Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion java/pom.xml
Original file line number Diff line number Diff line change
Expand Up @@ -61,7 +61,7 @@
<swagger.core.version>1.5.24</swagger.core.version>
<okhttp.version>3.14.7</okhttp.version>
<commons.lang3.version>3.10</commons.lang3.version>
<jackson.version>2.12.6</jackson.version>
<jackson.version>2.14.0</jackson.version>
<javax.xml.bind.version>2.3.1</javax.xml.bind.version>
<javax.annotation.version>1.3.2</javax.annotation.version>
<javax.validation.version>2.0.1.Final</javax.validation.version>
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,6 @@

import pyarrow as pa
import pyarrow.parquet as pq
import s3fs
from bytewax.dataflow import Dataflow # type: ignore
from bytewax.execution import cluster_main
from bytewax.inputs import ManualInputConfig, distribute
Expand All @@ -29,8 +28,7 @@ def __init__(
self._run_dataflow()

def process_path(self, path):
fs = s3fs.S3FileSystem()
dataset = pq.ParquetDataset(path, filesystem=fs, use_legacy_dataset=False)
dataset = pq.ParquetDataset(path, use_legacy_dataset=False)
batches = []
for fragment in dataset.fragments:
for batch in fragment.to_table().to_batches():
Expand Down
3 changes: 2 additions & 1 deletion setup.py
Original file line number Diff line number Diff line change
Expand Up @@ -91,6 +91,7 @@
"google-cloud-datastore>=2.1.0,<3",
"google-cloud-storage>=1.34.0,<3",
"google-cloud-bigtable>=2.11.0,<3",
"gcsfs",
]

REDIS_REQUIRED = [
Expand Down Expand Up @@ -158,7 +159,7 @@
"moto",
"mypy>=0.981,<0.990",
"avro==1.10.0",
"gcsfs>=0.4.0,<=2022.01.0",
"gcsfs",
"urllib3>=1.25.4,<2",
"psutil==5.9.0",
"py>=1.11.0", # https://github.com/pytest-dev/pytest/issues/10420
Expand Down