更新一版

scripts/migration/scan_legacy.py

@@ -17,6 +17,7 @@ from __future__ import annotations
 import argparse
 import csv
 import sys
+from dataclasses import dataclass
 from pathlib import Path
 
 sys.path.insert(0, str(Path(__file__).resolve().parent))
@@ -31,15 +32,30 @@ from lib.mapping_loader import (  # noqa: E402
 )
 
 
-def _read_iccid_pairs(cards_csv: Path) -> list[tuple[str, str, bool]]:
+@dataclass(frozen=True)
+class ICCIDInput:
+    """业务方提供的单行 ICCID 输入。"""
+
+    line_no: int
+    iccid_19: str
+    iccid_20: str
+    allow_iccid_19_lookup: bool
+
+    @property
+    def card_key(self) -> str:
+        """奇成扫描结果使用的业务方完整键。"""
+        return self.iccid_20 or self.iccid_19
+
+
+def _read_iccid_pairs(cards_csv: Path) -> list[ICCIDInput]:
     """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, allow_iccid_19_lookup) 列表。
+    返回带行号的 ICCID 输入列表。
     只填 iccid_20 时,iccid_19 从前 19 位派生,但不用于奇成主表兜底查询。
     """
     if not cards_csv.exists():
         raise FileNotFoundError(f"找不到 {cards_csv},请按 resources/README.md 准备")
-    pairs: dict[str, tuple[str, str, bool]] = {}
+    pairs: dict[str, ICCIDInput] = {}
     first_seen_line: dict[str, int] = {}
     errors: list[str] = []
     with cards_csv.open("r", encoding="utf-8-sig", newline="") as f:
@@ -75,7 +91,12 @@ def _read_iccid_pairs(cards_csv: Path) -> list[tuple[str, str, bool]]:
                 errors.append(f"第 {line_no} 行 {'iccid_20' if i20 else 'iccid_19'} 与第 {first_seen_line[dedup_key]} 行重复: {dedup_key!r}")
                 continue
             first_seen_line[dedup_key] = line_no
-            pairs[dedup_key] = (i19, i20, allow_i19_lookup)
+            pairs[dedup_key] = ICCIDInput(
+                line_no=line_no,
+                iccid_19=i19,
+                iccid_20=i20,
+                allow_iccid_19_lookup=allow_i19_lookup,
+            )
     if errors:
         preview = "\n".join(f"  - {msg}" for msg in errors[:20])
         if len(errors) > 20:
@@ -106,7 +127,10 @@ def main() -> int:
 
     dsn = mapping_loader.load_legacy_dsn(config_dir)
     with legacy_query.connect_readonly(dsn) as conn:
-        card_metas, dup_iccids = legacy_query.fetch_card_meta(conn, iccid_pairs)
+        card_metas, dup_iccids = legacy_query.fetch_card_meta(
+            conn,
+            [(x.iccid_19, x.iccid_20, x.allow_iccid_19_lookup) for x in 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)
 
@@ -120,8 +144,11 @@ def main() -> int:
     merged = _merge(existing, card_metas, meal_metas)
     out_path = mapping_loader.merge_and_save(config_dir, merged)
     todo = _collect_todo(merged)
+    unmatched = _collect_unmatched_iccids(iccid_pairs, card_metas, dup_iccids)
     _write_todo(config_dir / "mapping_todo.txt", todo)
-    _print_summary(out_path, card_metas, meal_metas, todo)
+    unmatched_path = config_dir / "unmatched_iccids.csv"
+    _write_unmatched_iccids(unmatched_path, unmatched)
+    _print_summary(out_path, card_metas, meal_metas, todo, unmatched_path, len(unmatched))
     return 0
 
 
@@ -134,6 +161,9 @@ def _merge(
     merged = Mapping(
         migration_user_id=existing.migration_user_id,
         migration_batch_no=existing.migration_batch_no,
+        ownership_rules=existing.ownership_rules,
+        package_rules=existing.package_rules,
+        overrides=existing.overrides,
         carriers=dict(existing.carriers),
         packages=dict(existing.packages),
         series=dict(existing.series),
@@ -210,6 +240,19 @@ def _collect_todo(mapping: Mapping) -> dict[str, list[str]]:
     return todo
 
 
+def _collect_unmatched_iccids(
+    iccid_pairs: list[ICCIDInput],
+    card_metas: dict[str, "legacy_query.LegacyCardMeta"],
+    duplicate_iccids: set[str],
+) -> list[ICCIDInput]:
+    """收集未在奇成 tbl_card 命中的 ICCID。
+
+    重复命中的卡属于脏数据异常,不是未命中,因此从未命中清单中排除。
+    """
+    resolved_keys = set(card_metas) | set(duplicate_iccids)
+    return [item for item in iccid_pairs if item.card_key not in resolved_keys]
+
+
 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"):
@@ -220,13 +263,47 @@ def _write_todo(path: Path, todo: dict[str, list[str]]) -> None:
     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:
+def _write_unmatched_iccids(path: Path, unmatched: list[ICCIDInput]) -> None:
+    """把未命中的 ICCID 写成 CSV,便于转给业务方核对。"""
+    path.parent.mkdir(parents=True, exist_ok=True)
+    with path.open("w", encoding="utf-8-sig", newline="") as f:
+        writer = csv.DictWriter(
+            f,
+            fieldnames=["line_no", "iccid_19", "iccid_20", "lookup_keys", "note"],
+        )
+        writer.writeheader()
+        for item in unmatched:
+            lookup_keys = [item.iccid_20 or item.iccid_19]
+            if item.iccid_20 and item.allow_iccid_19_lookup:
+                lookup_keys.append(item.iccid_19)
+            writer.writerow(
+                {
+                    "line_no": item.line_no,
+                    "iccid_19": item.iccid_19,
+                    "iccid_20": item.iccid_20,
+                    "lookup_keys": ";".join(lookup_keys),
+                    "note": "奇成 tbl_card 未命中",
+                }
+            )
+
+
+def _print_summary(
+    out_path: Path,
+    card_metas,
+    meal_metas,
+    todo: dict[str, list[str]],
+    unmatched_path: Path,
+    unmatched_count: int,
+) -> None:
     print(f"扫描完成,mapping 写入: {out_path}")
     print(f"  奇成卡命中     : {len(card_metas)}")
+    print(f"  奇成卡未命中   : {unmatched_count}")
     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 unmatched_count:
+        print(f"未命中清单: {unmatched_path}")
     if any(todo.values()):
         print(f"详见: {out_path.parent / 'mapping_todo.txt'}")