FileDocCategorySizeDatePackage
Parser.javaAPI DocAndroid 1.5 API38237Wed May 06 22:41:42 BST 2009org.ccil.cowan.tagsoup

Parser

public class Parser extends DefaultHandler implements ScanHandler, LexicalHandler, XMLReader
The SAX parser class.

Fields Summary
private ContentHandler
theContentHandler
private LexicalHandler
theLexicalHandler
private DTDHandler
theDTDHandler
private ErrorHandler
theErrorHandler
private EntityResolver
theEntityResolver
private Schema
theSchema
private Scanner
theScanner
private AutoDetector
theAutoDetector
private static boolean
DEFAULT_NAMESPACES
private static boolean
DEFAULT_IGNORE_BOGONS
private static boolean
DEFAULT_BOGONS_EMPTY
private static boolean
DEFAULT_ROOT_BOGONS
private static boolean
DEFAULT_DEFAULT_ATTRIBUTES
private static boolean
DEFAULT_TRANSLATE_COLONS
private static boolean
DEFAULT_RESTART_ELEMENTS
private static boolean
DEFAULT_IGNORABLE_WHITESPACE
private static boolean
DEFAULT_CDATA_ELEMENTS
private boolean
namespaces
private boolean
ignoreBogons
private boolean
bogonsEmpty
private boolean
rootBogons
private boolean
defaultAttributes
private boolean
translateColons
private boolean
restartElements
private boolean
ignorableWhitespace
private boolean
CDATAElements
public static final String
namespacesFeature
A value of "true" indicates namespace URIs and unprefixed local names for element and attribute names will be available.
public static final String
namespacePrefixesFeature
A value of "true" indicates that XML qualified names (with prefixes) and attributes (including xmlns* attributes) will be available. We don't support this value.
public static final String
externalGeneralEntitiesFeature
Reports whether this parser processes external general entities (it doesn't).
public static final String
externalParameterEntitiesFeature
Reports whether this parser processes external parameter entities (it doesn't).
public static final String
isStandaloneFeature
May be examined only during a parse, after the startDocument() callback has been completed; read-only. The value is true if the document specified standalone="yes" in its XML declaration, and otherwise is false. (It's always false.)
public static final String
lexicalHandlerParameterEntitiesFeature
A value of "true" indicates that the LexicalHandler will report the beginning and end of parameter entities (it won't).
public static final String
resolveDTDURIsFeature
A value of "true" indicates that system IDs in declarations will be absolutized (relative to their base URIs) before reporting. (This returns true but doesn't actually do anything.)
public static final String
stringInterningFeature
Has a value of "true" if all XML names (for elements, prefixes, attributes, entities, notations, and local names), as well as Namespace URIs, will have been interned using java.lang.String.intern. This supports fast testing of equality/inequality against string constants, rather than forcing slower calls to String.equals(). (We always intern.)
public static final String
useAttributes2Feature
Returns "true" if the Attributes objects passed by this parser in ContentHandler.startElement() implement the org.xml.sax.ext.Attributes2 interface. (They don't.)
public static final String
useLocator2Feature
Returns "true" if the Locator objects passed by this parser in ContentHandler.setDocumentLocator() implement the org.xml.sax.ext.Locator2 interface. (They don't.)
public static final String
useEntityResolver2Feature
Returns "true" if, when setEntityResolver is given an object implementing the org.xml.sax.ext.EntityResolver2 interface, those new methods will be used. (They won't be.)
public static final String
validationFeature
Controls whether the parser is reporting all validity errors (We don't report any validity errors.)
public static final String
unicodeNormalizationCheckingFeature
Controls whether the parser reports Unicode normalization errors as described in section 2.13 and Appendix B of the XML 1.1 Recommendation. (We don't normalize.)
public static final String
xmlnsURIsFeature
Controls whether, when the namespace-prefixes feature is set, the parser treats namespace declaration attributes as being in the http://www.w3.org/2000/xmlns/ namespace. (It doesn't.)
public static final String
XML11Feature
Returns "true" if the parser supports both XML 1.1 and XML 1.0. (Always false.)
public static final String
ignoreBogonsFeature
A value of "true" indicates that the parser will ignore unknown elements.
public static final String
bogonsEmptyFeature
A value of "true" indicates that the parser will give unknown elements a content model of EMPTY; a value of "false", a content model of ANY.
public static final String
rootBogonsFeature
A value of "true" indicates that the parser will allow unknown elements to be the root element.
public static final String
defaultAttributesFeature
A value of "true" indicates that the parser will return default attribute values for missing attributes that have default values.
public static final String
translateColonsFeature
A value of "true" indicates that the parser will translate colons into underscores in names.
public static final String
restartElementsFeature
A value of "true" indicates that the parser will attempt to restart the restartable elements.
public static final String
ignorableWhitespaceFeature
A value of "true" indicates that the parser will transmit whitespace in element-only content via the SAX ignorableWhitespace callback. Normally this is not done, because HTML is an SGML application and SGML suppresses such whitespace.
public static final String
CDATAElementsFeature
A value of "true" indicates that the parser will treat CDATA elements specially. Normally true, since the input is by default HTML.
public static final String
lexicalHandlerProperty
Used to see some syntax events that are essential in some applications: comments, CDATA delimiters, selected general entity inclusions, and the start and end of the DTD (and declaration of document element name). The Object must implement org.xml.sax.ext.LexicalHandler.
public static final String
scannerProperty
Specifies the Scanner object this Parser uses.
public static final String
schemaProperty
Specifies the Schema object this Parser uses.
public static final String
autoDetectorProperty
Specifies the AutoDetector (for encoding detection) this Parser uses.
private HashMap
theFeatures
private Element
theNewElement
private String
theAttributeName
private boolean
theDoctypeIsPresent
private String
theDoctypePublicId
private String
theDoctypeSystemId
private String
theDoctypeName
private String
thePITarget
private Element
theStack
private Element
theSaved
private Element
thePCDATA
private int
theEntity
private static char[]
etagchars
private boolean
virginStack
private static String
legal
private char[]
theCommentBuffer
Constructors Summary
Methods Summary
public voidadup(char[] buff, int offset, int length)

	// needs to support chars past U+FFFF

	          
		if (theNewElement == null || theAttributeName == null) return;
		theNewElement.setAttribute(theAttributeName, null, theAttributeName);
		theAttributeName = null;
public voidaname(char[] buff, int offset, int length)

		if (theNewElement == null) return;
		// Currently we don't rely on Schema to canonicalize
		// attribute names.
		theAttributeName = makeName(buff, offset, length).toLowerCase();
//		System.err.println("%% Attribute name " + theAttributeName);
public voidaval(char[] buff, int offset, int length)

		if (theNewElement == null || theAttributeName == null) return;
		String value = new String(buff, offset, length);
//		System.err.println("%% Attribute value [" + value + "]");
		value = expandEntities(value);
		theNewElement.setAttribute(theAttributeName, null, value);
		theAttributeName = null;
//		System.err.println("%% Aval done");
public voidcdsect(char[] buff, int offset, int length)

		theLexicalHandler.startCDATA();
		pcdata(buff, offset, length);
		theLexicalHandler.endCDATA();
private java.lang.StringcleanPublicid(java.lang.String src)


	    
		if (src == null) return null;
		int len = src.length();
		StringBuffer dst = new StringBuffer(len);
		boolean suppressSpace = true;
		for (int i = 0; i < len; i++) {
			char ch = src.charAt(i);
			if (legal.indexOf(ch) != -1) { 	// legal but not whitespace
				dst.append(ch);
				suppressSpace = false;
				}
			else if (suppressSpace) {	// normalizable whitespace or junk
				;
				}
			else {
				dst.append(' ");
				suppressSpace = true;
				}
			}
//		System.err.println("%% Publicid [" + dst.toString().trim() + "]");
		return dst.toString().trim();	// trim any final junk whitespace
public voidcmnt(char[] buff, int offset, int length)

	          
		theLexicalHandler.comment(buff, offset, length);
public voidcomment(char[] ch, int start, int length)
public voiddecl(char[] buff, int offset, int length)
Parsing the complete XML Document Type Definition is way too complex, but for many simple cases we can extract something useful from it. doctypedecl ::= '' DeclSep ::= PEReference | S intSubset ::= (markupdecl | DeclSep)* markupdecl ::= elementdecl | AttlistDecl | EntityDecl | NotationDecl | PI | Comment ExternalID ::= 'SYSTEM' S SystemLiteral | 'PUBLIC' S PubidLiteral S SystemLiteral

