Tulir Asokan
84 lines
2.5 KiB
Python
84 lines
2.5 KiB
Python
# -*- coding: future_fstrings -*-
|
|
# mautrix-telegram - A Matrix-Telegram puppeting bridge
|
|
# Copyright (C) 2018 Tulir Asokan
|
|
#
|
|
# 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/>.
|
|
from html import escape
|
|
import struct
|
|
import re
|
|
|
|
|
|
# add_surrogates and remove_surrogates are unicode surrogate utility functions from Telethon.
|
|
# Licensed under the MIT license.
|
|
# https://github.com/LonamiWebs/Telethon/blob/master/telethon/extensions/markdown.py
|
|
def add_surrogates(text):
|
|
if text is None:
|
|
return None
|
|
return "".join("".join(chr(y) for y in struct.unpack("<HH", x.encode("utf-16-le")))
|
|
if (0x10000 <= ord(x) <= 0x10FFFF) else x for x in text)
|
|
|
|
|
|
def remove_surrogates(text):
|
|
if text is None:
|
|
return None
|
|
return text.encode("utf-16", "surrogatepass").decode("utf-16")
|
|
|
|
|
|
def trim_reply_fallback_text(text):
|
|
if not text.startswith("> ") or "\n" not in text:
|
|
return text
|
|
lines = text.split("\n")
|
|
while len(lines) > 0 and lines[0].startswith("> "):
|
|
lines.pop(0)
|
|
return "\n".join(lines)
|
|
|
|
|
|
HTML_REPLY_FALLBACK_REGEX = re.compile(r"^<blockquote data-mx-reply>[\s\S]+?</blockquote>")
|
|
|
|
|
|
def trim_reply_fallback_html(html):
|
|
return HTML_REPLY_FALLBACK_REGEX.sub("", html)
|
|
|
|
|
|
def unicode_to_html(text, html, ctrl, tag):
|
|
if ctrl not in text:
|
|
return html
|
|
if not html:
|
|
html = escape(text)
|
|
tag_start = f"<{tag}>"
|
|
tag_end = f"</{tag}>"
|
|
characters = html.split(ctrl)
|
|
html = ""
|
|
in_tag = False
|
|
for char in characters:
|
|
if not in_tag:
|
|
if len(char) > 1:
|
|
html += char[0:-1]
|
|
char = char[-1]
|
|
html += tag_start
|
|
in_tag = True
|
|
html += char
|
|
else:
|
|
if len(char) > 1:
|
|
html += tag_end
|
|
in_tag = False
|
|
html += char
|
|
if in_tag:
|
|
html += tag_end
|
|
return html
|
|
|
|
|
|
def html_to_unicode(text, ctrl):
|
|
return ctrl.join(text) + ctrl
|