feat(data): 脚手架 + YAML 配置加载

config/data_platform.yaml

@@ -0,0 +1,34 @@
+# config/data_platform.yaml
+data_paths:
+  daily_dir: /volume1/stock/A股数据/日线数据/daily
+  minute_15_dir: /volume1/stock/minute_kline/15min
+  vnpy_db: /volume1/stock/sanguo_vnpy/data/quant_trading.db
+  stock_list: /volume1/stock/A股数据/stock_info/stock_basic_info_raw_20260326_113530.csv
+
+data_sources:
+  daily:
+    - name: eastmoney
+      enabled: true
+      interval: 4.0
+    - name: baostock
+      enabled: true
+      interval: 0.0
+      timeout: 30
+    - name: tencent
+      enabled: true
+      interval: 0.0
+  minute_15:
+    - name: eastmoney
+      enabled: true
+      interval: 4.0
+
+validation:
+  price_positive: true
+  ohlc_consistency: true
+  no_future_dates: true
+
+performance:
+  request_interval: 0.3
+  max_retries: 3
+  fail_window: 100
+  fail_threshold: 0.8

sanguo_data/__init__.py

@@ -0,0 +1,3 @@
+# sanguo_data/__init__.py
+from .config import DataConfig, load_config
+__all__ = ["DataConfig", "load_config"]

sanguo_data/config.py

@@ -0,0 +1,20 @@
+# sanguo_data/config.py
+from dataclasses import dataclass
+import yaml
+
+@dataclass(frozen=True)
+class DataConfig:
+    data_paths: dict
+    data_sources: dict
+    validation: dict
+    performance: dict
+
+def load_config(path: str) -> DataConfig:
+    with open(path, "r", encoding="utf-8") as f:
+        raw = yaml.safe_load(f)
+    return DataConfig(
+        data_paths=raw.get("data_paths", {}),
+        data_sources=raw.get("data_sources", {}),
+        validation=raw.get("validation", {}),
+        performance=raw.get("performance", {}),
+    )

tests/data/__init__.py

@@ -0,0 +1 @@
+# tests/data/__init__.py

tests/data/test_config.py

@@ -0,0 +1,27 @@
+# tests/data/test_config.py
+from sanguo_data.config import load_config, DataConfig
+
+def test_load_config_returns_dataconfig(tmp_path):
+    yaml_content = """
+data_paths:
+  daily_dir: /tmp/daily
+  minute_15_dir: /tmp/15min
+  vnpy_db: /tmp/quant.db
+  stock_list: /tmp/stock.csv
+data_sources:
+  daily:
+    - name: eastmoney
+      enabled: true
+      interval: 4.0
+validation:
+  price_positive: true
+performance:
+  max_retries: 3
+"""
+    p = tmp_path / "config.yaml"
+    p.write_text(yaml_content)
+    cfg = load_config(str(p))
+    assert isinstance(cfg, DataConfig)
+    assert cfg.data_paths["daily_dir"] == "/tmp/daily"
+    assert cfg.data_sources["daily"][0]["name"] == "eastmoney"
+    assert cfg.performance["max_retries"] == 3