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.edge.Edge;
24 import org.apache.giraph.worker.WorkerAggregatorDelegator;
25 import org.apache.hadoop.io.Writable;
26 import org.apache.hadoop.io.WritableComparable;
27 import org.apache.hadoop.mapreduce.InputSplit;
28 import org.apache.hadoop.mapreduce.TaskAttemptContext;
29
30 /**
31 * Analogous to org.apache.giraph.bsp.BspRecordReader for edges.
32 * Will read the edges from an input split.
33 *
34 * @param <I> Vertex id
35 * @param <E> Edge data
36 */
37 @SuppressWarnings("rawtypes")
38 public abstract class EdgeReader<I extends WritableComparable,
39 E extends Writable> extends WorkerAggregatorDelegator<
40 I, Writable, E> {
41
42 /**
43 * Use the input split and context to setup reading the edges.
44 * Guaranteed to be called prior to any other function.
45 *
46 * @param inputSplit Input split to be used for reading edges.
47 * @param context Context from the task.
48 * @throws java.io.IOException
49 * @throws InterruptedException
50 */
51 public abstract void initialize(InputSplit inputSplit,
52 TaskAttemptContext context)
53 throws IOException, InterruptedException;
54
55 /**
56 * Read the next edge.
57 *
58 * @return false iff there are no more edges
59 * @throws IOException
60 * @throws InterruptedException
61 */
62 public abstract boolean nextEdge() throws IOException, InterruptedException;
63
64 /**
65 * Get the current edge source id.
66 *
67 * @return Current edge source id which has been read.
68 * nextEdge() should be called first.
69 * @throws IOException
70 * @throws InterruptedException
71 */
72 public abstract I getCurrentSourceId()
73 throws IOException, InterruptedException;
74
75 /**
76 * Get the current edge.
77 *
78 * @return the current edge which has been read.
79 * nextEdge() should be called first.
80 * @throws IOException
81 * @throws InterruptedException
82 */
83 public abstract Edge<I, E> getCurrentEdge()
84 throws IOException, InterruptedException;
85
86 /**
87 * Close this {@link EdgeReader} to future operations.
88 *
89 * @throws IOException
90 */
91 public abstract void close() throws IOException;
92
93 /**
94 * How much of the input has the {@link EdgeReader} consumed i.e.
95 * has been processed by?
96 *
97 * @return Progress from <code>0.0</code> to <code>1.0</code>.
98 * @throws IOException
99 * @throws InterruptedException
100 */
101 public abstract float getProgress() throws IOException, InterruptedException;
102 }