Java Code Examples for org.apache.hadoop.mapreduce.Job#getMapOutputKeyClass()

The following examples show how to use org.apache.hadoop.mapreduce.Job#getMapOutputKeyClass() . These examples are extracted from open source projects. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source Project: hadoop   File: TotalOrderPartitioner.java    License: Apache License 2.0 4 votes vote down vote up
/**
 * Read in the partition file and build indexing data structures.
 * If the keytype is {@link org.apache.hadoop.io.BinaryComparable} and
 * <tt>total.order.partitioner.natural.order</tt> is not false, a trie
 * of the first <tt>total.order.partitioner.max.trie.depth</tt>(2) + 1 bytes
 * will be built. Otherwise, keys will be located using a binary search of
 * the partition keyset using the {@link org.apache.hadoop.io.RawComparator}
 * defined for this job. The input file must be sorted with the same
 * comparator and contain {@link Job#getNumReduceTasks()} - 1 keys.
 */
@SuppressWarnings("unchecked") // keytype from conf not static
public void setConf(Configuration conf) {
  try {
    this.conf = conf;
    String parts = getPartitionFile(conf);
    final Path partFile = new Path(parts);
    final FileSystem fs = (DEFAULT_PATH.equals(parts))
      ? FileSystem.getLocal(conf)     // assume in DistributedCache
      : partFile.getFileSystem(conf);

    Job job = Job.getInstance(conf);
    Class<K> keyClass = (Class<K>)job.getMapOutputKeyClass();
    K[] splitPoints = readPartitions(fs, partFile, keyClass, conf);
    if (splitPoints.length != job.getNumReduceTasks() - 1) {
      throw new IOException("Wrong number of partitions in keyset");
    }
    RawComparator<K> comparator =
      (RawComparator<K>) job.getSortComparator();
    for (int i = 0; i < splitPoints.length - 1; ++i) {
      if (comparator.compare(splitPoints[i], splitPoints[i+1]) >= 0) {
        throw new IOException("Split points are out of order");
      }
    }
    boolean natOrder =
      conf.getBoolean(NATURAL_ORDER, true);
    if (natOrder && BinaryComparable.class.isAssignableFrom(keyClass)) {
      partitions = buildTrie((BinaryComparable[])splitPoints, 0,
          splitPoints.length, new byte[0],
          // Now that blocks of identical splitless trie nodes are 
          // represented reentrantly, and we develop a leaf for any trie
          // node with only one split point, the only reason for a depth
          // limit is to refute stack overflow or bloat in the pathological
          // case where the split points are long and mostly look like bytes 
          // iii...iixii...iii   .  Therefore, we make the default depth
          // limit large but not huge.
          conf.getInt(MAX_TRIE_DEPTH, 200));
    } else {
      partitions = new BinarySearchNode(splitPoints, comparator);
    }
  } catch (IOException e) {
    throw new IllegalArgumentException("Can't read partitions file", e);
  }
}
 
Example 2
Source Project: big-c   File: TotalOrderPartitioner.java    License: Apache License 2.0 4 votes vote down vote up
/**
 * Read in the partition file and build indexing data structures.
 * If the keytype is {@link org.apache.hadoop.io.BinaryComparable} and
 * <tt>total.order.partitioner.natural.order</tt> is not false, a trie
 * of the first <tt>total.order.partitioner.max.trie.depth</tt>(2) + 1 bytes
 * will be built. Otherwise, keys will be located using a binary search of
 * the partition keyset using the {@link org.apache.hadoop.io.RawComparator}
 * defined for this job. The input file must be sorted with the same
 * comparator and contain {@link Job#getNumReduceTasks()} - 1 keys.
 */
@SuppressWarnings("unchecked") // keytype from conf not static
public void setConf(Configuration conf) {
  try {
    this.conf = conf;
    String parts = getPartitionFile(conf);
    final Path partFile = new Path(parts);
    final FileSystem fs = (DEFAULT_PATH.equals(parts))
      ? FileSystem.getLocal(conf)     // assume in DistributedCache
      : partFile.getFileSystem(conf);

    Job job = Job.getInstance(conf);
    Class<K> keyClass = (Class<K>)job.getMapOutputKeyClass();
    K[] splitPoints = readPartitions(fs, partFile, keyClass, conf);
    if (splitPoints.length != job.getNumReduceTasks() - 1) {
      throw new IOException("Wrong number of partitions in keyset");
    }
    RawComparator<K> comparator =
      (RawComparator<K>) job.getSortComparator();
    for (int i = 0; i < splitPoints.length - 1; ++i) {
      if (comparator.compare(splitPoints[i], splitPoints[i+1]) >= 0) {
        throw new IOException("Split points are out of order");
      }
    }
    boolean natOrder =
      conf.getBoolean(NATURAL_ORDER, true);
    if (natOrder && BinaryComparable.class.isAssignableFrom(keyClass)) {
      partitions = buildTrie((BinaryComparable[])splitPoints, 0,
          splitPoints.length, new byte[0],
          // Now that blocks of identical splitless trie nodes are 
          // represented reentrantly, and we develop a leaf for any trie
          // node with only one split point, the only reason for a depth
          // limit is to refute stack overflow or bloat in the pathological
          // case where the split points are long and mostly look like bytes 
          // iii...iixii...iii   .  Therefore, we make the default depth
          // limit large but not huge.
          conf.getInt(MAX_TRIE_DEPTH, 200));
    } else {
      partitions = new BinarySearchNode(splitPoints, comparator);
    }
  } catch (IOException e) {
    throw new IllegalArgumentException("Can't read partitions file", e);
  }
}