• Logstash—Filter模块grok


    一种将非机构化数据转换为结构化数据

    1.grok格式

    %{SYNTAX:SEMANTIC}
    # SYNTAX:匹配数据的模式(正则)名称
    # SEMANTIC:标识或字段名称

    2.相关参数

    filter {
        grok {
            add_field:增加数据
            add_tag:增加tag
            break_on_match:true 第一个匹配成功结束
            keep_empty_captures:true 保存空的事件字段
            match:匹配有值的字段
            named_captures_only:true 使用grok模式定义的字段
            overwrite:覆盖字段的值
            pattern_dir:目录
            pattern_files_glob:如果设置了目录,则用来选择目录中所有的文件
            periodic_flush:规定时间内周期调用flush方法
            remove_field:移除字段
            remove_tag:移除tag
            tag_on_failure:无法匹配则弹出tag出错
            tag_on_timeout:超时则产生新的tag
            timeout_millis:超时中断正则表达式
        }
    }
    ###################################################################
    filter {
        grok {
            add_field=>{"current_time"=>""%{@timestamp}}
            match=>{"message"=>"%{CISCOTIMESTAMP:timestmap}%{HOST:host} %{WORD:program}:\[%{NUMBER:duration}]%{GREEDYDATA:log}"}
            remove_field=>["host"]
            remove_tag=>["grok","test"]
        }
    }
    

    3.正则表达式库Oniguruma

    https://github.com/logstash-plugins/logstash-patterns-core/blob/main/patterns/ecs-v1/grok-patterns

    USERNAME [a-zA-Z0-9._-]+
    USER %{USERNAME}
    EMAILLOCALPART [a-zA-Z0-9!#$%&'*+\-/=?^_`{|}~]{1,64}(?:\.[a-zA-Z0-9!#$%&'*+\-/=?^_`{|}~]{1,62}){0,63}
    EMAILADDRESS %{EMAILLOCALPART}@%{HOSTNAME}
    INT (?:[+-]?(?:[0-9]+))
    BASE10NUM (?<![0-9.+-])(?>[+-]?(?:(?:[0-9]+(?:\.[0-9]+)?)|(?:\.[0-9]+)))
    NUMBER (?:%{BASE10NUM})
    BASE16NUM (?<![0-9A-Fa-f])(?:[+-]?(?:0x)?(?:[0-9A-Fa-f]+))
    BASE16FLOAT \b(?<![0-9A-Fa-f.])(?:[+-]?(?:0x)?(?:(?:[0-9A-Fa-f]+(?:\.[0-9A-Fa-f]*)?)|(?:\.[0-9A-Fa-f]+)))\b
    
    POSINT \b(?:[1-9][0-9]*)\b
    NONNEGINT \b(?:[0-9]+)\b
    WORD \b\w+\b
    NOTSPACE \S+
    SPACE \s*
    DATA .*?
    GREEDYDATA .*
    QUOTEDSTRING (?>(?<!\\)(?>"(?>\\.|[^\\"]+)+"|""|(?>'(?>\\.|[^\\']+)+')|''|(?>`(?>\\.|[^\\`]+)+`)|``))
    UUID [A-Fa-f0-9]{8}-(?:[A-Fa-f0-9]{4}-){3}[A-Fa-f0-9]{12}
    # URN, allowing use of RFC 2141 section 2.3 reserved characters
    URN urn:[0-9A-Za-z][0-9A-Za-z-]{0,31}:(?:%[0-9a-fA-F]{2}|[0-9A-Za-z()+,.:=@;$_!*'/?#-])+
    
