Backport PR #39605: REGR: appending to existing excel file created corrupt files (#39659)

Co-authored-by: Torsten Wörtwein <[email protected]>

Author: simonjayhawkins

doc/source/whatsnew/v1.2.2.rst

@@ -21,6 +21,7 @@ Fixed regressions
 - Fixed regression in :meth:`~DataFrame.to_pickle` failing to create bz2/xz compressed pickle files with ``protocol=5`` (:issue:`39002`)
 - Fixed regression in :func:`pandas.testing.assert_series_equal` and :func:`pandas.testing.assert_frame_equal` always raising ``AssertionError`` when comparing extension dtypes (:issue:`39410`)
 - Fixed regression in :meth:`~DataFrame.to_csv` opening ``codecs.StreamWriter`` in binary mode instead of in text mode and ignoring user-provided ``mode`` (:issue:`39247`)
+- Fixed regression in :meth:`~DataFrame.to_excel` creating corrupt files when appending (``mode="a"``) to an existing file (:issue:`39576`)
 - Fixed regression in :meth:`DataFrame.transform` failing in case of an empty DataFrame or Series (:issue:`39636`)
 - Fixed regression in :meth:`core.window.rolling.Rolling.count` where the ``min_periods`` argument would be set to ``0`` after the operation (:issue:`39554`)
 - Fixed regression in :func:`read_excel` that incorrectly raised when the argument ``io`` was a non-path and non-buffer and the ``engine`` argument was specified (:issue:`39528`)

pandas/io/excel/_openpyxl.py

@@ -1,4 +1,5 @@
 from distutils.version import LooseVersion
+import mmap
 from typing import TYPE_CHECKING, Dict, List, Optional
 
 import numpy as np
@@ -38,6 +39,7 @@ def __init__(
             from openpyxl import load_workbook
 
             self.book = load_workbook(self.handles.handle)
+            self.handles.handle.seek(0)
         else:
             # Create workbook object with default optimized_write=True.
             self.book = Workbook()
@@ -50,6 +52,9 @@ def save(self):
         Save workbook to disk.
         """
         self.book.save(self.handles.handle)
+        if "r+" in self.mode and not isinstance(self.handles.handle, mmap.mmap):
+            # truncate file to the written content
+            self.handles.handle.truncate()
 
     @classmethod
     def _convert_to_style_kwargs(cls, style_dict: dict) -> Dict[str, "Serialisable"]:

pandas/tests/io/excel/test_openpyxl.py

@@ -1,4 +1,5 @@
 from distutils.version import LooseVersion
+from pathlib import Path
 
 import numpy as np
 import pytest
@@ -169,3 +170,22 @@ def test_read_with_bad_dimension(
         wb.close()
     expected = DataFrame(expected_data)
     tm.assert_frame_equal(result, expected)
+
+
+def test_append_mode_file(ext):
+    # GH 39576
+    df = DataFrame()
+
+    with tm.ensure_clean(ext) as f:
+        df.to_excel(f, engine="openpyxl")
+
+        with ExcelWriter(f, mode="a", engine="openpyxl") as writer:
+            df.to_excel(writer)
+
+        # make sure that zip files are not concatenated by making sure that
+        # "docProps/app.xml" only occurs twice in the file
+        data = Path(f).read_bytes()
+        first = data.find(b"docProps/app.xml")
+        second = data.find(b"docProps/app.xml", first + 1)
+        third = data.find(b"docProps/app.xml", second + 1)
+        assert second != -1 and third == -1