LuceneTest

/**
 *
 */
package com.test;

import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.ResultSet;
import java.sql.SQLException;
import java.sql.Statement;

import net.paoding.analysis.analyzer.PaodingAnalyzer;
import net.paoding.analysis.examples.gettingstarted.BoldFormatter;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.TermPositionVector;
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;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.TokenSources;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

/**
 * @author Administrator
 *
 */
public class LuceneTest {

    private static String QUERY_FIELD = "address";
    private static String FIELD3 = "id";
    private static String FIELD1 = "name";
    private static String FIELD2 = "address";
   
    private static String QUERY = "中华  and 共和国";

    /**
     * @param args
     */
    public static void main(String[] args) {
        // TODO Auto-generated method stub

        String driver = "com.mysql.jdbc.Driver";
        String url = "jdbc:mysql://localhost:3306/mytest1?characterEncoding=utf-8";
        String user = "root";
        String password = "root";
        String sql = "select * from test1";
        Connection conn = null;
        Statement stmt = null;
        ResultSet rs = null;
        try {
            Class.forName(driver);
            conn = DriverManager.getConnection(url, user, password);

            stmt = conn.createStatement(ResultSet.TYPE_SCROLL_SENSITIVE, ResultSet.CONCUR_READ_ONLY);
            rs = stmt.executeQuery(sql);

            Analyzer analyzer = new PaodingAnalyzer();
            //Analyzer analyzer = new CJKAnalyzer();
            //Directory ramDir = new RAMDirectory();
            Directory ramDir = FSDirectory.getDirectory("d://luncene");
            IndexWriter writer = new IndexWriter(ramDir, analyzer);
           
           
            while (rs.next()) {
               
                System.out.println(rs.getString("address"));
                Document doc = new Document();
                Field fd1 = new Field(FIELD1, rs.getString("name"), Field.Store.YES, Field.Index.TOKENIZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
                Field fd2 = new Field(FIELD2, rs.getString("address"), Field.Store.YES, Field.Index.TOKENIZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
                Field fd3 = new Field(FIELD3, rs.getString("id"), Field.Store.YES, Field.Index.TOKENIZED, Field.TermVector.WITH_POSITIONS_OFFSETS);
                doc.add(fd1);
                doc.add(fd2);
                doc.add(fd3);
                writer.addDocument(doc);
                System.out.println("-------------------------------");
            }
           
           
            writer.optimize();
            writer.close();

            //
            IndexReader reader = IndexReader.open(ramDir);
            String queryString = QUERY;
            QueryParser parser = new QueryParser(QUERY_FIELD, analyzer);
            Query query = parser.parse(queryString);
            Searcher searcher = new IndexSearcher(ramDir);
            query = query.rewrite(reader);
            System.out.println("Searching for: " + query.toString(QUERY_FIELD));
            Hits hits = searcher.search(query);

            BoldFormatter formatter = new BoldFormatter();
            Highlighter highlighter = new Highlighter(formatter, new QueryScorer(query));
            highlighter.setTextFragmenter(new SimpleFragmenter(50));
            for (int i = 0; i < hits.length(); i++) {
                Document doc=hits.doc(i);
                String text = hits.doc(i).get(QUERY_FIELD);
                int maxNumFragmentsRequired = 5;
                String fragmentSeparator = "...";
                TermPositionVector tpv = (TermPositionVector) reader.getTermFreqVector(hits.id(i), QUERY_FIELD);
                TokenStream tokenStream = TokenSources.getTokenStream(tpv);
                String result = highlighter.getBestFragments(tokenStream, text, maxNumFragmentsRequired, fragmentSeparator);
                System.out.println(doc.getField(FIELD3).stringValue()+"\t"+doc.getField(FIELD1).stringValue()+"\n" + result);
            }
            reader.close();
        } catch (ClassNotFoundException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (SQLException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } finally {
            try {
                rs.close();
                stmt.close();
                conn.close();
            } catch (SQLException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }

        }

    }

}