GH-47167: [C++][Dev] Update clang-format dependency (#47168)

### Rationale for this change
Update clang-format to better match modern IDEs.

### What changes are included in this PR?
- Update clang-format
- Reformat code base with newer version

### Are these changes tested?
Yes

### Are there any user-facing changes?
No

* GitHub Issue: #47167

Lead-authored-by: AntoinePrv <AntoinePrv@users.noreply.github.com>
Co-authored-by: Rossi Sun <zanmato1984@gmail.com>
Signed-off-by: Rossi Sun <zanmato1984@gmail.com>

Author: AntoinePrv

.github/workflows/dev.yml

@@ -41,8 +41,8 @@ jobs:
 
   lint:
     name: Lint C++, Python, R, Docker, RAT
-    # Use Ubuntu 22.04 to ensure working pre-commit on Ubuntu 22.04.
-    runs-on: ubuntu-22.04
+    # Use Ubuntu 24.04 to ensure working pre-commit on Ubuntu 24.04.
+    runs-on: ubuntu-24.04
     if: ${{ !contains(github.event.pull_request.title, 'WIP') }}
     timeout-minutes: 15
     steps:

.pre-commit-config.yaml

@@ -50,7 +50,7 @@ repos:
           )
         types: []
   - repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v14.0.6
+    rev: v18.1.8
     hooks:
       - id: clang-format
         name: C++ Format
@@ -93,15 +93,15 @@ repos:
           ?^cpp/thirdparty/|
           )
   - repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v14.0.6
+    rev: v18.1.8
     hooks:
       - id: clang-format
         alias: c-glib
         name: C/GLib Format
         files: >-
           ^c_glib/
   - repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v14.0.6
+    rev: v18.1.8
     hooks:
       - id: clang-format
         name: MATLAB (C++) Format
@@ -156,7 +156,7 @@ repos:
         files: >-
           ^python/
   - repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v14.0.6
+    rev: v18.1.8
     hooks:
       - id: clang-format
         alias: python
@@ -213,7 +213,7 @@ repos:
         files: >-
             ^r/.*\.R$
   - repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v14.0.6
+    rev: v18.1.8
     hooks:
       - id: clang-format
         alias: r

cpp/src/arrow/acero/exec_plan.cc

@@ -137,7 +137,7 @@ struct ExecPlanImpl : public ExecPlan {
             opentelemetry::nostd::shared_ptr<opentelemetry::trace::Span> span =
                 ::arrow::internal::tracing::UnwrapSpan(span_.details.get());
             std::for_each(std::begin(pairs), std::end(pairs),
-                          [span](std::pair<std::string, std::string> const& pair) {
+                          [span](const std::pair<std::string, std::string>& pair) {
                             span->SetAttribute(pair.first, pair.second);
                           });
           }

cpp/src/arrow/compute/kernels/aggregate_test.cc

@@ -3889,8 +3889,7 @@ class TestPrimitiveQuantileKernel : public ::testing::Test {
 #define INTYPE(x) Datum(static_cast<typename TypeParam::c_type>(x))
 #define DOUBLE(x) Datum(static_cast<double>(x))
 // output type per interpolation: linear, lower, higher, nearest, midpoint
-#define O(a, b, c, d, e) \
-  { DOUBLE(a), INTYPE(b), INTYPE(c), INTYPE(d), DOUBLE(e) }
+#define O(a, b, c, d, e) {DOUBLE(a), INTYPE(b), INTYPE(c), INTYPE(d), DOUBLE(e)}
 
 template <typename ArrowType>
 class TestIntegerQuantileKernel : public TestPrimitiveQuantileKernel<ArrowType> {};

cpp/src/arrow/compute/kernels/hash_aggregate.cc

@@ -282,7 +282,7 @@ concept CFloatingPointConcept = std::floating_point<T> || std::same_as<T, util::
 
 template <typename T>
 concept CDecimalConcept = std::same_as<T, Decimal32> || std::same_as<T, Decimal64> ||
-    std::same_as<T, Decimal128> || std::same_as<T, Decimal256>;
+                          std::same_as<T, Decimal128> || std::same_as<T, Decimal256>;
 
 template <typename CType>
 struct AntiExtrema {

cpp/src/arrow/compute/kernels/temporal_internal.h

@@ -45,8 +45,8 @@ using std::chrono::duration_cast;
 using ArrowTimeZone = std::variant<const time_zone*, OffsetZone>;
 
