feat: add Solidity, Objective-C, CUDA, Groovy, Verilog language support (#729)

* feat: add Solidity, Objective-C, CUDA, Groovy, Verilog language support

* fix: correct Solidity state variable kind and struct member collection (#729)

- Change handleStateVarDecl to emit kind 'variable' instead of 'function'
  for state variables like `uint256 public totalSupply`
- Fix inverted condition in handleStructDecl that prevented struct members
  from ever being collected

* fix: resolve ObjC extractor name extraction for grammar compatibility (#729)

The tree-sitter-objc grammar does not expose class/protocol names as
named fields. Fall back to finding the first identifier child node when
childForFieldName('name') returns null.

* fix: resolve Verilog function/task name extraction and strengthen test assertions (#729)

- Add findFunctionOrTaskName helper that searches for function_identifier
  and task_identifier node types used by the tree-sitter-verilog grammar
- Remove duplicate handling of function_body_declaration/task_body_declaration
  from the walker to prevent double definitions
- Replace trivially-passing toBeGreaterThanOrEqual(0) assertions with
  specific content checks for module instantiations and package imports

Author: carlos-alm

package.json

@@ -174,6 +174,11 @@
     "tree-sitter-ruby": "^0.23.1",
     "tree-sitter-rust": "^0.24.0",
     "tree-sitter-scala": "^0.24.0",
+    "tree-sitter-solidity": "^1.2.13",
+    "tree-sitter-objc": "^3.0.2",
+    "tree-sitter-cuda": "^0.21.1",
+    "tree-sitter-groovy": "^0.1.2",
+    "tree-sitter-verilog": "^1.0.0",
     "tree-sitter-swift": "^0.7.1",
     "tree-sitter-typescript": "^0.23.2",
     "typescript": "^6.0.2",

scripts/build-wasm.ts

@@ -52,6 +52,11 @@ const grammars = [
   { name: 'tree-sitter-julia', pkg: 'tree-sitter-julia', sub: null },
   { name: 'tree-sitter-r', pkg: '@eagleoutice/tree-sitter-r', sub: null },
   { name: 'tree-sitter-erlang', pkg: 'tree-sitter-erlang', sub: null },
+  { name: 'tree-sitter-solidity', pkg: 'tree-sitter-solidity', sub: null },
+  { name: 'tree-sitter-objc', pkg: 'tree-sitter-objc', sub: null },
+  { name: 'tree-sitter-cuda', pkg: 'tree-sitter-cuda', sub: null },
+  { name: 'tree-sitter-groovy', pkg: 'tree-sitter-groovy', sub: null },
+  { name: 'tree-sitter-verilog', pkg: 'tree-sitter-verilog', sub: null },
 ];
 
 let failed = 0;

src/domain/parser.ts

@@ -21,27 +21,32 @@ export {
   extractCppSymbols,
   extractCSharpSymbols,
   extractCSymbols,
+  extractCudaSymbols,
   extractDartSymbols,
   extractElixirSymbols,
   extractErlangSymbols,
   extractFSharpSymbols,
   extractGleamSymbols,
   extractGoSymbols,
+  extractGroovySymbols,
   extractHaskellSymbols,
   extractHCLSymbols,
   extractJavaSymbols,
   extractJuliaSymbols,
   extractKotlinSymbols,
   extractLuaSymbols,
+  extractObjCSymbols,
   extractOCamlSymbols,
   extractPHPSymbols,
   extractPythonSymbols,
   extractRSymbols,
   extractRubySymbols,
   extractRustSymbols,
   extractScalaSymbols,
+  extractSoliditySymbols,
   extractSwiftSymbols,
   extractSymbols,
+  extractVerilogSymbols,
   extractZigSymbols,
 } from '../extractors/index.js';
 
@@ -51,27 +56,32 @@ import {
   extractCppSymbols,
   extractCSharpSymbols,
   extractCSymbols,
+  extractCudaSymbols,
   extractDartSymbols,
   extractElixirSymbols,
   extractErlangSymbols,
   extractFSharpSymbols,
   extractGleamSymbols,
   extractGoSymbols,
+  extractGroovySymbols,
   extractHaskellSymbols,
   extractHCLSymbols,
   extractJavaSymbols,
   extractJuliaSymbols,
   extractKotlinSymbols,
   extractLuaSymbols,
+  extractObjCSymbols,
   extractOCamlSymbols,
   extractPHPSymbols,
   extractPythonSymbols,
   extractRSymbols,
   extractRubySymbols,
   extractRustSymbols,
   extractScalaSymbols,
+  extractSoliditySymbols,
   extractSwiftSymbols,
   extractSymbols,
+  extractVerilogSymbols,
   extractZigSymbols,
 } from '../extractors/index.js';
 
@@ -588,6 +598,41 @@ export const LANGUAGE_REGISTRY: LanguageRegistryEntry[] = [
     extractor: extractErlangSymbols,
     required: false,
   },
+  {
+    id: 'solidity',
+    extensions: ['.sol'],
+    grammarFile: 'tree-sitter-solidity.wasm',
+    extractor: extractSoliditySymbols,
+    required: false,
+  },
+  {
+    id: 'objc',
+    extensions: ['.m'],
+    grammarFile: 'tree-sitter-objc.wasm',
+    extractor: extractObjCSymbols,
+    required: false,
+  },
+  {
+    id: 'cuda',
+    extensions: ['.cu', '.cuh'],
+    grammarFile: 'tree-sitter-cuda.wasm',
+    extractor: extractCudaSymbols,
+    required: false,
+  },
+  {
+    id: 'groovy',
+    extensions: ['.groovy', '.gvy'],
+    grammarFile: 'tree-sitter-groovy.wasm',
+    extractor: extractGroovySymbols,
+    required: false,
+  },
+  {
+    id: 'verilog',
+    extensions: ['.v', '.sv'],
+    grammarFile: 'tree-sitter-verilog.wasm',
+    extractor: extractVerilogSymbols,
+    required: false,
+  },
 ];
 
 const _extToLang: Map<string, LanguageRegistryEntry> = new Map();
@@ -820,7 +865,7 @@ export function getActiveEngine(opts: ParseEngineOpts = {}): {
  */
 export function createParseTreeCache(): any {
   const native = loadNative();
-  if (!native || !native.ParseTreeCache) return null;
+  if (!native?.ParseTreeCache) return null;
   return new native.ParseTreeCache();
 }