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>
This commit is contained in:
Colby McHenry
2026-04-03 19:25:59 -05:00
co-authored by Claude Opus 4.6
parent 0d63166f9d
commit c8407ad007
21 changed files with 2056 additions and 1852 deletions
+53
View File
@@ -0,0 +1,53 @@
import { getNodeText, getChildByField } from '../tree-sitter-helpers';
import type { LanguageExtractor } from '../tree-sitter-types';
export const pythonExtractor: LanguageExtractor = {
functionTypes: ['function_definition'],
classTypes: ['class_definition'],
methodTypes: ['function_definition'], // Methods are functions inside classes
interfaceTypes: [],
structTypes: [],
enumTypes: [],
typeAliasTypes: [],
importTypes: ['import_statement', 'import_from_statement'],
callTypes: ['call'],
variableTypes: ['assignment'], // Python uses assignment for variable declarations
nameField: 'name',
bodyField: 'body',
paramsField: 'parameters',
returnField: 'return_type',
getSignature: (node, source) => {
const params = getChildByField(node, 'parameters');
const returnType = getChildByField(node, 'return_type');
if (!params) return undefined;
let sig = getNodeText(params, source);
if (returnType) {
sig += ' -> ' + getNodeText(returnType, source);
}
return sig;
},
isAsync: (node) => {
const prev = node.previousSibling;
return prev?.type === 'async';
},
isStatic: (node) => {
// Check for @staticmethod decorator
const prev = node.previousNamedSibling;
if (prev?.type === 'decorator') {
const text = prev.text;
return text.includes('staticmethod');
}
return false;
},
extractImport: (node, source) => {
const importText = source.substring(node.startIndex, node.endIndex).trim();
if (node.type === 'import_from_statement') {
const moduleNode = node.childForFieldName('module_name');
if (moduleNode) {
return { moduleName: source.substring(moduleNode.startIndex, moduleNode.endIndex), signature: importText };
}
}
// import_statement creates multiple imports - return null for core fallback
return null;
},
};