1151 lines
43 KiB
Python
1151 lines
43 KiB
Python
"""PPT 生成模块 Blueprint 路由。"""
|
||
import os
|
||
import uuid
|
||
import json
|
||
import logging
|
||
from datetime import datetime
|
||
from flask import Blueprint, request, jsonify, send_file
|
||
from insurance.middleware.auth_middleware import jwt_required
|
||
from insurance.utils.response import success, error, ErrorCode
|
||
|
||
logger = logging.getLogger(__name__)
|
||
|
||
ppt_bp = Blueprint("ppt", __name__)
|
||
|
||
|
||
def _get_session(session_id: str, user_id: str):
|
||
"""获取会话记录。"""
|
||
from insurance.db.compat import db
|
||
from insurance.models.ppt_session import PptSession
|
||
session = PptSession.query.filter_by(id=session_id).first()
|
||
if not session:
|
||
return None
|
||
if session.user_id != user_id:
|
||
return None
|
||
return session
|
||
|
||
|
||
def _save_session(session):
|
||
"""保存会话记录。"""
|
||
from insurance.db.compat import db
|
||
db.session.add(session)
|
||
db.session.commit()
|
||
|
||
|
||
# ─── 健康检查 ─────────────────────────────────────────────
|
||
|
||
@ppt_bp.route("/health", methods=["GET"])
|
||
def health():
|
||
return success({"status": "ok"})
|
||
|
||
|
||
# ─── 渲染选项 ─────────────────────────────────────────────
|
||
|
||
@ppt_bp.route("/render-options", methods=["GET"])
|
||
def render_options():
|
||
"""获取可用的公司和模板风格列表。"""
|
||
from insurance.models.ppt_config import PptCompany, PptProduct, PptTemplate
|
||
companies = PptCompany.query.filter_by(status=1).order_by(
|
||
PptCompany.sort_order.asc(), PptCompany.id.asc()
|
||
).all()
|
||
products = PptProduct.query.filter_by(status=1).order_by(
|
||
PptProduct.sort_order.asc(), PptProduct.id.asc()
|
||
).all()
|
||
templates = PptTemplate.query.filter_by(status=1).order_by(
|
||
PptTemplate.plan_type.asc(), PptTemplate.id.asc()
|
||
).all()
|
||
return success({
|
||
"companies": [c.to_dict() for c in companies],
|
||
"products": [p.to_dict() for p in products],
|
||
"templates": [t.to_dict() for t in templates],
|
||
})
|
||
|
||
|
||
# ─── 上传 PDF ─────────────────────────────────────────────
|
||
|
||
@ppt_bp.route("/upload", methods=["POST"])
|
||
@jwt_required
|
||
def upload_pdfs():
|
||
"""上传 PDF 文件并创建会话。
|
||
|
||
支持 1～10 份计划书，五组并行数组(files/types/companies/products/passwords)长度必须一致。
|
||
采用"先校验后写入"的原子上传策略：任一文件校验失败时不创建会话。
|
||
"""
|
||
from flask import jsonify as _jsonify
|
||
MAX_UPLOAD_FILES = 10
|
||
VALID_TYPES = {"savings", "ci", "iul"}
|
||
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
files = request.files.getlist("files")
|
||
types = request.form.getlist("types")
|
||
companies = request.form.getlist("companies")
|
||
products = request.form.getlist("products")
|
||
passwords = request.form.getlist("passwords")
|
||
|
||
# ── 基础参数校验 ──
|
||
if not files:
|
||
return error(ErrorCode.PARAM_ERROR, "请至少上传 1 份计划书")
|
||
if len(files) > MAX_UPLOAD_FILES:
|
||
return error(ErrorCode.PARAM_ERROR, f"最多支持上传 {MAX_UPLOAD_FILES} 份计划书")
|
||
for name, arr in [("types", types), ("companies", companies),
|
||
("products", products), ("passwords", passwords)]:
|
||
if len(arr) != len(files):
|
||
return error(ErrorCode.PARAM_ERROR, f"{name} 数组长度与 files 不一致")
|
||
for i, t in enumerate(types):
|
||
if t not in VALID_TYPES:
|
||
return error(ErrorCode.PARAM_ERROR, f"第 {i + 1} 份文件的险种 '{t}' 不合法")
|
||
|
||
# ── 第一阶段：校验全部文件，不写入磁盘 ──
|
||
from insurance.utils.security import prepare_pdf_upload
|
||
from insurance.models.ppt_config import PptCompany, PptProduct
|
||
|
||
validated = [] # (f, pdf_bytes, file_record) 通过校验的文件
|
||
file_errors = [] # 结构化错误列表
|
||
|
||
for i, f in enumerate(files):
|
||
fname = f.filename or f"文件{i + 1}"
|
||
if not f.filename or not f.filename.lower().endswith(".pdf"):
|
||
file_errors.append({"index": i, "fileName": fname, "field": "file", "message": "仅支持 PDF 格式"})
|
||
continue
|
||
|
||
plan_type = types[i]
|
||
company_id = companies[i] if i < len(companies) else ""
|
||
product_id = products[i] if i < len(products) else ""
|
||
password = passwords[i] if i < len(passwords) else ""
|
||
|
||
# 保司校验
|
||
company = PptCompany.query.filter_by(id=company_id, status=1).first() if company_id else None
|
||
if company_id and not company:
|
||
file_errors.append({"index": i, "fileName": fname, "field": "company", "message": "所选保司不存在或已停用"})
|
||
continue
|
||
|
||
# 产品校验
|
||
product = PptProduct.query.filter_by(id=product_id, status=1).first() if product_id else None
|
||
if product_id and (
|
||
not product
|
||
or product.plan_type != plan_type
|
||
or (company_id and product.company_id != company_id)
|
||
):
|
||
file_errors.append({"index": i, "fileName": fname, "field": "product", "message": "所选产品与险种或保司不匹配"})
|
||
continue
|
||
if product and not company_id:
|
||
company_id = product.company_id
|
||
|
||
# PDF 安全校验
|
||
is_valid, err_msg, pdf_bytes = prepare_pdf_upload(f, password)
|
||
if not is_valid:
|
