feat: OCR v2 batch + RIIN waybill + 双系统 label-ocr flow(hourly)

flows/shared/db.py

@@ -100,22 +100,25 @@ class SyncDB:
 
     # ---------- OCR 面单 enrichment ----------
 
-    def get_ocr_pending(self, limit: int = 200) -> list[tuple[str, datetime, str, str | None]]:
-        """查待 OCR 的 SDS 订单:(orderNo, createdAt, labelPdfUrl, destinationCountry)。
+    def get_ocr_pending(self, limit: int = 0) -> list[tuple[str, datetime, str, str | None]]:
+        """查待 OCR 订单(所有系统):(orderNo, createdAt, labelPdfUrl, destinationCountry)。
 
-        条件:SDS、有 labelPdfUrl、ocr_layout 未处理(Null)、已发货/已完成。
+        条件:有 labelPdfUrl、ocr_layout 未处理(Null)。
+        limit=0 表示不限。
         """
+        sql = (
+            'SELECT "orderNo","createdAt","labelPdfUrl","destinationCountry" '
+            'FROM "Orders" '
+            'WHERE "labelPdfUrl" IS NOT NULL AND "ocr_layout" IS NULL '
+            'ORDER BY "orderedAt" DESC'
+        )
+        params: list = []
+        if limit > 0:
+            sql += " LIMIT %s"
+            params.append(limit)
         with self._conn() as conn:
             with conn.cursor() as cur:
-                cur.execute(
-                    '''SELECT "orderNo","createdAt","labelPdfUrl","destinationCountry"
-                       FROM "Orders"
-                       WHERE "systemName"=%s AND "labelPdfUrl" IS NOT NULL
-                         AND "ocr_layout" IS NULL
-                         AND "systemStatus"=ANY(%s)
-                       ORDER BY "orderedAt" DESC LIMIT %s''',
-                    ("SDS", ["已完成", "部分发货", "备货中", "待确认"], limit),
-                )
+                cur.execute(sql, params)
                 return [(r[0], r[1], r[2], r[3]) for r in cur.fetchall()]
 
     def update_ocr_fields(
@@ -135,6 +138,34 @@ class SyncDB:
                 )
             conn.commit()
 
+    def update_ocr_batch(self, updates: list[tuple[str, datetime, dict[str, str | None]]]) -> int:
+        """批量更新 ocr 字段(单连接单事务)。updates: [(orderNo, createdAt, {field: value})]。
+
+        返回更新行数。
+        """
+        if not updates:
+            return 0
+        rows = 0
+        with self._conn() as conn:
+            try:
+                with conn.cursor() as cur:
+                    for order_no, created_at, fields in updates:
+                        if not fields:
+                            continue
+                        assignments = ", ".join(f'"{k}"=%s' for k in fields)
+                        params = list(fields.values()) + [order_no, created_at]
+                        cur.execute(
+                            f'''UPDATE "Orders" SET {assignments}
+                                WHERE "orderNo"=%s AND "createdAt"=%s''',
+                            params,
+                        )
+                        rows += cur.rowcount
+                conn.commit()
+            except Exception:
+                conn.rollback()
+                raise
+        return rows
+
     def count_ocr_status(self) -> dict[str, int]:
         """统计 OCR 处理状态(done/error/unsupported/pending)。"""
         with self._conn() as conn:

flows/shared/mappers.py

@@ -195,7 +195,7 @@ def map_riin_order(raw: Any) -> OrderUpsertInput:
         addressLine3=raw.receiver_town,
         postalCode=raw.post_code,
         storeName=raw.platform_shop_name,
-        labelPdfUrl=None,
+        labelPdfUrl=raw.waybill,
     )