#32: Added clang tidy to bazel via bazelrc and aspect

.github/workflows/check_bazel_tests.yml

@@ -15,6 +15,36 @@ env:
   ZMQ_LIBRARY_PREFIX: /usr/lib/x86_64-linux-gnu
   ZMQ_INCLUDE_PREFIX: /usr/include
 jobs:
+  v2:
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v6
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential curl
+      - uses: bazel-contrib/setup-bazel@0.19.0
+        with:
+          bazelisk-cache: true
+      - name: Build
+        run: bazel build --verbose_failures //...
+        working-directory: ./udf-runner-cpp/v2
+      - name: Install clang-tidy
+        run: |
+          sudo bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)" -- 22
+          sudo apt-get install -y clang-tidy-22
+      - name: Run clang-tidy
+        run: bazel build --verbose_failures --config clang-tidy //...
+        working-directory: ./udf-runner-cpp/v2
+      - name: Install clang-format
+        run: sudo apt-get install -y clang-format
+      - name: Run clang-format
+        run: bazel build --verbose_failures --config clang-format //...
+        working-directory: ./udf-runner-cpp/v2
+      - name: Run tests
+        run: bazel test --verbose_failures //...
+        working-directory: ./udf-runner-cpp/v2
+
   build:
     runs-on: ubuntu-24.04
     steps:

doc/changes/unreleased.md

@@ -0,0 +1,18 @@
+## Summary
+
+
+## Bug Fixes
+
+n/a
+
+## Features / Enhancements
+
+ - 32: Added clang tidy to v2
+
+## Refactorings
+
+n/a
+
+## Internal
+
+* Updated Poetry dependencies and added developer guide and added .gitignore

udf-runner-cpp/v2/.bazelrc

@@ -0,0 +1,22 @@
+# The clang-tidy and clang-format rule packages are published in this registry.
+common --registry=https://raw.githubusercontent.com/digiboys/bazel-registry/main
+common --registry=https://bcr.bazel.build
+
+build:clang-tidy --@rules_clang_tidy//:config=//tools/clang-tidy:config
+build:clang-tidy --@rules_clang_tidy//:clang-tidy=//tools/clang-tidy:wrapper
+build:clang-tidy --aspects=@rules_clang_tidy//:aspects.bzl%check
+build:clang-tidy --output_groups=report
+build:clang-tidy --remote_download_outputs=toplevel
+build:clang-tidy --keep_going
+build:clang-tidy --build_tag_filters=-noclangtidy
+build:clang-tidy --copt=-Wno-pragma-once-outside-header
+
+build:clang-format --aspects=@bazel_clang_format//:defs.bzl%check_aspect
+build:clang-format --output_groups=report
+build:clang-format --@bazel_clang_format//:config=//tools/clang-format:clang-format-config
+build:clang-format --build_tag_filters=-noclangtidy
+
+build:clang-format-fix --aspects=@bazel_clang_format//:defs.bzl%fix_aspect
+build:clang-format-fix --output_groups=report
+build:clang-format-fix --use_action_cache=false
+build:clang-format-fix --@bazel_clang_format//:config=//tools/clang-format:clang-format-config

udf-runner-cpp/v2/BUILD.bazel

@@ -109,7 +109,7 @@ cc_binary(
 
 cc_test(
     name = "udf_protocol_symbol_leak_test",
-    srcs = ["udf_protocol_symbol_leak_test.cc"],
+    srcs = ["nm_runner.hpp", "udf_protocol_symbol_leak_test.cc"],
     copts = ["-std=c++20"],
     # The test inspects the built shared object with nm. data makes the
     # artifact available at runtime and args passes its runfiles path.
@@ -121,7 +121,7 @@ cc_test(
 
 cc_test(
     name = "udf_protocol_static_symbol_leak_test",
-    srcs = ["udf_protocol_static_symbol_leak_test.cc"],
+    srcs = ["nm_runner.hpp", "udf_protocol_static_symbol_leak_test.cc"],
     copts = ["-std=c++20"],
     # cc_library produces multiple artifacts, so the test receives all
     # locations and selects the static .a archive for nm inspection.
@@ -146,6 +146,9 @@ cc_test(
 alias(
     name = "arrow_core",
     actual = "@v2_arrow//:arrow_core",
+    # Arrow and its vendored sources are third-party code. Keep them out of
+    # the repository's clang-tidy and clang-format CI profiles.
+    tags = ["noclangtidy"],
 )
 
 filegroup(

udf-runner-cpp/v2/MODULE.bazel

@@ -8,6 +8,18 @@ bazel_dep(name = "platforms", version = "1.0.0")
 bazel_dep(name = "flatbuffers", version = "25.2.10")
 bazel_dep(name = "google_benchmark", version = "1.9.5")
 
+bazel_dep(
+    name = "rules_clang_tidy",
+    version = "0.0.0",
+    dev_dependency = True,
+)
+
+bazel_dep(
+    name = "bazel_clang_format",
+    version = "0.0.0",
+    dev_dependency = True,
+)
+
 # FlatBuffers currently selects versions of these transitive build tools that
 # still use the removed incompatible_use_toolchain_transition rule attribute.
 # Override them so the v2 module can be analyzed by Bazel 9.

