ODS 完成

etl_billiards/api/local_json_client.py

@@ -0,0 +1,74 @@
+# -*- coding: utf-8 -*-
+"""本地 JSON 客户端，模拟 APIClient 的分页接口，从落盘的 JSON 回放数据。"""
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from typing import Iterable, Tuple
+
+from api.client import APIClient
+from utils.json_store import endpoint_to_filename
+
+
+class LocalJsonClient:
+    """
+    读取 RecordingAPIClient 生成的 JSON，提供 iter_paginated/get_paginated 接口。
+    """
+
+    def __init__(self, base_dir: str | Path):
+        self.base_dir = Path(base_dir)
+        if not self.base_dir.exists():
+            raise FileNotFoundError(f"JSON 目录不存在: {self.base_dir}")
+
+    def iter_paginated(
+        self,
+        endpoint: str,
+        params: dict | None,
+        page_size: int = 200,
+        page_field: str = "page",
+        size_field: str = "limit",
+        data_path: tuple = ("data",),
+        list_key: str | None = None,
+    ) -> Iterable[Tuple[int, list, dict, dict]]:
+        file_path = self.base_dir / endpoint_to_filename(endpoint)
+        if not file_path.exists():
+            raise FileNotFoundError(f"未找到匹配的 JSON 文件: {file_path}")
+
+        with file_path.open("r", encoding="utf-8") as fp:
+            payload = json.load(fp)
+
+        pages = payload.get("pages")
+        if not isinstance(pages, list) or not pages:
+            pages = [{"page": 1, "request": params or {}, "response": payload}]
+
+        for idx, page in enumerate(pages, start=1):
+            response = page.get("response", {})
+            request_params = page.get("request") or {}
+            page_no = page.get("page") or idx
+            records = APIClient._extract_list(response, data_path, list_key)  # type: ignore[attr-defined]
+            yield page_no, records, request_params, response
+
+    def get_paginated(
+        self,
+        endpoint: str,
+        params: dict,
+        page_size: int = 200,
+        page_field: str = "page",
+        size_field: str = "limit",
+        data_path: tuple = ("data",),
+        list_key: str | None = None,
+    ) -> tuple[list, list]:
+        records: list = []
+        pages_meta: list = []
+        for page_no, page_records, request_params, response in self.iter_paginated(
+            endpoint=endpoint,
+            params=params,
+            page_size=page_size,
+            page_field=page_field,
+            size_field=size_field,
+            data_path=data_path,
+            list_key=list_key,
+        ):
+            records.extend(page_records)
+            pages_meta.append({"page": page_no, "request": request_params, "response": response})
+        return records, pages_meta