Class JavaScriptParser

gitvizz/gitvizz/graph_generator.py:579–759

class JavaScriptParser(LanguageParser):  # This is the old regex-based parser
    def __init__(self):
        # Regex for functions, classes, and basic imports/exports.
        # WARNING: Regex-based parsing for JS/TS is very limited and error-prone.
        # A proper AST parser (e.g., esprima, acorn, or tree-sitter) is highly recommended for robust analysis.

        # function funcName(...) or const funcName = (...) => { ... } or let funcName = function(...)
        self.function_pattern = re.compile(
            r"^\s*(?:async\s+)?function\s+([a-zA-Z0-9_]+)\s*\(|"  # function foo()
            r"^\s*(?:const|let|var)\s+([a-zA-Z0-9_]+)\s*=\s*(?:async\s*)?\(?[^)]*\)?\s*=>|"  # const foo = () =>
            r"^\s*(?:const|let|var)\s+([a-zA-Z0-9_]+)\s*=\s*function\s*\(",  # const foo = function()
            re.MULTILINE,
        )

        self.class_pattern = re.compile(
            r"^\s*class\s+([a-zA-Z0-9_]+)(?:\s+extends\s+([a-zA-Z0-9_]+))?",
            re.MULTILINE,
        )

        # import defaultExport from 'module'; import { namedExport } from 'module'; import * as name from 'module';
        self.import_pattern = re.compile(
            r"import\s+(?:(.+?)\s+from\s+)?['\"]([^'\"]+)['\"]", re.MULTILINE
        )
        pass

    def parse(
        self, files_data: List[Dict[str, Any]], all_files_content: Dict[str, str]
    ) -> Tuple[List[GraphNodeData], List[GraphEdgeData]]:
        nodes_data: List[GraphNodeData] = []
        edges_data: List[GraphEdgeData] = []

        for file_data in files_data:
            path = file_data["path"]
            # Ensure the parser only processes files it's supposed to handle,
            # although GraphGenerator._get_parser should already filter.
            if not (path.endswith((".js", ".jsx", ".ts", ".tsx"))):
                continue

            content = file_data["content"]
            # Module ID from path, similar to Python
            module_id = path.replace("/", ".").rsplit(".", 1)[0]
            if (
                Path(path).name == Path(path).stem and "." not in Path(path).stem
            ):  # for files like 'index' without extension in id
                module_id = path.replace("/", ".")

            # Create module node
            module_node: GraphNodeData = {
                "id": module_id,
                "name": Path(path).name,  # Use full filename as name for module
                "category": "module",
                "file": path,
                "start_line": 1,
                "end_line": len(content.splitlines()),
                "code": None,
                "parent_id": str(Path(path).parent),  # Set parent to directory path
                "imports": [],
            }