I using new configuration of kinesis stream, Below is configuration details.
# Default configuration for s3-loader
# Sources currently supported are:
# 'kinesis' for reading records from a Kinesis stream
# 'nsq' for reading records from a NSQ topic
source = "kinesis"
# Sink is used for sending events which processing failed.
# Sinks currently supported are:
# 'kinesis' for writing records to a Kinesis stream
# 'nsq' for writing records to a NSQ topic
sink = "kinesis"
# The following are used to authenticate for the Amazon Kinesis sink.
# If both are set to 'default', the default provider chain is used
# (see http://docs.aws.amazon.com/AWSJavaSDK/latest/javadoc/com/amazonaws/auth/DefaultAWSCredentialsProviderChain.html)
# If both are set to 'iam', use AWS IAM Roles to provision credentials.
# If both are set to 'env', use environment variables AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY
aws {
accessKey = "xxxx"
secretKey = "xxxxxxx"
}
# Config for NSQ
nsq {
# Channel name for NSQ source
# If more than one application reading from the same NSQ topic at the same time,
# all of them must have unique channel name for getting all the data from the same topic
# channelName = "{{nsqSourceChannelName}}"
# Host name for NSQ tools
# host = "{{nsqHost}}"
# HTTP port for nsqd
# port = {{nsqdPort}}
# HTTP port for nsqlookupd
# lookupPort = {{nsqlookupdPort}}
}
kinesis {
# LATEST: most recent data.
# TRIM_HORIZON: oldest available data.
# "AT_TIMESTAMP": Start from the record at or after the specified timestamp
# Note: This only affects the first run of this application on a stream.
initialPosition = "TRIM_HORIZON"
# Need to be specified when initialPosition is "AT_TIMESTAMP".
# Timestamp format need to be in "yyyy-MM-ddTHH:mm:ssZ".
# Ex: "2017-05-17T10:00:00Z"
# Note: Time need to specified in UTC.
initialTimestamp = "2017-12-17T10:00:00Z"
# Maximum number of records to read per GetRecords call
maxRecords = 100000
region = "us-east-1"
# "appName" is used for a DynamoDB table to maintain stream state.
appName = "snowplowunilog"
}
streams {
# Input stream name
inStreamName = "GoodStream"
# Stream for events for which the storage process fails
outStreamName = "BadStream"
# Events are accumulated in a buffer before being sent to S3.
# The buffer is emptied whenever:
# - the combined size of the stored records exceeds byteLimit or
# - the number of stored records exceeds recordLimit or
# - the time in milliseconds since it was last emptied exceeds timeLimit
buffer {
byteLimit = 4500000 # Not supported by NSQ; will be ignored
recordLimit = 500
timeLimit = 60000 # Not supported by NSQ; will be ignored
}
}
s3 {
region = "us-east-1"
bucket = "sample1bucketevents"
# Format is one of lzo or gzip
# Note, that you can use gzip only for enriched data stream.
format = "lzo"
# Maximum Timeout that the application is allowed to fail for
maxTimeout = 1
}
# Optional section for tracking endpoints
monitoring {
snowplow{
collectorUri = "172.31.38.39:8082"
collectorPort = 8082
appId = "1"
method = "GET"
}
}
I am running using below command.
java -jar snowplow-s3-loader-0.6.0.jar --config kinesisnew2.conf
I am getting below error.
configuration error: ConfigReaderFailures(KeyNotFound(nsq.channelName,Some(ConfigValueLocation(file:/home/ubuntu/kinesis-s3/target/scala-2.11/kinesisnew2.conf,25)),Set()),List(KeyNotFound(nsq.host,Some(ConfigValueLocation(file:/home/ubuntu/kinesis-s3/target/scala-2.11/kinesisnew2.conf,25)),Set()), KeyNotFound(nsq.port,Some(ConfigValueLocation(file:/home/ubuntu/kinesis-s3/target/scala-2.11/kinesisnew2.conf,25)),Set()), KeyNotFound(nsq.lookupPort,Some(ConfigValueLocation(file:/home/ubuntu/kinesis-s3/target/scala-2.11/kinesisnew2.conf,25)),Set())))
please help me to resolve this configuration error.