fix(python): Ensure NoDataError raised consistently between engines…

… for Excel reads (#19712)

py-polars/polars/io/spreadsheet/functions.py

@@ -776,7 +776,7 @@ def _drop_null_data(
 
     If `drop_empty_rows` is set to `False`, empty rows are not dropped.
     """
-    null_cols = []
+    null_cols: list[str] = []
     for col_name in df.columns:
         # note that if multiple unnamed columns are found then all but the first one
         # will be named as "_duplicated_{n}" (or "__UNNAMED__{n}" from calamine)
@@ -955,15 +955,15 @@ def _read_spreadsheet_calamine(
         ):
             df.columns = [f"column_{i}" for i in range(1, len(df.columns) + 1)]
 
+    df = _drop_null_data(
+        df, raise_if_empty=raise_if_empty, drop_empty_rows=drop_empty_rows
+    )
+
     # note: even if we applied parser dtypes we still re-apply schema_overrides
     # natively as we can refine integer/float types, temporal precision, etc.
     if schema_overrides:
         df = df.cast(dtypes=schema_overrides)
 
-    df = _drop_null_data(
-        df, raise_if_empty=raise_if_empty, drop_empty_rows=drop_empty_rows
-    )
-
     # standardise on string dtype for null columns in empty frame
     if df.is_empty():
         df = df.cast({Null: String})

py-polars/tests/unit/io/test_spreadsheet.py

@@ -18,7 +18,7 @@
     from collections.abc import Sequence
     from pathlib import Path
 
-    from polars._typing import ExcelSpreadsheetEngine, SelectorType
+    from polars._typing import ExcelSpreadsheetEngine, SchemaDict, SelectorType
 
 # pytestmark = pytest.mark.slow()
 
@@ -918,24 +918,31 @@ def test_excel_freeze_panes() -> None:
 
 
 @pytest.mark.parametrize(
-    ("read_spreadsheet", "source"),
+    ("read_spreadsheet", "source", "schema_overrides"),
     [
-        (pl.read_excel, "path_xlsx_empty"),
-        (pl.read_excel, "path_xlsb_empty"),
-        (pl.read_excel, "path_xls_empty"),
-        (pl.read_ods, "path_ods_empty"),
+        (pl.read_excel, "path_xlsx_empty", None),
+        (pl.read_excel, "path_xlsb_empty", None),
+        (pl.read_excel, "path_xls_empty", None),
+        (pl.read_ods, "path_ods_empty", None),
+        # Test with schema overrides, to ensure they don't interfere with
+        # raising NoDataErrors.
+        (pl.read_excel, "path_xlsx_empty", {"a": pl.Int64}),
+        (pl.read_excel, "path_xlsb_empty", {"a": pl.Int64}),
+        (pl.read_excel, "path_xls_empty", {"a": pl.Int64}),
+        (pl.read_ods, "path_ods_empty", {"a": pl.Int64}),
     ],
 )
 def test_excel_empty_sheet(
     read_spreadsheet: Callable[..., pl.DataFrame],
     source: str,
     request: pytest.FixtureRequest,
+    schema_overrides: SchemaDict | None,
 ) -> None:
     ods = (empty_spreadsheet_path := request.getfixturevalue(source)).suffix == ".ods"
     read_spreadsheet = pl.read_ods if ods else pl.read_excel  # type: ignore[assignment]
 
     with pytest.raises(NoDataError, match="empty Excel sheet"):
-        read_spreadsheet(empty_spreadsheet_path)
+        read_spreadsheet(empty_spreadsheet_path, schema_overrides=schema_overrides)
 
     engine_params = [{}] if ods else [{"engine": "calamine"}]
     for params in engine_params: