Merge PR #714

agent/src/tools/trade_journal_parsers.py

@@ -162,8 +162,22 @@ def _normalize_side(raw: Any) -> str:
     raise ValueError(f"Unsupported trade side: {raw!r}")
 
 
+def _is_empty_code(raw: Any) -> bool:
+    """True for None/NaN/blank securities codes from CSV/Excel cells."""
+    if raw is None:
+        return True
+    try:
+        if pd.isna(raw):
+            return True
+    except (TypeError, ValueError):
+        pass
+    return not str(raw).strip()
+
+
 def _qualify_a_share(code: str) -> str:
     """Append .SH/.SZ/.BJ suffix to a bare A-share ticker."""
+    if _is_empty_code(code):
+        raise ValueError("empty securities code")
     code = str(code).strip().zfill(6)
     if "." in code:
         return code.upper()
@@ -193,13 +207,16 @@ def parse_tonghuashun(df: pd.DataFrame) -> list[TradeRecord]:
     """
     records: list[TradeRecord] = []
     for _, row in df.iterrows():
+        raw_code = row.get("证券代码", "")
+        if _is_empty_code(raw_code):
+            continue
         qty = _to_float(row.get("成交数量"))
         price = _to_float(row.get("成交价格"))
         amount = _to_float(row.get("成交金额")) or qty * price
         fee = _to_float(row.get("手续费")) + _to_float(row.get("印花税")) + _to_float(row.get("过户费"))
         records.append(TradeRecord(
             datetime=str(row.get("成交时间", "")).strip(),
-            symbol=_qualify_a_share(row.get("证券代码", "")),
+            symbol=_qualify_a_share(raw_code),
             name=str(row.get("证券名称", "")).strip(),
             side=_normalize_side(row.get("操作")),
             quantity=qty,
@@ -219,6 +236,9 @@ def parse_eastmoney(df: pd.DataFrame) -> list[TradeRecord]:
     """
     records: list[TradeRecord] = []
     for _, row in df.iterrows():
+        raw_code = row.get("股票代码", "")
+        if _is_empty_code(raw_code):
+            continue
         raw_date = str(row.get("成交日期", "")).strip()
         raw_time = str(row.get("成交时间", "")).strip()
         if len(raw_date) == 8 and raw_date.isdigit():
@@ -232,7 +252,7 @@ def parse_eastmoney(df: pd.DataFrame) -> list[TradeRecord]:
         fee = _to_float(row.get("佣金")) + _to_float(row.get("印花税"))
         records.append(TradeRecord(
             datetime=dt,
-            symbol=_qualify_a_share(row.get("股票代码", "")),
+            symbol=_qualify_a_share(raw_code),
             name=str(row.get("股票名称", "")).strip(),
             side=_normalize_side(row.get("买卖标志")),
             quantity=qty,

agent/tests/test_trade_journal.py

@@ -19,6 +19,8 @@ from src.tools.trade_journal_parsers import (
     _infer_market_from_symbol,
     _normalize_side,
     _qualify_a_share,
+    parse_tonghuashun,
+    parse_eastmoney,
     detect_format,
     parse_file,
     records_to_dataframe,
@@ -506,3 +508,60 @@ def test_analyze_with_filter(allow_tmp: Path) -> None:
     assert result["status"] == "ok"
     assert result["total_records"] == 1
     assert result["filter_applied"] == "symbol=AAPL"
+
+
+def test_qualify_a_share_rejects_empty() -> None:
+    with pytest.raises(ValueError, match="empty"):
+        _qualify_a_share("")
+    with pytest.raises(ValueError, match="empty"):
+        _qualify_a_share("   ")
+
+
+def test_parse_tonghuashun_skips_blank_code_rows() -> None:
+    df = pd.DataFrame([{
+        "成交时间": "2024-01-01 10:00:00", "证券代码": "", "证券名称": "",
+        "操作": "买入", "成交数量": 100, "成交价格": 10.0, "成交金额": 1000,
+        "手续费": 0, "印花税": 0, "过户费": 0,
+    }, {
+        "成交时间": "2024-01-01 10:01:00", "证券代码": "600519", "证券名称": "茅台",
+        "操作": "买入", "成交数量": 100, "成交价格": 10.0, "成交金额": 1000,
+        "手续费": 0, "印花税": 0, "过户费": 0,
+    }])
+    rec = parse_tonghuashun(df)
+    assert len(rec) == 1
+    assert rec[0].symbol == "600519.SH"
+
+
+def test_qualify_a_share_rejects_nan() -> None:
+    with pytest.raises(ValueError, match="empty"):
+        _qualify_a_share(float("nan"))
+
+
+def test_parse_tonghuashun_skips_nan_code_rows() -> None:
+    df = pd.DataFrame([{
+        "成交时间": "2024-01-01 10:00:00", "证券代码": float("nan"), "证券名称": "",
+        "操作": "买入", "成交数量": 100, "成交价格": 10.0, "成交金额": 1000,
+        "手续费": 0, "印花税": 0, "过户费": 0,
+    }, {
+        "成交时间": "2024-01-01 10:01:00", "证券代码": "600519", "证券名称": "茅台",
+        "操作": "买入", "成交数量": 100, "成交价格": 10.0, "成交金额": 1000,
+        "手续费": 0, "印花税": 0, "过户费": 0,
+    }])
+    rec = parse_tonghuashun(df)
+    assert len(rec) == 1
+    assert rec[0].symbol == "600519.SH"
+
+
+def test_parse_eastmoney_skips_nan_code_rows() -> None:
+    df = pd.DataFrame([{
+        "成交日期": "20240101", "成交时间": "10:00:00", "股票代码": float("nan"),
+        "股票名称": "", "买卖标志": "B", "成交数量": 100, "成交均价": 10.0,
+        "成交金额": 1000, "佣金": 0, "印花税": 0,
+    }, {
+        "成交日期": "20240101", "成交时间": "10:01:00", "股票代码": "000001",
+        "股票名称": "平安", "买卖标志": "B", "成交数量": 100, "成交均价": 10.0,
+        "成交金额": 1000, "佣金": 0, "印花税": 0,
+    }])
+    rec = parse_eastmoney(df)
+    assert len(rec) == 1
+    assert rec[0].symbol == "000001.SZ"