Normalize whitespace (#6238)

This PR applies `pre-commit` hooks to normalize whitespace (trimming trailing whitespace and enforcing consistent end-of-file newlines).

These rules are already applied to most other RAPIDS repos, so this PR aligns with the norm in RAPIDS.

Authors:
  - Bradley Dice (https://github.com/bdice)

Approvers:
  - Jake Awe (https://github.com/AyodeAwe)
  - Vyas Ramasubramani (https://github.com/vyasr)
  - Dante Gama Dessavre (https://github.com/dantegd)

URL: #6238

Author: bdice

.github/labeler.yml

@@ -5,7 +5,7 @@
 Cython / Python:
   - 'python/**'
   - 'notebooks/**'
-  
+
 CUDA/C++:
   - 'cpp/**'
 
@@ -18,4 +18,3 @@ ci:
 
 conda:
   - 'conda/**'
-  

.pre-commit-config.yaml

@@ -1,7 +1,12 @@
 ---
-# Copyright (c) 2023, NVIDIA CORPORATION.
+# Copyright (c) 2023-2025, NVIDIA CORPORATION.
 
 repos:
+    - repo: https://github.com/pre-commit/pre-commit-hooks
+      rev: v5.0.0
+      hooks:
+          - id: trailing-whitespace
+          - id: end-of-file-fixer
     - repo: https://github.com/psf/black
       rev: 22.10.0
       hooks:

LICENSE

@@ -187,7 +187,7 @@
       identification within third-party archives.
 
    Copyright 2018 NVIDIA CORPORATION
-   
+
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.
    You may obtain a copy of the License at

ci/checks/black_lists.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-# Copyright (c) 2019-2023, NVIDIA CORPORATION.
+# Copyright (c) 2019-2025, NVIDIA CORPORATION.
 ##########################################
 # cuML black listed function call Tester #
 ##########################################
@@ -40,7 +40,7 @@ done
 
 for cond_black_listed in cudaMemcpy cudaMemset; do
     TMP=`git --no-pager diff --ignore-submodules -w --minimal -U0 -S"$cond_black_listed" $PR_TARGET_BRANCH | grep '^+' | grep -v '^+++' | grep -P "$cond_black_listed(?!Async)"`
-    
+
     if [ "$TMP" != "" ]; then
         for filename in `git --no-pager diff --ignore-submodules -w --minimal --name-only -S"$cond_black_listed" $PR_TARGET_BRANCH`; do
             basefilename=$(basename -- "$filename")

codecov.yml

@@ -11,4 +11,4 @@ comment:
 # undocumented option:
 # https://community.codecov.io/t/unable-to-determine-a-parent-commit-to-compare-against-in-base-branch-after-squash-and-merge/2480/15
 codecov:
-  allow_coverage_offsets: true
+  allow_coverage_offsets: true

cpp/.clang-tidy

@@ -4,7 +4,7 @@ WarningsAsErrors: '*'
 HeaderFilterRegex: ''
 AnalyzeTemporaryDtors: false
 FormatStyle:     none
-CheckOptions:    
+CheckOptions:
   - key:             cert-dcl16-c.NewSuffixes
     value:           'L;LL;LU;LLU'
   - key:             cppcoreguidelines-non-private-member-variables-in-classes.IgnoreClassesWithAllMemberVariablesBeingPublic
@@ -142,4 +142,3 @@ CheckOptions:
   - key:             readability-identifier-naming.TypedefSuffix
     value:           ''
 ...
-

cpp/CMakeLists.txt

@@ -115,7 +115,7 @@ message(VERBOSE "CUML_CPP: RMM_LOGGING_LEVEL = '${RMM_LOGGING_LEVEL}'.")
 set(LIBCUML_LOGGING_LEVEL
     "DEBUG"
     CACHE STRING "Choose the logging level."
-)                                                                                                
+)
 set_property(
   CACHE LIBCUML_LOGGING_LEVEL PROPERTY STRINGS "TRACE" "DEBUG" "INFO" "WARN" "ERROR" "CRITICAL"
                                        "OFF"

cpp/cmake/modules/ConfigureAlgorithms.cmake

@@ -1,5 +1,5 @@
 #=============================================================================
-# Copyright (c) 2022-2024, NVIDIA CORPORATION.
+# Copyright (c) 2022-2025, NVIDIA CORPORATION.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -129,4 +129,3 @@ else()
         set(LINK_CUVS ON)
     endif()
 endif()
-

