Adds Lua (.lua) and Luau (.luau) extraction — functions, methods with receivers, type aliases (Luau), require imports (incl. Roblox instance-path), and call edges. Vendors the ABI-15 Lua and ABI-14 Luau tree-sitter grammars. Addresses #232.
2577 lines
96 KiB
TypeScript
2577 lines
96 KiB
TypeScript
/**
|
|
* Tree-sitter Parser Wrapper
|
|
*
|
|
* Handles parsing source code and extracting structural information.
|
|
*/
|
|
|
|
import { Node as SyntaxNode, Tree } from 'web-tree-sitter';
|
|
import * as path from 'path';
|
|
import {
|
|
Language,
|
|
Node,
|
|
Edge,
|
|
NodeKind,
|
|
ExtractionResult,
|
|
ExtractionError,
|
|
UnresolvedReference,
|
|
} from '../types';
|
|
import { getParser, detectLanguage, isLanguageSupported } from './grammars';
|
|
import { generateNodeId, getNodeText, getChildByField, getPrecedingDocstring } from './tree-sitter-helpers';
|
|
import type { LanguageExtractor, ExtractorContext } from './tree-sitter-types';
|
|
import { EXTRACTORS } from './languages';
|
|
import { LiquidExtractor } from './liquid-extractor';
|
|
import { SvelteExtractor } from './svelte-extractor';
|
|
import { DfmExtractor } from './dfm-extractor';
|
|
import { VueExtractor } from './vue-extractor';
|
|
import {
|
|
getAllFrameworkResolvers,
|
|
getApplicableFrameworks,
|
|
} from '../resolution/frameworks';
|
|
|
|
// Re-export for backward compatibility
|
|
export { generateNodeId } from './tree-sitter-helpers';
|
|
|
|
/**
|
|
* Extract the name from a node based on language
|
|
*/
|
|
function extractName(node: SyntaxNode, source: string, extractor: LanguageExtractor): string {
|
|
// Try field name first
|
|
const nameNode = getChildByField(node, extractor.nameField);
|
|
if (nameNode) {
|
|
// Unwrap pointer_declarator(s) for C/C++ pointer return types
|
|
let resolved = nameNode;
|
|
while (resolved.type === 'pointer_declarator') {
|
|
const inner = getChildByField(resolved, 'declarator') || resolved.namedChild(0);
|
|
if (!inner) break;
|
|
resolved = inner;
|
|
}
|
|
// Handle complex declarators (C/C++)
|
|
if (resolved.type === 'function_declarator' || resolved.type === 'declarator') {
|
|
const innerName = getChildByField(resolved, 'declarator') || resolved.namedChild(0);
|
|
return innerName ? getNodeText(innerName, source) : getNodeText(resolved, source);
|
|
}
|
|
// Lua: `function t.f()` / `function t:m()` — the name node is a dot/method
|
|
// index expression; the simple name is the trailing field/method (the table
|
|
// receiver is captured separately via getReceiverType).
|
|
if (resolved.type === 'dot_index_expression') {
|
|
const field = getChildByField(resolved, 'field');
|
|
if (field) return getNodeText(field, source);
|
|
}
|
|
if (resolved.type === 'method_index_expression') {
|
|
const method = getChildByField(resolved, 'method');
|
|
if (method) return getNodeText(method, source);
|
|
}
|
|
return getNodeText(resolved, source);
|
|
}
|
|
|
|
// For Dart method_signature, look inside inner signature types
|
|
if (node.type === 'method_signature') {
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child && (
|
|
child.type === 'function_signature' ||
|
|
child.type === 'getter_signature' ||
|
|
child.type === 'setter_signature' ||
|
|
child.type === 'constructor_signature' ||
|
|
child.type === 'factory_constructor_signature'
|
|
)) {
|
|
// Find identifier inside the inner signature
|
|
for (let j = 0; j < child.namedChildCount; j++) {
|
|
const inner = child.namedChild(j);
|
|
if (inner?.type === 'identifier') {
|
|
return getNodeText(inner, source);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
// Arrow/function expressions get their name from the parent variable_declarator,
|
|
// 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') {
|
|
return '<anonymous>';
|
|
}
|
|
|
|
// Fall back to first identifier child
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (
|
|
child &&
|
|
(child.type === 'identifier' ||
|
|
child.type === 'type_identifier' ||
|
|
child.type === 'simple_identifier' ||
|
|
child.type === 'constant')
|
|
) {
|
|
return getNodeText(child, source);
|
|
}
|
|
}
|
|
|
|
return '<anonymous>';
|
|
}
|
|
|
|
/**
|
|
* Tree-sitter node kinds that represent constructor invocations
|
|
* (`new Foo()` and friends). Used by extractInstantiation to emit
|
|
* an `instantiates` reference targeting the class name.
|
|
*/
|
|
const INSTANTIATION_KINDS: ReadonlySet<string> = new Set([
|
|
'new_expression', // typescript / javascript / tsx / jsx
|
|
'object_creation_expression', // java / c#
|
|
'instance_creation_expression', // some grammars
|
|
]);
|
|
|
|
/**
|
|
* TreeSitterExtractor - Main extraction class
|
|
*/
|
|
export class TreeSitterExtractor {
|
|
private filePath: string;
|
|
private language: Language;
|
|
private source: string;
|
|
private tree: Tree | null = null;
|
|
private nodes: Node[] = [];
|
|
private edges: Edge[] = [];
|
|
private unresolvedReferences: UnresolvedReference[] = [];
|
|
private errors: ExtractionError[] = [];
|
|
private extractor: LanguageExtractor | null = null;
|
|
private nodeStack: string[] = []; // Stack of parent node IDs
|
|
private methodIndex: Map<string, string> | null = null; // lookup key → node ID for Pascal defProc lookup
|
|
|
|
constructor(filePath: string, source: string, language?: Language) {
|
|
this.filePath = filePath;
|
|
this.source = source;
|
|
this.language = language || detectLanguage(filePath, source);
|
|
this.extractor = EXTRACTORS[this.language] || null;
|
|
}
|
|
|
|
/**
|
|
* Parse and extract from the source code
|
|
*/
|
|
extract(): ExtractionResult {
|
|
const startTime = Date.now();
|
|
|
|
if (!isLanguageSupported(this.language)) {
|
|
return {
|
|
nodes: [],
|
|
edges: [],
|
|
unresolvedReferences: [],
|
|
errors: [
|
|
{
|
|
message: `Unsupported language: ${this.language}`,
|
|
filePath: this.filePath,
|
|
severity: 'error',
|
|
code: 'unsupported_language',
|
|
},
|
|
],
|
|
durationMs: Date.now() - startTime,
|
|
};
|
|
}
|
|
|
|
const parser = getParser(this.language);
|
|
if (!parser) {
|
|
return {
|
|
nodes: [],
|
|
edges: [],
|
|
unresolvedReferences: [],
|
|
errors: [
|
|
{
|
|
message: `Failed to get parser for language: ${this.language}`,
|
|
filePath: this.filePath,
|
|
severity: 'error',
|
|
code: 'parser_error',
|
|
},
|
|
],
|
|
durationMs: Date.now() - startTime,
|
|
};
|
|
}
|
|
|
|
try {
|
|
this.tree = parser.parse(this.source) ?? null;
|
|
if (!this.tree) {
|
|
throw new Error('Parser returned null tree');
|
|
}
|
|
|
|
// Create file node representing the source file
|
|
const fileNode: Node = {
|
|
id: `file:${this.filePath}`,
|
|
kind: 'file',
|
|
name: path.basename(this.filePath),
|
|
qualifiedName: this.filePath,
|
|
filePath: this.filePath,
|
|
language: this.language,
|
|
startLine: 1,
|
|
endLine: this.source.split('\n').length,
|
|
startColumn: 0,
|
|
endColumn: 0,
|
|
isExported: false,
|
|
updatedAt: Date.now(),
|
|
};
|
|
this.nodes.push(fileNode);
|
|
|
|
// Push file node onto stack so top-level declarations get contains edges
|
|
this.nodeStack.push(fileNode.id);
|
|
this.visitNode(this.tree.rootNode);
|
|
this.nodeStack.pop();
|
|
} catch (error) {
|
|
const msg = error instanceof Error ? error.message : String(error);
|
|
|
|
// WASM memory errors leave the module in a corrupted state — all subsequent
|
|
// parses would also fail. Re-throw so the worker can detect and crash,
|
|
// forcing a clean restart with a fresh heap.
|
|
if (msg.includes('memory access out of bounds') || msg.includes('out of memory')) {
|
|
throw error;
|
|
}
|
|
|
|
this.errors.push({
|
|
message: `Parse error: ${msg}`,
|
|
filePath: this.filePath,
|
|
severity: 'error',
|
|
code: 'parse_error',
|
|
});
|
|
} finally {
|
|
// Free tree-sitter WASM memory immediately — trees hold native heap memory
|
|
// invisible to V8's GC that accumulates across thousands of files.
|
|
if (this.tree) {
|
|
this.tree.delete();
|
|
this.tree = null;
|
|
}
|
|
// Release source string to reduce GC pressure
|
|
this.source = '';
|
|
}
|
|
|
|
return {
|
|
nodes: this.nodes,
|
|
edges: this.edges,
|
|
unresolvedReferences: this.unresolvedReferences,
|
|
errors: this.errors,
|
|
durationMs: Date.now() - startTime,
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Visit a node and extract information
|
|
*/
|
|
private visitNode(node: SyntaxNode): void {
|
|
if (!this.extractor) return;
|
|
|
|
const nodeType = node.type;
|
|
let skipChildren = false;
|
|
|
|
// Language-specific custom visitor hook
|
|
if (this.extractor.visitNode) {
|
|
const ctx = this.makeExtractorContext();
|
|
const handled = this.extractor.visitNode(node, ctx);
|
|
if (handled) return;
|
|
}
|
|
|
|
// Pascal-specific AST handling
|
|
if (this.language === 'pascal') {
|
|
skipChildren = this.visitPascalNode(node);
|
|
if (skipChildren) return;
|
|
}
|
|
|
|
// Check for function declarations
|
|
// For Python/Ruby, function_definition inside a class should be treated as method
|
|
if (this.extractor.functionTypes.includes(nodeType)) {
|
|
if (this.isInsideClassLikeNode() && this.extractor.methodTypes.includes(nodeType)) {
|
|
// Inside a class - treat as method
|
|
this.extractMethod(node);
|
|
skipChildren = true; // extractMethod visits children via visitFunctionBody
|
|
} else {
|
|
this.extractFunction(node);
|
|
skipChildren = true; // extractFunction visits children via visitFunctionBody
|
|
}
|
|
}
|
|
// Check for class declarations
|
|
else if (this.extractor.classTypes.includes(nodeType)) {
|
|
// Some languages reuse class_declaration for structs/enums (e.g. Swift)
|
|
const classification = this.extractor.classifyClassNode?.(node) ?? 'class';
|
|
if (classification === 'struct') {
|
|
this.extractStruct(node);
|
|
} else if (classification === 'enum') {
|
|
this.extractEnum(node);
|
|
} else if (classification === 'interface') {
|
|
this.extractInterface(node);
|
|
} else if (classification === 'trait') {
|
|
this.extractClass(node, 'trait');
|
|
} else {
|
|
this.extractClass(node);
|
|
}
|
|
skipChildren = true; // extractClass visits body children
|
|
}
|
|
// Extra class node types (e.g. Dart mixin_declaration, extension_declaration)
|
|
else if (this.extractor.extraClassNodeTypes?.includes(nodeType)) {
|
|
this.extractClass(node);
|
|
skipChildren = true;
|
|
}
|
|
// Check for method declarations (only if not already handled by functionTypes)
|
|
else if (this.extractor.methodTypes.includes(nodeType)) {
|
|
this.extractMethod(node);
|
|
skipChildren = true; // extractMethod visits children via visitFunctionBody
|
|
}
|
|
// Check for interface/protocol/trait declarations
|
|
else if (this.extractor.interfaceTypes.includes(nodeType)) {
|
|
this.extractInterface(node);
|
|
skipChildren = true; // extractInterface visits body children
|
|
}
|
|
// Check for struct declarations
|
|
else if (this.extractor.structTypes.includes(nodeType)) {
|
|
this.extractStruct(node);
|
|
skipChildren = true; // extractStruct visits body children
|
|
}
|
|
// Check for enum declarations
|
|
else if (this.extractor.enumTypes.includes(nodeType)) {
|
|
this.extractEnum(node);
|
|
skipChildren = true; // extractEnum visits body children
|
|
}
|
|
// Check for type alias declarations (e.g. `type X = ...` in TypeScript)
|
|
// For Go, type_spec wraps struct/interface definitions — resolveTypeAliasKind
|
|
// detects these and extractTypeAlias creates the correct node kind.
|
|
else if (this.extractor.typeAliasTypes.includes(nodeType)) {
|
|
skipChildren = this.extractTypeAlias(node);
|
|
}
|
|
// Check for class properties (e.g. C# property_declaration)
|
|
else if (this.extractor.propertyTypes?.includes(nodeType) && this.isInsideClassLikeNode()) {
|
|
this.extractProperty(node);
|
|
skipChildren = true;
|
|
}
|
|
// Check for class fields (e.g. Java field_declaration, C# field_declaration)
|
|
else if (this.extractor.fieldTypes?.includes(nodeType) && this.isInsideClassLikeNode()) {
|
|
this.extractField(node);
|
|
skipChildren = true;
|
|
}
|
|
// Check for variable declarations (const, let, var, etc.)
|
|
// Only extract top-level variables (not inside functions/methods)
|
|
else if (this.extractor.variableTypes.includes(nodeType) && !this.isInsideClassLikeNode()) {
|
|
this.extractVariable(node);
|
|
skipChildren = true; // extractVariable handles children
|
|
}
|
|
// `export_statement` itself is not extracted — the walker descends
|
|
// into children, where the inner declaration (lexical_declaration,
|
|
// function_declaration, class_declaration, etc.) is dispatched to
|
|
// its own extractor. `isExported` walks the parent chain, so the
|
|
// exported flag is preserved automatically.
|
|
//
|
|
// Calling extractExportedVariables here AND descending caused every
|
|
// `export const X = ...` to produce two nodes for the same symbol —
|
|
// one kind:'variable' from extractExportedVariables and one
|
|
// kind:'constant' from extractVariable. The dedicated dispatch is
|
|
// the correct one (it picks kind from isConst, captures the
|
|
// initializer signature, and walks type annotations); the
|
|
// export-statement helper was redundant.
|
|
// Check for imports
|
|
else if (this.extractor.importTypes.includes(nodeType)) {
|
|
this.extractImport(node);
|
|
}
|
|
// Check for function calls
|
|
else if (this.extractor.callTypes.includes(nodeType)) {
|
|
this.extractCall(node);
|
|
}
|
|
// `new Foo(...)` / `Foo::new(...)` / object_creation_expression —
|
|
// produce an `instantiates` reference. Children still walked so
|
|
// nested calls inside the constructor args (`new Foo(bar())`) get
|
|
// their own `calls` refs.
|
|
else if (INSTANTIATION_KINDS.has(nodeType)) {
|
|
this.extractInstantiation(node);
|
|
}
|
|
// (Decorator handling lives inside the symbol-creating extractors
|
|
// — extractClass / extractFunction / extractProperty — because the
|
|
// decorator node sits BEFORE the symbol in the AST and the walker
|
|
// would otherwise see the wrong nodeStack head.)
|
|
// Rust: `impl Trait for Type { ... }` — creates implements edge from Type to Trait
|
|
else if (nodeType === 'impl_item') {
|
|
this.extractRustImplItem(node);
|
|
}
|
|
|
|
// Visit children (unless the extract method already visited them)
|
|
if (!skipChildren) {
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child) {
|
|
this.visitNode(child);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Create a Node object
|
|
*/
|
|
private createNode(
|
|
kind: NodeKind,
|
|
name: string,
|
|
node: SyntaxNode,
|
|
extra?: Partial<Node>
|
|
): Node | null {
|
|
// Skip nodes with empty/missing names — they are not meaningful symbols
|
|
// and would cause FK violations when edges reference them (see issue #42)
|
|
if (!name) {
|
|
return null;
|
|
}
|
|
|
|
const id = generateNodeId(this.filePath, kind, name, node.startPosition.row + 1);
|
|
|
|
const newNode: Node = {
|
|
id,
|
|
kind,
|
|
name,
|
|
qualifiedName: this.buildQualifiedName(name),
|
|
filePath: this.filePath,
|
|
language: this.language,
|
|
startLine: node.startPosition.row + 1,
|
|
endLine: node.endPosition.row + 1,
|
|
startColumn: node.startPosition.column,
|
|
endColumn: node.endPosition.column,
|
|
updatedAt: Date.now(),
|
|
...extra,
|
|
};
|
|
|
|
this.nodes.push(newNode);
|
|
|
|
// Add containment edge from parent
|
|
if (this.nodeStack.length > 0) {
|
|
const parentId = this.nodeStack[this.nodeStack.length - 1];
|
|
if (parentId) {
|
|
this.edges.push({
|
|
source: parentId,
|
|
target: id,
|
|
kind: 'contains',
|
|
});
|
|
}
|
|
}
|
|
|
|
return newNode;
|
|
}
|
|
|
|
/**
|
|
* Find first named child whose type is in the given list.
|
|
* Used to locate inner type nodes (e.g. enum_specifier inside a typedef).
|
|
*/
|
|
private findChildByTypes(node: SyntaxNode, types: string[]): SyntaxNode | null {
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child && types.includes(child.type)) return child;
|
|
}
|
|
return null;
|
|
}
|
|
|
|
/**
|
|
* Build qualified name from node stack
|
|
*/
|
|
private buildQualifiedName(name: string): string {
|
|
// Build a qualified name from the semantic hierarchy only (no file path).
|
|
// The file path is stored separately in filePath and pollutes FTS if included here.
|
|
const parts: string[] = [];
|
|
for (const nodeId of this.nodeStack) {
|
|
const node = this.nodes.find((n) => n.id === nodeId);
|
|
if (node && node.kind !== 'file') {
|
|
parts.push(node.name);
|
|
}
|
|
}
|
|
parts.push(name);
|
|
return parts.join('::');
|
|
}
|
|
|
|
/**
|
|
* Build an ExtractorContext for passing to language-specific visitNode hooks.
|
|
*/
|
|
private makeExtractorContext(): ExtractorContext {
|
|
// eslint-disable-next-line @typescript-eslint/no-this-alias
|
|
const self = this;
|
|
return {
|
|
createNode: (kind, name, node, extra) => self.createNode(kind, name, node, extra),
|
|
visitNode: (node) => self.visitNode(node),
|
|
visitFunctionBody: (body, functionId) => self.visitFunctionBody(body, functionId),
|
|
addUnresolvedReference: (ref) => self.unresolvedReferences.push(ref),
|
|
pushScope: (nodeId) => self.nodeStack.push(nodeId),
|
|
popScope: () => self.nodeStack.pop(),
|
|
get filePath() { return self.filePath; },
|
|
get source() { return self.source; },
|
|
get nodeStack() { return self.nodeStack; },
|
|
get nodes() { return self.nodes; },
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Check if the current node stack indicates we are inside a class-like node
|
|
* (class, struct, interface, trait). File nodes do not count as class-like.
|
|
*/
|
|
private isInsideClassLikeNode(): boolean {
|
|
if (this.nodeStack.length === 0) return false;
|
|
const parentId = this.nodeStack[this.nodeStack.length - 1];
|
|
if (!parentId) return false;
|
|
const parentNode = this.nodes.find((n) => n.id === parentId);
|
|
if (!parentNode) return false;
|
|
return (
|
|
parentNode.kind === 'class' ||
|
|
parentNode.kind === 'struct' ||
|
|
parentNode.kind === 'interface' ||
|
|
parentNode.kind === 'trait' ||
|
|
parentNode.kind === 'enum' ||
|
|
parentNode.kind === 'module'
|
|
);
|
|
}
|
|
|
|
/**
|
|
* Extract a function
|
|
*/
|
|
private extractFunction(node: SyntaxNode): void {
|
|
if (!this.extractor) return;
|
|
|
|
// If the language provides getReceiverType and this function has a receiver
|
|
// (e.g., Rust function_item inside an impl block), extract as method instead
|
|
if (this.extractor.getReceiverType?.(node, this.source)) {
|
|
this.extractMethod(node);
|
|
return;
|
|
}
|
|
|
|
let name = extractName(node, this.source, this.extractor);
|
|
// For arrow functions and function expressions assigned to variables,
|
|
// resolve the name from the parent variable_declarator.
|
|
// e.g. `export const useAuth = () => { ... }` — the arrow_function node
|
|
// has no `name` field; the name lives on the variable_declarator.
|
|
if (
|
|
name === '<anonymous>' &&
|
|
(node.type === 'arrow_function' || node.type === 'function_expression')
|
|
) {
|
|
const parent = node.parent;
|
|
if (parent?.type === 'variable_declarator') {
|
|
const varName = getChildByField(parent, 'name');
|
|
if (varName) {
|
|
name = getNodeText(varName, this.source);
|
|
}
|
|
}
|
|
}
|
|
if (name === '<anonymous>') return; // Skip anonymous functions
|
|
|
|
// Check for misparse artifacts (e.g. C++ macros causing "namespace detail" functions)
|
|
// Skip the node but still visit the body for calls and structural nodes
|
|
if (this.extractor.isMisparsedFunction?.(name, node)) {
|
|
const body = this.extractor.resolveBody?.(node, this.extractor.bodyField)
|
|
?? getChildByField(node, this.extractor.bodyField);
|
|
if (body) {
|
|
this.visitFunctionBody(body, '');
|
|
}
|
|
return;
|
|
}
|
|
|
|
const docstring = getPrecedingDocstring(node, this.source);
|
|
const signature = this.extractor.getSignature?.(node, this.source);
|
|
const visibility = this.extractor.getVisibility?.(node);
|
|
const isExported = this.extractor.isExported?.(node, this.source);
|
|
const isAsync = this.extractor.isAsync?.(node);
|
|
const isStatic = this.extractor.isStatic?.(node);
|
|
|
|
const funcNode = this.createNode('function', name, node, {
|
|
docstring,
|
|
signature,
|
|
visibility,
|
|
isExported,
|
|
isAsync,
|
|
isStatic,
|
|
});
|
|
if (!funcNode) return;
|
|
|
|
// Extract type annotations (parameter types and return type)
|
|
this.extractTypeAnnotations(node, funcNode.id);
|
|
|
|
// Extract decorators applied to the function (rare in JS/TS but
|
|
// present in Python `@decorator def f():` and Java/Kotlin
|
|
// annotations on free functions).
|
|
this.extractDecoratorsFor(node, funcNode.id);
|
|
|
|
// Push to stack and visit body
|
|
this.nodeStack.push(funcNode.id);
|
|
const body = this.extractor.resolveBody?.(node, this.extractor.bodyField)
|
|
?? getChildByField(node, this.extractor.bodyField);
|
|
if (body) {
|
|
this.visitFunctionBody(body, funcNode.id);
|
|
}
|
|
this.nodeStack.pop();
|
|
}
|
|
|
|
/**
|
|
* Extract a class
|
|
*/
|
|
private extractClass(node: SyntaxNode, kind: NodeKind = 'class'): void {
|
|
if (!this.extractor) return;
|
|
|
|
const name = extractName(node, this.source, this.extractor);
|
|
const docstring = getPrecedingDocstring(node, this.source);
|
|
const visibility = this.extractor.getVisibility?.(node);
|
|
const isExported = this.extractor.isExported?.(node, this.source);
|
|
|
|
const classNode = this.createNode(kind, name, node, {
|
|
docstring,
|
|
visibility,
|
|
isExported,
|
|
});
|
|
if (!classNode) return;
|
|
|
|
// Extract extends/implements
|
|
this.extractInheritance(node, classNode.id);
|
|
|
|
// Extract decorators applied to the class (`@Foo class X {}`).
|
|
this.extractDecoratorsFor(node, classNode.id);
|
|
|
|
// Push to stack and visit body
|
|
this.nodeStack.push(classNode.id);
|
|
let body = this.extractor.resolveBody?.(node, this.extractor.bodyField)
|
|
?? getChildByField(node, this.extractor.bodyField);
|
|
if (!body) body = node;
|
|
|
|
// Visit all children for methods and properties
|
|
for (let i = 0; i < body.namedChildCount; i++) {
|
|
const child = body.namedChild(i);
|
|
if (child) {
|
|
this.visitNode(child);
|
|
}
|
|
}
|
|
this.nodeStack.pop();
|
|
}
|
|
|
|
/**
|
|
* Extract a method
|
|
*/
|
|
private extractMethod(node: SyntaxNode): void {
|
|
if (!this.extractor) return;
|
|
|
|
// For languages with receiver types (Go, Rust), include receiver in qualified name
|
|
// so FTS can match "scrapeLoop.run" → qualified_name "...::scrapeLoop::run"
|
|
const receiverType = this.extractor.getReceiverType?.(node, this.source);
|
|
|
|
// For most languages, only extract as method if inside a class-like node
|
|
// Languages with methodsAreTopLevel (e.g. Go) always treat them as methods
|
|
// Languages with getReceiverType (e.g. Rust) extract as method when receiver is found
|
|
if (!this.isInsideClassLikeNode() && !this.extractor.methodsAreTopLevel && !receiverType) {
|
|
// Skip method_definition nodes inside object literals (getters/setters/methods
|
|
// in inline objects). These are ephemeral and create noise (e.g., Svelte context
|
|
// objects: `ctx.set({ get view() { ... } })`).
