From b90e33469e1870b38bf70712cfd1b5a021d5fe24 Mon Sep 17 00:00:00 2001
From: thjbdvlt <109964512+thjbdvlt@users.noreply.github.com>
Date: Tue, 10 Sep 2024 14:17:33 +0200
Subject: [PATCH] universe-package-quelquhui (#13514) [ci skip]

Co-authored-by: Ines Montani <ines@ines.io>
---
 website/meta/universe.json | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/website/meta/universe.json b/website/meta/universe.json
index 46be50665..ec8887276 100644
--- a/website/meta/universe.json
+++ b/website/meta/universe.json
@@ -4552,6 +4552,26 @@
             },
             "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 and more.",
+            "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"]
+        },
         {
             "id": "gliner-spacy",
             "title": "GLiNER spaCy Wrapper",
@@ -4579,7 +4599,6 @@
             "category": ["pipeline"],
             "tags": ["NER"]
         }
-        
     ],
 
     "categories": [