||
file_errors.append({"index": i, "fileName": fname, "field": "password", "message": err_msg or "PDF 校验失败"})
|
||
continue
|
||
|
||
validated.append((f, pdf_bytes, {
|
||
"name": fname,
|
||
"type": plan_type,
|
||
"companyId": company_id,
|
||
"productId": product_id,
|
||
}))
|
||
|
||
# 任一文件失败则整体拒绝
|
||
if file_errors:
|
||
return _jsonify({
|
||
"code": ErrorCode.FILE_FORMAT_ERROR,
|
||
"message": "部分计划书校验失败",
|
||
"data": {"fileErrors": file_errors},
|
||
}), 400
|
||
|
||
if not validated:
|
||
return error(ErrorCode.FILE_FORMAT_ERROR, "无有效 PDF 文件")
|
||
|
||
# ── 第二阶段：全部通过，统一写入磁盘并创建会话 ──
|
||
from insurance.config import get_storage_root
|
||
upload_dir = os.path.join(get_storage_root(), "uploads", "ppt", user_id)
|
||
os.makedirs(upload_dir, exist_ok=True)
|
||
|
||
file_records = []
|
||
for f, pdf_bytes, meta in validated:
|
||
filename = f"{uuid.uuid4().hex[:8]}_{meta['name']}"
|
||
filepath = os.path.join(upload_dir, filename)
|
||
with open(filepath, "wb") as output:
|
||
output.write(pdf_bytes)
|
||
file_records.append({
|
||
"path": filepath,
|
||
"name": meta["name"],
|
||
"type": meta["type"],
|
||
"companyId": meta["companyId"],
|
||
"productId": meta["productId"],
|
||
})
|
||
|
||
session_id = uuid.uuid4().hex
|
||
from insurance.models.ppt_session import PptSession
|
||
session = PptSession(
|
||
id=session_id,
|
||
user_id=user_id,
|
||
status="created",
|
||
files_json=json.dumps(file_records, ensure_ascii=False),
|
||
)
|
||
_save_session(session)
|
||
|
||
return success({
|
||
"sessionId": session_id,
|
||
"files": [f["name"] for f in file_records],
|
||
})
|
||
|
||
|
||
# ─── 解析 PDF ─────────────────────────────────────────────
|
||
|
||
@ppt_bp.route("/parse/<session_id>", methods=["POST"])
|
||
@jwt_required
|
||
def parse_session(session_id):
|
||
"""触发 AI 解析 PDF（异步任务）。"""
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
session = _get_session(session_id, user_id)
|
||
if not session:
|
||
return error(ErrorCode.NOT_FOUND, "会话不存在")
|
||
|
||
files = json.loads(session.files_json) if session.files_json else []
|
||
if not files:
|
||
return error(ErrorCode.PARAM_ERROR, "没有可解析的 PDF 文件")
|
||
|
||
if session.status == "parsing":
|
||
_reconcile_parse_task(session)
|
||
if session.status == "parsing":
|
||
return success(_build_parse_status(session), "解析任务正在进行")
|
||
|
||
# 创建异步任务
|
||
from insurance.generation import task_service
|
||
session.status = "parsing"
|
||
session.parse_progress = 0
|
||
session.parse_message = "解析任务已提交"
|
||
session.parse_error = None
|
||
session.parse_started_at = datetime.now()
|
||
session.parse_finished_at = None
|
||
session.extractions_json = json.dumps([], ensure_ascii=False)
|
||
_save_session(session)
|
||
|
||
result = task_service.create_task(
|
||
user_id=user_id,
|
||
artifact_type="ppt",
|
||
operation="parse",
|
||
workspace_id=session_id,
|
||
title=session.title or f"PPT {session_id[:8]}",
|
||
input_snapshot={"files": files},
|
||
input_revision=session.draft_revision or 1,
|
||
)
|
||
|
||
if result.get("code") != 0:
|
||
message = result.get("message", "解析任务提交失败")
|
||
session.status = "error"
|
||
session.parse_progress = 100
|
||
session.parse_message = "处理失败"
|
||
session.parse_error = message
|
||
session.parse_finished_at = datetime.now()
|
||
_save_session(session)
|
||
return error(ErrorCode.SERVER_ERROR, message, status=503)
|
||
|
||
session.latest_task_id = result["data"]["id"]
|
||
_save_session(session)
|
||
message = "解析任务已启动"
|
||
|
||
return success({
|
||
"sessionId": session_id,
|
||
"status": session.status,
|
||
"progress": session.parse_progress or 0,
|
||
"message": message,
|
||
"taskId": result.get("data", {}).get("id") if result.get("code") == 0 else None,
|
||
})
|
||
|
||
|
||
@ppt_bp.route("/parse/<session_id>/status", methods=["GET"])
|
||
@jwt_required
|
||
def parse_status(session_id):
|
||
"""获取 AI 解析进度。"""
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
session = _get_session(session_id, user_id)
|
||
if not session:
|
||
return error(ErrorCode.NOT_FOUND, "会话不存在")
|
||
_reconcile_parse_task(session)
|
||
return success(_build_parse_status(session))
|
||
|
||
|
||
def _reconcile_parse_task(session):
|
||
"""修正任务表与 PPT 会话不一致的终态。"""
|
||
if session.status != "parsing" or not session.latest_task_id:
|
||
return
|
||
|
||
from insurance.models.generation_task import GenerationTask
|
||
|
||
task = GenerationTask.query.get(session.latest_task_id)
|
||
if not task or task.status not in ("failed", "cancelled"):
|
||
return
|
||
|
||
session.status = "error"
|
||
session.parse_progress = 100
|
||
session.parse_message = "处理失败"
|
||
session.parse_error = task.error_message or (
|
||
"任务已取消" if task.status == "cancelled" else "解析任务失败，请重新提交"
|
||
)
|
||
session.parse_finished_at = task.finished_at or datetime.now()
|
||
_save_session(session)
|
||
|
||
|
||
def _build_parse_status(session):
