Feature: Add YAML support

Cargo.toml

@@ -64,6 +64,7 @@ tree-sitter-rust = "<0.25.0"
 tree-sitter-swift = "<0.8.0"
 tree-sitter-toml-ng = "<0.8.0"
 tree-sitter-typescript = "0.23.2"
+tree-sitter-yaml = "0.7.2"
 tree-sitter-zig = "<2"
 tree-sitter-c-sharp= "<0.24.0"
 codebook-tree-sitter-latex = "<0.7.0"

README.md

@@ -158,6 +158,7 @@ Codebook is in active development. As better dictionaries are added, words that
 | TOML | ✅ |
 | TypeScript | ✅ |
 | Typst | ⚠️ |
+| YAML | ⚠️ |
 | Zig | ✅ |
 
 ✅ = Good to go.

crates/codebook/Cargo.toml

@@ -52,6 +52,7 @@ tree-sitter-swift.workspace = true
 tree-sitter-toml-ng.workspace = true
 tree-sitter-typescript.workspace = true
 codebook-tree-sitter-typst.workspace = true
+tree-sitter-yaml.workspace = true
 tree-sitter-zig.workspace = true
 tree-sitter-c-sharp.workspace = true
 tree-sitter.workspace = true

crates/codebook/src/queries.rs

@@ -29,6 +29,7 @@ pub enum LanguageType {
     Text,
     Typescript,
     Typst,
+    YAML,
     Zig,
 }
 
@@ -217,6 +218,13 @@ pub static LANGUAGE_SETTINGS: &[LanguageSetting] = &[
         query: include_str!("queries/r.scm"),
         extensions: &["r", "R"],
     },
+    LanguageSetting {
+        type_: LanguageType::YAML,
+        ids: &["yaml"],
+        dictionary_ids: &["yaml"],
+        query: include_str!("queries/yaml.scm"),
+        extensions: &["yaml", "yml"],
+    },
     LanguageSetting {
         type_: LanguageType::Zig,
         ids: &["zig"],
@@ -278,6 +286,7 @@ impl LanguageSetting {
             LanguageType::Text => None,
             LanguageType::Typescript => Some(tree_sitter_typescript::LANGUAGE_TYPESCRIPT.into()),
             LanguageType::Typst => Some(codebook_tree_sitter_typst::LANGUAGE.into()),
+            LanguageType::YAML => Some(tree_sitter_yaml::LANGUAGE.into()),
             LanguageType::Zig => Some(tree_sitter_zig::LANGUAGE.into()),
         }
     }

crates/codebook/src/queries/yaml.scm

@@ -0,0 +1,28 @@
+; Capture YAML comments and scalar values for spell-checking
+(comment) @comment
+
+; Unquoted plain scalars
+(plain_scalar) @string
+
+; Single- and double-quoted scalars
+(single_quote_scalar) @string
+(double_quote_scalar) @string
+
+; Block scalars (literal '|' and folded '>')
+(block_scalar) @string
+
+; Capture mapping keys as identifiers (useful for keys that are plain scalars)
+(block_mapping_pair
+  key: (flow_node
+    [
+      (double_quote_scalar)
+      (single_quote_scalar)
+    ] @identifier))
+
+(flow_mapping
+  (_
+    key: (flow_node
+      [
+        (double_quote_scalar)
+        (single_quote_scalar)
+      ] @identifier)))

crates/codebook/tests/test_yaml.rs

@@ -0,0 +1,120 @@
+use codebook::{
+    parser::{TextRange, WordLocation},
+    queries::LanguageType,
+};
+
+mod utils;
+
+#[test]
+fn test_yaml_simple() {
+    utils::init_logging();
+    let processor = utils::get_processor();
+    let sample_text = r#"
+      # On a sepaate line
+      title: "Example lne"
+      nested:
+        name: Naame
+        nested:
+          item_name: Iteem name
+      details: |
+        # can be inented
+        This is comented out
+        this wors, too
+      options:
+        - opttions
+        - parameters
+      flags: froozen
+      var: 'helo'
+      symbol: ':hello'
+    "#;
+    let expected = vec![
+        "Iteem", "Naame", "comented", "froozen", "helo", "inented", "lne", "opttions", "sepaate",
+        "wors",
+    ];
+    let binding = processor
+        .spell_check(sample_text, Some(LanguageType::YAML), None)
+        .to_vec();
+    let mut misspelled = binding
+        .iter()
+        .map(|r| r.word.as_str())
+        .collect::<Vec<&str>>();
+    misspelled.sort();
+    println!("Misspelled words: {misspelled:?}");
+    assert_eq!(misspelled, expected);
+}
+
+#[test]
+fn test_yaml_code() {
+    utils::init_logging();
+    let sample_yaml_code = r#"
+      # On a separate line
+      tiitle: "Example line"
+      subtiitle: Subtitle
+      descriptioon: 'hello'
+      nested_struucture:
+        name: "Name"
+        nestted:
+          item_name: 'Item name'
+          another_name: Another Name
+      options:
+        - parameters:
+        - parameters
+      items: [ { id: 1, naame: "one" }, { id: 2, name: "two" } ]
+
+    "#;
+
+    let expected = vec![
+        WordLocation::new(
+            "tiitle".to_string(),
+            vec![TextRange {
+                start_byte: 34,
+                end_byte: 40,
+            }],
+        ),
+        WordLocation::new(
+            "subtiitle".to_string(),
+            vec![TextRange {
+                start_byte: 63,
+                end_byte: 72,
+            }],
+        ),
+        WordLocation::new(
+            "descriptioon".to_string(),
+            vec![TextRange {
+                start_byte: 89,
+                end_byte: 101,
+            }],
+        ),
+        WordLocation::new(
+            "struucture".to_string(),
+            vec![TextRange {
+                start_byte: 124,
+                end_byte: 134,
+            }],
+        ),
+        WordLocation::new(
+            "nestted".to_string(),
+            vec![TextRange {
+                start_byte: 165,
+                end_byte: 172,
+            }],
+        ),
+        WordLocation::new(
+            "naame".to_string(),
+            vec![TextRange {
+                start_byte: 326,
+                end_byte: 331,
+            }],
+        ),
+    ];
+    let processor = utils::get_processor();
+    let misspelled = processor
+        .spell_check(sample_yaml_code, Some(LanguageType::YAML), None)
+        .to_vec();
+    println!("Misspelled words: {misspelled:?}");
+    for e in &expected {
+        let miss = misspelled.iter().find(|r| r.word == e.word).unwrap();
+        println!("Expecting: {e:?}");
+        assert_eq!(miss.locations, e.locations);
+    }
+}

editors/vscode/package.json

@@ -44,6 +44,7 @@
     "onLanguage:toml",
     "onLanguage:typescript",
     "onLanguage:typst",
+    "onLanguage:yaml",
     "onLanguage:zig",
     "onLanguage:csharp"
   ],

editors/vscode/src/languages.ts

@@ -19,6 +19,7 @@ export const SUPPORTED_LANGUAGES = [
   "toml",
   "typescript",
   "typst",
+  "yaml",
   "zig",
   "csharp"
 ] as const;