{
  "id": "character_encoding",
  "name": "Character encoding (charset)",
  "status": "draft",
  "doc": "Name of the character encoding of a text, as in the charset parameter of a MIME type, an HTML meta tag, an XML declaration or a file's metadata. The IANA Character Sets registry lists the names and aliases for use on the Internet: up to 40 printable US-ASCII characters, compared without regard to case, such as UTF-8, ISO-8859-1, windows-1251 and KOI8-R. Software also writes unregistered spellings (utf8, cp1251). Field names are charset, encoding and character_set.",
  "categories": [
    {
      "id": "texts",
      "name": "Texts and  articles"
    },
    {
      "id": "software",
      "name": "Software development"
    }
  ],
  "langs": [
    {
      "id": "common",
      "name": "Common to most languages"
    }
  ],
  "is_pii": false,
  "classification": "categorical",
  "examples": [
    {
      "value": "UTF-8",
      "description": "Unicode, preferred MIME name in the IANA registry"
    },
    {
      "value": "windows-1251",
      "description": "Windows Cyrillic code page"
    },
    {
      "value": "KOI8-R",
      "description": "Russian KOI8 encoding"
    },
    {
      "value": "Shift_JIS",
      "description": "Japanese encoding"
    }
  ],
  "links": [
    {
      "type": "doc",
      "url": "https://www.iana.org/assignments/character-sets/character-sets.xhtml"
    },
    {
      "type": "wikipedia",
      "url": "https://en.wikipedia.org/wiki/Character_encoding"
    }
  ],
  "translations": {
    "ru": {
      "name": "Кодировка символов",
      "doc": "Название кодировки текста, например UTF-8, windows-1251 или KOI8-R, по реестру Character Sets IANA."
    }
  },
  "type": "datatype"
}