001package org.apache.lucene.demo.facet; 002 003/* 004 * Licensed to the Apache Software Foundation (ASF) under one or more 005 * contributor license agreements. See the NOTICE file distributed with 006 * this work for additional information regarding copyright ownership. 007 * The ASF licenses this file to You under the Apache License, Version 2.0 008 * (the "License"); you may not use this file except in compliance with 009 * the License. You may obtain a copy of the License at 010 * 011 * http://www.apache.org/licenses/LICENSE-2.0 012 * 013 * Unless required by applicable law or agreed to in writing, software 014 * distributed under the License is distributed on an "AS IS" BASIS, 015 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 016 * See the License for the specific language governing permissions and 017 * limitations under the License. 018 */ 019 020import java.io.IOException; 021import java.util.ArrayList; 022import java.util.List; 023 024import org.apache.lucene.analysis.core.WhitespaceAnalyzer; 025import org.apache.lucene.document.Document; 026import org.apache.lucene.facet.DrillDownQuery; 027import org.apache.lucene.facet.DrillSideways.DrillSidewaysResult; 028import org.apache.lucene.facet.DrillSideways; 029import org.apache.lucene.facet.FacetField; 030import org.apache.lucene.facet.FacetResult; 031import org.apache.lucene.facet.Facets; 032import org.apache.lucene.facet.FacetsCollector; 033import org.apache.lucene.facet.FacetsConfig; 034import org.apache.lucene.facet.taxonomy.FastTaxonomyFacetCounts; 035import org.apache.lucene.facet.taxonomy.TaxonomyReader; 036import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader; 037import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyWriter; 038import org.apache.lucene.index.DirectoryReader; 039import org.apache.lucene.index.IndexWriter; 040import org.apache.lucene.index.IndexWriterConfig; 041import org.apache.lucene.search.IndexSearcher; 042import org.apache.lucene.search.MatchAllDocsQuery; 043import org.apache.lucene.store.Directory; 044import org.apache.lucene.store.RAMDirectory; 045 046/** Shows simple usage of faceted indexing and search. */ 047public class SimpleFacetsExample { 048 049 private final Directory indexDir = new RAMDirectory(); 050 private final Directory taxoDir = new RAMDirectory(); 051 private final FacetsConfig config = new FacetsConfig(); 052 053 /** Empty constructor */ 054 public SimpleFacetsExample() { 055 config.setHierarchical("Publish Date", true); 056 } 057 058 /** Build the example index. */ 059 private void index() throws IOException { 060 IndexWriter indexWriter = new IndexWriter(indexDir, new IndexWriterConfig(FacetExamples.EXAMPLES_VER, 061 new WhitespaceAnalyzer(FacetExamples.EXAMPLES_VER))); 062 063 // Writes facet ords to a separate directory from the main index 064 DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir); 065 066 Document doc = new Document(); 067 doc.add(new FacetField("Author", "Bob")); 068 doc.add(new FacetField("Publish Date", "2010", "10", "15")); 069 indexWriter.addDocument(config.build(taxoWriter, doc)); 070 071 doc = new Document(); 072 doc.add(new FacetField("Author", "Lisa")); 073 doc.add(new FacetField("Publish Date", "2010", "10", "20")); 074 indexWriter.addDocument(config.build(taxoWriter, doc)); 075 076 doc = new Document(); 077 doc.add(new FacetField("Author", "Lisa")); 078 doc.add(new FacetField("Publish Date", "2012", "1", "1")); 079 indexWriter.addDocument(config.build(taxoWriter, doc)); 080 081 doc = new Document(); 082 doc.add(new FacetField("Author", "Susan")); 083 doc.add(new FacetField("Publish Date", "2012", "1", "7")); 084 indexWriter.addDocument(config.build(taxoWriter, doc)); 085 086 doc = new Document(); 087 doc.add(new FacetField("Author", "Frank")); 088 doc.add(new FacetField("Publish Date", "1999", "5", "5")); 089 indexWriter.addDocument(config.build(taxoWriter, doc)); 090 091 indexWriter.close(); 092 taxoWriter.close(); 093 } 094 095 /** User runs a query and counts facets. */ 096 private List<FacetResult> facetsWithSearch() throws IOException { 097 DirectoryReader indexReader = DirectoryReader.open(indexDir); 098 IndexSearcher searcher = new IndexSearcher(indexReader); 099 TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir); 100 101 FacetsCollector fc = new FacetsCollector(); 102 103 // MatchAllDocsQuery is for "browsing" (counts facets 104 // for all non-deleted docs in the index); normally 105 // you'd use a "normal" query: 106 FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc); 107 108 // Retrieve results 109 List<FacetResult> results = new ArrayList<>(); 110 111 // Count both "Publish Date" and "Author" dimensions 112 Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc); 113 results.add(facets.getTopChildren(10, "Author")); 114 results.add(facets.getTopChildren(10, "Publish Date")); 115 116 indexReader.close(); 117 taxoReader.close(); 118 119 return results; 120 } 121 122 /** User runs a query and counts facets only without collecting the matching documents.