Files
zed/crates/languages/src/cpp.rs
T
ab3697f163 Extract language_core and grammars crates from language (#52238)
This extracts a `language_core` crate from the existing `language`
crate, and creates a `grammars` data crate. The goal is to separate
tree-sitter grammar infrastructure, language configuration, and LSP
adapter types from the heavier buffer/editor integration layer in
`language`.

## Motivation

The `language` crate pulls in `text`, `theme`, `settings`, `rpc`,
`task`, `fs`, `clock`, `sum_tree`, and `fuzzy` — all of which are needed
for buffer integration (`Buffer`, `SyntaxMap`, `Outline`,
`DiagnosticSet`) but not for grammar parsing or language configuration.
Extracting the core types lets downstream consumers depend on
`language_core` without pulling in the full integration stack.

## Dependency graph after extraction

```
language_core   ← gpui, lsp, tree-sitter, util, collections
grammars        ← language_core, rust_embed, tree-sitter-{rust,python,...}
language        ← language_core, text, theme, settings, rpc, task, fs, ...
languages       ← language, grammars
```

## What moved to `language_core`

- `Grammar`, `GrammarId`, and all query config/builder types
- `LanguageConfig`, `LanguageMatcher`, bracket/comment/indent config
types
- `HighlightMap`, `HighlightId` (theme-dependent free functions
`highlight_style` and `highlight_name` stay in `language`)
- `LanguageName`, `LanguageId`
- `LanguageQueries`, `QUERY_FILENAME_PREFIXES`
- `CodeLabel`, `CodeLabelBuilder`, `Symbol`
- `Diagnostic`, `DiagnosticSourceKind`
- `Toolchain`, `ToolchainScope`, `ToolchainList`, `ToolchainMetadata`
- `ManifestName`
- `SoftWrap`
- LSP data types: `BinaryStatus`, `ServerHealth`,
`LanguageServerStatusUpdate`, `PromptResponseContext`, `ToLspPosition`

## What stays in `language`

- `Buffer`, `BufferSnapshot`, `SyntaxMap`, `Outline`, `DiagnosticSet`,
`LanguageScope`
- `LspAdapter`, `CachedLspAdapter`, `LspAdapterDelegate` (reference
`Arc<Language>` and `WorktreeId`)
- `ToolchainLister`, `LanguageToolchainStore` (reference `task` and
`settings` types)
- `ManifestQuery`, `ManifestProvider`, `ManifestDelegate` (reference
`WorktreeId`)
- Parser/query cursor pools, `PLAIN_TEXT`, point conversion functions

## What the `grammars` crate provides

- Embedded `.scm` query files and `config.toml` files for all built-in
languages (via `rust_embed`)
- `load_queries(name)`, `load_config(name)`,
`load_config_for_feature(name, grammars_loaded)`, and `get_file(path)`
functions
- `native_grammars()` for tree-sitter grammar registration (behind
`load-grammars` feature)

## Pre-cleanup (also in this PR)

- Removed unused `Option<&Buffer>` from
`LspAdapter::process_diagnostics`
- Removed unused `&App` from `LspAdapter::retain_old_diagnostic`
- Removed `fs: &dyn Fs` from `ToolchainLister` trait methods
(`PythonToolchainProvider` captures `fs` at construction time instead)
- Moved `Diagnostic`/`DiagnosticSourceKind` out of `buffer.rs` into
their own module

## Backward compatibility

The `language` crate re-exports everything from `language_core`, so
existing `use language::Grammar` (etc.) continues to work unchanged. The
only downstream change required is importing `CodeLabelExt` where
`.fallback_for_completion()` is called on the now-foreign `CodeLabel`
type.

Release Notes:

- N/A

---------

Co-authored-by: Agus Zubiaga <agus@zed.dev>
Co-authored-by: Tom Houlé <tom@tomhoule.com>
2026-03-25 23:41:09 +00:00

