flume.conf

#potrei utilizzare serializzatore nel sink per decidere come scrivere dai in kafka, ma per un parsing intelligente dovrei usare un interceptor

# Name the components on this agent

a1.sources = r1
a1.sinks = k1
a1.channels = c1

# Describe/configure the source

a1.sources.r1.type = spooldir
a1.sources.r1.spoolDir = /Users/cardu/Dev/spark/csv
a1.sources.r1.fileHeader = true

# Describe the sink
a1.sinks.k1.type = org.apache.flume.sink.kafka.KafkaSink
a1.sinks.k1.kafka.topic = foo
a1.sinks.k1.kafka.bootstrap.servers = localhost:9092
a1.sinks.k1.kafka.flumeBatchSize = 20
a1.sinks.k1.kafka.producer.acks = 1
a1.sinks.k1.kafka.producer.linger.ms = 1

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

# Bind the source and sink to the channel
a1.sinks.k1.channel = c1
a1.sources.r1.channels = c1