Github user nickwallen commented on a diff in the pull request:
https://github.com/apache/metron/pull/1245#discussion_r237651771
--- Diff:
metron-platform/metron-parsers/src/test/resources/config/RegularExpressionsInvalidParserConfig.json
---
@@ -0,0 +1,208 @@
+{
+ "convertCamelCaseToUnderScore": true,
+ "messageHeaderRegex":
"(?<syslogpriority>(?<=^<)\\d{1,4}(?=>)).*?(?<timestampDeviceOriginal>(?<=>)[A-Za-z]{3}\\s{1,2}\\d{1,2}\\s\\d{1,2}:\\d{1,2}:\\d{1,2}(?=\\s)).*?(?<deviceName>(?<=\\s).*?(?=\\s))",
+ "recordTypeRegex":
"(?<dstProcessName>(?<=\\s)\\b(tch-replicant|audispd|syslog|ntpd|sendmail|pure-ftpd|usermod|useradd|anacron|unix_chkpwd|sudo|dovecot|postfix\\/smtpd|postfix\\/smtp|postfix\\/qmgr|klnagent|systemd|(?i)crond(?-i)|clamd|kesl|sshd|run-parts|automount|suexec|freshclam|kernel|vsftpd|ftpd|su)\\b(?=\\[|:))",
+ "fields": [
+ {
+ "recordType": "syslog",
+ "regex":
".*(?<dstProcessId>(?<=PID\\s=\\s).*?(?=\\sLine)).*(?<filePath>(?<=64\\s)\/([A-Za-z0-9_-]+\/)+(?=\\w))(?<fileName>.*?(?=\")).*(?<eventInfo>(?<=\").*?(?=$))"
+ },
+ {
+ "recordType": "pure-ftpd",
+ "regex":
".*(?<srcUserId>(?<=\\:\\s\\().*?(?=\\)\\s)).*?(?<messageLevel>(?<=\\s\\[).*?(?=\\]\\s)).*?(?<eventInfo>(?<=\\]\\s).*?(?=$))"
+ },
+ {
+ "recordType": "systemd",
+ "regex": [
+
".*(?<eventInfo>(?<=\\ssystemd\\:\\s).*?(?=\\d+)).*?(?<sessionName>(?<=\\sSession\\s).*?(?=\\sof)).*?(?<srcUserId>(?<=\\suser\\s).*?(?=\\.)).*$",
+
".*(?<eventInfo>(?<=\\ssystemd\\:\\s).*?(?=\\sof)).*?(?<srcUserId>(?<=\\sof\\s).*?(?=\\.)).*$"
+ ]
+ },
+ {
+ "recordType": "kesl",
+ "regex": ".*(?<eventInfo>(?<=\\:).*?(?=$))"
+ },
+ {
+ "recordType": "dovecot",
+ "regex": [
+
".*(?<subprocess>(?<=\\sdovecot:\\s).*?(?=\\:)).*?(?<eventInfo>(?<=\\:).*?(?=\\:\\suser)).*?(?<srcUserId>(?<=user\\=\\<).*?(?=\\>)).*?(?<rip>(?<=rip\\=).*?(?=,)).*?(?<lip>(?<=lip\\=).*?(?=,)).*?(?<connectionType>(?<=,\\s).*?(?=,)).*?(?<sessionName>(?<=session\\=\\<).*?(?=\\>)).*$",
+
".*(?<subprocess>(?<=\\sdovecot:\\s).*?(?=\\:)).*?(?<eventInfo>(?<=\\:).*?(?=\\:\\srip)).*?(?<rip>(?<=rip\\=).*?(?=,)).*?(?<lip>(?<=lip\\=).*?(?=,)).*?(?<connectionType>(?<=,\\s).*?(?=$))",
+
".*(?<subprocess>(?<=\\sdovecot:\\s).*?(?=\\:)).*?(?<eventInfo>(?<=\\:).*?(?=$))"
+ ]
+ },
+ {
+ "recordType": "postfix/smtpd",
+ "regex": [
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<eventInfo>(?<=\\:).*?(?=$))",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\]:)).*?(?<eventInfo>(?<=\\:\\s)disconnect(?=\\sfrom)).*?(?<srcHost>(?<=from).*(?=\\[)).*?(?<ipSrcAddr>(?<=\\[).*(?=\\])).*$"
+ ]
+ },
+ {
+ "recordType": "postfix/smtp",
+ "regex": [
