forked from TelegramPlayground/PyroTGFork
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathmarkdown.py
More file actions
241 lines (208 loc) · 8.33 KB
/
Copy pathmarkdown.py
File metadata and controls
241 lines (208 loc) · 8.33 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
# Pyrogram - Telegram MTProto API Client Library for Python
# Copyright (C) 2017-present 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 html
import logging
import re
from typing import Optional
import pyrogram
from pyrogram.enums import MessageEntityType
from . import utils
from .html import HTML
BOLD_DELIM = "**"
ITALIC_DELIM = "__"
UNDERLINE_DELIM = "--"
STRIKE_DELIM = "~~"
SPOILER_DELIM = "||"
CODE_DELIM = "`"
PRE_DELIM = "```"
BLOCKQUOTE_DELIM = ">"
BLOCKQUOTE_EXPANDABLE_DELIM = "**>"
MARKDOWN_RE = re.compile(r"({d})|(!?)\[(.+?)\]\((.+?)\)".format(
d="|".join(
["".join(i) for i in [
[rf"\{j}" for j in i]
for i in [
PRE_DELIM,
CODE_DELIM,
STRIKE_DELIM,
UNDERLINE_DELIM,
ITALIC_DELIM,
BOLD_DELIM,
SPOILER_DELIM
]
]]
)))
OPENING_TAG = "<{}>"
CLOSING_TAG = "</{}>"
URL_MARKUP = '<a href="{}">{}</a>'
EMOJI_MARKUP = '<emoji id={}>{}</emoji>'
FIXED_WIDTH_DELIMS = [CODE_DELIM, PRE_DELIM]
class Markdown:
def __init__(self, client: Optional["pyrogram.Client"]):
self.html = HTML(client)
def _parse_blockquotes(self, text: str):
text = html.unescape(text)
lines = text.split('\n')
result = []
in_blockquote = False
is_expandable_blockquote = False
current_blockquote = []
for line in lines:
if line.startswith(BLOCKQUOTE_DELIM):
in_blockquote = True
current_blockquote.append(line[1:].strip())
elif line.startswith(BLOCKQUOTE_EXPANDABLE_DELIM):
in_blockquote = True
is_expandable_blockquote = True
current_blockquote.append(line[3:].strip())
else:
if in_blockquote:
in_blockquote = False
result.append(
(f"<blockquote expandable>" if is_expandable_blockquote else OPENING_TAG.format("blockquote")) +
'\n'.join(current_blockquote) +
CLOSING_TAG.format("blockquote")
)
current_blockquote = []
result.append(line)
if in_blockquote:
result.append(
(f"<blockquote expandable>" if is_expandable_blockquote else OPENING_TAG.format("blockquote")) +
'\n'.join(current_blockquote) +
CLOSING_TAG.format("blockquote")
)
return '\n'.join(result)
async def parse(self, text: str, strict: bool = False):
if strict:
text = html.escape(text)
text = self._parse_blockquotes(text)
text = self._parse_blockquotes(text)
delims = set()
is_fixed_width = False
for i, match in enumerate(re.finditer(MARKDOWN_RE, text)):
start, _ = match.span()
delim, is_emoji, text_url, url = match.groups()
full = match.group(0)
if delim in FIXED_WIDTH_DELIMS:
is_fixed_width = not is_fixed_width
if is_fixed_width and delim not in FIXED_WIDTH_DELIMS:
continue
if not is_emoji and text_url:
text = utils.replace_once(text, full, URL_MARKUP.format(url, text_url), start)
continue
if is_emoji:
emoji = text_url
emoji_id = url.lstrip("tg://emoji?id=")
text = utils.replace_once(text, full, EMOJI_MARKUP.format(emoji_id, emoji), start)
continue
if delim == BOLD_DELIM:
tag = "b"
elif delim == ITALIC_DELIM:
tag = "i"
elif delim == UNDERLINE_DELIM:
tag = "u"
elif delim == STRIKE_DELIM:
tag = "s"
elif delim == CODE_DELIM:
tag = "code"
elif delim == PRE_DELIM:
tag = "pre"
elif delim == SPOILER_DELIM:
tag = "spoiler"
else:
continue
if delim not in delims:
delims.add(delim)
tag = OPENING_TAG.format(tag)
else:
delims.remove(delim)
tag = CLOSING_TAG.format(tag)
if delim == PRE_DELIM and delim in delims:
delim_and_language = text[text.find(PRE_DELIM):].split("\n")[0]
language = delim_and_language[len(PRE_DELIM):]
text = utils.replace_once(text, delim_and_language, f'<pre language="{language}">', start)
continue
text = utils.replace_once(text, delim, tag, start)
return await self.html.parse(text)
@staticmethod
def unparse(text: str, entities: list):
text = utils.add_surrogates(text)
entities_offsets = []
for entity in entities:
entity_type = entity.type
start = entity.offset
end = start + entity.length
if entity_type == MessageEntityType.BOLD:
start_tag = end_tag = BOLD_DELIM
elif entity_type == MessageEntityType.ITALIC:
start_tag = end_tag = ITALIC_DELIM
elif entity_type == MessageEntityType.UNDERLINE:
start_tag = end_tag = UNDERLINE_DELIM
elif entity_type == MessageEntityType.STRIKETHROUGH:
start_tag = end_tag = STRIKE_DELIM
elif entity_type == MessageEntityType.CODE:
start_tag = end_tag = CODE_DELIM
elif entity_type == MessageEntityType.PRE:
language = getattr(entity, "language", "") or ""
start_tag = f"{PRE_DELIM}{language}\n"
end_tag = f"\n{PRE_DELIM}"
elif entity_type == MessageEntityType.BLOCKQUOTE:
start_tag = BLOCKQUOTE_DELIM + " "
end_tag = ""
blockquote_text = text[start:end]
lines = blockquote_text.split("\n")
last_length = 0
for line in lines:
if len(line) == 0 and last_length == end:
continue
start_offset = start+last_length
last_length = last_length+len(line)
end_offset = start_offset+last_length
entities_offsets.append((start_tag, start_offset,))
entities_offsets.append((end_tag, end_offset,))
last_length = last_length+1
continue
elif entity_type == MessageEntityType.SPOILER:
start_tag = end_tag = SPOILER_DELIM
elif entity_type == MessageEntityType.TEXT_LINK:
url = entity.url
start_tag = "["
end_tag = f"]({url})"
elif entity_type == MessageEntityType.TEXT_MENTION:
user = entity.user
start_tag = "["
end_tag = f"](tg://user?id={user.id})"
elif entity_type == MessageEntityType.CUSTOM_EMOJI:
emoji_id = entity.custom_emoji_id
start_tag = ""
else:
continue
entities_offsets.append((start_tag, start,))
entities_offsets.append((end_tag, end,))
entities_offsets = map(
lambda x: x[1],
sorted(
enumerate(entities_offsets),
key=lambda x: (x[1][1], x[0]),
reverse=True
)
)
for entity, offset in entities_offsets:
text = text[:offset] + entity + text[offset:]
return utils.remove_surrogates(text)