org.apache.cassandra.hadoop
Class ColumnFamilyInputFormat

java.lang.Object
  extended by org.apache.hadoop.mapreduce.InputFormat<java.lang.String,java.util.SortedMap<byte[],IColumn>>
      extended by org.apache.cassandra.hadoop.ColumnFamilyInputFormat

public class ColumnFamilyInputFormat
extends org.apache.hadoop.mapreduce.InputFormat<java.lang.String,java.util.SortedMap<byte[],IColumn>>


Constructor Summary
ColumnFamilyInputFormat()
           
 
Method Summary
 org.apache.hadoop.mapreduce.RecordReader<java.lang.String,java.util.SortedMap<byte[],IColumn>> createRecordReader(org.apache.hadoop.mapreduce.InputSplit inputSplit, org.apache.hadoop.mapreduce.TaskAttemptContext taskAttemptContext)
           
 java.util.List<org.apache.hadoop.mapreduce.InputSplit> getSplits(org.apache.hadoop.mapreduce.JobContext context)
           
static void setColumnFamily(org.apache.hadoop.mapreduce.Job job, java.lang.String keyspace, java.lang.String columnFamily)
           
static void setInputSplitSize(org.apache.hadoop.mapreduce.Job job, int splitsize)
          Set the size of the input split.
static void setSlicePredicate(org.apache.hadoop.mapreduce.Job job, org.apache.cassandra.thrift.SlicePredicate predicate)
           
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

ColumnFamilyInputFormat

public ColumnFamilyInputFormat()
Method Detail

setColumnFamily

public static void setColumnFamily(org.apache.hadoop.mapreduce.Job job,
                                   java.lang.String keyspace,
                                   java.lang.String columnFamily)

setInputSplitSize

public static void setInputSplitSize(org.apache.hadoop.mapreduce.Job job,
                                     int splitsize)
Set the size of the input split. This affects the number of maps created, if the number is too small the overhead of each map will take up the bulk of the job time.

Parameters:
job - Job you are about to run.
splitsize - Size of the input split

setSlicePredicate

public static void setSlicePredicate(org.apache.hadoop.mapreduce.Job job,
                                     org.apache.cassandra.thrift.SlicePredicate predicate)

getSplits

public java.util.List<org.apache.hadoop.mapreduce.InputSplit> getSplits(org.apache.hadoop.mapreduce.JobContext context)
                                                                 throws java.io.IOException
Specified by:
getSplits in class org.apache.hadoop.mapreduce.InputFormat<java.lang.String,java.util.SortedMap<byte[],IColumn>>
Throws:
java.io.IOException

createRecordReader

public org.apache.hadoop.mapreduce.RecordReader<java.lang.String,java.util.SortedMap<byte[],IColumn>> createRecordReader(org.apache.hadoop.mapreduce.InputSplit inputSplit,
                                                                                                                         org.apache.hadoop.mapreduce.TaskAttemptContext taskAttemptContext)
                                                                                                                  throws java.io.IOException,
                                                                                                                         java.lang.InterruptedException
Specified by:
createRecordReader in class org.apache.hadoop.mapreduce.InputFormat<java.lang.String,java.util.SortedMap<byte[],IColumn>>
Throws:
java.io.IOException
java.lang.InterruptedException


Copyright © 2010 The Apache Software Foundation