		String s = new String(buff, offset, length);
		String name = null;
		String systemid = null;
		String publicid = null;
		String[] v = split(s);
		if (v.length > 0 && "DOCTYPE".equals(v[0])) {
			if (theDoctypeIsPresent) return;		// one doctype only!
			theDoctypeIsPresent = true;
			if (v.length > 1) {
				name = v[1];
				if (v.length>3 && "SYSTEM".equals(v[2])) {
				systemid = v[3];
				}
			else if (v.length > 3 && "PUBLIC".equals(v[2])) {
				publicid = v[3];
				if (v.length > 4) {
					systemid = v[4];
					}
				else {
					systemid = "";
					}
                    }
                }
            }
		publicid = trimquotes(publicid);
		systemid = trimquotes(systemid);
		if (name != null) {
			publicid = cleanPublicid(publicid);
			theLexicalHandler.startDTD(name, publicid, systemid);
			theLexicalHandler.endDTD();
			theDoctypeName = name;
			theDoctypePublicId = publicid;
		if (theScanner instanceof Locator) {    // Must resolve systemid
                    theDoctypeSystemId  = ((Locator)theScanner).getSystemId();
                    try {
                        theDoctypeSystemId = new URL(new URL(theDoctypeSystemId), systemid).toString();
                    } catch (Exception e) {}
                }
            }
public voidendCDATA()
public voidendDTD()
public voidendEntity(java.lang.String name)
public voidentity(char[] buff, int offset, int length)

		theEntity = lookupEntity(buff, offset, length);
public voideof(char[] buff, int offset, int length)

		if (virginStack) rectify(thePCDATA);
		while (theStack.next() != null) {
			pop();
			}
		if (!(theSchema.getURI().equals("")))
			theContentHandler.endPrefixMapping(theSchema.getPrefix());
		theContentHandler.endDocument();
public voidetag(char[] buff, int offset, int length)

		if (etag_cdata(buff, offset, length)) return;
		etag_basic(buff, offset, length);
public voidetag_basic(char[] buff, int offset, int length)

		theNewElement = null;
		String name;
		if (length != 0) {
			// Canonicalize case of name
			name = makeName(buff, offset, length);
//			System.err.println("got etag [" + name + "]");
			ElementType type = theSchema.getElementType(name);
			if (type == null) return;	// mysterious end-tag
			name = type.name();
			}
		else {
			name = theStack.name();
			}
//		System.err.println("%% Got end of " + name);

		Element sp;
		boolean inNoforce = false;
		for (sp = theStack; sp != null; sp = sp.next()) {
			if (sp.name().equals(name)) break;
			if ((sp.flags() & Schema.F_NOFORCE) != 0) inNoforce = true;
			}

		if (sp == null) return;		// Ignore unknown etags
		if (sp.next() == null || sp.next().next() == null) return;
		if (inNoforce) {		// inside an F_NOFORCE element?
			sp.preclose();		// preclose the matching element
			}
		else {			// restartably pop everything above us
			while (theStack != sp) {
				restartablyPop();
				}
			pop();
			}
		// pop any preclosed elements now at the top
		while (theStack.isPreclosed()) {
			pop();
			}
		restart(null);
public booleanetag_cdata(char[] buff, int offset, int length)

	          
		String currentName = theStack.name();
		// If this is a CDATA element and the tag doesn't match,
		// or isn't properly formed (junk after the name),
		// restart CDATA mode and process the tag as characters.
		if (CDATAElements && (theStack.flags() & Schema.F_CDATA) != 0) {
			boolean realTag = (length == currentName.length());
			if (realTag) {
				for (int i = 0; i < length; i++) {
					if (Character.toLowerCase(buff[offset + i]) != Character.toLowerCase(currentName.charAt(i))) {
						realTag = false;
						break;
						}
					}
				}
			if (!realTag) {
				theContentHandler.characters(etagchars, 0, 2);
				theContentHandler.characters(buff, offset, length);
				theContentHandler.characters(etagchars, 2, 1);
				theScanner.startCDATA();
				return true;
				}
			}
		return false;
private java.lang.StringexpandEntities(java.lang.String src)

