Files
codegraph/src/resolution/frameworks/express.ts
T
74327814ee feat: wire up framework route extraction (#89)
* docs: add framework extract wiring plan

* feat(resolution): replace extractNodes with extract() returning nodes and references

* feat(resolution): add getApplicableFrameworks helper for per-language dispatch

* feat(django): emit route nodes and route->view references in extract()

* feat(flask,fastapi): emit route nodes and route->handler references

* feat(express): emit route nodes and route->handler references

* feat(laravel): emit route nodes and route->handler references

* feat(rails): emit route nodes and route->handler references

* feat(spring): emit route nodes and route->handler references

* feat(go): emit route nodes and route->handler references

* feat(rust): emit route nodes and route->handler references

* feat(aspnet): emit route nodes and route->handler references

* feat(swift,vapor): emit route nodes and route->handler references

* chore(react,svelte): migrate resolvers to extract() interface

* feat(extraction): run framework extractors after tree-sitter parse

* docs: document framework route extraction

* feat(strip-comments): add per-language comment stripper for framework extractors

Replaces comment characters and string-literal contents with spaces (not
removal) so source offsets stay valid for downstream regex match index ->
line number conversion. Handles Python triple-quoted docstrings, Ruby
=begin/=end, Rust nested block comments, and the standard //, #, /* */
forms across the supported languages.

This is consumed by framework extract() methods in a follow-up commit so
that commented-out / docstring routing examples don't surface as phantom
route nodes in the graph.

* feat(frameworks): strip comments before regex extraction (prevents phantom routes)

Pipes the per-language stripCommentsForRegex helper into every framework
extract() that scans raw source: django/flask/fastapi (python.ts),
express, laravel, rails, spring, go, rust, aspnet, vapor, plus
swiftui/uikit struct extraction in swift.ts.

Without this, examples like:

    # path('/admin/', AdminPanel.as_view())
    """ path('/users/', UserListView.as_view()) """
    urlpatterns = [path('/real/', RealView.as_view())]

produced 3 phantom route nodes. Now only the real one is extracted.

Each framework gets a regression test in __tests__/frameworks.test.ts
asserting that line-, block-, docstring- and (where relevant)
heredoc-style commented-out routes do not surface as nodes.

---------

Co-authored-by: Colby McHenry <me@colbymchenry.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 22:03:33 -05:00

