Skip to content
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

Added AzureBlobFileSystem support for StructuredDatasets #1109

Merged
merged 2 commits into from
Jul 25, 2022
Merged

Added AzureBlobFileSystem support for StructuredDatasets #1109

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
82da680
Added AzureBlobFileSystem support for StructuredDatasets
Jul 21, 2022
f5bdbb3
Added adlfs to extras_require of flytekit-data-fsspec
Jul 22, 2022
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: 2 additions & 1 deletion flytekit/types/structured/basic_dfs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@
from flytekit.models.literals import StructuredDatasetMetadata
from flytekit.models.types import StructuredDatasetType
from flytekit.types.structured.structured_dataset import (
ABFS,
GCS,
LOCAL,
PARQUET,
Expand Down Expand Up @@ -106,7 +107,7 @@ def decode(


# Don't override default protocol
for protocol in [LOCAL, S3, GCS]:
for protocol in [LOCAL, S3, GCS, ABFS]:
StructuredDatasetTransformerEngine.register(PandasToParquetEncodingHandler(protocol), default_for_type=False)
StructuredDatasetTransformerEngine.register(ParquetToPandasDecodingHandler(protocol), default_for_type=False)
StructuredDatasetTransformerEngine.register(ArrowToParquetEncodingHandler(protocol), default_for_type=False)
Expand Down
1 change: 1 addition & 0 deletions flytekit/types/structured/structured_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@
# Protocols
BIGQUERY = "bq"
S3 = "s3"
ABFS = "abfs"
GCS = "gs"
LOCAL = "/"
Comment on lines 40 to 44
Copy link
Collaborator

Choose a reason for hiding this comment

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

Is it time to turn this into an enum, @wild-endeavor ?


Expand Down
5 changes: 4 additions & 1 deletion plugins/flytekit-data-fsspec/flytekitplugins/fsspec/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@

from flytekit import StructuredDatasetTransformerEngine, logger
from flytekit.configuration import internal
from flytekit.types.structured.structured_dataset import GCS, S3
from flytekit.types.structured.structured_dataset import ABFS, GCS, S3

from .arrow import ArrowToParquetEncodingHandler, ParquetToArrowDecodingHandler
from .pandas import PandasToParquetEncodingHandler, ParquetToPandasDecodingHandler
Expand All @@ -41,6 +41,9 @@ def _register(protocol: str):
StructuredDatasetTransformerEngine.register(ParquetToArrowDecodingHandler(protocol), True, True)


if importlib.util.find_spec("adlfs"):
_register(ABFS)

if importlib.util.find_spec("s3fs"):
_register(S3)

Expand Down
1 change: 1 addition & 0 deletions plugins/flytekit-data-fsspec/setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
install_requires=plugin_requires,
extras_require={
# https://github.com/fsspec/filesystem_spec/blob/master/setup.py#L36
"abfs": ["adlfs>=2022.2.0"],
"aws": ["s3fs>=2021.7.0"],
"gcp": ["gcsfs>=2021.7.0"],
},
Expand Down
3 changes: 2 additions & 1 deletion plugins/flytekit-polars/flytekitplugins/polars/sd_transformers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@
from flytekit.models.literals import StructuredDatasetMetadata
from flytekit.models.types import StructuredDatasetType
from flytekit.types.structured.structured_dataset import (
ABFS,
GCS,
LOCAL,
PARQUET,
Expand Down Expand Up @@ -62,7 +63,7 @@ def decode(
return pl.read_parquet(path)


for protocol in [LOCAL, S3, GCS]:
for protocol in [LOCAL, S3, GCS, ABFS]:
StructuredDatasetTransformerEngine.register(
PolarsDataFrameToParquetEncodingHandler(protocol), default_for_type=False
)
Expand Down
6 changes: 5 additions & 1 deletion plugins/flytekit-spark/flytekitplugins/spark/sd_transformers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,11 @@
from flytekit.models.literals import StructuredDatasetMetadata
from flytekit.models.types import StructuredDatasetType
from flytekit.types.structured.structured_dataset import (
ABFS,
GCS,
LOCAL,
PARQUET,
S3,
StructuredDataset,
StructuredDatasetDecoder,
StructuredDatasetEncoder,
Expand Down Expand Up @@ -48,6 +52,6 @@ def decode(
return user_ctx.spark_session.read.parquet(flyte_value.uri)


for protocol in ["/", "s3"]:
for protocol in [LOCAL, S3, GCS, ABFS]:
StructuredDatasetTransformerEngine.register(SparkToParquetEncodingHandler(protocol), default_for_type=False)
StructuredDatasetTransformerEngine.register(ParquetToSparkDecodingHandler(protocol), default_for_type=False)