Automate include grouping order in .clang-format

.clang-format

@@ -71,8 +71,30 @@ ForEachMacros:
   - foreach
   - Q_FOREACH
   - BOOST_FOREACH
-IncludeBlocks: Preserve
-IncludeIsMainRegex: '([-_](test|unittest))?$'
+IncludeBlocks: Regroup
+IncludeCategories:
+  - Regex:           '^"' # quoted includes
+    Priority:        1
+  - Regex:           '^<(benchmarks|tests)/' # benchmark includes
+    Priority:        2
+  - Regex:           '^<cudf_test/' # cuDF includes
+    Priority:        3
+  - Regex:           '^<cudf/' # cuDF includes
+    Priority:        4
+  - Regex:           '^<(nvtext|cudf_kafka)' # other libcudf includes
+    Priority:        5
+  - Regex:           '^<(cugraph|cuml|cuspatial|raft|kvikio)' # Other RAPIDS includes
+    Priority:        6
+  - Regex:           '^<rmm/' # RMM includes
+    Priority:        7
+  - Regex:           '^<(thrust|cub|cuda)/' # CCCL includes
+    Priority:        8
+  - Regex:           '^<(cooperative_groups|cuco|cuda.h|cuda_runtime|device_types|math_constants|nvtx3)' # CUDA includes
+    Priority:        8
+  - Regex:           '^<.*\..*' # other system includes (e.g. with a '.')
+    Priority:        9
+  - Regex:           '^<[^.]+' # STL includes (no '.')
+    Priority:        10
 IndentCaseLabels: true
 IndentPPDirectives: None
 IndentWidth:     2

cpp/benchmarks/common/generate_input.cu

@@ -33,6 +33,7 @@
 #include <rmm/device_uvector.hpp>
 #include <rmm/mr/device/per_device_resource.hpp>
 
+#include <cuda/functional>
 #include <thrust/binary_search.h>
 #include <thrust/copy.h>
 #include <thrust/device_ptr.h>
@@ -53,8 +54,6 @@
 #include <thrust/transform.h>
 #include <thrust/tuple.h>
 
-#include <cuda/functional>
-
 #include <algorithm>
 #include <cstdint>
 #include <memory>

cpp/benchmarks/fixture/benchmark_fixture.hpp

@@ -16,14 +16,15 @@
 
 #pragma once
 
-#include <benchmark/benchmark.h>
 #include <rmm/cuda_device.hpp>
 #include <rmm/mr/device/cuda_memory_resource.hpp>
 #include <rmm/mr/device/owning_wrapper.hpp>
 #include <rmm/mr/device/per_device_resource.hpp>
 #include <rmm/mr/device/pool_memory_resource.hpp>
 #include <rmm/mr/device/statistics_resource_adaptor.hpp>
 
+#include <benchmark/benchmark.h>
+
 namespace cudf {
 
 namespace {

cpp/benchmarks/io/cuio_common.cpp

@@ -15,16 +15,17 @@
  */
 
 #include <benchmarks/io/cuio_common.hpp>
+
 #include <cudf/detail/utilities/integer_utils.hpp>
 #include <cudf/detail/utilities/logger.hpp>
 
+#include <unistd.h>
+
 #include <cstdio>
 #include <fstream>
 #include <numeric>
 #include <string>
 
-#include <unistd.h>
-
 temp_directory const cuio_source_sink_pair::tmpdir{"cudf_gbench"};
 
 std::string random_file_in_dir(std::string const& dir_path)

cpp/benchmarks/io/fst.cu

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2022-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2022-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -14,11 +14,10 @@
  * limitations under the License.
  */
 
-#include <benchmarks/common/generate_input.hpp>
-
-#include <io/fst/lookup_tables.cuh>
-#include <io/utilities/hostdevice_vector.hpp>  //TODO find better replacement
+#include "io/fst/lookup_tables.cuh"
+#include "io/utilities/hostdevice_vector.hpp"  //TODO find better replacement
 
