# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^\d+ +(?<=.{11})"
test_str = ("Don't want to match below\n"
"1 , 52\n"
"123 ,abc\n"
"1234 abcd\n"
"12345 ,asdht\n"
"123456 ahcb\n\n"
"Don't want to match below\n"
"33406 +%global blind rpttyp ;\n"
"33407 +\n"
"33408 +%let blind=N;\n"
"33409 +%let rpttyp =2;\n"
"33410 +%let var = %sysfunc(cats(blah));\n"
" \n"
"Want to match below\n"
"33413 /*************************************************************************************\n"
"33414 \n"
"33439 17APR2018\n"
"33440 19APR2018\n"
"33441 23APR2018 \n"
"33442 24APR2018\n"
"33443 **************************************************************************************\n"
"33444 Program Notes:\n"
"33445 \n"
"33446 **************************************************************************************/\n"
"33447 options mprint mlogic symbolgen source source2 nobyline;\n"
"33448 \n"
"33449 %let source=%str(myds);\n\n"
"Last goal:\n"
"1 2 4 ")
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