xml11documentscannerimpl.java

java1.6众多例子参考

/*
 * The Apache Software License, Version 1.1
 *
 *
 * Copyright (c) 1999-2004 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) 1999, 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.msg.XMLMessageFormatter;
import com.sun.org.apache.xerces.internal.util.XML11Char;
import com.sun.org.apache.xerces.internal.util.XMLChar;
import com.sun.org.apache.xerces.internal.util.XMLStringBuffer;
import com.sun.org.apache.xerces.internal.xni.XMLString;
import com.sun.org.apache.xerces.internal.xni.XNIException;

/**
 * This class is responsible for scanning XML document structure
 * and content. The scanner acts as the source for the document
 * information which is communicated to the document handler.
 * <p>
 * This component requires the following features and properties from the
 * component manager that uses it:
 * <ul>
 *  <li>http://xml.org/sax/features/namespaces</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 Glenn Marcy, IBM
 * @author Andy Clark, IBM
 * @author Arnaud  Le Hors, IBM
 * @author Eric Ye, IBM
 *
 * @version $Id: XML11DocumentScannerImpl.java,v 1.2 2005/08/16 22:51:38 jeffsuttor Exp $
 */
public class XML11DocumentScannerImpl
    extends XMLDocumentScannerImpl {


    /** Array of 3 strings. */
    private String[] fStrings = new String[3];

    
    /** String buffer. */
    private XMLStringBuffer fStringBuffer = new XMLStringBuffer();
    private XMLStringBuffer fStringBuffer2 = new XMLStringBuffer();
    private XMLStringBuffer fStringBuffer3 = new XMLStringBuffer();

    //
    // Constructors
    //

    /** Default constructor. */
    public XML11DocumentScannerImpl() {super();} // <init>()

    //
    // overridden methods
    //

    // XMLDocumentFragmentImpl methods

    /**
     * Scans element content.
     *
     * @return Returns the next character on the stream.
     */
    protected int scanContent(XMLStringBuffer content) throws IOException, XNIException {
        
        fTempString.length = 0;
        int c = fEntityScanner.scanContent(fTempString);
        content.append(fTempString);
        
        if (c == '\r' || c == 0x85 || c == 0x2028) {
            // happens when there is the character reference &#13;
            // but scanContent doesn't do entity expansions...
            // is this *really* necessary???  - NG
            fEntityScanner.scanChar();
            content.append((char)c);
            c = -1;
        }
        /*if (fDocumentHandler != null && content.length > 0) {
            fDocumentHandler.characters(content, null);
        } */

        if (c == ']') {
            content.append((char)fEntityScanner.scanChar());
            // remember where we are in case we get an endEntity before we
            // could flush the buffer out - this happens when we're parsing an
            // entity which ends with a ]
            fInScanContent = true;
            //
            // We work on a single character basis to handle cases such as:
            // ']]]>' which we might otherwise miss.
            //
            if (fEntityScanner.skipChar(']')) {
                content.append(']'); 
                while (fEntityScanner.skipChar(']')) {
                    content.append(']'); 
                }
                if (fEntityScanner.skipChar('>')) {
                    reportFatalError("CDEndInContent", null);
                }
            }
            /*if (fDocumentHandler != null && fStringBuffer.length != 0) {
                fDocumentHandler.characters(fStringBuffer, null);
            }*/
            fInScanContent = false;
            c = -1;
        }
        return c;

    } // scanContent():int

    /**
     * Scans an attribute value and normalizes whitespace converting all
     * whitespace characters to space characters.
     * 
     * [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.
     *
     * @return true if the non-normalized and normalized value are the same
     * 
     * <strong>Note:</strong> This method uses fStringBuffer2, anything in it
     * at the time of calling is lost.
     **/
    protected boolean 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() + "\"");
        }
        
        int fromIndex = 0;
        if (c == quote && (fromIndex = isUnchangedByNormalization(value)) == -1) {
            /** Both the non-normalized and normalized attribute values are equal. **/
            nonNormalizedValue.setValues(value);
            int cquote = fEntityScanner.scanChar();
            if (cquote != quote) {
                reportFatalError("CloseQuoteExpected", new Object[]{eleName,atName});
            }
            return true;
        }
        fStringBuffer2.clear();
        fStringBuffer2.append(value);
        normalizeWhitespace(value, fromIndex);
        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()
                                                   + "\"");