Add string.wrap APIs to pylibcudf (#16935)

Contributes to #15162

Authors:
  - Matthew Roeschke (https://github.com/mroeschke)
  - Vyas Ramasubramani (https://github.com/vyasr)

Approvers:
  - Vyas Ramasubramani (https://github.com/vyasr)

URL: #16935

docs/cudf/source/user_guide/api_docs/pylibcudf/strings/index.rst

@@ -18,3 +18,4 @@ strings
     slice
     split
     strip
+    wrap

docs/cudf/source/user_guide/api_docs/pylibcudf/strings/wrap.rst

@@ -0,0 +1,6 @@
+====
+wrap
+====
+
+.. automodule:: pylibcudf.strings.wrap
+   :members:

python/cudf/cudf/_lib/strings/wrap.pyx

@@ -1,17 +1,13 @@
 # Copyright (c) 2020-2024, NVIDIA CORPORATION.
 
-from libcpp.memory cimport unique_ptr
-from libcpp.utility cimport move
-
 from cudf.core.buffer import acquire_spill_lock
 
-from pylibcudf.libcudf.column.column cimport column
-from pylibcudf.libcudf.column.column_view cimport column_view
-from pylibcudf.libcudf.strings.wrap cimport wrap as cpp_wrap
 from pylibcudf.libcudf.types cimport size_type
 
 from cudf._lib.column cimport Column
 
+import pylibcudf as plc
+
 
 @acquire_spill_lock()
 def wrap(Column source_strings,
@@ -21,14 +17,8 @@ def wrap(Column source_strings,
     in the Column to be formatted in paragraphs
     with length less than a given `width`.
     """
-
-    cdef unique_ptr[column] c_result
-    cdef column_view source_view = source_strings.view()
-
-    with nogil:
-        c_result = move(cpp_wrap(
-            source_view,
-            width
-        ))
-
-    return Column.from_unique_ptr(move(c_result))
+    plc_result = plc.strings.wrap.wrap(
+        source_strings.to_pylibcudf(mode="read"),
+        width
+    )
+    return Column.from_pylibcudf(plc_result)

python/pylibcudf/pylibcudf/libcudf/strings/wrap.pxd

@@ -9,5 +9,5 @@ from pylibcudf.libcudf.types cimport size_type
 cdef extern from "cudf/strings/wrap.hpp" namespace "cudf::strings" nogil:
 
     cdef unique_ptr[column] wrap(
-        column_view source_strings,
+        column_view input,
         size_type width) except +

python/pylibcudf/pylibcudf/strings/CMakeLists.txt

@@ -30,6 +30,7 @@ set(cython_sources
     slice.pyx
     strip.pyx
     translate.pyx
+    wrap.pyx
 )
 
 set(linked_libraries cudf::cudf)

python/pylibcudf/pylibcudf/strings/__init__.pxd

@@ -18,6 +18,7 @@ from . cimport (
     split,
     strip,
     translate,
+    wrap,
 )
 from .side_type cimport side_type
 
@@ -39,4 +40,5 @@ __all__ = [
     "split",
     "side_type",
     "translate",
+    "wrap",
 ]

python/pylibcudf/pylibcudf/strings/__init__.py

@@ -19,6 +19,7 @@
     split,
     strip,
     translate,
+    wrap,
 )
 from .side_type import SideType
 
@@ -40,4 +41,5 @@
     "split",
     "SideType",
     "translate",
+    "wrap",
 ]

python/pylibcudf/pylibcudf/strings/wrap.pxd

@@ -0,0 +1,7 @@
+# Copyright (c) 2024, NVIDIA CORPORATION.
+
+from pylibcudf.column cimport Column
+from pylibcudf.libcudf.types cimport size_type
+
+
+cpdef Column wrap(Column input, size_type width)

python/pylibcudf/pylibcudf/strings/wrap.pyx

@@ -0,0 +1,42 @@
+# Copyright (c) 2024, NVIDIA CORPORATION.
+
+from libcpp.memory cimport unique_ptr
+from libcpp.utility cimport move
+from pylibcudf.column cimport Column
+from pylibcudf.libcudf.column.column cimport column
+from pylibcudf.libcudf.strings cimport wrap as cpp_wrap
+from pylibcudf.libcudf.types cimport size_type
+
+
+cpdef Column wrap(Column input, size_type width):
+    """
+    Wraps strings onto multiple lines shorter than `width` by
+    replacing appropriate white space with
+    new-line characters (ASCII 0x0A).
+
+    For details, see :cpp:func:`cudf::strings::wrap`.
+
+    Parameters
+    ----------
+    input : Column
+        String column
+
+    width : int
+        Maximum character width of a line within each string
+
+    Returns
+    -------
+    Column
+        Column of wrapped strings
+    """
+    cdef unique_ptr[column] c_result
+
+    with nogil:
+        c_result = move(
+            cpp_wrap.wrap(
+                input.view(),
+                width,
+            )
+        )
+
+    return Column.from_libcudf(move(c_result))

python/pylibcudf/pylibcudf/tests/test_string_wrap.py

@@ -0,0 +1,24 @@
+# Copyright (c) 2024, NVIDIA CORPORATION.
+import textwrap
+
+import pyarrow as pa
+import pylibcudf as plc
+from utils import assert_column_eq
+
+
+def test_wrap():
+    pa_array = pa.array(
+        [
+            "the quick brown fox jumped over the lazy brown dog",
+            "hello, world",
+            None,
+        ]
+    )
+    result = plc.strings.wrap.wrap(plc.interop.from_arrow(pa_array), 12)
+    expected = pa.array(
+        [
+            textwrap.fill(val, 12) if isinstance(val, str) else val
+            for val in pa_array.to_pylist()
+        ]
+    )
+    assert_column_eq(expected, result)