| 1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855 |
- /**
- * 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 } from './tree-sitter-types';
- import { EXTRACTORS } from './languages';
- import { LiquidExtractor } from './liquid-extractor';
- import { SvelteExtractor } from './svelte-extractor';
- import { DfmExtractor } from './dfm-extractor';
- // 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) {
- // Handle complex declarators (C/C++)
- if (nameNode.type === 'function_declarator' || nameNode.type === 'declarator') {
- const innerName = getChildByField(nameNode, 'declarator') || nameNode.namedChild(0);
- return innerName ? getNodeText(innerName, source) : getNodeText(nameNode, source);
- }
- return getNodeText(nameNode, 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);
- }
- }
- }
- }
- }
- // 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>';
- }
- /**
- * 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);
- 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;
- // 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 {
- 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 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
- }
- // Check for export statements containing non-function variable declarations
- // e.g. `export const X = create(...)`, `export const X = { ... }`
- else if (nodeType === 'export_statement') {
- this.extractExportedVariables(node);
- // Don't skip children — still need to visit inner nodes (functions, calls, etc.)
- }
- // 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);
- }
- // 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;
- }
- /**
- * 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('::');
- }
- /**
- * 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'
- );
- }
- /**
- * Extract a function
- */
- private extractFunction(node: SyntaxNode): void {
- if (!this.extractor) 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
- 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);
- // 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): 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('class', name, node, {
- docstring,
- visibility,
- isExported,
- });
- if (!classNode) return;
- // Extract extends/implements
- this.extractInheritance(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 most languages, only extract as method if inside a class-like node
- // Languages with methodsAreTopLevel (e.g. Go) always treat them as methods
- if (!this.isInsideClassLikeNode() && !this.extractor.methodsAreTopLevel) {
- // Not inside a class-like node and not Go, treat as function
- this.extractFunction(node);
- return;
- }
- const name = extractName(node, this.source, this.extractor);
- 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);
- // For languages with receiver types (Go), include receiver in qualified name
- // so FTS can match "scrapeLoop.run" → qualified_name "...::scrapeLoop::run"
- const receiverType = this.extractor.getReceiverType?.(node, this.source);
- 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;
- // Extract type annotations (parameter types and return type)
- this.extractTypeAnnotations(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);
- }
- /**
- * Extract a struct
- */
- private extractStruct(node: SyntaxNode): 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 structNode = this.createNode('struct', name, node, {
- docstring,
- visibility,
- isExported,
- });
- if (!structNode) return;
- // Push to stack for field extraction
- this.nodeStack.push(structNode.id);
- const body = getChildByField(node, this.extractor.bodyField) || node;
- 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;
- 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 body = this.extractor.resolveBody?.(node, this.extractor.bodyField)
- ?? getChildByField(node, this.extractor.bodyField)
- ?? node;
- 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 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;"
- // Children include modifiers, type, variable_declarator(s)
- const declarators = node.namedChildren.filter(
- c => c.type === 'variable_declarator'
- );
- if (declarators.length > 0) {
- // Get field type from the type child
- const typeNode = node.namedChildren.find(
- c => c.type !== 'modifiers' && c.type !== 'variable_declarator'
- && 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');
- if (!nameNode) continue;
- const name = getNodeText(nameNode, this.source);
- const signature = typeText ? `${typeText} ${name}` : name;
- this.createNode('field', name, decl, {
- docstring,
- signature,
- visibility,
- isStatic,
- });
- }
- } 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) {
- 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 {
- // 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);
- const typeChild = getChildByField(node, 'type');
- 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 === '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;
- }
- /**
- * Extract an exported variable declaration that isn't a function.
- * Handles patterns like:
- * export const X = create(...)
- * export const X = { ... }
- * export const X = [...]
- * export const X = "value"
- *
- * This is called for `export_statement` nodes that contain a
- * `lexical_declaration` with `variable_declarator` children whose
- * values are NOT already handled by functionTypes (arrow_function,
- * function_expression).
