ro.calin.snowball.SnowballAnalyzer.java Source code

Java tutorial

Introduction

Here is the source code for ro.calin.snowball.SnowballAnalyzer.java

Source

package ro.calin.snowball;

/**
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

import org.apache.lucene.analysis.*;
import org.apache.lucene.analysis.standard.*;

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

/** Filters {@link StandardTokenizer} with {@link StandardFilter}, {@link
 * LowerCaseFilter}, {@link StopFilter} and {@link SnowballFilter}.
 *
 * Available stemmers are listed in {@link net.sf.snowball.ext}.  The name of a
 * stemmer is the part of the class name before "Stemmer", e.g., the stemmer in
 * {@link org.tartarus.snowball.ext.EnglishStemmer} is named "English".
 */
public class SnowballAnalyzer extends Analyzer {
    private String name;
    private Set stopSet;

    /** Builds the named analyzer with no stop words. */
    public SnowballAnalyzer(String name) {
        this.name = name;
    }

    /** Builds the named analyzer with the given stop words. */
    public SnowballAnalyzer(String name, String[] stopWords) {
        this(name);
        stopSet = StopFilter.makeStopSet(stopWords);
    }

    /** Constructs a {@link StandardTokenizer} filtered by a {@link
        StandardFilter}, a {@link LowerCaseFilter} and a {@link StopFilter}. */
    public TokenStream tokenStream(String fieldName, Reader reader) {
        TokenStream result = new StandardTokenizer(reader);
        result = new StandardFilter(result);
        result = new LowerCaseFilter(result);
        if (stopSet != null)
            result = new StopFilter(result, stopSet);
        result = new SnowballFilter(result, name);
        return result;
    }
}