A Hive UDF in C# (for HDInsight)

example.hql

add file wasb:///HiveUDF.exe;

SELECT TRANSFORM (clientid, devicemake, devicemodel)
  USING 'HiveUDF.exe' AS
  (clientid string, phoneLabel string, phoneHash string)
FROM hivesampletable
ORDER BY clientid LIMIT 50;

hiveudf.cs

using System;
using System.Security.Cryptography;
using System.Text;
using System.Threading.Tasks;

namespace HiveUDF
{
    class Program
    {
        static void Main(string[] args)
        {
            string line;
            try
            {
                while ((line = Console.ReadLine()) != null)
                {
                    //do stuff
                    line = line.TrimEnd('\n');
                    string[] field = line.Split('\t');
                    string phoneLabel = field[1] + ' ' + field[2];
                    Console.WriteLine("{0}\t{1}\t{2}", field[0], phoneLabel, GetMD5Hash(phoneLabel));
                }
            }
            catch (Exception ex)
            {
                //bad format or end of line so do nothing
            }
        }
        static string GetMD5Hash(string input)
        {
            // step 1, calculate MD5 hash from input
            MD5 md5 = System.Security.Cryptography.MD5.Create();
            byte[] inputBytes = System.Text.Encoding.ASCII.GetBytes(input);
            byte[] hash = md5.ComputeHash(inputBytes);
 
            // step 2, convert byte array to hex string
            StringBuilder sb = new StringBuilder();
            for (int i = 0; i < hash.Length; i++)
            {
                sb.Append(hash[i].ToString("x2"));
            }
            return sb.ToString();
        }
    }
}

A basic example of a C# UDF that can be used from Hive on Azure HDInsight. Note that this works either with Windows-based HDInsight (compiled using VS 2013,) or Linux-based HDInsight (with Mono installed.)