parser.java

This is a resource based on j2me embedded,if you dont understand,you can connection with me .

/*
 * Copyright  1990-2006 Sun Microsystems, Inc. All Rights Reserved. 
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER 
 *  
 * This program is free software; you can redistribute it and/or 
 * modify it under the terms of the GNU General Public License version 
 * 2 only, as published by the Free Software Foundation. 
 *  
 * 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. See the GNU 
 * General Public License version 2 for more details (a copy is 
 * included at /legal/license.txt). 
 *  
 * You should have received a copy of the GNU General Public License 
 * version 2 along with this work; if not, write to the Free Software 
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 
 * 02110-1301 USA 
 *  
 * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa 
 * Clara, CA 95054 or visit www.sun.com if you need additional 
 * information or have any questions.
 */

/*
 * @(#)Parser.java	1.14 05/10/20
 */


package com.sun.ukit.jaxp;

import java.util.Hashtable;
import java.io.InputStream;
import java.io.Reader;
import java.io.InputStreamReader;
import java.io.IOException;
import java.io.UnsupportedEncodingException;

import org.xml.sax.helpers.DefaultHandler;
import org.xml.sax.Locator;
import org.xml.sax.InputSource;
import org.xml.sax.Attributes;
import org.xml.sax.SAXParseException;
import org.xml.sax.SAXException;

import javax.xml.parsers.SAXParser;

/**
 * XML non-validating parser.
 *
 * This non-validating parser conforms to <a href="http://www.w3.org/TR/REC-xml"
 * >Extensible Markup Language (XML) 1.0</a> and <a href="http://www.w3.org/TR/REC-xml-names"
 * >"Namespaces in XML"</a> specifications. 
 * The API used by the parser is <a href="http://www.jcp.org/en/jsr/detail?id=172"
 * >JSR-172</a> subset of <a href="http://java.sun.com/xml/jaxp/index.html">JAXP</a> 
 * and <a href="http://www.saxproject.org/">SAX2</a>.
 *
 * @see org.xml.sax.helpers.DefaultHandler
 */

public final class Parser
	extends SAXParser
	implements Locator
{
	public final static String	FAULT	= "";

	private final static short  BUFFSIZE_READER	= 512;
	private final static short  BUFFSIZE_PARSER	= 128;
	private final static short  BUFFSIZE_ENTITY	= 32;

	/** The end of stream character. */
	public final static char	EOS		= 0xffff;

	private Pair			mNoNS;		// there is no namespace
	private Pair			mXml;		// the xml namespace

	private DefaultHandler	mHand;		// a document handler
	private Hashtable		mEnt;		// the entities look up table
	private Hashtable		mPEnt;		// the parmeter entities look up table

	private boolean			mIsNSAware;	// if true - to report QName

	private short			mSt;		// global state of the parser
	// mSt values:
	// - 0 : the begining of the document
	// - 1 : misc before DTD
	// - 2 : DTD
	// - 3 : misc after DTD
	// - 4 : document's element
	// - 5 : misc after document's element

	private char			mESt;		// built-in entity recognizer state
	// mESt values:
	//   0x100   : the initial state
	//   > 0x100 : unrecognized name
	//   < 0x100 : replacement character

	private char[]			mBuff;		// parser buffer
	private short			mBuffIdx;	// index of the last char

	private Pair			mPref;		// stack of prefixes
	private Pair			mElm;		// stack of elements

	private Pair			mAttL;		// list of defined attributes by element name

	private Input			mInp;		// stack of entities
	private Input			mDoc;		// document entity

	private char[]			mChars;		// reading buffer
	private char			mChLen;		// current capacity
	private char			mChIdx;		// index to the next char
 
	private Attrs			mAttrs;		// attributes of the curr. element
	private String[]		mItems;		// attributes array of the curr. element
	private char			mAttrIdx;	// attributes counter/index

	private Pair			mDltd;		// deleted objects for reuse

	/**
	 * Default prefixes
	 */
	private final static char NONS[];
	private final static char XML[];
	private final static char XMLNS[];
	static {
		NONS = new char[1];
		NONS[0] = (char)0;

