...
- First create a CSV file and write the file to HDFS location hdfs://localhost:9000/source
- Create a job configuration file with the properties set as shown below.
- Run the example as
bin/gobblin-standalone.sh start --conf /path/to/job/conf --workdir /tmp
- The output avro file should be under the "/final" dir on HDFS.
job.name=CSVToAvroQuickStart
fs.uri=hdfs://localhost:9000
converter.classes=org.apache.gobblin.converter.csv.CsvToJsonConverter,org.apache.gobblin.converter.avro.JsonIntermediateToAvroConverter
writer.builder.class=org.apache.gobblin.writer.AvroDataWriterBuilder
source.class=org.apache.gobblin.source.extractor.filebased.TextFileBasedSource
source.filebased.data.directory=${fs.uri}/sourcesource.filebased.fs.uri=${fs.uri}source.schema=[{"columnName":"ID","comment":"","isNullable":"true","dataType":{"type":"String"}},{"columnName":"NAME","comment":"","isNullable":"true","dataType":{"type":"String"}}]source.skip.first.record=false
extract.table.name=CsvToAvro
extract.namespace=org.apache.gobblin.example
extract.table.type=APPEND_ONLY
converter.csv.to.json.delimiter=","
writer.output.format=AVRO
writer.destination.type=HDFS
writer.fs.uri=${fs.uri}writer.staging.dir=/writer-staging
writer.output.dir=/output
state.store.dir=/state
state.store.fs.uri=hdfs://localhost:9000
state.store.dir=/gobblin-kafka/state-store
data.publisher.final.dir=/final
...