InputFormat牛逼（5）org.apache.hadoop.mapreduce.lib.db.DBInputFormat

@Public
@Stable

A InputFormat that reads input data from an SQL table.

DBInputFormat emits LongWritables containing the record number as key and DBWritables as value. The SQL query, and input class can be using one of the two setInput methods.

InputFormat核心方法有两个：getSplits和createRecordReader
核心方法一

  /** {@inheritDoc} */
  public List<InputSplit> getSplits(JobContext job) throws IOException {

    ResultSet results = null;  
    Statement statement = null;
    try {
      statement = connection.createStatement();

      results = statement.executeQuery(getCountQuery());
      results.next();

      long count = results.getLong(1);
      int chunks = job.getConfiguration().getInt(MRJobConfig.NUM_MAPS, 1);
      long chunkSize = (count / chunks);

      results.close();
      statement.close();

      List<InputSplit> splits = new ArrayList<InputSplit>();

      // Split the rows into n-number of chunks and adjust the last chunk
      // accordingly
      for (int i = 0; i < chunks; i++) {
        DBInputSplit split;

        if ((i + 1) == chunks)
          split = new DBInputSplit(i * chunkSize, count);
        else
          split = new DBInputSplit(i * chunkSize, (i * chunkSize)
              + chunkSize);

        splits.add(split);
      }

      connection.commit();
      return splits;
    } catch (SQLException e) {
      throw new IOException("Got SQLException", e);
    } finally {
      try {
        if (results != null) { results.close(); }
      } catch (SQLException e1) {}
      try {
        if (statement != null) { statement.close(); }
      } catch (SQLException e1) {}

      closeConnection();
    }
  }

核心方法二

public RecordReader<LongWritable, T> createRecordReader(InputSplit split,
      TaskAttemptContext context) throws IOException, InterruptedException {  

    return createDBRecordReader((DBInputSplit) split, context.getConfiguration());
  }

protected RecordReader<LongWritable, T> createDBRecordReader(DBInputSplit split,
      Configuration conf) throws IOException {

    @SuppressWarnings("unchecked")
    Class<T> inputClass = (Class<T>) (dbConf.getInputClass());
    try {
      // use database product name to determine appropriate record reader.
      if (dbProductName.startsWith("ORACLE")) {
        // use Oracle-specific db reader.
        return new OracleDBRecordReader<T>(split, inputClass,
            conf, getConnection(), getDBConf(), conditions, fieldNames,
            tableName);
      } else if (dbProductName.startsWith("MYSQL")) {
        // use MySQL-specific db reader.
        return new MySQLDBRecordReader<T>(split, inputClass,
            conf, getConnection(), getDBConf(), conditions, fieldNames,
            tableName);
      } else {
        // Generic reader.
        return new DBRecordReader<T>(split, inputClass,
            conf, getConnection(), getDBConf(), conditions, fieldNames,
            tableName);
      }
    } catch (SQLException ex) {
      throw new IOException(ex.getMessage());
    }
  }