# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<=^|[^_])__(((\\_)|((?![\s_])(?:(?:[^_]|_(?!_))+?)?[^\s_]))+)__(?=[^_]|$)"
test_str = ("-- funciona\n"
"__foo bar__\n"
"__f o o b a r__\n"
"**teste __lorem ipsum__ dolor sit**\n"
"__teste **lorem ipsum** dolor sit__\n"
"abc__xyz__teste\n\n"
"-- não funcionava na primeira versão\n"
"__foo_bar__\n"
"__a__\n"
"__*__\n"
"__foo_*bar__\n\n"
"-- não é para funcionar\n"
"__ foo bar__\n"
"__foo bar __\n"
"_foo__\n"
"__ foo __\n"
"_foo_\n"
"__foo_\n"
"__ __\n"
"__a____\n"
"____a__\n"
"_____\n\n"
"-- corner case: aninhado (não tratei pois não sei o que deveria fazer)\n"
"__abc__xyz__123__\n"
"__abc __xyz__ 123__\n\n"
"-- corner case: escape (chega a reconhecer alguns casos, mas não substitui \"\\_\" por \"_\"\n"
"__\\___\n"
"__a\\___\n"
"__abc\\___\n"
"__\\_abc_\\__ -- errado, mas não consegui tratar")
subst = "<i>\\1<\\i>"
# 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