Skip to content

Writing v3 Table Metadata #3551

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
rambleraptor wants to merge 1 commit into
base: main
Choose a base branch
from
+11 −11
Open

Writing v3 Table Metadata #3551

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
3 changes: 0 additions & 3 deletions pyiceberg/table/metadata.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -574,9 +574,6 @@ def construct_refs(self) -> TableMetadata:
next_row_id: int | None = Field(alias="next-row-id", default=None)
"""A long higher than all assigned row IDs; the next snapshot's `first-row-id`."""

def model_dump_json(self, exclude_none: bool = True, exclude: Any | None = None, by_alias: bool = True, **kwargs: Any) -> str:

@abnobdoss abnobdoss Jun 23, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is row lineage fully wired up? If I'm not mistaken, row lineage would be a pre-requisite for v3 enablement?

raise NotImplementedError("Writing V3 is not yet supported, see: https://github.com/apache/iceberg-python/issues/1551")


TableMetadata = Annotated[TableMetadataV1 | TableMetadataV2 | TableMetadataV3, Field(discriminator="format_version")]

Expand Down
8 changes: 4 additions & 4 deletions tests/integration/test_writes/test_writes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2373,10 +2373,10 @@ def test_nanosecond_support_on_catalog(

_create_table(session_catalog, identifier, {"format-version": "3"}, schema=arrow_table_schema_with_all_timestamp_precisions)

with pytest.raises(NotImplementedError, match="Writing V3 is not yet supported"):
catalog.create_table(
"ns.table1", schema=arrow_table_schema_with_all_timestamp_precisions, properties={"format-version": "3"}
)
table_v3 = catalog.create_table(
"ns.table1", schema=arrow_table_schema_with_all_timestamp_precisions, properties={"format-version": "3"}
)
assert table_v3.metadata.format_version == 3

with pytest.raises(
UnsupportedPyArrowTypeException, match=re.escape("Column 'timestamp_ns' has an unsupported type: timestamp[ns]")
Expand Down
11 changes: 7 additions & 4 deletions tests/table/test_metadata.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -184,12 +184,15 @@ def test_serialize_v2(example_table_metadata_v2: dict[str, Any]) -> None:


def test_serialize_v3(example_table_metadata_v3: dict[str, Any]) -> None:
# Writing will be part of https://github.com/apache/iceberg-python/issues/1551
table_metadata = TableMetadataV3(**example_table_metadata_v3).model_dump_json()
expected = """{"location":"s3://bucket/test/location","table-uuid":"9c12d441-03fe-4693-9a96-a0705ddf69c1","last-updated-ms":1602638573590,"last-column-id":3,"schemas":[{"type":"struct","fields":[{"id":1,"name":"x","type":"long","required":true}],"schema-id":0,"identifier-field-ids":[]},{"type":"struct","fields":[{"id":1,"name":"x","type":"long","required":true},{"id":2,"name":"y","type":"long","required":true,"doc":"comment"},{"id":3,"name":"z","type":"long","required":true},{"id":4,"name":"u","type":"unknown","required":true},{"id":5,"name":"ns","type":"timestamp_ns","required":true},{"id":6,"name":"nstz","type":"timestamptz_ns","required":true}],"schema-id":1,"identifier-field-ids":[1,2]}],"current-schema-id":1,"partition-specs":[{"spec-id":0,"fields":[{"source-id":1,"field-id":1000,"transform":"identity","name":"x"}]}],"default-spec-id":0,"last-partition-id":1000,"properties":{"read.split.target.size":"134217728"},"current-snapshot-id":3055729675574597004,"snapshots":[{"snapshot-id":3051729675574597004,"sequence-number":0,"timestamp-ms":1515100955770,"manifest-list":"s3://a/b/1.avro","summary":{"operation":"append"}},{"snapshot-id":3055729675574597004,"parent-snapshot-id":3051729675574597004,"sequence-number":1,"timestamp-ms":1555100955770,"manifest-list":"s3://a/b/2.avro","summary":{"operation":"append"},"schema-id":1}],"snapshot-log":[{"snapshot-id":3051729675574597004,"timestamp-ms":1515100955770},{"snapshot-id":3055729675574597004,"timestamp-ms":1555100955770}],"metadata-log":[{"metadata-file":"s3://bucket/.../v1.json","timestamp-ms":1515100}],"sort-orders":[{"order-id":3,"fields":[{"source-id":2,"transform":"identity","direction":"asc","null-order":"nulls-first"},{"source-id":3,"transform":"bucket[4]","direction":"desc","null-order":"nulls-last"}]}],"default-sort-order-id":3,"refs":{"test":{"snapshot-id":3051729675574597004,"type":"tag","max-ref-age-ms":10000000},"main":{"snapshot-id":3055729675574597004,"type":"branch"}},"statistics":[],"partition-statistics":[],"format-version":3,"last-sequence-number":34,"next-row-id":1}"""
assert table_metadata == expected

with pytest.raises(NotImplementedError) as exc_info:
_ = TableMetadataV3(**example_table_metadata_v3).model_dump_json()

assert "Writing V3 is not yet supported, see: https://github.com/apache/iceberg-python/issues/1551" in str(exc_info.value)
def test_serialize_v3_round_trip(example_table_metadata_v3: dict[str, Any]) -> None:
table_metadata = TableMetadataV3(**example_table_metadata_v3)
reparsed = TableMetadataV3(**json.loads(table_metadata.model_dump_json()))
assert table_metadata == reparsed


def test_migrate_v1_schemas(example_table_metadata_v1: dict[str, Any]) -> None:
Expand Down