Merge branch 'branch-25.04' into cudftestutil-followup

cpp/include/cudf/interop.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2020-2024, NVIDIA CORPORATION.
+ * Copyright (c) 2020-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -327,6 +327,8 @@ unique_device_array_t to_arrow_host(
  *
  * @throws cudf::data_type_error if the input array is not a struct array.
  *
+ * @throws std::overflow_error if the input arrow object exceeds the column size limit.
+ *
  * The conversion will not call release on the input Array.
  *
  * @param schema `ArrowSchema` pointer to describe the type of the data
@@ -367,6 +369,8 @@ std::unique_ptr<cudf::column> from_arrow_column(
  *
  * @throws std::invalid_argument if the device_type is not `ARROW_DEVICE_CPU`
  *
+ * @throws std::overflow_error if the input arrow object exceeds the column size limit.
+ *
  * @throws cudf::data_type_error if the input array is not a struct array,
  * non-struct arrays should be passed to `from_arrow_host_column` instead.
  *
@@ -411,6 +415,8 @@ std::unique_ptr<table> from_arrow_stream(
  *
  * @throws cudf::data_type_error if input arrow data type is not supported in cudf.
  *
+ * @throws std::overflow_error if the input arrow object exceeds the column size limit.
+ *
  * The conversion will not call release on the input Array.
  *
  * @param schema `ArrowSchema` pointer to describe the type of the data
@@ -483,6 +489,8 @@ using unique_table_view_t =
  *
  * @throws cudf::data_type_error if the input arrow data type is not supported.
  *
+ * @throws std::overflow_error if the input arrow object exceeds the column size limit.
+ *
  * Each child of the input struct will be the columns of the resulting table_view.
  *
  * @note The custom deleter used for the unique_ptr to the table_view maintains ownership
@@ -528,6 +536,8 @@ using unique_column_view_t =
  *
  * @throws cudf::data_type_error input arrow data type is not supported.
  *
+ * @throws std::overflow_error if the input arrow object exceeds the column size limit.
+ *
  * @note The custom deleter used for the unique_ptr to the table_view maintains ownership
  * over any memory which is allocated, such as converting boolean columns from the bitmap
  * used by Arrow to the 1-byte per value for cudf.

cpp/src/interop/from_arrow_device.cu

@@ -40,6 +40,10 @@
 #include <nanoarrow/nanoarrow.hpp>
 #include <nanoarrow/nanoarrow_device.h>
 
+#include <cstdint>
+#include <limits>
+#include <stdexcept>
+
 namespace cudf {
 
 namespace detail {
@@ -317,6 +321,11 @@ dispatch_tuple_t get_column(ArrowSchemaView* schema,
                             rmm::cuda_stream_view stream,
                             rmm::device_async_resource_ref mr)
 {
+  CUDF_EXPECTS(
+    input->length <= static_cast<std::int64_t>(std::numeric_limits<cudf::size_type>::max()),
+    "Total number of rows in Arrow column exceeds the column size limit.",
+    std::overflow_error);
+
   return type.id() != type_id::EMPTY
            ? std::move(type_dispatcher(
                type, dispatch_from_arrow_device{}, schema, input, type, skip_mask, stream, mr))

cpp/src/interop/from_arrow_host.cu

@@ -43,6 +43,10 @@
 #include <nanoarrow/nanoarrow.hpp>
 #include <nanoarrow/nanoarrow_device.h>
 
+#include <cstdint>
+#include <limits>
+#include <stdexcept>
+
 namespace cudf {
 namespace detail {
 
@@ -381,6 +385,11 @@ std::unique_ptr<column> get_column_copy(ArrowSchemaView* schema,
                                         rmm::cuda_stream_view stream,
                                         rmm::device_async_resource_ref mr)
 {
+  CUDF_EXPECTS(
+    input->length <= static_cast<std::int64_t>(std::numeric_limits<cudf::size_type>::max()),
+    "Total number of rows in Arrow column exceeds the column size limit.",
+    std::overflow_error);
+
   return type.id() != type_id::EMPTY
            ? std::move(type_dispatcher(
                type, dispatch_copy_from_arrow_host{stream, mr}, schema, input, type, skip_mask))

cpp/src/interop/from_arrow_stream.cu

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2024, NVIDIA CORPORATION.
+ * Copyright (c) 2024-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -121,6 +121,7 @@ std::unique_ptr<table> from_arrow_stream(ArrowArrayStream* input,
 
   schema.release(&schema);
 
+  if (chunks.size() == 1) { return std::move(chunks[0]); }
   auto chunk_views = std::vector<table_view>{};
   chunk_views.reserve(chunks.size());
   std::transform(