#!/usr/bin/env python3
# encoding: utf-8
# Copyright (C) 2020, 2024 Denis 'GNUtoo' Carikli <GNUtoo@cyberdimension.org>
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program.  If not, see <https://www.gnu.org/licenses/>.

import bs4
import enum
import os
import re
import sys

def usage(progname):
    print("{} path/to/file.html".format(progname))
    sys.exit(1)

def fixup_html(html):
    open_p = 0
    buf = [None]  * 4
    for c in html:
        buf[0] = buf[1]
        buf[1] = buf[2]
        buf[2] = buf[3]
        buf[3] = c

        if buf[1] == '<' and buf[2] == 'p' and buf[3] == '>':
            open_p += 1
        if buf[0] == '<' and buf[1] == '/' and buf[2] == 'p' and buf[3] == '>':
            open_p -= 1

        if c == '\n' and open_p > 0:
            print(' ', end='')
        else:
            print(c, end='')
def main():
    if len(sys.argv) != 2:
        usage(sys.argv[0])

    html_file_path = sys.argv[1]

    with open(html_file_path) as html_file:
        soup = bs4.BeautifulSoup(html_file, 'html.parser')

        #################
        # Article title #
        #################
        article_title = soup.find(id='title').text
        print("Title: {}".format(article_title))

        ################
        # Post content #
        ################
        post_content = soup.find(id='post-content').extract()
        pretty_html = post_content.prettify()
        # Remove the outer <div id="post-content"> and </div>
        div_content = os.linesep.join(pretty_html.split(os.linesep)[1:-1]) + os.linesep
        print("Post content:")
        print('-' * 38 + ' %< ' + '-' * 38)
        fixup_html(div_content)
        print('-' * 38 + ' >% ' + '-' * 38)

if __name__ == '__main__':
    main()