Sync grok processor patterns with Logstash (elastic#76752)

libs/grok/build.gradle

@@ -16,6 +16,10 @@ dependencies {
   }
 }
 
+tasks.named("forbiddenPatterns").configure {
+  exclude '**/nagios'
+}
+
 tasks.named('forbiddenApisMain').configure {
   replaceSignatureFiles 'jdk-signatures'
 }

libs/grok/src/main/java/org/elasticsearch/grok/Grok.java

@@ -299,7 +299,7 @@ public List<GrokCaptureConfig> captureConfig() {
     private static Map<String, String> loadBuiltinPatterns() {
         String[] patternNames = new String[] {
             "aws", "bacula", "bind", "bro", "exim", "firewalls", "grok-patterns", "haproxy",
-            "java", "junos", "linux-syslog", "maven", "mcollective-patterns", "mongodb", "nagios",
+            "httpd", "java", "junos", "linux-syslog", "maven", "mcollective-patterns", "mongodb", "nagios",
             "postgresql", "rails", "redis", "ruby", "squid"
         };
         Map<String, String> builtinPatterns = new LinkedHashMap<>();

libs/grok/src/main/resources/patterns/aws

@@ -8,6 +8,6 @@ ELB_URI %{URIPROTO:proto}://(?:%{USER}(?::[^@]*)?@)?(?:%{URIHOST:urihost})?(?:%{
 
 ELB_REQUEST_LINE (?:%{WORD:verb} %{ELB_URI:request}(?: HTTP/%{NUMBER:httpversion})?|%{DATA:rawrequest})
 
-ELB_ACCESS_LOG %{TIMESTAMP_ISO8601:timestamp} %{NOTSPACE:elb} %{IP:clientip}:%{INT:clientport:int} (?:(%{IP:backendip}:?:%{INT:backendport:int})|-) %{NUMBER:request_processing_time:float} %{NUMBER:backend_processing_time:float} %{NUMBER:response_processing_time:float} %{INT:response:int} %{INT:backend_response:int} %{INT:received_bytes:int} %{INT:bytes:int} "%{ELB_REQUEST_LINE}"
+ELB_ACCESS_LOG %{TIMESTAMP_ISO8601:timestamp} %{NOTSPACE:elb} %{IP:clientip}:%{INT:clientport:int} (?:(?:%{IP:backendip}:?:%{INT:backendport:int})|-) %{NUMBER:request_processing_time:float} %{NUMBER:backend_processing_time:float} %{NUMBER:response_processing_time:float} %{INT:response:int} (?:-|%{INT:backend_response:int}) %{INT:received_bytes:int} %{INT:bytes:int} "%{ELB_REQUEST_LINE}"
 
 CLOUDFRONT_ACCESS_LOG (?<timestamp>%{YEAR}-%{MONTHNUM}-%{MONTHDAY}\t%{TIME})\t%{WORD:x_edge_location}\t(?:%{NUMBER:sc_bytes:int}|-)\t%{IPORHOST:clientip}\t%{WORD:cs_method}\t%{HOSTNAME:cs_host}\t%{NOTSPACE:cs_uri_stem}\t%{NUMBER:sc_status:int}\t%{GREEDYDATA:referrer}\t%{GREEDYDATA:agent}\t%{GREEDYDATA:cs_uri_query}\t%{GREEDYDATA:cookies}\t%{WORD:x_edge_result_type}\t%{NOTSPACE:x_edge_request_id}\t%{HOSTNAME:x_host_header}\t%{URIPROTO:cs_protocol}\t%{INT:cs_bytes:int}\t%{GREEDYDATA:time_taken:float}\t%{GREEDYDATA:x_forwarded_for}\t%{GREEDYDATA:ssl_protocol}\t%{GREEDYDATA:ssl_cipher}\t%{GREEDYDATA:x_edge_response_result_type}