cpp/examples/symreg/README.md

@@ -1,5 +1,5 @@
 # symbolic regression
-This subfolder contains an example on how perform symbolic regression in cuML (from C++) 
+This subfolder contains an example on how perform symbolic regression in cuML (from C++)
 There are two `CMakeLists.txt` in this folder:
 1. `CMakeLists.txt` (default) which is included when building cuML
 2. `CMakeLists_standalone.txt` as an example for a stand alone project linking to `libcuml.so`
@@ -11,7 +11,7 @@ $ cmake .. -DCUML_LIBRARY_DIR=/path/to/directory/with/libcuml.so -DCUML_INCLUDE_
 ```
 Then build with `make` or `ninja`
 ```
-$ make  
+$ make
 Scanning dependencies of target raft
 [ 10%] Creating directories for 'raft'
 [ 20%] Performing download step (git clone) for 'raft'
@@ -28,7 +28,7 @@ Scanning dependencies of target symreg_example
 [100%] Linking CUDA executable symreg_example
 [100%] Built target symreg_example
 ```
-`CMakeLists_standalone.txt` also loads a minimal set of header dependencies(namely [raft](https://github.com/rapidsai/raft) and [cub](https://github.com/NVIDIA/cub)) if they are not detected in the system. 
+`CMakeLists_standalone.txt` also loads a minimal set of header dependencies(namely [raft](https://github.com/rapidsai/raft) and [cub](https://github.com/NVIDIA/cub)) if they are not detected in the system.
 ## Run
 
 1. Generate a toy training and test dataset
@@ -53,7 +53,7 @@ $ ./symreg_example -n_cols 2                   \
                    -stopping_criteria 0.01     \
                    -p_crossover 0.7            \
                    -p_subtree 0.1              \
-                   -p_hoist 0.05               \ 
+                   -p_hoist 0.05               \
                    -p_point 0.1                \
                    -parsimony_coefficient 0.01
 ```
@@ -77,11 +77,11 @@ Finished training for 4 generations.
            Best AST equation :( add( sub( mult( X0, X0) , div( X1, X1) ) , sub( X1, mult( X1, X1) ) ) )
 Training time =    626.658ms
 ***************************************
-Beginning Inference on Test dataset... 
+Beginning Inference on Test dataset...
 Inference score on test set = 5.29271e-08
 Inference time =    0.35248ms
 Some Predicted test values:
 -1.65061;-1.64081;-0.91711;-2.28976;-0.280688;
 Corresponding Actual test values:
 -1.65061;-1.64081;-0.91711;-2.28976;-0.280688;
-```
+```

cpp/include/cuml/common/pinned_host_vector.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2021-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -61,4 +61,4 @@ class pinned_host_vector {
   std::size_t size_;
 };
 
-}  // namespace ML
+}  // namespace ML

cpp/include/cuml/experimental/fil/README.md

@@ -3,11 +3,11 @@ RAPIDS Forest Inference Library (FIL) provides accelerated inference for
 tree-based machine learning models. Unlike packages like XGBoost,
 LightGBM, or even Scikit-Learn/cuML's random forest implementations, FIL
 cannot be used to _train_ forest models. Instead, its goal is to speed up
-inference using forest models trained by all of those packages. 
+inference using forest models trained by all of those packages.
 
 This directory contains an experimental new implementation of FIL which
 provides both CPU and GPU execution. Its GPU implementation also offers
-improved performance relative to the existing implementation in many but not all cases. 
+improved performance relative to the existing implementation in many but not all cases.
 
 For Python usage information and more extensive information on
 parameter-tuning and other end-user functionality, check out

cpp/include/cuml/solvers/params.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2018, NVIDIA CORPORATION.
+ * Copyright (c) 2018-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -33,4 +33,4 @@ enum loss_funct {
 
 enum penalty { NONE, L1, L2, ELASTICNET };
 
-};  // namespace ML
+};  // namespace ML

cpp/include/cuml/tsa/holtwinters_params.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2021, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -46,4 +46,4 @@ struct OptimParams {
 
 enum Norm { L0, L1, L2, LINF };
 
-}  // namespace ML
+}  // namespace ML

cpp/src/dbscan/vertexdeg/pack.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2018-2024, NVIDIA CORPORATION.
+ * Copyright (c) 2018-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -65,4 +65,4 @@ struct Pack {
 
