Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Python ai4sciencedocument-analysisdocxextract-datalayout-analysisocrparserpdfpdf-converterpdf-extractor-llmpdf-extractor-pretrainpdf-extractor-ragpdf-parserpptxpythonxlsx
"""Doclib 本机 HTTP 接口统一 Bearer 凭证校验。"""
from __future__ import annotations
import secrets
from pydantic import SecretStr
from starlette.requests import Request
from starlette.responses import JSONResponse
from starlette.types import ASGIApp, Receive, Scope, Send
from ..config import validate_doclib_token
from ..errors import MineruError, error_response
class DoclibAuthMiddleware:
"""在路由和业务依赖执行前校验凭证,覆盖状态、文档和关闭等全部 HTTP 接口。"""
def __init__(self, app: ASGIApp, *, token: SecretStr) -> None:
"""保存当前实例的凭证快照,配置更新须重启后生效。"""
self.app = app
self._token = validate_doclib_token(token.get_secret_value()).encode("ascii")
async def __call__(self, scope: Scope, receive: Receive, send: Send) -> None:
"""拒绝缺失、重复或不匹配的授权头,认证失败不消费请求正文。"""
if scope["type"] != "http":
await self.app(scope, receive, send)
return
request = Request(scope)
authorization = request.headers.getlist("authorization")
scheme, _, value = authorization[0].partition(" ") if len(authorization) == 1 else ("", "", "")
if scheme.lower() != "bearer" or not secrets.compare_digest(value.encode("utf-8"), self._token):
response = JSONResponse(
error_response(MineruError("invalid_doclib_token", "A valid Doclib Bearer token is required.")),
status_code=401,
headers={"WWW-Authenticate": "Bearer"},
)
await response(scope, receive, send)
return
await self.app(scope, receive, send)
__all__ = ["DoclibAuthMiddleware"]