# SPDX-FileCopyrightText: 2026 Matthew Fennell <matthew@fennell.dev>
#
# SPDX-License-Identifier: AGPL-3.0-or-later

from __future__ import absolute_import, division, print_function

import html2text

class filter(object):

    def __init__(self, *args, feed=None, item=None, **kwargs):
        if item.get('content'):
            item['content_plain'] = ''.join([self.parse(x.value)
                                             for x in item.get('content')])
        elif item.get('description') and item.get('description').strip():
            item['content_plain'] = self.parse(item.get('description'))

    @staticmethod
    def parse(html=None):
        if html is None:
            return None
        text_maker = html2text.HTML2Text()
        text_maker.inline_links = False
        text_maker.images_to_alt = True
        text_maker.unicode_snob = True
        text_maker.links_each_paragraph = True
        text_maker.protect_links = True
        text_maker.wrap_links = False
        return text_maker.handle(html)