|
||
extractions = json.loads(session.extractions_json) if session.extractions_json else []
|
||
return {
|
||
"sessionId": session.id,
|
||
"status": session.status,
|
||
"progress": session.parse_progress or 0,
|
||
"message": session.parse_message or "",
|
||
"error": session.parse_error,
|
||
"extractions": [{
|
||
"pdfName": e.get("pdfName", ""),
|
||
"planType": e.get("planType", ""),
|
||
"status": e.get("status", ""),
|
||
"productName": e.get("productName", ""),
|
||
"yearCount": e.get("yearCount", 0),
|
||
"error": e.get("error"),
|
||
} for e in extractions],
|
||
}
|
||
|
||
|
||
def _reassess_extraction(ext: dict):
|
||
from insurance.ppt.extraction import assess_extraction_payload, infer_plan_type
|
||
|
||
data = ext.get("data")
|
||
if not data:
|
||
return
|
||
|
||
plan_type = infer_plan_type(data)
|
||
status, extraction_error = assess_extraction_payload(data, plan_type)
|
||
data["product_type"] = plan_type
|
||
ext["planType"] = plan_type
|
||
ext["status"] = status
|
||
ext["productName"] = (data.get("product_name") or "").strip() or "unknown"
|
||
ext["error"] = extraction_error or None
|
||
rows = data.get("benefit_illustration") or data.get("benefitRows") or []
|
||
ext["yearCount"] = len(rows) if isinstance(rows, list) else 0
|
||
|
||
|
||
# ─── 获取会话状态 ─────────────────────────────────────────
|
||
|
||
@ppt_bp.route("/session/<session_id>", methods=["GET"])
|
||
@jwt_required
|
||
def get_session(session_id):
|
||
"""获取完整会话状态。"""
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
session = _get_session(session_id, user_id)
|
||
if not session:
|
||
return error(ErrorCode.NOT_FOUND, "会话不存在")
|
||
|
||
return success(session.to_dict())
|
||
|
||
|
||
# ─── 对话 ─────────────────────────────────────────────────
|
||
|
||
@ppt_bp.route("/chat/<session_id>", methods=["POST"])
|
||
@jwt_required
|
||
def chat(session_id):
|
||
"""AI 保险顾问对话。"""
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
session = _get_session(session_id, user_id)
|
||
if not session:
|
||
return error(ErrorCode.NOT_FOUND, "会话不存在")
|
||
|
||
data = request.get_json(silent=True) or {}
|
||
message = data.get("message", "").strip()
|
||
if not message:
|
||
return error(ErrorCode.PARAM_ERROR, "消息不能为空")
|
||
|
||
import asyncio
|
||
from insurance.ppt.llm_client import llm_client
|
||
|
||
# 构建上下文
|
||
extractions = json.loads(session.extractions_json) if session.extractions_json else []
|
||
context_parts = []
|
||
for ext in extractions:
|
||
if ext.get("data"):
|
||
context_parts.append(f"产品: {ext['productName']}, 类型: {ext['planType']}")
|
||
data_inner = ext["data"]
|
||
policy = data_inner.get("policy", {})
|
||
context_parts.append(f"年缴保费: {policy.get('annual_premium', 'N/A')}")
|
||
context_parts.append(f"缴费年期: {policy.get('premium_payment_period', 'N/A')}")
|
||
|
||
system_prompt = (
|
||
"你是一位资深的香港保险顾问，擅长为保险经纪人分析保险计划书。"
|
||
"请基于以下保单数据，用温暖、专业、数据驱动的方式回答问题。\n\n"
|
||
f"保单数据：\n{''.join(context_parts)}"
|
||
)
|
||
|
||
try:
|
||
response = asyncio.run(llm_client.chat(message, system_prompt))
|
||
reply = response.content
|
||
except Exception as e:
|
||
reply = f"抱歉，暂时无法回答。错误信息：{e}"
|
||
|
||
# 更新对话历史
|
||
history = json.loads(session.chat_history_json) if session.chat_history_json else []
|
||
history.append({"role": "user", "content": message})
|
||
history.append({"role": "assistant", "content": reply})
|
||
# 保留最近 20 条
|
||
history = history[-20:]
|
||
session.chat_history_json = json.dumps(history, ensure_ascii=False)
|
||
_save_session(session)
|
||
|
||
return success({
|
||
"sessionId": session_id,
|
||
"message": reply,
|
||
"history": history,
|
||
})
|
||
|
||
|
||
# ─── 生成 PPT ─────────────────────────────────────────────
|
||
|
||
@ppt_bp.route("/generate/<session_id>", methods=["POST"])
|
||
@jwt_required
|
||
def generate_ppt(session_id):
|
||
"""生成 PPT（异步任务）。
|
||
|
||
创建任务后立即返回 202，前端通过任务接口轮询状态。
|
||
"""
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
session = _get_session(session_id, user_id)
|
||
if not session:
|
||
return error(ErrorCode.NOT_FOUND, "会话不存在")
|
||
|
||
data = request.get_json(silent=True) or {}
|
||
theme = data.get("theme") or data.get("style") or "broker"
|
||
company_id = data.get("companyId", "")
|
||
template_id = data.get("templateId", "")
|
||
use_masked_data = bool(data.get("useMaskedData"))
|
||
files = json.loads(session.files_json) if session.files_json else []
|
||
product_ids = [item.get("productId") for item in files if item.get("productId")]
|
||
if not company_id:
|
||
company_id = next(
|
||
(item.get("companyId") for item in files if item.get("companyId")), ""
|
||
)
|
||
if company_id:
|
||
from insurance.models.ppt_config import PptCompany
|
||
if not PptCompany.query.filter_by(id=company_id, status=1).first():
|
||
return error(ErrorCode.PARAM_ERROR, "所选保司不存在或已停用")
|
||
|
||
if template_id:
|
||
