def create_empty_dataset_header(
store,
dataset_uuid,
table_meta,
partition_on=None,
metadata=None,
overwrite=False,
metadata_storage_format=DEFAULT_METADATA_STORAGE_FORMAT,
metadata_version=DEFAULT_METADATA_VERSION,
):
"""
Create an dataset header without any partitions. This may be used in combination
with :func:`~kartothek.io.eager.write_single_partition` to create implicitly partitioned datasets.
.. note::
The created dataset will **always** have explicit_partition==False
.. warning::
This function should only be used in very rare occasions. Usually you're better off using
full end-to-end pipelines.
Parameters
----------
"""
store = lazy_store(store)()
if not overwrite:
raise_if_dataset_exists(dataset_uuid=dataset_uuid, store=store)
for table, schema in table_meta.items():
table_meta[table] = make_meta(schema,
origin=table,
partition_keys=partition_on)
store_schema_metadata(
schema=table_meta[table],
dataset_uuid=dataset_uuid,
store=store,
table=table,
)
dataset_builder = DatasetMetadataBuilder(
uuid=dataset_uuid,
metadata_version=metadata_version,
partition_keys=partition_on,
explicit_partitions=False,
table_meta=table_meta,
)
if metadata:
for key, value in metadata.items():
dataset_builder.add_metadata(key, value)
if metadata_storage_format.lower() == "json":
store.put(*dataset_builder.to_json())
elif metadata_storage_format.lower() == "msgpack":
store.put(*dataset_builder.to_msgpack())
else:
raise ValueError(
"Unknown metadata storage format encountered: {}".format(
metadata_storage_format))
return dataset_builder.to_dataset()
def test_builder_full(metadata_version, frozen_time):
expected = {
"dataset_uuid": "uuid",
"dataset_metadata_version": metadata_version,
"partitions": {
"run_id=1/L=1/P=1/part_1": {
"files": {
"core": "uuid/core/run_id=1/L=1/P=1/part_1.parquet",
"helper": "uuid/helper/run_id=1/L=1/P=1/part_1.parquet",
}
}
},
"metadata": {
"key": "value",
"creation_time": TIME_TO_FREEZE_ISO
},
"indices": {
"col1": {
"a": ["run_id=1/L=1/P=1/part_1"],
"b": ["run_id=2/L=1/P=1/part_1"],
},
"col2": "uuid.col2.by-dataset-index.parquet",
},
"partition_keys": ["L", "P"],
}
builder = DatasetMetadataBuilder("uuid",
metadata_version=metadata_version,
partition_keys=["L", "P"])
part_2 = Partition(
label="run_id=1/L=1/P=1/part_1",
files={
"core": "uuid/core/run_id=1/L=1/P=1/part_1.parquet",
"helper": "uuid/helper/run_id=1/L=1/P=1/part_1.parquet",
},
)
builder.add_partition("run_id=1/L=1/P=1/part_1", part_2)
builder.add_metadata("key", "value")
builder.add_external_index("col2")
builder.add_embedded_index(
"col1",
ExplicitSecondaryIndex("col1", {
"a": ["run_id=1/L=1/P=1/part_1"],
"b": ["run_id=2/L=1/P=1/part_1"]
}),
)
key, result = builder.to_json()
result = simplejson.loads(result)
assert key == "uuid.by-dataset-metadata.json"
assert result == expected
def test_builder_empty_partition_keys(store, metadata_version, frozen_time):
expected = {
"dataset_uuid": "uuid",
"dataset_metadata_version": metadata_version,
"metadata": {
"creation_time": TIME_TO_FREEZE_ISO
},
"partition_keys": ["L", "P"],
"partitions": {},
}
builder = DatasetMetadataBuilder("uuid",
metadata_version=4,
partition_keys=["L", "P"])
key, result = builder.to_json()
result = simplejson.loads(result)
assert key == "uuid.by-dataset-metadata.json"
assert result == expected
result_from_dict = DatasetMetadata.load_from_dict(result, store).to_dict()
assert result_from_dict == expected
def store_dataset_from_partitions(
partition_list,
store,
dataset_uuid,
dataset_metadata=None,
metadata_merger=None,
update_dataset=None,
remove_partitions=None,
metadata_storage_format=naming.DEFAULT_METADATA_STORAGE_FORMAT,
):
store = _instantiate_store(store)
if update_dataset:
dataset_builder = DatasetMetadataBuilder.from_dataset(update_dataset)
metadata_version = dataset_builder.metadata_version
else:
mp = next(iter(partition_list), None)
if mp is None:
raise ValueError(
"Cannot store empty datasets, partition_list must not be empty if in store mode."
