FIX-#6637: Fix 'skiprows' parameter usage for 'read_excel' (#6638)

Signed-off-by: Anatoly Myachev <[email protected]>

modin/core/io/text/excel_dispatcher.py

@@ -59,6 +59,13 @@ def _read(cls, io, **kwargs):
                 **kwargs
             )
 
+        if kwargs.get("skiprows") is not None:
+            return cls.single_worker_read(
+                io,
+                reason="Modin doesn't support 'skiprows' parameter of `read_excel`",
+                **kwargs
+            )
+
         if isinstance(io, bytes):
             io = BytesIO(io)
 

modin/core/storage_formats/pandas/parsers.py

@@ -580,7 +580,6 @@ def parse(fname, **kwargs):
         num_splits = kwargs.pop("num_splits", None)
         start = kwargs.pop("start", None)
         end = kwargs.pop("end", None)
-        _skiprows = kwargs.pop("skiprows")
         excel_header = kwargs.get("_header")
         sheet_name = kwargs.get("sheet_name", 0)
         footer = b"</sheetData></worksheet>"
@@ -589,6 +588,8 @@ def parse(fname, **kwargs):
         if start is None or end is None:
             return pandas.read_excel(fname, **kwargs)
 
+        _skiprows = kwargs.pop("skiprows")
+
         import re
         from zipfile import ZipFile
 

modin/pandas/test/test_io.py

@@ -2197,6 +2197,17 @@ def test_read_excel(self, pathlike, make_excel_file):
             io=Path(unique_filename) if pathlike else unique_filename,
         )
 
+    @check_file_leaks
+    @pytest.mark.parametrize("skiprows", [2, [1, 3], lambda x: x in [0, 2]])
+    def test_read_excel_skiprows(self, skiprows, make_excel_file):
+        eval_io(
+            fn_name="read_excel",
+            # read_excel kwargs
+            io=make_excel_file(),
+            skiprows=skiprows,
+            check_kwargs_callable=False,
+        )
+
     @check_file_leaks
     @pytest.mark.parametrize(
         "dtype_backend", [lib.no_default, "numpy_nullable", "pyarrow"]