/* ====================================================================
 * The Apache Software License, Version 1.1
 *
 * Copyright (c) 2001 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 "Apache" and "Apache Software Foundation" and
 *    "Apache Lucene" 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",
 *    "Apache Lucene", 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.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
*/

package org.apache.lucene.analysis.cjk;

import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.Token;
import java.io.Reader;

/**
 * CJKTokenizer was modified from StopTokenizer which does a decent job for most European 
 * languages. and it perferm other token method for double-byte Characters: the token will 
 * return at each two charactors with overlap match. 
 * Example: "java C1C2C3C4" will be segment to: "java" "C1C2" "C2C3" "C3C4"
 * it also need filter filter zero length token ""
 *
 * for more info on Asia language(Chinese Japanese Korean) text segmentation:
 * http://www.google.com/search?q=overlap+match+chinese+segment
 * for Digit: the prefix digit will token: "3dmax"=>"3" "dmax"; "U2"=>"u2"
 * for Punc: '_' will token as a letter, '+' '#' will token as a digit
 *
 * @author    Che, Dong chedong@bigfoot.com
 * @version   $Id$ 
*/

public final class CJKTokenizer extends Tokenizer {
	private int offset = 0, bufferIndex=0, dataLen=0;
	private final static int MAX_WORD_LEN = 255;
	private final static int IO_BUFFER_SIZE = 256;//
	private final char[] buffer = new char[MAX_WORD_LEN];
	private final char[] ioBuffer = new char[IO_BUFFER_SIZE];
	private String tokenType = "word"; //single=>ASCII  double=>non-ASCII word=>default
	private boolean preIsTokened = false;//previous character is a cached double-byte character

	public CJKTokenizer(Reader in) {
		input = in;
	}

	public final Token next() throws java.io.IOException {
		int length = 0;
		int start = offset;
		while (true) {
			char c;
			Character.UnicodeBlock ub;

			offset++;
			if (bufferIndex >= dataLen) {
				dataLen = input.read(ioBuffer);
				bufferIndex = 0;
			}
			if (dataLen == -1) {
				if (length > 0){
					if (preIsTokened == true){
						length = 0;//empty buffer
						preIsTokened = false;
					}
					break;
				}
				else
					return null;
			}
			else {
				c = (char) ioBuffer[bufferIndex++];
				ub = Character.UnicodeBlock.of(c);
			}

			//ASCII and Extend ASCII
			if (ub == Character.UnicodeBlock.BASIC_LATIN
				 || ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS ) {

				//convert  HALFWIDTH_AND_FULLWIDTH_FORMS to BASIC_LATIN
				if  (ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {
					int i  = (int) c ;
					i = i - 65248;
					c = (char) i;
				}

				// if it's a letter or "_"
				if (Character.isLetter(c) || c == '_') { 
					if (length == 0) { // start of token
						start = offset - 1;
					}
					else if (tokenType == "double") {
						offset --;
						bufferIndex --;
						tokenType = "single";
						if (preIsTokened == true) {
							length = 0;//empty buffer
							preIsTokened = false;
							break;
						}
						else {
							break;
						}
					}
					else if (tokenType == "digit"){
						offset --;
						bufferIndex --;
						break;
					}

					buffer[length++] = Character.toLowerCase(c);  // buffer it
					tokenType = "single";
					if (length == MAX_WORD_LEN) // buffer overflow!
						break;
				}
				else if  (Character.isDigit(c) || c == '+'  ||  c == '#') {
					if (length == 0) { // start of token
						if (c == '+'  ||  c == '#') {
							//ignore '++i'
							break;
						}
						start = offset - 1;
					}
					else if (tokenType == "double") {
						offset --;
						bufferIndex --;
						tokenType = "digit";
						if (preIsTokened == true){
							length = 0;//empty buffer
							preIsTokened = false;
							break;
						}
						else {
							break;
						}
					}

					tokenType = "digit";
					buffer[length++] = c;// buffer it

					if (length == MAX_WORD_LEN)// buffer overflow!
						break;
				}
				else if (length > 0) {			  // at non-Letter w/ chars
					if (preIsTokened == true) {
						length = 0;//empty buffer
						preIsTokened = false;
					}
					else {
						break;
					}
				}					  
			}
			//non-ASCII
			else {
				if (Character.isLetter(c)) {// if it's a letter
				     	if (length == 0){
				     		start = offset -1 ;
				     		buffer[length++] = c;
				     		tokenType = "double";
					}
					else{
						if (tokenType == "single" || tokenType == "digit"){
							offset --;
							bufferIndex--;
							break;
						}
						else{
							buffer[length++] = c;
							tokenType = "double";
							if (length == 2){
								offset --;
								bufferIndex--;
								preIsTokened = true;
								break;
							}
						}
					}
				}
				else if (length > 0){
					if (preIsTokened == true){
						length = 0;//empty buffer
						preIsTokened = false;
					}
					else{
						break;
					}
				}
			}
		}
		return new Token(new String(buffer, 0, length), start, start+length, tokenType);
	}
}