 template <class Duration, class Func>
-auto ApplyTimeZone(const ArrowTimeZone& tz, sys_time<Duration> st, Func&& func)
-    -> decltype(func(zoned_time<Duration>{})) {
+auto ApplyTimeZone(const ArrowTimeZone& tz, sys_time<Duration> st,
+                   Func&& func) -> decltype(func(zoned_time<Duration>{})) {
   return std::visit(
       [&](auto&& zone) {
         if constexpr (std::is_pointer_v<std::decay_t<decltype(zone)> >) {
@@ -60,8 +60,8 @@ auto ApplyTimeZone(const ArrowTimeZone& tz, sys_time<Duration> st, Func&& func)
 
 template <class Duration, class Func>
 auto ApplyTimeZone(const ArrowTimeZone& tz, local_time<Duration> lt,
-                   std::optional<choose> c, Func&& func)
-    -> decltype(func(zoned_time<Duration>{})) {
+                   std::optional<choose> c,
+                   Func&& func) -> decltype(func(zoned_time<Duration>{})) {
   return std::visit(
       [&](auto&& zone) {
         if constexpr (std::is_pointer_v<std::decay_t<decltype(zone)> >) {

cpp/src/arrow/compute/kernels/vector_selection_filter_internal.cc

@@ -368,7 +368,7 @@ class PrimitiveFilterImpl {
           }
         }
       }  // !filter_block.AllSet()
-    }    // while(in_position < values_length_)
+    }  // while(in_position < values_length_)
   }
 
   // Write the next out_position given the selected in_position for the input

cpp/src/arrow/compute/kernels/vector_sort_test.cc

@@ -76,8 +76,8 @@ std::ostream& operator<<(std::ostream& os, NullPlacement null_placement) {
 // Tests for NthToIndices
 
 template <typename ArrayType>
-auto GetLogicalValue(const ArrayType& array, uint64_t index)
-    -> decltype(array.GetView(index)) {
+auto GetLogicalValue(const ArrayType& array,
+                     uint64_t index) -> decltype(array.GetView(index)) {
   return array.GetView(index);
 }
 

cpp/src/arrow/dataset/dataset_writer_test.cc

@@ -613,8 +613,8 @@ TEST_F(DatasetWriterTestFixture, ErrOnExistingData) {
                      fs::File("testdir/chunk-5.arrow"), fs::File("testdir/blah.txt")}));
   filesystem_ = std::dynamic_pointer_cast<MockFileSystem>(fs);
   write_options_.filesystem = filesystem_;
-  ASSERT_RAISES(Invalid, DatasetWriter::Make(
-                             write_options_, scheduler_, [] {}, [] {}, [] {}));
+  ASSERT_RAISES(Invalid,
+                DatasetWriter::Make(write_options_, scheduler_, [] {}, [] {}, [] {}));
   AssertEmptyFiles(
       {"testdir/chunk-0.arrow", "testdir/chunk-5.arrow", "testdir/blah.txt"});
 
@@ -627,8 +627,8 @@ TEST_F(DatasetWriterTestFixture, ErrOnExistingData) {
   filesystem_ = std::dynamic_pointer_cast<MockFileSystem>(fs2);
   write_options_.filesystem = filesystem_;
   write_options_.base_dir = "testdir";
-  ASSERT_RAISES(Invalid, DatasetWriter::Make(
-                             write_options_, scheduler_, [] {}, [] {}, [] {}));
+  ASSERT_RAISES(Invalid,
+                DatasetWriter::Make(write_options_, scheduler_, [] {}, [] {}, [] {}));
   AssertEmptyFiles({"testdir/part-0.arrow"});
 }
 

cpp/src/arrow/dataset/file_test.cc

@@ -594,11 +594,12 @@ class FileSystemWriteTest : public testing::TestWithParam<std::tuple<bool, bool>
 };
 
 TEST_P(FileSystemWriteTest, Write) {
-  auto plan_factory = [](const FileSystemDatasetWriteOptions& write_options,
-                         std::function<Future<std::optional<cp::ExecBatch>>()>*
-                             sink_gen) {
-    return std::vector<acero::Declaration>{{"write", WriteNodeOptions{write_options}}};
-  };
+  auto plan_factory =
+      [](const FileSystemDatasetWriteOptions& write_options,
+         std::function<Future<std::optional<cp::ExecBatch>>()>* sink_gen) {
+        return std::vector<acero::Declaration>{
+            {"write", WriteNodeOptions{write_options}}};
+      };
   TestDatasetWriteRoundTrip(plan_factory, /*has_output=*/false);
 }