benstull/vscode-cowriting-plugin
1
0
Fork 0
Code Issues 9 Pull Requests Actions Packages Projects Releases Wiki Activity

fix: render added blocks via markdown-safe sentinel path emitting cw-ins-* (heading/list structure preserved)

Browse Source 
Defect: an ADDED block was colored via `render(wordDiffByAuthor("", raw, ...))`, which
wrapped the whole raw markdown in an inline `<ins>` BEFORE markdown-it parsed it — so
`## X` rendered as literal text, not `<h2>`. Same structural bug for list, blockquote,
and thematic-break blocks.

Fix (three-part, pure / vscode-free):
1. `blockContentStart(raw)`: new helper returning the offset past block-level markers
   (ATX headings `## `, unordered/ordered list markers, blockquotes). Open sentinels must
   not precede these markers or markdown-it cannot recognise the block construct.
2. `injectSentinels`: clamp the open-sentinel lower-bound to `blockContentStart(raw)`,
   so for `## New Section` the sentinel lands AFTER `## ` (at position 3) instead of at
   position 0, letting the heading parse correctly.
3. `sentinelsToSpans` / `colorByAuthor`: add optional `kind: "by" | "ins" = "by"`
   parameter so the sentinel path can emit `cw-ins-{author}` for added blocks while all
   existing `colorByAuthor`/`cw-by-*` call-sites are unchanged.
4. `renderReview` ADDED block path: `render(wordDiffByAuthor("", raw, ...))` →
   `colorByAuthor(raw, blk.start, landedSpans, render, "ins")`. The CHANGED non-atomic
   prose path (`wordDiffByAuthor(before, after, ...)`) is untouched — it correctly keeps
   the block markers at column 0 of the unchanged prefix.
5. `renderReviewOp`: removed the now-vestigial `colored` parameter (was always `render`
   after the added-block path moved to `changedHtml`); unchanged blocks now call
   `render(op.block.raw)` directly.