263 lines
7.6 KiB
Rust

use settings::SemanticTokenRules;
pub(crate) fn semantic_token_rules() -> SemanticTokenRules {
let content = grammars::get_file("cpp/semantic_token_rules.json")
.expect("missing cpp/semantic_token_rules.json");
let json = std::str::from_utf8(&content.data).expect("invalid utf-8 in semantic_token_rules");
settings::parse_json_with_comments::<SemanticTokenRules>(json)
.expect("failed to parse cpp semantic_token_rules.json")
}
#[cfg(test)]
mod tests {
use gpui::{AppContext as _, BorrowAppContext, TestAppContext};
use language::{AutoindentMode, Buffer};
use settings::SettingsStore;
use std::num::NonZeroU32;
use unindent::Unindent;
#[gpui::test]
async fn test_cpp_autoindent_basic(cx: &mut TestAppContext) {
cx.update(|cx| {
let test_settings = SettingsStore::test(cx);
cx.set_global(test_settings);
cx.update_global::<SettingsStore, _>(|store, cx| {
store.update_user_settings(cx, |s| {
s.project.all_languages.defaults.tab_size = NonZeroU32::new(2);
});
});
});
let language = crate::language("cpp", tree_sitter_cpp::LANGUAGE.into());
cx.new(|cx| {
let mut buffer = Buffer::local("", cx).with_language(language, cx);
buffer.edit([(0..0, "int main() {}")], None, cx);
let ix = buffer.len() - 1;
buffer.edit([(ix..ix, "\n\n")], Some(AutoindentMode::EachLine), cx);
assert_eq!(
buffer.text(),
"int main() {\n \n}",
"content inside braces should be indented"
);
buffer
});
}
#[gpui::test]
async fn test_cpp_autoindent_if_else(cx: &mut TestAppContext) {
cx.update(|cx| {
let test_settings = SettingsStore::test(cx);
cx.set_global(test_settings);
cx.update_global::<SettingsStore, _>(|store, cx| {
store.update_user_settings(cx, |s| {
s.project.all_languages.defaults.tab_size = NonZeroU32::new(2);
});
});
});
let language = crate::language("cpp", tree_sitter_cpp::LANGUAGE.into());
cx.new(|cx| {
let mut buffer = Buffer::local("", cx).with_language(language, cx);
buffer.edit(
[(
0..0,
r#"
int main() {
if (a)
b;
}
"#
.unindent(),
)],
Some(AutoindentMode::EachLine),
cx,
);
assert_eq!(
buffer.text(),
r#"
int main() {
if (a)
b;
}
"#
.unindent(),
"body of if-statement without braces should be indented"
);
let ix = buffer.len() - 4;
buffer.edit([(ix..ix, "\n.c")], Some(AutoindentMode::EachLine), cx);
assert_eq!(
buffer.text(),
r#"
int main() {
if (a)
b
.c;
}
"#
.unindent(),
"field expression (.c) should be indented further than the statement body"
);
buffer.edit([(0..buffer.len(), "")], Some(AutoindentMode::EachLine), cx);
buffer.edit(
[(
0..0,
r#"
int main() {
if (a) a++;
else b++;
}
"#
.unindent(),
)],
Some(AutoindentMode::EachLine),
cx,
);
assert_eq!(
buffer.text(),
r#"
int main() {
if (a) a++;
else b++;
}
"#
.unindent(),
"single-line if/else without braces should align at the same level"
);
buffer.edit([(0..buffer.len(), "")], Some(AutoindentMode::EachLine), cx);
buffer.edit(
[(
0..0,
r#"
int main() {
if (a)
b++;
else
c++;
}
"#
.unindent(),
)],
Some(AutoindentMode::EachLine),
cx,
);
assert_eq!(
buffer.text(),
r#"
int main() {
if (a)
b++;
else
c++;
}
"#
.unindent(),
"multi-line if/else without braces should indent statement bodies"
);
buffer.edit([(0..buffer.len(), "")], Some(AutoindentMode::EachLine), cx);
buffer.edit(
[(
0..0,
r#"
int main() {
if (a)
if (b)
c++;
}
"#
.unindent(),
)],
Some(AutoindentMode::EachLine),
cx,
);
assert_eq!(
buffer.text(),
r#"
int main() {
if (a)
if (b)
c++;
}
"#
.unindent(),
"nested if statements without braces should indent properly"
);
buffer.edit([(0..buffer.len(), "")], Some(AutoindentMode::EachLine), cx);
buffer.edit(
[(
0..0,
r#"
int main() {
if (a)
b++;
else if (c)
d++;
else
f++;
}
"#
.unindent(),
)],
Some(AutoindentMode::EachLine),
cx,
);
assert_eq!(
buffer.text(),
r#"
int main() {
if (a)
b++;
else if (c)
d++;
else
f++;
}
"#
.unindent(),
"else-if chains should align all conditions at same level with indented bodies"
);
buffer.edit([(0..buffer.len(), "")], Some(AutoindentMode::EachLine), cx);
buffer.edit(
[(
0..0,
r#"
int main() {
if (a) {
b++;
} else
c++;
}
"#
.unindent(),
)],
Some(AutoindentMode::EachLine),
cx,
);
assert_eq!(
buffer.text(),
r#"
int main() {
if (a) {
b++;
} else
c++;
}
"#
.unindent(),
"mixed braces should indent properly"
);
buffer
});
}
}