feat(extraction): add ArkTS language support

src/extraction/grammars.ts

@@ -38,6 +38,7 @@ const WASM_GRAMMAR_FILES: Record<GrammarLanguage, string> = {
   lua: 'tree-sitter-lua.wasm',
   luau: 'tree-sitter-luau.wasm',
   objc: 'tree-sitter-objc.wasm',
+  arkts: 'tree-sitter-arkts.wasm',
 };
 
 /**
@@ -49,6 +50,7 @@ export const EXTENSION_MAP: Record<string, Language> = {
   // ESM/CJS TypeScript module extensions — parsed as TS (no JSX). (#366)
   '.mts': 'typescript',
   '.cts': 'typescript',
+  '.ets': 'arkts',
   '.js': 'javascript',
   '.mjs': 'javascript',
   '.cjs': 'javascript',
@@ -185,7 +187,7 @@ export async function loadGrammarsForLanguages(languages: Language[]): Promise<v
       // ABI-13 build that corrupts the shared WASM heap under web-tree-sitter
       // 0.25 (drops nested calls/imports on every file after the first); we
       // vendor the upstream ABI-15 wasm instead.
-      const wasmPath = (lang === 'pascal' || lang === 'scala' || lang === 'lua' || lang === 'luau')
+      const wasmPath = (lang === 'pascal' || lang === 'scala' || lang === 'lua' || lang === 'luau' || lang === 'arkts')
         ? path.join(__dirname, 'wasm', wasmFile)
         : require.resolve(`tree-sitter-wasms/out/${wasmFile}`);
       const language = await WasmLanguage.load(wasmPath);
@@ -384,6 +386,7 @@ export function getLanguageDisplayName(language: Language): string {
     lua: 'Lua',
     luau: 'Luau',
     objc: 'Objective-C',
+    arkts: 'ArkTS',
     yaml: 'YAML',
     twig: 'Twig',
     xml: 'XML',

src/extraction/languages/arkts.ts

@@ -0,0 +1,23 @@
+import type { LanguageExtractor } from '../tree-sitter-types';
+import { typescriptExtractor } from './typescript';
+
+/**
+ * ArkTS language extractor.
+ *
+ * ArkTS is a TypeScript superset used in HarmonyOS/ArkUI development.
+ * It extends TypeScript with:
+ *   - `struct` keyword for component definitions (@Component struct X { ... })
+ *   - Decorator-first patterns (@State, @Prop, @Link, @Builder, @Styles, etc.)
+ *   - `.ets` file extension
+ *
+ * The base TypeScript extractor handles all shared syntax. ArkTS-specific
+ * constructs (decorators, structs) are recognized through the existing
+ * decorator and struct extraction paths.
+ */
+export const arktsExtractor: LanguageExtractor = {
+  ...typescriptExtractor,
+
+  // ArkTS uses `struct` keyword for component definitions.
+  // tree-sitter-arkts grammar parses these as `struct_declaration` nodes.
+  structTypes: ['struct_declaration'],
+};

src/extraction/languages/index.ts

@@ -26,6 +26,7 @@ import { scalaExtractor } from './scala';
 import { luaExtractor } from './lua';
 import { luauExtractor } from './luau';
 import { objcExtractor } from './objc';
+import { arktsExtractor } from './arkts';
 
 export const EXTRACTORS: Partial<Record<Language, LanguageExtractor>> = {
   typescript: typescriptExtractor,
@@ -49,4 +50,5 @@ export const EXTRACTORS: Partial<Record<Language, LanguageExtractor>> = {
   lua: luaExtractor,
   luau: luauExtractor,
   objc: objcExtractor,
+  arkts: arktsExtractor,
 };

src/types.ts

@@ -88,6 +88,7 @@ export const LANGUAGES = [
   'lua',
   'luau',
   'objc',
+  'arkts',
   'yaml',
   'twig',
   'xml',