xmlparser.java

来自「kaffe Java 解释器语言,源码,Java的子集系统,开放源代码」· Java 代码 · 共 2,494 行 · 第 1/5 页

/*
 * Copyright (C) 1999-2001 David Brownell
 * 
 * This file is part of GNU JAXP, a library.
 *
 * GNU JAXP is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 * 
 * GNU JAXP is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 * 
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 * As a special exception, if you link this library with other files to
 * produce an executable, this library does not by itself cause the
 * resulting executable to be covered by the GNU General Public License.
 * This exception does not however invalidate any other reasons why the
 * executable file might be covered by the GNU General Public License. 
 */

//
// Copyright (c) 1997, 1998 by Microstar Software Ltd.
// From Microstar's README (the entire original license):
//
//	Separate statements also said it's in the public domain.
//	All modifications are distributed under the license
//	above (GPL with library exception).
//
// AElfred is free for both commercial and non-commercial use and
// redistribution, provided that Microstar's copyright and disclaimer are
// retained intact.  You are free to modify AElfred for your own use and
// to redistribute AElfred with your modifications, provided that the
// modifications are clearly documented.
//
// This program is distributed in the hope that it will be useful, but
// WITHOUT ANY WARRANTY; without even the implied warranty of
// merchantability or fitness for a particular purpose.  Please use it AT
// YOUR OWN RISK.
//


package gnu.xml.aelfred2;

import java.io.BufferedInputStream;
import java.io.CharConversionException;
import java.io.EOFException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.IOException;
import java.io.Reader;
import java.io.UnsupportedEncodingException;
import java.net.URL;
import java.net.URLConnection;

// maintaining 1.1 compatibility for now ...
// Iterator and Hashmap ought to be faster
import java.util.Enumeration;
import java.util.Hashtable;
import java.util.Stack;

import org.xml.sax.InputSource;
import org.xml.sax.SAXException;


/**
 * Parse XML documents and return parse events through call-backs.
 * Use the <code>SAXDriver</code> class as your entry point, as all
 * internal parser interfaces are subject to change.
 *
 * @author Written by David Megginson &lt;[e-mail]&gt;
 *	(version 1.2a with bugfixes)
 * @author Updated by David Brownell &lt;[e-mail]&gt;
 * @see SAXDriver
 */
final class XmlParser
{
    // avoid slow per-character readCh()
    private final static boolean USE_CHEATS = true;


    //////////////////////////////////////////////////////////////////////
    // Constructors.
    ////////////////////////////////////////////////////////////////////////


    /**
     * Construct a new parser with no associated handler.
     * @see #setHandler
     * @see #parse
     */
    // package private
    XmlParser ()
    {
    }


    /**
     * Set the handler that will receive parsing events.
     * @param handler The handler to receive callback events.
     * @see #parse
     */
    // package private
    void setHandler (SAXDriver handler)
    {
	this.handler = handler;
    }


    /**
     * Parse an XML document from the character stream, byte stream, or URI
     * that you provide (in that order of preference).  Any URI that you
     * supply will become the base URI for resolving relative URI, and may
     * be used to acquire a reader or byte stream.
     *
     * <p> Only one thread at a time may use this parser; since it is
     * private to this package, post-parse cleanup is done by the caller,
     * which MUST NOT REUSE the parser (just null it).
     *
     * @param systemId Absolute URI of the document; should never be null,
     *	but may be so iff a reader <em>or</em> a stream is provided.
     * @param publicId The public identifier of the document, or null.
     * @param reader A character stream; must be null if stream isn't.
     * @param stream A byte input stream; must be null if reader isn't.
     * @param encoding The suggested encoding, or null if unknown.
     * @exception java.lang.Exception Basically SAXException or IOException
     */
    // package private 
    void doParse (
	String		systemId,
	String		publicId,
	Reader		reader,
	InputStream	stream,
	String		encoding
    ) throws Exception
    {
	if (handler == null)
	    throw new IllegalStateException ("no callback handler");

	initializeVariables ();

	// predeclare the built-in entities here (replacement texts)
	// we don't need to intern(), since we're guaranteed literals
	// are always (globally) interned.
	setInternalEntity ("amp", "&#38;");
	setInternalEntity ("lt", "&#60;");
	setInternalEntity ("gt", "&#62;");
	setInternalEntity ("apos", "&#39;");
	setInternalEntity ("quot", "&#34;");

	try {
	    // pushURL first to ensure locator is correct in startDocument
	    // ... it might report an IO or encoding exception.
	    // FIXME that could call endDocument without startDocument!
	    pushURL (false, "[document]",
			// default baseURI: null
		    new String [] { publicId, systemId, null},
		    reader, stream, encoding, false);

	    handler.startDocument ();
	    parseDocument ();
	} finally {
	    if (reader != null)
		try { reader.close ();
		} catch (IOException e) { /* ignore */ }
	    if (stream != null)
		try { stream.close ();
		} catch (IOException e) { /* ignore */ }
	    if (is != null)
		try { is.close ();
		} catch (IOException e) { /* ignore */ }
	    if (reader != null)
		try {
		    reader.close ();
		} catch (IOException e) { /* ignore */
		}
	    scratch = null;
	}
    }


