Logstash經常使用正則表達式

grok-patterns

USERNAME [a-zA-Z0-9._-]+
USER %{USERNAME}
EMAILLOCALPART [a-zA-Z][a-zA-Z0-9_.+-=:]+
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
PATH (?:%{UNIXPATH}|%{WINPATH})
UNIXPATH (/([\w_%!$@:.,+~-]+|\\.)*)+
TTY (?:/dev/(pts|tty([pq])?)(\w+)?/?(?:[0-9]+))
WINPATH (?>[A-Za-z]+:|\\)(?:\\[^\\?*]*)+
URIPROTO [A-Za-z]([A-Za-z0-9+\-.]+)+
URIHOST %{IPORHOST}(?::%{POSINT:port})?
# uripath comes loosely from RFC1738, but mostly from what Firefox
# doesn't turn into %XX
URIPATH (?:/[A-Za-z0-9$.+!*'(){},~:;=@#%&_\-]*)+
#URIPARAM \?(?:[A-Za-z0-9]+(?:=(?:[^&]*))?(?:&(?:[A-Za-z0-9]+(?:=(?:[^&]*))?)?)*)?
URIPARAM \?[A-Za-z0-9$.+!*'|(){},~@#%&/=:;_?\-\[\]<>]*
URIPATHPARAM %{URIPATH}(?:%{URIPARAM})?
URI %{URIPROTO}://(?:%{USER}(?::[^@]*)?@)?(?:%{URIHOST})?(?:%{URIPATHPARAM})?

# 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)?|[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}|60)
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:program}(?:\[%{POSINT:pid}\])?
SYSLOGHOST %{IPORHOST}
SYSLOGFACILITY <%{NONNEGINT:facility}.%{NONNEGINT:priority}>
HTTPDATE %{MONTHDAY}/%{MONTH}/%{YEAR}:%{TIME} %{INT}

# Shortcuts
QS %{QUOTEDSTRING}

# Log formats
SYSLOGBASE %{SYSLOGTIMESTAMP:timestamp} (?:%{SYSLOGFACILITY} )?%{SYSLOGHOST:logsource} %{SYSLOGPROG}:

# Log Levels
LOGLEVEL ([Aa]lert|ALERT|[Tt]race|TRACE|[Dd]ebug|DEBUG|[Nn]otice|NOTICE|[Ii]nfo|INFO|[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)?)

httpd

HTTPDUSER %{EMAILADDRESS}|%{USER}
HTTPDERROR_DATE %{DAY} %{MONTH} %{MONTHDAY} %{TIME} %{YEAR}

# Log formats
HTTPD_COMMONLOG %{IPORHOST:clientip} %{HTTPDUSER:ident} %{HTTPDUSER:auth} \[%{HTTPDATE:timestamp}\] "(?:%{WORD:verb} %{NOTSPACE:request}(?: HTTP/%{NUMBER:httpversion})?|%{DATA:rawrequest})" %{NUMBER:response} (?:%{NUMBER:bytes}|-)
HTTPD_COMBINEDLOG %{HTTPD_COMMONLOG} %{QS:referrer} %{QS:agent}

# Error logs
HTTPD20_ERRORLOG \[%{HTTPDERROR_DATE:timestamp}\] \[%{LOGLEVEL:loglevel}\] (?:\[client %{IPORHOST:clientip}\] ){0,1}%{GREEDYDATA:message}
HTTPD24_ERRORLOG \[%{HTTPDERROR_DATE:timestamp}\] \[%{WORD:module}:%{LOGLEVEL:loglevel}\] \[pid %{POSINT:pid}(:tid %{NUMBER:tid})?\]( \(%{POSINT:proxy_errorcode}\)%{DATA:proxy_message}:)?( \[client %{IPORHOST:clientip}:%{POSINT:clientport}\])?( %{DATA:errorcode}:)? %{GREEDYDATA:message}
HTTPD_ERRORLOG %{HTTPD20_ERRORLOG}|%{HTTPD24_ERRORLOG}

# Deprecated
COMMONAPACHELOG %{HTTPD_COMMONLOG}
COMBINEDAPACHELOG %{HTTPD_COMBINEDLOG}

java

JAVACLASS (?:[a-zA-Z$_][a-zA-Z$_0-9]*\.)*[a-zA-Z$_][a-zA-Z$_0-9]*
#Space is an allowed character to match special cases like 'Native Method' or 'Unknown Source'
JAVAFILE (?:[A-Za-z0-9_. -]+)
#Allow special <init>, <clinit> methods
JAVAMETHOD (?:(<(?:cl)?init>)|[a-zA-Z$_][a-zA-Z$_0-9]*)
#Line number is optional in special cases 'Native method' or 'Unknown source'
JAVASTACKTRACEPART %{SPACE}at %{JAVACLASS:class}\.%{JAVAMETHOD:method}\(%{JAVAFILE:file}(?::%{NUMBER:line})?\)
# Java Logs
JAVATHREAD (?:[A-Z]{2}-Processor[\d]+)
JAVACLASS (?:[a-zA-Z0-9-]+\.)+[A-Za-z0-9$]+
JAVAFILE (?:[A-Za-z0-9_.-]+)
JAVALOGMESSAGE (.*)
# MMM dd, yyyy HH:mm:ss eg: Jan 9, 2014 7:13:13 AM
CATALINA_DATESTAMP %{MONTH} %{MONTHDAY}, 20%{YEAR} %{HOUR}:?%{MINUTE}(?::?%{SECOND}) (?:AM|PM)
# yyyy-MM-dd HH:mm:ss,SSS ZZZ eg: 2014-01-09 17:32:25,527 -0800
TOMCAT_DATESTAMP 20%{YEAR}-%{MONTHNUM}-%{MONTHDAY} %{HOUR}:?%{MINUTE}(?::?%{SECOND}) %{ISO8601_TIMEZONE}
CATALINALOG %{CATALINA_DATESTAMP:timestamp} %{JAVACLASS:class} %{JAVALOGMESSAGE:logmessage}
# 2014-01-09 20:03:28,269 -0800 | ERROR | com.example.service.ExampleService - something compeletely unexpected happened...
TOMCATLOG %{TOMCAT_DATESTAMP:timestamp} \| %{LOGLEVEL:level} \| %{JAVACLASS:class} - %{JAVALOGMESSAGE:logmessage}

轉自：logstash-patterns-core