Java Facets.getTopChildren方法代码示例

import org.apache.lucene.facet.Facets; //导入方法依赖的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.Facets; //导入方法依赖的package包/类
/** 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;
}
 

import org.apache.lucene.facet.Facets; //导入方法依赖的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.Facets; //导入方法依赖的package包/类
/** 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");
}
 

import org.apache.lucene.facet.Facets; //导入方法依赖的package包/类
/** User runs a query and counts facets. */
public FacetResult search() throws IOException {

  FacetsCollector fc = new FacetsCollector();

  searcher.search(new MatchAllDocsQuery(), fc);

  Facets facets = new DoubleRangeFacetCounts("field", getDistanceValueSource(), fc,
                                             getBoundingBoxFilter(ORIGIN_LATITUDE, ORIGIN_LONGITUDE, 10.0),
                                             ONE_KM,
                                             TWO_KM,
                                             FIVE_KM,
                                             TEN_KM);

  return facets.getTopChildren(10, "field");
}
 

import org.apache.lucene.facet.Facets; //导入方法依赖的package包/类
/** 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;
}
 

import org.apache.lucene.facet.Facets; //导入方法依赖的package包/类
public int getTotalVariationsCountFacet(List<? extends FeatureFile> files, Query query) throws IOException {
    if (CollectionUtils.isEmpty(files)) {
        return 0;
    }

    SimpleFSDirectory[] indexes = fileManager.getIndexesForFiles(files);

    try (MultiReader reader = openMultiReader(indexes)) {
        if (reader.numDocs() == 0) {
            return 0;
        }

        FacetsCollector facetsCollector = new FacetsCollector();
        IndexSearcher searcher = new IndexSearcher(reader);
        searcher.search(query, facetsCollector);

        Facets facets = new SortedSetDocValuesFacetCounts(new DefaultSortedSetDocValuesReaderState(reader,
                                                       FeatureIndexFields.FACET_UID.fieldName), facetsCollector);
        FacetResult res = facets.getTopChildren(reader.numDocs(), FeatureIndexFields.F_UID.getFieldName());
        if (res == null) {
            return 0;
        }

        return res.childCount;
    } finally {
        for (SimpleFSDirectory index : indexes) {
            IOUtils.closeQuietly(index);
        }
    }
}
 

import org.apache.lucene.facet.Facets; //导入方法依赖的package包/类
/**
 * Returns a {@code List} of chromosome IDs for a project, specified by ID, where variations exist and satisfy a
 * specified query
 *
 * @param projectId an ID of a project, which index to query
 * @param query     a query to filter variations
 * @return a {@code List} of chromosome IDs
 * @throws IOException
 */
public List<Long> getChromosomeIdsWhereVariationsPresentFacet(long projectId, Query query) throws IOException {
    List<Long> chromosomeIds = new ArrayList<>();

    try (
        Directory index = fileManager.getIndexForProject(projectId);
        IndexReader reader = DirectoryReader.open(index)
    ) {
        if (reader.numDocs() == 0) {
            return Collections.emptyList();
        }

        FacetsCollector facetsCollector = new FacetsCollector();
        IndexSearcher searcher = new IndexSearcher(reader);
        searcher.search(query, facetsCollector);

        Facets facets = new SortedSetDocValuesFacetCounts(new DefaultSortedSetDocValuesReaderState(reader,
                FeatureIndexFields.FACET_CHR_ID.getFieldName()), facetsCollector);
        FacetResult res = facets.getTopChildren(FACET_LIMIT, FeatureIndexFields.CHR_ID.getFieldName());
        if (res == null) {
            return Collections.emptyList();
        }

        for (LabelAndValue labelAndValue : res.labelValues) {
            chromosomeIds.add(Long.parseLong(labelAndValue.label));
        }
    }

    return chromosomeIds;
}
 

import org.apache.lucene.facet.Facets; //导入方法依赖的package包/类
/**
 * Processes the faceting results and adds them to the QueryResults builder.
 *
 * @param indexSearcher the IndexSearcher performing the query
 * @param facetsCollector the FacetsCollector that was used for the search
 * @param facetFields the fields to Facet on
 * @param resultBuilder the QueryResults.Builder
 * @throws IOException if an error occurs performing faceting
 */
protected void processFacetResults(final IndexSearcher indexSearcher, final FacetsCollector facetsCollector, final Set<String> facetFields,
                                   final QueryResults.Builder<QR> resultBuilder) throws IOException {
    if (facetFields == null) {
        return;
    }

    for (String facetField : facetFields) {
        final List<FacetCount> facetResultCounts = new ArrayList<>();

