Add io/timezone APIs to pylibcudf (#16771)

Contributes to #15162

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

Approvers:
  - Vyas Ramasubramani (https://github.com/vyasr)
  - GALI PREM SAGAR (https://github.com/galipremsagar)

URL: #16771

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

@@ -19,3 +19,4 @@ I/O Functions
     csv
     json
     parquet
+    timezone

docs/cudf/source/user_guide/api_docs/pylibcudf/io/timezone.rst

@@ -0,0 +1,6 @@
+========
+Timezone
+========
+
+.. automodule:: pylibcudf.io.timezone
+   :members:

python/cudf/cudf/_lib/timezone.pyx

@@ -1,29 +1,10 @@
 # Copyright (c) 2023-2024, NVIDIA CORPORATION.
 
-from libcpp.memory cimport unique_ptr
-from libcpp.optional cimport make_optional
-from libcpp.string cimport string
-from libcpp.utility cimport move
+import pylibcudf as plc
 
-from pylibcudf.libcudf.io.timezone cimport (
-    make_timezone_transition_table as cpp_make_timezone_transition_table,
-)
-from pylibcudf.libcudf.table.table cimport table
-
-from cudf._lib.utils cimport columns_from_unique_ptr
+from cudf._lib.column cimport Column
 
 
 def make_timezone_transition_table(tzdir, tzname):
-    cdef unique_ptr[table] c_result
-    cdef string c_tzdir = tzdir.encode()
-    cdef string c_tzname = tzname.encode()
-
-    with nogil:
-        c_result = move(
-            cpp_make_timezone_transition_table(
-                make_optional[string](c_tzdir),
-                c_tzname
-            )
-        )
-
-    return columns_from_unique_ptr(move(c_result))
+    plc_table = plc.io.timezone.make_timezone_transition_table(tzdir, tzname)
+    return [Column.from_pylibcudf(col) for col in plc_table.columns()]

python/pylibcudf/pylibcudf/io/CMakeLists.txt

@@ -12,7 +12,9 @@
 # the License.
 # =============================================================================
 
-set(cython_sources avro.pyx csv.pyx datasource.pyx json.pyx orc.pyx parquet.pyx types.pyx)
+set(cython_sources avro.pyx csv.pyx datasource.pyx json.pyx orc.pyx parquet.pyx timezone.pyx
+                   types.pyx
+)
 
 set(linked_libraries cudf::cudf)
 rapids_cython_create_modules(

python/pylibcudf/pylibcudf/io/__init__.pxd

@@ -1,5 +1,5 @@
 # Copyright (c) 2024, NVIDIA CORPORATION.
 
 # CSV is removed since it is def not cpdef (to force kw-only arguments)
-from . cimport avro, datasource, json, orc, parquet, types
+from . cimport avro, datasource, json, orc, parquet, timezone, types
 from .types cimport SourceInfo, TableWithMetadata

python/pylibcudf/pylibcudf/io/__init__.py

@@ -1,4 +1,4 @@
 # Copyright (c) 2024, NVIDIA CORPORATION.
 
-from . import avro, csv, datasource, json, orc, parquet, types
+from . import avro, csv, datasource, json, orc, parquet, timezone, types
 from .types import SinkInfo, SourceInfo, TableWithMetadata

python/pylibcudf/pylibcudf/io/timezone.pxd

@@ -0,0 +1,6 @@
+# Copyright (c) 2024, NVIDIA CORPORATION.
+
+from ..table cimport Table
+
+
+cpdef Table make_timezone_transition_table(str tzif_dir, str timezone_name)

python/pylibcudf/pylibcudf/io/timezone.pyx

@@ -0,0 +1,43 @@
+# Copyright (c) 2024, NVIDIA CORPORATION.
+
+from libcpp.memory cimport unique_ptr
+from libcpp.optional cimport make_optional
+from libcpp.string cimport string
+from libcpp.utility cimport move
+from pylibcudf.libcudf.io.timezone cimport (
+    make_timezone_transition_table as cpp_make_timezone_transition_table,
+)
+from pylibcudf.libcudf.table.table cimport table
+
+from ..table cimport Table
+
+
+cpdef Table make_timezone_transition_table(str tzif_dir, str timezone_name):
+    """
+    Creates a transition table to convert ORC timestamps to UTC.
+
+    Parameters
+    ----------
+    tzif_dir : str
+        The directory where the TZif files are located
+    timezone_name : str
+        standard timezone name
+
+    Returns
+    -------
+    Table
+        The transition table for the given timezone.
+    """
+    cdef unique_ptr[table] c_result
+    cdef string c_tzdir = tzif_dir.encode()
+    cdef string c_tzname = timezone_name.encode()
+
+    with nogil:
+        c_result = move(
+            cpp_make_timezone_transition_table(
+                make_optional[string](c_tzdir),
+                c_tzname
+            )
+        )
+
+    return Table.from_libcudf(move(c_result))

python/pylibcudf/pylibcudf/tests/io/test_timezone.py

@@ -0,0 +1,16 @@
+# Copyright (c) 2024, NVIDIA CORPORATION.
+import zoneinfo
+
+import pylibcudf as plc
+import pytest
+
+
+def test_make_timezone_transition_table():
+    if len(zoneinfo.TZPATH) == 0:
+        pytest.skip("No TZPATH available.")
+    tz_path = zoneinfo.TZPATH[0]
+    result = plc.io.timezone.make_timezone_transition_table(
+        tz_path, "America/Los_Angeles"
+    )
+    assert isinstance(result, plc.Table)
+    assert result.num_rows() > 0