#!/usr/bin/env python3 """扫描奇成,自动生成/增量补全 config/mapping.yaml。 工作流: 1. 读 resources/cards.csv 拿到 iccid 列表 2. 连奇成只读查询每张卡的 category / agent_id / 当前生效套餐 / 套餐系列 3. 加载已有的 config/mapping.yaml(若没有则创建空的) 4. 把扫描到的 legacy_* 增量补到 mapping 里(已有项的 target_* 字段保留,新项的 target_* 为 null) 5. 写回 config/mapping.yaml 6. 输出"待人工填写"清单到 console + config/mapping_todo.txt 用法: python3 scan_legacy.py [--config-dir config] [--resources-dir resources] """ from __future__ import annotations import argparse import csv import sys from pathlib import Path sys.path.insert(0, str(Path(__file__).resolve().parent)) from lib import legacy_query, mapping_loader # noqa: E402 from lib.mapping_loader import ( # noqa: E402 AgentMapping, CarrierMapping, Mapping, PackageMapping, SeriesMapping, ) def _read_iccid_pairs(cards_csv: Path) -> list[tuple[str, str]]: """从 cards.csv 读 iccid_19 + iccid_20 列(只关心这两列,其他列忽略)。 返回 (iccid_19, iccid_20) 列表;iccid_20 可为空字符串(CTCC 卡留空)。 """ if not cards_csv.exists(): raise FileNotFoundError(f"找不到 {cards_csv},请按 resources/README.md 准备") pairs: dict[str, str] = {} with cards_csv.open("r", encoding="utf-8-sig", newline="") as f: reader = csv.DictReader(f) headers = reader.fieldnames or [] if "iccid_19" not in headers: raise ValueError(f"{cards_csv} 必须包含 iccid_19 列") if "iccid_20" not in headers: raise ValueError(f"{cards_csv} 必须包含 iccid_20 列(CTCC 卡留空)") for row in reader: i19 = (row.get("iccid_19") or "").strip() i20 = (row.get("iccid_20") or "").strip() if i19: pairs[i19] = i20 return sorted(pairs.items()) def main() -> int: parser = argparse.ArgumentParser(description="奇成元数据预扫描,自动生成 mapping.yaml") parser.add_argument("--config-dir", default="config", help="yaml 配置目录") parser.add_argument("--resources-dir", default="resources", help="CSV 资源目录") args = parser.parse_args() base = Path(__file__).resolve().parent config_dir = (base / args.config_dir).resolve() resources_dir = (base / args.resources_dir).resolve() iccid_pairs = _read_iccid_pairs(resources_dir / "cards.csv") if not iccid_pairs: print("cards.csv 中没有 iccid_19,无需扫描", file=sys.stderr) return 1 print(f"读到 {len(iccid_pairs)} 个 ICCID,连接奇成扫描元数据...") dsn = mapping_loader.load_legacy_dsn(config_dir) with legacy_query.connect_readonly(dsn) as conn: card_metas, dup_iccid_19 = legacy_query.fetch_card_meta(conn, iccid_pairs) meal_ids = {m.current_meal_id for m in card_metas.values() if m.current_meal_id} meal_metas = legacy_query.fetch_meal_meta(conn, meal_ids) if dup_iccid_19: print(f"警告:{len(dup_iccid_19)} 张卡的 iccid_19 在奇成 tbl_card 命中多条记录:") for x in sorted(dup_iccid_19): print(f" - {x}") print("这些卡 migrate_assets 阶段会写 errors.csv 阻断,请业务方人工确认。") existing = mapping_loader.load_mapping(config_dir) merged = _merge(existing, card_metas, meal_metas) out_path = mapping_loader.merge_and_save(config_dir, merged) todo = _collect_todo(merged) _write_todo(config_dir / "mapping_todo.txt", todo) _print_summary(out_path, card_metas, meal_metas, todo) return 0 def _merge( existing: Mapping, card_metas: dict[str, "legacy_query.LegacyCardMeta"], meal_metas: dict[str, "legacy_query.LegacyMealMeta"], ) -> Mapping: """把扫描到的 legacy_* 增量合并到现有 mapping(保留已填的 target_*)。""" merged = Mapping( migration_user_id=existing.migration_user_id, migration_batch_no=existing.migration_batch_no, carriers=dict(existing.carriers), packages=dict(existing.packages), series=dict(existing.series), agents=dict(existing.agents), ) for meta in card_metas.values(): # carrier if meta.category and meta.category not in merged.carriers: merged.carriers[meta.category] = CarrierMapping( legacy_category=meta.category, legacy_category_name=meta.category_name, target_carrier_id=None, target_carrier_type=None, target_carrier_name=None, ) elif meta.category in merged.carriers and not merged.carriers[meta.category].legacy_category_name: # 补全 legacy_category_name(如果之前是空的) old = merged.carriers[meta.category] merged.carriers[meta.category] = CarrierMapping( legacy_category=old.legacy_category, legacy_category_name=meta.category_name, target_carrier_id=old.target_carrier_id, target_carrier_type=old.target_carrier_type, target_carrier_name=old.target_carrier_name, ) # agent if meta.agent_id and meta.agent_id not in merged.agents: merged.agents[meta.agent_id] = AgentMapping( legacy_agent_id=meta.agent_id, legacy_agent_name=meta.agent_name, target_shop_code=None, ) for mm in meal_metas.values(): if mm.meal_id not in merged.packages: merged.packages[mm.meal_id] = PackageMapping( legacy_meal_id=mm.meal_id, legacy_meal_name=mm.meal_name, target_package_id=None, ) if mm.series_id and mm.series_id not in merged.series: merged.series[mm.series_id] = SeriesMapping( legacy_series_id=mm.series_id, legacy_series_name=mm.series_name, target_series_id=None, ) return merged def _collect_todo(mapping: Mapping) -> dict[str, list[str]]: """收集所有待填写的项,按类别分组。""" todo: dict[str, list[str]] = {"carriers": [], "packages": [], "agents": []} for c in sorted(mapping.carriers.values(), key=lambda x: x.legacy_category): if not c.target_carrier_id or not c.target_carrier_type or not c.target_carrier_name: todo["carriers"].append(f"category={c.legacy_category} ({c.legacy_category_name})") for p in sorted(mapping.packages.values(), key=lambda x: x.legacy_meal_id): if not p.target_package_id: todo["packages"].append(f"meal_id={p.legacy_meal_id} ({p.legacy_meal_name})") for a in sorted(mapping.agents.values(), key=lambda x: x.legacy_agent_id): if not (a.target_shop_code or "").strip(): todo["agents"].append(f"agent_id={a.legacy_agent_id} ({a.legacy_agent_name})") return todo def _write_todo(path: Path, todo: dict[str, list[str]]) -> None: lines = ["奇成迁移映射待填写清单", "=" * 40, ""] for kind in ("carriers", "packages", "agents"): lines.append(f"## {kind} (待填: {len(todo[kind])})") for item in todo[kind]: lines.append(f" - {item}") lines.append("") path.write_text("\n".join(lines), encoding="utf-8") def _print_summary(out_path: Path, card_metas, meal_metas, todo: dict[str, list[str]]) -> None: print(f"扫描完成,mapping 写入: {out_path}") print(f" 奇成卡命中 : {len(card_metas)}") print(f" 奇成套餐命中 : {len(meal_metas)}") print(f" 待填 carriers : {len(todo['carriers'])}") print(f" 待填 packages : {len(todo['packages'])}") print(f" 待填 agents : {len(todo['agents'])}") if any(todo.values()): print(f"详见: {out_path.parent / 'mapping_todo.txt'}") if __name__ == "__main__": sys.exit(main())