From 08c39f36d3af50d4f6c423ee780ef2db06953ee6 Mon Sep 17 00:00:00 2001
From: "Ankit.Ahlawat@ibm.com" <Ankit.Ahlawat@ibm.com>
Date: Fri, 22 May 2026 12:24:57 +0530
Subject: [PATCH 1/2] GH-50012[Python]: Fix list_ storage crashes when values
 exceed int32 offsets

---
 python/pyarrow/array.pxi                    | 10 ++-
 python/pyarrow/tests/test_extension_type.py | 75 +++++++++++++++++++++
 2 files changed, 84 insertions(+), 1 deletion(-)

diff --git a/python/pyarrow/array.pxi b/python/pyarrow/array.pxi
index ecdbb342d3e2..7c3b634ea6bc 100644
--- a/python/pyarrow/array.pxi
+++ b/python/pyarrow/array.pxi
@@ -401,7 +401,15 @@ def array(object obj, type=None, mask=None, size=None, from_pandas=None,
             result = _sequence_to_array(obj, mask, size, type, pool, c_from_pandas)
 
     if extension_type is not None:
-        result = ExtensionArray.from_storage(extension_type, result)
+        if isinstance(result, ChunkedArray):
+            # Handle ChunkedArray case (e.g., when data overflows int32)
+            chunks = []
+            for chunk in result.chunks:
+                ext_chunk = ExtensionArray.from_storage(extension_type, chunk)
+                chunks.append(ext_chunk)
+            result = chunked_array(chunks, type=extension_type)
+        else:
+            result = ExtensionArray.from_storage(extension_type, result)
     return result
 
 
diff --git a/python/pyarrow/tests/test_extension_type.py b/python/pyarrow/tests/test_extension_type.py
index 465b556876b4..679370a55ea0 100644
--- a/python/pyarrow/tests/test_extension_type.py
+++ b/python/pyarrow/tests/test_extension_type.py
@@ -2120,3 +2120,78 @@ def test_json(storage_type, pickle_module):
                 pa.ArrowInvalid,
                 match=f"Invalid storage type for JsonExtensionType: {storage_type}"):
             pa.json_(storage_type)
+
+
+class ListExtensionType(pa.ExtensionType):
+    """Extension type with a list field for testing int32 overflow."""
+
+    def __init__(self):
+        super().__init__(
+            pa.struct({"data": pa.list_(pa.uint8())}),
+            "test_list_ext",
+        )
+
+    def __arrow_ext_serialize__(self):
+        return b""
+
+    @classmethod
+    def __arrow_ext_deserialize__(cls, storage_type, serialized):
+        return cls()
+
+
+@pytest.mark.large_memory
+def test_extension_type_list_overflow():
+    """
+    Test that extension types with list fields handle int32 offset overflow.
+    """
+    try:
+        pa.register_extension_type(ListExtensionType())
+    except pa.ArrowKeyError:
+        pass
+
+    schema = pa.schema({"col": ListExtensionType()})
+
+    # Create data that exceeds int32 max cumulative values
+    # 5 rows × 500M values = 2.5B > int32 max (2,147,483,647)
+    arr = np.zeros(500_000_000, dtype=np.uint8)
+    rows = [{"col": {"data": arr}} for _ in range(5)]
+
+    result = pa.Table.from_pylist(rows, schema=schema)
+
+    assert result.num_rows == 5
+    assert result.num_columns == 1
+    assert result.schema[0].type == ListExtensionType()
+
+    col = result.column(0)
+    assert isinstance(col, pa.ChunkedArray)
+    assert col.type == ListExtensionType()
+
+    for chunk_idx in range(col.num_chunks):
+        chunk_data = col.chunk(chunk_idx)
+        assert chunk_data.type == ListExtensionType()
+
+
+def test_extension_type_no_overflow():
+    """Test that extension types work normally when there's no overflow."""
+    try:
+        pa.register_extension_type(ListExtensionType())
+    except pa.ArrowKeyError:
+        # Already registered
+        pass
+
+    schema = pa.schema({"col": ListExtensionType()})
+
+    # Small data that won't overflow
+    arr = np.array([1, 2, 3], dtype=np.uint8)
+    rows = [{"col": {"data": arr}} for _ in range(3)]
+
+    result = pa.Table.from_pylist(rows, schema=schema)
+
+    assert result.num_rows == 3
+    assert result.num_columns == 1
+    assert result.schema[0].type == ListExtensionType()
+
+    # The column should be a ChunkedArray with a single chunk
+    col = result.column(0)
+    assert isinstance(col, pa.ChunkedArray)
+    assert col.type == ListExtensionType()

From c554be546fbf388548d4c34921b58b55c089fdaa Mon Sep 17 00:00:00 2001
From: "Ankit.Ahlawat@ibm.com" <Ankit.Ahlawat@ibm.com>
Date: Fri, 22 May 2026 13:02:59 +0530
Subject: [PATCH 2/2] GH-50012[Python] Add NumPy decorator to extension type
 tests

---
 python/pyarrow/tests/test_extension_type.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/python/pyarrow/tests/test_extension_type.py b/python/pyarrow/tests/test_extension_type.py
index 679370a55ea0..e9387c7088cc 100644
--- a/python/pyarrow/tests/test_extension_type.py
+++ b/python/pyarrow/tests/test_extension_type.py
@@ -2140,6 +2140,7 @@ def __arrow_ext_deserialize__(cls, storage_type, serialized):
 
 
 @pytest.mark.large_memory
+@pytest.mark.numpy
 def test_extension_type_list_overflow():
     """
     Test that extension types with list fields handle int32 offset overflow.
@@ -2171,6 +2172,7 @@ def test_extension_type_list_overflow():
         assert chunk_data.type == ListExtensionType()
 
 
+@pytest.mark.numpy
 def test_extension_type_no_overflow():
     """Test that extension types work normally when there's no overflow."""
     try: