From a9ca135ad5111463b8a4676c377f42350e079df7 Mon Sep 17 00:00:00 2001 From: Virgil Date: Thu, 2 Apr 2026 01:49:24 +0000 Subject: [PATCH] feat(reversal): expand French article matching Co-Authored-By: Virgil --- reversal/tokeniser.go | 2 +- reversal/tokeniser_test.go | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/reversal/tokeniser.go b/reversal/tokeniser.go index b00cfbf..f49887b 100644 --- a/reversal/tokeniser.go +++ b/reversal/tokeniser.go @@ -632,7 +632,7 @@ func (t *Tokeniser) MatchArticle(word string) (string, bool) { } if t.isFrenchLanguage() { switch lower { - case "l'", "l’", "d'", "d’", "j'", "j’", "m'", "m’", "t'", "t’", "s'", "s’", "n'", "n’", "c'", "c’", "qu'", "qu’", "de l'", "de l’", "les", "au", "aux", "du": + case "l'", "l’", "d'", "d’", "j'", "j’", "m'", "m’", "t'", "t’", "s'", "s’", "n'", "n’", "c'", "c’", "qu'", "qu’", "de l'", "de l’", "de la", "les", "au", "aux", "du": return "definite", true case "un", "une", "des": return "indefinite", true diff --git a/reversal/tokeniser_test.go b/reversal/tokeniser_test.go index 5fb3a05..be505fc 100644 --- a/reversal/tokeniser_test.go +++ b/reversal/tokeniser_test.go @@ -220,6 +220,7 @@ func TestTokeniser_MatchArticle_FrenchGendered(t *testing.T) { {"la", "definite", true}, {"Le", "definite", true}, {"La", "definite", true}, + {"de la", "definite", true}, {"de l'", "definite", true}, {"de l’", "definite", true}, {"un", "indefinite", true}, -- 2.45.3