elasticsearch相关日志解析匹配正则表达式

Posted 2021-02-10 qinghe123

USERNAME [a-zA-Z0-9._-]+
USER %{USERNAME}
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 (?<![0-9A-Fa-f.])(?:[+-]?(?:0x)?(?:(?:[0-9A-Fa-f]+(?:.[0-9A-Fa-f]*)?)|(?:.[0-9A-Fa-f]+)))

POSINT (?:[1-9][0-9]*)
NONNEGINT (?:[0-9]+)
WORD w+
NOTSPACE S+
SPACE s*
DATA .*?
GREEDYDATA .*
QUOTEDSTRING (?>(?<!\)(?>"(?>\.|[^\"]+)+"|""|(?>‘(?>\.|[^\‘]+)+‘)|‘‘|(?>`(?>\.|[^\`]+)+`)|``))
UUID [A-Fa-f0-9]{8}-(?:[A-Fa-f0-9]{4}-){3}[A-Fa-f0-9]{12}

# 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|1dd|[1-9]?d)(.(25[0-5]|2[0-4]d|1dd|[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|1dd|[1-9]?d)(.(25[0-5]|2[0-4]d|1dd|[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|1dd|[1-9]?d)(.(25[0-5]|2[0-4]d|1dd|[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|1dd|[1-9]?d)(.(25[0-5]|2[0-4]d|1dd|[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|1dd|[1-9]?d)(.(25[0-5]|2[0-4]d|1dd|[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|1dd|[1-9]?d)(.(25[0-5]|2[0-4]d|1dd|[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|1dd|[1-9]?d)(.(25[0-5]|2[0-4]d|1dd|[1-9]?d)){3}))|:)))(%.+)?
IPV4 (?<![0-9])(?:(?:25[0-5]|2[0-4][0-9]|[0-1]?[0-9]{1,2})[.](?:25[0-5]|2[0-4][0-9]|[0-1]?[0-9]{1,2})[.](?:25[0-5]|2[0-4][0-9]|[0-1]?[0-9]{1,2})[.](?:25[0-5]|2[0-4][0-9]|[0-1]?[0-9]{1,2}))(?![0-9])
IP (?:%{IPV6}|%{IPV4})
HOSTNAME (?:[0-9A-Za-z][0-9A-Za-z-]{0,62})(?:.(?:[0-9A-Za-z][0-9A-Za-z-]{0,62}))*(.?|)
HOST %{HOSTNAME}
IPORHOST (?:%{HOSTNAME}|%{IP})
HOSTPORT %{IPORHOST}:%{POSINT}

# paths
PATH (?:%{UNIXPATH}|%{WINPATH})
UNIXPATH (?>/(?>[w_%[email protected]:.,-]+|\.)*)+
TTY (?:/dev/(pts|tty([pq])?)(w+)?/?(?:[0-9]+))
WINPATH (?>[A-Za-z]+:|\)(?:\[^\?*]*)+
URIPROTO [A-Za-z]+(+[A-Za-z+]+)?
URIHOST %{IPORHOST}(?::%{POSINT:port})?
# uripath comes loosely from RFC1738, but mostly from what Firefox
# doesn‘t turn into %XX
URIPATH (?:/[A-Za-z0-9$.+!*‘(){},~:;[email protected]#%_-]*)+
#URIPARAM ?(?:[A-Za-z0-9]+(?:=(?:[^&]*))?(?:&(?:[A-Za-z0-9]+(?:=(?:[^&]*))?)?)*)?
URIPARAM ?[A-Za-z0-9$.+!*‘|(){},[email protected]#%&/=:;_?-[]]*
URIPATHPARAM %{URIPATH}(?:%{URIPARAM})?
URI %{URIPROTO}://(?:%{USER}(?::[^@]*)[email protected])?(?:%{URIHOST})?(?:%{URIPATHPARAM})?

# Months: January, Feb, 3, 03, 12, December
MONTH (?:Jan(?:uary)?|Feb(?:ruary)?|Mar(?:ch)?|Apr(?:il)?|May|Jun(?:e)?|Jul(?:y)?|Aug(?:ust)?|Sep(?:tember)?|Oct(?:ober)?|Nov(?:ember)?|Dec(?:ember)?)
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 (?>dd){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 (?:[PMCE][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 (?:[w._/%-]+)
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}:
COMMONAPACHELOG %{IPORHOST:clientip} %{USER:ident} %{USER:auth} [%{HTTPDATE:timestamp}] "(?:%{WORD:verb} %{NOTSPACE:request}(?: HTTP/%{NUMBER:httpversion})?|%{DATA:rawrequest})" %{NUMBER:response} (?:%{NUMBER:bytes}|-)
COMBINEDAPACHELOG %{COMMONAPACHELOG} %{QS:referrer} %{QS:agent}

# Log Levels
LOGLEVEL ([A|a]lert|ALERT|[T|t]race|TRACE|[D|d]ebug|DEBUG|[N|n]otice|NOTICE|[I|i]nfo|INFO|[W|w]arn?(?:ing)?|WARN?(?:ING)?|[E|e]rr?(?:or)?|ERR?(?:OR)?|[C|c]rit?(?:ical)?|CRIT?(?:ICAL)?|[F|f]atal|FATAL|[S|s]evere|SEVERE|EMERG(?:ENCY)?|[Ee]merg(?:ency)?)

#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]+)
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}