    ////////////////////////////////////////////////////////////////////////
    // Constants.
    ////////////////////////////////////////////////////////////////////////

    //
    // Constants for element content type.
    //

    /**
     * Constant: an element has not been declared.
     * @see #getElementContentType
     */
    public final static int CONTENT_UNDECLARED = 0;

    /**
     * Constant: the element has a content model of ANY.
     * @see #getElementContentType
     */
    public final static int CONTENT_ANY = 1;

    /**
     * Constant: the element has declared content of EMPTY.
     * @see #getElementContentType
     */
    public final static int CONTENT_EMPTY = 2;

    /**
     * Constant: the element has mixed content.
     * @see #getElementContentType
     */
    public final static int CONTENT_MIXED = 3;

    /**
     * Constant: the element has element content.
     * @see #getElementContentType
     */
    public final static int CONTENT_ELEMENTS = 4;


    //
    // Constants for the entity type.
    //

    /**
     * Constant: the entity has not been declared.
     * @see #getEntityType
     */
    public final static int ENTITY_UNDECLARED = 0;

    /**
     * Constant: the entity is internal.
     * @see #getEntityType
     */
    public final static int ENTITY_INTERNAL = 1;

    /**
     * Constant: the entity is external, non-parsable data.
     * @see #getEntityType
     */
    public final static int ENTITY_NDATA = 2;

    /**
     * Constant: the entity is external XML data.
     * @see #getEntityType
     */
    public final static int ENTITY_TEXT = 3;


    //
    // Attribute type constants are interned literal strings.
    //

    //
    // Constants for supported encodings.  "external" is just a flag.
    //
    private final static int ENCODING_EXTERNAL = 0;
    private final static int ENCODING_UTF_8 = 1;
    private final static int ENCODING_ISO_8859_1 = 2;
    private final static int ENCODING_UCS_2_12 = 3;
    private final static int ENCODING_UCS_2_21 = 4;
    private final static int ENCODING_UCS_4_1234 = 5;
    private final static int ENCODING_UCS_4_4321 = 6;
    private final static int ENCODING_UCS_4_2143 = 7;
    private final static int ENCODING_UCS_4_3412 = 8;
    private final static int ENCODING_ASCII = 9;


    //
    // Constants for attribute default value.
    //

    /**
     * Constant: the attribute is not declared.
     * @see #getAttributeDefaultValueType
     */
    public final static int ATTRIBUTE_DEFAULT_UNDECLARED = 30;

    /**
     * Constant: the attribute has a literal default value specified.
     * @see #getAttributeDefaultValueType
     * @see #getAttributeDefaultValue
     */
    public final static int ATTRIBUTE_DEFAULT_SPECIFIED = 31;

    /**
     * Constant: the attribute was declared #IMPLIED.
     * @see #getAttributeDefaultValueType
     */
    public final static int ATTRIBUTE_DEFAULT_IMPLIED = 32;

    /**
     * Constant: the attribute was declared #REQUIRED.
     * @see #getAttributeDefaultValueType
     */
    public final static int ATTRIBUTE_DEFAULT_REQUIRED = 33;

    /**
     * Constant: the attribute was declared #FIXED.
     * @see #getAttributeDefaultValueType
     * @see #getAttributeDefaultValue
     */
    public final static int ATTRIBUTE_DEFAULT_FIXED = 34;


    //
    // Constants for input.
    //
    private final static int INPUT_NONE = 0;
    private final static int INPUT_INTERNAL = 1;
    private final static int INPUT_STREAM = 3;
    private final static int INPUT_READER = 5;


    //
    // Flags for reading literals.
    //
	// expand general entity refs (attribute values in dtd and content)
    private final static int LIT_ENTITY_REF = 2;
	// normalize this value (space chars) (attributes, public ids)
    private final static int LIT_NORMALIZE = 4;
	// literal is an attribute value 
    private final static int LIT_ATTRIBUTE = 8;
	// don't expand parameter entities
    private final static int LIT_DISABLE_PE = 16;
	// don't expand [or parse] character refs
    private final static int LIT_DISABLE_CREF = 32;
	// don't parse general entity refs
    private final static int LIT_DISABLE_EREF = 64;
	// literal is a public ID value 
    private final static int LIT_PUBID = 256;


