Lucene example source code file (TestArabicAnalyzer.java)

This example Lucene source code file (TestArabicAnalyzer.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

arabicanalyzer, arabicanalyzer, basetokenstreamtestcase, english, exception, exception, hashset, hashset, io, ioexception, set, string, string, testarabicanalyzer, the, util

The Lucene TestArabicAnalyzer.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.util.Collections;
import java.util.HashSet;
import java.util.Set;

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

/**
 * Test the Arabic Analyzer
 *
 */
public class TestArabicAnalyzer extends BaseTokenStreamTestCase {
  
  /** This test fails with NPE when the 
   * stopwords file is missing in classpath */
  public void testResourcesAvailable() {
    new ArabicAnalyzer(TEST_VERSION_CURRENT);
  }
  
  /**
   * Some simple tests showing some features of the analyzer, how some regular forms will conflate
   */
  public void testBasicFeatures() throws Exception {
    ArabicAnalyzer a = new ArabicAnalyzer(TEST_VERSION_CURRENT);
    assertAnalyzesTo(a, "كبير", new String[] { "كبير" });
    assertAnalyzesTo(a, "كبيرة", new String[] { "كبير" }); // feminine marker
    
    assertAnalyzesTo(a, "مشروب", new String[] { "مشروب" });
    assertAnalyzesTo(a, "مشروبات", new String[] { "مشروب" }); // plural -at
    
    assertAnalyzesTo(a, "أمريكيين", new String[] { "امريك" }); // plural -in
    assertAnalyzesTo(a, "امريكي", new String[] { "امريك" }); // singular with bare alif
    
    assertAnalyzesTo(a, "كتاب", new String[] { "كتاب" }); 
    assertAnalyzesTo(a, "الكتاب", new String[] { "كتاب" }); // definite article
    
    assertAnalyzesTo(a, "ما ملكت أيمانكم", new String[] { "ملكت", "ايمانكم"});
    assertAnalyzesTo(a, "الذين ملكت أيمانكم", new String[] { "ملكت", "ايمانكم" }); // stopwords
  }
  
  /**
   * Simple tests to show things are getting reset correctly, etc.
   */
  public void testReusableTokenStream() throws Exception {
    ArabicAnalyzer a = new ArabicAnalyzer(TEST_VERSION_CURRENT);
    assertAnalyzesToReuse(a, "كبير", new String[] { "كبير" });
    assertAnalyzesToReuse(a, "كبيرة", new String[] { "كبير" }); // feminine marker
  }

  /**
   * Non-arabic text gets treated in a similar way as SimpleAnalyzer.
   */
  public void testEnglishInput() throws Exception {
    assertAnalyzesTo(new ArabicAnalyzer(TEST_VERSION_CURRENT), "English text.", new String[] {
        "english", "text" });
  }
  
  /**
   * Test that custom stopwords work, and are not case-sensitive.
   */
  public void testCustomStopwords() throws Exception {
    Set<String> set = new HashSet();
    Collections.addAll(set, "the", "and", "a");
    ArabicAnalyzer a = new ArabicAnalyzer(TEST_VERSION_CURRENT, set);
    assertAnalyzesTo(a, "The quick brown fox.", new String[] { "quick",
        "brown", "fox" });
  }
  
  public void testWithStemExclusionSet() throws IOException {
    Set<String> set = new HashSet();
    set.add("ساهدهات");
    ArabicAnalyzer a = new ArabicAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, set);
    assertAnalyzesTo(a, "كبيرة the quick ساهدهات", new String[] { "كبير","the", "quick", "ساهدهات" });
    assertAnalyzesToReuse(a, "كبيرة the quick ساهدهات", new String[] { "كبير","the", "quick", "ساهدهات" });

    
    a = new ArabicAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, CharArraySet.EMPTY_SET);
    assertAnalyzesTo(a, "كبيرة the quick ساهدهات", new String[] { "كبير","the", "quick", "ساهد" });
    assertAnalyzesToReuse(a, "كبيرة the quick ساهدهات", new String[] { "كبير","the", "quick", "ساهد" });
  }
  
  /** blast some random strings through the analyzer */
  public void testRandomStrings() throws Exception {
    checkRandomData(random, new ArabicAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
  }
}