Move formatting classes inside the Client sub-package
This commit is contained in:
parent
ae92c92c06
commit
c39bf3043d
@ -1,5 +1,22 @@
|
|||||||
|
# Pyrogram - Telegram MTProto API Client Library for Python
|
||||||
|
# Copyright (C) 2017-2018 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/>.
|
||||||
|
|
||||||
import re
|
import re
|
||||||
from struct import unpack
|
|
||||||
|
|
||||||
from pyrogram.api.types import (
|
from pyrogram.api.types import (
|
||||||
MessageEntityBold as Bold,
|
MessageEntityBold as Bold,
|
||||||
@ -10,6 +27,7 @@ from pyrogram.api.types import (
|
|||||||
MessageEntityMentionName as MentionInvalid,
|
MessageEntityMentionName as MentionInvalid,
|
||||||
InputMessageEntityMentionName as Mention,
|
InputMessageEntityMentionName as Mention,
|
||||||
)
|
)
|
||||||
|
from . import utils
|
||||||
|
|
||||||
|
|
||||||
class HTML:
|
class HTML:
|
||||||
@ -17,24 +35,12 @@ class HTML:
|
|||||||
HTML_RE = re.compile(r"<(\w+)(?: href=\"(.*)\")?>(.*)</\1>")
|
HTML_RE = re.compile(r"<(\w+)(?: href=\"(.*)\")?>(.*)</\1>")
|
||||||
MENTION_RE = re.compile(r"tg://user\?id=(\d+)")
|
MENTION_RE = re.compile(r"tg://user\?id=(\d+)")
|
||||||
|
|
||||||
@classmethod
|
|
||||||
def add_surrogates(cls, text):
|
|
||||||
return cls.SMP_RE.sub(
|
|
||||||
lambda match: # Split SMP in two surrogates
|
|
||||||
"".join(chr(i) for i in unpack("<HH", match.group().encode("utf-16le"))),
|
|
||||||
text
|
|
||||||
)
|
|
||||||
|
|
||||||
@staticmethod
|
|
||||||
def remove_surrogates(text):
|
|
||||||
return text.encode("utf-16", "surrogatepass").decode("utf-16")
|
|
||||||
|
|
||||||
def __init__(self, peers_by_id):
|
def __init__(self, peers_by_id):
|
||||||
self.peers_by_id = peers_by_id
|
self.peers_by_id = peers_by_id
|
||||||
|
|
||||||
def parse(self, text):
|
def parse(self, text):
|
||||||
entities = []
|
entities = []
|
||||||
text = self.add_surrogates(text)
|
text = utils.add_surrogates(text)
|
||||||
offset = 0
|
offset = 0
|
||||||
|
|
||||||
for match in self.HTML_RE.finditer(text):
|
for match in self.HTML_RE.finditer(text):
|
||||||
@ -71,6 +77,6 @@ class HTML:
|
|||||||
offset += len(style) * 2 + 5 + (len(url) + 8 if url else 0)
|
offset += len(style) * 2 + 5 + (len(url) + 8 if url else 0)
|
||||||
|
|
||||||
return dict(
|
return dict(
|
||||||
message=self.remove_surrogates(text),
|
message=utils.remove_surrogates(text),
|
||||||
entities=entities
|
entities=entities
|
||||||
)
|
)
|
@ -17,7 +17,6 @@
|
|||||||
# along with Pyrogram. If not, see <http://www.gnu.org/licenses/>.
|
# along with Pyrogram. If not, see <http://www.gnu.org/licenses/>.
|
||||||
|
|
||||||
import re
|
import re
|
||||||
from struct import unpack
|
|
||||||
|
|
||||||
from pyrogram.api.types import (
|
from pyrogram.api.types import (
|
||||||
MessageEntityBold as Bold,
|
MessageEntityBold as Bold,
|
||||||
@ -27,6 +26,7 @@ from pyrogram.api.types import (
|
|||||||
MessageEntityPre as Pre,
|
MessageEntityPre as Pre,
|
||||||
InputMessageEntityMentionName as Mention
|
InputMessageEntityMentionName as Mention
|
||||||
)
|
)
|
||||||
|
from . import utils
|
||||||
|
|
||||||
|
|
||||||
class Markdown:
|
class Markdown:
|
||||||
@ -36,9 +36,6 @@ class Markdown:
|
|||||||
"`": Code
|
"`": Code
|
||||||
}
|
}
|
||||||
|
|
||||||
# SMP = Supplementary Multilingual Plane: https://en.wikipedia.org/wiki/Plane_(Unicode)#Overview
|
|
||||||
SMP_RE = re.compile(r"[\U00010000-\U0010FFFF]")
|
|
||||||
|
|
||||||
# ``` python
|
# ``` python
|
||||||
# for i in range(10):
|
# for i in range(10):
|
||||||
# print(i)
|
# print(i)
|
||||||
@ -69,26 +66,12 @@ class Markdown:
|
|||||||
|
|
||||||
MARKDOWN_RE = re.compile("|".join([PRE_RE, MENTION_RE, URL_RE, INLINE_RE]))
|
MARKDOWN_RE = re.compile("|".join([PRE_RE, MENTION_RE, URL_RE, INLINE_RE]))
|
||||||
|
|
||||||
@classmethod
|
|
||||||
def add_surrogates(cls, text):
|
|
||||||
# Replace each SMP code point with a surrogate pair
|
|
||||||
return cls.SMP_RE.sub(
|
|
||||||
lambda match: # Split SMP in two surrogates
|
|
||||||
"".join(chr(i) for i in unpack("<HH", match.group().encode("utf-16le"))),
|
|
||||||
text
|
|
||||||
)
|
|
||||||
|
|
||||||
@staticmethod
|
|
||||||
def remove_surrogates(text):
|
|
||||||
# Replace each surrogate pair with a SMP code point
|
|
||||||
return text.encode("utf-16", "surrogatepass").decode("utf-16")
|
|
||||||
|
|
||||||
def __init__(self, peers_by_id):
|
def __init__(self, peers_by_id):
|
||||||
self.peers_by_id = peers_by_id
|
self.peers_by_id = peers_by_id
|
||||||
|
|
||||||
def parse(self, text):
|
def parse(self, text):
|
||||||
entities = []
|
entities = []
|
||||||
text = self.add_surrogates(text)
|
text = utils.add_surrogates(text)
|
||||||
offset = 0
|
offset = 0
|
||||||
|
|
||||||
for match in self.MARKDOWN_RE.finditer(text):
|
for match in self.MARKDOWN_RE.finditer(text):
|
||||||
@ -130,6 +113,6 @@ class Markdown:
|
|||||||
text = text.replace(pattern, replace)
|
text = text.replace(pattern, replace)
|
||||||
|
|
||||||
return dict(
|
return dict(
|
||||||
message=self.remove_surrogates(text),
|
message=utils.remove_surrogates(text),
|
||||||
entities=entities
|
entities=entities
|
||||||
)
|
)
|
37
pyrogram/client/style/utils.py
Normal file
37
pyrogram/client/style/utils.py
Normal file
@ -0,0 +1,37 @@
|
|||||||
|
# Pyrogram - Telegram MTProto API Client Library for Python
|
||||||
|
# Copyright (C) 2017-2018 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/>.
|
||||||
|
|
||||||
|
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")
|
Loading…
Reference in New Issue
Block a user