View Javadoc

1   /**
2    * Copyright 2011 The Apache Software Foundation
3    *
4    * Licensed to the Apache Software Foundation (ASF) under one
5    * or more contributor license agreements.  See the NOTICE file
6    * distributed with this work for additional information
7    * regarding copyright ownership.  The ASF licenses this file
8    * to you under the Apache License, Version 2.0 (the
9    * "License"); you may not use this file except in compliance
10   * with the License.  You may obtain a copy of the License at
11   *
12   *     http://www.apache.org/licenses/LICENSE-2.0
13   *
14   * Unless required by applicable law or agreed to in writing, software
15   * distributed under the License is distributed on an "AS IS" BASIS,
16   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
17   * See the License for the specific language governing permissions and
18   * limitations under the License.
19   */
20  package org.apache.hadoop.hbase.mapreduce;
21  
22  import java.io.IOException;
23  
24  import org.apache.hadoop.hbase.client.HTable;
25  import org.apache.hadoop.hbase.client.Result;
26  import org.apache.hadoop.hbase.client.Scan;
27  import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
28  import org.apache.hadoop.mapreduce.InputSplit;
29  import org.apache.hadoop.mapreduce.RecordReader;
30  import org.apache.hadoop.mapreduce.TaskAttemptContext;
31  
32  /**
33   * Iterate over an HBase table data, return (ImmutableBytesWritable, Result)
34   * pairs.
35   */
36  public class TableRecordReader
37  extends RecordReader<ImmutableBytesWritable, Result> {
38  
39    private TableRecordReaderImpl recordReaderImpl = new TableRecordReaderImpl();
40  
41    /**
42     * Restart from survivable exceptions by creating a new scanner.
43     *
44     * @param firstRow  The first row to start at.
45     * @throws IOException When restarting fails.
46     */
47    public void restart(byte[] firstRow) throws IOException {
48      this.recordReaderImpl.restart(firstRow);
49    }
50  
51  
52    /**
53     * Sets the HBase table.
54     *
55     * @param htable  The {@link HTable} to scan.
56     */
57    public void setHTable(HTable htable) {
58      this.recordReaderImpl.setHTable(htable);
59    }
60  
61    /**
62     * Sets the scan defining the actual details like columns etc.
63     *
64     * @param scan  The scan to set.
65     */
66    public void setScan(Scan scan) {
67      this.recordReaderImpl.setScan(scan);
68    }
69  
70    /**
71     * Closes the split.
72     *
73     * @see org.apache.hadoop.mapreduce.RecordReader#close()
74     */
75    @Override
76    public void close() {
77      this.recordReaderImpl.close();
78    }
79  
80    /**
81     * Returns the current key.
82     *
83     * @return The current key.
84     * @throws IOException
85     * @throws InterruptedException When the job is aborted.
86     * @see org.apache.hadoop.mapreduce.RecordReader#getCurrentKey()
87     */
88    @Override
89    public ImmutableBytesWritable getCurrentKey() throws IOException,
90        InterruptedException {
91      return this.recordReaderImpl.getCurrentKey();
92    }
93  
94    /**
95     * Returns the current value.
96     *
97     * @return The current value.
98     * @throws IOException When the value is faulty.
99     * @throws InterruptedException When the job is aborted.
100    * @see org.apache.hadoop.mapreduce.RecordReader#getCurrentValue()
101    */
102   @Override
103   public Result getCurrentValue() throws IOException, InterruptedException {
104     return this.recordReaderImpl.getCurrentValue();
105   }
106 
107   /**
108    * Initializes the reader.
109    *
110    * @param inputsplit  The split to work with.
111    * @param context  The current task context.
112    * @throws IOException When setting up the reader fails.
113    * @throws InterruptedException When the job is aborted.
114    * @see org.apache.hadoop.mapreduce.RecordReader#initialize(
115    *   org.apache.hadoop.mapreduce.InputSplit,
116    *   org.apache.hadoop.mapreduce.TaskAttemptContext)
117    */
118   @Override
119   public void initialize(InputSplit inputsplit,
120       TaskAttemptContext context) throws IOException,
121       InterruptedException {
122     this.recordReaderImpl.initialize(inputsplit, context);
123   }
124 
125   /**
126    * Positions the record reader to the next record.
127    *
128    * @return <code>true</code> if there was another record.
129    * @throws IOException When reading the record failed.
130    * @throws InterruptedException When the job was aborted.
131    * @see org.apache.hadoop.mapreduce.RecordReader#nextKeyValue()
132    */
133   @Override
134   public boolean nextKeyValue() throws IOException, InterruptedException {
135     return this.recordReaderImpl.nextKeyValue();
136   }
137 
138   /**
139    * The current progress of the record reader through its data.
140    *
141    * @return A number between 0.0 and 1.0, the fraction of the data read.
142    * @see org.apache.hadoop.mapreduce.RecordReader#getProgress()
143    */
144   @Override
145   public float getProgress() {
146     return this.recordReaderImpl.getProgress();
147   }
148 }