#!/usr/bin/env python3
"""Replace template content with thesis content from docs/ folder using BeautifulSoup."""
import re
import os
from bs4 import BeautifulSoup, NavigableString
BASE_DIR = '/Users/sergio/Desktop/MastersThesis'
TEMPLATE = 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
def read_file(path):
try:
with open(path, 'r', encoding='utf-8') as f:
return f.read()
except UnicodeDecodeError:
with open(path, 'r', encoding='latin-1') as f:
return f.read()
def write_file(path, content):
with open(path, 'w', encoding='utf-8') as f:
f.write(content)
def md_to_html_para(text):
"""Convert markdown inline formatting to HTML."""
# Bold
text = re.sub(r'\*\*([^*]+)\*\*', r'\1', text)
# Italic
text = re.sub(r'\*([^*]+)\*', r'\1', text)
# Inline code
text = re.sub(r'`([^`]+)`', r'\1', text)
return text
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()
if line.startswith('**Tabla') or line.startswith('*Tabla'):
return line
if line and not line.startswith('|'):
break
return None
def extract_figure_title_from_mermaid(lines, current_index):
"""Extract title from mermaid diagram or preceding text."""
# Look for title in mermaid content
for i in range(current_index + 1, min(len(lines), current_index + 20)):
line = lines[i].strip()
if line.startswith('```'):
break
if 'title' in line.lower():
# Extract title from: title "Some Title"
match = re.search(r'title\s+["\']([^"\']+)["\']', line)
if match:
return match.group(1)
# Check preceding lines for figure reference
for i in range(current_index - 1, max(0, current_index - 3), -1):
line = lines[i].strip()
if line.startswith('**Figura') or 'Figura' in line:
return line
return None
def parse_md_to_html_blocks(md_content):
"""Convert markdown content to HTML blocks with template styles."""
global table_counter, figure_counter
html_blocks = []
lines = md_content.split('\n')
i = 0
while i < len(lines):
line = lines[i]
# Skip empty lines
if not line.strip():
i += 1
continue
# Mermaid diagram - convert to figure with actual image
if line.strip().startswith('```mermaid'):
figure_counter += 1
mermaid_lines = []
i += 1
while i < len(lines) and not lines[i].strip() == '```':
mermaid_lines.append(lines[i])
i += 1
# Try to extract title from mermaid content
mermaid_content = '\n'.join(mermaid_lines)
title_match = re.search(r'title\s+["\']?([^"\'"\n]+)["\']?', mermaid_content)
if title_match:
fig_title = title_match.group(1).strip()
else:
fig_title = f"Diagrama {figure_counter}"
# Check if the generated PNG exists
fig_file = f'figures/figura_{figure_counter}.png'
fig_path = os.path.join(BASE_DIR, 'thesis_output', fig_file)
# Create figure with MsoCaption class and bookmark for Word cross-reference
bookmark_id = f"_TocFigura{figure_counter}"
html_blocks.append(f'''Figura {figure_counter}. {fig_title}
''')
if os.path.exists(fig_path):
# Use actual image with proper Word-compatible format
html_blocks.append(f'''
''')
else:
# Fallback to placeholder
html_blocks.append(f'''[Insertar diagrama Mermaid aquí]
''')
html_blocks.append(f'''Fuente: Elaboración propia.
''')
html_blocks.append('
')
i += 1
continue
# Code block (non-mermaid)
if line.strip().startswith('```'):
code_lang = line.strip()[3:]
code_lines = []
i += 1
while i < len(lines) and not lines[i].strip().startswith('```'):
code_lines.append(lines[i])
i += 1
code = '\n'.join(code_lines)
# Escape HTML entities in code
code = code.replace('&', '&').replace('<', '<').replace('>', '>')
html_blocks.append(f'{code}
')
i += 1
continue
# Headers - ## becomes h2, ### becomes h3
if line.startswith('####'):
text = line.lstrip('#').strip()
html_blocks.append(f'{text}
')
i += 1
continue
elif line.startswith('###'):
text = line.lstrip('#').strip()
html_blocks.append(f'{text}
')
i += 1
continue
elif line.startswith('##'):
text = line.lstrip('#').strip()
html_blocks.append(f'{text}
')
i += 1
continue
elif line.startswith('#'):
# Skip h1 - we keep the original
i += 1
continue
# Table - check for table title pattern first
if '|' in line and i + 1 < len(lines) and '---' in lines[i + 1]:
table_counter += 1
# Check if previous line has table title (e.g., **Tabla 1.** *Title*)
table_title = None
table_source = "Elaboración propia"
# Look back for table title
for j in range(i - 1, max(0, i - 5), -1):
prev_line = lines[j].strip()
if prev_line.startswith('**Tabla') or prev_line.startswith('*Tabla'):
# Extract title text
table_title = re.sub(r'\*+', '', prev_line).strip()
break
elif prev_line and not prev_line.startswith('|'):
break
# Parse table
table_lines = []
while i < len(lines) and '|' in lines[i]:
if '---' not in lines[i]:
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
# Add table title with MsoCaption class and bookmark for Word cross-reference
bookmark_id = f"_TocTabla{table_counter}"
if table_title:
clean_title = table_title.replace(f"Tabla {table_counter}.", "").strip()
html_blocks.append(f'Tabla {table_counter}. {clean_title}
')
else:
html_blocks.append(f'Tabla {table_counter}. Tabla de datos.
