Snowplow Config

config.yml

aws:
  access_key_id: my_id
  secret_access_key: my_key
  s3:
    region: us-east-1
    buckets:
      assets: s3://snowplow-hosted-assets # DO NOT CHANGE unless you are hosting the jarfiles etc yourself in your own bucket
      jsonpath_assets: s3://snowplow-looker/jsonpaths
      log: s3n://snowplow-looker-emr-log/
      raw:
        in:
          - s3://elasticbeanstalk-us-east-1-734261250617/resources/environments/logs/publish/e-uftusxb7dt/
        processing: s3://snowplow-looker-emr-processing/events1/
        archive: s3://snowplow-looker-emr-archive/raw1/
      enriched:
        good: s3://snowplow-looker-emr-out/enriched1/good/
        bad: s3://snowplow-looker-emr-out/enriched1/bad/
        errors: s3://snowplow-looker-emr-out/enriched1/error/
        archive: s3://snowplow-looker-emr-out/enriched1/error/archive/
      shredded:
        good: s3://snowplow-looker-emr-out/shredded1/good/
        bad: s3://snowplow-looker-emr-out/shredded1/bad/
        errors:              # Leave blank unless :continue_on_unexpected_error: set to true below
        archive: s3://snowplow-looker-emr-out/shredded1/archive/
  emr:
    ami_version: 3.7.0                # Don't change this
    region: us-east-1
    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-23ff3a53    # Set this if running in VPC. Leave blank otherwise
    ec2_key_name: snowplow-etl
    bootstrap: []           # Set this to specify custom boostrap actions. Leave empty otherwise
    software:
      hbase:                # To launch on cluster, provide version, "0.92.0", keep quotes
      lingual:              # To launch on cluster, provide version, "1.1", keep quotes
    # Adjust your Hadoop cluster below
    jobflow:
      master_instance_type: m1.large
      core_instance_count: 2
      core_instance_type: m1.medium
      task_instance_count: 0   # Increase to use spot instances
      task_instance_type: m1.small
      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
collectors:
  format: clj-tomcat      # Or 'clj-tomcat' for the Clojure Collector, or 'thrift' for Thrift records, or 'tsv/com.amazon.aws.cloudfront/wd_access_log' for Cloudfront access logs
enrich:
  job_name: New Snowplow ETL  # Give your job a name
  versions:
    hadoop_enrich: 1.2.0 # Version of the Hadoop Enrichment process
    hadoop_shred: 0.5.0 # Version of the Hadoop Shredding 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: GZIP # 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: "Meta Redshift Cluster"
      type: redshift
      host: my_redshift_host
      database: meta
      port: 5439
      ssl_mode: disable # One of disable (default), require, verify-ca or verify-full
      table: snowplow.events  #using a custom schema here
      username: my_user
      password: my_password
      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: post
    app_id: snowping # e.g. snowplow
    collector: snowping.looker.com # e.g. d3rkrsqld9gmqf.cloudfront.net
iglu:
  schema: iglu:com.snowplowanalytics.iglu/resolver-config/jsonschema/1-0-0
  data:
    cache_size: 500
    repositories:
      - name: "Iglu Central"
        priority: 0
        vendor_prefixes:
          - com.snowplowanalytics
        connection:
          http:
            uri: http://iglucentral.com
      - name: "Looker Repository"
        priority: 5
        vendor_prefixes:
          - com.looker
        connection:
          http:
            uri: https://s3.amazonaws.com/snowplow-looker