|
|
if (node.parent?.type === 'object' || node.parent?.type === 'object_expression') {
|
|
return;
|
|
}
|
|
// Not inside a class-like node and no receiver type, treat as function
|
|
this.extractFunction(node);
|
|
return;
|
|
}
|
|
|
|
const name = extractName(node, this.source, this.extractor);
|
|
|
|
// Check for misparse artifacts (e.g. C++ "switch" inside macro-confused class body)
|
|
if (this.extractor.isMisparsedFunction?.(name, node)) {
|
|
const body = this.extractor.resolveBody?.(node, this.extractor.bodyField)
|
|
?? getChildByField(node, this.extractor.bodyField);
|
|
if (body) {
|
|
this.visitFunctionBody(body, '');
|
|
}
|
|
return;
|
|
}
|
|
|
|
const docstring = getPrecedingDocstring(node, this.source);
|
|
const signature = this.extractor.getSignature?.(node, this.source);
|
|
const visibility = this.extractor.getVisibility?.(node);
|
|
const isAsync = this.extractor.isAsync?.(node);
|
|
const isStatic = this.extractor.isStatic?.(node);
|
|
const extraProps: Partial<Node> = {
|
|
docstring,
|
|
signature,
|
|
visibility,
|
|
isAsync,
|
|
isStatic,
|
|
};
|
|
if (receiverType) {
|
|
extraProps.qualifiedName = `${receiverType}::${name}`;
|
|
}
|
|
|
|
const methodNode = this.createNode('method', name, node, extraProps);
|
|
if (!methodNode) return;
|
|
|
|
// For methods with a receiver type but no class-like parent on the stack
|
|
// (e.g., Rust impl blocks), add a contains edge from the owning struct/trait
|
|
if (receiverType && !this.isInsideClassLikeNode()) {
|
|
const ownerNode = this.nodes.find(
|
|
(n) =>
|
|
n.name === receiverType &&
|
|
n.filePath === this.filePath &&
|
|
(n.kind === 'struct' || n.kind === 'class' || n.kind === 'enum' || n.kind === 'trait')
|
|
);
|
|
if (ownerNode) {
|
|
this.edges.push({
|
|
source: ownerNode.id,
|
|
target: methodNode.id,
|
|
kind: 'contains',
|
|
});
|
|
}
|
|
}
|
|
|
|
// Extract type annotations (parameter types and return type)
|
|
this.extractTypeAnnotations(node, methodNode.id);
|
|
|
|
// Extract decorators (`@Get('/list') list() {}`).
|
|
this.extractDecoratorsFor(node, methodNode.id);
|
|
|
|
// Push to stack and visit body
|
|
this.nodeStack.push(methodNode.id);
|
|
const body = this.extractor.resolveBody?.(node, this.extractor.bodyField)
|
|
?? getChildByField(node, this.extractor.bodyField);
|
|
if (body) {
|
|
this.visitFunctionBody(body, methodNode.id);
|
|
}
|
|
this.nodeStack.pop();
|
|
}
|
|
|
|
/**
|
|
* Extract an interface/protocol/trait
|
|
*/
|
|
private extractInterface(node: SyntaxNode): void {
|
|
if (!this.extractor) return;
|
|
|
|
const name = extractName(node, this.source, this.extractor);
|
|
const docstring = getPrecedingDocstring(node, this.source);
|
|
const isExported = this.extractor.isExported?.(node, this.source);
|
|
|
|
const kind: NodeKind = this.extractor.interfaceKind ?? 'interface';
|
|
|
|
const interfaceNode = this.createNode(kind, name, node, {
|
|
docstring,
|
|
isExported,
|
|
});
|
|
if (!interfaceNode) return;
|
|
|
|
// Extract extends (interface inheritance)
|
|
this.extractInheritance(node, interfaceNode.id);
|
|
|
|
// Visit body children for interface methods and nested types
|
|
this.nodeStack.push(interfaceNode.id);
|
|
let body = this.extractor.resolveBody?.(node, this.extractor.bodyField)
|
|
?? getChildByField(node, this.extractor.bodyField);
|
|
if (!body) body = node;
|
|
for (let i = 0; i < body.namedChildCount; i++) {
|
|
const child = body.namedChild(i);
|
|
if (child) {
|
|
this.visitNode(child);
|
|
}
|
|
}
|
|
this.nodeStack.pop();
|
|
}
|
|
|
|
/**
|
|
* Extract a struct
|
|
*/
|
|
private extractStruct(node: SyntaxNode): void {
|
|
if (!this.extractor) return;
|
|
|
|
// Skip forward declarations and type references (no body = not a definition)
|
|
const body = getChildByField(node, this.extractor.bodyField);
|
|
if (!body) return;
|
|
|
|
const name = extractName(node, this.source, this.extractor);
|
|
const docstring = getPrecedingDocstring(node, this.source);
|
|
const visibility = this.extractor.getVisibility?.(node);
|
|
const isExported = this.extractor.isExported?.(node, this.source);
|
|
|
|
const structNode = this.createNode('struct', name, node, {
|
|
docstring,
|
|
visibility,
|
|
isExported,
|
|
});
|
|
if (!structNode) return;
|
|
|
|
// Extract inheritance (e.g. Swift: struct HTTPMethod: RawRepresentable)
|
|
this.extractInheritance(node, structNode.id);
|
|
|
|
// Push to stack for field extraction
|
|
this.nodeStack.push(structNode.id);
|
|
for (let i = 0; i < body.namedChildCount; i++) {
|
|
const child = body.namedChild(i);
|
|
if (child) {
|
|
this.visitNode(child);
|
|
}
|
|
}
|
|
this.nodeStack.pop();
|
|
}
|
|
|
|
/**
|
|
* Extract an enum
|
|
*/
|
|
private extractEnum(node: SyntaxNode): void {
|
|
if (!this.extractor) return;
|
|
|
|
// Skip forward declarations and type references (no body = not a definition)
|
|
const body = this.extractor.resolveBody?.(node, this.extractor.bodyField)
|
|
?? getChildByField(node, this.extractor.bodyField);
|
|
if (!body) return;
|
|
|
|
const name = extractName(node, this.source, this.extractor);
|
|
const docstring = getPrecedingDocstring(node, this.source);
|
|
const visibility = this.extractor.getVisibility?.(node);
|
|
const isExported = this.extractor.isExported?.(node, this.source);
|
|
|
|
const enumNode = this.createNode('enum', name, node, {
|
|
docstring,
|
|
visibility,
|
|
isExported,
|
|
});
|
|
if (!enumNode) return;
|
|
|
|
// Extract inheritance (e.g. Swift: enum AFError: Error)
|
|
this.extractInheritance(node, enumNode.id);
|
|
|
|
// Push to stack and visit body children (enum members, nested types, methods)
|
|
this.nodeStack.push(enumNode.id);
|
|
|
|
const memberTypes = this.extractor.enumMemberTypes;
|
|
for (let i = 0; i < body.namedChildCount; i++) {
|
|
const child = body.namedChild(i);
|
|
if (!child) continue;
|
|
|
|
if (memberTypes?.includes(child.type)) {
|
|
this.extractEnumMembers(child);
|
|
} else {
|
|
this.visitNode(child);
|
|
}
|
|
}
|
|
this.nodeStack.pop();
|
|
}
|
|
|
|
/**
|
|
* Extract enum member names from an enum member node.
|
|
* Handles multi-case declarations (Swift: `case put, delete`) and single-case patterns.
|
|
*/
|
|
private extractEnumMembers(node: SyntaxNode): void {
|
|
// Try field-based name first (e.g. Rust enum_variant has a 'name' field)
|
|
const nameNode = getChildByField(node, 'name');
|
|
if (nameNode) {
|
|
this.createNode('enum_member', getNodeText(nameNode, this.source), node);
|
|
return;
|
|
}
|
|
|
|
// Check for identifier-like children (Swift: simple_identifier, TS: property_identifier)
|
|
let found = false;
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child && (child.type === 'simple_identifier' || child.type === 'identifier' || child.type === 'property_identifier')) {
|
|
this.createNode('enum_member', getNodeText(child, this.source), child);
|
|
found = true;
|
|
}
|
|
}
|
|
|
|
// If the node itself IS the identifier (e.g. TS property_identifier directly in enum body)
|
|
if (!found && node.namedChildCount === 0) {
|
|
this.createNode('enum_member', getNodeText(node, this.source), node);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Extract a class property declaration (e.g. C# `public string Name { get; set; }`).
|
|
* Extracts as 'property' kind node inside the owning class.
|
|
*/
|
|
private extractProperty(node: SyntaxNode): void {
|
|
if (!this.extractor) return;
|
|
|
|
const docstring = getPrecedingDocstring(node, this.source);
|
|
const visibility = this.extractor.getVisibility?.(node);
|
|
const isStatic = this.extractor.isStatic?.(node) ?? false;
|
|
|
|
// Property name is a direct identifier child
|
|
const nameNode = getChildByField(node, 'name')
|
|
|| node.namedChildren.find(c => c.type === 'identifier');
|
|
if (!nameNode) return;
|
|
|
|
const name = getNodeText(nameNode, this.source);
|
|
|
|
// Get property type from the type child (first named child that isn't modifier or identifier)
|
|
const typeNode = node.namedChildren.find(
|
|
c => c.type !== 'modifier' && c.type !== 'modifiers'
|
|
&& c.type !== 'identifier' && c.type !== 'accessor_list'
|
|
&& c.type !== 'accessors' && c.type !== 'equals_value_clause'
|
|
);
|
|
const typeText = typeNode ? getNodeText(typeNode, this.source) : undefined;
|
|
const signature = typeText ? `${typeText} ${name}` : name;
|
|
|
|
const propNode = this.createNode('property', name, node, {
|
|
docstring,
|
|
signature,
|
|
visibility,
|
|
isStatic,
|
|
});
|
|
|
|
// `@Inject() private svc: Foo` and similar — capture the
|
|
// decorator->target relationship for class properties too.
|
|
if (propNode) {
|
|
this.extractDecoratorsFor(node, propNode.id);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Extract a class field declaration (e.g. Java field_declaration, C# field_declaration).
|
|
* Extracts each declarator as a 'field' kind node inside the owning class.
|
|
*/
|
|
private extractField(node: SyntaxNode): void {
|
|
if (!this.extractor) return;
|
|
|
|
const docstring = getPrecedingDocstring(node, this.source);
|
|
const visibility = this.extractor.getVisibility?.(node);
|
|
const isStatic = this.extractor.isStatic?.(node) ?? false;
|
|
|
|
// Java field_declaration: "private final String name = value;" → variable_declarator(s) are direct children
|
|
// C# field_declaration: wraps in variable_declaration → variable_declarator(s)
|
|
let declarators = node.namedChildren.filter(
|
|
c => c.type === 'variable_declarator'
|
|
);
|
|
// C#: look inside variable_declaration wrapper
|
|
if (declarators.length === 0) {
|
|
const varDecl = node.namedChildren.find(c => c.type === 'variable_declaration');
|
|
if (varDecl) {
|
|
declarators = varDecl.namedChildren.filter(c => c.type === 'variable_declarator');
|
|
}
|
|
}
|
|
|
|
// PHP property_declaration: property_element → variable_name → name
|
|
if (declarators.length === 0) {
|
|
const propElements = node.namedChildren.filter(c => c.type === 'property_element');
|
|
if (propElements.length > 0) {
|
|
// Get type annotation if present (e.g. "string", "int", "?Foo")
|
|
const typeNode = node.namedChildren.find(
|
|
c => c.type !== 'visibility_modifier' && c.type !== 'static_modifier'
|
|
&& c.type !== 'readonly_modifier' && c.type !== 'property_element'
|
|
&& c.type !== 'var_modifier'
|
|
);
|
|
const typeText = typeNode ? getNodeText(typeNode, this.source) : undefined;
|
|
|
|
for (const elem of propElements) {
|
|
const varName = elem.namedChildren.find(c => c.type === 'variable_name');
|
|
const nameNode = varName?.namedChildren.find(c => c.type === 'name');
|
|
if (!nameNode) continue;
|
|
const name = getNodeText(nameNode, this.source);
|
|
const signature = typeText ? `${typeText} $${name}` : `$${name}`;
|
|
this.createNode('field', name, elem, {
|
|
docstring,
|
|
signature,
|
|
visibility,
|
|
isStatic,
|
|
});
|
|
}
|
|
return;
|
|
}
|
|
}
|
|
|
|
if (declarators.length > 0) {
|
|
// Get field type from the type child
|
|
// Java: type is a direct child of field_declaration
|
|
// C#: type is inside variable_declaration wrapper
|
|
const varDecl = node.namedChildren.find(c => c.type === 'variable_declaration');
|
|
const typeSearchNode = varDecl ?? node;
|
|
const typeNode = typeSearchNode.namedChildren.find(
|
|
c => c.type !== 'modifiers' && c.type !== 'modifier' && c.type !== 'variable_declarator'
|
|
&& c.type !== 'variable_declaration' && c.type !== 'marker_annotation' && c.type !== 'annotation'
|
|
);
|
|
const typeText = typeNode ? getNodeText(typeNode, this.source) : undefined;
|
|
|
|
for (const decl of declarators) {
|
|
const nameNode = getChildByField(decl, 'name')
|
|
|| decl.namedChildren.find(c => c.type === 'identifier');
|
|
if (!nameNode) continue;
|
|
const name = getNodeText(nameNode, this.source);
|
|
const signature = typeText ? `${typeText} ${name}` : name;
|
|
const fieldNode = this.createNode('field', name, decl, {
|
|
docstring,
|
|
signature,
|
|
visibility,
|
|
isStatic,
|
|
});
|
|
// Java/Kotlin annotations / TS field decorators sit on the
|
|
// outer field_declaration, not on the individual declarator.
