xml11nsdocumentscannerimpl.java

java1.6众多例子参考

/*
 * The Apache Software License, Version 1.1
 *
 *
 * Copyright (c) 1999-2003 The Apache Software Foundation.
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Xerces" and "Apache Software Foundation" must
 *    not be used to endorse or promote products derived from this
 *    software without prior written permission. For written
 *    permission, please contact [e-mail].
 *
 * 5. Products derived from this software may not be called "Apache",
 *    nor may "Apache" appear in their name, without prior written
 *    permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation and was
 * originally based on software copyright (c) 2002, International
 * Business Machines, Inc., http://www.apache.org.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 */

package com.sun.org.apache.xerces.internal.impl;

import java.io.IOException;

import com.sun.org.apache.xerces.internal.impl.dtd.XMLDTDValidatorFilter;
import com.sun.org.apache.xerces.internal.impl.msg.XMLMessageFormatter;
import com.sun.org.apache.xerces.internal.util.XMLAttributesImpl;
import com.sun.org.apache.xerces.internal.util.XMLSymbols;
import com.sun.org.apache.xerces.internal.xni.NamespaceContext;
import com.sun.org.apache.xerces.internal.xni.QName;
import com.sun.org.apache.xerces.internal.xni.XMLDocumentHandler;
import com.sun.org.apache.xerces.internal.xni.XNIException;
import com.sun.org.apache.xerces.internal.xni.parser.XMLComponentManager;
import com.sun.org.apache.xerces.internal.xni.parser.XMLConfigurationException;
import com.sun.org.apache.xerces.internal.xni.parser.XMLDocumentSource;
import javax.xml.stream.events.XMLEvent;


/**
 * The scanner acts as the source for the document
 * information which is communicated to the document handler.
 *
 * This class scans an XML document, checks if document has a DTD, and if
 * DTD is not found the scanner will remove the DTD Validator from the pipeline and perform
 * namespace binding.
 *
 * Note: This scanner should only be used when the namespace processing is on!
 *
 * <p>
 * This component requires the following features and properties from the
 * component manager that uses it:
 * <ul>
 *  <li>http://xml.org/sax/features/namespaces {true} -- if the value of this
 *      feature is set to false this scanner must not be used.</li>
 *  <li>http://xml.org/sax/features/validation</li>
 *  <li>http://apache.org/xml/features/nonvalidating/load-external-dtd</li>
 *  <li>http://apache.org/xml/features/scanner/notify-char-refs</li>
 *  <li>http://apache.org/xml/features/scanner/notify-builtin-refs</li>
 *  <li>http://apache.org/xml/properties/internal/symbol-table</li>
 *  <li>http://apache.org/xml/properties/internal/error-reporter</li>
 *  <li>http://apache.org/xml/properties/internal/entity-manager</li>
 *  <li>http://apache.org/xml/properties/internal/dtd-scanner</li>
 * </ul>
 * 
 * @xerces.internal
 *
 * @author Elena Litani, IBM
 * @author Michael Glavassevich, IBM
 * @author Sunitha Reddy, Sun Microsystems
 * @version $Id: XML11NSDocumentScannerImpl.java,v 1.3 2005/10/03 14:55:33 sunithareddy Exp $
 */
public class XML11NSDocumentScannerImpl extends XML11DocumentScannerImpl {

    /** 
     * If is true, the dtd validator is no longer in the pipeline
     * and the scanner should bind namespaces 
     */
    protected boolean fBindNamespaces;

    /** 
     * If validating parser, make sure we report an error in the
     *  scanner if DTD grammar is missing.
     */
    protected boolean fPerformValidation;

    // private data
    //

    /** DTD validator */
    private XMLDTDValidatorFilter fDTDValidator;
    
    /** 
     * Saw spaces after element name or between attributes.
     * 
     * This is reserved for the case where scanning of a start element spans
     * several methods, as is the case when scanning the start of a root element 
     * where a DTD external subset may be read after scanning the element name.
     */
    private boolean fSawSpace;

    
    /**
     * The scanner is responsible for removing DTD validator
     * from the pipeline if it is not needed.
     * 
     * @param validator the DTD validator from the pipeline
     */
    public void setDTDValidator(XMLDTDValidatorFilter validator) {
        fDTDValidator = validator;
    }

    /**
     * Scans a start element. This method will handle the binding of
     * namespace information and notifying the handler of the start
     * of the element.
     * <p>
     * <pre>
     * [44] EmptyElemTag ::= '&lt;' Name (S Attribute)* S? '/>'
     * [40] STag ::= '&lt;' Name (S Attribute)* S? '>'
     * </pre>
     * <p>
     * <strong>Note:</strong> This method assumes that the leading
     * '&lt;' character has been consumed.
     * <p>
     * <strong>Note:</strong> This method uses the fElementQName and
     * fAttributes variables. The contents of these variables will be
     * destroyed. The caller should copy important information out of
     * these variables before calling this method.
     *
     * @return True if element is empty. (i.e. It matches
     *          production [44].
     */
    protected boolean scanStartElement() throws IOException, XNIException {
        
