AccessPath / tools /sanitize_output_metadata.py
anonymous-accesspath's picture
Audited anonymous-review AccessPath release
2f382c4 verified
Raw
History Blame Contribute Delete
2.53 kB
#!/usr/bin/env python3
"""Remove workstation identity and absolute prefixes from text metadata."""
from __future__ import annotations
import argparse
import os
import sys
import tempfile
from pathlib import Path
PROJECT_ROOT = Path(__file__).resolve().parents[1]
if str(PROJECT_ROOT) not in sys.path:
sys.path.insert(0, str(PROJECT_ROOT))
from accesspath3r.privacy import sanitize_text # noqa: E402
TEXT_SUFFIXES = {".err", ".json", ".jsonl", ".log", ".md", ".out", ".txt"}
def sanitize_file(
path: Path,
*,
project_root: Path,
output_root: Path,
sensitive_paths: list[str],
) -> bool:
try:
original = path.read_text(encoding="utf-8")
except (OSError, UnicodeDecodeError):
return False
sanitized = sanitize_text(
original,
project_root=project_root,
output_root=output_root,
sensitive_paths=sensitive_paths,
)
if sanitized == original:
return False
original_mode = path.stat().st_mode & 0o7777
file_descriptor, temporary_name = tempfile.mkstemp(
prefix=f".{path.name}.",
suffix=".tmp",
dir=path.parent,
)
try:
os.fchmod(file_descriptor, original_mode)
with os.fdopen(file_descriptor, "w", encoding="utf-8") as handle:
handle.write(sanitized)
handle.flush()
os.fsync(handle.fileno())
os.replace(temporary_name, path)
except BaseException:
try:
os.unlink(temporary_name)
except OSError:
pass
raise
return True
def build_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser()
parser.add_argument("--root", type=Path, required=True)
parser.add_argument("--project-root", type=Path, required=True)
parser.add_argument("--sensitive-path", action="append", default=[])
return parser
def main() -> int:
args = build_parser().parse_args()
if args.root.is_file():
paths = [args.root]
output_root = args.root.parent
elif args.root.is_dir():
paths = args.root.rglob("*")
output_root = args.root
else:
return 0
for path in paths:
if path.is_file() and path.suffix.lower() in TEXT_SUFFIXES:
sanitize_file(
path,
project_root=args.project_root,
output_root=output_root,
sensitive_paths=args.sensitive_path,
)
return 0
if __name__ == "__main__":
raise SystemExit(main())