See Unicode on Wiktionary
Download JSON data for Unicode meaning in All languages combined (17.2kB)
{
"etymology_templates": [
{
"args": {
"1": "en",
"2": "uni",
"3": "code"
},
"expansion": "uni- + code",
"name": "prefix"
}
],
"etymology_text": "Published as a draft proposal in 1988, “intended to suggest a unique, unified, universal encoding”. From uni- + code.",
"head_templates": [
{
"args": {},
"expansion": "Unicode",
"name": "en-proper noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "name",
"senses": [
{
"categories": [
{
"kind": "topical",
"langcode": "en",
"name": "Computing",
"orig": "en:Computing",
"parents": [
"Technology",
"All topics",
"Fundamental"
],
"source": "w"
},
{
"_dis": "61 39",
"kind": "other",
"name": "English entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "38 25 37",
"kind": "other",
"name": "English entries with language name categories using raw markup",
"parents": [
"Entries with language name categories using raw markup",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "26 33 41",
"kind": "other",
"name": "English terms prefixed with uni-",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "32 37 31",
"kind": "other",
"name": "English trademarks",
"parents": [],
"source": "w+disamb"
}
],
"examples": [
{
"text": "This character isn't in Unicode.",
"type": "example"
}
],
"glosses": [
"A series of character encoding standards intended to support the characters used by a large number of the world’s languages."
],
"id": "en-Unicode-en-name-~qM9QHbn",
"links": [
[
"computing",
"computing#Noun"
],
[
"character encoding",
"character encoding"
]
],
"qualifier": "international standards",
"raw_glosses": [
"(international standards, computing) A series of character encoding standards intended to support the characters used by a large number of the world’s languages."
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
],
"translations": [
{
"_dis1": "66 34",
"code": "sq",
"lang": "Albanian",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "am",
"lang": "Amharic",
"roman": "yunikod",
"sense": "series of computer encoding standards",
"word": "ዩኒኮድ"
},
{
"_dis1": "66 34",
"code": "ar",
"lang": "Arabic",
"roman": "yūnīkūd",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "يُونِيكُود"
},
{
"_dis1": "66 34",
"code": "hy",
"lang": "Armenian",
"roman": "Yunikod",
"sense": "series of computer encoding standards",
"word": "Յունիկոդ"
},
{
"_dis1": "66 34",
"code": "be",
"lang": "Belarusian",
"roman": "Junikód",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Юніко́д"
},
{
"_dis1": "66 34",
"code": "bn",
"lang": "Bengali",
"roman": "iunikōḍ",
"sense": "series of computer encoding standards",
"word": "ইউনিকোড"
},
{
"_dis1": "66 34",
"code": "byn",
"lang": "Blin",
"roman": "yunikod",
"sense": "series of computer encoding standards",
"word": "ዩኒኮድ"
},
{
"_dis1": "66 34",
"code": "bg",
"lang": "Bulgarian",
"roman": "Unikód",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Унико́д"
},
{
"_dis1": "66 34",
"code": "ca",
"lang": "Catalan",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "yue",
"lang": "Chinese Cantonese",
"sense": "series of computer encoding standards",
"word": "統一碼"
},
{
"_dis1": "66 34",
"code": "yue",
"lang": "Chinese Cantonese",
"roman": "tung² jat¹ maa⁵",
"sense": "series of computer encoding standards",
"word": "统一码"
},
{
"_dis1": "66 34",
"code": "yue",
"lang": "Chinese Cantonese",
"sense": "series of computer encoding standards",
"word": "萬國碼"
},
{
"_dis1": "66 34",
"code": "yue",
"lang": "Chinese Cantonese",
"roman": "maan⁶ gwok³ maa⁵",
"sense": "series of computer encoding standards",
"word": "万国码"
},
{
"_dis1": "66 34",
"code": "yue",
"lang": "Chinese Cantonese",
"sense": "series of computer encoding standards",
"word": "單一碼"
},
{
"_dis1": "66 34",
"code": "yue",
"lang": "Chinese Cantonese",
"roman": "daan¹ jat¹ maa⁵",
