bdd687b49f
R7b batch 4 #3 (docs/design/scala-kernel-port-checklist.md is the authoritative quirk list). The third vendored-grammar-C language and the biggest grammar in the tree (35MB parser.c): the vendored wasm is tree-sitter/tree-sitter-scala master@0aca5d0a6f — a post-v0.26.0 generation sync that is not a release (the 0.26.0 crate is 30 states BEHIND, so a crate pin would be a silent downgrade). NO wasm change: production has parsed with this exact revision since #91 — the kernel-grammar-parity row (ABI 15, 26,650 states, 32 fields, id-by-id tables) is the whole alignment proof. Preserved bug-for-bug (all probe-pinned): the leak-through asymmetries — extension methods mint NO nodes (first def's body calls leak to the enclosing scope, later defs invisible, and the braced form resolves its body field to the `{` TOKEN via first-match-wins field lookup → whole extension invisible); anonymous `new T { … }` template_body members leak to the enclosing scope (findAnonymousClassBody misses template_body); the bodied-vs-bodiless class asymmetry (bodiless headers walk class_parameters → default-value calls emit FROM the class; bodied ones never see them) — plus first-segment import names (`import com.example.C` → `com`), the val/var hook keyed on the enclosing-definition NODE TYPE (object vals → constants/value-ref targets, class/trait/enum/given vals → fields) with consumed initializers, every def routed through extractMethod with the top-level function fallback, nested defs in bodies minting NOTHING (the inverse of kotlin) while body-local classes extract fully, curried signatures keeping only the FIRST parameter list (type params win the `parameters` field), enum cases positioned at the CASE node with invisible params/extends tails, extends with-chains via scalaBaseTypeName, `@deprecated(args)` decorates, the #750 capitalized-chain re-encode (`WidgetS.create().render`), literal-receiver silence, static-member reads AND writes, infix invisibility, `derives` silence, scaladoc retention with the CRLF `\r` pin, full value-reference machinery (shadow prune, last-wins same-name targets, `$X`/`${X}` interpolation reads), and SCALA_SPEC fn-refs (bare ids + postfix eta unwrap + varinit, var-init non-capture). Gates: parity sweeps first-run 0-diff on os-lib/cats/scala3-compiler-src/ scala3-library-src — 1,935 clean files byte-parity, deferrals 0/15/57/116 matching the survey's predictions exactly (scala-3's PHANTOM hasError files — flag-true, zero ERROR nodes, capture-checking `^` — defer on the FLAG); full-init dumps byte-identical ×3 (os-lib, cats, scala3 whole-repo 950,889 dump lines); kernel-scala-parity suite (9 fixtures + 9 in-memory CRLF variants incl. Scala-3 indentation through the external scanner + phantom/real-error defer pins + first-segment/namespace/value-ref pins); full suite 2,669 green ×3 with CODEGRAPH_KERNEL_EXPECT=1 (kernel-scaffold's stays-wasm example moved scala → pascal). DEFAULT_ROUTED += scala (19 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', 'kotlin', 'r', 'lua', 'luau', 'scala'];
|
|
|
|
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 ?? ''));
|
|
});
|
|
});
|