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

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
    indicators: Optional[list[str]] = None


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


@router.post("/report/parse", response_model=ParseResponse)
async def parse_report(req: ParseRequest):
    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: file_path=%s family_id=%s user_id=%s",
                req.file_path, req.family_id, req.user_id)
    agent = get_agent()
    try:
        result = await agent.parse(req.file_path, req.indicators)
        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={})


class TypedParseRequest(BaseModel):
    file_path: str
    report_type: str = "auto"
    extra_context: Optional[dict] = None
    indicators: Optional[list[str]] = None


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


@router.post("/report/parse-typed", response_model=TypedParseResponse)
async def parse_report_typed(req: TypedParseRequest):
    """按报告类型解析。

    支持的报告类型:
    - auto: 自动检测（默认）
    - brain_status: 脑状态测量报告
    - cognitive_aptitude: 先天智力潜能/皮纹学测评报告
    - scanned_image: 扫描图片 PDF（无文字层，需多模态 LLM）
    - generic: 通用 LLM 解析
    - gut_flora: 肠道菌群报告（算法解析 + LLM 兜底）
    """
    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_typed: file_path=%s type=%s",
                req.file_path, req.report_type)
    agent = get_agent()
    try:
        result = await agent.parse_by_type(req.file_path, req.report_type, req.extra_context, req.indicators)
        return TypedParseResponse(data=result)
    except Exception as e:
        logger.error("类型报告解析失败: %s", e, exc_info=True)
        return TypedParseResponse(code=500, message=f"解析失败: {str(e)}", data={})


class TypedParseRequest2(BaseModel):
    file_path: str


@router.post("/report/detect-type", response_model=TypedParseResponse)
async def detect_report_type(req: TypedParseRequest2):
    """检测报告类型，返回检测结果（不执行解析）。"""
    if not os.path.exists(req.file_path):
        raise HTTPException(status_code=400, detail=f"文件不存在: {req.file_path}")

    agent = get_agent()
    try:
        detected = agent._detect_report_type(req.file_path)
        return TypedParseResponse(data={"detectedType": detected})
    except Exception as e:
        logger.error("报告类型检测失败: %s", e, exc_info=True)
        return TypedParseResponse(code=500, message=f"检测失败: {str(e)}", data={})