#!/usr/bin/env python3
# encoding: utf-8
# Copyright (C) 2020 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/>.

# How to use:
# - Download the release notes from Wordpress. If it's not published yet you
#   can still click on preview and save-as the page
# - Point this program to the resulting html file, it will generate a text
#   version of it.

from bs4 import BeautifulSoup
from html2text import config, HTML2Text

try:
    # This has been removed in more recent
    # versions of python-html2text. See commit
    # b361467894fb277563b4547ec9d4df49f5e0c6e3
    # (b361467 Remove support for Python ≤ 3.4)
    # in https://github.com/Alir3z4/html2text.git
    from html2text.utils import wrapwrite
except:
    pass

import os
import re
import sys

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

# A "[1]" in the html becomes "[[1]][6]" in text.
# As we already uses references at the end a [6] would
# be enough.
def fix_wordpress_references_link(string):
    open_square_bracket = re.escape('[')
    close_square_bracket = re.escape(']')
    whitespaces = '\s*'
    numbers = '\d+'

    # [ [ 1 ] ] [ 6 ]
    wordpress_link_regex = \
        \
          open_square_bracket + whitespaces \
        + open_square_bracket + whitespaces \
        + numbers + whitespaces \
        + close_square_bracket + whitespaces \
        + close_square_bracket + whitespaces \
        \
        + open_square_bracket + whitespaces \
        + numbers + whitespaces \
        + close_square_bracket + whitespaces \

    results = re.findall(wordpress_link_regex, string)

    part_to_remove = '^' \
        + open_square_bracket + whitespaces \
        + open_square_bracket + whitespaces \
        + numbers + whitespaces \
        + close_square_bracket + whitespaces \
        + close_square_bracket + whitespaces \

    for result in results:
        replacement = re.sub(part_to_remove, '', result)
        string = string.replace(result, replacement)

    return string

def fix_alignment(string):
    new_string = ""
    for line in string.split(os.linesep):
        new_line = re.sub('^  ', '', line)
        new_string += (new_line + os.linesep)

    return new_string

# Emacs breaks lists when doing a fill-paragraph to adjust a paragraph to the
# maximum width so we make sure that there is at least one blank line before
# the '*'
def fix_lists(string):
    new_string = ''
    nr_lineseps_before_star = 0
    for c in string:
        if c == '*' and nr_lineseps_before_star == 1:
            new_string += os.linesep

        if c == os.linesep:
            nr_lineseps_before_star += 1
        else:
            nr_lineseps_before_star = 0

        new_string += c
    return new_string

def convert(html_file_path):
    with open(html_file_path) as html_file:
        try:
            soup = BeautifulSoup(html_file, features="html5lib").article
        except:
            try:
                # For some reason the lxml parser isn't found with
                # python-beautifulsoup4 4.9.3-3.0 on Parabola. It's
                # probably better to use an html5 parser anyway as the
                # Replicant blog (now?) uses the html doctype and the
                # theme seems to include an html5.js file for the IE 9
                # browser.
                soup = BeautifulSoup(html_file, features="lxml").article
            except:
                print("Cannot find html5lib or lxml parsers")
                sys.exit(1)

    # Format the output to be compatible with mail conventions but make sure
    # that the links are not split between two lines
    config.INLINE_LINKS = False
    config.PROTECT_LINKS = True
    config.WRAP_LIST_ITEMS = True
    config.BODY_WIDTH = 70

    parser = HTML2Text()

    article = soup.find('div', class_='entry-content')
    text = parser.handle(article.decode())

    text = fix_wordpress_references_link(text)
    text = fix_alignment(text)
    text = fix_lists(text)

    return text

def main():
    if len(sys.argv) != 2:
        usage(sys.argv[0])

    html_file_path = sys.argv[1]

    text = convert(html_file_path)

    try:
        wrapwrite(text)
    except:
        sys.stdout.write(text)

if __name__ == '__main__':
    main()