LUCENE-8891: Add snowball stemmer and analyzer for Estonian language.

Signed-off-by: Tomoko Uchida <tomoko@apache.org>
This commit is contained in:
Gert Morten Paimla 2019-06-30 09:12:55 +09:00 committed by Tomoko Uchida
parent cfd6e1adfa
commit 42a1eb0403
6 changed files with 3720 additions and 0 deletions

View File

@ -52,6 +52,9 @@ API Changes
New Features
* LUCENE-8891: Snowball stemmer/analyzer for the Estonian language.
(Gert Morten Paimla via Tomoko Uchida)
* LUCENE-8815: Provide a DoubleValues implementation for retrieving the value of features without
requiring a separate numeric field. Note that as feature values are stored with only 8 bits of
mantissa the values returned may have a delta from the original values indexed.

View File

@ -0,0 +1,127 @@
/*
* 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 org.apache.lucene.analysis.et;
import java.io.IOException;
import java.io.Reader;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.LowerCaseFilter;
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.miscellaneous.SetKeywordMarkerFilter;
import org.apache.lucene.analysis.snowball.SnowballFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.tartarus.snowball.ext.EstonianStemmer;
/**
* {@link Analyzer} for Estonian.
*/
public final class EstonianAnalyzer extends StopwordAnalyzerBase {
private final CharArraySet stemExclusionSet;
/** File containing default Estonian stopwords. */
public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt";
/**
* 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 = loadStopwordSet(false,
EstonianAnalyzer.class, DEFAULT_STOPWORD_FILE, "#");
} 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 EstonianAnalyzer() {
this(DefaultSetHolder.DEFAULT_STOP_SET);
}
/**
* Builds an analyzer with the given stop words.
*
* @param stopwords a stopword set
*/
public EstonianAnalyzer(CharArraySet stopwords) {
this(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 stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
public EstonianAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(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 LowerCaseFilter}, {@link StopFilter}
* , {@link SetKeywordMarkerFilter} if a stem exclusion set is
* provided and {@link SnowballFilter}.
*/
@Override
protected TokenStreamComponents createComponents(String fieldName) {
final Tokenizer source = new StandardTokenizer();
TokenStream result = new LowerCaseFilter(source);
result = new StopFilter(result, stopwords);
if(!stemExclusionSet.isEmpty())
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
result = new SnowballFilter(result, new EstonianStemmer());
return new TokenStreamComponents(source, result);
}
@Override
protected TokenStream normalize(String fieldName, TokenStream in) {
return new LowerCaseFilter(in);
}
}

View File

@ -0,0 +1,21 @@
/*
* 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.
*/
/**
* Analyzer for Estonian.
*/
package org.apache.lucene.analysis.et;

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,62 @@
/*
* 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 org.apache.lucene.analysis.et;
import java.io.IOException;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
public class TestEstonianAnalyzer extends BaseTokenStreamTestCase {
/** This test fails with NPE when the
* stopwords file is missing in classpath */
public void testResourcesAvailable() {
new EstonianAnalyzer().close();
}
/** test stopwords and stemming */
public void testBasics() throws IOException {
Analyzer a = new EstonianAnalyzer();
// stemming
checkOneTerm(a, "teadaolevalt", "teadaole");
checkOneTerm(a, "teadaolevaid", "teadaole");
checkOneTerm(a, "teadaolevatest", "teadaole");
checkOneTerm(a, "teadaolevail", "teadaole");
checkOneTerm(a, "teadaolevatele", "teadaole");
checkOneTerm(a, "teadaolevatel", "teadaole");
checkOneTerm(a, "teadaolevateks", "teadaole");
checkOneTerm(a, "teadaolevate", "teadaole");
checkOneTerm(a, "teadaolevaks", "teadaole");
checkOneTerm(a, "teadaoleval", "teadaole");
checkOneTerm(a, "teadaolevates", "teadaole");
checkOneTerm(a, "teadaolevat", "teadaole");
checkOneTerm(a, "teadaolevast", "teadaole");
checkOneTerm(a, "teadaoleva", "teadaole");
checkOneTerm(a, "teadaolevais", "teadaole");
checkOneTerm(a, "teadaolevas", "teadaole");
checkOneTerm(a, "teadaolevad", "teadaole");
checkOneTerm(a, "teadaolevale", "teadaole");
checkOneTerm(a, "teadaolevatesse", "teadaole");
// stopword
assertAnalyzesTo(a, "alla", new String[] { });
a.close();
}
}