Leyenda

apply_content.py

@@ -15,6 +15,8 @@ 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*(.*)$', re.IGNORECASE)
+# Accept Leyenda lines with or without markdown bold
+LEYENDA_LINE_RE = re.compile(r'^\s*(?:\*{1,2})?Leyenda:(?:\*{1,2})?\s*(.*)$', re.IGNORECASE)
 
 # Global counters for tables and figures
 table_counter = 0
@@ -83,6 +85,17 @@ 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_leyenda_from_line(line):
+    """Return leyenda text if line is a Leyenda line, otherwise None."""
+    match = LEYENDA_LINE_RE.match(line.strip())
+    if not match:
+        return None
+    return match.group(1).strip()
+
+def is_leyenda_line(line):
+    """Check whether a line starts with Leyenda: (optionally bold)."""
+    return LEYENDA_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
@@ -172,8 +185,11 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
             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...
+            # Add TC field so Anexo figures appear in Table of Figures index
+            # Use \f c to match the TOC field identifier in the template
             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>''')
+                tc_field = f'''<!--[if supportFields]><span style='mso-element:field-begin'></span> TC "Figura {fig_num}. {fig_title}" \\f c \\l 1 <span style='mso-element:field-end'></span><![endif]-->'''
+                html_blocks.append(f'''<a name="{bookmark_id}"></a>{tc_field}<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>''')
 
@@ -204,6 +220,7 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
 
             # Check if next non-empty line has custom Fuente
             custom_source = None
+            fig_leyenda = None
             lookahead = i + 1
             while lookahead < len(lines) and not lines[lookahead].strip():
                 lookahead += 1
@@ -217,6 +234,13 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
                         custom_source += '.'
                     # Skip this line by advancing i past it
                     i = lookahead
+                    # Check for Leyenda after source
+                    leyenda_idx = i + 1
+                    while leyenda_idx < len(lines) and not lines[leyenda_idx].strip():
+                        leyenda_idx += 1
+                    if leyenda_idx < len(lines) and is_leyenda_line(lines[leyenda_idx]):
+                        fig_leyenda = extract_leyenda_from_line(lines[leyenda_idx])
+                        i = leyenda_idx
 
             if custom_source:
                 source_html = md_to_html_para(custom_source)
@@ -224,6 +248,13 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
             else:
                 html_blocks.append(f'''<p class=Piedefoto-tabla style="margin-left:0cm;text-align:center"><span lang=ES>Fuente: Elaboración propia.</span></p>''')
 
+            # Add leyenda if present (same style as Fuente, new line)
+            if fig_leyenda:
+                leyenda_html = md_to_html_para(fig_leyenda)
+                if not fig_leyenda.endswith('.'):
+                    leyenda_html += '.'
+                html_blocks.append(f'''<p class=Piedefoto-tabla style="margin-left:0cm;text-align:center"><span lang=ES>Leyenda: {leyenda_html}</span></p>''')
+
             html_blocks.append('<p class=MsoNormal><span lang=ES><o:p>&nbsp;</o:p></span></p>')
             i += 1
             continue
@@ -249,7 +280,7 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
         if line.startswith('####'):
             text = line.lstrip('#').strip()
             # 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>')
+            html_blocks.append(f'<h4 style="mso-list:none"><b><span lang=ES style="text-transform:none">{text}</span></b></h4>')
             i += 1
             continue
         elif line.startswith('###'):
@@ -314,11 +345,19 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
 
             # Look ahead for source (skip blank lines first)
             source_idx = i
+            table_leyenda = None
             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
+                # Check for Leyenda after source (skip blank lines)
+                leyenda_idx = i
+                while leyenda_idx < len(lines) and not lines[leyenda_idx].strip():
+                    leyenda_idx += 1
+                if leyenda_idx < len(lines) and is_leyenda_line(lines[leyenda_idx]):
+                    table_leyenda = extract_leyenda_from_line(lines[leyenda_idx])
+                    i = leyenda_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)
@@ -334,8 +373,11 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
                 clean_title = "Tabla de datos."
             # 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...
+            # Add TC field so Anexo tables appear in Table of Tables index
+            # Use \f t identifier - template TOC field will be modified to include this
             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>''')
+                tc_field = f'''<!--[if supportFields]><span style='mso-element:field-begin'></span> TC "Tabla {table_num}. {clean_title}" \\f t \\l 1 <span style='mso-element:field-end'></span><![endif]-->'''
+                html_blocks.append(f'''<a name="{bookmark_id}"></a>{tc_field}<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>''')
 
