Fix parsing corner case closes pandas-dev#19382 (pandas-dev#19529)

Author: jbrockmendel

doc/source/whatsnew/v0.23.0.txt

@@ -550,6 +550,7 @@ Datetimelike
 - Bug in :func:`Series.truncate` which raises ``TypeError`` with a monotonic ``PeriodIndex`` (:issue:`17717`)
 - Bug in :func:`~DataFrame.pct_change` using ``periods`` and ``freq`` returned different length outputs (:issue:`7292`)
 - Bug in comparison of :class:`DatetimeIndex` against ``None`` or ``datetime.date`` objects raising ``TypeError`` for ``==`` and ``!=`` comparisons instead of all-``False`` and all-``True``, respectively (:issue:`19301`)
+- Bug in :class:`Timestamp` and :func:`to_datetime` where a string representing a barely out-of-bounds timestamp would be incorrectly rounded down instead of raising ``OutOfBoundsDatetime`` (:issue:`19382`)
 -
 
 Timezones

pandas/_libs/tslib.pyx

@@ -609,20 +609,38 @@ cpdef array_to_datetime(ndarray[object] values, errors='raise',
                         value = tz_convert_single(value, tz, 'UTC')
                     iresult[i] = value
                     check_dts_bounds(&dts)
+                except OutOfBoundsDatetime:
+                    # GH#19382 for just-barely-OutOfBounds falling back to
+                    # dateutil parser will return incorrect result because
+                    # it will ignore nanoseconds
+                    if require_iso8601:
+                        if _parse_today_now(val, &iresult[i]):
+                            continue
+                        elif is_coerce:
+                            iresult[i] = NPY_NAT
+                            continue
+                        elif is_raise:
+                            raise ValueError("time data {val} doesn't match "
+                                             "format specified"
+                                             .format(val=val))
+                        return values
+                    elif is_coerce:
+                        iresult[i] = NPY_NAT
+                        continue
+                    raise
                 except ValueError:
                     # if requiring iso8601 strings, skip trying other formats
                     if require_iso8601:
                         if _parse_today_now(val, &iresult[i]):
                             continue
-                        if is_coerce:
+                        elif is_coerce:
                             iresult[i] = NPY_NAT
                             continue
                         elif is_raise:
-                            raise ValueError(
-                                "time data %r doesn't match format "
-                                "specified" % (val,))
-                        else:
-                            return values
+                            raise ValueError("time data {val} doesn't match "
+                                             "format specified"
+                                             .format(val=val))
+                        return values
 
                     try:
                         py_dt = parse_datetime_string(val, dayfirst=dayfirst,

pandas/_libs/tslibs/conversion.pyx

@@ -26,6 +26,7 @@ from np_datetime cimport (check_dts_bounds,
                           dt64_to_dtstruct, dtstruct_to_dt64,
                           get_datetime64_unit, get_datetime64_value,
                           pydatetime_to_dt64)
+from np_datetime import OutOfBoundsDatetime
 
 from util cimport (is_string_object,
                    is_datetime64_object,
@@ -472,6 +473,13 @@ cdef _TSObject convert_str_to_tsobject(object ts, object tz, object unit,
                     ts = tz_localize_to_utc(np.array([ts], dtype='i8'), tz,
                                             ambiguous='raise',
                                             errors='raise')[0]
+
+        except OutOfBoundsDatetime:
+            # GH#19382 for just-barely-OutOfBounds falling back to dateutil
+            # parser will return incorrect result because it will ignore
+            # nanoseconds
+            raise
+
         except ValueError:
             try:
                 ts = parse_datetime_string(ts, dayfirst=dayfirst,

pandas/tests/indexes/datetimes/test_tools.py

@@ -17,6 +17,7 @@
 from pandas._libs.tslibs import parsing
 from pandas.core.tools import datetimes as tools
 
+from pandas.errors import OutOfBoundsDatetime
 from pandas.compat import lmap
 from pandas.compat.numpy import np_array_datetime64_compat
 from pandas.core.dtypes.common import is_datetime64_ns_dtype
@@ -783,7 +784,6 @@ def test_dataframe_dtypes(self, cache):
 
 
 class TestToDatetimeMisc(object):
-
     @pytest.mark.parametrize('cache', [True, False])
     def test_to_datetime_iso8601(self, cache):
         result = to_datetime(["2012-01-01 00:00:00"], cache=cache)
@@ -1596,6 +1596,20 @@ def test_coerce_of_invalid_datetimes(self):
             )
         )
 
+    def test_to_datetime_barely_out_of_bounds(self):
+        # GH#19529
+        # GH#19382 close enough to bounds that dropping nanos would result
+        # in an in-bounds datetime
+        arr = np.array(['2262-04-11 23:47:16.854775808'], dtype=object)
+
+        with pytest.raises(OutOfBoundsDatetime):
+            to_datetime(arr)
+
+        with pytest.raises(OutOfBoundsDatetime):
+            # Essentially the same as above, but more directly calling
+            # the relevant function
+            tslib.array_to_datetime(arr)
+
 
 def test_normalize_date():
     value = date(2012, 9, 7)

pandas/tests/scalar/test_timestamp.py

@@ -18,6 +18,7 @@
 from pandas._libs.tslibs import conversion
 from pandas._libs.tslibs.timezones import get_timezone, dateutil_gettz as gettz
 
+from pandas.errors import OutOfBoundsDatetime
 from pandas.compat import long, PY3
 from pandas.compat.numpy import np_datetime64_compat
 from pandas import Timestamp, Period, Timedelta
@@ -410,6 +411,13 @@ def test_out_of_bounds_string(self):
         with pytest.raises(ValueError):
             Timestamp('2263-01-01')
 
+    def test_barely_out_of_bounds(self):
+        # GH#19529
+        # GH#19382 close enough to bounds that dropping nanos would result
+        # in an in-bounds datetime
+        with pytest.raises(OutOfBoundsDatetime):
+            Timestamp('2262-04-11 23:47:16.854775808')
+
     def test_bounds_with_different_units(self):
         out_of_bounds_dates = ('1677-09-21', '2262-04-12')