[ci] [c++] use 'pre-commit' to run 'cpplint', upgrade to 'cpplint' 2.0.2 (#7002)

* [ci] [c++] use 'pre-commit' to run 'cpplint', upgrade to 'cpplint' 2.0.2

* remove bashisms

* one more pipefail use

* another pipefail

Author: jameslamb

.ci/lint-cpp.sh renamed to .ci/check-omp-pragmas.sh

@@ -1,13 +1,6 @@
 #!/bin/bash
 
-set -e -E -u -o pipefail
-
-echo "running cpplint"
-cpplint \
-    --filter=-build/c++11,-build/include_subdir,-build/header_guard,-whitespace/line_length \
-    --recursive ./src ./include ./R-package ./swig ./tests \
-|| exit 1
-echo "done running cpplint"
+set -e -u
 
 echo "checking that all OpenMP pragmas specify num_threads()"
 get_omp_pragmas_without_num_threads() {
@@ -28,11 +21,11 @@ get_omp_pragmas_without_num_threads() {
 # consider this a failure and stop execution of the script.
 #
 # ref: https://www.gnu.org/software/grep/manual/html_node/Exit-Status.html
-set +e +o pipefail
+set +e
 PROBLEMATIC_LINES=$(
     get_omp_pragmas_without_num_threads
 )
-set -e -o pipefail
+set -e
 if test "${PROBLEMATIC_LINES}" != ""; then
     get_omp_pragmas_without_num_threads
     echo "Found '#pragma omp parallel' not using explicit num_threads() configuration. Fix those."

.ci/test.sh

@@ -105,7 +105,6 @@ if [[ $TASK == "lint" ]]; then
     conda create -q -y -n "${CONDA_ENV}" \
         "${CONDA_PYTHON_REQUIREMENT}" \
         'biome>=1.9.3' \
-        'cpplint>=1.6.0' \
         'matplotlib-base>=3.9.1' \
         'mypy>=1.11.1' \
         'pre-commit>=3.8.0' \
@@ -118,8 +117,6 @@ if [[ $TASK == "lint" ]]; then
     bash ./.ci/run-pre-commit-mypy.sh || exit 1
     echo "Linting R code"
     Rscript ./.ci/lint-r-code.R "${BUILD_DIRECTORY}" || exit 1
-    echo "Linting C++ code"
-    bash ./.ci/lint-cpp.sh || exit 1
     echo "Linting JavaScript code"
     bash ./.ci/lint-js.sh || exit 1
     exit 0

.pre-commit-config.yaml

@@ -22,6 +22,22 @@ repos:
     hooks:
       - id: cmakelint
         args: ["--linelength=120", "--filter=-convention/filename,-package/stdargs,-readability/wonkycase"]
+  - repo: https://github.com/cpplint/cpplint
+    rev: '2.0.2'
+    hooks:
+      - id: cpplint
+        args:
+          - --recursive
+          - --filter=-build/c++11,-build/include_subdir,-build/include_what_you_use,-build/header_guard,-whitespace/indent_namespace,-whitespace/line_length
+  - repo: local
+    hooks:
+      - id: check-omp-pragmas
+        name: check-omp-pragmas
+        entry: sh
+        args:
+          - .ci/check-omp-pragmas.sh
+        language: system
+        pass_filenames: false
   - repo: https://github.com/adrienverge/yamllint
     rev: v1.37.1
     hooks:

include/LightGBM/dataset.h

@@ -554,9 +554,13 @@ class Dataset {
   }
 
   inline void FinishOneRow(int tid, data_size_t row_idx, const std::vector<bool>& is_feature_added) {
-    if (is_finish_load_) { return; }
+    if (is_finish_load_) {
+      return;
+    }
     for (auto fidx : feature_need_push_zeros_) {
-      if (is_feature_added[fidx]) { continue; }
+      if (is_feature_added[fidx]) {
+        continue;
+      }
       const int group = feature2group_[fidx];
       const int sub_feature = feature2subfeature_[fidx];
       feature_groups_[group]->PushData(tid, sub_feature, row_idx, 0.0f);
@@ -587,10 +591,14 @@ class Dataset {
   }
 