udf-runner-cpp/v2/arrow_c_data_demo.cc

@@ -50,7 +50,8 @@ arrow::Result<std::shared_ptr<arrow::RecordBatch>> MakeDemoRecordBatch() {
 
 arrow::Status ExportDemoRecordBatch(ArrowArray* out_array, ArrowSchema* out_schema) {
     if (out_array == nullptr || out_schema == nullptr) {
-        return arrow::Status::Invalid("output ArrowArray and ArrowSchema pointers must not be null");
+        return arrow::Status::Invalid(
+            "output ArrowArray and ArrowSchema pointers must not be null");
     }
 
     std::memset(out_array, 0, sizeof(*out_array));
@@ -64,8 +65,10 @@ arrow::Status ExportDemoRecordBatch(ArrowArray* out_array, ArrowSchema* out_sche
     return arrow::Status::OK();
 }
 
-arrow::Status ConsumeDemoRecordBatch(ArrowArray* array, ArrowSchema* schema,
-                                     int64_t* out_row_count, int64_t* out_id_sum) {
+arrow::Status ConsumeDemoRecordBatch(ArrowArray* array,
+                                     ArrowSchema* schema,
+                                     int64_t* out_row_count,
+                                     int64_t* out_id_sum) {
     if (array == nullptr || schema == nullptr || out_row_count == nullptr ||
         out_id_sum == nullptr) {
         return arrow::Status::Invalid("input and output pointers must not be null");
@@ -75,12 +78,11 @@ arrow::Status ConsumeDemoRecordBatch(ArrowArray* array, ArrowSchema* schema,
     if (batch->num_columns() != 2) {
         return arrow::Status::Invalid("expected two columns");
     }
-    if (batch->schema()->field(0)->name() != "id" ||
-        batch->schema()->field(1)->name() != "name") {
+    if (batch->schema()->field(0)->name() != "id" || batch->schema()->field(1)->name() != "name") {
         return arrow::Status::Invalid("unexpected schema");
     }
 
-    auto ids = std::static_pointer_cast<arrow::Int64Array>(batch->column(0));
+    auto ids    = std::static_pointer_cast<arrow::Int64Array>(batch->column(0));
     int64_t sum = 0;
     for (int64_t index = 0; index < ids->length(); ++index) {
         if (!ids->IsNull(index)) {
@@ -89,11 +91,11 @@ arrow::Status ConsumeDemoRecordBatch(ArrowArray* array, ArrowSchema* schema,
     }
 
     *out_row_count = batch->num_rows();
-    *out_id_sum = sum;
+    *out_id_sum    = sum;
     return arrow::Status::OK();
 }
 
-}  // namespace
+} // namespace
 
 extern "C" UDF_RUNNER_CPP_V2_EXPORT int udf_runner_cpp_v2_demo_export_record_batch(
     ArrowArray* out_array, ArrowSchema* out_schema) {
@@ -107,10 +109,8 @@ extern "C" UDF_RUNNER_CPP_V2_EXPORT int udf_runner_cpp_v2_demo_export_record_bat
 }
 
 extern "C" UDF_RUNNER_CPP_V2_EXPORT int udf_runner_cpp_v2_demo_consume_record_batch(
-    ArrowArray* array, ArrowSchema* schema, int64_t* out_row_count,
-    int64_t* out_id_sum) {
-    const arrow::Status status =
-        ConsumeDemoRecordBatch(array, schema, out_row_count, out_id_sum);
+    ArrowArray* array, ArrowSchema* schema, int64_t* out_row_count, int64_t* out_id_sum) {
+    const arrow::Status status = ConsumeDemoRecordBatch(array, schema, out_row_count, out_id_sum);
     if (!status.ok()) {
         SetLastError(status);
         return 1;

udf-runner-cpp/v2/arrow_c_data_demo.h

@@ -17,13 +17,13 @@ extern "C" {
 UDF_RUNNER_CPP_V2_EXPORT int udf_runner_cpp_v2_demo_export_record_batch(
     struct ArrowArray* out_array, struct ArrowSchema* out_schema);
 
-UDF_RUNNER_CPP_V2_EXPORT int udf_runner_cpp_v2_demo_consume_record_batch(
-    struct ArrowArray* array, struct ArrowSchema* schema, int64_t* out_row_count,
-    int64_t* out_id_sum);
+UDF_RUNNER_CPP_V2_EXPORT int udf_runner_cpp_v2_demo_consume_record_batch(struct ArrowArray* array,
+                                                                         struct ArrowSchema* schema,
+                                                                         int64_t* out_row_count,
+                                                                         int64_t* out_id_sum);
 
 UDF_RUNNER_CPP_V2_EXPORT const char* udf_runner_cpp_v2_demo_last_error(void);
 
 #ifdef __cplusplus
-}  // extern "C"
+} // extern "C"
 #endif
-