Backport PR #37613 on branch 1.1.x: BUG: read-only values in cython funcs

Author: jbrockmendel

doc/source/whatsnew/v1.1.5.rst

@@ -24,6 +24,7 @@ Fixed regressions
 Bug fixes
 ~~~~~~~~~
 - Bug in metadata propagation for ``groupby`` iterator (:issue:`37343`)
+- Bug in :func:`to_datetime` and :func:`to_timedelta` with a read-only array incorrectly raising (:issue:`34857`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/_libs/join.pyx

@@ -268,7 +268,7 @@ ctypedef fused join_t:
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def left_join_indexer_unique(join_t[:] left, join_t[:] right):
+def left_join_indexer_unique(ndarray[join_t] left, ndarray[join_t] right):
     cdef:
         Py_ssize_t i, j, nleft, nright
         ndarray[int64_t] indexer

pandas/_libs/tslibs/strptime.pyx

@@ -12,7 +12,7 @@ from _thread import allocate_lock as _thread_allocate_lock
 import numpy as np
 import pytz
 
-from numpy cimport int64_t
+from numpy cimport int64_t, ndarray
 
 from pandas._libs.tslibs.nattype cimport (
     NPY_NAT,
@@ -51,7 +51,7 @@ cdef dict _parse_code_table = {'y': 0,
                                'u': 22}
 
 
-def array_strptime(object[:] values, object fmt, bint exact=True, errors='raise'):
+def array_strptime(ndarray[object] values, object fmt, bint exact=True, errors='raise'):
     """
     Calculates the datetime structs represented by the passed array of strings
 

pandas/_libs/tslibs/timedeltas.pyx

@@ -226,7 +226,7 @@ cdef convert_to_timedelta64(object ts, str unit):
 
 @cython.boundscheck(False)
 @cython.wraparound(False)
-def array_to_timedelta64(object[:] values, str unit=None, str errors="raise"):
+def array_to_timedelta64(ndarray[object] values, str unit=None, str errors="raise"):
     """
     Convert an ndarray to an array of timedeltas. If errors == 'coerce',
     coerce non-convertible objects to NaT. Otherwise, raise.

pandas/core/arrays/datetimelike.py

@@ -1334,9 +1334,8 @@ def _addsub_object_array(self, other: np.ndarray, op):
         result : same class as self
         """
         assert op in [operator.add, operator.sub]
-        if len(other) == 1:
+        if len(other) == 1 and self.ndim == 1:
             # If both 1D then broadcasting is unambiguous
-            # TODO(EA2D): require self.ndim == other.ndim here
             return op(self, other[0])
 
         warnings.warn(

pandas/tests/test_join.py

@@ -43,9 +43,14 @@ def test_outer_join_indexer(self, dtype):
         tm.assert_numpy_array_equal(rindexer, exp)
 
 
-def test_left_join_indexer_unique():
+@pytest.mark.parametrize("readonly", [True, False])
+def test_left_join_indexer_unique(readonly):
     a = np.array([1, 2, 3, 4, 5], dtype=np.int64)
     b = np.array([2, 2, 3, 4, 4], dtype=np.int64)
+    if readonly:
+        # GH#37312, GH#37264
+        a.setflags(write=False)
+        b.setflags(write=False)
 
     result = _join.left_join_indexer_unique(b, a)
     expected = np.array([1, 1, 2, 3, 3], dtype=np.int64)

pandas/tests/tools/test_to_datetime.py

@@ -36,6 +36,16 @@
 
 
 class TestTimeConversionFormats:
+    @pytest.mark.parametrize("readonly", [True, False])
+    def test_to_datetime_readonly(self, readonly):
+        # GH#34857
+        arr = np.array([], dtype=object)
+        if readonly:
+            arr.setflags(write=False)
+        result = to_datetime(arr)
+        expected = to_datetime([])
+        tm.assert_index_equal(result, expected)
+
     @pytest.mark.parametrize("cache", [True, False])
     def test_to_datetime_format(self, cache):
         values = ["1/1/2000", "1/2/2000", "1/3/2000"]

pandas/tests/tools/test_to_timedelta.py

@@ -9,6 +9,16 @@
 
 
 class TestTimedeltas:
+    @pytest.mark.parametrize("readonly", [True, False])
+    def test_to_timedelta_readonly(self, readonly):
+        # GH#34857
+        arr = np.array([], dtype=object)
+        if readonly:
+            arr.setflags(write=False)
+        result = to_timedelta(arr)
+        expected = to_timedelta([])
+        tm.assert_index_equal(result, expected)
+
     def test_to_timedelta(self):
 
         result = to_timedelta(["", ""])