')
# Build table HTML
table_html = ''
for j, tline in enumerate(table_lines):
cells = [c.strip() for c in tline.split('|')[1:-1]]
table_html += ''
for cell in cells:
if j == 0:
# Header row
table_html += f'{md_to_html_para(cell)} | '
else:
table_html += f'{md_to_html_para(cell)} | '
table_html += '
'
table_html += '
'
html_blocks.append(table_html)
# Add source with proper template format
html_blocks.append(f'Fuente: {table_source}.
')
html_blocks.append('
')
continue
# Blockquote
if line.startswith('>'):
quote_text = line[1:].strip()
i += 1
while i < len(lines) and lines[i].startswith('>'):
quote_text += ' ' + lines[i][1:].strip()
i += 1
html_blocks.append(f'{md_to_html_para(quote_text)}
')
continue
# Bullet list
if re.match(r'^[\-\*\+]\s', line):
while i < len(lines) and re.match(r'^[\-\*\+]\s', lines[i]):
item_text = lines[i][2:].strip()
html_blocks.append(f'· {md_to_html_para(item_text)}
')
i += 1
continue
# Numbered list
if re.match(r'^\d+\.\s', line):
num = 1
while i < len(lines) and re.match(r'^\d+\.\s', lines[i]):
item_text = re.sub(r'^\d+\.\s*', '', lines[i]).strip()
html_blocks.append(f'{num}. {md_to_html_para(item_text)}
')
num += 1
i += 1
continue
# Skip lines that are just table/figure titles (they'll be handled with the table/figure)
if line.strip().startswith('**Tabla') or line.strip().startswith('*Tabla'):
i += 1
continue
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
# Regular paragraph
para_lines = [line]
i += 1
while i < len(lines) and lines[i].strip() and not lines[i].startswith('#') and not lines[i].startswith('```') and not lines[i].startswith('>') and not re.match(r'^[\-\*\+]\s', lines[i]) and not re.match(r'^\d+\.\s', lines[i]) and '|' not in lines[i]:
para_lines.append(lines[i])
i += 1
para_text = ' '.join(para_lines)
html_blocks.append(f'{md_to_html_para(para_text)}
')
return '\n\n'.join(html_blocks)
def extract_section_content(md_content):
"""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)
def find_section_element(soup, keyword):
"""Find element containing keyword (h1 or special paragraph classes)."""
# First try h1
for h1 in soup.find_all('h1'):
text = h1.get_text()
if keyword.lower() in text.lower():
return h1
# Try special paragraph classes for unnumbered sections
for p in soup.find_all('p', class_=['Ttulo1sinnumerar', 'Anexo', 'MsoNormal']):
text = p.get_text()
if keyword.lower() in text.lower():
classes = p.get('class', [])
if 'Ttulo1sinnumerar' in classes or 'Anexo' in classes:
return p
if re.match(r'^\d+\.?\s', text.strip()):
return p
return None
def remove_elements_between(start_elem, end_elem):
"""Remove all elements between start and end (exclusive)."""
current = start_elem.next_sibling
elements_to_remove = []
while current and current != end_elem:
elements_to_remove.append(current)
current = current.next_sibling
for elem in elements_to_remove:
if hasattr(elem, 'decompose'):
elem.decompose()
elif isinstance(elem, NavigableString):
elem.extract()
def format_references(refs_content):
"""Format references with proper MsoBibliography style."""
