4957: Update charabia feature flags r=dureuill a=ManyTheFish

# Pull Request

Add charabia's `turkish` feature flag into Meilisearch default tokenization flag



[All tests pipeline](https://github.com/meilisearch/meilisearch/actions/runs/11030036031)

Co-authored-by: ManyTheFish <many@meilisearch.com>
This commit is contained in:
meili-bors[bot] 2024-09-26 20:19:21 +00:00 committed by GitHub
commit 71b364286b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 9 additions and 11 deletions

View File

@ -66,5 +66,8 @@ khmer = ["milli/khmer"]
vietnamese = ["milli/vietnamese"]
# force swedish character recomposition
swedish-recomposition = ["milli/swedish-recomposition"]
# force german character recomposition
# allow german tokenization
german = ["milli/german"]
# allow turkish normalization
turkish = ["milli/turkish"]

View File

@ -154,6 +154,7 @@ khmer = ["meilisearch-types/khmer"]
vietnamese = ["meilisearch-types/vietnamese"]
swedish-recomposition = ["meilisearch-types/swedish-recomposition"]
german = ["meilisearch-types/german"]
turkish = ["meilisearch-types/turkish"]
[package.metadata.mini-dashboard]
assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.14/build.zip"

View File

@ -98,16 +98,7 @@ rand = { version = "0.8.5", features = ["small_rng"] }
[features]
all-tokenizations = [
"charabia/chinese",
"charabia/hebrew",
"charabia/japanese",
"charabia/thai",
"charabia/korean",
"charabia/greek",
"charabia/khmer",
"charabia/vietnamese",
"charabia/swedish-recomposition",
"charabia/german-segmentation",
"charabia/default",
]
# Use POSIX semaphores instead of SysV semaphores in LMDB
@ -146,5 +137,8 @@ german = ["charabia/german-segmentation"]
# force swedish character recomposition
swedish-recomposition = ["charabia/swedish-recomposition"]
# allow turkish specialized tokenization
turkish = ["charabia/turkish"]
# allow CUDA support, see <https://github.com/meilisearch/meilisearch/issues/4306>
cuda = ["candle-core/cuda"]