errors: implement fallback diagnostic translation

This commit updates the signatures of all diagnostic functions to accept
types that can be converted into a `DiagnosticMessage`. This enables
existing diagnostic calls to continue to work as before and Fluent
identifiers to be provided. The `SessionDiagnostic` derive just
generates normal diagnostic calls, so these APIs had to be modified to
accept Fluent identifiers.

In addition, loading of the "fallback" Fluent bundle, which contains the
built-in English messages, has been implemented.

Each diagnostic now has "arguments" which correspond to variables in the
Fluent messages (necessary to render a Fluent message) but no API for
adding arguments has been added yet. Therefore, diagnostics (that do not
require interpolation) can be converted to use Fluent identifiers and
will be output as before.

Author: davidtwco

Cargo.lock

@@ -1238,6 +1238,50 @@ dependencies = [
  "miniz_oxide",
 ]
 
+[[package]]
+name = "fluent"
+version = "0.16.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "61f69378194459db76abd2ce3952b790db103ceb003008d3d50d97c41ff847a7"
+dependencies = [
+ "fluent-bundle",
+ "unic-langid",
+]
+
+[[package]]
+name = "fluent-bundle"
+version = "0.15.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e242c601dec9711505f6d5bbff5bedd4b61b2469f2e8bb8e57ee7c9747a87ffd"
+dependencies = [
+ "fluent-langneg",
+ "fluent-syntax",
+ "intl-memoizer",
+ "intl_pluralrules",
+ "rustc-hash",
+ "self_cell",
+ "smallvec",
+ "unic-langid",
+]
+
+[[package]]
+name = "fluent-langneg"
+version = "0.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2c4ad0989667548f06ccd0e306ed56b61bd4d35458d54df5ec7587c0e8ed5e94"
+dependencies = [
+ "unic-langid",
+]
+
+[[package]]
+name = "fluent-syntax"
+version = "0.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c0abed97648395c902868fee9026de96483933faa54ea3b40d652f7dfe61ca78"
+dependencies = [
+ "thiserror",
+]
+
 [[package]]
 name = "fnv"
 version = "1.0.7"
@@ -1782,6 +1826,26 @@ dependencies = [
  "cfg-if 1.0.0",
 ]
 
+[[package]]
+name = "intl-memoizer"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c310433e4a310918d6ed9243542a6b83ec1183df95dff8f23f87bb88a264a66f"
+dependencies = [
+ "type-map",
+ "unic-langid",
+]
+
+[[package]]
+name = "intl_pluralrules"
+version = "7.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b18f988384267d7066cc2be425e6faf352900652c046b6971d2e228d3b1c5ecf"
+dependencies = [
+ "tinystr",
+ "unic-langid",
+]
+
 [[package]]
 name = "itertools"
 version = "0.10.1"
@@ -2812,6 +2876,12 @@ dependencies = [
  "version_check",
 ]
 
+[[package]]
+name = "proc-macro-hack"
+version = "0.5.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dbf0c48bc1d91375ae5c3cd81e3722dff1abcf81a30960240640d223f59fe0e5"
+
 [[package]]
 name = "proc-macro2"
 version = "1.0.30"
@@ -3649,9 +3719,13 @@ version = "0.0.0"
 name = "rustc_error_messages"
 version = "0.0.0"
 dependencies = [
+ "fluent",
+ "rustc_data_structures",
  "rustc_macros",
  "rustc_serialize",
  "rustc_span",
+ "tracing",
+ "unic-langid",
 ]
 
 [[package]]
@@ -4585,6 +4659,12 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "self_cell"
+version = "0.10.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1ef965a420fe14fdac7dd018862966a4c14094f900e1650bbc71ddd7d580c8af"
+
 [[package]]
 name = "semver"
 version = "1.0.3"
@@ -5116,6 +5196,12 @@ dependencies = [
  "winapi",
 ]
 
+[[package]]
+name = "tinystr"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "29738eedb4388d9ea620eeab9384884fc3f06f586a2eddb56bedc5885126c7c1"
+
 [[package]]
 name = "tinyvec"
 version = "0.3.4"
@@ -5274,6 +5360,15 @@ dependencies = [
  "tracing-subscriber",
 ]
 
+[[package]]
+name = "type-map"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6d3364c5e96cb2ad1603037ab253ddd34d7fb72a58bdddf4b7350760fc69a46"
+dependencies = [
+ "rustc-hash",
+]
+
 [[package]]
 name = "typenum"
 version = "1.12.0"
@@ -5328,6 +5423,49 @@ dependencies = [
  "unic-ucd-version",
 ]
 