"sense": "series of computer encoding standards",
"word": "单一码"
},
{
"_dis1": "66 34",
"code": "cmn",
"lang": "Chinese Mandarin",
"sense": "series of computer encoding standards",
"word": "統一碼"
},
{
"_dis1": "66 34",
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "tǒngyīmǎ",
"sense": "series of computer encoding standards",
"word": "统一码"
},
{
"_dis1": "66 34",
"code": "cmn",
"lang": "Chinese Mandarin",
"sense": "series of computer encoding standards",
"word": "萬國碼"
},
{
"_dis1": "66 34",
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "wànguómǎ",
"sense": "series of computer encoding standards",
"word": "万国码"
},
{
"_dis1": "66 34",
"code": "cmn",
"lang": "Chinese Mandarin",
"sense": "series of computer encoding standards",
"word": "單一碼"
},
{
"_dis1": "66 34",
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "dānyīmǎ",
"sense": "series of computer encoding standards",
"word": "单一码"
},
{
"_dis1": "66 34",
"code": "cs",
"lang": "Czech",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "da",
"lang": "Danish",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "nl",
"lang": "Dutch",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "eo",
"lang": "Esperanto",
"sense": "series of computer encoding standards",
"word": "Unikodo"
},
{
"_dis1": "66 34",
"code": "fi",
"lang": "Finnish",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "fr",
"lang": "French",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "ka",
"lang": "Georgian",
"roman": "uniḳodi",
"sense": "series of computer encoding standards",
"word": "უნიკოდი"
},
{
"_dis1": "66 34",
"code": "de",
"lang": "German",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "el",
"lang": "Greek",
"sense": "series of computer encoding standards",
"tags": [
"neuter"
],
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "he",
"lang": "Hebrew",
"roman": "yunikod",
"sense": "series of computer encoding standards",
"word": "יוניקוד"
},
{
"_dis1": "66 34",
"code": "hi",
"lang": "Hindi",
"roman": "yūnikoḍ",
"sense": "series of computer encoding standards",
"word": "यूनिकोड"
},
{
"_dis1": "66 34",
"code": "hu",
"lang": "Hungarian",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "ig",
"lang": "Igbo",
"sense": "series of computer encoding standards",
"word": "Yunikod"
},
{
"_dis1": "66 34",
"code": "id",
"lang": "Indonesian",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "ia",
"lang": "Interlingua",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "it",
"lang": "Italian",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "ja",
"lang": "Japanese",
"roman": "yunikōdo",
"sense": "series of computer encoding standards",
"word": "ユニコード"
},
{
"_dis1": "66 34",
"code": "kn",
"lang": "Kannada",
"roman": "yunikōḍ",
"sense": "series of computer encoding standards",
"word": "ಯುನಿಕೋಡ್"
},
{
"_dis1": "66 34",
"code": "kkh",
"lang": "Khün",
"sense": "series of computer encoding standards",
"word": "ᨿᩪᨶᩥᨤ᩠ᨯᩰᨯ᩼"
},
{
"_dis1": "66 34",
"code": "ko",
"lang": "Korean",
"roman": "yunikodeu",
"sense": "series of computer encoding standards",
"word": "유니코드"
},
{
"_dis1": "66 34",
"code": "lv",
"lang": "Latvian",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unikods"
},
{
"_dis1": "66 34",
"code": "lt",
"lang": "Lithuanian",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unikodas"
},
{
"_dis1": "66 34",
"code": "mi",
"lang": "Maori",
"sense": "series of computer encoding standards",
"word": "waehereao"
},
{
"_dis1": "66 34",
"code": "mr",
"lang": "Marathi",
"roman": "yunikoḍ",
"sense": "series of computer encoding standards",
"word": "युनिकोड"
},
{
"_dis1": "66 34",
"code": "mn",
"lang": "Mongolian",
"roman": "Junikod",
"sense": "series of computer encoding standards",
"word": "Юникод"
},
{
"_dis1": "66 34",
"code": "no",
"lang": "Norwegian",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "fa",
"lang": "Persian",
"roman": "yuni-kod",
"sense": "series of computer encoding standards",
"word": "یونیکد"
},
{
"_dis1": "66 34",
"code": "pl",
"lang": "Polish",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "pt",
"lang": "Portuguese",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "ro",
"lang": "Romanian",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "ru",
"lang": "Russian",
"roman": "Junikód",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Юнико́д"
},
{
"_dis1": "66 34",
"code": "ru",
"lang": "Russian",
"roman": "Unikód",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Унико́д"
},
{
"_dis1": "66 34",
"code": "sgw",
"lang": "Sebat Bet Gurage",
"sense": "series of computer encoding standards",
"word": "ዩኒኮድ"
},
{
"_dis1": "66 34",
"code": "sh",
"lang": "Serbo-Croatian",
"sense": "series of computer encoding standards",
"tags": [
"Cyrillic",
"masculine"
],
"word": "Уникод"
},
{
"_dis1": "66 34",
"code": "sh",
"lang": "Serbo-Croatian",
"sense": "series of computer encoding standards",
"tags": [
"Roman",
"masculine"
],
"word": "Unikod"
},
{
"_dis1": "66 34",
"code": "sd",
"lang": "Sindhi",
"sense": "series of computer encoding standards",
"word": "يونيڪوڊ"
},
{
"_dis1": "66 34",
"code": "hsb",
"lang": "Upper Sorbian",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "es",
"lang": "Spanish",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "sv",
"lang": "Swedish",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "tl",
"lang": "Tagalog",
"sense": "series of computer encoding standards",
"word": "Yunikowd"
},
{
"_dis1": "66 34",
"code": "ta",
"lang": "Tamil",
"roman": "yūṉikkōṭu",
"sense": "series of computer encoding standards",
"word": "யூனிக்கோடு"
},
{
"_dis1": "66 34",
"code": "te",
"lang": "Telugu",
"roman": "viśva saṅkēta māla",
"sense": "series of computer encoding standards",
"word": "విశ్వ సంకేత మాల"
},
{
"_dis1": "66 34",
"code": "te",
"lang": "Telugu",
"roman": "yūnīkōḍ",
"sense": "series of computer encoding standards",
"word": "యూనీకోడ్"
},
{
"_dis1": "66 34",
"code": "th",
"lang": "Thai",
"roman": "yooníkôht",
"sense": "series of computer encoding standards",
"word": "ยูนิโคด"
},
{
"_dis1": "66 34",
"code": "ti",
"lang": "Tigrinya",
"roman": "yunikod",
"sense": "series of computer encoding standards",
"word": "ዩኒኮድ"
},
{
"_dis1": "66 34",
"code": "tr",
"lang": "Turkish",
"sense": "series of computer encoding standards",
"word": "Evrensel Kod"
},
{
"_dis1": "66 34",
"code": "tr",
"lang": "Turkish",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "uk",
"lang": "Ukrainian",
"roman": "Junikód",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Юніко́д"
},
{
"_dis1": "66 34",
"code": "ug",
"lang": "Uyghur",
"roman": "yunikod",
"sense": "series of computer encoding standards",
"word": "يۇنىكود"
},
{
"_dis1": "66 34",
"code": "vi",
"lang": "Vietnamese",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "cy",
"lang": "Welsh",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"_dis1": "66 34",
"code": "xan",
"lang": "Xamtanga",
"sense": "series of computer encoding standards",
"word": "ዩኒኮድ"
}
]
},
{
"categories": [
{
"kind": "topical",
"langcode": "en",
"name": "Computing",
"orig": "en:Computing",
"parents": [
"Technology",
"All topics",
"Fundamental"
],
"source": "w"
},
{
"_dis": "38 25 37",
"kind": "other",
"name": "English entries with language name categories using raw markup",
"parents": [
"Entries with language name categories using raw markup",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "26 33 41",
"kind": "other",
"name": "English terms prefixed with uni-",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "32 37 31",
"kind": "other",
"name": "English trademarks",
"parents": [],
"source": "w+disamb"
}
],
"examples": [
{
"text": "convert to Unicode",
"type": "example"
}
],
"glosses": [
"The Unicode standards, together with standards for representing character strings as byte strings."
],
"id": "en-Unicode-en-name-mrb9FDk7",
"links": [
[
"computing",
"computing#Noun"
],
[
"character",
"character"
],
[
"string",
"string"
],
[
"byte",
"byte"
]
],
"raw_glosses": [
"(computing) The Unicode standards, together with standards for representing character strings as byte strings."
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
}
],
"sounds": [
{
"ipa": "/ˈjunɪˌkoʊd/",
"tags": [
"US"
]
},
{
"ipa": "/ˈjuːnɪˌkəʊd/",
"tags": [
"UK"
]
},
{
"audio": "en-uk-Unicode.ogg",
"mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/b/b2/En-uk-Unicode.ogg/En-uk-Unicode.ogg.mp3",
"ogg_url": "https://upload.wikimedia.org/wikipedia/commons/b/b2/En-uk-Unicode.ogg",
"tags": [
"UK"
],
"text": "Audio (UK)"
}
],
"wikipedia": [
"Unicode"
],
"word": "Unicode"
}
{
"etymology_templates": [
{
"args": {
"1": "en",
"2": "uni",
"3": "code"
},
"expansion": "uni- + code",
"name": "prefix"
}
],
"etymology_text": "Published as a draft proposal in 1988, “intended to suggest a unique, unified, universal encoding”. From uni- + code.",
"head_templates": [
{
"args": {
"1": "-"
},
"expansion": "Unicode (uncountable)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "topical",
"langcode": "en",
"name": "Computing",
"orig": "en:Computing",
"parents": [
"Technology",
"All topics",
"Fundamental"
],
"source": "w"
},
{
"_dis": "38 25 37",
"kind": "other",
"name": "English entries with language name categories using raw markup",
"parents": [
"Entries with language name categories using raw markup",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "26 33 41",
"kind": "other",
"name": "English terms prefixed with uni-",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "32 37 31",
"kind": "other",
"name": "English trademarks",
"parents": [],
"source": "w+disamb"
}
],
"examples": [
{
"text": "Since most users on the site are westerners, we have banned Unicode in all text input boxes.",
"type": "example"
}
],
"glosses": [
"Characters from a contextually different script, often used in a nonstandard fashion. Sometimes used as an antonym to the characters of the Latin alphabet."
],
"id": "en-Unicode-en-noun-yaHQTIfO",
"links": [
[
"computing",
"computing#Noun"
],
[
"Latin alphabet",
"Latin alphabet#English"
]
],
"raw_glosses": [
"(computing, by extension, informal) Characters from a contextually different script, often used in a nonstandard fashion. Sometimes used as an antonym to the characters of the Latin alphabet."
],
"related": [
{
"word": "ASCII"
},
{
"word": "EBCDIC"
},
{
"word": "UTF-7"
},
{
"word": "UTF-8"
},
{
"word": "UTF-16"
}
],
"tags": [
"broadly",
"informal",
"uncountable"
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
}
],
"sounds": [
{
"ipa": "/ˈjunɪˌkoʊd/",
"tags": [
"US"
]
},
{
"ipa": "/ˈjuːnɪˌkəʊd/",
"tags": [
"UK"
]
},
{
"audio": "en-uk-Unicode.ogg",
"mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/b/b2/En-uk-Unicode.ogg/En-uk-Unicode.ogg.mp3",
"ogg_url": "https://upload.wikimedia.org/wikipedia/commons/b/b2/En-uk-Unicode.ogg",
"tags": [
"UK"
],
"text": "Audio (UK)"
}
],
"wikipedia": [
"Unicode"
],
"word": "Unicode"
}
{
"head_templates": [
{
"args": {
"1": "pt",
"2": "proper noun",
"3": "",
"4": "",
"g": "m",
"g2": "",
"g3": "",
"head": ""
},
"expansion": "Unicode m",
"name": "head"
},
{
"args": {
"1": "m"
},
"expansion": "Unicode m",
"name": "pt-proper noun"
}
],
"lang": "Portuguese",
"lang_code": "pt",
"pos": "name",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "Portuguese entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w"
},
{
"kind": "topical",
"langcode": "pt",
"name": "Computing",
"orig": "pt:Computing",
"parents": [
"Technology",
"All topics",
"Fundamental"
],
"source": "w"
}
],
"glosses": [
