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

Lucene example source code file (DefaultICUTokenizerConfig.java)

This example Lucene source code file (DefaultICUTokenizerConfig.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

breakiterator, breakiterator, io, override, rulebasedbreakiterator, string, string, word_hangul, word_hangul, word_hiragana, word_hiragana, word_ideo, word_katakana, word_letter, word_number

The Lucene DefaultICUTokenizerConfig.java source code

package org.apache.lucene.analysis.icu.segmentation;

 * 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,
 * See the License for the specific language governing permissions and
 * limitations under the License.

import java.io.IOException;
import java.io.InputStream;

import org.apache.lucene.analysis.standard.StandardTokenizer;

import com.ibm.icu.lang.UScript;
import com.ibm.icu.text.BreakIterator;
import com.ibm.icu.text.RuleBasedBreakIterator;
import com.ibm.icu.util.ULocale;

 * Default {@link ICUTokenizerConfig} that is generally applicable
 * to many languages.
 * <p>
 * Generally tokenizes Unicode text according to UAX#29 
 * ({@link BreakIterator#getWordInstance(ULocale) BreakIterator.getWordInstance(ULocale.ROOT)}), 
 * but with the following tailorings:
 * <ul>
 *   <li>Thai text is broken into words with a 
 *   {@link com.ibm.icu.text.DictionaryBasedBreakIterator}
 *   <li>Lao, Myanmar, and Khmer text is broken into syllables
 *   based on custom BreakIterator rules.
 *   <li>Hebrew text has custom tailorings to handle special cases
 *   involving punctuation.
 * </ul>
 * @lucene.experimental
public class DefaultICUTokenizerConfig extends ICUTokenizerConfig {
  /** Token type for words containing ideographic characters */
  public static final String WORD_IDEO = StandardTokenizer.TOKEN_TYPES[StandardTokenizer.IDEOGRAPHIC];
  /** Token type for words containing Japanese hiragana */
  public static final String WORD_HIRAGANA = StandardTokenizer.TOKEN_TYPES[StandardTokenizer.HIRAGANA];
  /** Token type for words containing Japanese katakana */
  public static final String WORD_KATAKANA = StandardTokenizer.TOKEN_TYPES[StandardTokenizer.KATAKANA];
  /** Token type for words containing Korean hangul  */
  public static final String WORD_HANGUL = StandardTokenizer.TOKEN_TYPES[StandardTokenizer.HANGUL];
  /** Token type for words that contain letters */
  public static final String WORD_LETTER = StandardTokenizer.TOKEN_TYPES[StandardTokenizer.ALPHANUM];
  /** Token type for words that appear to be numbers */
  public static final String WORD_NUMBER = StandardTokenizer.TOKEN_TYPES[StandardTokenizer.NUM];
   * the default breakiterators in use. these can be expensive to
   * instantiate, cheap to clone.
  private static final BreakIterator rootBreakIterator = 
  private static final BreakIterator thaiBreakIterator = 
    BreakIterator.getWordInstance(new ULocale("th_TH"));
  private static final BreakIterator hebrewBreakIterator = 
  private static final BreakIterator khmerBreakIterator = 
  private static final BreakIterator laoBreakIterator = 
    new LaoBreakIterator(readBreakIterator("Lao.brk"));
  private static final BreakIterator myanmarBreakIterator = 
  public BreakIterator getBreakIterator(int script) {
    switch(script) {
      case UScript.THAI: return (BreakIterator)thaiBreakIterator.clone();
      case UScript.HEBREW: return (BreakIterator)hebrewBreakIterator.clone();
      case UScript.KHMER: return (BreakIterator)khmerBreakIterator.clone();
      case UScript.LAO: return (BreakIterator)laoBreakIterator.clone();
      case UScript.MYANMAR: return (BreakIterator)myanmarBreakIterator.clone();
      default: return (BreakIterator)rootBreakIterator.clone();

  public String getType(int script, int ruleStatus) {
    switch (ruleStatus) {
      case RuleBasedBreakIterator.WORD_IDEO:
        return WORD_IDEO;
      case RuleBasedBreakIterator.WORD_KANA:
        return script == UScript.HIRAGANA ? WORD_HIRAGANA : WORD_KATAKANA;
      case RuleBasedBreakIterator.WORD_LETTER:
        return script == UScript.HANGUL ? WORD_HANGUL : WORD_LETTER;
      case RuleBasedBreakIterator.WORD_NUMBER:
        return WORD_NUMBER;
      default: /* some other custom code */
        return "<OTHER>";

  private static RuleBasedBreakIterator readBreakIterator(String filename) {
    InputStream is = 
    try {
      RuleBasedBreakIterator bi = 
      return bi;
    } catch (IOException e) {
      throw new RuntimeException(e);

Other Lucene examples (source code examples)

Here is a short list of links related to this Lucene DefaultICUTokenizerConfig.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.