refactor: Update yscope-dev-utils and apply latest clang-format settings.

lint-requirements.txt

@@ -1,6 +1,5 @@
 black>=24.4.2
-# Lock to v18.x until we can upgrade our code to meet v19's formatting standards.
-clang-format~=18.1
+clang-format>=20.1.0
 # Lock to v19.x until we can upgrade our code to fix new v20 issues.
 clang-tidy~=19.1
 ruff>=0.4.4

lint-tasks.yaml

@@ -32,7 +32,7 @@ tasks:
         vars:
           FLAGS: "--in-place"
 
-  cpp-configs: "tools/yscope-dev-utils/lint-configs/symlink-cpp-lint-configs.sh"
+  cpp-configs: "tools/yscope-dev-utils/exports/lint-configs/symlink-cpp-lint-configs.sh"
 
   cpp-check:
     cmds:
@@ -45,51 +45,33 @@ tasks:
       - task: "cpp-static-fix"
 
   cpp-format-check:
-    sources: &cpp_format_src_files
-      - "{{.G_LINT_VENV_CHECKSUM_FILE}}"
-      - "{{.G_SRC_SPIDER_DIR}}/.clang-format"
-      - "{{.G_EXAMPLES_DIR}}/**/*.cpp"
-      - "{{.G_EXAMPLES_DIR}}/**/*.h"
-      - "{{.G_EXAMPLES_DIR}}/**/*.hpp"
-      - "{{.G_SRC_SPIDER_DIR}}/**/*.cpp"
-      - "{{.G_SRC_SPIDER_DIR}}/**/*.h"
-      - "{{.G_SRC_SPIDER_DIR}}/**/*.hpp"
-      - "{{.G_TEST_DIR}}/**/*.cpp"
-      - "{{.G_TEST_DIR}}/**/*.h"
-      - "{{.G_TEST_DIR}}/**/*.hpp"
+    sources: &cpp_source_files
+      - "{{.ROOT_DIR}}/.clang-format"
+      - "{{.ROOT_DIR}}/.clang-tidy"
       - "{{.TASKFILE}}"
-      - "tools/yscope-dev-utils/lint-configs/.clang-format"
+      - "{{.G_SRC_SPIDER_DIR}}/.clang-format"
+      - "{{.G_EXAMPLES_DIR}}/**"
+      - "{{.G_SRC_SPIDER_DIR}}/**"
+      - "{{.G_TEST_DIR}}/**"
     deps: ["cpp-configs", "venv"]
     cmds:
-      - task: "clang-format"
-        vars:
-          FLAGS: "--dry-run"
-          SRC_DIR: "{{.G_SRC_SPIDER_DIR}}"
-      - task: "clang-format"
-        vars:
-          FLAGS: "--dry-run"
-          SRC_DIR: "{{.G_TEST_DIR}}"
-      - task: "clang-format"
+      - task: ":utils:cpp-lint:clang-format"
         vars:
-          FLAGS: "--dry-run"
-          SRC_DIR: "{{.G_EXAMPLES_DIR}}"
+          FLAGS: ["--dry-run"]
+          INCLUDE_FILENAME_PATTERNS: ["*.cpp", "*.h", "*.hpp", "*.inc"]
+          ROOT_PATHS: *cpp_source_files
+          VENV_DIR: "{{.G_LINT_VENV_DIR}}"
 
   cpp-format-fix:
-    sources: *cpp_format_src_files
+    sources: *cpp_source_files
     deps: ["cpp-configs", "venv"]
     cmds:
-      - task: "clang-format"
+      - task: ":utils:cpp-lint:clang-format"
         vars:
-          FLAGS: "-i"
-          SRC_DIR: "{{.G_SRC_SPIDER_DIR}}"
-      - task: "clang-format"
-        vars:
-          FLAGS: "-i"
-          SRC_DIR: "{{.G_TEST_DIR}}"
-      - task: "clang-format"
-        vars:
-          FLAGS: "-i"
-          SRC_DIR: "{{.G_EXAMPLES_DIR}}"
+          FLAGS: ["-i"]
+          INCLUDE_FILENAME_PATTERNS: ["*.cpp", "*.h", "*.hpp", "*.inc"]
+          ROOT_PATHS: *cpp_source_files
+          VENV_DIR: "{{.G_LINT_VENV_DIR}}"
 
