zygm0nt

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.coprocessor.BaseRegionObserver;
import org.apache.hadoop.hbase.coprocessor.ObserverContext;
import org.apache.hadoop.hbase.coprocessor.RegionCoprocessorEnvironment;
import org.apache.hadoop.hbase.regionserver.HRegion;

zygm0nt

    > db.items.find({_id:ObjectId("4f7f4ae4251735803a942b2c")}).pretty()
    {
    	"_id" : ObjectId("4f7f4ae4251735803a942b2c"),
    	"category" : "",
    	"title" : "sample title",
    	"permalink" : "http://",
    	"source" : "s",
    	"description" : "Sample Description",
    	"image" : "http://",
    	"modificationDate" : ISODate("2012-04-06T19:58:28.448Z"),

zygm0nt

public class MRJob extends Configured implements Tool {


    public static void main(String[] args) throws Exception {
        int res = ToolRunner.run(HBaseConfiguration.create(), new MRJob(), args);
        System.exit(res);
    }

    @Override
    public int run(String[] args) throws Exception {

zygm0nt

#!/bin/bash
# Description of script

# bash strict mode: http://redsymbol.net/articles/unofficial-bash-strict-mode/
set -euo pipefail
IFS=$'\n\t'

# Display usage if no parameters given
if [[ -z "$@" ]]; then
  echo " ${0##*/} <input> - description"

zygm0nt

Important!

Remember to run google-chrome like this, for the time of installing this user script:

$ google-chrome --enable-easy-off-store-extension-install

zygm0nt

require 'rubygems'
require 'nokogiri'
require 'fileutils'
require 'date'
require 'uri'

# usage: ruby import.rb my-blog.xml
# my-blog.xml is a file from Settings -> Basic -> Export in blogger.

data = File.read ARGV[0]

zygm0nt

Guide: Writing Testable Code

To keep our code at Google in the best possible shape we provided our software engineers with these constant reminders. Now, we are happy to share them with the world.

Many thanks to these folks for inspiration and hours of hard work getting this guide done:

* Jonathan Wolter
* Russ Ruffer
* Miško Hevery

zygm0nt

<property>
  <name>fs.default.name/name>
  <value>hdfs://example-cluster</value>
</property>

zygm0nt

<property>
  <name>fs.default.name/name>
  <value>hdfs://example-cluster</value>
</property>

zygm0nt

<h2>Hadoop Configuration</h2><pre>Configuration: core-default.xml, core-site.xml, mapred-default.xml, mapred-site.xml, yarn-default.xml, yarn-site.xml, hdfs-default.xml, hdfs-site.xml

<table><tr><th>Key</th><th>Value</th></tr><tr><td>dfs.datanode.data.dir</td><td>file://${hadoop.tmp.dir}/dfs/data</td</tr><tr><td>dfs.namenode.checkpoint.txns</td><td>40000</td</tr><tr><td>s3.replication</td><td>3</td</tr><tr><td>mapreduce.output.fileoutputformat.compress.type</td><td>RECORD</td</tr><tr><td>mapreduce.jobtracker.jobhistory.lru.cache.size</td><td>5</td</tr><tr><td>dfs.datanode.failed.volumes.tolerated</td><td>0</td</tr><tr><td>hadoop.http.filter.initializers</td><td>org.apache.hadoop.http.lib.StaticUserWebFilter</td</tr><tr><td>mapreduce.cluster.temp.dir</td><td>${hadoop.tmp.dir}/mapred/temp</td</tr><tr><td>mapreduce.reduce.shuffle.memory.limit.percent</td><td>0.25</td</tr><tr><td>yarn.nodemanager.keytab</td><td>/etc/krb5.keytab</td</tr><tr><td>mapreduce.reduce.skip.maxgroups</td><td>0</td</tr><tr><td>dfs.https.