Patch-Source: https://github.com/meilisearch/meilisearch/pull/3687 (rebased)
--
From 2fd515a34c8a9648f32320ececa09d68cc0b7719 Mon Sep 17 00:00:00 2001
From: Jakub Jirutka <jakub@jirutka.cz>
Date: Mon, 24 Apr 2023 00:26:08 +0200
Subject: [PATCH] Allow to disable specialized tokenizations (again)

In PR #2773, I added the `chinese`, `hebrew`, `japanese` and `thai`
feature flags to allow melisearch to be built without huge specialed
tokenizations that took up 90% of the melisearch binary size.
Unfortunately, due to some recent changes, this doesn't work anymore.
The problem lies in excessive use of the `default` feature flag, which
infects the dependency graph.

Instead of adding `default-features = false` here and there, it's easier
and more future-proof to not declare `default` in `milli` and
`meilisearch-types`. I've renamed it to `all-tokenizers`, which also
makes it a bit clearer what it's about.

diff --git a/benchmarks/Cargo.toml b/benchmarks/Cargo.toml
index 5203a76014..0de81413b5 100644
--- a/benchmarks/Cargo.toml
+++ b/benchmarks/Cargo.toml
@@ -13,7 +13,7 @@ license.workspace = true
 [dependencies]
 anyhow = "1.0.65"
 csv = "1.1.6"
-milli = { path = "../milli", default-features = false }
+milli = { path = "../milli" }
 mimalloc = { version = "0.1.29", default-features = false }
 serde_json = { version = "1.0.85", features = ["preserve_order"] }
 
@@ -31,7 +31,7 @@ flate2 = "1.0.24"
 reqwest = { version = "0.11.12", features = ["blocking", "rustls-tls"], default-features = false }
 
 [features]
-default = ["milli/default"]
+default = ["milli/all-tokenizations"]
 
 [[bench]]
 name = "search_songs"
diff --git a/meilisearch-types/Cargo.toml b/meilisearch-types/Cargo.toml
index 9828c5f493..b8a3f3bb44 100644
--- a/meilisearch-types/Cargo.toml
+++ b/meilisearch-types/Cargo.toml
@@ -22,7 +22,7 @@ file-store = { path = "../file-store" }
 flate2 = "1.0.24"
 fst = "0.4.7"
 memmap2 = "0.5.7"
-milli = { path = "../milli", default-features = false }
+milli = { path = "../milli" }
 roaring = { version = "0.10.0", features = ["serde"] }
 serde = { version = "1.0.145", features = ["derive"] }
 serde-cs = "0.2.4"
@@ -40,7 +40,7 @@ meili-snap = { path = "../meili-snap" }
 
 [features]
 # all specialized tokenizations
-default = ["milli/default"]
+all-tokenizations = ["milli/all-tokenizations"]
 
 # chinese specialized tokenization
 chinese = ["milli/chinese"]
diff --git a/meilisearch/Cargo.toml b/meilisearch/Cargo.toml
index d4b7723224..c9aa7850ff 100644
--- a/meilisearch/Cargo.toml
+++ b/meilisearch/Cargo.toml
@@ -106,7 +106,7 @@ vergen = { version = "7.4.2", default-features = false, features = ["git"] }
 zip = { version = "0.6.2", optional = true }
 
 [features]
-default = ["analytics", "meilisearch-types/default", "mini-dashboard"]
+default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
 analytics = ["segment"]
 mini-dashboard = ["actix-web-static-files", "static-files", "anyhow", "cargo_toml", "hex", "reqwest", "sha-1", "tempfile", "zip"]
 chinese = ["meilisearch-types/chinese"]
--- a/milli/Cargo.toml
+++ b/milli/Cargo.toml
@@ -19 +19 @@
-charabia = { version = "0.7.1", default-features = false }
+charabia = { version = "0.7.2", default-features = false }
@@ -68,7 +68,7 @@ rand = {version = "0.8.5", features = ["small_rng"] }
 fuzzcheck = "0.12.1"
 
 [features]
-default = [ "charabia/default" ]
+all-tokenizations = [ "charabia/default" ]
 
 # Use POSIX semaphores instead of SysV semaphores in LMDB
 # For more information on this feature, see heed's Cargo.toml
--- a/milli/src/update/index_documents/mod.rs
+++ b/milli/src/update/index_documents/mod.rs
@@ -1558,7 +1558,7 @@
     use super::*;
     use crate::index::tests::TempIndex;
 
-    #[cfg(feature = "default")]
+    #[cfg(feature = "japanese")]
     #[test]
     fn test_kanji_language_detection() {
         let index = TempIndex::new();
--- a/milli/src/search/mod.rs
+++ b/milli/src/search/mod.rs
@@ -451,7 +451,7 @@
     use super::*;
     use crate::index::tests::TempIndex;
 
-    #[cfg(feature = "default")]
+    #[cfg(feature = "japanese")]
     #[test]
     fn test_kanji_language_detection() {
         let index = TempIndex::new();