Skip to content

Instantly share code, notes, and snippets.

@ruebot
Last active June 17, 2020 17:21
Show Gist options
  • Save ruebot/b4d565c2a0cdc5e72678366f6d616388 to your computer and use it in GitHub Desktop.
Save ruebot/b4d565c2a0cdc5e72678366f6d616388 to your computer and use it in GitHub Desktop.
AUT Spark 3.0.0 Testing
/home/nruest/bin/spark-3.0.0-bin-hadoop2.7/bin/spark-submit --master local\[2\] --driver-memory 4g --conf spark.driver.maxResultSize=0 --class io.archivesunleashed.app.CommandLineAppRunner /home/nruest/Projects/au/aut/target/aut-0.80.1-SNAPSHOT-fatjar.jar --extractor AudioInformationExtractor --input /home/nruest/Projects/au/sample-data/geocities --output /home/nruest/Projects/au/sample-data/3.0.0-testing/audio/csv
/home/nruest/bin/spark-3.0.0-bin-hadoop2.7/bin/spark-submit --master local\[2\] --driver-memory 4g --conf spark.driver.maxResultSize=0 --class io.archivesunleashed.app.CommandLineAppRunner /home/nruest/Projects/au/aut/target/aut-0.80.1-SNAPSHOT-fatjar.jar --extractor DomainFrequencyExtractor --input /home/nruest/Projects/au/sample-data/geocities --output /home/nruest/Projects/au/sample-data/3.0.0-testing/domains/csv
/home/nruest/bin/spark-3.0.0-bin-hadoop2.7/bin/spark-submit --master local\[2\] --driver-memory 4g --conf spark.driver.maxResultSize=0 --class io.archivesunleashed.app.CommandLineAppRunner /home/nruest/Projects/au/aut/target/aut-0.80.1-SNAPSHOT-fatjar.jar --extractor DomainGraphExtractor --input /home/nruest/Projects/au/sample-data/geocities --output /home/nruest/Projects/au/sample-data/3.0.0-testing/domaingraph/csv
/home/nruest/bin/spark-3.0.0-bin-hadoop2.7/bin/spark-submit --master local\[2\] --driver-memory 4g --conf spark.driver.maxResultSize=0 --class io.archivesunleashed.app.CommandLineAppRunner /home/nruest/Projects/au/aut/target/aut-0.80.1-SNAPSHOT-fatjar.jar --extractor ImageGraph --input /home/nruest/Projects/au/sample-data/geocities --output /home/nruest/Projects/au/sample-data/3.0.0-testing/ImageGraph/csv
/home/nruest/bin/spark-3.0.0-bin-hadoop2.7/bin/spark-submit --master local\[2\] --driver-memory 4g --conf spark.driver.maxResultSize=0 --class io.archivesunleashed.app.CommandLineAppRunner /home/nruest/Projects/au/aut/target/aut-0.80.1-SNAPSHOT-fatjar.jar --extractor ImageInformationExtractor --input /home/nruest/Projects/au/sample-data/geocities --output /home/nruest/Projects/au/sample-data/3.0.0-testing/ImageInformationExtractor/csv
/home/nruest/bin/spark-3.0.0-bin-hadoop2.7/bin/spark-submit --master local\[2\] --driver-memory 4g --conf spark.driver.maxResultSize=0 --class io.archivesunleashed.app.CommandLineAppRunner /home/nruest/Projects/au/aut/target/aut-0.80.1-SNAPSHOT-fatjar.jar --extractor PDFInformationExtractor --input /home/nruest/Projects/au/sample-data/geocities --output /home/nruest/Projects/au/sample-data/3.0.0-testing/PDFInformationExtractor/csv
/home/nruest/bin/spark-3.0.0-bin-hadoop2.7/bin/spark-submit --master local\[2\] --driver-memory 4g --conf spark.driver.maxResultSize=0 --class io.archivesunleashed.app.CommandLineAppRunner /home/nruest/Projects/au/aut/target/aut-0.80.1-SNAPSHOT-fatjar.jar --extractor PlainTextExtractor --input /home/nruest/Projects/au/sample-data/geocities --output /home/nruest/Projects/au/sample-data/3.0.0-testing/PlainTextExtractor/csv
