# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
\A\s*
(?: #########################################################################
# Matches against Australian postal addresses
# [<floor> <number>]
# [<unit type>] [<unit>] <house number> <street name> <street type>
# [<anything trailing>
#########################################################################
(?:(?P<c_level_type>level|lvl|floor|flr)\s*(?P<c_level_number>\w+),?\s*)? # Level (floor, etc)
\s*,?\s* # Optional comma
(?:(?P<c_unit_type>[[:alpha:]][\w-']*)?\s*)? # Type (suite, unit, etc)
(?:(?P<c_unit_number>[\w\.]*(?!\d))\s*[,\/]*\s*)? # Unit
(?P<c_house_number>\pN+[[:alpha:]]?(?:\s*[-\/\pP]\s*\pN+[[:alpha:]]?)*) # House number
\s*,?\s* # Optional comma
(?P<c_street_name>[\w-\s]*?) # Street name
\s+
\b(?P<c_street_type>fire\s*track|right\s*of\s*way|service\s*way|shopping\s*centre|state\s*highway|\w{2,})\b # Street type
(?:\s*\R+(?P<c_trailing>.+))? # Trailing data not captured
)
\s*\Z
"""
test_str = "level 2, 100 smith avenue"
matches = re.finditer(regex, test_str, re.VERBOSE | re.UNICODE | re.IGNORECASE | re.DOTALL)
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