erochest

CREATE EXTENSION xml2;

-- Credit where credit's due. Or blame:
-- http://dba.publicexchange.com/a/8188
create or replace function bytea_import(p_path text, p_result out bytea) 
                   language plpgsql as $$
declare
  l_oid oid;
  r record;
begin

erochest

(function(window, $, undefined) {
    var $window = $(window);
    
/**
 * Show or hide the button depending on the scroll position.
 */
function animateButton() {
    var button = $('#back-to-top');
    var scrollPosition = $window.scrollTop();
    if (scrollPosition > 400) {

erochest

#!/bin/sh

R -e 'library(Rserve)' -e 'Rserve(args="--vanilla")'

erochest

@echo off

setLocal EnableExtensions EnableDelayedExpansion

set LEIN_VERSION=2.0.0

if "%LEIN_VERSION:~-9%" == "-SNAPSHOT" (
    set SNAPSHOT=YES
) else (
    set SNAPSHOT=NO

erochest

# A palate cleanser for apt.

exec { 'apt-get update':
  path => ['/usr/bin'],
}

## These two use this module: https://github.com/erochest/puppet-omeka
## Use this to automate getting that set up: https://github.com/erochest/omeka-vm

class { 'omeka':

erochest

[1, 1, 2, 3, 5].each { |x| x * 2 }

erochest

<address class="vcard" vocab="http://www.w3.org/2006/vcard/ns#" resource="http://scholarslab.org/" typeof="Organization">
  <span class="org fn">
    <a class="url organization-name" href="http://scholarslab.org/">
      <span property="formattedName">Scholars’ Lab</span>
    </a>
    <a class="organization-unit extended-address" href="http://lib.virginia.edu/" property="hasOrganizationName" resource="http://lib.virginia.edu/" typeof="Organization">
      <span property="formattedName">University of Virginia Library</span>
    </a>
  </span>
  <span property="hasAddress" typeof="Work">

erochest

Notes

This contains the files I used to perform the timings, as well as the timings themselves.

The timings are to process one bag with 60,000 small files and one bag with one large (10GB) file. Scripts related to the bag with many files are named like *-lots, and scripts related to the bag with one large file are named like *-large.

What I'm Timing

Ruby

erochest

#!/usr/bin/env python


import codecs
import os

import lxml.etree as ET


## CHANGE THIS:

erochest

#!/usr/bin/env python


import codecs
import os

import lxml.etree as ET


## CHANGE THIS: