See character set in All languages combined, or Wiktionary
{
"forms": [
{
"form": "character sets",
"tags": [
"plural"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "character set (plural character sets)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"related": [
{
"_dis1": "50 50",
"word": "charset"
},
{
"_dis1": "50 50",
"word": "character encoding"
},
{
"_dis1": "50 50",
"word": "repertoire"
},
{
"_dis1": "50 50",
"word": "DRCS"
},
{
"_dis1": "50 50",
"word": "UCS"
}
],
"senses": [
{
"categories": [
{
"kind": "topical",
"langcode": "en",
"name": "Computing",
"orig": "en:Computing",
"parents": [
"Technology",
"All topics",
"Fundamental"
],
"source": "w"
},
{
"_dis": "51 49",
"kind": "other",
"name": "English entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "52 48",
"kind": "other",
"name": "Entries with translation boxes",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "53 47",
"kind": "other",
"name": "Pages with 1 entry",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "54 46",
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "57 43",
"kind": "other",
"name": "Terms with Danish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "52 48",
"kind": "other",
"name": "Terms with Esperanto translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "58 42",
"kind": "other",
"name": "Terms with Estonian translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "58 42",
"kind": "other",
"name": "Terms with Faroese translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "56 44",
"kind": "other",
"name": "Terms with Finnish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "58 42",
"kind": "other",
"name": "Terms with French translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "56 44",
"kind": "other",
"name": "Terms with German translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "57 43",
"kind": "other",
"name": "Terms with Hungarian translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "58 42",
"kind": "other",
"name": "Terms with Icelandic translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "53 47",
"kind": "other",
"name": "Terms with Irish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "57 43",
"kind": "other",
"name": "Terms with Mandarin translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "58 42",
"kind": "other",
"name": "Terms with Norwegian Bokmål translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "60 40",
"kind": "other",
"name": "Terms with Norwegian Nynorsk translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "53 47",
"kind": "other",
"name": "Terms with Portuguese translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "53 47",
"kind": "other",
"name": "Terms with Swedish translations",
"parents": [],
"source": "w+disamb"
}
],
"examples": [
{
"ref": "1995 May 2, Dan Connolly, “Character Set Considered Harmful, Internet Draft”, in HTML Working Group:",
"text": "In conventional mathematics terminology then, a \"character set\" is not just a set of characters, but a function whose domain is a set of integers, and whose range is a set of characters.",
"type": "quote"
}
],
"glosses": [
"The set of characters encoded by a given character encoding."
],
"id": "en-character_set-en-noun-s7Iey7uW",
"links": [
[
"computing",
"computing#Noun"
],
[
"character encoding",
"character encoding"
]
],
"raw_glosses": [
"(computing) The set of characters encoded by a given character encoding."
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
},
{
"categories": [
{
"kind": "topical",
"langcode": "en",
"name": "Computing",
"orig": "en:Computing",
"parents": [
"Technology",
"All topics",
"Fundamental"
],
"source": "w"
},
{
"_dis": "51 49",
"kind": "other",
"name": "English entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "52 48",
"kind": "other",
"name": "Entries with translation boxes",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "53 47",
"kind": "other",
"name": "Pages with 1 entry",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "54 46",
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "52 48",
"kind": "other",
"name": "Terms with Esperanto translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "53 47",
"kind": "other",
"name": "Terms with Irish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "53 47",
"kind": "other",
"name": "Terms with Portuguese translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "53 47",
"kind": "other",
"name": "Terms with Swedish translations",
"parents": [],
"source": "w+disamb"
}
],
"glosses": [
"A set of characters together with a character encoding."
],
"id": "en-character_set-en-noun-nsVVrghx",
"links": [
[
"computing",
"computing#Noun"
],
[
"character encoding",
"character encoding"
]
],
"raw_glosses": [
"(computing) A set of characters together with a character encoding."