+
".*(?<dstProcessId>(?<=smtp\\[).*?(?=\\]:)).*(?<toEmail>(?<=to=#\\<).*?(?=>,)).*(?<relay>(?<=relay=).*?(?=,)).*(?<delay>(?<=delay=).*?(?=,)).*(?<delays>(?<=delays=).*?(?=,)).*(?<dsn>(?<=dsn=).*?(?=,)).*(?<status>(?<=status=).*?(?=\\()).*?(?<dstHost>(?<=connect
to).*?(?=\\[)).*?(?<ipDstAddr>(?<=\\[).*?(?=\\])).*?(?<ipDstPort>(?<=\\]:).*?(?=:\\s)).*?(?<eventInfo>(?<=:\\s).*?(?=$))",
+
".*(?<dstProcessId>(?<=smtp\\[).*?(?=\\]:)).*?(?<dstHost>(?<=connect
to).*?(?=\\[)).*?(?<ipDstAddr>(?<=\\[).*?(?=\\])).*(?<ipDstPort>(?<=:).*?(?=\\s)).*(?<eventInfo>(?<=\\s).*?(?=$))",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<eventInfo>(?<=\\:).*?(?=$))"
+ ]
+ },
+ {
+ "recordType": "crond",
+ "regex": [
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<srcUserId>(?<=\\]:\\s\\().*?(?=\\)\\s)).*?(?<commandLine>(?<=CMD\\s\\().*?(?=\\))).*$",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<srcUserId>(?<=\\]:\\s\\().*?(?=\\)\\s)).*?(?<eventInfo>(?<=\\().*?(?=\\))).*$",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<srcUserId>(?<=\\]:\\s\\().*?(?=\\)\\s)).*?(?<commandLine>(?<=CMD\\s\\().*?(?=\\))).*$",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<eventInfo>(?<=\\:).*?(?=$))"
+ ]
+ },
+ {
+ "recordType": "clamd",
+ "regex": [
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<subProcess>(?<=\\:\\s).*?(?=\\:)).*?(?<eventInfo>(?<=\\:).*?(?=$))",
+
".*(?<subProcess>(?<=\\:\\s).*?(?=\\:)).*?(?<eventInfo>(?<=\\:).*?(?=$))"
+ ]
+ },
+ {
+ "recordType": "run-parts",
+ "regex": ".*(?<eventInfo>(?<=\\sparts).*?(?=$))"
+ },
+ {
+ "recordType": "sshd",
+ "regex": [
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<event_Info>(?<=\\]:\\s).*?(?=\\sfor)).*?(?<dstUserId>(?<=\\sfor\\s).*?(?=\\sfrom)).*?(?<ipSrcAddr>(?<=\\sfrom\\s).*?(?=\\sport)).*?(?<ipSrcPort>(?<=\\sport\\s).*?(?=\\s)).*?(?<appProtocol>(?<=port\\s\\d{1,5}\\s).*(?=:\\s)).*?(?<encryptionAlgorithm>(?<=:\\s).+?(?=\\s)).*(?<correlationId>(?<=\\s).+?(?=$))",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<eventInfo>(?<=\\]:\\s).*?(?=\\sfor)).*?(?<dstUserId>(?<=\\sfor\\s).*?(?=\\sfrom)).*?(?<ipSrcAddr>(?<=\\sfrom\\s).*?(?=\\sport)).*?(?<ipSrcPort>(?<=\\sport\\s).*?(?=\\s)).*?(?<appProtocol>(?<=port\\s\\d{1,5}\\s).*?(?=$))",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<ipDstAddr>(?<=Remote:).*?(?=\\-)).*?(?<ipDstPort>(?<=\\-).*?(?=;)).*?(?<appProtocol>(?<=Protocol:).*?(?=;)).*?(?<sshClient>(?<=Client:).*?(?=$))",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<appProtocol>(?<=\\]:).*?(?=:)).*?(?<ipDstAddr>(?<=Remote:).*?(?=\\-)).*?(?<ipDstPort>(?