fix(pdf-creator): resolve CJK text garbled in weasyprint code blocks

weasyprint renders <pre> blocks with monospace fonts that lack CJK glyphs,
causing Chinese/Japanese/Korean characters to display as garbled text.

Fix: add _fix_cjk_code_blocks() preprocessor that detects CJK in <pre><code>
and converts to <div class="cjk-code-block"> with inherited body font.
Pure-ASCII code blocks are left untouched.

Also adds code/pre/pre-code CSS rules to both themes (default + warm-terra)
that were previously missing entirely.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.claude-plugin/marketplace.json

@@ -416,7 +416,7 @@
       "description": "Create PDF documents from markdown with Chinese font support. Supports theme system (default for formal docs, warm-terra for training materials) and dual backend (weasyprint or Chrome). Triggers include convert to PDF, generate PDF, markdown to PDF, or printable documents",
       "source": "./",
       "strict": false,
-      "version": "1.2.0",
+      "version": "1.3.0",
       "category": "document-conversion",
       "keywords": [
         "pdf",
@@ -425,6 +425,7 @@
         "chrome",
         "themes",
         "chinese-fonts",
+        "cjk",
         "document-generation",
         "legal",
         "reports",

pdf-creator/SKILL.md

@@ -57,4 +57,6 @@ uv run --with weasyprint scripts/batch_convert.py *.md --output-dir ./pdfs
 
 **weasyprint import error**: Run with `uv run --with weasyprint` or use `--backend chrome` instead.
 
+**CJK text in code blocks garbled (weasyprint)**: The script auto-detects code blocks containing Chinese/Japanese/Korean characters and converts them to styled divs with CJK-capable fonts. If you still see issues, use `--backend chrome` which has native CJK support. Alternatively, convert code blocks to markdown tables before generating the PDF.
+
 **Chrome header/footer appearing**: The script passes `--no-pdf-header-footer`. If it still appears, your Chrome version may not support this flag — update Chrome.

pdf-creator/scripts/md_to_pdf.py

@@ -125,6 +125,35 @@ def _ensure_list_spacing(text: str) -> str:
     return "\n".join(result)
 
 
+_CJK_RANGE = re.compile(
+    r"[\u4e00-\u9fff\u3400-\u4dbf\uf900-\ufaff"
+    r"\U00020000-\U0002a6df\U0002a700-\U0002ebef"
+    r"\u3000-\u303f\uff00-\uffef]"
+)
+
+
+def _fix_cjk_code_blocks(html: str) -> str:
+    """Replace <pre><code> blocks containing CJK with styled divs.
+
+    weasyprint renders <pre> blocks using monospace fonts that lack CJK glyphs,
+    causing garbled output. This converts CJK-heavy code blocks to styled divs
+    that use the document's CJK font stack instead.
+    """
+
+    def _replace_if_cjk(match: re.Match) -> str:
+        content = match.group(1)
+        if _CJK_RANGE.search(content):
+            return f'<div class="cjk-code-block">{content}</div>'
+        return match.group(0)
+
+    return re.sub(
+        r"<pre><code(?:\s[^>]*)?>(.+?)</code></pre>",
+        _replace_if_cjk,
+        html,
+        flags=re.DOTALL,
+    )
+
+
 def _md_to_html(md_file: str) -> str:
     """Convert markdown to HTML using pandoc with list spacing preprocessing."""
     if not shutil.which("pandoc"):
@@ -147,7 +176,9 @@ def _md_to_html(md_file: str) -> str:
         print(f"Error: pandoc failed: {result.stderr}", file=sys.stderr)
         sys.exit(1)
 
-    return result.stdout
+    html = result.stdout
+    html = _fix_cjk_code_blocks(html)
+    return html
 
 
 def _build_full_html(html_content: str, css: str, title: str) -> str:

pdf-creator/themes/default.css

@@ -86,3 +86,46 @@ hr {
     border-top: 1px solid #ccc;
     margin: 1.5em 0;
 }
+
+code {
+    font-family: 'Menlo', 'PingFang SC', 'Heiti SC', 'Noto Sans CJK SC', monospace;
+    background: #f5f5f5;
+    padding: 1px 4px;
+    border-radius: 3px;
+    font-size: 10pt;
+}
+
+pre {
+    background: #f5f5f5;
+    border: 1px solid #ddd;
+    border-radius: 4px;
+    padding: 12px 16px;
+    margin: 1em 0;
+    overflow-wrap: break-word;
+    white-space: pre-wrap;
+    word-break: break-all;
+}
+
+pre code {
+    font-family: 'Menlo', 'PingFang SC', 'Heiti SC', 'Noto Sans CJK SC', monospace;
+    background: none;
+    padding: 0;
+    border-radius: 0;
+    font-size: 9pt;
+    line-height: 1.6;
+}
+
+/* CJK code blocks converted to styled divs by preprocessor.
+   Uses inherit to reuse body's CJK font (weasyprint may not find PingFang SC). */
+.cjk-code-block {
+    font-family: inherit;
+    background: #f5f5f5;
+    border: 1px solid #ddd;
+    border-radius: 4px;
+    padding: 12px 16px;
+    margin: 1em 0;
+    font-size: 10pt;
+    line-height: 1.8;
+    white-space: pre-wrap;
+    word-break: break-all;
+}

pdf-creator/themes/warm-terra.css

@@ -110,12 +110,48 @@ header, .date {
 }
 
 code {
+    font-family: 'Menlo', 'PingFang SC', 'Microsoft YaHei', 'Noto Sans CJK SC', monospace;
     background: #faf5f0;
     padding: 1px 4px;
     border-radius: 3px;
     font-size: 12px;
 }
 
+pre {
+    background: #faf5f0;
+    border: 1px solid #e2d6c8;
+    border-radius: 4px;
+    padding: 12px 16px;
+    margin: 10px 0;
+    overflow-wrap: break-word;
+    white-space: pre-wrap;
+    word-break: break-all;
+}
+
+pre code {
+    font-family: 'Menlo', 'PingFang SC', 'Microsoft YaHei', 'Noto Sans CJK SC', monospace;
+    background: none;
+    padding: 0;
+    border-radius: 0;
+    font-size: 11px;
+    line-height: 1.6;
+}
+
+/* CJK code blocks converted to styled divs by preprocessor.
+   Uses inherit to reuse body's CJK font (weasyprint may not resolve all font names). */
+.cjk-code-block {
+    font-family: inherit;
+    background: #faf5f0;
+    border: 1px solid #e2d6c8;
+    border-radius: 4px;
+    padding: 12px 16px;
+    margin: 10px 0;
+    font-size: 12px;
+    line-height: 1.7;
+    white-space: pre-wrap;
+    word-break: break-all;
+}
+
 strong {
     color: #1f1b17;
 }