fix(export): handle metadata-only notes and HTML image resources

backend/app/export/markdown.py

@@ -178,6 +178,8 @@ class _AstMapper:
                 type="link", node_id=self.next_id(), attributes=attributes,
                 children=self.map_inline(token.get("children", [])),
             )
+        if kind == "inline_html":
+            return DocumentNode(type="text", node_id=self.next_id(), text=token.get("raw", ""), attributes={"raw_html": True})
         if kind == "codespan":
             return DocumentNode(type="codespan", node_id=self.next_id(), text=token.get("raw", ""))
         if kind == "image":

backend/app/export/service.py

@@ -411,12 +411,23 @@ async def preview_resources(request: ExportRequest):
     from app.export.assets import enrich_document
     from app.plot.parser import parse_source
     from app.plot.render import render_svg
-    from app.export.document import Document
+    from app.export.document import Document, DocumentNode
+    from html.parser import HTMLParser
     markdown, _, metadata = await _resolve_source(request.source, True)
     def prepare():
         document = parse_document(markdown)
         images, plots = [], []
+        class HtmlImages(HTMLParser):
+            def handle_starttag(self, tag, attrs):
+                if tag == 'img':
+                    src = dict(attrs).get('src')
+                    if src:
+                        visit(DocumentNode(type='image', node_id='html-image', attributes={'src':src}))
         def visit(node):
+            if node.type == 'html_block' or node.attributes.get('raw_html'):
+                parser = HtmlImages(convert_charrefs=True)
+                parser.feed(node.text)
+                parser.close()
             if node.type == 'image':
                 warnings = enrich_document(Document(node_id='pdf-resources', children=[node]), (metadata or {}).get('file_path'), True, request.options, preserve_alpha=True)
                 raw = node.attributes.get('static_png')

backend/tests/test_pdf_browser.py

@@ -45,3 +45,25 @@ def test_browser_prints_css_without_executing_document_scripts(tmp_path):
         text=subprocess.check_output(['pdftotext',str(pdf),'-']).decode('utf-8')
         assert 'Theme Snapshot' in text
         assert 'EXECUTED' not in text
+
+
+@pytest.mark.parametrize('source', ['<div><IMG SRC="assets/a&amp;b.png"></div>', 'inline <img src="assets/a&amp;b.png"/> image'])
+def test_preview_embeds_html_images(source):
+    from app.config import get_settings
+    from PIL import Image
+    import base64
+    folder=get_settings().vault_path/'notes'/'assets'
+    folder.mkdir(parents=True)
+    Image.new('RGBA',(2,2),(10,20,30,128)).save(folder/'a&b.png')
+    resources=asyncio.run(service.preview_resources(ExportRequest(format='pdf',source={'type':'markdown','markdown':source,'file_path':'notes/test.md'})))
+    image=resources['images'][0]
+    assert image['source']=='assets/a&b.png'
+    assert base64.b64decode(image['data'].split(',')[1]).startswith(b'\x89PNG')
+    assert image['warnings']==[]
+
+
+def test_html_images_keep_path_validation_and_code_is_not_an_image():
+    source='<img src="../../private.png">\n\ninline <img src="https://example.com/a.png">\n\n`<img src="code.png">`\n\n```html\n<img src="fenced.png">\n```'
+    resources=asyncio.run(service.preview_resources(ExportRequest(format='pdf',source={'type':'markdown','markdown':source})))
+    assert [image['source'] for image in resources['images']]==['../../private.png','https://example.com/a.png']
+    assert all(image['data'] is None and image['warnings'] for image in resources['images'])