Skip to content

Instantly share code, notes, and snippets.

@Ardagan
Last active March 26, 2019 23:49
Show Gist options
  • Save Ardagan/848b89a7a60645203afb1ea77f62c8cc to your computer and use it in GitHub Desktop.
Save Ardagan/848b89a7a60645203afb1ea77f62c8cc to your computer and use it in GitHub Desktop.
Beam run java worker pipeline
# build all binaries skipping docker images and running tests
./gradlew build -x rat -x javadoc -x test -x website -x docs -x sdist -x lintPy27 -x lintPy27_3 -x lintPy3 -x testWebsite -x spotlessJava -x goTest -x checkstyleMain -x buildDockerImage -x spotbugsMain -x checkstyleTest -x buildLocalWebsite -x goVet -x gofmt
# skip compiling java tests
-x compileTestJava -x shadowJar -x compileJava
# Build java worker jav (DF runner harness)
./gradlew :beam-runners-google-cloud-dataflow-java-fn-api-worker:build -x spotlessJava -x rat -x test
./gradlew :beam-runners-google-cloud-dataflow-java-fn-api-worker:shadowJar
# Build Python SDK Harness docker image
./gradlew -Pdocker-repository-root=gcr.io/dataflow-build/migryz/beam -p sdks/python/container docker
gcloud docker -- push gcr.io/dataflow-build/migryz/beam/python:latest
# run pipeline
virtualenv env
. ./env/bin/activate
clear && clear && java -cp beam-examples-java-2.12.0-SNAPSHOT.jar org.apache.beam.examples.MinimalWordCount --runner DataflowRunner --num_workers 1 --project google.com:clouddfe --input gs://dataflow-samples/shakespeare/kinglear.txt --output gs://clouddfe-test/staging-$USER/output --temp_location gs://clouddfe-test/staging-$USER/ --worker_harness_container_image gcr.io/dataflow-build/$USER/beam/python:latest --sdk_location build/apache-beam-2.12.0.dev0.tar.gz --dataflow_worker_jar '/usr/local/google/home/migryz/work/osbeam/myfork/runners/google-cloud-dataflow-java/worker/build/libs/beam-runners-google-cloud-dataflow-java-fn-api-worker-2.12.0-SNAPSHOT.jar'
clear && clear && python -m apache_beam.examples.wordcount --runner DataflowRunner --num_workers 1 --project google.com:clouddfe --output gs://clouddfe-test/staging-$USER/output --temp_location gs://clouddfe-test/staging-$USER/ --worker_harness_container_image gcr.io/dataflow-build/$USER/beam/python:latest --experiment beam_fn_api --sdk_location build/apache-beam-2.12.0.dev0.tar.gz --dataflow_worker_jar '/usr/local/google/home/migryz/work/osbeam/myfork/runners/google-cloud-dataflow-java/worker/build/libs/beam-runners-google-cloud-dataflow-java-fn-api-worker-2.12.0-SNAPSHOT.jar'
# run unittests for python
python setup.py nosetests -s --tests apache_beam.runners.portability.fn_api_runner_test:FnApiRunnerTest.test_element_count_metrics
# run unittest for java
clear && clear && ./gradlew :beam-runners-google-cloud-dataflow-java-fn-api-worker:test --tests org.apache.beam.runners.dataflow.worker.SystemIdToDfePCollectionNameMappingBuilderTest -s --info
############################################
# run HelloWorld examples integration test
./gradlew :beam-runners-google-cloud-dataflow-java-fn-api-worker:build -x spotlessJava -x rat -x test
./gradlew :beam-runners-google-cloud-dataflow-java-fn-api-worker:shadowJar
# Disabling undesired test
sed -i 's/^ \/\/ include \"\*\*\/WindowedWordCountIT\.class\"$/ include \"\*\*\/WindowedWordCountIT\.class\"/' ./runners/google-cloud-dataflow-java/examples/build.gradle
# Enabling test back
sed -i 's/^ include \"\*\*\/WindowedWordCountIT\.class\"$/ \/\/ include \"\*\*\/WindowedWordCountIT\.class\"/' ./runners/google-cloud-dataflow-java/examples/build.gradle
clear && clear && ./gradlew :beam-runners-google-cloud-dataflow-java-examples:preCommitFnApiWorker -PdataflowProject=google.com:clouddfe -Pproject=google.com:clouddfe -PgcpProject=google.com:clouddfe -PgcsTempRoot=gs://clouddfe-test/stating-migryz -PdataflowTempRoot=gs://clouddfe-test/staging-migryz -PdockerImageRoot=gcr.io/dataflow-build/migryz/beam
clear && clear && ./gradlew :beam-runners-google-cloud-dataflow-java-examples:preCommitLegacyWorker -PdataflowProject=google.com:clouddfe -Pproject=google.com:clouddfe -PgcpProject=google.com:clouddfe -PgcsTempRoot=gs://clouddfe-test/stating-migryz -PdataflowTempRoot=gs://clouddfe-test/staging-migryz -PdockerImageRoot=gcr.io/dataflow-build/migryz/beam
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment