nginx_access_ingest.json

{
    "description": "Pipeline for parsing Nginx access logs. Requires the geoip and user_agent plugins.",
    "processors": [
        {
            "grok": {
                "field": "message",
                "patterns": [
                    "\"?(?:%{IP_LIST:nginx.access.remote_ip_list}|%{DATA:source.address}) - %{DATA:user.name} \\[%{HTTPDATE:nginx.access.time}\\] \"%{DATA:nginx.access.info}\" %{NUMBER:http.response.status_code:long} %{NUMBER:http.response.body.bytes:long} \"%{DATA:http.request.referrer}\" \"%{DATA:user_agent.original}\"\\s?(?<message_postfix>.*)"
                ],
                "pattern_definitions": {
                    "IP_LIST": "%{IP}(\"?,?\\s*%{IP})*"
                },
                "ignore_missing": true
            }
        },
        {
            "grok": {
                "field": "nginx.access.info",
                "patterns": [
                    "%{WORD:http.request.method} %{DATA:url.original} HTTP/%{NUMBER:http.version}",
                    ""
                ],
                "ignore_missing": true
            }
        },
        {
            "remove": {
                "field": "nginx.access.info"
            }
        },
        {
            "split": {
                "field": "nginx.access.remote_ip_list",
                "separator": "\"?,?\\s+",
                "ignore_missing": true
            }
        },
        {
            "split": {
                "field": "nginx.access.origin",
                "separator": "\"?,?\\s+",
                "ignore_missing": true
            }
        },
        {
            "set": {
                "field": "source.ip",
                "value": ""
            }
        },
        {
            "script": {
                "lang": "painless",
                "source": "boolean isPrivate(def dot, def ip) { try { StringTokenizer tok = new StringTokenizer(ip, dot); int firstByte = Integer.parseInt(tok.nextToken());       int secondByte = Integer.parseInt(tok.nextToken());       if (firstByte == 10) {         return true;       }       if (firstByte == 192 && secondByte == 168) {         return true;       }       if (firstByte == 172 && secondByte >= 16 && secondByte <= 31) {         return true;       }       if (firstByte == 127) {         return true;       }       return false;     } catch (Exception e) {       return false;     }   }   try {    ctx.source.ip = null;    if (ctx.nginx.access.remote_ip_list == null) { return; }    def found = false;    for (def item : ctx.nginx.access.remote_ip_list) {        if (!isPrivate(params.dot, item)) {            ctx.source.ip = item;            found = true;            break;        }    }    if (!found) {     ctx.source.ip = ctx.nginx.access.remote_ip_list[0];   }} catch (Exception e) { ctx.source.ip = null; }",
                "params": {
                    "dot": "."
                }
            }
        },
        {
            "remove": {
                "field": "source.ip",
                "if": "ctx.source.ip == null"
            }
        },
        {
            "convert": {
                "field": "source.ip",
                "target_field": "source.address",
                "type": "string",
                "ignore_missing": true
            }
        },
        {
            "rename": {
                "field": "@timestamp",
                "target_field": "event.created"
            }
        },
        {
            "date": {
                "field": "nginx.access.time",
                "target_field": "@timestamp",
                "formats": [
                    "dd/MMM/yyyy:H:m:s Z"
                ],
                {< if .convert_timezone >}"timezone": "{{ event.timezone }}",{< end >}
                "ignore_failure": true
            }
        },
        {
            "remove": {
                "field": "nginx.access.time"
            }
        },
        {
            "user_agent": {
                "field": "user_agent.original"
            }
        },
        {
            "geoip": {
                "field": "source.ip",
                "target_field": "source.geo",
                "ignore_missing": true
            }
        },
        {
            "kv": {
                "field": "message_postfix",
                "field_split": " ",
                "value_split": "=",
                "prefix": "http.request.",
                "ignore_missing": true
            }
        },
        {
            "remove": {
                "field": "message_postfix"
            }
        }
    ],
    "on_failure": [
        {
            "set": {
                "field": "error.message",
                "value": "{{ _ingest.on_failure_message }}"
            }
        }
    ]
}