dimus

# USAGE: Hash.from_xml:(YOUR_XML_STRING)
require 'nokogiri'
# modified from http://stackoverflow.com/questions/1230741/convert-a-nokogiri-document-to-a-ruby-hash/1231297#1231297

class Hash
  class << self
    def from_xml(xml_io) 
      begin
        result = Nokogiri::XML(xml_io)
        return { result.root.name.to_sym => xml_node_to_hash(result.root)} 

atomotic

#!/bin/bash

. heritrix.conf

if [ -z "$1" ] || [ -z "$2" ]; then 
  echo usage: $0 jobname seedsfile
  exit
fi

JOB=$1

dchud

#!/usr/bin/env python

import grp
import mimetypes
from optparse import OptionParser
import os
from pprint import pprint
import pwd
from stat import *
import sys

dchud

<?xml version="1.0" encoding="UTF-8" ?>
<!--
 Licensed to the Apache Software Foundation (ASF) under one or more
 contributor license agreements.  See the NOTICE file distributed with
 this work for additional information regarding copyright ownership.
 The ASF licenses this file to You under the Apache License, Version 2.0
 (the "License"); you may not use this file except in compliance with
 the License.  You may obtain a copy of the License at

     http://www.apache.org/licenses/LICENSE-2.0

Access 2010 Hackfest PHP Chart Generator

<?php
// The gChart PHP library is required in order to make this work. You can download it from http://code.google.com/p/gchartphp/

// Make sure you put it in the same directory as this script

ini_set('display_errors','1');
$server_address = 'http://142.132.138.20:8983';
require ('gChart.php');
if ( isset($_GET['query'])) {
	$query =  'mimetype:' . strtolower($_GET['query']) . '*';

acdha

def ocr_file(filename, languages, output_base, temp_dir):
    log.info("Launching tesseract on %s", filename)
    output = subprocess.check_output(['tesseract', filename, output_base,
                                      '-l', '+'.join(languages), TESSERACT_CONFIG],
                                     cwd=temp_dir,
                                     stderr=subprocess.STDOUT)

    with OCR_STORAGE.open('%s/%s/%s.log' % (item_id, group, index), 'w') as log_f:
        log_f.write(output)

richardlehane

package itforarchivists

import (
	"encoding/json"
	"fmt"
	"net/http"

	"github.com/richardlehane/siegfried/pkg/core"
	"github.com/richardlehane/siegfried/pkg/pronom"
)

mschoch

#!/bin/sh

# create a custom mapping
cat > /tmp/mapping.json << MAPPING
{
  "types": {
    "_default": {
      "properties": {
        "location": {
          "properties": {

ryanfb

#!/bin/bash

PREFIX=$(basename "$1" .pdf)
if [ ! -z "$TESSERACT_FLAGS" ]; then
  echo "Picked up TESSERACT_FLAGS: $TESSERACT_FLAGS"
fi
echo "Prefix is: $PREFIX"
echo "Converting to TIFF..."
if command -v parallel >/dev/null 2>&1; then
  LAST_PAGE=$(($(pdfinfo "$1"|grep '^Pages:'|awk '{print $2}') - 1))

olberger

#!/bin/sh

#set -x

# Usage: shibb-cas-get.sh {username} {password} # If you have any errors try removing the redirects to get more information
# The service to be called, and a url-encoded version (the url encoding isn't perfect, if you're encoding complex stuff you may wish to replace with a different method)

DEST=https://myapp.example.com/
SP=https://myapp.example.com/index.php
IDP="https://myidp.example.com/idp/shibboleth&btn_sso=SSOok"