 }  // namespace VertexDeg
 }  // namespace Dbscan
-}  // namespace ML
+}  // namespace ML

cpp/src/decisiontree/batched-levelalgo/bins.cuh

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2022, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -73,4 +73,4 @@ struct AggregateBin {
   }
 };
 }  // namespace DT
-}  // namespace ML
+}  // namespace ML

cpp/src/genetic/constants.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021, NVIDIA CORPORATION.
+ * Copyright (c) 2021-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -28,4 +28,4 @@ const int GENE_TPB = 256;
 const int MAX_STACK_SIZE = 20;
 
 }  // namespace genetic
-}  // namespace cuml
+}  // namespace cuml

cpp/src/glm/qn/mg/glm_base_mg.cuh

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2023-2024, NVIDIA CORPORATION.
+ * Copyright (c) 2023-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -204,4 +204,4 @@ struct GLMWithDataMG : ML::GLM::detail::GLMWithData<T, GLMObjective> {
 };
 };  // namespace opg
 };  // namespace GLM
-};  // namespace ML
+};  // namespace ML

cpp/src/glm/qn/mg/standardization.cuh

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2023-2024, NVIDIA CORPORATION.
+ * Copyright (c) 2023-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -377,4 +377,4 @@ struct Standardizer {
 
 };  // namespace opg
 };  // namespace GLM
-};  // namespace ML
+};  // namespace ML

cpp/src/hdbscan/detail/kernels/membership.cuh

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021, NVIDIA CORPORATION.
+ * Copyright (c) 2021-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -70,4 +70,4 @@ struct probabilities_functor {
 };  // namespace Membership
 };  // namespace detail
 };  // namespace HDBSCAN
-};  // namespace ML
+};  // namespace ML

cpp/src/hdbscan/detail/kernels/stabilities.cuh

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021, NVIDIA CORPORATION.
+ * Copyright (c) 2021-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -61,4 +61,4 @@ struct stabilities_functor {
 };  // namespace Stability
 };  // namespace detail
 };  // namespace HDBSCAN
-};  // namespace ML
+};  // namespace ML

cpp/src/hdbscan/detail/predict.cuh

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2022-2024, NVIDIA CORPORATION.
+ * Copyright (c) 2022-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -272,4 +272,4 @@ void approximate_predict(const raft::handle_t& handle,
 };  // end namespace Predict
 };  // end namespace detail
 };  // end namespace HDBSCAN
-};  // end namespace ML
+};  // end namespace ML

cpp/src/tsne/kluger_lab_license.txt

@@ -132,4 +132,4 @@ General Public License. (e.g. they do not require you to accompany any object
 code using FFTW with the corresponding source code.) For these alternative
 terms you must purchase a license from MIT’s Technology Licensing Office. Users
 interested in such a license should contact us ([email protected]) for more
-information.
+information.

cpp/src_prims/datasets/boston.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2021, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -535,4 +535,4 @@ static const int n_features = 13;
 
 }  // namespace Boston
 }  // namespace Datasets
-}  // namespace MLCommon
+}  // namespace MLCommon

cpp/src_prims/datasets/breast_cancer.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2021, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -1989,4 +1989,4 @@ static const int n_features = 30;
 
 }  // namespace BreastCancer
 }  // namespace Datasets
-}  // namespace MLCommon
+}  // namespace MLCommon

cpp/src_prims/datasets/diabetes.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2021, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -1504,4 +1504,4 @@ static const int n_features = 10;
 
 }  // namespace Diabetes
 }  // namespace Datasets
-}  // namespace MLCommon
+}  // namespace MLCommon

cpp/test/c_api/README.md

@@ -17,4 +17,4 @@ To help prevent accidentally including the C-API files when compiling `libcuml++
 #error \
   "This header is only for the C-API and should not be included from the C++ API."
 #endif
-```
+```

cpp/test/mg/kmeans_test.cu

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2022-2024, NVIDIA CORPORATION.
+ * Copyright (c) 2022-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -203,4 +203,4 @@ INSTANTIATE_TEST_CASE_P(KmeansTests, KmeansTestF, ::testing::ValuesIn(inputsf2))
 
 INSTANTIATE_TEST_CASE_P(KmeansTests, KmeansTestD, ::testing::ValuesIn(inputsd2));
 
-}  // end namespace ML
+}  // end namespace ML

cpp/test/sg/handle_test.cu

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2024, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2025, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -45,4 +45,4 @@ TEST(HandleTest, DoubleDestoryFails)
   // handle is destroyed
   status = cumlDestroy(handle);
   EXPECT_EQ(CUML_INVALID_HANDLE, status);
-}
+}