diff --git a/website/meta/universe.json b/website/meta/universe.json index 6278dd489..5b5da84b9 100644 --- a/website/meta/universe.json +++ b/website/meta/universe.json @@ -1,3 +1,4 @@ + { "resources": [ { @@ -4517,6 +4518,21 @@ "website": "https://redfield.ai" }, "category": ["standalone"] + }, + { + "id": "quelquhui", + "title": "quelquhui", + "slogan": "tokenizer for contemporary french", + "description": "A tokenizer for french that handles inword parentheses like in _(b)rouille_, inclusive language (won't split _relecteur.rice.s_,but will split _mais.maintenant_), hyphens (split _peut-on_, or _pouvons-vous_ but not _tubulu-pimpant_), apostrophes (split _j'arrive_ or _j'arrivons_, but not _aujourd'hui_ or _r'garder_), emoticons, text-emoji (_:happy:_), urls, mails, ...", + "github": "thjbdvlt/quelquhui", + "code_example": ["import spacy", "import quelquhui", "nlp = spacy.load('fr_core_news_lg')", "nlp.tokenizer = quelquhui.Toquenizer(nlp.vocab)"], + "code_language": "python", + "author": "thjbdvlt", + "author_links": { + "github": "thjbdvlt" + }, + "category": ["pipeline"], + "tags": ["tokenizer", "french"] } ], @@ -4608,3 +4624,4 @@ } ] } +