Kris
71fec609bb
新增了Telegram适配器的全套基础模块，包括： 1. 核心适配器入口与会话工具 2. 账号管理、认证与配置系统 3. 连接相关的轮询、Webhook、更新偏移管理 4. 话题路由、管理与缓存系统 5. 消息反抖动、超时配置与工具类 6. 响应式UI与命令交互系统 7. 反应表情与通知系统 8. 审批与安全审计模块 9. 健康检查与状态监控 10. 贴纸缓存与视觉工具 11. 流式响应与协作功能 12. 群组迁移与目标归一化处理
111 lines
3.3 KiB
Python
111 lines
3.3 KiB
Python
from __future__ import annotations
|
|
|
|
import re
|
|
from html import escape
|
|
|
|
_ESCAPE_CHARS = {"&": "&", "<": "<", ">": ">"}
|
|
|
|
_TAG_PATTERN = r"<(?!/?(?:b|strong|i|em|u|ins|s|strike|del|code|pre|a|tg-spoiler|tg-emoji)\b)[^>]*>"
|
|
_TAG_PLACEHOLDER_PATTERN = re.compile(_TAG_PATTERN)
|
|
|
|
_CODE_BLOCK_RE = re.compile(r"```(?:\w+)?\n.+?```", re.DOTALL)
|
|
_INLINE_CODE_RE = re.compile(r"`([^`\n]+?)`")
|
|
|
|
_PLACEHOLDER_PREFIX = "\x00MDPLACEHOLDER"
|
|
|
|
|
|
def markdown_to_html(text: str) -> str:
|
|
code_blocks: dict[str, str] = {}
|
|
text = _protect_code_spans(text, _CODE_BLOCK_RE, code_blocks)
|
|
text = _protect_code_spans(text, _INLINE_CODE_RE, code_blocks)
|
|
|
|
text = _convert_bold(text)
|
|
text = _convert_italic(text)
|
|
text = _convert_strikethrough(text)
|
|
text = _convert_underline(text)
|
|
text = _convert_links(text)
|
|
text = _convert_spoiler(text)
|
|
|
|
text = _restore_code_spans(text, code_blocks)
|
|
text = _sanitize_html(text)
|
|
return text
|
|
|
|
|
|
def strip_all_tags(text: str) -> str:
|
|
return re.sub(r"<[^>]+>", "", text)
|
|
|
|
|
|
def strip_html_tags(text: str) -> str:
|
|
return strip_all_tags(text)
|
|
|
|
|
|
def _protect_code_spans(text: str, pattern: re.Pattern, storage: dict[str, str]) -> str:
|
|
result = []
|
|
idx = 0
|
|
for m in pattern.finditer(text):
|
|
result.append(text[idx : m.start()])
|
|
placeholder = f"{_PLACEHOLDER_PREFIX}{len(storage)}"
|
|
storage[placeholder] = m.group(0)
|
|
result.append(placeholder)
|
|
idx = m.end()
|
|
result.append(text[idx:])
|
|
return "".join(result)
|
|
|
|
|
|
def _restore_code_spans(text: str, storage: dict[str, str]) -> str:
|
|
result = text
|
|
for placeholder, code_text in storage.items():
|
|
if placeholder.startswith(f"{_PLACEHOLDER_PREFIX}") and "```" in code_text:
|
|
inner = code_text[3:].rstrip("`").lstrip("\n")
|
|
lang_end = inner.find("\n")
|
|
inner = inner[lang_end + 1 :] if lang_end >= 0 else inner
|
|
safe = escape(inner, quote=False)
|
|
result = result.replace(placeholder, f"<pre>{safe}</pre>")
|
|
elif placeholder in result:
|
|
inner = code_text.strip("`")
|
|
safe = escape(inner, quote=False)
|
|
result = result.replace(placeholder, f"<code>{safe}</code>")
|
|
return result
|
|
|
|
|
|
def _convert_bold(text: str) -> str:
|
|
return re.sub(r"\*\*(.+?)\*\*", r"<b>\1</b>", text)
|
|
|
|
|
|
def _convert_italic(text: str) -> str:
|
|
text = re.sub(r"(?<!\*)\*([^*\n]+?)\*(?!\*)", r"<i>\1</i>", text)
|
|
text = re.sub(r"(?<!_)_([^_\n]+?)_(?!_)", r"<i>\1</i>", text)
|
|
return text
|
|
|
|
|
|
def _convert_strikethrough(text: str) -> str:
|
|
return re.sub(r"~~(.+?)~~", r"<s>\1</s>", text)
|
|
|
|
|
|
def _convert_underline(text: str) -> str:
|
|
return re.sub(r"__(\w.*?\w)__", r"<u>\1</u>", text)
|
|
|
|
|
|
def _convert_links(text: str) -> str:
|
|
return re.sub(r"\[(.+?)\]\((.+?)\)", r'<a href="\2">\1</a>', text)
|
|
|
|
|
|
def _convert_spoiler(text: str) -> str:
|
|
return re.sub(r"\|\|(.+?)\|\|", r"<tg-spoiler>\1</tg-spoiler>", text)
|
|
|
|
|
|
def _sanitize_html(text: str) -> str:
|
|
result = []
|
|
depth = 0
|
|
for ch in text:
|
|
if ch == "<":
|
|
depth += 1
|
|
elif ch == ">":
|
|
depth = max(0, depth - 1)
|
|
elif depth == 0:
|
|
if ch in _ESCAPE_CHARS:
|
|
result.append(_ESCAPE_CHARS[ch])
|
|
continue
|
|
result.append(ch)
|
|
return "".join(result)
|