d1b75a1a27
R7b batch 4 #4 — the FINAL R7b language (docs/design/dart-kernel-port-checklist.md is the authoritative quirk list). The fourth vendored-grammar-C language, with a twist: production dart resolved its wasm from tree-sitter-wasms, whose dart dependency is an UNPINNED github:UserNobody14/tree-sitter-dart — a routine dependency update would have silently changed dart's grammar. This PR byte-copies the shipping 0.1.13 artifact into src/extraction/wasm/ (VENDORED_WASM_LANGS += dart) and compiles the same-commit (d4d8f3e337d8) parser.c/scanner.c in the kernel — table identity proven by the kernel-grammar-parity row. crates.io tree-sitter-dart is the nielsenko fork (different lineage) — rejected. The center of gravity is THE SIBLING-BODY DOUBLE-WALK, reproduced bug-for-bug: dart attaches every function/method body as a NEXT SIBLING of its signature, and the TS walkers consume each body TWICE — once via resolveBody (attributed to the function/method) and once via the enclosing generic walk (attributed to the file/class). Duplicate local-function nodes with the SAME id under different parents, duplicated calls/instantiates refs, and file/class-attributed fn-ref twins all emit in the exact observed interleave (a dedicated fixture pins the duplicate-id rows; the bloc kind-census spot-check pins the counts). Also preserved (probe-pinned): the extractBareCall selector matrix (the first callTypes=[] language — cascades completely invisible, `?.` encodes like `.`, the `ConfigT.load()` calls+references double emission with no callee-of-call skip, capitalized-chain `Foo.create().run` re-encode, const-object callee names); the constructor hooks (unnamed ctor skipped, named ctors/factories renamed to the CTOR name with the class as returnType, `@override (T) m()` record-misparse rescued by class-name validation); operator methods minting `method "<anonymous>"`; static_final_declaration constants via the visitNode hook while instance fields mint NOTHING; the prefixed-return-type prefix bug (`other.OtherClass f()` → returnType `other`); enum `with` mixins silent vs `implements` working; anonymous extensions named after the ON type; deferred imports invisible; named-argument callbacks NOT fn-ref-captured (the Flutter `onPressed:` idiom — future accuracy PR, TS-side first); `async*`/`sync*` NOT async; value-refs with the LIVE dart sibling-body pull and the `$X`-vs-`${X}` interpolation asymmetry; dartdoc kept in all three comment forms with the annotation-broken chain. Gates: parity sweeps first-run 0-diff on shelf/bloc/flutter — 5,815 clean files byte-parity, deferrals 10/21/1341 ≈ the survey's 10/21/~1340 (both-arm grammar reality: empty object patterns — the sealed-class idiom — and unnamed `library;` dominate; --max-deferral 0.3); full-init dumps byte-identical ×3 (shelf 7,959 / bloc 40,026 / flutter 1,855,319 dump lines); bloc per-kind node census identical across arms (the double-walk duplicate rows survive the store identically); kernel-dart-parity suite (7 fixtures + in-memory CRLF variants + double-walk duplicate-id pin + generated-file skip pin + two defer pins); full suite 2,688 green ×2 with CODEGRAPH_KERNEL_EXPECT=1. DEFAULT_ROUTED += dart (20 langs — R7b COMPLETE). 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', 'kotlin', 'r', 'lua', 'luau', 'scala', 'dart'];
|
|
|
|
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 ?? ''));
|
|
});
|
|
});
|