from insurance.models.ppt_config import PptTemplate
|
||
from insurance.ppt.comparison import detect_generation_scenario
|
||
template = PptTemplate.query.filter_by(id=template_id, status=1).first()
|
||
if not template:
|
||
return error(ErrorCode.PARAM_ERROR, "所选 PPT 模板不存在或已停用")
|
||
template_data = template.to_dict()
|
||
file_kinds = [
|
||
{"kind": item.get("type")}
|
||
for item in files
|
||
if item.get("type")
|
||
]
|
||
file_scenario = detect_generation_scenario(file_kinds) if file_kinds else ""
|
||
primary_plan_type = file_kinds[0]["kind"] if file_kinds else ""
|
||
if template.scenario_tag and file_scenario and template.scenario_tag != file_scenario:
|
||
return error(ErrorCode.PARAM_ERROR, "所选 PPT 模板不适用于当前计划书组合")
|
||
if (
|
||
not template.scenario_tag
|
||
and primary_plan_type
|
||
and template.plan_type != primary_plan_type
|
||
):
|
||
return error(ErrorCode.PARAM_ERROR, "所选 PPT 模板不适用于当前险种")
|
||
applicable_companies = template_data.get("applicableCompanyIds") or []
|
||
applicable_products = template_data.get("applicableProductIds") or []
|
||
if applicable_companies and company_id not in applicable_companies:
|
||
return error(ErrorCode.PARAM_ERROR, "所选 PPT 模板不适用于当前保司")
|
||
if applicable_products and not set(product_ids).intersection(applicable_products):
|
||
return error(ErrorCode.PARAM_ERROR, "所选 PPT 模板不适用于当前产品")
|
||
theme = template.style_preset
|
||
|
||
extractions = json.loads(session.extractions_json) if session.extractions_json else []
|
||
if not extractions:
|
||
return error(ErrorCode.PARAM_ERROR, "无解析数据")
|
||
|
||
# 快速校验：确保有可生成的数据
|
||
has_valid = any(
|
||
e.get("status") in ("success", "partial") and e.get("data")
|
||
for e in extractions
|
||
)
|
||
if not has_valid:
|
||
return error(ErrorCode.PARAM_ERROR, "无有效提取数据")
|
||
|
||
from insurance.ppt.comparison import detect_generation_scenario
|
||
scenario = detect_generation_scenario([
|
||
{"kind": e.get("planType") or (e.get("data") or {}).get("product_type")}
|
||
for e in extractions
|
||
if e.get("status") in ("success", "partial") and e.get("data")
|
||
])
|
||
|
||
# 更新会话草稿选项
|
||
import uuid
|
||
session.draft_options_json = json.dumps({
|
||
"theme": theme, "templateId": template_id,
|
||
"companyId": company_id, "productIds": product_ids,
|
||
"useMaskedData": use_masked_data,
|
||
"scenario": scenario,
|
||
}, ensure_ascii=False)
|
||
session.draft_revision = (session.draft_revision or 1) + 1
|
||
_save_session(session)
|
||
|
||
# 创建异步任务
|
||
from insurance.generation import task_service
|
||
result = task_service.create_task(
|
||
user_id=user_id,
|
||
artifact_type="ppt",
|
||
operation="generate",
|
||
workspace_id=session_id,
|
||
title=session.title or f"PPT {session_id[:8]}",
|
||
input_snapshot={
|
||
"theme": theme,
|
||
"templateId": template_id,
|
||
"companyId": company_id,
|
||
"productIds": product_ids,
|
||
"useMaskedData": use_masked_data,
|
||
"scenario": scenario,
|
||
},
|
||
input_revision=session.draft_revision or 1,
|
||
idempotency_key=f"ppt_gen_{session_id}_{session.draft_revision}",
|
||
)
|
||
|
||
if result.get("code") != 0:
|
||
return error(ErrorCode.PARAM_ERROR, result.get("message", "创建任务失败"))
|
||
|
||
task_data = result["data"]
|
||
session.latest_task_id = task_data["id"]
|
||
_save_session(session)
|
||
|
||
from flask import jsonify, make_response
|
||
resp = make_response(jsonify({
|
||
"code": 0,
|
||
"data": {
|
||
"taskId": task_data["id"],
|
||
"status": "queued",
|
||
"sessionId": session_id,
|
||
"scenario": scenario,
|
||
"pollUrl": f"/insurance/workspace/tasks/{task_data['id']}",
|
||
},
|
||
}))
|
||
resp.status_code = 202
|
||
return resp
|
||
|
||
|
||
# ─── 下载 PPT ─────────────────────────────────────────────
|
||
|
||
@ppt_bp.route("/download/<session_id>", methods=["GET"])
|
||
@jwt_required
|
||
def download_ppt(session_id):
|
||
"""下载生成的 PPT。"""
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
session = _get_session(session_id, user_id)
|
||
if not session:
|
||
return error(ErrorCode.NOT_FOUND, "会话不存在")
|
||
|
||
if not session.ppt_path or not os.path.exists(session.ppt_path):
|
||
return error(ErrorCode.NOT_FOUND, "PPT 文件不存在")
|
||
|
||
# 记录下载历史
|
||
try:
|
||
_record_history(
|
||
user_id=user_id,
|
||
action_type="download",
|
||
session_id=session_id,
|
||
file_url=session.ppt_path,
|
||
)
|
||
except Exception:
|
||
logger.warning("记录下载历史失败", exc_info=True)
|
||
|
||
return send_file(
|
||
session.ppt_path,
|
||
as_attachment=True,
|
||
download_name=f"{session_id}.pptx",
|
||
mimetype="application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
||
)
|
||
|
||
|
||
# ─── 验证提取数据 ─────────────────────────────────────────
|
||
|
||
@ppt_bp.route("/validate/<session_id>", methods=["GET"])
|
||
@jwt_required
|
||
def validate_extraction(session_id):
|
||
"""验证提取数据完整性。"""
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
session = _get_session(session_id, user_id)
