Merge #2772 #2773

2772: Improve issue template display to avoid support in Meilisearch issues r=curquiza a=curquiza

Move the support line higher to make it more visible
Like this: https://github.com/meilisearch/meilisearch/discussions/2780

2773: Allow building without specialized tokenizations r=curquiza a=jirutka

Fixes #2774

(Some of) these specialized tokenizations include huge dictionaries that currently account for 90% (!) of the meilisearch binary size.

This commit adds `chinese`, `hebrew`, `japanese`, and `thai` feature flags that are propagated via `milli` down to the `charabia` crate. To keep it backwards compatible, they are enabled by default.

Related to meilisearch/milli#632

Co-authored-by: Clémentine Urquizar - curqui <clementine@meilisearch.com>
Co-authored-by: Jakub Jirutka <jakub@jirutka.cz>

.github/ISSUE_TEMPLATE/config.yml

@@ -1,13 +1,13 @@
 contact_links:
+  - name: Support questions & other
+    url: https://github.com/meilisearch/meilisearch/discussions/new
+    about: For any other question, open a discussion in this repository
   - name: Language support request & feedback
     url: https://github.com/meilisearch/product/discussions/categories/feedback-feature-proposal?discussions_q=label%3Aproduct%3Acore%3Atokenizer+category%3A%22Feedback+%26+Feature+Proposal%22
     about:  The requests and feedback regarding Language support are not managed in this repository. Please upvote the related discussion in our dedicated product repository or open a new one if it doesn't exist.
-  - name: Feature request & feedback
+  - name: Any other feature request & feedback
     url: https://github.com/meilisearch/product/discussions/categories/feedback-feature-proposal
     about: The feature requests and feedback regarding the already existing features are not managed in this repository. Please open a discussion in our dedicated product repository
   - name: Documentation issue
     url: https://github.com/meilisearch/documentation/issues/new
     about: For documentation issues, open an issue or a PR in the documentation repository
-  - name: Support questions & other
-    url: https://github.com/meilisearch/meilisearch/discussions/new
-    about: For any other question, open a discussion in this repository

Cargo.lock

@@ -1119,8 +1119,8 @@ dependencies = [
 
 [[package]]
 name = "filter-parser"
-version = "0.33.0"
-source = "git+https://github.com/meilisearch/milli.git?tag=v0.33.0#a79ff8a1a98a807f40f970131c8de2ab11560de5"
+version = "0.33.4"
+source = "git+https://github.com/meilisearch/milli.git?tag=v0.33.4#4fc6331cb6526c07f3137584564cfe3493fb25bd"
 dependencies = [
  "nom",
  "nom_locate",
@@ -1144,8 +1144,8 @@ dependencies = [
 
 [[package]]
 name = "flatten-serde-json"
-version = "0.33.0"
-source = "git+https://github.com/meilisearch/milli.git?tag=v0.33.0#a79ff8a1a98a807f40f970131c8de2ab11560de5"
+version = "0.33.4"
+source = "git+https://github.com/meilisearch/milli.git?tag=v0.33.4#4fc6331cb6526c07f3137584564cfe3493fb25bd"
 dependencies = [
  "serde_json",
 ]
@@ -1657,8 +1657,8 @@ dependencies = [
 
 [[package]]
 name = "json-depth-checker"
-version = "0.33.0"
-source = "git+https://github.com/meilisearch/milli.git?tag=v0.33.0#a79ff8a1a98a807f40f970131c8de2ab11560de5"
+version = "0.33.4"
+source = "git+https://github.com/meilisearch/milli.git?tag=v0.33.4#4fc6331cb6526c07f3137584564cfe3493fb25bd"
 dependencies = [
  "serde_json",
 ]
@@ -2195,8 +2195,8 @@ dependencies = [
 
 [[package]]
 name = "milli"
-version = "0.33.0"
-source = "git+https://github.com/meilisearch/milli.git?tag=v0.33.0#a79ff8a1a98a807f40f970131c8de2ab11560de5"
+version = "0.33.4"
+source = "git+https://github.com/meilisearch/milli.git?tag=v0.33.4#4fc6331cb6526c07f3137584564cfe3493fb25bd"
 dependencies = [
  "bimap",
  "bincode",

meilisearch-auth/Cargo.toml

@@ -7,7 +7,7 @@ edition = "2021"
 enum-iterator = "0.7.0"
 hmac = "0.12.1"
 meilisearch-types = { path = "../meilisearch-types" }
-milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.33.0" }
+milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.33.4", default-features = false }
 rand = "0.8.4"
 serde = { version = "1.0.136", features = ["derive"] }
 serde_json = { version = "1.0.85", features = ["preserve_order"] }

meilisearch-http/Cargo.toml

@@ -46,7 +46,7 @@ jsonwebtoken = "8.0.1"
 log = "0.4.14"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-meilisearch-lib = { path = "../meilisearch-lib" }
+meilisearch-lib = { path = "../meilisearch-lib", default-features = false }
 mimalloc = { version = "0.1.29", default-features = false }
 mime = "0.3.16"
 num_cpus = "1.13.1"
@@ -90,7 +90,7 @@ urlencoding = "2.1.0"
 yaup = "0.2.0"
 
 [features]
-default = ["analytics", "mini-dashboard"]
+default = ["analytics", "meilisearch-lib/default", "mini-dashboard"]
 metrics = ["prometheus"]
 analytics = ["segment"]
 mini-dashboard = [
@@ -104,6 +104,10 @@ mini-dashboard = [
     "tempfile",
     "zip",
 ]
+chinese = ["meilisearch-lib/chinese"]
+hebrew = ["meilisearch-lib/hebrew"]
+japanese = ["meilisearch-lib/japanese"]
+thai = ["meilisearch-lib/thai"]
 
 [package.metadata.mini-dashboard]
 assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.1/build.zip"

meilisearch-lib/Cargo.toml

@@ -28,7 +28,7 @@ lazy_static = "1.4.0"
 log = "0.4.14"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.33.0" }
+milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.33.4", default-features = false }
 mime = "0.3.16"
 num_cpus = "1.13.1"
 obkv = "0.2.0"
@@ -64,3 +64,19 @@ nelson = { git = "https://github.com/meilisearch/nelson.git", rev = "675f1388554
 paste = "1.0.6"
 proptest = "1.0.0"
 proptest-derive = "0.3.0"
+
+[features]
+# all specialized tokenizations
+default = ["milli/default"]
+
+# chinese specialized tokenization
+chinese = ["milli/chinese"]
+
+# hebrew specialized tokenization
+hebrew = ["milli/hebrew"]
+
+# japanese specialized tokenization
+japanese = ["milli/japanese"]
+
+# thai specialized tokenization
+thai = ["milli/thai"]