Files
codegraph/__tests__/closure-collection-synthesizer.test.ts
T
e76a355df5 fix(resolution): gate closure-collection synthesis to Swift/Kotlin and de-quadratic its line accounting (#1235) (#1237)
closureCollectionEdges scanned every method/function node in every
language, but its dispatcher patterns ({ $0( / { it( ) are Swift/Kotlin
trailing-closure syntax — on PHP/JS repos the pass can never emit an
edge, yet .push(/.add( fired its append gate on nearly every function.
Per match it computed the line via src.slice(0, idx).split('\n'), which
is O(source) per match and goes quadratic on match-dense generated
functions (two-byte content roughly doubles it). On a 12,860-file
PHP/JS app that was 20+ minutes of the "Resolving refs" tail — frozen
at 97% — and a #850 watchdog kill; profiled on CRMEB it was 127s of a
166s index for zero edges.

- Skip nodes whose language isn't swift/kotlin before any file I/O.
- makeLineAt(): lazy newline index + binary search, shared with the
  emitter passes' per-file lineOf.
- Yield every 256 regex matches inside the scan's match loops so a
  single pathological function can't starve the watchdog.

CRMEB (ThinkPHP, 2,913 files): 166.8s -> 72.7s, graph byte-identical.
Alamofire: closure-collection edges byte-identical (9 edges, 4 fields).
Drupal core control: graph byte-identical.

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-09 20:54:45 -05:00

160 lines
5.7 KiB
TypeScript

import { describe, it, expect, beforeEach, afterEach } from 'vitest';
import * as fs from 'node:fs';
import * as path from 'node:path';
import * as os from 'node:os';
import { CodeGraph } from '../src';
/**
* End-to-end synthesizer test for closure-collection dynamic dispatch.
*
* A method appends a closure to a collection property; another method iterates
* that property *invoking each element* (`coll.forEach { $0() }`) — a dynamic
* dispatch tree-sitter can't resolve, so a flow into the dispatcher dead-ends
* before the registered closures. This is Alamofire's request-validation shape:
* `DataRequest.validate` does `validators.write { $0.append(validator) }`, the
* base `Request.didCompleteTask` runs `validators.forEach { $0() }`.
*
* Verify the synthesizer (1) links the dispatcher → each same-named registrar
* across files/classes, (2) handles both the Swift `prop.write { $0.append }`
* and the direct `prop.append(...)` registrar forms, (3) surfaces the wiring
* site, and (4) does NOT fire on a `.forEach` that doesn't invoke its element
* (the closure-invoke is the precision gate — a plain collection is skipped).
*/
describe('closure-collection synthesizer', () => {
let dir: string;
beforeEach(() => {
dir = fs.mkdtempSync(path.join(os.tmpdir(), 'closure-coll-fixture-'));
});
afterEach(() => {
fs.rmSync(dir, { recursive: true, force: true });
});
it('links dispatcher → registrars across files, both append forms, and skips non-invoked collections', async () => {
// Base class: the dispatchers (iterate-and-invoke) + a non-closure control.
fs.writeFileSync(
path.join(dir, 'Request.swift'),
`class Request {
var validators: [() -> Void] = []
var handlers: [() -> Void] = []
var names: [String] = []
func didCompleteTask() {
let validators = validators
validators.forEach { $0() }
}
func runHandlers() {
handlers.forEach { $0() }
}
func printNames() {
names.forEach { print($0) }
}
}
`
);
// Subclass: the registrars (append a closure) in a DIFFERENT file/class.
fs.writeFileSync(
path.join(dir, 'DataRequest.swift'),
`class DataRequest: Request {
func validate(_ validation: @escaping () -> Void) -> Self {
let validator: () -> Void = { validation() }
validators.write { $0.append(validator) }
return self
}
func onEvent(_ handler: @escaping () -> Void) {
handlers.append(handler)
}
func addName(_ n: String) {
names.append(n)
}
}
`
);
const cg = await CodeGraph.init(dir, { silent: true });
await cg.indexAll();
const db = (cg as any).db.db;
const rows = db
.prepare(
`SELECT s.name source_name, s.kind source_kind, t.name target_name,
json_extract(e.metadata,'$.field') field,
json_extract(e.metadata,'$.registeredAt') registeredAt
FROM edges e
JOIN nodes s ON s.id = e.source
JOIN nodes t ON t.id = e.target
WHERE json_extract(e.metadata,'$.synthesizedBy') = 'closure-collection'`
)
.all();
cg.close?.();
expect(rows.length).toBeGreaterThan(0);
// Every edge originates from a dispatcher method and is a real `calls` hop.
expect(rows.every((r: any) => r.source_kind === 'method')).toBe(true);
// The validators flow: didCompleteTask → validate, captured via the Swift
// Protected `prop.write { $0.append }` form, wiring site surfaced.
const validatorsEdge = rows.find(
(r: any) => r.field === 'validators' && r.target_name === 'validate'
);
expect(validatorsEdge).toBeTruthy();
expect(validatorsEdge.source_name).toBe('didCompleteTask');
// Exact wiring-site line, not just shape: pins the binary-search line
// resolver (#1235) to the same answer as the old per-match slice+split.
expect(validatorsEdge.registeredAt).toBe('DataRequest.swift:4');
// The handlers flow: runHandlers → onEvent, via the direct `prop.append`
// form — proves both registrar shapes are covered.
const handlersEdge = rows.find(
(r: any) => r.field === 'handlers' && r.target_name === 'onEvent'
);
expect(handlersEdge).toBeTruthy();
expect(handlersEdge.source_name).toBe('runHandlers');
// Precision gate: `names.forEach { print($0) }` does NOT invoke its element,
// so `names` is not a closure collection — no edge, and addName is never a target.
expect(rows.some((r: any) => r.field === 'names')).toBe(false);
expect(rows.some((r: any) => r.target_name === 'addName')).toBe(false);
});
it('is a no-op on non-Swift/Kotlin code even when the text patterns occur (#1235)', async () => {
// JS that contains every textual trigger the scanner looks for —
// `.forEach`, `.push(`, even a `{ $0(` lookalike inside a string — but
// `{ $0( ` / `{ it( ` element-invocation is Swift/Kotlin trailing-closure
// syntax, so the pass must skip the language entirely (this scan running
// ungated over `.push(`-heavy JS/PHP was the #1235 25-minute index).
fs.writeFileSync(
path.join(dir, 'queue.js'),
`class Queue {
constructor() { this.tasks = []; }
register(fn) { this.tasks.push(fn); }
drain() { this.tasks.forEach(function (t) { t(); }); }
weird() { const s = "tasks.forEach { $0( } tasks.push("; return s; }
}
module.exports = Queue;
`
);
const cg = await CodeGraph.init(dir, { silent: true });
await cg.indexAll();
const db = (cg as any).db.db;
const count = db
.prepare(
`SELECT count(*) c FROM edges
WHERE json_extract(metadata,'$.synthesizedBy') = 'closure-collection'`
)
.get();
cg.close?.();
expect(count.c).toBe(0);
});
});