|
| 1 | +#!/usr/bin/env python3 |
| 2 | +""" |
| 3 | +Step 3 Refactor: Token class parser, exporter, and controller |
| 4 | +Enhanced to capture attributes, setters, add/remove methods, and key SDK methods (to_proto/from_proto). |
| 5 | +""" |
| 6 | + |
| 7 | +import ast |
| 8 | +from pathlib import Path |
| 9 | +from typing import Dict, List, Any |
| 10 | + |
| 11 | + |
| 12 | +class TokenClassParser: |
| 13 | + """Parses .py files to extract token class attributes and methods.""" |
| 14 | + |
| 15 | + def __init__(self, tokens_dir: Path): |
| 16 | + self.tokens_dir = tokens_dir |
| 17 | + self.errors: List[str] = [] |
| 18 | + |
| 19 | + def extract_classes_from_file(self, file_path: Path) -> Dict[str, Dict[str, List[str]]]: |
| 20 | + """Extract classes with attributes and SDK methods from a Python file.""" |
| 21 | + classes_info = {} |
| 22 | + try: |
| 23 | + with open(file_path, "r", encoding="utf-8") as f: |
| 24 | + tree = ast.parse(f.read(), filename=str(file_path)) |
| 25 | + except Exception as e: |
| 26 | + self.errors.append(f"{file_path}: Failed to parse ({e})") |
| 27 | + return classes_info |
| 28 | + |
| 29 | + for node in tree.body: |
| 30 | + if isinstance(node, ast.ClassDef): |
| 31 | + cls_name = node.name |
| 32 | + attributes = [] |
| 33 | + setters = [] |
| 34 | + others = [] |
| 35 | + |
| 36 | + for item in node.body: |
| 37 | + if isinstance(item, ast.FunctionDef): |
| 38 | + # Attributes from __init__ |
| 39 | + if item.name == "__init__": |
| 40 | + attributes = [arg.arg for arg in item.args.args if arg.arg != "self"] |
| 41 | + |
| 42 | + # SDK setters / repeated field methods |
| 43 | + elif item.name.startswith(("set_", "add_", "remove_")): |
| 44 | + setters.append(item.name) |
| 45 | + |
| 46 | + # Other methods (proto conversion, validation, helpers) |
| 47 | + elif item.name in ("to_proto", "from_proto", "validate", "freeze", "unfreeze"): |
| 48 | + others.append(item.name) |
| 49 | + |
| 50 | + # Optionally, include any other public methods |
| 51 | + elif not item.name.startswith("_"): |
| 52 | + others.append(item.name) |
| 53 | + |
| 54 | + classes_info[cls_name] = { |
| 55 | + "attributes": attributes, |
| 56 | + "setters": setters, |
| 57 | + "other_methods": others |
| 58 | + } |
| 59 | + |
| 60 | + return classes_info |
| 61 | + |
| 62 | + def parse_all(self) -> Dict[str, Any]: |
| 63 | + """Walk tokens directory and parse all classes.""" |
| 64 | + all_classes_info = {} |
| 65 | + modules_seen = set() |
| 66 | + |
| 67 | + for py_file in self.tokens_dir.glob("*.py"): |
| 68 | + if py_file.name == "__init__.py": |
| 69 | + continue |
| 70 | + module_name = py_file.stem |
| 71 | + modules_seen.add(module_name) |
| 72 | + class_info = self.extract_classes_from_file(py_file) |
| 73 | + if class_info: |
| 74 | + all_classes_info.update({f"{module_name}.{k}": v for k, v in class_info.items()}) |
| 75 | + else: |
| 76 | + self.errors.append(f"{py_file}: No classes found or all failed parsing.") |
| 77 | + |
| 78 | + return {"modules": sorted(modules_seen), "classes": all_classes_info, "errors": self.errors} |
| 79 | + |
| 80 | + |
| 81 | +class TokenClassExporter: |
| 82 | + """Handles writing the parsed data to files.""" |
| 83 | + |
| 84 | + def __init__(self, output_dir: Path): |
| 85 | + self.output_dir = output_dir |
| 86 | + self.output_file = output_dir / "steps_3_token_classes_info_readable.py" |
| 87 | + self.error_file = output_dir / "steps_3_token_classes_errors.log" |
| 88 | + self.output_dir.mkdir(parents=True, exist_ok=True) |
| 89 | + |
| 90 | + def write_class_info(self, modules: List[str], classes_info: Dict[str, Any]) -> None: |
| 91 | + with open(self.output_file, "w", encoding="utf-8") as f: |
| 92 | + f.write("# Auto-generated class info: attributes, setters, other methods\n\n") |
| 93 | + for mod in modules: |
| 94 | + f.write(f"from hiero_sdk_python.tokens import {mod}\n") |
| 95 | + f.write("\n") |
| 96 | + |
| 97 | + for full_cls_name, info in sorted(classes_info.items()): |
| 98 | + file_name = full_cls_name.split(".")[0] + ".py" |
| 99 | + f.write(f"# File: {file_name}\n") |
| 100 | + f.write(f"{full_cls_name} = {{\n") |
| 101 | + f.write(" 'attributes': [\n") |
| 102 | + for attr in info['attributes']: |
| 103 | + f.write(f" '{attr}',\n") |
| 104 | + f.write(" ],\n") |
| 105 | + f.write(" 'setters': [\n") |
| 106 | + for setter in info['setters']: |
| 107 | + f.write(f" '{setter}',\n") |
| 108 | + f.write(" ],\n") |
| 109 | + f.write(" 'other_methods': [\n") |
| 110 | + for method in info['other_methods']: |
| 111 | + f.write(f" '{method}',\n") |
| 112 | + f.write(" ]\n") |
| 113 | + f.write("}\n\n") |
| 114 | + |
| 115 | + def write_error_log(self, errors: List[str]) -> None: |
| 116 | + with open(self.error_file, "w", encoding="utf-8") as f: |
| 117 | + if errors: |
| 118 | + f.write("# Errors encountered during parsing\n\n") |
| 119 | + for err in errors: |
| 120 | + f.write(err + "\n") |
| 121 | + else: |
| 122 | + f.write("# No errors encountered\n") |
| 123 | + |
| 124 | + def export(self, modules, classes_info, errors): |
| 125 | + self.write_class_info(modules, classes_info) |
| 126 | + self.write_error_log(errors) |
| 127 | + print(f"✅ Class info written to: {self.output_file}") |
| 128 | + print(f"🪶 Errors (if any) written to: {self.error_file}") |
| 129 | + |
| 130 | + |
| 131 | +class TokenClassExtractor: |
| 132 | + """Controller that ties everything together.""" |
| 133 | + |
| 134 | + def __init__(self, project_root: Path): |
| 135 | + self.tokens_dir = project_root / "src" / "hiero_sdk_python" / "tokens" |
| 136 | + self.output_dir = project_root / "scripts" / "src_vs_proto" |
| 137 | + |
| 138 | + def run(self): |
| 139 | + parser = TokenClassParser(self.tokens_dir) |
| 140 | + exporter = TokenClassExporter(self.output_dir) |
| 141 | + |
| 142 | + print(f"🔍 Scanning token modules in {self.tokens_dir}...") |
| 143 | + result = parser.parse_all() |
| 144 | + |
| 145 | + exporter.export(result["modules"], result["classes"], result["errors"]) |
| 146 | + print("✅ Done.") |
| 147 | + |
| 148 | + |
| 149 | +if __name__ == "__main__": |
| 150 | + project_root = Path(__file__).resolve().parent.parent.parent |
| 151 | + TokenClassExtractor(project_root).run() |
0 commit comments