Replace Python ANTLR parser with C++ parser and AST builder

.github/workflows/release.yml

@@ -12,19 +12,43 @@ permissions:
   contents: read
 
 jobs:
-  release:
-    runs-on: ubuntu-latest
+  build-wheels:
+    name: Build wheels on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
 
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
-      - name: Install poetry
-        run: pipx install poetry
-      - name: Set up Python
-        uses: actions/setup-python@v5
+
+      - name: Build wheels
+        uses: pypa/cibuildwheel@v2.22
+
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels-${{ matrix.os }}
+          path: wheelhouse/*.whl
+
+  publish:
+    name: Publish to PyPI
+    needs: [build-wheels]
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+
+    steps:
+      - name: Download all artifacts
+        uses: actions/download-artifact@v4
         with:
-          python-version: "3.x"
-      - name: Build package
-        run: poetry build
+          path: dist
+          merge-multiple: true
+
       - name: Publish to PyPI
-        run: poetry publish --username=__token__ --password=${{ secrets.PYPI_TOKEN }}
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          password: ${{ secrets.PYPI_TOKEN }}

.github/workflows/testing.yml

@@ -19,7 +19,7 @@ jobs:
       matrix:
         os: [ubuntu-latest, macos-latest, windows-latest]
         python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
-        
+
     steps:
     - name: Checkout code
       uses: actions/checkout@v4
@@ -29,8 +29,24 @@ jobs:
       uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
-    - name: Install dependencies
-      run: poetry install --all-extras
+        cache: poetry
+    - name: Cache C++ parser wheel
+      uses: actions/cache@v4
+      id: cpp-cache
+      with:
+        path: .cpp-wheel
+        key: cpp-parser-${{ runner.os }}-py${{ matrix.python-version }}-${{ hashFiles('src/vtlengine/AST/Grammar/_cpp_parser/**', 'CMakeLists.txt', 'pyproject.toml', 'scripts/setup_antlr4_runtime.sh') }}
+    - name: Download ANTLR4 C++ runtime
+      if: steps.cpp-cache.outputs.cache-hit != 'true'
+      run: bash scripts/setup_antlr4_runtime.sh
+    - name: Build C++ parser wheel
+      if: steps.cpp-cache.outputs.cache-hit != 'true'
+      run: pip wheel . -w .cpp-wheel --no-deps -v
+    - name: Install package and dependencies
+      run: |
+        poetry install --no-root --all-extras
+        poetry run pip install .cpp-wheel/*.whl
+      shell: bash
     - name: Check compliance with code formatting guidelines
       run: poetry run ruff format --no-cache --check
     - name: Run lint checks

.github/workflows/ubuntu_test_24_04.yml

@@ -17,11 +17,17 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v4
 
+      - name: Cache C++ parser wheel
+        uses: actions/cache@v4
+        id: cpp-cache
+        with:
+          path: .cpp-wheel
+          key: cpp-parser-ubuntu2404-py3.12-${{ hashFiles('src/vtlengine/AST/Grammar/_cpp_parser/**', 'CMakeLists.txt', 'pyproject.toml', 'scripts/setup_antlr4_runtime.sh') }}
+
       - name: Install system dependencies
         run: |
           sudo apt-get update
           sudo apt-get install -y \
-            python3-antlr4 \
             python3-pip \
             python3-httpx \
             python3-pandas \
@@ -31,7 +37,10 @@ jobs:
             python3-jsonschema \
             python3-networkx \
             python3-sqlglot \
-            python3-pytest
+            python3-pytest \
+            cmake \
+            g++ \
+            pybind11-dev
 
       - name: Install pip-only dependencies
         run: |
@@ -43,18 +52,18 @@ jobs:
             duckdb==1.1 \
             pysdmx==1.9.0
 
-      - name: Install Poetry
-        run: |
-          pip install poetry
-          poetry config virtualenvs.create false
+      - name: Download ANTLR4 C++ runtime
+        if: steps.cpp-cache.outputs.cache-hit != 'true'
+        run: bash scripts/setup_antlr4_runtime.sh
 
-      - name: Build wheel
-        run: |
-          poetry build -f wheel -o .
+      - name: Build C++ parser wheel
+        if: steps.cpp-cache.outputs.cache-hit != 'true'
+        run: pip wheel . -w .cpp-wheel --no-deps -v
+        env:
+          PIP_BREAK_SYSTEM_PACKAGES: "1"
 
-      - name: Install built package
-        run: |
-          pip install "./vtlengine-$(poetry version -s)-py3-none-any.whl" --no-dependencies --break-system-packages
+      - name: Install C++ parser
+        run: pip install --break-system-packages --no-deps .cpp-wheel/*.whl
 
       - name: Run tests
         run: pytest --verbose --tb=short --strict-markers --strict-config --durations=10

