Java DirectoryTaxonomyReader类代码示例

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
/** 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<FacetResult>();

  // 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;
}
 

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
/** 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;
}
 

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
/** User drills down on 'Publish Date/2010', and we
 *  return facets for both 'Publish Date' and 'Author',
 *  using DrillSideways. */
private List<FacetResult> drillSideways() 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");

  DrillSideways ds = new DrillSideways(searcher, config, taxoReader);
  DrillSidewaysResult result = ds.search(q, 10);

  // Retrieve results
  List<FacetResult> facets = result.facets.getAllDims(10);

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

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
/** 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<FacetResult>();
  results.add(tags.getTopChildren(10, "tags"));
  results.add(genre.getTopChildren(10, "genre"));

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

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
/** 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;
}
 

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
/** 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;
}
 

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
/** 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;
}
 

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
/** Command-line tool. */
public static void main(String[] args) throws IOException {
  boolean printTree = false;
  String path = null;
  for(int i=0;i<args.length;i++) {
    if (args[i].equals("-printTree")) {
      printTree = true;
    } else {
      path = args[i];
    }
  }
  if (args.length != (printTree ? 2 : 1)) {
    System.out.println("\nUsage: java -classpath ... org.apache.lucene.facet.util.PrintTaxonomyStats [-printTree] /path/to/taxononmy/index\n");
    System.exit(1);
  }
  Directory dir = FSDirectory.open(new File(path));
  TaxonomyReader r = new DirectoryTaxonomyReader(dir);
  printStats(r, System.out, printTree);
  r.close();
  dir.close();
}
 

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
@Override
protected SearcherAndTaxonomy refreshIfNeeded(SearcherAndTaxonomy ref) throws IOException {
  // Must re-open searcher first, otherwise we may get a
  // new reader that references ords not yet known to the
  // taxonomy reader:
  final IndexReader r = ref.searcher.getIndexReader();
  final IndexReader newReader = DirectoryReader.openIfChanged((DirectoryReader) r);
  if (newReader == null) {
    return null;
  } else {
    DirectoryTaxonomyReader tr = TaxonomyReader.openIfChanged(ref.taxonomyReader);
    if (tr == null) {
      ref.taxonomyReader.incRef();
      tr = ref.taxonomyReader;
    } else if (taxoWriter != null && taxoWriter.getTaxonomyEpoch() != taxoEpoch) {
      IOUtils.close(newReader, tr);
      throw new IllegalStateException("DirectoryTaxonomyWriter.replaceTaxonomy was called, which is not allowed when using SearcherTaxonomyManager");
    }

    return new SearcherAndTaxonomy(SearcherManager.getSearcher(searcherFactory, newReader), tr);
  }
}
 

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
public void testEmptyIndex() throws Exception {
  // LUCENE-5045: make sure DrillSideways works with an empty index
  Directory dir = newDirectory();
  Directory taxoDir = newDirectory();
  RandomIndexWriter writer = new RandomIndexWriter(random(), dir);
  DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir, IndexWriterConfig.OpenMode.CREATE);
  IndexSearcher searcher = newSearcher(writer.getReader());
  TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoWriter);

  // Count "Author"
  FacetsConfig config = new FacetsConfig();
  DrillSideways ds = new DrillSideways(searcher, config, taxoReader);
  DrillDownQuery ddq = new DrillDownQuery(config);
  ddq.add("Author", "Lisa");
  
  DrillSidewaysResult r = ds.search(ddq, 10); // this used to fail on IllegalArgEx
  assertEquals(0, r.hits.totalHits);

  r = ds.search(ddq, null, null, 10, new Sort(new SortField("foo", SortField.Type.INT)), false, false); // this used to fail on IllegalArgEx
  assertEquals(0, r.hits.totalHits);
  
  IOUtils.close(writer, taxoWriter, searcher.getIndexReader(), taxoReader, dir, taxoDir);
}
 

