# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(?<rank>(?:(?:[ \t]|^)[a-z]+)+?)(?!(?:[ \t][a-z.]+){4,}$)[ \t](?<first>[a-z]+)[ \t](?:(?<middle>[a-z.]+)[ \t])?(?<last>[a-z]+)$"
test_str = ("High Sheriff John Caldwell. Cook\n"
"Deputy Sheriff John A. Gooch\n"
"Marshall Robert Forsyth\n"
"Constable Darius Quimby\n\n"
"#Exception (when you have First, Last and more than 1 word for the rank):\n"
"Deputy Sheriff John Gooch\n\n"
"#In the last example you have to define a list of rank prefixes which mean that there's another word definitely going after it and capture it greedy or with possessive quantifier. E.g.: Deputy,High.")
matches = re.finditer(regex, test_str, re.IGNORECASE | 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