Mailing-List: contact lucene-dev-help@jakarta.apache.org; run by ezmlm
Precedence: bulk
Reply-To: "Lucene Developers List" <lucene-dev@jakarta.apache.org>
From: "Rasik Pandey" <rasik.pandey@ajlsm.com>
To: "'Lucene Developers List'" <lucene-dev@jakarta.apache.org>,
	<korfut@lycos.com>
Subject: RE : Query Term Collector (was: Re: New highlighter package
 available)
Date: Wed, 17 Mar 2004 13:36:08 +0100
Message-ID: <001101c40c1c$6f5b79a0$8f7ba8c0@diderot>
MIME-Version: 1.0
Content-Type: text/plain;
	charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
In-Reply-To: <IIOKHNKNCHGGGDAA@mailcity.com>
Importance: Normal

Hello All,

I don't know how this Thread/issue was resolved, but if you are still =
interested I have a simple way of doing this term collection ONLY at =
query time. I've tested it and it works with highlighting, etc. without =
the extra rewrite() call on the index.

Comments are welcome!


package org.apache.lucene.search;

import org.apache.lucene.search.Weight;
import org.apache.lucene.search.Searcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.Similarity;
import org.apache.lucene.index.IndexReader;

import java.io.IOException;

/*Rasik Pandey rasik.pandey@ajlsm.com*/
/**Simple wrapper for a Lucene query that
 * collects all queries generated by calling
 * rewrite on the original Lucene query and stores
 * them in a BooleanQuery.
 *
 * A Searcher will call the rewrite() method
 * for each index and hence generate a query
 * containing terms for the respective index. This
 * class collects these queries so that they may be
 * used for highlighting, query expansion, etc. by
 * retrieving the underlying terms.
 *
 * @see #rewrite
 * @see #getRewrittenQueries
 * @see #resetRewrittenQueries
 * @see #getOriginalQuery
 */
public class CachingRewrittenQueryWrapper extends Query{
    protected org.apache.lucene.search.Query originalQuery =3D null;
    protected BooleanQuery rewrittenQueries =3D new BooleanQuery();

    public CachingRewrittenQueryWrapper(Query originalQuery) {
        this.originalQuery =3D originalQuery;
    }

    public BooleanQuery getRewrittenQueries() {
        return this.rewrittenQueries;
    }

    public void resetRewrittenQueries() {
        BooleanQuery newCachedQuery =3D new BooleanQuery();
        =
newCachedQuery.setMaxClauseCount(this.rewrittenQueries.getMaxClauseCount(=
));
        this.rewrittenQueries =3D newCachedQuery;
    }

    public Query getOriginalQuery() {
        return this.originalQuery;
    }

    public void setBoost(float b) {
        this.originalQuery.setBoost(b);
    }

    public float getBoost() {
        return this.originalQuery.getBoost();
    }


    protected Weight createWeight(Searcher searcher) {
        return this.originalQuery.createWeight(searcher);
    }

    public Query rewrite(IndexReader reader) throws IOException {
        Query rewrittenQuery =3D  this.originalQuery.rewrite(reader);
        this.rewrittenQueries.add(rewrittenQuery, false, false);
        return rewrittenQuery;
    }

    public Query combine(Query[] queries) {
        return this.originalQuery.combine(queries);
    }

    public Similarity getSimilarity(Searcher searcher) {
        return this.originalQuery.getSimilarity(searcher);
    }

    protected void finalize() throws Throwable {
        super.finalize();
        //TODO maybe something here to ensure that all resources held by =
rewrittenQueries are cleaned up properly
    }

    public String toString() {
        return this.originalQuery.toString();
    }

    public String toString(String field) {
       return this.originalQuery.toString(field);
    }
}


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