dagster-duckdb-pyspark 0.18.1__tar.gz → 0.18.3__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of dagster-duckdb-pyspark might be problematic. Click here for more details.
- {dagster-duckdb-pyspark-0.18.1/dagster_duckdb_pyspark.egg-info → dagster-duckdb-pyspark-0.18.3}/PKG-INFO +1 -5
- {dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/dagster_duckdb_pyspark/duckdb_pyspark_type_handler.py +5 -1
- dagster-duckdb-pyspark-0.18.3/dagster_duckdb_pyspark/version.py +1 -0
- {dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3/dagster_duckdb_pyspark.egg-info}/PKG-INFO +1 -5
- {dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/dagster_duckdb_pyspark.egg-info/requires.txt +2 -2
- {dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/setup.py +3 -3
- dagster-duckdb-pyspark-0.18.1/dagster_duckdb_pyspark/version.py +0 -1
- {dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/LICENSE +0 -0
- {dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/MANIFEST.in +0 -0
- {dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/README.md +0 -0
- {dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/dagster_duckdb_pyspark/__init__.py +0 -0
- {dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/dagster_duckdb_pyspark/py.typed +0 -0
- {dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/dagster_duckdb_pyspark.egg-info/SOURCES.txt +0 -0
- {dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/dagster_duckdb_pyspark.egg-info/dependency_links.txt +0 -0
- {dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/dagster_duckdb_pyspark.egg-info/not-zip-safe +0 -0
- {dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/dagster_duckdb_pyspark.egg-info/top_level.txt +0 -0
- {dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/setup.cfg +0 -0
|
@@ -1,12 +1,11 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: dagster-duckdb-pyspark
|
|
3
|
-
Version: 0.18.
|
|
3
|
+
Version: 0.18.3
|
|
4
4
|
Summary: Package for storing PySpark DataFrames in DuckDB.
|
|
5
5
|
Home-page: https://github.com/dagster-io/dagster/tree/master/python_modules/libraries/dagster-duckb-pyspark
|
|
6
6
|
Author: Elementl
|
|
7
7
|
Author-email: hello@elementl.com
|
|
8
8
|
License: Apache-2.0
|
|
9
|
-
Platform: UNKNOWN
|
|
10
9
|
Classifier: Programming Language :: Python :: 3.7
|
|
11
10
|
Classifier: Programming Language :: Python :: 3.8
|
|
12
11
|
Classifier: Programming Language :: Python :: 3.9
|
|
@@ -14,6 +13,3 @@ Classifier: Programming Language :: Python :: 3.10
|
|
|
14
13
|
Classifier: License :: OSI Approved :: Apache Software License
|
|
15
14
|
Classifier: Operating System :: OS Independent
|
|
16
15
|
License-File: LICENSE
|
|
17
|
-
|
|
18
|
-
UNKNOWN
|
|
19
|
-
|
|
@@ -4,6 +4,7 @@ from dagster import InputContext, MetadataValue, OutputContext, TableColumn, Tab
|
|
|
4
4
|
from dagster._core.storage.db_io_manager import DbTypeHandler, TableSlice
|
|
5
5
|
from dagster_duckdb.io_manager import DuckDbClient, build_duckdb_io_manager
|
|
6
6
|
from pyspark.sql import SparkSession
|
|
7
|
+
from pyspark.sql.types import StructType
|
|
7
8
|
|
|
8
9
|
|
|
9
10
|
class DuckDBPySparkTypeHandler(DbTypeHandler[pyspark.sql.DataFrame]):
|
|
@@ -69,8 +70,11 @@ class DuckDBPySparkTypeHandler(DbTypeHandler[pyspark.sql.DataFrame]):
|
|
|
69
70
|
self, context: InputContext, table_slice: TableSlice, connection
|
|
70
71
|
) -> pyspark.sql.DataFrame:
|
|
71
72
|
"""Loads the return of the query as the correct type."""
|
|
72
|
-
pd_df = connection.execute(DuckDbClient.get_select_statement(table_slice)).fetchdf()
|
|
73
73
|
spark = SparkSession.builder.getOrCreate()
|
|
74
|
+
if table_slice.partition_dimensions and len(context.asset_partition_keys) == 0:
|
|
75
|
+
return spark.createDataFrame([], StructType([]))
|
|
76
|
+
|
|
77
|
+
pd_df = connection.execute(DuckDbClient.get_select_statement(table_slice)).fetchdf()
|
|
74
78
|
return spark.createDataFrame(pd_df)
|
|
75
79
|
|
|
76
80
|
@property
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
__version__ = "0.18.3"
|
|
@@ -1,12 +1,11 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: dagster-duckdb-pyspark
|
|
3
|
-
Version: 0.18.
|
|
3
|
+
Version: 0.18.3
|
|
4
4
|
Summary: Package for storing PySpark DataFrames in DuckDB.
|
|
5
5
|
Home-page: https://github.com/dagster-io/dagster/tree/master/python_modules/libraries/dagster-duckb-pyspark
|
|
6
6
|
Author: Elementl
|
|
7
7
|
Author-email: hello@elementl.com
|
|
8
8
|
License: Apache-2.0
|
|
9
|
-
Platform: UNKNOWN
|
|
10
9
|
Classifier: Programming Language :: Python :: 3.7
|
|
11
10
|
Classifier: Programming Language :: Python :: 3.8
|
|
12
11
|
Classifier: Programming Language :: Python :: 3.9
|
|
@@ -14,6 +13,3 @@ Classifier: Programming Language :: Python :: 3.10
|
|
|
14
13
|
Classifier: License :: OSI Approved :: Apache Software License
|
|
15
14
|
Classifier: Operating System :: OS Independent
|
|
16
15
|
License-File: LICENSE
|
|
17
|
-
|
|
18
|
-
UNKNOWN
|
|
19
|
-
|
|
@@ -7,7 +7,7 @@ from setuptools import find_packages, setup
|
|
|
7
7
|
def get_version() -> str:
|
|
8
8
|
version: Dict[str, str] = {}
|
|
9
9
|
with open(Path(__file__).parent / "dagster_duckdb_pyspark/version.py", encoding="utf8") as fp:
|
|
10
|
-
exec(fp.read(), version)
|
|
10
|
+
exec(fp.read(), version)
|
|
11
11
|
|
|
12
12
|
return version["__version__"]
|
|
13
13
|
|
|
@@ -34,8 +34,8 @@ setup(
|
|
|
34
34
|
packages=find_packages(exclude=["dagster_duckdb_pyspark_tests*"]),
|
|
35
35
|
include_package_data=True,
|
|
36
36
|
install_requires=[
|
|
37
|
-
"dagster==1.2.
|
|
38
|
-
"dagster-duckdb==0.18.
|
|
37
|
+
"dagster==1.2.3",
|
|
38
|
+
"dagster-duckdb==0.18.3",
|
|
39
39
|
# Pyspark 2.x is incompatible with Python 3.8+
|
|
40
40
|
'pyspark>=3.0.0; python_version >= "3.8"',
|
|
41
41
|
'pyspark>=2.0.2; python_version < "3.8"',
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
__version__ = "0.18.1"
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/dagster_duckdb_pyspark/__init__.py
RENAMED
|
File without changes
|
{dagster-duckdb-pyspark-0.18.1 → dagster-duckdb-pyspark-0.18.3}/dagster_duckdb_pyspark/py.typed
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|