使用 JdbcDirectory 在数据库中创建 Lucene 索引

JDBCIndexer.java

    package test.lucene.chaima;

import java.io.IOException;
import java.sql.Connection;
import java.sql.PreparedStatement;
import java.sql.ResultSet;
import java.sql.SQLException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.SimpleAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.store.jdbc.JdbcDirectory;
import org.apache.lucene.store.jdbc.dialect.PostgreSQLDialect;
import org.apache.lucene.util.Version;

/**
 * The Class JDBCIndexer.
 *
 * @author chaima
 */
public class JDBCIndexer {

    /** The jdbc directory. */
    private Directory   jdbcDirectory   = null;

    /**
     * Instantiates a new jDBC indexer.
     *
     * @param jdbcDirectory
     *            the jdbc directory
     */
    public JDBCIndexer(Directory jdbcDirectory) {
        super();
        this.jdbcDirectory = jdbcDirectory;
    }
    /**
     * Gets the jdbc directory.
     *
     * @return the jdbc directory
     */
    public Directory getJdbcDirectory() {
        if (jdbcDirectory == null) {
            throw new IllegalStateException("Index not yet build, rerun indexing");
        }
        return jdbcDirectory;
    }

    /**
     * Sets the jdbc directory.
     *
     * @param jdbcDirectory
     *            the new jdbc directory
     */
    public void setJdbcDirectory(Directory jdbcDirectory) {
        this.jdbcDirectory = jdbcDirectory;
    }

    /**
     * Builds the index.
     */
    public void buildIndex() {
        createAndBuildIndex();
    }

    /**
     * Creates the and build index.
     */
    private void createAndBuildIndex() {
       createIndexTable();
        index();
    }

    /**
     * Index.
     */
    private void index() {
        Analyzer analyzer = new SimpleAnalyzer(Version.LUCENE_36);
        IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_36, analyzer);
        IndexWriter indexWriter = null;
        try {
            indexWriter = new IndexWriter(getJdbcDirectory(), analyzer,true, IndexWriter.MaxFieldLength.UNLIMITED);
            Boolean locked=indexWriter.isLocked(jdbcDirectory);
            addIndex(indexWriter);
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (LockObtainFailedException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (indexWriter != null) {
                try {
                    indexWriter.close();
                } catch (CorruptIndexException e) {
                    e.printStackTrace();
                } catch (IOException e) {
                    e.printStackTrace();
                } finally {
                    indexWriter = null;
                }
            }
        }
    }

    /**
     * 
     *
     * @param indexWriter
     *            the index writer
     */
    private void addIndex(IndexWriter indexWriter) throws CorruptIndexException, IOException {
     try {
      Connection connection = JDBCDatabaseUtil.getConnection();
      connection.setAutoCommit(false);
      String query = "SELECT id, name, lastname FROM users";
      PreparedStatement pstmt = connection.prepareStatement(query);
      ResultSet resultSet = pstmt.executeQuery();
      while (resultSet.next()) {
       Document document = new Document();
       document.add(new Field("id", String.valueOf(resultSet.getInt(1)), Field.Store.YES, Field.Index.ANALYZED));
       document.add(new Field("name", String.valueOf(resultSet.getString(2)), Field.Store.YES, Field.Index.ANALYZED));
       document.add(new Field("lastname", String.valueOf(resultSet.getString(3)), Field.Store.YES, Field.Index.ANALYZED));

       indexWriter.addDocument(document);
       indexWriter.commit();
     }
     indexWriter.close();   
     } catch (SQLException e) {
      e.printStackTrace();
     }
    }

    /**
     * Creates the index table.
     */
    private void createIndexTable() {
        if (this.jdbcDirectory == null) {
            setJdbcDirectory(new MyJDBCDirectory(JDBCDatabaseUtil.getDataSource(), new PostgreSQLDialect(), "LUCENE_INDEX_TABLE"));
        }
        try {
            /**
             * No need to manually create index table, create method will
             * automatically create it.
             */
           boolean existe= ((JdbcDirectory) getJdbcDirectory()).tableExists();
           if(existe)
               System.out.println("table existe");
           else{
               System.out.println("table non existe");
               ((JdbcDirectory) getJdbcDirectory()).create(); 
           }

        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public static void main(String[] args) {
        new JDBCIndexer(null).buildIndex();
    }
}

和表用户:

    CREATE TABLE users
(
  id integer NOT NULL,
  name character(20),
  lastname character(20),
  CONSTRAINT pk_id PRIMARY KEY (id)
)
WITH (
  OIDS=FALSE
);
ALTER TABLE users
  OWNER TO postgres;

还有罐子:

    commons-logging-1.0.4.jar
compass-2.2.0.jar
lucene-core-3.6.1.jar
postgresql-9.2-1002.jdbc4.jar

推荐答案

我已经创建了自己的 JdbcDirectory 实现，尽管它会依赖 JEE6 来利用 @Singleton 注释.代码本身并不是太简单，无法粘贴到 StackOverflow 帖子中，它仍然有一些限制.关键部分是由于数据库锁定语义，您不能使用多个线程对单个事务执行多个操作.