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

Lucene example source code file (TestTermVectorAccessor.java)

This example Lucene source code file (TestTermVectorAccessor.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

directory, document, document, exception, indexreader, indexwriter, indexwriter, mockanalyzer, parallelarraytermvectormapper, parallelarraytermvectormapper, termfreqvector, termvectoraccessor, termvectoraccessor, testtermvectoraccessor

The Lucene TestTermVectorAccessor.java source code

package org.apache.lucene.index;

import org.apache.lucene.analysis.MockAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.LuceneTestCase;

/*
 *  Licensed 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.
 *
 */

public class TestTermVectorAccessor extends LuceneTestCase {

  public void test() throws Exception {
    Directory dir = newDirectory();
    IndexWriter iw = new IndexWriter(dir, newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random)));

    Document doc;

    doc = new Document();
    doc.add(newField("a", "a b a c a d a e a f a g a h a", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
    doc.add(newField("b", "a b c b d b e b f b g b h b", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
    doc.add(newField("c", "a c b c d c e c f c g c h c", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
    iw.addDocument(doc);

    doc = new Document();
    doc.add(newField("a", "a b a c a d a e a f a g a h a", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS));
    doc.add(newField("b", "a b c b d b e b f b g b h b", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS));
    doc.add(newField("c", "a c b c d c e c f c g c h c", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS));
    iw.addDocument(doc);

    doc = new Document();
    doc.add(newField("a", "a b a c a d a e a f a g a h a", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.YES));
    doc.add(newField("b", "a b c b d b e b f b g b h b", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.YES));
    doc.add(newField("c", "a c b c d c e c f c g c h c", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.YES));
    iw.addDocument(doc);

    doc = new Document();
    doc.add(newField("a", "a b a c a d a e a f a g a h a", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.NO));
    doc.add(newField("b", "a b c b d b e b f b g b h b", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.NO));
    doc.add(newField("c", "a c b c d c e c f c g c h c", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.NO));
    iw.addDocument(doc);

    doc = new Document();
    doc.add(newField("a", "a b a c a d a e a f a g a h a", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
    doc.add(newField("b", "a b c b d b e b f b g b h b", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.NO));
    doc.add(newField("c", "a c b c d c e c f c g c h c", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.YES));
    iw.addDocument(doc);

    iw.close();

    IndexReader ir = IndexReader.open(dir, false);

    TermVectorAccessor accessor = new TermVectorAccessor();

    ParallelArrayTermVectorMapper mapper;
    TermFreqVector tfv;

    for (int i = 0; i < ir.maxDoc(); i++) {

      mapper = new ParallelArrayTermVectorMapper();
      accessor.accept(ir, i, "a", mapper);
      tfv = mapper.materializeVector();
      assertEquals("doc " + i, "a", tfv.getTerms()[0]);
      assertEquals("doc " + i, 8, tfv.getTermFrequencies()[0]);

      mapper = new ParallelArrayTermVectorMapper();
      accessor.accept(ir, i, "b", mapper);
      tfv = mapper.materializeVector();
      assertEquals("doc " + i, 8, tfv.getTermFrequencies().length);
      assertEquals("doc " + i, "b", tfv.getTerms()[1]);
      assertEquals("doc " + i, 7, tfv.getTermFrequencies()[1]);

      mapper = new ParallelArrayTermVectorMapper();
      accessor.accept(ir, i, "c", mapper);
      tfv = mapper.materializeVector();
      assertEquals("doc " + i, 8, tfv.getTermFrequencies().length);
      assertEquals("doc " + i, "c", tfv.getTerms()[2]);
      assertEquals("doc " + i, 7, tfv.getTermFrequencies()[2]);

      mapper = new ParallelArrayTermVectorMapper();
      accessor.accept(ir, i, "q", mapper);
      tfv = mapper.materializeVector();
      assertNull("doc " + i, tfv);

    }

    ir.close();

    dir.close();


  }

}

Other Lucene examples (source code examples)

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