/home/nruest/bin/spark-3.0.0-bin-hadoop2.7/bin/spark-submit --master local\[2\] --driver-memory 4g --conf spark.driver.maxResultSize=0 --class io.archivesunleashed.app.CommandLineAppRunner /home/nruest/Projects/au/aut/target/aut-0.80.1-SNAPSHOT-fatjar.jar --extractor PresentationProgramInformationExtractor --input /home/nruest/Projects/au/sample-data/geocities --output /home/nruest/Projects/au/sample-data/3.0.0-testing/PresentationProgramInformationExtractor/csv
/home/nruest/bin/spark-3.0.0-bin-hadoop2.7/bin/spark-submit --master local\[2\] --driver-memory 4g --conf spark.driver.maxResultSize=0 --class io.archivesunleashed.app.CommandLineAppRunner /home/nruest/Projects/au/aut/target/aut-0.80.1-SNAPSHOT-fatjar.jar --extractor SpreadsheetInformationExtractor --input /home/nruest/Projects/au/sample-data/geocities --output /home/nruest/Projects/au/sample-data/3.0.0-testing/SpreadsheetInformationExtractor/csv
/home/nruest/bin/spark-3.0.0-bin-hadoop2.7/bin/spark-submit --master local\[2\] --driver-memory 4g --conf spark.driver.maxResultSize=0 --class io.archivesunleashed.app.CommandLineAppRunner /home/nruest/Projects/au/aut/target/aut-0.80.1-SNAPSHOT-fatjar.jar --extractor VideoInformationExtractor --input /home/nruest/Projects/au/sample-data/geocities --output /home/nruest/Projects/au/sample-data/3.0.0-testing/VideoInformationExtractor/csv
/home/nruest/bin/spark-3.0.0-bin-hadoop2.7/bin/spark-submit --master local\[2\] --driver-memory 4g --conf spark.driver.maxResultSize=0 --class io.archivesunleashed.app.CommandLineAppRunner /home/nruest/Projects/au/aut/target/aut-0.80.1-SNAPSHOT-fatjar.jar --extractor WebGraphExtractor --input /home/nruest/Projects/au/sample-data/geocities --output /home/nruest/Projects/au/sample-data/3.0.0-testing/WebGraphExtractor/csv
/home/nruest/bin/spark-3.0.0-bin-hadoop2.7/bin/spark-submit --master local\[2\] --driver-memory 4g --conf spark.driver.maxResultSize=0 --class io.archivesunleashed.app.CommandLineAppRunner /home/nruest/Projects/au/aut/target/aut-0.80.1-SNAPSHOT-fatjar.jar --extractor WebPagesExtractor --input /home/nruest/Projects/au/sample-data/geocities --output /home/nruest/Projects/au/sample-data/3.0.0-testing/WebPagesExtractor/csv
/home/nruest/bin/spark-3.0.0-bin-hadoop2.7/bin/spark-submit --master local\[2\] --driver-memory 4g --conf spark.driver.maxResultSize=0 --class io.archivesunleashed.app.CommandLineAppRunner /home/nruest/Projects/au/aut/target/aut-0.80.1-SNAPSHOT-fatjar.jar --extractor WordProcessorInformationExtractor --input /home/nruest/Projects/au/sample-data/geocities --output /home/nruest/Projects/au/sample-data/3.0.0-testing/WordProcessorInformationExtractor/csv
export PYSPARK_DRIVER_PYTHON=jupyter; export PYSPARK_DRIVER_PYTHON_OPTS=notebook; ~/bin/spark-3.0.0-bin-hadoop2.7/bin/pyspark --py-files /home/nruest/Projects/au/aut/target/aut.zip --jars /home/nruest/Projects/au/aut/target/aut-0.80.1-SNAPSHOT-fatjar.jar --driver-memory 6g
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment