BUG: mixed-type mixed-timezone/awareness

doc/source/whatsnew/v2.2.0.rst

@@ -326,6 +326,7 @@ Datetimelike
 - Bug in :class:`DatetimeIndex` when passing an object-dtype ndarray of float objects and a ``tz`` incorrectly localizing the result (:issue:`55780`)
 - Bug in :func:`concat` raising ``AttributeError`` when concatenating all-NA DataFrame with :class:`DatetimeTZDtype` dtype DataFrame. (:issue:`52093`)
 - Bug in :func:`to_datetime` and :class:`DatetimeIndex` when passing a list of mixed-string-and-numeric types incorrectly raising (:issue:`55780`)
+- Bug in :func:`to_datetime` and :class:`DatetimeIndex` when passing mixed-type objects with a mix of timezones or mix of timezone-awareness failing to raise ``ValueError`` (:issue:`55693`)
 - Bug in :meth:`DatetimeIndex.union` returning object dtype for tz-aware indexes with the same timezone but different units (:issue:`55238`)
 - Bug in :meth:`Index.is_monotonic_increasing` and :meth:`Index.is_monotonic_decreasing` always caching :meth:`Index.is_unique` as ``True`` when first value in index is ``NaT`` (:issue:`55755`)
 - Bug in :meth:`Index.view` to a datetime64 dtype with non-supported resolution incorrectly raising (:issue:`55710`)

pandas/_libs/tslib.pyx

@@ -71,6 +71,7 @@ from pandas._libs.tslibs.nattype cimport (
     c_nat_strings as nat_strings,
 )
 from pandas._libs.tslibs.timestamps cimport _Timestamp
+from pandas._libs.tslibs.timezones cimport tz_compare
 
 from pandas._libs.tslibs import (
     Resolution,
@@ -487,9 +488,11 @@ cpdef array_to_datetime(
             elif PyDate_Check(val):
                 iresult[i] = pydate_to_dt64(val, &dts, reso=creso)
                 check_dts_bounds(&dts, creso)
+                state.found_other = True
 
             elif is_datetime64_object(val):
                 iresult[i] = get_datetime64_nanos(val, creso)
+                state.found_other = True
 
             elif is_integer_object(val) or is_float_object(val):
                 # these must be ns unit by-definition
@@ -499,6 +502,7 @@ cpdef array_to_datetime(
                 else:
                     # we now need to parse this as if unit='ns'
                     iresult[i] = cast_from_unit(val, "ns", out_reso=creso)
+                    state.found_other = True
 
             elif isinstance(val, str):
                 # string
@@ -534,6 +538,7 @@ cpdef array_to_datetime(
                     # Add a marker for naive string, to track if we are
                     # parsing mixed naive and aware strings
                     out_tzoffset_vals.add("naive")
+                    state.found_naive_str = True
 
             else:
                 raise TypeError(f"{type(val)} is not convertible to datetime")
@@ -557,9 +562,29 @@ cpdef array_to_datetime(
         is_same_offsets = len(out_tzoffset_vals) == 1
         if not is_same_offsets:
             return _array_to_datetime_object(values, errors, dayfirst, yearfirst)
+        elif state.found_naive or state.found_other:
+            # e.g. test_to_datetime_mixed_awareness_mixed_types
+            raise ValueError("Cannot mix tz-aware with tz-naive values")
+        elif tz_out is not None:
+            # GH#55693
+            tz_offset = out_tzoffset_vals.pop()
+            tz_out2 = timezone(timedelta(seconds=tz_offset))
+            if not tz_compare(tz_out, tz_out2):
+                # e.g. test_to_datetime_mixed_tzs_mixed_types
+                raise ValueError(
+                    "Mixed timezones detected. pass utc=True in to_datetime "
+                    "or tz='UTC' in DatetimeIndex to convert to a common timezone."
+                )
+            # e.g. test_to_datetime_mixed_types_matching_tzs
         else:
             tz_offset = out_tzoffset_vals.pop()
             tz_out = timezone(timedelta(seconds=tz_offset))
+    elif not utc_convert:
+        if tz_out and (state.found_other or state.found_naive_str):
+            # found_other indicates a tz-naive int, float, dt64, or date
+            # e.g. test_to_datetime_mixed_awareness_mixed_types
+            raise ValueError("Cannot mix tz-aware with tz-naive values")
+
     return result, tz_out
 
 

pandas/_libs/tslibs/strptime.pxd

@@ -14,6 +14,8 @@ cdef class DatetimeParseState:
     cdef:
         bint found_tz
         bint found_naive
+        bint found_naive_str
+        bint found_other
         bint creso_ever_changed
         NPY_DATETIMEUNIT creso
 

pandas/_libs/tslibs/strptime.pyx

@@ -240,6 +240,9 @@ cdef class DatetimeParseState:
     def __cinit__(self, NPY_DATETIMEUNIT creso=NPY_DATETIMEUNIT.NPY_FR_ns):
         self.found_tz = False
         self.found_naive = False
+        self.found_naive_str = False
+        self.found_other = False
+
         self.creso = creso
         self.creso_ever_changed = False
 

pandas/tests/tools/test_to_datetime.py

@@ -3723,3 +3723,142 @@ def test_to_datetime_with_empty_str_utc_false_offsets_and_format_mixed():
         to_datetime(
             ["2020-01-01 00:00+00:00", "2020-01-01 00:00+02:00", ""], format="mixed"
         )
+
+
+def test_to_datetime_mixed_tzs_mixed_types():
+    # GH#55793, GH#55693 mismatched tzs but one is str and other is
+    #  datetime object
+    ts = Timestamp("2016-01-02 03:04:05", tz="US/Pacific")
+    dtstr = "2023-10-30 15:06+01"
+    arr = [ts, dtstr]
+
+    msg = (
+        "Mixed timezones detected. pass utc=True in to_datetime or tz='UTC' "
+        "in DatetimeIndex to convert to a common timezone"
+    )
+    with pytest.raises(ValueError, match=msg):
+        to_datetime(arr)
+    with pytest.raises(ValueError, match=msg):
+        to_datetime(arr, format="mixed")
+    with pytest.raises(ValueError, match=msg):
+        DatetimeIndex(arr)
+
+
+def test_to_datetime_mixed_types_matching_tzs():
+    # GH#55793
+    dtstr = "2023-11-01 09:22:03-07:00"
+    ts = Timestamp(dtstr)
+    arr = [ts, dtstr]
+    res1 = to_datetime(arr)
+    res2 = to_datetime(arr[::-1])[::-1]
+    res3 = to_datetime(arr, format="mixed")
+    res4 = DatetimeIndex(arr)
+
+    expected = DatetimeIndex([ts, ts])
+    tm.assert_index_equal(res1, expected)
+    tm.assert_index_equal(res2, expected)
+    tm.assert_index_equal(res3, expected)
+    tm.assert_index_equal(res4, expected)
+
+
+dtstr = "2020-01-01 00:00+00:00"
+ts = Timestamp(dtstr)
+
+
+@pytest.mark.filterwarnings("ignore:Could not infer format:UserWarning")
+@pytest.mark.parametrize(
+    "aware_val",
+    [dtstr, Timestamp(dtstr)],
+    ids=lambda x: type(x).__name__,
+)
+@pytest.mark.parametrize(
+    "naive_val",
+    [dtstr[:-6], ts.tz_localize(None), ts.date(), ts.asm8, ts.value, float(ts.value)],
+    ids=lambda x: type(x).__name__,
+)
+@pytest.mark.parametrize("naive_first", [True, False])
+def test_to_datetime_mixed_awareness_mixed_types(aware_val, naive_val, naive_first):
+    # GH#55793, GH#55693
+    # Empty string parses to NaT
+    vals = [aware_val, naive_val, ""]
+
+    vec = vals
+    if naive_first:
+        # alas, the behavior is order-dependent, so we test both ways
+        vec = [naive_val, aware_val, ""]
+
+    # both_strs-> paths that were previously already deprecated with warning
+    #  issued in _array_to_datetime_object
+    both_strs = isinstance(aware_val, str) and isinstance(naive_val, str)
+    isinstance(aware_val, str) or isinstance(naive_val, str)
+    has_numeric = isinstance(naive_val, (int, float))
+
+    depr_msg = "In a future version of pandas, parsing datetimes with mixed time zones"
+
+    first_non_null = next(x for x in vec if x != "")
+    # if first_non_null is a not a string, _guess_datetime_format_for_array
+    #  doesn't guess a format so we don't go through array_strptime
+    if not isinstance(first_non_null, str):
+        # that case goes through array_strptime which has different behavior
+        msg = "Cannot mix tz-aware with tz-naive values"
+        if naive_first and isinstance(aware_val, Timestamp):
+            if isinstance(naive_val, Timestamp):
+                msg = "Tz-aware datetime.datetime cannot be converted to datetime64"
+            with pytest.raises(ValueError, match=msg):
+                to_datetime(vec)
+        else:
+            with pytest.raises(ValueError, match=msg):
+                to_datetime(vec)
+
+        # No warning/error with utc=True
+        to_datetime(vec, utc=True)
+
+    elif has_numeric and vec.index(aware_val) < vec.index(naive_val):
+        msg = "time data .* doesn't match format"
+        with pytest.raises(ValueError, match=msg):
+            to_datetime(vec)
+        with pytest.raises(ValueError, match=msg):
+            to_datetime(vec, utc=True)
+
+    elif both_strs and vec.index(aware_val) < vec.index(naive_val):
+        msg = r"time data \"2020-01-01 00:00\" doesn't match format"
+        with pytest.raises(ValueError, match=msg):
+            to_datetime(vec)
+        with pytest.raises(ValueError, match=msg):
+            to_datetime(vec, utc=True)
+
+    elif both_strs and vec.index(naive_val) < vec.index(aware_val):
+        msg = "unconverted data remains when parsing with format"
+        with pytest.raises(ValueError, match=msg):
+            to_datetime(vec)
+        with pytest.raises(ValueError, match=msg):
+            to_datetime(vec, utc=True)
+
+    else:
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            to_datetime(vec)
+
+        # No warning/error with utc=True
+        to_datetime(vec, utc=True)
+
+    if both_strs:
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            to_datetime(vec, format="mixed")
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            msg = "DatetimeIndex has mixed timezones"
+            with pytest.raises(TypeError, match=msg):
+                DatetimeIndex(vec)
+    else:
+        msg = "Cannot mix tz-aware with tz-naive values"
+        if naive_first and isinstance(aware_val, Timestamp):
+            if isinstance(naive_val, Timestamp):
+                msg = "Tz-aware datetime.datetime cannot be converted to datetime64"
+            with pytest.raises(ValueError, match=msg):
+                to_datetime(vec, format="mixed")
+            with pytest.raises(ValueError, match=msg):
+                DatetimeIndex(vec)
+        else:
+            with pytest.raises(ValueError, match=msg):
+                to_datetime(vec, format="mixed")
+            with pytest.raises(ValueError, match=msg):
+                DatetimeIndex(vec)