refs_content = refs_content.replace('# Referencias bibliográficas {.unnumbered}', '').strip()
refs_html = ''
for line in refs_content.split('\n\n'):
line = line.strip()
if not line:
continue
# Apply markdown formatting
formatted = md_to_html_para(line)
# Use MsoBibliography style with hanging indent (36pt indent, -36pt text-indent)
refs_html += f'''{formatted}
\n'''
return refs_html
def extract_resumen_parts(resumen_content):
"""Extract Spanish resumen and English abstract from 00_resumen.md"""
parts = resumen_content.split('---')
spanish_part = parts[0] if len(parts) > 0 else ''
english_part = parts[1] if len(parts) > 1 else ''
# Extract Spanish content
spanish_text = ''
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()
else:
spanish_text = spanish_part.replace('# Resumen', '').strip()
# 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()
else:
english_text = english_part.replace('# Abstract', '').strip()
return spanish_text, spanish_keywords, english_text, english_keywords
def main():
global table_counter, figure_counter
print("Reading template...")
html_content = read_file(TEMPLATE)
soup = BeautifulSoup(html_content, 'html.parser')
print("Reading docs content...")
docs = {
'resumen': read_file(os.path.join(DOCS_DIR, '00_resumen.md')),
'intro': read_file(os.path.join(DOCS_DIR, '01_introduccion.md')),
'contexto': read_file(os.path.join(DOCS_DIR, '02_contexto_estado_arte.md')),
'objetivos': read_file(os.path.join(DOCS_DIR, '03_objetivos_metodologia.md')),
'desarrollo': read_file(os.path.join(DOCS_DIR, '04_desarrollo_especifico.md')),
'conclusiones': read_file(os.path.join(DOCS_DIR, '05_conclusiones_trabajo_futuro.md')),
'referencias': read_file(os.path.join(DOCS_DIR, '06_referencias_bibliograficas.md')),
'anexo': read_file(os.path.join(DOCS_DIR, '07_anexo_a.md')),
}
# Extract resumen and abstract
spanish_text, spanish_kw, english_text, english_kw = extract_resumen_parts(docs['resumen'])
# Replace title
print("Replacing title...")
for elem in soup.find_all(string=re.compile(r'Título del TFE', re.IGNORECASE)):
elem.replace_with(elem.replace('Título del TFE', 'Optimización de Hiperparámetros OCR con Ray Tune para Documentos Académicos en Español'))
# Replace Resumen section
print("Replacing Resumen...")
resumen_title = soup.find('p', class_='Ttulondices', string=re.compile(r'Resumen'))
if resumen_title:
# Find and replace content after Resumen title until Abstract
current = resumen_title.find_next_sibling()
elements_to_remove = []
while current:
text = current.get_text() if hasattr(current, 'get_text') else str(current)
if 'Abstract' in text and current.name == 'p' and 'Ttulondices' in str(current.get('class', [])):
break
elements_to_remove.append(current)
current = current.find_next_sibling()
for elem in elements_to_remove:
if hasattr(elem, 'decompose'):
elem.decompose()
# Insert new resumen content
resumen_html = f'''{spanish_text}
Palabras clave: {spanish_kw}
'''
resumen_soup = BeautifulSoup(resumen_html, 'html.parser')
insert_point = resumen_title
for new_elem in reversed(list(resumen_soup.children)):
insert_point.insert_after(new_elem)
print(" ✓ Replaced Resumen")
# Replace Abstract section
print("Replacing Abstract...")
abstract_title = soup.find('p', class_='Ttulondices', string=re.compile(r'Abstract'))
if abstract_title:
# Find and replace content after Abstract title until next major section
current = abstract_title.find_next_sibling()
elements_to_remove = []
while current:
# Stop at page break or next title
if current.name == 'span' and 'page-break' in str(current):
break
text = current.get_text() if hasattr(current, 'get_text') else str(current)
if current.name == 'p' and ('Ttulondices' in str(current.get('class', [])) or 'MsoToc' in str(current.get('class', []))):
break
elements_to_remove.append(current)
current = current.find_next_sibling()
for elem in elements_to_remove:
if hasattr(elem, 'decompose'):
elem.decompose()
# Insert new abstract content
abstract_html = f'''{english_text}
Keywords: {english_kw}
'''
abstract_soup = BeautifulSoup(abstract_html, 'html.parser')
insert_point = abstract_title
for new_elem in reversed(list(abstract_soup.children)):
insert_point.insert_after(new_elem)
print(" ✓ Replaced Abstract")
# Remove "Importante" callout boxes (template instructions)
print("Removing template instructions...")
for div in soup.find_all('div'):
text = div.get_text()
if 'Importante:' in text and 'extensión mínima' in text:
div.decompose()
print(" ✓ Removed 'Importante' box")
# Remove "Ejemplo de nota al pie" footnote
for elem in soup.find_all(string=re.compile(r'Ejemplo de nota al pie')):
parent = elem.parent
if parent:
# Find the footnote container and remove it
while parent and parent.name != 'p':
parent = parent.parent
if parent:
parent.decompose()
print(" ✓ Removed footnote example")
# Clear old figure/table index entries (they need to be regenerated in Word)
print("Clearing old index entries...")
