# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
^\s*
# date
(?<date>\d{4}-\d{2}-\d{2}\s+\d{2}:\d{2}:\d{2})
# facility.severity
\s(?<facility>\S+)\.(?<severity>\S+)
# server
\s(?<server>\S*)
# date
\s(?<otherDate>\d{4}-\d{2}-\d{2}:\s\d{2}:\d{2}:\d{2})
# time zone
\s(?<timeZone>\S*)
# ip address
\s(?<ip>\S*)
# legacy email address
\s(?<legacyEmailAddress>\S*)
# first name
\s(?|"(?<firstName>[^"\n]+)"|(?<firstName>\S*))
# last name
\s(?|"(?<lastName>[^"\n]+)"|(?<lastName>\S*))
# account number
\s(?<account>\S*)
# program code
\s(?<programCode>\S*)
# uid
\s(?<uid>\S*)
# email address
\s(?<emailAddress>\S*)
# event type
\s(?<eventType>\S*)
# source
\s(?<source>\S*)
# category
\s(?<category>\S*)
\s*$
"""
test_str = ("2016-01-29 18:19:54 local1.info server.domain.com 2016-01-29: 11:19:54 MST UNKNOWN UNKNOWN FOO \"BAR BAZ\" UNKNOWN UNKNOWN UNKNOWN EMAIL@EXAMPLE.COM PROFILE_CHANGE ProfileChangeProcessor A\n"
"2016-01-29 18:20:25 local4.info server.domain.com 2016-01-29: 11:20:25 MST UNKNOWN UNKNOWN \"F B\" BAZ ABC12345 GP SOME_UID EMAIL@EXAMPLE.COM EVENT_FROM_SOME_PROCESS UNKNOWN UNKNOWN\n"
"2016-01-29 18:23:10 local1.info server.domain.com 2016-01-29: 11:23:10 MST UNKNOWN UNKNOWN FOO BAR UNKNOWN UNKNOWN UNKNOWN EMAIL@EXAMPLE.COM SOME_CHANGE ProfileChangeProcessor AP\n"
"2016-01-29 18:26:24 local1.info server.domain.com 2016-01-29: 11:26:24 MST UNKNOWN EMAIL@EXAMPLE.COM FOO \"B'Baz\" UNKNOWN UNKNOWN UNKNOWN SOME_CHANGE ProfileChangeProcessor O\n"
"2016-01-29 18:26:55 local1.info server.domain.com 2016-01-29: 11:26:55 MST UNKNOWN EMAIL@EXAMPLE.COM \"FOO OR BAR\" BAZ SXR12646 GP UNKNOWN SOME_CHANGE ProfileChangeProcessor M")
matches = re.finditer(regex, test_str, re.MULTILINE | re.VERBOSE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html