thesis/convert.py

#!/usr/bin/env python3
import sys
import re
from subprocess import run
from os.path import splitext
from glob import glob

title_re = re.compile(r'^# (.*)$', re.MULTILINE)
tex_re = re.compile(r'\\begin{document}(.*)\\end{document}', re.MULTILINE | re.DOTALL)


def parse_title(infilename):
    # Find chapter title
    with open(infilename) as f:
        matches = title_re.findall(f.read())
    if matches:
        return matches[0]
    else:
        return splitext(infilename.split('/')[-1])[0]


def make_tex(infilename):
    title = parse_title(infilename)
    outfilename = splitext(infilename)[0]+'.tex'
    run(('pandoc', '-F', 'pandoc-crossref', '-F', 'pandoc-citeproc', '-s', infilename, '-o', outfilename,))
    with open(outfilename, 'r') as f:
        full = f.read()
        body = tex_re.findall(full)[0]
        body = body.replace('section{'+title+'}', 'chapter{'+title+'}')
    with open(outfilename, 'w') as f:
        f.write(body)


def make_html(infilename):
    title = parse_title(infilename)
    outfilename = splitext(infilename)[0]+'.html'
    run(('pandoc', '-F', 'pandoc-crossref', '-F', 'pandoc-citeproc', '-s', infilename, '-o', outfilename,
         '--metadata=linkReferences:true', f'--metadata=pagetitle:{title}'))


def main():
    if len(sys.argv) != 2 or sys.argv[1] not in ('html', 'tex'):
        print('usage: ./convert.py [html|tex]')
        sys.exit(1)
    for infilename in glob('content/*_*.md'):
        if sys.argv[1] == 'html':
            make_html(infilename)
        else:
            make_tex(infilename)


if __name__ == '__main__':
    main()