{
  "version": "v1",
  "kind": "casing",
  "description": "Case-mapping traps: Turkish I, sharp s, final sigma, digraphs, ligatures",
  "count": 10,
  "seed": null,
  "items": [
    {
      "id": "casing-01",
      "text": "İstanbul ılık",
      "note": "Turkish dotted capital I and dotless small i: locale-sensitive case mapping",
      "lang": "tr",
      "length": {
        "codepoints": 13,
        "utf16_units": 13,
        "utf8_bytes": 16
      },
      "codepoints": "U+0130 U+0073 U+0074 U+0061 U+006E U+0062 U+0075 U+006C U+0020 U+0131 U+006C U+0131 U+006B"
    },
    {
      "id": "casing-02",
      "text": "straße STRASSE ẞ",
      "note": "Sharp s upper-cases to SS; capital sharp s U+1E9E exists",
      "lang": "de",
      "length": {
        "codepoints": 16,
        "utf16_units": 16,
        "utf8_bytes": 19
      },
      "codepoints": "U+0073 U+0074 U+0072 U+0061 U+00DF U+0065 U+0020 U+0053 U+0054 U+0052 U+0041 U+0053 U+0053 U+0045 U+0020 U+1E9E"
    },
    {
      "id": "casing-03",
      "text": "ΟΔΥΣΣΕΥΣ οδυσσευς",
      "note": "Greek capital sigma lower-cases to ς at word end",
      "lang": "el",
      "length": {
        "codepoints": 17,
        "utf16_units": 17,
        "utf8_bytes": 33
      },
      "codepoints": "U+039F U+0394 U+03A5 U+03A3 U+03A3 U+0395 U+03A5 U+03A3 U+0020 U+03BF U+03B4 U+03C5 U+03C3 U+03C3 U+03B5 U+03C5 U+03C2"
    },
    {
      "id": "casing-04",
      "text": "Džemal dž DŽ",
      "note": "Titlecase digraph U+01C5 (three case forms)",
      "lang": "hr",
      "length": {
        "codepoints": 9,
        "utf16_units": 9,
        "utf8_bytes": 12
      },
      "codepoints": "U+01C5 U+0065 U+006D U+0061 U+006C U+0020 U+01C6 U+0020 U+01C4"
    },
    {
      "id": "casing-05",
      "text": "ffice",
      "note": "ffi ligature U+FB03: upper-cases to three letters",
      "lang": null,
      "length": {
        "codepoints": 3,
        "utf16_units": 3,
        "utf8_bytes": 5
      },
      "codepoints": "U+FB03 U+0063 U+0065"
    },
    {
      "id": "casing-06",
      "text": "IJsbeer",
      "note": "Dutch IJ digraph: both letters capitalized",
      "lang": "nl",
      "length": {
        "codepoints": 7,
        "utf16_units": 7,
        "utf8_bytes": 7
      },
      "codepoints": "U+0049 U+004A U+0073 U+0062 U+0065 U+0065 U+0072"
    },
    {
      "id": "casing-07",
      "text": "ʼn",
      "note": "U+0149 upper-cases to two code points",
      "lang": null,
      "length": {
        "codepoints": 1,
        "utf16_units": 1,
        "utf8_bytes": 2
      },
      "codepoints": "U+0149"
    },
    {
      "id": "casing-08",
      "text": "K ſ",
      "note": "Kelvin sign U+212A and long s U+017F: case-fold to k and s",
      "lang": null,
      "length": {
        "codepoints": 3,
        "utf16_units": 3,
        "utf8_bytes": 6
      },
      "codepoints": "U+212A U+0020 U+017F"
    },
    {
      "id": "casing-09",
      "text": "և",
      "note": "Armenian ligature ech-yiwn: upper-cases to two letters",
      "lang": "hy",
      "length": {
        "codepoints": 1,
        "utf16_units": 1,
        "utf8_bytes": 2
      },
      "codepoints": "U+0587"
    },
    {
      "id": "casing-10",
      "text": "ǰ",
      "note": "U+01F0: upper-case form needs a combining mark",
      "lang": null,
      "length": {
        "codepoints": 1,
        "utf16_units": 1,
        "utf8_bytes": 2
      },
      "codepoints": "U+01F0"
    }
  ]
}