# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^\(?[1-9]{2}\)?( ?)?([1-9]{1}[0-9]{3}|[0-9]{3}) ?[0-9]{4}$"
test_str = ("(98) 9 8111 2233\n"
"(98) 98111 2233\n"
"(98) 981112233\n"
"(98)981112233\n"
"(98)9 8111 2233\n"
"(98)9 81112233\n"
"(98) 981112233\n"
"(98) 2222 3333\n"
"(98) 22223333\n"
"(98)22223333\n"
"98 9 8111 2233\n"
"98 98111 2233\n"
"98 981112233\n"
"98981112233\n"
"989 8111 2233\n"
"989 81112233\n"
"98 981112233\n"
"98 2222 3333\n"
"98 22223333\n"
"9822223333\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