        if (DEBUG_START_END_ELEMENT)
            System.out.println(">>> scanStartElementNS()");
                // Note: namespace processing is on by default
        fEntityScanner.scanQName(fElementQName);
        // REVISIT - [Q] Why do we need this local variable? -- mrglavas
        String rawname = fElementQName.rawname;
        if (fBindNamespaces) {
            fNamespaceContext.pushContext();
            if (fScannerState == SCANNER_STATE_ROOT_ELEMENT) {
                if (fPerformValidation) {
                    fErrorReporter.reportError(
                        XMLMessageFormatter.XML_DOMAIN,
                        "MSG_GRAMMAR_NOT_FOUND",
                        new Object[] { rawname },
                        XMLErrorReporter.SEVERITY_ERROR);

                    if (fDoctypeName == null
                        || !fDoctypeName.equals(rawname)) {
                        fErrorReporter.reportError(
                            XMLMessageFormatter.XML_DOMAIN,
                            "RootElementTypeMustMatchDoctypedecl",
                            new Object[] { fDoctypeName, rawname },
                            XMLErrorReporter.SEVERITY_ERROR);
                    }
                }
            }
        }

        // push element stack
        fCurrentElement = fElementStack.pushElement(fElementQName);

        // attributes
        boolean empty = false;
        fAttributes.removeAllAttributes();
        do {
            // spaces
            boolean sawSpace = fEntityScanner.skipSpaces();

            // end tag?
            int c = fEntityScanner.peekChar();
            if (c == '>') {
                fEntityScanner.scanChar();
                break;
            } else if (c == '/') {
                fEntityScanner.scanChar();
                if (!fEntityScanner.skipChar('>')) {
                    reportFatalError(
                        "ElementUnterminated",
                        new Object[] { rawname });
                }
                empty = true;
                break;
            } else if (!isValidNameStartChar(c) || !sawSpace) {
                // Second chance. Check if this character is a high
                // surrogate of a valid name start character.
                if (!isValidNameStartHighSurrogate(c) || !sawSpace) {
                    reportFatalError(
                        "ElementUnterminated",
                        new Object[] { rawname });
                }
            }

            // attributes
            scanAttribute(fAttributes);
            if (fSecurityManager != null && fAttributes.getLength() > fElementAttributeLimit){                
                fErrorReporter.reportError(XMLMessageFormatter.XML_DOMAIN,
                                             "ElementAttributeLimit",
                                             new Object[]{rawname, new Integer(fElementAttributeLimit) },
                                             XMLErrorReporter.SEVERITY_FATAL_ERROR );
            }           

        } while (true);

        if (fBindNamespaces) {
            // REVISIT: is it required? forbit xmlns prefix for element
            if (fElementQName.prefix == XMLSymbols.PREFIX_XMLNS) {
                fErrorReporter.reportError(
                    XMLMessageFormatter.XMLNS_DOMAIN,
                    "ElementXMLNSPrefix",
                    new Object[] { fElementQName.rawname },
                    XMLErrorReporter.SEVERITY_FATAL_ERROR);
            }

            // bind the element
            String prefix =
                fElementQName.prefix != null
                    ? fElementQName.prefix
                    : XMLSymbols.EMPTY_STRING;
            // assign uri to the element
            fElementQName.uri = fNamespaceContext.getURI(prefix);
            // make sure that object in the element stack is updated as well
            fCurrentElement.uri = fElementQName.uri;

            if (fElementQName.prefix == null && fElementQName.uri != null) {
                fElementQName.prefix = XMLSymbols.EMPTY_STRING;
                // making sure that the object in the element stack is updated too.
                fCurrentElement.prefix = XMLSymbols.EMPTY_STRING;
            }
            if (fElementQName.prefix != null && fElementQName.uri == null) {
                fErrorReporter.reportError(
                    XMLMessageFormatter.XMLNS_DOMAIN,
                    "ElementPrefixUnbound",
                    new Object[] {
                        fElementQName.prefix,
                        fElementQName.rawname },
                    XMLErrorReporter.SEVERITY_FATAL_ERROR);
            }

            // bind attributes (xmlns are already bound bellow)
            int length = fAttributes.getLength();
            for (int i = 0; i < length; i++) {
                fAttributes.getName(i, fAttributeQName);

                String aprefix =
                    fAttributeQName.prefix != null
                        ? fAttributeQName.prefix
                        : XMLSymbols.EMPTY_STRING;
                String uri = fNamespaceContext.getURI(aprefix);
                // REVISIT: try removing the first "if" and see if it is faster.
                //
                if (fAttributeQName.uri != null
                    && fAttributeQName.uri == uri) {
                    continue;
                }
                if (aprefix != XMLSymbols.EMPTY_STRING) {
                    fAttributeQName.uri = uri;
                    if (uri == null) {
                        fErrorReporter.reportError(
                            XMLMessageFormatter.XMLNS_DOMAIN,
                            "AttributePrefixUnbound",
                            new Object[] {
                                fElementQName.rawname,
                                fAttributeQName.rawname,
                                aprefix },
                            XMLErrorReporter.SEVERITY_FATAL_ERROR);
                    }
                    fAttributes.setURI(i, uri);