home | career | drupal | java | mac | mysql | perl | scala | uml | unix  

Lucene example source code file (IndicTokenizer.java)

This example Lucene source code file (IndicTokenizer.java) is included in the DevDaily.com "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" TM.

Java - Lucene tags/keywords

attributefactory, attributesource, attributesource, chartokenizer, chartokenizer, indictokenizer, indictokenizer, io, override, reader, reader

The Lucene IndicTokenizer.java source code

package org.apache.lucene.analysis.in;

/**
 * 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.Reader;

import org.apache.lucene.analysis.CharTokenizer;
import org.apache.lucene.util.AttributeSource;
import org.apache.lucene.util.Version;

/**
 * Simple Tokenizer for text in Indian Languages.
 */
public final class IndicTokenizer extends CharTokenizer {
 
  public IndicTokenizer(Version matchVersion, AttributeFactory factory, Reader input) {
    super(matchVersion, factory, input);
  }

  public IndicTokenizer(Version matchVersion, AttributeSource source, Reader input) {
    super(matchVersion, source, input);
  }

  public IndicTokenizer(Version matchVersion, Reader input) {
    super(matchVersion, input);
  }

  @Override
  protected boolean isTokenChar(int c) {
    return Character.isLetter(c)
    || Character.getType(c) == Character.NON_SPACING_MARK
    || Character.getType(c) == Character.FORMAT
    || Character.getType(c) == Character.COMBINING_SPACING_MARK;
  }
}

Other Lucene examples (source code examples)

Here is a short list of links related to this Lucene IndicTokenizer.java source code file:



my book on functional programming

 

new blog posts

 

Copyright 1998-2019 Alvin Alexander, alvinalexander.com
All Rights Reserved.

A percentage of advertising revenue from
pages under the /java/jwarehouse URI on this website is
paid back to open source projects.