lucene系列-facet搜索

facet搜索,方面搜索,电商中使用的非常多.例如

统计field中值的分组分布情况, 只是每个域值中的命中数量.

facet搜索主要用于:

1.Facet Counting facet域值统计
2.Facet Associations facet域值分类匹配度.描述一个doc属于某一个category的程度.
3.Multiple Facet Requests 了解多个fecet的结果分布情况
4.Facet Labels at Search Time 请求数据category,facet标签搜索.

用DirectoryTaxonomyWriter对索引封装

IndexWriter indexWriter = new IndexWriter(indexDir, new IndexWriterConfig(Version.LUCENE_4_10_0,
new WhitespaceAnalyzer()));
// Writes facet ords to a separate directory from the main index
DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);

facet实现原理

facet数据底层实现是利用DocValues中的SortedSetDocValuesFacetField, 当doc的某些field需要切面搜索的时候,lucene建索引的过程中建立docid->field tokens的正向映射.
index:

    IndexWriter writer = ...
    TaxonomyWriter taxo = new DirectoryTaxonomyWriter(taxoDir, OpenMode.CREATE);
    ...
    Document doc = new Document();
    doc.add(new Field("title", titleText, Store.YES, Index.ANALYZED));
    ...
    List<CategoryPath> categories = new ArrayList<CategoryPath>();
    categories.add(new CategoryPath("author", "Mark Twain"));
    categories.add(new CategoryPath("year", "2010"));
    ...
    DocumentBuilder categoryDocBuilder = new CategoryDocumentBuilder(taxo);
    categoryDocBuilder.setCategoryPaths(categories);
    categoryDocBuilder.build(doc);
    writer.addDocument(doc);

addDocument到updateDocument之后 lucene底层实现数据的存储.利用**DocValuesWriter写入disk中

facet搜索demo

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.facet.DrillDownQuery;
import org.apache.lucene.facet.DrillSideways;
import org.apache.lucene.facet.DrillSideways.DrillSidewaysResult;
import org.apache.lucene.facet.FacetField;
import org.apache.lucene.facet.FacetResult;
import org.apache.lucene.facet.Facets;
import org.apache.lucene.facet.FacetsCollector;
import org.apache.lucene.facet.FacetsConfig;
import org.apache.lucene.facet.taxonomy.FastTaxonomyFacetCounts;
import org.apache.lucene.facet.taxonomy.TaxonomyReader;
import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader;
import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyWriter;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.MatchAllDocsQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;

/** Shows simple usage of faceted indexing and search. */
public class FacetDemo {

  private final Directory indexDir = new RAMDirectory();
  private final Directory taxoDir = new RAMDirectory();
  private final FacetsConfig config = new FacetsConfig();

  /** Empty constructor */
  public FacetDemo() {
    config.setHierarchical("Publish Date", true);
  }

  /** Build the example index. */
  private void index() throws IOException {
    IndexWriter indexWriter = new IndexWriter(indexDir, new IndexWriterConfig(Version.LUCENE_48, new WhitespaceAnalyzer(
        Version.LUCENE_48)));

    // Writes facet ords to a separate directory from the main index
    DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);

    Document doc = new Document();
    doc.add(new FacetField("Author", "Bob"));
    doc.add(new FacetField("Publish Date", "2010", "10", "15"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Lisa"));
    doc.add(new FacetField("Publish Date", "2010", "10", "20"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Lisa"));
    doc.add(new FacetField("Publish Date", "2012", "1", "1"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Susan"));
    doc.add(new FacetField("Publish Date", "2012", "1", "7"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Frank"));
    doc.add(new FacetField("Publish Date", "1999", "5", "5"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    indexWriter.close();
    taxoWriter.close();
  }

  /** User runs a query and counts facets. */
  private List<FacetResult> facetsWithSearch() throws IOException {
    DirectoryReader indexReader = DirectoryReader.open(indexDir);
    IndexSearcher searcher = new IndexSearcher(indexReader);
    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);

    FacetsCollector fc = new FacetsCollector();

    // MatchAllDocsQuery is for "browsing" (counts facets
    // for all non-deleted docs in the index); normally
    // you'd use a "normal" query:
    FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);

    // Retrieve results
    List<FacetResult> results = new ArrayList<FacetResult>();

