Examples of org.apache.lucene.facet.taxonomy.TaxonomyReader

Package org.apache.lucene.facet.taxonomy

Examples of org.apache.lucene.facet.taxonomy.TaxonomyReader

org.apache.lucene.facet.taxonomy.TaxonomyReader
TaxonomyReader is the read-only interface with which the faceted-search library uses the taxonomy during search time.
A TaxonomyReader holds a list of categories. Each category has a serial number which we call an "ordinal", and a hierarchical "path" name:
- The ordinal is an integer that starts at 0 for the first category (which is always the root category), and grows contiguously as more categories are added; Note that once a category is added, it can never be deleted.
- The path is a CategoryPath object specifying the category's position in the hierarchy.
Notes about concurrent access to the taxonomy:
An implementation must allow multiple readers to be active concurrently with a single writer. Readers follow so-called "point in time" semantics, i.e., a TaxonomyReader object will only see taxonomy entries which were available at the time it was created. What the writer writes is only available to (new) readers after the writer's commit() is called.
In faceted search, two separate indices are used: the main Lucene index, and the taxonomy. Because the main index refers to the categories listed in the taxonomy, it is important to open the taxonomy *after* opening the main index, and it is also necessary to reopen() the taxonomy after reopen()ing the main index.
This order is important, otherwise it would be possible for the main index to refer to a category which is not yet visible in the old snapshot of the taxonomy. Note that it is indeed fine for the the taxonomy to be opened after the main index - even a long time after. The reason is that once a category is added to the taxonomy, it can never be changed or deleted, so there is no danger that a "too new" taxonomy not being consistent with an older index. @lucene.experimental

  
  /** User drills down on 'tags/solr'. */
  private FacetResult drillDown() throws IOException {
    DirectoryReader indexReader = DirectoryReader.open(indexDir);
    IndexSearcher searcher = new IndexSearcher(indexReader);
    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);


    // Passing no baseQuery means we drill down on all
    // documents ("browse only"):
    DrillDownQuery q = new DrillDownQuery(config);


    // Now user drills down on Publish Date/2010:
    q.add("tags", "solr");
    FacetsCollector fc = new FacetsCollector();
    FacetsCollector.search(searcher, q, 10, fc);


    // Retrieve results
    Facets facets = new TaxonomyFacetSumFloatAssociations("$genre", taxoReader, config, fc);
    FacetResult result = facets.getTopChildren(10, "genre");


    indexReader.close();
    taxoReader.close();
    
    return result;
  }

View Full Code Here

  
  @Test
  public void testDifferentNumResults() throws Exception {
    // test the collector w/ FacetRequests and different numResults
    DirectoryReader indexReader = DirectoryReader.open(indexDir);
    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
    IndexSearcher searcher = newSearcher(indexReader);
    
    FacetsCollector sfc = new FacetsCollector();
    TermQuery q = new TermQuery(A);
    searcher.search(q, sfc);

View Full Code Here

  }
  
  @Test
  public void testAllCounts() throws Exception {
    DirectoryReader indexReader = DirectoryReader.open(indexDir);
    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
    IndexSearcher searcher = newSearcher(indexReader);
    
    FacetsCollector sfc = new FacetsCollector();
    searcher.search(new MatchAllDocsQuery(), sfc);

View Full Code Here

  }
  
  @Test
  public void testBigNumResults() throws Exception {
    DirectoryReader indexReader = DirectoryReader.open(indexDir);
    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
    IndexSearcher searcher = newSearcher(indexReader);
    
    FacetsCollector sfc = new FacetsCollector();
    searcher.search(new MatchAllDocsQuery(), sfc);

View Full Code Here

  }
  
  @Test
  public void testNoParents() throws Exception {
    DirectoryReader indexReader = DirectoryReader.open(indexDir);
    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
    IndexSearcher searcher = newSearcher(indexReader);
    
    FacetsCollector sfc = new FacetsCollector();
    searcher.search(new MatchAllDocsQuery(), sfc);

View Full Code Here

  }
  
  private void doTestReadRecreatedTaxonomy(Random random, boolean closeReader) throws Exception {
    Directory dir = null;
    TaxonomyWriter tw = null;
    TaxonomyReader tr = null;
    
