BUG: underflow on Timestamp creation

Author: chris-b1

doc/source/whatsnew/v0.19.1.txt

@@ -39,7 +39,7 @@ Bug Fixes
 
 
 
-
+- Bug in ``Timestamp`` where dates very near the minimum (1677-09) could underflow on creation (:issue:`14415`)
 
 
 

pandas/src/datetime/np_datetime.c

@@ -846,7 +846,8 @@ convert_datetime_to_datetimestruct(pandas_datetime_metadata *meta,
                 dt  = dt % perday;
             }
             else {
-                set_datetimestruct_days((dt - (perday-1)) / perday, out);
+                set_datetimestruct_days(dt / perday - (dt % perday == 0 ? 0 : 1),
+                                        out);
                 dt = (perday-1) + (dt + 1) % perday;
             }
             out->hour = dt;
@@ -860,7 +861,8 @@ convert_datetime_to_datetimestruct(pandas_datetime_metadata *meta,
                 dt  = dt % perday;
             }
             else {
-                set_datetimestruct_days((dt - (perday-1)) / perday, out);
+                set_datetimestruct_days(dt / perday - (dt % perday == 0 ? 0 : 1),
+                                        out);
                 dt = (perday-1) + (dt + 1) % perday;
             }
             out->hour = dt / 60;
@@ -875,7 +877,8 @@ convert_datetime_to_datetimestruct(pandas_datetime_metadata *meta,
                 dt  = dt % perday;
             }
             else {
-                set_datetimestruct_days((dt - (perday-1)) / perday, out);
+                set_datetimestruct_days(dt / perday - (dt % perday == 0 ? 0 : 1),
+                                        out);
                 dt = (perday-1) + (dt + 1) % perday;
             }
             out->hour = dt / (60*60);
@@ -891,7 +894,8 @@ convert_datetime_to_datetimestruct(pandas_datetime_metadata *meta,
                 dt  = dt % perday;
             }
             else {
-                set_datetimestruct_days((dt - (perday-1)) / perday, out);
+                set_datetimestruct_days(dt / perday - (dt % perday == 0 ? 0 : 1),
+                                        out);
                 dt = (perday-1) + (dt + 1) % perday;
             }
             out->hour = dt / (60*60*1000LL);
@@ -908,7 +912,8 @@ convert_datetime_to_datetimestruct(pandas_datetime_metadata *meta,
                 dt  = dt % perday;
             }
             else {
-                set_datetimestruct_days((dt - (perday-1)) / perday, out);
+                set_datetimestruct_days(dt / perday - (dt % perday == 0 ? 0 : 1),
+                                        out);
                 dt = (perday-1) + (dt + 1) % perday;
             }
             out->hour = dt / (60*60*1000000LL);
@@ -925,7 +930,8 @@ convert_datetime_to_datetimestruct(pandas_datetime_metadata *meta,
                 dt  = dt % perday;
             }
             else {
-                set_datetimestruct_days((dt - (perday-1)) / perday, out);
+                set_datetimestruct_days(dt / perday - (dt % perday == 0 ? 0 : 1),
+                                        out);
                 dt = (perday-1) + (dt + 1) % perday;
             }
             out->hour = dt / (60*60*1000000000LL);
@@ -943,7 +949,8 @@ convert_datetime_to_datetimestruct(pandas_datetime_metadata *meta,
                 dt  = dt % perday;
             }
             else {
-                set_datetimestruct_days((dt - (perday-1)) / perday, out);
+                set_datetimestruct_days(dt / perday - (dt % perday == 0 ? 0 : 1),
+                                        out);
                 dt = (perday-1) + (dt + 1) % perday;
             }
             out->hour = dt / (60*60*1000000000000LL);

pandas/tseries/tests/test_timeseries.py

@@ -4463,6 +4463,15 @@ def test_basics_nanos(self):
         self.assertEqual(stamp.microsecond, 0)
         self.assertEqual(stamp.nanosecond, 500)
 
+        # GH 14415
+        val = np.iinfo(np.int64).min + 80000000000000
+        stamp = Timestamp(val)
+        self.assertEqual(stamp.year, 1677)
+        self.assertEqual(stamp.month, 9)
+        self.assertEqual(stamp.day, 21)
+        self.assertEqual(stamp.microsecond, 145224)
+        self.assertEqual(stamp.nanosecond, 192)
+
     def test_unit(self):
 
         def check(val, unit=None, h=1, s=1, us=0):

pandas/tslib.pyx

@@ -24,6 +24,11 @@ from cpython cimport (
     PyUnicode_AsUTF8String,
 )
 
+
+cdef extern from "headers/stdint.h":
+    enum: INT64_MAX
+    enum: INT64_MIN
+
 # Cython < 0.17 doesn't have this in cpython
 cdef extern from "Python.h":
     cdef PyTypeObject *Py_TYPE(object)
@@ -904,10 +909,9 @@ cpdef object get_value_box(ndarray arr, object loc):
 
 
 # Add the min and max fields at the class level
-# These are defined as magic numbers due to strange
-# wraparound behavior when using the true int64 lower boundary
-cdef int64_t _NS_LOWER_BOUND = -9223285636854775000LL
-cdef int64_t _NS_UPPER_BOUND = 9223372036854775807LL
+# INT64_MIN is reserved for NaT
+cdef int64_t _NS_LOWER_BOUND = INT64_MIN + 1
+cdef int64_t _NS_UPPER_BOUND = INT64_MAX
 
 cdef pandas_datetimestruct _NS_MIN_DTS, _NS_MAX_DTS
 pandas_datetime_to_datetimestruct(_NS_LOWER_BOUND, PANDAS_FR_ns, &_NS_MIN_DTS)