org.apache.lucene.analysis.fr.FrenchAnalyzer Maven / Gradle / Ivy
The newest version!
package org.apache.lucene.analysis.fr;
/**
* 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.Analyzer;
import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.KeywordMarkerFilter;
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.WordlistLoader;
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.standard.StandardAnalyzer; // for javadoc
import org.apache.lucene.util.IOUtils;
import org.apache.lucene.util.Version;
import java.io.File;
import java.io.IOException;
import java.io.Reader;
import java.util.Arrays;
import java.util.HashSet;
import java.util.Collections;
import java.util.Map;
import java.util.Set;
/**
* {@link Analyzer} for French language.
*
* Supports an external list of stopwords (words that
* will not be indexed at all) and an external list of exclusions (word that will
* not be stemmed, but indexed).
* A default set of stopwords is used unless an alternative list is specified, but the
* exclusion list is empty by default.
*
*
*
* You must specify the required {@link Version}
* compatibility when creating FrenchAnalyzer:
*
* - As of 3.6, FrenchLightStemFilter is used for less aggressive stemming.
*
- As of 3.1, Snowball stemming is done with SnowballFilter,
* LowerCaseFilter is used prior to StopFilter, and ElisionFilter and
* Snowball stopwords are used by default.
*
- As of 2.9, StopFilter preserves position
* increments
*
*
* NOTE: This class uses the same {@link Version}
* dependent settings as {@link StandardAnalyzer}.
*/
public final class FrenchAnalyzer extends StopwordAnalyzerBase {
/**
* Extended list of typical French stopwords.
* @deprecated use {@link #getDefaultStopSet()} instead
*/
@Deprecated
public final static String[] FRENCH_STOP_WORDS = {
"a", "afin", "ai", "ainsi", "après", "attendu", "au", "aujourd", "auquel", "aussi",
"autre", "autres", "aux", "auxquelles", "auxquels", "avait", "avant", "avec", "avoir",
"c", "car", "ce", "ceci", "cela", "celle", "celles", "celui", "cependant", "certain",
"certaine", "certaines", "certains", "ces", "cet", "cette", "ceux", "chez", "ci",
"combien", "comme", "comment", "concernant", "contre", "d", "dans", "de", "debout",
"dedans", "dehors", "delà", "depuis", "derrière", "des", "désormais", "desquelles",
"desquels", "dessous", "dessus", "devant", "devers", "devra", "divers", "diverse",
"diverses", "doit", "donc", "dont", "du", "duquel", "durant", "dès", "elle", "elles",
"en", "entre", "environ", "est", "et", "etc", "etre", "eu", "eux", "excepté", "hormis",
"hors", "hélas", "hui", "il", "ils", "j", "je", "jusqu", "jusque", "l", "la", "laquelle",
"le", "lequel", "les", "lesquelles", "lesquels", "leur", "leurs", "lorsque", "lui", "là",
"ma", "mais", "malgré", "me", "merci", "mes", "mien", "mienne", "miennes", "miens", "moi",
"moins", "mon", "moyennant", "même", "mêmes", "n", "ne", "ni", "non", "nos", "notre",
"nous", "néanmoins", "nôtre", "nôtres", "on", "ont", "ou", "outre", "où", "par", "parmi",
"partant", "pas", "passé", "pendant", "plein", "plus", "plusieurs", "pour", "pourquoi",
"proche", "près", "puisque", "qu", "quand", "que", "quel", "quelle", "quelles", "quels",
"qui", "quoi", "quoique", "revoici", "revoilà", "s", "sa", "sans", "sauf", "se", "selon",
"seront", "ses", "si", "sien", "sienne", "siennes", "siens", "sinon", "soi", "soit",
"son", "sont", "sous", "suivant", "sur", "ta", "te", "tes", "tien", "tienne", "tiennes",
"tiens", "toi", "ton", "tous", "tout", "toute", "toutes", "tu", "un", "une", "va", "vers",
"voici", "voilà", "vos", "votre", "vous", "vu", "vôtre", "vôtres", "y", "à", "ça", "ès",
"été", "être", "ô"
};
/** File containing default French stopwords. */
public final static String DEFAULT_STOPWORD_FILE = "french_stop.txt";
/**
* Contains words that should be indexed but not stemmed.
*/
private Set excltable = CharArraySet.EMPTY_SET;
/**
* Returns an unmodifiable instance of the default stop-words set.
* @return an unmodifiable instance of the default stop-words set.
*/
public static Set getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
private static class DefaultSetHolder {
/** @deprecated remove this in Lucene 5.0 */
@Deprecated
static final Set DEFAULT_STOP_SET_30 = CharArraySet
.unmodifiableSet(new CharArraySet(Version.LUCENE_CURRENT, Arrays.asList(FRENCH_STOP_WORDS),
false));
static final Set DEFAULT_STOP_SET;
static {
try {
DEFAULT_STOP_SET = WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class,
DEFAULT_STOPWORD_FILE, IOUtils.CHARSET_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 #getDefaultStopSet}).
*/
public FrenchAnalyzer(Version matchVersion) {
this(matchVersion,
matchVersion.onOrAfter(Version.LUCENE_31) ? DefaultSetHolder.DEFAULT_STOP_SET
: DefaultSetHolder.DEFAULT_STOP_SET_30);
}
/**
* Builds an analyzer with the given stop words
*
* @param matchVersion
* lucene compatibility version
* @param stopwords
* a stopword set
*/
public FrenchAnalyzer(Version matchVersion, Set stopwords){
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
/**
* Builds an analyzer with the given stop words
*
* @param matchVersion
* lucene compatibility version
* @param stopwords
* a stopword set
* @param stemExclutionSet
* a stemming exclusion set
*/
public FrenchAnalyzer(Version matchVersion, Set stopwords,
Set stemExclutionSet) {
super(matchVersion, stopwords);
this.excltable = CharArraySet.unmodifiableSet(CharArraySet
.copy(matchVersion, stemExclutionSet));
}
/**
* Builds an analyzer with the given stop words.
* @deprecated use {@link #FrenchAnalyzer(Version, Set)} instead
*/
@Deprecated
public FrenchAnalyzer(Version matchVersion, String... stopwords) {
this(matchVersion, StopFilter.makeStopSet(matchVersion, stopwords));
}
/**
* Builds an analyzer with the given stop words.
* @throws IOException
* @deprecated use {@link #FrenchAnalyzer(Version, Set)} instead
*/
@Deprecated
public FrenchAnalyzer(Version matchVersion, File stopwords) throws IOException {
this(matchVersion, WordlistLoader.getWordSet(IOUtils.getDecodingReader(stopwords,
IOUtils.CHARSET_UTF_8), matchVersion));
}
/**
* Builds an exclusionlist from an array of Strings.
* @deprecated use {@link #FrenchAnalyzer(Version, Set, Set)} instead
*/
@Deprecated
public void setStemExclusionTable(String... exclusionlist) {
excltable = StopFilter.makeStopSet(matchVersion, exclusionlist);
setPreviousTokenStream(null); // force a new stemmer to be created
}
/**
* Builds an exclusionlist from a Map.
* @deprecated use {@link #FrenchAnalyzer(Version, Set, Set)} instead
*/
@Deprecated
public void setStemExclusionTable(Map exclusionlist) {
excltable = new HashSet