Merge branch 'main' of https://github.com/JimLiu/baoyu-skills

skills/baoyu-post-to-x/scripts/md-to-html.test.ts

@@ -98,3 +98,68 @@ test('parseMarkdown resolves encoded spaces and literal percent image paths', as
   assert.equal(result.contentImages[0]?.localPath, path.join(root, 'Pasted image.png'));
   assert.equal(result.contentImages[1]?.localPath, path.join(root, '100%.png'));
 });
+
+test('parseMarkdown renders CJK-adjacent bold and italics (no literal asterisks)', async (t) => {
+  const root = await makeTempDir('x-md-to-html-cjk-bold-');
+  t.after(() => fs.rm(root, { recursive: true, force: true }));
+
+  const markdownPath = path.join(root, 'post.md');
+  const tempDir = path.join(root, 'tmp');
+  await fs.mkdir(tempDir, { recursive: true });
+  await fs.writeFile(
+    markdownPath,
+    [
+      '# 标题',
+      '',
+      '分工在变细。**国际大厂卷基础设施，中文项目卷场景落地。**这其实是生态成熟的表现。',
+      '',
+      '半角场景 **Top 10 里平均有 8 个** 项目。',
+      '',
+      '斜体 *数据来源 GitHub* 收尾。',
+      '',
+      '参考 **[docs][d]** 了解更多。',
+      '',
+      '[d]: https://example.com',
+    ].join('\n'),
+  );
+
+  const result = await parseMarkdown(markdownPath, { tempDir });
+
+  // Bold directly adjacent to CJK (closing ** followed by CJK) must render.
+  assert.match(result.html, /<strong>国际大厂卷基础设施，中文项目卷场景落地。<\/strong>/);
+  assert.match(result.html, /<strong>Top 10 里平均有 8 个<\/strong>/);
+  // Italics.
+  assert.match(result.html, /<em>数据来源 GitHub<\/em>/);
+  // Reference-style links inside emphasis must render as links, not plain text.
+  assert.match(result.html, /<strong><a href="https:\/\/example\.com" rel="noopener noreferrer nofollow">docs<\/a><\/strong>/);
+  // No literal emphasis delimiters should leak into the output.
+  assert.doesNotMatch(result.html, /\*\*/);
+  assert.doesNotMatch(result.html, /(?<!\*)\*(?!\*)[^*\n]+\*(?!\*)/);
+});
+
+test('parseMarkdown does not decode author-written literal HTML entities into tags', async (t) => {
+  const root = await makeTempDir('x-md-to-html-entities-');
+  t.after(() => fs.rm(root, { recursive: true, force: true }));
+
+  const markdownPath = path.join(root, 'post.md');
+  const tempDir = path.join(root, 'tmp');
+  await fs.mkdir(tempDir, { recursive: true });
+  await fs.writeFile(
+    markdownPath,
+    [
+      '# 标题',
+      '',
+      '正文中写 &#x3C;b&#x3E;literal&#x3C;/b&#x3E; 想显示字面标签。**加粗**收尾。',
+      '',
+      '代码里写 `&#x3C;b&#x3E;` 同样保留。',
+    ].join('\n'),
+  );
+
+  const result = await parseMarkdown(markdownPath, { tempDir });
+
+  // CJK-adjacent bold still renders.
+  assert.match(result.html, /<strong>加粗<\/strong>/);
+  // Author-written literal entities must NOT be decoded into real tags.
+  assert.doesNotMatch(result.html, /<b>literal<\/b>/);
+  assert.match(result.html, /&lt;b&gt;literal&lt;\/b&gt;/);
+});

skills/baoyu-post-to-x/scripts/md-to-html.ts

@@ -136,6 +136,21 @@ function highlightCode(code: string, lang: string): string {
   }
 }
 
+// Normalize CJK-adjacent emphasis so `marked` renders it correctly.
+//
+// `marked`'s emphasis tokenizer treats a closing `**`/`*` directly followed by a
+// CJK character as not right-flanking, so it leaves the delimiters literal
+// (e.g. `**加粗**这` renders as plain text with the asterisks intact). We round-trip
+// the markdown through `remark-cjk-friendly`, whose stringify serializes the
+// boundary character as an HTML entity (`这`); the entity is treated as
+// punctuation by `marked`'s flanking rules, so emphasis parses as expected.
+//
+// We deliberately do NOT decode the entities afterward. They are valid HTML
+// character references that render correctly when the article HTML is pasted into
+// the X editor, and `marked` only emits them for characters outside the emphasis
+// span (the boundary char), never inside it. A blanket decode of the rendered
+// HTML would risk turning author-written literal entities (e.g. `<b>`
+// meant to display `<b>` as text) into real tags, so we leave them intact.
 function preprocessCjkMarkdown(markdown: string): string {
   try {
     const processor = unified()
@@ -143,8 +158,7 @@ function preprocessCjkMarkdown(markdown: string): string {
       .use(remarkCjkFriendly)
       .use(remarkStringify);
 
-    const result = String(processor.processSync(markdown));
-    return result.replace(/&#x([0-9A-Fa-f]+);/g, (_, hex: string) => String.fromCodePoint(parseInt(hex, 16)));
+    return String(processor.processSync(markdown));
   } catch {
     return markdown;
   }