Rollup merge of #104047 - crlf0710:icu_based_list_formatting, r=davidtwco

Diagnostics `icu4x` based list formatting.

This adds a new kind of `DiagnosticArg` and add the ability to convert it to a `FluentValue::Custom`. When emitting fluent output, it makes use of `ListFormatter` from `icu4x` project to convert it to localized version of list following the fluent locale, as a kind of eager translation.

Tested locally with locales like `en`, `ja`, etc, and they work fine. <del>Though neither `zh-CN` nor `zh-Hans` works correctly, it seems they fallback to `und` locale somehow, emitting only comma-based list. I believe this is an internal issue of `icu4x` itself.</del>(Works fine after #104047 (comment))

Would love to hear what others think.

r? `@davidtwco`
cc `@Manishearth`

Author: Manishearth

Cargo.lock

@@ -211,7 +211,7 @@ checksum = "ba3569f383e8f1598449f1a423e72e99569137b47740b1da11ef19af3d5c3223"
 dependencies = [
  "lazy_static",
  "memchr",
- "regex-automata",
+ "regex-automata 0.1.10",
 ]
 
 [[package]]
@@ -1710,6 +1710,73 @@ version = "2.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3c1ad908cc71012b7bea4d0c53ba96a8cba9962f048fa68d143376143d863b7a"
 
+[[package]]
+name = "icu_list"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c40218275f081c4493f190357c5395647b06734c2dc3dcb41cc099a0f60168b1"
+dependencies = [
+ "displaydoc",
+ "icu_locid",
+ "icu_provider",
+ "regex-automata 0.2.0",
+ "writeable",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_locid"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "34b3de5d99a0e275fe6193b9586dbf37364daebc0d39c89b5cf8376a53b789e8"
+dependencies = [
+ "displaydoc",
+ "litemap",
+ "tinystr",
+ "writeable",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_provider"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2f911086e3c521a8a824d4f8bfd87769645ced2f07ff913b521c0d793be07100"
+dependencies = [
+ "displaydoc",
+ "icu_locid",
+ "icu_provider_macros",
+ "stable_deref_trait",
+ "writeable",
+ "yoke",
+ "zerofrom",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_provider_adapters"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "980c71d8a91b246ebbb97847178a4b816eea39d1d550c70ee566384555bb6545"
+dependencies = [
+ "icu_locid",
+ "icu_provider",
+ "tinystr",
+ "yoke",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_provider_macros"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "38cf6f5b65cf81f0b4298da647101acbfe6ae0e25263f92bd7a22597e9d6d606"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "idna"
 version = "0.2.0"
@@ -2037,6 +2104,12 @@ dependencies = [
  "walkdir",
 ]
 
+[[package]]
+name = "litemap"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f34a3f4798fac63fb48cf277eefa38f94d3443baff555bb98e4f56bc9092368e"
+
 [[package]]
 name = "lld-wrapper"
 version = "0.1.0"
@@ -2103,7 +2176,7 @@ version = "0.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8263075bb86c5a1b1427b5ae862e8889656f126e9f77c484496e8b47cf5c5558"
 dependencies = [
- "regex-automata",
+ "regex-automata 0.1.10",
 ]
 
 [[package]]
@@ -2930,6 +3003,15 @@ dependencies = [
  "regex-syntax",
 ]
 
+[[package]]
+name = "regex-automata"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e9368763f5a9b804326f3af749e16f9abf378d227bcdee7634b13d8f17793782"
+dependencies = [
+ "memchr",
+]
+
 [[package]]
 name = "regex-syntax"
 version = "0.6.26"
@@ -3204,6 +3286,18 @@ dependencies = [
  "rustc_span",
 ]
 
+[[package]]
+name = "rustc_baked_icu_data"
+version = "0.0.0"
+dependencies = [
+ "icu_list",
+ "icu_locid",
+ "icu_provider",
+ "icu_provider_adapters",
+ "litemap",
+ "zerovec",
+]
+
 [[package]]
 name = "rustc_borrowck"
 version = "0.0.0"
@@ -3424,13 +3518,18 @@ version = "0.0.0"
 dependencies = [
  "fluent-bundle",
  "fluent-syntax",
+ "icu_list",
+ "icu_locid",
+ "icu_provider_adapters",
  "intl-memoizer",
+ "rustc_baked_icu_data",
  "rustc_data_structures",
  "rustc_macros",
  "rustc_serialize",
  "rustc_span",
  "tracing",
  "unic-langid",
+ "writeable",
 ]
 
 [[package]]
@@ -4934,6 +5033,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f8aeafdfd935e4a7fe16a91ab711fa52d54df84f9c8f7ca5837a9d1d902ef4c2"
 dependencies = [
  "displaydoc",
+ "zerovec",
 ]
 
 [[package]]
@@ -5544,6 +5644,12 @@ version = "0.42.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f40009d85759725a34da6d89a94e63d7bdc50a862acf0dbc7c8e488f1edcb6f5"
 
