# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"[A-HJ-NP-TV-Z]{2}[\s-]{0,1}[0-9]{3}[\s-]{0,1}[A-HJ-NP-TV-Z]{2}|[0-9]{2,4}[\s-]{0,1}[A-Z]{1,3}[\s-]{0,1}[0-9]{2}"
test_str = ("## OLD FROMAT (complete) ##\n"
"3123 AA 11\n"
"3123-AA-11\n"
"3123AA11\n"
"8987 VG 33\n"
"8987VG33\n\n"
"## OLD FORMAT (with few characters) ##\n"
"31 F 11\n\n"
"## NEW FORMAT ##\n"
"AA 123 BB\n"
"AA-222-BB\n"
"DD345EE\n\n"
"AO 123 BB // O is excluded\n"
"AI-123-BB // I is excluded\n"
"AU123BB // U is exclided\n"
"AZ 123 BI\n"
"AZ-123-BU\n"
"AZ123BO")
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