Test out different

unicode_test.py

import os
import subprocess
import sys
import unicodedata


def run_test(val, forms):
    print("---- print")

    for form in forms:
        print(f"{form}\t{unicodedata.normalize(form, val)}")

    print("\n---- unicode escaped\n")

    for form in forms:
        print(
            f"{form}\t{unicodedata.normalize(form, val).encode('unicode_escape').decode('utf-8')}"
        )

    print("\n---- ls -1\n")

    files = [
        {
            "filename": unicodedata.normalize(form, f"{form}-{val}.txt"),
            "content": unicodedata.normalize(form, val) + "\n",
        }
        for form in forms
    ]

    for file in files:
        with open(file["filename"], "w", encoding="utf-8") as f:
            f.write(file["content"])

    subprocess.run(["ls", "-1"] + [file["filename"] for file in files])

    print("\n---- cat\n ")

    for file in files:
        print(f"-- {file['filename']}")
        subprocess.run(["cat", file["filename"]])

    for file in files:
        os.remove(file["filename"])


if __name__ == "__main__":
    default_val = "\uc548\ub155\ud558\uc138\uc694"  # 안녕하세요
    forms = ["NFD", "NFKD", "NFC", "NFKC"]

    val = sys.argv[1] if len(sys.argv) > 1 else default_val

    run_test(val, forms)