From c0a73acd0315734ecf2b1f6453886e850f779cb0 Mon Sep 17 00:00:00 2001 From: apex Date: Wed, 25 Jun 2025 02:16:26 -0400 Subject: [PATCH] notes documenting input and output objects of gendictionary compiler --- notes.jsonc | 93 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 93 insertions(+) create mode 100644 notes.jsonc diff --git a/notes.jsonc b/notes.jsonc new file mode 100644 index 0000000..fed255e --- /dev/null +++ b/notes.jsonc @@ -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: [ + + ] +}