"Unicode (series of computer encoding standards)"
],
"id": "en-Unicode-pt-name-m~pxRvu0",
"links": [
[
"computing",
"computing#Noun"
],
[
"Unicode",
"Unicode#English"
]
],
"raw_glosses": [
"(computing) Unicode (series of computer encoding standards)"
],
"tags": [
"masculine"
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
}
],
"word": "Unicode"
}
{
"categories": [
"English 3-syllable words",
"English entries with incorrect language header",
"English entries with language name categories using raw markup",
"English lemmas",
"English nouns",
"English proper nouns",
"English terms prefixed with uni-",
"English terms with IPA pronunciation",
"English terms with audio links",
"English trademarks",
"English uncountable nouns"
],
"etymology_templates": [
{
"args": {
"1": "en",
"2": "uni",
"3": "code"
},
"expansion": "uni- + code",
"name": "prefix"
}
],
"etymology_text": "Published as a draft proposal in 1988, “intended to suggest a unique, unified, universal encoding”. From uni- + code.",
"head_templates": [
{
"args": {},
"expansion": "Unicode",
"name": "en-proper noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "name",
"senses": [
{
"categories": [
"English terms with usage examples",
"en:Computing"
],
"examples": [
{
"text": "This character isn't in Unicode.",
"type": "example"
}
],
"glosses": [
"A series of character encoding standards intended to support the characters used by a large number of the world’s languages."
],
"links": [
[
"computing",
"computing#Noun"
],
[
"character encoding",
"character encoding"
]
],
"qualifier": "international standards",
"raw_glosses": [
"(international standards, computing) A series of character encoding standards intended to support the characters used by a large number of the world’s languages."
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
},
{
"categories": [
"English terms with usage examples",
"en:Computing"
],
"examples": [
{
"text": "convert to Unicode",
"type": "example"
}
],
"glosses": [
"The Unicode standards, together with standards for representing character strings as byte strings."
],
"links": [
[
"computing",
"computing#Noun"
],
[
"character",
"character"
],
[
"string",
"string"
],
[
"byte",
"byte"
]
],
"raw_glosses": [
"(computing) The Unicode standards, together with standards for representing character strings as byte strings."
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
}
],
"sounds": [
{
"ipa": "/ˈjunɪˌkoʊd/",
"tags": [
"US"
]
},
{
"ipa": "/ˈjuːnɪˌkəʊd/",
"tags": [
"UK"
]
},
{
"audio": "en-uk-Unicode.ogg",
"mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/b/b2/En-uk-Unicode.ogg/En-uk-Unicode.ogg.mp3",
"ogg_url": "https://upload.wikimedia.org/wikipedia/commons/b/b2/En-uk-Unicode.ogg",
"tags": [
"UK"
],
"text": "Audio (UK)"
}
],
"translations": [
{
"code": "sq",
"lang": "Albanian",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "am",
"lang": "Amharic",
"roman": "yunikod",
"sense": "series of computer encoding standards",
"word": "ዩኒኮድ"
},
{
"code": "ar",
"lang": "Arabic",
"roman": "yūnīkūd",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "يُونِيكُود"
},
{
"code": "hy",
"lang": "Armenian",
"roman": "Yunikod",
"sense": "series of computer encoding standards",
"word": "Յունիկոդ"
},
{
"code": "be",
"lang": "Belarusian",
"roman": "Junikód",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Юніко́д"
},
{
"code": "bn",
"lang": "Bengali",
"roman": "iunikōḍ",
"sense": "series of computer encoding standards",
"word": "ইউনিকোড"
},
{
"code": "byn",
"lang": "Blin",
"roman": "yunikod",
"sense": "series of computer encoding standards",
"word": "ዩኒኮድ"
},
{
"code": "bg",
"lang": "Bulgarian",
"roman": "Unikód",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Унико́д"
