cfc/cfc-langgraph/app/api/report_parse.py

from fastapi import APIRouter, HTTPException
from pydantic import BaseModel
from typing import Optional, Any
from app.agents.report_parse_agent import ReportParseAgent
import logging
import os
import json
import tempfile

logger = logging.getLogger(__name__)
router = APIRouter(prefix="/api/v1", tags=["report_parse"])
_agent = None


def get_agent():
    global _agent
    if _agent is None:
        _agent = ReportParseAgent()
    return _agent


class ParseRequest(BaseModel):
    file_path: str
    family_id: Optional[int] = None
    user_id: Optional[int] = None


class ParseResponse(BaseModel):
    code: int = 200
    message: str = "ok"
    data: dict = {}


async def resolve_local_path(file_path: str) -> str:
    """将 file_path 解析为本地文件路径。
    支持：本地路径、/uploads 共享卷路径、http(s) 远程 OSS URL（下载到临时文件）。"""
    if file_path.startswith(('http://', 'https://')):
        import httpx
        logger.info("report_parse: 远程文件 %s，下载到临时文件", file_path)
        async with httpx.AsyncClient(timeout=120, follow_redirects=True) as client:
            resp = await client.get(file_path)
            resp.raise_for_status()
        ext = os.path.splitext(file_path.split('?')[0])[1] or '.pdf'
        fd, tmp = tempfile.mkstemp(suffix=ext)
        with os.fdopen(fd, 'wb') as f:
            f.write(resp.content)
        logger.info("report_parse: 下载完成 -> %s", tmp)
        return tmp
    return file_path


@router.post("/report/parse", response_model=ParseResponse)
async def parse_report(req: ParseRequest):
    local = await resolve_local_path(req.file_path)
    if not os.path.exists(local):
        raise HTTPException(status_code=400, detail=f"文件不存在: {req.file_path}")

    logger.info("report_parse: file_path=%s family_id=%s user_id=%s", local, req.family_id, req.user_id)
    agent = get_agent()
    try:
        result = await agent.parse(local)
        return ParseResponse(data=result)
    except Exception as e:
        logger.error("报告解析失败: %s", e, exc_info=True)
        return ParseResponse(code=500, message=f"解析失败: {str(e)}", data={})


class GenericParseRequest(BaseModel):
    file_path: str
    extra_context: Optional[dict] = None


class GenericParseResponse(BaseModel):
    code: int = 200
    message: str = "ok"
    data: dict = {}


@router.post("/report/parse-generic", response_model=GenericParseResponse)
async def parse_report_generic(req: GenericParseRequest):
    """通用报告 LLM 兜底解析。

    适用于指纹检测未匹配的未知类型报告。
    直接交给 LLM 提取结构化数据，不经过算法预解析。
    """
    if not os.path.exists(req.file_path):
        raise HTTPException(status_code=400, detail=f"文件不存在: {req.file_path}")

    logger.info("report_parse_generic: file_path=%s", req.file_path)
    agent = get_agent()
    try:
        result = await agent.parse_generic(req.file_path, req.extra_context)
        return GenericParseResponse(data=result)
    except Exception as e:
        logger.error("通用报告解析失败: %s", e, exc_info=True)
        return GenericParseResponse(code=500, message=f"解析失败: {str(e)}", data={})