Remove filetype compatibility check for ExcelFile. Remove whatsnew entry. Clarifications in the ExcelFile and read_excel docs.

Author: miguelmarques1904

doc/source/whatsnew/v1.1.0.rst

@@ -236,7 +236,6 @@ Other enhancements
   and :class:`~pandas.io.stata.StataWriterUTF8` (:issue:`26599`).
 - :meth:`HDFStore.put` now accepts `track_times` parameter. Parameter is passed to ``create_table`` method of ``PyTables`` (:issue:`32682`).
 - Make :class:`pandas.core.window.Rolling` and :class:`pandas.core.window.Expanding` iterable（:issue:`11704`)
-- :meth:`read_excel` now checks if the engine passed as an argument can process the file provided and outputs a suggestion if it cannot (:issue:`34237`).
 
 .. ---------------------------------------------------------------------------
 

pandas/io/excel/_base.py

@@ -103,12 +103,12 @@
     of dtype conversion.
 engine : str, default None
     If io is not a buffer or path, this must be set to identify io.
-    Acceptable values are None, "auto", "xlrd", "openpyxl", "odf", or "pyxlsb".
+    Acceptable values are None, "xlrd", "openpyxl", "odf", or "pyxlsb".
     File compatibility:
-    "xlrd" engine supports .xls, .xlsx, and .xlsm files.
-    "openpyxl" engine supports .xlsx, and .xlsm files.
-    "odf" engine supports .odf, .ods, and .odt files.
-    "pyxlsb" engine supports .xlsb files.
+    "xlrd" supports most old/new Excel file formats.
+    "openpyxl" engine supports newer Excel file formats.
+    "odf" engine supports OpenDocument file formats (.odf, .ods, .odt).
+    "pyxlsb" engine supports Binary Excel files.
 converters : dict, default None
     Dict of functions for converting values in certain columns. Keys can
     either be integers or column labels, values are functions that take one
@@ -789,23 +789,23 @@ def close(self):
 class ExcelFile:
     """
     Class for parsing tabular excel sheets into DataFrame objects.
-    Uses xlrd. See read_excel for more documentation
+    Uses xlrd by default. See read_excel for more documentation
 
     Parameters
     ----------
     io : str, path object (pathlib.Path or py._path.local.LocalPath),
         a file-like object, xlrd workbook or openpypl workbook.
         If a string or path object, expected to be a path to a
-        .xls, .xlsx, .xlsb, .xlsm, .xltx, .xltm or .odf file.
+        .xls, .xlsx, .xlsb, .xlsm, .odf, .ods, or .odt file.
     engine : str, default None
         If io is not a buffer or path, this must be set to identify io.
-        Acceptable values are None, ``auto``, ``xlrd``, ``openpyxl``,
+        Acceptable values are None, ``xlrd``, ``openpyxl``,
         ``odf``, or ``pyxlsb``.
         File compatibility:
-        ``xlrd`` engine supports .xls, .xlsx, and .xlsm files.
-        ``openpyxl`` engine supports .xlsx, and .xlsm files.
-        ``odf`` engine supports .odf, .ods, and .odt files.
-        ``pyxlsb`` engine supports .xlsb files.
+        ``xlrd`` supports most old/new Excel file formats.
+        ``openpyxl`` engine supports newer Excel file formats.
+        ``odf`` engine supports OpenDocument file formats (.odf, .ods, .odt).
+        ``pyxlsb`` engine supports Binary Excel files.
     """
 
     from pandas.io.excel._odfreader import _ODFReader
@@ -820,15 +820,6 @@ class ExcelFile:
         "pyxlsb": _PyxlsbReader,
     }
 
-    # Excel templates are not supported by read_excel according to the
-    #  documentation, but openpyxl specifies them as supported.
-    _supported_engine_filetypes = {
-        "xlrd": ["xls", "xlsx", "xlsm"],
-        "openpyxl": ["xlsx", "xlsm", "xltx", "xltm"],
-        "odf": ["odf", "ods", "odt"],
-        "pyxlsb": ["xlsb"],
-    }
-
     def __init__(self, io, engine=None):
         if engine is None:
             engine = "xlrd"
@@ -837,11 +828,7 @@ def __init__(self, io, engine=None):
 
         self.engine = engine
 
-        # 'io' could be a str, ExcelFile, Book, etc.
-        if isinstance(io, str):
-            # Check engine-extension compatibility
-            ext = os.path.splitext(io)[-1][1:]
-            self.check_extension(engine, ext)
+        # Could be a str, ExcelFile, Book, etc.
         self.io = io
         # Always a string
         self._io = stringify_path(io)
@@ -921,32 +908,6 @@ def book(self):
     def sheet_names(self):
         return self._reader.sheet_names
 
-    @classmethod
-    def check_extension(cls, engine, ext):
-        """
-        checks that the provided path's extension is supported by the reader engine.
-        If it isn't supported, raises a ValueError.
-        """
-        if ext.startswith("."):
-            ext = ext[1:]
-        if ext not in cls._supported_engine_filetypes.get(engine):
-            supporting_engines = [
-                k for k, v in cls._supported_engine_filetypes.items() if ext in v
-            ]
-            if not supporting_engines:
-                eng_info = " No engines currently support the provided file extension."
-            else:
-                eng_info = (
-                    " Use engine(s) "
-                    + ", ".join("'{0}'".format(e) for e in supporting_engines)
-                    + " instead."
-                )
-            raise ValueError(
-                f"Unsupported extension for engine '{engine}': '.{ext}'." + eng_info
-            )
-        else:
-            return True
-
     def close(self):
         """close io if necessary"""
         self._reader.close()