net.sf.zekr.engine.search.lucene.ZekrLuceneAnalyzerTest.java Source code

Introduction

Here is the source code for net.sf.zekr.engine.search.lucene.ZekrLuceneAnalyzerTest.java

Source

/*
 *               In the name of Allah
 * This file is part of The Zekr Project. Use is subject to
 * license terms.
 *
 * Author:         Mohsen Saboorian
 * Start Date:     Jul 25, 2008
 */

package net.sf.zekr.engine.search.lucene;

import java.io.StringReader;

import net.sf.zekr.ZekrBaseTest;

import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.WhitespaceTokenizer;
import org.apache.lucene.analysis.tokenattributes.TermAttribute;

/**
 * Test case for {@link ZekrLuceneAnalyzer} class. It should test with as many language as possible.
 * 
 * @author Mohsen Saboorian
 */
public class ZekrLuceneAnalyzerTest extends ZekrBaseTest {
    private static final String ARABIC_STR_ORIG1 = "  ? ? ??? ? ?  ? ????";
    private static final String ARABIC_STR1 = "         ";

    private static final String ARABIC_STR_ORIG2 = "?  ?? ? ??? ? ???  ? ? ? ??? ? ??? ? ? ??";
    private static final String ARABIC_STR2 = "    ?       ?     ";

    public ZekrLuceneAnalyzerTest() throws Exception {
        super();
    }

    protected void setUp() throws Exception {
        super.setUp();
    }

    protected void tearDown() throws Exception {
        super.tearDown();
    }

    public void testNextToken1() throws Exception {
        ZekrLuceneAnalyzer zla = new ZekrLuceneAnalyzer(ZekrLuceneAnalyzer.QURAN_LANG_CODE, null);
        TokenStream ts1 = zla.tokenStream(null, new StringReader(ARABIC_STR_ORIG1));
        TokenStream ts2 = new WhitespaceTokenizer(new StringReader(ARABIC_STR1));
        boolean hasMore = ts1.incrementToken();
        ts2.incrementToken();
        TermAttribute t1 = (TermAttribute) ts1
                .getAttribute(org.apache.lucene.analysis.tokenattributes.TermAttribute.class);
        TermAttribute t2 = (TermAttribute) ts2
                .getAttribute(org.apache.lucene.analysis.tokenattributes.TermAttribute.class);
        while (hasMore) {
            assertEquals(new String(t1.termBuffer(), 0, t1.termLength()),
                    new String(t2.termBuffer(), 0, t2.termLength()));
            hasMore = ts1.incrementToken();
            ts2.incrementToken();
            t1 = (TermAttribute) ts1.getAttribute(org.apache.lucene.analysis.tokenattributes.TermAttribute.class);
            t2 = (TermAttribute) ts2.getAttribute(org.apache.lucene.analysis.tokenattributes.TermAttribute.class);
        }
    }

    public void testNextToken2() throws Exception {
        ZekrLuceneAnalyzer zla = new ZekrLuceneAnalyzer(ZekrLuceneAnalyzer.QURAN_LANG_CODE, null);
        TokenStream ts1 = zla.tokenStream(null, new StringReader(ARABIC_STR_ORIG2));
        TokenStream ts2 = new WhitespaceTokenizer(new StringReader(ARABIC_STR2));
        boolean hasMore = ts1.incrementToken();
        ts2.incrementToken();
        TermAttribute t1 = (TermAttribute) ts1
                .getAttribute(org.apache.lucene.analysis.tokenattributes.TermAttribute.class);
        TermAttribute t2 = (TermAttribute) ts2
                .getAttribute(org.apache.lucene.analysis.tokenattributes.TermAttribute.class);
        while (hasMore) {
            assertEquals(new String(t1.termBuffer(), 0, t1.termLength()),
                    new String(t2.termBuffer(), 0, t2.termLength()));
            hasMore = ts1.incrementToken();
            ts2.incrementToken();
            t1 = (TermAttribute) ts1.getAttribute(org.apache.lucene.analysis.tokenattributes.TermAttribute.class);
            t2 = (TermAttribute) ts2.getAttribute(org.apache.lucene.analysis.tokenattributes.TermAttribute.class);
        }
    }
}