# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"([CDEFGAB](#|##|b|bb)?)((M|m|aug|dim|sus|add)?(6|7|9|11|13|-5|\+5)?)"
test_str = ("Bm7 E7 E/A F#m7 Bm7\n"
"어두운 밤 골목길을 혼자 털레털레 오르다 c 올라\n"
"Bm7 E7 E/A F#m7\n"
"지나가는 네 생각에 내가 눈물이 난 게 아니고\n"
" Bm7 E7 C#m7 F#7\n"
"이부자리를 치우다 너의 양말 한 짝이 나와서\n"
" Bm7 E7 C#m7 F#7\n"
"갈아 신던 그 모습이 내가 그리워져 운 게 아니고\n"
" Bm7 E7 E/A F#m7\n"
"보일러가 고장 나서 울지")
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