libs/grok/src/main/resources/patterns/bacula

@@ -13,9 +13,9 @@ BACULA_LOG_NEW_VOLUME Created new Volume \"%{BACULA_VOLUME:volume}\" in catalog.
 BACULA_LOG_NEW_LABEL Labeled new Volume \"%{BACULA_VOLUME:volume}\" on device \"%{BACULA_DEVICE:device}\" \(%{BACULA_DEVICEPATH}\).
 BACULA_LOG_WROTE_LABEL Wrote label to prelabeled Volume \"%{BACULA_VOLUME:volume}\" on device \"%{BACULA_DEVICE}\" \(%{BACULA_DEVICEPATH}\)
 BACULA_LOG_NEW_MOUNT New volume \"%{BACULA_VOLUME:volume}\" mounted on device \"%{BACULA_DEVICE:device}\" \(%{BACULA_DEVICEPATH}\) at %{MONTHDAY}-%{MONTH}-%{YEAR} %{HOUR}:%{MINUTE}.
-BACULA_LOG_NOOPEN \s+Cannot open %{DATA}: ERR=%{GREEDYDATA:berror}
-BACULA_LOG_NOOPENDIR \s+Could not open directory %{DATA}: ERR=%{GREEDYDATA:berror}
-BACULA_LOG_NOSTAT \s+Could not stat %{DATA}: ERR=%{GREEDYDATA:berror}
+BACULA_LOG_NOOPEN \s*Cannot open %{DATA}: ERR=%{GREEDYDATA:berror}
+BACULA_LOG_NOOPENDIR \s*Could not open directory %{DATA}: ERR=%{GREEDYDATA:berror}
+BACULA_LOG_NOSTAT \s*Could not stat %{DATA}: ERR=%{GREEDYDATA:berror}
 BACULA_LOG_NOJOBS There are no more Jobs associated with Volume \"%{BACULA_VOLUME:volume}\". Marking it purged.
 BACULA_LOG_ALL_RECORDS_PRUNED All records pruned from Volume \"%{BACULA_VOLUME:volume}\"; marking it \"Purged\"
 BACULA_LOG_BEGIN_PRUNE_JOBS Begin pruning Jobs older than %{INT} month %{INT} days .
@@ -41,10 +41,10 @@ BACULA_LOG_DUPLICATE Fatal error: JobId %{INT:duplicate} already running. Duplic
 BACULA_LOG_NOJOBSTAT Fatal error: No Job status returned from FD.
 BACULA_LOG_FATAL_CONN Fatal error: bsock.c:133 Unable to connect to (Client: %{BACULA_HOST:client}|Storage daemon) on %{HOSTNAME}:%{POSINT}. ERR=(?<berror>%{GREEDYDATA})
 BACULA_LOG_NO_CONNECT Warning: bsock.c:127 Could not connect to (Client: %{BACULA_HOST:client}|Storage daemon) on %{HOSTNAME}:%{POSINT}. ERR=(?<berror>%{GREEDYDATA})
-BACULA_LOG_NO_AUTH Fatal error: Unable to authenticate with File daemon at %{HOSTNAME}. Possible causes:
+BACULA_LOG_NO_AUTH Fatal error: Unable to authenticate with File daemon at %{DATA}. Possible causes:
 BACULA_LOG_NOSUIT No prior or suitable Full backup found in catalog. Doing FULL backup.
 BACULA_LOG_NOPRIOR No prior Full backup Job record found.
 
 BACULA_LOG_JOB (Error: )?Bacula %{BACULA_HOST} %{BACULA_VERSION} \(%{BACULA_VERSION}\):
 
