ShadowRZ
/
nyx-bot
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update

This commit is contained in:
夜坂雅 2023-02-15 07:11:31 +08:00
parent b1e81e2c8d
commit 308396df74
2 changed files with 13 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
nyx_bot/utils.py
View File

@ -1,4 +1,5 @@
import math
import re
from datetime import datetime
from html.parser import HTMLParser
from io import StringIO
@ -215,6 +216,13 @@ async def parse_wordcloud_args(
return sender, days
RE_DATA = r"""(?i)\b((?:https?://|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’]))"""
def strip_urls(input: str) -> str:
return re.sub(RE_DATA, "", input)
def should_record_message_content(room_features, room_id: str) -> bool:
return room_features[room_id]["record_messages"]

10
nyx_bot/wordcloud.py
View File

@ -15,7 +15,7 @@ from wordcloud import WordCloud
import nyx_bot
from nyx_bot.chat_functions import send_text_to_room
from nyx_bot.storage import MatrixMessage
from nyx_bot.utils import strip_tags
from nyx_bot.utils import strip_tags, strip_urls
CUTWORDS_EXE = "nyx_bot-cutword"
FONT = os.path.join(nyx_bot.__path__[0], "wordcloud_font.ttf")
@ -136,7 +136,7 @@ async def send_wordcloud(
await client.room_send(room.room_id, message_type="m.room.message", content=content)
DROP_USERS = {"@telegram_1454289754:nichi.co", "@matterbridge:nichi.co"}
DROP_USERS = {"@telegram_1454289754:nichi.co", "@variation:matrix.org", "@bot:bgme.me"}
def gather_messages(
@ -176,14 +176,14 @@ def gather_messages(
)
if fwd_match is not None:
string = fwd_match.group(1)
print(strip_tags(string), file=stringio)
print(strip_urls(strip_tags(string)), file=stringio)
elif msg_item.body is not None:
# XXX: Special case for Arch Linux CN
if msg_item.sender == "@matterbridge:nichi.co":
data = re.sub(r"^\[.*\] ", "", msg_item.body)
print(data.strip(), file=stringio)
print(strip_tags(data.strip()), file=stringio)
else:
print(msg_item.body, file=stringio)
print(strip_urls(msg_item.body), file=stringio)
else:
continue