mirror of
https://github.com/kuhyx/utils.git
synced 2026-11-10 21:07:15 +01:00
Krzysztof kuhy Rudnicki
3589d166cd
Some checks are pending
crdt-sync pre-commit / pre-commit (push) Waiting to run
crdt-sync tests / test (3.10) (push) Waiting to run
crdt-sync tests / test (3.11) (push) Waiting to run
crdt-sync tests / test (3.12) (push) Waiting to run
gatelock pre-commit / pre-commit (push) Waiting to run
gatelock tests / test (3.10) (push) Waiting to run
gatelock tests / test (3.11) (push) Waiting to run
gatelock tests / test (3.12) (push) Waiting to run
palette drift / palette (push) Waiting to run
_sync.py 456 -> 245 + _syncstate 131 + _pull 106 + _revisions 34 _firebase_auth 412 -> 242 + _credentials 146 + _autherrors 69 _firebase.py 336 -> 250 + _fbkeys 100 google_id_token 316 -> 232 + tool/_oauth_callback 105 _github.py 255 -> 238 + _gherrors 30 revision_of became its own leaf module because both the push and pull halves need it; without that the two would have imported each other. _fbkeys holds the RTDB key escaping — the escape tables moved with the functions that read them, since the pair has to round-trip exactly or a device silently stops seeing its own writes. crdt-sync/tool/ is outside the coverage source, so the split there has no test net: verified by running it the documented way instead (`python3 -m tool.google_id_token --help` prints its usage, and `from tool.google_id_token import TokenError, fetch_id_token` — what seed_session.py does — still resolves). An AST pass over each pair caught what the suite would not have: _is_revoked needs the error type, so it stayed with it rather than following the credentials; _TERMINAL_AUTH_REASONS and _CONSENT_TIMEOUT_SECONDS had to be carried to their new callers. 259 passed at 100% branch coverage. crdt-sync/tool/seed_session.py and firebase-debug.log are pre-existing local changes and are deliberately not in this commit. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CFSGeWxHPY5rHUGrPqhcmG
101 lines
2.9 KiB
Python
101 lines
2.9 KiB
Python
"""Escaping arbitrary strings into Firebase Realtime Database keys.
|
|
|
|
Split from :mod:`crdt_sync._firebase`, which keeps the client. RTDB forbids
|
|
``.``, ``$``, ``#``, ``[``, ``]`` and ``/`` in a key, but the app stores
|
|
record ids and file paths that contain them, so every key is escaped on the
|
|
way in and unescaped on the way out. The pair has to round-trip exactly or a
|
|
device silently stops seeing its own writes.
|
|
|
|
Re-exported from :mod:`crdt_sync._firebase`, so existing imports keep working.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
# Characters Realtime Database forbids in a key, plus ``~`` itself because it
|
|
# is this module's escape character. ``/`` is absent deliberately: it is the
|
|
# path separator, handled by splitting into segments before escaping.
|
|
_ESCAPES = {
|
|
"~": "~7E",
|
|
".": "~2E",
|
|
"$": "~24",
|
|
"#": "~23",
|
|
"[": "~5B",
|
|
"]": "~5D",
|
|
}
|
|
_UNESCAPES = {escape: char for char, escape in _ESCAPES.items()}
|
|
_ESCAPE_LENGTH = 3
|
|
|
|
|
|
def encode_key(segment: str) -> str:
|
|
"""Escape one path segment into a legal Realtime Database key.
|
|
|
|
RTDB rejects ``. $ # [ ] /`` in keys, and the REST API's trailing
|
|
``.json`` is a *format suffix* rather than part of the path -- so a
|
|
filename like ``log.json`` cannot be stored verbatim. The mapping is a
|
|
reversible ``~XX`` escape (``log.json`` -> ``log~2Ejson``) rather than a
|
|
lossy "strip the extension", because callers see these names again:
|
|
todo-app lists *filenames*, not device directories, and must keep getting
|
|
``<uuid>.json`` back.
|
|
|
|
``~`` is the escape character because it is legal in RTDB keys and
|
|
unreserved in URLs, so the escaped form needs no percent-encoding --
|
|
which the server would otherwise decode back into the illegal character.
|
|
|
|
Parameters
|
|
----------
|
|
segment : str
|
|
One path segment, with no ``/`` in it.
|
|
|
|
Returns:
|
|
-------
|
|
str
|
|
The escaped key.
|
|
|
|
"""
|
|
return "".join(_ESCAPES.get(char, char) for char in segment)
|
|
|
|
|
|
def decode_key(key: str) -> str:
|
|
"""Reverse :func:`encode_key`.
|
|
|
|
Parameters
|
|
----------
|
|
key : str
|
|
An escaped Realtime Database key.
|
|
|
|
Returns:
|
|
-------
|
|
str
|
|
The original segment.
|
|
|
|
"""
|
|
out: list[str] = []
|
|
index = 0
|
|
while index < len(key):
|
|
escape = key[index : index + _ESCAPE_LENGTH]
|
|
char = _UNESCAPES.get(escape)
|
|
if char is None:
|
|
out.append(key[index])
|
|
index += 1
|
|
else:
|
|
out.append(char)
|
|
index += _ESCAPE_LENGTH
|
|
return "".join(out)
|
|
|
|
|
|
def encode_path(path: str) -> str:
|
|
"""Escape every segment of a ``/``-separated logical path.
|
|
|
|
Parameters
|
|
----------
|
|
path : str
|
|
A logical path such as ``"todo-sync/notes/abc.json"``.
|
|
|
|
Returns:
|
|
-------
|
|
str
|
|
The path with each segment escaped, empty segments dropped.
|
|
|
|
"""
|
|
return "/".join(encode_key(part) for part in path.split("/") if part)
|