CI: Test on Cython 3.0 on numpydev (pandas-dev#46029)

Author: lithomas1

ci/deps/actions-310-numpydev.yaml

@@ -16,7 +16,8 @@ dependencies:
   - pytz
   - pip
   - pip:
-    - cython==0.29.24 # GH#34014
+    #- cython # TODO: don't install from master after Cython 3.0.0a11 is released
+    - "git+https://github.com/cython/cython.git@master"
     - "--extra-index-url https://pypi.anaconda.org/scipy-wheels-nightly/simple"
     - "--pre"
     - "numpy"

pandas/_libs/interval.pyx

@@ -404,6 +404,8 @@ cdef class Interval(IntervalMixin):
         ):
             return Interval(self.left + y, self.right + y, closed=self.closed)
         elif (
+            # __radd__ pattern
+            # TODO(cython3): remove this
             isinstance(y, Interval)
             and (
                 isinstance(self, numbers.Number)
@@ -414,6 +416,15 @@ cdef class Interval(IntervalMixin):
             return Interval(y.left + self, y.right + self, closed=y.closed)
         return NotImplemented
 
+    def __radd__(self, other):
+        if (
+                isinstance(other, numbers.Number)
+                or PyDelta_Check(other)
+                or is_timedelta64_object(other)
+        ):
+            return Interval(self.left + other, self.right + other, closed=self.closed)
+        return NotImplemented
+
     def __sub__(self, y):
         if (
             isinstance(y, numbers.Number)
@@ -427,9 +438,16 @@ cdef class Interval(IntervalMixin):
         if isinstance(y, numbers.Number):
             return Interval(self.left * y, self.right * y, closed=self.closed)
         elif isinstance(y, Interval) and isinstance(self, numbers.Number):
+            # __radd__ semantics
+            # TODO(cython3): remove this
             return Interval(y.left * self, y.right * self, closed=y.closed)
         return NotImplemented
 
+    def __rmul__(self, other):
+        if isinstance(other, numbers.Number):
+            return Interval(self.left * other, self.right * other, closed=self.closed)
+        return NotImplemented
+
     def __truediv__(self, y):
         if isinstance(y, numbers.Number):
             return Interval(self.left / y, self.right / y, closed=self.closed)

pandas/_libs/tslibs/nattype.pyx

@@ -143,6 +143,7 @@ cdef class _NaT(datetime):
 
     def __add__(self, other):
         if self is not c_NaT:
+            # TODO(cython3): remove this it moved to __radd__
             # cython __radd__ semantics
             self, other = other, self
 
@@ -169,6 +170,9 @@ cdef class _NaT(datetime):
         # Includes Period, DateOffset going through here
         return NotImplemented
 
+    def __radd__(self, other):
+        return self.__add__(other)
+
     def __sub__(self, other):
         # Duplicate some logic from _Timestamp.__sub__ to avoid needing
         # to subclass; allows us to @final(_Timestamp.__sub__)
@@ -177,6 +181,7 @@ cdef class _NaT(datetime):
 
         if self is not c_NaT:
             # cython __rsub__ semantics
+            # TODO(cython3): remove __rsub__ logic from here
             self, other = other, self
             is_rsub = True
 
@@ -200,6 +205,8 @@ cdef class _NaT(datetime):
                     result.fill("NaT")
                     return result
 
+                # __rsub__ logic here
+                # TODO(cython3): remove this, move above code out of ``if not is_rsub`` block
                 # timedelta64 - NaT we have to treat NaT as timedelta64
                 #  for this to be meaningful, and the result is timedelta64
                 result = np.empty(other.shape, dtype="timedelta64[ns]")
@@ -220,6 +227,24 @@ cdef class _NaT(datetime):
         # Includes Period, DateOffset going through here
         return NotImplemented
 