<=\\-).*?(?=;)).*?(?<encryptionAlgorithm>(?<=Enc:\\s).*?(?=$))",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<ipDstAddr>(?<=Remote:).*?(?=\\-)).*?(?<ipDstPort>(?<=\\-).*?(?=;)).*?(?<encryptionAlgorithm>(?<=Enc:\\s).*?(?=$))",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<eventInfo>(?<=:).*?(?=for)).*?(?<dstUserId>(?<=for).*?(?=from)).*?(?<ipSrcAddr>(?<=from).*?(?=port)).*?(?<ipSrcPort>(?<=port).*?(?=\\s)).*?(?<appProtocol>(?<=\\s).*?(?=$))",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\]))]:\\s.*?(?<eventInfo>subsystem.*?(?=by\\suser)).*?(?<srcUserId>(?<=user).*?(?=$))",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<action>(?<=Received).*?(?=from)).*?(?<ipSrcAddr>(?<=from).*?(?=:)).*?(?<eventInfo>(?<=11:).*?(?=$))",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<eventInfo>(?<=\\]:\\s)Server\\slistening(?=\\s)).*?(?<ipSrcAddr>(?<=\\son\\s).*?(?=port)).*?(?<ipSrcPort>(?<=port\\s)\\d{1,6}(?=\\.)).*$",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<eventInfo>(?<=\\]:\\s)Invalid
user(?=\\s)).*?(?<dstUserId>(?<=\\s).*?(?=from)).*?(?<ipSrcAddr>(?<=from\\s).*(?=$))",
+
".*(?<dstProcessId>(?<=\\[).*?(?=]:\\s)).*(?<subProcess>(?<=]:\\s).*\\)(?=:)).*(?<eventInfo>(?<=:\\s).*(?=;)).*(?<logname>(?<=logname=).*?(?=\\s)).*(?<dstUserId>(?<=uid=).*?(?=\\s)).*(?<effectiveUserId>(?<=euid=).*?(?=\\s)).*(?<sessionName>(?<=tty=).*?(?=\\s)).*(?<srcUserId>(?<=ruser=).*?(?=\\s)).*(?<ipSrcAddr>(?<=rhost=).*?(?=\\s)).*(?<userId>(?<=user=).*?(?=$))",
+
".*(?<dstProcessId>(?<=\\[).*?(?=]:\\s)).*(?<eventInfo>(?<=:\\s).*(?=;)).*(?<logname>(?<=logname=).*?(?=\\s)).*(?<dstUserId>(?<=uid=).*?(?=\\s)).*(?<effectiveUserId>(?<=euid=).*?(?=\\s)).*(?<sessionName>(?<=tty=).*?(?=\\s)).*(?<srcUserId>(?<=ruser=).*?(?=\\s)).*(?<ipSrcAddr>(?<=rhost=).*?(?=\\s)).*(?<userId>(?<=user=).*?(?=$))",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<eventInfo>(?<=\\]:\\s).*?(?=for)).*?(?<dstUserId>(?<=\\sfor).*?(?=\\[)).*?(?<subProcess>(?<=\\[).*?(?=\\])).*$",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<eventInfo>(?<=:\\s)Excess
permission or bad ownership on
file(?=\\s\\/)).*?(?<filePath>(?<=\\s).*(?=\\/)).*?(?<fileName>(?<=\\/).*(?=$))",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<eventInfo>(?<=:).*?(?=;)).*$",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<eventInfo>(?<=:).*?(?=\\d)).*$",
+
".*(?<dstProcessId>(?<=\\[).*?(?=\\])).*?(?<eventInfo>(?<=:).*?(?=$))"
--- End diff --
Help me understand why you need 17 different regular expressions to parse
SSHD records? Is it just that you see it in 17 different forms?
---