-BACULA_LOGLINE %{BACULA_TIMESTAMP:bts} %{BACULA_HOST:hostname} JobId %{INT:jobid}: (%{BACULA_LOG_MAX_CAPACITY}|%{BACULA_LOG_END_VOLUME}|%{BACULA_LOG_NEW_VOLUME}|%{BACULA_LOG_NEW_LABEL}|%{BACULA_LOG_WROTE_LABEL}|%{BACULA_LOG_NEW_MOUNT}|%{BACULA_LOG_NOOPEN}|%{BACULA_LOG_NOOPENDIR}|%{BACULA_LOG_NOSTAT}|%{BACULA_LOG_NOJOBS}|%{BACULA_LOG_ALL_RECORDS_PRUNED}|%{BACULA_LOG_BEGIN_PRUNE_JOBS}|%{BACULA_LOG_BEGIN_PRUNE_FILES}|%{BACULA_LOG_PRUNED_JOBS}|%{BACULA_LOG_PRUNED_FILES}|%{BACULA_LOG_ENDPRUNE}|%{BACULA_LOG_STARTJOB}|%{BACULA_LOG_STARTRESTORE}|%{BACULA_LOG_USEDEVICE}|%{BACULA_LOG_DIFF_FS}|%{BACULA_LOG_JOBEND}|%{BACULA_LOG_NOPRUNE_JOBS}|%{BACULA_LOG_NOPRUNE_FILES}|%{BACULA_LOG_VOLUME_PREVWRITTEN}|%{BACULA_LOG_READYAPPEND}|%{BACULA_LOG_CANCELLING}|%{BACULA_LOG_MARKCANCEL}|%{BACULA_LOG_CLIENT_RBJ}|%{BACULA_LOG_VSS}|%{BACULA_LOG_MAXSTART}|%{BACULA_LOG_DUPLICATE}|%{BACULA_LOG_NOJOBSTAT}|%{BACULA_LOG_FATAL_CONN}|%{BACULA_LOG_NO_CONNECT}|%{BACULA_LOG_NO_AUTH}|%{BACULA_LOG_NOSUIT}|%{BACULA_LOG_JOB}|%{BACULA_LOG_NOPRIOR})
+BACULA_LOGLINE %{BACULA_TIMESTAMP:bts} %{BACULA_HOST:hostname}(?: JobId %{INT:jobid})?:? (%{BACULA_LOG_MAX_CAPACITY}|%{BACULA_LOG_END_VOLUME}|%{BACULA_LOG_NEW_VOLUME}|%{BACULA_LOG_NEW_LABEL}|%{BACULA_LOG_WROTE_LABEL}|%{BACULA_LOG_NEW_MOUNT}|%{BACULA_LOG_NOOPEN}|%{BACULA_LOG_NOOPENDIR}|%{BACULA_LOG_NOSTAT}|%{BACULA_LOG_NOJOBS}|%{BACULA_LOG_ALL_RECORDS_PRUNED}|%{BACULA_LOG_BEGIN_PRUNE_JOBS}|%{BACULA_LOG_BEGIN_PRUNE_FILES}|%{BACULA_LOG_PRUNED_JOBS}|%{BACULA_LOG_PRUNED_FILES}|%{BACULA_LOG_ENDPRUNE}|%{BACULA_LOG_STARTJOB}|%{BACULA_LOG_STARTRESTORE}|%{BACULA_LOG_USEDEVICE}|%{BACULA_LOG_DIFF_FS}|%{BACULA_LOG_JOBEND}|%{BACULA_LOG_NOPRUNE_JOBS}|%{BACULA_LOG_NOPRUNE_FILES}|%{BACULA_LOG_VOLUME_PREVWRITTEN}|%{BACULA_LOG_READYAPPEND}|%{BACULA_LOG_CANCELLING}|%{BACULA_LOG_MARKCANCEL}|%{BACULA_LOG_CLIENT_RBJ}|%{BACULA_LOG_VSS}|%{BACULA_LOG_MAXSTART}|%{BACULA_LOG_DUPLICATE}|%{BACULA_LOG_NOJOBSTAT}|%{BACULA_LOG_FATAL_CONN}|%{BACULA_LOG_NO_CONNECT}|%{BACULA_LOG_NO_AUTH}|%{BACULA_LOG_NOSUIT}|%{BACULA_LOG_JOB}|%{BACULA_LOG_NOPRIOR})

libs/grok/src/main/resources/patterns/bind

@@ -1,3 +1,3 @@
 BIND9_TIMESTAMP %{MONTHDAY}[-]%{MONTH}[-]%{YEAR} %{TIME}
 
-BIND9 %{BIND9_TIMESTAMP:timestamp} queries: %{LOGLEVEL:loglevel}: client %{IP:clientip}#%{POSINT:clientport} \(%{GREEDYDATA:query}\): query: %{GREEDYDATA:query} IN %{GREEDYDATA:querytype} \(%{IP:dns}\)
+BIND9 %{BIND9_TIMESTAMP:timestamp} queries: %{LOGLEVEL:loglevel}: client(:? @0x(?:[0-9A-Fa-f]+))? %{IP:clientip}#%{POSINT:clientport} \(%{GREEDYDATA:query}\): query: %{GREEDYDATA:query} IN %{GREEDYDATA:querytype} \(%{IP:dns}\)