		XML = new char[4];
		XML[0] = (char)4;
		XML[1] = 'x';
		XML[2] = 'm';
		XML[3] = 'l';

		XMLNS = new char[6];
		XMLNS[0] = (char)6;
		XMLNS[1] = 'x';
		XMLNS[2] = 'm';
		XMLNS[3] = 'l';
		XMLNS[4] = 'n';
		XMLNS[5] = 's';
	}

	/**
	 * ASCII character type array.
	 *
	 * This array maps an ASCII (7 bit) character to the character type.<br /> 
	 * Possible character type values are:<br /> 
	 * - ' ' for any kind of white space character;<br /> 
	 * - 'a' for any lower case alphabetical character value;<br /> 
	 * - 'A' for any upper case alphabetical character value;<br /> 
	 * - 'd' for any decimal digit character value;<br /> 
	 * - 'z' for any character less then ' ' except '\t', '\n', '\r';<br /> 
	 * An ASCII (7 bit) character which does not fall in any category listed 
	 * above is mapped to it self.
	 */
	private static final byte asctyp[];

	/**
	 * Static constructor.
	 *
	 * Sets up the ASCII character type array which is used by 
	 * {@link #asctyp asctyp} method.
	 */
	static {
		asctyp	= new byte[0x80];
		short	i	= 0;
		while (i <= 0x1f)
			asctyp[i++]	= (byte)'z';
		asctyp['\t']	= (byte)' ';
		asctyp['\r']	= (byte)' ';
		asctyp['\n']	= (byte)' ';
		for (;i <= 0x2f; i++)
			asctyp[i]	= (byte)i;
		while (i <= 0x39)
			asctyp[i++]	= (byte)'d';
		for (;i <= 0x40; i++)
			asctyp[i]	= (byte)i;
		while (i <= 0x5a)
			asctyp[i++]	= (byte)'A';
		for (;i <= 0x60; i++)
			asctyp[i]	= (byte)i;
		while (i <= 0x7a)
			asctyp[i++]	= (byte)'a';
		for (;i <= 0x7f; i++)
			asctyp[i]	= (byte)i;
	}

	/**
	 * Constructor.
	 */
	public Parser(boolean nsaware)
	{
		super();
		mIsNSAware	= nsaware;

		//		Initialize the parser
		mBuff	= new char[BUFFSIZE_PARSER];
		mAttrs	= new Attrs();

		//		Default namespace
		mPref	= pair(mPref);
		mPref.name	= "";
		mPref.value	= "";
		mPref.chars	= NONS;
		mNoNS	= mPref;	// no namespace
		//		XML namespace
		mPref	= pair(mPref);
		mPref.name	= "xml";
		mPref.value	= "http://www.w3.org/XML/1998/namespace";
		mPref.chars	= XML;
		mXml	= mPref;	// XML namespace
	}

	/**
	 * Return the public identifier for the current document event.
	 *
	 * <p>The return value is the public identifier of the document
	 * entity or of the external parsed entity in which the markup
	 * triggering the event appears.</p>
	 *
	 * @return A string containing the public identifier, or
	 *	null if none is available.
	 *
	 * @see #getSystemId
	 */
	public String getPublicId()
	{
		return (mInp != null)? mInp.pubid: null;
	}

	/**
	 * Return the system identifier for the current document event.
	 *
	 * <p>The return value is the system identifier of the document
	 * entity or of the external parsed entity in which the markup
	 * triggering the event appears.</p>
	 *
	 * <p>If the system identifier is a URL, the parser must resolve it
	 * fully before passing it to the application.</p>
	 *
	 * @return A string containing the system identifier, or null
	 *	if none is available.
	 *
	 * @see #getPublicId
	 */
	public String getSystemId()
	{
		return (mInp != null)? mInp.sysid: null;
	}

	/**
	 * Return the line number where the current document event ends.
	 *
	 * @return Always returns -1 indicating the line number is not 
	 *	available.
	 *
	 * @see #getColumnNumber
	 */
	public int getLineNumber()
	{
		return -1;
	}