Regression test added: "renderReview: an added heading block renders as a heading AND
is author-colored as an insertion" — RED on old code, GREEN after fix. All 259 tests
pass; typecheck clean.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
BenStullsBets
2026-06-26 14:09:19 -07:00
parent 08557827da
commit 44ef0a21db
2 changed files with 52 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/trackChangesModel.ts
+40 -12
View File
@@ -671,11 +671,38 @@ function clampOffDelimiterRun(raw: string, at: number): number {
return p;
}
/**
* Returns the offset within `raw` after block-level markdown markers (ATX
* headings, list markers, blockquote markers). Open sentinels must not be
* injected before these markers — a PUA char at position 0 would prevent
* markdown-it from recognising the block construct (e.g. `##` is only a
* heading marker when it is the very first char on the line).
*/
function blockContentStart(raw: string): number {
// ATX headings: "#{1,6} " at the start of the line.
const heading = raw.match(/^#{1,6} /);
if (heading) return heading[0].length;
// Unordered list markers: "- ", "* ", "+ ".
const ul = raw.match(/^[-*+] /);
if (ul) return ul[0].length;
// Ordered list markers: "N. " or "N) ".
const ol = raw.match(/^\d+[.)]\s+/);
if (ol) return ol[0].length;
// Blockquotes: "> " or ">".
const bq = raw.match(/^> ?/);
if (bq) return bq[0].length;
return 0;
}
/** Inject paired sentinels into a prose block's raw text for the spans clipped to it. */
function injectSentinels(raw: string, blockStart: number, spans: AuthorSpan[]): string {
const inserts: { at: number; marker: string }[] = [];
// Open sentinels must not precede block-level markdown markers (heading/list/
// blockquote syntax at position 0) — a PUA char before "## " prevents markdown-it
// from recognising the heading. Clamp to the content-start offset.
const minOpen = blockContentStart(raw);
for (const s of spans) {
const lo = clampOffDelimiterRun(raw, Math.max(0, s.start - blockStart));
const lo = Math.max(minOpen, clampOffDelimiterRun(raw, Math.max(0, s.start - blockStart)));
const hi = clampOffDelimiterRun(raw, Math.min(raw.length, s.end - blockStart));
if (hi <= lo) continue; // empty (or clamped to empty) span contributes nothing
inserts.push({ at: lo, marker: SENT[s.author].open });
@@ -711,13 +738,13 @@ const ALL_SENTINELS = new RegExp(
* (one `<span>` segment per text run). Tags are copied verbatim (with any stray
* sentinel stripped, so no Private-Use-Area char ever leaks). Pure, deterministic.
*/
function sentinelsToSpans(html: string): string {
function sentinelsToSpans(html: string, kind: "by" | "ins" = "by"): string {
const out: string[] = [];
let current: AuthorKind | null = null; // which author region we're inside
let spanOpen = false; // whether a <span> is currently open in `out`
const openSpan = () => {
if (current && !spanOpen) {
out.push(`<span class="cw-by-${current}">`);
out.push(`<span class="cw-${kind}-${current}">`);
spanOpen = true;
}
};
@@ -765,10 +792,11 @@ export function colorByAuthor(
blockStart: number,
spans: AuthorSpan[],
render: (src: string) => string,
kind: "by" | "ins" = "by",
): string {
const overlapping = spans.filter((s) => s.end > blockStart && s.start < blockStart + raw.length);
const injected = injectSentinels(raw, blockStart, overlapping);
return sentinelsToSpans(render(injected));
return sentinelsToSpans(render(injected), kind);
}
/**
@@ -839,7 +867,6 @@ function proposalBlockHtml(p: ProposalView, render: (src: string) => string): st
function renderReviewOp(
op: BlockOp,
render: (src: string) => string,
colored: (raw: string) => string,
src: string,
changedHtml?: string,
): string {
@@ -851,9 +878,9 @@ function renderReviewOp(
return `<div class="cw-blk cw-changed"${src}>${changedHtml}</div>`;
}
if (op.kind === "removed" || op.kind === "changed") return renderOp(op, render, src);
// "added": use changedHtml (author-colored word-diff from empty before, all insertions).
// "unchanged": colored() returns plain render(raw) — color means "changed since baseline".
return `<div class="cw-blk ${op.kind === "added" ? "cw-added" : "cw-unchanged"}"${src}>${changedHtml ?? colored(op.block.raw)}</div>`;
// "added": changedHtml is colorByAuthor sentinel output (markdown-safe, cw-ins-*).
// "unchanged": render(raw) — plain, no author coloring (color = "changed since baseline").
return `<div class="cw-blk ${op.kind === "added" ? "cw-added" : "cw-unchanged"}"${src}>${changedHtml ?? render(op.block.raw)}</div>`;
}
/**
@@ -967,19 +994,20 @@ export function renderReview(
const blk = op.kind === "removed" ? undefined : ranges[ci++];
// Only ADDED and CHANGED prose blocks are author-colored (they differ since baseline);
// UNCHANGED blocks render plain (color means "changed since baseline").
const colored = (raw: string): string => render(raw);
// A non-atomic changed prose block: author-colored word diff (ins by author,
// del by adjacency). An added block: word diff from empty before — all insertions.
// del by adjacency). An added block: sentinel-safe colorByAuthor with kind="ins"
// (markdown-it parses the block first, so ## → <h2> before sentinels become spans;
// the old wordDiffByAuthor path wrapped raw in <ins> BEFORE parsing — structural bug).
// `blk.start` is the landed offset of the after-side text.
const changedHtml =
blk && !clean
? op.kind === "changed" && !op.atomic
? render(wordDiffByAuthor(op.before.raw, op.block.raw, blk.start, landedSpans))
: op.kind === "added"
? render(wordDiffByAuthor("", op.block.raw, blk.start, landedSpans))
? colorByAuthor(op.block.raw, blk.start, landedSpans, render, "ins")
: undefined
: undefined;
bodyParts.push(renderReviewOp(op, render, colored, srcAttr(blk), changedHtml));
bodyParts.push(renderReviewOp(op, render, srcAttr(blk), changedHtml));
const here = blockIndex >= 0 ? byBlock.get(blockIndex) : undefined;
if (here) for (const p of here) bodyParts.push(proposalBlockHtml(p, render));
}
test/trackChangesModel.test.ts
+12
View File
@@ -491,6 +491,18 @@ describe("renderReview", () => {
const html = renderReview("Keep.", "Keep.\n\nFresh line.", [{ start: 6, end: 17, author: "human" }], []);
expect(html).toContain("cw-ins-human");
});
test("renderReview: an added heading block renders as a heading AND is author-colored as an insertion", () => {
// "Intro.\n\n" = 8 chars; "## New Section" = 14 chars → offset 8..22 in currentText.
// Before fix: wordDiffByAuthor wrapped raw in <ins> BEFORE markdown-it parsed it,
// so "## New Section" rendered as literal text (structural bug). After fix:
// colorByAuthor uses the sentinel technique — markdown-it parses the block first,
// so ## becomes a real <h2>, THEN sentinels are replaced with cw-ins-* spans.
const html = renderReview("Intro.", "Intro.\n\n## New Section", [{ start: 8, end: 22, author: "human" }], []);
expect(html).toMatch(/<h[12][^>]*>/); // real heading element, not literal "## "
expect(html).toContain("cw-ins-human"); // author-colored insertion
expect(html).not.toContain("&gt;&gt;"); // sanity: markers not escaped as text
});
});
import { renderTrackChanges as rtc2 } from "../src/trackChangesModel";