add 'use-grammars' to languages.toml

The vision with 'use-grammars' is to allow the long-requested feature
of being able to declare your own set of grammars that you would like.
A simple schema with only/except grammar names controls the list
of grammars that is fetched and built. It does not (yet) control which
grammars may be loaded at runtime if they already exist.

book/src/languages.md

@@ -28,4 +28,13 @@ name = "c"
 source = { path = "/path/to/tree-sitter-c" }
 ```
 
-If a user has a `languages.toml`, only the grammars in that `languages.toml` are evaluated when running `hx --fetch-grammars` and `hx --build-grammars`. Otherwise the [default `languages.toml`](https://github.com/helix-editor/helix/blob/master/languages.toml) is used.
+You may use a top-level `use-grammars` key to control which grammars are fetched and built.
+
+```toml
+# Note: this key must come **before** the [[language]] and [[grammar]] sections
+use-grammars = { only = [ "rust", "c", "cpp" ] }
+# or
+use-grammars = { except = [ "yaml", "json" ] }
+```
+
+When omitted, all grammars are fetched and built.

helix-core/src/indent.rs

@@ -445,6 +445,7 @@ where
                 auto_pairs: None,
             }],
             grammar: vec![],
+            grammar_selection: None,
         });
 
         // set runtime path so we can find the queries

helix-core/src/syntax.rs

@@ -81,12 +81,21 @@ where
 }
 
 #[derive(Debug, Serialize, Deserialize)]
-#[serde(deny_unknown_fields)]
+#[serde(rename_all = "kebab-case", deny_unknown_fields)]
 pub struct Configuration {
+    #[serde(rename = "use-grammars")]
+    pub grammar_selection: Option<GrammarSelection>,
     pub language: Vec<LanguageConfiguration>,
     pub grammar: Vec<GrammarConfiguration>,
 }
 
+#[derive(Debug, Serialize, Deserialize)]
+#[serde(rename_all = "lowercase", untagged)]
+pub enum GrammarSelection {
+    Only(HashSet<String>),
+    Except(HashSet<String>),
+}
+
 // largely based on tree-sitter/cli/src/loader.rs
 #[derive(Debug, Serialize, Deserialize)]
 #[serde(rename_all = "kebab-case", deny_unknown_fields)]
@@ -2110,6 +2119,7 @@ mod test {
         let loader = Loader::new(Configuration {
             language: vec![],
             grammar: vec![],
+            grammar_selection: None,
         });
 
         let language = get_language(&crate::RUNTIME_DIR, "Rust").unwrap();

helix-term/src/grammars.rs

@@ -7,7 +7,7 @@ use std::{
     sync::mpsc::channel,
 };
 
-use helix_core::syntax::{GrammarConfiguration, GrammarSource, DYLIB_EXTENSION};
+use helix_core::syntax::{GrammarConfiguration, GrammarSelection, GrammarSource, DYLIB_EXTENSION};
 
 const BUILD_TARGET: &str = env!("BUILD_TARGET");
 const REMOTE_NAME: &str = "origin";
@@ -163,7 +163,19 @@ fn build_grammar(grammar: GrammarConfiguration) -> Result<()> {
 fn get_grammar_configs() -> Vec<GrammarConfiguration> {
     let config = helix_core::config::user_syntax_loader().expect("Could not parse languages.toml");
 
-    config.grammar
+    match config.grammar_selection {
+        Some(GrammarSelection::Only(selections)) => config
+            .grammar
+            .into_iter()
+            .filter(|grammar| selections.contains(&grammar.grammar_id))
+            .collect(),
+        Some(GrammarSelection::Except(rejections)) => config
+            .grammar
+            .into_iter()
+            .filter(|grammar| !rejections.contains(&grammar.grammar_id))
+            .collect(),
+        None => config.grammar,
+    }
 }
 
 fn build_tree_sitter_library(src_path: &Path, grammar: GrammarConfiguration) -> Result<()> {