#!/bin/python3
# hrtime - transgender research website
# Copyright (C) 2025 Olive <hello@grasswren.net>
# see LICENCE file for licensing information

import re
import sys


def ch(st: str) -> str:
    st = re.sub(r'&', r'&amp;', st)
    st = re.sub(r'>', r'&gt;', st)
    st = re.sub(r'<', r'&lt;', st)
    return st


def qch(st: str) -> str:
    return re.sub('\'', r'&apos;', ch(st))


def mdh(line: str) -> str:
    ret = ''
    while len(line) > 0:
        match = re.match(r'!\[(.*?)\]\((.*?)\)', line)
        if match != None:
            line = line[match.span()[1]:]
            ret += f"<span class='n' title='{qch(match.group(2))}'>" + \
                    f'{ch(match.group(1))}</span>'
            continue

        match = re.match(r'\[(.*?)\]\(([^ ]*)\)', line)
        if match != None:
            line = line[match.span()[1]:]
            ret += f"<a href='{qch(match.group(2))}' target='_blank'" \
                    + f'>{ch(match.group(1))}</a>'
            continue

        match = re.match(r'`(.)(.*?)`', line)
        if match != None:
            line = line[match.span()[1]:]
            ret += r"<code" + (f" class='{match.group(1)}'" if match.group(1) \
                    != '/' else '') + f'>{ch(match.group(2))}</code>'
            continue

        ret += ch(line[0])
        line = line[1:]

    ret = re.sub(r'NOBREAK', r'&NoBreak;', ret)
    return ret


def md(line: str) -> str:
    # allows '|' and '||' escaping to work
    ret, do = '', True
    for sec in line.strip().split('|'):
        if len(sec) == 0:
            ret += '|'
        else:
            ret += mdh(sec) if do else sec
            do = not do
    return ret


def media(line: str):
    file, alt = tuple(line.strip().split('|'))
    file = qch(file)
    if file[-5:] in ('.webp'):
        print(f"<img src='{file}' alt='{qch(alt)}'>")
    if file[-4:] in ('.mp4'):
        print('<video controls>')
        print(f"<source src='{file}' type='video/mp4' alt='{qch(alt)}'>")
        print('</video>')
    if file[-4:] in ('.pdf'):
        print(f"<object data='{file}' type='application/pdf' height='80%'>")
        print(f"<a href='{file}'>{ch(alt)}</a>")
        print('</object>')


def doc(lines: list[str]):
    head = ''
    with open('head.html', 'r') as file:
        head = file.read()

    lines[0] = lines[0].strip()
    if len(lines[0]) > 0:
        lines[0] = ' — ' + lines[0]
    head = re.sub(r'TITLE', lines[0], head, count=2)
    print(head, end='')
    lines = lines[1:]

    mode=''
    for line in lines:
        if line[1:4] == '   ':
            if mode != '</code></pre>':
                if line[0] != '/':
                    cls = f" class='{line[0]}'"
                print(f'<pre><code{cls}>', end='')
                mode = '</code></pre>'
            print(ch(line[4:].rstrip()))
            continue
        elif line[:2] == '  ':
            if mode != '</ul>':
                print("<ul class='l'>")
                mode = '</ul>'
            print(f'<li>{md(line[2:])}</li>')
            continue
        elif line[:2] == '- ':
            if mode != '</ul>':
                print('<ul>')
                mode = '</ul>'
            print(f'<li>{md(line[2:])}</li>')
            continue

        if mode != '':
            print(mode)
            mode = ''

        if len(line) == 1:
            print('</section>\n<section>')
        elif line[:2] == '# ':
            print(f'<h1>{md(line[2:])}</h1>')
        elif line[:3] == '## ':
            print(f'<h2>{md(line[3:])}</h2>')
        elif line[:2] == '! ':
            media(line[2:])
        elif line[:2] == '@ ':
            title, link, desc, date = tuple(line[2:].split('|'))
            print('<article>\n<div>')
            print(f"<h1><a href='{qch(link)}'>{md(title)}</a></h1>")
            print('</div>\n<div>')
            print(f'<p>{md(desc)}</p>')
            print(f'<p>(<time>{date.strip()}</time>)</p>')
            print('</div>\n</article>')
        else:
            print('<p>' + md(line) + '</p>')

    if mode != '':
        print(mode)

    with open('foot.html', 'r') as file:
        print(file.read(), end='')


if __name__ == '__main__':
    if len(sys.argv) != 2:
        print('usage: md [file]')
    else:
        with open(sys.argv[1], 'r') as file:
            doc(list(file))