[Cpp Parser] centralize source path filtering

cpp/libclang/integration_test/cases/std_internal_namespace_rendering/BUILD

@@ -0,0 +1,25 @@
+# *******************************************************************************
+# 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("//cpp/libclang/integration_test:test_rules.bzl", "cpp_parser_integration_test")
+
+cc_library(
+    name = "std_internal_namespace_rendering",
+    srcs = ["transport.cpp"],
+    visibility = ["//cpp/libclang:__subpackages__"],
+)
+
+cpp_parser_integration_test(
+    name = "test_std_internal_namespace_rendering",
+    expected_output = ["expected.json"],
+    target = ":std_internal_namespace_rendering",
+)

cpp/libclang/integration_test/cases/std_internal_namespace_rendering/expected.json

@@ -0,0 +1,61 @@
+{
+  "functions": [],
+  "types": {
+    "TextCache": {
+      "enclosing_namespace_id": null,
+      "entity_type": "Class",
+      "enum_literals": [],
+      "id": "TextCache",
+      "methods": [
+        {
+          "modifiers": [],
+          "name": "Find",
+          "parameters": [
+            {
+              "is_variadic": false,
+              "name": "key",
+              "param_type": "const std::string &"
+            }
+          ],
+          "return_type": "std::string_view",
+          "source_location": {
+            "file": "cpp/libclang/integration_test/cases/std_internal_namespace_rendering/transport.cpp",
+            "line": 20
+          },
+          "template_parameters": null,
+          "visibility": "public"
+        }
+      ],
+      "name": "TextCache",
+      "relationships": [],
+      "source_location": {
+        "file": "cpp/libclang/integration_test/cases/std_internal_namespace_rendering/transport.cpp",
+        "line": 17
+      },
+      "template_parameters": null,
+      "type_aliases": [],
+      "variables": [
+        {
+          "data_type": "std::string",
+          "is_static": false,
+          "name": "name_",
+          "source_location": {
+            "file": "cpp/libclang/integration_test/cases/std_internal_namespace_rendering/transport.cpp",
+            "line": 23
+          },
+          "visibility": "private"
+        },
+        {
+          "data_type": "std::unordered_map<std::string, std::string_view>",
+          "is_static": false,
+          "name": "cache_",
+          "source_location": {
+            "file": "cpp/libclang/integration_test/cases/std_internal_namespace_rendering/transport.cpp",
+            "line": 24
+          },
+          "visibility": "private"
+        }
+      ]
+    }
+  }
+}

cpp/libclang/integration_test/cases/std_internal_namespace_rendering/run_test.rs

@@ -0,0 +1,19 @@
+// *******************************************************************************
+// 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
+// *******************************************************************************
+
+use test_framework::run_parser_case;
+
+#[test]
+fn test_std_internal_namespace_rendering() {
+    run_parser_case();
+}

cpp/libclang/integration_test/cases/std_internal_namespace_rendering/transport.cpp

@@ -0,0 +1,25 @@
+/********************************************************************************
+ * 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
+ ********************************************************************************/
+#include <string>
+#include <string_view>
+#include <unordered_map>
+
+class TextCache
+{
+  public:
+    std::string_view Find(const std::string& key);
+
+  private:
+    std::string name_;
+    std::unordered_map<std::string, std::string_view> cache_;
+};

cpp/libclang/integration_test/cases/std_template_specialization_filter/BUILD

@@ -0,0 +1,26 @@
+# *******************************************************************************
+# 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("//cpp/libclang/integration_test:test_rules.bzl", "cpp_parser_integration_test")
+
+cc_library(
+    name = "std_template_specialization_filter",
+    srcs = ["specialization.cpp"],
+    hdrs = ["specialization.h"],
+    visibility = ["//cpp/libclang:__subpackages__"],
+)
+
+cpp_parser_integration_test(
+    name = "test_std_template_specialization_filter",
+    expected_output = ["expected.json"],
+    target = ":std_template_specialization_filter",
+)

cpp/libclang/integration_test/cases/std_template_specialization_filter/expected.json

@@ -0,0 +1,32 @@
+{
+  "functions": [],
+  "types": {
+    "demo::Key": {
+      "enclosing_namespace_id": "demo",
+      "entity_type": "Struct",
+      "enum_literals": [],
+      "id": "demo::Key",
+      "methods": [],
+      "name": "Key",
+      "relationships": [],
+      "source_location": {
+        "file": "./cpp/libclang/integration_test/cases/std_template_specialization_filter/specialization.h",
+        "line": 23
+      },
+      "template_parameters": null,
+      "type_aliases": [],
+      "variables": [
+        {
+          "data_type": "std::uint32_t",
+          "is_static": false,
+          "name": "value",
+          "source_location": {
+            "file": "./cpp/libclang/integration_test/cases/std_template_specialization_filter/specialization.h",
+            "line": 25
+          },
+          "visibility": "public"
+        }
+      ]
+    }
+  }
+}

cpp/libclang/integration_test/cases/std_template_specialization_filter/run_test.rs

@@ -0,0 +1,19 @@
+// *******************************************************************************
+// 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
+// *******************************************************************************
+
+use test_framework::run_parser_case;
+
+#[test]
+fn test_std_template_specialization_filter() {
+    run_parser_case();
+}

cpp/libclang/integration_test/cases/std_template_specialization_filter/specialization.cpp

