fix: address markdown renderer review findings

Restore the replaced pipeline's synthetic fence newline so a real trailing
blank line inside a fence survives CodeBlock's display trim, and pin it
plus header-only tables in the DOM-parity corpus. Route
extractMarkdownPlainText through parseGfm so the grammar has one source.
Document the fixture provenance check (all 46 fixtures reproduce
byte-identically from react-markdown at 9e8101b800), the deliberate
O(prefix) divergence memcmp, the per-arm scope of grammar consistency,
the React 18 MathML namespace limitation, and the prefix-equivalence
corpus constraint.
This commit is contained in:
07akioni
2026-08-06 14:58:33 +08:00
parent d1e4fb91d2
commit 31b99930d9
14 changed files with 152 additions and 21 deletions

View File

@@ -1,12 +1,12 @@
/**
* Markdown-to-plain-text projection for compact summaries and labels.
* Parsing shares the renderer's GFM grammar; raw HTML stays literal, links
* keep their labels, images keep alt text, and code keeps its source text.
* Parsing shares the renderer's streaming GFM grammar ({@link parseGfm}), so
* the projection strips exactly the markup the renderer would draw; raw HTML
* stays literal, links keep their labels, images keep alt text, and code
* keeps its source text.
*/
import { fromMarkdown } from 'mdast-util-from-markdown'
import { gfmFromMarkdown } from 'mdast-util-gfm'
import { gfm } from 'micromark-extension-gfm'
import { parseGfm } from './parse.ts'
/** Amount of parsed Markdown content returned by the extractor. */
export type MarkdownPlainTextMode = 'all' | 'first-line' | 'first-paragraph'
@@ -108,10 +108,7 @@ export function extractMarkdownPlainText(
options: MarkdownPlainTextOptions = {},
): string {
const { mode = 'all' } = options
const root = fromMarkdown(markdown, {
extensions: [gfm()],
mdastExtensions: [gfmFromMarkdown()],
}) as MarkdownNode
const root = parseGfm(markdown) as MarkdownNode
const all = fullText(root)
switch (mode) {
case 'all':