262 lines
7.9 KiB
TypeScript

/**
* Express/Node.js Framework Resolver
*
* Handles Express and general Node.js patterns.
*/
import { Node } from '../../types';
import { FrameworkResolver, UnresolvedRef, ResolvedRef, ResolutionContext } from '../types';
import { stripCommentsForRegex } from '../strip-comments';
function extractTailIdent(expr: string): string | null {
const cleaned = expr.replace(/\s+/g, '').replace(/\(\)$/, '');
const m = cleaned.match(/(?:\.|^)([A-Za-z_][A-Za-z0-9_]*)$/);
return m ? m[1]! : null;
}
export const expressResolver: FrameworkResolver = {
name: 'express',
languages: ['javascript', 'typescript'],
detect(context: ResolutionContext): boolean {
// Check for Express in package.json
const packageJson = context.readFile('package.json');
if (packageJson) {
try {
const pkg = JSON.parse(packageJson);
const deps = { ...pkg.dependencies, ...pkg.devDependencies };
if (deps.express || deps.fastify || deps.koa || deps.hapi) {
return true;
}
} catch {
// Invalid JSON
}
}
// Check for common Express patterns
const allFiles = context.getAllFiles();
for (const file of allFiles) {
if (
file.includes('routes') ||
file.includes('controllers') ||
file.includes('middleware')
) {
const content = context.readFile(file);
if (content && (content.includes('express') || content.includes('app.get') || content.includes('router.get'))) {
return true;
}
}
}
return false;
},
resolve(ref: UnresolvedRef, context: ResolutionContext): ResolvedRef | null {
// Pattern 1: Middleware references
if (isMiddlewareName(ref.referenceName)) {
const result = resolveMiddleware(ref.referenceName, context);
if (result) {
return {
original: ref,
targetNodeId: result,
confidence: 0.8,
resolvedBy: 'framework',
};
}
}
// Pattern 2: Controller method references
const controllerMatch = ref.referenceName.match(/^(\w+)Controller\.(\w+)$/);
if (controllerMatch) {
const [, controller, method] = controllerMatch;
const result = resolveControllerMethod(controller!, method!, context);
if (result) {
return {
original: ref,
targetNodeId: result,
confidence: 0.85,
resolvedBy: 'framework',
};
}
}
// Pattern 3: Service/helper references
const serviceMatch = ref.referenceName.match(/^(\w+)(Service|Helper|Utils?)\.(\w+)$/);
if (serviceMatch) {
const [, name, suffix, method] = serviceMatch;
const result = resolveServiceMethod(name! + suffix!, method!, context);
if (result) {
return {
original: ref,
targetNodeId: result,
confidence: 0.8,
resolvedBy: 'framework',
};
}
}
return null;
},
extract(filePath, content) {
if (!/\.(m?js|tsx?|cjs)$/.test(filePath)) return { nodes: [], references: [] };
const nodes: Node[] = [];
const references: UnresolvedRef[] = [];
const now = Date.now();
const lang = detectLanguage(filePath);
const safe = stripCommentsForRegex(content, lang);
// (app|router).METHOD('/path', handler-expr)
const regex = /\b(app|router)\.(get|post|put|patch|delete|all|use)\s*\(\s*['"]([^'"]+)['"]\s*,\s*([^)]+)\)/g;
let match: RegExpExecArray | null;
while ((match = regex.exec(safe)) !== null) {
const [, _obj, method, routePath, handlers] = match;
if (method === 'use' && !routePath!.startsWith('/')) continue;
const line = safe.slice(0, match.index).split('\n').length;
const routeNode: Node = {
id: `route:${filePath}:${line}:${method!.toUpperCase()}:${routePath}`,
kind: 'route',
name: `${method!.toUpperCase()} ${routePath}`,
qualifiedName: `${filePath}::${method!.toUpperCase()}:${routePath}`,
filePath,
startLine: line,
endLine: line,
startColumn: 0,
endColumn: match[0].length,
language: detectLanguage(filePath),
updatedAt: now,
};
nodes.push(routeNode);
// Handler is the LAST comma-separated argument; earlier ones are middleware.
const parts = handlers!.split(',').map((s) => s.trim()).filter(Boolean);
const last = parts[parts.length - 1];
const handlerName = last ? extractTailIdent(last) : null;
if (handlerName) {
references.push({
fromNodeId: routeNode.id,
referenceName: handlerName,
referenceKind: 'references',
line,
column: 0,
filePath,
language: detectLanguage(filePath),
});
}
}
return { nodes, references };
},
};
/**
* Check if a name looks like middleware
*/
function isMiddlewareName(name: string): boolean {
const middlewarePatterns = [
/^auth$/i,
/^authenticate$/i,
/^authorization$/i,
/^validate/i,
/^sanitize/i,
/^rateLimit/i,
/^cors$/i,
/^helmet$/i,
/^logger$/i,
/^errorHandler$/i,
/^notFound$/i,
/Middleware$/i,
];
return middlewarePatterns.some((p) => p.test(name));
}
/**
* Resolve middleware reference using name-based lookup
*/
function resolveMiddleware(
name: string,
context: ResolutionContext
): string | null {
// Try exact name first
const candidates = context.getNodesByName(name);
const match = candidates.find((n) =>
n.name.toLowerCase() === name.toLowerCase() ||
n.name.toLowerCase() === name.replace(/Middleware$/i, '').toLowerCase()
);
if (match) return match.id;
// Try without Middleware suffix
const baseName = name.replace(/Middleware$/i, '');
if (baseName !== name) {
const baseCandidates = context.getNodesByName(baseName);
const MIDDLEWARE_DIRS = ['/middleware/', '/middlewares/'];
const preferred = baseCandidates.filter((n) =>
MIDDLEWARE_DIRS.some((d) => n.filePath.includes(d))
);
if (preferred.length > 0) return preferred[0]!.id;
if (baseCandidates.length > 0) return baseCandidates[0]!.id;
}
return null;
}
/**
* Resolve controller method using name-based lookup
*/
function resolveControllerMethod(
controller: string,
method: string,
context: ResolutionContext
): string | null {
// Look for the method name directly
const methodCandidates = context.getNodesByName(method);
const methodNodes = methodCandidates.filter(
(n) => (n.kind === 'method' || n.kind === 'function') &&
n.filePath.toLowerCase().includes(controller.toLowerCase())
);
if (methodNodes.length > 0) return methodNodes[0]!.id;
// Fall back: look for controller class, then find the method in its file
const controllerName = controller + 'Controller';
const controllerCandidates = context.getNodesByName(controllerName);
for (const ctrl of controllerCandidates) {
const nodesInFile = context.getNodesInFile(ctrl.filePath);
const methodNode = nodesInFile.find(
(n) => (n.kind === 'method' || n.kind === 'function') && n.name === method
);
if (methodNode) return methodNode.id;
}
return null;
}
/**
* Resolve service/helper method using name-based lookup
*/
function resolveServiceMethod(
serviceName: string,
method: string,
context: ResolutionContext
): string | null {
// Look for the method in files matching the service name
const methodCandidates = context.getNodesByName(method);
const stripped = serviceName.replace(/(Service|Helper|Utils?)$/i, '').toLowerCase();
const methodNodes = methodCandidates.filter(
(n) => (n.kind === 'method' || n.kind === 'function') &&
n.filePath.toLowerCase().includes(stripped)
);
if (methodNodes.length > 0) return methodNodes[0]!.id;
return null;
}
/**
* Detect language from file extension
*/
function detectLanguage(filePath: string): 'typescript' | 'javascript' {
if (filePath.endsWith('.ts') || filePath.endsWith('.tsx')) {
return 'typescript';
}
return 'javascript';
}