@@ -363,6 +405,14 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
             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>')
+
+            # Add leyenda if present (same style as Fuente, new line)
+            if table_leyenda:
+                leyenda_html = md_to_html_para(table_leyenda)
+                if not table_leyenda.endswith('.'):
+                    leyenda_html += '.'
+                html_blocks.append(f'<p class=Piedefoto-tabla style="margin-left:0cm"><span lang=ES>Leyenda: {leyenda_html}</span></p>')
+
             html_blocks.append('<p class=MsoNormal><span lang=ES><o:p>&nbsp;</o:p></span></p>')
             continue
 
@@ -376,24 +426,63 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
             html_blocks.append(f'<p class=MsoQuote><i><span lang=ES>{md_to_html_para(quote_text)}</span></i></p>')
             continue
 
-        # Bullet list
+        # Bullet list (handle blank lines between items)
         if re.match(r'^[\-\*\+]\s', line):
-            while i < len(lines) and re.match(r'^[\-\*\+]\s', lines[i]):
+            # Collect all bullet items first
+            bullet_items = []
+            while i < len(lines):
+                # Skip blank lines
+                while i < len(lines) and not lines[i].strip():
+                    i += 1
+                # Check if next non-blank line is a bullet item
+                if i < len(lines) and re.match(r'^[\-\*\+]\s', lines[i]):
                     item_text = lines[i][2:].strip()
                     item_text = convert_latex_formulas(item_text)
-                html_blocks.append(f'<p class=MsoListParagraphCxSpMiddle style="margin-left:36pt;text-indent:-18pt"><span lang=ES style="font-family:Symbol">·</span><span lang=ES style="font-size:7pt">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</span><span lang=ES>{md_to_html_para(item_text)}</span></p>')
+                    bullet_items.append(md_to_html_para(item_text))
                     i += 1
+                else:
+                    break
+            # Output with proper First/Middle/Last classes
+            for idx, item in enumerate(bullet_items):
+                if len(bullet_items) == 1:
+                    cls = 'MsoListParagraph'
+                elif idx == 0:
+                    cls = 'MsoListParagraphCxSpFirst'
+                elif idx == len(bullet_items) - 1:
+                    cls = 'MsoListParagraphCxSpLast'
+                else:
+                    cls = 'MsoListParagraphCxSpMiddle'
+                html_blocks.append(f'<p class={cls} style="margin-left:36pt;text-indent:-18pt"><span lang=ES style="font-family:Symbol">·</span><span lang=ES style="font-size:7pt">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</span><span lang=ES>{item}</span></p>')
             continue
 
-        # Numbered list
+        # Numbered list (handle blank lines between items)
         if re.match(r'^\d+\.\s', line):
-            num = 1
-            while i < len(lines) and re.match(r'^\d+\.\s', lines[i]):
+            # Collect all numbered items first
+            numbered_items = []
+            while i < len(lines):
+                # Skip blank lines
+                while i < len(lines) and not lines[i].strip():
+                    i += 1
+                # Check if next non-blank line is a numbered item
+                if i < len(lines) and re.match(r'^\d+\.\s', lines[i]):
                     item_text = re.sub(r'^\d+\.\s*', '', lines[i]).strip()
                     item_text = convert_latex_formulas(item_text)
-                html_blocks.append(f'<p class=MsoListParagraphCxSpMiddle style="margin-left:36pt;text-indent:-18pt"><span lang=ES>{num}.<span style="font-size:7pt">&nbsp;&nbsp;&nbsp;</span>{md_to_html_para(item_text)}</span></p>')
-                num += 1
+                    numbered_items.append(md_to_html_para(item_text))
                     i += 1
+                else:
+                    break
+            # Output with proper First/Middle/Last classes
+            for idx, item in enumerate(numbered_items):
+                num = idx + 1
+                if len(numbered_items) == 1:
+                    cls = 'MsoListParagraph'
+                elif idx == 0:
+                    cls = 'MsoListParagraphCxSpFirst'
+                elif idx == len(numbered_items) - 1:
+                    cls = 'MsoListParagraphCxSpLast'
+                else:
+                    cls = 'MsoListParagraphCxSpMiddle'
+                html_blocks.append(f'<p class={cls} style="margin-left:36pt;text-indent:-18pt"><span lang=ES>{num}.<span style="font-size:7pt">&nbsp;&nbsp;&nbsp;</span>{item}</span></p>')
             continue
 