},
{
"code": "ca",
"lang": "Catalan",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unicode"
},
{
"code": "yue",
"lang": "Chinese Cantonese",
"sense": "series of computer encoding standards",
"word": "統一碼"
},
{
"code": "yue",
"lang": "Chinese Cantonese",
"roman": "tung² jat¹ maa⁵",
"sense": "series of computer encoding standards",
"word": "统一码"
},
{
"code": "yue",
"lang": "Chinese Cantonese",
"sense": "series of computer encoding standards",
"word": "萬國碼"
},
{
"code": "yue",
"lang": "Chinese Cantonese",
"roman": "maan⁶ gwok³ maa⁵",
"sense": "series of computer encoding standards",
"word": "万国码"
},
{
"code": "yue",
"lang": "Chinese Cantonese",
"sense": "series of computer encoding standards",
"word": "單一碼"
},
{
"code": "yue",
"lang": "Chinese Cantonese",
"roman": "daan¹ jat¹ maa⁵",
"sense": "series of computer encoding standards",
"word": "单一码"
},
{
"code": "cmn",
"lang": "Chinese Mandarin",
"sense": "series of computer encoding standards",
"word": "統一碼"
},
{
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "tǒngyīmǎ",
"sense": "series of computer encoding standards",
"word": "统一码"
},
{
"code": "cmn",
"lang": "Chinese Mandarin",
"sense": "series of computer encoding standards",
"word": "萬國碼"
},
{
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "wànguómǎ",
"sense": "series of computer encoding standards",
"word": "万国码"
},
{
"code": "cmn",
"lang": "Chinese Mandarin",
"sense": "series of computer encoding standards",
"word": "單一碼"
},
{
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "dānyīmǎ",
"sense": "series of computer encoding standards",
"word": "单一码"
},
{
"code": "cs",
"lang": "Czech",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "da",
"lang": "Danish",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "nl",
"lang": "Dutch",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "eo",
"lang": "Esperanto",
"sense": "series of computer encoding standards",
"word": "Unikodo"
},
{
"code": "fi",
"lang": "Finnish",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "fr",
"lang": "French",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unicode"
},
{
"code": "ka",
"lang": "Georgian",
"roman": "uniḳodi",
"sense": "series of computer encoding standards",
"word": "უნიკოდი"
},
{
"code": "de",
"lang": "German",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unicode"
},
{
"code": "el",
"lang": "Greek",
"sense": "series of computer encoding standards",
"tags": [
"neuter"
],
"word": "Unicode"
},
{
"code": "he",
"lang": "Hebrew",
"roman": "yunikod",
"sense": "series of computer encoding standards",
"word": "יוניקוד"
},
{
"code": "hi",
"lang": "Hindi",
"roman": "yūnikoḍ",
"sense": "series of computer encoding standards",
"word": "यूनिकोड"
},
{
"code": "hu",
"lang": "Hungarian",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "ig",
"lang": "Igbo",
"sense": "series of computer encoding standards",
"word": "Yunikod"
},
{
"code": "id",
"lang": "Indonesian",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "ia",
"lang": "Interlingua",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "it",
"lang": "Italian",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unicode"
},
{
"code": "ja",
"lang": "Japanese",
"roman": "yunikōdo",
"sense": "series of computer encoding standards",
"word": "ユニコード"
},
{
"code": "kn",
"lang": "Kannada",
"roman": "yunikōḍ",
"sense": "series of computer encoding standards",
"word": "ಯುನಿಕೋಡ್"
},
{
"code": "kkh",
"lang": "Khün",
"sense": "series of computer encoding standards",
"word": "ᨿᩪᨶᩥᨤ᩠ᨯᩰᨯ᩼"
},
{
"code": "ko",
"lang": "Korean",
"roman": "yunikodeu",
"sense": "series of computer encoding standards",
"word": "유니코드"
},
{
"code": "lv",