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
}
],
"translations": [
{
"_dis1": "50 50",
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "zìfújí",
"sense": "set of characters in a character encoding",
"word": "字符集"
},
{
"_dis1": "50 50",
"code": "da",
"lang": "Danish",
"sense": "set of characters in a character encoding",
"tags": [
"neuter"
],
"word": "tegnsæt"
},
{
"_dis1": "50 50",
"code": "da",
"lang": "Danish",
"sense": "set of characters in a character encoding",
"word": "tegntabel"
},
{
"_dis1": "50 50",
"code": "eo",
"lang": "Esperanto",
"sense": "set of characters in a character encoding",
"word": "alfabeto"
},
{
"_dis1": "50 50",
"code": "eo",
"lang": "Esperanto",
"sense": "set of characters in a character encoding",
"word": "signaro"
},
{
"_dis1": "50 50",
"code": "et",
"lang": "Estonian",
"sense": "set of characters in a character encoding",
"word": "märgistik"
},
{
"_dis1": "50 50",
"code": "et",
"lang": "Estonian",
"sense": "set of characters in a character encoding",
"word": "märgirühm"
},
{
"_dis1": "50 50",
"code": "fo",
"lang": "Faroese",
"sense": "set of characters in a character encoding",
"word": "stavafeingi"
},
{
"_dis1": "50 50",
"code": "fo",
"lang": "Faroese",
"sense": "set of characters in a character encoding",
"word": "teknfeingi"
},
{
"_dis1": "50 50",
"code": "fo",
"lang": "Faroese",
"sense": "set of characters in a character encoding",
"word": "stavtalva"
},
{
"_dis1": "50 50",
"code": "fo",
"lang": "Faroese",
"sense": "set of characters in a character encoding",
"word": "tekntalva"
},
{
"_dis1": "50 50",
"code": "fi",
"lang": "Finnish",
"sense": "set of characters in a character encoding",
"word": "merkistö"
},
{
"_dis1": "50 50",
"code": "fr",
"lang": "French",
"sense": "set of characters in a character encoding",
"tags": [
"masculine"
],
"word": "jeu de caractères"
},
{
"_dis1": "50 50",
"code": "de",
"lang": "German",
"sense": "set of characters in a character encoding",
"word": "Zeichensatz"
},
{
"_dis1": "50 50",
"code": "hu",
"lang": "Hungarian",
"sense": "set of characters in a character encoding",
"word": "karakterkészlet"
},
{
"_dis1": "50 50",
"code": "is",
"lang": "Icelandic",
"sense": "set of characters in a character encoding",
"tags": [
"neuter"
],
"word": "stafasett"
},
{
"_dis1": "50 50",
"code": "is",
"lang": "Icelandic",
"sense": "set of characters in a character encoding",
"tags": [
"feminine"
],
"word": "stafatafla"
},
{
"_dis1": "50 50",
"code": "ga",
"lang": "Irish",
"sense": "set of characters in a character encoding",
"tags": [
"masculine"
],
"word": "tacar carachtar"
},
{
"_dis1": "50 50",
"code": "nb",
"lang": "Norwegian Bokmål",
"sense": "set of characters in a character encoding",
"word": "tegnsett"
},
{
"_dis1": "50 50",
"code": "nn",
"lang": "Norwegian Nynorsk",
"sense": "set of characters in a character encoding",
"word": "teiknsett"
},
{
"_dis1": "50 50",
"code": "pt",
"lang": "Portuguese",
"sense": "set of characters in a character encoding",
"tags": [
"masculine"
],
"word": "conjunto de caracteres"
},
{
"_dis1": "50 50",
"code": "sv",
"lang": "Swedish",
"sense": "set of characters in a character encoding",
"tags": [
"common-gender"
],
"word": "teckenuppsättning"
}
],
"word": "character set"
}
{
"categories": [
"English countable nouns",
"English entries with incorrect language header",
"English lemmas",
"English multiword terms",
"English nouns",
"Entries with translation boxes",
"Pages with 1 entry",
"Pages with entries",
"Terms with Danish translations",
"Terms with Esperanto translations",
"Terms with Estonian translations",
"Terms with Faroese translations",
"Terms with Finnish translations",
"Terms with French translations",
"Terms with German translations",
"Terms with Hungarian translations",
"Terms with Icelandic translations",
"Terms with Irish translations",
"Terms with Mandarin translations",
"Terms with Norwegian Bokmål translations",
"Terms with Norwegian Nynorsk translations",
"Terms with Portuguese translations",
"Terms with Swedish translations"
],
"forms": [
{
"form": "character sets",
"tags": [
"plural"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "character set (plural character sets)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"related": [
{
"word": "charset"
},
{
"word": "character encoding"
},
{
"word": "repertoire"
},
{
"word": "DRCS"
},
{
"word": "UCS"
}
],
"senses": [
{
"categories": [
"English terms with quotations",
"en:Computing"
],
"examples": [
{
"ref": "1995 May 2, Dan Connolly, “Character Set Considered Harmful, Internet Draft”, in HTML Working Group:",
"text": "In conventional mathematics terminology then, a \"character set\" is not just a set of characters, but a function whose domain is a set of integers, and whose range is a set of characters.",
"type": "quote"
}
],
"glosses": [
"The set of characters encoded by a given character encoding."
