Normalisateur de texte Unicode

import unicodedata

text = "e\u0301"  # 'e' + combining acute accent (looks like 'é')

# NFC: Canonical Decomposition, then Canonical Composition
nfc = unicodedata.normalize("NFC", text)
print(f"NFC:  {nfc!r}  len={len(nfc)}")   # 'é'  len=1

# NFD: Canonical Decomposition
nfd = unicodedata.normalize("NFD", text)
print(f"NFD:  {nfd!r}  len={len(nfd)}")   # 'é'  len=2

# NFKC: Compatibility Decomposition, then Canonical Composition
full_width = "\uff41\uff42\uff43"  # ａｂｃ full-width
nfkc = unicodedata.normalize("NFKC", full_width)
print(f"NFKC: {nfkc!r}")  # 'abc'

# NFKD: Compatibility Decomposition
nfkd = unicodedata.normalize("NFKD", full_width)
print(f"NFKD: {nfkd!r}")  # 'abc'

# Check if two strings are canonically equivalent
def canon_equal(a: str, b: str) -> bool:
    return unicodedata.normalize("NFC", a) == unicodedata.normalize("NFC", b)

print(canon_equal("é", "e\u0301"))  # True