Convert markdown to LaTeX

md_to_tex.py

#!/usr/local/bin/python3
#
# Usage:
#  md_to_tex.py <md_filename> > myfile.tex
#
# Converts simple markdown to a LaTeX file.
# Use, for example, "pdflatex myfile.tex" to
# generate a pdf file using your output file.
#
# The current script does *not* parse all
# markdown syntax; only a subset so far.
#

import os
import re
import sys

tex_start = r"""
\documentclass[11pt,oneside]{amsart}
\usepackage{geometry}
\geometry{letterpaper}
%\usepackage[parfill]{parskip}    % Activate to begin paragraphs with an empty line rather than an indent
\usepackage{graphicx}
\usepackage{amssymb}
\usepackage{epstopdf}
\DeclareGraphicsRule{.tif}{png}{.png}{`convert #1 `dirname #1`/`basename #1 .tif`.png}

\begin{document}
"""

tex_end = r"\end{document}"

indents = []
is_in_quote = False

def repl_quote(quote_match):
  global is_in_quote
  repl = r"''" if is_in_quote else r'``'
  is_in_quote = not is_in_quote
  return repl

# Accepts indent=-1 to indicate that
# the current list has ended completely.
def move_to_indent(indent):
  global indents
  if indent >= 0 and (len(indents) == 0 or indents[-1] < indent):
    indents.append(indent)
    print(r'\begin{itemize}')
    return
  while len(indents) > 0 and indents[-1] > indent:
    indents.pop()
    print(r'\end{itemize}')

def handle_line(line):
  global indents
  line = line.rstrip()

  always_subs = [[r'\*\*(\S.*?)\*\*', r'{\\bf \1}'],
                 [r'\*(\S.*?)\*',     r'{\\it \1}'],
                 [r'^---\s*$',        r'\\hrule'  ],
                 [r'"',               repl_quote  ]]
  for s in always_subs: line = re.sub(s[0], s[1], line)

  m = re.search(r'^( *)\* (.*)', line)
  if m:
    move_to_indent(len(m.group(1)))
    line = r'\item ' + m.group(2)
  else:
    indent = -1
    if re.search(r'^( +)\S', line) and len(indents): indent = indents[-1]
    move_to_indent(indent)

  normal_subs = [[r'^# (.*)',      r'\\rightline{\\Large \1}'],
                 [r'^## (.*)',     r'\\section{\1}'          ],
                 [r'^### (.*)',    r'\\subsection{\1}'       ],
                 [r'^#### (.*)',   r'\\subsubsection{\1}'    ],
                 [r'^#####+ (.*)', r'{\\bf \1}'              ]]
  for s in normal_subs: line = re.sub(s[0], s[1], line)

  print(line)

if __name__ == '__main__':

  if len(sys.argv) < 2:
    print('Usage: %s <md_filename>' % os.path.basename(sys.argv[0]))
    print('Output is sent to stdout.')
    exit(2)
  
  print(tex_start)

  with open(sys.argv[1]) as f:
    for line in f:
      handle_line(line)

  print(tex_end)