def update_partitions(dataset_builder, add_partitions, remove_partitions):
for mp in add_partitions:
for sub_mp_dct in mp.metapartitions:
# label is None in case of an empty partition
if sub_mp_dct["label"] is not None:
partition = Partition(label=sub_mp_dct["label"],
files=sub_mp_dct["files"])
dataset_builder.add_partition(sub_mp_dct["label"], partition)
for partition_name in remove_partitions:
del dataset_builder.partitions[partition_name]
return dataset_builder
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_eq():
assert not (Partition("label") == Partition("other_label"))
assert not (Partition("label") == Partition("label",
files={"some": "file"}))
assert Partition(label="label",
files={"some":
"file"}) == Partition(label="label",
files={"some": "file"})
def test_builder_to_dataset(metadata_version, frozen_time):
expected = {
"dataset_uuid": "uuid",
"dataset_metadata_version": metadata_version,
"partitions": {
"part_2": {
"files": {
"core": "uuid/core/part_2.parquet"
}
}
},
"metadata": {
"key": "value",
"creation_time": TIME_TO_FREEZE_ISO
},
"indices": {
"col1": {
"a": ["part1"],
"b": ["part2"]
}
},
}
builder = DatasetMetadataBuilder("uuid", metadata_version=metadata_version)
part_2 = Partition("part_2", {"core": "uuid/core/part_2.parquet"})
builder.add_partition("part_2", part_2)
builder.add_metadata("key", "value")
builder.add_embedded_index(
"col1", ExplicitSecondaryIndex("col1", {
"a": ["part1"],
"b": ["part2"]
}))
result = builder.to_dataset()
expected_from_dict = DatasetMetadata.from_dict(expected)
assert result == expected_from_dict
def partition(self) -> Partition:
return Partition(label=self.label, files={self.table_name: self.file})