import re
def get_word_before_last(text: str) -> str:
"""
Returns the word before the last word in a string.
Handles ASCII and Unicode punctuation/whitespace.
"""
# Use regex to split by any non-alphanumeric character.
# \W+ matches one or more non-word characters (punctuation, spaces, etc.)
# Python's \W is Unicode-aware by default in Python 3.
# We filter out empty strings resulting from leading/trailing punctuation.
words = [w for w in re.split(r'\W+', text) if w]
if len(words) < 2:
return ""
return words[-2]
def main():
print("=== Testing: Get Word Before Last ===\n")
tests = [
"python c++",
" many spaces here now ",
"OneWord",
"",
" ",
"Hello, world!",
"Tabs\tand\nnewlines work too",
"Unicode 世界、こんにちは",
"Ends with punctuation.",
"Multiple words, with punctuation, here!",
"state-of-the-art program example"
]
for t in tests:
result = get_word_before_last(t)
# Using f-strings for clean output formatting
display_result = result if result else "null"
print(f'Input: "{t}"')
print(f'Output: {display_result}')
print("-" * 40)
if __name__ == "__main__":
main()
"""
OUTPUT:
=== Testing: Get Word Before Last ===
Input: "python c++"
Output: python
----------------------------------------
Input: " many spaces here now "
Output: here
----------------------------------------
Input: "OneWord"
Output: null
----------------------------------------
Input: ""
Output: null
----------------------------------------
Input: " "
Output: null
----------------------------------------
Input: "Hello, world!"
Output: Hello
----------------------------------------
Input: "Tabs and
newlines work too"
Output: work
----------------------------------------
Input: "Unicode 世界、こんにちは"
Output: 世界
----------------------------------------
Input: "Ends with punctuation."
Output: with
----------------------------------------
Input: "Multiple words, with punctuation, here!"
Output: punctuation
----------------------------------------
Input: "state-of-the-art program example"
Output: program
----------------------------------------
"""