libs/grok/src/main/resources/patterns/exim

@@ -1,13 +1,19 @@
 EXIM_MSGID [0-9A-Za-z]{6}-[0-9A-Za-z]{6}-[0-9A-Za-z]{2}
 EXIM_FLAGS (<=|[-=>*]>|[*]{2}|==)
 EXIM_DATE %{YEAR:exim_year}-%{MONTHNUM:exim_month}-%{MONTHDAY:exim_day} %{TIME:exim_time}
-EXIM_PID \[%{POSINT}\]
+EXIM_PID \[%{POSINT:pid}\]
 EXIM_QT ((\d+y)?(\d+w)?(\d+d)?(\d+h)?(\d+m)?(\d+s)?)
 EXIM_EXCLUDE_TERMS (Message is frozen|(Start|End) queue run| Warning: | retry time not reached | no (IP address|host name) found for (IP address|host) | unexpected disconnection while reading SMTP command | no immediate delivery: |another process is handling this message)
-EXIM_REMOTE_HOST (H=(%{NOTSPACE:remote_hostname} )?(\(%{NOTSPACE:remote_heloname}\) )?\[%{IP:remote_host}\])
+EXIM_REMOTE_HOST (H=(%{NOTSPACE:remote_hostname} )?(\(%{NOTSPACE:remote_heloname}\) )?\[%{IP:remote_host}\])(?::%{POSINT:remote_port})?
 EXIM_INTERFACE (I=\[%{IP:exim_interface}\](:%{NUMBER:exim_interface_port}))
 EXIM_PROTOCOL (P=%{NOTSPACE:protocol})
 EXIM_MSG_SIZE (S=%{NUMBER:exim_msg_size})
 EXIM_HEADER_ID (id=%{NOTSPACE:exim_header_id})
 EXIM_SUBJECT (T=%{QS:exim_subject})
 
+EXIM_UNKNOWN_FIELD (?:[A-Za-z0-9]{1,4}=%{NOTSPACE})
+EXIM_NAMED_FIELDS (?: (?:%{EXIM_REMOTE_HOST}|%{EXIM_INTERFACE}|%{EXIM_PROTOCOL}|%{EXIM_MSG_SIZE}|%{EXIM_HEADER_ID}|%{EXIM_SUBJECT}|%{EXIM_UNKNOWN_FIELD}))*
+
+EXIM_MESSAGE_ARRIVAL %{EXIM_DATE:timestamp} (?:%{EXIM_PID} )?%{EXIM_MSGID:exim_msgid} (?<exim_flags><=) (?<exim_status>[a-z:] )?%{EMAILADDRESS:exim_sender_email}%{EXIM_NAMED_FIELDS}(?: for %{EMAILADDRESS:exim_recipient_email})?
+
+EXIM %{EXIM_MESSAGE_ARRIVAL}

libs/grok/src/main/resources/patterns/firewalls

@@ -84,9 +84,8 @@ CISCOFW733100 \[\s*%{DATA:drop_type}\s*\] drop %{DATA:drop_rate_id} exceeded. Cu
 #== End Cisco ASA ==
 
