Skip to content

Validate snapshot sequence numbers on v3 tables #4125

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.

Sign up for GitHub

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

Open
porkedchop wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Validate snapshot sequence numbers on v3 tables #4125

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion pyiceberg/table/update/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -435,7 +435,7 @@ def _(update: AddSnapshotUpdate, base_metadata: TableMetadata, context: _TableMe
elif base_metadata.snapshot_by_id(update.snapshot.snapshot_id) is not None:
raise ValueError(f"Snapshot with id {update.snapshot.snapshot_id} already exists")
elif (
base_metadata.format_version == 2
base_metadata.format_version >= 2
and update.snapshot.sequence_number is not None
and update.snapshot.sequence_number <= base_metadata.last_sequence_number
and update.snapshot.parent_snapshot_id is not None
Expand Down
20 changes: 20 additions & 0 deletions tests/table/test_init.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1966,6 +1966,26 @@ def test_add_snapshot_update_fails_with_smaller_first_row_id(table_v3: Table) ->
update_table_metadata(table_v3.metadata, (AddSnapshotUpdate(snapshot=new_snapshot),))


@pytest.mark.parametrize("table", [lf("table_v2"), lf("table_v3")])
def test_add_snapshot_update_fails_with_stale_sequence_number(table: Table) -> None:
new_snapshot = Snapshot(
snapshot_id=25,
parent_snapshot_id=3055729675574597004,
sequence_number=table.metadata.last_sequence_number,
timestamp_ms=1602638593590,
manifest_list="s3:/a/b/c.avro",
summary=Summary(Operation.APPEND),
schema_id=1,
first_row_id=2,
)

with pytest.raises(
ValueError,
match="Cannot add snapshot with sequence number 34 older than last sequence number 34",
):
update_table_metadata(table.metadata, (AddSnapshotUpdate(snapshot=new_snapshot),))


def test_add_snapshot_update_updates_next_row_id(table_v3: Table) -> None:
new_snapshot = Snapshot(
snapshot_id=25,
Expand Down
Loading