input {
  beats {
    port => "5044"
  }
}

filter {
  ## beat and LSF compatibility
  ## https://discuss.elastic.co/t/problem-with-transfer-filebeat-6-1-3-logstash-6-1-3-elasticsearch-6-1-3/136264/6
  ## https://discuss.elastic.co/t/logstash-errors-after-upgrading-to-filebeat-6-3-0/135984/6
  if [beat][hostname] {
    if [source] {
      if ![file] {
        mutate {
          add_field => {
            "file" => "%{source}"
          }
        }
      }
    }
    mutate {
      remove_field => [ "[host]" ]
    }
    mutate {
      add_field => {
        "host" => "%{[beat][hostname]}"
      }
    }
  }

  # ## apache2 module 
  # ## filebeat apache module https://www.elastic.co/guide/en/logstash/current/logstash-config-for-filebeat-modules.html
  if [fileset][module] == "apache2" {
    if [fileset][name] == "access" {
      grok {
        match => { "message" => ["%{IPORHOST:[apache2][access][remote_ip]} - %{DATA:[apache2][access][user_name]} \[%{HTTPDATE:[apache2][access][time]}\] \"%{WORD:[apache2][access][method]} %{DATA:[apache2][access][url]} HTTP/%{NUMBER:[apache2][access][http_version]}\" %{NUMBER:[apache2][access][response_code]} %{NUMBER:[apache2][access][body_sent][bytes]}( \"%{DATA:[apache2][access][referrer]}\")?( \"%{DATA:[apache2][access][agent]}\")?",
        "%{IPORHOST:[apache2][access][remote_ip]} - %{DATA:[apache2][access][user_name]} \\[%{HTTPDATE:[apache2][access][time]}\\] \"-\" %{NUMBER:[apache2][access][response_code]} -" ] }
        remove_field => "message"
      }
      mutate {
        add_field => { "read_timestamp" => "%{@timestamp}" }
      }
      date {
        match => [ "[apache2][access][time]", "dd/MMM/YYYY:H:m:s Z" ]
        remove_field => "[apache2][access][time]"
      }
      useragent {
        source => "[apache2][access][agent]"
        target => "[apache2][access][user_agent]"
        remove_field => "[apache2][access][agent]"
      }
      geoip {
        source => "[apache2][access][remote_ip]"
        target => "[apache2][access][geoip]"
      }
    }
    else if [fileset][name] == "error" {
      grok {
        match => { "message" => ["\[%{APACHE_TIME:[apache2][error][timestamp]}\] \[%{LOGLEVEL:[apache2][error][level]}\]( \[client %{IPORHOST:[apache2][error][client]}\])? %{GREEDYDATA:[apache2][error][message]}",
        "\[%{APACHE_TIME:[apache2][error][timestamp]}\] \[%{DATA:[apache2][error][module]}:%{LOGLEVEL:[apache2][error][level]}\] \[pid %{NUMBER:[apache2][error][pid]}(:tid %{NUMBER:[apache2][error][tid]})?\]( \[client %{IPORHOST:[apache2][error][client]}\])? %{GREEDYDATA:[apache2][error][message1]}" ] }
        pattern_definitions => {
          "APACHE_TIME" => "%{DAY} %{MONTH} %{MONTHDAY} %{TIME} %{YEAR}"
        }
        remove_field => "message"
      }
      mutate {
        rename => { "[apache2][error][message1]" => "[apache2][error][message]" }
      }
      date {
        match => [ "[apache2][error][timestamp]", "EEE MMM dd H:m:s YYYY", "EEE MMM dd H:m:s.SSSSSS YYYY" ]
        remove_field => "[apache2][error][timestamp]"
      }
    }
  }


  ## syslog, there might be a module for this as well
  if [type] == "syslog" {
    ### "$RepeatedMsgReduction off" /etc/rsyslog.conf
    #if [message] =~ /last message repeated [0-9]+ times/ {
    #  drop { }
    #}
    ## enable high precision timestamps
    # comment out $ActionFileDefaultTemplate RSYSLOG_TraditionalFileFormat
    grok {
      match => { "message" => "(?:%{SYSLOGTIMESTAMP:syslog_timestamp}|%{TIMESTAMP_ISO8601:syslog_timestamp}) %{SYSLOGHOST:syslog_hostname} %{DATA:syslog_program}(?:\[%{POSINT:syslog_pid}\])?: %{GREEDYDATA:syslog_message}" }
      add_field => {
        "syslog_received_at" => "%{@timestamp}"
        "syslog_received_from" => "%{host}"
      }
    }
    syslog_pri {

    }
    date {
      match => [ "syslog_timestamp", "MMM  d HH:mm:ss", "MMM dd HH:mm:ss", "ISO8601" ]
      timezone => "Europe/Madrid"
    }
    mutate {
      replace => { "syslog_timestamp" => "%{@timestamp}" }
    }
    # for check grok data type conversion bug???
    mutate {
      convert => {
        "syslog_pid" => "integer"
      }
    }
  }

  ## old apache filter
  # if [type] == "apache" {
  #   grok {
  #     match => { "message" => "%{COMBINEDAPACHELOG}" }
  #   }
  #   date {
  #     match => [ "timestamp" , "dd/MMM/yyyy:HH:mm:ss Z" ]
  #     timezone => "America/New York"
  #   }
  # }
}

output {
  elasticsearch {
    hosts => ["elasticsearch:9200"]
    index => "apache"
    document_type => "log"
  }
#  stdout { codec => rubydebug }
}