 # Shorewall firewall logs
-SHOREWALL (%{SYSLOGTIMESTAMP:timestamp}) (%{WORD:nf_host}) kernel:.*Shorewall:(%{WORD:nf_action1})?:(%{WORD:nf_action2})?.*IN=(%{USERNAME:nf_in_interface})?.*(OUT= *MAC=(%{COMMONMAC:nf_dst_mac}):(%{COMMONMAC:nf_src_mac})?|OUT=%{USERNAME:nf_out_interface}).*SRC=(%{IPV4:nf_src_ip}).*DST=(%{IPV4:nf_dst_ip}).*LEN=(%{WORD:nf_len}).?*TOS=(%{WORD:nf_tos}).?*PREC=(%{WORD:nf_prec}).?*TTL=(%{INT:nf_ttl}).?*ID=(%{INT:nf_id}).?*PROTO=(%{WORD:nf_protocol}).?*SPT=(%{INT:nf_src_port}?.*DPT=%{INT:nf_dst_port}?.*)
+SHOREWALL (%{SYSLOGTIMESTAMP:timestamp}) (%{WORD:nf_host}) .*Shorewall:(%{WORD:nf_action1})?:(%{WORD:nf_action2})?.*IN=(%{USERNAME:nf_in_interface})?.*(OUT= *MAC=(%{COMMONMAC:nf_dst_mac}):(%{COMMONMAC:nf_src_mac})?|OUT=%{USERNAME:nf_out_interface}).*SRC=(%{IPV4:nf_src_ip}).*DST=(%{IPV4:nf_dst_ip}).*LEN=(%{WORD:nf_len}).?*TOS=(%{WORD:nf_tos}).?*PREC=(%{WORD:nf_prec}).?*TTL=(%{INT:nf_ttl}).?*ID=(%{INT:nf_id}).?*PROTO=(%{WORD:nf_protocol}).?*SPT=(%{INT:nf_src_port}?.*DPT=%{INT:nf_dst_port}?.*)
 #== End Shorewall
-
 #== SuSE Firewall 2 ==
-SFW2 ((%{SYSLOGTIMESTAMP})|(%{TIMESTAMP_ISO8601}))\s*%{HOSTNAME}\s*kernel\S+\s*%{NAGIOSTIME}\s*SFW2\-INext\-%{NOTSPACE:nf_action}\s*IN=%{USERNAME:nf_in_interface}.*OUT=((\s*%{USERNAME:nf_out_interface})|(\s*))MAC=((%{COMMONMAC:nf_dst_mac}:%{COMMONMAC:nf_src_mac})|(\s*)).*SRC=%{IP:nf_src_ip}\s*DST=%{IP:nf_dst_ip}.*PROTO=%{WORD:nf_protocol}((.*SPT=%{INT:nf_src_port}.*DPT=%{INT:nf_dst_port}.*)|())
+SFW2 ((%{SYSLOGTIMESTAMP:timestamp})|(%{TIMESTAMP_ISO8601:timestamp}))\s*%{HOSTNAME}\s*kernel\S+\s*(?:%{NAGIOSTIME}\s*)?SFW2\-INext\-%{NOTSPACE:nf_action}\s*IN=%{USERNAME:nf_in_interface}.*OUT=(\s*%{USERNAME:nf_out_interface})?\s*MAC=((%{COMMONMAC:nf_dst_mac}:%{COMMONMAC:nf_src_mac})|(\s*)).*SRC=%{IP:nf_src_ip}\s*DST=%{IP:nf_dst_ip}.*PROTO=%{WORD:nf_protocol}((.*SPT=%{INT:nf_src_port}.*DPT=%{INT:nf_dst_port}.*)|())
 #== End SuSE ==

libs/grok/src/main/resources/patterns/grok-patterns

@@ -2,7 +2,6 @@ USERNAME [a-zA-Z0-9._-]+
 USER %{USERNAME}
 EMAILLOCALPART [a-zA-Z][a-zA-Z0-9_.+-=:]+
 EMAILADDRESS %{EMAILLOCALPART}@%{HOSTNAME}
-HTTPDUSER %{EMAILADDRESS}|%{USER}
 INT (?:[+-]?(?:[0-9]+))
 BASE10NUM (?<![0-9.+-])(?>[+-]?(?:(?:[0-9]+(?:\.[0-9]+)?)|(?:\.[0-9]+)))
 NUMBER (?:%{BASE10NUM})
@@ -78,7 +77,6 @@ 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}
-HTTPDERROR_DATE %{DAY} %{MONTH} %{MONTHDAY} %{TIME} %{YEAR}
 
 # Syslog Dates: Month Day HH:MM:SS
 SYSLOGTIMESTAMP %{MONTH} +%{MONTHDAY} %{TIME}
@@ -93,11 +91,6 @@ QS %{QUOTEDSTRING}
 
 # Log formats
 SYSLOGBASE %{SYSLOGTIMESTAMP:timestamp} (?:%{SYSLOGFACILITY} )?%{SYSLOGHOST:logsource} %{SYSLOGPROG}:
-COMMONAPACHELOG %{IPORHOST:clientip} %{HTTPDUSER:ident} %{USER:auth} \[%{HTTPDATE:timestamp}\] "(?:%{WORD:verb} %{NOTSPACE:request}(?: HTTP/%{NUMBER:httpversion})?|%{DATA:rawrequest})" %{NUMBER:response} (?:%{NUMBER:bytes}|-)
-COMBINEDAPACHELOG %{COMMONAPACHELOG} %{QS:referrer} %{QS:agent}
-HTTPD20_ERRORLOG \[%{HTTPDERROR_DATE:timestamp}\] \[%{LOGLEVEL:loglevel}\] (?:\[client %{IPORHOST:clientip}\] ){0,1}%{GREEDYDATA:errormsg}
-HTTPD24_ERRORLOG \[%{HTTPDERROR_DATE:timestamp}\] \[(%{WORD:module})?:%{LOGLEVEL:loglevel}\] \[pid %{POSINT:pid}(:tid %{NUMBER:tid})?\]( \(%{POSINT:proxy_errorcode}\)%{DATA:proxy_errormessage}:)?( \[client %{IPORHOST:client}:%{POSINT:clientport}\])?( %{DATA:errorcode}:)? %{GREEDYDATA:message}
-HTTPD_ERRORLOG %{HTTPD20_ERRORLOG}|%{HTTPD24_ERRORLOG}
 
