Skip to content

Instantly share code, notes, and snippets.

View dimaspivak's full-sized avatar

Dima Spivak dimaspivak

View GitHub Profile
import pytest
@pytest.mark.parametrize('data_format', ['DELIMITED'])
@pytest.mark.parametrize('header_line', ['WITH_HEADER'])
@pytest.mark.parametrize('config_value', ['False', 'True'])
def test_directory_origin_config_allow_extra_columns(sdc_builder, sdc_executor, config_value, data_format, header_line):
pass
import pytest
@pytest.mark.parametrize('data_format', ['DELIMITED'])
@pytest.mark.parametrize('header_line', ['WITH_HEADER'])
@pytest.mark.parametrize('config_value', ['False', 'True'])
def test_directory_origin_config_allow_extra_columns(sdc_builder, sdc_executor, config_value, data_format, header_line):
pass
from streamsets.sdk import DataCollector
SDC_URL = 'localhost:18630'
SDC_USERNAME = 'admin'
SDC_PASSWORD = 'admin'
STAGE_NAME = 'com_streamsets_pipeline_stage_destination_mapreduce_MapReduceDExecutor'
LEGACY_LIBRARY = 'streamsets-datacollector-cdh_5_12-lib'
NEW_LIBRARY = 'streamsets-datacollector-cdh_5_15-lib'
from streamsets.sdk import DataCollector
SDC_URL = 'localhost:18630'
SDC_USERNAME = 'admin'
SDC_PASSWORD = 'admin'
STAGE_NAME = 'com_streamsets_pipeline_stage_destination_mapreduce_MapReduceDExecutor'
LEGACY_LIBRARY = 'streamsets-datacollector-cdh_5_12-lib'
NEW_LIBRARY = 'streamsets-datacollector-cdh_5_15-lib'
ARG SDC_VERSION=3.17.0
# Set up stage libs here. Naming allows you to refer to them by name instead of by integer.
FROM streamsets/datacollector-libs:streamsets-datacollector-jdbc-lib-${SDC_VERSION} as jdbc-lib
# Using build args for the directories just makes things easier to read. These can be found in the image layers
# page on Docker Hub.
ARG JDBC_LIB_DIR=/opt/streamsets-datacollector-${SDC_VERSION}/streamsets-libs/streamsets-datacollector-jdbc-lib
FROM streamsets/datacollector:${SDC_VERSION}
COPY --from=jdbc-lib ${JDBC_LIB_DIR} ${JDBC_LIB_DIR}