Sync grok patterns with logstash patterns (#50381)

In order to ensure that logstash and Elasticsearch are able to understand
the same patterns, this commit adapts to changes in logstash, adds a few
patterns and changes a few.

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

@@ -277,9 +277,9 @@ public final class Grok {
     private static Map<String, String> loadBuiltinPatterns() throws IOException {
         // Code for loading built-in grok patterns packaged with the jar file:
         String[] PATTERN_NAMES = new String[] {
-            "aws", "bacula", "bro", "exim", "firewalls", "grok-patterns", "haproxy",
-            "java", "junos", "linux-syslog", "mcollective-patterns", "mongodb", "nagios",
-            "postgresql", "rails", "redis", "ruby"
+            "aws", "bacula", "bind", "bro", "exim", "firewalls", "grok-patterns", "haproxy",
+            "java", "junos", "linux-syslog", "maven", "mcollective-patterns", "mongodb", "nagios",
+            "postgresql", "rails", "redis", "ruby", "squid"
         };
         Map<String, String> builtinPatterns = new HashMap<>();
         for (String pattern : PATTERN_NAMES) {

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

@@ -9,3 +9,5 @@ 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}"
+
+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/bind

@@ -0,0 +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} \(%{IP:dns}\)

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

@@ -36,7 +36,7 @@ CISCOFW106006_106007_106010 %{CISCO_ACTION:action} %{CISCO_DIRECTION:direction}
 # ASA-3-106014
 CISCOFW106014 %{CISCO_ACTION:action} %{CISCO_DIRECTION:direction} %{WORD:protocol} src %{DATA:src_interface}:%{IP:src_ip}(\(%{DATA:src_fwuser}\))? dst %{DATA:dst_interface}:%{IP:dst_ip}(\(%{DATA:dst_fwuser}\))? \(type %{INT:icmp_type}, code %{INT:icmp_code}\)
 # ASA-6-106015
-CISCOFW106015 %{CISCO_ACTION:action} %{WORD:protocol} \(%{DATA:policy_id}\) from %{IP:src_ip}/%{INT:src_port} to %{IP:dst_ip}/%{INT:dst_port} flags %{DATA:tcp_flags}  on interface %{GREEDYDATA:interface}
+CISCOFW106015 %{CISCO_ACTION:action} %{WORD:protocol} \(%{DATA:policy_id}\) from %{IP:src_ip}/%{INT:src_port} to %{IP:dst_ip}/%{INT:dst_port} flags %{DATA:tcp_flags} on interface %{GREEDYDATA:interface}
 # ASA-1-106021
 CISCOFW106021 %{CISCO_ACTION:action} %{WORD:protocol} reverse path check from %{IP:src_ip} to %{IP:dst_ip} on interface %{GREEDYDATA:interface}
 # ASA-4-106023
@@ -45,6 +45,8 @@ CISCOFW106023 %{CISCO_ACTION:action}( protocol)? %{WORD:protocol} src %{DATA:src
 CISCOFW106100_2_3 access-list %{NOTSPACE:policy_id} %{CISCO_ACTION:action} %{WORD:protocol} for user '%{DATA:src_fwuser}' %{DATA:src_interface}/%{IP:src_ip}\(%{INT:src_port}\) -> %{DATA:dst_interface}/%{IP:dst_ip}\(%{INT:dst_port}\) hit-cnt %{INT:hit_count} %{CISCO_INTERVAL:interval} \[%{DATA:hashcode1}, %{DATA:hashcode2}\]
 # ASA-5-106100
 CISCOFW106100 access-list %{NOTSPACE:policy_id} %{CISCO_ACTION:action} %{WORD:protocol} %{DATA:src_interface}/%{IP:src_ip}\(%{INT:src_port}\)(\(%{DATA:src_fwuser}\))? -> %{DATA:dst_interface}/%{IP:dst_ip}\(%{INT:dst_port}\)(\(%{DATA:src_fwuser}\))? hit-cnt %{INT:hit_count} %{CISCO_INTERVAL:interval} \[%{DATA:hashcode1}, %{DATA:hashcode2}\]
+# ASA-5-304001
+CISCOFW304001 %{IP:src_ip}(\(%{DATA:src_fwuser}\))? Accessed URL %{IP:dst_ip}:%{GREEDYDATA:dst_url}
 # ASA-6-110002
 CISCOFW110002 %{CISCO_REASON:reason} for %{WORD:protocol} from %{DATA:src_interface}:%{IP:src_ip}/%{INT:src_port} to %{IP:dst_ip}/%{INT:dst_port}
 # ASA-6-302010
@@ -84,3 +86,7 @@ CISCOFW733100 \[\s*%{DATA:drop_type}\s*\] drop %{DATA:drop_rate_id} exceeded. Cu
 # 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}?.*)
 #== 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}.*)|())
+#== End SuSE ==

