datapipelab 0.2.1__tar.gz → 0.2.2__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.
Files changed (37) hide show
  1. {datapipelab-0.2.1 → datapipelab-0.2.2}/PKG-INFO +1 -1
  2. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/sink/hive_node.py +2 -1
  3. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/pipeline_handler.py +4 -0
  4. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab.egg-info/PKG-INFO +1 -1
  5. {datapipelab-0.2.1 → datapipelab-0.2.2}/setup.py +1 -1
  6. {datapipelab-0.2.1 → datapipelab-0.2.2}/MANIFEST.in +0 -0
  7. {datapipelab-0.2.1 → datapipelab-0.2.2}/README.md +0 -0
  8. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/__init__.py +0 -0
  9. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/__init__.py +0 -0
  10. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/connector_node/__init__.py +0 -0
  11. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/__init__.py +0 -0
  12. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/custom_node.py +0 -0
  13. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/processor/__init__.py +0 -0
  14. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/processor/bigquery_api_node.py +0 -0
  15. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/processor/bigquery_spark_node.py +0 -0
  16. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/processor/custom_node.py +0 -0
  17. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/processor/shell_node.py +0 -0
  18. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/processor/spark_node.py +0 -0
  19. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/sink/__init__.py +0 -0
  20. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/sink/csv_node.py +0 -0
  21. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/sink/delta_node.py +0 -0
  22. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/sink/pandas_csv_node.py +0 -0
  23. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/sink/teams_notification_node.py +0 -0
  24. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/source/__init__.py +0 -0
  25. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/source/delta_node.py +0 -0
  26. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/source/hive_node.py +0 -0
  27. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/source/spark_node.py +0 -0
  28. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/app/node/tnode.py +0 -0
  29. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/engine.py +0 -0
  30. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/logger.py +0 -0
  31. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/pipeline.py +0 -0
  32. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab/pipeline_config.py +0 -0
  33. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab.egg-info/SOURCES.txt +0 -0
  34. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab.egg-info/dependency_links.txt +0 -0
  35. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab.egg-info/requires.txt +0 -0
  36. {datapipelab-0.2.1 → datapipelab-0.2.2}/datapipelab.egg-info/top_level.txt +0 -0
  37. {datapipelab-0.2.1 → datapipelab-0.2.2}/setup.cfg +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: datapipelab
3
- Version: 0.2.1
3
+ Version: 0.2.2
4
4
  Summary: A data pipeline library with connectors, sources, processors, and sinks.
5
5
  Requires-Dist: json5
6
6
  Requires-Dist: loguru
@@ -1,5 +1,5 @@
1
1
  from datapipelab.app.node.tnode import TNode
2
-
2
+ from datapipelab.logger import logger
3
3
 
4
4
  class HiveSinkNode(TNode):
5
5
  def __init__(self, spark, tnode_config, df):
@@ -20,6 +20,7 @@ class HiveSinkNode(TNode):
20
20
  self.df = self.df.repartition(int(self.partition_count))
21
21
  else:
22
22
  self.df = self.df.repartition(int(self.partition_count), self.partition_by)
23
+ logger.info("Start writing to Hive")
23
24
  self.df.write.insertInto(f'{self.database_name}.{self.table_name}', overwrite=self.overwrite)
24
25
 
25
26
  def _process(self):
@@ -1,5 +1,6 @@
1
1
  from datapipelab.app.node.processor.custom_node import CustomNode
2
2
  from datapipelab.app.node.processor.shell_node import ShellProcessorNode
3
+ from datapipelab.app.node.source.hive_node import HiveSourceNode
3
4
  from datapipelab.app.node.source.spark_node import SparkSourceNode
4
5
  from datapipelab.app.node.source.delta_node import DeltaSourceNode
5
6
  from datapipelab.app.node.processor.spark_node import SparkProcessorNode
@@ -33,6 +34,9 @@ class PipelineHandler:
33
34
  if input_type == 'spark':
34
35
  if input_format == 'spark':
35
36
  source_df = SparkSourceNode(self.spark, tnode_config).run()
37
+ if input_type == 'hive':
38
+ if input_format == 'hive':
39
+ source_df = HiveSourceNode(self.spark, tnode_config).run()
36
40
  if input_type == 'adls_path':
37
41
  if input_format == 'delta':
38
42
  source_df = DeltaSourceNode(self.spark, tnode_config).run()
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: datapipelab
3
- Version: 0.2.1
3
+ Version: 0.2.2
4
4
  Summary: A data pipeline library with connectors, sources, processors, and sinks.
5
5
  Requires-Dist: json5
6
6
  Requires-Dist: loguru
@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
2
2
 
3
3
  setup(
4
4
  name='datapipelab',
5
- version='0.2.1',
5
+ version='0.2.2',
6
6
  description='A data pipeline library with connectors, sources, processors, and sinks.',
7
7
  packages=find_packages(),
8
8
  include_package_data=True,
File without changes
File without changes
File without changes