MTPyroger/pyrogram/client/style/html.py

129 lines
4.7 KiB
Python
Raw Normal View History

# Pyrogram - Telegram MTProto API Client Library for Python
2019-01-01 11:36:16 +00:00
# Copyright (C) 2017-2019 Dan Tès <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/>.
2018-01-21 23:26:43 +00:00
import re
from collections import OrderedDict
2018-01-21 23:26:43 +00:00
import pyrogram
2018-01-21 23:26:43 +00:00
from pyrogram.api.types import (
MessageEntityBold as Bold,
MessageEntityItalic as Italic,
MessageEntityCode as Code,
MessageEntityTextUrl as Url,
MessageEntityPre as Pre,
2018-01-23 13:43:12 +00:00
MessageEntityMentionName as MentionInvalid,
InputMessageEntityMentionName as Mention,
2018-01-21 23:26:43 +00:00
)
from pyrogram.errors import PeerIdInvalid
from . import utils
2019-02-26 16:24:00 +00:00
from ..session_storage import SessionStorage
2018-01-21 23:26:43 +00:00
class HTML:
HTML_RE = re.compile(r"<(\w+)(?: href=([\"'])([^<]+)\2)?>([^>]+)</\1>")
2018-01-23 13:43:12 +00:00
MENTION_RE = re.compile(r"tg://user\?id=(\d+)")
2018-01-21 23:26:43 +00:00
def __init__(self, session_storage: SessionStorage, client: "pyrogram.BaseClient" = None):
self.client = client
2019-02-26 16:24:00 +00:00
self.session_storage = session_storage
2018-01-21 23:26:43 +00:00
def parse(self, message: str):
2018-01-21 23:26:43 +00:00
entities = []
message = utils.add_surrogates(str(message or ""))
2018-01-21 23:26:43 +00:00
offset = 0
for match in self.HTML_RE.finditer(message):
2018-01-21 23:26:43 +00:00
start = match.start() - offset
style, url, body = match.group(1, 3, 4)
2018-01-23 13:43:12 +00:00
if url:
mention = self.MENTION_RE.match(url)
if mention:
user_id = int(mention.group(1))
2019-02-26 16:24:00 +00:00
try:
input_user = self.session_storage.get_peer_by_id(user_id)
except KeyError:
input_user = None
2018-01-21 23:26:43 +00:00
2018-01-23 13:43:12 +00:00
entity = (
Mention(offset=start, length=len(body), user_id=input_user)
if input_user else MentionInvalid(offset=start, length=len(body), user_id=user_id)
2018-01-23 13:43:12 +00:00
)
else:
entity = Url(offset=start, length=len(body), url=url)
2018-01-21 23:26:43 +00:00
else:
2018-01-23 13:43:12 +00:00
if style == "b" or style == "strong":
entity = Bold(offset=start, length=len(body))
2018-01-23 13:43:12 +00:00
elif style == "i" or style == "em":
entity = Italic(offset=start, length=len(body))
2018-01-23 13:43:12 +00:00
elif style == "code":
entity = Code(offset=start, length=len(body))
2018-01-23 13:43:12 +00:00
elif style == "pre":
entity = Pre(offset=start, length=len(body), language="")
2018-01-23 13:43:12 +00:00
else:
continue
2018-01-21 23:26:43 +00:00
entities.append(entity)
message = message.replace(match.group(), body)
2018-01-23 13:43:12 +00:00
offset += len(style) * 2 + 5 + (len(url) + 8 if url else 0)
2018-01-21 23:26:43 +00:00
# TODO: OrderedDict to be removed in Python3.6
return OrderedDict([
("message", utils.remove_surrogates(message)),
("entities", entities)
])
2018-05-11 11:37:49 +00:00
def unparse(self, message: str, entities: list):
message = utils.add_surrogates(message).strip()
offset = 0
for entity in entities:
start = entity.offset + offset
type = entity.type
url = entity.url
user = entity.user
sub = message[start: start + entity.length]
if type == "bold":
style = "b"
elif type == "italic":
style = "i"
elif type == "code":
style = "code"
elif type == "pre":
style = "pre"
elif type == "text_link":
offset += 15 + len(url)
message = message[:start] + message[start:].replace(
sub, "<a href=\"{}\">{}</a>".format(url, sub), 1)
continue
elif type == "text_mention":
offset += 28 + len(str(user.id))
message = message[:start] + message[start:].replace(
sub, "<a href=\"tg://user?id={}\">{}</a>".format(user.id, sub), 1)
continue
else:
continue
offset += len(style) * 2 + 5
message = message[:start] + message[start:].replace(
sub, "<{0}>{1}</{0}>".format(style, sub), 1)
return utils.remove_surrogates(message)