|
|
if (fieldNode) this.extractDecoratorsFor(node, fieldNode.id);
|
|
}
|
|
} else {
|
|
// Fallback: try to find an identifier child directly
|
|
const nameNode = getChildByField(node, 'name')
|
|
|| node.namedChildren.find(c => c.type === 'identifier');
|
|
if (nameNode) {
|
|
const name = getNodeText(nameNode, this.source);
|
|
this.createNode('field', name, node, {
|
|
docstring,
|
|
visibility,
|
|
isStatic,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Extract a variable declaration (const, let, var, etc.)
|
|
*
|
|
* Extracts top-level and module-level variable declarations.
|
|
* Captures the variable name and first 100 chars of initializer in signature for searchability.
|
|
*/
|
|
private extractVariable(node: SyntaxNode): void {
|
|
if (!this.extractor) return;
|
|
|
|
// Different languages have different variable declaration structures
|
|
// TypeScript/JavaScript: lexical_declaration contains variable_declarator children
|
|
// Python: assignment has left (identifier) and right (value)
|
|
// Go: var_declaration, short_var_declaration, const_declaration
|
|
|
|
const isConst = this.extractor.isConst?.(node) ?? false;
|
|
const kind: NodeKind = isConst ? 'constant' : 'variable';
|
|
const docstring = getPrecedingDocstring(node, this.source);
|
|
const isExported = this.extractor.isExported?.(node, this.source) ?? false;
|
|
|
|
// Extract variable declarators based on language
|
|
if (this.language === 'typescript' || this.language === 'javascript' ||
|
|
this.language === 'tsx' || this.language === 'jsx') {
|
|
// Handle lexical_declaration and variable_declaration
|
|
// These contain one or more variable_declarator children
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child?.type === 'variable_declarator') {
|
|
const nameNode = getChildByField(child, 'name');
|
|
const valueNode = getChildByField(child, 'value');
|
|
|
|
if (nameNode) {
|
|
// Skip destructured patterns (e.g., `let { x, y } = $props()` in Svelte)
|
|
// These produce ugly multi-line names like "{ class: className }"
|
|
if (nameNode.type === 'object_pattern' || nameNode.type === 'array_pattern') {
|
|
continue;
|
|
}
|
|
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')) {
|
|
this.extractFunction(valueNode);
|
|
continue;
|
|
}
|
|
|
|
// Capture first 100 chars of initializer for context (stored in signature for searchability)
|
|
const initValue = valueNode ? getNodeText(valueNode, this.source).slice(0, 100) : undefined;
|
|
const initSignature = initValue ? `= ${initValue}${initValue.length >= 100 ? '...' : ''}` : undefined;
|
|
|
|
const varNode = this.createNode(kind, name, child, {
|
|
docstring,
|
|
signature: initSignature,
|
|
isExported,
|
|
});
|
|
|
|
// Extract type annotation references (e.g., const x: ITextModel = ...)
|
|
if (varNode) {
|
|
this.extractVariableTypeAnnotation(child, varNode.id);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} else if (this.language === 'python' || this.language === 'ruby') {
|
|
// Python/Ruby assignment: left = right
|
|
const left = getChildByField(node, 'left') || node.namedChild(0);
|
|
const right = getChildByField(node, 'right') || node.namedChild(1);
|
|
|
|
if (left && left.type === 'identifier') {
|
|
const name = getNodeText(left, this.source);
|
|
// Skip if name starts with lowercase and looks like a function call result
|
|
// Python constants are usually UPPER_CASE
|
|
const initValue = right ? getNodeText(right, this.source).slice(0, 100) : undefined;
|
|
const initSignature = initValue ? `= ${initValue}${initValue.length >= 100 ? '...' : ''}` : undefined;
|
|
|
|
this.createNode(kind, name, node, {
|
|
docstring,
|
|
signature: initSignature,
|
|
});
|
|
}
|
|
} else if (this.language === 'go') {
|
|
// Go: var_declaration, short_var_declaration, const_declaration
|
|
// These can have multiple identifiers on the left
|
|
const specs = node.namedChildren.filter(c =>
|
|
c.type === 'var_spec' || c.type === 'const_spec'
|
|
);
|
|
|
|
for (const spec of specs) {
|
|
const nameNode = spec.namedChild(0);
|
|
if (nameNode && nameNode.type === 'identifier') {
|
|
const name = getNodeText(nameNode, this.source);
|
|
const valueNode = spec.namedChildCount > 1 ? spec.namedChild(spec.namedChildCount - 1) : null;
|
|
const initValue = valueNode ? getNodeText(valueNode, this.source).slice(0, 100) : undefined;
|
|
const initSignature = initValue ? `= ${initValue}${initValue.length >= 100 ? '...' : ''}` : undefined;
|
|
|
|
this.createNode(node.type === 'const_declaration' ? 'constant' : 'variable', name, spec, {
|
|
docstring,
|
|
signature: initSignature,
|
|
});
|
|
}
|
|
}
|
|
|
|
// Handle short_var_declaration (:=)
|
|
if (node.type === 'short_var_declaration') {
|
|
const left = getChildByField(node, 'left');
|
|
const right = getChildByField(node, 'right');
|
|
|
|
if (left) {
|
|
// Can be expression_list with multiple identifiers
|
|
const identifiers = left.type === 'expression_list'
|
|
? left.namedChildren.filter(c => c.type === 'identifier')
|
|
: [left];
|
|
|
|
for (const id of identifiers) {
|
|
const name = getNodeText(id, this.source);
|
|
const initValue = right ? getNodeText(right, this.source).slice(0, 100) : undefined;
|
|
const initSignature = initValue ? `= ${initValue}${initValue.length >= 100 ? '...' : ''}` : undefined;
|
|
|
|
this.createNode('variable', name, node, {
|
|
docstring,
|
|
signature: initSignature,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
} else if (this.language === 'lua' || this.language === 'luau') {
|
|
// Lua/Luau: variable_declaration → assignment_statement → variable_list
|
|
// (name: identifier...) = expression_list. `local x, y = 1, 2`
|
|
// declares multiple names; only plain identifiers are locals.
|
|
const assign = node.namedChildren.find((c) => c.type === 'assignment_statement') ?? node;
|
|
const varList = assign.namedChildren.find((c) => c.type === 'variable_list');
|
|
const exprList = assign.namedChildren.find((c) => c.type === 'expression_list');
|
|
const values = exprList ? exprList.namedChildren : [];
|
|
const names = varList ? varList.namedChildren.filter((c) => c.type === 'identifier') : [];
|
|
names.forEach((nameNode, i) => {
|
|
const name = getNodeText(nameNode, this.source);
|
|
if (!name) return;
|
|
const valueNode = values[i];
|
|
const initValue = valueNode ? getNodeText(valueNode, this.source).slice(0, 100) : undefined;
|
|
const initSignature = initValue ? `= ${initValue}${initValue.length >= 100 ? '...' : ''}` : undefined;
|
|
this.createNode(kind, name, nameNode, { docstring, signature: initSignature, isExported });
|
|
});
|
|
} else {
|
|
// Generic fallback for other languages
|
|
// Try to find identifier children
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child?.type === 'identifier' || child?.type === 'variable_declarator') {
|
|
const name = child.type === 'identifier'
|
|
? getNodeText(child, this.source)
|
|
: extractName(child, this.source, this.extractor);
|
|
|
|
if (name && name !== '<anonymous>') {
|
|
this.createNode(kind, name, child, {
|
|
docstring,
|
|
isExported,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Extract a type alias (e.g. `export type X = ...` in TypeScript).
|
|
* For languages like Go, resolveTypeAliasKind detects when the type_spec
|
|
* wraps a struct or interface definition and creates the correct node kind.
|
|
* Returns true if children should be skipped (struct/interface handled body visiting).
|
|
*/
|
|
private extractTypeAlias(node: SyntaxNode): boolean {
|
|
if (!this.extractor) return false;
|
|
|
|
const name = extractName(node, this.source, this.extractor);
|
|
if (name === '<anonymous>') return false;
|
|
const docstring = getPrecedingDocstring(node, this.source);
|
|
const isExported = this.extractor.isExported?.(node, this.source);
|
|
|
|
// Check if this type alias is actually a struct or interface definition
|
|
// (e.g. Go: `type Foo struct { ... }` is a type_spec wrapping struct_type)
|
|
const resolvedKind = this.extractor.resolveTypeAliasKind?.(node, this.source);
|
|
|
|
if (resolvedKind === 'struct') {
|
|
const structNode = this.createNode('struct', name, node, { docstring, isExported });
|
|
if (!structNode) return true;
|
|
// Visit body children for field extraction
|
|
this.nodeStack.push(structNode.id);
|
|
// Try Go-style 'type' field first, then find inner struct child (C typedef struct)
|
|
const typeChild = getChildByField(node, 'type')
|
|
|| this.findChildByTypes(node, this.extractor.structTypes);
|
|
if (typeChild) {
|
|
// Extract struct embedding (e.g. Go: `type DB struct { *Head; Queryable }`)
|
|
this.extractInheritance(typeChild, structNode.id);
|
|
const body = getChildByField(typeChild, this.extractor.bodyField) || typeChild;
|
|
for (let i = 0; i < body.namedChildCount; i++) {
|
|
const child = body.namedChild(i);
|
|
if (child) this.visitNode(child);
|
|
}
|
|
}
|
|
this.nodeStack.pop();
|
|
return true;
|
|
}
|
|
|
|
if (resolvedKind === 'enum') {
|
|
const enumNode = this.createNode('enum', name, node, { docstring, isExported });
|
|
if (!enumNode) return true;
|
|
this.nodeStack.push(enumNode.id);
|
|
// Find the inner enum type child (e.g. C: typedef enum { ... } name)
|
|
const innerEnum = this.findChildByTypes(node, this.extractor.enumTypes);
|
|
if (innerEnum) {
|
|
this.extractInheritance(innerEnum, enumNode.id);
|
|
const body = this.extractor.resolveBody?.(innerEnum, this.extractor.bodyField)
|
|
?? getChildByField(innerEnum, this.extractor.bodyField);
|
|
if (body) {
|
|
const memberTypes = this.extractor.enumMemberTypes;
|
|
for (let i = 0; i < body.namedChildCount; i++) {
|
|
const child = body.namedChild(i);
|
|
if (!child) continue;
|
|
if (memberTypes?.includes(child.type)) {
|
|
this.extractEnumMembers(child);
|
|
} else {
|
|
this.visitNode(child);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
this.nodeStack.pop();
|
|
return true;
|
|
}
|
|
|
|
if (resolvedKind === 'interface') {
|
|
const kind: NodeKind = this.extractor.interfaceKind ?? 'interface';
|
|
const interfaceNode = this.createNode(kind, name, node, { docstring, isExported });
|
|
if (!interfaceNode) return true;
|
|
// Extract interface inheritance from the inner type node
|
|
const typeChild = getChildByField(node, 'type');
|
|
if (typeChild) this.extractInheritance(typeChild, interfaceNode.id);
|
|
return true;
|
|
}
|
|
|
|
const typeAliasNode = this.createNode('type_alias', name, node, {
|
|
docstring,
|
|
isExported,
|
|
});
|
|
|
|
// Extract type references from the alias value (e.g., `type X = ITextModel | null`)
|
|
if (typeAliasNode && this.TYPE_ANNOTATION_LANGUAGES.has(this.language)) {
|
|
// The value is everything after the `=`, which is typically the last named child
|
|
// In tree-sitter TS: type_alias_declaration has name + value children
|
|
const value = getChildByField(node, 'value');
|
|
if (value) {
|
|
this.extractTypeRefsFromSubtree(value, typeAliasNode.id);
|
|
}
|
|
}
|
|
return false;
|
|
}
|
|
|
|
// extractExportedVariables removed — the walker now descends into
|
|
// export_statement children and the inner declaration's dedicated
|
|
// extractor (extractVariable, extractFunction, extractClass, etc.)
