org.elasticsearch.analysis.hunspell.fr.FrenchHunspellAnalyzer.java Source code

Introduction

Here is the source code for org.elasticsearch.analysis.hunspell.fr.FrenchHunspellAnalyzer.java

Source

package org.elasticsearch.analysis.hunspell.fr;

/*
 * Licensed to Elasticsearch under one or more contributor
 * license agreements. See the NOTICE file distributed with
 * this work for additional information regarding copyright
 * ownership. Elasticsearch 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.nio.charset.StandardCharsets;

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.fr.FrenchAnalyzer;
import org.apache.lucene.analysis.hunspell.Dictionary;
import org.apache.lucene.analysis.hunspell.HunspellStemFilter;
import org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter;
import org.apache.lucene.analysis.snowball.SnowballFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.ElisionFilter;
import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
import org.apache.lucene.analysis.util.WordlistLoader;
import org.apache.lucene.util.IOUtils;

/** 
 * Hunspell-based analyzer for French
 */
public final class FrenchHunspellAnalyzer extends StopwordAnalyzerBase {
    private final Dictionary dictionary;
    private final CharArraySet stemExclusionTable;

    /** 
     * Creates a new analyzer with the specified hunspell dictionary,
     * but with default stopwords and no stem exclusions.
     * 
     * @param dictionary Hunspell dictionary for this language
     */
    public FrenchHunspellAnalyzer(Dictionary dictionary) {
        this(dictionary, getDefaultStopSet(), CharArraySet.EMPTY_SET);
    }

    /** 
     * Creates a new analyzer with the specified hunspell dictionary,
     * specified stopwords and stem exclusions.
     * 
     * @param dictionary Hunspell dictionary for this language
     * @param stopwords a stopword set
     * @param stemExclusionTable a stemming exclusion set
     */
    public FrenchHunspellAnalyzer(Dictionary dictionary, CharArraySet stopwords, CharArraySet stemExclusionTable) {
        super(stopwords);
        this.dictionary = dictionary;
        this.stemExclusionTable = stemExclusionTable;
    }

    private static class DefaultSetHolder {
        private static final CharArraySet DEFAULT_SET;

        static {
            try {
                DEFAULT_SET = WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class,
                        FrenchAnalyzer.DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8), new CharArraySet(16, true));
            } catch (IOException ex) {
                // default set should always be present as it is part of the
                // distribution (JAR)
                throw new RuntimeException("Unable to load default stopword set");
            }
        }
    }

    /**
     * Returns a set of default (case-insensitive) stopwords
     */
    public static final CharArraySet getDefaultStopSet() {
        return DefaultSetHolder.DEFAULT_SET;
    }

    @Override
    protected TokenStreamComponents createComponents(String field) {
        final Tokenizer source = new StandardTokenizer();
        TokenStream result = new ElisionFilter(source, FrenchAnalyzer.DEFAULT_ARTICLES);
        result = new StopFilter(result, stopwords);
        if (!this.stemExclusionTable.isEmpty()) {
            result = new SetKeywordMarkerFilter(result, stemExclusionTable);
        }
        result = new HunspellStemFilter(result, dictionary);
        result = new LowerCaseFilter(result);
        return new TokenStreamComponents(source, result);
    }
}