Preprocessor (•)(•)

.clang-tidy

@@ -1,20 +1,103 @@
-Checks: '-*,
+Checks: "-*,
   modernize-*,
   performance-*,
   cppcoreguidelines-*,
   bugprone-*,
+  misc-header-include-cycle,
+  readability-delete-null-pointer,
+  readability-identifier-naming,
+  readability-misleading-indentation,
+  readability-redundant-control-flow,
+  readability-static-accessed-through-instance,
+  llvm-namespace-comment,
   -modernize-use-trailing-return-type,
   -performance-no-int-to-ptr,
   -cppcoreguidelines-avoid-const-or-ref-data-members,
   -cppcoreguidelines-pro-type-reinterpret-cast,
   -cppcoreguidelines-pro-type-union-access,
   -cppcoreguidelines-pro-bounds-pointer-arithmetic,
   -bugprone-exception-escape,
-  -bugprone-easily-swappable-parameters'
+  -bugprone-easily-swappable-parameters"
 
-WarningsAsErrors: ''
-HeaderFilterRegex: ''
+WarningsAsErrors: ""
+HeaderFilterRegex: ""
 FormatStyle: none
 CheckOptions:
   - key: modernize-use-using.IgnoreMacros
-    value: 'true'
+    value: "true"
+  - key: readability-identifier-naming.NamespaceCase
+    value: "lower_case"
+  - key: readability-identifier-naming.ClassCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.StructCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.TemplateParameterCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.FunctionCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.VariableCase
+    value: "lower_case"
+  - key: readability-identifier-naming.ClassMemberCase
+    value: "lower_case"
+  - key: readability-identifier-naming.ClassMemberSuffix
+    value: "_"
+  - key: readability-identifier-naming.PrivateMemberSuffix
+    value: "_"
+  - key: readability-identifier-naming.ProtectedMemberSuffix
+    value: "_"
+  - key: readability-identifier-naming.EnumConstantCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.EnumConstantPrefix
+    value: "k"
+  - key: readability-identifier-naming.ConstexprVariableCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.ConstexprVariablePrefix
+    value: "k"
+  - key: readability-identifier-naming.GlobalConstantCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.GlobalConstantPrefix
+    value: "k"
+  - key: readability-identifier-naming.MemberConstantCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.MemberConstantPrefix
+    value: "k"
+  - key: readability-identifier-naming.StaticConstantCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.StaticConstantPrefix
+    value: "k"
+  - key: readability-identifier-naming.StructCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.TemplateParameterCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.FunctionCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.VariableCase
+    value: "lower_case"
+  - key: readability-identifier-naming.ClassMemberCase
+    value: "lower_case"
+  - key: readability-identifier-naming.ClassMemberSuffix
+    value: "_"
+  - key: readability-identifier-naming.PrivateMemberSuffix
+    value: "_"
+  - key: readability-identifier-naming.ProtectedMemberSuffix
+    value: "_"
+  - key: readability-identifier-naming.EnumConstantCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.EnumConstantPrefix
+    value: "k"
+  - key: readability-identifier-naming.ConstexprVariableCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.ConstexprVariablePrefix
+    value: "k"
+  - key: readability-identifier-naming.GlobalConstantCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.GlobalConstantPrefix
+    value: "k"
+  - key: readability-identifier-naming.MemberConstantCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.MemberConstantPrefix
+    value: "k"
+  - key: readability-identifier-naming.StaticConstantCase
+    value: "CamelCase"
+  - key: readability-identifier-naming.StaticConstantPrefix
+    value: "k"

.github/workflows/ci_tests.yml

@@ -3,47 +3,6 @@ name: "CI tests"
 on: [ push, workflow_dispatch ]
 
