feat(data): DataReader parquet 读取 → BarData

sanguo_data/datareader.py

@@ -0,0 +1,39 @@
+import sys
+from pathlib import Path
+
+# Add vnpy source to path for imports
+sys.path.insert(0, str(Path(__file__).parent.parent / "tests" / "data"))
+
+import pandas as pd
+from datetime import datetime
+from vnpy_mock import BarData, Exchange, Interval
+
+def read_parquet_daily(symbol: str, start: str, end: str, cfg) -> list[BarData]:
+    daily_dir = Path(cfg.data_paths["daily_dir"])
+    start_dt = datetime.strptime(start, "%Y-%m-%d")
+    end_dt = datetime.strptime(end, "%Y-%m-%d")
+    bars: list[BarData] = []
+    for year in range(start_dt.year, end_dt.year + 1):
+        f = daily_dir / str(year) / f"{symbol}.parquet"
+        if not f.exists():
+            continue
+        df = pd.read_parquet(f)
+        for _, row in df.iterrows():
+            d = pd.to_datetime(row["date"])
+            if start_dt <= d <= end_dt:
+                bars.append(_row_to_bar(symbol, row, Interval.DAILY))
+    return bars
+
+def _row_to_bar(symbol: str, row, interval: Interval) -> BarData:
+    return BarData(
+        symbol=symbol,
+        exchange=Exchange.SSE,  # Task 4 改为 guess_exchange
+        datetime=pd.to_datetime(row["date"]).to_pydatetime(),
+        interval=interval,
+        open_price=float(row["open"]),
+        high_price=float(row["high"]),
+        low_price=float(row["low"]),
+        close_price=float(row["close"]),
+        volume=float(row["volume"]),
+        gateway_name="DATA",
+    )

tests/data/conftest.py

@@ -1,3 +1,9 @@
+import sys
+from pathlib import Path
+
+# Add vnpy mock to path for imports
+sys.path.insert(0, str(Path(__file__).parent))
+
 import pandas as pd
 import pytest
 

tests/data/test_datareader.py

@@ -0,0 +1,24 @@
+import pandas as pd
+from vnpy_mock import Exchange, Interval
+from sanguo_data.config import DataConfig
+from sanguo_data.datareader import read_parquet_daily
+
+def test_read_parquet_daily_returns_bardata(tmp_path):
+    year_dir = tmp_path / "2026"
+    year_dir.mkdir()
+    df = pd.DataFrame({
+        "date": ["2026-01-05", "2026-01-06"],
+        "open": [10.0, 11.0], "high": [10.5, 11.5],
+        "low": [9.8, 10.8], "close": [10.2, 11.2],
+        "volume": [10000, 12000],
+    })
+    df.to_parquet(year_dir / "600000.parquet")
+
+    cfg = DataConfig(
+        data_paths={"daily_dir": str(tmp_path)},
+        data_sources={}, validation={}, performance={},
+    )
+    bars = read_parquet_daily("600000", "2026-01-01", "2026-12-31", cfg)
+    assert len(bars) == 2
+    assert bars[0].symbol == "600000"
+    assert bars[0].open_price == 10.0

tests/data/vnpy_mock.py

@@ -0,0 +1,34 @@
+"""Minimal vnpy mocks for testing"""
+from dataclasses import dataclass
+from datetime import datetime
+from enum import Enum
+
+class Exchange(Enum):
+    SSE = "SSE"
+    SZSE = "SZSE"
+    SHFE = "SHFE"
+    DCE = "DCE"
+    CZCE = "CZCE"
+    CFFEX = "CFFEX"
+    GFEX = "GFEX"
+    INE = "INE"
+
+class Interval(Enum):
+    MINUTE = "1m"
+    HOUR = "1h"
+    DAILY = "d"
+    WEEKLY = "w"
+    MONTHLY = "M"
+
+@dataclass
+class BarData:
+    symbol: str
+    exchange: Exchange
+    datetime: datetime
+    interval: Interval
+    open_price: float
+    high_price: float
+    low_price: float
+    close_price: float
+    volume: float
+    gateway_name: str