#!/usr/bin/ruby

require 'rubygems'
require 'aws/s3'

# for non-us buckets, we need to change the endpoint
AWS.config(:s3_endpoint => "s3-eu-west-1.amazonaws.com")

# connect to S3
s3 = AWS::S3.new(:access_key_id => S3_ACCESS_KEY, :secret_access_key => S3_SECRET_KEY)

# grab the bucket where the logs are stored
bucket = s3.buckets[BUCKET_NAME]

File.open("/var/log/s3_bucket.log", 'w') do |file|

  # grab all the objects in the bucket, can also use a prefix here and limit what S3 returns
  bucket.objects.with_prefix('staticassets-logs/').each do |log|
    log.read do |line|
      file.write(line)
    end
  end
end

#!/bin/bash
export PATH=$PATH:/bin:/usr/bin
cd /var/log/s3/$S3_BUCKET/
export s3url=s3://$S3_BUCKET/$S3_PREFIX
s3cmd -c /home/logstash/.s3cfg sync --skip-existing $s3url .

input {
  file {
    type => "s3-access-log"
    path => "/var/log/s3/$S3_BUCKET/$S3_BUCKET/*"
    sincedb_path => "/dev/null"
    start_position => "beginning"
  }
}
filter {
    if [type] == "s3-access-log" {
        grok {
            patterns_dir => ["/etc/logstash/conf.d/patterns"]
            match => { "message" => "%{S3_ACCESS_LOG}" }
            remove_field => ["message"]
        }
        date {
            match => [ "timestamp" , "dd/MMM/yyyy:HH:mm:ss Z" ]
            remove_field => ["timestamp"]
        }
    }
}
output {
  elasticsearch { host => localhost }
  stdout { codec => rubydebug }
}