Java Code Examples for org.apache.lucene.facet.FacetsCollector#search()

/** User runs a query and counts facets. */
public FacetResult search() throws IOException {

  // Aggregates the facet counts
  FacetsCollector fc = new FacetsCollector();

  // MatchAllDocsQuery is for "browsing" (counts facets
  // for all non-deleted docs in the index); normally
  // you'd use a "normal" query:
  FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);

  Facets facets = new LongRangeFacetCounts("timestamp", fc,
                                           PAST_HOUR,
                                           PAST_SIX_HOURS,
                                           PAST_DAY);
  return facets.getTopChildren(10, "timestamp");
}
 

/** User runs a query and counts facets. */
private List<FacetResult> facetsWithSearch() throws IOException {
  DirectoryReader indexReader = DirectoryReader.open(indexDir);
  IndexSearcher searcher = new IndexSearcher(indexReader);
  TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);

  FacetsCollector fc = new FacetsCollector();

  // MatchAllDocsQuery is for "browsing" (counts facets
  // for all non-deleted docs in the index); normally
  // you'd use a "normal" query:
  FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);

  // Retrieve results
  List<FacetResult> results = new ArrayList<>();

  // Count both "Publish Date" and "Author" dimensions
  Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc);
  results.add(facets.getTopChildren(10, "Author"));
  results.add(facets.getTopChildren(10, "Publish Date"));
  
  indexReader.close();
  taxoReader.close();
  
  return results;
}
 

/** User drills down on 'Publish Date/2010', and we
 *  return facets for 'Author' */
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("Publish Date", "2010");
  FacetsCollector fc = new FacetsCollector();
  FacetsCollector.search(searcher, q, 10, fc);

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

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

/** User runs a query and counts facets. */
private List<FacetResult> search() throws IOException {
  DirectoryReader indexReader = DirectoryReader.open(indexDir);
  IndexSearcher searcher = new IndexSearcher(indexReader);
  SortedSetDocValuesReaderState state = new DefaultSortedSetDocValuesReaderState(indexReader);

  // Aggregatses the facet counts
  FacetsCollector fc = new FacetsCollector();

  // MatchAllDocsQuery is for "browsing" (counts facets
  // for all non-deleted docs in the index); normally
  // you'd use a "normal" query:
  FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);

  // Retrieve results
  Facets facets = new SortedSetDocValuesFacetCounts(state, fc);

  List<FacetResult> results = new ArrayList<>();
  results.add(facets.getTopChildren(10, "Author"));
  results.add(facets.getTopChildren(10, "Publish Year"));
  indexReader.close();
  
  return results;
}
 

/** User drills down on 'Publish Year/2010'. */
private FacetResult drillDown() throws IOException {
  DirectoryReader indexReader = DirectoryReader.open(indexDir);
  IndexSearcher searcher = new IndexSearcher(indexReader);
  SortedSetDocValuesReaderState state = new DefaultSortedSetDocValuesReaderState(indexReader);

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

  // Retrieve results
  Facets facets = new SortedSetDocValuesFacetCounts(state, fc);
  FacetResult result = facets.getTopChildren(10, "Author");
  indexReader.close();
  
  return result;
}
 

/** User runs a query and aggregates facets by summing their association values. */
private List<FacetResult> sumAssociations() throws IOException {
  DirectoryReader indexReader = DirectoryReader.open(indexDir);
  IndexSearcher searcher = new IndexSearcher(indexReader);
  TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
  
  FacetsCollector fc = new FacetsCollector();
  
  // MatchAllDocsQuery is for "browsing" (counts facets
  // for all non-deleted docs in the index); normally
  // you'd use a "normal" query:
  FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);
  
  Facets tags = new TaxonomyFacetSumIntAssociations("$tags", taxoReader, config, fc);
  Facets genre = new TaxonomyFacetSumFloatAssociations("$genre", taxoReader, config, fc);

  // Retrieve results
  List<FacetResult> results = new ArrayList<>();
  results.add(tags.getTopChildren(10, "tags"));
  results.add(genre.getTopChildren(10, "genre"));

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

/** 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;
}
 

/** User drills down on 'Publish Year/2010'. */
private FacetResult drillDown() throws IOException {
	DirectoryReader indexReader = DirectoryReader.open(directory);
	IndexSearcher searcher = new IndexSearcher(indexReader);
	SortedSetDocValuesReaderState state = new DefaultSortedSetDocValuesReaderState(indexReader);
	
