erochest

#!/bin/bash

SOURCE=origin
DEST=bitbucket

for b in $(git branch -r | grep $SOURCE | grep -v -- '->' | sed 's/origin\///' | tr -d ' '); do
    echo $b
    git checkout $b
    git pull
    git push $DEST $b

erochest

#!/usr/bin/env python


"""Run a command and generate an alert when it's done."""


import argparse
import subprocess

erochest

#!/usr/bin/env python


# Dependencies:
# - pip install lxml
# - pip install cssselect
# - pip install requests

import collections
import csv

erochest

#!/bin/bash

USAGE=<<EOF
cabal-brew PACKAGE VERSION
EOF

CABAL=cabal
package="$1"
keg="cabal-$package"
version="$2"

erochest

# vi: set ft=ruby :

VAGRANTFILE_API_VERSION = "2"

Vagrant.configure(VAGRANTFILE_API_VERSION) do |config|
  config.vm.box = "ubuntu-13.10"
  config.vm.box_url = "http://cloud-images.ubuntu.com/vagrant/saucy/current/saucy-server-cloudimg-amd64-vagrant-disk1.box"
end

erochest

# -*- mode: ruby -*-
# vi: set ft=ruby :

# Vagrantfile API/syntax version. Don't touch unless you know what you're doing!
VAGRANTFILE_API_VERSION = "2"

Vagrant.configure(VAGRANTFILE_API_VERSION) do |config|
  config.vm.box = "ubuntu-13.10"
  config.vm.box_url = "http://cloud-images.ubuntu.com/vagrant/saucy/current/saucy-server-cloudimg-amd64-vagrant-disk1.box"
end

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:

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

<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">