		int refStart = -1;
		int len = src.length();
		char[] dst = new char[len];
		int dstlen = 0;
		for (int i = 0; i < len; i++) {
			char ch = src.charAt(i);
			dst[dstlen++] = ch;
//			System.err.print("i = " + i + ", d = " + dstlen + ", ch = [" + ch + "] ");
			if (ch == '&" && refStart == -1) {
				// start of a ref excluding &
				refStart = dstlen;
//				System.err.println("start of ref");
				}
			else if (refStart == -1) {
				// not in a ref
//				System.err.println("not in ref");
				}
			else if (Character.isLetter(ch) ||
					Character.isDigit(ch) ||
					ch == '#") {
				// valid entity char
//				System.err.println("valid");
				}
			else if (ch == ';") {
				// properly terminated ref
//				System.err.print("got [" + new String(dst, refStart, dstlen-refStart-1) + "]");
				int ent = lookupEntity(dst, refStart, dstlen - refStart - 1);
//				System.err.println(" = " + ent);
				if (ent > 0xFFFF) {
					ent -= 0x10000;
					dst[refStart - 1] = (char)((ent>>10) + 0xD800);
					dst[refStart] = (char)((ent&0x3FF) + 0xDC00);
					dstlen = refStart + 1;
					}
				else if (ent != 0) {
					dst[refStart - 1] = (char)ent;
					dstlen = refStart;
					}
				refStart = -1;
				}
			else {
				// improperly terminated ref
//				System.err.println("end of ref");
				refStart = -1;
				}
			}
		return new String(dst, 0, dstlen);
private booleanforeign(java.lang.String prefix, java.lang.String namespace)

//		System.err.print("%% Testing " + prefix + " and " + namespace + " for foreignness -- ");
		boolean foreign = !(prefix.equals("") || namespace.equals("") ||
			namespace.equals(theSchema.getURI()));
//		System.err.println(foreign);
		return foreign;
public org.xml.sax.ContentHandlergetContentHandler()

		return (theContentHandler == this) ? null : theContentHandler;
public org.xml.sax.DTDHandlergetDTDHandler()

		return (theDTDHandler == this) ? null : theDTDHandler;
public intgetEntity()

		return theEntity;
public org.xml.sax.EntityResolvergetEntityResolver()

		return (theEntityResolver == this) ? null : theEntityResolver;
public org.xml.sax.ErrorHandlergetErrorHandler()

		return (theErrorHandler == this) ? null : theErrorHandler;
public booleangetFeature(java.lang.String name)

		Boolean b = (Boolean)theFeatures.get(name);
		if (b == null) {
			throw new SAXNotRecognizedException("Unknown feature " + name);
			}
		return b.booleanValue();
private java.io.InputStreamgetInputStream(java.lang.String publicid, java.lang.String systemid)

		URL basis = new URL("file", "", System.getProperty("user.dir") + "/.");
		URL url = new URL(basis, systemid);
		URLConnection c = url.openConnection();
		return c.getInputStream();
public java.lang.ObjectgetProperty(java.lang.String name)

		if (name.equals(lexicalHandlerProperty)) {
			return theLexicalHandler == this ? null : theLexicalHandler;
			}
		else if (name.equals(scannerProperty)) {
			return theScanner;
			}
		else if (name.equals(schemaProperty)) {
			return theSchema;
			}
		else if (name.equals(autoDetectorProperty)) {
			return theAutoDetector;
			}
		else {
			throw new SAXNotRecognizedException("Unknown property " + name);
			}
private java.io.ReadergetReader(org.xml.sax.InputSource s)

