Backport PR #32544: BUG: pd.ExcelFile closes stream on destruction (#32657)

Co-authored-by: Robert de Vries <[email protected]>

Author: meeseeksmachine

doc/source/whatsnew/v1.0.2.rst

@@ -29,6 +29,7 @@ Fixed regressions
 - Fixed regression in the repr of an object-dtype :class:`Index` with bools and missing values (:issue:`32146`)
 - Fixed regression in :meth:`read_csv` in which the ``encoding`` option was not recognized with certain file-like objects (:issue:`31819`)
 - Fixed regression in :meth:`DataFrame.reindex` and :meth:`Series.reindex` when reindexing with (tz-aware) index and ``method=nearest`` (:issue:`26683`)
+- Fixed regression in :class:`ExcelFile` where the stream passed into the function was closed by the destructor. (:issue:`31467`)
 - Fixed regression in :meth:`DataFrame.reindex_like` on a :class:`DataFrame` subclass raised an  ``AssertionError`` (:issue:`31925`)
 - Fixed regression in :meth:`Series.shift` with ``datetime64`` dtype when passing an integer ``fill_value`` (:issue:`32591`)
 

pandas/io/excel/_base.py

@@ -367,6 +367,9 @@ def _workbook_class(self):
     def load_workbook(self, filepath_or_buffer):
         pass
 
+    def close(self):
+        pass
+
     @property
     @abc.abstractmethod
     def sheet_names(self):
@@ -895,14 +898,7 @@ def sheet_names(self):
 
     def close(self):
         """close io if necessary"""
-        if self.engine == "openpyxl":
-            # https://stackoverflow.com/questions/31416842/
-            #  openpyxl-does-not-close-excel-workbook-in-read-only-mode
-            wb = self.book
-            wb._archive.close()
-
-        if hasattr(self.io, "close"):
-            self.io.close()
+        self._reader.close()
 
     def __enter__(self):
         return self

pandas/io/excel/_openpyxl.py

@@ -497,6 +497,11 @@ def load_workbook(self, filepath_or_buffer: FilePathOrBuffer):
             filepath_or_buffer, read_only=True, data_only=True, keep_links=False
         )
 
+    def close(self):
+        # https://stackoverflow.com/questions/31416842/
+        #  openpyxl-does-not-close-excel-workbook-in-read-only-mode
+        self.book.close()
+
     @property
     def sheet_names(self) -> List[str]:
         return self.book.sheetnames

pandas/tests/io/excel/test_readers.py

@@ -628,6 +628,17 @@ def test_read_from_py_localpath(self, read_ext):
 
         tm.assert_frame_equal(expected, actual)
 
+    @td.check_file_leaks
+    def test_close_from_py_localpath(self, read_ext):
+
+        # GH31467
+        str_path = os.path.join("test1" + read_ext)
+        with open(str_path, "rb") as f:
+            x = pd.read_excel(f, "Sheet1", index_col=0)
+            del x
+            # should not throw an exception because the passed file was closed
+            f.read()
+
     def test_reader_seconds(self, read_ext):
         if pd.read_excel.keywords["engine"] == "pyxlsb":
             pytest.xfail("Sheets containing datetimes not supported by pyxlsb")
@@ -1019,10 +1030,10 @@ def test_excel_read_buffer(self, engine, read_ext):
         tm.assert_frame_equal(expected, actual)
 
     def test_reader_closes_file(self, engine, read_ext):
-        f = open("test1" + read_ext, "rb")
-        with pd.ExcelFile(f) as xlsx:
-            # parses okay
-            pd.read_excel(xlsx, "Sheet1", index_col=0, engine=engine)
+        with open("test1" + read_ext, "rb") as f:
+            with pd.ExcelFile(f) as xlsx:
+                # parses okay
+                pd.read_excel(xlsx, "Sheet1", index_col=0, engine=engine)
 
         assert f.closed