001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *     http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.lucene.demo.facet;
018
019import java.io.IOException;
020import java.util.ArrayList;
021import java.util.List;
022import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
023import org.apache.lucene.document.Document;
024import org.apache.lucene.facet.FacetField;
025import org.apache.lucene.facet.FacetResult;
026import org.apache.lucene.facet.Facets;
027import org.apache.lucene.facet.FacetsCollector;
028import org.apache.lucene.facet.FacetsCollectorManager;
029import org.apache.lucene.facet.FacetsConfig;
030import org.apache.lucene.facet.taxonomy.FastTaxonomyFacetCounts;
031import org.apache.lucene.facet.taxonomy.TaxonomyReader;
032import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader;
033import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyWriter;
034import org.apache.lucene.index.DirectoryReader;
035import org.apache.lucene.index.IndexWriter;
036import org.apache.lucene.index.IndexWriterConfig;
037import org.apache.lucene.index.IndexWriterConfig.OpenMode;
038import org.apache.lucene.search.IndexSearcher;
039import org.apache.lucene.search.MatchAllDocsQuery;
040import org.apache.lucene.store.ByteBuffersDirectory;
041import org.apache.lucene.store.Directory;
042import org.apache.lucene.util.IOUtils;
043
044/** Demonstrates indexing categories into different indexed fields. */
045public class MultiCategoryListsFacetsExample {
046
047  private final Directory indexDir = new ByteBuffersDirectory();
048  private final Directory taxoDir = new ByteBuffersDirectory();
049  private final FacetsConfig config = new FacetsConfig();
050
051  /** Creates a new instance and populates the category list params mapping. */
052  public MultiCategoryListsFacetsExample() {
053    config.setIndexFieldName("Author", "author");
054    config.setIndexFieldName("Publish Date", "pubdate");
055    config.setHierarchical("Publish Date", true);
056  }
057
058  /** Build the example index. */
059  private void index() throws IOException {
060    IndexWriter indexWriter =
061        new IndexWriter(
062            indexDir, new IndexWriterConfig(new WhitespaceAnalyzer()).setOpenMode(OpenMode.CREATE));
063
064    // Writes facet ords to a separate directory from the main index
065    DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);
066
067    Document doc = new Document();
068    doc.add(new FacetField("Author", "Bob"));
069    doc.add(new FacetField("Publish Date", "2010", "10", "15"));
070    indexWriter.addDocument(config.build(taxoWriter, doc));
071
072    doc = new Document();
073    doc.add(new FacetField("Author", "Lisa"));
074    doc.add(new FacetField("Publish Date", "2010", "10", "20"));
075    indexWriter.addDocument(config.build(taxoWriter, doc));
076
077    doc = new Document();
078    doc.add(new FacetField("Author", "Lisa"));
079    doc.add(new FacetField("Publish Date", "2012", "1", "1"));
080    indexWriter.addDocument(config.build(taxoWriter, doc));
081
082    doc = new Document();
083    doc.add(new FacetField("Author", "Susan"));
084    doc.add(new FacetField("Publish Date", "2012", "1", "7"));
085    indexWriter.addDocument(config.build(taxoWriter, doc));
086
087    doc = new Document();
088    doc.add(new FacetField("Author", "Frank"));
089    doc.add(new FacetField("Publish Date", "1999", "5", "5"));
090    indexWriter.addDocument(config.build(taxoWriter, doc));
091
092    IOUtils.close(indexWriter, taxoWriter);
093  }
094
095  /** User runs a query and counts facets. */
096  private List<FacetResult> search() throws IOException {
097    DirectoryReader indexReader = DirectoryReader.open(indexDir);
098    IndexSearcher searcher = new IndexSearcher(indexReader);
099    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
100
101    FacetsCollectorManager fcm = new FacetsCollectorManager();
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 fc =
107        FacetsCollectorManager.search(searcher, MatchAllDocsQuery.INSTANCE, 10, fcm)
108            .facetsCollector();
109
110    // Retrieve results
111    List<FacetResult> results = new ArrayList<>();
112
113    // Count both "Publish Date" and "Author" dimensions
114    Facets author = new FastTaxonomyFacetCounts("author", taxoReader, config, fc);
115    results.add(author.getTopChildren(10, "Author"));
116
117    Facets pubDate = new FastTaxonomyFacetCounts("pubdate", taxoReader, config, fc);
118    results.add(pubDate.getTopChildren(10, "Publish Date"));
119
120    IOUtils.close(indexReader, taxoReader);
121
122    return results;
123  }
124
125  /** Runs the search example. */
126  public List<FacetResult> runSearch() throws IOException {
127    index();
128    return search();
129  }
130
131  /** Runs the search example and prints the results. */
132  public static void main(String[] args) throws Exception {
133    System.out.println("Facet counting over multiple category lists example:");
134    System.out.println("-----------------------");
135    List<FacetResult> results = new MultiCategoryListsFacetsExample().runSearch();
136    System.out.println("Author: " + results.get(0));
137    System.out.println("Publish Date: " + results.get(1));
138  }
139}