        // TODO this will produce an exception if no documents were indexed with the field to facet on
        // java.lang.IllegalArgumentException: field "foo" was not indexed with SortedSetDocValues
        // at org.apache.lucene.facet.sortedset.DefaultSortedSetDocValuesReaderState.<init>(DefaultSortedSetDocValuesReaderState.java:72)

       if (facetsCollector.getMatchingDocs() != null && facetsCollector.getMatchingDocs().size() > 0) {
            final SortedSetDocValuesReaderState state = new DefaultSortedSetDocValuesReaderState(indexSearcher.getIndexReader(), facetField);
            final Facets facets = new SortedSetDocValuesFacetCounts(state, facetsCollector);

            org.apache.lucene.facet.FacetResult result = facets.getTopChildren(10, facetField);
            for (int i = 0; i < result.childCount; i++) {
                LabelAndValue lv = result.labelValues[i];
                facetResultCounts.add(new FacetCount(lv.label, lv.value.longValue()));
            }
        }
        resultBuilder.addFacetResult(new FacetResult(facetField, facetResultCounts));
    }
}
 

import org.apache.lucene.facet.Facets; //导入方法依赖的package包/类
public int getTotalVariationsCountFacet(List<? extends FeatureFile> files, Query query) throws IOException {
    if (CollectionUtils.isEmpty(files)) {
        return 0;
    }

    SimpleFSDirectory[] indexes = fileManager.getIndexesForFiles(files);
    long totalIndexSize = getTotalIndexSize(indexes);
    if (totalIndexSize > luceneIndexMaxSizeForGrouping) {
        return 0;
    }

    try (MultiReader reader = openMultiReader(indexes)) {
        if (reader.numDocs() == 0) {
            return 0;
        }

        FacetsCollector facetsCollector = new FacetsCollector();
        IndexSearcher searcher = new IndexSearcher(reader);
        searcher.search(query, facetsCollector);

        Facets facets = new SortedSetDocValuesFacetCounts(new DefaultSortedSetDocValuesReaderState(reader,
                FeatureIndexFields.FACET_UID.fieldName), facetsCollector);
        FacetResult res = facets.getTopChildren(reader.numDocs(), FeatureIndexFields.F_UID.getFieldName());
        if (res == null) {
            return 0;
        }

        return res.childCount;
    } finally {
        for (SimpleFSDirectory index : indexes) {
            IOUtils.closeQuietly(index);
        }
    }
}
 

import org.apache.lucene.facet.Facets; //导入方法依赖的package包/类
/**
 * Returns a {@code List} of chromosome IDs for a project, specified by ID, where variations exist and satisfy a
 * specified query
 *
 * @param projectId an ID of a project, which index to query
 * @param query     a query to filter variations
 * @return a {@code List} of chromosome IDs
 * @throws IOException
 */
public List<Long> getChromosomeIdsWhereVariationsPresentFacet(long projectId, Query query) throws IOException {
    List<Long> chromosomeIds = new ArrayList<>();

    try (
            Directory index = fileManager.getIndexForProject(projectId);
            IndexReader reader = DirectoryReader.open(index)
    ) {
        if (reader.numDocs() == 0) {
            return Collections.emptyList();
        }

        FacetsCollector facetsCollector = new FacetsCollector();
        IndexSearcher searcher = new IndexSearcher(reader);
        searcher.search(query, facetsCollector);

        Facets facets = new SortedSetDocValuesFacetCounts(new DefaultSortedSetDocValuesReaderState(reader,
                FeatureIndexFields.FACET_CHR_ID.getFieldName()), facetsCollector);
        FacetResult res = facets.getTopChildren(FACET_LIMIT, FeatureIndexFields.CHR_ID.getFieldName());
        if (res == null) {
            return Collections.emptyList();
        }

        for (LabelAndValue labelAndValue : res.labelValues) {
            chromosomeIds.add(Long.parseLong(labelAndValue.label));
        }
    }

    return chromosomeIds;
}
 

import org.apache.lucene.facet.Facets; //导入方法依赖的package包/类
/** 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(new SortField("_score", SortField.Type.SCORE)); // the score of the document
  bindings.add(new SortField("popularity", SortField.Type.LONG)); // 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.getValueSource(bindings));
  FacetResult result = facets.getTopChildren(10, "A");
  
  indexReader.close();
  taxoReader.close();
  
  return result;
}
 

import org.apache.lucene.facet.Facets; //导入方法依赖的package包/类
public void testBasicLong() throws Exception {
  Directory d = newDirectory();
  RandomIndexWriter w = new RandomIndexWriter(random(), d);
  Document doc = new Document();
  NumericDocValuesField field = new NumericDocValuesField("field", 0L);
  doc.add(field);
  for(long l=0;l<100;l++) {
    field.setLongValue(l);
    w.addDocument(doc);
  }

