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.FacetResult;
028import org.apache.lucene.facet.Facets;
029import org.apache.lucene.facet.FacetsCollector;
030import org.apache.lucene.facet.FacetsConfig;
031import org.apache.lucene.facet.taxonomy.FloatAssociationFacetField;
032import org.apache.lucene.facet.taxonomy.IntAssociationFacetField;
033import org.apache.lucene.facet.taxonomy.TaxonomyFacetSumFloatAssociations;
034import org.apache.lucene.facet.taxonomy.TaxonomyFacetSumIntAssociations;
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 example usage of category associations. */
047public class AssociationsFacetsExample {
048
049  private final Directory indexDir = new RAMDirectory();
050  private final Directory taxoDir = new RAMDirectory();
051  private final FacetsConfig config;
052
053  /** Empty constructor */
054  public AssociationsFacetsExample() {
055    config = new FacetsConfig();
056    config.setMultiValued("tags", true);
057    config.setIndexFieldName("tags", "$tags");
058    config.setMultiValued("genre", true);
059    config.setIndexFieldName("genre", "$genre");
060  }
061  
062  /** Build the example index. */
063  private void index() throws IOException {
064    IndexWriterConfig iwc = new IndexWriterConfig(FacetExamples.EXAMPLES_VER, 
065                                                  new WhitespaceAnalyzer(FacetExamples.EXAMPLES_VER));
066    IndexWriter indexWriter = new IndexWriter(indexDir, iwc);
067
068    // Writes facet ords to a separate directory from the main index
069    DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);
070
071    Document doc = new Document();
072    // 3 occurrences for tag 'lucene'
073    doc.add(new IntAssociationFacetField(3, "tags", "lucene"));
074    // 87% confidence level of genre 'computing'
075    doc.add(new FloatAssociationFacetField(0.87f, "genre", "computing"));
076    indexWriter.addDocument(config.build(taxoWriter, doc));
077
078    doc = new Document();
079    // 1 occurrence for tag 'lucene'
080    doc.add(new IntAssociationFacetField(1, "tags", "lucene"));
081    // 2 occurrence for tag 'solr'
082    doc.add(new IntAssociationFacetField(2, "tags", "solr"));
083    // 75% confidence level of genre 'computing'
084    doc.add(new FloatAssociationFacetField(0.75f, "genre", "computing"));
085    // 34% confidence level of genre 'software'
086    doc.add(new FloatAssociationFacetField(0.34f, "genre", "software"));
087    indexWriter.addDocument(config.build(taxoWriter, doc));
088
089    indexWriter.close();
090    taxoWriter.close();
091  }
092
093  /** User runs a query and aggregates facets by summing their association values. */
094  private List<FacetResult> sumAssociations() throws IOException {
095    DirectoryReader indexReader = DirectoryReader.open(indexDir);
096    IndexSearcher searcher = new IndexSearcher(indexReader);
097    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
098    
099    FacetsCollector fc = new FacetsCollector();
100    
101    // MatchAllDocsQuery is for "browsing" (counts facets
102    // for all non-deleted docs in the index); normally
103    // you'd use a "normal" query:
104    FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);
105    
106    Facets tags = new TaxonomyFacetSumIntAssociations("$tags", taxoReader, config, fc);
107    Facets genre = new TaxonomyFacetSumFloatAssociations("$genre", taxoReader, config, fc);
108
109    // Retrieve results
110    List<FacetResult> results = new ArrayList<>();
111    results.add(tags.getTopChildren(10, "tags"));
112    results.add(genre.getTopChildren(10, "genre"));
113
114    indexReader.close();
115    taxoReader.close();
116    
117    return results;
118  }
119  
120  /** User drills down on 'tags/solr'. */
121  private FacetResult drillDown() throws IOException {
122    DirectoryReader indexReader = DirectoryReader.open(indexDir);
123    IndexSearcher searcher = new IndexSearcher(indexReader);
124    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
125
126    // Passing no baseQuery means we drill down on all
127    // documents ("browse only"):
128    DrillDownQuery q = new DrillDownQuery(config);
129
130    // Now user drills down on Publish Date/2010:
131    q.add("tags", "solr");
132    FacetsCollector fc = new FacetsCollector();
133    FacetsCollector.search(searcher, q, 10, fc);
134
135    // Retrieve results
136    Facets facets = new TaxonomyFacetSumFloatAssociations("$genre", taxoReader, config, fc);
137    FacetResult result = facets.getTopChildren(10, "genre");
138
139    indexReader.close();
140    taxoReader.close();
141    
142    return result;
143  }
144  
145  /** Runs summing association example. */
146  public List<FacetResult> runSumAssociations() throws IOException {
147    index();
148    return sumAssociations();
149  }
150  
151  /** Runs the drill-down example. */
152  public FacetResult runDrillDown() throws IOException {
153    index();
154    return drillDown();
155  }
156
157  /** Runs the sum int/float associations examples and prints the results. */
158  public static void main(String[] args) throws Exception {
159    System.out.println("Sum associations example:");
160    System.out.println("-------------------------");
161    List<FacetResult> results = new AssociationsFacetsExample().runSumAssociations();
162    System.out.println("tags: " + results.get(0));
163    System.out.println("genre: " + results.get(1));
164  }
165}