View Javadoc

1   /**
2    * Copyright 2009 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.util.TreeSet;
23  
24  import org.apache.hadoop.hbase.KeyValue;
25  import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
26  import org.apache.hadoop.mapreduce.Reducer;
27  
28  /**
29   * Emits sorted KeyValues.
30   * Reads in all KeyValues from passed Iterator, sorts them, then emits
31   * KeyValues in sorted order.  If lots of columns per row, it will use lots of
32   * memory sorting.
33   * @see HFileOutputFormat
34   */
35  public class KeyValueSortReducer extends Reducer<ImmutableBytesWritable, KeyValue, ImmutableBytesWritable, KeyValue> {
36    protected void reduce(ImmutableBytesWritable row, java.lang.Iterable<KeyValue> kvs,
37        org.apache.hadoop.mapreduce.Reducer<ImmutableBytesWritable, KeyValue, ImmutableBytesWritable, KeyValue>.Context context)
38    throws java.io.IOException, InterruptedException {
39      TreeSet<KeyValue> map = new TreeSet<KeyValue>(KeyValue.COMPARATOR);
40      for (KeyValue kv: kvs) {
41        map.add(kv.clone());
42      }
43      context.setStatus("Read " + map.getClass());
44      int index = 0;
45      for (KeyValue kv: map) {
46        context.write(row, kv);
47        if (++index % 100 == 0) context.setStatus("Wrote " + index);
48      }
49    }
50  }