# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?i)(data)\s+((\w+)(?=(\s*))(?:\4\w+)+)?\s*(\(((.|\n)*?)\);)?"
test_str = ("data foo (drop = DISCOUNT price RENAME = ( PROV_NM1= PROV_NM PROV_ST_NM1 = PROV_ST_NM) where = ( product = 'whizmo' and product < 10 )) bar( drop= DISCOUNT price rename= ( startDate = beginDate ) );\n\n"
"Data Data_asof&YrMon.;\n\n"
"data halfYear( drop= DISCOUNT price\n"
" rename= ( startDate = beginDate ) where=(product = 'abc' and price > 10) );\n\n"
"data apply_adj_v2 non_adjusted incorrect_acct;\n\n"
"data apply_adj_v2;\n\n"
"DATA INPDTL1(RENAME=(PROV_NM1=PROV_NM PROV_ST_NM1=PROV_ST_NM));\n\n"
"DATA REIMB_MTHD_CLM2;\n\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