"lang": "Latvian",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unikods"
},
{
"code": "lt",
"lang": "Lithuanian",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unikodas"
},
{
"code": "mi",
"lang": "Maori",
"sense": "series of computer encoding standards",
"word": "waehereao"
},
{
"code": "mr",
"lang": "Marathi",
"roman": "yunikoḍ",
"sense": "series of computer encoding standards",
"word": "युनिकोड"
},
{
"code": "mn",
"lang": "Mongolian",
"roman": "Junikod",
"sense": "series of computer encoding standards",
"word": "Юникод"
},
{
"code": "no",
"lang": "Norwegian",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "fa",
"lang": "Persian",
"roman": "yuni-kod",
"sense": "series of computer encoding standards",
"word": "یونیکد"
},
{
"code": "fa",
"lang": "Persian",
"roman": "yuni-kod",
"sense": "series of computer encoding standards",
"word": "یونیکد"
},
{
"code": "pl",
"lang": "Polish",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "pt",
"lang": "Portuguese",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unicode"
},
{
"code": "ro",
"lang": "Romanian",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unicode"
},
{
"code": "ru",
"lang": "Russian",
"roman": "Junikód",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Юнико́д"
},
{
"code": "ru",
"lang": "Russian",
"roman": "Unikód",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Унико́д"
},
{
"code": "sgw",
"lang": "Sebat Bet Gurage",
"sense": "series of computer encoding standards",
"word": "ዩኒኮድ"
},
{
"code": "sh",
"lang": "Serbo-Croatian",
"sense": "series of computer encoding standards",
"tags": [
"Cyrillic",
"masculine"
],
"word": "Уникод"
},
{
"code": "sh",
"lang": "Serbo-Croatian",
"sense": "series of computer encoding standards",
"tags": [
"Roman",
"masculine"
],
"word": "Unikod"
},
{
"code": "sd",
"lang": "Sindhi",
"sense": "series of computer encoding standards",
"word": "يونيڪوڊ"
},
{
"code": "hsb",
"lang": "Upper Sorbian",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "es",
"lang": "Spanish",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Unicode"
},
{
"code": "sv",
"lang": "Swedish",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "tl",
"lang": "Tagalog",
"sense": "series of computer encoding standards",
"word": "Yunikowd"
},
{
"code": "ta",
"lang": "Tamil",
"roman": "yūṉikkōṭu",
"sense": "series of computer encoding standards",
"word": "யூனிக்கோடு"
},
{
"code": "te",
"lang": "Telugu",
"roman": "viśva saṅkēta māla",
"sense": "series of computer encoding standards",
"word": "విశ్వ సంకేత మాల"
},
{
"code": "te",
"lang": "Telugu",
"roman": "yūnīkōḍ",
"sense": "series of computer encoding standards",
"word": "యూనీకోడ్"
},
{
"code": "th",
"lang": "Thai",
"roman": "yooníkôht",
"sense": "series of computer encoding standards",
"word": "ยูนิโคด"
},
{
"code": "ti",
"lang": "Tigrinya",
"roman": "yunikod",
"sense": "series of computer encoding standards",
"word": "ዩኒኮድ"
},
{
"code": "tr",
"lang": "Turkish",
"sense": "series of computer encoding standards",
"word": "Evrensel Kod"
},
{
"code": "tr",
"lang": "Turkish",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "uk",
"lang": "Ukrainian",
"roman": "Junikód",
"sense": "series of computer encoding standards",
"tags": [
"masculine"
],
"word": "Юніко́д"
},
{
"code": "ug",
"lang": "Uyghur",
"roman": "yunikod",
"sense": "series of computer encoding standards",
"word": "يۇنىكود"
},
{
"code": "vi",
"lang": "Vietnamese",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "cy",
"lang": "Welsh",
"sense": "series of computer encoding standards",
"word": "Unicode"
},
{
"code": "xan",
"lang": "Xamtanga",
"sense": "series of computer encoding standards",
"word": "ዩኒኮድ"
}
],
"wikipedia": [
"Unicode"
],
