org.eclipse.epf.web.search/src/org/eclipse/epf/web/search/analysis/ChineseFilter.java

//------------------------------------------------------------------------------
// Copyright (c) 2004, 200 IBM Corporation.  All Rights Reserved.
//------------------------------------------------------------------------------
package org.eclipse.epf.web.search.analysis;

import java.util.Hashtable;
import java.util.ResourceBundle;
import java.util.StringTokenizer;

import org.apache.lucene.analysis.StopAnalyzer;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;


public class ChineseFilter extends TokenFilter {

	private Hashtable _stopTable;

    public ChineseFilter(TokenStream in) 
    {
    	super(in);
    	
        input = in;

        if (_stopTable == null) {
			loadStopWords();
		}
    }

    public final Token next() throws java.io.IOException {

        for (Token token = input.next(); token != null; token = input.next()) {
            String text = token.termText();

            if (_stopTable.get(text) == null) {
                switch (Character.getType(text.charAt(0))) {

				// June 3, 2003 - fchong added support for digits for Rational
				case Character.DECIMAL_DIGIT_NUMBER:
				case Character.LETTER_NUMBER:
                case Character.LOWERCASE_LETTER:
                case Character.UPPERCASE_LETTER:

                    // English word/token should larger than 1 character.
                    if (text.length()>1) {
                        return token;
                    }
                    break;
                case Character.OTHER_LETTER:

                    // One Chinese character as one Chinese word.
                    // Chinese word extraction to be added later here.

                    return token;
                }

            }

        }
        return null;
    }
    
    /**
	 * Loads the stop words defined in the StopWords.properties file.
	 */
	private void loadStopWords() {
		String[] words = null;
		try {
			ResourceBundle bundle = ResourceBundle.getBundle(ChineseFilter.class
					.getPackage().getName()
					+ ".StopWords"); //$NON-NLS-1$				
			String property = bundle.getString("Search.stopWords"); //$NON-NLS-1$
			words = split(property, " ,", -1); //$NON-NLS-1$		
		} catch (Exception e) {
			words = StopAnalyzer.ENGLISH_STOP_WORDS;
		}
		_stopTable = StopFilter.makeStopTable(words);
	}
	
	/**
	 * Splits a string into an array of string tokens.
	 * 
	 * @param str
	 *            A string.
	 * @param sep
	 *            A string containing the string separators.
	 * @param count
	 *            The desired number of string tokens.
	 * @return An array of string tokens.
	 */
	public static String[] split(String str, String sep, int count) {
		if (str == null || count == 0 || count < -1) {
			return null;
		}

		StringTokenizer tokenizer = new StringTokenizer(str, sep,
				count == -1 ? false : true);

		if (count == -1) {
			count = tokenizer.countTokens();
		}

		String[] result = new String[count];
		int i = 0;
		while (tokenizer.hasMoreTokens()) {
			String t = tokenizer.nextToken();
			if (i < count) {
				if ((t.length() == 1) && (sep.indexOf(t) != -1)) {
					continue;
				}
				result[i++] = t;
			} else {
				result[count - 1] += t;
			}
		}
		return result;
	}
}