	// Now user drills down on Publish Year/2010:
	DrillDownQuery q = new DrillDownQuery(config);
	q.add("Publish Year", "2010");
	FacetsCollector fc = new FacetsCollector();
	FacetsCollector.search(searcher, q, 10, fc);
	
	// Retrieve results
	Facets facets = new SortedSetDocValuesFacetCounts(state, fc);
	FacetResult result = facets.getTopChildren(10, "Author");
	indexReader.close();
	
	return result;
}
 

/** User runs a query and aggregates facets. */
private FacetResult search() throws IOException, ParseException {
  DirectoryReader indexReader = DirectoryReader.open(indexDir);
  IndexSearcher searcher = new IndexSearcher(indexReader);
  TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);

  // Aggregate categories by an expression that combines the document's score
  // and its popularity field
  Expression expr = JavascriptCompiler.compile("_score * sqrt(popularity)");
  SimpleBindings bindings = new SimpleBindings();
  bindings.add("_score", DoubleValuesSource.SCORES); // the score of the document
  bindings.add("popularity", DoubleValuesSource.fromLongField("popularity")); // the value of the 'popularity' field

  // Aggregates the facet values
  FacetsCollector fc = new FacetsCollector(true);

  // MatchAllDocsQuery is for "browsing" (counts facets
  // for all non-deleted docs in the index); normally
  // you'd use a "normal" query:
  FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);

  // Retrieve results
  Facets facets = new TaxonomyFacetSumValueSource(taxoReader, config, fc, expr.getDoubleValuesSource(bindings));
  FacetResult result = facets.getTopChildren(10, "A");
  
  indexReader.close();
  taxoReader.close();
  
  return result;
}
 

/** User runs a query and counts facets. */
private List<FacetResult> search() throws IOException {
  DirectoryReader indexReader = DirectoryReader.open(indexDir);
  IndexSearcher searcher = new IndexSearcher(indexReader);
  TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);

  FacetsCollector fc = new FacetsCollector();

  // MatchAllDocsQuery is for "browsing" (counts facets
  // for all non-deleted docs in the index); normally
  // you'd use a "normal" query:
  FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);

  // Retrieve results
  List<FacetResult> results = new ArrayList<>();

  // Count both "Publish Date" and "Author" dimensions
  Facets author = new FastTaxonomyFacetCounts("author", taxoReader, config, fc);
  results.add(author.getTopChildren(10, "Author"));

  Facets pubDate = new FastTaxonomyFacetCounts("pubdate", taxoReader, config, fc);
  results.add(pubDate.getTopChildren(10, "Publish Date"));

  indexReader.close();
  taxoReader.close();

  return results;
}
 

private void verifyResults(Directory indexDir, Directory taxoDir) throws IOException {
  DirectoryReader indexReader = DirectoryReader.open(indexDir);
  DirectoryTaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
  IndexSearcher searcher = newSearcher(indexReader);
  
  FacetsCollector collector = new FacetsCollector();
  FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, collector);

  // tag facets
  Facets tagFacets = new FastTaxonomyFacetCounts("$tags", taxoReader, facetConfig, collector);
  FacetResult result = tagFacets.getTopChildren(10, "tag");
  for (LabelAndValue lv: result.labelValues) {
    if (VERBOSE) {
      System.out.println(lv);
    }
    assertEquals(NUM_DOCS, lv.value.intValue());
  }
  
  // id facets
  Facets idFacets = new FastTaxonomyFacetCounts(taxoReader, facetConfig, collector);
  FacetResult idResult = idFacets.getTopChildren(10, "id");
  assertEquals(NUM_DOCS, idResult.childCount);
  assertEquals(NUM_DOCS * 2, idResult.value); // each "id" appears twice
  
  BinaryDocValues bdv = MultiDocValues.getBinaryValues(indexReader, "bdv");
  BinaryDocValues cbdv = MultiDocValues.getBinaryValues(indexReader, "cbdv");
  for (int i = 0; i < indexReader.maxDoc(); i++) {
    assertEquals(i, bdv.nextDoc());
    assertEquals(i, cbdv.nextDoc());
    assertEquals(Integer.parseInt(cbdv.binaryValue().utf8ToString()), Integer.parseInt(bdv.binaryValue().utf8ToString())*2);
  }
  IOUtils.close(indexReader, taxoReader);
}
 

public void testSumScoreAggregator() throws Exception {
  Directory indexDir = newDirectory();
  Directory taxoDir = newDirectory();

  DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);
  IndexWriter iw = new IndexWriter(indexDir, newIndexWriterConfig(new MockAnalyzer(random())));

  FacetsConfig config = new FacetsConfig();

  for(int i = atLeast(30); i > 0; --i) {
    Document doc = new Document();
    if (random().nextBoolean()) { // don't match all documents
      doc.add(new StringField("f", "v", Field.Store.NO));
    }
    doc.add(new FacetField("dim", "a"));
    iw.addDocument(config.build(taxoWriter, doc));
  }
  
  DirectoryReader r = DirectoryReader.open(iw);
  DirectoryTaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoWriter);
  
  FacetsCollector fc = new FacetsCollector(true);
  BoostQuery csq = new BoostQuery(new ConstantScoreQuery(new MatchAllDocsQuery()), 2f);
  
  TopDocs td = FacetsCollector.search(newSearcher(r), csq, 10, fc);

  Facets facets = new TaxonomyFacetSumValueSource(taxoReader, config, fc, DoubleValuesSource.SCORES);
  
  int expected = (int) (csq.getBoost() * td.totalHits.value);
  assertEquals(expected, facets.getSpecificValue("dim", "a").intValue());

  iw.close();
  IOUtils.close(taxoWriter, taxoReader, taxoDir, r, indexDir);
}
 

public void testWithScore() throws Exception {
  Directory indexDir = newDirectory();
  Directory taxoDir = newDirectory();

  DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);
  IndexWriter iw = new IndexWriter(indexDir, newIndexWriterConfig(new MockAnalyzer(random())));

  FacetsConfig config = new FacetsConfig();
  for (int i = 0; i < 4; i++) {
    Document doc = new Document();
    doc.add(new NumericDocValuesField("price", (i+1)));
    doc.add(new FacetField("a", Integer.toString(i % 2)));
    iw.addDocument(config.build(taxoWriter, doc));
  }
  
  DirectoryReader r = DirectoryReader.open(iw);
  DirectoryTaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoWriter);
  
  FacetsCollector fc = new FacetsCollector(true);
  // score documents by their 'price' field - makes asserting the correct counts for the categories easier
  Query q = new FunctionQuery(new LongFieldSource("price"));
  FacetsCollector.search(newSearcher(r), q, 10, fc);
  Facets facets = new TaxonomyFacetSumValueSource(taxoReader, config, fc, DoubleValuesSource.SCORES);
  
  assertEquals("dim=a path=[] value=10.0 childCount=2\n  1 (6.0)\n  0 (4.0)\n", facets.getTopChildren(10, "a").toString());

  iw.close();
  IOUtils.close(taxoWriter, taxoReader, taxoDir, r, indexDir);
}
 

public void testCountAndSumScore() throws Exception {
  Directory indexDir = newDirectory();
  Directory taxoDir = newDirectory();
  
  DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);
  IndexWriter iw = new IndexWriter(indexDir, newIndexWriterConfig(new MockAnalyzer(random())));
  FacetsConfig config = new FacetsConfig();
  config.setIndexFieldName("b", "$b");
  
  for(int i = atLeast(30); i > 0; --i) {
    Document doc = new Document();
    doc.add(new StringField("f", "v", Field.Store.NO));
    doc.add(new FacetField("a", "1"));
    doc.add(new FacetField("b", "1"));
    iw.addDocument(config.build(taxoWriter, doc));
  }
  
  DirectoryReader r = DirectoryReader.open(iw);
  DirectoryTaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoWriter);
  
  FacetsCollector fc = new FacetsCollector(true);
  FacetsCollector.search(newSearcher(r), new MatchAllDocsQuery(), 10, fc);
  
  Facets facets1 = getTaxonomyFacetCounts(taxoReader, config, fc);
  Facets facets2 = new TaxonomyFacetSumValueSource(new DocValuesOrdinalsReader("$b"), taxoReader, config, fc, DoubleValuesSource.SCORES);

  assertEquals(r.maxDoc(), facets1.getTopChildren(10, "a").value.intValue());
  assertEquals(r.maxDoc(), facets2.getTopChildren(10, "b").value.doubleValue(), 1E-10);
  iw.close();
  IOUtils.close(taxoWriter, taxoReader, taxoDir, r, indexDir);
}