|
|
// handles the symbol with isExported=true via parent-walk in the
|
|
// language extractor's isExported predicate.
|
|
|
|
/**
|
|
* Extract an import
|
|
*
|
|
* Creates an import node with the full import statement stored in signature for searchability.
|
|
* Also creates unresolved references for resolution purposes.
|
|
*/
|
|
private extractImport(node: SyntaxNode): void {
|
|
if (!this.extractor) return;
|
|
|
|
const importText = getNodeText(node, this.source).trim();
|
|
|
|
// Try language-specific hook first
|
|
if (this.extractor.extractImport) {
|
|
const info = this.extractor.extractImport(node, this.source);
|
|
if (info) {
|
|
this.createNode('import', info.moduleName, node, {
|
|
signature: info.signature,
|
|
});
|
|
// Create unresolved reference unless the hook handled it
|
|
if (!info.handledRefs && info.moduleName && this.nodeStack.length > 0) {
|
|
const parentId = this.nodeStack[this.nodeStack.length - 1];
|
|
if (parentId) {
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: parentId,
|
|
referenceName: info.moduleName,
|
|
referenceKind: 'imports',
|
|
line: node.startPosition.row + 1,
|
|
column: node.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
return;
|
|
}
|
|
// Hook returned null — fall through to multi-import inline handlers only
|
|
// (hook returning null means "I didn't handle this" for multi-import cases,
|
|
// NOT "use generic fallback" — the hook already declined)
|
|
}
|
|
|
|
// Multi-import cases that create multiple nodes (can't be expressed with single-return hook)
|
|
|
|
// Python import_statement: import os, sys (creates one import per module)
|
|
if (this.language === 'python' && node.type === 'import_statement') {
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child?.type === 'dotted_name') {
|
|
this.createNode('import', getNodeText(child, this.source), node, {
|
|
signature: importText,
|
|
});
|
|
} else if (child?.type === 'aliased_import') {
|
|
const dottedName = child.namedChildren.find(c => c.type === 'dotted_name');
|
|
if (dottedName) {
|
|
this.createNode('import', getNodeText(dottedName, this.source), node, {
|
|
signature: importText,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
return;
|
|
}
|
|
|
|
// Go imports: single or grouped (creates one import per spec)
|
|
if (this.language === 'go') {
|
|
const parentId = this.nodeStack.length > 0 ? this.nodeStack[this.nodeStack.length - 1] : null;
|
|
const extractFromSpec = (spec: SyntaxNode): void => {
|
|
const stringLiteral = spec.namedChildren.find(c => c.type === 'interpreted_string_literal');
|
|
if (stringLiteral) {
|
|
const importPath = getNodeText(stringLiteral, this.source).replace(/['"]/g, '');
|
|
if (importPath) {
|
|
this.createNode('import', importPath, spec, {
|
|
signature: getNodeText(spec, this.source).trim(),
|
|
});
|
|
// Create unresolved reference so the resolver can create imports edges
|
|
if (parentId) {
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: parentId,
|
|
referenceName: importPath,
|
|
referenceKind: 'imports',
|
|
line: spec.startPosition.row + 1,
|
|
column: spec.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
};
|
|
|
|
const importSpecList = node.namedChildren.find(c => c.type === 'import_spec_list');
|
|
if (importSpecList) {
|
|
for (const spec of importSpecList.namedChildren.filter(c => c.type === 'import_spec')) {
|
|
extractFromSpec(spec);
|
|
}
|
|
} else {
|
|
const importSpec = node.namedChildren.find(c => c.type === 'import_spec');
|
|
if (importSpec) {
|
|
extractFromSpec(importSpec);
|
|
}
|
|
}
|
|
return;
|
|
}
|
|
|
|
// PHP grouped imports: use X\{A, B} (creates one import per item)
|
|
if (this.language === 'php') {
|
|
const namespacePrefix = node.namedChildren.find(c => c.type === 'namespace_name');
|
|
const useGroup = node.namedChildren.find(c => c.type === 'namespace_use_group');
|
|
if (namespacePrefix && useGroup) {
|
|
const prefix = getNodeText(namespacePrefix, this.source);
|
|
const useClauses = useGroup.namedChildren.filter((c: SyntaxNode) =>
|
|
c.type === 'namespace_use_group_clause' || c.type === 'namespace_use_clause'
|
|
);
|
|
for (const clause of useClauses) {
|
|
const nsName = clause.namedChildren.find((c: SyntaxNode) => c.type === 'namespace_name');
|
|
const name = nsName
|
|
? nsName.namedChildren.find((c: SyntaxNode) => c.type === 'name')
|
|
: clause.namedChildren.find((c: SyntaxNode) => c.type === 'name');
|
|
if (name) {
|
|
const fullPath = `${prefix}\\${getNodeText(name, this.source)}`;
|
|
this.createNode('import', fullPath, node, {
|
|
signature: importText,
|
|
});
|
|
}
|
|
}
|
|
return;
|
|
}
|
|
}
|
|
|
|
// If a hook exists but returned null, it intentionally declined this node — don't create fallback
|
|
if (this.extractor.extractImport) return;
|
|
|
|
// Generic fallback for languages without hooks
|
|
this.createNode('import', importText, node, {
|
|
signature: importText,
|
|
});
|
|
}
|
|
|
|
/**
|
|
* Extract a function call
|
|
*/
|
|
private extractCall(node: SyntaxNode): void {
|
|
if (this.nodeStack.length === 0) return;
|
|
|
|
const callerId = this.nodeStack[this.nodeStack.length - 1];
|
|
if (!callerId) return;
|
|
|
|
// Get the function/method being called
|
|
let calleeName = '';
|
|
|
|
// Java/Kotlin method_invocation has 'object' + 'name' fields instead of 'function'
|
|
// PHP member_call_expression has 'object' + 'name', scoped_call_expression has 'scope' + 'name'
|
|
const nameField = getChildByField(node, 'name');
|
|
const objectField = getChildByField(node, 'object') || getChildByField(node, 'scope');
|
|
|
|
if (nameField && objectField && (node.type === 'method_invocation' || node.type === 'member_call_expression' || node.type === 'scoped_call_expression')) {
|
|
// Method call with explicit receiver: receiver.method() / $receiver->method() / ClassName::method()
|
|
const methodName = getNodeText(nameField, this.source);
|
|
let receiverName = getNodeText(objectField, this.source);
|
|
// Strip PHP $ prefix from variable names
|
|
receiverName = receiverName.replace(/^\$/, '');
|
|
|
|
if (methodName) {
|
|
// Skip self/this/parent/static receivers — they don't aid resolution
|
|
const SKIP_RECEIVERS = new Set(['self', 'this', 'cls', 'super', 'parent', 'static']);
|
|
if (SKIP_RECEIVERS.has(receiverName)) {
|
|
calleeName = methodName;
|
|
} else {
|
|
calleeName = `${receiverName}.${methodName}`;
|
|
}
|
|
}
|
|
} else {
|
|
const func = getChildByField(node, 'function') || node.namedChild(0);
|
|
|
|
if (func) {
|
|
if (func.type === 'member_expression' || func.type === 'attribute' || func.type === 'selector_expression' || func.type === 'navigation_expression') {
|
|
// Method call: obj.method() or obj.field.method()
|
|
// Go uses selector_expression with 'field', JS/TS uses member_expression with 'property'
|
|
// Kotlin uses navigation_expression with navigation_suffix > simple_identifier
|
|
let property = getChildByField(func, 'property') || getChildByField(func, 'field');
|
|
if (!property) {
|
|
const child1 = func.namedChild(1);
|
|
// Kotlin: navigation_suffix wraps the method name — extract simple_identifier from it
|
|
if (child1?.type === 'navigation_suffix') {
|
|
property = child1.namedChildren.find((c: SyntaxNode) => c.type === 'simple_identifier') ?? child1;
|
|
} else {
|
|
property = child1;
|
|
}
|
|
}
|
|
if (property) {
|
|
const methodName = getNodeText(property, this.source);
|
|
// Include receiver name for qualified resolution (e.g., console.print → "console.print")
|
|
// This helps the resolver distinguish method calls from bare function calls
|
|
// (e.g., Python's console.print() vs builtin print())
|
|
// Skip self/this/cls as they don't aid resolution
|
|
const receiver = getChildByField(func, 'object') || getChildByField(func, 'operand') || func.namedChild(0);
|
|
const SKIP_RECEIVERS = new Set(['self', 'this', 'cls', 'super']);
|
|
if (receiver && (receiver.type === 'identifier' || receiver.type === 'simple_identifier')) {
|
|
const receiverName = getNodeText(receiver, this.source);
|
|
if (!SKIP_RECEIVERS.has(receiverName)) {
|
|
calleeName = `${receiverName}.${methodName}`;
|
|
} else {
|
|
calleeName = methodName;
|
|
}
|
|
} else {
|
|
calleeName = methodName;
|
|
}
|
|
}
|
|
} else if (func.type === 'scoped_identifier' || func.type === 'scoped_call_expression') {
|
|
// Scoped call: Module::function()
|
|
calleeName = getNodeText(func, this.source);
|
|
} else {
|
|
calleeName = getNodeText(func, this.source);
|
|
}
|
|
}
|
|
}
|
|
|
|
if (calleeName) {
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: callerId,
|
|
referenceName: calleeName,
|
|
referenceKind: 'calls',
|
|
line: node.startPosition.row + 1,
|
|
column: node.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
|
|
/**
|
|
* `new Foo(...)` / `Foo::new(...)` / object_creation_expression —
|
|
* emit an `instantiates` reference to the class name. The resolver
|
|
* then links it to the class node, producing the `instantiates`
|
|
* edge that powers "what creates instances of X" queries.
|
|
*
|
|
* Children are still walked so nested calls inside the constructor
|
|
* arguments (`new Foo(bar())`) get their own `calls` references.
|
|
*/
|
|
private extractInstantiation(node: SyntaxNode): void {
|
|
if (this.nodeStack.length === 0) return;
|
|
const fromId = this.nodeStack[this.nodeStack.length - 1];
|
|
if (!fromId) return;
|
|
|
|
// The class name is in the `constructor`/`type`/first-named-child
|
|
// depending on grammar.
|
|
const ctor =
|
|
getChildByField(node, 'constructor') ||
|
|
getChildByField(node, 'type') ||
|
|
getChildByField(node, 'name') ||
|
|
node.namedChild(0);
|
|
if (!ctor) return;
|
|
|
|
let className = getNodeText(ctor, this.source);
|
|
// Strip type-argument suffix first: `new Map<K, V>()` would
|
|
// otherwise produce className 'Map<K, V>' (the constructor
|
|
// field is a `generic_type` node) and resolution would fail
|
|
// because no class is named with the angle-bracket suffix.
|
|
const ltIdx = className.indexOf('<');
|
|
if (ltIdx > 0) className = className.slice(0, ltIdx);
|
|
// For namespaced/qualified constructors (`new ns.Foo()`,
|
|
// `new ns::Foo()`) keep the trailing identifier — that's what
|
|
// matches a class node in the index.
|
|
const lastDot = Math.max(
|
|
className.lastIndexOf('.'),
|
|
className.lastIndexOf('::')
|
|
);
|
|
if (lastDot >= 0) className = className.slice(lastDot + 1).replace(/^[:.]/, '');
|
|
className = className.trim();
|
|
|
|
if (className) {
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: fromId,
|
|
referenceName: className,
|
|
referenceKind: 'instantiates',
|
|
line: node.startPosition.row + 1,
|
|
column: node.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Scan `declNode` and its preceding siblings (within the parent's
|
|
* named children) for decorator nodes, emitting a `decorates`
|
|
* reference from `decoratedId` to each decorator's function name.
|
|
*
|
|
* Why preceding siblings: in TypeScript, `@Foo class Bar {}` parses
|
|
* as an `export_statement` (or top-level wrapper) with the
|
|
* `decorator` as a child *before* the `class_declaration` — so the
|
|
* decorator isn't a child of the class itself. For methods/
|
|
* properties, the decorator IS a direct child of the declaration,
|
|
* so we also scan declNode.namedChildren.
|
|
*
|
|
* Idempotent across grammars: if neither location yields decorators
|
|
* (most non-decorator-using languages), the function is a no-op.
|
|
*/
|
|
private extractDecoratorsFor(declNode: SyntaxNode, decoratedId: string): void {
|
|
const consider = (n: SyntaxNode | null): void => {
|
|
if (!n) return;
|
|
// `marker_annotation` is Java's grammar for arg-less annotations
|
|
// (`@Override`, `@Deprecated`); without including it, every
|
|
// such Java annotation would be silently skipped.
|
|
if (
|
|
n.type !== 'decorator' &&
|
|
n.type !== 'annotation' &&
|
|
n.type !== 'marker_annotation'
|
|
) {
|
|
return;
|
|
}
|
|
// Find the leading identifier: skip the `@` punct, unwrap
|
|
// a call_expression if the decorator is invoked with args.
