config.hocon.sample

# 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 = "{{source}}"

# 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 = "{{sink}}"

# 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 = "iam"
  secretKey = "iam"
}

# 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 = "{{kinesisInitialPosition}}"

  # 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 = "{{timestamp}}"

  # Maximum number of records to read per GetRecords call     
  maxRecords = {{kinesisMaxRecords}}

  region = "{{kinesisRegion}}"

  # "appName" is used for a DynamoDB table to maintain stream state.
  appName = "{{appName}}"

  ## Optional endpoint url configuration to override aws kinesis endpoints,
  ## this can be used to specify local endpoints when using localstack
  # customEndpoint = {{kinesisEndpoint}}

  # Optional override to disable CloudWatch metrics for KCL
  # disableCloudWatch = true
}

streams {
  # Input stream name
  inStreamName = "{{inStreamName}}"

  # Stream for events for which the storage process fails
  outStreamName = "{{outStreamName}}"

  # 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 = {{bufferByteThreshold}} # Not supported by NSQ; will be ignored
    recordLimit = {{bufferRecordThreshold}}
    timeLimit = {{bufferTimeThreshold}} # Not supported by NSQ; will be ignored
  }
}

s3 {
  region = "{{s3Region}}"
  bucket = "{{s3bucket}}"
  # optional bucket where to store partitioned data
  partitionedBucket = "{{s3bucket}}/partitioned"

  # optional date format prefix for directory pattern
  # eg: {YYYY}/{MM}/{dd}/{HH}
  dateFormat = "{{s3DateFormat}}"

  # optional directory structure to use while storing data on s3 (followed by dateFormat config)
  # eg: outputDirectory = "enriched/good/"
  outputDirectory = "{{s3OutputDirectory}}"

  # optional filename prefix
  # eg: output
  filenamePrefix = "{{s3DFilenamePrefix}}"

  # Format is one of lzo or gzip
  # Note, that you can use gzip only for enriched data stream.
  format = "{{format}}"

  # Maximum Timeout that the application is allowed to fail for (in milliseconds)
  maxTimeout = {{maxTimeout}}

  ## Optional endpoint url configuration to override aws s3 endpoints,
  ## this can be used to specify local endpoints when using localstack
  # customEndpoint = {{kinesisEndpoint}}
}

# Optional section for tracking endpoints
monitoring {
  snowplow{
    collectorUri = "{{collectorUri}}"
    collectorPort = 80 
    appId = "{{appName}}"
    method = "{{method}}"
  }
}