],
"links": [
[
"computing",
"computing#Noun"
],
[
"character encoding",
"character encoding"
]
],
"raw_glosses": [
"(computing) The set of characters encoded by a given character encoding."
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
},
{
"categories": [
"en:Computing"
],
"glosses": [
"A set of characters together with a character encoding."
],
"links": [
[
"computing",
"computing#Noun"
],
[
"character encoding",
"character encoding"
]
],
"raw_glosses": [
"(computing) A set of characters together with a character encoding."
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
}
],
"translations": [
{
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "zìfújí",
"sense": "set of characters in a character encoding",
"word": "字符集"
},
{
"code": "da",
"lang": "Danish",
"sense": "set of characters in a character encoding",
"tags": [
"neuter"
],
"word": "tegnsæt"
},
{
"code": "da",
"lang": "Danish",
"sense": "set of characters in a character encoding",
"word": "tegntabel"
},
{
"code": "eo",
"lang": "Esperanto",
"sense": "set of characters in a character encoding",
"word": "alfabeto"
},
{
"code": "eo",
"lang": "Esperanto",
"sense": "set of characters in a character encoding",
"word": "signaro"
},
{
"code": "et",
"lang": "Estonian",
"sense": "set of characters in a character encoding",
"word": "märgistik"
},
{
"code": "et",
"lang": "Estonian",
"sense": "set of characters in a character encoding",
"word": "märgirühm"
},
{
"code": "fo",
"lang": "Faroese",
"sense": "set of characters in a character encoding",
"word": "stavafeingi"
},
{
"code": "fo",
"lang": "Faroese",
"sense": "set of characters in a character encoding",
"word": "teknfeingi"
},
{
"code": "fo",
"lang": "Faroese",
"sense": "set of characters in a character encoding",
"word": "stavtalva"
},
{
"code": "fo",
"lang": "Faroese",
"sense": "set of characters in a character encoding",
"word": "tekntalva"
},
{
"code": "fi",
"lang": "Finnish",
"sense": "set of characters in a character encoding",
"word": "merkistö"
},
{
"code": "fr",
"lang": "French",
"sense": "set of characters in a character encoding",
"tags": [
"masculine"
],
"word": "jeu de caractères"
},
{
"code": "de",
"lang": "German",
"sense": "set of characters in a character encoding",
"word": "Zeichensatz"
},
{
"code": "hu",
"lang": "Hungarian",
"sense": "set of characters in a character encoding",
"word": "karakterkészlet"
},
{
"code": "is",
"lang": "Icelandic",
"sense": "set of characters in a character encoding",
"tags": [
"neuter"
],
"word": "stafasett"
},
{
"code": "is",
"lang": "Icelandic",
"sense": "set of characters in a character encoding",
"tags": [
"feminine"
],
"word": "stafatafla"
},
{
"code": "ga",
"lang": "Irish",
"sense": "set of characters in a character encoding",
"tags": [
"masculine"
],
"word": "tacar carachtar"
},
{
"code": "nb",
"lang": "Norwegian Bokmål",
"sense": "set of characters in a character encoding",
"word": "tegnsett"
},
{
"code": "nn",
"lang": "Norwegian Nynorsk",
"sense": "set of characters in a character encoding",
"word": "teiknsett"
},
{
"code": "pt",
"lang": "Portuguese",
"sense": "set of characters in a character encoding",
"tags": [
"masculine"
],
"word": "conjunto de caracteres"
},
{
"code": "sv",
"lang": "Swedish",
"sense": "set of characters in a character encoding",
"tags": [
"common-gender"
],
"word": "teckenuppsättning"
}
],
"word": "character set"
}
Download raw JSONL data for character set meaning in English (4.9kB)
This page is a part of the kaikki.org machine-readable English dictionary. This dictionary is based on structured data extracted on 2024-11-06 from the enwiktionary dump dated 2024-10-02 using wiktextract (fbeafe8 and 7f03c9b). 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.