# Remove ALL content from MsoTof paragraphs that reference template examples
# The indices will be regenerated when user opens in Word and presses Ctrl+A, F9
for p in soup.find_all('p', class_='MsoTof'):
text = p.get_text()
# Check for figure index entries with template examples
if 'Figura' in text and 'Ejemplo' in text:
# Remove all tags (the actual index entry links)
for a in p.find_all('a'):
a.decompose()
# Also remove any remaining text content that shows the example
for span in p.find_all('span', style=lambda x: x and 'mso-no-proof' in str(x)):
if 'Ejemplo' in span.get_text():
span.decompose()
print(" ✓ Cleared figure index example entry")
# Check for table index entries with template examples
if 'Tabla' in text and 'Ejemplo' in text:
for a in p.find_all('a'):
a.decompose()
for span in p.find_all('span', style=lambda x: x and 'mso-no-proof' in str(x)):
if 'Ejemplo' in span.get_text():
span.decompose()
print(" ✓ Cleared table index example entry")
# Remove old figure index entries that reference template examples
for p in soup.find_all('p', class_='MsoToc3'):
text = p.get_text()
if 'Figura 1. Ejemplo' in text or 'Tabla 1. Ejemplo' in text:
p.decompose()
print(" ✓ Removed template index entry")
# Also clear the specific figure/table from template
for p in soup.find_all('p', class_='Imagencentrada'):
p.decompose()
print(" ✓ Removed template figure placeholder")
# Remove template table example
for table in soup.find_all('table', class_='MsoTableGrid'):
# Check if this is the template example table
text = table.get_text()
if 'Celda 1' in text or 'Encabezado 1' in text:
# 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()
table.decompose()
print(" ✓ Removed template table example")
break
# Define chapters with their keywords and next chapter keywords
chapters = [
('Introducción', 'intro', 'Contexto'),
('Contexto', 'contexto', 'Objetivos'),
('Objetivos', 'objetivos', 'Desarrollo'),
('Desarrollo', 'desarrollo', 'Conclusiones'),
('Conclusiones', 'conclusiones', 'Referencias'),
]
print("Replacing chapter contents...")
for chapter_keyword, doc_key, next_keyword in chapters:
print(f" Processing: {chapter_keyword}")
# Reset counters for consistent numbering per chapter (optional - remove if you want global numbering)
# table_counter = 0
# figure_counter = 0
start_elem = find_section_element(soup, chapter_keyword)
end_elem = find_section_element(soup, next_keyword)
if start_elem and end_elem:
remove_elements_between(start_elem, end_elem)
new_content_html = extract_section_content(docs[doc_key])
new_soup = BeautifulSoup(new_content_html, 'html.parser')
insert_point = start_elem
for new_elem in reversed(list(new_soup.children)):
insert_point.insert_after(new_elem)
print(f" ✓ Replaced content")
else:
if not start_elem:
print(f" Warning: Could not find start element for {chapter_keyword}")
if not end_elem:
print(f" Warning: Could not find end element for {next_keyword}")
# Handle Referencias
print(" Processing: Referencias bibliográficas")
refs_start = find_section_element(soup, 'Referencias')
anexo_elem = find_section_element(soup, 'Anexo')
if refs_start and anexo_elem:
remove_elements_between(refs_start, anexo_elem)
refs_html = format_references(docs['referencias'])
refs_soup = BeautifulSoup(refs_html, 'html.parser')
insert_point = refs_start
for new_elem in reversed(list(refs_soup.children)):
insert_point.insert_after(new_elem)
print(f" ✓ Replaced content")
# Handle Anexo (last section)
print(" Processing: Anexo")
if anexo_elem:
body = soup.find('body')
if body:
current = anexo_elem.next_sibling
while current:
next_elem = current.next_sibling
if hasattr(current, 'decompose'):
current.decompose()
elif isinstance(current, NavigableString):
current.extract()
current = next_elem
anexo_content = extract_section_content(docs['anexo'])
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("Saving modified template...")
output_html = str(soup)
write_file(TEMPLATE, output_html)
print(f"✓ Done! Modified: {TEMPLATE}")
print("\nTo convert to DOCX:")
print("1. Open the .htm file in Microsoft Word")
print("2. Replace [Insertar diagrama Mermaid aquí] placeholders with actual diagrams")
print("3. Update indices: Select all (Ctrl+A) then press F9 to update fields")
print(" - This will regenerate: Índice de contenidos, Índice de figuras, Índice de tablas")
print("4. Save as .docx")
if __name__ == '__main__':
main()