+    def __rsub__(self, other):
+        if util.is_array(other):
+            if other.dtype.kind == "m":
+                # timedelta64 - NaT we have to treat NaT as timedelta64
+                #  for this to be meaningful, and the result is timedelta64
+                result = np.empty(other.shape, dtype="timedelta64[ns]")
+                result.fill("NaT")
+                return result
+
+            elif other.dtype.kind == "M":
+                # We treat NaT as a datetime, so regardless of whether this is
+                #  NaT - other or other - NaT, the result is timedelta64
+                result = np.empty(other.shape, dtype="timedelta64[ns]")
+                result.fill("NaT")
+                return result
+        # other cases are same, swap operands is allowed even though we subtract because this is NaT
+        return self.__sub__(other)
+
     def __pos__(self):
         return NaT
 

pandas/_libs/tslibs/offsets.pyx

@@ -450,6 +450,7 @@ cdef class BaseOffset:
     def __add__(self, other):
         if not isinstance(self, BaseOffset):
             # cython semantics; this is __radd__
+            # TODO(cython3): remove this, this moved to __radd__
             return other.__add__(self)
 
         elif util.is_array(other) and other.dtype == object:
@@ -460,19 +461,26 @@ cdef class BaseOffset:
         except ApplyTypeError:
             return NotImplemented
 
+    def __radd__(self, other):
+        return self.__add__(other)
+
     def __sub__(self, other):
         if PyDateTime_Check(other):
             raise TypeError('Cannot subtract datetime from offset.')
         elif type(other) == type(self):
             return type(self)(self.n - other.n, normalize=self.normalize,
                               **self.kwds)
         elif not isinstance(self, BaseOffset):
+            # TODO(cython3): remove, this moved to __rsub__
             # cython semantics, this is __rsub__
             return (-other).__add__(self)
         else:
             # e.g. PeriodIndex
             return NotImplemented
 
+    def __rsub__(self, other):
+        return (-self).__add__(other)
+
     def __call__(self, other):
         warnings.warn(
             "DateOffset.__call__ is deprecated and will be removed in a future "
@@ -499,10 +507,14 @@ cdef class BaseOffset:
             return type(self)(n=other * self.n, normalize=self.normalize,
                               **self.kwds)
         elif not isinstance(self, BaseOffset):
+            # TODO(cython3): remove this, this moved to __rmul__
             # cython semantics, this is __rmul__
             return other.__mul__(self)
         return NotImplemented
 
+    def __rmul__(self, other):
+        return self.__mul__(other)
+
     def __neg__(self):
         # Note: we are deferring directly to __mul__ instead of __rmul__, as
         # that allows us to use methods that can go in a `cdef class`
@@ -887,6 +899,7 @@ cdef class Tick(SingleConstructorOffset):
 
     def __mul__(self, other):
         if not isinstance(self, Tick):
+            # TODO(cython3), remove this, this moved to __rmul__
             # cython semantics, this is __rmul__
             return other.__mul__(self)
         if is_float_object(other):
@@ -900,6 +913,9 @@ cdef class Tick(SingleConstructorOffset):
             return new_self * other
         return BaseOffset.__mul__(self, other)
 
+    def __rmul__(self, other):
+        return self.__mul__(other)
+
     def __truediv__(self, other):
         if not isinstance(self, Tick):
             # cython semantics mean the args are sometimes swapped
@@ -908,9 +924,14 @@ cdef class Tick(SingleConstructorOffset):
             result = self.delta.__truediv__(other)
         return _wrap_timedelta_result(result)
 
+    def __rtruediv__(self, other):
+        result = self.delta.__rtruediv__(other)
+        return _wrap_timedelta_result(result)
+
     def __add__(self, other):
         if not isinstance(self, Tick):
             # cython semantics; this is __radd__
+            # TODO(cython3): remove this, this moved to __radd__
             return other.__add__(self)
 
         if isinstance(other, Tick):
@@ -928,6 +949,9 @@ cdef class Tick(SingleConstructorOffset):
                 f"the add operation between {self} and {other} will overflow"
             ) from err
 