		Reader r = s.getCharacterStream();
		InputStream i = s.getByteStream();
		String encoding = s.getEncoding();
		String publicid = s.getPublicId();
		String systemid = s.getSystemId();
		if (r == null) {
			if (i == null) i = getInputStream(publicid, systemid);
//			i = new BufferedInputStream(i);
			if (encoding == null) {
				r = theAutoDetector.autoDetectingReader(i);
				}
			else {
				try {
					r = new InputStreamReader(i, encoding);
					}
				catch (UnsupportedEncodingException e) {
					r = new InputStreamReader(i);
					}
				}
			}
//		r = new BufferedReader(r);
		return r;
public voidgi(char[] buff, int offset, int length)

		if (theNewElement != null) return;
		String name = makeName(buff, offset, length);
		if (name == null) return;
		ElementType type = theSchema.getElementType(name);
		if (type == null) {
			// Suppress unknown elements if ignore-bogons is on
			if (ignoreBogons) return;
			int bogonModel = bogonsEmpty ? Schema.M_EMPTY : Schema.M_ANY;
			int bogonMemberOf = rootBogons ? Schema.M_ANY : (Schema.M_ANY & ~ Schema.M_ROOT);
			theSchema.elementType(name, bogonModel, bogonMemberOf, 0);
			if (!rootBogons) theSchema.parent(name, theSchema.rootElementType().name());
			type = theSchema.getElementType(name);
			}

		theNewElement = new Element(type, defaultAttributes);
//		System.err.println("%% Got GI " + theNewElement.name());
private intlookupEntity(char[] buff, int offset, int length)

		int result = 0;
		if (length < 1) return result;
//		System.err.println("%% Entity at " + offset + " " + length);
//		System.err.println("%% Got entity [" + new String(buff, offset, length) + "]");
		if (buff[offset] == '#") {
                        if (length > 1 && (buff[offset+1] == 'x"
                                        || buff[offset+1] == 'X")) {
                                try {
                                        return Integer.parseInt(new String(buff, offset + 2, length - 2), 16);
                                        }
                                catch (NumberFormatException e) { return 0; }
                                }
                        try {
                                return Integer.parseInt(new String(buff, offset + 1, length - 1), 10);
                                }
                        catch (NumberFormatException e) { return 0; }
                        }
		return theSchema.getEntity(new String(buff, offset, length));
private java.lang.StringmakeName(char[] buff, int offset, int length)

		StringBuffer dst = new StringBuffer(length + 2);
		boolean seenColon = false;
		boolean start = true;
//		String src = new String(buff, offset, length); // DEBUG
		for (; length-- > 0; offset++) {
			char ch = buff[offset];
			if (Character.isLetter(ch) || ch == '_") {
				start = false;
				dst.append(ch);
				}
			else if (Character.isDigit(ch) || ch == '-" || ch == '.") {
				if (start) dst.append('_");
				start = false;
				dst.append(ch);
				}
			else if (ch == ':" && !seenColon) {
				seenColon = true;
				if (start) dst.append('_");
				start = true;
				dst.append(translateColons ? '_" : ch);
				}
			}
		int dstLength = dst.length();
		if (dstLength == 0 || dst.charAt(dstLength - 1) == ':") dst.append('_");
//		System.err.println("Made name \"" + dst + "\" from \"" + src + "\"");
		return dst.toString().intern();
public voidparse(org.xml.sax.InputSource input)

		setup();
		Reader r = getReader(input);
		theContentHandler.startDocument();
		theScanner.resetDocumentLocator(input.getPublicId(), input.getSystemId());
		if (theScanner instanceof Locator) {
			theContentHandler.setDocumentLocator((Locator)theScanner);
			}
		if (!(theSchema.getURI().equals("")))
			theContentHandler.startPrefixMapping(theSchema.getPrefix(),
				theSchema.getURI());
		theScanner.scan(r, this);
public voidparse(java.lang.String systemid)

		parse(new InputSource(systemid));
public voidpcdata(char[] buff, int offset, int length)

		if (length == 0) return;
		boolean allWhite = true;
		for (int i = 0; i < length; i++) {
			if (!Character.isWhitespace(buff[offset+i])) {
				allWhite = false;
				}
			}
		if (allWhite && !theStack.canContain(thePCDATA)) {
			if (ignorableWhitespace) {
				theContentHandler.ignorableWhitespace(buff, offset, length);
				}
			}
		else {
			rectify(thePCDATA);
			theContentHandler.characters(buff, offset, length);
			}
public voidpi(char[] buff, int offset, int length)

