Crypto hash UDF for apache hive. Allows users to hash values using hive QL. Can be used to obfuscate data using MD5 or sha-1

README

1. compile the code
2. inside hive shell - run "add jar YOUR_JAR.jar;"
3. still inside shell - run "create temporary function crypt_hash as 'com.hiveextensions.udf.CryptoHash';"
4. usage - crypt_hash(FIELD_TO_HASH,ALGORITHM)   where algorithm can be any of {"sha-1","md5",...} 


http://docs.oracle.com/javase/6/docs/technotes/guides/security/StandardNames.html#MessageDigest

CryptoHash.java

package com.hiveextensions.udf;

import java.security.MessageDigest;
import java.security.NoSuchAlgorithmException;

import org.apache.hadoop.hive.ql.exec.UDF;

public final class CryptoHash extends UDF {

  public String evaluate(final String s, final String algorithm) {

		if (s == null)
			return null;
		try {
			MessageDigest md = MessageDigest.getInstance(algorithm);
			md.update(s.getBytes());
			byte[] mdhash = md.digest();
			StringBuilder builder = new StringBuilder();
			for (byte b : mdhash) {
				builder.append(Integer.toString((b & 0xff) + 0x100, 16).substring(1));
			}
			return builder.toString();
		} catch (NoSuchAlgorithmException nsae) {
			System.out.println("Unable to find encryption algorithm! msg[ "+nsae,getMessage()+" ]");
			System.exit(-1);
		}
		return null;
	}
}