latex-control-char-replace.py uses regexes to replace latex control characters in tags other than tex-math

latex-control-char-replace.py

import re

from lxml import etree

def _escape_latex_control_chars_in(text):
  text = re.sub('#', r'\#', text)
  text = re.sub('{', r'\{', text)
  text = re.sub('}', r'\}', text)
  text = re.sub('~', r'\\textasciitilde', text) 
  text = re.sub('_', r'\_', text)
  text = re.sub('\^', r'\\textasciicircum', text)
  text = re.sub('%', r'\%', text)
  text = re.sub('\$', r'\$', text)

  return text

def escape_latex_control_chars(root):
  for elem in root.iter():
    text = elem.text
    tail = elem.tail

    if elem.tag != 'tex-math' and text and isinstance(text, (str, unicode)):
      elem.text = _escape_latex_control_chars_in(text)

    if tail and isinstance(tail, (str, unicode)):
      elem.tail = _escape_latex_control_chars_in(tail)

def unicode_replace(in_filename, out_filename):
  in_file = file(in_filename)
  in_tree = etree.parse(in_file)

  escape_latex_control_chars(in_tree)
  in_tree.write(file(out_filename, 'w'))

def out_filename_for(in_filename):
  return ''.join(in_filename.rsplit('.', 1)[:-1] + ['-unicode.xml'])

if __name__ == "__main__":
  import sys

  in_filename = sys.argv[1]
  out_filename = out_filename_for(in_filename)
  unicode_replace(in_filename, out_filename)