Add pre-commit configuration file

.clang-tidy

@@ -0,0 +1,19 @@
+Checks:
+  - -*
+  - cppcoreguidelines-pro-type-member-init
+  - modernize-redundant-void-arg
+  - modernize-use-bool-literals
+  - modernize-use-default-member-init
+  - modernize-use-nullptr
+  - readability-braces-around-statements
+  - readability-redundant-member-init
+HeaderFileExtensions: ['', h, hh, hpp, hxx, inc]
+ImplementationFileExtensions: [c, cc, cpp, cxx]
+HeaderFilterRegex: (extension/src/openvic-dataloader)/
+FormatStyle: file
+CheckOptions:
+  cppcoreguidelines-pro-type-member-init.IgnoreArrays: true
+  cppcoreguidelines-pro-type-member-init.UseAssignment: true
+  modernize-use-bool-literals.IgnoreMacros: false
+  modernize-use-default-member-init.IgnoreMacros: false
+  modernize-use-default-member-init.UseAssignment: true

.github/workflows/builds.yml

@@ -10,9 +10,44 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  static-checks:
+    name: Code style, file formatting, and docs
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout project
+        uses: actions/[email protected]
+        with:
+          fetch-depth: 2
+
+      - name: Install APT dependencies
+        uses: awalsh128/cache-apt-pkgs-action@latest
+        with:
+          packages: libxml2-utils
+
+      - name: Get changed files
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          git config diff.wsErrorHighlight all
+          if [ "${{ github.event_name }}" == "pull_request" -o "${{ github.event.forced }}" == "true" -o "${{ github.event.created }}" == "true" ]; then
+            files=$(git diff-tree --no-commit-id --name-only -r HEAD^1..HEAD 2> /dev/null || true)
+          elif [ "${{ github.event_name }}" == "push" -a "${{ github.event.created }}" == "false" ]; then
+            files=$(git diff-tree --no-commit-id --name-only -r ${{ github.event.before }}..${{ github.event.after }} 2> /dev/null || true)
+          fi
+          echo "$files" >> changed.txt
+          cat changed.txt
+          files=$(echo "$files" | xargs -I {} sh -c 'echo "\"./{}\""' | tr '\n' ' ')
+          echo "CHANGED_FILES=$files" >> $GITHUB_ENV
+
+      - name: Style checks via pre-commit
+        uses: pre-commit/[email protected]
+        with:
+          extra_args: --files ${{ env.CHANGED_FILES }}
+
   build:
     runs-on: ${{matrix.os}}
     name: ${{matrix.name}}
+    needs: static-checks
     permissions: write-all
     strategy:
       fail-fast: false

.github/workflows/cache_cleanup.yml

@@ -0,0 +1,32 @@
+# https://github.com/actions/cache/blob/main/tips-and-workarounds.md#force-deletion-of-caches-overriding-default-cache-eviction-policy
+name: 🧹 Cache Cleanup
+on:
+  pull_request:
+    types:
+      - closed
+
+jobs:
+  cleanup:
+    name: Cleanup PR caches
+    runs-on: ubuntu-latest
+    permissions:
+      # `actions:write` permission is required to delete caches
+      actions: write
+      contents: read
+    steps:
+      - name: Cleanup
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GH_REPO: ${{ github.repository }}
+          BRANCH: refs/pull/${{ github.event.pull_request.number }}/merge
+        run: |
+          echo "Fetching list of cache key"
+          cache_keys_for_pr=$(gh cache list --ref $BRANCH --limit 100 --json id --jq '.[].id')
+          # Setting this to not fail the workflow while deleting cache keys.
+          set +e
+          echo "Deleting caches..."
+          for cache_key in $cache_keys_for_pr; do
+            gh cache delete $cache_key
+            echo "Deleted: $cache_key"
+          done
+          echo "Done"

.pre-commit-config.yaml

@@ -0,0 +1,41 @@
+default_language_version:
+  python: python3
+
+repos:
+  - repo: https://github.com/pre-commit/mirrors-clang-format
+    rev: v19.1.3
+    hooks:
+      - id: clang-format
+        files: \.(c|h|cpp|hpp|cc|hh|cxx|hxx|inc)$
+        types_or: [text]
+
+  - repo: https://github.com/pocc/pre-commit-hooks
+    rev: v1.3.5
+    hooks:
+      - id: clang-tidy
+        files: \.(c|h|cpp|hpp)$
+        args: [--fix, --quiet, --use-color]
+        types_or: [text]
+        additional_dependencies: [clang-tidy==19.1.0]
+        require_serial: true
+        stages: [manual] # Not automatically triggered, invoked via `pre-commit run --hook-stage manual clang-tidy`
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.9.10
+    hooks:
+      - id: ruff
+        args: [--fix]
+        files: (\.py|SConstruct|SCsub)$
+        types_or: [text]
+      - id: ruff-format
+        files: (\.py|SConstruct|SCsub)$
+        types_or: [text]
+
+  - repo: https://github.com/crate-ci/typos
+    rev: v1.30.2
+    hooks:
+      - id: typos
+        # exclude: |
+        #   (?x)^(
+        #   )
+        additional_dependencies: [tomli]

