# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b(([a-z] ){3,5}|[a-z]{3,5}) ?\d[\d\- ]{3,15}\d\b|\b\d[\d -]{3,18}\d\b"
test_str = ("my shipment CSD12345678.\n"
"check CAS 1234567 please\n"
"let's try C A S 123-456-789 for me\n"
"or it should be MULTI12345678 forever\n"
"it is 123454677!\n"
"it is COE 123454677!\n"
"superMULTI 12345678 25 two\n"
"twenty symbols code iss 00123456781234567890")
matches = re.finditer(regex, test_str, re.IGNORECASE)
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