notes documenting input and output objects of gendictionary compiler

This commit is contained in:
apex 2025-06-25 02:16:26 -04:00
parent a7e6424882
commit c0a73acd03

93
notes.jsonc Normal file
View File

@ -0,0 +1,93 @@
/*
THIS FILE IS NOT VALID JSON, ITS JUST NOTES ABOUT THE EXPECTED
STRUCTURE IN OBJECTS LOCATED IN A KAIKKI DICTIONARY
*/
//relevant object data to extract
{
"word": string,
"lang_code": string, //en, es, pt, etc...
"pos": string, //part of speech, noun, verb, etc
"senses": [ //various definitions of the word
{
"glosses": [ //actual definition
string,
]
}
],
"sounds": [
{
"tags": [
//recieved pronunciation -important
//US
],
"ipa": string
//OR
"enpr": string
},
{
"audio": string,
"ogg_url": URLSTRING
},
{
"rhymes": string
},
{
"homophone": string
},
],
}
//PERMUTE TO >
// {{some_path}}/dictionary/{{lang_code}}/{{word}}/{{pos}}/definitions.json
// {{some_path}}/dictionary/{{lang_code}}/{{word}}/{{pos}}/sounds.json
//definitions.json
{
"glosses": [ //combined list of glosses
]
}
//sounds.json
{
"pronunciations": [ //copies of pronunciation objects from sounds lists
],
"audios": [ //copies of audio objects from sounds lists
],
"rhymes": [ //collections of strings from rhyme key of rhyme object from sounds lists
],
"homophones": [ //same as rhymes but with homphones
]
}
//thesaurus.json
{
synonyms: [
],
antynoms: [
]
}