Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: Safely compare UUID replication keys with state bookmarks #2756

Merged
merged 1 commit into from
Nov 11, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions singer_sdk/helpers/_state.py
Original file line number Diff line number Diff line change
Expand Up @@ -218,6 +218,10 @@ def increment_state(
extra={"replication_key": replication_key},
)
progress_dict = stream_or_partition_state[PROGRESS_MARKERS]
# TODO: Instead of forcing all values to be JSON-compatible strings and hope
# we catch all cases, we should allow the stream to define how to
# the values from the state and the record should be pre-processed.
# https://github.com/meltano/sdk/issues/2753
old_rk_value = to_json_compatible(progress_dict.get("replication_key_value"))
new_rk_value = to_json_compatible(latest_record[replication_key])

Expand Down
3 changes: 3 additions & 0 deletions singer_sdk/helpers/_typing.py
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@
import datetime
import logging
import typing as t
import uuid
from enum import Enum
from functools import lru_cache

Expand Down Expand Up @@ -42,6 +43,8 @@ def to_json_compatible(val: t.Any) -> t.Any: # noqa: ANN401
if isinstance(val, (datetime.datetime,)):
# Make naive datetimes UTC
return (val.replace(tzinfo=UTC) if val.tzinfo is None else val).isoformat("T")
if isinstance(val, (uuid.UUID,)):
return str(val)
return val


Expand Down
19 changes: 19 additions & 0 deletions tests/core/test_state_handling.py
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
from __future__ import annotations

import logging
import uuid

import pytest

Expand Down Expand Up @@ -155,3 +156,21 @@ def test_null_replication_value(caplog):
), "State should not be updated."
assert caplog.records[0].levelname == "WARNING"
assert "is null" in caplog.records[0].message


def test_uuidv7_replication_value():
stream_state = {
"replication_key": "id",
"replication_key_value": "01931c63-b14e-7ff3-8621-e577ed392dc8",
}
new_string_val = "01931c63-b14e-7ff3-8621-e578edbca9a3"

_state.increment_state(
stream_state,
latest_record={"id": uuid.UUID(new_string_val)},
replication_key="id",
is_sorted=True,
check_sorted=True,
)

assert stream_state["replication_key_value"] == new_string_val
Loading