add tree-sitter sources to languages.toml

Here we add syntax to the languages.toml languge

    [[grammar]]
    name = "<name>"
    source = { .. }

Which can be used to specify a tree-sitter grammar separately of
the language that defines it, and we make this distinction for
two reasons:

* In later commits, we will separate this code from helix-core
  and bring it to a new helix-loader crate. Using separate schemas
  for language and grammar configurations allows for a nice divide
  between the types needed to be declared in helix-loader and in
  helix-core/syntax

* Two different languages may use the same grammar. This is currently
  the case with llvm-mir-yaml and yaml. We could accomplish a config
  that works for this with just `[[languages]]`, but it gets a bit
  dicey with languages depending on one another. If you enable
  llvm-mir-yaml and disable yaml, does helix still need to fetch and
  build tree-sitter-yaml? It could be a matter of interpretation.

2 files changed, 29 insertions, 1 deletions

diff --git a/helix-core/src/indent.rs b/helix-core/src/indent.rs
index 9a329d95..83b2be94 100644
--- a/helix-core/src/indent.rs
+++ b/helix-core/src/indent.rs
@@ -444,6 +444,7 @@ where
                 debugger: None,
                 auto_pairs: None,
             }],
+            grammar: vec![],
         });
 
         // set runtime path so we can find the queries
diff --git a/helix-core/src/syntax.rs b/helix-core/src/syntax.rs
index c39e0584..53d20da3 100644
--- a/helix-core/src/syntax.rs
+++ b/helix-core/src/syntax.rs
@@ -54,6 +54,7 @@ where
 #[serde(deny_unknown_fields)]
 pub struct Configuration {
     pub language: Vec<LanguageConfiguration>,
+    pub grammar: Vec<GrammarConfiguration>,
 }
 
 // largely based on tree-sitter/cli/src/loader.rs
@@ -239,6 +240,29 @@ pub struct IndentQuery {
     pub outdent: HashSet<String>,
 }
 
+#[derive(Debug, Serialize, Deserialize)]
+pub struct GrammarConfiguration {
+    #[serde(rename = "name")]
+    pub grammar_id: String, // c-sharp, rust
+    pub source: GrammarSource,
+    pub path: Option<String>,
+}
+
+#[derive(Debug, Serialize, Deserialize)]
+#[serde(rename_all = "lowercase")]
+#[serde(untagged)]
+pub enum GrammarSource {
+    Local {
+        path: String,
+    },
+    Git {
+        #[serde(rename = "git")]
+        remote: String,
+        #[serde(rename = "rev")]
+        revision: String,
+    },
+}
+
 #[derive(Debug)]
 pub struct TextObjectQuery {
     pub query: Query,
@@ -2055,7 +2079,10 @@ mod test {
         .map(String::from)
         .collect();
 
-        let loader = Loader::new(Configuration { language: vec![] });
+        let loader = Loader::new(Configuration {
+            language: vec![],
+            grammar: vec![],
+        });
 
         let language = get_language(&crate::RUNTIME_DIR, "Rust").unwrap();
         let config = HighlightConfiguration::new(