lucene-java-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From mark harwood <markharw...@yahoo.co.uk>
Subject Re: Pagination
Date Tue, 03 Jul 2007 15:58:01 GMT
>>I get the ids then I do look the items in the database using select item.* from item
where item.id in ( ids )

Hmm. That's likely to confuse the already confused :)
The ids referred to so far are Lucene internal document ids and are typically only meaningful
to Lucene during a single IndexReader session. I wouldn't recommend storing them in a database
because a Lucene document id can point to an entirely different document after deletes/updates
are performed on the Lucene index and the IndexReader is reopened.

For the avoidance of further confusion I have extended the "main" method in my previous example
(reposted below in full) to include examples of
1) Retrieving document content
2) Retrieving a "next" page (starting from result 11)
The values "1" and "11" used below in the calls to HitPageCollector constructor define the
page start. This value is typically something you would get the client to pass to you e.g.
note the number "10" in this URL http://www.google.com/search?q=lucene&start=10 which
is used to select results from "10" onwards. Note also that this URL http://www.google.com/search?q=lucene&&start=10000
does not work because Google have placed a restriction on the maximum value for "start" -
you should too.

Cheers
Mark


package lucene.pagination;

import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.HitCollector;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.util.PriorityQueue;

/**
 * A HitCollector that retrieves a specific page of results 
 * @author maharwood
 */
public class HitPageCollector extends HitCollector
{
    //Demo code showing pagination
    public static void main(String[] args) throws Exception
    {
        IndexSearcher s=new IndexSearcher("/indexes/nasa");
        Query q=new TermQuery(new Term("contents","sea"));

        //Retrieve page 1  (hits 1-10)
        HitPageCollector hpc=new HitPageCollector(1,10);
        s.search(q,hpc);
        ScoreDoc[] sd = hpc.getScores();
        System.out.println("Hits "+ hpc.getStart()+" - "+ hpc.getEnd()+" of "+hpc.getTotalAvailable());
        for (int i = 0; i < sd.length; i++)
        {
            Document doc=s.doc(sd[i].doc);
            System.out.println(sd[i].score +" "+doc.get("title"));
        }
        
        //Example retrieve page 2 (hits 11-20)
        hpc=new HitPageCollector(11,10);
        s.search(q,hpc);
        sd = hpc.getScores();
        System.out.println("Hits "+ hpc.getStart()+" - "+ hpc.getEnd()+" of "+hpc.getTotalAvailable());
        for (int i = 0; i < sd.length; i++)
        {
            Document doc=s.doc(sd[i].doc);
            System.out.println(sd[i].score +" "+doc.get("title"));
        }
        
        
        s.close();
    }

    int nDocs;
    PriorityQueue hq;
    float minScore = 0.0f;
    int totalHits = 0;
    int start;
    int maxNumHits;
    int totalInThisPage;

    public HitPageCollector(int start, int maxNumHits)
    {
        this.nDocs = start + maxNumHits;
        this.start = start;
        this.maxNumHits = maxNumHits;
        hq = new HitQueue(nDocs);
    }

    public void collect(int doc, float score)
    {
        totalHits++;
        if((hq.size()<nDocs)||(score >= minScore))
        {
            ScoreDoc scoreDoc = new ScoreDoc(doc,score);
            hq.insert(scoreDoc);              // update hit queue
            minScore = ((ScoreDoc)hq.top()).score; // reset minScore
        }
        totalInThisPage=hq.size();
    }
    

    public ScoreDoc[] getScores()
    {
        //just returns the number of hits required from the required start point
        /*
            So, given hits:
                1234567890
            and a start of 2 + maxNumHits of 3 should return:
                234
            or, given hits
                12
            should return
                2
            and so, on.
        */
        if (start <= 0)
        {
            throw new IllegalArgumentException("Invalid start :" + start+" - start should
be >=1");
        }
        int numReturned = Math.min(maxNumHits, (hq.size() - (start - 1)));
        if (numReturned <= 0)
        {
            return new ScoreDoc[0];
        }
        ScoreDoc[] scoreDocs = new ScoreDoc[numReturned];
        ScoreDoc scoreDoc;
        for (int i = hq.size() - 1; i >= 0; i--) // put docs in array, working backwards
from lowest count
        {
            scoreDoc = (ScoreDoc) hq.pop();
            if (i < (start - 1))
            {
                break; //off the beginning of the results array
            }
            if (i < (scoreDocs.length + (start - 1)))
            {
                scoreDocs[i - (start - 1)] = scoreDoc; //within scope of results array
            }
        }
        return scoreDocs;
    }

    public int getTotalAvailable()
    {
        return totalHits;
    }

    public int getStart()
    {
        return start;
    }
    
    public int getEnd()
    {
        return start+totalInThisPage-1;
    }
    
    public class HitQueue extends PriorityQueue 
    {
          public HitQueue(int size) 
          {
            initialize(size);
          }
          public final boolean lessThan(Object a, Object b) 
          {
            ScoreDoc hitA = (ScoreDoc)a;
            ScoreDoc hitB = (ScoreDoc)b;
            if (hitA.score == hitB.score)
              return hitA.doc > hitB.doc;
            else
              return hitA.score < hitB.score;
          }
    }
}






      ___________________________________________________________ 
Yahoo! Mail is the world's favourite email. Don't settle for less, sign up for
your free account today http://uk.rd.yahoo.com/evt=44106/*http://uk.docs.yahoo.com/mail/winter07.html


---------------------------------------------------------------------
To unsubscribe, e-mail: java-user-unsubscribe@lucene.apache.org
For additional commands, e-mail: java-user-help@lucene.apache.org


Mime
View raw message