BUG: Bad shift_forward around UTC+0 when DST (#56017)

* add tests * fix * add whatsnew * refactor * Revert "refactor" This reverts commit 4482dd8. * fix bug * update * more cmt
pandas-dev · Nov 21, 2023 · df6a323 · df6a323
1 parent 1e1f53c
commit df6a323
Show file tree

Hide file tree

Showing 3 changed files with 46 additions and 3 deletions.
diff --git a/doc/source/whatsnew/v2.2.0.rst b/doc/source/whatsnew/v2.2.0.rst
@@ -381,7 +381,7 @@ Timezones
 ^^^^^^^^^
 - Bug in :class:`AbstractHolidayCalendar` where timezone data was not propagated when computing holiday observances (:issue:`54580`)
 - Bug in :class:`Timestamp` construction with an ambiguous value and a ``pytz`` timezone failing to raise ``pytz.AmbiguousTimeError`` (:issue:`55657`)
--
+- Bug in :meth:`Timestamp.tz_localize` with ``nonexistent="shift_forward`` around UTC+0 during DST (:issue:`51501`)
 
 Numeric
 ^^^^^^^

diff --git a/pandas/_libs/tslibs/tzconversion.pyx b/pandas/_libs/tslibs/tzconversion.pyx
@@ -416,8 +416,13 @@ timedelta-like}
 
                 else:
                     delta_idx = bisect_right_i8(info.tdata, new_local, info.ntrans)
-
-                    delta_idx = delta_idx - delta_idx_offset
+                    # Logic similar to the precompute section. But check the current
+                    # delta in case we are moving between UTC+0 and non-zero timezone
+                    if (shift_forward or shift_delta > 0) and \
+                       info.deltas[delta_idx - 1] >= 0:
+                        delta_idx = delta_idx - 1
+                    else:
+                        delta_idx = delta_idx - delta_idx_offset
                     result[i] = new_local - info.deltas[delta_idx]
             elif fill_nonexist:
                 result[i] = NPY_NAT

diff --git a/pandas/tests/scalar/timestamp/methods/test_tz_localize.py b/pandas/tests/scalar/timestamp/methods/test_tz_localize.py
@@ -123,6 +123,44 @@ def test_tz_localize_nonexistent(self, stamp, tz):
             ts.tz_localize(tz, nonexistent="raise")
         assert ts.tz_localize(tz, nonexistent="NaT") is NaT
 
+    @pytest.mark.parametrize(
+        "stamp, tz, forward_expected, backward_expected",
+        [
+            (
+                "2015-03-29 02:00:00",
+                "Europe/Warsaw",
+                "2015-03-29 03:00:00",
+                "2015-03-29 01:59:59",
+            ),  # utc+1 -> utc+2
+            (
+                "2023-03-12 02:00:00",
+                "America/Los_Angeles",
+                "2023-03-12 03:00:00",
+                "2023-03-12 01:59:59",
+            ),  # utc-8 -> utc-7
+            (
+                "2023-03-26 01:00:00",
+                "Europe/London",
+                "2023-03-26 02:00:00",
+                "2023-03-26 00:59:59",
+            ),  # utc+0 -> utc+1
+            (
+                "2023-03-26 00:00:00",
+                "Atlantic/Azores",
+                "2023-03-26 01:00:00",
+                "2023-03-25 23:59:59",
+            ),  # utc-1 -> utc+0
+        ],
+    )
+    def test_tz_localize_nonexistent_shift(
+        self, stamp, tz, forward_expected, backward_expected
+    ):
+        ts = Timestamp(stamp)
+        forward_ts = ts.tz_localize(tz, nonexistent="shift_forward")
+        assert forward_ts == Timestamp(forward_expected, tz=tz)
+        backward_ts = ts.tz_localize(tz, nonexistent="shift_backward")
+        assert backward_ts == Timestamp(backward_expected, tz=tz)
+
     def test_tz_localize_ambiguous_raise(self):
         # GH#13057
         ts = Timestamp("2015-11-1 01:00")