         # Skip lines that are just table/figure titles (they'll be handled with the table/figure)
@@ -406,6 +495,9 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
         if is_source_line(line):
             i += 1
             continue
+        if is_leyenda_line(line):
+            i += 1
+            continue
 
         # Regular paragraph
         para_lines = [line]
@@ -523,6 +615,17 @@ def main():
 
     print("Reading template...")
     html_content = read_file(TEMPLATE_INPUT)
+
+    # Modify the Table of Tables TOC field to include TC entries with \f t identifier
+    # Original: TOC \h \z \t "Tablas;1" \c "Tabla"
+    # Modified: TOC \f t \h \z \t "Tablas;1" \c "Tabla"
+    # Use regex to handle whitespace/HTML variations in the TOC field
+    html_content = re.sub(
+        r'(TOC\s+)(\\h\s+\\z\s+\\t\s*\n?\s*&quot;Tablas;1&quot;)',
+        r'\1\\f t \2',
+        html_content
+    )
+
     soup = BeautifulSoup(html_content, 'html.parser')
 
     print("Reading docs content...")

docs/00_resumen.md

@@ -6,7 +6,7 @@ Se realizó un estudio comparativo de tres soluciones OCR de código abierto: Ea
 
 Los resultados demuestran que la optimización de hiperparámetros logró mejoras significativas: el mejor trial individual alcanzó un CER de 0.79% (precisión del 99.21%), cumpliendo el objetivo de CER < 2%. Al validar la configuración optimizada sobre el dataset completo de 45 páginas, se obtuvo una mejora del 12.8% en CER (de 8.85% a 7.72%). El hallazgo más relevante fue que el parámetro `textline_orientation` (clasificación de orientación de línea de texto) tiene un impacto crítico en el rendimiento. Adicionalmente, se identificó que el umbral de detección (`text_det_thresh`) presenta una correlación positiva moderada (0.43) con el error, lo que indica que valores más bajos tienden a mejorar el rendimiento.
 
-**Fuente:** [`docs/metrics/metrics_paddle.md`](https://seryus.ddns.net/unir/MastersThesis/src/branch/main/docs/metrics/metrics_paddle.md), [`src/results/correlations/paddle_correlations.csv`](https://seryus.ddns.net/unir/MastersThesis/src/branch/main/src/results/correlations/paddle_correlations.csv).
+**Fuente:** [`metrics_paddle.md`](https://seryus.ddns.net/unir/MastersThesis/src/branch/main/docs/metrics/metrics_paddle.md), [`paddle_correlations.csv`](https://seryus.ddns.net/unir/MastersThesis/src/branch/main/src/results/correlations/paddle_correlations.csv).
 
 Este trabajo demuestra que la optimización de hiperparámetros es una alternativa viable al fine-tuning, especialmente útil cuando se dispone de modelos preentrenados para el idioma objetivo. La infraestructura dockerizada desarrollada permite reproducir los experimentos y facilita la evaluación sistemática de configuraciones OCR.
 
@@ -22,7 +22,7 @@ A comparative study of three open-source OCR solutions was conducted with EasyOC
 
 Results demonstrate that hyperparameter optimization achieved significant improvements. The best individual trial reached a CER of 0.79% (99.21% accuracy), meeting the CER < 2% objective. When validating the optimized configuration on the full 45-page dataset, a 12.8% CER improvement was obtained (from 8.85% to 7.72%). The most relevant finding was that the `textline_orientation` parameter (text line orientation classification) has a critical impact on performance. Additionally, the detection threshold (`text_det_thresh`) showed a moderate positive correlation (0.43) with error, indicating that lower values tend to improve performance.
 
