sujee

System.out.println ("1000000 ms = " + StringUtils.formatTime(1000000));
long t1 = System.currentTimeMillis();
// execute a command
long t2 = System.currentTimeMillis();
t2 += 10000000; // adjust for this demo
System.out.println ("operation took : " + StringUtils.formatTimeDiff(t2, t1));

/* output:
1000000 ms = 16mins, 40sec
operation took : 2hrs, 46mins, 40sec

sujee

import org.apache.hadoop.util.StringUtils;

// ----------------- String Utils : bytes <--> hex ---------
String s = "aj89y1_xxy";
byte[] b = s.getBytes();
String hex = StringUtils.byteToHexString(b);
byte[] b2 = StringUtils.hexStringToByte(hex);
String s2 = new String(b2);
System.out.println(s + " --> " + hex + " <-- " + s2);

sujee

import org.apache.hadoop.util.StringUtils;

// --- human readable  byte lengths -----
System.out.println ("1024 bytes = " + StringUtils.byteDesc(1024));
System.out.println ("67108864 bytes = " + StringUtils.byteDesc(67108864));
System.out.println ("1000000 bytes = " + StringUtils.byteDesc(1000000));

/* produces:
1024 bytes = 1 KB
67108864 bytes = 64 MB

sujee

import org.apache.hadoop.util.Shell.ShellCommandExecutor;

String[] cmd =    { "ls", "/usr" };
ShellCommandExecutor shell = new ShellCommandExecutor(cmd);
shell.execute();
System.out.println("* shell exit code : " + shell.getExitCode());
System.out.println("* shell output: \n" + shell.getOutput());

/* output:
* shell exit code : 0

sujee

<?php


$API_KEY="api_key_here";

$response = file_get_contents("https://covercake.com/api/v1/feeds?key=$API_KEY");
$j = json_decode($response);
#var_dump($j);

if (strcasecmp($j->status, "OK") != 0)

sujee

require 'rubygems'
#install the following gems
require 'json'
require 'rest_client'

API_KEY="your_key_here"

response = RestClient.get "https://covercake.com/api/v1/feeds",  {:params => {:key => API_KEY}}
j = JSON::parse(response)
#p response

sujee

#!/bin/bash

# config
# if changing machine type, also change mapred config file
MASTER_INSTANCE_TYPE="m1.large"
SLAVE_INSTANCE_TYPE="c1.xlarge"
INSTANCES=5
export JOBNAME="MyMR"
export TIMESTAMP=$(date +%Y%m%d-%H%M%S)
# end config

sujee

package amazonemr;

import java.net.URI;
import java.util.Enumeration;
import java.util.Properties;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;

sujee

require 'rubygems'
require 'json'

a = JSON::parse(ARGF.read)
#p a 
p a["JobFlows"][0]["ExecutionStatusDetail"]["State"]

sujee

#!/bin/bash
## http://sujee.net/tech/articles/amazon-emr-beyond-basics/

echo "=== $JOBID started...."

LOGDIR="/var/logs/hadoop-logs/${JOBNAME}__${JOBID}__${TIMESTAMP}"
mkdir -p "${LOGDIR}"

## stuff below is to wait till the jobs is done