alvinalexander.com | career | drupal | java | mac | mysql | perl | scala | uml | unix  

Lucene example source code file (PerFieldAnalyzerWrapper.java)

This example Lucene source code file (PerFieldAnalyzerWrapper.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

analyzer, analyzer, hashmap, io, ioexception, map, override, override, perfieldanalyzerwrapper, perfieldanalyzerwrapper, reader, reader, string, tokenstream, util

The Lucene PerFieldAnalyzerWrapper.java source code

package org.apache.lucene.analysis;

/**
 * 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.document.Fieldable;

import java.io.Reader;
import java.io.IOException;
import java.util.Map;
import java.util.HashMap;

/**
 * This analyzer is used to facilitate scenarios where different
 * fields require different analysis techniques.  Use {@link #addAnalyzer}
 * to add a non-default analyzer on a field name basis.
 * 
 * <p>Example usage:
 * 
 * <pre>
 *   PerFieldAnalyzerWrapper aWrapper =
 *      new PerFieldAnalyzerWrapper(new StandardAnalyzer());
 *   aWrapper.addAnalyzer("firstname", new KeywordAnalyzer());
 *   aWrapper.addAnalyzer("lastname", new KeywordAnalyzer());
 * </pre>
 * 
 * <p>In this example, StandardAnalyzer will be used for all fields except "firstname"
 * and "lastname", for which KeywordAnalyzer will be used.
 * 
 * <p>A PerFieldAnalyzerWrapper can be used like any other analyzer, for both indexing
 * and query parsing.
 */
public final class PerFieldAnalyzerWrapper extends Analyzer {
  private Analyzer defaultAnalyzer;
  private Map<String,Analyzer> analyzerMap = new HashMap();


  /**
   * Constructs with default analyzer.
   *
   * @param defaultAnalyzer Any fields not specifically
   * defined to use a different analyzer will use the one provided here.
   */
  public PerFieldAnalyzerWrapper(Analyzer defaultAnalyzer) {
    this(defaultAnalyzer, null);
  }
  
  /**
   * Constructs with default analyzer and a map of analyzers to use for 
   * specific fields.
   *
   * @param defaultAnalyzer Any fields not specifically
   * defined to use a different analyzer will use the one provided here.
   * @param fieldAnalyzers a Map (String field name to the Analyzer) to be 
   * used for those fields 
   */
  public PerFieldAnalyzerWrapper(Analyzer defaultAnalyzer, 
      Map<String,Analyzer> fieldAnalyzers) {
    this.defaultAnalyzer = defaultAnalyzer;
    if (fieldAnalyzers != null) {
      analyzerMap.putAll(fieldAnalyzers);
    }
  }
  

  /**
   * Defines an analyzer to use for the specified field.
   *
   * @param fieldName field name requiring a non-default analyzer
   * @param analyzer non-default analyzer to use for field
   */
  public void addAnalyzer(String fieldName, Analyzer analyzer) {
    analyzerMap.put(fieldName, analyzer);
  }

  @Override
  public TokenStream tokenStream(String fieldName, Reader reader) {
    Analyzer analyzer = analyzerMap.get(fieldName);
    if (analyzer == null) {
      analyzer = defaultAnalyzer;
    }

    return analyzer.tokenStream(fieldName, reader);
  }
  
  @Override
  public TokenStream reusableTokenStream(String fieldName, Reader reader) throws IOException {
    Analyzer analyzer = analyzerMap.get(fieldName);
    if (analyzer == null)
      analyzer = defaultAnalyzer;

    return analyzer.reusableTokenStream(fieldName, reader);
  }
  
  /** Return the positionIncrementGap from the analyzer assigned to fieldName */
  @Override
  public int getPositionIncrementGap(String fieldName) {
    Analyzer analyzer = analyzerMap.get(fieldName);
    if (analyzer == null)
      analyzer = defaultAnalyzer;
    return analyzer.getPositionIncrementGap(fieldName);
  }

  /** Return the offsetGap from the analyzer assigned to field */
  @Override
  public int getOffsetGap(Fieldable field) {
    Analyzer analyzer = analyzerMap.get(field.name());
    if (analyzer == null)
      analyzer = defaultAnalyzer;
    return analyzer.getOffsetGap(field);
  }
  
  @Override
  public String toString() {
    return "PerFieldAnalyzerWrapper(" + analyzerMap + ", default=" + defaultAnalyzer + ")";
  }
}

Other Lucene examples (source code examples)

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

... this post is sponsored by my books ...

#1 New Release!

FP Best Seller

 

new blog posts

 

Copyright 1998-2021 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.