[ci] update pre-commit hooks, fix typos (#7108)

* [ci] update pre-commit hooks, fix typos

* remove unnecessary indentation settings in biome.json

Author: jameslamb

.pre-commit-config.yaml

@@ -13,8 +13,10 @@ exclude: |
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v6.0.0
     hooks:
+      - id: check-toml
+      - id: check-xml
       - id: end-of-file-fixer
       - id: trailing-whitespace
   - repo: https://github.com/cmake-lint/cmake-lint
@@ -63,7 +65,7 @@ repos:
           - sphinx>=8.1.3
           - sphinx_rtd_theme>=3.0.1
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.14.0
+    rev: v0.14.10
     hooks:
       - id: ruff-check
         args: ["--config", "python-package/pyproject.toml"]
@@ -72,30 +74,30 @@ repos:
         args: ["--config", "python-package/pyproject.toml"]
         types_or: [python, jupyter]
   - repo: https://github.com/biomejs/pre-commit
-    rev: v2.2.5
+    rev: v2.3.10
     hooks:
       - id: biome-ci
         args:
           - --config-path=./biome.json
           - --diagnostic-level=info
           - --error-on-warnings
   - repo: https://github.com/shellcheck-py/shellcheck-py
-    rev: v0.10.0.1
+    rev: v0.11.0.1
     hooks:
       - id: shellcheck
   - repo: https://github.com/crate-ci/typos
-    rev: v1.34.0
+    rev: v1.40.0
     hooks:
       - id: typos
         args: ["--force-exclude"]
         exclude: (\.gitignore$)|(^\.editorconfig$)
   - repo: https://github.com/henryiii/validate-pyproject-schema-store
-    rev: 2025.07.14
+    rev: 2025.11.21
     hooks:
       - id: validate-pyproject
         files: python-package/pyproject.toml$
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.18.2
+    rev: v1.19.1
     hooks:
       - id: mypy
         verbose: true

.typos.toml

@@ -8,6 +8,7 @@ default.extend-ignore-re = [
 [default.extend-words]
 MAPE = "MAPE"
 datas = "datas"
+indx = "indx"
 interprete = "interprete"
 mape = "mape"
 splitted = "splitted"

R-package/demo/cross_validation.R

@@ -38,7 +38,7 @@ lgb.cv(
   , showsd = FALSE
 )
 
-# You can also do cross validation with cutomized loss function
+# You can also do cross validation with customized loss function
 print("Running cross validation, with cutomsized loss function")
 
 logregobj <- function(preds, dtrain) {

biome.json

@@ -5,8 +5,18 @@
         "clientKind": "git",
         "useIgnoreFile": true
     },
+    "files": {
+        "includes": [
+            "**",
+            "!build",
+            "!external_libs",
+            "!lightgbm-python",
+            "!lightgbm_r"
+        ]
+    },
     "formatter": {
         "enabled": true,
+        "expand": "always",
         "useEditorconfig": true,
         "lineWidth": 120
     },

examples/regression/forced_bins.json

@@ -1,10 +1,18 @@
 [
     {
         "feature": 0,
-        "bin_upper_bound": [0.3, 0.35, 0.4]
+        "bin_upper_bound": [
+            0.3,
+            0.35,
+            0.4
+        ]
     },
     {
         "feature": 1,
-        "bin_upper_bound": [-0.1, -0.15, -0.2]
+        "bin_upper_bound": [
+            -0.1,
+            -0.15,
+            -0.2
+        ]
     }
 ]

examples/regression/forced_bins2.json

@@ -1,6 +1,11 @@
 [
     {
         "feature": 0,
-        "bin_upper_bound": [0.19, 0.39, 0.59, 0.79]
+        "bin_upper_bound": [
+            0.19,
+            0.39,
+            0.59,
+            0.79
+        ]
     }
 ]

include/LightGBM/dataset.h

@@ -645,7 +645,7 @@ class Dataset {
   inline int Feature2Group(int feature_idx) const {
     return feature2group_[feature_idx];
   }
-  inline int Feture2SubFeature(int feature_idx) const {
+  inline int Feature2SubFeature(int feature_idx) const {
     return feature2subfeature_[feature_idx];
   }
   inline uint64_t GroupBinBoundary(int group_idx) const {

src/c_api.cpp

@@ -922,10 +922,10 @@ using LightGBM::SingleRowPredictor;
 // some help functions used to convert data
 
 std::function<std::vector<double>(int row_idx)>
-RowFunctionFromDenseMatric(const void* data, int num_row, int num_col, int data_type, int is_row_major);
+RowFunctionFromDenseMatrix(const void* data, int num_row, int num_col, int data_type, int is_row_major);
 
