Python class to shorten double byte string and set correct adapted format length for output print

double_byte_string_format.py

#!/usr/bin/env python3

"""
formatting with double width characters

"""

import unicodedata

def shorten_string_cjk(intput_string, width, placeholder='..'):
    """
    shorten a string with CJK (double byte) characters

    Args:
        intput_string (string): input string to shorten
        width (int): character count to shorten too
        placeholder (str, optional): cut of end characters if space is there
            Defaults to '..'.

    Returns:
        string: shortend string
    """
    # get the length with double byte charactes
    string_len_cjk = string_length_cjk(str(intput_string))
    # if double byte width is too big
    if string_len_cjk > width:
        # set current length and output string
        cur_len = 0
        out_string = ''
        # loop through each character
        for char in str(intput_string):
            # set the current length if we add the character
            cur_len += 2 if unicodedata.east_asian_width(char) in "WF" else 1
            # if the new length is smaller than the output length to shorten too add the char
            if cur_len <= (width - len(placeholder)):
                out_string += char
        # return string with new width and placeholder
        return f"{out_string}{placeholder}"
    else:
        return str(intput_string)

def string_length_cjk(input_string):
    """
    string lenth for a CJK (double byte) string

    Args:
        string (string): string to get length for

    Returns:
        int: length of characters, where CJK (double byte) will count as one
    """
    # return string len including double count for double width characters
    return sum(1 + (unicodedata.east_asian_width(c) in "WF") for c in input_string)

def format_string_length(input_string, length):
    """
    returns length udpated for string with double byte characters
    get string length normal, get string length including double byte characters
    then subtract that from the original length

    Args:
        input_string (string): string to calculate length of
        length (int): maxium length for string

    Returns:
        int: correct length for string to shorten too
    """
    return length - (string_length_cjk(input_string) - len(input_string))

def main():
    """
    main call:
    test with various strings
    """
    string = [
        "Some string 123 other text",
        "Some string 日本語 other text",
        "日本語は string 123 other text",
        "あいうえおかきくけこさしすせそなにぬねのまみむめも〜",
        "あいうえおかきくけこさしす 1 other text",
        "Some string すせそなにぬねのまみむめも〜",
        "SOME OTHER STRING THAT IS LONGER THAN TWENTYSIX CHARACTERS"
    ]

    # format_str = "|{{:<{len}}}|"
    format_len = 26
    string_len = 26
    print("Original string")
    for _string in string:
        print(
            "Normal  (CJK len "
            f"{string_length_cjk(_string):>2}/len {len(_string):>2}): |{_string}|"
        )
    print("Shorten string")
    for _string in string:
        print(
            f"Calculate> format_len: {format_len}, string_len: {string_len}, "
            "stringLenCJK(short) "
            f"{string_length_cjk(shorten_string_cjk(_string, width=string_len))}, "
            f"len(short) {len(shorten_string_cjk(_string, width=string_len))}, "
            "new format_len: "
            f"{format_string_length(shorten_string_cjk(_string, width=string_len), format_len)}"
        )
    # shorten format length by the number of double bye characters found
    # in the shortened string
    # string shorten uses double byte character count
    for _string in string:
        string_to_print = shorten_string_cjk(_string, width=string_len)
        string_length = format_string_length(
            shorten_string_cjk(_string, width=string_len),
            format_len
        )
        print(
            "Normal: "
            f"|{string_to_print:<{string_length}}|"
        )

main()

# __END__

Updated with Python 3.9/10
pylance linting pass