    # Networking
    MAC (?:%{CISCOMAC}|%{WINDOWSMAC}|%{COMMONMAC})
    CISCOMAC (?:(?:[A-Fa-f0-9]{4}\.){2}[A-Fa-f0-9]{4})
    WINDOWSMAC (?:(?:[A-Fa-f0-9]{2}-){5}[A-Fa-f0-9]{2})
    COMMONMAC (?:(?:[A-Fa-f0-9]{2}:){5}[A-Fa-f0-9]{2})
    IPV6 ((([0-9A-Fa-f]{1,4}:){7}([0-9A-Fa-f]{1,4}|:))|(([0-9A-Fa-f]{1,4}:){6}(:[0-9A-Fa-f]{1,4}|((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3})|:))|(([0-9A-Fa-f]{1,4}:){5}(((:[0-9A-Fa-f]{1,4}){1,2})|:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3})|:))|(([0-9A-Fa-f]{1,4}:){4}(((:[0-9A-Fa-f]{1,4}){1,3})|((:[0-9A-Fa-f]{1,4})?:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){3}(((:[0-9A-Fa-f]{1,4}){1,4})|((:[0-9A-Fa-f]{1,4}){0,2}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){2}(((:[0-9A-Fa-f]{1,4}){1,5})|((:[0-9A-Fa-f]{1,4}){0,3}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){1}(((:[0-9A-Fa-f]{1,4}){1,6})|((:[0-9A-Fa-f]{1,4}){0,4}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(:(((:[0-9A-Fa-f]{1,4}){1,7})|((:[0-9A-Fa-f]{1,4}){0,5}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:)))(%.+)?
    IPV4 (?<![0-9])(?:(?:[0-1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])[.](?:[0-1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])[.](?:[0-1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5])[.](?:[0-1]?[0-9]{1,2}|2[0-4][0-9]|25[0-5]))(?![0-9])
    IP (?:%{IPV6}|%{IPV4})
    HOSTNAME \b(?:[0-9A-Za-z][0-9A-Za-z-]{0,62})(?:\.(?:[0-9A-Za-z][0-9A-Za-z-]{0,62}))*(\.?|\b)
    IPORHOST (?:%{IP}|%{HOSTNAME})
    HOSTPORT %{IPORHOST}:%{POSINT}
    
    # paths (only absolute paths are matched)
    PATH (?:%{UNIXPATH}|%{WINPATH})
    UNIXPATH (/[[[:alnum:]]_%!$@:.,+~-]*)+
    TTY (?:/dev/(pts|tty([pq])?)(\w+)?/?(?:[0-9]+))
    WINPATH (?>[A-Za-z]+:|\\)(?:\\[^\\?*]*)+
    URIPROTO [A-Za-z]([A-Za-z0-9+\-.]+)+
    URIHOST %{IPORHOST}(?::%{POSINT})?
    # uripath comes loosely from RFC1738, but mostly from what Firefox doesn't turn into %XX
    URIPATH (?:/[A-Za-z0-9$.+!*'(){},~:;=@#%&_\-]*)+
    URIQUERY [A-Za-z0-9$.+!*'|(){},~@#%&/=:;_?\-\[\]<>]*
    # deprecated (kept due compatibility):
    URIPARAM \?%{URIQUERY}
    URIPATHPARAM %{URIPATH}(?:\?%{URIQUERY})?
    URI %{URIPROTO}://(?:%{USER}(?::[^@]*)?@)?(?:%{URIHOST})?(?:%{URIPATH}(?:\?%{URIQUERY})?)?
    
    # Months: January, Feb, 3, 03, 12, December
    MONTH \b(?:[Jj]an(?:uary|uar)?|[Ff]eb(?:ruary|ruar)?|[Mm](?:a|ä)?r(?:ch|z)?|[Aa]pr(?:il)?|[Mm]a(?:y|i)?|[Jj]un(?:e|i)?|[Jj]ul(?:y|i)?|[Aa]ug(?:ust)?|[Ss]ep(?:tember)?|[Oo](?:c|k)?t(?:ober)?|[Nn]ov(?:ember)?|[Dd]e(?:c|z)(?:ember)?)\b
    MONTHNUM (?:0?[1-9]|1[0-2])
    MONTHNUM2 (?:0[1-9]|1[0-2])
    MONTHDAY (?:(?:0[1-9])|(?:[12][0-9])|(?:3[01])|[1-9])
    
    # Days: Monday, Tue, Thu, etc...
    DAY (?:Mon(?:day)?|Tue(?:sday)?|Wed(?:nesday)?|Thu(?:rsday)?|Fri(?:day)?|Sat(?:urday)?|Sun(?:day)?)
    