|
|
let target: SyntaxNode | null = null;
|
|
for (let i = 0; i < n.namedChildCount; i++) {
|
|
const child = n.namedChild(i);
|
|
if (!child) continue;
|
|
if (child.type === 'call_expression') {
|
|
const fn = getChildByField(child, 'function') ?? child.namedChild(0);
|
|
if (fn) target = fn;
|
|
if (target) break;
|
|
}
|
|
if (
|
|
child.type === 'identifier' ||
|
|
child.type === 'member_expression' ||
|
|
child.type === 'scoped_identifier' ||
|
|
child.type === 'navigation_expression'
|
|
) {
|
|
target = child;
|
|
break;
|
|
}
|
|
}
|
|
if (!target) return;
|
|
let name = getNodeText(target, this.source);
|
|
const lastDot = Math.max(name.lastIndexOf('.'), name.lastIndexOf('::'));
|
|
if (lastDot >= 0) name = name.slice(lastDot + 1).replace(/^[:.]/, '');
|
|
if (!name) return;
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: decoratedId,
|
|
referenceName: name,
|
|
referenceKind: 'decorates',
|
|
line: n.startPosition.row + 1,
|
|
column: n.startPosition.column,
|
|
});
|
|
};
|
|
|
|
// 1. Decorators that are direct children of the declaration
|
|
// (method/property style, also some grammars for class).
|
|
for (let i = 0; i < declNode.namedChildCount; i++) {
|
|
consider(declNode.namedChild(i));
|
|
}
|
|
|
|
// 2. Decorators that are PRECEDING siblings of the declaration
|
|
// inside the parent's children (TypeScript class style).
|
|
// Walk BACKWARDS from the declaration and stop at the first
|
|
// non-decorator sibling — without that stop, decorators
|
|
// belonging to an EARLIER unrelated declaration leak in
|
|
// (e.g. `@A class Foo {} @B class Bar {}` would otherwise
|
|
// attribute @A to Bar).
|
|
//
|
|
// Note on identity: tree-sitter web bindings return fresh JS
|
|
// wrapper objects from `parent`/`namedChild` navigation, so
|
|
// `sibling === declNode` is unreliable — `startIndex` does
|
|
// the matching instead.
|
|
const parent = declNode.parent;
|
|
if (parent) {
|
|
const declStart = declNode.startIndex;
|
|
let declIdx = -1;
|
|
for (let i = 0; i < parent.namedChildCount; i++) {
|
|
const sibling = parent.namedChild(i);
|
|
if (sibling && sibling.startIndex === declStart) {
|
|
declIdx = i;
|
|
break;
|
|
}
|
|
}
|
|
if (declIdx > 0) {
|
|
for (let j = declIdx - 1; j >= 0; j--) {
|
|
const sibling = parent.namedChild(j);
|
|
if (!sibling) continue;
|
|
if (sibling.type !== 'decorator' && sibling.type !== 'annotation' && sibling.type !== 'marker_annotation') {
|
|
break; // non-decorator separator → stop consuming
|
|
}
|
|
consider(sibling);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Visit function body and extract calls (and structural nodes).
|
|
*
|
|
* In addition to call expressions, this also detects class/struct/enum
|
|
* definitions inside function bodies. This handles two cases:
|
|
* 1. Local class/struct/enum definitions (valid in C++, Java, etc.)
|
|
* 2. C++ macro misparsing — macros like NLOHMANN_JSON_NAMESPACE_BEGIN cause
|
|
* tree-sitter to interpret the namespace block as a function_definition,
|
|
* hiding real class/struct/enum nodes inside the "function body".
|
|
*/
|
|
private visitFunctionBody(body: SyntaxNode, _functionId: string): void {
|
|
if (!this.extractor) return;
|
|
|
|
const visitForCallsAndStructure = (node: SyntaxNode): void => {
|
|
const nodeType = node.type;
|
|
|
|
if (this.extractor!.callTypes.includes(nodeType)) {
|
|
this.extractCall(node);
|
|
} else if (INSTANTIATION_KINDS.has(nodeType)) {
|
|
// `new Foo()` inside a function body — emit an `instantiates`
|
|
// reference. Without this branch the body walker only knew
|
|
// about `call_expression`, so constructor invocations
|
|
// produced no graph edges at all.
|
|
this.extractInstantiation(node);
|
|
} else if (this.extractor!.extractBareCall) {
|
|
const calleeName = this.extractor!.extractBareCall(node, this.source);
|
|
if (calleeName && this.nodeStack.length > 0) {
|
|
const callerId = this.nodeStack[this.nodeStack.length - 1];
|
|
if (callerId) {
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: callerId,
|
|
referenceName: calleeName,
|
|
referenceKind: 'calls',
|
|
line: node.startPosition.row + 1,
|
|
column: node.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
|
|
// Extract structural nodes found inside function bodies.
|
|
// Each extract method visits its own children, so we return after extracting.
|
|
if (this.extractor!.classTypes.includes(nodeType)) {
|
|
const classification = this.extractor!.classifyClassNode?.(node) ?? 'class';
|
|
if (classification === 'struct') this.extractStruct(node);
|
|
else if (classification === 'enum') this.extractEnum(node);
|
|
else if (classification === 'interface') this.extractInterface(node);
|
|
else if (classification === 'trait') this.extractClass(node, 'trait');
|
|
else this.extractClass(node);
|
|
return;
|
|
}
|
|
if (this.extractor!.structTypes.includes(nodeType)) {
|
|
this.extractStruct(node);
|
|
return;
|
|
}
|
|
if (this.extractor!.enumTypes.includes(nodeType)) {
|
|
this.extractEnum(node);
|
|
return;
|
|
}
|
|
if (this.extractor!.interfaceTypes.includes(nodeType)) {
|
|
this.extractInterface(node);
|
|
return;
|
|
}
|
|
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child) {
|
|
visitForCallsAndStructure(child);
|
|
}
|
|
}
|
|
};
|
|
|
|
visitForCallsAndStructure(body);
|
|
}
|
|
|
|
/**
|
|
* Extract inheritance relationships
|
|
*/
|
|
private extractInheritance(node: SyntaxNode, classId: string): void {
|
|
// Look for extends/implements clauses
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (!child) continue;
|
|
|
|
if (
|
|
child.type === 'extends_clause' ||
|
|
child.type === 'superclass' ||
|
|
child.type === 'base_clause' || // PHP class extends
|
|
child.type === 'extends_interfaces' // Java interface extends
|
|
) {
|
|
// Extract parent class/interface names
|
|
// Java uses type_list wrapper: superclass -> type_identifier, extends_interfaces -> type_list -> type_identifier
|
|
const typeList = child.namedChildren.find((c: SyntaxNode) => c.type === 'type_list');
|
|
const targets = typeList ? typeList.namedChildren : [child.namedChild(0)];
|
|
for (const target of targets) {
|
|
if (target) {
|
|
const name = getNodeText(target, this.source);
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: classId,
|
|
referenceName: name,
|
|
referenceKind: 'extends',
|
|
line: target.startPosition.row + 1,
|
|
column: target.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
|
|
if (
|
|
child.type === 'implements_clause' ||
|
|
child.type === 'class_interface_clause' ||
|
|
child.type === 'super_interfaces' || // Java class implements
|
|
child.type === 'interfaces' // Dart
|
|
) {
|
|
// Extract implemented interfaces
|
|
// Java uses type_list wrapper: super_interfaces -> type_list -> type_identifier
|
|
const typeList = child.namedChildren.find((c: SyntaxNode) => c.type === 'type_list');
|
|
const targets = typeList ? typeList.namedChildren : child.namedChildren;
|
|
for (const iface of targets) {
|
|
if (iface) {
|
|
const name = getNodeText(iface, this.source);
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: classId,
|
|
referenceName: name,
|
|
referenceKind: 'implements',
|
|
line: iface.startPosition.row + 1,
|
|
column: iface.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
|
|
// Python superclass list: `class Flask(Scaffold, Mixin):`
|
|
// argument_list contains identifier children for each parent class
|
|
if (child.type === 'argument_list' && node.type === 'class_definition') {
|
|
for (const arg of child.namedChildren) {
|
|
if (arg.type === 'identifier' || arg.type === 'attribute') {
|
|
const name = getNodeText(arg, this.source);
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: classId,
|
|
referenceName: name,
|
|
referenceKind: 'extends',
|
|
line: arg.startPosition.row + 1,
|
|
column: arg.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
|
|
// Go interface embedding: `type Querier interface { LabelQuerier; ... }`
|
|
// constraint_elem wraps the embedded interface type identifier
|
|
if (child.type === 'constraint_elem') {
|
|
const typeId = child.namedChildren.find((c: SyntaxNode) => c.type === 'type_identifier');
|
|
if (typeId) {
|
|
const name = getNodeText(typeId, this.source);
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: classId,
|
|
referenceName: name,
|
|
referenceKind: 'extends',
|
|
line: typeId.startPosition.row + 1,
|
|
column: typeId.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
|
|
// Go struct embedding: field_declaration without field_identifier
|
|
// e.g. `type DB struct { *Head; Queryable }` — no field name means embedded type
|
|
if (child.type === 'field_declaration') {
|
|
const hasFieldIdentifier = child.namedChildren.some((c: SyntaxNode) => c.type === 'field_identifier');
|
|
if (!hasFieldIdentifier) {
|
|
const typeId = child.namedChildren.find((c: SyntaxNode) => c.type === 'type_identifier');
|
|
if (typeId) {
|
|
const name = getNodeText(typeId, this.source);
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: classId,
|
|
referenceName: name,
|
|
referenceKind: 'extends',
|
|
line: typeId.startPosition.row + 1,
|
|
column: typeId.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
|
|
// Rust trait supertraits: `trait SubTrait: SuperTrait + Display { ... }`
|
|
// trait_bounds contains type_identifier, generic_type, or higher_ranked_trait_bound children
|
|
if (child.type === 'trait_bounds') {
|
|
for (const bound of child.namedChildren) {
|
|
let typeName: string | undefined;
|
|
let posNode: SyntaxNode | undefined;
|
|
|
|
if (bound.type === 'type_identifier') {
|
|
typeName = getNodeText(bound, this.source);
|
|
posNode = bound;
|
|
} else if (bound.type === 'generic_type') {
|
|
// e.g. `Deserialize<'de>`
|
|
const inner = bound.namedChildren.find((c: SyntaxNode) => c.type === 'type_identifier');
|
|
if (inner) { typeName = getNodeText(inner, this.source); posNode = inner; }
|
|
} else if (bound.type === 'higher_ranked_trait_bound') {
|
|
// e.g. `for<'de> Deserialize<'de>`
|
|
const generic = bound.namedChildren.find((c: SyntaxNode) => c.type === 'generic_type');
|
|
const typeId = generic?.namedChildren.find((c: SyntaxNode) => c.type === 'type_identifier')
|
|
?? bound.namedChildren.find((c: SyntaxNode) => c.type === 'type_identifier');
|
|
if (typeId) { typeName = getNodeText(typeId, this.source); posNode = typeId; }
|
|
}
|
|
|
|
if (typeName && posNode) {
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: classId,
|
|
referenceName: typeName,
|
|
referenceKind: 'extends',
|
|
line: posNode.startPosition.row + 1,
|
|
column: posNode.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
|
|
// C#: `class Movie : BaseItem, IPlugin` → base_list with identifier children
|
|
// base_list combines both base class and interfaces in a single colon-separated list.
|
|
// We emit all as 'extends' since the syntax doesn't distinguish them.
