sanitize.py 文件源码

def shave_marks_latin(txt):
    """Remove all diacritic marks from Latin base characters"""
    norm_txt = unicodedata.normalize('NFD', txt)  # <1>
    latin_base = False
    keepers = []
    for c in norm_txt:
        if unicodedata.combining(c) and latin_base:   # <2>
            continue  # ignore diacritic on Latin base char
        keepers.append(c)                             # <3>
        # if it isn't combining char, it's a new base char
        if not unicodedata.combining(c):              # <4>
            latin_base = c in string.ascii_letters
    shaved = ''.join(keepers)
    return unicodedata.normalize('NFC', shaved)   # <5>
# END SHAVE_MARKS_LATIN

# BEGIN ASCIIZE