{
  "version": "v1",
  "kind": "confusables",
  "description": "Look-alike characters: homograph domains, styled letters, dashes and quotes",
  "count": 10,
  "seed": null,
  "items": [
    {
      "id": "confusables-01",
      "text": "exаmple.com",
      "note": "Cyrillic a (U+0430) in a Latin domain (IDN homograph)",
      "lang": null,
      "length": {
        "codepoints": 11,
        "utf16_units": 11,
        "utf8_bytes": 12
      },
      "codepoints": "U+0065 U+0078 U+0430 U+006D U+0070 U+006C U+0065 U+002E U+0063 U+006F U+006D"
    },
    {
      "id": "confusables-02",
      "text": "еxаmplе.com",
      "note": "Cyrillic e and a mixed into a Latin domain",
      "lang": null,
      "length": {
        "codepoints": 11,
        "utf16_units": 11,
        "utf8_bytes": 14
      },
      "codepoints": "U+0435 U+0078 U+0430 U+006D U+0070 U+006C U+0435 U+002E U+0063 U+006F U+006D"
    },
    {
      "id": "confusables-03",
      "text": "admin admіn",
      "note": "Second word uses Cyrillic i (U+0456)",
      "lang": null,
      "length": {
        "codepoints": 11,
        "utf16_units": 11,
        "utf8_bytes": 12
      },
      "codepoints": "U+0061 U+0064 U+006D U+0069 U+006E U+0020 U+0061 U+0064 U+006D U+0456 U+006E"
    },
    {
      "id": "confusables-04",
      "text": "0O o0 l1I |",
      "note": "ASCII look-alikes: zero/O, one/l/I, pipe",
      "lang": null,
      "length": {
        "codepoints": 11,
        "utf16_units": 11,
        "utf8_bytes": 11
      },
      "codepoints": "U+0030 U+004F U+0020 U+006F U+0030 U+0020 U+006C U+0031 U+0049 U+0020 U+007C"
    },
    {
      "id": "confusables-05",
      "text": "𝐁𝐨𝐥𝐝 𝘐𝘵𝘢𝘭𝘪𝘤",
      "note": "Mathematical bold and italic letters used as fake styled text",
      "lang": null,
      "length": {
        "codepoints": 11,
        "utf16_units": 21,
        "utf8_bytes": 41
      },
      "codepoints": "U+1D401 U+1D428 U+1D425 U+1D41D U+0020 U+1D610 U+1D635 U+1D622 U+1D62D U+1D62A U+1D624"
    },
    {
      "id": "confusables-06",
      "text": "ＡＤＭＩＮ",
      "note": "Full-width Latin (NFKC folds it to ADMIN)",
      "lang": null,
      "length": {
        "codepoints": 5,
        "utf16_units": 5,
        "utf8_bytes": 15
      },
      "codepoints": "U+FF21 U+FF24 U+FF2D U+FF29 U+FF2E"
    },
    {
      "id": "confusables-07",
      "text": "example․com",
      "note": "One-dot leader U+2024 posing as a period",
      "lang": null,
      "length": {
        "codepoints": 11,
        "utf16_units": 11,
        "utf8_bytes": 13
      },
      "codepoints": "U+0065 U+0078 U+0061 U+006D U+0070 U+006C U+0065 U+2024 U+0063 U+006F U+006D"
    },
    {
      "id": "confusables-08",
      "text": "user＠example.com",
      "note": "Full-width @ (U+FF20)",
      "lang": null,
      "length": {
        "codepoints": 16,
        "utf16_units": 16,
        "utf8_bytes": 18
      },
      "codepoints": "U+0075 U+0073 U+0065 U+0072 U+FF20 U+0065 U+0078 U+0061 U+006D U+0070 U+006C U+0065 U+002E U+0063 U+006F U+006D"
    },
    {
      "id": "confusables-09",
      "text": "‐‑‒–—―−-",
      "note": "Eight different dashes and hyphens",
      "lang": null,
      "length": {
        "codepoints": 8,
        "utf16_units": 8,
        "utf8_bytes": 22
      },
      "codepoints": "U+2010 U+2011 U+2012 U+2013 U+2014 U+2015 U+2212 U+002D"
    },
    {
      "id": "confusables-10",
      "text": "‘’‚‛“”„«»‹›'\"",
      "note": "Quote marks: curly, low, guillemets and ASCII",
      "lang": null,
      "length": {
        "codepoints": 13,
        "utf16_units": 13,
        "utf8_bytes": 33
      },
      "codepoints": "U+2018 U+2019 U+201A U+201B U+201C U+201D U+201E U+00AB U+00BB U+2039 U+203A U+0027 U+0022"
    }
  ]
}