RangeQuery, FilterdQuery and HitCollector

[Youngho Cho]

Hello,

I would like to use a Filter for rangeQuery ( to avoid potential TooManyClauses 
exception )
and found out 

http://wiki.apache.org/jakarta-lucene/FilteringOptions

wiki said that FilteredQuery is best one.
But Interesting is that 
when I used the option with HitCollector , FilteredQuery test is fail.

Am I something missing or FilteredQuery with HitCollector is forbid or a bug ?


Please refer to the my test code.

----------------------------------------------------------
import junit.framework.TestCase;

import org.apache.lucene.analysis.cjk.CJKAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.NumberTools;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.Filter;
import org.apache.lucene.search.FilteredQuery;
import org.apache.lucene.search.HitCollector;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.RangeFilter;
import org.apache.lucene.search.Searcher;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;

import java.io.IOException;
import java.io.Serializable;

import java.util.Collection;
import java.util.HashSet;

public class FilteredRangeQueryTest extends TestCase
{
    private Directory ramDir;

    protected void setUp() throws Exception
    {
        ramDir = new RAMDirectory();
        addDocuments();
    }

    public void testRangeQuery()
        throws Exception
    {
        IndexSearcher searcher = new IndexSearcher(ramDir);

        Filter filter = RangeFilter.Less("num", NumberTools.longToString(1L));

        Term term = new Term("attid", NumberTools.longToString(113L));
        Query query = new TermQuery(term);

        Hits hits = searcher.search(query, filter);

        assertEquals(0, hits.length());

        HitCollector hitCollector = new TestHitCollector();

        ((TestHitCollector) hitCollector).setSearcher(searcher);

        //////// This test is Pass !!!!  ////////////////
        searcher.search(query, filter, hitCollector);
        assertEquals(0, ((TestHitCollector) hitCollector).getIds().size());
    }

    public void testFilteredQuery()
        throws Exception
    {
        IndexSearcher searcher = new IndexSearcher(ramDir);

        Filter filter = RangeFilter.Less("num", NumberTools.longToString(1L));

        Term term = new Term("attid", NumberTools.longToString(113L));
        Query query = new TermQuery(term);

        FilteredQuery fq = new FilteredQuery(query, filter);

        Hits hits = searcher.search(fq);

        assertEquals(0, hits.length());

        HitCollector hitCollector = new TestHitCollector();

        ((TestHitCollector) hitCollector).setSearcher(searcher);

        ////////// This test is FAIL !!!! //////////////
        searcher.search(fq, hitCollector);
        assertEquals(0, ((TestHitCollector) hitCollector).getIds().size());
    }

    private void addDocuments()
        throws IOException
    {
        IndexWriter writer = new IndexWriter(ramDir, new CJKAnalyzer(), true);

        Document doc = new Document();

        doc.add(Field.Keyword("num", NumberTools.longToString(1000L)));
        doc.add(Field.Keyword("attid", NumberTools.longToString(113L)));
        doc.add(Field.Keyword("itid", "111"));
        writer.addDocument(doc);

        writer.optimize();
        writer.close();
    }

    public class TestHitCollector extends HitCollector implements Serializable
    {
        private transient Searcher searcher;
        private transient Collection res;

        public TestHitCollector()
        {
        }

        public void setSearcher(Searcher searcher)
        {
            res = new HashSet();
            this.searcher = searcher;
        }

        public void collect(int i, float v)
        {
            try
            {
                final Document doc = searcher.doc(i);

                res.add(doc.get("itid"));
            }
            catch (IOException e)
            {
                // ignored
            }
        }

        public Collection getIds()
        {
            return res;
        }
    }
}


Thanks,

Youngho