Migrate cpp parser

Author: melodyoncode

MODULE.bazel

@@ -128,6 +128,41 @@ crate.spec(
     package = "flatbuffers",
     version = "25.9.23",
 )
+crate.spec(
+    package = "clang",
+    version = "=1.0.3",
+)
+crate.spec(
+    package = "clang-sys",
+    version = "=1.8.1",
+)
+crate.spec(
+    package = "libloading",
+    version = ">=0.9.0",
+)
+crate.spec(
+    package = "assert-json-diff",
+    version = "2.0.0",
+)
+
+# Annotations for libclang
+crate.annotation(
+    crate = "clang-sys",
+    crate_features = [
+        "runtime",
+        "clang_18_0",
+    ],
+    patch_args = ["-p1"],
+    patches = [
+        "//third_party:libclang/patchv1.8.2.patch",
+        "//third_party:libclang/patchv1.9.0.patch",
+    ],
+    deps = ["@crates//:libloading"],
+)
+crate.annotation(
+    crate = "clang",
+    crate_features = ["runtime"],
+)
 crate.from_specs()
 use_repo(crate, "crates")
 
@@ -294,3 +329,37 @@ pip.parse(
     },
 )
 use_repo(pip, "pip_ai_checker")
+
+###############################################################################
+# LLVM Toolchain
+###############################################################################
+bazel_dep(name = "toolchains_llvm", version = "1.6.0", dev_dependency = True)
+
+llvm = use_extension(
+    "@toolchains_llvm//toolchain/extensions:llvm.bzl",
+    "llvm",
+    dev_dependency = True,
+)
+llvm.toolchain(
+    compile_flags = {"": [
+        "-march=nehalem",
+        "-ffp-model=strict",
+        # Security
+        "-U_FORTIFY_SOURCE",  # https://github.com/google/sanitizers/issues/247
+        "-fstack-protector",
+        "-fno-omit-frame-pointer",
+        # Diagnostics
+        "-fcolor-diagnostics",
+        "-Wno-deprecated-declarations",
+        "-Wno-error=self-assign-overloaded",
+        "-Wthread-safety",
+    ]},
+    cxx_standard = {"": "c++17"},
+    extra_link_libs = {"": [
+        "-lrt",
+        # This is the agreed way to ensure linking for targets using std::atomic operations.
+        "-latomic",
+    ]},
+    llvm_version = "19.1.7",
+)
+use_repo(llvm, "llvm_toolchain", "llvm_toolchain_llvm")

cpp/libclang/BUILD

@@ -0,0 +1,31 @@
+# *******************************************************************************
+# Copyright (c) 2026 Contributors to the Eclipse Foundation
+#
+# See the NOTICE file(s) distributed with this work for additional
+# information regarding copyright ownership.
+#
+# This program and the accompanying materials are made available under the
+# terms of the Apache License Version 2.0 which is available at
+# https://www.apache.org/licenses/LICENSE-2.0
+#
+# SPDX-License-Identifier: Apache-2.0
+# *******************************************************************************
+load("@rules_rust//rust:defs.bzl", "rust_binary")
+
+rust_binary(
+    name = "clang_rs_parser",
+    srcs = ["src/main.rs"],
+    data = [
+        "@llvm_toolchain_llvm//:libclang",
+    ],
+    env = {
+        "LIBCLANG_PATH": "$(rootpath @llvm_toolchain_llvm//:libclang)",
+    },
+    visibility = ["//visibility:public"],
+    deps = [
+        "//cpp/libclang/src/visitor:visit_tu",
+        "@crates//:clang",
+        "@crates//:clap",
+        "@crates//:serde_json",
+    ],
+)

cpp/libclang/README.md

@@ -0,0 +1,31 @@
+# Run C++ parser targets
+
+## Configure a parser target in `BUILD`
+
+If you want to parse a specific Bazel target, use the `cpp_parser(...)` rule in the `BUILD` file like:
+
+```
+load("//cpp/libclang:cpp_parser.bzl", "cpp_parser")
+
+cpp_parser(
+  name = "cpp_parser_include_3rdparty",
+  extra_args = [
+  ],
+  target = "//cpp/libclang/integration_test/cases/include_3rdparty",
+  tool = ":clang_rs_parser",
+)
+```
+
+Where:
+
+- `target` is the Bazel target you want to parse.
+
+Expected result:
+
+- Bazel creates parser output artifact:
+  - `bazel-bin/cpp/libclang/cpp_parser_include_3rdparty_result.json`
+
+## Quick check (optional)
+
+```bash
+ls -l bazel-bin/cpp/libclang/cpp_parser_include_3rdparty_result.json