.github/workflows/version.yml

@@ -16,33 +16,5 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v4
 
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.12'
-
-      - name: Install poetry
-        run: pipx install poetry
-      - name: Install dependencies
-        run: poetry install
-
-      - name: Extract __version__ from module
-        id: module-version
-        run: |
-          echo "MODULE_VERSION=$(poetry run python -c 'import vtlengine; print(vtlengine.__version__)')" >> $GITHUB_OUTPUT
-
-      - name: Extract version from pyproject.toml
-        id: pyproject-version
-        run: |
-          echo "value=$(poetry version --short)" >> $GITHUB_OUTPUT
-
       - name: Compare versions
-        run: |
-          if [ "${{ steps.pyproject-version.outputs.value }}" != "${{ steps.module-version.outputs.MODULE_VERSION }}" ]; then
-            echo "❌ Version mismatch detected!"
-            echo "pyproject.toml version: ${{ steps.pyproject-version.outputs.value }}"
-            echo "__version__ value: ${{ steps.module-version.outputs.MODULE_VERSION }}"
-            exit 1
-          else
-            echo "✅ Versions match (${{ steps.pyproject-version.outputs.value }})"
-          fi
+        run: bash scripts/check_version.sh

.gitignore

@@ -187,6 +187,10 @@ docs/plans/
 !/CONTRIBUTING.md
 !/SECURITY.md
 
+# C++ parser build artifacts
+third_party/
+build/
+
 # Claude Code settings
 .claude/*
 !.claude/CLAUDE.md

CMakeLists.txt

@@ -0,0 +1,70 @@
+cmake_minimum_required(VERSION 3.15...3.30)
+project(vtlengine_cpp_parser LANGUAGES CXX)
+
+set(CMAKE_CXX_STANDARD 17)
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
+# Find pybind11
+find_package(pybind11 CONFIG REQUIRED)
+
+# -------------------------------------------------------------------
+# ANTLR4 C++ runtime (vendored as static library)
+# -------------------------------------------------------------------
+set(ANTLR4_SRC_DIR "${CMAKE_SOURCE_DIR}/third_party/antlr4-cpp-runtime/src")
+
+# Collect all ANTLR4 runtime .cpp files
+file(GLOB_RECURSE ANTLR4_RUNTIME_SOURCES "${ANTLR4_SRC_DIR}/*.cpp")
+
+add_library(antlr4_runtime STATIC ${ANTLR4_RUNTIME_SOURCES})
+target_include_directories(antlr4_runtime PUBLIC "${ANTLR4_SRC_DIR}")
+target_compile_definitions(antlr4_runtime PUBLIC ANTLR4CPP_STATIC)
+
+# Suppress warnings from third-party code
+if(MSVC)
+    target_compile_options(antlr4_runtime PRIVATE /w)
+    # Fix missing chrono include in ProfilingATNSimulator on MSVC
+    target_compile_options(antlr4_runtime PRIVATE /FI"chrono")
+else()
+    target_compile_options(antlr4_runtime PRIVATE -w)
+endif()
+
+# -------------------------------------------------------------------
+# Generated VTL parser (C++ files from ANTLR)
+# -------------------------------------------------------------------
+set(VTL_PARSER_DIR "${CMAKE_SOURCE_DIR}/src/vtlengine/AST/Grammar/_cpp_parser")
+
+set(VTL_PARSER_SOURCES
+    "${VTL_PARSER_DIR}/VtlLexer.cpp"
+    "${VTL_PARSER_DIR}/VtlParser.cpp"
+    "${VTL_PARSER_DIR}/VtlBaseListener.cpp"
+    "${VTL_PARSER_DIR}/VtlBaseVisitor.cpp"
+    "${VTL_PARSER_DIR}/VtlListener.cpp"
+    "${VTL_PARSER_DIR}/VtlVisitor.cpp"
+)
+
+# -------------------------------------------------------------------
+# pybind11 module
+# -------------------------------------------------------------------
+pybind11_add_module(vtl_cpp_parser
+    "${VTL_PARSER_DIR}/bindings.cpp"
+    "${VTL_PARSER_DIR}/ast_builder.cpp"
+    ${VTL_PARSER_SOURCES}
+)
+
+target_include_directories(vtl_cpp_parser PRIVATE
+    "${ANTLR4_SRC_DIR}"
+    "${VTL_PARSER_DIR}"
+)
+
+target_link_libraries(vtl_cpp_parser PRIVATE antlr4_runtime)
+
+# Suppress warnings from generated parser code
+if(MSVC)
+    target_compile_options(vtl_cpp_parser PRIVATE /w)
+else()
+    target_compile_options(vtl_cpp_parser PRIVATE -w)
+endif()
+
+# Install the module into the vtlengine._cpp_parser package
+install(TARGETS vtl_cpp_parser DESTINATION vtlengine/AST/Grammar/_cpp_parser)