    // prepare a few categories
    int  n = 10;
    FacetLabel[] cp = new FacetLabel[n];
    for (int i=0; i<n; i++) {
      cp[i] = new FacetLabel("a", Integer.toString(i));
    }
    
    try {
      dir = newDirectory();
      
      tw = new DirectoryTaxonomyWriter(dir);
      tw.addCategory(new FacetLabel("a"));
      tw.close();
      
      tr = new DirectoryTaxonomyReader(dir);
      int baseNumCategories = tr.getSize();
      
      for (int i=0; i<n; i++) {
        int k = random.nextInt(n);
        tw = new DirectoryTaxonomyWriter(dir, OpenMode.CREATE);
        for (int j = 0; j <= k; j++) {
          tw.addCategory(cp[j]);
        }
        tw.close();
        if (closeReader) {
          tr.close();
          tr = new DirectoryTaxonomyReader(dir);
        } else {
          TaxonomyReader newtr = TaxonomyReader.openIfChanged(tr);
          assertNotNull(newtr);
          tr.close();
          tr = newtr;
        }
        assertEquals("Wrong #categories in taxonomy (i="+i+", k="+k+")", baseNumCategories + 1 + k, tr.getSize());

View Full Code Here


    DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(dir);
    taxoWriter.addCategory(new FacetLabel("a"));
    taxoWriter.commit();


    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(dir);
    assertEquals("wrong refCount", 1, taxoReader.getRefCount());


    taxoReader.incRef();
    assertEquals("wrong refCount", 2, taxoReader.getRefCount());


    taxoWriter.addCategory(new FacetLabel("a", "b"));
    taxoWriter.commit();
    TaxonomyReader newtr = TaxonomyReader.openIfChanged(taxoReader);
    assertNotNull(newtr);
    taxoReader.close();
    taxoReader = newtr;
    assertEquals("wrong refCount", 1, taxoReader.getRefCount());

View Full Code Here

        LogMergePolicy lmp = (LogMergePolicy) conf.getMergePolicy();
        lmp.setMergeFactor(2);
        return conf;
      }
    };
    TaxonomyReader reader = new DirectoryTaxonomyReader(writer);
    
    int numRounds = random().nextInt(10) + 10;
    int numCategories = 1; // one for root
    for (int i = 0; i < numRounds; i++) {
      int numCats = random().nextInt(4) + 1;
      for (int j = 0; j < numCats; j++) {
        writer.addCategory(new FacetLabel(Integer.toString(i), Integer.toString(j)));
      }
      numCategories += numCats + 1 /* one for round-parent */;
      TaxonomyReader newtr = TaxonomyReader.openIfChanged(reader);
      assertNotNull(newtr);
      reader.close();
      reader = newtr;
      
      // assert categories

View Full Code Here

          IndexWriterConfig config) throws IOException {
        return iw;
      }
    };
    
    TaxonomyReader reader = new DirectoryTaxonomyReader(writer);
    assertEquals(1, reader.getSize());
    assertEquals(1, reader.getParallelTaxonomyArrays().parents().length);


    // add category and call forceMerge -- this should flush IW and merge segments down to 1
    // in ParentArray.initFromReader, this used to fail assuming there are no parents.
    writer.addCategory(new FacetLabel("1"));
    iw.forceMerge(1);
    
    // now calling openIfChanged should trip on the bug
    TaxonomyReader newtr = TaxonomyReader.openIfChanged(reader);
    assertNotNull(newtr);
    reader.close();
    reader = newtr;
    assertEquals(2, reader.getSize());
    assertEquals(2, reader.getParallelTaxonomyArrays().parents().length);

View Full Code Here

    
    // add a category so that the following DTR open will cause a flush and 
    // a new segment will be created
    writer.addCategory(new FacetLabel("a"));
    
    TaxonomyReader reader = new DirectoryTaxonomyReader(writer);
    assertEquals(2, reader.getSize());
    assertEquals(2, reader.getParallelTaxonomyArrays().parents().length);


    // merge all the segments so that NRT reader thinks there's a change 
    iw.forceMerge(1);
    
    // now calling openIfChanged should trip on the wrong assert in ParetArray's ctor
    TaxonomyReader newtr = TaxonomyReader.openIfChanged(reader);
    assertNotNull(newtr);
    reader.close();
    reader = newtr;
    assertEquals(2, reader.getSize());
    assertEquals(2, reader.getParallelTaxonomyArrays().parents().length);

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.lucene.facet.taxonomy.TaxonomyReader

com.gentics.cr.lucene.search.CRSearcher

org.apache.lucene.benchmark.byTask.tasks.CloseTaxonomyReaderTask

org.apache.lucene.benchmark.byTask.TestPerfTasksLogic

org.apache.lucene.demo.facet.AssociationsFacetsExample

org.apache.lucene.demo.facet.ExpressionAggregationFacetsExample

org.apache.lucene.demo.facet.MultiCategoryListsFacetsExample

org.apache.lucene.demo.facet.SimpleFacetsExample

org.apache.lucene.facet.complements.TestTotalFacetCounts

org.apache.lucene.facet.complements.TestTotalFacetCountsCache

org.apache.lucene.facet.example.adaptive.AdaptiveSearcher

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.