# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(\b(?:\w+)?\d+(?:\w+)?(?:[\-\/])?(?:\w+)?(?:\d+)?\b)"
test_str = ("Park Avenue number 100\n"
"Baker Street number 100\n"
"Baker Street 100\n"
"The bakery shop is located on 109-111 Wharfside Street\n"
"My mother's house is on 40-42 Parkway\n"
"My schoolmate lives in 25b-26 Sun Street\n"
"The apartment is located on R2-R3 City Quay\n"
"I live in 43a Garden Walk\n"
"I live in 6/7 Marine Road\n"
"I live in 10-12 Acacia Ave\n"
"I live in 4513 3RD STREET CIRCLE WEST\n"
"I live in 1/2 Fifth Avenue\n"
"number C3-H4 sawojajar Malang")
matches = re.finditer(regex, test_str)
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