Bug: Fix for overflow at edge cases in normalize() by raising exception

doc/source/whatsnew/v3.0.0.rst

@@ -640,6 +640,7 @@ Datetimelike
 - Bug in :attr:`is_year_start` where a DateTimeIndex constructed via a date_range with frequency 'MS' wouldn't have the correct year or quarter start attributes (:issue:`57377`)
 - Bug in :class:`DataFrame` raising ``ValueError`` when ``dtype`` is ``timedelta64`` and ``data`` is a list containing ``None`` (:issue:`60064`)
 - Bug in :class:`Timestamp` constructor failing to raise when ``tz=None`` is explicitly specified in conjunction with timezone-aware ``tzinfo`` or data (:issue:`48688`)
+- Bug in :class:`Timestamp` where :meth:`normalize` overflows at edge cases without raising an exception (:issue:`60583`)
 - Bug in :func:`date_range` where the last valid timestamp would sometimes not be produced (:issue:`56134`)
 - Bug in :func:`date_range` where using a negative frequency value would not include all points between the start and end values (:issue:`56147`)
 - Bug in :func:`tseries.api.guess_datetime_format` would fail to infer time format when "%Y" == "%H%M" (:issue:`57452`)

pandas/_libs/tslibs/timestamps.pyx

@@ -1269,7 +1269,7 @@ cdef class _Timestamp(ABCTimestamp):
  int64_t ppd = periods_per_day(self._creso)
  _Timestamp ts
 
- normalized = normalize_i8_stamp(local_val, ppd)
+ normalized = normalize_i8_stamp(self, local_val, ppd)
  ts = type(self)._from_value_and_reso(normalized, reso=self._creso, tz=None)
  return ts.tz_localize(self.tzinfo)
 
@@ -3438,9 +3438,9 @@ Timestamp.daysinmonth = Timestamp.days_in_month
 # ----------------------------------------------------------------------
 # Scalar analogues to functions in vectorized.pyx
 
-
+@cython.overflowcheck(True)
 @cython.cdivision(False)
-cdef int64_t normalize_i8_stamp(int64_t local_val, int64_t ppd) noexcept nogil:
+def normalize_i8_stamp(self, int64_t local_val, int64_t ppd):
  """
  Round the localized nanosecond timestamp down to the previous midnight.
 
@@ -3454,4 +3454,15 @@ cdef int64_t normalize_i8_stamp(int64_t local_val, int64_t ppd) noexcept nogil:
  -------
  int64_t
  """
- return local_val - (local_val % ppd)
+ cdef:
+ int64_t remainder
+ int64_t result
+ try:
+ remainder = local_val % ppd
+ result = local_val - remainder
+ except (OverflowError, OutOfBoundsDatetime) as err:
+ raise OutOfBoundsDatetime(
+ f"Cannot normalize {self} to midnight without overflow"
+ ) from err
+
+ return result

pandas/tests/scalar/timestamp/methods/test_normalize.py

@@ -2,6 +2,7 @@
 
 from pandas._libs.tslibs import Timestamp
 from pandas._libs.tslibs.dtypes import NpyDatetimeUnit
+from pandas._libs.tslibs.np_datetime import OutOfBoundsDatetime
 
 
 class TestTimestampNormalize:
@@ -19,3 +20,16 @@ def test_normalize_pre_epoch_dates(self):
  result = Timestamp("1969-01-01 09:00:00").normalize()
  expected = Timestamp("1969-01-01 00:00:00")
  assert result == expected
+
+ def test_normalize_edge_cases(self):
+ # GH: 60583
+ expected_msg = (
+ r"Cannot normalize 1677-09-21 00:12:43\.145224193 to midnight "
+ "without overflow"
+ )
+ with pytest.raises(OutOfBoundsDatetime, match=expected_msg):
+ Timestamp.min.normalize()
+
+ result = Timestamp.max.normalize()
+ excepted = Timestamp("2262-04-11 00:00:00")
+ assert result == excepted