standardanalyzer.java

中文分词,中科院分词的改装版。使用java调用dll来实现的。

package org.apache.lucene.analysis.standard;

/**
 * Copyright 2004 The Apache Software Foundation
 *
 * Licensed 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 org.apache.lucene.analysis.*;

import java.io.File;
import java.io.IOException;
import java.io.Reader;
import java.util.Set;

/**
 * Filters {@link StandardTokenizer} with {@link StandardFilter}, {@link
 * LowerCaseFilter} and {@link StopFilter}, using a list of English stop words.
 *
 * @version $Id: StandardAnalyzer.java 219090 2005-07-14 20:36:28Z dnaber $
 */
public class StandardAnalyzer extends Analyzer {
  private Set stopSet;

  /** An array containing some common English words that are usually not
  useful for searching. */
  public static final String[] STOP_WORDS = StopAnalyzer.ENGLISH_STOP_WORDS;

  /** Builds an analyzer with the default stop words ({@link #STOP_WORDS}). */
  public StandardAnalyzer() {
    this(STOP_WORDS);
  }

  /** Builds an analyzer with the given stop words. */
  public StandardAnalyzer(Set stopWords) {
    stopSet = stopWords;
  }

  /** Builds an analyzer with the given stop words. */
  public StandardAnalyzer(String[] stopWords) {
    stopSet = StopFilter.makeStopSet(stopWords);
  }

  /** Builds an analyzer with the stop words from the given file.
   * @see WordlistLoader#getWordSet(File)
   */
  public StandardAnalyzer(File stopwords) throws IOException {
    stopSet = WordlistLoader.getWordSet(stopwords);
  }

  /** Builds an analyzer with the stop words from the given reader.
   * @see WordlistLoader#getWordSet(Reader)
   */
  public StandardAnalyzer(Reader stopwords) throws IOException {
    stopSet = WordlistLoader.getWordSet(stopwords);
  }

  /** Constructs a {@link StandardTokenizer} filtered by a {@link
  StandardFilter}, a {@link LowerCaseFilter} and a {@link StopFilter}. */
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new StandardTokenizer(reader);
    result = new StandardFilter(result);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, stopSet);
    System.out.println("StandardAnalyzer result:"+result);
    return result;
  }
}