 std::function<std::vector<std::pair<int, double>>(int row_idx)>
-RowPairFunctionFromDenseMatric(const void* data, int num_row, int num_col, int data_type, int is_row_major);
+RowPairFunctionFromDenseMatrix(const void* data, int num_row, int num_col, int data_type, int is_row_major);
 
 std::function<std::vector<std::pair<int, double>>(int row_idx)>
 RowPairFunctionFromDenseRows(const void** data, int num_col, int data_type);
@@ -1140,7 +1140,7 @@ int LGBM_DatasetPushRows(DatasetHandle dataset,
                          int32_t start_row) {
   API_BEGIN();
   auto p_dataset = reinterpret_cast<Dataset*>(dataset);
-  auto get_row_fun = RowFunctionFromDenseMatric(data, nrow, ncol, data_type, 1);
+  auto get_row_fun = RowFunctionFromDenseMatrix(data, nrow, ncol, data_type, 1);
   if (p_dataset->has_raw()) {
     p_dataset->ResizeRaw(p_dataset->num_numeric_features() + nrow);
   }
@@ -1179,7 +1179,7 @@ int LGBM_DatasetPushRowsWithMetadata(DatasetHandle dataset,
     Log::Fatal("data cannot be null.");
   }
   auto p_dataset = reinterpret_cast<Dataset*>(dataset);
-  auto get_row_fun = RowFunctionFromDenseMatric(data, nrow, ncol, data_type, 1);
+  auto get_row_fun = RowFunctionFromDenseMatrix(data, nrow, ncol, data_type, 1);
   if (p_dataset->has_raw()) {
     p_dataset->ResizeRaw(p_dataset->num_numeric_features() + nrow);
   }
@@ -1344,7 +1344,7 @@ int LGBM_DatasetCreateFromMats(int32_t nmat,
 
   std::vector<std::function<std::vector<double>(int row_idx)>> get_row_fun;
   for (int j = 0; j < nmat; ++j) {
-    get_row_fun.push_back(RowFunctionFromDenseMatric(data[j], nrow[j], ncol, data_type, is_row_major[j]));
+    get_row_fun.push_back(RowFunctionFromDenseMatrix(data[j], nrow[j], ncol, data_type, is_row_major[j]));
   }
 
   if (reference == nullptr) {
@@ -1614,7 +1614,7 @@ int LGBM_DatasetCreateFromCSC(const void* col_ptr,
       continue;
     }
     int group = ret->Feature2Group(feature_idx);
-    int sub_feature = ret->Feture2SubFeature(feature_idx);
+    int sub_feature = ret->Feature2SubFeature(feature_idx);
     CSC_RowIterator col_it(col_ptr, col_ptr_type, indices, data, data_type, ncol_ptr, nelem, i);
     auto bin_mapper = ret->FeatureBinMapper(feature_idx);
     if (bin_mapper->GetDefaultBin() == bin_mapper->GetMostFreqBin()) {
@@ -2531,7 +2531,7 @@ int LGBM_BoosterPredictForMat(BoosterHandle handle,
   config.Set(param);
   OMP_SET_NUM_THREADS(config.num_threads);
   Booster* ref_booster = reinterpret_cast<Booster*>(handle);
-  auto get_row_fun = RowPairFunctionFromDenseMatric(data, nrow, ncol, data_type, is_row_major);
+  auto get_row_fun = RowPairFunctionFromDenseMatrix(data, nrow, ncol, data_type, is_row_major);
   ref_booster->Predict(start_iteration, num_iteration, predict_type, nrow, ncol, get_row_fun,
                        config, out_result, out_len);
   API_END();
@@ -2554,7 +2554,7 @@ int LGBM_BoosterPredictForMatSingleRow(BoosterHandle handle,
   config.Set(param);
   OMP_SET_NUM_THREADS(config.num_threads);
   Booster* ref_booster = reinterpret_cast<Booster*>(handle);
-  auto get_row_fun = RowPairFunctionFromDenseMatric(data, 1, ncol, data_type, is_row_major);
+  auto get_row_fun = RowPairFunctionFromDenseMatrix(data, 1, ncol, data_type, is_row_major);
   ref_booster->SetSingleRowPredictorInner(start_iteration, num_iteration, predict_type, config);
   ref_booster->PredictSingleRow(predict_type, ncol, get_row_fun, config, out_result, out_len);
   API_END();
@@ -2587,7 +2587,7 @@ int LGBM_BoosterPredictForMatSingleRowFast(FastConfigHandle fastConfig_handle,
   API_BEGIN();
   SingleRowPredictor *single_row_predictor = reinterpret_cast<SingleRowPredictor*>(fastConfig_handle);
   // Single row in row-major format:
-  auto get_row_fun = RowPairFunctionFromDenseMatric(data, 1, single_row_predictor->num_cols, single_row_predictor->data_type, 1);
+  auto get_row_fun = RowPairFunctionFromDenseMatrix(data, 1, single_row_predictor->num_cols, single_row_predictor->data_type, 1);
   single_row_predictor->Predict(get_row_fun, out_result, out_len);
   API_END();
 }
@@ -2819,7 +2819,7 @@ int LGBM_GetMaxThreads(int* out) {
 
