Logstash configuration file for throwing CloudFront logs to Amazon ES

cloudfront-logstash.conf

input {
  s3 {
    bucket => "<CLOUDFRONT_LOG_BUCKET>"
    prefix => "<CLOUDFRONT_LOG_KEY_PREFIX>"
    region => "<BUCKET_REGION_NAME>"
  }
}


filter {
  grok {
    match => { "message" => "%{DATE_EU:date}\t%{TIME:time}\t%{WORD:x_edge_location}\t(?:%{NUMBER:sc_bytes:int}|-)\t%{IPORHOST:c_ip}\t%{WORD:cs_method}\t%{HOSTNAME:cs_host}\t%{NOTSPACE:cs_uri_stem}\t%{NUMBER:sc_status:int}\t%{GREEDYDATA:referrer}\t%{GREEDYDATA:User_Agent}\t%{GREEDYDATA:cs_uri_stem}\t%{GREEDYDATA:cookies}\t%{WORD:x_edge_result_type}\t%{NOTSPACE:x_edge_request_id}\t%{HOSTNAME:x_host_header}\t%{URIPROTO:cs_protocol}\t%{INT:cs_bytes:int}\t%{GREEDYDATA:time_taken}\t%{GREEDYDATA:x_forwarded_for}\t%{GREEDYDATA:ssl_protocol}\t%{GREEDYDATA:ssl_cipher}\t%{GREEDYDATA:x_edge_response_result_type}" }
  }

  mutate {
    add_field => [ "listener_timestamp", "%{date} %{time}" ]
  }

  date {
    match => [ "listener_timestamp", "yy-MM-dd HH:mm:ss" ]
    target => "@timestamp"
  }

  geoip {
    source => "c_ip"
  }

  useragent {
    source => "User_Agent"
    target => "useragent"
  }

  mutate {
    remove_field => ["date", "time", "listener_timestamp", "cloudfront_version", "message", "cloudfront_fields", "User_Agent"]
  }
}

output {
  amazon_es {
    hosts => ["<AMAZON_ES_DOMAIN_ENDPOINT>"]
    region => "<AMAZON_ES_DOMAIN_REGION_NAME>"
    index => "cloudfront-logs-%{+YYYY.MM.dd}"
    template => "/etc/logstash/cloudfront.template.json"
  }
}