test

apply_content.py

@@ -92,9 +92,13 @@ def parse_md_to_html_blocks(md_content):
                 mermaid_lines.append(lines[i])
                 i += 1
 
-            # Try to extract title from mermaid content
+            # Try to extract title from mermaid content (YAML format: title: "...")
             mermaid_content = '\n'.join(mermaid_lines)
-            title_match = re.search(r'title\s+["\']?([^"\'"\n]+)["\']?', mermaid_content)
+            # Match YAML format: title: "Title" or title: 'Title'
+            title_match = re.search(r'title:\s*["\']([^"\']+)["\']', mermaid_content)
+            if not title_match:
+                # Fallback to non-YAML format: title "Title"
+                title_match = re.search(r'title\s+["\']?([^"\'"\n]+)["\']?', mermaid_content)
             if title_match:
                 fig_title = title_match.group(1).strip()
             else:
@@ -106,12 +110,13 @@ def parse_md_to_html_blocks(md_content):
 
             # Create figure with MsoCaption class and proper Word SEQ field for cross-reference
             # Format: "Figura X." in bold, title in italic (per UNIR guidelines)
-            bookmark_id = f"_TocFigura{figure_counter}"
-            html_blocks.append(f'''<p class=MsoCaption style="text-align:center"><a name="{bookmark_id}"><b><span lang=ES style="font-size:12.0pt;line-height:150%">Figura </span></b></a><!--[if supportFields]><span style='mso-element:field-begin'></span> SEQ Figura \\* ARABIC <span style='mso-element:field-separator'></span><![endif]--><b><span lang=ES style="font-size:12.0pt;line-height:150%">{figure_counter}</span></b><!--[if supportFields]><span style='mso-element:field-end'></span><![endif]--><b><span lang=ES style="font-size:12.0pt;line-height:150%">.</span></b><span lang=ES style="font-size:12.0pt;line-height:150%"> </span><i><span lang=ES style="font-size:12.0pt;line-height:150%;font-weight:normal">{fig_title}</span></i></p>''')
+            # Word TOC looks for text with Caption style - anchor must be outside main caption text
+            bookmark_id = f"_Ref_Fig{figure_counter}"
+            html_blocks.append(f'''<a name="{bookmark_id}"></a><p class=MsoCaption style="text-align:center"><b><span lang=ES style="font-size:12.0pt;line-height:150%">Figura <!--[if supportFields]><span style='mso-element:field-begin'></span> SEQ Figura \\* ARABIC <span style='mso-element:field-separator'></span><![endif]-->{figure_counter}<!--[if supportFields]><span style='mso-element:field-end'></span><![endif]-->.</span></b><span lang=ES style="font-size:12.0pt;line-height:150%"> </span><i><span lang=ES style="font-size:12.0pt;line-height:150%">{fig_title}</span></i></p>''')
 
             if os.path.exists(fig_path):
-                # Use actual image with proper Word-compatible format (max 350px width, 400px height to fit page with caption)
-                html_blocks.append(f'''<p class=MsoNormal style="text-align:center"><span lang=ES><img style="max-width:350px;max-height:400px;width:auto;height:auto" src="{fig_file}" alt="{fig_title}"/></span></p>''')
+                # Use Word-compatible width in cm (A4 text area is ~16cm wide, use ~12cm max)
+                html_blocks.append(f'''<p class=MsoNormal style="text-align:center"><span lang=ES><img style="width:12cm;max-width:100%" src="{fig_file}" alt="{fig_title}"/></span></p>''')
             else:
                 # Fallback to placeholder
                 html_blocks.append(f'''<p class=MsoNormal style="text-align:center;border:1px dashed #999;padding:20px;margin:10px 40px;background:#f9f9f9"><span lang=ES style="color:#666">[Insertar diagrama Mermaid aquí]</span></p>''')
@@ -189,12 +194,13 @@ def parse_md_to_html_blocks(md_content):
 
             # Add table title with MsoCaption class and proper Word SEQ field for cross-reference
             # Format: "Tabla X." in bold, title in italic (per UNIR guidelines)
-            bookmark_id = f"_TocTabla{table_counter}"
+            # Word TOC looks for text with Caption style - anchor must be outside main caption text
+            bookmark_id = f"_Ref_Tab{table_counter}"
             if table_title:
                 clean_title = table_title.replace(f"Tabla {table_counter}.", "").strip()
             else:
                 clean_title = "Tabla de datos."
-            html_blocks.append(f'''<p class=MsoCaption><a name="{bookmark_id}"><b><span lang=ES style="font-size:12.0pt;line-height:150%">Tabla </span></b></a><!--[if supportFields]><span style='mso-element:field-begin'></span> SEQ Tabla \\* ARABIC <span style='mso-element:field-separator'></span><![endif]--><b><span lang=ES style="font-size:12.0pt;line-height:150%">{table_counter}</span></b><!--[if supportFields]><span style='mso-element:field-end'></span><![endif]--><b><span lang=ES style="font-size:12.0pt;line-height:150%">.</span></b><span lang=ES style="font-size:12.0pt;line-height:150%"> </span><i><span lang=ES style="font-size:12.0pt;line-height:150%;font-weight:normal">{clean_title}</span></i></p>''')
+            html_blocks.append(f'''<a name="{bookmark_id}"></a><p class=MsoCaption><b><span lang=ES style="font-size:12.0pt;line-height:150%">Tabla <!--[if supportFields]><span style='mso-element:field-begin'></span> SEQ Tabla \\* ARABIC <span style='mso-element:field-separator'></span><![endif]-->{table_counter}<!--[if supportFields]><span style='mso-element:field-end'></span><![endif]-->.</span></b><span lang=ES style="font-size:12.0pt;line-height:150%"> </span><i><span lang=ES style="font-size:12.0pt;line-height:150%">{clean_title}</span></i></p>''')
 
             # Build table HTML with APA style (horizontal lines only, no vertical)
             table_html = '<table class=MsoTableGrid border=0 cellspacing=0 cellpadding=0 style="border-collapse:collapse;border:none">'

generate_mermaid_figures.py

@@ -64,10 +64,10 @@ def convert_to_png(diagrams):
         with open(temp_file, 'w', encoding='utf-8') as f:
             f.write(diagram['code'])
 
-        # Convert using mmdc with higher resolution for better readability
+        # Convert using mmdc with moderate size for page fit
         try:
             result = subprocess.run(
-                [MMDC, '-i', temp_file, '-o', output_file, '-b', 'white', '-w', '1600', '-s', '2'],
+                [MMDC, '-i', temp_file, '-o', output_file, '-b', 'white', '-w', '800', '-s', '1.5'],
                 capture_output=True,
                 text=True,
                 timeout=60