{
  "version": "v1",
  "kind": "long-words",
  "description": "Long compound words, unbroken strings, long URLs, e-mails and paths",
  "count": 28,
  "seed": null,
  "items": [
    {
      "id": "long-words-01",
      "text": "Donaudampfschifffahrtsgesellschaftskapitän",
      "note": "German compound noun",
      "lang": "de",
      "length": {
        "codepoints": 42,
        "utf16_units": 42,
        "utf8_bytes": 43
      },
      "codepoints": null
    },
    {
      "id": "long-words-02",
      "text": "Rindfleischetikettierungsüberwachungsaufgabenübertragungsgesetz",
      "note": "German compound noun (former law name)",
      "lang": "de",
      "length": {
        "codepoints": 63,
        "utf16_units": 63,
        "utf8_bytes": 65
      },
      "codepoints": null
    },
    {
      "id": "long-words-03",
      "text": "Grundstücksverkehrsgenehmigungszuständigkeitsübertragungsverordnung",
      "note": "German compound noun",
      "lang": "de",
      "length": {
        "codepoints": 67,
        "utf16_units": 67,
        "utf8_bytes": 70
      },
      "codepoints": null
    },
    {
      "id": "long-words-04",
      "text": "Kraftfahrzeug-Haftpflichtversicherung",
      "note": "German compound with hyphen (break opportunity)",
      "lang": "de",
      "length": {
        "codepoints": 37,
        "utf16_units": 37,
        "utf8_bytes": 37
      },
      "codepoints": "U+004B U+0072 U+0061 U+0066 U+0074 U+0066 U+0061 U+0068 U+0072 U+007A U+0065 U+0075 U+0067 U+002D U+0048 U+0061 U+0066 U+0074 U+0070 U+0066 U+006C U+0069 U+0063 U+0068 U+0074 U+0076 U+0065 U+0072 U+0073 U+0069 U+0063 U+0068 U+0065 U+0072 U+0075 U+006E U+0067"
    },
    {
      "id": "long-words-05",
      "text": "Donau­dampf­schiff­fahrts­gesell­schafts­kapitän",
      "note": "German compound with soft hyphens (U+00AD): should hyphenate, not overflow",
      "lang": "de",
      "length": {
        "codepoints": 48,
        "utf16_units": 48,
        "utf8_bytes": 55
      },
      "codepoints": null
    },
    {
      "id": "long-words-06",
      "text": "lentokonesuihkuturbiinimoottoriapumekaanikkoaliupseerioppilas",
      "note": "Finnish compound noun",
      "lang": "fi",
      "length": {
        "codepoints": 61,
        "utf16_units": 61,
        "utf8_bytes": 61
      },
      "codepoints": null
    },
    {
      "id": "long-words-07",
      "text": "epäjärjestelmällistyttämättömyydellänsäkäänköhän",
      "note": "Finnish heavily inflected word",
      "lang": "fi",
      "length": {
        "codepoints": 48,
        "utf16_units": 48,
        "utf8_bytes": 60
      },
      "codepoints": null
    },
    {
      "id": "long-words-08",
      "text": "kindercarnavalsoptochtvoorbereidingswerkzaamhedenplan",
      "note": "Dutch compound noun",
      "lang": "nl",
      "length": {
        "codepoints": 53,
        "utf16_units": 53,
        "utf8_bytes": 53
      },
      "codepoints": null
    },
    {
      "id": "long-words-09",
      "text": "arbeidsongeschiktheidsverzekering",
      "note": "Dutch compound noun",
      "lang": "nl",
      "length": {
        "codepoints": 33,
        "utf16_units": 33,
        "utf8_bytes": 33
      },
      "codepoints": "U+0061 U+0072 U+0062 U+0065 U+0069 U+0064 U+0073 U+006F U+006E U+0067 U+0065 U+0073 U+0063 U+0068 U+0069 U+006B U+0074 U+0068 U+0065 U+0069 U+0064 U+0073 U+0076 U+0065 U+0072 U+007A U+0065 U+006B U+0065 U+0072 U+0069 U+006E U+0067"
    },
    {
      "id": "long-words-10",
      "text": "Nordöstersjökustartilleriflygspaningssimulatoranläggningsmaterielunderhållsuppföljningssystemdiskussionsinläggsförberedelsearbeten",
