xinyin025/LangBot
1
0
Fork 0
mirror of https://github.com/langbot-app/LangBot.git synced 2026-10-23 17:05:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(telegram): respect entity boundaries when parsing bot mentions

Browse Source
This commit is contained in:
fluo-rite
2026-10-13 02:29:07 -04:00
parent 688e7761e7
commit 607a94f324
3 changed files with 136 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/langbot/pkg/platform/sources/telegram.py
+22 -7
View File
@@ -149,23 +149,38 @@ class TelegramMessageConverter(abstract_platform_adapter.AbstractMessageConverte
async def target2yiri(message: telegram.Message, bot: telegram.Bot, bot_account_id: str):
message_components = []
def parse_message_text(text: str) -> list[platform_message.MessageComponent]:
def parse_message_text(
text: str, entities: dict[telegram.MessageEntity, str]
) -> list[platform_message.MessageComponent]:
msg_components = []
mention = f'@{bot_account_id}'
bot_mentions = [
entity
for entity, value in entities.items()
if (entity.type == telegram.MessageEntity.MENTION and value == mention)
or (entity.type == telegram.MessageEntity.BOT_COMMAND and value.endswith(mention))
]
if f'@{bot_account_id}' in text:
if bot_mentions:
# Telegram entity offsets use UTF-16 code units, not Python character indexes.
encoded = text.encode('utf-16-le')
for entity in sorted(bot_mentions, key=lambda entity: entity.offset, reverse=True):
end = (entity.offset + entity.length) * 2
start = end - len(mention.encode('utf-16-le'))
encoded = encoded[:start] + encoded[end:]
msg_components.append(platform_message.At(target=bot_account_id))
text = text.replace(f'@{bot_account_id}', '')
text = encoded.decode('utf-16-le')
msg_components.append(platform_message.Plain(text=text))
return msg_components
if message.text:
message_text = message.text
message_components.extend(parse_message_text(message_text))
message_components.extend(parse_message_text(message_text, message.parse_entities()))
if message.photo:
if message.caption:
message_components.extend(parse_message_text(message.caption))
message_components.extend(parse_message_text(message.caption, message.parse_caption_entities()))
file = await message.photo[-1].get_file()
@@ -192,7 +207,7 @@ class TelegramMessageConverter(abstract_platform_adapter.AbstractMessageConverte
if message.voice:
if message.caption:
message_components.extend(parse_message_text(message.caption))
message_components.extend(parse_message_text(message.caption, message.parse_caption_entities()))
file = await message.voice.get_file()
@@ -215,7 +230,7 @@ class TelegramMessageConverter(abstract_platform_adapter.AbstractMessageConverte
if message.document:
if message.caption:
message_components.extend(parse_message_text(message.caption))
message_components.extend(parse_message_text(message.caption, message.parse_caption_entities()))
file = await message.document.get_file()
file_name = message.document.file_name or 'document'