   inline void PushOneRow(int tid, data_size_t row_idx, const std::vector<std::pair<int, double>>& feature_values) {
-    if (is_finish_load_) { return; }
+    if (is_finish_load_) {
+      return;
+    }
     std::vector<bool> is_feature_added(num_features_, false);
     for (auto& inner_data : feature_values) {
-      if (inner_data.first >= num_total_features_) { continue; }
+      if (inner_data.first >= num_total_features_) {
+        continue;
+      }
       int feature_idx = used_feature_map_[inner_data.first];
       if (feature_idx >= 0) {
         is_feature_added[feature_idx] = true;

include/LightGBM/utils/array_args.h

@@ -112,17 +112,33 @@ class ArrayArgs {
     VAL_T v = ref[end - 1];
     for (;;) {
       while (ref[++i] > v) {}
-      while (v > ref[--j]) { if (j == start) { break; } }
-      if (i >= j) { break; }
+      while (v > ref[--j]) {
+        if (j == start) {
+          break;
+        }
+      }
+      if (i >= j) {
+        break;
+      }
       std::swap(ref[i], ref[j]);
-      if (ref[i] == v) { p++; std::swap(ref[p], ref[i]); }
-      if (v == ref[j]) { q--; std::swap(ref[j], ref[q]); }
+      if (ref[i] == v) {
+        p++;
+        std::swap(ref[p], ref[i]);
+      }
+      if (v == ref[j]) {
+        q--;
+        std::swap(ref[j], ref[q]);
+      }
     }
     std::swap(ref[i], ref[end - 1]);
     j = i - 1;
     i = i + 1;
-    for (int k = start; k <= p; k++, j--) { std::swap(ref[k], ref[j]); }
-    for (int k = end - 2; k >= q; k--, i++) { std::swap(ref[i], ref[k]); }
+    for (int k = start; k <= p; k++, j--) {
+      std::swap(ref[k], ref[j]);
+    }
+    for (int k = end - 2; k >= q; k--, i++) {
+      std::swap(ref[i], ref[k]);
+    }
     *l = j;
     *r = i;
   }

include/LightGBM/utils/common.h

@@ -315,9 +315,18 @@ inline static const char* Atof(const char* p, double* out) {
       }
       if (expon > 308) expon = 308;
       // Calculate scaling factor.
-      while (expon >= 50) { scale *= 1E50; expon -= 50; }
-      while (expon >= 8) { scale *= 1E8;  expon -= 8; }
-      while (expon > 0) { scale *= 10.0; expon -= 1; }
+      while (expon >= 50) {
+        scale *= 1E50;
+        expon -= 50;
+      }
+      while (expon >= 8) {
+        scale *= 1E8;
+        expon -= 8;
+      }
+      while (expon > 0) {
+        scale *= 10.0;
+        expon -= 1;
+      }
     }
     // Return signed and scaled floating point result.
     *out = sign * (frac ? (value / scale) : (value * scale));
@@ -713,7 +722,9 @@ static void ParallelSort(_RanIt _First, _RanIt _Last, _Pr _Pred, _VTRanIt*) {
       size_t mid = left + s;
       size_t right = mid + s;
       right = std::min(len, right);
-      if (mid >= right) { continue; }
+      if (mid >= right) {
+        continue;
+      }
       std::copy(_First + left, _First + mid, buf + left);
       std::merge(buf + left, buf + mid, _First + mid, _First + right, _First + left, _Pred);
     }

include/LightGBM/utils/openmp_wrapper.h

@@ -62,9 +62,13 @@ class ThreadExceptionHelper {
   }
   void CaptureException() {
     // only catch first exception.
-    if (ex_ptr_ != nullptr) { return; }
+    if (ex_ptr_ != nullptr) {
+      return;
+    }
     std::unique_lock<std::mutex> guard(lock_);
-    if (ex_ptr_ != nullptr) { return; }
+    if (ex_ptr_ != nullptr) {
+      return;
+    }
     ex_ptr_ = std::current_exception();
   }
 

include/LightGBM/utils/text_reader.h

@@ -124,7 +124,9 @@ class TextReader {
           ++i;
           ++total_cnt;
           // skip end of line
-          while ((buffer_process[i] == '\n' || buffer_process[i] == '\r') && i < read_cnt) { ++i; }
+          while ((buffer_process[i] == '\n' || buffer_process[i] == '\r') && i < read_cnt) {
+            ++i;
+          }
           last_i = i;
         } else {
           ++i;
@@ -284,7 +286,9 @@ class TextReader {
           ++i;
           ++total_cnt;
           // skip end of line
-          while ((buffer_process[i] == '\n' || buffer_process[i] == '\r') && i < read_cnt) { ++i; }
+          while ((buffer_process[i] == '\n' || buffer_process[i] == '\r') && i < read_cnt) {
+            ++i;
+          }
           last_i = i;
         } else {
           ++i;

src/application/application.cpp

@@ -121,7 +121,9 @@ void Application::LoadData() {
   if (config_.is_provide_training_metric) {
     for (auto metric_type : config_.metric) {
       auto metric = std::unique_ptr<Metric>(Metric::CreateMetric(metric_type, config_));
-      if (metric == nullptr) { continue; }
+      if (metric == nullptr) {
+        continue;
+      }
       metric->Init(train_data_->metadata(), train_data_->num_data());
       train_metric_.push_back(std::move(metric));
     }
@@ -149,7 +151,9 @@ void Application::LoadData() {
       valid_metrics_.emplace_back();
       for (auto metric_type : config_.metric) {
         auto metric = std::unique_ptr<Metric>(Metric::CreateMetric(metric_type, config_));
-        if (metric == nullptr) { continue; }
+        if (metric == nullptr) {
+          continue;
+        }
         metric->Init(valid_datas_.back()->metadata(),
                      valid_datas_.back()->num_data());
         valid_metrics_.back().push_back(std::move(metric));

src/boosting/gbdt.cpp

@@ -210,7 +210,9 @@ void GBDT::AddValidDataset(const Dataset* valid_data,
 
   if (early_stopping_round_ > 0) {
     auto num_metrics = valid_metrics.size();
-    if (es_first_metric_only_) { num_metrics = 1; }
+    if (es_first_metric_only_) {
+      num_metrics = 1;
+    }
     best_iter_.emplace_back(num_metrics, 0);
     best_score_.emplace_back(num_metrics, kMinScore);
     best_msg_.emplace_back(num_metrics);
@@ -452,7 +454,9 @@ bool GBDT::TrainOneIter(const score_t* gradients, const score_t* hessians) {
 }
 
 void GBDT::RollbackOneIter() {
-  if (iter_ <= 0) { return; }
+  if (iter_ <= 0) {
+    return;
+  }
   // reset score
   for (int cur_tree_id = 0; cur_tree_id < num_tree_per_iteration_; ++cur_tree_id) {
     auto curr_tree = models_.size() - num_tree_per_iteration_ + cur_tree_id;
@@ -588,15 +592,19 @@ std::string GBDT::OutputMetric(int iter) {
             msg_buf << tmp_buf.str() << '\n';
           }
         }
-        if (es_first_metric_only_ && j > 0) { continue; }
+        if (es_first_metric_only_ && j > 0) {
+          continue;
+        }
         if (ret.empty() && early_stopping_round_ > 0) {
           auto cur_score = valid_metrics_[i][j]->factor_to_bigger_better() * test_scores.back();
           if (cur_score - best_score_[i][j] > early_stopping_min_delta_) {
             best_score_[i][j] = cur_score;
             best_iter_[i][j] = iter;
             meet_early_stopping_pairs.emplace_back(i, j);
           } else {
-            if (iter - best_iter_[i][j] >= early_stopping_round_) { ret = best_msg_[i][j]; }
+            if (iter - best_iter_[i][j] >= early_stopping_round_) {
+              ret = best_msg_[i][j];
+            }
           }
         }
       }