*/ 123 private List<FacetResult> facetsOnly() throws IOException { 124 DirectoryReader indexReader = DirectoryReader.open(indexDir); 125 IndexSearcher searcher = new IndexSearcher(indexReader); 126 TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir); 127 128 FacetsCollector fc = new FacetsCollector(); 129 130 // MatchAllDocsQuery is for "browsing" (counts facets 131 // for all non-deleted docs in the index); normally 132 // you'd use a "normal" query: 133 searcher.search(new MatchAllDocsQuery(), null /*Filter */, fc); 134 135 // Retrieve results 136 List<FacetResult> results = new ArrayList<>(); 137 138 // Count both "Publish Date" and "Author" dimensions 139 Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc); 140 141 results.add(facets.getTopChildren(10, "Author")); 142 results.add(facets.getTopChildren(10, "Publish Date")); 143 144 indexReader.close(); 145 taxoReader.close(); 146 147 return results; 148 } 149 150 /** User drills down on 'Publish Date/2010', and we 151 * return facets for 'Author' */ 152 private FacetResult drillDown() throws IOException { 153 DirectoryReader indexReader = DirectoryReader.open(indexDir); 154 IndexSearcher searcher = new IndexSearcher(indexReader); 155 TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir); 156 157 // Passing no baseQuery means we drill down on all 158 // documents ("browse only"): 159 DrillDownQuery q = new DrillDownQuery(config); 160 161 // Now user drills down on Publish Date/2010: 162 q.add("Publish Date", "2010"); 163 FacetsCollector fc = new FacetsCollector(); 164 FacetsCollector.search(searcher, q, 10, fc); 165 166 // Retrieve results 167 Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc); 168 FacetResult result = facets.getTopChildren(10, "Author"); 169 170 indexReader.close(); 171 taxoReader.close(); 172 173 return result; 174 } 175 176 /** User drills down on 'Publish Date/2010', and we 177 * return facets for both 'Publish Date' and 'Author', 178 * using DrillSideways. */ 179 private List<FacetResult> drillSideways() throws IOException { 180 DirectoryReader indexReader = DirectoryReader.open(indexDir); 181 IndexSearcher searcher = new IndexSearcher(indexReader); 182 TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir); 183 184 // Passing no baseQuery means we drill down on all 185 // documents ("browse only"): 186 DrillDownQuery q = new DrillDownQuery(config); 187 188 // Now user drills down on Publish Date/2010: 189 q.add("Publish Date", "2010"); 190 191 DrillSideways ds = new DrillSideways(searcher, config, taxoReader); 192 DrillSidewaysResult result = ds.search(q, 10); 193 194 // Retrieve results 195 List<FacetResult> facets = result.facets.getAllDims(10); 196 197 indexReader.close(); 198 taxoReader.close(); 199 200 return facets; 201 } 202 203 /** Runs the search example. */ 204 public List<FacetResult> runFacetOnly() throws IOException { 205 index(); 206 return facetsOnly(); 207 } 208 209 /** Runs the search example. */ 210 public List<FacetResult> runSearch() throws IOException { 211 index(); 212 return facetsWithSearch(); 213 } 214 215 /** Runs the drill-down example. */ 216 public FacetResult runDrillDown() throws IOException { 217 index(); 218 return drillDown(); 219 } 220 221 /** Runs the drill-sideways example. */ 222 public List<FacetResult> runDrillSideways() throws IOException { 223 index(); 224 return drillSideways(); 225 } 226 227 /** Runs the search and drill-down examples and prints the results. */ 228 public static void main(String[] args) throws Exception { 229 System.out.println("Facet counting example:"); 230 System.out.println("-----------------------"); 231 SimpleFacetsExample example1 = new SimpleFacetsExample(); 232 List<FacetResult> results1 = example1.runFacetOnly(); 233 System.out.println("Author: " + results1.get(0)); 234 System.out.println("Publish Date: " + results1.get(1)); 235 236 System.out.println("Facet counting example (combined facets and search):"); 237 System.out.println("-----------------------"); 238 SimpleFacetsExample example = new SimpleFacetsExample(); 239 List<FacetResult> results = example.runSearch(); 240 System.out.println("Author: " + results.get(0)); 241 System.out.println("Publish Date: " + results.get(1)); 242 243 System.out.println("\n"); 244 System.out.println("Facet drill-down example (Publish Date/2010):"); 245 System.out.println("---------------------------------------------"); 246 System.out.println("Author: " + example.runDrillDown()); 247 248 System.out.println("\n"); 249 System.out.println("Facet drill-sideways example (Publish Date/2010):"); 250 System.out.println("---------------------------------------------"); 251 for(FacetResult result : example.runDrillSideways()) { 252 System.out.println(result); 253 } 254 } 255 256}