xmlentityscanner.java

来自「JAVA的一些源码 JAVA2 STANDARD EDITION DEVELO」· Java 代码 · 共 1,660 行 · 第 1/5 页

/*
 * 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) 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.EOFException;
import java.io.IOException;
import java.util.Locale;

import com.sun.org.apache.xerces.internal.impl.io.UCSReader;
import com.sun.org.apache.xerces.internal.impl.msg.XMLMessageFormatter;
import com.sun.org.apache.xerces.internal.util.SymbolTable;
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.QName;
import com.sun.org.apache.xerces.internal.xni.XMLLocator;
import com.sun.org.apache.xerces.internal.xni.XMLString;

/**
 * Implements the entity scanner methods.
 *
 * @author Andy Clark, IBM
 * @author Neil Graham, IBM
 * @version $Id: XMLEntityScanner.java,v 1.19 2003/11/13 18:45:59 mrglavas Exp $
 */

public class XMLEntityScanner implements XMLLocator {

    // constants
    private static final boolean DEBUG_ENCODINGS = false;
    private static final boolean DEBUG_BUFFER = false;

    //
    // Data
    //

    private XMLEntityManager fEntityManager = null;
    protected XMLEntityManager.ScannedEntity fCurrentEntity = null;

    protected SymbolTable fSymbolTable = null;

    protected int fBufferSize = XMLEntityManager.DEFAULT_BUFFER_SIZE;

    /**
     * Error reporter. This property identifier is:
     * http://apache.org/xml/properties/internal/error-reporter
     */
    protected XMLErrorReporter fErrorReporter;
    //
    // Constructors
    //

    /** Default constructor. */
    public XMLEntityScanner() {
    } // <init>()

    //
    // XMLEntityScanner methods
    //

    /**
     * Returns the base system identifier of the currently scanned
     * entity, or null if none is available.
     */
    public String getBaseSystemId() {
        return (fCurrentEntity != null && fCurrentEntity.entityLocation != null) ? fCurrentEntity.entityLocation.getExpandedSystemId() : null;
    } // getBaseSystemId():String

    /**
     * Sets the encoding of the scanner. This method is used by the
     * scanners if the XMLDecl or TextDecl line contains an encoding
     * pseudo-attribute.
     * <p>
     * <strong>Note:</strong> The underlying character reader on the
     * current entity will be changed to accomodate the new encoding.
     * However, the new encoding is ignored if the current reader was
     * not constructed from an input stream (e.g. an external entity
     * that is resolved directly to the appropriate java.io.Reader
     * object).
     *
     * @param encoding The IANA encoding name of the new encoding.
     *
     * @throws IOException Thrown if the new encoding is not supported.
     *
     * @see com.sun.org.apache.xerces.internal.util.EncodingMap
     */
    public void setEncoding(String encoding) throws IOException {

        if (DEBUG_ENCODINGS) {
            System.out.println("$$$ setEncoding: "+encoding);
        }

        if (fCurrentEntity.stream != null) {
            // if the encoding is the same, don't change the reader and
            // re-use the original reader used by the OneCharReader
            // NOTE: Besides saving an object, this overcomes deficiencies
            //       in the UTF-16 reader supplied with the standard Java
            //       distribution (up to and including 1.3). The UTF-16
            //       decoder buffers 8K blocks even when only asked to read
            //       a single char! -Ac
            if (fCurrentEntity.encoding == null ||
                !fCurrentEntity.encoding.equals(encoding)) {
                // UTF-16 is a bit of a special case.  If the encoding is UTF-16,
                // and we know the endian-ness, we shouldn't change readers.
                // If it's ISO-10646-UCS-(2|4), then we'll have to deduce
                // the endian-ness from the encoding we presently have.
                if(fCurrentEntity.encoding != null && fCurrentEntity.encoding.startsWith("UTF-16")) {
                    String ENCODING = encoding.toUpperCase(Locale.ENGLISH);
                    if(ENCODING.equals("UTF-16")) return;
                    if(ENCODING.equals("ISO-10646-UCS-4")) {
                        if(fCurrentEntity.encoding.equals("UTF-16BE")) {
                            fCurrentEntity.reader = new UCSReader(fCurrentEntity.stream, UCSReader.UCS4BE);
                        } else {
                            fCurrentEntity.reader = new UCSReader(fCurrentEntity.stream, UCSReader.UCS4LE);
                        }
                        return;
                    }
                    if(ENCODING.equals("ISO-10646-UCS-2")) {
                        if(fCurrentEntity.encoding.equals("UTF-16BE")) {
                            fCurrentEntity.reader = new UCSReader(fCurrentEntity.stream, UCSReader.UCS2BE);
                        } else {
                            fCurrentEntity.reader = new UCSReader(fCurrentEntity.stream, UCSReader.UCS2LE);
                        }
                        return;
                    }
                }
                // wrap a new reader around the input stream, changing
                // the encoding
                if (DEBUG_ENCODINGS) {
                    System.out.println("$$$ creating new reader from stream: "+
                                    fCurrentEntity.stream);
                }
                //fCurrentEntity.stream.reset();
                fCurrentEntity.setReader(fCurrentEntity.stream, encoding, null);
                fCurrentEntity.encoding = encoding;
            } else {
                if (DEBUG_ENCODINGS)
                    System.out.println("$$$ reusing old reader on stream");
            }
        }

