macros: introduce `fluent_messages` macro

Adds a new `fluent_messages` macro which performs compile-time
validation of the compiler's Fluent resources (i.e. that the resources
parse and don't multiply define the same messages) and generates
constants that make using those messages in diagnostics more ergonomic.

For example, given the following invocation of the macro..

```ignore (rust)
fluent_messages! {
    typeck => "./typeck.ftl",
}
```
..where `typeck.ftl` has the following contents..

```fluent
typeck-field-multiply-specified-in-initializer =
    field `{$ident}` specified more than once
    .label = used more than once
    .label-previous-use = first use of `{$ident}`
```
...then the macro parse the Fluent resource, emitting a diagnostic if it
fails to do so, and will generate the following code:

```ignore (rust)
pub static DEFAULT_LOCALE_RESOURCES: &'static [&'static str] = &[
    include_str!("./typeck.ftl"),
];

mod fluent_generated {
    mod typeck {
        pub const field_multiply_specified_in_initializer: DiagnosticMessage =
            DiagnosticMessage::fluent("typeck-field-multiply-specified-in-initializer");
        pub const field_multiply_specified_in_initializer_label_previous_use: DiagnosticMessage =
            DiagnosticMessage::fluent_attr(
                "typeck-field-multiply-specified-in-initializer",
                "previous-use-label"
            );
    }
}
```

When emitting a diagnostic, the generated constants can be used as
follows:

```ignore (rust)
let mut err = sess.struct_span_err(
    span,
    fluent::typeck::field_multiply_specified_in_initializer
);
err.span_default_label(span);
err.span_label(
    previous_use_span,
    fluent::typeck::field_multiply_specified_in_initializer_label_previous_use
);
err.emit();
```

