/*
* 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.core;
import java.io.IOException;
import java.io.Reader;
import java.nio.file.Path;
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.WordlistLoader;
Since: 3.1
/**
* Filters {@link LetterTokenizer} with {@link LowerCaseFilter} and {@link StopFilter}.
*
* @since 3.1
*/
public final class StopAnalyzer extends StopwordAnalyzerBase {
Builds an analyzer with the stop words from the given set.
Params: - stopWords – Set of stop words
/** Builds an analyzer with the stop words from the given set.
* @param stopWords Set of stop words */
public StopAnalyzer(CharArraySet stopWords) {
super(stopWords);
}
Builds an analyzer with the stop words from the given path.
Params: - stopwordsFile – File to load stop words from
See Also: - getWordSet.getWordSet(Reader)
/** Builds an analyzer with the stop words from the given path.
* @see WordlistLoader#getWordSet(Reader)
* @param stopwordsFile File to load stop words from */
public StopAnalyzer(Path stopwordsFile) throws IOException {
this(loadStopwordSet(stopwordsFile));
}
Builds an analyzer with the stop words from the given reader.
Params: - stopwords – Reader to load stop words from
See Also: - getWordSet.getWordSet(Reader)
/** Builds an analyzer with the stop words from the given reader.
* @see WordlistLoader#getWordSet(Reader)
* @param stopwords Reader to load stop words from */
public StopAnalyzer(Reader stopwords) throws IOException {
this(loadStopwordSet(stopwords));
}
Creates TokenStreamComponents
used to tokenize all the text in the provided Reader
. Returns: TokenStreamComponents
built from a LetterTokenizer
filtered with StopFilter
/**
* Creates
* {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
* used to tokenize all the text in the provided {@link Reader}.
*
* @return {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
* built from a {@link LetterTokenizer} filtered with
* {@link StopFilter}
*/
@Override
protected TokenStreamComponents createComponents(String fieldName) {
final Tokenizer source = new LetterTokenizer();
return new TokenStreamComponents(source, new StopFilter(new LowerCaseFilter(source), stopwords));
}
@Override
protected TokenStream normalize(String fieldName, TokenStream in) {
return new LowerCaseFilter(in);
}
}