Shows how to implement grouping queries in Lucene

GroupingApproach.java

package com.exzeo.spock;

import junit.framework.TestCase;
import org.apache.commons.io.FileUtils;
import org.apache.lucene.analysis.core.SimpleAnalyzer;
import org.apache.lucene.document.*;
import org.apache.lucene.index.*;
import org.apache.lucene.search.*;
import org.apache.lucene.search.grouping.GroupDocs;
import org.apache.lucene.search.grouping.GroupingSearch;
import org.apache.lucene.search.grouping.TopGroups;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.SimpleFSDirectory;
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.Version;

import java.io.File;
import java.io.IOException;

/**
 * Shows how Lucene used for implementing grouping options
 *
 * @author Vadi (vadi@exzeo.com)
 * @since 02/03/14
 */
public class GroupingApproach extends TestCase {

    File path = new File("target/grouping");
    Directory directory;
    Directory directoryNew;
    IndexWriter writer;
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_46, new SimpleAnalyzer(Version.LUCENE_46));

    @Override
    public void setUp() throws IOException {

        if (path.exists()) {
            FileUtils.deleteDirectory(path);
        }

        directory = new SimpleFSDirectory(path);
        directoryNew = new SimpleFSDirectory(new File("target/grouping/new"));
        writer = new IndexWriter(directory, config);

    }

    @Override
    public void tearDown() throws IOException {

        if (writer != null)
            writer.close();

        if (directory != null)
            directory.close();

        FileUtils.deleteDirectory(path);
    }

    public void testGrouping() throws IOException {

        addDocument(writer, "w1", "s1", "ram", 101);
        addDocument(writer, "w2", "s1", "ram", 102);
        addDocument(writer, "w3", "s2", "ram", 103);
        addDocument(writer, "w1", "s1", "sita", 104);

        writer.commit();
        writer.close();

        IndexReader reader = DirectoryReader.open(directoryNew);
        IndexSearcher searcher = new IndexSearcher(reader);

        final TermQuery termQuery = new TermQuery(new Term("s", "s1"));

        GroupingSearch search = new GroupingSearch("activity.owner");
        search.setGroupSort(Sort.RELEVANCE);
        search.setGroupDocsLimit(1);
        search.setAllGroups(true);
        search.setFillSortFields(true);

        final TopGroups<BytesRef> search1 = search.search(searcher, null, new MatchAllDocsQuery(), 0, 5);

        printDocs(search1.groups, reader);
    }

    void printDocs(GroupDocs<BytesRef>[] search1, IndexReader reader) throws IOException {

        for (GroupDocs<BytesRef> group : search1) {
            System.out.println(group.groupValue.utf8ToString() + " " + group.totalHits);

            for (ScoreDoc scoreDoc : group.scoreDocs) {
                final Document document = reader.document(scoreDoc.doc);
                printDoc(document);
            }

            for (Object groupSortValue : group.groupSortValues) {
                System.out.println(groupSortValue);
            }

        }

    }

    void printDoc(Document document) {

        for (IndexableField indexableField : document) {
            System.out.print(indexableField.name() + " : " + indexableField.stringValue() + ",");
        }

        System.out.println();
    }

    public void addDocument(IndexWriter writer, String workkard, String status, String assignee, int id) throws IOException {
        Document document = new Document();
        document.add(new StringField("w", workkard, Field.Store.YES));
        document.add(new StringField("s", status, Field.Store.YES));
        document.add(new StringField("a", assignee, Field.Store.YES));
        document.add(new IntField("id", id, Field.Store.YES));
        document.add(new SortedDocValuesField("a_dv", new BytesRef(assignee)));
        writer.addDocument(document);
    }
}