    // Count both "Publish Date" and "Author" dimensions
    Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc);
    results.add(facets.getTopChildren(10, "Author"));
    results.add(facets.getTopChildren(10, "Publish Date"));

    indexReader.close();
    taxoReader.close();

    return results;
  }

  /**
   * User runs a query and counts facets only without collecting the matching
   * documents.
   */
  private List<FacetResult> facetsOnly() throws IOException {
    DirectoryReader indexReader = DirectoryReader.open(indexDir);
    IndexSearcher searcher = new IndexSearcher(indexReader);
    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);

    FacetsCollector fc = new FacetsCollector();

    // MatchAllDocsQuery is for "browsing" (counts facets
    // for all non-deleted docs in the index); normally
    // you'd use a "normal" query:
    searcher.search(new MatchAllDocsQuery(), null /* Filter */, fc);

    // Retrieve results
    List<FacetResult> results = new ArrayList<FacetResult>();

    // Count both "Publish Date" and "Author" dimensions
    Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc);

    results.add(facets.getTopChildren(10, "Author"));
    results.add(facets.getTopChildren(10, "Publish Date"));

    indexReader.close();
    taxoReader.close();

    return results;
  }

  /**
   * User drills down on 'Publish Date/2010', and we return facets for
   * 'Author'
   */
  private FacetResult drillDown() throws IOException {
    DirectoryReader indexReader = DirectoryReader.open(indexDir);
    IndexSearcher searcher = new IndexSearcher(indexReader);
    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);

    // Passing no baseQuery means we drill down on all
    // documents ("browse only"):
    DrillDownQuery q = new DrillDownQuery(config);

    // Now user drills down on Publish Date/2010:
    q.add("Publish Date", "2010");
    FacetsCollector fc = new FacetsCollector();
    FacetsCollector.search(searcher, q, 10, fc);

    // Retrieve results
    Facets facets = new FastTaxonomyFacetCounts(taxoReader, config, fc);
    FacetResult result = facets.getTopChildren(10, "Author");

    indexReader.close();
    taxoReader.close();

    return result;
  }

  /**
   * User drills down on 'Publish Date/2010', and we return facets for both
   * 'Publish Date' and 'Author', using DrillSideways.
   */
  private List<FacetResult> drillSideways() throws IOException {
    DirectoryReader indexReader = DirectoryReader.open(indexDir);
    IndexSearcher searcher = new IndexSearcher(indexReader);
    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);

    // Passing no baseQuery means we drill down on all
    // documents ("browse only"):
    DrillDownQuery q = new DrillDownQuery(config);

    // Now user drills down on Publish Date/2010:
    q.add("Publish Date", "2010");

    DrillSideways ds = new DrillSideways(searcher, config, taxoReader);
    DrillSidewaysResult result = ds.search(q, 10);

    // Retrieve results
    List<FacetResult> facets = result.facets.getAllDims(10);

    indexReader.close();
    taxoReader.close();

    return facets;
  }

  /** Runs the search example. */
  public List<FacetResult> runFacetOnly() throws IOException {
    index();
    return facetsOnly();
  }

  /** Runs the search example. */
  public List<FacetResult> runSearch() throws IOException {
    index();
    return facetsWithSearch();
  }

  /** Runs the drill-down example. */
  public FacetResult runDrillDown() throws IOException {
    index();
    return drillDown();
  }

  /** Runs the drill-sideways example. */
  public List<FacetResult> runDrillSideways() throws IOException {
    index();
    return drillSideways();
  }

  /** Runs the search and drill-down examples and prints the results. */
  public static void main(String[] args) throws Exception {
    System.out.println("Facet counting example:");
    System.out.println("-----------------------");
    FacetDemo example1 = new FacetDemo();
    List<FacetResult> results1 = example1.runFacetOnly();
    System.out.println("Author: " + results1.get(0));
    System.out.println("Publish Date: " + results1.get(1));

    System.out.println("Facet counting example (combined facets and search):");
    System.out.println("-----------------------");
    FacetDemo example = new FacetDemo();
    List<FacetResult> results = example.runSearch();
    System.out.println("Author: " + results.get(0));
    System.out.println("Publish Date: " + results.get(1));

    System.out.println("\n");
    System.out.println("Facet drill-down example (Publish Date/2010):");
    System.out.println("---------------------------------------------");
    System.out.println("Author: " + example.runDrillDown());

    System.out.println("\n");
    System.out.println("Facet drill-sideways example (Publish Date/2010):");
    System.out.println("---------------------------------------------");
    for (FacetResult result : example.runDrillSideways()) {
      System.out.println(result);
    }
  }
}