refactor: Extract per-language configs and standalone extractors from tree-sitter.ts

Splits the monolithic tree-sitter.ts (3,358 lines) into modular files: - 14 language config files under src/extraction/languages/ - 3 standalone extractors (Liquid, Svelte, DFM) - Shared helpers and types modules to avoid circular imports Also fixes a bug where Java's extractImport hook incorrectly set handledRefs: true, preventing unresolved reference creation and degrading codegraph_explore results for Java codebases. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-03 19:25:59 -05:00
parent 0d63166f9d
commit c8407ad007
21 changed files with 2056 additions and 1852 deletions
@@ -0,0 +1,83 @@
+import type { Node as SyntaxNode } from 'web-tree-sitter';
+import { getNodeText } from '../tree-sitter-helpers';
+import type { LanguageExtractor } from '../tree-sitter-types';
+
+export const cExtractor: LanguageExtractor = {
+  functionTypes: ['function_definition'],
+  classTypes: [],
+  methodTypes: [],
+  interfaceTypes: [],
+  structTypes: ['struct_specifier'],
+  enumTypes: ['enum_specifier'],
+  typeAliasTypes: ['type_definition'], // typedef
+  importTypes: ['preproc_include'],
+  callTypes: ['call_expression'],
+  variableTypes: ['declaration'],
+  nameField: 'declarator',
+  bodyField: 'body',
+  paramsField: 'parameters',
+  extractImport: (node, source) => {
+    const importText = source.substring(node.startIndex, node.endIndex).trim();
+    // C includes: #include <stdio.h>, #include "myheader.h"
+    const systemLib = node.namedChildren.find((c: SyntaxNode) => c.type === 'system_lib_string');
+    if (systemLib) {
+      return { moduleName: getNodeText(systemLib, source).replace(/^<|>$/g, ''), signature: importText };
+    }
+    const stringLiteral = node.namedChildren.find((c: SyntaxNode) => c.type === 'string_literal');
+    if (stringLiteral) {
+      const stringContent = stringLiteral.namedChildren.find((c: SyntaxNode) => c.type === 'string_content');
+      if (stringContent) {
+        return { moduleName: getNodeText(stringContent, source), signature: importText };
+      }
+    }
+    return null;
+  },
+};
+
+export const cppExtractor: LanguageExtractor = {
+  functionTypes: ['function_definition'],
+  classTypes: ['class_specifier'],
+  methodTypes: ['function_definition'],
+  interfaceTypes: [],
+  structTypes: ['struct_specifier'],
+  enumTypes: ['enum_specifier'],
+  typeAliasTypes: ['type_definition', 'alias_declaration'], // typedef and using
+  importTypes: ['preproc_include'],
+  callTypes: ['call_expression'],
+  variableTypes: ['declaration'],
+  nameField: 'declarator',
+  bodyField: 'body',
+  paramsField: 'parameters',
+  getVisibility: (node) => {
+    // Check for access specifier in parent
+    const parent = node.parent;
+    if (parent) {
+      for (let i = 0; i < parent.childCount; i++) {
+        const child = parent.child(i);
+        if (child?.type === 'access_specifier') {
+          const text = child.text;
+          if (text.includes('public')) return 'public';
+          if (text.includes('private')) return 'private';
+          if (text.includes('protected')) return 'protected';
+        }
+      }
+    }
+    return undefined;
+  },
+  extractImport: (node, source) => {
+    const importText = source.substring(node.startIndex, node.endIndex).trim();
+    // C++ includes: #include <iostream>, #include "myheader.h"
+    const systemLib = node.namedChildren.find((c: SyntaxNode) => c.type === 'system_lib_string');
+    if (systemLib) {
+      return { moduleName: getNodeText(systemLib, source).replace(/^<|>$/g, ''), signature: importText };
+    }
+    const stringLiteral = node.namedChildren.find((c: SyntaxNode) => c.type === 'string_literal');
+    if (stringLiteral) {
+      const stringContent = stringLiteral.namedChildren.find((c: SyntaxNode) => c.type === 'string_content');
+      if (stringContent) {
+        return { moduleName: getNodeText(stringContent, source), signature: importText };
+      }
+    }
+    return null;
+  },
+};