# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(?>[^\w\n]*(\w++)(?=.*\R(\2?+[^\w\n]*\1\b)))+[^\w\n]*\R(?=\2[^\w\n]*$)"
test_str = ("Rough work iconoclasm but the only way to get the truth. Oliver Wendell Holmes\n"
"Rough work, iconoclasm, but the only way to get the truth. Oliver Wendell Holmes\n\n"
"Rule No. 1: Never lose money. Rule No. 2: Never forget rule No. 1. Warren Buffett\n"
"Rule No.1: Never lose money. Rule No.2: Never forget rule No.1. Warren Buffett\n\n"
"Self-esteem isn't everything, it's just that there's nothing without it. Gloria Steinem \n"
"Self-esteem isn't everything it's just that there's nothing without it. Gloria Steinem\n\n"
"You said she's a senior? Babe we're all crazy.\n"
"You said, she's a senior! Babe we're ALL crazy.\n"
"You said, she's a senior? Babe we're ALL crazy!\n\n"
"a\n"
"a a\n"
"a a a\n\n"
"a\n"
"a b\n"
"a b c\n"
"a b\n"
"a")
subst = ""
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.MULTILINE | re.IGNORECASE)
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