first use of ak.str

src/dask_awkward/__init__.py

@@ -6,6 +6,7 @@
 import dask_awkward.lib.operations as operations
 import dask_awkward.lib.optimize as optimize
 import dask_awkward.lib.reducers as reducers
+import dask_awkward.lib.str as str
 import dask_awkward.lib.structure as structure
 from dask_awkward.lib.core import Array, PartitionCompatibility, Record, Scalar
 from dask_awkward.lib.core import _type as type

src/dask_awkward/lib/__init__.py

@@ -1,3 +1,4 @@
+import dask_awkward.lib.str as str
 from dask_awkward.lib.core import Array, PartitionCompatibility, Record, Scalar
 from dask_awkward.lib.core import _type as type
 from dask_awkward.lib.core import (

src/dask_awkward/lib/str.py

@@ -0,0 +1,20 @@
+import awkward as ak
+
+from dask_awkward.lib.core import Array, map_partitions
+
+
+def split_whitespace(
+ array: Array,
+ *,
+ max_splits: int | None = None,
+ reverse: bool = False,
+ highlevel: bool = True,
+ behavior: dict | None = None,
+):
+ return map_partitions(
+ ak.str.split_whitespace,
+ array,
+ max_splits=max_splits,
+ reverse=reverse,
+ behavior=behavior,
+ )

tests/test_str.py

@@ -0,0 +1,22 @@
+from __future__ import annotations
+
+import awkward as ak
+
+import dask_awkward as dak
+from dask_awkward.lib.testutils import assert_eq
+
+
+def test_split_whitespace():
+ a = ak.Array(
+ [
+ ["abc 123", "fooo ooo", "123"],
+ ["hij\tj"],
+ ["lmn op", ""],
+ ["123 456 789", "98765 43210"],
+ ]
+ )
+ b = dak.from_awkward(a, npartitions=2)
+ a2 = ak.str.split_whitespace(a)
+ b2 = dak.str.split_whitespace(b)
+ assert_eq(a2, b2)
+ assert_eq(ak.num(a2, axis=2), ak.num(b2, axis=2))