# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"select\s+(\*|((\w+(\.\w+)?)+(\s?,\s?\w+(\.\w+)?)*)|((\w+\([^\s]|(\w+\.\w+)?\))(\s+\,\s+)?)+)\s+from\s+(\w+(\s?,\s?\w+)*\;?)(\s+((\w+\s+join)\s+(\w+(\.\w)?\s+on\s+(\w+(\.\w+)?\s+=\s+\w+(\.\w+)?)?)(\s+,\s+)?)+)?(\s+((limit\s+(\w+)?\s?(\,\w+\;)?)|((where)?\s+?([^\;]+\s?;))))?"
test_str = ("select * from table4;\n"
"select * from table4,table5;\n"
"select table4.id from table4,table5;\n"
"select table4.id from table4,table5 where table4.id=table5.id;\n"
"select * from table4,table5 where table4.id=table5.id;\n"
"select * from table4,table5 where table4.id=table5.id and table4.id => 1 ;\n"
"select table4.id,table5.name from table4,table5 where table4.id=table5.id and table4.id>1 ;\n"
"select table4.id from table4,table5 where table4.id=table5.id like %ll%;\n"
"select table4.id from table4,table5 where table4.id=table5.id limit 1,10;\n"
"select table4.id from table4,table5 limit 1,10;\n"
"select table4.id from table4,table5 limit 1 ;\n"
"select table4.id from table4,table5 where id <> 1 limit 1 ;\n"
"select count(*) from table4,table5 where id <> 1 limit 1 ;\n"
"select count(*) from table4,table5 where id <> 1 having dd group by dd ;\n"
"select count(*) , max(table4.id) from table4,table5 where id <> 1 having dd group by dd ;\n"
"select * from tab1 left join tab2 on tab1.size = tab2.size where tab2.name = AAA;\n"
"select * from tab1 left join tab2 on tab1.size = tab2.size , right join tab2 on tab1.size = tab2.size where tab2.name = AAA and dd = dd;\n"
"select count(*) , max(table4.id) from table4,table5 left join tab2 on tab1.size = tab2.size , right join tab2 on tab1.size = tab2.size where id <> 1 having dd group by dd ;\n")
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