@@ -0,0 +1,13 @@
+/********************************************************************************
+ * 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
+ ********************************************************************************/
+#include "cpp/libclang/integration_test/cases/std_template_specialization_filter/specialization.h"

cpp/libclang/integration_test/cases/std_template_specialization_filter/specialization.h

@@ -0,0 +1,44 @@
+/********************************************************************************
+ * 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
+ ********************************************************************************/
+#ifndef CPP_LIBCLANG_INTEGRATION_TEST_CASES_STD_TEMPLATE_SPECIALIZATION_FILTER_SPECIALIZATION_H
+#define CPP_LIBCLANG_INTEGRATION_TEST_CASES_STD_TEMPLATE_SPECIALIZATION_FILTER_SPECIALIZATION_H
+
+#include <cstddef>
+#include <cstdint>
+#include <functional>
+
+namespace demo
+{
+
+struct Key
+{
+    std::uint32_t value;
+};
+
+}  // namespace demo
+
+namespace std
+{
+
+template <>
+struct hash<demo::Key>
+{
+    std::size_t operator()(const demo::Key& key) const noexcept
+    {
+        return std::hash<std::uint32_t>{}(key.value);
+    }
+};
+
+}  // namespace std
+
+#endif

cpp/libclang/src/main.rs

@@ -22,8 +22,7 @@ use class_diagram::{ClassDiagram, SimpleEntity};
 use class_serializer::ClassSerializer;
 
 use utils::{render_entity_tree, write_debug_json, write_entity_tree, write_fbs_output};
-use visit_tu::visitor;
-use visit_tu::{FunctionDef, VisitContext, Visitor};
+use visit_tu::{is_external_dependency_path, FunctionDef, VisitContext, Visitor};
 
 #[derive(ClapParser, Debug)]
 #[command(name = "cpp_parser")]
@@ -120,7 +119,7 @@ fn parse_file(
     debug!("Parsing TU: {:?}", file);
 
     if let Some(path_str) = file.to_str() {
-        if visitor::is_external_dependency_path(path_str) {
+        if is_external_dependency_path(path_str) {
             debug!("Skipping external dependency file: {:?}", file);
             return;
         }

cpp/libclang/src/visitor/BUILD

@@ -21,6 +21,7 @@ rust_library(
         "src/enum_visitor.rs",
         "src/function_visitor.rs",
         "src/lib.rs",
+        "src/source_filter.rs",
         "src/visitor.rs",
     ],
     visibility = ["//cpp/libclang:__subpackages__"],
@@ -38,6 +39,7 @@ rust_test(
     srcs = [
         "src/class_parser_helper.rs",
         "src/class_parser_helper_test.rs",
+        "src/source_filter.rs",
     ],
     deps = [
         "@crates//:clang",

cpp/libclang/src/visitor/src/class_parser_helper.rs

@@ -13,6 +13,7 @@
 
 #![cfg_attr(test, allow(dead_code))]
 
+use crate::source_filter;
 use clang::{Entity, EntityKind, Type, TypeKind};
 use serde::{Deserialize, Serialize};
 
@@ -306,26 +307,11 @@ fn is_declared_in_external_or_system_header(ty: &Type) -> bool {
         .and_then(|decl| decl.get_location())
         .map(|location| {
             let (path, _, _) = location.get_presumed_location();
-            is_external_or_system_path(&path)
+            source_filter::is_external_or_system_path(&path)
         })
         .unwrap_or(false)
 }
 
-fn is_external_or_system_path(path: &str) -> bool {
-    is_system_header_path(path)
-        || path.contains("/external/")
-        || path.contains("external/")
-        || path.contains("_virtual_includes/")
-        || (path.contains("bazel-out/") && path.contains("/external/"))
-}
-
-fn is_system_header_path(path: &str) -> bool {
-    path.starts_with("/usr/include")
-        || path.starts_with("/usr/local/include")
-        || path.starts_with("/opt/")
-        || path.contains("/gcc/")
-}
-
 fn contains_template_type(resolved: &ResolvedType) -> bool {
     match resolved {
         ResolvedType::Template { .. } => true,

cpp/libclang/src/visitor/src/class_parser_helper_test.rs

@@ -13,6 +13,8 @@
 
 #[path = "class_parser_helper.rs"]
 mod class_parser_helper;
+#[path = "source_filter.rs"]
+mod source_filter;
 
 use class_parser_helper::{collapse_std_internal_namespaces, ResolvedType};
 

cpp/libclang/src/visitor/src/lib.rs

@@ -16,6 +16,7 @@ mod class_visitor;
 pub mod context;
 mod enum_visitor;
 mod function_visitor;
+mod source_filter;
 pub mod visitor;
 
 pub use class_parser_helper::ResolvedType;
@@ -24,5 +25,6 @@ pub use context::VisitContext;
 pub use enum_visitor::EnumVisitor;
 pub use function_visitor::FunctionVisitor;
 pub use sequence_logic::{BodyItem, FunctionDef};
+pub use source_filter::is_external_dependency_path;
 pub use visitor::AstVisitor;
 pub use visitor::Visitor;