LUCENE-5525: implement MultiFacets.getAllDims

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1578042 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Michael McCandless 2014-03-16 11:45:34 +00:00
parent d99d2992cd
commit f44831feb9
5 changed files with 83 additions and 6 deletions

View File

@ -184,6 +184,10 @@ Bug fixes
ArrayIndexOutOfBoundsException if a parent document had no children
(Sally Ang via Mike McCandless)
* LUCENE-5525: Implement MultiFacets.getAllDims, so you can do sparse
facets through DrillSideways, for example. (Jose Peleteiro, Mike
McCandless)
Test Framework
* LUCENE-5449: Rename _TestUtil and _TestHelper to remove the leading _.

View File

@ -24,6 +24,8 @@ import java.util.List;
import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.facet.DrillDownQuery;
import org.apache.lucene.facet.DrillSideways.DrillSidewaysResult;
import org.apache.lucene.facet.DrillSideways;
import org.apache.lucene.facet.FacetField;
import org.apache.lucene.facet.FacetResult;
import org.apache.lucene.facet.Facets;
@ -145,7 +147,8 @@ public class SimpleFacetsExample {
return results;
}
/** User drills down on 'Publish Date/2010'. */
/** 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);
@ -170,6 +173,33 @@ public class SimpleFacetsExample {
return result;
}
/** 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;
}
/** Runs the search example. */
public List<FacetResult> runFacetOnly() throws IOException {
index();
@ -188,6 +218,12 @@ public class SimpleFacetsExample {
return drillDown();
}
/** Runs the drill-sideways example. */
public List<FacetResult> runDrillSideways() throws IOException {
index();
return drillSideways();
}
/** Runs the search and drill-down examples and prints the results. */
public static void main(String[] args) throws Exception {
System.out.println("Facet counting example:");
@ -204,11 +240,17 @@ public class SimpleFacetsExample {
System.out.println("Author: " + results.get(0));
System.out.println("Publish Date: " + results.get(1));
System.out.println("\n");
System.out.println("Facet drill-down example (Publish Date/2010):");
System.out.println("---------------------------------------------");
System.out.println("Author: " + example.runDrillDown());
System.out.println("\n");
System.out.println("Facet drill-sideways example (Publish Date/2010):");
System.out.println("---------------------------------------------");
for(FacetResult result : example.runDrillSideways()) {
System.out.println(result);
}
}
}

View File

@ -20,7 +20,6 @@ package org.apache.lucene.demo.facet;
import java.util.List;
import org.apache.lucene.facet.FacetResult;
import org.apache.lucene.facet.taxonomy.FacetLabel;
import org.apache.lucene.util.LuceneTestCase;
import org.junit.Test;
@ -48,4 +47,11 @@ public class TestSimpleFacetsExample extends LuceneTestCase {
FacetResult result = new SimpleFacetsExample().runDrillDown();
assertEquals("dim=Author path=[] value=2 childCount=2\n Bob (1)\n Lisa (1)\n", result.toString());
}
@Test
public void testDrillSideways() throws Exception {
List<FacetResult> result = new SimpleFacetsExample().runDrillSideways();
assertEquals("dim=Publish Date path=[] value=5 childCount=3\n 2010 (2)\n 2012 (2)\n 1999 (1)\n", result.get(0).toString());
assertEquals("dim=Author path=[] value=2 childCount=2\n Bob (1)\n Lisa (1)\n", result.get(1).toString());
}
}

View File

@ -18,6 +18,7 @@ package org.apache.lucene.facet;
*/
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
@ -65,7 +66,25 @@ public class MultiFacets extends Facets {
@Override
public List<FacetResult> getAllDims(int topN) throws IOException {
// TODO
throw new UnsupportedOperationException();
List<FacetResult> results = new ArrayList<FacetResult>();
// First add the specific dim's facets:
for(Map.Entry<String,Facets> ent : dimToFacets.entrySet()) {
results.add(ent.getValue().getTopChildren(topN, ent.getKey()));
}
if (defaultFacets != null) {
// Then add all default facets as long as we didn't
// already add that dim:
for(FacetResult result : defaultFacets.getAllDims(topN)) {
if (dimToFacets.containsKey(result.dim) == false) {
results.add(result);
}
}
}
return results;
}
}

View File

@ -148,7 +148,7 @@ public class TestDrillSideways extends FacetTestCase {
// published once:
assertEquals("dim=Author path=[] value=5 childCount=4\n Lisa (2)\n Bob (1)\n Susan (1)\n Frank (1)\n", r.facets.getTopChildren(10, "Author").toString());
// Another simple case: drill-down on on single fields
// Another simple case: drill-down on single fields
// but OR of two values
ddq = new DrillDownQuery(config);
ddq.add("Author", "Lisa");
@ -163,6 +163,12 @@ public class TestDrillSideways extends FacetTestCase {
// published once:
assertEquals("dim=Author path=[] value=5 childCount=4\n Lisa (2)\n Bob (1)\n Susan (1)\n Frank (1)\n", r.facets.getTopChildren(10, "Author").toString());
assertTrue(r.facets instanceof MultiFacets);
List<FacetResult> allResults = r.facets.getAllDims(10);
assertEquals(2, allResults.size());
assertEquals("dim=Author path=[] value=5 childCount=4\n Lisa (2)\n Bob (1)\n Susan (1)\n Frank (1)\n", allResults.get(0).toString());
assertEquals("dim=Publish Date path=[] value=3 childCount=2\n 2010 (2)\n 2012 (1)\n", allResults.get(1).toString());
// More interesting case: drill-down on two fields
ddq = new DrillDownQuery(config);
ddq.add("Author", "Lisa");