deliberable_04_01_2026

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

apply_content.py

@@ -4,18 +4,25 @@
 import re
 import os
 import shutil
-from bs4 import BeautifulSoup, NavigableString
-from latex2mathml.converter import convert as latex_to_mathml
-from PIL import Image
-
-BASE_DIR = os.path.dirname(os.path.abspath(__file__))
-TEMPLATE_INPUT = os.path.join(BASE_DIR, 'instructions/plantilla_individual.htm')
-TEMPLATE_OUTPUT = os.path.join(BASE_DIR, 'thesis_output/plantilla_individual.htm')
-DOCS_DIR = os.path.join(BASE_DIR, 'docs')
-
-# Global counters for tables and figures
-table_counter = 0
-figure_counter = 0
+from bs4 import BeautifulSoup, NavigableString
+from latex2mathml.converter import convert as latex_to_mathml
+from PIL import Image
+
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+TEMPLATE_INPUT = os.path.join(BASE_DIR, 'instructions/plantilla_individual.htm')
+TEMPLATE_OUTPUT = os.path.join(BASE_DIR, 'thesis_output/plantilla_individual.htm')
+DOCS_DIR = os.path.join(BASE_DIR, 'docs')
+
+# Accept Fuente/Source lines with or without markdown bold
+SOURCE_LINE_RE = re.compile(r'^\s*(?:\*{1,2})?(Fuente|Source):(?:\*{1,2})?\s*(.*)$', re.IGNORECASE)
+
+# Global counters for tables and figures
+table_counter = 0
+figure_counter = 0
+anexo_table_counter = 0
+anexo_figure_counter = 0
+# Global sequential counter for figure filenames (figura_1.png, figura_2.png, etc.)
+global_figure_index = 0
 
 def read_file(path):
     try:
@@ -41,7 +48,7 @@ def md_to_html_para(text):
     text = re.sub(r'\[([^\]]+)\]\(([^)]+)\)', r'<a href="\2">\1</a>', text)
     return text
 
-def convert_latex_formulas(text):
+def convert_latex_formulas(text):
     """Convert LaTeX formulas to MathML for Word compatibility."""
     # Block formulas $$...$$
     def convert_block(match):
@@ -62,11 +69,22 @@ def convert_latex_formulas(text):
         except:
             return match.group(0)
 
-    text = re.sub(r'\$([^$]+)\$', convert_inline, text)
-    return text
-
-def extract_table_title(lines, current_index):
-    """Look for table title in preceding lines (e.g., **Tabla 1.** *Title*)."""
+    text = re.sub(r'\$([^$]+)\$', convert_inline, text)
+    return text
+
+def extract_source_from_line(line):
+    """Return source text if line is a Fuente/Source line, otherwise None."""
+    match = SOURCE_LINE_RE.match(line.strip())
+    if not match:
+        return None
+    return match.group(2).strip()
+
+def is_source_line(line):
+    """Check whether a line starts with Fuente:/Source: (optionally bold)."""
+    return SOURCE_LINE_RE.match(line.strip()) is not None
+
+def extract_table_title(lines, current_index):
+    """Look for table title in preceding lines (e.g., **Tabla 1.** *Title*)."""
     # Check previous non-empty lines for table title
     for i in range(current_index - 1, max(0, current_index - 5), -1):
         line = lines[i].strip()
@@ -97,9 +115,9 @@ def extract_figure_title_from_mermaid(lines, current_index):
 
     return None
 
-def parse_md_to_html_blocks(md_content):
+def parse_md_to_html_blocks(md_content, is_anexo=False):
     """Convert markdown content to HTML blocks with template styles."""
-    global table_counter, figure_counter
+    global table_counter, figure_counter, anexo_table_counter, anexo_figure_counter, global_figure_index
 
     html_blocks = []
     lines = md_content.split('\n')
@@ -115,7 +133,17 @@ def parse_md_to_html_blocks(md_content):
 
