fix(reference): preserve distinct parse failures

This commit is contained in:
N0zoM1z0 2026-07-14 20:27:31 +00:00
parent 528c05e2fa
commit 543510f62f
3 changed files with 41 additions and 7 deletions

View File

@ -1,6 +1,7 @@
import { isSecretLikePath } from "../domain/referenceSourceClassification.js";
import {
createHistoricalSourceGraph,
historicalSourceParseFailureKey,
type HistoricalSourceGraph,
type HistoricalSourceGraphInput,
} from "../domain/referenceSourceGraph.js";
@ -205,16 +206,20 @@ export const importReferenceSource = async (
const uniqueRelationships = deduplicateRelationships(relationships);
const uniqueFailures = [...parseFailures]
.sort((left, right) => {
const byPath = byCodePoint(left.path, right.path);
if (byPath !== 0) return byPath;
return byCodePoint(left.parser, right.parser);
})
.sort((left, right) =>
byCodePoint(
historicalSourceParseFailureKey(left),
historicalSourceParseFailureKey(right),
),
)
.filter((value, index, array) => {
if (index === 0) return true;
const previous = array[index - 1];
if (previous === undefined) return true;
return value.path !== previous.path || value.parser !== previous.parser;
return (
historicalSourceParseFailureKey(value) !==
historicalSourceParseFailureKey(previous)
);
});
const sortedEntries = [...entries].sort((left, right) =>

View File

@ -225,6 +225,11 @@ export type HistoricalSourceManifest = z.infer<
typeof historicalSourceManifestBaseSchema
>;
/** Stable identity used to sort and deduplicate source parse failures. */
export const historicalSourceParseFailureKey = (
failure: HistoricalSourceGraphInput["parse_failures"][number],
): string => `${failure.path}\u0000${failure.parser}\u0000${failure.reason}`;
const canonicalJson = (value: unknown): string => {
const serialized = canonicalize(value);
if (serialized === undefined)
@ -400,7 +405,7 @@ function checkGraphInvariants(
context,
);
checkSortedUnique(
graph.parse_failures.map(({ path, parser }) => `${path}\u0000${parser}`),
graph.parse_failures.map(historicalSourceParseFailureKey),
"parse_failures",
context,
);

View File

@ -5,6 +5,7 @@ import {
createHistoricalSourceGraph,
createHistoricalSourceManifest,
historicalSourceGraphSchema,
historicalSourceParseFailureKey,
parseHistoricalSourceGraph,
parseHistoricalSourceManifest,
type HistoricalSourceGraphInput,
@ -192,6 +193,29 @@ describe("historical source graph", () => {
).toThrow(/Complete inventory/u);
});
it("keeps distinct parse failure reasons for the same path and parser", () => {
const input = graphInput();
const malformed = {
path: "src/main.ts",
parser: "typescript",
reason: "Malformed input",
};
const unexpected = {
path: "src/main.ts",
parser: "typescript",
reason: "Unexpected token",
};
input.inventory_state = "partial";
input.parse_failures = [malformed, unexpected];
expect(createHistoricalSourceGraph(input).parse_failures).toEqual(
input.parse_failures,
);
expect(historicalSourceParseFailureKey(malformed)).not.toBe(
historicalSourceParseFailureKey(unexpected),
);
});
it("rejects strict unknown fields, invalid VCS, dangling internal edges, and false manifests", () => {
expect(() =>
createHistoricalSourceGraph({ ...graphInput(), surprise: true }),