davidgin

davidgin / schema.sql

Created June 15, 2016 08:52 — forked from fernandomantoan/schema.sql

Schema for PostgreSQL to use with JdbcTokenStore (Spring Security OAuth2)

	create table oauth_client_details (
	client_id VARCHAR(256) PRIMARY KEY,
	resource_ids VARCHAR(256),
	client_secret VARCHAR(256),
	scope VARCHAR(256),
	authorized_grant_types VARCHAR(256),
	web_server_redirect_uri VARCHAR(256),
	authorities VARCHAR(256),
	access_token_validity INTEGER,
	refresh_token_validity INTEGER,

davidgin / MultipleOutputs.scala

Created September 26, 2015 16:42 — forked from silasdavis/MultipleOutputs.scala

Wrapping OutputFormat to produce multiple outputs with hadoop MultipleOutputs

	/**
	* This file contains the core idea of wrapping an underlying OutputFormat with an OutputFormat
	* with an augmented key that writes to partitions using MultipleOutputs (or something similar)
	*/

	package model.hadoop

	import model.hadoop.HadoopIO.MultipleOutputer
	import model.hadoop.HadoopIO.MultipleOutputer._
	import org.apache.hadoop.io.{DataInputBuffer, NullWritable}

davidgin / query.hive.template

Created January 18, 2013 19:59 — forked from tovbinm/query.hive.template

	ADD JAR s3://<s3-bucket>/jars/hive_contrib-0.5.jar;

	CREATE TEMPORARY FUNCTION now as 'com.mt.utils.udf.Now';
	CREATE TEMPORARY FUNCTION user_agent_f as 'com.mt.utils.UserAgent';

	set hive.merge.mapredfiles=true;
	set hive.merge.mapfiles=true;
	set hive.merge.size.per.task=500000000;

	CREATE EXTERNAL TABLE data

davidgin / gist:4151316

Created November 26, 2012 23:21 — forked from criccomini/gist:3775858

Sort Reducer Input Values in Hadoop

	public class SortReducerByValues {
	public static final String INPUT = "/tmp/data_in";
	public static final String OUTPUT = "/tmp/data_out";

	public static void main(String[] args) throws IOException {
	new SortReducerByValues().run();
	}

	public void run() throws IOException {
	JobConf conf = new JobConf();