From 1bfeee7575e137bc75741cb2caf015e55ecab2cd Mon Sep 17 00:00:00 2001
From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>
Date: Wed, 13 Sep 2023 14:23:14 -1000
Subject: [PATCH] Raise NotImplementedError for datetime strings with UTC
 offset (#14070)

Avoids e.g. DatetimeIndex(["2022-07-22 00:00:00+02:00"]) from dropping the +02:00 since timezones are not supported

Authors:
  - Matthew Roeschke (https://github.com/mroeschke)

Approvers:
  - Lawrence Mitchell (https://github.com/wence-)
  - Vyas Ramasubramani (https://github.com/vyasr)

URL: https://github.com/rapidsai/cudf/pull/14070
---
 python/cudf/cudf/core/column/column.py  | 18 ++++++++++++++++--
 python/cudf/cudf/tests/test_datetime.py |  6 ++++++
 2 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/python/cudf/cudf/core/column/column.py b/python/cudf/cudf/core/column/column.py
index 59ab3569814..d2e2f11a12e 100644
--- a/python/cudf/cudf/core/column/column.py
+++ b/python/cudf/cudf/core/column/column.py
@@ -2519,11 +2519,11 @@ def _construct_array(
         arbitrary = cupy.asarray(arbitrary, dtype=dtype)
     except (TypeError, ValueError):
         native_dtype = dtype
-        inferred_dtype = None
+        inferred_dtype = infer_dtype(arbitrary, skipna=False)
         if (
             dtype is None
             and not cudf._lib.scalar._is_null_host_scalar(arbitrary)
-            and (inferred_dtype := infer_dtype(arbitrary, skipna=False))
+            and inferred_dtype
             in (
                 "mixed",
                 "mixed-integer",
@@ -2533,6 +2533,20 @@ def _construct_array(
         if inferred_dtype == "interval":
             # Only way to construct an Interval column.
             return pd.array(arbitrary)
+        elif (
+            inferred_dtype == "string" and getattr(dtype, "kind", None) == "M"
+        ):
+            # We may have date-like strings with timezones
+            try:
+                pd_arbitrary = pd.to_datetime(arbitrary)
+                if isinstance(pd_arbitrary.dtype, pd.DatetimeTZDtype):
+                    raise NotImplementedError(
+                        "cuDF does not yet support timezone-aware datetimes"
+                    )
+            except pd.errors.OutOfBoundsDatetime:
+                # https://github.com/pandas-dev/pandas/issues/55096
+                pass
+
         arbitrary = np.asarray(
             arbitrary,
             dtype=native_dtype
diff --git a/python/cudf/cudf/tests/test_datetime.py b/python/cudf/cudf/tests/test_datetime.py
index 5cab19eedc6..0cc7112454c 100644
--- a/python/cudf/cudf/tests/test_datetime.py
+++ b/python/cudf/cudf/tests/test_datetime.py
@@ -2141,6 +2141,12 @@ def test_daterange_pandas_compatibility():
     assert_eq(expected, actual)
 
 
+def test_strings_with_utc_offset_not_implemented():
+    with pytest.warns(DeprecationWarning, match="parsing timezone"):  # cupy
+        with pytest.raises(NotImplementedError):
+            DatetimeIndex(["2022-07-22 00:00:00+02:00"])
+
+
 @pytest.mark.parametrize("code", ["z", "Z"])
 def test_format_timezone_not_implemented(code):
     with pytest.raises(NotImplementedError):