Backport pure-C parser

.clang-format

@@ -0,0 +1,74 @@
+---
+Language: Cpp
+
+# Indentation
+UseTab: Never
+IndentWidth: 4
+BreakBeforeBraces: Attach
+IndentCaseLabels: false
+NamespaceIndentation: None
+ContinuationIndentWidth: 4
+IndentPPDirectives: None
+IndentWrappedFunctionNames: false
+AccessModifierOffset: -2
+
+# Alignment
+AlignAfterOpenBracket: BlockIndent
+AlignConsecutiveAssignments: false
+AlignConsecutiveDeclarations: false
+AlignConsecutiveMacros: false
+AlignEscapedNewlines: Left
+AlignOperands: false
+AlignTrailingComments: true
+DerivePointerAlignment: false
+PointerAlignment: Right
+
+# Function calls formatting
+BinPackArguments: false
+BinPackParameters: false
+AllowAllArgumentsOnNextLine: false
+ExperimentalAutoDetectBinPacking: false
+PenaltyBreakBeforeFirstCallParameter: 1
+AlwaysBreakAfterDefinitionReturnType: None
+
+# Wrapping and Breaking
+ColumnLimit: 0
+AllowShortBlocksOnASingleLine: Never
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: All
+AllowShortIfStatementsOnASingleLine: Always
+AllowShortLoopsOnASingleLine: false
+AlwaysBreakAfterReturnType: None
+AlwaysBreakBeforeMultilineStrings: false
+AlwaysBreakTemplateDeclarations: No
+BreakBeforeBinaryOperators: None
+BreakBeforeTernaryOperators: false
+BreakConstructorInitializers: BeforeColon
+BreakInheritanceList: BeforeColon
+BreakStringLiterals: false
+CompactNamespaces: false
+ConstructorInitializerAllOnOneLineOrOnePerLine: false
+Cpp11BracedListStyle: false
+ReflowComments: false
+SortIncludes: Never
+
+# Spaces
+SpaceAfterCStyleCast: true
+SpaceAfterLogicalNot: false
+SpaceAfterTemplateKeyword: true
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeCpp11BracedList: true
+SpaceBeforeCtorInitializerColon: true
+SpaceBeforeInheritanceColon: true
+SpaceBeforeParens: ControlStatements
+SpaceBeforeRangeBasedForLoopColon: true
+SpaceBeforeSquareBrackets: false
+SpaceInEmptyBlock: false
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 1
+SpacesInAngles: false
+SpacesInCStyleCastParentheses: false
+SpacesInConditionalStatement: false
+SpacesInContainerLiterals: true
+SpacesInParentheses: false
+SpacesInSquareBrackets: false

.github/workflows/c-check.yml

@@ -0,0 +1,54 @@
+name: C Code Generation and Formatting Check
+
+on:
+  push:
+  pull_request: {}
+  merge_group: {}
+
+jobs:
+  format-check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: "3.4"
+          bundler-cache: none
+      - name: Set working directory as safe
+        run: git config --global --add safe.directory $(pwd)
+      - name: Install dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libdb-dev curl autoconf automake m4 libtool
+      - name: Install clang-format from LLVM
+        run: |
+          wget -O - https://apt.llvm.org/llvm-snapshot.gpg.key | sudo apt-key add -
+          sudo apt-add-repository "deb http://apt.llvm.org/jammy/ llvm-toolchain-jammy-20 main"
+          sudo apt-get update
+          sudo apt-get install -y clang-format-20
+          sudo ln -sf /usr/bin/clang-format-20 /usr/local/bin/clang-format
+          clang-format --version
+      - name: Count processors
+        run: nproc
+      - name: Install Re2c
+        run: |
+          cd /tmp
+          curl -L https://github.com/skvadrik/re2c/archive/refs/tags/4.3.tar.gz > re2c-4.3.tar.gz
+          tar xf re2c-4.3.tar.gz
+          cd re2c-4.3
+          autoreconf -i -W all
+          ./configure
+          make -j"$(nproc)" -l"$(nproc)"
+          sudo make install
+      - name: Update rubygems & bundler
+        run: |
+          ruby -v
+          gem update --system
+      - name: bin/setup
+        run: |
+          bin/setup
+      - name: Check C code generation and formatting
+        run: |
+          clang-format --version
+          bundle exec rake lexer templates compile confirm_lexer confirm_templates
+          bundle exec rake format:c_check

