Backport PR #48167 on branch 1.4.x (BUG: DTI.intersection with DST transition) (#48189)

Backport PR #48167: BUG: DTI.intersection with DST transition

Co-authored-by: Matthew Roeschke <[email protected]>

Author: meeseeksmachine

doc/source/whatsnew/v1.4.4.rst

@@ -22,6 +22,7 @@ Fixed regressions
 - Fixed regression in :meth:`DataFrame.loc` not aligning index in some cases when setting a :class:`DataFrame` (:issue:`47578`)
 - Fixed regression in :meth:`DataFrame.loc` setting a length-1 array like value to a single value in the DataFrame (:issue:`46268`)
 - Fixed regression in setting ``None`` or non-string value into a ``string``-dtype Series using a mask (:issue:`47628`)
+- Fixed regression in :meth:`DatetimeIndex.intersection` when the :class:`DatetimeIndex` has dates crossing daylight savings time (:issue:`46702`)
 - Fixed regression in :func:`merge` throwing an error when passing a :class:`Series` with a multi-level name (:issue:`47946`)
 - Fixed regression in :meth:`DataFrame.eval` creating a copy when updating inplace (:issue:`47449`)
 -

pandas/_libs/tslibs/timezones.pxd

@@ -17,6 +17,6 @@ cpdef object get_timezone(tzinfo tz)
 cpdef tzinfo maybe_get_tz(object tz)
 
 cdef timedelta get_utcoffset(tzinfo tz, datetime obj)
-cdef bint is_fixed_offset(tzinfo tz)
+cpdef bint is_fixed_offset(tzinfo tz)
 
 cdef object get_dst_info(tzinfo tz)

pandas/_libs/tslibs/timezones.pyi

@@ -23,3 +23,4 @@ def get_dst_info(
 def maybe_get_tz(tz: str | int | np.int64 | tzinfo | None) -> tzinfo | None: ...
 def get_timezone(tz: tzinfo) -> tzinfo | str: ...
 def is_utc(tz: tzinfo | None) -> bool: ...
+def is_fixed_offset(tz: tzinfo) -> bool: ...

pandas/_libs/tslibs/timezones.pyx

@@ -198,7 +198,7 @@ cdef timedelta get_utcoffset(tzinfo tz, datetime obj):
         return tz.utcoffset(obj)
 
 
-cdef inline bint is_fixed_offset(tzinfo tz):
+cpdef inline bint is_fixed_offset(tzinfo tz):
     if treat_tz_as_dateutil(tz):
         if len(tz._trans_idx) == 0 and len(tz._trans_list) == 0:
             return 1

pandas/core/indexes/datetimes.py

@@ -383,6 +383,23 @@ def _formatter_func(self):
     # --------------------------------------------------------------------
     # Set Operation Methods
 
+    def _can_range_setop(self, other) -> bool:
+        # GH 46702: If self or other have non-UTC tzs, DST transitions prevent
+        # range representation due to no singular step
+        if (
+            self.tz is not None
+            and not timezones.is_utc(self.tz)
+            and not timezones.is_fixed_offset(self.tz)
+        ):
+            return False
+        if (
+            other.tz is not None
+            and not timezones.is_utc(other.tz)
+            and not timezones.is_fixed_offset(other.tz)
+        ):
+            return False
+        return super()._can_range_setop(other)
+
     def union_many(self, others):
         """
         A bit of a hack to accelerate unioning a collection of indexes.

pandas/tests/indexes/datetimes/test_setops.py

@@ -2,6 +2,7 @@
 
 import numpy as np
 import pytest
+import pytz
 
 import pandas.util._test_decorators as td
 
@@ -597,3 +598,14 @@ def test_intersection_bug(self):
         result = a.intersection(b)
         tm.assert_index_equal(result, b)
         assert result.freq == b.freq
+
+    @pytest.mark.parametrize(
+        "tz", [None, "UTC", "Europe/Berlin", pytz.FixedOffset(-60)]
+    )
+    def test_intersection_dst_transition(self, tz):
+        # GH 46702: Europe/Berlin has DST transition
+        idx1 = date_range("2020-03-27", periods=5, freq="D", tz=tz)
+        idx2 = date_range("2020-03-30", periods=5, freq="D", tz=tz)
+        result = idx1.intersection(idx2)
+        expected = date_range("2020-03-30", periods=2, freq="D", tz=tz)
+        tm.assert_index_equal(result, expected)