View Javadoc

1   /**
2    *
3    * Licensed to the Apache Software Foundation (ASF) under one
4    * or more contributor license agreements.  See the NOTICE file
5    * distributed with this work for additional information
6    * regarding copyright ownership.  The ASF licenses this file
7    * to you under the Apache License, Version 2.0 (the
8    * "License"); you may not use this file except in compliance
9    * with the License.  You may obtain a copy of the License at
10   *
11   *     http://www.apache.org/licenses/LICENSE-2.0
12   *
13   * Unless required by applicable law or agreed to in writing, software
14   * distributed under the License is distributed on an "AS IS" BASIS,
15   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16   * See the License for the specific language governing permissions and
17   * limitations under the License.
18   */
19  package org.apache.hadoop.hbase.mapred;
20  
21  import java.io.IOException;
22  
23  import org.apache.commons.logging.Log;
24  import org.apache.commons.logging.LogFactory;
25  import org.apache.hadoop.hbase.classification.InterfaceAudience;
26  import org.apache.hadoop.hbase.classification.InterfaceStability;
27  import org.apache.hadoop.fs.Path;
28  import org.apache.hadoop.hbase.TableName;
29  import org.apache.hadoop.hbase.client.Connection;
30  import org.apache.hadoop.hbase.client.ConnectionFactory;
31  import org.apache.hadoop.hbase.client.HTable;
32  import org.apache.hadoop.hbase.util.Bytes;
33  import org.apache.hadoop.mapred.FileInputFormat;
34  import org.apache.hadoop.mapred.JobConf;
35  import org.apache.hadoop.mapred.JobConfigurable;
36  import org.apache.hadoop.util.StringUtils;
37  
38  /**
39   * Convert HBase tabular data into a format that is consumable by Map/Reduce.
40   */
41  @InterfaceAudience.Public
42  @InterfaceStability.Stable
43  public class TableInputFormat extends TableInputFormatBase implements
44      JobConfigurable {
45    private static final Log LOG = LogFactory.getLog(TableInputFormat.class);
46  
47    /**
48     * space delimited list of columns
49     */
50    public static final String COLUMN_LIST = "hbase.mapred.tablecolumns";
51  
52    public void configure(JobConf job) {
53      Path[] tableNames = FileInputFormat.getInputPaths(job);
54      String colArg = job.get(COLUMN_LIST);
55      String[] colNames = colArg.split(" ");
56      byte [][] m_cols = new byte[colNames.length][];
57      for (int i = 0; i < m_cols.length; i++) {
58        m_cols[i] = Bytes.toBytes(colNames[i]);
59      }
60      setInputColumns(m_cols);
61      try {
62        Connection connection = ConnectionFactory.createConnection(job);
63        setHTable((HTable) connection.getTable(TableName.valueOf(tableNames[0].getName())));
64      } catch (Exception e) {
65        LOG.error(StringUtils.stringifyException(e));
66      }
67    }
68  
69    public void validateInput(JobConf job) throws IOException {
70      // expecting exactly one path
71      Path [] tableNames = FileInputFormat.getInputPaths(job);
72      if (tableNames == null || tableNames.length > 1) {
73        throw new IOException("expecting one table name");
74      }
75  
76      // connected to table?
77      if (getHTable() == null) {
78        throw new IOException("could not connect to table '" +
79          tableNames[0].getName() + "'");
80      }
81  
82      // expecting at least one column
83      String colArg = job.get(COLUMN_LIST);
84      if (colArg == null || colArg.length() == 0) {
85        throw new IOException("expecting at least one column");
86      }
87    }
88  }