#!/bin/bash

# create local dummy file to place on HDFS
echo "Hello this will be my first distributed and fault-tolerant data set\!"" | cat >> my_file.txt

# list directories from top level of HDFS. This should display nothing but a temp directory
hdfs dfs -ls /

# create /user directory on HDFS
hdfs dfs -mkdir /user
hdfs dfs -ls /
# Found 1 items
# drwxr-xr-x - ubuntu supergroup 0 2015-05-06 22:41 /user

# copy local file a few times onto HDFS
hdfs dfs -copyFromLocal ~/my_file.txt /user
hdfs dfs -copyFromLocal ~/my_file.txt /user/my_file2.txt
hdfs dfs -copyFromLocal ~/my_file.txt /user/my_file3.txt

# list files in /user directory
hdfs dfs -ls /user
# Found 1 items
# -rw-r--r-- 3 ubuntu supergroup 50 2015-05-06 22:43 /user/my_file.txt
# -rw-r--r-- 3 ubuntu supergroup 50 2015-05-06 22:43 /user/my_file2.txt
# -rw-r--r-- 3 ubuntu supergroup 50 2015-05-06 22:43 /user/my_file3.txt

# clear all data and folders on HDFS
hdfs dfs -rm /user/my_file*
# 15/05/06 22:49:06 INFO fs.TrashPolicyDefault: Namenode trash configuration: Deletion interval = 0 minutes, Emptier interval = 0 minutes.
# Deleted /user/my_file.txt
# 15/05/06 22:49:06 INFO fs.TrashPolicyDefault: Namenode trash configuration: Deletion interval = 0 minutes, Emptier interval = 0 minutes.
# Deleted /user/my_file2.txt
# 15/05/06 22:49:06 INFO fs.TrashPolicyDefault: Namenode trash configuration: Deletion interval = 0 minutes, Emptier interval = 0 minutes.
# Deleted /user/my_file3.txt

hdfs dfs -rmdir /user