BUG: fix parsing of ODF time values with comments

doc/source/whatsnew/v2.2.0.rst

@@ -282,6 +282,7 @@ Bug fixes
 - Bug in :func:`pandas.api.types.is_string_dtype` while checking object array with no elements is of the string dtype (:issue:`54661`)
 - Bug in :meth:`DataFrame.apply` where passing ``raw=True`` ignored ``args`` passed to the applied function (:issue:`55009`)
 - Bug in :meth:`pandas.DataFrame.melt` where it would not preserve the datetime (:issue:`55254`)
+- Bug in :meth:`pandas.read_excel` where ODS files with comments on time value cells failed to parse (:issue:`55200`)
 - Bug in :meth:`pandas.read_excel` with a ODS file without cached formatted cell for float values (:issue:`55219`)
 
 Categorical

pandas/io/excel/_odfreader.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+import datetime
+import re
 from typing import (
     TYPE_CHECKING,
     cast,
@@ -26,6 +28,12 @@
 
     from pandas._libs.tslibs.nattype import NaTType
 
+# ODF variant of ISO 8601 time/duration format: "PThhhHmmMss.sssS"
+# see https://www.w3.org/TR/xmlschema-2/#duration for details
+ODF_ISOTIME_PATTERN = re.compile(
+    r"^\s*PT\s*(\d+)\s*H\s*(\d+)\s*M\s*(\d+)(\.(\d+))?\s*S$"
+)
+
 
 @doc(storage_options=_shared_docs["storage_options"])
 class ODFReader(BaseExcelReader["OpenDocument"]):
@@ -214,9 +222,9 @@ def _get_cell_value(self, cell) -> Scalar | NaTType:
             cell_value = cell.attributes.get((OFFICENS, "date-value"))
             return pd.Timestamp(cell_value)
         elif cell_type == "time":
-            stamp = pd.Timestamp(str(cell))
+            stamp = self._get_cell_time_value(cell)
             # cast needed here because Scalar doesn't include datetime.time
-            return cast(Scalar, stamp.time())
+            return cast(Scalar, stamp)
         else:
             self.close()
             raise ValueError(f"Unrecognized type {cell_type}")
@@ -247,3 +255,28 @@ def _get_cell_string_value(self, cell) -> str:
             else:
                 value.append(str(fragment).strip("\n"))
         return "".join(value)
+
+    def _get_cell_time_value(self, cell) -> datetime.time:
+        """
+        This helper function parses ODF time value
+        """
+        from odf.namespaces import OFFICENS
+
+        value = cell.attributes.get((OFFICENS, "time-value"))
+        parts = ODF_ISOTIME_PATTERN.match(value)
+        if parts is None:
+            raise ValueError(f"Failed to parse ODF time value: {value}")
+        hours, minutes, seconds, _, second_part = parts.group(*range(1, 6))
+        if second_part is None:
+            microseconds = 0
+        else:
+            microseconds = int(int(second_part) * pow(10, 6 - len(second_part)))
+
+        return datetime.time(
+            # ignore date part from some representations
+            # and datetime.time restrict hour values to 0..23
+            hour=int(hours) % 24,
+            minute=int(minutes),
+            second=int(seconds),
+            microsecond=microseconds,
+        )

pandas/tests/io/excel/test_readers.py

@@ -1014,6 +1014,11 @@ def test_reader_seconds(self, request, engine, read_ext):
         actual = pd.read_excel("times_1904" + read_ext, sheet_name="Sheet1")
         tm.assert_frame_equal(actual, expected)
 
+        if read_ext == ".ods":
+            msg = "Failed to parse ODF time value: PT01H5a2M00S"
+            with pytest.raises(ValueError, match=msg):
+                pd.read_excel("test_corrupted_time" + read_ext)
+
     def test_read_excel_multiindex(self, request, engine, read_ext):
         # see gh-4679
         if engine == "pyxlsb":