Difference between calamine and openpyxl readers fixed

pandas/io/excel/_calamine.py

@@ -10,8 +10,10 @@
     TYPE_CHECKING,
     Any,
     Union,
+    cast,
 )
 
+from pandas._typing import Scalar
 from pandas.compat._optional import import_optional_dependency
 from pandas.util._decorators import doc
 
@@ -28,13 +30,11 @@
 
     from pandas._typing import (
         FilePath,
-        NaTType,
         ReadBuffer,
-        Scalar,
         StorageOptions,
     )
 
-_CellValue = Union[int, float, str, bool, time, date, datetime, timedelta]
+_CellValueT = Union[int, float, str, bool, time, date, datetime, timedelta]
 
 
 class CalamineReader(BaseExcelReader["CalamineWorkbook"]):
@@ -75,8 +75,7 @@ def load_workbook(
         from python_calamine import load_workbook
 
         return load_workbook(
-            filepath_or_buffer,
-            **engine_kwargs,
+            filepath_or_buffer, **engine_kwargs  # type: ignore[arg-type]
         )
 
     @property
@@ -99,26 +98,31 @@ def get_sheet_by_index(self, index: int) -> CalamineSheet:
 
     def get_sheet_data(
         self, sheet: CalamineSheet, file_rows_needed: int | None = None
-    ) -> list[list[Scalar | NaTType | time]]:
-        def _convert_cell(value: _CellValue) -> Scalar | NaTType | time:
+    ) -> list[list[Scalar]]:
+        def _convert_cell(value: _CellValueT) -> Scalar:
+            # Avoid explicit conversion to pd.Timestamp and pd.Timedelta
             if isinstance(value, float):
                 val = int(value)
                 if val == value:
                     return val
                 else:
                     return value
             elif isinstance(value, date):
-                return pd.Timestamp(value)
+                return value
             elif isinstance(value, timedelta):
-                return pd.Timedelta(value)
-            elif isinstance(value, time):
                 return value
+            elif isinstance(value, time):
+                # cast needed here because Scalar doesn't include datetime.time
+                return cast(Scalar, value)
 
             return value
 
-        rows: list[list[_CellValue]] = sheet.to_python(
-            skip_empty_area=False, nrows=file_rows_needed
-        )
-        data = [[_convert_cell(cell) for cell in row] for row in rows]
+        rows: list[list[_CellValueT]] = sheet.to_python(skip_empty_area=False)
+        data: list[list[Scalar]] = []
+
+        for row in rows:
+            data.append([_convert_cell(cell) for cell in row])
+            if file_rows_needed is not None and len(data) >= file_rows_needed:
+                break
 
         return data