ilia/nanobot
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

feat(telegram): markdown support

Browse Source
This commit is contained in:
Re-bin 2026-02-01 18:35:27 +00:00
parent dbb070e5fd
commit d888e51d1c
1 changed files with 77 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

80
nanobot/channels/telegram.py
View File

@ -1,7 +1,7 @@
"""Telegram channel implementation using python-telegram-bot."""
import asyncio
from typing import Any
import re
from loguru import logger
from telegram import Update
@ -13,6 +13,69 @@ from nanobot.channels.base import BaseChannel
from nanobot.config.schema import TelegramConfig
def _markdown_to_telegram_html(text: str) -> str:
"""
Convert markdown to Telegram-safe HTML.
"""
if not text:
return ""
# 1. Extract and protect code blocks (preserve content from other processing)
code_blocks: list[str] = []
def save_code_block(m: re.Match) -> str:
code_blocks.append(m.group(1))
return f"\x00CB{len(code_blocks) - 1}\x00"
text = re.sub(r'```[\w]*\n?([\s\S]*?)```', save_code_block, text)
# 2. Extract and protect inline code
inline_codes: list[str] = []
def save_inline_code(m: re.Match) -> str:
inline_codes.append(m.group(1))
return f"\x00IC{len(inline_codes) - 1}\x00"
text = re.sub(r'`([^`]+)`', save_inline_code, text)
# 3. Headers # Title -> just the title text
text = re.sub(r'^#{1,6}\s+(.+)$', r'\1', text, flags=re.MULTILINE)
# 4. Blockquotes > text -> just the text (before HTML escaping)
text = re.sub(r'^>\s*(.*)$', r'\1', text, flags=re.MULTILINE)
# 5. Escape HTML special characters
text = text.replace("&", "&amp;").replace("<", "&lt;").replace(">", "&gt;")
# 6. Links [text](url) - must be before bold/italic to handle nested cases
text = re.sub(r'\[([^\]]+)\]\(([^)]+)\)', r'<a href="\2">\1</a>', text)
# 7. Bold **text** or __text__
text = re.sub(r'\*\*(.+?)\*\*', r'<b>\1</b>', text)
text = re.sub(r'__(.+?)__', r'<b>\1</b>', text)
# 8. Italic _text_ (avoid matching inside words like some_var_name)
text = re.sub(r'(?<![a-zA-Z0-9])_([^_]+)_(?![a-zA-Z0-9])', r'<i>\1</i>', text)
# 9. Strikethrough ~~text~~
text = re.sub(r'~~(.+?)~~', r'<s>\1</s>', text)
# 10. Bullet lists - item -> • item
text = re.sub(r'^[-*]\s+', '• ', text, flags=re.MULTILINE)
# 11. Restore inline code with HTML tags
for i, code in enumerate(inline_codes):
# Escape HTML in code content
escaped = code.replace("&", "&amp;").replace("<", "&lt;").replace(">", "&gt;")
text = text.replace(f"\x00IC{i}\x00", f"<code>{escaped}</code>")
# 12. Restore code blocks with HTML tags
for i, code in enumerate(code_blocks):
# Escape HTML in code content
escaped = code.replace("&", "&amp;").replace("<", "&lt;").replace(">", "&gt;")
text = text.replace(f"\x00CB{i}\x00", f"<pre><code>{escaped}</code></pre>")
return text
class TelegramChannel(BaseChannel):
"""
Telegram channel using long polling.
@ -96,14 +159,25 @@ class TelegramChannel(BaseChannel):
try:
# chat_id should be the Telegram chat ID (integer)
chat_id = int(msg.chat_id)
# Convert markdown to Telegram HTML
html_content = _markdown_to_telegram_html(msg.content)
await self._app.bot.send_message(
chat_id=chat_id,
text=msg.content
text=html_content,
parse_mode="HTML"
)
except ValueError:
logger.error(f"Invalid chat_id: {msg.chat_id}")
except Exception as e:
logger.error(f"Error sending Telegram message: {e}")
# Fallback to plain text if HTML parsing fails
logger.warning(f"HTML parse failed, falling back to plain text: {e}")
try:
await self._app.bot.send_message(
chat_id=int(msg.chat_id),
text=msg.content
)
except Exception as e2:
logger.error(f"Error sending Telegram message: {e2}")
async def _on_start(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Handle /start command."""