+    def __radd__(self, other):
+        return self.__add__(other)
+
     def _apply(self, other):
         # Timestamp can handle tz and nano sec, thus no need to use apply_wraps
         if isinstance(other, _Timestamp):

pandas/_libs/tslibs/period.pyx

@@ -1710,6 +1710,7 @@ cdef class _Period(PeriodMixin):
     def __add__(self, other):
         if not is_period_object(self):
             # cython semantics; this is analogous to a call to __radd__
+            # TODO(cython3): remove this
             if self is NaT:
                 return NaT
             return other.__add__(self)
@@ -1734,9 +1735,13 @@ cdef class _Period(PeriodMixin):
 
         return NotImplemented
 
+    def __radd__(self, other):
+        return self.__add__(other)
+
     def __sub__(self, other):
         if not is_period_object(self):
             # cython semantics; this is like a call to __rsub__
+            # TODO(cython3): remove this
             if self is NaT:
                 return NaT
             return NotImplemented
@@ -1760,6 +1765,11 @@ cdef class _Period(PeriodMixin):
 
         return NotImplemented
 
+    def __rsub__(self, other):
+        if other is NaT:
+            return NaT
+        return NotImplemented
+
     def asfreq(self, freq, how='E') -> "Period":
         """
         Convert Period to desired frequency, at the start or end of the interval.

pandas/_libs/tslibs/timestamps.pyx

@@ -280,13 +280,19 @@ cdef class _Timestamp(ABCTimestamp):
             return other.tzinfo is not None
         return other.tzinfo is None
 
+    @cython.overflowcheck(True)
     def __add__(self, other):
         cdef:
             int64_t nanos = 0
 
         if is_any_td_scalar(other):
             nanos = delta_to_nanoseconds(other)
-            result = type(self)(self.value + nanos, tz=self.tzinfo)
+            try:
+                result = type(self)(self.value + nanos, tz=self.tzinfo)
+            except OverflowError:
+                # Use Python ints
+                # Hit in test_tdi_add_overflow
+                result = type(self)(int(self.value) + int(nanos), tz=self.tzinfo)
             if result is not NaT:
                 result._set_freq(self._freq)  # avoid warning in constructor
             return result
@@ -307,9 +313,16 @@ cdef class _Timestamp(ABCTimestamp):
 
         elif not isinstance(self, _Timestamp):
             # cython semantics, args have been switched and this is __radd__
+            # TODO(cython3): remove this it moved to __radd__
             return other.__add__(self)
         return NotImplemented
 
+    def __radd__(self, other):
+        # Have to duplicate checks to avoid infinite recursion due to NotImplemented
+        if is_any_td_scalar(other) or is_integer_object(other) or is_array(other):
+            return self.__add__(other)
+        return NotImplemented
+
     def __sub__(self, other):
 
         if is_any_td_scalar(other) or is_integer_object(other):
@@ -336,6 +349,7 @@ cdef class _Timestamp(ABCTimestamp):
                 and (PyDateTime_Check(other) or is_datetime64_object(other))):
             # both_timestamps is to determine whether Timedelta(self - other)
             # should raise the OOB error, or fall back returning a timedelta.
+            # TODO(cython3): clean out the bits that moved to __rsub__
             both_timestamps = (isinstance(other, _Timestamp) and
                                isinstance(self, _Timestamp))
             if isinstance(self, _Timestamp):
@@ -366,10 +380,22 @@ cdef class _Timestamp(ABCTimestamp):
         elif is_datetime64_object(self):
             # GH#28286 cython semantics for __rsub__, `other` is actually
             #  the Timestamp
+            # TODO(cython3): remove this, this moved to __rsub__
             return type(other)(self) - other
 
         return NotImplemented
 
+    def __rsub__(self, other):
+        if PyDateTime_Check(other):
+            try:
+                return type(self)(other) - self
+            except (OverflowError, OutOfBoundsDatetime) as err:
+                # We get here in stata tests, fall back to stdlib datetime
+                #  method and return stdlib timedelta object
+                pass
+        elif is_datetime64_object(other):
+            return type(self)(other) - self
+        return NotImplemented
     # -----------------------------------------------------------------
 
     cdef int64_t _maybe_convert_value_to_local(self):