クリップボードにコピーしているテキストのコードポイントや Unicode/UTF-16 エスケープシーケンスを確認するスクリプト 👉 https://android.benigumo.com/20230530/dump-text/

clipboard-text-dump.py

#!/usr/bin/env python

import pyperclip
from regex import regex


def graphemes(text):
  return regex.findall(r'\X', text)


def str_to_hex_codepoints_str(text):
  cps = [r'0x{:X}'.format(ord(c)) for c in text]
  return ' '.join(cps)


def str_to_escape_sequence_unicode(text):
  ss = graphemes(text)
  cps = []
  for s in ss:
    for c in s:
      cp = ord(c)
      cps.append(cp)
  return ''.join([r'\U{:08X}'.format(cp) for cp in cps])


def str_to_escape_sequence_utf16(text):
  ss = graphemes(text)
  cps = []
  for s in ss:
    for c in s:
      cp = ord(c)
      if cp > 0x10000:
        cp -= 0x10000
        hsg = cp // 0x400 + 0xd800
        lsg = cp % 0x400 + 0xdc00
        cps.append(hsg)
        cps.append(lsg)
      else:
        cps.append(cp)
  return ''.join([r'\u{:04X}'.format(cp) for cp in cps])


def dump(text):
  ss = graphemes(text)
  print(text)
  print(len(ss))
  print(len(text))

  print(str_to_escape_sequence_unicode(text))
  print(str_to_escape_sequence_utf16(text))
  print(str_to_hex_codepoints_str(text))
  print()

  # ss(str) -> s(str) = cs(list) -> c(str)
  for s in ss:
    print(s)
    print(str_to_escape_sequence_unicode(s))
    print(str_to_escape_sequence_utf16(s))
    print(str_to_hex_codepoints_str(s))

    cs = list(s)
    for c in cs:
      uni = str_to_escape_sequence_unicode(c)
      u16 = str_to_escape_sequence_utf16(c)
      hcp = str_to_hex_codepoints_str(c)
      print(' ', uni, u16, hcp, f'({c})')

    print()


def main():
  text = pyperclip.paste().strip()
  # text = '🫶💀🔥🥹🫛👨‍👩‍👧‍👦'
  dump(text)


if __name__ == '__main__':
  main()