hakanilter

CREATE TABLE sampledb.test_empty_array_parquet
WITH (
     format = 'PARQUET', 
     external_location = 's3://somewhere'
)
AS SELECT *
FROM sampledb.test_empty_array

hakanilter

/*
  Add following dependencies:
    com.microsoft.azure:azure-storage:2.0.0
    org.apache.hadoop:hadoop-azure:2.7.3
  Exclude:
    com.fasterxml.jackson.core:*:*
*/
spark.conf.set(
  "fs.azure.account.key.<your-storage-account-name>.blob.core.windows.net",
  "<your-storage-account-access-key>")

hakanilter

#! /bin/sh
### BEGIN INIT INFO
# Provides:          elasticsearch
# Required-Start:    $all
# Required-Stop:     $all
# Default-Start:     2 3 4 5
# Default-Stop:      0 1 6
# Short-Description: Starts elasticsearch
# Description:       Starts elasticsearch using start-stop-daemon
### END INIT INFO

hakanilter

import org.apache.spark.sql.functions.udf
import spark.implicits._

// read avro
val input = "/Users/hakanilter/dev/workspace/mc/data/avroFiles/*"
val data = spark.read
            .format("com.databricks.spark.avro")
            .option("header","true")
            .load(input)

hakanilter

# Script for generating csv partitions report for Impala
IMPALA_DAEMON=localhost

databases=$(impala-shell --quiet -i $IMPALA_DAEMON -d default --delimited -q "SHOW DATABASES" | cut -f1 | grep -e dl -e ods_)
for database in $databases
do
    echo $database
    directory="partitions/$database"
    mkdir -p $directory

hakanilter

tier1.sources  = source1
tier1.channels = channel1
tier1.sinks = sink1

# sources
tier1.sources.source1.type = org.apache.flume.source.kafka.KafkaSource
tier1.sources.source1.zookeeperConnect = localhost:2181
tier1.sources.source1.topic = network-data
tier1.sources.source1.groupId = flume-kafka-test
tier1.sources.source1.channels = channel1

hakanilter

Create a new instance, edit following file

sudo vim /etc/yum.repos.d/cassandra.repo

Add Cassandra repo

[cassandra]
name=Apache Cassandra
baseurl=https://www.apache.org/dist/cassandra/redhat/311x/

hakanilter

#!/bin/bash

# install git
sudo yum install git

# maven
sudo wget http://repos.fedorapeople.org/repos/dchen/apache-maven/epel-apache-maven.repo -O /etc/yum.repos.d/epel-apache-maven.repo
sudo sed -i s/\$releasever/6/g /etc/yum.repos.d/epel-apache-maven.repo
sudo yum install -y apache-maven
mvn --version

hakanilter

var elasticsearch = require('elasticsearch');
var elastic = new elasticsearch.Client({
    host: 'localhost:9200',
    log: 'info'
});

var kafka = require('kafka-node'),
HighLevelConsumer = kafka.HighLevelConsumer,
client = new kafka.Client(),
consumer = new HighLevelConsumer(

hakanilter

SparkConf sparkConf = new SparkConf()
        .setAppName(JdbcDynamoDbExportJob.class.getSimpleName())
        .setMaster(config.getProperty("spark.master"));
JavaSparkContext jsc = new JavaSparkContext(sparkConf);
SQLContext sqlContext = new SQLContext(jsc);

// read from database
Properties properties = new Properties();
properties.setProperty("user", config.getProperty("jdbc.user"));
properties.setProperty("password", config.getProperty("jdbc.pass"));