lucene/analysis/common/src/java/org/apache/lucene/analysis/te/TeluguStemFilter.java

/*
 * 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.te;

import java.io.IOException;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;

/**
 * A {@link TokenFilter} that applies {@link TeluguStemmer} to stem Telugu words.
 *
 * @since 9.0.0
 */
public final class TeluguStemFilter extends TokenFilter {
  private final CharTermAttribute termAttribute = addAttribute(CharTermAttribute.class);
  private final KeywordAttribute keywordAttribute = addAttribute(KeywordAttribute.class);
  private final TeluguStemmer teluguStemmer = new TeluguStemmer();

  public TeluguStemFilter(TokenStream input) {
    super(input);
  }

  @Override
  public boolean incrementToken() throws IOException {
    if (input.incrementToken()) {
      if (!keywordAttribute.isKeyword()) {
        termAttribute.setLength(teluguStemmer.stem(termAttribute.buffer(), termAttribute.length()));
      }
      return true;
    } else {
      return false;
    }
  }
}