      "note": "Swedish compound noun (constructed)",
      "lang": "sv",
      "length": {
        "codepoints": 130,
        "utf16_units": 130,
        "utf8_bytes": 137
      },
      "codepoints": null
    },
    {
      "id": "long-words-11",
      "text": "realisationsvinstbeskattning",
      "note": "Swedish compound noun",
      "lang": "sv",
      "length": {
        "codepoints": 28,
        "utf16_units": 28,
        "utf8_bytes": 28
      },
      "codepoints": "U+0072 U+0065 U+0061 U+006C U+0069 U+0073 U+0061 U+0074 U+0069 U+006F U+006E U+0073 U+0076 U+0069 U+006E U+0073 U+0074 U+0062 U+0065 U+0073 U+006B U+0061 U+0074 U+0074 U+006E U+0069 U+006E U+0067"
    },
    {
      "id": "long-words-12",
      "text": "menneskerettighetsorganisasjonene",
      "note": "Norwegian compound noun",
      "lang": "nb",
      "length": {
        "codepoints": 33,
        "utf16_units": 33,
        "utf8_bytes": 33
      },
      "codepoints": "U+006D U+0065 U+006E U+006E U+0065 U+0073 U+006B U+0065 U+0072 U+0065 U+0074 U+0074 U+0069 U+0067 U+0068 U+0065 U+0074 U+0073 U+006F U+0072 U+0067 U+0061 U+006E U+0069 U+0073 U+0061 U+0073 U+006A U+006F U+006E U+0065 U+006E U+0065"
    },
    {
      "id": "long-words-13",
      "text": "speciallægepraksisplanlægningsstabiliseringsperiode",
      "note": "Danish compound noun",
      "lang": "da",
      "length": {
        "codepoints": 51,
        "utf16_units": 51,
        "utf8_bytes": 53
      },
      "codepoints": null
    },
    {
      "id": "long-words-14",
      "text": "Llanfairpwllgwyngyllgogerychwyndrobwllllantysiliogogogoch",
      "note": "Welsh place name",
      "lang": "cy",
      "length": {
        "codepoints": 57,
        "utf16_units": 57,
        "utf8_bytes": 57
      },
      "codepoints": null
    },
    {
      "id": "long-words-15",
      "text": "Konstantynopolitańczykowianeczka",
      "note": "Polish long word",
      "lang": "pl",
      "length": {
        "codepoints": 32,
        "utf16_units": 32,
        "utf8_bytes": 33
      },
      "codepoints": "U+004B U+006F U+006E U+0073 U+0074 U+0061 U+006E U+0074 U+0079 U+006E U+006F U+0070 U+006F U+006C U+0069 U+0074 U+0061 U+0144 U+0063 U+007A U+0079 U+006B U+006F U+0077 U+0069 U+0061 U+006E U+0065 U+0063 U+007A U+006B U+0061"
    },
    {
      "id": "long-words-16",
      "text": "превысокомногорассмотрительствующий",
      "note": "Russian long word (Cyrillic)",
      "lang": "ru",
      "length": {
        "codepoints": 35,
        "utf16_units": 35,
        "utf8_bytes": 70
      },
      "codepoints": "U+043F U+0440 U+0435 U+0432 U+044B U+0441 U+043E U+043A U+043E U+043C U+043D U+043E U+0433 U+043E U+0440 U+0430 U+0441 U+0441 U+043C U+043E U+0442 U+0440 U+0438 U+0442 U+0435 U+043B U+044C U+0441 U+0442 U+0432 U+0443 U+044E U+0449 U+0438 U+0439"
    },
    {
      "id": "long-words-17",
      "text": "pneumonoultramicroscopicsilicovolcanoconiosis",
      "note": "English long word",
      "lang": "en",
      "length": {
        "codepoints": 45,
        "utf16_units": 45,
        "utf8_bytes": 45
      },
      "codepoints": null
    },
    {
      "id": "long-words-18",
      "text": "การทดสอบการตัดคำภาษาไทยซึ่งไม่มีการเว้นวรรคระหว่างคำ",
      "note": "Thai sentence with no spaces between words: needs dictionary line breaking",
      "lang": "th",
      "length": {
        "codepoints": 52,
        "utf16_units": 52,
        "utf8_bytes": 156
      },
      "codepoints": null
    },
    {
      "id": "long-words-19",
      "text": "WWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWWW",
      "note": "64 x W, the widest Latin glyph in most fonts",
      "lang": null,