         # Mermaid diagram - convert to figure with actual image
         if line.strip().startswith('```mermaid'):
-            figure_counter += 1
+            # Always increment global index for sequential filenames
+            global_figure_index += 1
+
+            # Use Anexo-specific counter with "A" prefix for display, or global counter
+            if is_anexo:
+                anexo_figure_counter += 1
+                fig_num = f"A{anexo_figure_counter}"  # Display number: A1, A2, A3...
+            else:
+                figure_counter += 1
+                fig_num = str(figure_counter)  # Display number: 1, 2, 3...
+
             mermaid_lines = []
             i += 1
             while i < len(lines) and not lines[i].strip() == '```':
@@ -132,17 +160,22 @@ def parse_md_to_html_blocks(md_content):
             if title_match:
                 fig_title = title_match.group(1).strip()
             else:
-                fig_title = f"Diagrama {figure_counter}"
+                fig_title = f"Diagrama {fig_num}"
 
-            # Check if the generated PNG exists
-            fig_file = f'figures/figura_{figure_counter}.png'
+            # Use global sequential index for filename (figura_1.png, figura_2.png, etc.)
+            fig_file = f'figures/figura_{global_figure_index}.png'
             fig_path = os.path.join(BASE_DIR, 'thesis_output', fig_file)
 
             # Create figure with MsoCaption class and proper Word SEQ field for cross-reference
             # Format: "Figura X." in bold, title in italic (per UNIR guidelines)
             # 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>''')
+            bookmark_id = f"_Ref_Fig{fig_num}"
+            # mso-pagination:keep-with-next ensures caption stays with figure image (correct MSO property)
+            # For Anexo figures, use static text (no SEQ field) to prevent Word from overwriting A1, A2...
+            if is_anexo:
+                html_blocks.append(f'''<a name="{bookmark_id}"></a><p class=MsoCaption style="text-align:center;mso-pagination:keep-with-next"><b><span lang=ES style="font-size:12.0pt;line-height:150%">Figura {fig_num}.</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>''')
+            else:
+                html_blocks.append(f'''<a name="{bookmark_id}"></a><p class=MsoCaption style="text-align:center;mso-pagination:keep-with-next"><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]-->{fig_num}<!--[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):
                 # Read actual image dimensions and scale to fit page width
@@ -162,12 +195,35 @@ def parse_md_to_html_blocks(md_content):
                 w_pt = new_w * 0.75
                 h_pt = new_h * 0.75
 
-                html_blocks.append(f'''<p class=MsoNormal style="text-align:center"><span lang=ES><img width="{new_w}" height="{new_h}" style="width:{w_pt}pt;height:{h_pt}pt;display:block;margin:0 auto" src="{fig_file}" alt="{fig_title}"/></span></p>''')
+                # mso-pagination:keep-with-next ensures image stays with source line
+                html_blocks.append(f'''<p class=MsoNormal style="text-align:center;mso-pagination:keep-with-next"><span lang=ES><img width="{new_w}" height="{new_h}" style="width:{w_pt}pt;height:{h_pt}pt;display:block;margin:0 auto" 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>''')
+                # mso-pagination:keep-with-next ensures placeholder stays with source line
+                html_blocks.append(f'''<p class=MsoNormal style="text-align:center;mso-pagination:keep-with-next;border:1px dashed #999;padding:20px;margin:10px 40px;background:#f9f9f9"><span lang=ES style="color:#666">[Insertar diagrama Mermaid aquí]</span></p>''')
+
+            # Check if next non-empty line has custom Fuente
+            custom_source = None
+            lookahead = i + 1
+            while lookahead < len(lines) and not lines[lookahead].strip():
+                lookahead += 1
+            if lookahead < len(lines):
+                next_line = lines[lookahead].strip()
+                if is_source_line(next_line):
+                    # Extract custom source, removing markdown formatting
+                    custom_source = extract_source_from_line(next_line)
+                    # Ensure it ends with a period
+                    if custom_source and not custom_source.endswith('.'):
+                        custom_source += '.'
+                    # Skip this line by advancing i past it
+                    i = lookahead
+
+            if custom_source:
+                source_html = md_to_html_para(custom_source)
+                html_blocks.append(f'''<p class=Piedefoto-tabla style="margin-left:0cm;text-align:center"><span lang=ES>Fuente: {source_html}</span></p>''')
+            else:
+                html_blocks.append(f'''<p class=Piedefoto-tabla style="margin-left:0cm;text-align:center"><span lang=ES>Fuente: Elaboración propia.</span></p>''')
 
-            html_blocks.append(f'''<p class=Piedefoto-tabla style="margin-left:0cm;text-align:center"><span lang=ES>Fuente: Elaboración propia.</span></p>''')
             html_blocks.append('<p class=MsoNormal><span lang=ES><o:p>&nbsp;</o:p></span></p>')
             i += 1
             continue
@@ -192,17 +248,28 @@ def parse_md_to_html_blocks(md_content):
         # Headers - ## becomes h2, ### becomes h3
         if line.startswith('####'):
             text = line.lstrip('#').strip()
-            html_blocks.append(f'<h4><span lang=ES>{text}</span></h4>')
+            # Apply consistent styling like h2/h3, disable numbering for h4
+            html_blocks.append(f'<h4 style="mso-list:none"><span lang=ES style="text-transform:none">{text}</span></h4>')
             i += 1
             continue
         elif line.startswith('###'):
             text = line.lstrip('#').strip()
-            html_blocks.append(f'<h3 style="mso-list:l22 level3 lfo18"><span lang=ES style="text-transform:none">{text}</span></h3>')
+            # Disable auto-numbering for Anexo content or A.x headings
+            if is_anexo or re.match(r'^A\.\d+', text):
+                # mso-list:none explicitly disables inherited list numbering from template CSS
+                html_blocks.append(f'<h3 style="mso-list:none"><span lang=ES style="text-transform:none">{text}</span></h3>')
+            else:
+                html_blocks.append(f'<h3 style="mso-list:l22 level3 lfo18"><span lang=ES style="text-transform:none">{text}</span></h3>')
             i += 1
             continue
         elif line.startswith('##'):
             text = line.lstrip('#').strip()
-            html_blocks.append(f'<h2 style="mso-list:l22 level2 lfo18"><span lang=ES style="text-transform:none">{text}</span></h2>')
+            # Disable auto-numbering for Anexo content or A.x headings
+            if is_anexo or re.match(r'^A\.\d+', text):
+                # mso-list:none explicitly disables inherited list numbering from template CSS
+                html_blocks.append(f'<h2 style="mso-list:none"><span lang=ES style="text-transform:none">{text}</span></h2>')
+            else:
+                html_blocks.append(f'<h2 style="mso-list:l22 level2 lfo18"><span lang=ES style="text-transform:none">{text}</span></h2>')
             i += 1
             continue
         elif line.startswith('#'):
@@ -212,7 +279,13 @@ def parse_md_to_html_blocks(md_content):
 
         # Table - check for table title pattern first
         if '|' in line and i + 1 < len(lines) and '---' in lines[i + 1]:
-            table_counter += 1
+            # Use Anexo-specific counter with "A" prefix, or global counter
+            if is_anexo:
+                anexo_table_counter += 1
+                table_num = f"A{anexo_table_counter}"
+            else:
+                table_counter += 1
+                table_num = str(table_counter)
 
             # Check if previous line has table title (e.g., **Tabla 1.** *Title*)
             table_title = None
@@ -239,15 +312,18 @@ def parse_md_to_html_blocks(md_content):
                     table_lines.append(lines[i])
                 i += 1
 
-            # Look ahead for source
-            if i < len(lines) and 'Fuente:' in lines[i]:
-                table_source = lines[i].replace('*', '').replace('Fuente:', '').strip()
-                i += 1
+            # Look ahead for source (skip blank lines first)
+            source_idx = i
+            while source_idx < len(lines) and not lines[source_idx].strip():
+                source_idx += 1
+            if source_idx < len(lines) and is_source_line(lines[source_idx]):
+                table_source = extract_source_from_line(lines[source_idx])
+                i = source_idx + 1
 
             # 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)
             # Word TOC looks for text with Caption style - anchor must be outside main caption text
-            bookmark_id = f"_Ref_Tab{table_counter}"
+            bookmark_id = f"_Ref_Tab{table_num}"
             if table_title:
                 # Remove any "Tabla X." or "Tabla AX." pattern from the title
                 clean_title = re.sub(r'^Tabla\s+[A-Z]?\d+\.\s*', '', table_title).strip()
@@ -256,10 +332,14 @@ def parse_md_to_html_blocks(md_content):
                 clean_title = alt_title
             else:
                 clean_title = "Tabla de datos."
-            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>''')
+            # mso-pagination:keep-with-next ensures caption stays with table (correct MSO property)
+            # For Anexo tables, use static text (no SEQ field) to prevent Word from overwriting A1, A2...
+            if is_anexo:
+                html_blocks.append(f'''<a name="{bookmark_id}"></a><p class=MsoCaption style="mso-pagination:keep-with-next"><b><span lang=ES style="font-size:12.0pt;line-height:150%">Tabla {table_num}.</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>''')
+            else:
+                html_blocks.append(f'''<a name="{bookmark_id}"></a><p class=MsoCaption style="mso-pagination:keep-with-next"><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_num}<!--[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)
-            # Wrap in centered div for Word compatibility
             table_html = '<div align="center"><table class=MsoTableGrid border=1 cellspacing=0 cellpadding=0 align="center" style="border-collapse:collapse;margin-left:auto;margin-right:auto;mso-table-style-name:\'Plain Table 1\'">'
             for j, tline in enumerate(table_lines):
                 cells = [c.strip() for c in tline.split('|')[1:-1]]
@@ -278,8 +358,11 @@ def parse_md_to_html_blocks(md_content):
             table_html += '</table></div>'
             html_blocks.append(table_html)
 
-            # Add source with proper template format
-            html_blocks.append(f'<p class=Piedefoto-tabla style="margin-left:0cm"><span lang=ES>Fuente: {table_source}.</span></p>')
+            # Add source with proper template format (convert markdown links to HTML)
+            source_html = md_to_html_para(table_source)
+            if not table_source.endswith('.'):
+                source_html += '.'
+            html_blocks.append(f'<p class=Piedefoto-tabla style="margin-left:0cm"><span lang=ES>Fuente: {source_html}</span></p>')
             html_blocks.append('<p class=MsoNormal><span lang=ES><o:p>&nbsp;</o:p></span></p>')
             continue
 
@@ -320,9 +403,9 @@ def parse_md_to_html_blocks(md_content):
         if line.strip().startswith('**Figura') or line.strip().startswith('*Figura'):
             i += 1
             continue
-        if line.strip().startswith('*Fuente:') or line.strip().startswith('Fuente:'):
-            i += 1
-            continue
+        if is_source_line(line):
+            i += 1
+            continue
 
         # Regular paragraph
         para_lines = [line]
@@ -341,10 +424,10 @@ def parse_md_to_html_blocks(md_content):
 
     return '\n\n'.join(html_blocks)
 
-def extract_section_content(md_content):
+def extract_section_content(md_content, is_anexo=False):
     """Extract content from markdown, skipping the first # header."""
     md_content = re.sub(r'^#\s+[^\n]+\n+', '', md_content, count=1)
-    return parse_md_to_html_blocks(md_content)
+    return parse_md_to_html_blocks(md_content, is_anexo=is_anexo)
 
 def find_section_element(soup, keyword):
     """Find element containing keyword (h1 or special paragraph classes)."""
@@ -396,6 +479,16 @@ def format_references(refs_content):
 
     return refs_html
 
+def split_into_paragraphs(text, lang='ES'):
+    """Split text by double newlines and wrap each paragraph in <p> tags."""
+    paragraphs = []
+    for para in text.split('\n\n'):
+        para = para.strip()
+        if para:
+            formatted = md_to_html_para(para)
+            paragraphs.append(f'<p class=MsoNormal><span lang={lang}>{formatted}</span></p>')
+    return '\n'.join(paragraphs)
+
 def extract_resumen_parts(resumen_content):
     """Extract Spanish resumen and English abstract from 00_resumen.md"""
     parts = resumen_content.split('---')
@@ -408,25 +501,25 @@ def extract_resumen_parts(resumen_content):
     spanish_keywords = ''
     if '**Palabras clave:**' in spanish_part:
         text_part, kw_part = spanish_part.split('**Palabras clave:**')
-        spanish_text = text_part.replace('# Resumen', '').strip()
-        spanish_keywords = kw_part.strip()
+        spanish_text = split_into_paragraphs(text_part.replace('# Resumen', '').strip(), 'ES')
+        spanish_keywords = md_to_html_para(kw_part.strip())
     else:
-        spanish_text = spanish_part.replace('# Resumen', '').strip()
+        spanish_text = split_into_paragraphs(spanish_part.replace('# Resumen', '').strip(), 'ES')
 
     # Extract English content
     english_text = ''
     english_keywords = ''
     if '**Keywords:**' in english_part:
         text_part, kw_part = english_part.split('**Keywords:**')
-        english_text = text_part.replace('# Abstract', '').strip()
-        english_keywords = kw_part.strip()
+        english_text = split_into_paragraphs(text_part.replace('# Abstract', '').strip(), 'EN-US')
+        english_keywords = md_to_html_para(kw_part.strip())
     else:
-        english_text = english_part.replace('# Abstract', '').strip()
+        english_text = split_into_paragraphs(english_part.replace('# Abstract', '').strip(), 'EN-US')
 
     return spanish_text, spanish_keywords, english_text, english_keywords
 
 def main():
-    global table_counter, figure_counter
+    global table_counter, figure_counter, anexo_table_counter, anexo_figure_counter
 
     print("Reading template...")
     html_content = read_file(TEMPLATE_INPUT)
@@ -470,8 +563,8 @@ def main():
             if hasattr(elem, 'decompose'):
                 elem.decompose()
 
-        # Insert new resumen content
-        resumen_html = f'''<p class=MsoNormal><span lang=ES>{spanish_text}</span></p>
+        # Insert new resumen content (spanish_text already contains <p> tags)
+        resumen_html = f'''{spanish_text}
 <p class=MsoNormal><span lang=ES><o:p>&nbsp;</o:p></span></p>
 <p class=MsoNormal><b><span lang=ES>Palabras clave:</span></b><span lang=ES> {spanish_kw}</span></p>
 <p class=MsoNormal><span lang=ES><o:p>&nbsp;</o:p></span></p>'''
@@ -502,8 +595,8 @@ def main():
             if hasattr(elem, 'decompose'):
                 elem.decompose()
 
-        # Insert new abstract content
-        abstract_html = f'''<p class=MsoNormal><span lang=EN-US>{english_text}</span></p>
+        # Insert new abstract content (english_text already contains <p> tags)
+        abstract_html = f'''{english_text}
 <p class=MsoNormal><span lang=EN-US><o:p>&nbsp;</o:p></span></p>
 <p class=MsoNormal><b><span lang=EN-US>Keywords:</span></b><span lang=EN-US> {english_kw}</span></p>
 <p class=MsoNormal><span lang=EN-US><o:p>&nbsp;</o:p></span></p>'''
@@ -578,10 +671,10 @@ def main():
             # Also remove surrounding caption and source
             prev_sib = table.find_previous_sibling()
             next_sib = table.find_next_sibling()
-            if prev_sib and 'Tabla 1. Ejemplo' in prev_sib.get_text():
-                prev_sib.decompose()
-            if next_sib and 'Fuente:' in next_sib.get_text():
-                next_sib.decompose()
+            if prev_sib and 'Tabla 1. Ejemplo' in prev_sib.get_text():
+                prev_sib.decompose()
+            if next_sib and SOURCE_LINE_RE.search(next_sib.get_text().strip()):
+                next_sib.decompose()
             table.decompose()
             print("    ✓ Removed template table example")
             break
@@ -648,14 +741,14 @@ def main():
                     current.extract()
                 current = next_elem
 
-            anexo_content = extract_section_content(docs['anexo'])
+            anexo_content = extract_section_content(docs['anexo'], is_anexo=True)
             anexo_soup = BeautifulSoup(anexo_content, 'html.parser')
             insert_point = anexo_elem
             for new_elem in reversed(list(anexo_soup.children)):
                 insert_point.insert_after(new_elem)
             print(f"    ✓ Replaced content")
 
-    print(f"\nSummary: {table_counter} tables, {figure_counter} figures processed")
+    print(f"\nSummary: {table_counter} tables + {anexo_table_counter} Anexo tables, {figure_counter} figures + {anexo_figure_counter} Anexo figures processed")
 
     print("Saving modified template...")
     output_html = str(soup)