%%bash
#set -x
HADOOP_URL="https://dlcdn.apache.org/hadoop/common/hadoop-3.3.6/hadoop-3.3.6.tar.gz"
wget --quiet --no-clobber $HADOOP_URL >/dev/null
[ ! -d $(basename $HADOOP_URL .tar.gz) ] && tar -xzf $(basename $HADOOP_URL)
HADOOP_HOME=$(pwd)'/'$(basename $HADOOP_URL .tar.gz)'/bin'
PATH=$HADOOP_HOME:$PATH
which java >/dev/null|| apt install -y openjdk-19-jre-headless
export JAVA_HOME=$(realpath $(which java) | sed 's/\/bin\/java$//')
echo -e "Hello, World!">hello.txt
output_dir="output"$(date +"%Y%m%dT%H%M")
sleep 10
mapred streaming -input hello.txt -output $output_dir
ls -lR output*
cat $output_dir/part-00000