-Sources: [`docs/metrics/metrics_paddle.md`](https://seryus.ddns.net/unir/MastersThesis/src/branch/main/docs/metrics/metrics_paddle.md), [`src/results/correlations/paddle_correlations.csv`](https://seryus.ddns.net/unir/MastersThesis/src/branch/main/src/results/correlations/paddle_correlations.csv).
+Sources: [`metrics_paddle.md`](https://seryus.ddns.net/unir/MastersThesis/src/branch/main/docs/metrics/metrics_paddle.md), [`paddle_correlations.csv`](https://seryus.ddns.net/unir/MastersThesis/src/branch/main/src/results/correlations/paddle_correlations.csv).
 
 This work demonstrates that hyperparameter optimization is a viable alternative to fine-tuning, especially useful when pre-trained models for the target language are available. The dockerized infrastructure developed enables experiment reproducibility and facilitates systematic evaluation of OCR configurations.
 

docs/compliance.md

@@ -0,0 +1,157 @@
+# UNIR Style Compliance Checklist
+
+This document lists the UNIR TFE style requirements to verify before final submission.
+
+## Page Layout
+
+| Requirement | Specification | Check |
+|-------------|---------------|-------|
+| Page size | A4 | ☐ |
+| Left margin | 3.0 cm | ☐ |
+| Right margin | 2.0 cm | ☐ |
+| Top margin | 2.5 cm | ☐ |
+| Bottom margin | 2.5 cm | ☐ |
+| Header | Student name + TFE title | ☐ |
+| Footer | Page number | ☐ |
+
+## Typography
+
+| Element | Specification | Check |
+|---------|---------------|-------|
+| Body text | Calibri 12pt, justified, 1.5 line spacing | ☐ |
+| Título 1 (H1) | Calibri Light 18pt, blue, numbered (1., 2., ...) | ☐ |
+| Título 2 (H2) | Calibri Light 14pt, blue, numbered (1.1, 1.2, ...) | ☐ |
+| Título 3 (H3) | Calibri Light 12pt, numbered (1.1.1, 1.1.2, ...) | ☐ |
+| Título 4 (H4) | Calibri 12pt, bold, unnumbered | ☐ |
+| Footnotes | Calibri 10pt, justified, single spacing | ☐ |
+| Code blocks | Consolas 10pt | ☐ |
+
+## Document Structure
+
+| Section | Requirements | Check |
+|---------|--------------|-------|
+| Portada | Title, Author, Type, Director, Date | ☐ |
+| Resumen | 150-300 words in Spanish + Palabras clave (3-5) | ☐ |
+| Abstract | 150-300 words in English + Keywords (3-5) | ☐ |
+| Índice de contenidos | Auto-generated, new page | ☐ |
+| Índice de figuras | Auto-generated, new page | ☐ |
+| Índice de tablas | Auto-generated, new page | ☐ |
+| Cap. 1 Introducción | 1.1 Motivación, 1.2 Planteamiento, 1.3 Estructura | ☐ |
+| Cap. 2 Contexto | 2.1 Contexto, 2.2 Estado del arte, 2.3 Conclusiones | ☐ |
+| Cap. 3 Objetivos | 3.1 Objetivo general, 3.2 Específicos, 3.3 Metodología | ☐ |
+| Cap. 4 Desarrollo | Structure depends on work type | ☐ |
+| Cap. 5 Conclusiones | 5.1 Conclusiones, 5.2 Trabajo futuro | ☐ |
+| Referencias | APA format, alphabetical order | ☐ |
+| Anexos | Code repository URL, supplementary data | ☐ |
+
+## Tables
+
+| Requirement | Specification | Check |
+|-------------|---------------|-------|
+| Title position | Above the table | ☐ |
+| Title format | **Tabla N.** *Descriptive title in italics.* | ☐ |
+| Numbering | Sequential (1, 2, 3...), Anexo uses A1, A2... | ☐ |
+| Border style | APA: horizontal lines only (top, header bottom, table bottom) | ☐ |
+| Source position | Below the table, centered | ☐ |
+| Source format | Fuente: Author, Year. or Fuente: Elaboración propia. | ☐ |
+| Leyenda (if needed) | Below Fuente, same style (Piedefoto-tabla) | ☐ |
+| In TOT index | All tables appear in Índice de tablas | ☐ |
+
+## Figures
+
+| Requirement | Specification | Check |
+|-------------|---------------|-------|
