Add string.attributes APIs to pylibcudf (#16785)

Contributes to #15162

Authors:
  - Matthew Roeschke (https://github.com/mroeschke)
  - Matthew Murray (https://github.com/Matt711)

Approvers:
  - Matthew Murray (https://github.com/Matt711)
  - Vyas Ramasubramani (https://github.com/vyasr)

URL: #16785

python/cudf/cudf/_lib/strings/attributes.pyx

@@ -2,33 +2,21 @@
 
 from cudf.core.buffer import acquire_spill_lock
 
-from libcpp.memory cimport unique_ptr
-from libcpp.utility cimport move
-
-from pylibcudf.libcudf.column.column cimport column
-from pylibcudf.libcudf.column.column_view cimport column_view
-from pylibcudf.libcudf.strings.attributes cimport (
-    code_points as cpp_code_points,
-    count_bytes as cpp_count_bytes,
-    count_characters as cpp_count_characters,
-)
-
 from cudf._lib.column cimport Column
 
+import pylibcudf as plc
+
 
 @acquire_spill_lock()
 def count_characters(Column source_strings):
     """
     Returns an integer numeric column containing the
     length of each string in characters.
     """
-    cdef unique_ptr[column] c_result
-    cdef column_view source_view = source_strings.view()
-
-    with nogil:
-        c_result = move(cpp_count_characters(source_view))
-
-    return Column.from_unique_ptr(move(c_result))
+    plc_column = plc.strings.attributes.count_characters(
+        source_strings.to_pylibcudf(mode="read")
+    )
+    return Column.from_pylibcudf(plc_column)
 
 
 @acquire_spill_lock()
@@ -37,13 +25,10 @@ def count_bytes(Column source_strings):
     Returns an integer numeric column containing the
     number of bytes of each string.
     """
-    cdef unique_ptr[column] c_result
-    cdef column_view source_view = source_strings.view()
-
-    with nogil:
-        c_result = move(cpp_count_bytes(source_view))
-
-    return Column.from_unique_ptr(move(c_result))
+    plc_column = plc.strings.attributes.count_bytes(
+        source_strings.to_pylibcudf(mode="read")
+    )
+    return Column.from_pylibcudf(plc_column)
 
 
 @acquire_spill_lock()
@@ -52,10 +37,7 @@ def code_points(Column source_strings):
     Creates a numeric column with code point values (integers)
     for each character of each string.
     """
-    cdef unique_ptr[column] c_result
-    cdef column_view source_view = source_strings.view()
-
-    with nogil:
-        c_result = move(cpp_code_points(source_view))
-
-    return Column.from_unique_ptr(move(c_result))
+    plc_column = plc.strings.attributes.code_points(
+        source_strings.to_pylibcudf(mode="read")
+    )
+    return Column.from_pylibcudf(plc_column)

python/pylibcudf/pylibcudf/strings/CMakeLists.txt

@@ -13,8 +13,21 @@
 # =============================================================================
 
 set(cython_sources
-    capitalize.pyx case.pyx char_types.pyx contains.pyx extract.pyx find.pyx findall.pyx
-    regex_flags.pyx regex_program.pyx repeat.pyx replace.pyx side_type.pyx slice.pyx strip.pyx
+    attributes.pyx
+    capitalize.pyx
+    case.pyx
+    char_types.pyx
+    contains.pyx
+    extract.pyx
+    find.pyx
+    findall.pyx
+    regex_flags.pyx
+    regex_program.pyx
+    repeat.pyx
+    replace.pyx
+    side_type.pyx
+    slice.pyx
+    strip.pyx
 )
 
 set(linked_libraries cudf::cudf)

python/pylibcudf/pylibcudf/strings/__init__.pxd

@@ -1,6 +1,7 @@
 # Copyright (c) 2024, NVIDIA CORPORATION.
 
