# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(\/\*[\s\S]*?\*\/|\/\/.*?$)|(?:\b(?=[A-Za-z][A-Za-z\d]*(?:_[A-Za-z\d]++)+\b)|\G(?<!\b))([A-Za-z\d])([A-Za-z\d]*)(?:_|\b)"
test_str = ("_here _is an_EX4mple, thisisnot_, BUT_th1s_1s, also_not_, y_3_s_sir\n\n"
"/* Ok, we are inside a comment so_this_does_not_count, nor_this\n"
"and_def_not_this\n"
"or_this */ outside_is_fair_game\n\n"
"some other_stuff here /* another_multiline_comment */\n\n"
"no_double__underscore but_yes_this not__this\n"
"this_comes_before // a single_line comment\n\n"
"and stuff_aFTER_tHE_CoMmEnT, except 1cannot_start_with_a_number, and finally_\n"
"not_4cr0ss_mult1p13_l1nes")
subst = "$1\\U$2\\L$3\\E"
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.MULTILINE)
if result:
print (result)
# 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