Skip comments in regex brace matching

desloppify/languages/csharp/_parse_helpers.py

@@ -28,27 +28,47 @@ def find_matching_brace(content: str, open_pos: int) -> int | None:
     depth = 0
     in_string: str | None = None
     escape = False
-    for i in range(open_pos, len(content)):
+    i = open_pos
+    length = len(content)
+    while i < length:
         ch = content[i]
         if in_string:
             if escape:
                 escape = False
+                i += 1
                 continue
             if ch == "\\":
                 escape = True
+                i += 1
                 continue
             if ch == in_string:
                 in_string = None
+            i += 1
             continue
         if ch in ("'", '"'):
             in_string = ch
+            i += 1
+            continue
+        if ch == "/" and i + 1 < length and content[i + 1] == "*":
+            i += 2
+            while i + 1 < length:
+                if content[i] == "*" and content[i + 1] == "/":
+                    i += 2
+                    break
+                i += 1
+            continue
+        if ch == "/" and i + 1 < length and content[i + 1] == "/":
+            i += 2
+            while i < length and content[i] != "\n":
+                i += 1
             continue
         if ch == "{":
             depth += 1
         elif ch == "}":
             depth -= 1
             if depth == 0:
                 return i
+        i += 1
     return None
 
 

desloppify/languages/csharp/tests/test_csharp_parse_helpers.py

@@ -50,6 +50,14 @@ def test_empty_body(self):
         content = "{}"
         assert find_matching_brace(content, 0) == 1
 
+    def test_skips_block_comments_with_unbalanced_braces(self):
+        content = "{ /* } }} {{{ */ return 1; }"
+        assert find_matching_brace(content, 0) == len(content) - 1
+
+    def test_skips_line_comments_with_unbalanced_braces(self):
+        content = "{ // } }}\n return 1; }"
+        assert find_matching_brace(content, 0) == len(content) - 1
+
 
 class TestFindExpressionEnd:
     def test_simple(self):

desloppify/languages/cxx/_parse_helpers.py

@@ -8,27 +8,47 @@ def find_matching_brace(content: str, open_pos: int) -> int | None:
     depth = 0
     in_string: str | None = None
     escape = False
-    for i in range(open_pos, len(content)):
+    i = open_pos
+    length = len(content)
+    while i < length:
         ch = content[i]
         if in_string:
             if escape:
                 escape = False
+                i += 1
                 continue
             if ch == "\\":
                 escape = True
+                i += 1
                 continue
             if ch == in_string:
                 in_string = None
+            i += 1
             continue
         if ch in ("'", '"'):
             in_string = ch
+            i += 1
+            continue
+        if ch == "/" and i + 1 < length and content[i + 1] == "*":
+            i += 2
+            while i + 1 < length:
+                if content[i] == "*" and content[i + 1] == "/":
+                    i += 2
+                    break
+                i += 1
+            continue
+        if ch == "/" and i + 1 < length and content[i + 1] == "/":
+            i += 2
+            while i < length and content[i] != "\n":
+                i += 1
             continue
         if ch == "{":
             depth += 1
         elif ch == "}":
             depth -= 1
             if depth == 0:
                 return i
+        i += 1
     return None
 
 

desloppify/languages/cxx/tests/test_extractors.py

@@ -43,4 +43,30 @@ def test_find_cxx_files_includes_common_header_only_extensions(tmp_path):
 
 
 def test_cxx_extractors_use_local_brace_helper():
-    assert cxx_extractors.find_matching_brace.__module__ == "desloppify.languages.cxx._parse_helpers"
+    assert cxx_extractors.find_matching_brace.__module__ == "desloppify.languages.cxx._parse_helpers"
+
+
+def test_extract_function_with_unbalanced_brace_in_comment(tmp_path):
+    source = tmp_path / "test.cpp"
+    source.write_text(
+        """void validateInput() {
+    /* Validate against old schema:
+       { "type": "required" }
+       See ticket #1234 for context }
+     */
+    if (input.isValid()) {
+        return;
+    }
+    throw std::runtime_error("Invalid");
+}
+""",
+        encoding="utf-8",
+    )
+
+    functions = extract_all_cxx_functions([str(source)])
+
+    assert len(functions) == 1
+    func = functions[0]
+    assert func.name == "validateInput"
+    assert func.end_line == 10
+    assert "input.isValid()" in func.body

desloppify/languages/dart/tests/test_extractors.py

@@ -0,0 +1,32 @@
+"""Tests for Dart regex-based function extraction."""
+
+from __future__ import annotations
+
+from desloppify.languages.dart.extractors import extract_dart_functions
+
+
+def test_extract_dart_functions_ignores_unbalanced_braces_inside_comments(tmp_path):
+    source = tmp_path / "lib" / "app.dart"
+    source.parent.mkdir(parents=True, exist_ok=True)
+    source.write_text(
+        """void validateInput() {
+  /* Validate against old schema:
+     { "type": "required" }
+     See ticket #1234 for context }
+   */
+  if (input.isValid()) {
+    return;
+  }
+  throw StateError("Invalid");
+}
+""",
+        encoding="utf-8",
+    )
+
+    functions = extract_dart_functions(str(source))
+
+    assert len(functions) == 1
+    func = functions[0]
+    assert func.name == "validateInput"
+    assert func.end_line == 10
+    assert "input.isValid()" in func.body

desloppify/languages/rust/extractors.py

@@ -81,7 +81,8 @@ def _find_matching_brace(content: str, open_pos: int) -> int | None:
     depth = 0
     in_string: str | None = None
     i = open_pos
-    while i < len(content):
+    length = len(content)
+    while i < length:
         char = content[i]
         if in_string:
             if char == "\\":
@@ -95,6 +96,19 @@ def _find_matching_brace(content: str, open_pos: int) -> int | None:
             in_string = char
             i += 1
             continue
+        if char == "/" and i + 1 < length and content[i + 1] == "*":
+            i += 2
+            while i + 1 < length:
+                if content[i] == "*" and content[i + 1] == "/":
+                    i += 2
+                    break
+                i += 1
+            continue
+        if char == "/" and i + 1 < length and content[i + 1] == "/":
+            i += 2
+            while i < length and content[i] != "\n":
+                i += 1
+            continue
         if char == "{":
             depth += 1
         elif char == "}":

desloppify/languages/rust/tests/test_extractors.py

@@ -75,3 +75,30 @@ def test_normalize_rust_body_strips_comments_and_logging():
     assert "// comment" not in normalized
     assert "println!" not in normalized
     assert "let value = 1;" in normalized
+
+
+def test_extract_rust_functions_ignores_unbalanced_braces_inside_comments(tmp_path):
+    filepath = _write(
+        tmp_path,
+        "src/lib.rs",
+        """
+pub fn validate_input() {
+    /* Validate against old schema:
+       { "type": "required" }
+       See ticket #1234 for context }
+     */
+    if input_is_valid() {
+        return;
+    }
+    panic!("Invalid");
+}
+""",
+    )
+
+    functions = extract_rust_functions(filepath)
+
+    assert len(functions) == 1
+    func = functions[0]
+    assert func.name == "validate_input"
+    assert func.end_line == 11
+    assert "input_is_valid()" in func.body