View Javadoc

1   /*
2    * Licensed to the Apache Software Foundation (ASF) under one
3    * or more contributor license agreements.  See the NOTICE file
4    * distributed with this work for additional information
5    * regarding copyright ownership.  The ASF licenses this file
6    * to you under the Apache License, Version 2.0 (the
7    * "License"); you may not use this file except in compliance
8    * with the License.  You may obtain a copy of the License at
9    *
10   *     http://www.apache.org/licenses/LICENSE-2.0
11   *
12   * Unless required by applicable law or agreed to in writing, software
13   * distributed under the License is distributed on an "AS IS" BASIS,
14   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15   * See the License for the specific language governing permissions and
16   * limitations under the License.
17   */
18  
19  package org.apache.giraph.io;
20  
21  import java.io.IOException;
22  
23  import org.apache.giraph.conf.DefaultImmutableClassesGiraphConfigurable;
24  import org.apache.hadoop.io.Writable;
25  import org.apache.hadoop.io.WritableComparable;
26  import org.apache.hadoop.mapreduce.JobContext;
27  import org.apache.hadoop.mapreduce.OutputCommitter;
28  import org.apache.hadoop.mapreduce.TaskAttemptContext;
29  
30  /**
31   * abstract class which can only write edges
32   *
33   * @param <I> Vertex id
34   * @param <V> Vertex value
35   * @param <E> Edge value
36   */
37  @SuppressWarnings("rawtypes")
38  public abstract class EdgeOutputFormat<
39      I extends WritableComparable, V extends Writable,
40      E extends Writable> extends
41      DefaultImmutableClassesGiraphConfigurable<I, V, E> {
42    /**
43     * Create an edge writer for a given split. The framework will call
44     * {@link EdgeWriter#initialize(TaskAttemptContext)} before
45     * the split is used.
46     *
47     * @param context the information about the task
48     * @return a new vertex writer
49     * @throws IOException
50     * @throws InterruptedException
51     */
52    public abstract EdgeWriter<I, V, E> createEdgeWriter(
53      TaskAttemptContext context) throws IOException, InterruptedException;
54  
55    /**
56     * Check for validity of the output-specification for the job.
57     * (Copied from Hadoop OutputFormat)
58     *
59     * <p>This is to validate the output specification for the job when it is
60     * a job is submitted.  Typically checks that it does not already exist,
61     * throwing an exception when it already exists, so that output is not
62     * overwritten.</p>
63     *
64     * @param  context information about the job
65     * @throws IOException when output should not be attempted
66     */
67    public abstract void checkOutputSpecs(JobContext context)
68      throws IOException, InterruptedException;
69  
70    /**
71     * Get the output committer for this output format. This is responsible
72     * for ensuring the output is committed correctly.
73     * (Copied from Hadoop OutputFormat)
74     *
75     * @param context the task context
76     * @return an output committer
77     * @throws IOException
78     * @throws InterruptedException
79     */
80    public abstract OutputCommitter getOutputCommitter(
81      TaskAttemptContext context) throws IOException, InterruptedException;
82  }