Totally untested, but here is a hack at what the scorer might look
like when the number of terms is large.
-Yonik
package org.apache.lucene.search;
import org.apache.lucene.index.TermEnum;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.TermDocs;
import java.io.IOException;
/**
* @author yonik
* @version $Id$
*/
public class MultiTermScorer extends Scorer{
protected final float[] scores;
protected int pos;
protected float docScore;
public MultiTermScorer(Similarity similarity, IndexReader reader,
Weight w, TermEnum terms, byte[] norms, boolean include_idf, boolean
include_tf) throws IOException {
super(similarity);
float weightVal = w.getValue();
int maxDoc = reader.maxDoc();
this.scores = new float[maxDoc];
float[] normDecoder = Similarity.getNormDecoder();
TermDocs tdocs = reader.termDocs();
while (terms.next()) {
tdocs.seek(terms);
float termScore = weightVal;
if (include_idf) {
termScore *= similarity.idf(terms.docFreq(),maxDoc);
}
while (tdocs.next()) {
int doc = tdocs.doc();
float subscore = termScore;
if (include_tf) subscore *= tdocs.freq();
if (norms!=null) subscore *= normDecoder[norms[doc&0xff]];
scores[doc] += subscore;
}
}
pos=-1;
}
// could also use a bitset to keep track of docs in the set...
public boolean next() throws IOException {
while (++pos < scores.length) {
if (scores[pos] != 0) return true;
}
return false;
}
public int doc() {
return pos;
}
public float score() throws IOException {
return scores[pos];
}
public boolean skipTo(int target) throws IOException {
pos=target-1;
return next();
}
public Explanation explain(int doc) throws IOException {
return null;
}
}
-Yonik
Now hiring -- http://forms.cnet.com/slink?231706
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
