djpillen’s gists

djpillen / setup_mysql.sh

Last active January 18, 2016 17:22

Setup MySQL for Archivgrant

	#!/usr/bin/env bash

	# Export MySQL root password before installing to prevent MySQL from prompting for a password during the installation process
	# http://stackoverflow.com/questions/18812293/vagrant-ssh-provisioning-mysql-password
	echo "mysql-server mysql-server/root_password password rootpwd" \| debconf-set-selections
	echo "mysql-server mysql-server/root_password_again password rootpwd" \| debconf-set-selections

	# Install mysql-server and create the archivesspace database
	# http://archivesspace.github.io/archivesspace/user/running-archivesspace-against-mysql/
	# https://gist.github.com/rrosiek/8190550

djpillen / setup_python.sh

Last active January 18, 2016 17:22

Setup Python for Archivagrant

djpillen / Vagrantfile

Created January 18, 2016 16:57

ArchivesSpace Vagrantfile

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

	Vagrant.configure(2) do \|config\|

	config.vm.box = "hashicorp/precise32"

	config.vm.network "forwarded_port", guest: 8080, host: 8080
	config.vm.network "forwarded_port", guest: 8089, host: 8089

djpillen / date_tails.py

Last active August 29, 2015 14:25

Find dates with tails

	from lxml import etree
	import os
	from os.path import join
	import re

	text = re.compile(r'\w')

	for filename in os.listdir(path):
	tree = etree.parse(join(path,filename))
	titles = tree.xpath('//unittitle')

djpillen / replace_normalized_dates.py

Last active August 29, 2015 14:24

Insert normalized dates from an OpenRefine exported CSV into EADs

	# import what we need
	import csv
	from lxml import etree
	from os.path import join

	path = 'path/to/eads' # Enter the path to your EAD directory here

	normalized_file = 'path/to/exported_csv.csv' # Enter the path to the exported CSV here

	with open(normalized_file, 'rb') as csvfile:

djpillen / get_non-normalized_dates.py

Last active August 29, 2015 14:23

Output the text of all <unitdate> tags that are not 'undated' and do not have a 'normal' attribute

	import csv
	import lxml
	from lxml import etree
	import os
	from os.path import join
	import re


	path = '/path/to/EADs' # Enter the path to your EAD directory

djpillen / normalize_dates.py

Last active August 29, 2015 14:21

Add a normal attribute to dates that are years or ranges of years

	#import what we need
	import lxml
	from lxml import etree
	import os
	from os.path import join
	import re


	path = 'path/to/EADs' #<-- Change this to your EAD directory path

djpillen / missingtitles.py

Last active August 29, 2015 14:21

Find missing titles

	import lxml
	from lxml import etree
	import os
	from os.path import join

	# Enter the path to the folder containing your EADs
	path = 'path/to/EADs'

	# Check each file in the EAD folder
	for filename in os.listdir(path):

djpillen / printextents.py

Last active August 29, 2015 14:21

Print Extents from EADs

	import lxml
	from lxml import etree
	import os
	from os.path import join

	# Enter the path to the folder containing your EADs
	path = 'path/to/EADs'

	# Check each file in the EAD folder
	for filename in os.listdir(path):

Dallas Pillen djpillen