用java代码实现sqoop代码

1，客户端编写：

public class SqoopTest {
    public static void main(String[] args) {
        SqoopOptions options = new SqoopOptions();
        options.setConnectString("jdbc:oracle:thin:@192.168.176.11:1521:orcl");
        
        options.setTableName("STUDENT2");
        
        options.setWhereClause("id > 0");     // this where clause works when importing whole table, ie when setTableName() is used
        options.setUsername("edata");
        options.setPassword("edata");
        options.setDirectMode(true);    // Make sure the direct mode is off when importing data to HBase
        options.setNumMappers(1);         // Default value is 4
        options.setSqlQuery("SELECT * FROM student2 WHERE $CONDITIONS ");
        options.setSplitByCol("id");
        
        String[] strs = {"id","name","age"} ;
        options.setColumns(strs);
        
        // HBase options
        options.setHBaseTable("xun_sq");
        options.setHBaseColFamily("f");
        options.setCreateHBaseTable(true);    // Create HBase table, if it does not exist
        options.setHBaseRowKeyColumn("id,name");
//        options.setHBaseRowKeyColumn("age");
        Configuration config = new Configuration();
        //如果该语句不起作用，就在sqoop的conf.xml文件配置下并重启sqoop，这行是自定义rowkey生成规则
        config.set("sqoop.hbase.insert.put.transformer.class", "com.edata.sqoop.DdtMapInfoTransFormat");
//        config.set("sqoop.hbase.add.row.key","true");
        config.setBoolean("sqoop.hbase.add.row.key",true);
       String dd = config.get("sqoop.hbase.add.row.key");
        options.setConf(config);

        int ret = new ImportTool().run(options);
        
    }

}

2，如果自定义rowkey规则代码：

 
public class DdtMapInfoTransFormat extends PutTransformer {
 
  public static final Log LOG = LogFactory.getLog(DdtMapInfoTransFormat.class.getName());
  private Map<String, byte[]> serializedFieldNames;
 
  public DdtMapInfoTransFormat() {
      serializedFieldNames = new TreeMap<String, byte[]>();
  } 
  
  /**
   * Return the serialized bytes for a field name, using the cache if it's
   * already in there.
   */
  private byte[] getFieldNameBytes(String fieldName) {
      byte[] cachedName = serializedFieldNames.get(fieldName);
      if (null != cachedName) {
          // Cache hit. We're done.
          return cachedName;
      }
      // Do the serialization and memoize the result.
      byte[] nameBytes = Bytes.toBytes(fieldName);
      serializedFieldNames.put(fieldName, nameBytes);
      return nameBytes;
  }
 
  @Override
  /** {@inheritDoc} */
  public List<Put> getPutCommand(Map<String, Object> fields)throws IOException {
      
      String rowKeyCol = getRowKeyColumn();
      
      //if many columns  make up rowkey
      
      String colFamily = getColumnFamily();
      
      String[] rowkeyFamilys = rowKeyCol.split(",");
      String rowKey = "";
      for(int i = 0;i < rowkeyFamilys.length;i++){
           rowKey += fields.get(rowkeyFamilys[i])+"";
      }
      
      byte[] colFamilyBytes = Bytes.toBytes(colFamily);
      
//      Object rowKey = fields.get(rowKeyCol);
      
//      com.cloudera.sqoop.SqoopOptions
      if (null == rowKey) {
          // If the row-key column is null, we don't insert this row.
          LOG.warn("Could not insert row with null value for row-key column: "+ rowKeyCol);
          return null;
      }
      Put put = new Put(Bytes.toBytes(rowKey.toString() + ":uuid"));
      
      for (Map.Entry<String, Object> fieldEntry : fields.entrySet()) {
          String colName = fieldEntry.getKey();
          
          List rowkeyColList = Arrays.asList(rowkeyFamilys);
          
              // This is a regular field, not the row key.
              // Add it if it's not null.
              Object val = fieldEntry.getValue();
              if (null != val) {
                  put.add(colFamilyBytes, getFieldNameBytes(colName),Bytes.toBytes(val.toString()));
              }
          
//        
      }
      return Collections.singletonList(put);
  }
}

3，生成jar文件放在sqoop lib下，然后运行客户端