- */
- private extractExportedVariables(exportNode: SyntaxNode): void {
- if (!this.extractor) return;
- // Find the lexical_declaration or variable_declaration child
- for (let i = 0; i < exportNode.namedChildCount; i++) {
- const decl = exportNode.namedChild(i);
- if (!decl || (decl.type !== 'lexical_declaration' && decl.type !== 'variable_declaration')) {
- continue;
- }
- // Iterate over each variable_declarator in the declaration
- for (let j = 0; j < decl.namedChildCount; j++) {
- const declarator = decl.namedChild(j);
- if (!declarator || declarator.type !== 'variable_declarator') continue;
- const nameNode = getChildByField(declarator, 'name');
- if (!nameNode) continue;
- const name = getNodeText(nameNode, this.source);
- // Skip if the value is a function type — those are already handled
- // by extractFunction via the functionTypes dispatch
- const value = getChildByField(declarator, 'value');
- if (value) {
- const valueType = value.type;
- if (
- this.extractor.functionTypes.includes(valueType)
- ) {
- continue; // Already handled by extractFunction
- }
- }
- const docstring = getPrecedingDocstring(exportNode, this.source);
- this.createNode('variable', name, declarator, {
- docstring,
- isExported: true,
- });
- }
- }
- }
- /**
- * 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'
- const nameField = getChildByField(node, 'name');
- const objectField = getChildByField(node, 'object');
- if (nameField && objectField && node.type === 'method_invocation') {
- // Java-style method call: receiver.method()
- const methodName = getNodeText(nameField, this.source);
- const receiverName = getNodeText(objectField, this.source);
- if (methodName) {
- // Emit receiver.method form for qualified resolution
- 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') {
- // Method call: obj.method() or obj.field.method()
- // Go uses selector_expression with 'field', JS/TS uses member_expression with 'property'
- const property = getChildByField(func, 'property') || getChildByField(func, 'field') || func.namedChild(1);
- 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') {
- 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,
- });
- }
- }
- /**
- * Visit function body and extract calls
- */
- private visitFunctionBody(body: SyntaxNode, _functionId: string): void {
- if (!this.extractor) return;
- // Recursively find all call expressions
- const visitForCalls = (node: SyntaxNode): void => {
- if (this.extractor!.callTypes.includes(node.type)) {
- this.extractCall(node);
- }
- for (let i = 0; i < node.namedChildCount; i++) {
- const child = node.namedChild(i);
- if (child) {
- visitForCalls(child);
- }
- }
- };
- visitForCalls(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 === 'class_heritage' ||
- child.type === 'superclass' ||
- 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,
- });
- }
- }
- }
- // Recurse into container nodes (e.g. field_declaration_list in Go structs)
- if (child.type === 'field_declaration_list') {
- this.extractInheritance(child, classId);
- }
- }
- }
- /**
- * 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
- */
- export function extractFromSource(
- filePath: string,
- source: string,
- language?: Language
- ): ExtractionResult {
- const detectedLanguage = language || detectLanguage(filePath);
- const fileExtension = path.extname(filePath).toLowerCase();
- // Use custom extractor for Svelte
- if (detectedLanguage === 'svelte') {
- const extractor = new SvelteExtractor(filePath, source);
- return extractor.extract();
- }
- // Use custom extractor for Liquid
- if (detectedLanguage === 'liquid') {
- const extractor = new LiquidExtractor(filePath, source);
- return extractor.extract();
- }
- // Use custom extractor for DFM/FMX form files
- if (
- detectedLanguage === 'pascal' &&
- (fileExtension === '.dfm' || fileExtension === '.fmx')
- ) {
- const extractor = new DfmExtractor(filePath, source);
- return extractor.extract();
- }
- const extractor = new TreeSitterExtractor(filePath, source, detectedLanguage);
- return extractor.extract();
- }
|