 jobs:
-  build-mingw:
-    name: Tests and application run on Windows Latest MinGW
-    runs-on: windows-latest
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install MinGW toolchain
-        shell: powershell
-        run: |
-          choco install mingw --yes --no-progress
-          echo "C:\tools\mingw64\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
-
-      - name: Create CMake cache
-        run: |
-          cmake -S . -B cmake-build-release -DCMAKE_BUILD_TYPE=Release -G "MinGW Makefiles"
-          cmake -S . -B cmake-build-debug -DCMAKE_BUILD_TYPE=Debug -G "MinGW Makefiles"
-
-      - name: Build main target
-        shell: bash
-        run: |
-          cmake --build cmake-build-release || echo Built with errors
-
-      - name: Build tests target
-        shell: bash
-        run: |
-          cmake --build cmake-build-debug --target ovumc_tests || echo Built with errors
-
-      - name: Run program
-        working-directory: .\cmake-build-release
-        shell: bash
-        run: |
-          ./ovumc.exe --help
-
-      - name: Run tests
-        working-directory: .\cmake-build-debug
-        shell: bash
-        run: |
-          # ./ovumc_tests.exe
-          echo "Tests are not run on Windows MinGW due to issues with the test runner"
-
   build-matrix:
     name: Tests and application run on ${{ matrix.config.name }}
     runs-on: ${{ matrix.config.os }}

.gitignore

@@ -11,6 +11,7 @@ build/
 
 # Clangd rules
 .clangd
+.cache/
 
 # File-based project format
 *.iws

.gitmodules

@@ -0,0 +1,4 @@
+[submodule "tests/test_data/examples"]
+	path = tests/test_data/examples
+	url = https://github.com/Ovum-Programming-Language/OvumExamples
+	branch = main

bin/main.cpp

@@ -3,14 +3,6 @@
 #include "lib/compiler_ui/compiler_ui_functions.hpp"
 
 int main(int32_t argc, char** argv) {
-  const std::string sample = R"ovum(
-// demo
-fun Main(args: StringArray): Int {
-    val count: Int = args.Length()
-    sys::Print("Args count: " + count.ToString())
-    return 0
-}
-)ovum";
-
-  return StartCompilerConsoleUI({"ovumc", sample}, std::cout, std::cerr);
+  std::vector<std::string> args = std::vector<std::string>(argv, argv + argc);
+  return StartCompilerConsoleUI(args, std::cout, std::cerr);
 }

lib/compiler_ui/CMakeLists.txt

@@ -5,6 +5,7 @@ add_library(compiler_ui STATIC
 
 target_link_libraries(compiler_ui PUBLIC
         lexer
+        preprocessor
 )
 
 target_include_directories(compiler_ui PUBLIC ${PROJECT_SOURCE_DIR})

lib/compiler_ui/compiler_ui_functions.cpp

@@ -1,28 +1,50 @@
-#include "lib/lexer/Lexer.hpp"
-
-#include <exception>
-
 #include "compiler_ui_functions.hpp"
 
+#include "lib/preprocessor/Preprocessor.hpp"
+
 int32_t StartCompilerConsoleUI(const std::vector<std::string>& args, std::ostream& out, std::ostream& err) {
   if (args.size() < 2) {
-    err << "Insufficient arguments\n";
+    err << "Usage: ovumc <main_file.ovum> [include_path1] [include_path2] ...\n";
+    err << "Example: ovumc sample.ovum /path/to/includes\n";
     return 1;
   }
 
-  const std::string& sample = args[1];
-  Lexer lx(sample, true);
+  if (args[1] == "--help") {
+    out << "Usage: ovumc <main_file.ovum> [include_path1] [include_path2] ...\n";
+    out << "Example: ovumc sample.ovum /path/to/includes\n";
+    return 0;
+  }
+
+  std::filesystem::path main_file = args[1];
+  std::set<std::filesystem::path> include_paths;
+
+  include_paths.emplace(main_file.parent_path());
+
+  for (size_t i = 2; i < args.size(); ++i) {
+    include_paths.emplace(args[i]);
+  }
 
-  try {
-    auto toks = lx.Tokenize();
+  std::unordered_set<std::string> predefined_symbols;
 
-    for (auto& t : toks) {
-      out << t->ToString() << "\n";
-    }
-  } catch (const std::exception& e) {
-    err << "Lexer error: " << e.what() << "\n";
+  ovum::compiler::preprocessor::PreprocessingParameters params{
+      .include_paths = include_paths, .predefined_symbols = predefined_symbols, .main_file = main_file};
+
+  ovum::compiler::preprocessor::Preprocessor preprocessor(params);
+
+  auto result = preprocessor.Process();
+
+  if (!result) {
+    err << result.error().what() << "\n";
     return 1;
   }
 