+[[package]]
+name = "unic-langid"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "73328fcd730a030bdb19ddf23e192187a6b01cd98be6d3140622a89129459ce5"
+dependencies = [
+ "unic-langid-impl",
+ "unic-langid-macros",
+]
+
+[[package]]
+name = "unic-langid-impl"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1a4a8eeaf0494862c1404c95ec2f4c33a2acff5076f64314b465e3ddae1b934d"
+dependencies = [
+ "tinystr",
+]
+
+[[package]]
+name = "unic-langid-macros"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "18f980d6d87e8805f2836d64b4138cc95aa7986fa63b1f51f67d5fbff64dd6e5"
+dependencies = [
+ "proc-macro-hack",
+ "tinystr",
+ "unic-langid-impl",
+ "unic-langid-macros-impl",
+]
+
+[[package]]
+name = "unic-langid-macros-impl"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "29396ffd97e27574c3e01368b1a64267d3064969e4848e2e130ff668be9daa9f"
+dependencies = [
+ "proc-macro-hack",
+ "quote",
+ "syn",
+ "unic-langid-impl",
+]
+
 [[package]]
 name = "unic-ucd-version"
 version = "0.9.0"

compiler/rustc_borrowck/src/diagnostics/region_name.rs

@@ -109,7 +109,7 @@ impl RegionName {
                     *span,
                     format!("lifetime `{}` represents this closure's body", self),
                 );
-                diag.note(&note);
+                diag.note(note);
             }
             RegionNameSource::AnonRegionFromArgument(RegionNameHighlight::CannotMatchHirTy(
                 span,

compiler/rustc_codegen_ssa/src/back/write.rs

@@ -1707,23 +1707,33 @@ impl SharedEmitter {
 
 impl Emitter for SharedEmitter {
     fn emit_diagnostic(&mut self, diag: &rustc_errors::Diagnostic) {
+        let fluent_args = self.to_fluent_args(diag.args());
         drop(self.sender.send(SharedEmitterMessage::Diagnostic(Diagnostic {
-            msg: diag.message().to_string(),
+            msg: self.translate_messages(&diag.message, &fluent_args).to_string(),
             code: diag.code.clone(),
             lvl: diag.level(),
         })));
         for child in &diag.children {
             drop(self.sender.send(SharedEmitterMessage::Diagnostic(Diagnostic {
-                msg: child.message().to_string(),
+                msg: self.translate_messages(&child.message, &fluent_args).to_string(),
                 code: None,
                 lvl: child.level,
             })));
         }
         drop(self.sender.send(SharedEmitterMessage::AbortIfErrors));
     }
+
     fn source_map(&self) -> Option<&Lrc<SourceMap>> {
         None
     }
+
+    fn fluent_bundle(&self) -> Option<&Lrc<rustc_errors::FluentBundle>> {
+        None
+    }
+
+    fn fallback_fluent_bundle(&self) -> &Lrc<rustc_errors::FluentBundle> {
+        panic!("shared emitter attempted to translate a diagnostic");
+    }
 }
 
 impl SharedEmitterMain {
@@ -1754,9 +1764,9 @@ impl SharedEmitterMain {
                     let msg = msg.strip_prefix("error: ").unwrap_or(&msg);
 
                     let mut err = match level {
-                        Level::Error { lint: false } => sess.struct_err(&msg).forget_guarantee(),
-                        Level::Warning => sess.struct_warn(&msg),
-                        Level::Note => sess.struct_note_without_error(&msg),
+                        Level::Error { lint: false } => sess.struct_err(msg).forget_guarantee(),
+                        Level::Warning => sess.struct_warn(msg),
+                        Level::Note => sess.struct_note_without_error(msg),
                         _ => bug!("Invalid inline asm diagnostic level"),
                     };
 

compiler/rustc_driver/src/lib.rs

@@ -1172,9 +1172,11 @@ static DEFAULT_HOOK: SyncLazy<Box<dyn Fn(&panic::PanicInfo<'_>) + Sync + Send +
 /// When `install_ice_hook` is called, this function will be called as the panic
 /// hook.
 pub fn report_ice(info: &panic::PanicInfo<'_>, bug_report_url: &str) {
+    let fallback_bundle = rustc_errors::fallback_fluent_bundle();
     let emitter = Box::new(rustc_errors::emitter::EmitterWriter::stderr(
         rustc_errors::ColorConfig::Auto,
         None,
+        fallback_bundle,
         false,
         false,
         None,
@@ -1209,7 +1211,7 @@ pub fn report_ice(info: &panic::PanicInfo<'_>, bug_report_url: &str) {
     }
 
     for note in &xs {
-        handler.note_without_error(note);
+        handler.note_without_error(note.as_ref());
     }
 