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

@@ -18,6 +18,8 @@ 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})

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

@@ -1,8 +1,8 @@
 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> method
-JAVAMETHOD (?:(<init>)|[a-zA-Z$_][a-zA-Z$_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

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

@@ -11,6 +11,6 @@ SYSLOGLINE %{SYSLOGBASE2} %{GREEDYDATA:message}
 # IETF 5424 syslog(8) format (see http://www.rfc-editor.org/info/rfc5424)
 SYSLOG5424PRI <%{NONNEGINT:syslog5424_pri}>
 SYSLOG5424SD \[%{DATA}\]+
-SYSLOG5424BASE %{SYSLOG5424PRI}%{NONNEGINT:syslog5424_ver} +(?:%{TIMESTAMP_ISO8601:syslog5424_ts}|-) +(?:%{HOSTNAME:syslog5424_host}|-) +(-|%{SYSLOG5424PRINTASCII:syslog5424_app}) +(-|%{SYSLOG5424PRINTASCII:syslog5424_proc}) +(-|%{SYSLOG5424PRINTASCII:syslog5424_msgid}) +(?:%{SYSLOG5424SD:syslog5424_sd}|-|)
+SYSLOG5424BASE %{SYSLOG5424PRI}%{NONNEGINT:syslog5424_ver} +(?:%{TIMESTAMP_ISO8601:syslog5424_ts}|-) +(?:%{IPORHOST:syslog5424_host}|-) +(-|%{SYSLOG5424PRINTASCII:syslog5424_app}) +(-|%{SYSLOG5424PRINTASCII:syslog5424_proc}) +(-|%{SYSLOG5424PRINTASCII:syslog5424_msgid}) +(?:%{SYSLOG5424SD:syslog5424_sd}|-|)
 
 SYSLOG5424LINE %{SYSLOG5424BASE} +%{GREEDYDATA:syslog5424_msg}

libs/grok/src/main/resources/patterns/maven

@@ -0,0 +1 @@
+MAVEN_VERSION (?:(\d+)\.)?(?:(\d+)\.)?(\*|\d+)(?:[.-](RELEASE|SNAPSHOT))?

libs/grok/src/main/resources/patterns/redis

@@ -1,3 +1,3 @@
 REDISTIMESTAMP %{MONTHDAY} %{MONTH} %{TIME}
 REDISLOG \[%{POSINT:pid}\] %{REDISTIMESTAMP:timestamp} \* 
-
+REDISMONLOG %{NUMBER:timestamp} \[%{INT:database} %{IP:client}:%{NUMBER:port}\] "%{WORD:command}"\s?%{GREEDYDATA:params}

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

@@ -0,0 +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}

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

@@ -152,5 +152,5 @@ teardown:
 "Test Grok Patterns Retrieval":
   - do:
       ingest.processor_grok: {}
-  - length: { patterns: 303 }
+  - length: { patterns: 312 }
   - match: { patterns.PATH: "(?:%{UNIXPATH}|%{WINPATH})" }