lordjc

#!/usr/bin/python
import time
import datetime
import random
timestr = time.strftime("%Y%m%d-%H%M%S")

f = open('access_log_'+timestr+'.log','w')

ips=["123.221.14.56","16.180.70.237","10.182.189.79","218.193.16.244","198.122.118.164","114.214.178.92","233.192.62.103","244.157.45.12","81.73.150.239","237.43.24.118"]
referers=["-","http://www.casualcyclist.com","http://bestcyclingreviews.com/top_online_shops","http://bleater.com","http://searchengine.com"]

lordjc

// Use Gists to store code you would like to remember later on
console.log(window); // log the "window" object to the console

lordjc

#!/bin/bash
LINKDIR=/usr/bin
JHOME=/usr/java/jdk1.7.0_67-cloudera/
JREDIR=$JHOME/jre/bin
JDKDIR=$JHOME/bin


sudo alternatives --install $LINKDIR/java java $JREDIR/java 20000  \
  --slave $LINKDIR/keytool     keytool     $JREDIR/keytool         \
  --slave $LINKDIR/orbd        orbd        $JREDIR/orbd            \

lordjc

#!/bin/sh

setup_brew () {
    if ![-f "/usr/local/bin/brew"]; then
        /usr/bin/ruby -e "$(/usr/bin/curl -fsSL https://raw.github.com/mxcl/homebrew/master/Library/Contributions/install_homebrew.rb)"
    fi
}

setup_ipython () {
    brew install readline

lordjc

!/bin/bash

export tnow=$(date +"%Y-%m-%d")
export hnow=$(date +"%Y-%m-%d:%H")

export d_fname=ItemFulfillment-$tnow.csv
export h_fname=ItemFulfillment-$hnow.csv
export dirname=ItemFulfillment
export FTP_SERVER='IP'

lordjc

#!/usr/bin/python
import csv
import sys
import argparse
from string import Template
import subprocess

debug = False

def output(hdfspath,data):

lordjc

#!/usr/bin/python
import csv
import sys
import argparse
import io

def genSchema(coldict):

	ss = """
{"namespace": "example.avro",

lordjc

#!/usr/bin/python
import csv
import sys
import argparse
import io

csv.field_size_limit(sys.maxsize)

parser = argparse.ArgumentParser(description='Clean csv of in-line newlines')
parser.add_argument('infile',help='Path to input CSV file');

lordjc

<workflow-app name="sqoopSqlServerAndCreateHive" xmlns="uri:oozie:workflow:0.4">
  <global>
            <configuration>
                <property>
                    <name>table</name>
                    <value></value>
                </property>
                <property>
                    <name></name>
                    <value></value>

lordjc

#!/usr/bin/python
#
#pip install https://pyodbc.googlecode.com/files/pyodbc-2.1.11.zip
#Install the microsoft odbc driver for linux available here:
#http://www.microsoft.com/en-us/download/details.aspx?id=28160

import pyodbc

cnxn = pyodbc.connect('DRIVER=SQL Server Native Client 11.0;SERVER=<ip>;UID=<username>;PWD=<password>')
cursor = cnxn.cursor()