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.FacetField;
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.FastTaxonomyFacetCounts;
032import org.apache.lucene.facet.taxonomy.TaxonomyReader;
033import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader;
034import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyWriter;
035import org.apache.lucene.index.DirectoryReader;
036import org.apache.lucene.index.IndexWriter;
037import org.apache.lucene.index.IndexWriterConfig;
038import org.apache.lucene.search.IndexSearcher;
039import org.apache.lucene.search.MatchAllDocsQuery;
040import org.apache.lucene.store.Directory;
041import org.apache.lucene.store.RAMDirectory;
042
043/** Demonstrates indexing categories into different indexed fields. */
044public class MultiCategoryListsFacetsExample {
045
046  private final Directory indexDir = new RAMDirectory();
047  private final Directory taxoDir = new RAMDirectory();
048  private final FacetsConfig config = new FacetsConfig();
049
050  /** Creates a new instance and populates the catetory list params mapping. */
051  public MultiCategoryListsFacetsExample() {
052    config.setIndexFieldName("Author", "author");
053    config.setIndexFieldName("Publish Date", "pubdate");
054    config.setHierarchical("Publish Date", true);
055  }
056
057  /** Build the example index. */
058  private void index() throws IOException {
059    IndexWriter indexWriter = new IndexWriter(indexDir, new IndexWriterConfig(FacetExamples.EXAMPLES_VER, 
060        new WhitespaceAnalyzer(FacetExamples.EXAMPLES_VER)));
061
062    // Writes facet ords to a separate directory from the main index
063    DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);
064
065    Document doc = new Document();
066    doc.add(new FacetField("Author", "Bob"));
067    doc.add(new FacetField("Publish Date", "2010", "10", "15"));
068    indexWriter.addDocument(config.build(taxoWriter, doc));
069
070    doc = new Document();
071    doc.add(new FacetField("Author", "Lisa"));
072    doc.add(new FacetField("Publish Date", "2010", "10", "20"));
073    indexWriter.addDocument(config.build(taxoWriter, doc));
074
075    doc = new Document();
076    doc.add(new FacetField("Author", "Lisa"));
077    doc.add(new FacetField("Publish Date", "2012", "1", "1"));
078    indexWriter.addDocument(config.build(taxoWriter, doc));
079
080    doc = new Document();
081    doc.add(new FacetField("Author", "Susan"));
082    doc.add(new FacetField("Publish Date", "2012", "1", "7"));
083    indexWriter.addDocument(config.build(taxoWriter, doc));
084
085    doc = new Document();
086    doc.add(new FacetField("Author", "Frank"));
087    doc.add(new FacetField("Publish Date", "1999", "5", "5"));
088    indexWriter.addDocument(config.build(taxoWriter, doc));
089    
090    indexWriter.close();
091    taxoWriter.close();
092  }
093
094  /** User runs a query and counts facets. */
095  private List<FacetResult> search() throws IOException {
096    DirectoryReader indexReader = DirectoryReader.open(indexDir);
097    IndexSearcher searcher = new IndexSearcher(indexReader);
098    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
099
100    FacetsCollector fc = new FacetsCollector();
101
102    // MatchAllDocsQuery is for "browsing" (counts facets
103    // for all non-deleted docs in the index); normally
104    // you'd use a "normal" query:
105    FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);
106
107    // Retrieve results
108    List<FacetResult> results = new ArrayList<>();
109
110    // Count both "Publish Date" and "Author" dimensions
111    Facets author = new FastTaxonomyFacetCounts("author", taxoReader, config, fc);
112    results.add(author.getTopChildren(10, "Author"));
113
114    Facets pubDate = new FastTaxonomyFacetCounts("pubdate", taxoReader, config, fc);
115    results.add(pubDate.getTopChildren(10, "Publish Date"));
116    
117    indexReader.close();
118    taxoReader.close();
119    
120    return results;
121  }
122
123  /** Runs the search example. */
124  public List<FacetResult> runSearch() throws IOException {
125    index();
126    return search();
127  }
128  
129  /** Runs the search example and prints the results. */
130  public static void main(String[] args) throws Exception {
131    System.out.println("Facet counting over multiple category lists example:");
132    System.out.println("-----------------------");
133    List<FacetResult> results = new MultiCategoryListsFacetsExample().runSearch();
134    System.out.println("Author: " + results.get(0));
135    System.out.println("Publish Date: " + results.get(1));
136  }
137}