andre3k1

import java.util.Arrays;
import java.util.Date;
import java.util.List;
import java.util.UUID;

import com.amazonaws.AmazonServiceException;
import com.amazonaws.auth.AWSCredentials;
import com.amazonaws.auth.PropertiesCredentials;
import com.amazonaws.services.ec2.model.InstanceType;
import com.amazonaws.services.elasticmapreduce.AmazonElasticMapReduce;

andre3k1

package com.senzari

object Levenshtein {
  
  def distance(start: String, target: String): Int = {

    val slen = start.length()
    val tlen = target.length()
    
    def inner(start: String, target: String): Array[Array[Int]] = {

andre3k1

export HADOOP_DIRECTORY=???
export HDFS_DIRECTORY=???

mkdir -p $HDFS_DIRECTORY/name $HDFS_DIRECTORY/data $HDFS_DIRECTORY/backup

echo "<?xml version=\"1.0\"?>
<?xml-stylesheet type=\"text/xsl\" href=\"configuration.xsl\"?>

<!-- Put site-specific property overrides in this file. -->

andre3k1

export HADOOP_MASTER_IP=???
export HADOOP_DIRECTORY=???
export HDFS_DIRECTORY=???

mkdir -p $HDFS_DIRECTORY/tmp $HDFS_DIRECTORY/system

echo "<?xml version=\"1.0\"?>
<?xml-stylesheet type=\"text/xsl\" href=\"configuration.xsl\"?>

<!-- Put site-specific property overrides in this file. -->

andre3k1

def md5ToLong(md5: String) = {
  var hash = 1125899906842597L
  for (n <- 0 until md5.length) hash = 31 * hash + md5.charAt(n)
  hash
}

andre3k1

ARTIST CSV SCHEMA
-----------------
artistId,name,popularity,tags,image,url

RELEASE CSV SCHEMA
------------------
releaseId,title,version,artistId,artistAppearsAs,barcode,type,year,explicitContent,trackCount,duration,tags,licensorId,image,dateAdded,releaseDate,labelId,labelName,formats,price,rrp,url

TRACK CSV SCHEMA
----------------

andre3k1

ARTIST CSV SCHEMA
-----------------
artistId,name,popularity,tags,image,url

name

RELEASE CSV SCHEMA
------------------
releaseId,title,version,artistId,artistAppearsAs,barcode,type,year,explicitContent,trackCount,duration,tags,licensorId,image,dateAdded,releaseDate,labelId,labelName,formats,price,rrp,url

andre3k1

#!/bin/sh
export SCALA_VERSION=2.9.2 # This is the only configuration setting
sudo curl -O http://www.scala-lang.org/files/archive/scala-$SCALA_VERSION.tgz
sudo tar -zxf scala-$SCALA_VERSION.tgz
sudo rm -rf scala-$SCALA_VERSION.tgz
sudo mv scala-$SCALA_VERSION /usr/local
sudo ln -s /usr/local/scala-$SCALA_VERSION/bin/scala /usr/bin/scala
sudo ln -s /usr/local/scala-$SCALA_VERSION/bin/scalac /usr/bin/scalac
sudo ln -s /usr/local/scala-$SCALA_VERSION/bin/fsc /usr/bin/fsc
sudo ln -s /usr/local/scala-$SCALA_VERSION/bin/sbaz /usr/bin/sbaz

andre3k1

#!/bin/bash -ev

# Download Scala
wget http://www.scala-lang.org/files/archive/scala-2.9.3.tgz
tar -zxf scala-2.9.3.tgz
rm -rf scala-2.9.3.tgz
export SCALA_HOME=/home/hadoop/scala-2.9.3

# Download Spark
wget http://spark-project.org/files/spark-0.7.2-sources.tgz

andre3k1

#!/bin/bash
#
# This "post-receive" script receives from stdin three arguments in the form:
#   <oldrev> <newrev> <refname>
#
while read oldrev newrev ref
do
  branch=`echo $ref | cut -d/ -f3`
  if [ "master" == "$branch" ]; then
    git --work-tree=/var/www/default/public_html/ checkout -f $branch