# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(?:SELECT\s+([\s\S]+?)(?=\s+INTO\s+|\s+FROM|$))(?:.*?\s+INTO\s+([\S]+)\s*)?(?:\s+FROM\s+)([\s\S]+?)(?=\s+WHERE\s+|\s+GROUP\sBY\s+|\s+HAVING\s+|\s+ORDER\sBY|$)(?:.*?\s+WHERE\s+([\s\S]+?)(?=\s+GROUP\sBY\s+|\s+HAVING\s+|\s+ORDER\sBY|$))?(?:.*?\s+GROUP\sBY\s+([\s\S]+?)(?=\s+HAVING\s+|\s+ORDER\sBY|$))?(?:.*?\s+HAVING\s+([\s\S]+?)(?=\s+ORDER\sBY\s+|$))?(?:.*?\s+ORDER\sBY\s+([\s\S]+?)(?=\s*$))?$"
test_str = ("SELECT t1.dummy1, t1.dummy2 AS Error, t1.dummy3 INTO testResult\n"
"FROM (test1 t1 INNER JOIN test2 t2 ON t1.dummy4 = t2.dummy4) INNER JOIN test3 t3 ON t2.dummy9 = t3.dummy9 \n"
"WHERE t2.dummy6 = 'abc' AND t3.dummy10 <> 'def' AND t1.dummy11 = 'ghi' AND t2.dummy12 IS NULL\n"
"GROUP BY t1.dummy1\n"
"HAVING 1=1\n"
"ORDER BY 1;")
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