Signed-off-by: David Wood <david.wood@huawei.com>

1 files changed, 254 insertions, 0 deletions

diff --git a/compiler/rustc_macros/src/diagnostics/fluent.rs b/compiler/rustc_macros/src/diagnostics/fluent.rs
new file mode 100644
index 00000000000..8523d7fa9f9
--- /dev/null
+++ b/compiler/rustc_macros/src/diagnostics/fluent.rs
@@ -0,0 +1,254 @@
+use annotate_snippets::{
+    display_list::DisplayList,
+    snippet::{Annotation, AnnotationType, Slice, Snippet, SourceAnnotation},
+};
+use fluent_bundle::{FluentBundle, FluentError, FluentResource};
+use fluent_syntax::{
+    ast::{Attribute, Entry, Identifier, Message},
+    parser::ParserError,
+};
+use proc_macro::{Diagnostic, Level, Span};
+use proc_macro2::TokenStream;
+use quote::quote;
+use std::{
+    collections::HashMap,
+    fs::File,
+    io::Read,
+    path::{Path, PathBuf},
+};
+use syn::{
+    parse::{Parse, ParseStream},
+    parse_macro_input,
+    punctuated::Punctuated,
+    token, Ident, LitStr, Result,
+};
+use unic_langid::langid;
+
+struct Resource {
+    ident: Ident,
+    #[allow(dead_code)]
+    fat_arrow_token: token::FatArrow,
+    resource: LitStr,
+}
+
+impl Parse for Resource {
+    fn parse(input: ParseStream<'_>) -> Result<Self> {
+        Ok(Resource {
+            ident: input.parse()?,
+            fat_arrow_token: input.parse()?,
+            resource: input.parse()?,
+        })
+    }
+}
+
+struct Resources(Punctuated<Resource, token::Comma>);
+
+impl Parse for Resources {
+    fn parse(input: ParseStream<'_>) -> Result<Self> {
+        let mut resources = Punctuated::new();
+        loop {
+            if input.is_empty() || input.peek(token::Brace) {
+                break;
+            }
+            let value = input.parse()?;
+            resources.push_value(value);
+            if !input.peek(token::Comma) {
+                break;
+            }
+            let punct = input.parse()?;
+            resources.push_punct(punct);
+        }
+        Ok(Resources(resources))
+    }
+}
+
+/// Helper function for returning an absolute path for macro-invocation relative file paths.
+///
+/// If the input is already absolute, then the input is returned. If the input is not absolute,
+/// then it is appended to the directory containing the source file with this macro invocation.
+fn invocation_relative_path_to_absolute(span: Span, path: &str) -> PathBuf {
+    let path = Path::new(path);
+    if path.is_absolute() {
+        path.to_path_buf()
+    } else {
+        // `/a/b/c/foo/bar.rs` contains the current macro invocation
+        let mut source_file_path = span.source_file().path();
+        // `/a/b/c/foo/`
+        source_file_path.pop();
+        // `/a/b/c/foo/../locales/en-US/example.ftl`
+        source_file_path.push(path);
+        source_file_path
+    }
+}
+
+/// See [rustc_macros::fluent_messages].
+pub(crate) fn fluent_messages(input: proc_macro::TokenStream) -> proc_macro::TokenStream {
+    let resources = parse_macro_input!(input as Resources);
+
+    // Cannot iterate over individual messages in a bundle, so do that using the
+    // `FluentResource` instead. Construct a bundle anyway to find out if there are conflicting
+    // messages in the resources.
+    let mut bundle = FluentBundle::new(vec![langid!("en-US")]);
+
+    // Map of Fluent identifiers to the `Span` of the resource that defined them, used for better
+    // diagnostics.
+    let mut previous_defns = HashMap::new();
+
+    let mut includes = TokenStream::new();
+    let mut generated = TokenStream::new();
+    for res in resources.0 {
+        let ident_span = res.ident.span().unwrap();
+        let path_span = res.resource.span().unwrap();
+
+        let relative_ftl_path = res.resource.value();
+        let absolute_ftl_path =
+            invocation_relative_path_to_absolute(ident_span, &relative_ftl_path);
+        // As this macro also outputs an `include_str!` for this file, the macro will always be
+        // re-executed when the file changes.
+        let mut resource_file = match File::open(absolute_ftl_path) {
+            Ok(resource_file) => resource_file,
+            Err(e) => {
+                Diagnostic::spanned(path_span, Level::Error, "could not open Fluent resource")
+                    .note(e.to_string())
+                    .emit();
+                continue;
+            }
+        };
+        let mut resource_contents = String::new();
+        if let Err(e) = resource_file.read_to_string(&mut resource_contents) {
+            Diagnostic::spanned(path_span, Level::Error, "could not read Fluent resource")
+                .note(e.to_string())
+                .emit();
+            continue;
+        }
+        let resource = match FluentResource::try_new(resource_contents) {
+            Ok(resource) => resource,
+            Err((this, errs)) => {
+                Diagnostic::spanned(path_span, Level::Error, "could not parse Fluent resource")
+                    .help("see additional errors emitted")
+                    .emit();
+                for ParserError { pos, slice: _, kind } in errs {
+                    let mut err = kind.to_string();
+                    // Entirely unnecessary string modification so that the error message starts
+                    // with a lowercase as rustc errors do.
+                    err.replace_range(
+                        0..1,
+                        &err.chars().next().unwrap().to_lowercase().to_string(),
+                    );
+
+                    let line_starts: Vec<usize> = std::iter::once(0)
+                        .chain(
+                            this.source()
+                                .char_indices()
+                                .filter_map(|(i, c)| Some(i + 1).filter(|_| c == '\n')),
+                        )
+                        .collect();
+                    let line_start = line_starts
+                        .iter()
+                        .enumerate()
+                        .map(|(line, idx)| (line + 1, idx))
+                        .filter(|(_, idx)| **idx <= pos.start)
+                        .last()
+                        .unwrap()
+                        .0;
+
+                    let snippet = Snippet {
+                        title: Some(Annotation {
+                            label: Some(&err),
+                            id: None,
+                            annotation_type: AnnotationType::Error,
+                        }),
+                        footer: vec![],
+                        slices: vec![Slice {
+                            source: this.source(),
+                            line_start,
+                            origin: Some(&relative_ftl_path),
+                            fold: true,
+                            annotations: vec![SourceAnnotation {
+                                label: "",
+                                annotation_type: AnnotationType::Error,
+                                range: (pos.start, pos.end - 1),
+                            }],
+                        }],
+                        opt: Default::default(),
+                    };
+                    let dl = DisplayList::from(snippet);
+                    eprintln!("{}\n", dl);
+                }
+                continue;
+            }
+        };
+
+        let mut constants = TokenStream::new();
+        for entry in resource.entries() {
+            let span = res.ident.span();
+            if let Entry::Message(Message { id: Identifier { name }, attributes, .. }) = entry {
+                let _ = previous_defns.entry(name.to_string()).or_insert(ident_span);
+
+                // `typeck-foo-bar` => `foo_bar`
+                let snake_name = Ident::new(
+                    &name.replace(&format!("{}-", res.ident), "").replace("-", "_"),
+                    span,
+                );
+                constants.extend(quote! {
+                    pub const #snake_name: crate::DiagnosticMessage =
+                        crate::DiagnosticMessage::FluentIdentifier(
+                            std::borrow::Cow::Borrowed(#name),
+                            None
+                        );
+                });
+
+                for Attribute { id: Identifier { name: attr_name }, .. } in attributes {
+                    let attr_snake_name = attr_name.replace("-", "_");
+                    let snake_name = Ident::new(&format!("{snake_name}_{attr_snake_name}"), span);
+                    constants.extend(quote! {
+                        pub const #snake_name: crate::DiagnosticMessage =
+                            crate::DiagnosticMessage::FluentIdentifier(
+                                std::borrow::Cow::Borrowed(#name),
+                                Some(std::borrow::Cow::Borrowed(#attr_name))
+                            );
+                    });
+                }
+            }
+        }
+
+        if let Err(errs) = bundle.add_resource(resource) {
+            for e in errs {
+                match e {
+                    FluentError::Overriding { kind, id } => {
+                        Diagnostic::spanned(
+                            ident_span,
+                            Level::Error,
+                            format!("overrides existing {}: `{}`", kind, id),
+                        )
+                        .span_help(previous_defns[&id], "previously defined in this resource")
+                        .emit();
+                    }
+                    FluentError::ResolverError(_) | FluentError::ParserError(_) => unreachable!(),
+                }
+            }
+        }
+
+        includes.extend(quote! { include_str!(#relative_ftl_path), });
+
+        let ident = res.ident;
+        generated.extend(quote! {
+            pub mod #ident {
+                #constants
+            }
+        });
+    }
+
+    quote! {
+        #[allow(non_upper_case_globals)]
+        #[doc(hidden)]
+        pub mod fluent_generated {
+            pub static DEFAULT_LOCALE_RESOURCES: &'static [&'static str] = &[
+                #includes
+            ];
+
+            #generated
+        }
+    }
+    .into()
+}