaces();
}
// restore original literal value
if (currLiteral) currEnt.literal = true;
// REVISIT: should we remove this error reporting?
if (scanningTextDecl && state != STATE_DONE) {
reportFatalError("MorePseudoAttributes", null);
}
// If there is no data in the xml or text decl then we fail to report error
// for version or encoding info above.
if (scanningTextDecl) {
if (!dataFoundForTarget && encoding == null) {
reportFatalError("EncodingDeclRequired", null);
}
} else {
if (!dataFoundForTarget && version == null) {
reportFatalError("VersionInfoRequired", null);
}
}
// end
if (!fEntityScanner.skipChar('?')) {
reportFatalError("XMLDeclUnterminated", null);
}
if (!fEntityScanner.skipChar('>')) {
reportFatalError("XMLDeclUnterminated", null);
}
// fill in return array
pseudoAttributeValues[0] = version;
pseudoAttributeValues[1] = encoding;
pseudoAttributeValues[2] = standalone;
} // scanXMLDeclOrTextDecl(boolean)
/**
* Scans an XML or text declaration.
*
* <p>
*
* <pre>
* [23] XMLDecl ::= '<?xml' VersionInfo EncodingDecl? SDDecl? S? '?>'
* [24] VersionInfo ::= S 'version' Eq (' VersionNum ' | " VersionNum ")
* [80] EncodingDecl ::= S 'encoding' Eq ('"' EncName '"' | "'" EncName "'" )
* [81] EncName ::= [A-Za-z] ([A-Za-z0-9._] | '-')*
* [32] SDDecl ::= S 'standalone' Eq (("'" ('yes' | 'no') "'")
* | ('"' ('yes' | 'no') '"'))
*
* [77] TextDecl ::= '<?xml' VersionInfo? EncodingDecl S? '?>'
* </pre>
*
* @param scanningTextDecl True if a text declaration is to be scanned instead of an XML
* declaration.
* @param pseudoAttributeValues An array of size 3 to return the version, encoding and standalone
* pseudo attribute values (in that order).
* <p><strong>Note:</strong> This method uses fString, anything in it at the time of calling
* is lost.
*/
protected void scanXMLDeclOrTextDecl(boolean scanningTextDecl, String[] pseudoAttributeValues)
throws IOException, XNIException {
// pseudo-attribute values
String version = null;
String encoding = null;
String standalone = null;
// scan pseudo-attributes
final int STATE_VERSION = 0;
final int STATE_ENCODING = 1;
final int STATE_STANDALONE = 2;
final int STATE_DONE = 3;
int state = STATE_VERSION;
boolean dataFoundForTarget = false;
boolean sawSpace = fEntityScanner.skipSpaces();
while (fEntityScanner.peekChar() != '?') {
dataFoundForTarget = true;
String name = scanPseudoAttribute(scanningTextDecl, fString);
switch (state) {
case STATE_VERSION:
{
if (name.equals(fVersionSymbol)) {
if (!sawSpace) {
reportFatalError(
scanningTextDecl
? "SpaceRequiredBeforeVersionInTextDecl"
: "SpaceRequiredBeforeVersionInXMLDecl",
null);
}
version = fString.toString();
state = STATE_ENCODING;
if (!versionSupported(version)) {
reportFatalError("VersionNotSupported", new Object[] {version});
}
if (version.equals("1.1")) {
Entity.ScannedEntity top = fEntityManager.getTopLevelEntity();
if (top != null && (top.version == null || top.version.equals("1.0"))) {
reportFatalError("VersionMismatch", null);
}
fEntityManager.setScannerVersion(Constants.XML_VERSION_1_1);
}
} else if (name.equals(fEncodingSymbol)) {
if (!scanningTextDecl) {
reportFatalError("VersionInfoRequired", null);
}
if (!sawSpace) {
reportFatalError(
scanningTextDecl
? "SpaceRequiredBeforeEncodingInTextDecl"
: "SpaceRequiredBeforeEncodingInXMLDecl",
null);
}
encoding = fString.toString();
state = scanningTextDecl ? STATE_DONE : STATE_STANDALONE;
} else {
if (scanningTextDecl) {
reportFatalError("EncodingDeclRequired", null);
} else {
reportFatalError("VersionInfoRequired", null);
}
}
break;
}
case STATE_ENCODING:
{
if (name.equals(fEncodingSymbol)) {
if (!sawSpace) {
reportFatalError(
scanningTextDecl
? "SpaceRequiredBeforeEncodingInTextDecl"
: "SpaceRequiredBeforeEncodingInXMLDecl",
null);
}
encoding = fString.toString();
state = scanningTextDecl ? STATE_DONE : STATE_STANDALONE;
// TODO: check encoding name; set encoding on
// entity scanner
} else if (!scanningTextDecl && name.equals(fStandaloneSymbol)) {
if (!sawSpace) {
reportFatalError("SpaceRequiredBeforeStandalone", null);
}
standalone = fString.toString();
state = STATE_DONE;
if (!standalone.equals("yes") && !standalone.equals("no")) {
reportFatalError("SDDeclInvalid", new Object[] {standalone});
}
} else {
reportFatalError("EncodingDeclRequired", null);
}
break;
}
case STATE_STANDALONE:
{
if (name.equals(fStandaloneSymbol)) {
if (!sawSpace) {
reportFatalError("SpaceRequiredBeforeStandalone", null);
}
standalone = fString.toString();
state = STATE_DONE;
if (!standalone.equals("yes") && !standalone.equals("no")) {
reportFatalError("SDDeclInvalid", new Object[] {standalone});
}
} else {
reportFatalError("EncodingDeclRequired", null);
}
break;
}
default:
{
reportFatalError("NoMorePseudoAttributes", null);
}
}
sawSpace = fEntityScanner.skipSpaces();
}
// REVISIT: should we remove this error reporting?
if (scanningTextDecl && state != STATE_DONE) {
reportFatalError("MorePseudoAttributes", null);
}
// If there is no data in the xml or text decl then we fail to report error
// for version or encoding info above.
if (scanningTextDecl) {
if (!dataFoundForTarget && encoding == null) {
reportFatalError("EncodingDeclRequired", null);
}
} else {
if (!dataFoundForTarget && version == null) {
reportFatalError("VersionInfoRequired", null);
}
}
// end
if (!fEntityScanner.skipChar('?')) {
reportFatalError("XMLDeclUnterminated", null);
}
if (!fEntityScanner.skipChar('>')) {
reportFatalError("XMLDeclUnterminated", null);
}
// fill in return array
pseudoAttributeValues[0] = version;
pseudoAttributeValues[1] = encoding;
pseudoAttributeValues[2] = standalone;
} // scanXMLDeclOrTextDecl(boolean)