#!/bin/bash

HADOOP_HOME=${HADOOP_HOME-/usr/lib/hadoop}

input_file=${1} 		; shift
output_file=${1} 		; shift

if [ "$output_file" == "" ] ; then echo "$0 input_file output_file" ; exit ; fi

HADOOP_HOME=${HADOOP_HOME-/usr/lib/hadoop}

cmd="${HADOOP_HOME}/bin/hadoop \
     jar         ${HADOOP_HOME}/contrib/streaming/hadoop-*streaming*.jar	\
    -Dmapred.output.compress=true                                               \
    -Dmapred.output.compression.codec=org.apache.hadoop.io.compress.BZip2Codec  \
    -Dmapred.reduce.tasks=1                                                     \
    -mapper  	 \"/bin/cat\"                                                   \
    -reducer	 \"/bin/cat\"                                                   \
    -input       \"$input_file\"                                                \
    -output  	 \"$output_file\"                                               \
    "
echo $cmd
$cmd