Sample input format to go with SampleVertexData

LongSampleVertexDataNullTextInputFormat.java

import org.apache.giraph.io.formats.*;

import org.apache.giraph.edge.Edge;
import org.apache.giraph.edge.EdgeFactory;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.TaskAttemptContext;

import com.google.common.collect.Lists;

import java.io.IOException;
import java.util.List;
import java.util.regex.Pattern;

/**
 * Simple text-based {@link org.apache.giraph.io.VertexInputFormat} for
 * unweighted graphs with long ids.
 *
 * Each line consists of: vertex neighbor1 neighbor2 ...
 */
public class LongSampleVertexDataNullTextInputFormat extends
    TextVertexInputFormat<LongWritable, SampleVertexData, NullWritable> {
  /** Separator of the vertex and neighbors */
  private static final Pattern SEPARATOR = Pattern.compile("[\t ]");

  @Override
  public TextVertexReader createVertexReader(InputSplit split,
                                             TaskAttemptContext context)
    throws IOException {
    return new LongSampleVertexDataNullVertexReader();
  }

  /**
   * Vertex reader associated with LongSampleVertexDataNullTextInputFormat}.
   */
  public class LongSampleVertexDataNullVertexReader extends
      TextVertexReaderFromEachLineProcessed<String[]> {
    /** Cached vertex id for the current line */
    private LongWritable id;

    @Override
    protected String[] preprocessLine(Text line) throws IOException {
      String[] tokens = SEPARATOR.split(line.toString());
      id = new LongWritable(Long.parseLong(tokens[0]));
      return tokens;
    }

    @Override
    protected LongWritable getId(String[] tokens) throws IOException {
      return id;
    }

    @Override
    protected SampleVertexData getValue(String[] tokens) throws IOException {
      return new SampleVertexData();
    }

    @Override
    protected Iterable<Edge<LongWritable, NullWritable>> getEdges(
        String[] tokens) throws IOException {
      List<Edge<LongWritable, NullWritable>> edges =
          Lists.newArrayListWithCapacity(tokens.length - 1);
      for (int n = 1; n < tokens.length; n++) {
        edges.add(EdgeFactory.create(
            new LongWritable(Long.parseLong(tokens[n]))));
      }
      return edges;
    }
  }
}