.github/workflows/ruby.yml

@@ -28,8 +28,6 @@ jobs:
           - ruby: "3.4"
             job: stdlib_test
             rubyopt: "--enable-frozen-string-literal"
-          - ruby: "3.4"
-            job: lexer templates compile confirm_lexer confirm_templates
           - ruby: "3.4"
             job: rubocop validate test_doc build test_generate_stdlib raap
           - ruby: "3.4"
@@ -48,17 +46,6 @@ jobs:
         run: |
           sudo apt-get update
           sudo apt-get install -y libdb-dev curl autoconf automake m4 libtool python3
-      - name: Install Re2c
-        if: ${{ contains(matrix.job, 'lexer') }}
-        run: |
-          cd /tmp
-          curl -L https://github.com/skvadrik/re2c/archive/refs/tags/3.1.tar.gz > re2c-3.1.tar.gz
-          tar xf re2c-3.1.tar.gz
-          cd re2c-3.1
-          autoreconf -i -W all
-          ./configure
-          make
-          sudo make install
       - name: Update rubygems & bundler
         run: |
           ruby -v
@@ -102,3 +89,31 @@ jobs:
       - run: bundle exec rake test:valgrind
         env:
           RUBY_FREE_AT_EXIT: 1
+  C99_compile:
+    runs-on: macos-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        ruby: ['3.4', head]
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install dependencies
+        run: |
+          brew install ruby-build
+      - uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: ${{ matrix.ruby }}
+          bundler: none
+      - name: Set working directory as safe
+        run: git config --global --add safe.directory $(pwd)
+      - name: Update rubygems & bundler
+        run: |
+          ruby -v
+          gem update --system
+      - name: clang version
+        run: clang --version
+      - name: bin/setup
+        run: |
+          bin/setup
+      - run: bundle exec rake clean compile_c99
+

README.md

@@ -198,6 +198,43 @@ After checking out the repo, run `bin/setup` to install dependencies. Then, run
 
 To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
 
+### C Code Formatting
+
+This project uses `clang-format` to enforce consistent formatting of C code with a `.clang-format` configuration in the root directory.
+
+#### Setup
+
+First, install clang-format:
+
+```bash
+# macOS
+brew install clang-format
+
+# Ubuntu/Debian
+sudo apt-get install clang-format
+
+# Windows
+choco install llvm
+```
+
+#### Usage
+
+Format all C source files:
+
+```bash
+rake format:c
+```
+
+Check formatting without making changes:
+
+```bash
+rake format:c_check
+```
+
+#### Editor Integration
+
+For VS Code users, install the "clangd" extension which will automatically use the project's `.clang-format` file.
+
 ## Contributing
 
 Bug reports and pull requests are welcome on GitHub at https://github.com/ruby/rbs.

Rakefile

@@ -36,19 +36,98 @@ end
 multitask :default => [:test, :stdlib_test, :typecheck_test, :rubocop, :validate, :test_doc]
 
 task :lexer do
-  sh "re2c -W --no-generation-date -o ext/rbs_extension/lexer.c ext/rbs_extension/lexer.re"
+  sh "re2c -W --no-generation-date -o src/lexer.c src/lexer.re"
+  sh "clang-format -i -style=file src/lexer.c"
 end
 
 task :confirm_lexer => :lexer do
   puts "Testing if lexer.c is updated with respect to lexer.re"
-  sh "git diff --exit-code ext/rbs_extension/lexer.c"
+  sh "git diff --exit-code src/lexer.c"
 end
 
 task :confirm_templates => :templates do
   puts "Testing if generated code under include and src is updated with respect to templates"
   sh "git diff --exit-code -- include src"
 end
 
