AzimUddin

# mapreduce example with hadoop job configurations
$clusterName = "YourClusterName"
$jobConfig = @{ "mapred.output.compress"="true"; "mapred.output.compression.codec"="org.apache.hadoop.io.compress.GzipCodec" }
$myWordCountJob = New-AzureHDInsightMapReduceJobDefinition -JarFile "/example/jars/hadoop-examples.jar" -ClassName "wordcount" -jobName "WordCountJob" -StatusFolder "/MyMRJobs/WordCountJobStatus" -Defines $jobConfig 
$myWordCountJob.Arguments.Add("/example/data/gutenberg/davinci.txt")
$myWordCountJob.Arguments.Add("MyMRJobs/WordCountOutput")
$MyMRJob = Start-AzureHDInsightJob -Cluster $clusterName -JobDefinition $myWordCountJob

#Hive Job example with hadoop job configurations
$clusterName = "YourClusterName" 

AzimUddin

var mapReduceJob = new MapReduceJobCreateParameters() 
{
      ClassName = "wordcount", // required
      JobName = "MyWordCountJob", //optional
      JarFile = "/example/jars/hadoop-examples.jar",  // Required, alternative syntax: wasb://hdijobs@azimasv2.blob.core.windows.net/example/jar/hadoop-examples.jar
      StatusFolder = "/AzimMRJobs/WordCountJobStatus" //Optional, but good to use to know where logs are uploaded in Azure Storage
};

//WordCount progam needs two arguments
mapReduceJob.Arguments.Add("/example/data/gutenberg/davinci.txt"); //input file

AzimUddin

# An Example of using passing hadoop configurations for a job in HDInsight, via direct REST API
$MyHDInsightUserName = "YourClusterUserName"
$MyHDInsightPwd = "YourPwd"
$clusterName = "YourClusterName"
$storageAcctname = "YourStorageAcctname"
$containerName = "YourDefaultContainerName"

$HdInsightPwd = ConvertTo-SecureString $MyHDInsightPwd -AsPlainText -Force
$HdInsightCreds = New-Object System.Management.Automation.PSCredential ($MyHDInsightUserName, $HdInsightPwd)

AzimUddin

/*1. Create a Visual studio 2012 Project.
2. Add HDInsight SDK NuGet to your project -
In Visual Studio 2012, Click on Tools -> library package manager -> Package Manager Console 
PM> Install-Package Microsoft.WindowsAzure.Management.HDInsight 
3. Use the following code, fill up the relevant info, then build and run -
*/

using System;
using System.Collections.Generic;
using System.Linq;

AzimUddin

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
/**
 * Copyright 2010 The Apache Software Foundation
 *
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file

AzimUddin

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>com.microsoft.css</groupId>
  <artifactId>HBaseJavaApiTest</artifactId>
  <packaging>jar</packaging>
  <version>1.0-SNAPSHOT</version>
  <name>HBaseJavaApiTest</name>
  <url>http://maven.apache.org</url>
  <dependencies>

AzimUddin

package com.microsoft.css;
/**
 * Created by muddin on 6/4/2015.
 */
import java.sql.*;

public class MyHiveJdbcTest {

    public static void main(String[] args) throws SQLException {

AzimUddin

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>com.microsoft.css</groupId>
  <artifactId>HiveJdbcTest</artifactId>
  <packaging>jar</packaging>
  <version>1.0-SNAPSHOT</version>
  <name>HiveJdbcTest</name>
  <url>http://maven.apache.org</url>
  <dependencies>

AzimUddin

/// <summary>
/// Execute the function with retries on throttle
/// </summary>
/// <typeparam name="V"></typeparam>
/// <param name="client"></param>
/// <param name="function"></param>
/// <returns></returns>
private static async Task<V> ExecuteWithRetries<V>(DocumentClient client, Func<Task<V>> function)
{
        TimeSpan sleepTime = TimeSpan.Zero;

AzimUddin

/* Copied from: https://github.com/Azure/azure-documentdb-net/blob/master/samples/code-samples/ServerSideScripts/JS/BulkImport.js
*/

function bulkImport(docs) {
    var collection = getContext().getCollection();
    var collectionLink = collection.getSelfLink();

    // The count of imported docs, also used as current doc index.
    var count = 0;