C parser/forward struct declarations

c_parser/__init__.py

@@ -3,48 +3,102 @@
 
 from .models import (
     CArray,
+    CAtomic,
+    CBool,
+    CChar,
+    CComposedType,
+    CConst,
+    CDouble,
+    CDoubleComplex,
     CDiagnostic,
     CEnum,
     CEnumerator,
-    CField,
     CFile,
+    CFloat,
+    CFloatComplex,
     CFunction,
-    CGlobal,
+    CFunctionType,
     CInclude,
+    CInitializer,
+    CInt,
+    CLong,
+    CLongDouble,
+    CLongDoubleComplex,
+    CLongLong,
     CMacro,
     CParameter,
     CParseError,
     CPointer,
     CProject,
+    CQualifier,
+    CRestrict,
+    CShort,
+    CSignedChar,
     CSourceLocation,
     CStruct,
-    CTypeRef,
+    CType,
     CTypedef,
+    CUnknownType,
     CUnion,
+    CUnsignedChar,
+    CUnsignedInt,
+    CUnsignedLong,
+    CUnsignedLongLong,
+    CUnsignedShort,
+    CVariable,
+    CVoid,
+    CVolatile,
 )
 from .parser import CParser, parse_c_file, parse_c_project
 
 __all__ = (
     "CArray",
+    "CAtomic",
+    "CBool",
+    "CChar",
+    "CComposedType",
+    "CConst",
+    "CDouble",
+    "CDoubleComplex",
     "CDiagnostic",
     "CEnum",
     "CEnumerator",
-    "CField",
     "CFile",
+    "CFloat",
+    "CFloatComplex",
     "CFunction",
-    "CGlobal",
+    "CFunctionType",
     "CInclude",
+    "CInitializer",
+    "CInt",
+    "CLong",
+    "CLongDouble",
+    "CLongDoubleComplex",
+    "CLongLong",
     "CMacro",
     "CParameter",
     "CParseError",
     "CPointer",
     "CParser",
     "CProject",
+    "CQualifier",
+    "CRestrict",
+    "CShort",
+    "CSignedChar",
     "CSourceLocation",
     "CStruct",
-    "CTypeRef",
+    "CType",
     "CTypedef",
     "CUnion",
+    "CUnknownType",
+    "CUnsignedChar",
+    "CUnsignedInt",
+    "CUnsignedLong",
+    "CUnsignedLongLong",
+    "CUnsignedShort",
+    "CVariable",
+    "CVoid",
+    "CVolatile",
     "parse_c_file",
     "parse_c_project",
 )

c_parser/cli.py

@@ -50,7 +50,7 @@ def format_c_report(report: dict[str, dict]) -> str:
         lines.append(f"  Unions: {len(parsed.get('unions') or [])}")
         lines.append(f"  Enums: {len(parsed.get('enums') or [])}")
         lines.append(f"  Typedefs: {len(parsed.get('typedefs') or [])}")
-        lines.append(f"  Globals: {len(parsed.get('globals') or [])}")
+        lines.append(f"  Variables: {len(parsed.get('variables') or [])}")
         lines.append(f"  Macros: {len(parsed.get('macros') or [])}")
         lines.append(f"  Includes: {len(parsed.get('includes') or [])}")
         lines.append(f"  Diagnostics: {len(parsed.get('diagnostics') or [])}")

c_parser/lexer.py

@@ -169,6 +169,15 @@ def top_level_partition(text: str, delimiter: str = "=") -> tuple[str, str | Non
     return text.strip(), None
 
 
+def _is_aggregate_definition_header(header: str) -> bool:
+    """Identify a tag definition before deciding that a brace starts a body."""
+    compact = " ".join(header.split())
+    if "(" in compact or "=" in compact:
+        return False
+    words = compact.split()
+    return any(word in {"struct", "union", "enum"} for word in words)
+
+
 def split_top_level_c_source(
     source: str,
     filename: str | None = None,
@@ -198,6 +207,7 @@ def split_top_level_c_source(
     block_start_line = 1
     block_start_column = 1
     block_source_line: str | None = None
+    aggregate_block = False
 
     while i < len(stripped):
         char = stripped[i]
@@ -251,13 +261,15 @@ def split_top_level_c_source(
                     block_start_line = start_line
                     block_start_column = start_column
                     block_source_line = _source_line(source_lines, start_line)
+                    aggregate_block = _is_aggregate_definition_header(header)
             brace_depth = 1
-            start_index = None
+            if not aggregate_block:
+                start_index = None
         elif char == "{" and brace_depth:
             brace_depth += 1
         elif char == "}" and brace_depth:
             brace_depth -= 1
-            if brace_depth == 0 and block_header:
+            if brace_depth == 0 and block_header and not aggregate_block:
                 segments.append(
                     CTopLevelSegment(
                         text=block_header,
@@ -296,6 +308,9 @@ def split_top_level_c_source(
                     )
                 )
             start_index = None
+            block_header = None
+            block_source_line = None
+            aggregate_block = False
 
         line, column = _advance_position(char, line, column)
         i += 1