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

Lucene example source code file (ClassicAnalyzer.java)

This example Lucene source code file (ClassicAnalyzer.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

classicanalyzer, classicanalyzer, classicfilter, classictokenizer, default_max_token_length, io, ioexception, ioexception, override, reader, reader, set, stop_words_set, stop_words_set, tokenstreamcomponents, util

The Lucene ClassicAnalyzer.java source code

package org.apache.lucene.analysis.standard;

/**
 * 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 org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.StopAnalyzer;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.StopwordAnalyzerBase;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.WordlistLoader;
import org.apache.lucene.util.Version;

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

/**
 * Filters {@link ClassicTokenizer} with {@link ClassicFilter}, {@link
 * LowerCaseFilter} and {@link StopFilter}, using a list of
 * English stop words.
 *
 * <a name="version"/>
 * <p>You must specify the required {@link Version}
 * compatibility when creating ClassicAnalyzer:
 * <ul>
 *   <li> As of 3.1, StopFilter correctly handles Unicode 4.0
 *         supplementary characters in stopwords
 *   <li> As of 2.9, StopFilter preserves position
 *        increments
 *   <li> As of 2.4, Tokens incorrectly identified as acronyms
 *        are corrected (see <a href="https://issues.apache.org/jira/browse/LUCENE-1068">LUCENE-1068)
 * </ul>
 * 
 * ClassicAnalyzer was named StandardAnalyzer in Lucene versions prior to 3.1. 
 * As of 3.1, {@link StandardAnalyzer} implements Unicode text segmentation,
 * as specified by UAX#29.
 */
public final class ClassicAnalyzer extends StopwordAnalyzerBase {

  /** Default maximum allowed token length */
  public static final int DEFAULT_MAX_TOKEN_LENGTH = 255;

  private int maxTokenLength = DEFAULT_MAX_TOKEN_LENGTH;

  /**
   * Specifies whether deprecated acronyms should be replaced with HOST type.
   * See {@linkplain "https://issues.apache.org/jira/browse/LUCENE-1068"}
   */
  private final boolean replaceInvalidAcronym;

  /** An unmodifiable set containing some common English words that are usually not
  useful for searching. */
  public static final Set<?> STOP_WORDS_SET = StopAnalyzer.ENGLISH_STOP_WORDS_SET; 

  /** Builds an analyzer with the given stop words.
   * @param matchVersion Lucene version to match See {@link
   * <a href="#version">above}
   * @param stopWords stop words */
  public ClassicAnalyzer(Version matchVersion, Set<?> stopWords) {
    super(matchVersion, stopWords);
    replaceInvalidAcronym = matchVersion.onOrAfter(Version.LUCENE_24);
  }

  /** Builds an analyzer with the default stop words ({@link
   * #STOP_WORDS_SET}).
   * @param matchVersion Lucene version to match See {@link
   * <a href="#version">above}
   */
  public ClassicAnalyzer(Version matchVersion) {
    this(matchVersion, STOP_WORDS_SET);
  }

  /** Builds an analyzer with the stop words from the given file.
   * @see WordlistLoader#getWordSet(File)
   * @param matchVersion Lucene version to match See {@link
   * <a href="#version">above}
   * @param stopwords File to read stop words from */
  public ClassicAnalyzer(Version matchVersion, File stopwords) throws IOException {
    this(matchVersion, WordlistLoader.getWordSet(stopwords));
  }

  /** Builds an analyzer with the stop words from the given reader.
   * @see WordlistLoader#getWordSet(Reader)
   * @param matchVersion Lucene version to match See {@link
   * <a href="#version">above}
   * @param stopwords Reader to read stop words from */
  public ClassicAnalyzer(Version matchVersion, Reader stopwords) throws IOException {
    this(matchVersion, WordlistLoader.getWordSet(stopwords));
  }

  /**
   * Set maximum allowed token length.  If a token is seen
   * that exceeds this length then it is discarded.  This
   * setting only takes effect the next time tokenStream or
   * reusableTokenStream is called.
   */
  public void setMaxTokenLength(int length) {
    maxTokenLength = length;
  }
    
  /**
   * @see #setMaxTokenLength
   */
  public int getMaxTokenLength() {
    return maxTokenLength;
  }

  @Override
  protected TokenStreamComponents createComponents(final String fieldName, final Reader reader) {
    final ClassicTokenizer src = new ClassicTokenizer(matchVersion, reader);
    src.setMaxTokenLength(maxTokenLength);
    src.setReplaceInvalidAcronym(replaceInvalidAcronym);
    TokenStream tok = new ClassicFilter(src);
    tok = new LowerCaseFilter(matchVersion, tok);
    tok = new StopFilter(matchVersion, tok, stopwords);
    return new TokenStreamComponents(src, tok) {
      @Override
      protected boolean reset(final Reader reader) throws IOException {
        src.setMaxTokenLength(ClassicAnalyzer.this.maxTokenLength);
        return super.reset(reader);
      }
    };
  }
}

Other Lucene examples (source code examples)

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