kszucs commented on a change in pull request #7519:
URL: https://github.com/apache/arrow/pull/7519#discussion_r448560952
##########
File path: python/pyarrow/scalar.pxi
##########
@@ -1217,21 +767,95 @@ cdef dict _scalar_classes = {
_Type_INT16: Int16Scalar,
_Type_INT32: Int32Scalar,
_Type_INT64: Int64Scalar,
+ _Type_HALF_FLOAT: HalfFloatScalar,
_Type_FLOAT: FloatScalar,
_Type_DOUBLE: DoubleScalar,
+ _Type_DECIMAL: Decimal128Scalar,
+ _Type_DATE32: Date32Scalar,
+ _Type_DATE64: Date64Scalar,
+ _Type_TIME32: Time32Scalar,
+ _Type_TIME64: Time64Scalar,
+ _Type_TIMESTAMP: TimestampScalar,
+ _Type_DURATION: DurationScalar,
+ _Type_BINARY: BinaryScalar,
+ _Type_LARGE_BINARY: LargeBinaryScalar,
+ _Type_FIXED_SIZE_BINARY: FixedSizeBinaryScalar,
_Type_STRING: StringScalar,
+ _Type_LARGE_STRING: LargeStringScalar,
+ _Type_LIST: ListScalar,
+ _Type_LARGE_LIST: LargeListScalar,
+ _Type_FIXED_SIZE_LIST: FixedSizeListScalar,
+ _Type_STRUCT: StructScalar,
+ _Type_MAP: MapScalar,
+ _Type_DICTIONARY: DictionaryScalar,
+ _Type_SPARSE_UNION: UnionScalar,
+ _Type_DENSE_UNION: UnionScalar,
}
-cdef object box_scalar(DataType type, const shared_ptr[CArray]& sp_array,
- int64_t index):
- cdef ArrayValue value
- if type.type.id() == _Type_NA:
- return _NULL
- elif sp_array.get().IsNull(index):
- return _NULL
- else:
- klass = _array_value_classes[type.type.id()]
- value = klass.__new__(klass)
- value.init(type, sp_array, index)
- return value
+def scalar(value, DataType type=None, *, from_pandas=None,
+ MemoryPool memory_pool=None):
+ """
+ Create a pyarrow.Scalar instance from a Python object.
+
+ Parameters
+ ----------
+ value : Any
+ Python object coercible to arrow's type system.
+ type : pyarrow.DataType
+ Explicit type to attempt to coerce to, otherwise will be inferred from
+ the value.
+ from_pandas : bool, default None
+ Use pandas's semantics for inferring nulls from values in
+ ndarray-like data. Defaults to False if not passed explicitly by user,
+ or True if a pandas object is passed in.
+ memory_pool : pyarrow.MemoryPool, optional
+ If not passed, will allocate memory from the currently-set default
+ memory pool.
+
+ Returns
+ -------
+ scalar : pyarrow.Scalar
+
+ Notes
+ -----
+ Localized timestamps will currently be returned as UTC (pandas's native
+ representation). Timezone-naive data will be implicitly interpreted as
+ UTC.
Review comment:
Removing. Copied from `pa.array()`'s docstring, so we mey need to update
it there as well.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