)
metadata_version = mp.metadata_version
dataset_builder = DatasetMetadataBuilder(
uuid=dataset_uuid,
metadata_version=metadata_version,
partition_keys=mp.partition_keys,
)
dataset_builder.explicit_partitions = True
dataset_builder.table_meta = persist_common_metadata(
partition_list, update_dataset, store, dataset_uuid)
# We can only check for non unique partition labels here and if they occur we will
# fail hard. The resulting dataset may be corrupted or file may be left in the store
# without dataset metadata
partition_labels = partition_labels_from_mps(partition_list)
non_unique_labels = extract_duplicates(partition_labels)
if non_unique_labels:
raise ValueError(
"The labels {} are duplicated. Dataset metadata was not written.".
format(", ".join(non_unique_labels)))
if remove_partitions is None:
remove_partitions = []
if metadata_merger is None:
metadata_merger = combine_metadata
dataset_builder = update_metadata(dataset_builder, metadata_merger,
partition_list, dataset_metadata)
dataset_builder = update_partitions(dataset_builder, partition_list,
remove_partitions)
dataset_builder = update_indices(dataset_builder, store, partition_list,
remove_partitions)
if metadata_storage_format.lower() == "json":
store.put(*dataset_builder.to_json())
elif metadata_storage_format.lower() == "msgpack":
store.put(*dataset_builder.to_msgpack())
else:
raise ValueError(
"Unknown metadata storage format encountered: {}".format(
metadata_storage_format))
dataset = dataset_builder.to_dataset()
return dataset
def store_dataset_from_partitions(
partition_list,
store: StoreInput,
dataset_uuid,
dataset_metadata=None,
metadata_merger=None,
update_dataset=None,
remove_partitions=None,
metadata_storage_format=naming.DEFAULT_METADATA_STORAGE_FORMAT,
):
store = ensure_store(store)
schemas = set()
if update_dataset:
dataset_builder = DatasetMetadataBuilder.from_dataset(update_dataset)
metadata_version = dataset_builder.metadata_version
table_name = update_dataset.table_name
schemas.add(update_dataset.schema)
else:
mp = next(iter(partition_list), None)
if mp is None:
raise ValueError(
"Cannot store empty datasets, partition_list must not be empty if in store mode."
)
table_name = mp.table_name
metadata_version = mp.metadata_version
dataset_builder = DatasetMetadataBuilder(
uuid=dataset_uuid,
metadata_version=metadata_version,
partition_keys=mp.partition_keys,
)
for mp in partition_list:
if mp.schema:
schemas.add(mp.schema)
dataset_builder.schema = persist_common_metadata(
schemas=schemas,
update_dataset=update_dataset,
store=store,
dataset_uuid=dataset_uuid,
table_name=table_name,
)
# We can only check for non unique partition labels here and if they occur we will
# fail hard. The resulting dataset may be corrupted or file may be left in the store
# without dataset metadata
partition_labels = partition_labels_from_mps(partition_list)
# This could be safely removed since we do not allow to set this by the user
# anymore. It has implications on tests if mocks are used
non_unique_labels = extract_duplicates(partition_labels)
if non_unique_labels:
raise ValueError(
"The labels {} are duplicated. Dataset metadata was not written.".
format(", ".join(non_unique_labels)))
if remove_partitions is None:
remove_partitions = []
if metadata_merger is None:
metadata_merger = combine_metadata
dataset_builder = update_metadata(dataset_builder, metadata_merger,
dataset_metadata)
dataset_builder = update_partitions(dataset_builder, partition_list,
remove_partitions)
dataset_builder = update_indices(dataset_builder, store, partition_list,
remove_partitions)
if metadata_storage_format.lower() == "json":
store.put(*dataset_builder.to_json())
elif metadata_storage_format.lower() == "msgpack":
store.put(*dataset_builder.to_msgpack())
else:
raise ValueError(
"Unknown metadata storage format encountered: {}".format(
metadata_storage_format))
dataset = dataset_builder.to_dataset()
return dataset