my_code.MyRomanianAnalyzer.java Source code

Java tutorial

Introduction

Here is the source code for my_code.MyRomanianAnalyzer.java

Source

package my_code;

/*
 * 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 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.ASCIIFoldingFilter;
import org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.ro.RomanianAnalyzer;
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.std40.StandardTokenizer40;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
import org.apache.lucene.util.Version;
import org.tartarus.snowball.ext.RomanianStemmer;

public class MyRomanianAnalyzer extends StopwordAnalyzerBase {
    public MyRomanianAnalyzer() {
        super(RomanianAnalyzer.getDefaultStopSet());
    }

    @Override
    protected TokenStreamComponents createComponents(String fieldName) {
        final Tokenizer source = new StandardTokenizer();

        TokenStream result = source;
        result = new StandardFilter(source);
        result = new LowerCaseFilter(result);
        result = new StopFilter(result, getStopwordSet());
        result = new ASCIIFoldingFilter(result);
        return new TokenStreamComponents(source, result);
    }

}