|
|
if (child.type === 'base_list') {
|
|
for (const baseType of child.namedChildren) {
|
|
if (baseType) {
|
|
// For generic base types like `ClientBase<T>`, extract just the type name
|
|
const name = baseType.type === 'generic_name'
|
|
? getNodeText(baseType.namedChildren.find((c: SyntaxNode) => c.type === 'identifier') ?? baseType, this.source)
|
|
: getNodeText(baseType, this.source);
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: classId,
|
|
referenceName: name,
|
|
referenceKind: 'extends',
|
|
line: baseType.startPosition.row + 1,
|
|
column: baseType.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
|
|
// Kotlin: `class Foo : Bar, Baz` → delegation_specifier > user_type > type_identifier
|
|
// Also handles `class Foo : Bar()` → delegation_specifier > constructor_invocation > user_type
|
|
if (child.type === 'delegation_specifier') {
|
|
const userType = child.namedChildren.find((c: SyntaxNode) => c.type === 'user_type');
|
|
const constructorInvocation = child.namedChildren.find((c: SyntaxNode) => c.type === 'constructor_invocation');
|
|
const target = userType ?? constructorInvocation;
|
|
if (target) {
|
|
const typeId = target.type === 'user_type'
|
|
? target.namedChildren.find((c: SyntaxNode) => c.type === 'type_identifier') ?? target
|
|
: target.namedChildren.find((c: SyntaxNode) => c.type === 'user_type')?.namedChildren.find((c: SyntaxNode) => c.type === 'type_identifier')
|
|
?? target.namedChildren.find((c: SyntaxNode) => c.type === 'user_type') ?? target;
|
|
const name = getNodeText(typeId, this.source);
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: classId,
|
|
referenceName: name,
|
|
referenceKind: 'extends',
|
|
line: typeId.startPosition.row + 1,
|
|
column: typeId.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
|
|
// Swift: inheritance_specifier > user_type > type_identifier
|
|
// Used for class inheritance, protocol conformance, and protocol inheritance
|
|
if (child.type === 'inheritance_specifier') {
|
|
const userType = child.namedChildren.find((c: SyntaxNode) => c.type === 'user_type');
|
|
const typeId = userType?.namedChildren.find((c: SyntaxNode) => c.type === 'type_identifier');
|
|
if (typeId) {
|
|
const name = getNodeText(typeId, this.source);
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: classId,
|
|
referenceName: name,
|
|
referenceKind: 'extends',
|
|
line: typeId.startPosition.row + 1,
|
|
column: typeId.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
|
|
// JavaScript class_heritage has bare identifier without extends_clause wrapper
|
|
// e.g. `class Foo extends Bar {}` → class_heritage → identifier("Bar")
|
|
if (
|
|
(child.type === 'identifier' || child.type === 'type_identifier') &&
|
|
node.type === 'class_heritage'
|
|
) {
|
|
const name = getNodeText(child, this.source);
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: classId,
|
|
referenceName: name,
|
|
referenceKind: 'extends',
|
|
line: child.startPosition.row + 1,
|
|
column: child.startPosition.column,
|
|
});
|
|
}
|
|
|
|
// Recurse into container nodes (e.g. field_declaration_list in Go structs,
|
|
// class_heritage in TypeScript which wraps extends_clause/implements_clause)
|
|
if (child.type === 'field_declaration_list' || child.type === 'class_heritage') {
|
|
this.extractInheritance(child, classId);
|
|
}
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Rust `impl Trait for Type` — creates an implements edge from Type to Trait.
|
|
* For plain `impl Type { ... }` (no trait), no inheritance edge is needed.
|
|
*/
|
|
private extractRustImplItem(node: SyntaxNode): void {
|
|
// Check if this is `impl Trait for Type` by looking for a `for` keyword
|
|
const hasFor = node.children.some(
|
|
(c: SyntaxNode) => c.type === 'for' && !c.isNamed
|
|
);
|
|
if (!hasFor) return;
|
|
|
|
// In `impl Trait for Type`, the type_identifiers are:
|
|
// first = Trait name, last = implementing Type name
|
|
// Also handle generic types like `impl<T> Trait for MyStruct<T>`
|
|
const typeIdents = node.namedChildren.filter(
|
|
(c: SyntaxNode) => c.type === 'type_identifier' || c.type === 'generic_type' || c.type === 'scoped_type_identifier'
|
|
);
|
|
if (typeIdents.length < 2) return;
|
|
|
|
const traitNode = typeIdents[0]!;
|
|
const typeNode = typeIdents[typeIdents.length - 1]!;
|
|
|
|
// Get the trait name (handle scoped paths like std::fmt::Display)
|
|
const traitName = traitNode.type === 'scoped_type_identifier'
|
|
? this.source.substring(traitNode.startIndex, traitNode.endIndex)
|
|
: getNodeText(traitNode, this.source);
|
|
|
|
// Get the implementing type name (extract inner type_identifier for generics)
|
|
let typeName: string;
|
|
if (typeNode.type === 'generic_type') {
|
|
const inner = typeNode.namedChildren.find(
|
|
(c: SyntaxNode) => c.type === 'type_identifier'
|
|
);
|
|
typeName = inner ? getNodeText(inner, this.source) : getNodeText(typeNode, this.source);
|
|
} else {
|
|
typeName = getNodeText(typeNode, this.source);
|
|
}
|
|
|
|
// Find the struct/type node for the implementing type
|
|
const typeNodeId = this.findNodeByName(typeName);
|
|
if (typeNodeId) {
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: typeNodeId,
|
|
referenceName: traitName,
|
|
referenceKind: 'implements',
|
|
line: traitNode.startPosition.row + 1,
|
|
column: traitNode.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Find a previously-extracted node by name (used for back-references like impl blocks)
|
|
*/
|
|
private findNodeByName(name: string): string | undefined {
|
|
for (const node of this.nodes) {
|
|
if (node.name === name && (node.kind === 'struct' || node.kind === 'enum' || node.kind === 'class')) {
|
|
return node.id;
|
|
}
|
|
}
|
|
return undefined;
|
|
}
|
|
|
|
/**
|
|
* Languages that support type annotations (TypeScript, etc.)
|
|
*/
|
|
private readonly TYPE_ANNOTATION_LANGUAGES = new Set([
|
|
'typescript', 'tsx', 'dart', 'kotlin', 'swift', 'rust', 'go', 'java', 'csharp',
|
|
]);
|
|
|
|
/**
|
|
* Built-in/primitive type names that shouldn't create references
|
|
*/
|
|
private readonly BUILTIN_TYPES = new Set([
|
|
'string', 'number', 'boolean', 'void', 'null', 'undefined', 'never', 'any', 'unknown',
|
|
'object', 'symbol', 'bigint', 'true', 'false',
|
|
// Rust
|
|
'str', 'bool', 'i8', 'i16', 'i32', 'i64', 'i128', 'isize',
|
|
'u8', 'u16', 'u32', 'u64', 'u128', 'usize', 'f32', 'f64', 'char',
|
|
// Java/C#
|
|
'int', 'long', 'short', 'byte', 'float', 'double', 'char',
|
|
// Go
|
|
'int8', 'int16', 'int32', 'int64', 'uint8', 'uint16', 'uint32', 'uint64',
|
|
'float32', 'float64', 'complex64', 'complex128', 'rune', 'error',
|
|
]);
|
|
|
|
/**
|
|
* Extract type references from type annotations on a function/method/field node.
|
|
* Creates 'references' edges for parameter types, return types, and field types.
|
|
*/
|
|
private extractTypeAnnotations(node: SyntaxNode, nodeId: string): void {
|
|
if (!this.extractor) return;
|
|
if (!this.TYPE_ANNOTATION_LANGUAGES.has(this.language)) return;
|
|
|
|
// Extract parameter type annotations
|
|
const params = getChildByField(node, this.extractor.paramsField || 'parameters');
|
|
if (params) {
|
|
this.extractTypeRefsFromSubtree(params, nodeId);
|
|
}
|
|
|
|
// Extract return type annotation
|
|
const returnType = getChildByField(node, this.extractor.returnField || 'return_type');
|
|
if (returnType) {
|
|
this.extractTypeRefsFromSubtree(returnType, nodeId);
|
|
}
|
|
|
|
// Extract direct type annotation (for class fields like `model: ITextModel`)
|
|
const typeAnnotation = node.namedChildren.find(
|
|
(c: SyntaxNode) => c.type === 'type_annotation'
|
|
);
|
|
if (typeAnnotation) {
|
|
this.extractTypeRefsFromSubtree(typeAnnotation, nodeId);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Extract type references from a variable's type annotation.
|
|
*/
|
|
private extractVariableTypeAnnotation(node: SyntaxNode, nodeId: string): void {
|
|
if (!this.TYPE_ANNOTATION_LANGUAGES.has(this.language)) return;
|
|
|
|
// Find type_annotation child (covers TS `: Type`, Rust `: Type`, etc.)
|
|
const typeAnnotation = node.namedChildren.find(
|
|
(c: SyntaxNode) => c.type === 'type_annotation'
|
|
);
|
|
if (typeAnnotation) {
|
|
this.extractTypeRefsFromSubtree(typeAnnotation, nodeId);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Recursively walk a subtree and extract all type_identifier references.
|
|
* Handles unions, intersections, generics, arrays, etc.
|
|
*/
|
|
private extractTypeRefsFromSubtree(node: SyntaxNode, fromNodeId: string): void {
|
|
if (node.type === 'type_identifier') {
|
|
const typeName = getNodeText(node, this.source);
|
|
if (typeName && !this.BUILTIN_TYPES.has(typeName)) {
|
|
this.unresolvedReferences.push({
|
|
fromNodeId,
|
|
referenceName: typeName,
|
|
referenceKind: 'references',
|
|
line: node.startPosition.row + 1,
|
|
column: node.startPosition.column,
|
|
});
|
|
}
|
|
return; // type_identifier is a leaf
|
|
}
|
|
|
|
// Recurse into children (handles union_type, intersection_type, generic_type, etc.)
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child) {
|
|
this.extractTypeRefsFromSubtree(child, fromNodeId);
|
|
}
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Handle Pascal-specific AST structures.
|
|
* Returns true if the node was fully handled and children should be skipped.
|
|
*/
|
|
private visitPascalNode(node: SyntaxNode): boolean {
|
|
const nodeType = node.type;
|
|
|
|
// Unit/Program/Library → module node
|
|
if (nodeType === 'unit' || nodeType === 'program' || nodeType === 'library') {
|
|
const moduleNameNode = node.namedChildren.find(
|
|
(c: SyntaxNode) => c.type === 'moduleName'
|
|
);
|
|
const name = moduleNameNode ? getNodeText(moduleNameNode, this.source) : '';
|
|
// Fallback to filename without extension if module name is empty
|
|
const moduleName = name || path.basename(this.filePath).replace(/\.[^.]+$/, '');
|
|
this.createNode('module', moduleName, node);
|
|
// Continue visiting children (interface/implementation sections)
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child) this.visitNode(child);
|
|
}
|
|
return true;
|
|
}
|
|
|
|
// declType wraps declClass/declIntf/declEnum/type-alias
|
|
// The name lives on declType, the inner node determines the kind
|
|
if (nodeType === 'declType') {
|
|
this.extractPascalDeclType(node);
|
|
return true;
|
|
}
|
|
|
|
// declUses → import nodes for each unit name
|
|
if (nodeType === 'declUses') {
|
|
this.extractPascalUses(node);
|
|
return true;
|
|
}
|
|
|
|
// declConsts → container; visit children for individual declConst
|
|
if (nodeType === 'declConsts') {
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child?.type === 'declConst') {
|
|
this.extractPascalConst(child);
|
|
}
|
|
}
|
|
return true;
|
|
}
|
|
|
|
// declConst at top level (outside declConsts)
|
|
if (nodeType === 'declConst') {
|
|
this.extractPascalConst(node);
|
|
return true;
|
|
}
|
|
|
|
// declTypes → container for type declarations
|
|
if (nodeType === 'declTypes') {
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child) this.visitNode(child);
|
|
}
|
|
return true;
|
|
}
|
|
|
|
// declVars → container for variable declarations
|
|
if (nodeType === 'declVars') {
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child?.type === 'declVar') {
|
|
const nameNode = getChildByField(child, 'name');
|
|
if (nameNode) {
|
|
const name = getNodeText(nameNode, this.source);
|
|
this.createNode('variable', name, child);
|
|
}
|
|
}
|
|
}
|
|
return true;
|
|
}
|
|
|
|
// defProc in implementation section → extract calls but don't create duplicate nodes
|
|
if (nodeType === 'defProc') {
|
|
this.extractPascalDefProc(node);
|
|
return true;
|
|
}
|
|
|
|
// declProp → property node
|
|
if (nodeType === 'declProp') {
|
|
const nameNode = getChildByField(node, 'name');
|
|
if (nameNode) {
|
|
const name = getNodeText(nameNode, this.source);
|
|
const visibility = this.extractor!.getVisibility?.(node);
|
|
this.createNode('property', name, node, { visibility });
|
|
}
|
|
return true;
|
|
}
|
|
|
|
// declField → field node
|
|
if (nodeType === 'declField') {
|
|
const nameNode = getChildByField(node, 'name');