SConstruct

@@ -1,10 +1,6 @@
 #!/usr/bin/env python
 
 import os
-import platform
-import sys
-
-import SCons
 
 BINDIR = "bin"
 
@@ -15,10 +11,22 @@ env.PrependENVPath("PATH", os.getenv("PATH"))
 opts = env.SetupOptions()
 
 opts.Add(BoolVariable("run_ovdl_tests", "Build and run the openvic dataloader tests", env.is_standalone))
-opts.Add(BoolVariable("build_ovdl_library", "Build the openvic dataloader library.", env.get("build_ovdl_library", not env.is_standalone)))
+opts.Add(
+    BoolVariable(
+        "build_ovdl_library",
+        "Build the openvic dataloader library.",
+        env.get("build_ovdl_library", not env.is_standalone),
+    )
+)
 opts.Add(BoolVariable("build_ovdl_headless", "Build the openvic dataloader headless executable", env.is_standalone))
 
-opts.Add(BoolVariable("ubuntu_gcc_invalid_char_hang_bug", "Skips test section which triggers a hang build for gcc-12 on ubuntu-20", False))
+opts.Add(
+    BoolVariable(
+        "ubuntu_gcc_invalid_char_hang_bug",
+        "Skips test section which triggers a hang build for gcc-12 on ubuntu-20",
+        False,
+    )
+)
 
 env.FinalizeOptions()
 
@@ -88,7 +96,7 @@ if env["build_ovdl_headless"]:
     headless_program = headless_env.Program(
         target=os.path.join(BINDIR, headless_name),
         source=headless_env.headless_sources,
-        PROGSUFFIX=".headless" + env["PROGSUFFIX"]
+        PROGSUFFIX=".headless" + env["PROGSUFFIX"],
     )
     default_args += [headless_program]
 
@@ -105,4 +113,4 @@ if "env" in locals():
     # FIXME: This method mixes both cosmetic progress stuff and cache handling...
     env.show_progress(env)
 
-Return("env")
+Return("env")

deps/SCsub

@@ -3,6 +3,7 @@ import os
 
 Import("env")
 
+
 def build_lexy(env):
     env.Append(CPPDEFINES=["LEXY_HAS_UNICODE_DATABASE=1"])
     lexy_env = env.Clone()
@@ -17,13 +18,19 @@ def build_lexy(env):
     else:
         lexy_env.Append(CXXFLAGS=["-std=c++20"])
 
-        lexy_env.Append(CXXFLAGS=["-pedantic-errors", "-Werror", "-Wall", "-Wextra", "-Wconversion", "-Wsign-conversion"])
+        lexy_env.Append(
+            CXXFLAGS=["-pedantic-errors", "-Werror", "-Wall", "-Wextra", "-Wconversion", "-Wsign-conversion"]
+        )
         if lexy_env["CXX"] == "clang++":
             lexy_env.Append(CXXFLAGS=["-Wno-shift-op-parentheses", "-Wno-parentheses-equality"])
         else:
-            lexy_env.Append(CXXFLAGS=[
-                "-Wno-parentheses", "-Wno-unused-local-typedefs", "-Wno-array-bounds" #, "-Wno-maybe-uninitialized", "-Wno-restrict"
-            ])
+            lexy_env.Append(
+                CXXFLAGS=[
+                    "-Wno-parentheses",
+                    "-Wno-unused-local-typedefs",
+                    "-Wno-array-bounds",  # , "-Wno-maybe-uninitialized", "-Wno-restrict"
+                ]
+            )
 
     include_path = "lexy/include"
     source_path = "lexy/src"
@@ -46,6 +53,7 @@ def build_lexy(env):
     env.Append(LIBPATH=[source_dir])
     env.Prepend(LIBS=[library_name])
 
+
 def build_dryad(env):
     include_path = "dryad/include"
     include_dir = env.Dir(include_path)
@@ -59,6 +67,7 @@ def build_dryad(env):
 
     env.exposed_includes += env.dryad["INCPATH"]
 
+
 def build_fmt(env):
     fmt_env = env.Clone()
 
@@ -70,26 +79,43 @@ def build_fmt(env):
     else:
         fmt_env.Append(CXXFLAGS=["-std=c++20"])
 
