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

Lucene example source code file (TestPorterStemFilter.java)

This example Lucene source code file (TestPorterStemFilter.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

basetokenstreamtestcase, chararrayset, exception, exception, io, ioexception, mocktokenizer, mocktokenizer, porterstemfilter, porterstemfilter, reader, reusableanalyzerbase, tokenizer, tokenstreamcomponents, tokenstreamcomponents

The Lucene TestPorterStemFilter.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 java.io.IOException;
import java.io.Reader;
import java.io.StringReader;

import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;

import static org.apache.lucene.analysis.VocabularyAssert.*;

/**
 * Test the PorterStemFilter with Martin Porter's test data.
 */
public class TestPorterStemFilter extends BaseTokenStreamTestCase {  
  Analyzer a = new ReusableAnalyzerBase() {
    @Override
    protected TokenStreamComponents createComponents(String fieldName,
        Reader reader) {
      Tokenizer t = new MockTokenizer(reader, MockTokenizer.KEYWORD, false);
      return new TokenStreamComponents(t, new PorterStemFilter(t));
    }
  };

  /**
   * Run the stemmer against all strings in voc.txt
   * The output should be the same as the string in output.txt
   */
  public void testPorterStemFilter() throws Exception {
    assertVocabulary(a, getDataFile("porterTestData.zip"), "voc.txt", "output.txt");
  }
  
  public void testWithKeywordAttribute() throws IOException {
    CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
    set.add("yourselves");
    Tokenizer tokenizer = new MockTokenizer(new StringReader("yourselves yours"), MockTokenizer.WHITESPACE, false);
    TokenStream filter = new PorterStemFilter(new KeywordMarkerFilter(tokenizer, set));   
    assertTokenStreamContents(filter, new String[] {"yourselves", "your"});
  }
  
  /** blast some random strings through the analyzer */
  public void testRandomStrings() throws Exception {
    checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);
  }
}

Other Lucene examples (source code examples)

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