    //
    // Flags affecting PE handling in DTDs (if expandPE is true).
    // PEs expand with space padding, except inside literals.
    //
    private final static int CONTEXT_NORMAL = 0;
    private final static int CONTEXT_LITERAL = 1;


    //////////////////////////////////////////////////////////////////////
    // Error reporting.
    //////////////////////////////////////////////////////////////////////


    /**
     * Report an error.
     * @param message The error message.
     * @param textFound The text that caused the error (or null).
     * @see SAXDriver#error
     * @see #line
     */
    private void error (String message, String textFound, String textExpected)
    throws SAXException
    {
	if (textFound != null) {
	    message = message + " (found \"" + textFound + "\")";
	}
	if (textExpected != null) {
	    message = message + " (expected \"" + textExpected + "\")";
	}
	handler.fatal (message);

	// "can't happen"
	throw new SAXException (message);
    }


    /**
     * Report a serious error.
     * @param message The error message.
     * @param textFound The text that caused the error (or null).
     */
    private void error (String message, char textFound, String textExpected)
    throws SAXException
    {
	error (message, new Character (textFound).toString (), textExpected);
    }

    /** Report typical case fatal errors. */
    private void error (String message)
    throws SAXException
    {
	handler.fatal (message);
    }


    //////////////////////////////////////////////////////////////////////
    // Major syntactic productions.
    //////////////////////////////////////////////////////////////////////


    /**
     * Parse an XML document.
     * <pre>
     * [1] document ::= prolog element Misc*
     * </pre>
     * <p>This is the top-level parsing function for a single XML
     * document.  As a minimum, a well-formed document must have
     * a document element, and a valid document must have a prolog
     * (one with doctype) as well.
     */
    private void parseDocument ()
    throws Exception
    {
        try {                                       // added by MHK
    	    boolean sawDTD = parseProlog ();
    	    require ('<');
    	    parseElement (!sawDTD);
        } catch (EOFException ee) {                 // added by MHK
            error("premature end of file", "[EOF]", null);
        }
        
    	try {
    	    parseMisc ();   //skip all white, PIs, and comments
    	    char c = readCh ();    //if this doesn't throw an exception...
    	    error ("unexpected characters after document end", c, null);
    	} catch (EOFException e) {
    	    return;
    	}
    }

    static final char	startDelimComment [] = { '<', '!', '-', '-' };
    static final char	endDelimComment [] = { '-', '-' };

    /**
     * Skip a comment.
     * <pre>
     * [15] Comment ::= '&lt;!--' ((Char - '-') | ('-' (Char - '-')))* "-->"
     * </pre>
     * <p> (The <code>&lt;!--</code> has already been read.)
     */
    private void parseComment ()
    throws Exception
    {
	char c;
	boolean saved = expandPE;

	expandPE = false;
	parseUntil (endDelimComment);
	require ('>');
	expandPE = saved;
	handler.comment (dataBuffer, 0, dataBufferPos);
	dataBufferPos = 0;
    }

    static final char	startDelimPI [] = { '<', '?' };
    static final char	endDelimPI [] = { '?', '>' };

    /**
     * Parse a processing instruction and do a call-back.
     * <pre>
     * [16] PI ::= '&lt;?' PITarget
     *		(S (Char* - (Char* '?&gt;' Char*)))?
     *		'?&gt;'
     * [17] PITarget ::= Name - ( ('X'|'x') ('M'|m') ('L'|l') )
     * </pre>
     * <p> (The <code>&lt;?</code> has already been read.)
     */
    private void parsePI ()
    throws SAXException, IOException
    {
	String name;
	boolean saved = expandPE;

	expandPE = false;
	name = readNmtoken (true);
	if ("xml".equalsIgnoreCase (name))
	    error ("Illegal processing instruction target", name, null);
	if (!tryRead (endDelimPI)) {
	    requireWhitespace ();
	    parseUntil (endDelimPI);
	}
	expandPE = saved;
	handler.processingInstruction (name, dataBufferToString ());
    }


    static final char	endDelimCDATA [] = { ']', ']', '>' };

    /**
     * Parse a CDATA section.
     * <pre>
     * [18] CDSect ::= CDStart CData CDEnd
     * [19] CDStart ::= '&lt;![CDATA['
     * [20] CData ::= (Char* - (Char* ']]&gt;' Char*))
     * [21] CDEnd ::= ']]&gt;'
     * </pre>
     * <p> (The '&lt;![CDATA[' has already been read.)
     */
    private void parseCDSect ()
    throws Exception
    {