# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(?<timestamp>[^ ]*)\.(?<time_microseconds>\d*)\+[^ ]+ (?<host>[^ ]*) postgres\[(?<pid>\d*)\]: \[(?<groupid>[^ ]\d*)-(?<lineid>[^ ]\d*)\](?<message>.*)$"
test_str = ("2017-03-21T03:01:32.627434+00:00 ec317 postgres[82271]: [134-1] 2017-03-21 03:01:32 UTC [82271]: [2-1] user=unknown db=[unknown] LOG: incomplete startup packet\n"
"2017-03-21T03:01:32.761669+00:00 ec317 postgres[82270]: [135-1] 2017-03-21 03:01:32 UTC [82270]: [3-1] user=gz_kettle,db=greenzone LOG: disconnection: session time: 0:00:00.182 user=gz_kettle database=greenzone host=172.26.27.22 port=35849\n"
"2017-03-21T03:01:32.800403+00:00 ec317 postgres[82272]: [133-1] 2017-03-21 03:01:32 UTC [82272]: [1-1] user=[unknown],db=[unknown] LOG: connection received: host=172.26.27.22 port=35850\n"
"2017-03-21T03:01:32.801596+00:00 ec317 postgres[82272]: [134-1] 2017-03-21 03:01:32 UTC [82272]: [2-1] user=gz_kettle,db=greenzone LOG: connection authorized: user=gz_kettle database=greenzone")
matches = re.finditer(regex, test_str, re.MULTILINE)
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