From e7f3909ae96cb0a1e8f1ed4c0906fd19da25af8a Mon Sep 17 00:00:00 2001 From: Tatsunori Uchino Date: Wed, 9 Oct 2024 20:50:36 +0900 Subject: [PATCH 1/2] Update wana_kana to 4.0.0 --- charabia/Cargo.toml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/charabia/Cargo.toml b/charabia/Cargo.toml index c6b53b9..01e987f 100644 --- a/charabia/Cargo.toml +++ b/charabia/Cargo.toml @@ -26,7 +26,7 @@ lindera = { version = "=0.32.2", default-features = false, optional = true } pinyin = { version = "0.10", default-features = false, features = [ "with_tone", ], optional = true } -wana_kana = { version = "3.0.0", optional = true } +wana_kana = { version = "4.0.0", optional = true } unicode-normalization = "0.1.23" irg-kvariants = { path = "../irg-kvariants", version = "=0.1.1" } From bacd1c19b46eea6c345d9016f9ab588c2382a836 Mon Sep 17 00:00:00 2001 From: Tatsunori Uchino Date: Thu, 10 Oct 2024 22:54:59 +0900 Subject: [PATCH 2/2] Enable `japanese-transliteration` by default --- charabia/Cargo.toml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/charabia/Cargo.toml b/charabia/Cargo.toml index 01e987f..af14379 100644 --- a/charabia/Cargo.toml +++ b/charabia/Cargo.toml @@ -43,7 +43,7 @@ chinese-normalization-pinyin = ["dep:pinyin", "chinese-normalization"] hebrew = [] # allow japanese specialized tokenization -japanese = ["japanese-segmentation-unidic"] +japanese = ["japanese-segmentation-unidic", "japanese-transliteration"] japanese-segmentation-ipadic = ["lindera/ipadic", "lindera/compress"] japanese-segmentation-unidic = ["lindera/unidic", "lindera/compress"] japanese-transliteration = ["dep:wana_kana"]