	/**
	 * Return the column number where the current document event ends.
	 *
	 * @return Always returns -1 indicating the column number is not 
	 *	available.
	 *
	 * @see #getLineNumber
	 */
	public int getColumnNumber()
	{
		return -1;
	}

	/**
	 * Indicates whether or not this parser is configured to
	 * understand namespaces.
	 *
	 * @return true if this parser is configured to
	 *         understand namespaces; false otherwise.
	 */
	public boolean isNamespaceAware()
	{
		return mIsNSAware;
	}

    /**
     * Indicates whether or not this parser is configured to validate
     * XML documents.
     *
     * @return true if this parser is configured to validate XML
     *          documents; false otherwise.
     */
	public boolean isValidating()
	{
		return false;
	}

	/**
	 * Parse the content of the given {@link java.io.InputStream}
	 * instance as XML using the specified
	 * {@link org.xml.sax.helpers.DefaultHandler}.
	 *
	 * @param src InputStream containing the content to be parsed.
	 * @param handler The SAX DefaultHandler to use.
	 * @exception IOException If any IO errors occur.
	 * @exception IllegalArgumentException If the given InputStream or handler is null.
	 * @exception SAXException If the underlying parser throws a
	 * SAXException while parsing.
	 * @see org.xml.sax.helpers.DefaultHandler
	 */
	public void parse(InputStream src, DefaultHandler handler)
		throws SAXException, IOException
	{
		if ((src == null) || (handler == null))
			throw new IllegalArgumentException("");
		parse(new InputSource(src), handler);
	}

    /**
     * Parse the content given {@link org.xml.sax.InputSource}
     * as XML using the specified
     * {@link org.xml.sax.helpers.DefaultHandler}.
     *
     * @param is The InputSource containing the content to be parsed.
     * @param handler The SAX DefaultHandler to use.
	 * @exception IOException If any IO errors occur.
     * @exception IllegalArgumentException If the InputSource or handler is null.
     * @exception SAXException If the underlying parser throws a
     * SAXException while parsing.
	 * @see org.xml.sax.helpers.DefaultHandler
     */
	public void parse(InputSource is, DefaultHandler handler)
		throws SAXException, IOException
	{
		if ((is == null) || (handler == null))
			throw new IllegalArgumentException("");
		//		Set up the handler
		mHand	= handler;
		//		Set up the document
		mInp	= new Input(BUFFSIZE_READER);
		setinp(is);
		parse(handler);
	}

    /**
     * Parse the XML document content using the specified
     * {@link org.xml.sax.helpers.DefaultHandler}.
     *
     * @param handler The SAX DefaultHandler to use.
	 * @exception IOException If any IO errors occur.
     * @exception SAXException If the underlying parser throws a
     * SAXException while parsing.
	 * @see org.xml.sax.helpers.DefaultHandler
     */
	private void parse(DefaultHandler handler)
		throws SAXException, IOException
	{
		try {
			//		Initialize the parser
			mPEnt	= new Hashtable();
			mEnt	= new Hashtable();
			mDoc	= mInp;			// current input is document entity
			mChars	= mInp.chars;	// use document entity buffer
			//		Parse an xml document
			char	ch;
			mHand.setDocumentLocator(this);
			mHand.startDocument();
			mSt	= 1;
			while ((ch = next()) != EOS) {
				switch (chtyp(ch)) {
				case '<':
					ch	= next();
					switch (ch) {
					case '?':
						pi();
						break;

					case '!':
						ch	= next();
						back();
						if (ch == '-')
							comm();
						else
							dtd();
						break;

					default:			// must be the first char of an xml name 
						if (mSt == 5)	// misc after document's element
							panic(FAULT);
						//		Document's element.
						back();
						mSt	= 4;		// document's element
						elm();
						mSt	= 5;		// misc after document's element
						break;
					}
					break;

				case ' ':
					//		Skip white spaces
					break;