   cpp-static-check:
     # Alias task to `cpp-static-fix` since we don't currently support automatic fixes.
@@ -112,7 +94,7 @@ tasks:
       - "{{.G_SPIDER_COMPILE_COMMANDS_DB}}"
       - "{{.TASKFILE}}"
       - "taskfile.yaml"
-      - "tools/yscope-dev-utils/lint-configs/.clang-tidy"
+      - "tools/yscope-dev-utils/exports/lint-configs/.clang-tidy"
     deps: [":config-cmake-project", "cpp-configs", "venv"]
     cmds:
       - task: "clang-tidy"
@@ -165,7 +147,7 @@ tasks:
       - |-
         . "{{.G_LINT_VENV_DIR}}/bin/activate"
         yamllint \
-          --config-file "tools/yscope-dev-utils/lint-configs/.yamllint.yml" \
+          --config-file "tools/yscope-dev-utils/exports/lint-configs/.yamllint.yml" \
           --strict \
           .gersemirc \
           .github/ \
@@ -176,18 +158,6 @@ tasks:
           taskfile.yaml \
           test-tasks.yaml
 
-  clang-format:
-    internal: true
-    requires:
-      vars: ["FLAGS", "SRC_DIR"]
-    cmd: |-
-      . "{{.G_LINT_VENV_DIR}}/bin/activate"
-      find "{{.SRC_DIR}}" \
-        -type f \
-        \( -iname "*.cpp" -o -iname "*.h" -o -iname "*.hpp" \) \
-        -print0 | \
-          xargs -0 --no-run-if-empty clang-format {{.FLAGS}} -Werror
-
   clang-tidy:
     internal: true
     requires:
@@ -229,18 +199,18 @@ tasks:
     run: "once"
     deps:
       - ":init"
-      - task: ":utils:validate-checksum"
+      - task: ":utils:checksum:validate"
         vars:
           CHECKSUM_FILE: "{{.CHECKSUM_FILE}}"
-          DATA_DIR: "{{.OUTPUT_DIR}}"
+          INCLUDE_PATTERNS: ["{{.OUTPUT_DIR}}"]
     cmds:
-      - task: ":utils:create-venv"
+      - task: ":utils:misc:create-venv"
         vars:
           LABEL: "lint"
           OUTPUT_DIR: "{{.OUTPUT_DIR}}"
-          REQUIREMENTS_FILE: "lint-requirements.txt"
+          REQUIREMENTS_FILE: "{{.ROOT_DIR}}/lint-requirements.txt"
       # This command must be last
-      - task: ":utils:compute-checksum"
+      - task: ":utils:checksum:compute"
         vars:
-          DATA_DIR: "{{.OUTPUT_DIR}}"
-          OUTPUT_FILE: "{{.CHECKSUM_FILE}}"
+          CHECKSUM_FILE: "{{.CHECKSUM_FILE}}"
+          INCLUDE_PATTERNS: ["{{.OUTPUT_DIR}}"]

src/spider/client/Data.hpp

@@ -20,7 +20,6 @@
 #include "Exception.hpp"
 
 namespace spider {
-
 namespace core {
 class Data;
 class DataStorage;

src/spider/client/Driver.cpp

@@ -21,7 +21,6 @@
 #include "Exception.hpp"
 
 namespace spider {
-
 Driver::Driver(std::string const& storage_url)
         : m_storage_factory{std::make_shared<core::MySqlStorageFactory>(storage_url)} {
     boost::uuids::random_generator gen;
@@ -126,5 +125,4 @@ auto Driver::kv_store_get(std::string const& key) -> std::optional<std::string>
     }
     return value;
 }
-
 }  // namespace spider