    # Years?
    YEAR (?>\d\d){1,2}
    HOUR (?:2[0123]|[01]?[0-9])
    MINUTE (?:[0-5][0-9])
    # '60' is a leap second in most time standards and thus is valid.
    SECOND (?:(?:[0-5]?[0-9]|60)(?:[:.,][0-9]+)?)
    TIME (?!<[0-9])%{HOUR}:%{MINUTE}(?::%{SECOND})(?![0-9])
    # datestamp is YYYY/MM/DD-HH:MM:SS.UUUU (or something like it)
    DATE_US %{MONTHNUM}[/-]%{MONTHDAY}[/-]%{YEAR}
    DATE_EU %{MONTHDAY}[./-]%{MONTHNUM}[./-]%{YEAR}
    ISO8601_TIMEZONE (?:Z|[+-]%{HOUR}(?::?%{MINUTE}))
    ISO8601_SECOND %{SECOND}
    TIMESTAMP_ISO8601 %{YEAR}-%{MONTHNUM}-%{MONTHDAY}[T ]%{HOUR}:?%{MINUTE}(?::?%{SECOND})?%{ISO8601_TIMEZONE}?
    DATE %{DATE_US}|%{DATE_EU}
    DATESTAMP %{DATE}[- ]%{TIME}
    TZ (?:[APMCE][SD]T|UTC)
    DATESTAMP_RFC822 %{DAY} %{MONTH} %{MONTHDAY} %{YEAR} %{TIME} %{TZ}
    DATESTAMP_RFC2822 %{DAY}, %{MONTHDAY} %{MONTH} %{YEAR} %{TIME} %{ISO8601_TIMEZONE}
    DATESTAMP_OTHER %{DAY} %{MONTH} %{MONTHDAY} %{TIME} %{TZ} %{YEAR}
    DATESTAMP_EVENTLOG %{YEAR}%{MONTHNUM2}%{MONTHDAY}%{HOUR}%{MINUTE}%{SECOND}
    
    # Syslog Dates: Month Day HH:MM:SS
    SYSLOGTIMESTAMP %{MONTH} +%{MONTHDAY} %{TIME}
    PROG [\x21-\x5a\x5c\x5e-\x7e]+
    SYSLOGPROG %{PROG:[process][name]}(?:\[%{POSINT:[process][pid]:int}\])?
    SYSLOGHOST %{IPORHOST}
    SYSLOGFACILITY <%{NONNEGINT:[log][syslog][facility][code]:int}.%{NONNEGINT:[log][syslog][priority]:int}>
    HTTPDATE %{MONTHDAY}/%{MONTH}/%{YEAR}:%{TIME} %{INT}
    
    # Shortcuts
    QS %{QUOTEDSTRING}
    
    # Log formats
    SYSLOGBASE %{SYSLOGTIMESTAMP:timestamp} (?:%{SYSLOGFACILITY} )?%{SYSLOGHOST:[host][hostname]} %{SYSLOGPROG}:
    
    # Log Levels
    LOGLEVEL ([Aa]lert|ALERT|[Tt]race|TRACE|[Dd]ebug|DEBUG|[Nn]otice|NOTICE|[Ii]nfo?(?:rmation)?|INFO?(?:RMATION)?|[Ww]arn?(?:ing)?|WARN?(?:ING)?|[Ee]rr?(?:or)?|ERR?(?:OR)?|[Cc]rit?(?:ical)?|CRIT?(?:ICAL)?|[Ff]atal|FATAL|[Ss]evere|SEVERE|EMERG(?:ENCY)?|[Ee]merg(?:ency)?)

    4.在线校验

    http://grokdebug.herokuapp.com/

    http://www.5axxw.com/tools/v2/grok.html

    5.例子


    日志行

    Log flie:Jun 19 02:11:30 This is a sample log.

    grok

    %{CISCOTIMESTAMP:timestmap} %{GREEDYDATA:log}

    结果:

    {
      "timestmap": [
        [
          "Jun 19 02:11:30"
        ]
      ],
      "MONTH": [
        [
          "Jun"
        ]
      ],
      "MONTHDAY": [
        [
          "19"
        ]
      ],
      "YEAR": [
        [
          null
        ]
      ],
      "TIME": [
        [
          "02:11:30"
        ]
      ],
      "HOUR": [
        [
          "02"
        ]
      ],
      "MINUTE": [
        [
          "11"
        ]
      ],
      "SECOND": [
        [
          "30"
        ]
      ],
      "log": [
        [
          "This is a sample log."
        ]
      ]
    }

