org.apache.lucene.analysis.it.ItalianAnalyzer Maven / Gradle / Ivy
package org.apache.lucene.analysis.it;
/*
* 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.nio.charset.StandardCharsets;
import java.util.Arrays;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.snowball.SnowballFilter;
import org.apache.lucene.analysis.standard.StandardFilter;
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;
import org.apache.lucene.util.Version;
import org.tartarus.snowball.ext.ItalianStemmer;
/**
* {@link Analyzer} for Italian.
* You must specify the required {@link Version}
* compatibility when creating ItalianAnalyzer:
*
* - As of 3.6, ItalianLightStemFilter is used for less aggressive stemming.
*
- As of 3.2, ElisionFilter with a set of Italian
* contractions is used by default.
*
*/
public final class ItalianAnalyzer extends StopwordAnalyzerBase {
private final CharArraySet stemExclusionSet;
/** File containing default Italian stopwords. */
public final static String DEFAULT_STOPWORD_FILE = "italian_stop.txt";
private static final CharArraySet DEFAULT_ARTICLES = CharArraySet.unmodifiableSet(
new CharArraySet(Version.LUCENE_CURRENT,
Arrays.asList(
"c", "l", "all", "dall", "dell", "nell", "sull", "coll", "pell",
"gl", "agl", "dagl", "degl", "negl", "sugl", "un", "m", "t", "s", "v", "d"
), true));
/**
* Returns an unmodifiable instance of the default stop words set.
* @return default stop words set.
*/
public static CharArraySet 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 CharArraySet DEFAULT_STOP_SET;
static {
try {
DEFAULT_STOP_SET = WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class,
DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8), Version.LUCENE_CURRENT);
} 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");
}
}
}
/**
* Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
*/
public ItalianAnalyzer(Version matchVersion) {
this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET);
}
/**
* Builds an analyzer with the given stop words.
*
* @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
public ItalianAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, 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 SetKeywordMarkerFilter} before
* stemming.
*
* @param matchVersion lucene compatibility version
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
public ItalianAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet));
}
/**
* Creates a
* {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
* which tokenizes all the text in the provided {@link Reader}.
*
* @return A
* {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
* built from an {@link StandardTokenizer} filtered with
* {@link StandardFilter}, {@link ElisionFilter}, {@link LowerCaseFilter}, {@link StopFilter}
* , {@link SetKeywordMarkerFilter} if a stem exclusion set is
* provided and {@link ItalianLightStemFilter}.
*/
@Override
protected TokenStreamComponents createComponents(String fieldName,
Reader reader) {
final Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
if (matchVersion.onOrAfter(Version.LUCENE_3_2)) {
result = new ElisionFilter(result, DEFAULT_ARTICLES);
}
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
if(!stemExclusionSet.isEmpty())
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
if (matchVersion.onOrAfter(Version.LUCENE_3_6)) {
result = new ItalianLightStemFilter(result);
} else {
result = new SnowballFilter(result, new ItalianStemmer());
}
return new TokenStreamComponents(source, result);
}
}