# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(\s*(\S+\s+){3}([.?!]\s*)?([^\s.?!]+\s+)*\S+\s*[.?!]){7,}$"
test_str = ("This seems to work, but I have obviously fudged many things and wonder if anyone has a better idea. (It has to allow for html at any point, and a lot of other quirks from users' writing. rawr. moo moo . rawr!\n\n"
"I am not too concerned about people gaming the system - there are still manual checks, this is just a first-stage check to lighten the load.) My other main concern is efficiency - I'm new to regex and don't know what is a 'normal' calculation time, but the debugger(s) I'm using are struggling at times when I paste in a block of text to check, and I don't know if this is caused by my RegEx or the debugger. It is often timing out on longer sections of text where there is no match. Is there a more efficient way to do what I'm wanting?")
matches = re.finditer(regex, test_str)
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