+[[package]]
+name = "writeable"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f8e6ab4f5da1b24daf2c590cfac801bacb27b15b4f050e84eb60149ea726f06b"
+
 [[package]]
 name = "xattr"
 version = "0.2.2"
@@ -5596,3 +5702,71 @@ checksum = "fe5c30ade05e61656247b2e334a031dfd0cc466fadef865bdcdea8d537951bf1"
 dependencies = [
  "winapi",
 ]
+
+[[package]]
+name = "yoke"
+version = "0.6.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1fe1d55ca72c32d573bfbd5cb2f0ca65a497854c44762957a6d3da96041a5184"
+dependencies = [
+ "serde",
+ "stable_deref_trait",
+ "yoke-derive",
+ "zerofrom",
+]
+
+[[package]]
+name = "yoke-derive"
+version = "0.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1346e4cd025ae818b88566eac7eb65ab33a994ea55f355c86889af2e7e56b14e"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+ "synstructure",
+]
+
+[[package]]
+name = "zerofrom"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "79e9355fccf72b04b7deaa99ce7a0f6630530acf34045391b74460fcd714de54"
+dependencies = [
+ "zerofrom-derive",
+]
+
+[[package]]
+name = "zerofrom-derive"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2e8aa86add9ddbd2409c1ed01e033cd457d79b1b1229b64922c25095c595e829"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+ "synstructure",
+]
+
+[[package]]
+name = "zerovec"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b9d919a74c17749ccb17beaf6405562e413cd94e98ba52ca1e64bbe7eefbd8b8"
+dependencies = [
+ "yoke",
+ "zerofrom",
+ "zerovec-derive",
+]
+
+[[package]]
+name = "zerovec-derive"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "490e5f878c2856225e884c35927e7ea6db3c24cdb7229b72542c7526ad7ed49e"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+ "synstructure",
+]

compiler/rustc_baked_icu_data/Cargo.toml

@@ -0,0 +1,15 @@
+[package]
+name = "rustc_baked_icu_data"
+version = "0.0.0"
+edition = "2021"
+
+[dependencies]
+icu_list = "1.0.0"
+icu_locid = "1.0.0"
+icu_provider = "1.0.1"
+icu_provider_adapters = "1.0.0"
+litemap = "0.6.0"
+zerovec = "0.9.0"
+
+[features]
+rustc_use_parallel_compiler = ['icu_provider/sync']

compiler/rustc_baked_icu_data/src/data/any.rs

@@ -0,0 +1,42 @@
+// @generated
+impl AnyProvider for BakedDataProvider {
+    fn load_any(&self, key: DataKey, req: DataRequest) -> Result<AnyResponse, DataError> {
+        const ANDLISTV1MARKER: ::icu_provider::DataKeyHash =
+            ::icu_list::provider::AndListV1Marker::KEY.hashed();
+        const COLLATIONFALLBACKSUPPLEMENTV1MARKER: ::icu_provider::DataKeyHash =
+            ::icu_provider_adapters::fallback::provider::CollationFallbackSupplementV1Marker::KEY
+                .hashed();
+        const LOCALEFALLBACKLIKELYSUBTAGSV1MARKER: ::icu_provider::DataKeyHash =
+            ::icu_provider_adapters::fallback::provider::LocaleFallbackLikelySubtagsV1Marker::KEY
+                .hashed();
+        const LOCALEFALLBACKPARENTSV1MARKER: ::icu_provider::DataKeyHash =
+            ::icu_provider_adapters::fallback::provider::LocaleFallbackParentsV1Marker::KEY
+                .hashed();
+        #[allow(clippy::match_single_binding)]
+        match key.hashed() {
+            ANDLISTV1MARKER => list::and_v1::DATA
+                .get_by(|k| req.locale.strict_cmp(k.as_bytes()).reverse())
+                .copied()
+                .map(AnyPayload::from_static_ref)
+                .ok_or(DataErrorKind::MissingLocale),
+            COLLATIONFALLBACKSUPPLEMENTV1MARKER => fallback::supplement::co_v1::DATA
+                .get_by(|k| req.locale.strict_cmp(k.as_bytes()).reverse())
+                .copied()
+                .map(AnyPayload::from_static_ref)
+                .ok_or(DataErrorKind::MissingLocale),
+            LOCALEFALLBACKLIKELYSUBTAGSV1MARKER => fallback::likelysubtags_v1::DATA
+                .get_by(|k| req.locale.strict_cmp(k.as_bytes()).reverse())
+                .copied()
+                .map(AnyPayload::from_static_ref)
+                .ok_or(DataErrorKind::MissingLocale),
+            LOCALEFALLBACKPARENTSV1MARKER => fallback::parents_v1::DATA
+                .get_by(|k| req.locale.strict_cmp(k.as_bytes()).reverse())
+                .copied()
+                .map(AnyPayload::from_static_ref)
+                .ok_or(DataErrorKind::MissingLocale),
+            _ => Err(DataErrorKind::MissingDataKey),
+        }
+        .map_err(|e| e.with_req(key, req))
+        .map(|payload| AnyResponse { payload: Some(payload), metadata: Default::default() })
+    }
+}