com.mozilla.grouperfish.lucene.analysis.en.EnglishAnalyzer.java Source code

Introduction

Here is the source code for com.mozilla.grouperfish.lucene.analysis.en.EnglishAnalyzer.java

Source

/**
 * 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.
 */
package com.mozilla.grouperfish.lucene.analysis.en;

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

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.KeywordMarkerFilter;
import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.PorterStemFilter;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.StopwordAnalyzerBase;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.en.EnglishPossessiveFilter;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.apache.lucene.util.Version;

/**
 * {@link Analyzer} for English.
 */
public final class EnglishAnalyzer extends StopwordAnalyzerBase {

    private final boolean stem;
    private final Set<?> stemExclusionSet;

    /**
     * Returns an unmodifiable instance of the default stop words set.
     * 
     * @return default stop words set.
     */
    public static Set<?> getDefaultStopSet() {
        return DefaultSetHolder.DEFAULT_STOP_SET;
    }

    /**
     * Atomically loads the DEFAULT_STOP_SET in a lazy fashion once the outer
     * class accesses the static final set the first time.;
     */
    private static class DefaultSetHolder {
        static final Set<?> DEFAULT_STOP_SET = StandardAnalyzer.STOP_WORDS_SET;
    }

    /**
     * Builds an analyzer with the default stop words:
     * {@link #getDefaultStopSet}.
     */
    public EnglishAnalyzer(Version matchVersion) {
        this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET, false);
    }

    /**
     * @param matchVersion
     * @param stem
     */
    public EnglishAnalyzer(Version matchVersion, boolean stem) {
        this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET, stem);
    }

    /**
     * Builds an analyzer with the given stop words.
     * 
     * @param matchVersion
     *            lucene compatibility version
     * @param stopwords
     *            a stopword set
     */
    public EnglishAnalyzer(Version matchVersion, Set<?> stopwords, boolean stem) {
        this(matchVersion, stopwords, stem, CharArraySet.EMPTY_SET);
    }

    /**
     * Builds an analyzer with the given stop words. If a non-empty stem
     * exclusion set is provided this analyzer will add a
     * {@link KeywordMarkerFilter} before stemming.
     * 
     * @param matchVersion
     *            lucene compatibility version
     * @param stopwords
     *            a stopword set
     * @param stemExclusionSet
     *            a set of terms not to be stemmed
     */
    public EnglishAnalyzer(Version matchVersion, Set<?> stopwords, boolean stem, Set<?> stemExclusionSet) {
        super(matchVersion, stopwords);
        this.stem = stem;
        this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionSet));
    }

    /**
     * Creates a
     * {@link org.apache.lucene.analysis.ReusableAnalyzerBase.TokenStreamComponents}
     * which tokenizes all the text in the provided {@link Reader}.
     * 
     * @return A
     *         {@link org.apache.lucene.analysis.ReusableAnalyzerBase.TokenStreamComponents}
     *         built from an {@link StandardTokenizer} filtered with
     *         {@link StandardFilter}, {@link LowerCaseFilter},
     *         {@link StopFilter} , {@link KeywordMarkerFilter} if a stem
     *         exclusion set is provided and {@link PorterStemFilter}.
     */
    @Override
    protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        final Tokenizer source = new StandardTokenizer(matchVersion, reader);
        TokenStream result = new StandardFilter(matchVersion, source);
        // prior to this we get the classic behavior, standardfilter does it for
        // us.
        if (matchVersion.onOrAfter(Version.LUCENE_31)) {
            result = new EnglishPossessiveFilter(result);
        }
        result = new LowerCaseFilter(matchVersion, result);
        result = new StopFilter(matchVersion, result, stopwords);
        if (stem) {
            if (!stemExclusionSet.isEmpty())
                result = new KeywordMarkerFilter(result, stemExclusionSet);
            result = new PorterStemFilter(result);
            result = new StopFilter(matchVersion, result, stopwords);
        }
        return new TokenStreamComponents(source, result);
    }
}