source: trunk/indexers/lucene-gs/src/org/greenstone/LuceneWrapper/GS2LuceneQuery.java@ 12257

/**
 *
 * @author  [email protected]
 * @author  [email protected]
 * @version 
 */

package org.nzdl.gsdl.LuceneWrap;


import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.util.HashSet;
import java.util.Iterator;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.Searcher;


public class GS2LuceneQuery
{
    public static void main (String args[])
    {
    if (args.length == 0) {
        System.out.println("Usage: GS2LuceneQuery <index directory>");
        return;
    }

        try {
        Searcher searcher = new IndexSearcher(args[0]);
        Analyzer analyzer = new StandardAnalyzer();
        IndexReader reader = ((IndexSearcher) searcher).getIndexReader();

        BufferedReader in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
        while (true) {
        // Read the query from STDIN
        String query_string = in.readLine();
        if (query_string == null || query_string.length() == -1) {
            break;
        }
        System.err.println("**** query = " + query_string);

        // Parse the query and rewrite it into individual terms (eg. for wildcard searches)
        QueryParser query_parser = new QueryParser("TX", analyzer);
        Query query = query_parser.parse(query_string);
        query = query.rewrite(reader);

        // Perform the query
        Hits hits = searcher.search(query);
        System.out.println("<ResultSet>");
        System.out.println("  <QueryString>" + query.toString("TX")+"</QueryString>");

        // Return the list of expanded query terms and their frequencies
        HashSet terms = new HashSet();
        query.extractTerms(terms);
        Iterator iter = terms.iterator();
        while (iter.hasNext()) {
            Term term = (Term) iter.next();
            System.out.println("  <Term freq=\"" + reader.docFreq(term) + "\">" + term.text() + "</Term>");
        }

        // Return the matching documents
        System.out.println("  <MatchingDocsInfo num=\"" + hits.length() + "\"/>");
        for (int i = 0; i < hits.length(); i++) {
            Document doc = hits.doc(i);
            String node_id = doc.get("nodeID");
            System.out.println("  <Match id=\"" + node_id + "\"/>");
        }

        System.out.println("</ResultSet>");
        }
        
        searcher.close();
    }
    catch (Exception exception) {
        exception.printStackTrace();
        }
    }
}