 from . cimport (
+    attributes,
     capitalize,
     case,
     char_types,
@@ -16,3 +17,21 @@ from . cimport (
     strip,
 )
 from .side_type cimport side_type
+
+__all__ = [
+    "attributes",
+    "capitalize",
+    "case",
+    "char_types",
+    "contains",
+    "convert",
+    "extract",
+    "find",
+    "findall",
+    "regex_flags",
+    "regex_program",
+    "replace",
+    "slice",
+    "strip",
+    "side_type",
+]

python/pylibcudf/pylibcudf/strings/__init__.py

@@ -1,6 +1,7 @@
 # Copyright (c) 2024, NVIDIA CORPORATION.
 
 from . import (
+    attributes,
     capitalize,
     case,
     char_types,
@@ -17,3 +18,21 @@
     strip,
 )
 from .side_type import SideType
+
+__all__ = [
+    "attributes",
+    "capitalize",
+    "case",
+    "char_types",
+    "contains",
+    "convert",
+    "extract",
+    "find",
+    "findall",
+    "regex_flags",
+    "regex_program",
+    "replace",
+    "slice",
+    "strip",
+    "SideType",
+]

python/pylibcudf/pylibcudf/strings/attributes.pxd

@@ -0,0 +1,10 @@
+# Copyright (c) 2024, NVIDIA CORPORATION.
+
+from pylibcudf.column cimport Column
+
+
+cpdef Column count_characters(Column source_strings)
+
+cpdef Column count_bytes(Column source_strings)
+
+cpdef Column code_points(Column source_strings)

python/pylibcudf/pylibcudf/strings/attributes.pyx

@@ -0,0 +1,76 @@
+# 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 attributes as cpp_attributes
+
+
+cpdef Column count_characters(Column source_strings):
+    """
+    Returns a column containing character lengths of each string
+    in the given column.
+
+    Parameters
+    ----------
+    source_strings : Column
+        Column of strings.
+
+    Returns
+    -------
+    Column
+        New column with lengths for each string
+    """
+    cdef unique_ptr[column] c_result
+
+    with nogil:
+        c_result = move(cpp_attributes.count_characters(source_strings.view()))
+
+    return Column.from_libcudf(move(c_result))
+
+
+cpdef Column count_bytes(Column source_strings):
+    """
+    Returns a column containing byte lengths of each string
+    in the given column.
+
+    Parameters
+    ----------
+    source_strings : Column
+        Column of strings.
+
+    Returns
+    -------
+    Column
+        New column with the number of bytes for each string
+    """
+    cdef unique_ptr[column] c_result
+
+    with nogil:
+        c_result = move(cpp_attributes.count_bytes(source_strings.view()))
+
+    return Column.from_libcudf(move(c_result))
+
+
+cpdef Column code_points(Column source_strings):
+    """
+    Creates a numeric column with code point values (integers)
+    for each character of each string.
+
+    Parameters
+    ----------
+    source_strings : Column
+        Column of strings.
+
+    Returns
+    -------
+    Column
+        New column with code point integer values for each character
+    """
+    cdef unique_ptr[column] c_result
+
+    with nogil:
+        c_result = move(cpp_attributes.code_points(source_strings.view()))
+
+    return Column.from_libcudf(move(c_result))

python/pylibcudf/pylibcudf/tests/test_string_attributes.py

@@ -0,0 +1,32 @@
+# Copyright (c) 2024, NVIDIA CORPORATION.
+
+import pyarrow as pa
+import pyarrow.compute as pc
+import pylibcudf as plc
+import pytest
+from utils import assert_column_eq
+
+
+@pytest.fixture()
+def str_data():
+    pa_data = pa.array(["A", None])
+    return pa_data, plc.interop.from_arrow(pa_data)
+
+
+def test_count_characters(str_data):
+    result = plc.strings.attributes.count_characters(str_data[1])
+    expected = pc.utf8_length(str_data[0])
+    assert_column_eq(expected, result)
+
+
+def test_count_bytes(str_data):
+    result = plc.strings.attributes.count_characters(str_data[1])
+    expected = pc.binary_length(str_data[0])
+    assert_column_eq(expected, result)
+
+
+def test_code_points(str_data):
+    result = plc.strings.attributes.code_points(str_data[1])
+    exp_data = [ord(str_data[0].to_pylist()[0])]
+    expected = pa.chunked_array([exp_data], type=pa.int32())
+    assert_column_eq(expected, result)