xml11entityscanner.java

来自「JAVA 所有包」· Java 代码 · 共 1,525 行 · 第 1/5 页

/*
 * The Apache Software License, Version 1.1
 *
 *
 * Copyright (c) 1999-2002 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.XMLChar;
import com.sun.org.apache.xerces.internal.util.XML11Char;
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.XMLString;

/**
 * Implements the entity scanner methods in
 * the context of XML 1.1.
 *
 * @xerces.internal
 *
 * @author Michael Glavassevich, IBM
 * @author Neil Graham, IBM
 * @version $Id: XML11EntityScanner.java,v 1.2 2005/08/16 22:51:36 jeffsuttor Exp $
 */

public class XML11EntityScanner
    extends XMLEntityScanner {

    //
    // Constructors
    //

    /** Default constructor. */
    public XML11EntityScanner() {
        super();
    } // <init>()

    //
    // XMLEntityScanner methods
    //

    /**
     * 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 {

        // 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 (fCurrentEntity.isExternal()) {
            return (c != '\r' && c != 0x85 && c != 0x2028) ? 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 {

        // 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' || c == 0x85 || c == 0x2028) && (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) {
                int cc = fCurrentEntity.ch[fCurrentEntity.position++];
                if (cc != '\n' && cc != 0x85) {
                    fCurrentEntity.position--;
                }
            }
            c = '\n';
        }

        // return character that was scanned
        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.XML11Char#isXML11Name
     */
    public String scanNmtoken() throws IOException {
        // load more characters, if needed
        if (fCurrentEntity.position == fCurrentEntity.count) {
            load(0, true);
        }

        // scan nmtoken
        int offset = fCurrentEntity.position;
        
        do {
            char ch = fCurrentEntity.ch[fCurrentEntity.position];
            if (XML11Char.isXML11Name(ch)) {
                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);
                        fCurrentEntity.ch = tmp;
                    }
                    else {
                        System.arraycopy(fCurrentEntity.ch, offset,
                                         fCurrentEntity.ch, 0, length);
                    }
                    offset = 0;
                    if (load(length, false)) {
                        break;
                    }
                }
            }
            else if (XML11Char.isXML11NameHighSurrogate(ch)) {
                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);
                        fCurrentEntity.ch = tmp;
                    }
                    else {
                        System.arraycopy(fCurrentEntity.ch, offset,
                                         fCurrentEntity.ch, 0, length);
                    }
                    offset = 0;
                    if (load(length, false)) {
                        --fCurrentEntity.startPosition;
                        --fCurrentEntity.position;
                        break;
                    }
                }
                char ch2 = fCurrentEntity.ch[fCurrentEntity.position];
                if ( !XMLChar.isLowSurrogate(ch2) ||
                     !XML11Char.isXML11Name(XMLChar.supplemental(ch, ch2)) ) {
                    --fCurrentEntity.position;
                    break;
                }
                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);
                        fCurrentEntity.ch = tmp;
                    }
                    else {
                        System.arraycopy(fCurrentEntity.ch, offset,
                                         fCurrentEntity.ch, 0, length);
                    }
                    offset = 0;
                    if (load(length, false)) {
                        break;
                    }
                }
            }
            else {
                break;
            }
        }
        while (true);
        
        int length = fCurrentEntity.position - offset;
        fCurrentEntity.columnNumber += length;

        // return nmtoken
        String symbol = null;
        if (length > 0) {
            symbol = fSymbolTable.addSymbol(fCurrentEntity.ch, offset, length);
        }
        return symbol;

    } // scanNmtoken():String

    /**
     * Returns a string matching the Name production appearing immediately
     * on the input as a symbol, or null if no Name string is present.
     * <p>
     * <strong>Note:</strong> The Name 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.XML11Char#isXML11Name
     * @see com.sun.org.apache.xerces.internal.util.XML11Char#isXML11NameStart
     */
    public String scanName() throws IOException {
        // load more characters, if needed
        if (fCurrentEntity.position == fCurrentEntity.count) {
            load(0, true);
        }

        // scan name
        int offset = fCurrentEntity.position;
        char ch = fCurrentEntity.ch[offset];
        
        if (XML11Char.isXML11NameStart(ch)) {
            if (++fCurrentEntity.position == fCurrentEntity.count) {
                fCurrentEntity.ch[0] = ch;
                offset = 0;
                if (load(1, false)) {