Python で S式（整数の四則演算だけ）を字句解析する

tokenizer.py

from enum import Enum
from functools import wraps


def assert_simgle_char(f):
    @wraps(f)
    def inner(c: str):
        if len(c) != 1:
            raise ValueError(c)
        return f(c)
    return inner


@assert_simgle_char
def is_space(c):
    return c in '\s\n\t\r '

@assert_simgle_char
def is_numeric(c):
    return c in '0123456789'


def tokenize(code: str) -> list[str]:
    tokens = []
    i = 0
    while (True):
        c = code[i]
        if c in '()':
            tokens.append(c)
            i += 1
        elif c in '+-*/':
            tokens.append(c)
            i += 1
        elif is_numeric(c):
            buf = ''
            while (True):
                if is_numeric(code[i]):
                    buf += code[i]
                    i += 1
                    continue
                tokens.append(buf)
                break
        elif is_space(c):
            i += 1

        if len(code) <= i:
            break

    return tokens


if __name__ == '__main__':
    ret = tokenize('(+ 1 23)')
    print(ret)

    ret = tokenize('(* (+ 100 234) 987))')
    print(ret)

$ python -m tokenizer
['(', '+', '1', '23', ')']
['(', '*', '(', '+', '100', '234', ')', '987', ')', ')']