|
||
if not session:
|
||
return error(ErrorCode.NOT_FOUND, "会话不存在")
|
||
|
||
extractions = json.loads(session.extractions_json) if session.extractions_json else []
|
||
all_issues = []
|
||
|
||
from insurance.ppt.normalizer import normalize_savings_plan, normalize_ci_plan, normalize_iul_plan
|
||
from insurance.ppt.validator import validate_formal_savings_plan, validate_formal_ci_plan, validate_formal_iul_plan
|
||
|
||
for idx, ext in enumerate(extractions):
|
||
pdf_name = ext.get("pdfName", f"文件{idx + 1}")
|
||
product_name = ext.get("productName", "unknown")
|
||
|
||
# 解析失败的文件必须产生阻断问题，不能静默跳过
|
||
if ext.get("status") not in ("success", "partial") or not ext.get("data"):
|
||
error_detail = ext.get("error", "未知错误")
|
||
all_issues.append({
|
||
"extractionIndex": idx,
|
||
"pdfName": pdf_name,
|
||
"field": "EXTRACTION_FAILED",
|
||
"path": "",
|
||
"section": "fields",
|
||
"severity": "error",
|
||
"message": f"{pdf_name}（{product_name}）解析失败：{error_detail}",
|
||
"suggestedAction": "review",
|
||
"state": "unresolved",
|
||
})
|
||
continue
|
||
|
||
data = ext["data"]
|
||
plan_type = (ext.get("planType") or data.get("product_type") or "savings").lower()
|
||
pdf_path = ext.get("pdfPath")
|
||
try:
|
||
if plan_type == "ci":
|
||
normalized = normalize_ci_plan(data, pdf_path)
|
||
issues = validate_formal_ci_plan(normalized)
|
||
elif plan_type == "iul":
|
||
normalized = normalize_iul_plan(data, pdf_path)
|
||
issues = validate_formal_iul_plan(normalized)
|
||
else:
|
||
normalized = normalize_savings_plan(data, pdf_path)
|
||
issues = validate_formal_savings_plan(normalized)
|
||
all_issues.extend([{
|
||
"extractionIndex": idx,
|
||
"pdfName": pdf_name,
|
||
"field": i.code,
|
||
"path": i.path or "",
|
||
"section": i.section or "",
|
||
"severity": i.level,
|
||
"message": i.message,
|
||
"suggestedAction": i.suggested_action or "review",
|
||
"state": "unresolved",
|
||
} for i in issues])
|
||
except Exception as e:
|
||
all_issues.append({
|
||
"extractionIndex": idx,
|
||
"pdfName": pdf_name,
|
||
"field": "general",
|
||
"severity": "error",
|
||
"message": str(e),
|
||
})
|
||
|
||
error_count = sum(1 for i in all_issues if i["severity"] == "error")
|
||
warn_count = sum(1 for i in all_issues if i["severity"] == "warn")
|
||
|
||
# ── 跨文件兼容性校验（同险种比较场景） ──
|
||
valid_extractions = [
|
||
e for e in extractions
|
||
if e.get("status") in ("success", "partial") and e.get("data")
|
||
]
|
||
if len(valid_extractions) >= 2:
|
||
try:
|
||
from insurance.ppt.comparison import (
|
||
detect_generation_scenario,
|
||
generation_mode_for_scenario,
|
||
build_comparison_contract,
|
||
SCENARIO_GENERIC_COMPARE,
|
||
SCENARIO_MULTI_SAVINGS,
|
||
)
|
||
normalized_for_check = []
|
||
from insurance.ppt.normalizer import normalize_savings_plan as _ns, normalize_ci_plan as _nc, normalize_iul_plan as _ni
|
||
for ext in valid_extractions:
|
||
data = ext["data"]
|
||
pt = (ext.get("planType") or data.get("product_type") or "savings").lower()
|
||
try:
|
||
if pt == "ci":
|
||
n = _nc(data, ext.get("pdfPath"))
|
||
elif pt == "iul":
|
||
n = _ni(data, ext.get("pdfPath"))
|
||
else:
|
||
n = _ns(data, ext.get("pdfPath"))
|
||
n["kind"] = pt
|
||
normalized_for_check.append(n)
|
||
except Exception:
|
||
pass
|
||
|
||
if len(normalized_for_check) >= 2:
|
||
scenario = detect_generation_scenario(normalized_for_check)
|
||
mode = generation_mode_for_scenario(scenario)
|
||
try:
|
||
contract = build_comparison_contract(normalized_for_check, mode=mode)
|
||
for w in contract.get("warnings", []):
|
||
all_issues.append({"field": "comparison", "severity": "warn", "message": w})
|
||
except ValueError as ve:
|
||
all_issues.append({"field": "comparison", "severity": "error", "message": str(ve)})
|
||
error_count += 1
|
||
except Exception as e:
|
||
logger.warning("跨文件兼容性校验异常: %s", e)
|
||
|
||
return success({
|
||
"sessionId": session_id,
|
||
"validated": error_count == 0,
|
||
"errorCount": error_count,
|
||
"warnCount": warn_count,
|
||
"issues": all_issues,
|
||
})
|
||
|
||
|
||
# ─── 更新提取数据 ─────────────────────────────────────────
|
||
|
||
@ppt_bp.route("/session/<session_id>/extractions", methods=["PUT"])
|
||
@jwt_required
|
||
def update_extractions(session_id):
|
||
"""保存用户修改后的提取数据。"""
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
session = _get_session(session_id, user_id)
|
||
if not session:
|
||
return error(ErrorCode.NOT_FOUND, "会话不存在")
|
||
|
||
data = request.get_json(silent=True) or {}
|
||
extractions = data.get("extractions")
|
||
if not isinstance(extractions, list):
|
||
return error(ErrorCode.PARAM_ERROR, "extractions 必须是数组")
|
||
|
||
# 合并更新：只更新 data 字段，保留 pdfPath/status 等元信息
|
||
existing = json.loads(session.extractions_json) if session.extractions_json else []
|
||
existing_map = {e["pdfName"]: e for e in existing}
|
||
|
||
