|
|
|
On distinguera dans les documents les notions de "graphie" et "d'entrée lexicale" :
|
|
|
|
|
|
|
|
- nous appelons une **graphie**, une chaîne de caractères correspondant une forme écrite
|
|
|
|
- un **lemme** est une forme radicale d'un mot, sans modifications orthographiques ou grammaticales ("cheval" plutôt que "chevaux", "manger" plutôt que "mangerons")
|
|
|
|
- une **entrée lexicale** est un lemme complété par un certain nombre d'informations sur chacune des acceptions de celui-ci.
|
|
|
|
- un **mot-vedette** est une forme radicale d'un mot, sans modifications orthographiques ou grammaticales ("cheval" plutôt que "chevaux", "manger" plutôt que "mangerons")
|
|
|
|
- une **entrée lexicale** est un mot-vedette complété par un certain nombre d'informations sur chacune des acceptions de celui-ci.
|
|
|
|
|
|
|
|
## Informations relatives aux graphies
|
|
|
|
|
| ... | ... | @@ -23,78 +23,104 @@ Une entrée lexicale est constituée de : |
|
|
|
|
|
|
|
```json
|
|
|
|
{
|
|
|
|
"Lemma" : "sleep",
|
|
|
|
"Character" : { "graphical etymology" : "愛",
|
|
|
|
{
|
|
|
|
"Headword":"sleep",
|
|
|
|
"Items":[
|
|
|
|
{
|
|
|
|
"PartOfSpeech":"verb",
|
|
|
|
"Sense":{
|
|
|
|
"Etymology":"blabla",
|
|
|
|
"Translations":[
|
|
|
|
"translation1",
|
|
|
|
"...",
|
|
|
|
"translationn"
|
|
|
|
],
|
|
|
|
"Character":{
|
|
|
|
"graphical etymology":"愛",
|
|
|
|
"in composition":"blabla",
|
|
|
|
"classification":"blabla",
|
|
|
|
"dictionnary ref" : ["RDO153", "blabla", "blabla"...]
|
|
|
|
} // Only for chinese and japanese
|
|
|
|
["PartOfSpeech1" : { "Title" : "verb",
|
|
|
|
"Sense1" : { "Etymology" : "blabla",
|
|
|
|
"Translations" : ["translation1", ..., "translationn"],
|
|
|
|
"Pronunciation" : [{ "api1" : "\ˈsliːp\ ",
|
|
|
|
"dictionnary ref":[
|
|
|
|
"RDO153",
|
|
|
|
"blabla",
|
|
|
|
"blabla"
|
|
|
|
],
|
|
|
|
"hiragana":"",
|
|
|
|
"katakana":"",
|
|
|
|
"bopomofo":"",
|
|
|
|
"pinyin":"",
|
|
|
|
"romaji":""
|
|
|
|
},
|
|
|
|
"Pronunciation":[
|
|
|
|
{
|
|
|
|
"api1":"\\ˈsliːp\\ ",
|
|
|
|
"accent1":"RP",
|
|
|
|
"other transcriptions1" : "", //pinyin, bopomofo, hiragana....
|
|
|
|
"url1": "https://upload.wikimedia.org/wikipedia/commons/1/19/LL-Q1860_%28eng%29-Back_ache-water.wav"},
|
|
|
|
...
|
|
|
|
{"apik" : "\ˈsliːp\ ",
|
|
|
|
"accentk" : "RP",
|
|
|
|
"other transcriptionsk" : "", //pinyin, bopomofo, hiragana....
|
|
|
|
"urlk": "https://upload.wikimedia.org/wikipedia/commons/1/19/LL-Q1860_%28eng%29-Back_ache-water.wav"}]
|
|
|
|
|
|
|
|
["Definition1" : { "Image" : "Stilles Mineralwasser.jpg"
|
|
|
|
"Def" : "blabla",
|
|
|
|
"Examples" : ["ex1":"blabla", "ex2":"blabla", ... "exn":"blabla"],
|
|
|
|
"sub" : [{ "subdef1" : "blabla",
|
|
|
|
"subex1" : [ "subexa", "subexb", ..., "subexz"],
|
|
|
|
....