 
 # Log Levels

libs/grok/src/main/resources/patterns/haproxy

@@ -31,7 +31,7 @@ HAPROXYCAPTUREDRESPONSEHEADERS %{DATA:captured_response_headers}
 # HAPROXYCAPTUREDRESPONSEHEADERS %{DATA:response_header_content_type}\|%{DATA:response_header_content_encoding}\|%{DATA:response_header_cache_control}\|%{DATA:response_header_last_modified}
 
 # parse a haproxy 'httplog' line
-HAPROXYHTTPBASE %{IP:client_ip}:%{INT:client_port} \[%{HAPROXYDATE:accept_date}\] %{NOTSPACE:frontend_name} %{NOTSPACE:backend_name}/%{NOTSPACE:server_name} %{INT:time_request}/%{INT:time_queue}/%{INT:time_backend_connect}/%{INT:time_backend_response}/%{NOTSPACE:time_duration} %{INT:http_status_code} %{NOTSPACE:bytes_read} %{DATA:captured_request_cookie} %{DATA:captured_response_cookie} %{NOTSPACE:termination_state} %{INT:actconn}/%{INT:feconn}/%{INT:beconn}/%{INT:srvconn}/%{NOTSPACE:retries} %{INT:srv_queue}/%{INT:backend_queue} (\{%{HAPROXYCAPTUREDREQUESTHEADERS}\})?( )?(\{%{HAPROXYCAPTUREDRESPONSEHEADERS}\})?( )?"(<BADREQ>|(%{WORD:http_verb} (%{URIPROTO:http_proto}://)?(?:%{USER:http_user}(?::[^@]*)?@)?(?:%{URIHOST:http_host})?(?:%{URIPATHPARAM:http_request})?( HTTP/%{NUMBER:http_version})?))?"
+HAPROXYHTTPBASE %{IP:client_ip}:%{INT:client_port} \[%{HAPROXYDATE:accept_date}\] %{NOTSPACE:frontend_name} %{NOTSPACE:backend_name}/%{NOTSPACE:server_name} %{INT:time_request}/%{INT:time_queue}/%{INT:time_backend_connect}/%{INT:time_backend_response}/%{NOTSPACE:time_duration} %{INT:http_status_code} %{NOTSPACE:bytes_read} %{DATA:captured_request_cookie} %{DATA:captured_response_cookie} %{NOTSPACE:termination_state} %{INT:actconn}/%{INT:feconn}/%{INT:beconn}/%{INT:srvconn}/%{NOTSPACE:retries} %{INT:srv_queue}/%{INT:backend_queue} (\{%{HAPROXYCAPTUREDREQUESTHEADERS}\})?( )?(\{%{HAPROXYCAPTUREDRESPONSEHEADERS}\})?( )?"(<BADREQ>|(%{WORD:http_verb} (%{URIPROTO:http_proto}://)?(?:%{USER:http_user}(?::[^@]*)?@)?(?:%{URIHOST:http_host})?(?:%{URIPATHPARAM:http_request})?( HTTP/%{NUMBER:http_version})?))?"?
 
