config.yml

aws:
  # Credentials can be hardcoded or set in environment variables
  access_key_id: 'XXXXX'
  secret_access_key: 'XXXXX'
  s3:
    region: eu-west-1a
    buckets:
      assets: s3://snowplow-hosted-assets # DO NOT CHANGE unless you are hosting the jarfiles etc yourself in your own bucket
      jsonpath_assets: # If you have defined your own JSON Schemas, add the s3:// path to your own JSON Path files in your own bucket here
      log: s3://snwplw-enrich-logs
      raw:
        in:                  # Multiple in buckets are permitted
          - snwlpk-logs          # e.g. s3://my-in-bucket
#          - ADD HERE
        processing: s3://snwplw-enrich-processing
        archive: s3://snwplw-enrich-archive    # e.g. s3://my-archive-bucket/raw
      enriched:
        good: s3://snwplw-enriched-data/good       # e.g. s3://my-out-bucket/enriched/good
        bad: s3://snwplw-enriched-data/bad        # e.g. s3://my-out-bucket/enriched/bad
        errors:     # Leave blank unless :continue_on_unexpected_error: set to true below
        archive: s3://snwplw-enriched-data/archive    # Where to archive enriched events to, e.g. s3://my-archive-bucket/enriched
      shredded:
        good: s3://snwplw-shredded-data/good       # e.g. s3://my-out-bucket/shredded/good
        bad: s3://snwplw-shredded-data/bad        # e.g. s3://my-out-bucket/shredded/bad
        errors:     # Leave blank unless :continue_on_unexpected_error: set to true below
        archive: s3://snwplw-shredded-data/archive    # Where to archive shredded events to, e.g. s3://my-archive-bucket/shredded
  emr:
    ami_version: 4.5.0
    region: eu-west-1a        # Always set this
    jobflow_role: EMR_EC2_DefaultRole # Created using $ aws emr create-default-roles
    service_role: EMR_DefaultRole     # Created using $ aws emr create-default-roles
    placement:      # Set this if not running in VPC. Leave blank otherwise
    ec2_subnet_id: subnet-4f0cc717 # Set this if running in VPC. Leave blank otherwise
    ec2_key_name: ec2-snwplw-enr
    bootstrap: []           # Set this to specify custom boostrap actions. Leave empty otherwise
    software:
      hbase:                # Optional. To launch on cluster, provide version, "0.92.0", keep quotes. Leave empty otherwise.
      lingual:              # Optional. To launch on cluster, provide version, "1.1", keep quotes. Leave empty otherwise.
    # Adjust your Hadoop cluster below
    jobflow:
      master_instance_type: m1.medium
      core_instance_count: 2
      core_instance_type: m1.medium
      task_instance_count: 0 # Increase to use spot instances
      task_instance_type: m1.medium
      task_instance_bid: 0.015 # In USD. Adjust bid, or leave blank for non-spot-priced (i.e. on-demand) task instances
    bootstrap_failure_tries: 3 # Number of times to attempt the job in the event of bootstrap failures
    additional_info:        # Optional JSON string for selecting additional features
collectors:
  format: cloudfront # For example: 'clj-tomcat' for the Clojure Collector, 'thrift' for Thrift records, 'tsv/com.amazon.aws.cloudfront/wd_access_log' for Cloudfront access logs or 'ndjson/urbanairship.connect/v1' for UrbanAirship Connect events
enrich:
  job_name: Snowplow ETL # Give your job a name
  versions:
    hadoop_enrich: 1.7.0 # Version of the Hadoop Enrichment process
    hadoop_shred: 0.9.0 # Version of the Hadoop Shredding process
    hadoop_elasticsearch: 0.1.0 # Version of the Hadoop to Elasticsearch copying process
  continue_on_unexpected_error: false # Set to 'true' (and set :out_errors: above) if you don't want any exceptions thrown from ETL
  output_compression: NONE # Compression only supported with Redshift, set to NONE if you have Postgres targets. Allowed formats: NONE, GZIP
storage:
  download:
    folder: # Postgres-only config option. Where to store the downloaded files. Leave blank for Redshift
  targets:
    - name: "snwplw"
      type: redshift
      host: rs-snwplw-db.cv7vgkektjyu.eu-west-1.redshift.amazonaws.com:5439 # The endpoint as shown in the Redshift console
      database: snwplw # Name of database
      port: 5439 # Default Redshift port
      ssl_mode: disable # One of disable (default), require, verify-ca or verify-full
      table: atomic.events
      username: XXXXX
      password: XXXXX
      maxerror: 1 # Stop loading on first error, or increase to permit more load errors
      comprows: 200000 # Default for a 1 XL node cluster. Not used unless --include compupdate specified
monitoring:
  tags: {} # Name-value pairs describing this job
  logging:
    level: DEBUG # You can optionally switch to INFO for production
  snowplow:
    method: get
    app_id: snowplow # e.g. snowplow
    collector: d7y6axreyshzs.cloudfront.net # e.g. d3rkrsqld9gmqf.cloudfront.net