		if (theNewElement != null || thePITarget == null) return;
		if ("xml".equalsIgnoreCase(thePITarget)) return;
//		if (length > 0 && buff[length - 1] == '?') System.err.println("%% Removing ? from PI");
		if (length > 0 && buff[length - 1] == '?") length--;	// remove trailing ?
		theContentHandler.processingInstruction(thePITarget,
			new String(buff, offset, length));
		thePITarget = null;
public voidpitarget(char[] buff, int offset, int length)

		if (theNewElement != null) return;
		thePITarget = makeName(buff, offset, length).replace(':", '_");
private voidpop()

		if (theStack == null) return;		// empty stack
		String name = theStack.name();
		String localName = theStack.localName();
		String namespace = theStack.namespace();
		String prefix = prefixOf(name);

//		System.err.println("%% Popping " + name);
		if (!namespaces) namespace = localName = "";
		theContentHandler.endElement(namespace, localName, name);
		if (foreign(prefix, namespace)) {
			theContentHandler.endPrefixMapping(prefix);
//			System.err.println("%% Unmapping [" + prefix + "] for elements to " + namespace);
			}
		Attributes atts = theStack.atts();
		for (int i = atts.getLength() - 1; i >= 0; i--) {
			String attNamespace = atts.getURI(i);
			String attPrefix = prefixOf(atts.getQName(i));
			if (foreign(attPrefix, attNamespace)) {
				theContentHandler.endPrefixMapping(attPrefix);
//			System.err.println("%% Unmapping [" + attPrefix + "] for attributes to " + attNamespace);
				}
			}
		theStack = theStack.next();
private java.lang.StringprefixOf(java.lang.String name)

		int i = name.indexOf(':");
		String prefix = "";
		if (i != -1) prefix = name.substring(0, i);
//		System.err.println("%% " + prefix + " is prefix of " + name);
		return prefix;
private voidpush(Element e)

	      
		String name = e.name();
		String localName = e.localName();
		String namespace = e.namespace();
		String prefix = prefixOf(name);

//		System.err.println("%% Pushing " + name);
		e.clean();
		if (!namespaces) namespace = localName = "";
                if (virginStack && localName.equalsIgnoreCase(theDoctypeName)) {
                    try {
                        theEntityResolver.resolveEntity(theDoctypePublicId, theDoctypeSystemId);
                    } catch (IOException ew) { }   // Can't be thrown for root I believe.
                }
		if (foreign(prefix, namespace)) {
			theContentHandler.startPrefixMapping(prefix, namespace);
//			System.err.println("%% Mapping [" + prefix + "] for elements to " + namespace);
			}
		Attributes atts = e.atts();
		int len = atts.getLength();
		for (int i = 0; i < len; i++) {
			String attNamespace = atts.getURI(i);
			String attPrefix = prefixOf(atts.getQName(i));
			if (foreign(attPrefix, attNamespace)) {
				theContentHandler.startPrefixMapping(attPrefix, attNamespace);
//				System.err.println("%% Mapping [" + attPrefix + "] for attributes to " + attNamespace);
				}
			}
		theContentHandler.startElement(namespace, localName, name, e.atts());
		e.setNext(theStack);
		theStack = e;
		virginStack = false;
		if (CDATAElements && (theStack.flags() & Schema.F_CDATA) != 0) {
			theScanner.startCDATA();
			}
private voidrectify(Element e)

		Element sp;
		while (true) {
			for (sp = theStack; sp != null; sp = sp.next()) {
				if (sp.canContain(e)) break;
				}
			if (sp != null) break;
			ElementType parentType = e.parent();
			if (parentType == null) break;
			Element parent = new Element(parentType, defaultAttributes);
//			System.err.println("%% Ascending from " + e.name() + " to " + parent.name());
			parent.setNext(e);
			e = parent;
			}
		if (sp == null) return;		// don't know what to do
		while (theStack != sp) {
			if (theStack == null || theStack.next() == null ||
				theStack.next().next() == null) break;
			restartablyPop();
			}
		while (e != null) {
			Element nexte = e.next();
			if (!e.name().equals("<pcdata>")) push(e);
			e = nexte;
			restart(e);
			}
		theNewElement = null;
private voidrestart(Element e)

		while (theSaved != null && theStack.canContain(theSaved) &&
				(e == null || theSaved.canContain(e))) {
			Element next = theSaved.next();
			push(theSaved);
			theSaved = next;
			}
private voidrestartablyPop()

		Element popped = theStack;
		pop();
		if (restartElements && (popped.flags() & Schema.F_RESTART) != 0) {
			popped.anonymize();
			popped.setNext(theSaved);
			theSaved = popped;
			}
public voidsetContentHandler(org.xml.sax.ContentHandler handler)

		theContentHandler = (handler == null) ? this : handler;
public voidsetDTDHandler(org.xml.sax.DTDHandler handler)

		theDTDHandler = (handler == null) ? this : handler;
public voidsetEntityResolver(org.xml.sax.EntityResolver resolver)

		theEntityResolver = (resolver == null) ? this : resolver;
public voidsetErrorHandler(org.xml.sax.ErrorHandler handler)

		theErrorHandler = (handler == null) ? this : handler;
public voidsetFeature(java.lang.String name, boolean value)

		Boolean b = (Boolean)theFeatures.get(name);
		if (b == null) {
			throw new SAXNotRecognizedException("Unknown feature " + name);
			}
		if (value) theFeatures.put(name, Boolean.TRUE);
		else theFeatures.put(name, Boolean.FALSE);

		if (name.equals(namespacesFeature)) namespaces = value;
		else if (name.equals(ignoreBogonsFeature)) ignoreBogons = value;
		else if (name.equals(bogonsEmptyFeature)) bogonsEmpty = value;
		else if (name.equals(rootBogonsFeature)) rootBogons = value;
		else if (name.equals(defaultAttributesFeature)) defaultAttributes = value;
		else if (name.equals(translateColonsFeature)) translateColons = value;
		else if (name.equals(restartElementsFeature)) restartElements = value;
		else if (name.equals(ignorableWhitespaceFeature)) ignorableWhitespace = value;
		else if (name.equals(CDATAElementsFeature)) CDATAElements = value;
public voidsetProperty(java.lang.String name, java.lang.Object value)

		if (name.equals(lexicalHandlerProperty)) {
			if (value == null) {
				theLexicalHandler = this;
				}
			else if (value instanceof LexicalHandler) {
				theLexicalHandler = (LexicalHandler)value;
				}
			else {
				throw new SAXNotSupportedException("Your lexical handler is not a LexicalHandler");
				}
			}
		else if (name.equals(scannerProperty)) {
			if (value instanceof Scanner) {
				theScanner = (Scanner)value;
				}
			else {
				throw new SAXNotSupportedException("Your scanner is not a Scanner");
				}
			}
		else if (name.equals(schemaProperty)) {
			if (value instanceof Schema) {
				theSchema = (Schema)value;
				}
			else {
				 throw new SAXNotSupportedException("Your schema is not a Schema");
				}
			}
		else if (name.equals(autoDetectorProperty)) {
			if (value instanceof AutoDetector) {
				theAutoDetector = (AutoDetector)value;
				}
			else {
				throw new SAXNotSupportedException("Your auto-detector is not an AutoDetector");
				}
			}
		else {
			throw new SAXNotRecognizedException("Unknown property " + name);
			}
private voidsetup()

		if (theSchema == null) theSchema = new HTMLSchema();
		if (theScanner == null) theScanner = new HTMLScanner();
		if (theAutoDetector == null) {
			theAutoDetector = new AutoDetector() {
				public Reader autoDetectingReader(InputStream i) {
					return new InputStreamReader(i);
					}
				};
			}
		theStack = new Element(theSchema.getElementType("<root>"), defaultAttributes);
		thePCDATA = new Element(theSchema.getElementType("<pcdata>"), defaultAttributes);
		theNewElement = null;
		theAttributeName = null;
		thePITarget = null;
		theSaved = null;
		theEntity = 0;
		virginStack = true;
                theDoctypeName = theDoctypePublicId = theDoctypeSystemId = null;
private static java.lang.String[]split(java.lang.String val)

