| |
| """Audit the public WiSER release tree before upload.""" |
|
|
| from __future__ import annotations |
|
|
| import argparse |
| import json |
| import re |
| from pathlib import Path |
|
|
|
|
| SECRET_PATTERNS = [ |
| re.compile(r"ghp_[A-Za-z0-9_]+"), |
| re.compile(r"github_pat_[A-Za-z0-9_]+"), |
| re.compile(r"gho_[A-Za-z0-9_]+"), |
| re.compile(r"hf_[A-Za-z0-9_]+"), |
| re.compile(r"(?i)\b(password|secret|api[_-]?key|access[_-]?token|auth[_-]?token)\s*=\s*['\"][^'\"]+['\"]"), |
| ] |
|
|
| RAW_SCANNET_PATTERNS = [ |
| "mesh_aligned_0.05.ply", |
| "mesh_aligned_0.05_semantic.ply", |
| "segments.json", |
| "segments_anno.json", |
| "/iphone/", |
| "/dslr/", |
| "/scans/", |
| ] |
|
|
|
|
| def scan(root: Path) -> dict: |
| findings = {"secrets": [], "raw_scannetpp": [], "absolute_data_paths": []} |
| text_suffixes = {".py", ".md", ".txt", ".yml", ".yaml", ".json", ".sh", ".toml"} |
| for path in root.rglob("*"): |
| if path.is_dir(): |
| continue |
| rel = str(path.relative_to(root)) |
| rel_unix = rel.replace("\\", "/") |
| if rel_unix == "scripts/audit_release.py": |
| continue |
| if "__pycache__/" in rel_unix or rel_unix.endswith(".pyc"): |
| continue |
| if any(p in rel_unix or rel_unix.endswith(p) for p in RAW_SCANNET_PATTERNS): |
| findings["raw_scannetpp"].append(rel) |
| if path.suffix.lower() not in text_suffixes: |
| continue |
| try: |
| text = path.read_text(errors="ignore") |
| except OSError: |
| continue |
| for pat in SECRET_PATTERNS: |
| if pat.search(text): |
| findings["secrets"].append(rel) |
| break |
| if re.search(r"(^|[\"'\\s])/(data|home|mnt)/", text): |
| findings["absolute_data_paths"].append(rel) |
| findings["ok"] = not findings["secrets"] and not findings["raw_scannetpp"] |
| return findings |
|
|
|
|
| def main() -> None: |
| p = argparse.ArgumentParser() |
| p.add_argument("--root", default=".") |
| p.add_argument("--out-json", default=None) |
| args = p.parse_args() |
| root = Path(args.root).resolve() |
| findings = scan(root) |
| text = json.dumps(findings, indent=2) |
| if args.out_json: |
| out = Path(args.out_json) |
| out.parent.mkdir(parents=True, exist_ok=True) |
| out.write_text(text) |
| print(text) |
| raise SystemExit(0 if findings["ok"] else 2) |
|
|
|
|
| if __name__ == "__main__": |
| main() |
|
|