+| Title position | Above the figure | ☐ |
+| Title format | **Figura N.** *Descriptive title in italics.* | ☐ |
+| Numbering | Sequential (1, 2, 3...), Anexo uses A1, A2... | ☐ |
+| Alignment | Centered | ☐ |
+| Source position | Below the figure, centered | ☐ |
+| Source format | Fuente: Author, Year. or Fuente: Elaboración propia. | ☐ |
+| Leyenda (if needed) | Below Fuente, same style (Piedefoto-tabla) | ☐ |
+| In TOF index | All figures appear in Índice de figuras | ☐ |
+
+## Lists
+
+| Requirement | Specification | Check |
+|-------------|---------------|-------|
+| Bullet lists | Indented 36pt, bullet symbol (·) | ☐ |
+| Numbered lists | Indented 36pt, sequential numbers (1, 2, 3...) | ☐ |
+| Spacing | Proper First/Middle/Last paragraph spacing | ☐ |
+
+## Citations and References
+
+| Requirement | Specification | Check |
+|-------------|---------------|-------|
+| Citation format | APA 7th edition | ☐ |
+| Single author | (Author, Year) or Author (Year) | ☐ |
+| Two authors | (Author1 & Author2, Year) | ☐ |
+| Three+ authors | (Author1 et al., Year) | ☐ |
+| Reference list | Alphabetical by first author surname | ☐ |
+| Hanging indent | 36pt left margin, -36pt text indent | ☐ |
+| DOI/URL | Include when available | ☐ |
+| No Wikipedia | Wikipedia citations not allowed | ☐ |
+| Source variety | Books, journals, conferences (not just URLs) | ☐ |
+
+## SMART Objectives
+
+All objectives must be SMART:
+
+| Criterion | Requirement | Check |
+|-----------|-------------|-------|
+| **S**pecific | Clearly defined, unambiguous | ☐ |
+| **M**easurable | Quantifiable success metric (e.g., CER < 2%) | ☐ |
+| **A**ttainable | Feasible with available resources | ☐ |
+| **R**elevant | Demonstrable impact | ☐ |
+| **T**ime-bound | Achievable within timeframe | ☐ |
+
+## Writing Style
+
+| Requirement | Check |
+|-------------|-------|
+| Each chapter starts with introductory paragraph | ☐ |
+| Each paragraph has at least 3 sentences | ☐ |
+| No two consecutive headings without text between them | ☐ |
+| No superfluous phrases or repetition | ☐ |
+| All concepts defined with pertinent citations | ☐ |
+| Spelling checked (Word corrector) | ☐ |
+| Logical flow between paragraphs | ☐ |
+
+## Final Checks
+
+| Requirement | Check |
+|-------------|-------|
+| All cited references appear in reference list | ☐ |
+| All references in list are cited in text | ☐ |
+| All figures/tables have numbers and titles | ☐ |
+| Update all indices (Ctrl+A, F9 in Word) | ☐ |
+| Page count: 50-90 pages (excl. cover, indices, annexes) | ☐ |
+| Final format: PDF for deposit | ☐ |
+
+## Automated Checks (apply_content.py)
+
+The following are automatically handled by the generation scripts:
+
+- ✓ Table/Figure sequential numbering
+- ✓ Anexo items use A1, A2... prefix
+- ✓ TC fields for Anexo items (appear in indices)
+- ✓ Piedefoto-tabla style for Fuente/Leyenda
+- ✓ MsoCaption style for titles
+- ✓ APA table borders (horizontal only)
+- ✓ MsoBibliography style for references
+- ✓ MsoQuote style for blockquotes
+- ✓ List paragraph classes (First/Middle/Last)
+- ✓ Bold H4 headings (unnumbered)
+
+## Color Palette (UNIR Theme)
+
+| Color | Hex | Usage |
+|-------|-----|-------|
+| Primary Blue | `#0098CD` | Headings, diagram borders |
+| Light Blue BG | `#E6F4F9` | Diagram backgrounds |
+| Dark Gray | `#404040` | Body text |
+| Accent Blue | `#5B9BD5` | Table headers |
+| Light Accent | `#9CC2E5` | Table borders |
+
+---
+
+**Reference:** UNIR TFE Guidelines (`instructions/instrucciones.pdf`, `instructions/plantilla_individual.pdf`)