|
|
|
|
"subdefn" : "blabla",
|
|
|
|
"subexn" : [ "subexa", "subexb", ..., "subexz"],
|
|
|
|
}]
|
|
|
|
"url1":"https://upload.wikimedia.org/wikipedia/commons/1/19/LL-Q1860_%28eng%29-Back_ache-water.wav"
|
|
|
|
},
|
|
|
|
...
|
|
|
|
"Definitionn" : { "Image" : "Stilles Mineralwasser.jpg"
|
|
|
|
"..."
|
|
|
|
],
|
|
|
|
"Definitions":[
|
|
|
|
{
|
|
|
|
"Image":[
|
|
|
|
"Stilles Mineralwasser.jpg",
|
|
|
|
"..."
|
|
|
|
],
|
|
|
|
"Def":"blabla",
|
|
|
|
"Examples" : ["ex1":"blabla", "ex2":"blabla", ... "exn":"blabla"],
|
|
|
|
"sub" : [{ "subdef1" : "blabla",
|
|
|
|
"subex1" : [ "subexa", "subexb", ..., "subexz"],
|
|
|
|
....
|
|
|
|
"subdefn" : "blabla",
|
|
|
|
"subexn" : [ "subexa", "subexb", ..., "subexz"],
|
|
|
|
}]
|
|
|
|
"Examples":[
|
|
|
|
"blabla",
|
|
|
|
"blabli",
|
|
|
|
"...",
|
|
|
|
"blablou"
|
|
|
|
],
|
|
|
|
"subSense":[
|
|
|
|
{
|
|
|
|
"subdef":"blabla",
|
|
|
|
"subex":[
|
|
|
|
"subexa",
|
|
|
|
"subexb",
|
|
|
|
"...",
|
|
|
|
"subexz"
|
|
|
|
]
|
|
|
|
}
|
|
|
|
]}
|
|
|
|
...
|
|
|
|
"Sensen" : {"repeat"}
|
|
|
|
]
|
|
|
|
}
|
|
|
|
"PartOfSpeechn" : {"repeat"}
|
|
|
|
]
|
|
|
|
// Comment s'adapter à la généricité des données ?
|
|
|
|
"User-defined fields 1"
|
|
|
|
"User-defined fields 2"
|
|
|
|
"User-defined fields 3"
|
|
|
|
"User-defined fields 4"
|
|
|
|
"User-defined fields 5"
|
|
|
|
"Supplementary field for devs 1"
|
|
|
|
"Supplementary field for devs 2"
|
|
|
|
"Supplementary field for devs 3"
|
|
|
|
"Supplementary field for devs 4"
|
|
|
|
"Supplementary field for devs 5"
|
|
|
|
...
|
|
|
|
"Supplementary field for devs 10"
|
|
|
|
}
|
|
|
|
}
|
|
|
|
]
|
|
|
|
}
|
|
|
|
|
|
|
|
/*adapter à la généricité des données ?
|
|
|
|
\"User-defined fields 1\"
|
|
|
|
\"User-defined fields 2\"
|
|
|
|
\"User-defined fields 3\"
|
|
|
|
\"User-defined fields 4\"
|
|
|
|
\"User-defined fields 5\"
|
|
|
|
\"Supplementary field for devs 1\"
|
|
|
|
\"Supplementary field for devs 2\"
|
|
|
|
\"Supplementary field for devs 3\"
|
|
|
|
\"Supplementary field for devs 4\"
|
|
|
|
\"Supplementary field for devs 5\"
|
|
|
|
...
|
|
|
|
\"Supplementary field for devs 10\ */
|
|
|
|
```
|
|
|
|
|
|
|
|
## Structure minimale d'une entrée lexicale
|
|
|
|
|
|
|
|
```json
|
|
|
|
"lemma"
|
|
|
|
"partOfSpeech" :
|
|
|
|
{
|
|
|
|
"sense" :
|
|
|
|
"Headword":"sleep",
|
|
|
|
"Items":[
|
|
|
|
{
|
|
|
|
"PartOfSpeech":"verb",
|
|
|
|
"Sense":{
|
|
|
|
"Definitions":[
|
|
|
|
{
|
|
|
|
"definition"
|
|
|
|
"Def":"blabla"
|
|
|
|
}
|
|
|
|
]
|
|
|
|
}
|
|
|
|
}
|
|
|
|
]
|
|
|
|
}
|
|
|
|
```
|
|
|
|
|
| ... | ... | |
