jaxp/src/com/sun/org/apache/xerces/internal/impl/XML11DTDScannerImpl.java

/*
 * reserved comment block
 * DO NOT REMOVE OR ALTER!
 */
/*
 * 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 apache@apache.org.
 *
 * 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.util.SymbolTable;
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 the declarations found
 * in the internal and external subsets of a DTD in an XML document.
 * The scanner acts as the sources for the DTD information which is
 * communicated to the DTD handlers.
 * <p>
 * This component requires the following features and properties from the
 * component manager that uses it:
 * <ul>
 *  <li>http://xml.org/sax/features/validation</li>
 *  <li>http://apache.org/xml/features/scanner/notify-char-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>
 * </ul>
 *
 * @xerces.internal
 *
 * @author Arnaud  Le Hors, IBM
 * @author Andy Clark, IBM
 * @author Glenn Marcy, IBM
 * @author Eric Ye, IBM
 *
 */
public class XML11DTDScannerImpl
    extends XMLDTDScannerImpl {

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

    /** String. */
    private XMLString fString = new XMLString();

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

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

    //
    // Constructors
    //

    /** Default constructor. */
    public XML11DTDScannerImpl() {super();} // <init>()

    /** Constructor for he use of non-XMLComponentManagers. */
    public XML11DTDScannerImpl(SymbolTable symbolTable,
                XMLErrorReporter errorReporter, XMLEntityManager entityManager) {
        super(symbolTable, errorReporter, entityManager);
    }

    //
    // XMLDTDScanner methods
    //

    //
    // XMLScanner methods
    //
    // NOTE:  this is a carbon copy of the code in XML11DocumentScannerImpl;
    // we need to override these methods in both places.  Ah for
    // multiple inheritance...
    // This needs to be refactored!!!  - NG
    /**
     * Scans public ID literal.
     *
     * [12] PubidLiteral ::= '"' PubidChar* '"' | "'" (PubidChar - "'")* "'"
     * [13] PubidChar::= #x20 | #xD | #xA | [a-zA-Z0-9] | [-'()+,./:=?;!*#@$_%]
     *
     * The returned string is normalized according to the following rule,
     * from http://www.w3.org/TR/REC-xml#dt-pubid:
     *
     * Before a match is attempted, all strings of white space in the public
     * identifier must be normalized to single space characters (#x20), and
     * leading and trailing white space must be removed.
     *
     * @param literal The string to fill in with the public ID literal.
     * @return True on success.
     *
     * <strong>Note:</strong> This method uses fStringBuffer, anything in it at
     * the time of calling is lost.
     */
    protected boolean scanPubidLiteral(XMLString literal)
        throws IOException, XNIException
    {
        int quote = fEntityScanner.scanChar();
        if (quote != '\'' && quote != '"') {
            reportFatalError("QuoteRequiredInPublicID", null);
            return false;
        }

        fStringBuffer.clear();
        // skip leading whitespace
        boolean skipSpace = true;
        boolean dataok = true;
        while (true) {
            int c = fEntityScanner.scanChar();
            // REVISIT:  it could really only be \n or 0x20; all else is normalized, no?  - neilg
            if (c == ' ' || c == '\n' || c == '\r' || c == 0x85 || c == 0x2028) {
                if (!skipSpace) {
                    // take the first whitespace as a space and skip the others
                    fStringBuffer.append(' ');
                    skipSpace = true;
                }
            }
            else if (c == quote) {
                if (skipSpace) {
                    // if we finished on a space let's trim it
                    fStringBuffer.length--;
                }
                literal.setValues(fStringBuffer);
                break;
            }
            else if (XMLChar.isPubid(c)) {
                fStringBuffer.append((char)c);
                skipSpace = false;
            }
            else if (c == -1) {
                reportFatalError("PublicIDUnterminated", null);
                return false;
            }
            else {
                dataok = false;
                reportFatalError("InvalidCharInPublicID",
                                 new Object[]{Integer.toHexString(c)});
            }
        }
        return dataok;
   }

    /**
     * Normalize whitespace in an XMLString converting all whitespace
     * characters to space characters.
     */
    protected void normalizeWhitespace(XMLString value) {
        int end = value.offset + value.length;
        for (int i = value.offset; i < end; ++i) {
            int c = value.ch[i];
            if (XMLChar.isSpace(c)) {
                value.ch[i] = ' ';
            }
        }
    }

    /**
     * Normalize whitespace in an XMLString converting all whitespace
     * characters to space characters.
     */
    protected void normalizeWhitespace(XMLString value, int fromIndex) {
        int end = value.offset + value.length;
        for (int i = value.offset + fromIndex; i < end; ++i) {
            int c = value.ch[i];
            if (XMLChar.isSpace(c)) {
                value.ch[i] = ' ';
            }
        }
    }

    /**
     * Checks whether this string would be unchanged by normalization.
     *
     * @return -1 if the value would be unchanged by normalization,
     * otherwise the index of the first whitespace character which
     * would be transformed.
     */
    protected int isUnchangedByNormalization(XMLString value) {
        int end = value.offset + value.length;
        for (int i = value.offset; i < end; ++i) {
            int c = value.ch[i];
            if (XMLChar.isSpace(c)) {
                return i - value.offset;
            }
        }
        return -1;
    }

    // returns true if the given character is not
    // valid with respect to the version of
    // XML understood by this scanner.
    protected boolean isInvalid(int value) {
        return (!XML11Char.isXML11Valid(value));
    } // isInvalid(int):  boolean

    // returns true if the given character is not
    // valid or may not be used outside a character reference
    // with respect to the version of XML understood by this scanner.
    protected boolean isInvalidLiteral(int value) {
        return (!XML11Char.isXML11ValidLiteral(value));
    } // isInvalidLiteral(int):  boolean

    // returns true if the given character is
    // a valid nameChar with respect to the version of
    // XML understood by this scanner.
    protected boolean isValidNameChar(int value) {
        return (XML11Char.isXML11Name(value));
    } // isValidNameChar(int):  boolean

    // returns true if the given character is
    // a valid nameStartChar with respect to the version of
    // XML understood by this scanner.
    protected boolean isValidNameStartChar(int value) {
        return (XML11Char.isXML11NameStart(value));
    } // isValidNameStartChar(int):  boolean

    // returns true if the given character is
    // a valid NCName character with respect to the version of
    // XML understood by this scanner.
    protected boolean isValidNCName(int value) {
        return (XML11Char.isXML11NCName(value));
    } // isValidNCName(int):  boolean

    // returns true if the given character is
    // a valid high surrogate for a nameStartChar
    // with respect to the version of XML understood
    // by this scanner.
    protected boolean isValidNameStartHighSurrogate(int value) {
        return XML11Char.isXML11NameHighSurrogate(value);
    } // isValidNameStartHighSurrogate(int):  boolean

    // note that, according to 4.3.4 of the XML 1.1 spec, XML 1.1
    // documents may invoke 1.0 entities; thus either version decl (or none!)
    // is allowed to appear in this context
    protected boolean versionSupported(String version) {
        return version.equals("1.1") || version.equals ("1.0");
    } // versionSupported(String):  boolean

    // returns the error message key for unsupported
    // versions of XML with respect to the version of
    // XML understood by this scanner.
    protected String getVersionNotSupportedKey () {
        return "VersionNotSupported11";
    } // getVersionNotSupportedKey: String

} // class XML11DTDScannerImpl