Skip to content

Instantly share code, notes, and snippets.

@arjones
Forked from guenter/gist:1424333
Created November 10, 2012 15:10
Show Gist options
  • Save arjones/4051359 to your computer and use it in GitHub Desktop.
Save arjones/4051359 to your computer and use it in GitHub Desktop.
Lucene Facets Drill Down
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.facet.index.CategoryDocumentBuilder;
import org.apache.lucene.facet.index.params.DefaultFacetIndexingParams;
import org.apache.lucene.facet.index.params.FacetIndexingParams;
import org.apache.lucene.facet.search.DrillDown;
import org.apache.lucene.facet.search.FacetsCollector;
import org.apache.lucene.facet.search.params.CountFacetRequest;
import org.apache.lucene.facet.search.params.FacetRequest;
import org.apache.lucene.facet.search.params.FacetSearchParams;
import org.apache.lucene.facet.search.results.FacetResult;
import org.apache.lucene.facet.search.results.FacetResultNode;
import org.apache.lucene.facet.taxonomy.CategoryPath;
import org.apache.lucene.facet.taxonomy.TaxonomyReader;
import org.apache.lucene.facet.taxonomy.TaxonomyWriter;
import org.apache.lucene.facet.taxonomy.lucene.LuceneTaxonomyReader;
import org.apache.lucene.facet.taxonomy.lucene.LuceneTaxonomyWriter;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.MatchAllDocsQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.QueryWrapperFilter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
/**
* @author Tobi Knaup
*/
public class FacetExample {
Directory indexDirectory;
Directory taxonomyDirectory;
public static void main(String[] args) throws IOException {
FacetExample example = new FacetExample();
example.run();
}
FacetExample() throws IOException {
this.indexDirectory = new RAMDirectory();
this.taxonomyDirectory = new RAMDirectory();
}
void run() throws IOException {
IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_34, new StandardAnalyzer(Version.LUCENE_34));
IndexWriter indexWriter = new IndexWriter(indexDirectory, config);
TaxonomyWriter taxonomyWriter = new LuceneTaxonomyWriter(taxonomyDirectory);
CategoryDocumentBuilder categoryDocumentBuilder = new CategoryDocumentBuilder(taxonomyWriter);
CategoryPath mission = new CategoryPath("neighborhood", "Mission");
CategoryPath soma = new CategoryPath("neighborhood", "SOMA");
// Add document 1, with neighborhood Mission
Document doc1 = new Document();
List<CategoryPath> doc1Categories = new ArrayList<CategoryPath>();
doc1Categories.add(mission);
categoryDocumentBuilder.setCategoryPaths(doc1Categories).build(doc1);
indexWriter.addDocument(doc1);
// Add document 1, with neighborhood SOMA
Document doc2 = new Document();
List<CategoryPath> doc2Categories = new ArrayList<CategoryPath>();
doc2Categories.add(soma);
categoryDocumentBuilder.setCategoryPaths(doc2Categories).build(doc2);
indexWriter.addDocument(doc2);
indexWriter.commit();
taxonomyWriter.commit();
IndexReader indexReader = IndexReader.open(indexDirectory, true);
IndexSearcher indexSearcher = new IndexSearcher(indexReader);
// Search for all documents
Query matchAllDocsQuery1 = new MatchAllDocsQuery();
FacetsCollector facetsCollector1 = getFacetsCollector();
indexSearcher.search(matchAllDocsQuery1, new QueryWrapperFilter(matchAllDocsQuery1), facetsCollector1);
// Output:
// SOMA: 1
// Mission: 1
System.out.println("All documents query");
printFacetResult(facetsCollector1.getFacetResults());
// Drill down query for the Mission
Query matchAllDocsQuery2 = new MatchAllDocsQuery();
Query missionQuery = DrillDown.query(matchAllDocsQuery2, mission);
FacetsCollector facetsCollector2 = getFacetsCollector();
indexSearcher.search(missionQuery, new QueryWrapperFilter(matchAllDocsQuery2), facetsCollector2);
// Output:
// Mission: 1
// But I want the same facet counts like before.
// Is this possible without running two queries: one with the drill down query to retrieve the documents,
// and another one without the drill down query to count the facets?
System.out.println("Drill down query");
printFacetResult(facetsCollector2.getFacetResults());
}
void printFacetResult(List<FacetResult> facetResults) {
for (FacetResult facetResult : facetResults) {
FacetResultNode resultNode = facetResult.getFacetResultNode();
if (resultNode.getNumSubResults() > 0) {
int numSubResults = resultNode.getNumSubResults();
String facetName = resultNode.getLabel().lastComponent();
for (FacetResultNode node : resultNode.getSubResults()) {
String label = node.getLabel().lastComponent();
Integer count = (int) node.getValue();
System.out.println(label + ": " + count);
}
}
}
}
FacetsCollector getFacetsCollector() throws IOException {
IndexReader indexReader = IndexReader.open(indexDirectory, true);
TaxonomyReader taxonomyReader = new LuceneTaxonomyReader(taxonomyDirectory);
CategoryPath neighborhood = new CategoryPath("neighborhood");
FacetIndexingParams indexingParams = new DefaultFacetIndexingParams();
FacetSearchParams facetSearchParams = new FacetSearchParams(indexingParams);
FacetRequest neighborhoodFacetRequest = new CountFacetRequest(neighborhood, 10);
facetSearchParams.addFacetRequest(neighborhoodFacetRequest);
return new FacetsCollector(facetSearchParams, indexReader, taxonomyReader);
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment