MTPyroger/pyrogram/parser/utils.py
Dan 538f1e3972 Deep rewrite: preparing for v1.0
- Pyrogram core is now fully asynchronous
- Ditched Python 3.5, welcome 3.6 as minimum version.
- Moved all types to pyrogram.types
- Turned the Filters class into a module (filters)
- Moved all filters to pyrogram.filters
- Moved all handlers to pyrogram.handlers
- Moved all emoji to pyrogram.emoji
- Renamed pyrogram.api to pyrogram.raw
- Clock is now synced with server's time
- Telegram schema updated to Layer 117
- Greatly improved the TL compiler (proper type-constructor hierarchy)
- Added "do not edit" warning in generated files
- Crypto parts are executed in a thread pool to avoid blocking the event loop
- idle() is now a separate function (it doesn't deal with Client instances)
- Async storage, async filters and async progress callback (optional, can be sync too)
- Added getpass back, for hidden password inputs
2020-08-22 08:05:05 +02:00

42 lines
1.5 KiB
Python

# Pyrogram - Telegram MTProto API Client Library for Python
# Copyright (C) 2017-2020 Dan <https://github.com/delivrance>
#
# This file is part of Pyrogram.
#
# Pyrogram is free software: you can redistribute it and/or modify
# it under the terms of the GNU Lesser General Public License as published
# by the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# Pyrogram 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 Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public License
# along with Pyrogram. If not, see <http://www.gnu.org/licenses/>.
import re
from struct import unpack
# SMP = Supplementary Multilingual Plane: https://en.wikipedia.org/wiki/Plane_(Unicode)#Overview
SMP_RE = re.compile(r"[\U00010000-\U0010FFFF]")
def add_surrogates(text):
# Replace each SMP code point with a surrogate pair
return SMP_RE.sub(
lambda match: # Split SMP in two surrogates
"".join(chr(i) for i in unpack("<HH", match.group().encode("utf-16le"))),
text
)
def remove_surrogates(text):
# Replace each surrogate pair with a SMP code point
return text.encode("utf-16", "surrogatepass").decode("utf-16")
def replace_once(source: str, old: str, new: str, start: int):
return source[:start] + source[start:].replace(old, new, 1)