datedetector: extended default date-patterns (allows extra space between the date and time stamps);

* introduces 2 new format directives (with corresponding `%Ex` prefix for more precise parsing):
  - %k - one- or two-digit number giving the hour of the day (0-23) on a 24-hour clock,
   (corresponds %H, but allows space if not zero-padded).
  - %l - one- or two-digit number giving the hour of the day (12-11) on a 12-hour clock,
   (corresponds %I, but allows space if not zero-padded).
* mysqld-auth test extended to cover new date-format in log.
Closes gh-1639
pull/1981/head
sebres 2017-11-30 17:06:37 +01:00
parent fbf89e8cdd
commit 2e437937c3
3 changed files with 24 additions and 12 deletions

View File

@ -124,22 +124,22 @@ class DateDetectorCache(object):
"""
self.__tmpcache = [], []
# ISO 8601, simple date, optional subsecond and timezone:
# 2005-01-23T21:59:59.981746, 2005-01-23 21:59:59
# 2005-01-23T21:59:59.981746, 2005-01-23 21:59:59, 2005-01-23 8:59:59
# simple date: 2005/01/23 21:59:59
# custom for syslog-ng 2006.12.21 06:43:20
self._cacheTemplate("%ExY(?P<_sep>[-/.])%m(?P=_sep)%d[T ]%H:%M:%S(?:[.,]%f)?(?:\s*%z)?")
self._cacheTemplate("%ExY(?P<_sep>[-/.])%m(?P=_sep)%d(?:T| ?)%H:%M:%S(?:[.,]%f)?(?:\s*%z)?")
# asctime with optional day, subsecond and/or year:
# Sun Jan 23 21:59:59.011 2005
self._cacheTemplate("(?:%a )?%b %d %H:%M:%S(?:\.%f)?(?: %ExY)?")
self._cacheTemplate("(?:%a )?%b %d %k:%M:%S(?:\.%f)?(?: %ExY)?")
# asctime with optional day, subsecond and/or year coming after day
# http://bugs.debian.org/798923
# Sun Jan 23 2005 21:59:59.011
self._cacheTemplate("(?:%a )?%b %d %ExY %H:%M:%S(?:\.%f)?")
self._cacheTemplate("(?:%a )?%b %d %ExY %k:%M:%S(?:\.%f)?")
# simple date too (from x11vnc): 23/01/2005 21:59:59
# and with optional year given by 2 digits: 23/01/05 21:59:59
# (See http://bugs.debian.org/537610)
# 17-07-2008 17:23:25
self._cacheTemplate("%d(?P<_sep>[-/])%m(?P=_sep)(?:%ExY|%Exy) %H:%M:%S")
self._cacheTemplate("%d(?P<_sep>[-/])%m(?P=_sep)(?:%ExY|%Exy) %k:%M:%S")
# Apache format optional time zone:
# [31/Oct/2006:09:22:55 -0000]
# 26-Jul-2007 15:20:52
@ -150,8 +150,8 @@ class DateDetectorCache(object):
self._cacheTemplate("%m/%d/%ExY:%H:%M:%S")
# 01-27-2012 16:22:44.252
# subseconds explicit to avoid possible %m<->%d confusion
# with previous ("%d-%m-%ExY %H:%M:%S" by "%d(?P<_sep>[-/])%m(?P=_sep)(?:%ExY|%Exy) %H:%M:%S")
self._cacheTemplate("%m-%d-%ExY %H:%M:%S(?:\.%f)?")
# with previous ("%d-%m-%ExY %k:%M:%S" by "%d(?P<_sep>[-/])%m(?P=_sep)(?:%ExY|%Exy) %k:%M:%S")
self._cacheTemplate("%m-%d-%ExY %k:%M:%S(?:\.%f)?")
# Epoch
self._cacheTemplate('EPOCH')
# Only time information in the log
@ -163,14 +163,14 @@ class DateDetectorCache(object):
# Apache Tomcat
self._cacheTemplate("%b %d, %ExY %I:%M:%S %p")
# ASSP: Apr-27-13 02:33:06
self._cacheTemplate("^%b-%d-%Exy %H:%M:%S")
# 20050123T215959, 20050123 215959
self._cacheTemplate("%ExY%Exm%Exd[T ]%ExH%ExM%ExS(?:[.,]%f)?(?:\s*%z)?")
self._cacheTemplate("^%b-%d-%Exy %k:%M:%S")
# 20050123T215959, 20050123 215959, , 20050123 85959
self._cacheTemplate("%ExY%Exm%Exd(?:T| ?)%ExH%ExM%ExS(?:[.,]%f)?(?:\s*%z)?")
# prefixed with optional named time zone (monit):
# PDT Apr 16 21:05:29
self._cacheTemplate("(?:%Z )?(?:%a )?%b %d %H:%M:%S(?:\.%f)?(?: %ExY)?")
self._cacheTemplate("(?:%Z )?(?:%a )?%b %d %k:%M:%S(?:\.%f)?(?: %ExY)?")
# +00:00 Jan 23 21:59:59.011 2005
self._cacheTemplate("(?:%z )?(?:%a )?%b %d %H:%M:%S(?:\.%f)?(?: %ExY)?")
self._cacheTemplate("(?:%z )?(?:%a )?%b %d %k:%M:%S(?:\.%f)?(?: %ExY)?")
# TAI64N
self._cacheTemplate("TAI64N")
#

