From d8f469fb61af1824a9fe175b6c4bcdc1a0ceda3b Mon Sep 17 00:00:00 2001
From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>
Date: Thu, 19 Dec 2024 14:05:04 -0800
Subject: [PATCH] Fix pylibcudf to_arrow with multiple nested data types
 (#17504)

Fixes the following case

```python
In [25]: import pyarrow as pa, pylibcudf as plc

In [26]: pa_array = pa.array([[{"a": 1}]])

In [27]: pa_array.type
Out[27]: ListType(list<item: struct<a: int64>>)

In [28]: plc_table = plc.Table([plc.interop.from_arrow(pa_array)])

In [29]: plc.interop.to_arrow(plc_table)
RuntimeError: CUDF failure at: cpp/src/interop/to_arrow_schema.cpp:146: Number of field names and number of children doesn't match
```

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

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

URL: https://github.com/rapidsai/cudf/pull/17504
---
 python/pylibcudf/pylibcudf/interop.pyx        | 13 +++++++++--
 .../pylibcudf/pylibcudf/tests/test_interop.py | 22 +++++++++++++++++++
 2 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/python/pylibcudf/pylibcudf/interop.pyx b/python/pylibcudf/pylibcudf/interop.pyx
index bd5397ac328..7a102cf0c88 100644
--- a/python/pylibcudf/pylibcudf/interop.pyx
+++ b/python/pylibcudf/pylibcudf/interop.pyx
@@ -273,10 +273,19 @@ cdef void _release_array(object array_capsule) noexcept:
     free(array)
 
 
+def _maybe_create_nested_column_metadata(Column col):
+    return ColumnMetadata(
+        children_meta=[
+            _maybe_create_nested_column_metadata(child) for child in col.children()
+        ]
+    )
+
+
 def _table_to_schema(Table tbl, metadata):
     if metadata is None:
-        metadata = [ColumnMetadata() for _ in range(len(tbl.columns()))]
-    metadata = [ColumnMetadata(m) if isinstance(m, str) else m for m in metadata]
+        metadata = [_maybe_create_nested_column_metadata(col) for col in tbl.columns()]
+    else:
+        metadata = [ColumnMetadata(m) if isinstance(m, str) else m for m in metadata]
 
     cdef vector[column_metadata] c_metadata
     c_metadata.reserve(len(metadata))
diff --git a/python/pylibcudf/pylibcudf/tests/test_interop.py b/python/pylibcudf/pylibcudf/tests/test_interop.py
index af80b6e5978..ca42eacdfdb 100644
--- a/python/pylibcudf/pylibcudf/tests/test_interop.py
+++ b/python/pylibcudf/pylibcudf/tests/test_interop.py
@@ -40,6 +40,28 @@ def test_struct_dtype_roundtrip():
     assert arrow_type == struct_type
 
 
+def test_table_with_nested_dtype_to_arrow():
+    pa_array = pa.array([[{"": 1}]])
+    plc_table = plc.Table([plc.interop.from_arrow(pa_array)])
+    result = plc.interop.to_arrow(plc_table)
+    expected_schema = pa.schema(
+        [
+            pa.field(
+                "",
+                pa.list_(
+                    pa.field(
+                        "",
+                        pa.struct([pa.field("", pa.int64(), nullable=False)]),
+                        nullable=False,
+                    )
+                ),
+                nullable=False,
+            )
+        ]
+    )
+    assert result.schema == expected_schema
+
+
 def test_decimal128_roundtrip():
     decimal_type = pa.decimal128(10, 2)
     plc_type = plc.interop.from_arrow(decimal_type)