feat(data): DataFeed 多源 fallback + BaoStock 超时修复

2026-07-05 12:41:00 +08:00
parent 4e541040f1
commit 3015d6fa6b
2 changed files with 277 additions and 0 deletions
@@ -0,0 +1,49 @@
+# tests/data/test_datafeed.py
+import time
+import pandas as pd
+import pytest
+from unittest.mock import patch
+from sanguo_data.datafeed import fetch_with_fallback, _fetch_baostock_with_timeout
+
+def test_fetch_with_fallback_uses_second_when_first_fails():
+    df_good = pd.DataFrame({"date": ["2026-01-01"], "open": [10.0], "high": [11.0], "low": [9.0], "close": [10.5], "volume": [1000], "amount": [10000]})
+    with patch("sanguo_data.datafeed._fetch_eastmoney", side_effect=Exception("limit")), \
+         patch("sanguo_data.datafeed._fetch_baostock_with_timeout", return_value=df_good):
+        out = fetch_with_fallback("600000", "2026-01-01", "2026-01-02", ["eastmoney", "baostock"])
+    assert len(out) == 1
+    assert out["date"].iloc[0] == "2026-01-01"
+
+def test_baostock_timeout_does_not_hang():
+    """v1 卡死坑修复验证：超时必须返回，不能无限挂起"""
+    import sanguo_data.datafeed as df_module
+
+    # Save original worker
+    original_worker = df_module._baostock_worker
+
+    try:
+        # Replace with hanging worker (module-level function can be pickled)
+        df_module._baostock_worker = df_module._hanging_worker_for_test
+
+        start = time.time()
+        with pytest.raises(TimeoutError):
+            df_module._fetch_baostock_with_timeout("600000", "2026-01-01", "2026-01-02", timeout=2)
+        elapsed = time.time() - start
+        assert elapsed < 5, f"Timeout test took {elapsed:.2f}s, expected <5s"
+    finally:
+        # Restore original worker
+        df_module._baostock_worker = original_worker
+
+def test_fetch_with_fallback_all_sources_fail():
+    """所有源都失败时应该抛出异常"""
+    with patch("sanguo_data.datafeed._fetch_eastmoney", side_effect=Exception("em failed")), \
+         patch("sanguo_data.datafeed._fetch_baostock_with_timeout", side_effect=Exception("bs failed")):
+        with pytest.raises(RuntimeError, match="all sources failed"):
+            fetch_with_fallback("600000", "2026-01-01", "2026-01-02", ["eastmoney", "baostock"])
+
+def test_fetch_with_fallback_first_succeeds():
+    """第一个源成功时直接返回"""
+    df_good = pd.DataFrame({"date": ["2026-01-01"], "open": [10.0], "high": [11.0], "low": [9.0], "close": [10.5], "volume": [1000], "amount": [10000]})
+    with patch("sanguo_data.datafeed._fetch_eastmoney", return_value=df_good):
+        out = fetch_with_fallback("600000", "2026-01-01", "2026-01-02", ["eastmoney", "baostock"])
+    assert len(out) == 1
+    assert out["date"].iloc[0] == "2026-01-01"