import json from typing import Any from fastapi import UploadFile from sqlalchemy.ext.asyncio import AsyncSession from app.core.base_schema import AuthSchema, PageResultSchema, ImportResultSchema from app.core.exceptions import CustomException from app.core.logger import logger from app.utils.common_util import search_to_dict from app.utils.excel_util import ExcelUtil from .crud import BreedingAnalysisDatasetCRUD from .schema import ( AnalysisDatasetCreateSchema, AnalysisDatasetOutSchema, AnalysisDatasetQueryParam, AnalysisDatasetUpdateSchema, ) def _is_blank(v: Any) -> bool: return v is None or (isinstance(v, str) and v.strip() == "") def _none_if_blank(v: Any) -> Any: if _is_blank(v): return None return str(v).strip() if isinstance(v, str) else v def _to_int(v: Any) -> int | None: if _is_blank(v): return None try: return int(float(v)) except (TypeError, ValueError): return None def _parse_str_list(v: Any) -> list[str] | None: """导入用：逗号分隔/数组 → 字符串列表；空返回 None。""" if _is_blank(v): return None if isinstance(v, (list, tuple)): out = [str(x).strip() for x in v if not _is_blank(x)] return out or None out = [s.strip() for s in str(v).split(",") if s.strip()] return out or None def _parse_int_list(v: Any) -> list[int] | None: """导入用：逗号分隔/数组 → 整数列表；空返回 None。""" if _is_blank(v): return None if isinstance(v, (list, tuple)): out = [x for x in (_to_int(i) for i in v) if x is not None] return out or None out = [x for x in (_to_int(s) for s in str(v).split(",") if s.strip()) if x is not None] return out or None def _parse_config(v: Any) -> dict | None: """导入用：JSON 字符串/字典 → 对象；无法解析返回 None。""" if _is_blank(v): return None if isinstance(v, dict): return v try: parsed = json.loads(str(v)) return parsed if isinstance(parsed, dict) else None except (TypeError, ValueError): return None class AnalysisDatasetService: """分析数据集 模块服务层（纯元数据，无外键联表）。""" def __init__(self, auth: AuthSchema, db: AsyncSession) -> None: self.auth = auth self.db = db async def _attach_fk_labels(self, items: list[AnalysisDatasetOutSchema]) -> None: """本模块无外键联表字段 —— 保持签名与其它模块一致，避免导出/详情路径报错。""" return async def detail(self, id: int) -> AnalysisDatasetOutSchema: obj = await BreedingAnalysisDatasetCRUD(self.auth, self.db).get(id=id) if not obj: raise CustomException(msg="该分析数据集不存在") out = AnalysisDatasetOutSchema.model_validate(obj) await self._attach_fk_labels([out]) return out async def get_list( self, search: AnalysisDatasetQueryParam | None = None, order_by: list[dict[str, str]] | None = None, ) -> list[AnalysisDatasetOutSchema]: obj_list = await BreedingAnalysisDatasetCRUD(self.auth, self.db).get_list( search=search_to_dict(search), order_by=order_by ) outs = [AnalysisDatasetOutSchema.model_validate(obj) for obj in obj_list] await self._attach_fk_labels(outs) return outs async def page( self, page_no: int, page_size: int, search: AnalysisDatasetQueryParam | None = None, order_by: list[dict[str, str]] | None = None, ) -> PageResultSchema[AnalysisDatasetOutSchema]: offset = (page_no - 1) * page_size result = await BreedingAnalysisDatasetCRUD(self.auth, self.db).page( offset=offset, limit=page_size, order_by=order_by or [{"id": "asc"}], search=search_to_dict(search, {}), out_schema=AnalysisDatasetOutSchema, ) await self._attach_fk_labels(result.items) return result async def create(self, data: AnalysisDatasetCreateSchema) -> AnalysisDatasetOutSchema: if _is_blank(data.name): raise CustomException(msg="数据集名称不能为空") obj = await BreedingAnalysisDatasetCRUD(self.auth, self.db).create(data=data) out = AnalysisDatasetOutSchema.model_validate(obj) await self._attach_fk_labels([out]) return out async def update(self, id: int, data: AnalysisDatasetUpdateSchema) -> AnalysisDatasetOutSchema: obj = await BreedingAnalysisDatasetCRUD(self.auth, self.db).get(id=id) if not obj: raise CustomException(msg="更新失败，该分析数据集不存在") if data.name is not None and _is_blank(data.name): raise CustomException(msg="数据集名称不能为空") obj = await BreedingAnalysisDatasetCRUD(self.auth, self.db).update(id=id, data=data) out = AnalysisDatasetOutSchema.model_validate(obj) await self._attach_fk_labels([out]) return out async def delete(self, ids: list[int]) -> None: if not ids: raise CustomException(msg="删除失败，删除对象不能为空") objs = await BreedingAnalysisDatasetCRUD(self.auth, self.db).get_list(search={"id": ("in", ids)}) obj_map = {o.id: o for o in objs} for id_ in ids: if id_ not in obj_map: raise CustomException(msg="删除失败，该分析数据集不存在") await BreedingAnalysisDatasetCRUD(self.auth, self.db).delete(ids=ids) async def list_options(self) -> list[dict[str, Any]]: """供前端下拉选择使用：返回 [{value, label}]。""" obj_list = await BreedingAnalysisDatasetCRUD(self.auth, self.db).get_list(order_by=[{"id": "asc"}]) return [{"value": o.id, "label": o.name} for o in obj_list] @staticmethod def batch_export(obj_list: list[dict[str, Any]]) -> bytes: mapping_dict = { "name": "数据集名称", "description": "数据集描述", "trait_codes": "性状编码", "sample_ids": "样本ID", "config": "分析配置", "status": "状态", "created_time": "创建时间", "created_by": "创建者", } data = [dict(item) for item in obj_list] for item in data: creator = item.get("created_by") item["created_by"] = creator.get("name", "未知") if isinstance(creator, dict) else "未知" if isinstance(item.get("trait_codes"), (list, tuple)): item["trait_codes"] = ",".join(str(x) for x in item["trait_codes"]) if isinstance(item.get("sample_ids"), (list, tuple)): item["sample_ids"] = ",".join(str(x) for x in item["sample_ids"]) if isinstance(item.get("config"), (dict, list)): item["config"] = json.dumps(item["config"], ensure_ascii=False) return ExcelUtil.export_list2excel(list_data=data, mapping_dict=mapping_dict) async def batch_import(self, file: UploadFile, update_support: bool = False) -> ImportResultSchema: header_dict = { "数据集名称": "name", "数据集描述": "description", "性状编码": "trait_codes", "样本ID": "sample_ids", "分析配置": "config", "状态": "status", } try: contents = await file.read() rows = ExcelUtil.read_excel_to_dicts(contents) await file.close() if not rows: raise CustomException(msg="导入文件为空") missing_headers = [h for h in header_dict if h not in rows[0]] if missing_headers: raise CustomException(msg=f"导入文件缺少必要的列: {', '.join(missing_headers)}") error_msgs: list[str] = [] success_count = 0 crud = BreedingAnalysisDatasetCRUD(self.auth, self.db) for i, row in enumerate(rows, start=1): try: fields = { "name": _none_if_blank(row.get("name")), "description": _none_if_blank(row.get("description")), "trait_codes": _parse_str_list(row.get("trait_codes")), "sample_ids": _parse_int_list(row.get("sample_ids")), "config": _parse_config(row.get("config")), "status": _none_if_blank(row.get("status")) or "draft", } create_data = AnalysisDatasetCreateSchema(**fields) await crud.create(data=create_data) success_count += 1 except Exception as e: error_msgs.append(f"第{i}行: {e!s}") continue return ImportResultSchema( valid_count=success_count, invalid_count=len(error_msgs), message_list=error_msgs, ) except Exception as e: logger.error(f"批量导入分析数据集失败: {e!s}") raise CustomException(msg=f"导入失败: {e!s}") @staticmethod def import_template_download() -> bytes: header_list = [ "数据集名称", "数据集描述", "性状编码", "样本ID", "分析配置", "状态", ] selector_header_list = [] option_list = [] return ExcelUtil.get_excel_template( header_list=header_list, selector_header_list=selector_header_list, option_list=option_list, )