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

Lucene example source code file (TestTermScorer.java)

This example Lucene source code file (TestTermScorer.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

exception, indexreader, io, ioexception, override, override, scorer, string, term, term, termquery, termquery, testhit, testhit, util, weight

The Lucene TestTermScorer.java source code

package org.apache.lucene.search;

/**
 * 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.ArrayList;
import java.util.List;

import org.apache.lucene.analysis.MockAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.RandomIndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.LuceneTestCase;

public class TestTermScorer extends LuceneTestCase {
  protected Directory directory;
  private static final String FIELD = "field";
  
  protected String[] values = new String[] {"all", "dogs dogs", "like",
      "playing", "fetch", "all"};
  protected IndexSearcher indexSearcher;
  protected IndexReader indexReader;
  
  @Override
  public void setUp() throws Exception {
    super.setUp();
    directory = newDirectory();
    
    RandomIndexWriter writer = new RandomIndexWriter(random, directory, newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random)).setMergePolicy(newLogMergePolicy()));
    for (int i = 0; i < values.length; i++) {
      Document doc = new Document();
      doc
          .add(newField(FIELD, values[i], Field.Store.YES,
              Field.Index.ANALYZED));
      writer.addDocument(doc);
    }
    writer.optimize();
    indexReader = writer.getReader();
    writer.close();
    indexSearcher = newSearcher(indexReader);
  }
  
  @Override
  public void tearDown() throws Exception {
    indexSearcher.close();
    indexReader.close();
    directory.close();
    super.tearDown();
  }

  public void test() throws IOException {
    
    Term allTerm = new Term(FIELD, "all");
    TermQuery termQuery = new TermQuery(allTerm);
    
    Weight weight = indexSearcher.createNormalizedWeight(termQuery);
    IndexReader sub = indexSearcher.getIndexReader().getSequentialSubReaders() == null ?
                indexSearcher.getIndexReader() : indexSearcher.getIndexReader().getSequentialSubReaders()[0];
    Scorer ts = weight.scorer(sub, true, true);
    // we have 2 documents with the term all in them, one document for all the
    // other values
    final List<TestHit> docs = new ArrayList();
    // must call next first
    
    ts.score(new Collector() {
      private int base = 0;
      private Scorer scorer;
      
      @Override
      public void setScorer(Scorer scorer) throws IOException {
        this.scorer = scorer;
      }
      
      @Override
      public void collect(int doc) throws IOException {
        float score = scorer.score();
        doc = doc + base;
        docs.add(new TestHit(doc, score));
        assertTrue("score " + score + " is not greater than 0", score > 0);
        assertTrue("Doc: " + doc + " does not equal 0 or doc does not equal 5",
            doc == 0 || doc == 5);
      }
      
      @Override
      public void setNextReader(IndexReader reader, int docBase) {
        base = docBase;
      }
      
      @Override
      public boolean acceptsDocsOutOfOrder() {
        return true;
      }
    });
    assertTrue("docs Size: " + docs.size() + " is not: " + 2, docs.size() == 2);
    TestHit doc0 = docs.get(0);
    TestHit doc5 = docs.get(1);
    // The scores should be the same
    assertTrue(doc0.score + " does not equal: " + doc5.score,
        doc0.score == doc5.score);
    /*
     * Score should be (based on Default Sim.: All floats are approximate tf = 1
     * numDocs = 6 docFreq(all) = 2 idf = ln(6/3) + 1 = 1.693147 idf ^ 2 =
     * 2.8667 boost = 1 lengthNorm = 1 //there is 1 term in every document coord
     * = 1 sumOfSquaredWeights = (idf * boost) ^ 2 = 1.693147 ^ 2 = 2.8667
     * queryNorm = 1 / (sumOfSquaredWeights)^0.5 = 1 /(1.693147) = 0.590
     * 
     * score = 1 * 2.8667 * 1 * 1 * 0.590 = 1.69
     */
    assertTrue(doc0.score + " does not equal: " + 1.6931472f,
        doc0.score == 1.6931472f);
  }
  
  public void testNext() throws Exception {
    
    Term allTerm = new Term(FIELD, "all");
    TermQuery termQuery = new TermQuery(allTerm);
    
    Weight weight = indexSearcher.createNormalizedWeight(termQuery);
    
    IndexReader sub = indexSearcher.getIndexReader().getSequentialSubReaders() == null ?
        indexSearcher.getIndexReader() : indexSearcher.getIndexReader().getSequentialSubReaders()[0];
    Scorer ts = weight.scorer(sub, true, true);
    assertTrue("next did not return a doc",
        ts.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
    assertTrue("score is not correct", ts.score() == 1.6931472f);
    assertTrue("next did not return a doc",
        ts.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
    assertTrue("score is not correct", ts.score() == 1.6931472f);
    assertTrue("next returned a doc and it should not have",
        ts.nextDoc() == DocIdSetIterator.NO_MORE_DOCS);
  }
  
  public void testAdvance() throws Exception {
    
    Term allTerm = new Term(FIELD, "all");
    TermQuery termQuery = new TermQuery(allTerm);
    
    Weight weight = indexSearcher.createNormalizedWeight(termQuery);
    
    IndexReader sub = indexSearcher.getIndexReader().getSequentialSubReaders() == null ? 
        indexSearcher.getIndexReader() : indexSearcher.getIndexReader().getSequentialSubReaders()[0];
        
    Scorer ts = weight.scorer(sub, true, true);
    assertTrue("Didn't skip", ts.advance(3) != DocIdSetIterator.NO_MORE_DOCS);
    // The next doc should be doc 5
    assertTrue("doc should be number 5", ts.docID() == 5);
  }
  
  private class TestHit {
    public int doc;
    public float score;
    
    public TestHit(int doc, float score) {
      this.doc = doc;
      this.score = score;
    }
    
    @Override
    public String toString() {
      return "TestHit{" + "doc=" + doc + ", score=" + score + "}";
    }
  }
  
}

Other Lucene examples (source code examples)

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