for ext in extractions:
|
||
pdf_name = ext.get("pdfName")
|
||
if not pdf_name or pdf_name not in existing_map:
|
||
continue
|
||
# 更新数据字段
|
||
if "data" in ext:
|
||
existing_map[pdf_name]["data"] = ext["data"]
|
||
if "productName" in ext:
|
||
existing_map[pdf_name]["productName"] = ext["productName"]
|
||
if "planType" in ext:
|
||
existing_map[pdf_name]["planType"] = ext["planType"]
|
||
_reassess_extraction(existing_map[pdf_name])
|
||
|
||
updated = list(existing_map.values())
|
||
session.extractions_json = json.dumps(updated, ensure_ascii=False)
|
||
session.status = "parsed" # 回到 parsed 状态，需要重新生成
|
||
_save_session(session)
|
||
|
||
return success({
|
||
"sessionId": session_id,
|
||
"status": "updated",
|
||
"extractions": [{
|
||
"pdfName": e["pdfName"],
|
||
"planType": e["planType"],
|
||
"status": e["status"],
|
||
"productName": e["productName"],
|
||
"yearCount": e["yearCount"],
|
||
} for e in updated],
|
||
})
|
||
|
||
|
||
# ─── 公司知识库匹配 ───────────────────────────────────────
|
||
|
||
@ppt_bp.route("/company-kb/match", methods=["POST"])
|
||
@jwt_required
|
||
def match_company():
|
||
"""匹配公司知识库。"""
|
||
data = request.get_json(silent=True) or {}
|
||
product_name = data.get("productName")
|
||
company_hint = data.get("companyHint")
|
||
forced_company_id = data.get("companyId")
|
||
|
||
from insurance.models.ppt_config import PptCompany, PptProduct
|
||
from insurance.ppt.knowledge import match_company_knowledge
|
||
|
||
companies = [c.to_dict() for c in PptCompany.query.all()]
|
||
products = [p.to_dict() for p in PptProduct.query.all()]
|
||
|
||
result = match_company_knowledge(
|
||
product_name=product_name,
|
||
company_hint=company_hint,
|
||
forced_company_id=forced_company_id,
|
||
companies=companies,
|
||
products=products,
|
||
)
|
||
|
||
return success(result)
|
||
|
||
|
||
# ─── 历史记录 ─────────────────────────────────────────────
|
||
|
||
def _record_history(user_id, action_type, session_id=None, company_id=None,
|
||
product_id=None, template_id=None, content_snapshot=None,
|
||
file_url=None):
|
||
"""写入历史记录（内部函数）。"""
|
||
from insurance.db.compat import db
|
||
from insurance.models.ppt_history import PptHistory
|
||
from flask import request as req
|
||
record = PptHistory(
|
||
user_id=user_id,
|
||
session_id=session_id,
|
||
action_type=action_type,
|
||
company_id=company_id,
|
||
product_id=product_id,
|
||
template_id=template_id,
|
||
content_snapshot=json.dumps(content_snapshot, ensure_ascii=False) if content_snapshot else None,
|
||
file_url=file_url,
|
||
ip=req.remote_addr,
|
||
user_agent=req.headers.get("User-Agent", "")[:500],
|
||
)
|
||
db.session.add(record)
|
||
db.session.commit()
|
||
|
||
|
||
@ppt_bp.route("/history", methods=["GET"])
|
||
@jwt_required
|
||
def list_history():
|
||
"""当前用户的历史记录列表。"""
|
||
from insurance.db.compat import db
|
||
from insurance.models.ppt_history import PptHistory
|
||
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
page = max(1, request.args.get("page", 1, type=int))
|
||
page_size = min(100, max(1, request.args.get("page_size", 20, type=int)))
|
||
company_id = request.args.get("company_id", "")
|
||
action_type = request.args.get("action_type", "")
|
||
|
||
query = db.session.query(PptHistory).filter(PptHistory.user_id == user_id)
|
||
if company_id:
|
||
query = query.filter(PptHistory.company_id == company_id)
|
||
if action_type:
|
||
query = query.filter(PptHistory.action_type == action_type)
|
||
query = query.order_by(PptHistory.created_at.desc())
|
||
total = query.count()
|
||
items = query.offset((page - 1) * page_size).limit(page_size).all()
|
||
|
||
return success({
|
||
"total": total,
|
||
"items": [h.to_dict() for h in items],
|
||
})
|
||
|
||
|
||
@ppt_bp.route("/history/<int:history_id>", methods=["GET"])
|
||
@jwt_required
|
||
def get_history(history_id):
|
||
"""单条历史详情。"""
|
||
from insurance.models.ppt_history import PptHistory
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
record = PptHistory.query.get(history_id)
|
||
if not record or record.user_id != user_id:
|
||
return error(ErrorCode.NOT_FOUND, "记录不存在")
|
||
return success(record.to_dict())
|
||
|
||
|
||
@ppt_bp.route("/history/<int:history_id>/re-download", methods=["GET", "POST"])
|
||
@jwt_required
|
||
def re_download(history_id):
|
||
"""重新下载历史文件。"""
|
||
from insurance.models.ppt_history import PptHistory
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
record = PptHistory.query.get(history_id)
|
||
if not record or record.user_id != user_id:
|
||
return error(ErrorCode.NOT_FOUND, "记录不存在")
|
||
if not record.file_url or not os.path.exists(record.file_url):
|
||
return error(ErrorCode.NOT_FOUND, "文件不存在")
|
||
return send_file(record.file_url, as_attachment=True)
|
||
|
||
|
||
# ─── 预览接口 ─────────────────────────────────────────────
|
||
|
||
@ppt_bp.route("/preview/<session_id>", methods=["GET"])