		val = val.trim();
		if (val.length() == 0) {
			return new String[0];
			}
		else {
			ArrayList l = new ArrayList();
			int s = 0;
			int e = 0;
			boolean sq = false;	// single quote
			boolean dq = false;	// double quote
			char lastc = 0;
			int len = val.length();
			for (e=0; e < len; e++) {
				char c = val.charAt(e);
				if (!dq && c == '\'" && lastc != '\\") {
				sq = !sq;
				if (s < 0) s = e;
				}
			else if (!sq && c == '\"" && lastc != '\\") {
				dq = !dq;
				if (s < 0) s = e;
				}
			else if (!sq && !dq) {
				if (Character.isWhitespace(c)) {
					if (s >= 0) l.add(val.substring(s, e));
					s = -1;
					}
				else if (s < 0 && c != ' ") {
					s = e;
					}
				}
			lastc = c;
			}
		l.add(val.substring(s, e));
		return (String[])l.toArray(new String[0]);
		}
public voidstagc(char[] buff, int offset, int length)

//		System.err.println("%% Start-tag");
		if (theNewElement == null) return;
		rectify(theNewElement);
		if (theStack.model() == Schema.M_EMPTY) {
			// Force an immediate end tag
			etag_basic(buff, offset, length);
			}
public voidstage(char[] buff, int offset, int length)

//		System.err.println("%% Empty-tag");
		if (theNewElement == null) return;
		rectify(theNewElement);
		// Force an immediate end tag
		etag_basic(buff, offset, length);
public voidstartCDATA()
public voidstartDTD(java.lang.String name, java.lang.String publicid, java.lang.String systemid)
public voidstartEntity(java.lang.String name)
private static java.lang.Stringtrimquotes(java.lang.String in)

		if (in == null) return in;
		int length = in.length();
		if (length == 0) return in;
		char s = in.charAt(0);
		char e = in.charAt(length - 1);
		if (s == e && (s == '\'" || s == '"")) {
			in = in.substring(1, in.length() - 1);
			}
		return in;
private static java.lang.BooleantruthValue(boolean b)

	
		theFeatures.put(namespacesFeature, truthValue(DEFAULT_NAMESPACES));
		theFeatures.put(namespacePrefixesFeature, Boolean.FALSE);
		theFeatures.put(externalGeneralEntitiesFeature, Boolean.FALSE);
		theFeatures.put(externalParameterEntitiesFeature, Boolean.FALSE);
		theFeatures.put(isStandaloneFeature, Boolean.FALSE);
		theFeatures.put(lexicalHandlerParameterEntitiesFeature,
			Boolean.FALSE);
		theFeatures.put(resolveDTDURIsFeature, Boolean.TRUE);
		theFeatures.put(stringInterningFeature, Boolean.TRUE);
		theFeatures.put(useAttributes2Feature, Boolean.FALSE);
		theFeatures.put(useLocator2Feature, Boolean.FALSE);
		theFeatures.put(useEntityResolver2Feature, Boolean.FALSE);
		theFeatures.put(validationFeature, Boolean.FALSE);
		theFeatures.put(xmlnsURIsFeature, Boolean.FALSE);
		theFeatures.put(xmlnsURIsFeature, Boolean.FALSE);
		theFeatures.put(XML11Feature, Boolean.FALSE);
		theFeatures.put(ignoreBogonsFeature, truthValue(DEFAULT_IGNORE_BOGONS));
		theFeatures.put(bogonsEmptyFeature, truthValue(DEFAULT_BOGONS_EMPTY));
		theFeatures.put(rootBogonsFeature, truthValue(DEFAULT_ROOT_BOGONS));
		theFeatures.put(defaultAttributesFeature, truthValue(DEFAULT_DEFAULT_ATTRIBUTES));
		theFeatures.put(translateColonsFeature, truthValue(DEFAULT_TRANSLATE_COLONS));
		theFeatures.put(restartElementsFeature, truthValue(DEFAULT_RESTART_ELEMENTS));
		theFeatures.put(ignorableWhitespaceFeature, truthValue(DEFAULT_IGNORABLE_WHITESPACE));
		theFeatures.put(CDATAElementsFeature, truthValue(DEFAULT_CDATA_ELEMENTS));
		
		return b ? Boolean.TRUE : Boolean.FALSE;