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
public void testChildCount() throws Exception {
  // LUCENE-4885: FacetResult.numValidDescendants was not set properly by FacetsAccumulator
  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 < 10; i++) {
    Document doc = new Document();
    doc.add(new FacetField("a", Integer.toString(i)));
    iw.addDocument(config.build(taxoWriter, doc));
  }
  
  DirectoryReader r = DirectoryReader.open(iw, true);
  DirectoryTaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoWriter);
  
  FacetsCollector sfc = new FacetsCollector();
  newSearcher(r).search(new MatchAllDocsQuery(), sfc);
  Facets facets = getTaxonomyFacetCounts(taxoReader, config, sfc);
  
  assertEquals(10, facets.getTopChildren(2, "a").childCount);

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

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
/**  Test writing an empty index, and seeing that a reader finds in it
  the root category, and only it. We check all the methods on that
  root category return the expected results.
 */
@Test
public void testRootOnly() throws Exception {
  Directory indexDir = newDirectory();
  TaxonomyWriter tw = new DirectoryTaxonomyWriter(indexDir);
  // right after opening the index, it should already contain the
  // root, so have size 1:
  assertEquals(1, tw.getSize());
  tw.close();
  TaxonomyReader tr = new DirectoryTaxonomyReader(indexDir);
  assertEquals(1, tr.getSize());
  assertEquals(0, tr.getPath(0).length);
  assertEquals(TaxonomyReader.INVALID_ORDINAL, tr.getParallelTaxonomyArrays().parents()[0]);
  assertEquals(0, tr.getOrdinal(new FacetLabel()));
  tr.close();
  indexDir.close();
}
 

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
@Test
public void testNRT() throws Exception {
  Directory dir = newDirectory();
  DirectoryTaxonomyWriter writer = new DirectoryTaxonomyWriter(dir);
  TaxonomyReader reader = new DirectoryTaxonomyReader(writer);
  
  FacetLabel cp = new FacetLabel("a");
  writer.addCategory(cp);
  TaxonomyReader newReader = TaxonomyReader.openIfChanged(reader);
  assertNotNull("expected a new instance", newReader);
  assertEquals(2, newReader.getSize());
  assertNotSame(TaxonomyReader.INVALID_ORDINAL, newReader.getOrdinal(cp));
  reader.close();
  reader = newReader;
  
  writer.close();
  reader.close();
  
  dir.close();
}
 

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
public void testNoScore() 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, true);
  DirectoryTaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoWriter);

  FacetsCollector sfc = new FacetsCollector();
  newSearcher(r).search(new MatchAllDocsQuery(), sfc);
  Facets facets = new TaxonomyFacetSumValueSource(taxoReader, config, sfc, new LongFieldSource("price"));
  assertEquals("dim=a path=[] value=10.0 childCount=2\n  1 (6.0)\n  0 (4.0)\n", facets.getTopChildren(10, "a").toString());
  
  IOUtils.close(taxoWriter, iw, taxoReader, taxoDir, r, indexDir);
}
 

import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; //导入依赖的package包/类
@Test
public void testFaceting() throws Exception {
	DirectoryTaxonomyWriter tw = new DirectoryTaxonomyWriter(taxonomyDirectory);
	FacetsConfig cfg = new FacetsConfig();
	Document doc1 = new Document();
	Document doc2 = new Document();
	Document doc3 = new Document();
	doc1.add(new FacetField("category", "c2"));
	doc2.add(new FacetField("category", "c2"));
	doc3.add(new FacetField("category", "c1"));
	index(cfg.build(tw, doc1), cfg.build(tw, doc2), cfg.build(tw, doc3));
	tw.close();
	DirectoryTaxonomyReader tr = new DirectoryTaxonomyReader(taxonomyDirectory);
	FacetsCollector fc = new FacetsCollector();
	FacetsCollector.search(openSearcher(), new MatchAllDocsQuery(), 10, fc);
	Facets facets = new FastTaxonomyFacetCounts(tr, cfg, fc);
	FacetResult category = facets.getTopChildren(10, "category");

	assertEquals(2, category.childCount);

}