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.FacetsConfig;
029import org.apache.lucene.facet.taxonomy.FastTaxonomyFacetCounts;
030import org.apache.lucene.facet.taxonomy.TaxonomyReader;
031import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader;
032import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyWriter;
033import org.apache.lucene.index.DirectoryReader;
034import org.apache.lucene.index.IndexWriter;
035import org.apache.lucene.index.IndexWriterConfig;
036import org.apache.lucene.index.IndexWriterConfig.OpenMode;
037import org.apache.lucene.search.IndexSearcher;
038import org.apache.lucene.search.MatchAllDocsQuery;
039import org.apache.lucene.store.ByteBuffersDirectory;
040import org.apache.lucene.store.Directory;
041import org.apache.lucene.util.IOUtils;
042
043/** Demonstrates indexing categories into different indexed fields. */
044public class MultiCategoryListsFacetsExample {
045
046  private final Directory indexDir = new ByteBuffersDirectory();
047  private final Directory taxoDir = new ByteBuffersDirectory();
048  private final FacetsConfig config = new FacetsConfig();
049
050  /** Creates a new instance and populates the category 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 =
060        new IndexWriter(
061            indexDir, new IndexWriterConfig(new WhitespaceAnalyzer()).setOpenMode(OpenMode.CREATE));
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    IOUtils.close(indexWriter, taxoWriter);
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    IOUtils.close(indexReader, taxoReader);
118
119    return results;
120  }
121
122  /** Runs the search example. */
123  public List<FacetResult> runSearch() throws IOException {
124    index();
125    return search();
126  }
127
128  /** Runs the search example and prints the results. */
129  public static void main(String[] args) throws Exception {
130    System.out.println("Facet counting over multiple category lists example:");
131    System.out.println("-----------------------");
132    List<FacetResult> results = new MultiCategoryListsFacetsExample().runSearch();
133    System.out.println("Author: " + results.get(0));
134    System.out.println("Publish Date: " + results.get(1));
135  }
136}