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

Lucene example source code file (WordSegmenter.java)

This example Lucene source code file (WordSegmenter.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

hhmmsegmenter, hhmmsegmenter, list, list, segtoken, segtoken, segtokenfilter, segtokenfilter, string, util, wordsegmenter

The Lucene WordSegmenter.java source 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,
 * See the License for the specific language governing permissions and
 * limitations under the License.

package org.apache.lucene.analysis.cn.smart;

import java.util.Collections;
import java.util.List;

import org.apache.lucene.analysis.cn.smart.hhmm.HHMMSegmenter;
import org.apache.lucene.analysis.cn.smart.hhmm.SegToken;
import org.apache.lucene.analysis.cn.smart.hhmm.SegTokenFilter;

 * Segment a sentence of Chinese text into words.
 * @lucene.experimental
class WordSegmenter {

  private HHMMSegmenter hhmmSegmenter = new HHMMSegmenter();

  private SegTokenFilter tokenFilter = new SegTokenFilter();

   * Segment a sentence into words with {@link HHMMSegmenter}
   * @param sentence input sentence
   * @param startOffset start offset of sentence
   * @return {@link List} of {@link SegToken}
  public List<SegToken> segmentSentence(String sentence, int startOffset) {

    List<SegToken> segTokenList = hhmmSegmenter.process(sentence);
    // tokens from sentence, excluding WordType.SENTENCE_BEGIN and WordType.SENTENCE_END
    List<SegToken> result = Collections.emptyList();
    if (segTokenList.size() > 2) // if its not an empty sentence
      result = segTokenList.subList(1, segTokenList.size() - 1);
    for (SegToken st : result)
      convertSegToken(st, sentence, startOffset);
    return result;

   * Process a {@link SegToken} so that it is ready for indexing.
   * This method calculates offsets and normalizes the token with {@link SegTokenFilter}.
   * @param st input {@link SegToken}
   * @param sentence associated Sentence
   * @param sentenceStartOffset offset into sentence
   * @return Lucene {@link SegToken}
  public SegToken convertSegToken(SegToken st, String sentence,
      int sentenceStartOffset) {

    switch (st.wordType) {
      case WordType.STRING:
      case WordType.NUMBER:
      case WordType.FULLWIDTH_NUMBER:
      case WordType.FULLWIDTH_STRING:
        st.charArray = sentence.substring(st.startOffset, st.endOffset)

    st = tokenFilter.filter(st);
    st.startOffset += sentenceStartOffset;
    st.endOffset += sentenceStartOffset;
    return st;

Other Lucene examples (source code examples)

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