mirror of
https://github.com/kuhyx/utils.git
synced 2026-11-13 05:50:58 +01:00
Krzysztof kuhy Rudnicki
9102c4b6ff
Decodes an RTDB dump and lists plaintext leaves; the E2E done check. A grep for "title" misses escaped blobs. Todo: fda71ed1 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
64 lines
2.0 KiB
Python
64 lines
2.0 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki
|
|
"""Read-only E2E done check: list plaintext leaves in an RTDB JSON dump.
|
|
|
|
Feed it ``firebase database:get /<root>`` on stdin::
|
|
|
|
firebase database:get /todo-sync | python3 -m tool.e2e_audit todo-sync
|
|
|
|
Exit 0 when every leaf is sealed (or is the clear Argon2id header or a keyed
|
|
revision), 1 when any leaf is plaintext. A plain ``grep '"title"'`` misses
|
|
plaintext because RTDB serves each blob as an escaped JSON string; this
|
|
decodes the tree instead.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import re
|
|
import sys
|
|
|
|
from crdt_sync import is_e2e_envelope
|
|
|
|
_HEX64 = re.compile(r"[0-9a-f]{64}")
|
|
|
|
|
|
def _decode_key(key: str) -> str:
|
|
return re.sub(r"~([0-9A-F]{2})", lambda m: chr(int(m.group(1), 16)), key)
|
|
|
|
|
|
def _is_clear_leaf(value: str) -> bool:
|
|
# Envelopes and the Argon2id header both carry an integer "v"; keyed
|
|
# revisions are 64 hex chars; a bare E2eCipher blob is base64, not JSON.
|
|
if is_e2e_envelope(value) or _HEX64.fullmatch(value):
|
|
return True
|
|
return not value.lstrip().startswith(("{", "["))
|
|
|
|
|
|
def plaintext_paths(tree: object, prefix: str = "") -> list[str]:
|
|
"""Return the decoded paths of every plaintext leaf under ``tree``."""
|
|
found: list[str] = []
|
|
if isinstance(tree, dict):
|
|
for key, value in tree.items():
|
|
path = f"{prefix}/{_decode_key(key)}" if prefix else _decode_key(key)
|
|
found.extend(plaintext_paths(value, path))
|
|
elif isinstance(tree, str):
|
|
if not _is_clear_leaf(tree):
|
|
found.append(prefix)
|
|
elif tree is not None:
|
|
found.append(prefix)
|
|
return found
|
|
|
|
|
|
def main(argv: list[str]) -> int:
|
|
"""Audit the dump on stdin; ``argv[0]`` names the root for the report."""
|
|
root = argv[0] if argv else ""
|
|
paths = plaintext_paths(json.load(sys.stdin), root)
|
|
sys.stdout.write(f"plaintext leaves under /{root}: {len(paths)}\n")
|
|
for path in paths:
|
|
sys.stdout.write(f" {path}\n")
|
|
return 1 if paths else 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main(sys.argv[1:]))
|