# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<=[\s\.\,\!\?\"\;\:]|^)(?=[A-Za-z']*?[bcdfghj-np-tvwxyzBCDFGHJ-NP-TVWXYZ])(?=[A-Za-z']*?[aeiouyAEIOUY'])(?:[A-Za-z](?:'?[A-Za-z]){2}|(?:'?[A-Za-z]){2}[A-Za-z])\b'?(?=[\s\.\,\!\?\"\;\:]|$)"
test_str = ("This regex matches any three letter string that has at least one vowel and at least one consonant. As you can see, it's very effective and it only matches 3 letter words.\n"
"The word \"I'll\" should count as a 3 letter word. Words like \"isn't,\" \"you'dn't've,\" and \"let's\" shouldn't. Jo's dog is smart. The quick brown dog jumped over the lazy fox.\n"
"The qis' house. \"qis'\" is just a made up word to test stuff like \"kids'\" but for 3 letters.\n\n"
"asd\n"
"'asd\n"
"a'sd\n"
"as'd\n"
"asd'")
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