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

Lucene example source code file (TestArabicStemFilter.java)

This example Lucene source code file (TestArabicStemFilter.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

arabiclettertokenizer, arabiclettertokenizer, arabicstemfilter, arabicstemfilter, basetokenstreamtestcase, chararrayset, english, io, ioexception, ioexception, keywordmarkerfilter, string, string, stringreader, testarabicstemfilter

The Lucene TestArabicStemFilter.java source code

package org.apache.lucene.analysis.ar;

/**
 * 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.StringReader;

import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.KeywordMarkerFilter;

/**
 * Test the Arabic Normalization Filter
 *
 */
public class TestArabicStemFilter extends BaseTokenStreamTestCase {
  
  public void testAlPrefix() throws IOException {
    check("الحسن", "حسن");
  }    

  public void testWalPrefix() throws IOException {
    check("والحسن", "حسن");
  }    
  
  public void testBalPrefix() throws IOException {
    check("بالحسن", "حسن");
  }    
  
  public void testKalPrefix() throws IOException {
    check("كالحسن", "حسن");
  }    
  
  public void testFalPrefix() throws IOException {
    check("فالحسن", "حسن");
  }    

  public void testLlPrefix() throws IOException {
    check("للاخر", "اخر"); 
  }
  
  public void testWaPrefix() throws IOException {
    check("وحسن", "حسن");
  } 
  
  public void testAhSuffix() throws IOException {
    check("زوجها", "زوج");
  } 
  
  public void testAnSuffix() throws IOException {
    check("ساهدان", "ساهد");
  } 
  
  public void testAtSuffix() throws IOException {
    check("ساهدات", "ساهد");
  } 
  
  public void testWnSuffix() throws IOException {
    check("ساهدون", "ساهد");
  } 
  
  public void testYnSuffix() throws IOException {
    check("ساهدين", "ساهد");
  } 
  
  public void testYhSuffix() throws IOException {
    check("ساهديه", "ساهد");
  } 

  public void testYpSuffix() throws IOException {
    check("ساهدية", "ساهد");
  } 
  
  public void testHSuffix() throws IOException {
    check("ساهده", "ساهد");
  } 
  
  public void testPSuffix() throws IOException {
    check("ساهدة", "ساهد");
  }
  
  public void testYSuffix() throws IOException {
    check("ساهدي", "ساهد");
  }
  
  public void testComboPrefSuf() throws IOException {
    check("وساهدون", "ساهد");
  }
  
  public void testComboSuf() throws IOException {
    check("ساهدهات", "ساهد");
  }
  
  public void testShouldntStem() throws IOException {
    check("الو", "الو");
  }

  public void testNonArabic() throws IOException {
    check("English", "English");
  }
  
  public void testWithKeywordAttribute() throws IOException {
    CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
    set.add("ساهدهات");
    ArabicLetterTokenizer tokenStream  = new ArabicLetterTokenizer(TEST_VERSION_CURRENT, new StringReader("ساهدهات"));

    ArabicStemFilter filter = new ArabicStemFilter(new KeywordMarkerFilter(tokenStream, set));
    assertTokenStreamContents(filter, new String[]{"ساهدهات"});
  }

  private void check(final String input, final String expected) throws IOException {
    ArabicLetterTokenizer tokenStream  = new ArabicLetterTokenizer(TEST_VERSION_CURRENT, new StringReader(input));
    ArabicStemFilter filter = new ArabicStemFilter(tokenStream);
    assertTokenStreamContents(filter, new String[]{expected});
  }
}

Other Lucene examples (source code examples)

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