gistfile1.txt

***************
*** 18,52 ****
  
  import java.io.IOException;
  import java.nio.ByteBuffer;
- import java.util.*;
  
  import org.apache.cassandra.db.Column;
  import org.apache.cassandra.db.IColumn;
  import org.apache.cassandra.db.SuperColumn;
- import org.apache.cassandra.hadoop.*;
  import org.apache.cassandra.thrift.SlicePredicate;
  import org.apache.cassandra.thrift.SliceRange;
  import org.apache.cassandra.utils.FBUtilities;
- 
  import org.apache.hadoop.conf.Configuration;
  import org.apache.hadoop.fs.Path;
  import org.apache.hadoop.mapreduce.InputFormat;
  import org.apache.hadoop.mapreduce.Job;
  import org.apache.hadoop.mapreduce.RecordReader;
- 
  import org.apache.pig.LoadFunc;
  import org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigSplit;
  import org.apache.pig.data.DefaultDataBag;
- import org.apache.pig.data.DataByteArray;
  import org.apache.pig.data.Tuple;
  import org.apache.pig.data.TupleFactory;
  
  /**
   * A LoadFunc wrapping ColumnFamilyInputFormat.
   *
   * A row from a standard CF will be returned as nested tuples: (key, ((name1, val1), (name2, val2))).
   */
- public class CassandraStorage extends LoadFunc
  {
      // system environment variables that can be set to configure connection info:
      // alternatively, Hadoop JobConf variables can be set using keys from ConfigHelper
--- 18,71 ----
  
  import java.io.IOException;
  import java.nio.ByteBuffer;
+ import java.util.ArrayList;
+ import java.util.Arrays;
+ import java.util.List;
+ import java.util.Map;
+ import java.util.SortedMap;
  
+ import org.apache.cassandra.avro.ColumnOrSuperColumn;
+ import org.apache.cassandra.avro.Deletion;
+ import org.apache.cassandra.avro.Mutation;
  import org.apache.cassandra.db.Column;
  import org.apache.cassandra.db.IColumn;
  import org.apache.cassandra.db.SuperColumn;
+ import org.apache.cassandra.hadoop.ColumnFamilyInputFormat;
+ import org.apache.cassandra.hadoop.ColumnFamilyOutputFormat;
+ import org.apache.cassandra.hadoop.ConfigHelper;
  import org.apache.cassandra.thrift.SlicePredicate;
  import org.apache.cassandra.thrift.SliceRange;
  import org.apache.cassandra.utils.FBUtilities;
+ import org.apache.commons.logging.Log;
+ import org.apache.commons.logging.LogFactory;
  import org.apache.hadoop.conf.Configuration;
  import org.apache.hadoop.fs.Path;
  import org.apache.hadoop.mapreduce.InputFormat;
  import org.apache.hadoop.mapreduce.Job;
+ import org.apache.hadoop.mapreduce.OutputFormat;
  import org.apache.hadoop.mapreduce.RecordReader;
+ import org.apache.hadoop.mapreduce.RecordWriter;
  import org.apache.pig.LoadFunc;
+ import org.apache.pig.LoadPushDown;
+ import org.apache.pig.ResourceSchema;
+ import org.apache.pig.StoreFuncInterface;
+ import org.apache.pig.backend.executionengine.ExecException;
  import org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigSplit;
+ import org.apache.pig.data.DataByteArray;
+ import org.apache.pig.data.DataType;
  import org.apache.pig.data.DefaultDataBag;
  import org.apache.pig.data.Tuple;
  import org.apache.pig.data.TupleFactory;
+ import org.apache.pig.impl.logicalLayer.FrontendException;
  
+ import com.google.common.collect.Lists;
+ 
  /**
   * A LoadFunc wrapping ColumnFamilyInputFormat.
   *
   * A row from a standard CF will be returned as nested tuples: (key, ((name1, val1), (name2, val2))).
   */
+ public class CassandraStorage extends LoadFunc implements StoreFuncInterface, LoadPushDown
  {
      // system environment variables that can be set to configure connection info:
      // alternatively, Hadoop JobConf variables can be set using keys from ConfigHelper