questsul opened a new issue, #1106:
URL: https://github.com/apache/iceberg-python/issues/1106
### Apache Iceberg version
0.6.0
### Please describe the bug 🐞
When attempting to read the metadata.json file, which contains a list of
snapshots where some snapshot summaries lack the `operation` field, PyIceberg
encounters the following error:
TypeError: Summary.__init__() missing 1 required positional argument:
'operation'.
Interestingly, when parsing the same metadata file using the Iceberg Java
library, it works without any issues.
Full stack trace:
```
File "reader.py", line 91, in _get_iceberg_table
return StaticTable.from_metadata(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".venv/lib/python3.12/site-packages/pyiceberg/table/__init__.py",
line 1101, in from_metadata
metadata = FromInputFile.table_metadata(file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".venv/lib/python3.12/site-packages/pyiceberg/serializers.py", line
113, in table_metadata
return FromByteStream.table_metadata(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".venv/lib/python3.12/site-packages/pyiceberg/serializers.py", line
94, in table_metadata
return TableMetadataUtil.parse_raw(metadata)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".venv/lib/python3.12/site-packages/pyiceberg/table/metadata.py",
line 461, in parse_raw
return TableMetadataWrapper.model_validate_json(data).root
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".venv/lib/python3.12/site-packages/pydantic/main.py", line 580, in
model_validate_json
return cls.__pydantic_validator__.validate_json(json_data,
strict=strict, context=context)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: Summary.__init__() missing 1 required positional argument:
'operation'
```
Metadata.json example:
```json
{
"format-version" : 2,
"table-uuid" : "9996bcdf-3277-48f4-9e76-9e81766c9e0e",
"location" : "file://t/some_table/",
"last-sequence-number" : 45,
"last-updated-ms" : 1724611070351,
"last-column-id" : 79,
"current-schema-id" : 0,
"schemas" : [ {
"type" : "struct",
"schema-id" : 0,
"fields" : [ {
"id" : 1,
"name" : "DATA",
"required" : false,
"type" : "string"
}, {
"id" : 2,
"name" : "COLUMN_NAME",
"required" : false,
"type" : "string"
}]
} ],
"default-spec-id" : 0,
"partition-specs" : [ {
"spec-id" : 0,
"fields" : [ ]
} ],
"last-partition-id" : 999,
"default-sort-order-id" : 0,
"sort-orders" : [ {
"order-id" : 0,
"fields" : [ ]
} ],
"properties" : {
"format-version" : "2"
},
"current-snapshot-id" : 1724611070351000000,
"snapshots" : [ {
"sequence-number" : 44,
"snapshot-id" : 1724610129117000000,
"timestamp-ms" : 1724610129117,
"manifest-list" :
"file://t/some_table/metadata/snap-1724610129117000000-d9b50309-0dff-472d-8711-86ca70021ffb.avro",
"schema-id" : 0,
"summary" : {
"manifests-created" : "8",
"total-records" : "26508666891",
"added-files-size" : "3927895626752",
"manifests-kept" : "0",
"total-files-size" : "3927895626752",
"added-records" : "26508666891",
"added-data-files" : "231513",
"manifests-replaced" : "0",
"total-data-files" : "231513"
}
}, {
"sequence-number" : 43,
"snapshot-id" : 1724006578422000000,
"timestamp-ms" : 1724006578422,
"manifest-list" :
"file://t/some_table/metadata/snap-1724006578422000000-289566b5-78fe-4b60-9ffa-ab25dee1edde.avro",
"schema-id" : 0,
"summary" : {
"total-files-size" : "3888310341632",
"added-records" : "26224534820",
"added-data-files" : "225313",
"manifests-replaced" : "0",
"total-data-files" : "225313",
"manifests-created" : "56",
"total-records" : "26224534820",
"added-files-size" : "3888310341632",
"manifests-kept" : "0"
}
}, {
"sequence-number" : 45,
"snapshot-id" : 1724611070351000000,
"timestamp-ms" : 1724611070351,
"manifest-list" :
"file://t/some_table/metadata/snap-1724611070351000000-6a307203-7148-467f-88eb-f932b32dd7f4.avro",
"schema-id" : 0,
"summary" : {
"added-files-size" : "3929709293568",
"total-records" : "26508666891",
"manifests-created" : "8",
"total-data-files" : "227581",
"manifests-replaced" : "0",
"added-data-files" : "227581",
"added-records" : "26508666891",
"total-files-size" : "3929709293568",
"operation" : "append",
"manifests-kept" : "0"
}
} ],
"snapshot-log" : [ {
"snapshot-id" : 1724006578422000000,
"timestamp-ms" : 1724006578422
}, {
"snapshot-id" : 1724610129117000000,
"timestamp-ms" : 1724610129117
}, {
"snapshot-id" : 1724611070351000000,
"timestamp-ms" : 1724611070351
} ]
}
```
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
