-
-
Save jubnzv/10649e33865430d88de8eaa91fa50e9e to your computer and use it in GitHub Desktop.
Script to rename identifiers in Solidity corpus: https://nowarp.io/blog/compiler-testing-part-1
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env python3 | |
| import sys | |
| from pathlib import Path | |
| from tree_sitter import Language, Parser | |
| import tree_sitter_solidity | |
| SOL = Language(tree_sitter_solidity.language()) | |
| def rename(src: bytes) -> bytes: | |
| parser = Parser(SOL) | |
| tree = parser.parse(src) | |
| spots = [] | |
| def walk(node): | |
| if node.type == "identifier": | |
| spots.append((node.start_byte, node.end_byte)) | |
| for c in node.children: | |
| walk(c) | |
| walk(tree.root_node) | |
| mapping = {} | |
| for s, e in spots: | |
| name = bytes(src[s:e]) | |
| if name not in mapping: | |
| mapping[name] = f"v{len(mapping)}".encode() | |
| out = bytearray(src) | |
| for s, e in sorted(spots, key=lambda x: x[0], reverse=True): | |
| out[s:e] = mapping[bytes(src[s:e])] | |
| return bytes(out) | |
| def main(): | |
| src_dir, dst_dir = Path(sys.argv[1]), Path(sys.argv[2]) | |
| dst_dir.mkdir(parents=True, exist_ok=True) | |
| for p in sorted(src_dir.iterdir()): | |
| if not p.is_file(): | |
| continue | |
| data = p.read_bytes() | |
| try: | |
| (dst_dir / p.name).write_bytes(rename(data)) | |
| except Exception as ex: | |
| print(f"skip {p.name}: {ex}", file=sys.stderr) | |
| if __name__ == "__main__": | |
| main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment