portugueseanalyzer.java

来自「javaBB,一套很不錯的JSP源碼,特共享給大家」· Java 代码 · 共 23 行

/*
 * Copyright 28/03/2005 - Vicinity - www.vicinity.com.br All rights reserveds
 */
package org.javabb.lucene.analysis;


import java.io.Reader;
import java.util.HashSet;
import java.util.Set;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;


/**
 * <p>
 * Lucene Analyzer for brazilian portuguese language. This does not do stemmer
 * or others advanceds processing, only remove portuguese {@link #STOP_WORDS}
 * and avoid especial characters, like, but not only, "