src/spider/client/Driver.hpp

@@ -183,8 +183,8 @@ class Driver {
      * @throw spider::ConnectionException
      */
     template <TaskIo ReturnType, TaskIo... Params, TaskIo... Inputs>
-    auto
-    start(TaskFunction<ReturnType, Params...> const& task, Inputs&&... inputs) -> Job<ReturnType> {
+    auto start(TaskFunction<ReturnType, Params...> const& task, Inputs&&... inputs)
+            -> Job<ReturnType> {
         // Check input type
         static_assert(
                 sizeof...(Inputs) == sizeof...(Params),
@@ -247,8 +247,8 @@ class Driver {
      * @throw spider::ConnectionException
      */
     template <TaskIo ReturnType, TaskIo... Params, TaskIo... Inputs>
-    auto
-    start(TaskGraph<ReturnType, Params...> const& graph, Inputs&&... inputs) -> Job<ReturnType> {
+    auto start(TaskGraph<ReturnType, Params...> const& graph, Inputs&&... inputs)
+            -> Job<ReturnType> {
         // Check input type
         static_assert(
                 sizeof...(Inputs) == sizeof...(Params),

src/spider/client/Job.hpp

@@ -223,7 +223,8 @@ class Job {
             for_n<std::tuple_size_v<ReturnType>>([&](auto i) {
                 using T = std::tuple_element_t<i.cValue, ReturnType>;
                 if (task_index >= output_task_ids.size()) {
-                    throw ConnectionException{fmt::format("Not enough output tasks for job result")
+                    throw ConnectionException{
+                            fmt::format("Not enough output tasks for job result")
                     };
                 }
                 core::Task const& task = tasks[task_index];
@@ -266,7 +267,8 @@ class Job {
                         msgpack::object const& obj = handle.get();
                         std::get<i.cValue>(result) = obj.as<T>();
                     } catch (msgpack::type_error const& e) {
-                        throw ConnectionException{fmt::format("Failed to unpack data: {}", e.what())
+                        throw ConnectionException{
+                                fmt::format("Failed to unpack data: {}", e.what())
                         };
                     }
                 }
@@ -302,7 +304,8 @@ class Job {
                 }
                 err = m_data_storage->get_data(conn, optional_data_id.value(), &data);
                 if (!err.success()) {
-                    throw ConnectionException{fmt::format("Failed to get data: {}", err.description)
+                    throw ConnectionException{
+                            fmt::format("Failed to get data: {}", err.description)
                     };
                 }
                 return core::DataImpl::create_data<DataType>(

src/spider/client/TaskContext.cpp

@@ -15,7 +15,6 @@
 #include "Exception.hpp"
 
 namespace spider {
-
 auto TaskContext::get_id() const -> boost::uuids::uuid {
     return m_task_id;
 }
@@ -70,5 +69,4 @@ auto TaskContext::get_jobs() -> std::vector<boost::uuids::uuid> {
     }
     return job_ids;
 }
-
 }  // namespace spider

src/spider/client/TaskContext.hpp

@@ -129,8 +129,8 @@ class TaskContext {
      * @throw spider::ConnectionException
      */
     template <TaskIo ReturnType, TaskIo... Params, TaskIo... Inputs>
-    auto
-    start(TaskFunction<ReturnType, Params...> const& task, Inputs&&... inputs) -> Job<ReturnType> {
+    auto start(TaskFunction<ReturnType, Params...> const& task, Inputs&&... inputs)
+            -> Job<ReturnType> {
         // Check input type
         static_assert(
                 sizeof...(Inputs) == sizeof...(Params),
@@ -187,8 +187,8 @@ class TaskContext {
      * @throw spider::ConnectionException
      */
     template <TaskIo ReturnType, TaskIo... Params, TaskIo... Inputs>
-    auto
-    start(TaskGraph<ReturnType, Params...> const& graph, Inputs&&... inputs) -> Job<ReturnType> {
+    auto start(TaskGraph<ReturnType, Params...> const& graph, Inputs&&... inputs)
+            -> Job<ReturnType> {
         // Check input type
         static_assert(
                 sizeof...(Inputs) == sizeof...(Params),

src/spider/client/task.hpp

@@ -8,7 +8,6 @@
 #include "type_utils.hpp"
 
 namespace spider {
-
 /**
  * Concept that represents the input to or output from a Task.
  *
@@ -92,7 +91,6 @@ struct MergeTaskGraphTypes<TaskGraph<ReturnType, GraphParams...>, InputType, Inp
 
 template <TaskIo ReturnType, RunnableOrTaskIo... Inputs>
 using TaskGraphType = typename MergeTaskGraphTypes<TaskGraph<ReturnType>, Inputs...>::Type;
-
 }  // namespace spider
 