|
||
@jwt_required
|
||
def get_preview(session_id):
|
||
"""获取幻灯片预览数据（结构化 JSON + 质量报告）。"""
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
session = _get_session(session_id, user_id)
|
||
if not session:
|
||
return error(ErrorCode.NOT_FOUND, "会话不存在")
|
||
|
||
preview_status = session.preview_status or "none"
|
||
slides_data = None
|
||
|
||
if session.slides_json_path:
|
||
if os.path.exists(session.slides_json_path):
|
||
try:
|
||
with open(session.slides_json_path, "r", encoding="utf-8") as f:
|
||
slides_data = json.load(f)
|
||
except Exception as e:
|
||
logger.warning("读取 slides.json 失败: %s", e)
|
||
preview_status = "failed"
|
||
else:
|
||
logger.warning("slides.json 已被清理: %s", session.slides_json_path)
|
||
preview_status = "failed"
|
||
|
||
quality_report = None
|
||
if session.quality_report_json:
|
||
try:
|
||
quality_report = json.loads(session.quality_report_json)
|
||
except Exception:
|
||
pass
|
||
|
||
return success({
|
||
"sessionId": session_id,
|
||
"previewStatus": preview_status,
|
||
"slides": slides_data,
|
||
"qualityReport": quality_report,
|
||
"slideCount": session.slide_count or 0,
|
||
"versions": json.loads(session.versions_json) if session.versions_json else [],
|
||
"generatedRevision": session.generated_revision or 0,
|
||
})
|
||
|
||
|
||
@ppt_bp.route("/preview/<session_id>/slide/<int:index>", methods=["PUT"])
|
||
@jwt_required
|
||
def update_slide(session_id, index):
|
||
"""更新指定页的编辑内容。"""
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
session = _get_session(session_id, user_id)
|
||
if not session:
|
||
return error(ErrorCode.NOT_FOUND, "会话不存在")
|
||
|
||
if not session.slides_json_path or not os.path.exists(session.slides_json_path):
|
||
return error(ErrorCode.NOT_FOUND, "预览数据不存在")
|
||
|
||
data = request.get_json(silent=True) or {}
|
||
shapes = data.get("shapes")
|
||
hidden = data.get("hidden")
|
||
|
||
try:
|
||
with open(session.slides_json_path, "r", encoding="utf-8") as f:
|
||
slides_data = json.load(f)
|
||
except Exception:
|
||
return error(ErrorCode.SERVER_ERROR, "读取预览数据失败")
|
||
|
||
slides = slides_data.get("slides", [])
|
||
if index < 0 or index >= len(slides):
|
||
return error(ErrorCode.PARAM_ERROR, f"页码超出范围 (0-{len(slides) - 1})")
|
||
|
||
if shapes is not None:
|
||
if not isinstance(shapes, list):
|
||
return error(ErrorCode.PARAM_ERROR, "shapes 必须是数组")
|
||
slides[index]["shapes"] = shapes
|
||
if hidden is not None:
|
||
slides[index]["hidden"] = bool(hidden)
|
||
|
||
try:
|
||
with open(session.slides_json_path, "w", encoding="utf-8") as f:
|
||
json.dump(slides_data, f, ensure_ascii=False)
|
||
except Exception:
|
||
return error(ErrorCode.SERVER_ERROR, "保存预览数据失败")
|
||
|
||
# 记录编辑历史
|
||
try:
|
||
_record_history(
|
||
user_id=user_id,
|
||
action_type="edit_slide",
|
||
session_id=session_id,
|
||
content_snapshot={"slideIndex": index, "shapeCount": len(shapes)},
|
||
)
|
||
except Exception:
|
||
logger.warning("记录编辑历史失败", exc_info=True)
|
||
|
||
return success({"sessionId": session_id, "slideIndex": index, "updated": True})
|
||
|
||
|
||
@ppt_bp.route("/preview/<session_id>/quality-confirm", methods=["PUT"])
|
||
@jwt_required
|
||
def update_quality_confirm(session_id):
|
||
"""更新人工质量确认项。"""
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
session = _get_session(session_id, user_id)
|
||
if not session:
|
||
return error(ErrorCode.NOT_FOUND, "会话不存在")
|
||
|
||
if not session.quality_report_json:
|
||
return error(ErrorCode.NOT_FOUND, "质量报告不存在")
|
||
|
||
data = request.get_json(silent=True) or {}
|
||
key = data.get("key", "").strip()
|
||
confirmed = bool(data.get("confirmed"))
|
||
|
||
if not key:
|
||
return error(ErrorCode.PARAM_ERROR, "key 必填")
|
||
|
||
try:
|
||
report = json.loads(session.quality_report_json)
|
||
except Exception:
|
||
return error(ErrorCode.SERVER_ERROR, "质量报告解析失败")
|
||
|
||
# 更新人工确认项
|
||
updated = False
|
||
for item in report.get("manual", []):
|
||
if item["key"] == key:
|
||
item["confirmed"] = confirmed
|
||
updated = True
|
||
break
|
||
|
||
if not updated:
|
||
return error(ErrorCode.PARAM_ERROR, f"未知的确认项: {key}")
|
||
|
||
# 更新待确认计数
|
||
report["summary"]["manualPending"] = sum(
|
||
1 for m in report.get("manual", []) if not m.get("confirmed")
|
||
)
|
||
|
||
session.quality_report_json = json.dumps(report, ensure_ascii=False)
|
||
from insurance.db.compat import db
|
||
db.session.commit()
|
||
|
||
return success({"sessionId": session_id, "key": key, "confirmed": confirmed})
|
||
|
||
|
||
@ppt_bp.route("/preview/<session_id>/regenerate", methods=["POST"])
|
||
@jwt_required
|
||
def regenerate_version(session_id):
|
||
"""基于当前编辑内容重新生成新版本 PPT。
|
||
|
||
不覆盖当前版本，生成后追加到版本历史。
|
||
"""
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
session = _get_session(session_id, user_id)
|
||
if not session:
|
||
return error(ErrorCode.NOT_FOUND, "会话不存在")
