This is an automated email from the ASF dual-hosted git repository.
jorisvandenbossche pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow.git
The following commit(s) were added to refs/heads/main by this push:
new 2ebb3f70d8 GH-34411: [Python] Change array constructor to accept
pyarrow array (#34275)
2ebb3f70d8 is described below
commit 2ebb3f70d8c8a14a8fea392f00cb2f6bb1490931
Author: Alenka Frim <[email protected]>
AuthorDate: Thu Mar 2 14:29:31 2023 +0100
GH-34411: [Python] Change array constructor to accept pyarrow array (#34275)
### Rationale for this change
Currently, `pyarrow.array` doesn't accept pyarrow Arrays and this PR adds a
check to allow that.
* Closes: #34411
Authored-by: Alenka Frim <[email protected]>
Signed-off-by: Joris Van den Bossche <[email protected]>
---
python/pyarrow/array.pxi | 12 ++++++++++--
python/pyarrow/compute.py | 6 ++++--
python/pyarrow/tests/test_array.py | 26 ++++++++++++++++++++++++++
3 files changed, 40 insertions(+), 4 deletions(-)
diff --git a/python/pyarrow/array.pxi b/python/pyarrow/array.pxi
index b2fd413fc7..dca99af812 100644
--- a/python/pyarrow/array.pxi
+++ b/python/pyarrow/array.pxi
@@ -232,6 +232,11 @@ def array(object obj, type=None, mask=None, size=None,
from_pandas=None,
else:
c_from_pandas = from_pandas
+ if isinstance(obj, Array):
+ if type is not None and not obj.type.equals(type):
+ obj = obj.cast(type, safe=safe, memory_pool=memory_pool)
+ return obj
+
if hasattr(obj, '__arrow_array__'):
return _handle_arrow_array_protocol(obj, type, mask, size)
elif _is_array_like(obj):
@@ -904,7 +909,7 @@ cdef class Array(_PandasConvertible):
result = self.ap.Diff(deref(other.ap))
return frombytes(result, safe=True)
- def cast(self, object target_type=None, safe=None, options=None):
+ def cast(self, object target_type=None, safe=None, options=None,
memory_pool=None):
"""
Cast array values to another data type
@@ -918,12 +923,15 @@ cdef class Array(_PandasConvertible):
Whether to check for conversion errors such as overflow.
options : CastOptions, default None
Additional checks pass by CastOptions
+ memory_pool : MemoryPool, optional
+ memory pool to use for allocations during function execution.
Returns
-------
cast : Array
"""
- return _pc().cast(self, target_type, safe=safe, options=options)
+ return _pc().cast(self, target_type, safe=safe,
+ options=options, memory_pool=memory_pool)
def view(self, object target_type):
"""
diff --git a/python/pyarrow/compute.py b/python/pyarrow/compute.py
index 5eb681b5fb..e4daaf5e58 100644
--- a/python/pyarrow/compute.py
+++ b/python/pyarrow/compute.py
@@ -331,7 +331,7 @@ def _make_global_functions():
_make_global_functions()
-def cast(arr, target_type=None, safe=None, options=None):
+def cast(arr, target_type=None, safe=None, options=None, memory_pool=None):
"""
Cast array values to another data type. Can also be invoked as an array
instance method.
@@ -345,6 +345,8 @@ def cast(arr, target_type=None, safe=None, options=None):
Check for overflows or other unsafe conversions
options : CastOptions, default None
Additional checks pass by CastOptions
+ memory_pool : MemoryPool, optional
+ memory pool to use for allocations during function execution.
Examples
--------
@@ -395,7 +397,7 @@ def cast(arr, target_type=None, safe=None, options=None):
options = CastOptions.unsafe(target_type)
else:
options = CastOptions.safe(target_type)
- return call_function("cast", [arr], options)
+ return call_function("cast", [arr], options, memory_pool)
def index(data, value, start=None, end=None, *, memory_pool=None):
diff --git a/python/pyarrow/tests/test_array.py
b/python/pyarrow/tests/test_array.py
index fa3de35904..d974af99c6 100644
--- a/python/pyarrow/tests/test_array.py
+++ b/python/pyarrow/tests/test_array.py
@@ -3381,3 +3381,29 @@ def test_struct_array_sort():
{"a": 5, "b": "foo"},
None
]
+
+
+def test_array_accepts_pyarrow_array():
+ arr = pa.array([1, 2, 3])
+ result = pa.array(arr)
+ assert arr == result
+
+ # Test casting to a different type
+ result = pa.array(arr, type=pa.uint8())
+ expected = pa.array([1, 2, 3], type=pa.uint8())
+ assert expected == result
+ assert expected.type == pa.uint8()
+
+ # Test casting with safe keyword
+ arr = pa.array([2 ** 63 - 1], type=pa.int64())
+
+ with pytest.raises(pa.ArrowInvalid):
+ pa.array(arr, type=pa.int32())
+
+ expected = pa.array([-1], type=pa.int32())
+ result = pa.array(arr, type=pa.int32(), safe=False)
+ assert result == expected
+
+ # Test memory_pool keyword is accepted
+ result = pa.array(arr, memory_pool=pa.default_memory_pool())
+ assert arr == result
