# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(?<firstchar>(?=[A-Za-z]))((?<alphachars>[A-Za-z])|(?<specialchars>[A-Za-z]['-](?=[A-Za-z]))|(?<spaces> (?=[A-Za-z])))*$"
test_str = ("#First Name must contain letters only. It may contain spaces, hyphens, or apostrophes.\n"
"First name-and hy-phen's\n"
"#It must begin with letters.\n"
"First name\n"
"1shouldn't match\n"
"'shouldn't match\n"
"#All other characters and numbers are not valid.\n"
"Should match\n"
"Should not m@tch\n"
"Should not m#tch\n"
"#Special characters ‘ and – cannot be together (e.g. John’-s is not allowed)\n"
"Allow'd\n"
"NotAllow-'d\n"
"NotAllow'-d\n"
"#An alphabet should be present before and after the special characters ‘ and – (e.g. John ‘s is not allowed)\n"
"Allow'd\n"
"Also A'llowed\n"
"A'llowd\n"
"Not Allowd'\n"
"Not 'Allowd\n"
"#Two consecutive spaces are not allowed (e.g. Annia St is not allowed)\n\n\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