This project has retired. For details please refer to its Attic page.
IntNullTextEdgeInputFormat xref
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.formats;
20  
21  import org.apache.giraph.io.EdgeReader;
22  import org.apache.giraph.utils.IntPair;
23  import org.apache.hadoop.io.IntWritable;
24  import org.apache.hadoop.io.NullWritable;
25  import org.apache.hadoop.io.Text;
26  import org.apache.hadoop.mapreduce.InputSplit;
27  import org.apache.hadoop.mapreduce.TaskAttemptContext;
28  
29  import java.io.IOException;
30  import java.util.regex.Pattern;
31  
32  /**
33   * Simple text-based {@link org.apache.giraph.io.EdgeInputFormat} for
34   * unweighted graphs with int ids.
35   *
36   * Each line consists of: source_vertex, target_vertex
37   */
38  public class IntNullTextEdgeInputFormat extends
39      TextEdgeInputFormat<IntWritable, NullWritable> {
40    /** Splitter for endpoints */
41    private static final Pattern SEPARATOR = Pattern.compile("[\t ]");
42  
43    @Override
44    public EdgeReader<IntWritable, NullWritable> createEdgeReader(
45        InputSplit split, TaskAttemptContext context) throws IOException {
46      return new IntNullTextEdgeReader();
47    }
48  
49    /**
50     * {@link org.apache.giraph.io.EdgeReader} associated with
51     * {@link IntNullTextEdgeInputFormat}.
52     */
53    public class IntNullTextEdgeReader extends
54        TextEdgeReaderFromEachLineProcessed<IntPair> {
55      @Override
56      protected IntPair preprocessLine(Text line) throws IOException {
57        String[] tokens = SEPARATOR.split(line.toString());
58        return new IntPair(Integer.parseInt(tokens[0]),
59            Integer.parseInt(tokens[1]));
60      }
61  
62      @Override
63      protected IntWritable getSourceVertexId(IntPair endpoints)
64        throws IOException {
65        return new IntWritable(endpoints.getFirst());
66      }
67  
68      @Override
69      protected IntWritable getTargetVertexId(IntPair endpoints)
70        throws IOException {
71        return new IntWritable(endpoints.getSecond());
72      }
73  
74      @Override
75      protected NullWritable getValue(IntPair endpoints) throws IOException {
76        return NullWritable.get();
77      }
78    }
79  }