"word": "Unicode"
}
{
"categories": [
"English 3-syllable words",
"English entries with language name categories using raw markup",
"English lemmas",
"English nouns",
"English proper nouns",
"English terms prefixed with uni-",
"English terms with IPA pronunciation",
"English terms with audio links",
"English trademarks",
"English uncountable nouns"
],
"etymology_templates": [
{
"args": {
"1": "en",
"2": "uni",
"3": "code"
},
"expansion": "uni- + code",
"name": "prefix"
}
],
"etymology_text": "Published as a draft proposal in 1988, “intended to suggest a unique, unified, universal encoding”. From uni- + code.",
"head_templates": [
{
"args": {
"1": "-"
},
"expansion": "Unicode (uncountable)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"related": [
{
"word": "ASCII"
},
{
"word": "EBCDIC"
},
{
"word": "UTF-7"
},
{
"word": "UTF-8"
},
{
"word": "UTF-16"
}
],
"senses": [
{
"categories": [
"English informal terms",
"English terms with usage examples",
"en:Computing"
],
"examples": [
{
"text": "Since most users on the site are westerners, we have banned Unicode in all text input boxes.",
"type": "example"
}
],
"glosses": [
"Characters from a contextually different script, often used in a nonstandard fashion. Sometimes used as an antonym to the characters of the Latin alphabet."
],
"links": [
[
"computing",
"computing#Noun"
],
[
"Latin alphabet",
"Latin alphabet#English"
]
],
"raw_glosses": [
"(computing, by extension, informal) Characters from a contextually different script, often used in a nonstandard fashion. Sometimes used as an antonym to the characters of the Latin alphabet."
],
"tags": [
"broadly",
"informal",
"uncountable"
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
}
],
"sounds": [
{
"ipa": "/ˈjunɪˌkoʊd/",
"tags": [
"US"
]
},
{
"ipa": "/ˈjuːnɪˌkəʊd/",
"tags": [
"UK"
]
},
{
"audio": "en-uk-Unicode.ogg",
"mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/b/b2/En-uk-Unicode.ogg/En-uk-Unicode.ogg.mp3",
"ogg_url": "https://upload.wikimedia.org/wikipedia/commons/b/b2/En-uk-Unicode.ogg",
"tags": [
"UK"
],
"text": "Audio (UK)"
}
],
"wikipedia": [
"Unicode"
],
"word": "Unicode"
}
{
"head_templates": [
{
"args": {
"1": "pt",
"2": "proper noun",
"3": "",
"4": "",
"g": "m",
"g2": "",
"g3": "",
"head": ""
},
"expansion": "Unicode m",
"name": "head"
},
{
"args": {
"1": "m"
},
"expansion": "Unicode m",
"name": "pt-proper noun"
}
],
"lang": "Portuguese",
"lang_code": "pt",
"pos": "name",
"senses": [
{
"categories": [
"Portuguese entries with incorrect language header",
"Portuguese lemmas",
"Portuguese masculine nouns",
"Portuguese proper nouns",
"pt:Computing"
],
"glosses": [
"Unicode (series of computer encoding standards)"
],
"links": [
[
"computing",
"computing#Noun"
],
[
"Unicode",
"Unicode#English"
]
],
"raw_glosses": [
"(computing) Unicode (series of computer encoding standards)"
],
"tags": [
"masculine"
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
}
],
"word": "Unicode"
}
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2024-04-17 from the enwiktionary dump dated 2024-04-01 using wiktextract (0b52755 and 5cb0836). The data shown on this site has been post-processed and various details (e.g., extra categories) removed, some information disambiguated, and additional data merged from other sources. See the raw data download page for the unprocessed wiktextract data.
If you use this data in academic research, please cite Tatu Ylonen: Wiktextract: Wiktionary as Machine-Readable Structured Data, Proceedings of the 13th Conference on Language Resources and Evaluation (LREC), pp. 1317-1325, Marseille, 20-25 June 2022. Linking to the relevant page(s) under https://kaikki.org would also be greatly appreciated.