+#include <benchmarks/common/generate_input.hpp>
 #include <tests/io/fst/common.hpp>
 
 #include <cudf/scalar/scalar_factories.hpp>

cpp/benchmarks/io/json/nested_json.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2022-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2022-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -14,11 +14,10 @@
  * limitations under the License.
  */
 
+#include "io/json/nested_json.hpp"
+
 #include <benchmarks/common/generate_input.hpp>
 #include <benchmarks/fixture/benchmark_fixture.hpp>
-
-#include <io/json/nested_json.hpp>
-
 #include <tests/io/fst/common.hpp>
 
 #include <cudf/scalar/scalar_factories.hpp>

cpp/benchmarks/iterator/iterator.cu

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -27,7 +27,6 @@
 #include <rmm/device_uvector.hpp>
 
 #include <cub/device/device_reduce.cuh>
-
 #include <thrust/execution_policy.h>
 #include <thrust/iterator/counting_iterator.h>
 #include <thrust/iterator/transform_iterator.h>

cpp/benchmarks/join/join_common.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2021-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -31,14 +31,14 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/error.hpp>
 
-#include <nvbench/nvbench.cuh>
-
 #include <thrust/functional.h>
 #include <thrust/iterator/counting_iterator.h>
 #include <thrust/iterator/transform_iterator.h>
 #include <thrust/random/linear_congruential_engine.h>
 #include <thrust/random/uniform_int_distribution.h>
 
+#include <nvbench/nvbench.cuh>
+
 #include <vector>
 
 struct null75_generator {

cpp/benchmarks/merge/merge.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2020-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2020-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -16,6 +16,7 @@
 
 #include <benchmarks/fixture/benchmark_fixture.hpp>
 #include <benchmarks/synchronization/synchronization.hpp>
+
 #include <cudf_test/column_wrapper.hpp>
 
 #include <cudf/column/column.hpp>

cpp/benchmarks/sort/rank_lists.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2023, NVIDIA CORPORATION.
+ * Copyright (c) 2023-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -18,10 +18,10 @@
 
 #include <benchmarks/common/generate_nested_types.hpp>
 
-#include <cudf/sorting.hpp>
-
 #include <cudf_test/column_utilities.hpp>
 
+#include <cudf/sorting.hpp>
+
 #include <nvbench/nvbench.cuh>
 
 template <cudf::rank_method method>

cpp/benchmarks/sort/rank_structs.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2023, NVIDIA CORPORATION.
+ * Copyright (c) 2023-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -15,6 +15,7 @@
  */
 
 #include "rank_types_common.hpp"
+
 #include <benchmarks/common/generate_nested_types.hpp>
 
 #include <cudf/sorting.hpp>

cpp/benchmarks/stream_compaction/apply_boolean_mask.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -15,11 +15,12 @@
  */
 
 #include <benchmarks/common/generate_input.hpp>
-#include <fixture/benchmark_fixture.hpp>
-#include <synchronization/synchronization.hpp>
 
 #include <cudf/stream_compaction.hpp>
 
+#include <fixture/benchmark_fixture.hpp>
+#include <synchronization/synchronization.hpp>
+
 namespace {
 
 constexpr cudf::size_type hundredM      = 1e8;

cpp/benchmarks/string/string_bench_args.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021, NVIDIA CORPORATION.
+ * Copyright (c) 2021-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -15,10 +15,10 @@
  */
 #pragma once
 
-#include <benchmark/benchmark.h>
-
 #include <cudf/types.hpp>
 
+#include <benchmark/benchmark.h>
+
 #include <limits>
 
 /**

cpp/benchmarks/synchronization/synchronization.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2022, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -27,9 +27,10 @@
  * It is built on top of the idea of Resource acquisition is initialization
  * (RAII). In the following we show a minimal example of how to use this class.
 
