Add tool to detect strange characters in texts.

[PhilipMay]

No description provided.

[PhilipMay]

Like this?

from collections import Counter
from dataclasses import dataclass, field
import unicodedata

@dataclass
class CharCounter():

    char_counter: Counter = field(init=False, repr=False)

    def __post_init__(self):
        """Do post init."""
        self.char_counter = Counter()

    def fit(self, text: str):
        """Fit counter with text."""
        self.char_counter.update(text)

    # print top n uncommen characters in char_counter
    def print_top_n(self, n: int = 10):
        """Print top n uncommen characters in char_counter."""
        rare_chars = self.char_counter.most_common()[-n:]

        # print rare chars with their count unicode and hex representation
        for char, count in rare_chars:
            print(f">{char}< {hex(ord(char))} {unicodedata.category(char)}")