Github user merrimanr commented on a diff in the pull request: https://github.com/apache/incubator-metron/pull/308#discussion_r83230626 --- Diff: metron-platform/metron-parsers/src/main/config/zookeeper/parsers/websphere.json --- @@ -3,7 +3,7 @@ "sensorTopic":"websphere", "parserConfig": { - "grokPath":"/patterns/websphere", + "grokPattern":"# Days - two digit number is used\nDAY \\d{1,2}\n# Time - two digit hour, minute, and second\nTIME \\d{2}:\\d{2}:\\d{2}\n# Timestamp - month, day, and time\nTIMESTAMP %{MONTH:UNWANTED}\\s+%{DAY:UNWANTED} %{TIME:UNWANTED}\n# Generic word field\nWORD \\w+\n# Priority\nPRIORITY \\d+\n# Log start - the first part of the log line\nLOGSTART <%{PRIORITY:priority}>?%{TIMESTAMP:timestamp_string} %{WORD:hostname}\n# Security domain\nSECURITY_DOMAIN [%{WORD:security_domain}]\n# Log middle - the middle part of the log line\nLOGMIDDLE (\\[%{WORD:security_domain}\\])?\\[%{WORD:event_code}\\]\\[%{WORD:event_type}\\]\\[%{WORD:severity}\\]\n# Define IP address formats\nIPV6 ((([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}))|:)))(%.+)?\nIPV4 (?<![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])\nIP (?:%{IPV6:UNWANTED}|%{IPV4:UNWANTED})\n# Message - the message body of the log\nMESSAGE .*\n# WebSphere - the entire log message\nWEBSPHERE %{LOGSTART:UNWANTED} %{LOGMIDDLE:UNWANTED} %{MESSAGE:message}", --- End diff -- I like that idea but it's a significant increase in scope for this PR. When Grok patterns were kept in HDFS files you couldn't reuse or share them either so as far as I know there has not been a regression. This should be a separate follow on Jira in my opinion.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. ---