      "length": {
        "codepoints": 64,
        "utf16_units": 64,
        "utf8_bytes": 64
      },
      "codepoints": null
    },
    {
      "id": "long-words-20",
      "text": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
      "note": "255 characters, a common VARCHAR limit",
      "lang": null,
      "length": {
        "codepoints": 255,
        "utf16_units": 255,
        "utf8_bytes": 255
      },
      "codepoints": null
    },
    {
      "id": "long-words-21",
      "text": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
      "note": "256 characters, one over a common VARCHAR limit",
      "lang": null,
      "length": {
        "codepoints": 256,
        "utf16_units": 256,
        "utf8_bytes": 256
      },
      "codepoints": null
    },
    {
      "id": "long-words-22",
      "text": "a373ff095476d699923556a5def23f09b3963569b34117aad41ad37a06f2a3d23665911f7ef25b78e315336f36d170a5435f037634b966143bd725f4590a8667",
      "note": "128-character hex string (no break opportunities)",
      "lang": null,
      "length": {
        "codepoints": 128,
        "utf16_units": 128,
        "utf8_bytes": 128
      },
      "codepoints": null
    },
    {
      "id": "long-words-23",
      "text": "LNka48WXhrEOv8IVJ1IHYxO5ulQ9ES+fFDwvYVA8Vip2pZ3KkTEkudapKeyO30CqnsT4alKPSEPToCzATZC0vyzZGuPFl4axDr/CFSdSB2MTubpUPREvnxQ8L2FQPFYqdqWdypExJLnWqSnsjt9Aqp7E+GpSj0hD06AswE2QtL8=",
      "note": "Long base64 token (contains + and /)",
      "lang": null,
      "length": {
        "codepoints": 172,
        "utf16_units": 172,
        "utf8_bytes": 172
      },
      "codepoints": null
    },
    {
      "id": "long-words-24",
      "text": "https://www.example.com/products/category/subcategory/a-very-long-product-name-that-keeps-going-and-going?utm_source=newsletter&utm_medium=email&utm_campaign=autumn-sale-2026&redirect=https%3A%2F%2Fexample.org%2Fcheckout%3Fitem%3D12345%26qty%3D2#section-with-a-long-anchor-name",
      "note": "Long URL with query string and encoded redirect",
      "lang": null,
      "length": {
        "codepoints": 277,
        "utf16_units": 277,
        "utf8_bytes": 277
      },
      "codepoints": null
    },
    {
      "id": "long-words-25",
      "text": "firstname.middlename.lastname.department.team@subdomain.mail.example.com",
      "note": "Long e-mail address",
      "lang": null,
      "length": {
        "codepoints": 72,
        "utf16_units": 72,
        "utf8_bytes": 72
      },
      "codepoints": null
    },
    {
      "id": "long-words-26",
      "text": "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa@bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb.example.com",
      "note": "E-mail with a 64-character local part and a 63-character label (RFC 5321 maximums)",
      "lang": null,
      "length": {
        "codepoints": 140,
        "utf16_units": 140,
        "utf8_bytes": 140
      },
      "codepoints": null
    },
    {
      "id": "long-words-27",
      "text": "Quarterly_Report_FINAL_v2_reviewed_by_legal_and_finance_team_2026-10-08 (copy 3).pdf",
      "note": "Long file name with spaces and parentheses",
      "lang": null,
      "length": {
        "codepoints": 84,
        "utf16_units": 84,
        "utf8_bytes": 84
      },
      "codepoints": null
    },
    {
      "id": "long-words-28",
      "text": "/var/lib/application/data/users/00000000-0000-0000-0000-000000000000/uploads/2026/10/08/original/image.jpeg",
      "note": "Long path with UUID",
      "lang": null,
      "length": {
        "codepoints": 107,
        "utf16_units": 107,
        "utf8_bytes": 107
      },
      "codepoints": null
    }
  ]
}