-    #include <benchmark/benchmark.h>
     #include <cudf/utilities/default_stream.hpp>
 
+    #include <benchmark/benchmark.h>
+
     static void sample_cuda_benchmark(benchmark::State& state) {
 
       for (auto _ : state){
@@ -60,14 +61,12 @@
 
 #pragma once
 
-// Google Benchmark library
-#include <benchmark/benchmark.h>
-
 #include <cudf/types.hpp>
 #include <cudf/utilities/default_stream.hpp>
 
 #include <rmm/cuda_stream_view.hpp>
 
+#include <benchmark/benchmark.h>
 #include <driver_types.h>
 
 class cuda_event_timer {

cpp/benchmarks/text/edit_distance.cpp

@@ -20,10 +20,10 @@
 
 #include <nvtext/edit_distance.hpp>
 
-#include <nvbench/nvbench.cuh>
-
 #include <rmm/device_buffer.hpp>
 
+#include <nvbench/nvbench.cuh>
+
 static void bench_edit_distance(nvbench::state& state)
 {
   auto const num_rows  = static_cast<cudf::size_type>(state.get_int64("num_rows"));

cpp/benchmarks/text/hash_ngrams.cpp

@@ -20,10 +20,10 @@
 
 #include <nvtext/generate_ngrams.hpp>
 
-#include <nvbench/nvbench.cuh>
-
 #include <rmm/device_buffer.hpp>
 
+#include <nvbench/nvbench.cuh>
+
 static void bench_hash_ngrams(nvbench::state& state)
 {
   auto const num_rows  = static_cast<cudf::size_type>(state.get_int64("num_rows"));

cpp/benchmarks/text/jaccard.cpp

@@ -21,10 +21,10 @@
 
 #include <nvtext/jaccard.hpp>
 
-#include <nvbench/nvbench.cuh>
-
 #include <rmm/device_buffer.hpp>
 
+#include <nvbench/nvbench.cuh>
+
 static void bench_jaccard(nvbench::state& state)
 {
   auto const num_rows        = static_cast<cudf::size_type>(state.get_int64("num_rows"));

cpp/benchmarks/text/minhash.cpp

@@ -20,10 +20,10 @@
 
 #include <nvtext/minhash.hpp>
 
-#include <nvbench/nvbench.cuh>
-
 #include <rmm/device_buffer.hpp>
 
+#include <nvbench/nvbench.cuh>
+
 static void bench_minhash(nvbench::state& state)
 {
   auto const num_rows   = static_cast<cudf::size_type>(state.get_int64("num_rows"));

cpp/benchmarks/text/vocab.cpp

@@ -20,13 +20,13 @@
 #include <cudf_test/column_wrapper.hpp>
 
 #include <cudf/reduction.hpp>
-#include <nvtext/tokenize.hpp>
-
 #include <cudf/scalar/scalar.hpp>
 #include <cudf/strings/char_types/char_types.hpp>
 #include <cudf/strings/strings_column_view.hpp>
 #include <cudf/utilities/default_stream.hpp>
 
+#include <nvtext/tokenize.hpp>
+
 #include <nvbench/nvbench.cuh>
 
 static void bench_vocab_tokenize(nvbench::state& state)

cpp/examples/strings/custom_optimized.cu

@@ -23,10 +23,9 @@
 #include <rmm/device_uvector.hpp>
 #include <rmm/exec_policy.hpp>
 
-#include <thrust/scan.h>
-
 #include <cuda_runtime.h>
 #include <nvtx3/nvToolsExt.h>
+#include <thrust/scan.h>
 
 /**
  * @brief Computes the size of each output row

cpp/include/cudf/ast/detail/operators.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2020-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2020-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -20,9 +20,8 @@
 #include <cudf/utilities/error.hpp>
 #include <cudf/utilities/type_dispatcher.hpp>
 
-#include <thrust/optional.h>
-
 #include <cuda/std/type_traits>
+#include <thrust/optional.h>
 
 #include <cmath>
 #include <type_traits>