  // Also add Long.MAX_VALUE
  field.setLongValue(Long.MAX_VALUE);
  w.addDocument(doc);

  IndexReader r = w.getReader();
  w.close();

  FacetsCollector fc = new FacetsCollector();
  IndexSearcher s = newSearcher(r);
  s.search(new MatchAllDocsQuery(), fc);

  Facets facets = new LongRangeFacetCounts("field", fc,
      new LongRange("less than 10", 0L, true, 10L, false),
      new LongRange("less than or equal to 10", 0L, true, 10L, true),
      new LongRange("over 90", 90L, false, 100L, false),
      new LongRange("90 or above", 90L, true, 100L, false),
      new LongRange("over 1000", 1000L, false, Long.MAX_VALUE, true));

  FacetResult result = facets.getTopChildren(10, "field");
  assertEquals("dim=field path=[] value=22 childCount=5\n  less than 10 (10)\n  less than or equal to 10 (11)\n  over 90 (9)\n  90 or above (10)\n  over 1000 (1)\n",
               result.toString());
  
  r.close();
  d.close();
}
 

import org.apache.lucene.facet.Facets; //导入方法依赖的package包/类
public void testLongMinMax() throws Exception {

    Directory d = newDirectory();
    RandomIndexWriter w = new RandomIndexWriter(random(), d);
    Document doc = new Document();
    NumericDocValuesField field = new NumericDocValuesField("field", 0L);
    doc.add(field);
    field.setLongValue(Long.MIN_VALUE);
    w.addDocument(doc);
    field.setLongValue(0);
    w.addDocument(doc);
    field.setLongValue(Long.MAX_VALUE);
    w.addDocument(doc);

    IndexReader r = w.getReader();
    w.close();

    FacetsCollector fc = new FacetsCollector();
    IndexSearcher s = newSearcher(r);
    s.search(new MatchAllDocsQuery(), fc);

    Facets facets = new LongRangeFacetCounts("field", fc,
        new LongRange("min", Long.MIN_VALUE, true, Long.MIN_VALUE, true),
        new LongRange("max", Long.MAX_VALUE, true, Long.MAX_VALUE, true),
        new LongRange("all0", Long.MIN_VALUE, true, Long.MAX_VALUE, true),
        new LongRange("all1", Long.MIN_VALUE, false, Long.MAX_VALUE, true),
        new LongRange("all2", Long.MIN_VALUE, true, Long.MAX_VALUE, false),
        new LongRange("all3", Long.MIN_VALUE, false, Long.MAX_VALUE, false));

    FacetResult result = facets.getTopChildren(10, "field");
    assertEquals("dim=field path=[] value=3 childCount=6\n  min (1)\n  max (1)\n  all0 (3)\n  all1 (2)\n  all2 (2)\n  all3 (1)\n",
                 result.toString());
    
    r.close();
    d.close();
  }
 

import org.apache.lucene.facet.Facets; //导入方法依赖的package包/类
public void testOverlappedEndStart() throws Exception {
  Directory d = newDirectory();
  RandomIndexWriter w = new RandomIndexWriter(random(), d);
  Document doc = new Document();
  NumericDocValuesField field = new NumericDocValuesField("field", 0L);
  doc.add(field);
  for(long l=0;l<100;l++) {
    field.setLongValue(l);
    w.addDocument(doc);
  }
  field.setLongValue(Long.MAX_VALUE);
  w.addDocument(doc);

  IndexReader r = w.getReader();
  w.close();

  FacetsCollector fc = new FacetsCollector();
  IndexSearcher s = newSearcher(r);
  s.search(new MatchAllDocsQuery(), fc);

  Facets facets = new LongRangeFacetCounts("field", fc,
      new LongRange("0-10", 0L, true, 10L, true),
      new LongRange("10-20", 10L, true, 20L, true),
      new LongRange("20-30", 20L, true, 30L, true),
      new LongRange("30-40", 30L, true, 40L, true));
  
  FacetResult result = facets.getTopChildren(10, "field");
  assertEquals("dim=field path=[] value=41 childCount=4\n  0-10 (11)\n  10-20 (11)\n  20-30 (11)\n  30-40 (11)\n",
               result.toString());
  
  r.close();
  d.close();
}