# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(?:\d{1,4}[A-Za-z]|\/?\d{1,4})"
test_str = ("Streets numbers:\n"
"/1\n"
"78\n"
"3a\n"
"89/\n"
"-1 (special case)\n"
"1\n\n"
"Apartment:\n"
"1-\n"
"2-5\n"
"12\n"
"7a\n"
"3a\n\n"
"Aadresses for testing:\n"
"Põllu tn 3-1-\n"
"Joa tn 3a-1-3\n"
"Kapa vkt 78\n"
"Kivimäe/1\n"
"Aia tn 11/2-5\n"
"Männiku tee 89/1-438, Nõmme linnaosa, Tallinn, Harju maakond\n"
"Männiku pst\n"
"Männiku mnt 12345\n"
"1. Mai tn\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