-
Notifications
You must be signed in to change notification settings - Fork 351
Implement update for remove-snapshots
action
#1561
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
Changes from 3 commits
b6ba319
88064c0
818f771
9b31690
c5cbfe4
29feaf7
9e3f7c7
b9c912d
d515e74
c7481fe
da4db9f
19e17f0
32e1e85
e68dbb9
fb8f350
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -455,6 +455,19 @@ def _(update: SetSnapshotRefUpdate, base_metadata: TableMetadata, context: _Tabl | |
return base_metadata.model_copy(update=metadata_updates) | ||
|
||
|
||
@_apply_table_update.register(RemoveSnapshotsUpdate) | ||
def _(update: RemoveSnapshotsUpdate, base_metadata: TableMetadata, context: _TableMetadataUpdateContext) -> TableMetadata: | ||
for remove_snapshot_id in update.snapshot_ids: | ||
if remove_snapshot_id == base_metadata.current_snapshot_id: | ||
raise ValueError(f"Can't remove current snapshot id {remove_snapshot_id}") | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. should we block the current snapshot? There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I'm not an expert in iceberg spec, but it's not clear what should happen if you try to remove the current snapshot. I'm also not sure if I should update parent_snapshot_id in every snapshot that was referencing removed snapshots There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Decided to set parent_snapshot_id to None if the parent is gone There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more.
im looking at the java implementation for answers, i think you can just remove the current snapshot... because you can have an empty table with no snapshots There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Created a separate pr for |
||
if not any(s.snapshot_id == remove_snapshot_id for s in base_metadata.snapshots): | ||
raise ValueError(f"Snapshot with snapshot id {remove_snapshot_id} does not exist: {base_metadata.snapshots}") | ||
|
||
snapshots = [s for s in base_metadata.snapshots if s.snapshot_id not in update.snapshot_ids] | ||
context.add_update(update) | ||
return base_metadata.model_copy(update={"snapshots": snapshots}) | ||
|
||
|
||
@_apply_table_update.register(AddSortOrderUpdate) | ||
def _(update: AddSortOrderUpdate, base_metadata: TableMetadata, context: _TableMetadataUpdateContext) -> TableMetadata: | ||
context.add_update(update) | ||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -78,6 +78,7 @@ | |
AssertRefSnapshotId, | ||
AssertTableUUID, | ||
RemovePropertiesUpdate, | ||
RemoveSnapshotsUpdate, | ||
RemoveStatisticsUpdate, | ||
SetDefaultSortOrderUpdate, | ||
SetPropertiesUpdate, | ||
|
@@ -793,6 +794,34 @@ def test_update_metadata_set_snapshot_ref(table_v2: Table) -> None: | |
) | ||
|
||
|
||
def test_update_remove_snapshots(table_v2: Table) -> None: | ||
update = RemoveSnapshotsUpdate( | ||
snapshot_ids=[3051729675574597004], | ||
) | ||
new_metadata = update_table_metadata(table_v2.metadata, (update,)) | ||
assert len(new_metadata.snapshots) == 1 | ||
grihabor marked this conversation as resolved.
Show resolved
Hide resolved
|
||
assert new_metadata.snapshots[0].snapshot_id == 3055729675574597004 | ||
assert new_metadata.snapshots[0].parent_snapshot_id == None | ||
assert new_metadata.current_snapshot_id == 3055729675574597004 | ||
assert new_metadata.last_updated_ms > table_v2.metadata.last_updated_ms | ||
|
||
|
||
def test_update_remove_snapshots_doesnt_exist(table_v2: Table) -> None: | ||
update = RemoveSnapshotsUpdate( | ||
snapshot_ids=[123], | ||
) | ||
with pytest.raises(ValueError, match="Snapshot with snapshot id 123 does not exist"): | ||
update_table_metadata(table_v2.metadata, (update,)) | ||
|
||
|
||
def test_update_remove_snapshots_cant_remove_current_snapshot_id(table_v2: Table) -> None: | ||
update = RemoveSnapshotsUpdate( | ||
snapshot_ids=[3055729675574597004], | ||
) | ||
with pytest.raises(ValueError, match="Can't remove current snapshot id 3055729675574597004"): | ||
update_table_metadata(table_v2.metadata, (update,)) | ||
|
||
|
||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. lets also add some tests for There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Created a separate pr for remove-snapshot-ref and added a unit test there #1598 |
||
def test_update_metadata_add_update_sort_order(table_v2: Table) -> None: | ||
new_sort_order = SortOrder(order_id=table_v2.sort_order().order_id + 1) | ||
new_metadata = update_table_metadata( | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this is the java reference
https://github.com/apache/iceberg/blob/be6e9daf8901cdee63197e77fcf95624bb694f39/core/src/main/java/org/apache/iceberg/TableMetadata.java#L1396-L1426