Converter for SIKS dissertation list to LaTeX

siks2tex.py

#!/usr/bin/env python
'''
Quick and dirty hack to get the SIKS dissertation list in LaTeX.
Original code taken from https://gist.github.com/breuderink/1253855
'''
import argparse, re, operator, itertools, sys

def tex_escape(text):
	"""
		:param text: a plain text message
		:return: the message escaped to appear correctly in LaTeX
	"""
	conv = {
		'&': r'\&',
		'%': r'\%',
		'$': r'\$',
		'#': r'\#',
		'_': r'\_',
		'{': r'\{',
		'}': r'\}',
		'~': r'\textasciitilde{}',
		'^': r'\^{}',
		'\\': r'\textbackslash{}',
		'<': r'\textless ',
		'>': r'\textgreater ',
	}
	regex = re.compile('|'.join(re.escape(unicode(key)) for key in sorted(conv.keys(), key = lambda item: - len(item))))
	return regex.sub(lambda match: conv[match.group()], text)

parser = argparse.ArgumentParser(
  description='Convert SIKS dissertation list to LaTeX.')
parser.add_argument('txt')
parser.add_argument('tex')
parser.add_argument('-n', '--output-lines', type=int, default=10000)
parser.add_argument('-y', '--min-year', type=int, default=2011)

args = parser.parse_args()

dissertations = []
with open(args.txt, 'r') as f:
  for line in f:
    match =  re.search(r'\d{4}-\d+', line)
    if match:
		titleMatch = re.search(r'(\d{4}-\d+)\s+(\S.+)', line)
		if titleMatch:
			diss_id =  match.group(0)
			author = titleMatch.group(2)
		else: 
			diss_id =  match.group(0)
			author = f.next().strip()      
		title = f.next().strip()
		dissertations.append((diss_id, author, tex_escape(title)))

sorted_diss = sorted(dissertations, key=operator.itemgetter(0), reverse=False)

with open(args.tex, 'w') as f:
	diss_cmd = r'\newcommand{\SIKSdiss}[3]{{\textbf{#1}}\hspace*{1ex}#2, {\textit{#3}.}\\}'
	f.write('%s\n\n' % diss_cmd)
	year_cmd = r'\newcommand{\SIKSyear}[1]{{\textbf{#1}}\\}'
	f.write('%s\n\n' % year_cmd)
	oldYear = 0
	print args.min_year
	for diss in sorted_diss[:args.output_lines]:
		match = re.search(r'(\d{4})-(\d+)', diss[0])
		year = int(match.group(1))
		if year >= args.min_year:		
			if (year > oldYear):
				oldYear = year
				f.write('\\SIKSyear{%s}\n' % (year))
			number = match.group(2)
			f.write('\\SIKSdiss{%s}{%s}{%s}\n' % (number, diss[1], diss[2]))