badzil

#!/usr/bin/ruby
# This script installs to /usr/local only. To install elsewhere you can just
# unzip https://github.com/mxcl/homebrew/zipball/master anywhere you like.

module Tty extend self
  def blue; bold 34; end
  def white; bold 39; end
  def red; underline 31; end
  def reset; escape 0; end
  def bold n; escape "1;#{n}" end

badzil

* Strip spaces at start and end
* Replace tabs with space
* Collapse multiple spaces
* Reverse the affiliations file
* Load into Google refine.

badzil

import re

_RE_MULTIPLE_SPACES = re.compile('\s\s+')
_RE_AFFILIATION_PREFIX = re.compile('([A-Z][A-Z]+)\(')
_RE_AFFILIATION_SUFFIX = re.compile('\)[,;]? [A-Z][A-Z]+\(')
_RE_EMAIL = re.compile(';?\s?<EMAIL>\s?(.*?)\s?</EMAIL>;?')

def clean_affiliations_string(affiliations_string):
    """
    Strips the spaces and collapses multiple spaces.

badzil

Original inspiration found here:
http://www.openerp.com/forum/topic21864.html

== Install libxml2 ==

$ wget ftp://xmlsoft.org/libxml2/libxml2-sources-2.7.8.tar.gz
$ tar xvf libxml2-sources-2.7.8.tar.gz
$ cd libxml2-2.7.8/
$ ./configure --with-python=/usr/bin/python2.6
$ make

badzil

#!/usr/bin/python

from invenio.dbquery import run_sql
from invenio.websearchadminlib import add_col

def collection_exist(tag):
    """
    Checks if a collection exists.
    @return: The name of the collection if it exists, None otherwise.
    """