import re
regex = re.compile(r"(?<=\d)\t(?=\d)|\t(?=[A-Z@<:]{14})|(?<=[A-Z@<:]{14})\t", flags=re.MULTILINE)
test_str = ("C42TMACXX:5:2316:15161:76101 163 1 @<@DFFADDDF:DD NH:i:1 HI:i:1 AS:i:200 nM:i:0\n"
"C42TMACXX:5:2316:15161:76101 83 1 CCCCCACDDDCB@B NH:i:1 HI:i:1 nM:i:1\n"
"C42TMACXX:5:1305:26011:74469 163 1 CCCFFFFFHHHHGJ NH:i:1 HI:i:1 AS:i:200 nM:i:0")
matches = regex.finditer(test_str)
for match_num, match in enumerate(matches, start=1):
print(f"Match {match_num} was found at {match.start()}-{match.end()}: {match.group()}")
for group_num, group in enumerate(match.groups(), start=1):
print(f"Group {group_num} found at {match.start(group_num)}-{match.end(group_num)}: {group}")
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