				default:
					panic(FAULT);
				}
			}
			if (mSt != 5)	// misc after document's element
				panic(FAULT);
		} finally {
			mHand.endDocument();
			while (mAttL != null) {
				while (mAttL.list != null) {
					if (mAttL.list.list != null)
						del(mAttL.list.list);
					mAttL.list = del(mAttL.list);
				}
				mAttL = del(mAttL);
			}
			while (mElm != null)
				mElm	= del(mElm);
			while (mPref != mXml)
				mPref	= del(mPref);
			while (mInp != null)
				pop();
			if ((mDoc != null) && (mDoc.src != null)) {
				try { mDoc.src.close(); } catch (IOException ioe) {}
			}
			mPEnt	= null;
			mEnt	= null;
			mDoc	= null;
			mHand	= null;
		}
	}

	/**
	 * Parses the document type declaration.
	 *
	 * @exception SAXException 
	 * @exception IOException 
	 */
	private void dtd()
		throws SAXException, IOException
	{
		char	ch;
		String	str		= null;
		String	name	= null;
		Pair	psid	= null;
		// read 'DOCTYPE'
		if ("DOCTYPE".equals(name(false)) != true)
			panic(FAULT);
		mSt	= 2;	// DTD
		for (short st = 0; st >= 0;) {
			ch	= next();
			switch (st) {
			case 0:		// read the document type name
				if (chtyp(ch) != ' ') {
					back();
					name	= name(mIsNSAware);
					wsskip();
					st		= 1;	// read 'PUPLIC' or 'SYSTEM'
				}
				break;

			case 1:		// read 'PUPLIC' or 'SYSTEM'
				switch (chtyp(ch)) {
				case 'A':
					back();
					psid = pubsys(' ');
					st	= 2;	// skip spaces before internal subset
					break;

				case '[':
					back();
					st	= 2;	// skip spaces before internal subset
					break;

				case '>':
					back();
					st	= 3;	// skip spaces after internal subset
					break;

				default:
					panic(FAULT);
				}
				if (psid != null) {
					//		DTD external subset
					// The parser reports DTD external subset by resolveEntity, but 
					// does not expect to get back an InputSource object. There are 
					// two reasons:
					// 1. the parser does not support validation thus it may ignore 
					//    the DTD external subset.
					// 2. the parser does not support schemas
					if (mHand.resolveEntity(psid.name, psid.value) != null)
						panic(FAULT);
					del(psid);
					//		Unresolved DTD external subset
					mHand.skippedEntity("[dtd]");
				}
				break;

			case 2:		// skip spaces before internal subset
				switch (chtyp(ch)) {
				case '[':
					//		Process internal subset
					dtdint();
					st	= 3;	// skip spaces after internal subset
					break;

				case '>':
					back();
					st	= 3;	// skip spaces after internal subset
					break;

				case ' ':
					// skip white spaces
					break;

				default:
					panic(FAULT);
				}
				break;

			case 3:		// skip spaces after internal subset
				switch (chtyp(ch)) {
				case '>':
					st	= -1;	// end of DTD
					break;

				case ' ':
					// skip white spaces
					break;

				default:
					panic(FAULT);
				}
				break;

			default:
				panic(FAULT);
			}
		}
		mSt	= 3;	// misc after DTD
	}

	/**
	 * Parses the document type declaration internal subset.
	 *
	 * @exception SAXException 
	 * @exception IOException 
	 */
	private void dtdint()
		throws SAXException, IOException
	{
		char ch;
		for (short st = 0; st >= 0;) {
			ch	= next();
			switch (st) {
			case 0:		// skip white spaces before a declaration
				switch (chtyp(ch)) {
				case '<':
					ch	= next();
					switch (ch) {
					case '?':
						pi();
						break;

					case '!':
						ch	= next();
						back();
						if (ch == '-') {
							comm();
							break;
						}
						// markup or entity declaration
						bntok();
						switch (bkeyword()) {
						case 'n':
							dtdent();
							break;

						case 'a':
							dtdattl();		// parse attributes declaration
							break;

						case 'e':
							dtdelm();		// parse element declaration