+# Task to format C code using clang-format
+namespace :format do
+  dirs = ["src", "ext", "include"]
+
+  # Find all C source and header files
+  files = `find #{dirs.join(" ")} -type f \\( -name "*.c" -o -name "*.h" \\)`.split("\n")
+
+  desc "Format C source files using clang-format"
+  task :c do
+    puts "Formatting C files..."
+
+    # Check if clang-format is installed
+    unless system("which clang-format > /dev/null 2>&1")
+      abort "Error: clang-format not found. Please install clang-format first."
+    end
+
+    if files.empty?
+      puts "No C files found to format"
+      next
+    end
+
+    puts "Found #{files.length} files to format (excluding generated files)"
+
+    exit_status = 0
+    files.each do |file|
+      puts "Formatting #{file}"
+      unless system("clang-format -i -style=file #{file}")
+        puts "❌ Error formatting #{file}"
+        exit_status = 1
+      end
+    end
+
+    exit exit_status unless exit_status == 0
+    puts "✅ All files formatted successfully"
+  end
+
+  desc "Check if C source files are properly formatted"
+  task :c_check do
+    puts "Checking C file formatting..."
+
+    # Check if clang-format is installed
+    unless system("which clang-format > /dev/null 2>&1")
+      abort "Error: clang-format not found. Please install clang-format first."
+    end
+
+    if files.empty?
+      puts "No C files found to check"
+      next
+    end
+
+    puts "Found #{files.length} files to check (excluding generated files)"
+
+    needs_format = false
+    files.each do |file|
+      formatted = `clang-format -style=file #{file}`
+      original = File.read(file)
+
+      if formatted != original
+        puts "❌ #{file} needs formatting"
+        puts "Diff:"
+        # Save formatted version to temp file and run diff
+        temp_file = "#{file}.formatted"
+        File.write(temp_file, formatted)
+        system("diff -u #{file} #{temp_file}")
+        File.unlink(temp_file)
+        needs_format = true
+      end
+    end
+
+    if needs_format
+      warn "Some files need formatting. Run 'rake format:c' to format them."
+      exit 1
+    else
+      puts "✅ All files are properly formatted"
+    end
+  end
+end
+
 rule ".c" => ".re" do |t|
   puts "⚠️⚠️⚠️ #{t.name} is older than #{t.source}. You may need to run `rake lexer` ⚠️⚠️⚠️"
 end
@@ -70,17 +149,22 @@ task :confirm_annotation do
 end
 
 task :templates do
-  sh "#{ruby} templates/template.rb include/rbs/constants.h"
-  sh "#{ruby} templates/template.rb include/rbs/ruby_objs.h"
-  sh "#{ruby} templates/template.rb src/constants.c"
-  sh "#{ruby} templates/template.rb src/ruby_objs.c"
+  sh "#{ruby} templates/template.rb ext/rbs_extension/ast_translation.h"
+  sh "#{ruby} templates/template.rb ext/rbs_extension/ast_translation.c"
+
+  sh "#{ruby} templates/template.rb ext/rbs_extension/class_constants.h"
+  sh "#{ruby} templates/template.rb ext/rbs_extension/class_constants.c"
+
+  sh "#{ruby} templates/template.rb include/rbs/ast.h"
+  sh "#{ruby} templates/template.rb src/ast.c"
+
+  # Format the generated files
+  Rake::Task["format:c"].invoke
 end
 
-task :compile => "ext/rbs_extension/lexer.c"
-task :compile => "include/rbs/constants.h"
-task :compile => "include/rbs/ruby_objs.h"
-task :compile => "src/constants.c"
-task :compile => "src/ruby_objs.c"
+task :compile => "ext/rbs_extension/class_constants.h"
+task :compile => "ext/rbs_extension/class_constants.c"
+task :compile => "src/lexer.c"
 
 task :test_doc do
   files = Dir.chdir(File.expand_path('..', __FILE__)) do
@@ -430,3 +514,25 @@ task :changelog do
     puts "  (🤑 There is no *unreleased* pull request associated to the milestone.)"
   end
 end
+
+desc "Compile extension without C23 extensions"
+task :compile_c99 do
+  ENV["TEST_NO_C23"] = "true"
+  Rake::Task[:"compile"].invoke
+ensure
+  ENV.delete("TEST_NO_C23")
+end
+
+task :prepare_bench do
+  ENV.delete("DEBUG")
+  Rake::Task[:"clobber"].invoke
+  Rake::Task[:"templates"].invoke
+  Rake::Task[:"compile"].invoke
+end
+
+task :prepare_profiling do
+  ENV["DEBUG"] = "1"
+  Rake::Task[:"clobber"].invoke
+  Rake::Task[:"templates"].invoke
+  Rake::Task[:"compile"].invoke
+end