 HAPROXYHTTP (?:%{SYSLOGTIMESTAMP:syslog_timestamp}|%{TIMESTAMP_ISO8601:timestamp8601}) %{IPORHOST:syslog_server} %{SYSLOGPROG}: %{HAPROXYHTTPBASE}
 

libs/grok/src/main/resources/patterns/httpd

@@ -0,0 +1,15 @@
+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}

libs/grok/src/main/resources/patterns/java

@@ -1,13 +1,12 @@
 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_. -]+)
+JAVAFILE (?:[a-zA-Z$_0-9. -]+)
 #Allow special <init>, <clinit> methods
 JAVAMETHOD (?:(<(?:cl)?init>)|[a-zA-Z$_][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]+)
-JAVASTACKTRACEPART at %{JAVACLASS:class}\.%{WORD:method}\(%{JAVAFILE:file}:%{NUMBER:line}\)
 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)

libs/grok/src/main/resources/patterns/nagios

@@ -6,10 +6,10 @@
 # While it does not, this set intends to cover all possible Nagios logs.
 #
 # Some more work needs to be done to cover all External Commands:
-# http://old.nagios.org/developerinfo/externalcommands/commandlist.php
+#	http://old.nagios.org/developerinfo/externalcommands/commandlist.php
 #
 # If you need some support on these rules please contact:
-# Jelle Smet http://smetj.net
+#	Jelle Smet http://smetj.net
 #
 #################################################################################
 #################################################################################
@@ -89,7 +89,7 @@ NAGIOS_PASSIVE_HOST_CHECK %{NAGIOS_TYPE_PASSIVE_HOST_CHECK:nagios_type}: %{DATA:
 NAGIOS_SERVICE_EVENT_HANDLER %{NAGIOS_TYPE_SERVICE_EVENT_HANDLER:nagios_type}: %{DATA:nagios_hostname};%{DATA:nagios_service};%{DATA:nagios_state};%{DATA:nagios_statelevel};%{DATA:nagios_event_handler_name}
 NAGIOS_HOST_EVENT_HANDLER %{NAGIOS_TYPE_HOST_EVENT_HANDLER:nagios_type}: %{DATA:nagios_hostname};%{DATA:nagios_state};%{DATA:nagios_statelevel};%{DATA:nagios_event_handler_name}
 
-NAGIOS_TIMEPERIOD_TRANSITION %{NAGIOS_TYPE_TIMEPERIOD_TRANSITION:nagios_type}: %{DATA:nagios_service};%{DATA:nagios_unknown1};%{DATA:nagios_unknown2}
+NAGIOS_TIMEPERIOD_TRANSITION %{NAGIOS_TYPE_TIMEPERIOD_TRANSITION:nagios_type}: %{DATA:nagios_service};%{NUMBER:nagios_unknown1};%{NUMBER:nagios_unknown2}
 
 ####################
 #### External checks

libs/grok/src/main/resources/patterns/squid

@@ -1,4 +1,4 @@
 # Pattern squid3
 # Documentation of squid3 logs formats can be found at the following link:
 # http://wiki.squid-cache.org/Features/LogFormat
-SQUID3 %{NUMBER:timestamp}\s+%{NUMBER:duration}\s%{IP:client_address}\s%{WORD:cache_result}/%{POSINT:status_code}\s%{NUMBER:bytes}\s%{WORD:request_method}\s%{NOTSPACE:url}\s(%{NOTSPACE:user}|-)\s%{WORD:hierarchy_code}/%{IPORHOST:server}\s%{NOTSPACE:content_type}
+SQUID3 %{NUMBER:timestamp}\s+%{NUMBER:duration}\s%{IP:client_address}\s%{WORD:cache_result}/%{NONNEGINT:status_code}\s%{NUMBER:bytes}\s%{WORD:request_method}\s%{NOTSPACE:url}\s(%{NOTSPACE:user}|-)\s%{WORD:hierarchy_code}/(%{IPORHOST:server}|-)\s%{NOTSPACE:content_type}

modules/ingest-common/build.gradle

@@ -47,3 +47,9 @@ tasks.named("thirdPartyAudit").configure {
 tasks.named("transformV7RestTests").configure({ task ->
   task.addAllowedWarningRegex("\\[types removal\\].*")
 })
+
+tasks.named("yamlRestCompatTest").configure {
+  systemProperty 'tests.rest.blacklist', ([
+    'ingest/120_grok/Test Grok Patterns Retrieval' // un-mute this test after backporting
+  ]).join(',')
+}

modules/ingest-common/src/yamlRestTest/resources/rest-api-spec/test/ingest/120_grok.yml

@@ -152,5 +152,5 @@ teardown:
 "Test Grok Patterns Retrieval":
   - do:
       ingest.processor_grok: {}
-  - length: { patterns: 312 }
+  - length: { patterns: 318 }
   - match: { patterns.PATH: "(?:%{UNIXPATH}|%{WINPATH})" }