nl.knaw.huygens.timbuctoo.lucene.accentanalyzer.MySearchAnalyzer.java Source code

Introduction

Here is the source code for nl.knaw.huygens.timbuctoo.lucene.accentanalyzer.MySearchAnalyzer.java

Source

package nl.knaw.huygens.timbuctoo.lucene.accentanalyzer;

/*
 * 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 java.io.IOException;
import java.io.Reader;
import java.util.Arrays;
import java.util.List;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.util.WordlistLoader;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;

/**
 * Filters {@link StandardTokenizer} with {@link StandardFilter}, {@link
 * LowerCaseFilter} and {@link StopFilter}, using a list of
 * English stop words.
 */
public class MySearchAnalyzer extends Analyzer {

    /** An unmodifiable set containing some common English words that are not usually useful
    for searching.*/
    public static final CharArraySet ENGLISH_STOP_WORDS_SET;

    static {
        final List<String> stopWords = Arrays.asList("a", "an", "and", "are", "as", "at", "be", "but", "by", "for",
                "if", "in", "into", "is", "it", "no", "not", "of", "on", "or", "such", "that", "the", "their",
                "then", "there", "these", "they", "this", "to", "was", "will", "with");
        final org.apache.lucene.analysis.util.CharArraySet stopSet = new CharArraySet(stopWords, false);
        ENGLISH_STOP_WORDS_SET = CharArraySet.unmodifiableSet(stopSet);
    }

    /** Default maximum allowed token length */
    public static final int DEFAULT_MAX_TOKEN_LENGTH = 255;

    private int maxTokenLength = DEFAULT_MAX_TOKEN_LENGTH;

    /** An unmodifiable set containing some common English words that are usually not
    useful for searching. */
    public static final CharArraySet STOP_WORDS_SET = ENGLISH_STOP_WORDS_SET;

    /** Builds an analyzer with the given stop words.
     * @param stopWords stop words */
    public MySearchAnalyzer(CharArraySet stopWords) {
        super();
    }

    /** Builds an analyzer with the default stop words ({@link #STOP_WORDS_SET}).
     */
    public MySearchAnalyzer() {
        this(STOP_WORDS_SET);
    }

    /** Builds an analyzer with the stop words from the given reader.
     * @see WordlistLoader#getWordSet(Reader)
     * @param stopwords Reader to read stop words from */
    public MySearchAnalyzer(Reader stopwords) throws IOException {
        //    this(loadStopwordSet(stopwords));
    }

    /**
     * Set maximum allowed token length.  If a token is seen
     * that exceeds this length then it is discarded.  This
     * setting only takes effect the next time tokenStream or
     * tokenStream is called.
     */
    public void setMaxTokenLength(int length) {
        maxTokenLength = length;
    }

    /** Returns the current maximum token length
     * 
     *  @see #setMaxTokenLength */
    public int getMaxTokenLength() {
        return maxTokenLength;
    }

    @Override
    protected TokenStreamComponents createComponents(final String fieldName) {
        final StandardTokenizer src = new StandardTokenizer();
        src.setMaxTokenLength(maxTokenLength);
        TokenStream tok = new StandardFilter(src);
        return new TokenStreamComponents(src, tok) {
            @Override
            protected void setReader(final Reader reader) {
                src.setMaxTokenLength(MySearchAnalyzer.this.maxTokenLength);
                super.setReader(reader);
            }
        };
    }

    protected TokenStream normalize(String fieldName, TokenStream in) {
        TokenStream result = new StandardFilter(in);
        result = new LowerCaseFilter(result);
        return result;
    }
}