Files
gitmost/packages/editor-ext/src/lib/markdown/utils/turndown.dataloss.test.ts
claude code agent 227 2d36641f28 test(coverage): add regression tests for issues #192, #206, #204
Additive test coverage across server, editor-ext, client and mcp.

#192 — AiChatService.stream integration (Section 3, against real Postgres):
- new apps/server/test/integration/ai-chat-stream.int-spec.ts drives the real
  streamText through a seeded ai/test MockLanguageModelV3 and a real Node
  ServerResponse, covering: onError persists an assistant error record
  (status 'error' + partial answer + provider cause in metadata); external MCP
  client closed exactly once on BOTH onFinish and onError; anti-tamper —
  history is rebuilt from the DB transcript, not from body.messages.

#206 — red-team findings (most already fixed+tested in #212):
- mdrt-2 (UNFIXED, data loss): turndown.dataloss.test.ts documents that
  pageBreak / transclusionReference / mention are silently dropped on Markdown
  export (characterization + it.fails for the desired survive-export contract).
- persist-6 (UNFIXED, data loss): persistence-store.spec.ts adds an it.failing
  documenting that a momentarily-empty live doc overwrites non-empty content
  (left unfixed — a store-side empty-guard is a behaviour change).

#204 — test-strategy plan, highest-priority subset:
- Phase 1: mcp-clients.lease.spec.ts covers the external MCP client
  lease/refcount/eviction lifecycle (leak / premature-close / double-close).
- Phase 2 data-integrity pure functions: editor-ext table-utils
  (transpose/moveRow/convert round-trip) and math tokenizer false-positive
  guard; client emoji-menu (+ it.fails for the unguarded localStorage
  JSON.parse bug), sort-cells, normalizeTableColumnWidths; mcp htmlEmbed/
  pageBreak markdown data-loss + footnote-diff; server export
  getInternalLinkPageName extensionless-path bug — FIXED (small/clear) + tested.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-27 06:15:55 +03:00

78 lines
3.0 KiB
TypeScript

import { describe, it, expect } from "vitest";
import { htmlToMarkdown } from "./turndown.utils";
/**
* #206 mdrt-2 — Markdown export must never SILENTLY drop a block.
*
* `htmlToMarkdown` (turndown) only registers rules for a fixed set of custom
* nodes (callout, taskItem, details, math, iframe, htmlEmbed, image, video,
* footnote). Any other custom node — `transclusionReference`, `pageBreak`,
* `mention`, `status` — falls through to turndown's default handling: an empty
* wrapper is "blank" and removed, so the block disappears from the exported
* Markdown with no trace. The invariant "never silently lose a block" is broken.
*
* The `it.fails` cases assert the DESIRED contract (the block survives export in
* SOME form) and are RED today: they document the unfixed data loss and flip to
* green the moment a turndown rule (real syntax or a lossless HTML-comment
* placeholder) is added. A normal characterization `it` pins the exact current
* lossy output so the regression is unambiguous.
*/
describe("htmlToMarkdown — custom nodes without a turndown rule (#206 mdrt-2)", () => {
const wrap = (inner: string) =>
`<p>before</p>${inner}<p>after</p>`;
it("CURRENTLY drops a pageBreak entirely (data loss)", () => {
const md = htmlToMarkdown(
wrap('<div data-type="pageBreak" class="page-break"></div>'),
);
// The page break vanishes: only the two paragraphs remain, nothing between.
expect(md).toContain("before");
expect(md).toContain("after");
expect(md).not.toMatch(/page-?break/i);
expect(md).not.toContain("---"); // not even a horizontal-rule fallback
});
it("CURRENTLY drops a transclusionReference entirely (data loss)", () => {
const md = htmlToMarkdown(
wrap('<div data-type="transclusionReference" data-id="abc"></div>'),
);
expect(md).toContain("before");
expect(md).toContain("after");
// The data-id (the only thing that gives the reference identity) is gone.
expect(md).not.toContain("abc");
});
it.fails(
"should NOT lose a pageBreak block on Markdown export",
() => {
const md = htmlToMarkdown(
wrap('<div data-type="pageBreak" class="page-break"></div>'),
);
// Desired: the break survives in some form (e.g. a `---` rule or marker).
expect(md).toMatch(/(-{3,}|page-?break)/i);
},
);
it.fails(
"should NOT lose a transclusionReference's identity on Markdown export",
() => {
const md = htmlToMarkdown(
wrap('<div data-type="transclusionReference" data-id="abc"></div>'),
);
// Desired: the referenced id survives so the block can be rebuilt.
expect(md).toContain("abc");
},
);
it.fails(
"should NOT lose a mention's data-id on Markdown export",
() => {
const md = htmlToMarkdown(
'<p>hi <span data-type="mention" data-id="u1" data-label="Bob">@Bob</span> there</p>',
);
// Desired: the mention keeps its stable identity (data-id), not just text.
expect(md).toContain("u1");
},
);
});