|
|
if (nameNode) {
|
|
const name = getNodeText(nameNode, this.source);
|
|
const visibility = this.extractor!.getVisibility?.(node);
|
|
this.createNode('field', name, node, { visibility });
|
|
}
|
|
return true;
|
|
}
|
|
|
|
// declSection → visit children (propagates visibility via getVisibility)
|
|
if (nodeType === 'declSection') {
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child) this.visitNode(child);
|
|
}
|
|
return true;
|
|
}
|
|
|
|
// exprCall → extract function call reference
|
|
if (nodeType === 'exprCall') {
|
|
this.extractPascalCall(node);
|
|
return true;
|
|
}
|
|
|
|
// interface/implementation sections → visit children
|
|
if (nodeType === 'interface' || nodeType === 'implementation') {
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child) this.visitNode(child);
|
|
}
|
|
return true;
|
|
}
|
|
|
|
// block (begin..end) → visit for calls
|
|
if (nodeType === 'block') {
|
|
this.visitPascalBlock(node);
|
|
return true;
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
/**
|
|
* Extract a Pascal declType node (class, interface, enum, or type alias)
|
|
*/
|
|
private extractPascalDeclType(node: SyntaxNode): void {
|
|
const nameNode = getChildByField(node, 'name');
|
|
if (!nameNode) return;
|
|
const name = getNodeText(nameNode, this.source);
|
|
|
|
// Find the inner type declaration
|
|
const declClass = node.namedChildren.find(
|
|
(c: SyntaxNode) => c.type === 'declClass'
|
|
);
|
|
const declIntf = node.namedChildren.find(
|
|
(c: SyntaxNode) => c.type === 'declIntf'
|
|
);
|
|
const typeChild = node.namedChildren.find(
|
|
(c: SyntaxNode) => c.type === 'type'
|
|
);
|
|
|
|
if (declClass) {
|
|
const classNode = this.createNode('class', name, node);
|
|
if (classNode) {
|
|
// Extract inheritance from typeref children of declClass
|
|
this.extractPascalInheritance(declClass, classNode.id);
|
|
// Visit class body
|
|
this.nodeStack.push(classNode.id);
|
|
for (let i = 0; i < declClass.namedChildCount; i++) {
|
|
const child = declClass.namedChild(i);
|
|
if (child) this.visitNode(child);
|
|
}
|
|
this.nodeStack.pop();
|
|
}
|
|
} else if (declIntf) {
|
|
const ifaceNode = this.createNode('interface', name, node);
|
|
if (ifaceNode) {
|
|
// Visit interface members
|
|
this.nodeStack.push(ifaceNode.id);
|
|
for (let i = 0; i < declIntf.namedChildCount; i++) {
|
|
const child = declIntf.namedChild(i);
|
|
if (child) this.visitNode(child);
|
|
}
|
|
this.nodeStack.pop();
|
|
}
|
|
} else if (typeChild) {
|
|
// Check if it contains a declEnum
|
|
const declEnum = typeChild.namedChildren.find(
|
|
(c: SyntaxNode) => c.type === 'declEnum'
|
|
);
|
|
if (declEnum) {
|
|
const enumNode = this.createNode('enum', name, node);
|
|
if (enumNode) {
|
|
// Extract enum members
|
|
this.nodeStack.push(enumNode.id);
|
|
for (let i = 0; i < declEnum.namedChildCount; i++) {
|
|
const child = declEnum.namedChild(i);
|
|
if (child?.type === 'declEnumValue') {
|
|
const memberName = getChildByField(child, 'name');
|
|
if (memberName) {
|
|
this.createNode('enum_member', getNodeText(memberName, this.source), child);
|
|
}
|
|
}
|
|
}
|
|
this.nodeStack.pop();
|
|
}
|
|
} else {
|
|
// Simple type alias: type TFoo = string / type TFoo = Integer
|
|
this.createNode('type_alias', name, node);
|
|
}
|
|
} else {
|
|
// Fallback: could be a forward declaration or simple alias
|
|
this.createNode('type_alias', name, node);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Extract Pascal uses clause into individual import nodes
|
|
*/
|
|
private extractPascalUses(node: SyntaxNode): void {
|
|
const importText = getNodeText(node, this.source).trim();
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (child?.type === 'moduleName') {
|
|
const unitName = getNodeText(child, this.source);
|
|
this.createNode('import', unitName, child, {
|
|
signature: importText,
|
|
});
|
|
// Create unresolved reference for resolution
|
|
if (this.nodeStack.length > 0) {
|
|
const parentId = this.nodeStack[this.nodeStack.length - 1];
|
|
if (parentId) {
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: parentId,
|
|
referenceName: unitName,
|
|
referenceKind: 'imports',
|
|
line: child.startPosition.row + 1,
|
|
column: child.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Extract a Pascal constant declaration
|
|
*/
|
|
private extractPascalConst(node: SyntaxNode): void {
|
|
const nameNode = getChildByField(node, 'name');
|
|
if (!nameNode) return;
|
|
const name = getNodeText(nameNode, this.source);
|
|
const defaultValue = node.namedChildren.find(
|
|
(c: SyntaxNode) => c.type === 'defaultValue'
|
|
);
|
|
const sig = defaultValue ? getNodeText(defaultValue, this.source) : undefined;
|
|
this.createNode('constant', name, node, { signature: sig });
|
|
}
|
|
|
|
/**
|
|
* Extract Pascal inheritance (extends/implements) from declClass typeref children
|
|
*/
|
|
private extractPascalInheritance(declClass: SyntaxNode, classId: string): void {
|
|
const typerefs = declClass.namedChildren.filter(
|
|
(c: SyntaxNode) => c.type === 'typeref'
|
|
);
|
|
for (let i = 0; i < typerefs.length; i++) {
|
|
const ref = typerefs[i]!;
|
|
const name = getNodeText(ref, this.source);
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: classId,
|
|
referenceName: name,
|
|
referenceKind: i === 0 ? 'extends' : 'implements',
|
|
line: ref.startPosition.row + 1,
|
|
column: ref.startPosition.column,
|
|
});
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Extract calls and resolve method context from a Pascal defProc (implementation body).
|
|
* Does not create a new node — the declaration was already captured from the interface section.
|
|
*/
|
|
private extractPascalDefProc(node: SyntaxNode): void {
|
|
// Find the matching declaration node by name to use as call parent
|
|
const declProc = node.namedChildren.find(
|
|
(c: SyntaxNode) => c.type === 'declProc'
|
|
);
|
|
if (!declProc) return;
|
|
|
|
const nameNode = getChildByField(declProc, 'name');
|
|
if (!nameNode) return;
|
|
const fullName = getNodeText(nameNode, this.source).trim();
|
|
// fullName is like "TAuthService.Create"
|
|
const shortName = fullName.includes('.') ? fullName.split('.').pop()! : fullName;
|
|
const fullNameKey = fullName.toLowerCase();
|
|
const shortNameKey = shortName.toLowerCase();
|
|
|
|
// Build method index on first use (O(n) once, then O(1) per lookup)
|
|
if (!this.methodIndex) {
|
|
this.methodIndex = new Map();
|
|
for (const n of this.nodes) {
|
|
if (n.kind === 'method' || n.kind === 'function') {
|
|
const nameKey = n.name.toLowerCase();
|
|
// Keep first seen short-name mapping to avoid silently overwriting earlier entries.
|
|
if (!this.methodIndex.has(nameKey)) {
|
|
this.methodIndex.set(nameKey, n.id);
|
|
}
|
|
|
|
// For Pascal methods, also index qualified forms (e.g. TAuthService.Create).
|
|
if (n.kind === 'method') {
|
|
const qualifiedParts = n.qualifiedName.split('::');
|
|
if (qualifiedParts.length >= 2) {
|
|
// Create suffix keys so both "Module.Class.Method" and "Class.Method" can resolve.
|
|
for (let i = 0; i < qualifiedParts.length - 1; i++) {
|
|
const scopedName = qualifiedParts.slice(i).join('.').toLowerCase();
|
|
this.methodIndex.set(scopedName, n.id);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
const parentId =
|
|
this.methodIndex.get(fullNameKey) ||
|
|
this.methodIndex.get(shortNameKey) ||
|
|
this.nodeStack[this.nodeStack.length - 1];
|
|
if (!parentId) return;
|
|
|
|
// Visit the block for calls
|
|
const block = node.namedChildren.find(
|
|
(c: SyntaxNode) => c.type === 'block'
|
|
);
|
|
if (block) {
|
|
this.nodeStack.push(parentId);
|
|
this.visitPascalBlock(block);
|
|
this.nodeStack.pop();
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Extract function calls from a Pascal expression
|
|
*/
|
|
private extractPascalCall(node: SyntaxNode): void {
|
|
if (this.nodeStack.length === 0) return;
|
|
const callerId = this.nodeStack[this.nodeStack.length - 1];
|
|
if (!callerId) return;
|
|
|
|
// Get the callee name — first child is typically the identifier or exprDot
|
|
const firstChild = node.namedChild(0);
|
|
if (!firstChild) return;
|
|
|
|
let calleeName = '';
|
|
if (firstChild.type === 'exprDot') {
|
|
// Qualified call: Obj.Method(...)
|
|
const identifiers = firstChild.namedChildren.filter(
|
|
(c: SyntaxNode) => c.type === 'identifier'
|
|
);
|
|
if (identifiers.length > 0) {
|
|
calleeName = identifiers.map((id: SyntaxNode) => getNodeText(id, this.source)).join('.');
|
|
}
|
|
} else if (firstChild.type === 'identifier') {
|
|
calleeName = getNodeText(firstChild, this.source);
|
|
}
|
|
|
|
if (calleeName) {
|
|
this.unresolvedReferences.push({
|
|
fromNodeId: callerId,
|
|
referenceName: calleeName,
|
|
referenceKind: 'calls',
|
|
line: node.startPosition.row + 1,
|
|
column: node.startPosition.column,
|
|
});
|
|
}
|
|
|
|
// Also visit arguments for nested calls
|
|
const args = node.namedChildren.find(
|
|
(c: SyntaxNode) => c.type === 'exprArgs'
|
|
);
|
|
if (args) {
|
|
this.visitPascalBlock(args);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Recursively visit a Pascal block/statement tree for call expressions
|
|
*/
|
|
private visitPascalBlock(node: SyntaxNode): void {
|
|
for (let i = 0; i < node.namedChildCount; i++) {
|
|
const child = node.namedChild(i);
|
|
if (!child) continue;
|
|
if (child.type === 'exprCall') {
|
|
this.extractPascalCall(child);
|
|
} else if (child.type === 'exprDot') {
|
|
// Check if exprDot contains an exprCall
|
|
for (let j = 0; j < child.namedChildCount; j++) {
|
|
const grandchild = child.namedChild(j);
|
|
if (grandchild?.type === 'exprCall') {
|
|
this.extractPascalCall(grandchild);
|
|
}
|
|
}
|
|
} else {
|
|
this.visitPascalBlock(child);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
|
|
/**
|
|
* Extract nodes and edges from source code.
|
|
*
|
|
* If `frameworkNames` is provided, framework-specific extractors matching
|
|
* those names and the file's language are run after the tree-sitter pass.
|
|
* Their nodes/references/errors are merged into the returned result.
|
|
*/
|
|
export function extractFromSource(
|
|
filePath: string,
|
|
source: string,
|
|
language?: Language,
|
|
frameworkNames?: string[]
|
|
): ExtractionResult {
|
|
const detectedLanguage = language || detectLanguage(filePath, source);
|
|
const fileExtension = path.extname(filePath).toLowerCase();
|
|
|
|
let result: ExtractionResult;
|
|
|
|
// Use custom extractor for Svelte
|
|
if (detectedLanguage === 'svelte') {
|
|
const extractor = new SvelteExtractor(filePath, source);
|
|
result = extractor.extract();
|
|
} else if (detectedLanguage === 'vue') {
|
|
// Use custom extractor for Vue
|
|
const extractor = new VueExtractor(filePath, source);
|
|
result = extractor.extract();
|
|
} else if (detectedLanguage === 'liquid') {
|
|
// Use custom extractor for Liquid
|
|
const extractor = new LiquidExtractor(filePath, source);
|
|
result = extractor.extract();
|
|
} else if (
|
|
detectedLanguage === 'pascal' &&
|
|
(fileExtension === '.dfm' || fileExtension === '.fmx')
|
|
) {
|
|
// Use custom extractor for DFM/FMX form files
|
|
const extractor = new DfmExtractor(filePath, source);
|
|
result = extractor.extract();
|
|
} else {
|
|
const extractor = new TreeSitterExtractor(filePath, source, detectedLanguage);
|
|
result = extractor.extract();
|
|
}
|
|
|
|
// Framework-specific extraction (routes, middleware, etc.)
|
|
if (frameworkNames && frameworkNames.length > 0) {
|
|
const allResolvers = getAllFrameworkResolvers();
|
|
const applicable = getApplicableFrameworks(
|
|
allResolvers.filter((r) => frameworkNames.includes(r.name)),
|
|
detectedLanguage
|
|
);
|
|
for (const fw of applicable) {
|
|
if (!fw.extract) continue;
|
|
try {
|
|
const fwResult = fw.extract(filePath, source);
|
|
result.nodes.push(...fwResult.nodes);
|
|
result.unresolvedReferences.push(...fwResult.references);
|
|
} catch (err) {
|
|
result.errors.push({
|
|
message: `Framework extractor '${fw.name}' failed: ${
|
|
err instanceof Error ? err.message : String(err)
|
|
}`,
|
|
filePath,
|
|
severity: 'warning',
|
|
});
|
|
}
|
|
}
|
|
}
|
|
|
|
return result;
|
|
}
|