# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b[A-Z0-9]+(?:-[A-Z0-9]+)+"
test_str = ("I only want the Uppercase Letters and Numbers with dashes, so it does get GC-113, AO-1-GC-113, AO-2-GC-113, which is great!\n\n"
"\"I don't want this ------, but this is good GC-113, AO-1-GC-113, AO-2-GC-113\"\n\n"
"BUT if I come across one where there is no space between the number, but just another character like a comma or a period then it returns a match on the entire section \"GC-113,AO-1-GC-113,AO-2-GC-113\"\n\n"
"\"I don't want this ------, but this is good GC-113,AO-1-GC-113,AO-2-GC-113\"")
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