ndrluis commented on code in PR #1285: URL: https://github.com/apache/iceberg-python/pull/1285#discussion_r1828199465
########## tests/conftest.py: ########## @@ -918,6 +918,87 @@ def generate_snapshot( "refs": {"test": {"snapshot-id": 3051729675574597004, "type": "tag", "max-ref-age-ms": 10000000}}, } +TABLE_METADATA_V2_WITH_STATISTICS = { + "format-version": 2, + "table-uuid": "9c12d441-03fe-4693-9a96-a0705ddf69c1", + "location": "s3://bucket/test/location", + "last-sequence-number": 34, + "last-updated-ms": 1602638573590, + "last-column-id": 3, + "current-schema-id": 0, + "schemas": [ + { + "type": "struct", + "schema-id": 0, + "fields": [ + { + "id": 1, + "name": "x", + "required": True, + "type": "long", + } + ], + } + ], + "default-spec-id": 0, + "partition-specs": [{"spec-id": 0, "fields": []}], + "last-partition-id": 1000, + "default-sort-order-id": 0, + "sort-orders": [{"order-id": 0, "fields": []}], + "properties": {}, + "current-snapshot-id": 3055729675574597004, + "snapshots": [ + { + "snapshot-id": 3051729675574597004, + "timestamp-ms": 1515100955770, + "sequence-number": 0, + "summary": {"operation": "append"}, + "manifest-list": "s3://a/b/1.avro", + }, + { + "snapshot-id": 3055729675574597004, + "parent-snapshot-id": 3051729675574597004, + "timestamp-ms": 1555100955770, + "sequence-number": 1, + "summary": {"operation": "append"}, + "manifest-list": "s3://a/b/2.avro", + "schema-id": 1, + }, + ], + "statistics": [ + { + "snapshot-id": 3051729675574597004, + "statistics-path": "s3://a/b/stats.puffin", + "file-size-in-bytes": 413, + "file-footer-size-in-bytes": 42, + "blob-metadata": [ + { + "type": "ndv", + "snapshot-id": 3051729675574597004, + "sequence-number": 1, + "fields": [1], + } + ], + }, + { + "snapshot-id": 3055729675574597004, + "statistics-path": "s3://a/b/stats.puffin", Review Comment: No, there is no validation in place. This is only used for clients that support puffin files and for the expire snapshot procedure, which removes this information from the metadata. If the user wants, they can also remove the file as part of the expire snapshot procedure. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org