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

Lucene example source code file (TestFieldNormModifier.java)

This example Lucene source code file (TestFieldNormModifier.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, fieldnormmodifier, fieldnormmodifier, indexsearcher, indexsearcher, io, ioexception, ioexception, num_docs, override, override, scorer, string, term, termquery, util

The Lucene TestFieldNormModifier.java source code

package org.apache.lucene.index;

/**
 * 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.Arrays;

import org.apache.lucene.analysis.MockAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.search.Collector;
import org.apache.lucene.search.DefaultSimilarity;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Scorer;
import org.apache.lucene.search.Similarity;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.LuceneTestCase;

/**
 * Tests changing of field norms with a custom similarity and with fake norms.
 */
public class TestFieldNormModifier extends LuceneTestCase {
  public static int NUM_DOCS = 5;
  
  public Directory store;
  
  /** inverts the normal notion of lengthNorm */
  public static Similarity s = new DefaultSimilarity() {
    @Override
    public float computeNorm(String fieldName, FieldInvertState state) {
      return state.getBoost() * (discountOverlaps ? state.getLength() - state.getNumOverlap() : state.getLength());
    }
  };
  
  @Override
  public void setUp() throws Exception {
    super.setUp();
    store = newDirectory();
    IndexWriter writer = new IndexWriter(store, newIndexWriterConfig(
                                                                     TEST_VERSION_CURRENT, new MockAnalyzer(random)).setMergePolicy(newLogMergePolicy()));
    
    for (int i = 0; i < NUM_DOCS; i++) {
      Document d = new Document();
      d.add(newField("field", "word", Field.Store.YES, Field.Index.ANALYZED));
      d.add(newField("nonorm", "word", Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));
      d.add(newField("untokfield", "20061212 20071212", Field.Store.YES, Field.Index.ANALYZED));
      
      for (int j = 1; j <= i; j++) {
        d.add(newField("field", "crap", Field.Store.YES, Field.Index.ANALYZED));
        d.add(newField("nonorm", "more words", Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));
      }
      writer.addDocument(d);
    }
    writer.close();
  }
  
  @Override
  public void tearDown() throws Exception {
    store.close();
    super.tearDown();
  }
  
  public void testMissingField() throws Exception {
    FieldNormModifier fnm = new FieldNormModifier(store, s);
    try {
      fnm.reSetNorms("nobodyherebutuschickens");
    } catch (IllegalStateException e) {
      // expected
    }
  }
  
  public void testFieldWithNoNorm() throws Exception {
    
    IndexReader r = IndexReader.open(store, false);
    byte[] norms = r.norms("nonorm");
    
    // sanity check, norms should all be 1
    assertTrue("Whoops we have norms?", !r.hasNorms("nonorm"));
    assertNull(norms);
    
    r.close();
    
    FieldNormModifier fnm = new FieldNormModifier(store, s);
    try {
      fnm.reSetNorms("nonorm");
    } catch (IllegalStateException e) {
      // expected
    }
    
    // nothing should have changed
    r = IndexReader.open(store, false);
    
    norms = r.norms("nonorm");
    assertTrue("Whoops we have norms?", !r.hasNorms("nonorm"));
    assertNull(norms);

    r.close();
  }
  
  
  public void testGoodCases() throws Exception {
    
    IndexSearcher searcher = new IndexSearcher(store, true);
    final float[] scores = new float[NUM_DOCS];
    float lastScore = 0.0f;
    
    // default similarity should put docs with shorter length first
    searcher.search(new TermQuery(new Term("field", "word")), new Collector() {
      private int docBase = 0;
      private Scorer scorer;
      
      @Override
      public final void collect(int doc) throws IOException {
        scores[doc + docBase] = scorer.score();
      }
      @Override
      public void setNextReader(IndexReader reader, int docBase) {
        this.docBase = docBase;
      }
      @Override
      public void setScorer(Scorer scorer) throws IOException {
        this.scorer = scorer;
      }
      @Override
      public boolean acceptsDocsOutOfOrder() {
        return true;
      }
    });
    searcher.close();
    
    lastScore = Float.MAX_VALUE;
    for (int i = 0; i < NUM_DOCS; i++) {
      String msg = "i=" + i + ", " + scores[i] + " <= " + lastScore;
      assertTrue(msg, scores[i] <= lastScore);
      //System.out.println(msg);
      lastScore = scores[i];
    }

    FieldNormModifier fnm = new FieldNormModifier(store, s);
    fnm.reSetNorms("field");
    
    // new norm (with default similarity) should put longer docs first
    searcher = new IndexSearcher(store, true);
    searcher.search(new TermQuery(new Term("field", "word")),  new Collector() {
      private int docBase = 0;
      private Scorer scorer;
      @Override
      public final void collect(int doc) throws IOException {
        scores[doc + docBase] = scorer.score();
      }
      @Override
      public void setNextReader(IndexReader reader, int docBase) {
        this.docBase = docBase;
      }
      @Override
      public void setScorer(Scorer scorer) throws IOException {
        this.scorer = scorer;
      }
      @Override
      public boolean acceptsDocsOutOfOrder() {
        return true;
      }
    });
    searcher.close();
    
    lastScore = 0.0f;
    for (int i = 0; i < NUM_DOCS; i++) {
      String msg = "i=" + i + ", " + scores[i] + " >= " + lastScore;
      assertTrue(msg, scores[i] >= lastScore);
      //System.out.println(msg);
      lastScore = scores[i];
    }
  }

  public void testNormKiller() throws IOException {

    IndexReader r = IndexReader.open(store, false);
    byte[] oldNorms = r.norms("untokfield");    
    r.close();
    
    FieldNormModifier fnm = new FieldNormModifier(store, s);
    fnm.reSetNorms("untokfield");

    r = IndexReader.open(store, false);
    byte[] newNorms = r.norms("untokfield");
    r.close();
    assertFalse(Arrays.equals(oldNorms, newNorms));    

    
    // verify that we still get documents in the same order as originally
    IndexSearcher searcher = new IndexSearcher(store, true);
    final float[] scores = new float[NUM_DOCS];
    float lastScore = 0.0f;
    
    // default similarity should return the same score for all documents for this query
    searcher.search(new TermQuery(new Term("untokfield", "20061212")), new Collector() {
      private int docBase = 0;
      private Scorer scorer;
      @Override
      public final void collect(int doc) throws IOException {
        scores[doc + docBase] = scorer.score();
      }
      @Override
      public void setNextReader(IndexReader reader, int docBase) {
        this.docBase = docBase;
      }
      @Override
      public void setScorer(Scorer scorer) throws IOException {
        this.scorer = scorer;
      }
      @Override
      public boolean acceptsDocsOutOfOrder() {
        return true;
      }
    });
    searcher.close();
    
    lastScore = scores[0];
    for (int i = 0; i < NUM_DOCS; i++) {
      String msg = "i=" + i + ", " + scores[i] + " == " + lastScore;
      assertTrue(msg, scores[i] == lastScore);
      //System.out.println(msg);
      lastScore = scores[i];
    }
  }
}

Other Lucene examples (source code examples)

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