09e301bbfa
Fifth R7b batch-3 port, checklist-first recipe (docs/design/swift-kernel-port-checklist.md, 1,056 lines — the largest of the arc, with a built-extractor-validated emission pin and a childForFieldName truth table). Grammar bump first, validated standalone: tree-sitter-wasms ^0.4.0 (ABI 13) → crate 0.7.3 — with a provenance twist: the wasm is built from the CRATE TARBALL's src/ (alex-pinkus keeps generated files off main and the 0.7.3-with-generated-files tag ships an older ABI-14 generation that can never sha-match; grammar.json rules are JSON-equal; the tarball is byte-for-byte what the kernel's cargo build compiles — table identity by construction). Older crates evaluated and rejected: clean-parse shapes are byte-identical on 0.7.3 (53-line CST battery diff, all inert), so an older pin buys nothing and loses the macro-era wins. Delta = error-set membership (63 old-error files parse clean: swift-testing #expect, #Preview/#GET macros, package access, typed throws — vapor 23.1%→9.3%; 21 NEW-only regressions in 3 probed construct classes) + two gate-found categories: docstring boundaries near #if directives (7 clean files, docstring-field-only — verified mechanically) and array-literal-callee call refs (2 refs, 1 file). Every hunk classified via the error-union rule + parked-ref↔edge ripple pairing. Walker (the arc's biggest) centers on the #1020 DEDICATED property branch: computed properties → property nodes with the getter walked under the property (SwiftUI body), static let/var → constant/variable, stored → field, decorator/type-annotation/@Siblings-attr-arg refs all attached to the ENCLOSING TYPE, stored initializer calls attributed to the class. Preserved bug-for-bug: the never-resolving 'parameter' field (zero param type refs, zero signatures), present-false isAsync, open→internal visibility, everything-is-extends inheritance (first type_identifier per specifier), no instantiates refs ever, subscript reads as `calls arr`, `defer` as `calls defer`, multi-case enum entries minting only the first case, /** */ block docs ignored AND chain-breaking, init/deinit/subscript minting no nodes with visitNode-routed bodies (calls → class, static reads → nothing), multi- segment extension resolveName, sugar extension names, the #selector shapes, and the value_argument label-forward skip. ONE fix found by the sweep (then pinned in the fixture + checklist): the shared `assignment` shadow-prune case is swift-live — declared-then-assigned `let X: T` prunes X as a value-ref target. Gates: sweeps 0-diff Alamofire 89/98, vapor 224/247, swift-nio 407/554 (--max-deferral 0.3 — swift error incidence is 9–27% on BOTH arms, structural; every deferral count matches the survey's table exactly); full-init dumps byte-identical ×3 (31.9k/20.7k/126.3k lines); the Alamofire census reproduces property=348 (the #1020 number) on the kernel arm; kernel-swift-parity suite (206-line torture + CRLF + the #if-between-enum- cases defer fixture) + swift grammar-parity row; full suite 2,626 green ×2 under CODEGRAPH_KERNEL_EXPECT=1. DEFAULT_ROUTED += swift (14 langs). Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
71 lines
3.1 KiB
TypeScript
71 lines
3.1 KiB
TypeScript
/**
|
|
* Grammar-source parity gate (R1, migration plan §3.5).
|
|
*
|
|
* The native kernel compiles grammars from crates.io / vendored sources; the
|
|
* wasm fallback loads grammars from tree-sitter-wasms / src/extraction/wasm.
|
|
* If the two are built from different grammar revisions, a language's graph
|
|
* would depend on WHICH path extracted it — per-language routing (and the
|
|
* kernel-absent fallback) must be graph-neutral.
|
|
*
|
|
* Rather than trusting version metadata, this asserts the grammars are
|
|
* behaviorally identical where extraction can observe them: ABI version and
|
|
* the full node-kind and field tables, compared id by id.
|
|
*
|
|
* Runs wherever a kernel binary is staged (scripts/build-kernel.sh); skips
|
|
* otherwise. CI that builds the kernel sets CODEGRAPH_KERNEL_EXPECT=1 so the
|
|
* skip can't mask a missing build (asserted in kernel-scaffold.test.ts).
|
|
*/
|
|
|
|
import { describe, it, expect, beforeAll } from 'vitest';
|
|
import * as fs from 'fs';
|
|
import * as path from 'path';
|
|
import type { Language as WasmLanguage } from 'web-tree-sitter';
|
|
import { getKernel, resetKernelForTests } from '../src/extraction/kernel';
|
|
import { initGrammars, loadGrammarsForLanguages, getParser } from '../src/extraction/grammars';
|
|
import type { Language } from '../src/types';
|
|
|
|
const KERNEL_PATH = path.join(
|
|
__dirname,
|
|
'..',
|
|
'codegraph-kernel',
|
|
'prebuilds',
|
|
`${process.platform}-${process.arch}`,
|
|
'codegraph-kernel.node'
|
|
);
|
|
const kernelBuilt = fs.existsSync(KERNEL_PATH);
|
|
|
|
// Every kernel-capable language. `jsx` shares the javascript grammar on BOTH
|
|
// paths (langs.rs mirrors WASM_GRAMMAR_FILES), so the distinct grammars are:
|
|
const GRAMMAR_LANGUAGES: Language[] = ['typescript', 'tsx', 'javascript', 'java', 'python', 'go', 'c', 'cpp', 'rust', 'csharp', 'ruby', 'php', 'swift'];
|
|
|
|
describe.skipIf(!kernelBuilt)('kernel↔wasm grammar parity', () => {
|
|
beforeAll(async () => {
|
|
resetKernelForTests();
|
|
await initGrammars();
|
|
await loadGrammarsForLanguages(GRAMMAR_LANGUAGES);
|
|
});
|
|
|
|
it.each(GRAMMAR_LANGUAGES)('%s: node-kind and field tables are identical', (language) => {
|
|
const kernel = getKernel();
|
|
expect(kernel).not.toBeNull();
|
|
const native = kernel!.grammarInfo(language);
|
|
expect(native, `kernel has no grammar for ${language}`).not.toBeNull();
|
|
|
|
const wasmLang = getParser(language)?.language as WasmLanguage | null | undefined;
|
|
expect(wasmLang, `wasm grammar for ${language} not loaded`).toBeTruthy();
|
|
|
|
expect(native!.abiVersion, 'grammar ABI version').toBe(wasmLang!.abiVersion);
|
|
expect(native!.nodeKindCount, 'node-kind count').toBe(wasmLang!.nodeTypeCount);
|
|
expect(native!.fieldCount, 'field count').toBe(wasmLang!.fieldCount);
|
|
|
|
const wasmKinds: (string | null)[] = [];
|
|
for (let i = 0; i < wasmLang!.nodeTypeCount; i++) wasmKinds.push(wasmLang!.nodeTypeForId(i));
|
|
expect(native!.nodeKinds).toEqual(wasmKinds.map((k) => k ?? ''));
|
|
|
|
// Field ids are 1-based on both sides.
|
|
const wasmFields: (string | null)[] = [];
|
|
for (let i = 1; i <= wasmLang!.fieldCount; i++) wasmFields.push(wasmLang!.fieldNameForId(i));
|
|
expect(native!.fieldNames).toEqual(wasmFields.map((f) => f ?? ''));
|
|
});
|
|
});
|