fix(extraction): index TS/JS generator function declarations and expressions (#1741) (#1743)

Tree-sitter kinds generator_function_declaration / generator_function were
missing from both the wasm and native kernel function-type lists, so
function* / async function* (and const g = function* () {}) produced no
nodes. Add the kinds on both paths and cover TS+JS declaration/expression
forms in extraction tests.

Co-authored-by: Colby McHenry <colbymchenry@users.noreply.github.com>

src/extraction/languages/javascript.ts

@@ -3,7 +3,7 @@ import type { LanguageExtractor } from '../tree-sitter-types';
 import { classifyTsClassMember } from './typescript';
 
 export const javascriptExtractor: LanguageExtractor = {
-  functionTypes: ['function_declaration', 'arrow_function', 'function_expression'],
+  functionTypes: ['function_declaration', 'generator_function_declaration', 'arrow_function', 'function_expression', 'generator_function'],
   classTypes: ['class_declaration'],
   methodTypes: ['method_definition', 'field_definition'],
   // JS `field_definition` ≙ TS `public_field_definition`: plain fields are

src/extraction/languages/typescript.ts

@@ -39,7 +39,7 @@ export function classifyTsClassMember(node: SyntaxNode): 'method' | 'property' {
 }
 
 export const typescriptExtractor: LanguageExtractor = {
-  functionTypes: ['function_declaration', 'arrow_function', 'function_expression'],
+  functionTypes: ['function_declaration', 'generator_function_declaration', 'arrow_function', 'function_expression', 'generator_function'],
   classTypes: ['class_declaration', 'abstract_class_declaration'],
   methodTypes: ['method_definition', 'public_field_definition'],
   classifyMethodNode: classifyTsClassMember,

src/extraction/tree-sitter.ts

@@ -171,7 +171,7 @@ function extractNameRaw(node: SyntaxNode, source: string, extractor: LanguageExt
   // not from identifiers in their body. Without this, single-expression arrow
   // functions like `const fn = () => someIdentifier` get named "someIdentifier"
   // instead of "fn", because the fallback below finds the body identifier.
-  if (node.type === 'arrow_function' || node.type === 'function_expression') {
+  if (node.type === 'arrow_function' || node.type === 'function_expression' || node.type === 'generator_function') {
     return '<anonymous>';
   }
 
@@ -1556,7 +1556,7 @@ export class TreeSitterExtractor {
     if (
       !nameOverride &&
       name === '<anonymous>' &&
-      (node.type === 'arrow_function' || node.type === 'function_expression')
+      (node.type === 'arrow_function' || node.type === 'function_expression' || node.type === 'generator_function')
     ) {
       const parent = node.parent;
       if (parent?.type === 'variable_declarator') {
@@ -2623,7 +2623,7 @@ export class TreeSitterExtractor {
             }
             const name = getNodeText(nameNode, this.source);
             // Arrow functions / function expressions: extract as function instead of variable
-            if (valueNode && (valueNode.type === 'arrow_function' || valueNode.type === 'function_expression')) {
+            if (valueNode && (valueNode.type === 'arrow_function' || valueNode.type === 'function_expression' || valueNode.type === 'generator_function')) {
               this.extractFunction(valueNode);
               continue;
             }