     // If backtraces are enabled, also print the query stack

compiler/rustc_error_messages/Cargo.toml

@@ -7,6 +7,10 @@ edition = "2021"
 doctest = false
 
 [dependencies]
+fluent = "0.16.0"
+rustc_data_structures = { path = "../rustc_data_structures" }
 rustc_serialize = { path = "../rustc_serialize" }
 rustc_span = { path = "../rustc_span" }
 rustc_macros = { path = "../rustc_macros" }
+tracing = "0.1"
+unic-langid = { version = "0.9.0", features = ["macros"] }

compiler/rustc_error_messages/locales/en-US/diagnostics.ftl

@@ -0,0 +1,2 @@
+parser-struct-literal-body-without-path = struct literal body without path
+    .suggestion = you might have forgotten to add the struct literal inside the block

compiler/rustc_error_messages/src/lib.rs

@@ -1,31 +1,75 @@
+use rustc_data_structures::sync::Lrc;
 use rustc_macros::{Decodable, Encodable};
 use rustc_span::Span;
+use std::borrow::Cow;
+use tracing::debug;
+
+pub use fluent::{FluentArgs, FluentValue};
+
+static FALLBACK_FLUENT_RESOURCE: &'static str = include_str!("../locales/en-US/diagnostics.ftl");
+
+pub type FluentBundle = fluent::FluentBundle<fluent::FluentResource>;
+
+/// Return the default `FluentBundle` with standard en-US diagnostic messages.
+pub fn fallback_fluent_bundle() -> Lrc<FluentBundle> {
+    let fallback_resource = fluent::FluentResource::try_new(FALLBACK_FLUENT_RESOURCE.to_string())
+        .expect("failed to parse ftl resource");
+    debug!(?fallback_resource);
+    let mut fallback_bundle = FluentBundle::new(vec![unic_langid::langid!("en-US")]);
+    fallback_bundle.add_resource(fallback_resource).expect("failed to add resource to bundle");
+    let fallback_bundle = Lrc::new(fallback_bundle);
+    fallback_bundle
+}
+
+/// Identifier for the Fluent message/attribute corresponding to a diagnostic message.
+type FluentId = Cow<'static, str>;
 
 /// Abstraction over a message in a diagnostic to support both translatable and non-translatable
 /// diagnostic messages.
+///
+/// Intended to be removed once diagnostics are entirely translatable.
 #[derive(Clone, Debug, PartialEq, Eq, Hash, Encodable, Decodable)]
 pub enum DiagnosticMessage {
     /// Non-translatable diagnostic message.
+    // FIXME(davidtwco): can a `Cow<'static, str>` be used here?
     Str(String),
     /// Identifier for a Fluent message corresponding to the diagnostic message.
-    FluentIdentifier(String),
+    FluentIdentifier(FluentId, Option<FluentId>),
 }
 
 impl DiagnosticMessage {
-    /// Convert `DiagnosticMessage` to a `&str`.
-    pub fn as_str(&self) -> &str {
+    /// Returns the `String` contained within the `DiagnosticMessage::Str` variant, assuming that
+    /// this diagnostic message is of the legacy, non-translatable variety. Panics if this
+    /// assumption does not hold.
+    ///
+    /// Don't use this - it exists to support some places that do comparison with diagnostic
+    /// strings.
+    pub fn expect_str(&self) -> &str {
         match self {
-            DiagnosticMessage::Str(msg) => msg,
-            DiagnosticMessage::FluentIdentifier(..) => unimplemented!(),
+            DiagnosticMessage::Str(s) => s,
+            _ => panic!("expected non-translatable diagnostic message"),
         }
     }
 
-    /// Convert `DiagnosticMessage` to an owned `String`.
-    pub fn to_string(self) -> String {
-        match self {
-            DiagnosticMessage::Str(msg) => msg,
-            DiagnosticMessage::FluentIdentifier(..) => unimplemented!(),
-        }
+    /// Create a `DiagnosticMessage` for the provided Fluent identifier.
+    pub fn fluent(id: impl Into<Cow<'static, str>>) -> Self {
+        DiagnosticMessage::FluentIdentifier(id.into(), None)
+    }
+
+    /// Create a `DiagnosticMessage` for the provided Fluent identifier and attribute.
+    pub fn fluent_attr(
+        id: impl Into<Cow<'static, str>>,
+        attr: impl Into<Cow<'static, str>>,
+    ) -> Self {
+        DiagnosticMessage::FluentIdentifier(id.into(), Some(attr.into()))
+    }
+}
+
+/// `From` impl that enables existing diagnostic calls to functions which now take
+/// `impl Into<DiagnosticMessage>` to continue to work as before.
+impl<S: Into<String>> From<S> for DiagnosticMessage {
+    fn from(s: S) -> Self {
+        DiagnosticMessage::Str(s.into())
     }
 }
 
@@ -72,12 +116,8 @@ impl MultiSpan {
         MultiSpan { primary_spans: vec, span_labels: vec![] }
     }
 
-    pub fn push_span_label(&mut self, span: Span, label: String) {
-        self.span_labels.push((span, DiagnosticMessage::Str(label)));
-    }
-
-    pub fn push_span_message(&mut self, span: Span, message: DiagnosticMessage) {
-        self.span_labels.push((span, message));
+    pub fn push_span_label(&mut self, span: Span, label: impl Into<DiagnosticMessage>) {
+        self.span_labels.push((span, label.into()));
     }
 
     /// Selects the first primary span (if any).