feat(HEL-402): 接通网站首批只读 datahub 并建立双路对比

默认全部读取/影子开关关闭，网站继续走旧 Tushare 链路；开启单项时只替换该类原料并在失败时回旧，问天保持旧路径。 Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: multica-agent <github@multica.ai>
2026-09-02 17:09:28 +08:00
parent f5dc0f8076
commit 0d13066386
19 changed files with 1412 additions and 1 deletions
@@ -0,0 +1,120 @@
+from __future__ import annotations
+
+import json
+import os
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any, Mapping
+
+from backend.bootstrap.config import APP_DIR
+
+
+DATASETS = (
+    "calendar",
+    "stocks",
+    "daily",
+    "index_daily",
+    "valuation",
+    "moneyflow",
+    "auction",
+    "status",
+)
+
+ENV_DATASET = {
+    "calendar": "CALENDAR",
+    "stocks": "STOCKS",
+    "daily": "DAILY",
+    "index_daily": "INDEX_DAILY",
+    "valuation": "VALUATION",
+    "moneyflow": "MONEYFLOW",
+    "auction": "AUCTION",
+    "status": "STATUS",
+}
+
+DEFAULT_CONFIG_PATH = APP_DIR / "config" / "datahub.config.json"
+
+
+def _truthy(value: Any) -> bool:
+    return str(value or "").strip().lower() in {"1", "true", "yes", "on"}
+
+
+def _int(value: Any, default: int) -> int:
+    try:
+        return int(value)
+    except (TypeError, ValueError):
+        return default
+
+
+@dataclass(frozen=True)
+class DatasetFlags:
+    name: str
+    read: bool = False
+    shadow: bool = False
+
+
+@dataclass(frozen=True)
+class DatahubSettings:
+    base_url: str
+    token: str
+    timeout_seconds: int = 8
+    retries: int = 1
+    page_limit: int = 5000
+    stale_seconds_max: int = 86400
+    datasets: dict[str, DatasetFlags] | None = None
+
+    def flags(self, dataset: str) -> DatasetFlags:
+        mapped = self.datasets or {}
+        return mapped.get(dataset) or DatasetFlags(dataset)
+
+    def any_enabled(self) -> bool:
+        return any(item.read or item.shadow for item in (self.datasets or {}).values())
+
+    def secrets(self) -> tuple[str, ...]:
+        return tuple(item for item in (self.token,) if item)
+
+    @classmethod
+    def load(
+        cls,
+        path: Path | None = None,
+        environ: Mapping[str, str] | None = None,
+        credentials: Mapping[str, object] | None = None,
+    ) -> "DatahubSettings":
+        config_path = path or DEFAULT_CONFIG_PATH
+        payload: dict[str, Any] = {}
+        if config_path.is_file():
+            payload = json.loads(config_path.read_text(encoding="utf-8"))
+        env = dict(os.environ if environ is None else environ)
+        creds = dict(credentials or {})
+        dataset_flags: dict[str, DatasetFlags] = {}
+        raw_datasets = payload.get("datasets") or {}
+        for name in DATASETS:
+            item = raw_datasets.get(name) or {}
+            env_key = ENV_DATASET[name]
+            read = _truthy(env.get(f"DATAHUB_READ_{env_key}")) if f"DATAHUB_READ_{env_key}" in env else bool(item.get("read"))
+            shadow = (
+                _truthy(env.get(f"DATAHUB_SHADOW_{env_key}"))
+                if f"DATAHUB_SHADOW_{env_key}" in env
+                else bool(item.get("shadow"))
+            )
+            dataset_flags[name] = DatasetFlags(name, read=read, shadow=shadow)
+        token = str(
+            env.get("DATAHUB_TOKEN")
+            or creds.get("datahub_token")
+            or payload.get("token")
+            or ""
+        ).strip()
+        base_url = str(
+            env.get("DATAHUB_BASE_URL")
+            or creds.get("datahub_base_url")
+            or payload.get("base_url")
+            or "http://127.0.0.1:8766"
+        ).strip().rstrip("/")
+        return cls(
+            base_url=base_url,
+            token=token,
+            timeout_seconds=_int(env.get("DATAHUB_TIMEOUT") or payload.get("timeout_seconds"), 8),
+            retries=max(0, _int(env.get("DATAHUB_RETRIES") or payload.get("retries"), 1)),
+            page_limit=max(1, _int(payload.get("page_limit"), 5000)),
+            stale_seconds_max=max(0, _int(payload.get("stale_seconds_max"), 86400)),
+            datasets=dataset_flags,
+        )