View File

@ -43,6 +43,13 @@ def _getYearCentRE(cent=(0,3), distance=3, now=(MyTime.now(), MyTime.alternateNo
timeRE = TimeRE()
# %k - one- or two-digit number giving the hour of the day (0-23) on a 24-hour clock,
# (corresponds %H, but allows space if not zero-padded).
# %l - one- or two-digit number giving the hour of the day (12-11) on a 12-hour clock,
# (corresponds %I, but allows space if not zero-padded).
timeRE['k'] = r" ?(?P<H>[0-2]?\d)"
timeRE['l'] = r" ?(?P<I>1?\d)"
# TODO: because python currently does not support mixing of case-sensitive with case-insensitive matching,
# check how TZ (in uppercase) can be combined with %a/%b etc. (that are currently case-insensitive),
# to avoid invalid date-time recognition in strings like '11-Aug-2013 03:36:11.372 error ...'
@ -61,6 +68,8 @@ timeRE['Exz'] = r"(?P<z>(?:%s)?[+-][01]\d(?::?\d{2})?|%s)" % (TZ_ABBR_RE, TZ_ABB
timeRE['Exd'] = r"(?P<d>3[0-1]|[1-2]\d|0[1-9])"
timeRE['Exm'] = r"(?P<m>1[0-2]|0[1-9])"
timeRE['ExH'] = r"(?P<H>2[0-3]|[0-1]\d)"
timeRE['Exk'] = r" ?(?P<H>2[0-3]|[0-1]\d|\d)"
timeRE['Exl'] = r" ?(?P<I>1[0-2]|\d)"
timeRE['ExM'] = r"(?P<M>[0-5]\d)"
timeRE['ExS'] = r"(?P<S>6[0-1]|[0-5]\d)"
# more precise year patterns, within same century of last year and

View File

@ -17,6 +17,9 @@ Sep 16 21:30:32 catinthehat mysqld: 130916 21:30:32 [Warning] Access denied for
# failJSON: { "time": "2015-10-07T06:09:42", "match": true , "host": "127.0.0.1", "desc": "mysql 5.6 log format" }
2015-10-07 06:09:42 5907 [Warning] Access denied for user 'root'@'127.0.0.1' (using password: YES)
# failJSON: { "time": "2015-10-07T08:25:38", "match": true , "host": "192.0.2.1", "desc": "log format with extra space between the date and time stamps, gh-1639" }
2015-10-07 8:25:38 139845235329792 [Warning] Access denied for user 'user'@'192.0.2.1' (using password: YES)
# failJSON: { "time": "2016-02-24T15:26:18", "match": true , "host": "localhost", "desc": "mysql 5.6 log format, Note instead of Warning" }
2016-02-24T15:26:18.237955 6 [Note] Access denied for user 'root'@'localhost' (using password: YES)