cjk - review: Hangul, the long-vowel mark and a character inside a delimiter bound a highlight

README.md

@@ -133,7 +133,7 @@ read replaces mentions, attachments and macros with text.
 | `panel` | a GitHub alert, `> [!WARNING]`: info `NOTE`, note `IMPORTANT`, tip and success `TIP`, warning `WARNING`, error `CAUTION`, custom `NOTE` | `NOTE` info, `IMPORTANT` note, `TIP` tip, `WARNING` warning, `CAUTION` error, and Obsidian's: hint tip; success, check, done success; attention warning; danger, failure, fail, missing, bug, error error; any other word info — in any case; the rest of the marker's line is the first paragraph |
 | `expand`, `nestedExpand` | Obsidian's folded callout, `> [!NOTE]- Title` | `-` or `+` after any word, the rest of the marker's line the title; an expand inside an expand is a `nestedExpand` |
 | `taskList` | `- [x] Done`, `- [ ] Todo` | a bullet list whose every item is so marked, `[X]` too |
-| `backgroundColor` | `==text==` | `==text==` on one line, the text touching both delimiters, bounded outside by whitespace, punctuation, a line edge or a letter of a script written without spaces (Han, Hiragana, Katakana, Thai, Lao, Khmer, Myanmar), in the editor's default highlight `#f8e6a0` |
+| `backgroundColor` | `==text==` | `==text==` on one line, the text touching both delimiters, bounded outside by whitespace, punctuation or a line edge, or touching a Han, Hangul, Hiragana, Katakana, Thai, Lao, Khmer or Myanmar character on either side, in the editor's default highlight `#f8e6a0` |
 | `table` | a pipe table: the first row its header, a cell's blocks on one line, a span kept under its header by empty cells | — |
 | `decisionList` | a bullet list | — |
 | `mention`, `status`, `emoji`, `date` | their text: `@` kept, a mention with none `@` and its id, an emoji its `shortName` without, a date `2026-09-13` in UTC | — |

docs/decisions.md

@@ -151,10 +151,10 @@ renderer is the one the audience's markdown is read in.
 README §Plain markdown's rows come from a survey of GitHub, GitLab, Gitea, Obsidian, Pandoc,
 MkDocs, Docusaurus, Typora, Joplin, Logseq, Bear, Notion, Azure DevOps and Discord, GitHub's
 renderer confirming each shape. Reader panels settled `error` as an error panel, the `==` bounds
-(3 of 3) and a letter of a script written without spaces bounding them, so `は==日本語==で`
-highlights (3 of 3), the external image's two forms (6 of 7), the omission notes and a rule
-opening a list item dropping (3 of 3), and a list's numbering overflowing into bullets (3 of 3,
-5 of 7).
+(3 of 3) and a Han, Hangul, kana, Thai, Lao, Khmer or Myanmar character on either side bounding a
+delimiter, so `は==日本語==で` (3 of 3), `==한국어==에서만` and `iPhone==専用==` (6 of 7) highlight,
+the external image's two forms (6 of 7), the omission notes and a rule opening a list item
+dropping (3 of 3), and a list's numbering overflowing into bullets (3 of 3, 5 of 7).
 Reading takes other tools' spellings, since it reads their output and writes none of them.
 Rejected: `~sub~` and `^sup^` (`~2~` is a strike on GitHub, so `subsup` drops), underline and colour
 spellings, raw HTML (`<details>`, `<mark>`), MkDocs `!!!` and the `:::` admonition family,

src/conformance/property-harness.ts

@@ -23,7 +23,7 @@ export const propertyTimeout = 600000
 const depthIdentifier = fc.createDepthIdentifier()
 const emptyCell: AdfNode = { content: [{ type: 'paragraph' }], type: 'tableCell' }
 const flatCommonMarkShapeWeight = 4
-export const markdownPieces = fc.constantFrom(...'aZ09 \t\n!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~é\xa0🎉', '==', '[!NOTE]', '[x]', 'ab:', 'http://', directivePrefix, `${directivePrefix}a[`, `${directivePrefix}a{`)
+export const markdownPieces = fc.constantFrom(...'aZ09 \t\n!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~é\xa0🎉日ー한', '𠀀', '==', '[!NOTE]', '[x]', 'ab:', 'http://', directivePrefix, `${directivePrefix}a[`, `${directivePrefix}a{`)
 const nestingCommonMarkShapeWeight = 21
 const spelledTypes = new Set(['text', ...Object.keys(blockNodes), ...Object.keys(inlineNodes), ...Object.keys(markAttributes)])
 