-        fmt_env.Append(CXXFLAGS=[
-            "-Werror", "-Wall", "-Wextra", "-pedantic", "-Wconversion", "-Wundef"
-        ])
+        fmt_env.Append(CXXFLAGS=["-Werror", "-Wall", "-Wextra", "-pedantic", "-Wconversion", "-Wundef"])
         if fmt_env["CXX"] == "clang++":
-            fmt_env.Append(CXXFLAGS=[
-                "-Wweak-vtables", "-Wshadow",
-                "-Wno-gnu-zero-variadic-macro-arguments"
-            ])
+            fmt_env.Append(CXXFLAGS=["-Wweak-vtables", "-Wshadow", "-Wno-gnu-zero-variadic-macro-arguments"])
         else:
-            fmt_env.Append(CXXFLAGS=[
-                "-Wold-style-cast", "-Wundef", "-Wredundant-decls", "-Wwrite-strings",
-                "-Wpointer-arith", "-Wcast-qual", "-Wformat=2",
-                "-Wmissing-include-dirs", "-Wcast-align", "-Wctor-dtor-privacy",
-                "-Wdisabled-optimization", "-Winvalid-pch", "-Woverloaded-virtual",
-                "-Wconversion", "-Wundef", "-Wno-ctor-dtor-privacy", "-Wno-format-nonliteral",
-                "-Wno-dangling-else", "-Wno-unused-local-typedefs", "-Wdouble-promotion",
-                "-Wtrampolines", "-Wzero-as-null-pointer-constant", "-Wuseless-cast",
-                "-Wvector-operation-performance", "-Wsized-deallocation", "-Wshadow",
-                "-Wshift-overflow=2", "-Wnull-dereference", "-Wduplicated-cond"
-            ])
+            fmt_env.Append(
+                CXXFLAGS=[
+                    "-Wold-style-cast",
+                    "-Wundef",
+                    "-Wredundant-decls",
+                    "-Wwrite-strings",
+                    "-Wpointer-arith",
+                    "-Wcast-qual",
+                    "-Wformat=2",
+                    "-Wmissing-include-dirs",
+                    "-Wcast-align",
+                    "-Wctor-dtor-privacy",
+                    "-Wdisabled-optimization",
+                    "-Winvalid-pch",
+                    "-Woverloaded-virtual",
+                    "-Wconversion",
+                    "-Wundef",
+                    "-Wno-ctor-dtor-privacy",
+                    "-Wno-format-nonliteral",
+                    "-Wno-dangling-else",
+                    "-Wno-unused-local-typedefs",
+                    "-Wdouble-promotion",
+                    "-Wtrampolines",
+                    "-Wzero-as-null-pointer-constant",
+                    "-Wuseless-cast",
+                    "-Wvector-operation-performance",
+                    "-Wsized-deallocation",
+                    "-Wshadow",
+                    "-Wshift-overflow=2",
+                    "-Wnull-dereference",
+                    "-Wduplicated-cond",
+                ]
+            )
 
     include_path = "fmt/include"
     source_path = "fmt/src"
@@ -103,7 +129,6 @@ def build_fmt(env):
     Default(library)
 
     include_dir = fmt_env.Dir(include_path)
-    source_dir = fmt_env.Dir(source_path)
 
     env.fmt = {}
     env.fmt["INCPATH"] = [include_dir]
@@ -119,6 +144,7 @@ def build_fmt(env):
 
     env.exposed_includes += env.fmt["INCPATH"]
 
+
 def build_range_v3(env):
     include_path = "range-v3/include"
     sources = env.GlobRecursive("*.cpp", [include_path])
@@ -137,6 +163,7 @@ def build_range_v3(env):
 
     env.exposed_includes += env.range_v3["INCPATH"]
 
+
 def build_vmcontainer(env):
     vmcontainer_env = env.Clone()
 
@@ -167,8 +194,9 @@ def build_vmcontainer(env):
 
     env.exposed_includes += env.vmcontainer["INCPATH"]
 
+
 build_dryad(env)
 build_fmt(env)
 build_lexy(env)
 build_range_v3(env)
-build_vmcontainer(env)
+build_vmcontainer(env)

include/openvic-dataloader/Error.hpp

@@ -213,7 +213,9 @@ namespace ovdl::error {
 	}
 
 	inline void AnnotatedError::push_back(AnnotationList p_annotations) {
-		if (p_annotations.empty()) return;
+		if (p_annotations.empty()) {
+			return;
+		}
 		insert_child_list_after(_last_annotation, p_annotations);
 		_last_annotation = p_annotations.back();
 	}

include/openvic-dataloader/NodeLocation.hpp

@@ -28,10 +28,11 @@ namespace ovdl {
 		void set_from(const BasicNodeLocation<OtherCharT>& other) {
 			if constexpr (sizeof(CharT) <= sizeof(OtherCharT)) {
 				_begin = reinterpret_cast<const CharT*>(other.begin());
-				if (other.begin() == other.end())
+				if (other.begin() == other.end()) {
 					_end = _begin;
-				else
+				} else {
 					_end = reinterpret_cast<const CharT*>(other.end()) + (sizeof(OtherCharT) - sizeof(CharT));
+				}
 			} else {
 				_begin = reinterpret_cast<const CharT*>(other.begin());
 				if (other.end() - other.begin() <= 0) {
@@ -60,7 +61,9 @@ namespace ovdl {
 
 		static BasicNodeLocation make_from(const char_type* begin, const char_type* end) {
 			end++;
-			if (begin >= end) return BasicNodeLocation(begin);
+			if (begin >= end) {
+				return BasicNodeLocation(begin);
+			}
 			return BasicNodeLocation(begin, end);
 		}
 	};