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
+63
View File
@@ -0,0 +1,63 @@
import type { Node as SyntaxNode } from 'web-tree-sitter';
import { getNodeText } from '../tree-sitter-helpers';
import type { LanguageExtractor } from '../tree-sitter-types';
export const phpExtractor: LanguageExtractor = {
functionTypes: ['function_definition'],
classTypes: ['class_declaration'],
methodTypes: ['method_declaration'],
interfaceTypes: ['interface_declaration'],
structTypes: [],
enumTypes: ['enum_declaration'],
typeAliasTypes: [],
importTypes: ['namespace_use_declaration'],
callTypes: ['function_call_expression', 'member_call_expression', 'scoped_call_expression'],
variableTypes: ['property_declaration', 'const_declaration'],
nameField: 'name',
bodyField: 'body',
paramsField: 'parameters',
returnField: 'return_type',
getVisibility: (node) => {
for (let i = 0; i < node.childCount; i++) {
const child = node.child(i);
if (child?.type === 'visibility_modifier') {
const text = child.text;
if (text === 'public') return 'public';
if (text === 'private') return 'private';
if (text === 'protected') return 'protected';
}
}
return 'public'; // PHP defaults to public
},
isStatic: (node) => {
for (let i = 0; i < node.childCount; i++) {
const child = node.child(i);
if (child?.type === 'static_modifier') return true;
}
return false;
},
extractImport: (node, source) => {
const importText = source.substring(node.startIndex, node.endIndex).trim();
// Check for grouped imports: use X\{A, B} - return null for core fallback
const namespacePrefix = node.namedChildren.find((c: SyntaxNode) => c.type === 'namespace_name');
const useGroup = node.namedChildren.find((c: SyntaxNode) => c.type === 'namespace_use_group');
if (namespacePrefix && useGroup) {
return null; // Grouped imports create multiple nodes - let core handle
}
// Single import - find namespace_use_clause
const useClause = node.namedChildren.find((c: SyntaxNode) => c.type === 'namespace_use_clause');
if (useClause) {
const qualifiedName = useClause.namedChildren.find((c: SyntaxNode) => c.type === 'qualified_name');
if (qualifiedName) {
return { moduleName: getNodeText(qualifiedName, source), signature: importText };
}
const name = useClause.namedChildren.find((c: SyntaxNode) => c.type === 'name');
if (name) {
return { moduleName: getNodeText(name, source), signature: importText };
}
}
return null;
},
};