 template<typename T>
 std::function<std::vector<double>(int row_idx)>
-RowFunctionFromDenseMatric_helper(const void* data, int num_row, int num_col, int is_row_major) {
+RowFunctionFromDenseMatrix_helper(const void* data, int num_row, int num_col, int is_row_major) {
   const T* data_ptr = reinterpret_cast<const T*>(data);
   if (is_row_major) {
     return [=] (int row_idx) {
@@ -2842,19 +2842,19 @@ RowFunctionFromDenseMatric_helper(const void* data, int num_row, int num_col, in
 }
 
 std::function<std::vector<double>(int row_idx)>
-RowFunctionFromDenseMatric(const void* data, int num_row, int num_col, int data_type, int is_row_major) {
+RowFunctionFromDenseMatrix(const void* data, int num_row, int num_col, int data_type, int is_row_major) {
   if (data_type == C_API_DTYPE_FLOAT32) {
-    return RowFunctionFromDenseMatric_helper<float>(data, num_row, num_col, is_row_major);
+    return RowFunctionFromDenseMatrix_helper<float>(data, num_row, num_col, is_row_major);
   } else if (data_type == C_API_DTYPE_FLOAT64) {
-    return RowFunctionFromDenseMatric_helper<double>(data, num_row, num_col, is_row_major);
+    return RowFunctionFromDenseMatrix_helper<double>(data, num_row, num_col, is_row_major);
   }
-  Log::Fatal("Unknown data type in RowFunctionFromDenseMatric");
+  Log::Fatal("Unknown data type in RowFunctionFromDenseMatrix");
   return nullptr;
 }
 
 std::function<std::vector<std::pair<int, double>>(int row_idx)>
-RowPairFunctionFromDenseMatric(const void* data, int num_row, int num_col, int data_type, int is_row_major) {
-  auto inner_function = RowFunctionFromDenseMatric(data, num_row, num_col, data_type, is_row_major);
+RowPairFunctionFromDenseMatrix(const void* data, int num_row, int num_col, int data_type, int is_row_major) {
+  auto inner_function = RowFunctionFromDenseMatrix(data, num_row, num_col, data_type, is_row_major);
   if (inner_function != nullptr) {
     return [inner_function] (int row_idx) {
       auto raw_values = inner_function(row_idx);
@@ -2875,7 +2875,7 @@ RowPairFunctionFromDenseMatric(const void* data, int num_row, int num_col, int d
 std::function<std::vector<std::pair<int, double>>(int row_idx)>
 RowPairFunctionFromDenseRows(const void** data, int num_col, int data_type) {
   return [=](int row_idx) {
-    auto inner_function = RowFunctionFromDenseMatric(data[row_idx], 1, num_col, data_type, /* is_row_major */ true);
+    auto inner_function = RowFunctionFromDenseMatrix(data[row_idx], 1, num_col, data_type, /* is_row_major */ true);
     auto raw_values = inner_function(0);
     std::vector<std::pair<int, double>> ret;
     ret.reserve(raw_values.size());

src/treelearner/voting_parallel_tree_learner.cpp

@@ -389,7 +389,7 @@ void VotingParallelTreeLearner<TREELEARNER_T>::FindBestSplits(const Tree* tree)
   std::vector<int> smaller_top_features, larger_top_features;
   GlobalVoting(this->smaller_leaf_splits_->leaf_index(), smaller_top_k_splits_global, &smaller_top_features);
   GlobalVoting(this->larger_leaf_splits_->leaf_index(), larger_top_k_splits_global, &larger_top_features);
-  // copy local histgrams to buffer
+  // copy local histograms to buffer
   CopyLocalHistogram(smaller_top_features, larger_top_features);
 
   // Reduce scatter for histogram