    } // setEncoding(String)

    /** Returns true if the current entity being scanned is external. */
    public boolean isExternal() {
        return fCurrentEntity.isExternal();
    } // isExternal():boolean

    /**
     * Returns the next character on the input.
     * <p>
     * <strong>Note:</strong> The character is <em>not</em> consumed.
     *
     * @throws IOException  Thrown if i/o error occurs.
     * @throws EOFException Thrown on end of file.
     */
    public int peekChar() throws IOException {
        if (DEBUG_BUFFER) {
            System.out.print("(peekChar: ");
            XMLEntityManager.print(fCurrentEntity);
            System.out.println();
        }

        // load more characters, if needed
        if (fCurrentEntity.position == fCurrentEntity.count) {
            load(0, true);
        }

        // peek at character
        int c = fCurrentEntity.ch[fCurrentEntity.position];

        // return peeked character
        if (DEBUG_BUFFER) {
            System.out.print(")peekChar: ");
            XMLEntityManager.print(fCurrentEntity);
            if (fCurrentEntity.isExternal()) {
                System.out.println(" -> '"+(c!='\r'?(char)c:'\n')+"'");
            }
            else {
                System.out.println(" -> '"+(char)c+"'");
            }
        }
        if (fCurrentEntity.isExternal()) {
            return c != '\r' ? c : '\n';
        }
        else {
            return c;
        }

    } // peekChar():int

    /**
     * Returns the next character on the input.
     * <p>
     * <strong>Note:</strong> The character is consumed.
     *
     * @throws IOException  Thrown if i/o error occurs.
     * @throws EOFException Thrown on end of file.
     */
    public int scanChar() throws IOException {
        if (DEBUG_BUFFER) {
            System.out.print("(scanChar: ");
            XMLEntityManager.print(fCurrentEntity);
            System.out.println();
        }

        // load more characters, if needed
        if (fCurrentEntity.position == fCurrentEntity.count) {
            load(0, true);
        }

        // scan character
        int c = fCurrentEntity.ch[fCurrentEntity.position++];
        boolean external = false;
        if (c == '\n' ||
            (c == '\r' && (external = fCurrentEntity.isExternal()))) {
            fCurrentEntity.lineNumber++;
            fCurrentEntity.columnNumber = 1;
            if (fCurrentEntity.position == fCurrentEntity.count) {
                fCurrentEntity.ch[0] = (char)c;
                load(1, false);
            }
            if (c == '\r' && external) {
                if (fCurrentEntity.ch[fCurrentEntity.position++] != '\n') {
                    fCurrentEntity.position--;
                }
                c = '\n';
            }
        }

        // return character that was scanned
        if (DEBUG_BUFFER) {
            System.out.print(")scanChar: ");
            XMLEntityManager.print(fCurrentEntity);
            System.out.println(" -> '"+(char)c+"'");
        }
        fCurrentEntity.columnNumber++;
        return c;

    } // scanChar():int

    /**
     * Returns a string matching the NMTOKEN production appearing immediately
     * on the input as a symbol, or null if NMTOKEN Name string is present.
     * <p>
     * <strong>Note:</strong> The NMTOKEN characters are consumed.
     * <p>
     * <strong>Note:</strong> The string returned must be a symbol. The
     * SymbolTable can be used for this purpose.
     *
     * @throws IOException  Thrown if i/o error occurs.
     * @throws EOFException Thrown on end of file.
     *
     * @see com.sun.org.apache.xerces.internal.util.SymbolTable
     * @see com.sun.org.apache.xerces.internal.util.XMLChar#isName
     */
    public String scanNmtoken() throws IOException {
        if (DEBUG_BUFFER) {
            System.out.print("(scanNmtoken: ");
            XMLEntityManager.print(fCurrentEntity);
            System.out.println();
        }

        // load more characters, if needed
        if (fCurrentEntity.position == fCurrentEntity.count) {
            load(0, true);
        }

        // scan nmtoken
        int offset = fCurrentEntity.position;
        while (XMLChar.isName(fCurrentEntity.ch[fCurrentEntity.position])) {
            if (++fCurrentEntity.position == fCurrentEntity.count) {
                int length = fCurrentEntity.position - offset;
                if (length == fCurrentEntity.ch.length) {
                    // bad luck we have to resize our buffer
                    char[] tmp = new char[fCurrentEntity.ch.length << 1];
                    System.arraycopy(fCurrentEntity.ch, offset,
                                     tmp, 0, length);