src/markdown/emit/plain-reduction.test.ts

@@ -149,6 +149,7 @@ test('spells a highlight as a == pair around the run, whatever its colour', () =
   assert.equal(plain(paragraph(text('=', highlight('#fff')), text(' '), text('a==b', highlight('#fff')))), '==\\=== ==a==b==\n')
   assert.equal(plain(paragraph(text('x'), text('y', highlight('#fff')), text(' z'))), 'xy z\n')
   assert.equal(plain(paragraph(text('この機能は'), text('日本語', highlight('#fff')), text('でのみ'))), 'この機能は==日本語==でのみ\n')
+  assert.equal(plain(paragraph(text('サーバー'), text('停止', highlight('#fff')), text('中 iPhone'), text('専用', highlight('#fff')), text('アプリ 기능은 '), text('한국어', highlight('#fff')), text('에서만'))), 'サーバー==停止==中 iPhone==専用==アプリ 기능은 ==한국어==에서만\n')
   assert.equal(plain(paragraph(text('日==本==語'))), '日\\==本\\==語\n')
 })
 

src/markdown/parse/plain-markdown-to-adf.test.ts

@@ -149,8 +149,11 @@ test('reads a == pair to the editor default highlight, Yellow200 #f8e6a0 in @atl
   assert.deepEqual(read('==`a`==\n'), [paragraph(text('a', code))])
   assert.deepEqual(read('x==y==z ==a == b==, (==c==) _d_==e==\n'), [paragraph(text('x==y==z '), text('a == b', highlight), text(', ('), text('c', highlight), text(') '), text('d', em), text('e', highlight))])
   assert.deepEqual(read('😀==b== ==c==😀 é==d==\n'), [paragraph(text('😀'), text('b', highlight), text(' '), text('c', highlight), text('😀 é==d=='))])
-  assert.deepEqual(read('この機能は==日本語==でのみ、中文==重点==内容、ภาษา==ไทย==ดี a==日本==b\n'), [
-    paragraph(text('この機能は'), text('日本語', highlight), text('でのみ、中文'), text('重点', highlight), text('内容、ภาษา'), text('ไทย', highlight), text('ดี a==日本==b')),
+  assert.deepEqual(read('この機能は==日本語==でのみ、中文==重点==内容、ภาษา==ไทย==ดี 𠀀==𠀁==𠀂 이 기능은 ==한국어==에서만 サーバー==停止==中 このiPhone==専用==アプリ\n'), [
+    paragraph(
+      text('この機能は'), text('日本語', highlight), text('でのみ、中文'), text('重点', highlight), text('内容、ภาษา'), text('ไทย', highlight), text('ดี 𠀀'), text('𠀁', highlight),
+      text('𠀂 이 기능은 '), text('한국어', highlight), text('에서만 サーバー'), text('停止', highlight), text('中 このiPhone'), text('専用', highlight), text('アプリ'),
+    ),
   ])
   assert.deepEqual(read('# ==h==\n\n| ==c== |\n| --- |\n'), [
     node('heading', { level: 1 }, text('h', highlight)),

src/markdown/plain-conventions.ts

@@ -16,6 +16,9 @@ const alertWords: Readonly<Record<string, string>> = {
   warning: 'WARNING',
 }
 
+// ー, ｰ and the kana voicing marks are Script=Common; Script_Extensions would also take Latin combining marks.
+const boundingScript = /^[\u3099-\u309c\u30fc\uff70\uff9e\uff9f\p{Script=Han}\p{Script=Hangul}\p{Script=Hiragana}\p{Script=Katakana}\p{Script=Khmer}\p{Script=Lao}\p{Script=Myanmar}\p{Script=Thai}]$/u
+
 const panelTypesByWord: Readonly<Record<string, string>> = {
   attention: 'warning',
   bug: 'error',
@@ -34,8 +37,6 @@ const panelTypesByWord: Readonly<Record<string, string>> = {
   warning: 'warning',
 }
 
-const unspacedScript = /^[\p{Script=Han}\p{Script=Hiragana}\p{Script=Katakana}\p{Script=Khmer}\p{Script=Lao}\p{Script=Myanmar}\p{Script=Thai}]$/u
-
 export function alertMarker(panelType: unknown): string {
   const word = typeof panelType === 'string' && Object.hasOwn(alertWords, panelType) ? alertWords[panelType] : undefined
   return `[!${word ?? 'NOTE'}]`
@@ -62,11 +63,11 @@ export function highlightFlanking(source: string, index: number): { closes: bool
   const end = index + highlightDelimiter.length
   const before = Array.from(source.slice(Math.max(0, index - 2), index)).at(-1) ?? ''
   const after = Array.from(source.slice(end, end + 2))[0] ?? ''
-  return { closes: flanks(before) && bounds(after), opens: flanks(after) && bounds(before) }
+  return { closes: flanks(before) && bounds(after, before), opens: flanks(after) && bounds(before, after) }
 }
 
-function bounds(character: string): boolean {
-  return !isWordCharacter(character) || unspacedScript.test(character)
+function bounds(outside: string, inside: string): boolean {
+  return !isWordCharacter(outside) || boundingScript.test(outside) || boundingScript.test(inside)
 }
 
 function flanks(character: string): boolean {