Dockerfile

application.conf

# Copyright (c) 2013-2016 Snowplow Analytics Ltd. All rights reserved.
#
# This program is licensed to you under the Apache License Version 2.0, and
# you may not use this file except in compliance with the Apache License
# Version 2.0.  You may obtain a copy of the Apache License Version 2.0 at
# http://www.apache.org/licenses/LICENSE-2.0.
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the Apache License Version 2.0 is distributed on an "AS
# IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
# implied.  See the Apache License Version 2.0 for the specific language
# governing permissions and limitations there under.

# This file (application.conf.example) contains a template with
# configuration options for Stream Enrich.

enrich {
  # Sources currently supported are:
  # 'kinesis' for reading Thrift-serialized records from a Kinesis stream
  # 'stdin' for reading Base64-encoded Thrift-serialized records from stdin
  source = "kinesis"

  # Sinks currently supported are:
  # 'kinesis' for writing enriched events to one Kinesis stream and invalid events to another.
  # 'stdouterr' for writing enriched events to stdout and invalid events to stderr.
  #    Using "sbt assembly" and "java -jar" is recommended to disable sbt
  #    logging.
  sink = "kinesis"

  # AWS credentials
  #
  # If both are set to 'default', use the default AWS credentials provider chain.
  #
  # 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 {
    access-key: "env"
    secret-key: "env"
  }

  streams {
    in: {
      raw: ${KINESIS_GOOD_STREAM}

      # Maximum number of records to get from Kinesis per call to GetRecords
      maxRecords: 10000

      # After enrichment, are accumulated in a buffer before being sent to Kinesis.
      # The buffer is emptied whenever:
      # - the number of stored records reaches record-limit or
      # - the combined size of the stored records reaches byte-limit or
      # - the time in milliseconds since it was last emptied exceeds time-limit when
      #   a new event enters the buffer
      buffer: {
        byte-limit: 4500000 # 4.5MB
        record-limit: 500 # 500 records
        time-limit: 1000 # 1 second
      }
    }

    out: {
      enriched: ${KINESIS_GOOD_STREAM_ENRICHED}
      bad: ${KINESIS_BAD_STREAM_ENRICHED}

      # Minimum and maximum backoff periods
      # - Units: Milliseconds
      backoffPolicy: {
        minBackoff: 3000 # 3 s
        maxBackoff: 600000 # 5 min
      }
    }

    # "app-name" is used for a DynamoDB table to maintain stream state.
    # You can set it automatically using: "SnowplowKinesisEnrich-$\\{enrich.streams.in.raw\\}"
    app-name: ${ENRICHER_APP_NAME}

    # LATEST: most recent data.
    # TRIM_HORIZON: oldest available data.
    # Note: This only effects the first run of this application
    # on a stream.
    initial-position = "TRIM_HORIZON"

    region: "us-east-1"
  }

  # Optional section for tracking endpoints
  # monitoring {
  #   snowplow {
  #     collector-uri: "{{collectorUri}}"
  #     collector-port: 80
  #     app-id: "{{enrichAppName}}"
  #     method: "GET"
  #   }
  # }
}

Dockerfile

FROM williamyeh/sbt

RUN mkdir /var/app
WORKDIR /var/app
COPY project /var/app/project
COPY src /var/app/src

# Run the build
RUN sbt assembly

# Link the binary
RUN ln -s target/scala-2.10/snowplow-stream-enrich-0.8.1 enricher

# Include our config file
COPY application.conf .
COPY enrichments ./enrichments
COPY resolver.js .

# Specify the command
ENTRYPOINT ["./enricher"]
CMD ["--config", "application.conf", "--resolver", "file:resolver.js", "--enrichments", "file:enrichments"]