初始提交：飞球 ETL 系统全量代码

tasks/ods/orders_task.py

@@ -0,0 +1,91 @@
+# -*- coding: utf-8 -*-
+"""订单ETL任务"""
+import json
+
+from tasks.base_task import BaseTask, TaskContext
+from loaders.facts.order import OrderLoader
+from models.parsers import TypeParser
+
+
+class OrdersTask(BaseTask):
+    """订单数据ETL任务"""
+
+    def get_task_code(self) -> str:
+        return "ORDERS"
+
+    # ------------------------------------------------------------------ E/T/L 钩子
+    def extract(self, context: TaskContext) -> dict:
+        """调用 API 拉取订单记录"""
+        params = self._merge_common_params(
+            {
+                "siteId": context.store_id,
+                "rangeStartTime": TypeParser.format_timestamp(context.window_start, self.tz),
+                "rangeEndTime": TypeParser.format_timestamp(context.window_end, self.tz),
+            }
+        )
+        records, pages_meta = self.api.get_paginated(
+            endpoint="/Site/GetAllOrderSettleList",
+            params=params,
+            page_size=self.config.get("api.page_size", 200),
+            data_path=("data",),
+            list_key="settleList",
+        )
+        return {"records": records, "meta": pages_meta}
+
+    def transform(self, extracted: dict, context: TaskContext) -> dict:
+        """解析原始订单 JSON"""
+        parsed_records = []
+        skipped = 0
+
+        for rec in extracted.get("records", []):
+            parsed = self._parse_order(rec, context.store_id)
+            if parsed:
+                parsed_records.append(parsed)
+            else:
+                skipped += 1
+
+        return {
+            "records": parsed_records,
+            "fetched": len(extracted.get("records", [])),
+            "skipped": skipped,
+        }
+
+    def load(self, transformed: dict, context: TaskContext) -> dict:
+        """写入 fact_order"""
+        loader = OrderLoader(self.db)
+        inserted, updated, loader_skipped = loader.upsert_orders(
+            transformed["records"], context.store_id
+        )
+
+        counts = {
+            "fetched": transformed["fetched"],
+            "inserted": inserted,
+            "updated": updated,
+            "skipped": transformed["skipped"] + loader_skipped,
+            "errors": 0,
+        }
+        return counts
+
+    # ------------------------------------------------------------------ 辅助方法
+    def _parse_order(self, raw: dict, store_id: int) -> dict | None:
+        """解析单条订单记录"""
+        try:
+            return {
+                "store_id": store_id,
+                "order_id": TypeParser.parse_int(raw.get("orderId")),
+                "order_no": raw.get("orderNo"),
+                "member_id": TypeParser.parse_int(raw.get("memberId")),
+                "table_id": TypeParser.parse_int(raw.get("tableId")),
+                "order_time": TypeParser.parse_timestamp(raw.get("orderTime"), self.tz),
+                "end_time": TypeParser.parse_timestamp(raw.get("endTime"), self.tz),
+                "total_amount": TypeParser.parse_decimal(raw.get("totalAmount")),
+                "discount_amount": TypeParser.parse_decimal(raw.get("discountAmount")),
+                "final_amount": TypeParser.parse_decimal(raw.get("finalAmount")),
+                "pay_status": raw.get("payStatus"),
+                "order_status": raw.get("orderStatus"),
+                "remark": raw.get("remark"),
+                "raw_data": json.dumps(raw, ensure_ascii=False),
+            }
+        except Exception as exc:
+            self.logger.warning("解析订单失败: %s, 原始数据: %s", exc, raw)
+            return None