# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?P<timestamp>[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}.[0-9]{6}Z) ? ? ? ? ? ?(?P<connID>[0-9]+) (?P<name>[a-zA-Z]+) (?P<sqltext>[^\n]+)"
test_str = ("---my SQL--- \n\n"
"2018-03-31T15:38:44.521650Z 2356 Query SELECT c FROM sbtest1 WHERE id=164802\n"
"2018-03-31T15:38:44.521790Z 2356 Query SELECT c FROM sbtest1 WHERE id BETWEEN 95241 AND 95340\n"
"2018-03-31T15:38:44.522168Z 2356 Query SELECT SUM(k) FROM sbtest1 WHERE id BETWEEN 1 AND 100\n"
"2018-03-31T15:38:44.522500Z 2356 Query SELECT c FROM sbtest1 WHERE id BETWEEN 304556 AND 304655 ORDER BY c\n"
"2018-03-31T15:38:44.522941Z 2356 Query SELECT DISTINCT c FROM sbtest1 WHERE id BETWEEN 924 AND 1023 ORDER BY c\n"
"2018-03-31T15:38:44.523525Z 2356 Query UPDATE sbtest1 SET k=k+1 WHERE id=514")
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