 #endif  // SPIDER_CLIENT_TASK_HPP

src/spider/client/type_utils.hpp

@@ -58,6 +58,5 @@ struct ExtractTemplateParam<t<P>> {
 
 template <class T>
 using ExtractTemplateParamT = typename ExtractTemplateParam<T>::Type;
-
 }  // namespace spider
 #endif  // SPIDER_CLIENT_TYPE_UTILS_HPP

src/spider/core/Data.hpp

@@ -42,7 +42,6 @@ class Data {
         m_id = gen();
     }
 };
-
 }  // namespace spider::core
 
 #endif  // SPIDER_CORE_DATA_HPP

src/spider/core/DataImpl.hpp

@@ -9,7 +9,6 @@
 #include "Data.hpp"
 
 namespace spider::core {
-
 class DataImpl {
 public:
     template <class T>
@@ -26,7 +25,6 @@ class DataImpl {
         return data.get_impl();
     }
 };
-
 }  // namespace spider::core
 
 #endif

src/spider/core/Driver.hpp

@@ -7,7 +7,6 @@
 #include <boost/uuid/uuid.hpp>
 
 namespace spider::core {
-
 class Driver {
 public:
     explicit Driver(boost::uuids::uuid const id) : m_id{id} {}
@@ -36,7 +35,6 @@ class Scheduler {
     std::string m_addr;
     int m_port;
 };
-
 }  // namespace spider::core
 
 #endif  // SPIDER_CORE_DRIVER_HPP

src/spider/core/Error.hpp

@@ -29,7 +29,6 @@ struct StorageErr {
 
     [[nodiscard]] auto success() const -> bool { return StorageErrType::Success == type; }
 };
-
 }  // namespace spider::core
 
 #endif  // SPIDER_CORE_ERROR_HPP

src/spider/core/JobMetadata.hpp

@@ -7,7 +7,6 @@
 #include <boost/uuid/uuid.hpp>
 
 namespace spider::core {
-
 class JobMetadata {
 public:
     JobMetadata() = default;
@@ -41,7 +40,6 @@ enum class JobStatus : std::uint8_t {
     Failed,
     Cancelled
 };
-
 }  // namespace spider::core
 
 #endif  // SPIDER_CORE_JOBMETADATA_HPP

src/spider/core/Task.hpp

@@ -18,20 +18,22 @@
 namespace spider::core {
 class TaskInput {
 public:
-    explicit TaskInput(std::string type) : m_type(std::move(type)) {};
+    explicit TaskInput(std::string type) : m_type(std::move(type)) {}
 
     TaskInput(boost::uuids::uuid output_task_id, std::uint8_t position, std::string type)
             : m_task_output({output_task_id, position}),
-              m_type(std::move(type)) {};
+              m_type(std::move(type)) {}
+
     TaskInput(std::string value, std::string type)
             : m_value(std::move(value)),
-              m_type(std::move(type)) {};
+              m_type(std::move(type)) {}
+
     explicit TaskInput(boost::uuids::uuid data_id)
             : m_data_id(data_id),
-              m_type(typeid(spider::core::Data).name()) {};
+              m_type(typeid(spider::core::Data).name()) {}
 
-    [[nodiscard]] auto get_task_output(
-    ) const -> std::optional<std::tuple<boost::uuids::uuid, std::uint8_t>> {
+    [[nodiscard]] auto get_task_output() const
+            -> std::optional<std::tuple<boost::uuids::uuid, std::uint8_t>> {
         return m_task_output;
     }
 
@@ -145,8 +147,8 @@ class ScheduleTaskMetadata {
 
     auto set_client_id(boost::uuids::uuid const client_id) -> void { m_client_id = client_id; }
 
-    auto set_job_creation_time(std::chrono::system_clock::time_point const job_creation_time
-    ) -> void {
+    auto set_job_creation_time(std::chrono::system_clock::time_point const job_creation_time)
+            -> void {
         m_job_creation_time = job_creation_time;
     }
 
@@ -222,7 +224,6 @@ class Task {
     std::vector<TaskInput> m_inputs;
     std::vector<TaskOutput> m_outputs;
 };
-
 }  // namespace spider::core
 
 #endif  // SPIDER_CORE_TASK_HPP