    6.常用 表达式

    主机、ip、路径
    HOSTNAME 主机名称
    IPORHOST IP或者主机名称
    HOSTPORT 主机名(IP)+端口,如: 127.0.0.1:3306、api.stozen.NET:8000
    MAC MAC地址
    IP IP地址,IPv4或IPv6地址,比如:127.0.0.1、FE80:0000:0000:0000:AAAA:0000:00C2:0002等
    PATH 路径,Unix系统或者Windows系统里的路径格式,比如:/usr/xxx、c:\windows\xxx等
    字符串、数字
    USERNAME 或 USER \w+,比如:1234、Bob、Alex.Wong等
    WORD \b\w+\b,比如:String、3529345、ILoveYou等
    EMAILLOCALPART [a-zA-Z][a-zA-Z0-9_.+-=:]+
    EMAILADDRESS 电子邮件,%{EMAILLOCALPART}@%{HOSTNAME},比如:stone@abc.com、等
    BASE10NUM 十进制数字,包括整数和小数,比如:0、18、5.23等
    NUMBER 十进制数字,包括整数和小数,比如:0、18、5.23等
    BASE16NUM 十六进制数字,整数,比如:0x0045fa2d、-0x3F8709等
    BASE16FLOAT 十六进制数字,整数和小数
    WORD 字符串,包括数字和大小写字母,比如:String、3529345、ILoveYou等
    NOTSPACE 不带任何空格的字符串
    SPACE 空格字符串
    QUOTEDSTRING 或 QS 带引号的字符串,比如:"This is an apple"、'What is your name?'等
    UUID 标准UUID,比如:550E8400-E29B-11D4-A716-446655440000
    时间日期
    MONTH 月份名称,比如:Jan、January等
    MONTHNUM 月份数字,比如:03、9、12等
    MONTHDAY 日期数字,比如:03、9、31等
    DAY 星期几名称,比如:Mon、Monday等
    YEAR 年份数字
    HOUR 小时数字
    MINUTE 分钟数字
    SECOND 秒数字
    TIME 时间,比如:00:01:23
    DATE_US 美国日期格式,比如:10-15-1982、10/15/1982等
    DATE_EU 欧洲日期格式,比如:15-10-1982、15/10/1982、15.10.1982等
    DATE 日期,美国日期%{DATE_US}或者欧洲日期%{DATE_EU}
    ISO8601_TIMEZONE ISO8601时间格式,比如:+10:23、-1023等
    TIMESTAMP_ISO8601 ISO8601时间戳格式,比如:2016-07-03T00:34:06+08:00
    DATESTAMP 完整日期+时间,比如:07-03-2016 00:34:06
    HTTPDATE http默认日期格式,比如:03/Jul/2016:00:36:53 +0800
    LOGLEVEL 日志等级,比如:Alert、alert、ALERT、Error等
    HTTP
    URIPROTO URI协议,比如:http、ftp等
    URIHOST URI主机,比如:www.stozen.net、10.0.0.1:22等
    URIPATH URI路径,比如://www.stozen.Net/abc/、/api.PHP等
    URI 完整的URI,比如:http://www.stozen.net/abc/api.php?a=1&b=2&c=3
    URIPARAM URI里的GET参数,比如:?a=1&b=2&c=3
    URIPATHPARAM URI路径+GET参数,比如://www.stozen.net/abc/api.php?a=1&b=2&c=3
  • 相关阅读:
    Django 请求生命周期
    Django views.py中的 FBV(函数) CBV(类)
    cookie session
    Django admin
    Django ORM QuerySet集合对象的特性
    Django ORM 多对多操作 使用聚合函数和分组 F查询与Q查询
    Django ORM 一对多操作
    Django ORM 单表操作
    Django 模板 template
    css之background-clip: text
  • 原文地址:https://www.cnblogs.com/wuyuan2011woaini/p/16086960.html
Copyright © 2020-2023  润新知