|
||
|
||
if not session.ppt_path or not os.path.exists(session.ppt_path):
|
||
return error(ErrorCode.PARAM_ERROR, "当前无可用的 PPT 文件")
|
||
|
||
# 检查是否有运行中的任务
|
||
from insurance.generation import task_service
|
||
if session.latest_task_id:
|
||
from insurance.models.generation_task import GenerationTask
|
||
active = GenerationTask.query.filter(
|
||
GenerationTask.id == session.latest_task_id,
|
||
GenerationTask.status.in_(["queued", "running"]),
|
||
).first()
|
||
if active:
|
||
return error(ErrorCode.PARAM_ERROR, "有正在执行的任务，请等待完成")
|
||
|
||
# 读取当前编辑后的 slides.json
|
||
edits_data = None
|
||
if session.slides_json_path and os.path.exists(session.slides_json_path):
|
||
try:
|
||
with open(session.slides_json_path, "r", encoding="utf-8") as f:
|
||
edits_data = json.load(f)
|
||
except Exception:
|
||
pass
|
||
|
||
# 递增版本号
|
||
session.draft_revision = (session.draft_revision or 1) + 1
|
||
session.status = "generating"
|
||
_save_session(session)
|
||
|
||
# 创建异步任务，传递编辑数据
|
||
result = task_service.create_task(
|
||
user_id=user_id,
|
||
artifact_type="ppt",
|
||
operation="regenerate",
|
||
workspace_id=session_id,
|
||
title=session.title or f"PPT {session_id[:8]}",
|
||
input_snapshot={
|
||
"revision": session.draft_revision,
|
||
"edits": edits_data,
|
||
},
|
||
input_revision=session.draft_revision or 1,
|
||
idempotency_key=f"ppt_regen_{session_id}_{session.draft_revision}",
|
||
)
|
||
|
||
if result.get("code") != 0:
|
||
return error(ErrorCode.PARAM_ERROR, result.get("message", "创建任务失败"))
|
||
|
||
task_data = result["data"]
|
||
session.latest_task_id = task_data["id"]
|
||
_save_session(session)
|
||
|
||
return success({
|
||
"taskId": task_data["id"],
|
||
"status": "queued",
|
||
"sessionId": session_id,
|
||
"revision": session.draft_revision,
|
||
})
|
||
|
||
|
||
# ─── PDF 页面预览 ─────────────────────────────────────────
|
||
|
||
@ppt_bp.route("/pdf-preview/<session_id>/<int:extraction_index>/<int:page_number>", methods=["GET"])
|
||
@jwt_required
|
||
def pdf_page_preview(session_id, extraction_index, page_number):
|
||
"""返回 PDF 指定页的 PNG 预览图。
|
||
|
||
用于核对页面展示 PDF 原文证据。
|
||
"""
|
||
import tempfile
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
session = _get_session(session_id, user_id)
|
||
if not session:
|
||
return error(ErrorCode.NOT_FOUND, "会话不存在")
|
||
|
||
extractions = json.loads(session.extractions_json) if session.extractions_json else []
|
||
if extraction_index < 0 or extraction_index >= len(extractions):
|
||
return error(ErrorCode.PARAM_ERROR, "提取索引越界")
|
||
|
||
ext = extractions[extraction_index]
|
||
pdf_path = ext.get("pdfPath")
|
||
if not pdf_path or not os.path.exists(pdf_path):
|
||
return error(ErrorCode.NOT_FOUND, "PDF 文件不存在")
|
||
|
||
try:
|
||
try:
|
||
import fitz
|
||
except ImportError:
|
||
import pymupdf as fitz
|
||
|
||
doc = fitz.open(pdf_path)
|
||
if page_number < 1 or page_number > len(doc):
|
||
doc.close()
|
||
return error(ErrorCode.PARAM_ERROR, f"页码越界（共 {len(doc)} 页）")
|
||
|
||
page = doc[page_number - 1] # 1-based to 0-based
|
||
# 渲染为 PNG，2x 缩放（约 150 DPI，平衡质量和大小）
|
||
pixmap = page.get_pixmap(matrix=fitz.Matrix(2.0, 2.0))
|
||
doc.close()
|
||
|
||
# 写入临时文件返回
|
||
img_bytes = pixmap.tobytes("png")
|
||
import io
|
||
buf = io.BytesIO(img_bytes)
|
||
buf.seek(0)
|
||
return send_file(
|
||
buf,
|
||
mimetype="image/png",
|
||
as_attachment=False,
|
||
download_name=f"page-{page_number}.png",
|
||
)
|
||
except ImportError:
|
||
return error(ErrorCode.INTERNAL_ERROR, "PDF 渲染库未安装（需要 PyMuPDF）")
|
||
except Exception as e:
|
||
logger.error(f"PDF 页面预览失败: {e}")
|
||
return error(ErrorCode.INTERNAL_ERROR, f"PDF 渲染失败: {str(e)[:100]}")
|
||
|
||
|
||
@ppt_bp.route("/pdf-info/<session_id>/<int:extraction_index>", methods=["GET"])
|
||
@jwt_required
|
||
def pdf_info(session_id, extraction_index):
|
||
"""返回 PDF 基本信息（总页数等）。"""
|
||
user_id = str(getattr(request, "user_id", "guest"))
|
||
session = _get_session(session_id, user_id)
|
||
if not session:
|
||
return error(ErrorCode.NOT_FOUND, "会话不存在")
|
||
|
||
extractions = json.loads(session.extractions_json) if session.extractions_json else []
|
||
if extraction_index < 0 or extraction_index >= len(extractions):
|
||
return error(ErrorCode.PARAM_ERROR, "提取索引越界")
|
||
|
||
ext = extractions[extraction_index]
|
||
pdf_path = ext.get("pdfPath")
|
||
if not pdf_path or not os.path.exists(pdf_path):
|
||
return error(ErrorCode.NOT_FOUND, "PDF 文件不存在")
|
||
|
||
try:
|
||
try:
|
||
import fitz
|
||
except ImportError:
|
||
import pymupdf as fitz
|
||
doc = fitz.open(pdf_path)
|
||
page_count = len(doc)
|
||
doc.close()
|
||
return success({"pageCount": page_count, "pdfName": ext.get("pdfName", "")})
|
||
except ImportError:
|
||
return error(ErrorCode.INTERNAL_ERROR, "PDF 渲染库未安装")
|
||
except Exception as e:
|
||
return error(ErrorCode.INTERNAL_ERROR, str(e)[:100])
|