+  const auto& tokens = result.value();
+
+  for (const auto& t : tokens) {
+    out << t->ToString() << "\n";
+  }
+
+  out << "\nPreprocessed " << tokens.size() << " tokens successfully.\n";
+
   return 0;
 }

lib/lexer/handlers/ColonHandler.cpp

@@ -9,7 +9,7 @@ OptToken ColonHandler::Scan(SourceCodeWrapper& wrapper) {
 
   if (next != '\0') {
     std::string two = op + next;
-    if (wrapper.IsMultiOp(two)) {
+    if (SourceCodeWrapper::IsMultiOp(two)) {
       wrapper.Advance();
       op = two;
       return std::make_optional(TokenFactory::MakeOperator(std::move(op), wrapper.GetLine(), wrapper.GetTokenCol()));

lib/lexer/handlers/IdentifierHandler.cpp

@@ -21,7 +21,7 @@ OptToken IdentifierHandler::Scan(SourceCodeWrapper& wrapper) {
         TokenFactory::MakeFloatLiteral(s, std::nan(""), wrapper.GetLine(), wrapper.GetTokenCol()));
   }
 
-  if (wrapper.IsKeyword(s)) {
+  if (SourceCodeWrapper::IsKeyword(s)) {
     if (s == "true" || s == "false") {
       return std::make_optional(
           TokenFactory::MakeBoolLiteral(s, s == "true", wrapper.GetLine(), wrapper.GetTokenCol()));

lib/lexer/handlers/OperatorHandler.cpp

@@ -10,7 +10,7 @@ OptToken OperatorHandler::Scan(SourceCodeWrapper& wrapper) {
   if (p != '\0') {
     std::string two = op + p;
 
-    if (wrapper.IsMultiOp(two)) {
+    if (SourceCodeWrapper::IsMultiOp(two)) {
       wrapper.Advance();
       op = two;
     }

lib/preprocessor/CMakeLists.txt

@@ -1,14 +1,32 @@
 add_library(preprocessor STATIC
-    Preprocessor.cpp
-    token_processor_factory.cpp
+        Preprocessor.cpp
+        token_processor_factory.cpp
+        import_processor/TokenImportProcessor.cpp
+        directives_processor/TokenDirectivesProcessor.cpp
+        import_processor/FileGraph.cpp
+        directives_processor/directives_chain_factory.cpp
+        directives_processor/handlers/DefaultHandler.cpp
+        directives_processor/handlers/DefineHandler.cpp
+        directives_processor/handlers/ElseHandler.cpp
+        directives_processor/handlers/EndifHandler.cpp
+        directives_processor/handlers/UndefHandler.cpp
+        directives_processor/handlers/IfndefHandler.cpp
+        directives_processor/handlers/IfdefHandler.cpp
 )
 
 target_include_directories(preprocessor
-    PUBLIC
-    ${CMAKE_SOURCE_DIR}
+        PUBLIC
+        ${CMAKE_SOURCE_DIR}
 )
 
 target_include_directories(preprocessor
-    PRIVATE
-    ${CMAKE_CURRENT_SOURCE_DIR}
+        PRIVATE
+        ${CMAKE_CURRENT_SOURCE_DIR}
 )
+
+target_link_libraries(preprocessor PUBLIC
+        lexer
+)
+
+target_include_directories(preprocessor PUBLIC ${PROJECT_SOURCE_DIR})
+

lib/preprocessor/PreprocessingParameters.hpp

@@ -1,14 +1,19 @@
-#ifndef PREPROCESSINGPARAMETERS_HPP_
-#define PREPROCESSINGPARAMETERS_HPP_
+#ifndef PREPROCESSOR_PREPROCESSINGPARAMETERS_HPP_
+#define PREPROCESSOR_PREPROCESSINGPARAMETERS_HPP_
 
 #include <filesystem>
 #include <set>
 #include <string>
 #include <unordered_set>
 
+namespace ovum::compiler::preprocessor {
+
 struct PreprocessingParameters {
   std::set<std::filesystem::path> include_paths;
   std::unordered_set<std::string> predefined_symbols;
+  std::filesystem::path main_file;
 };
 
+} // namespace ovum::compiler::preprocessor
+
 #endif // PREPROCESSINGPARAMETERS_HPP_