unir/MastersThesis
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Cross references
Some checks failed
build_docker / essential (push) Successful in 1s
Details
build_docker / build_paddle_ocr (push) Successful in 5m6s
Details
build_docker / build_raytune (push) Has been cancelled
Details
build_docker / build_easyocr_gpu (push) Has been cancelled
Details
build_docker / build_doctr (push) Has been cancelled
Details
build_docker / build_doctr_gpu (push) Has been cancelled
Details
build_docker / build_paddle_ocr_gpu (push) Has started running
Details
build_docker / build_easyocr (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Sergio Jimenez Jimenez
2026-02-04 20:43:50 +01:00
parent 868f748a8d
commit e9c937a042
18 changed files with 1118 additions and 820 deletions
Download Patch File Download Diff File Expand all files Collapse all files

583
apply_content.py
View File

@@ -1,136 +1,62 @@
#!/usr/bin/env python3
"""Replace template content with thesis content from docs/ folder using BeautifulSoup."""
"""Replace template content with thesis content from docs/ folder using BeautifulSoup.
This module orchestrates the conversion of markdown documentation to UNIR's
Word template format. Content handling is delegated to:
- markdown_utils.py: Utility functions for markdown parsing
- content_handlers.py: Block-level content handlers (tables, figures, lists, etc.)
"""
import re
import os
import shutil
from bs4 import BeautifulSoup, NavigableString
from latex2mathml.converter import convert as latex_to_mathml
from PIL import Image
from markdown_utils import (
read_file,
write_file,
md_to_html_para,
convert_latex_formulas,
is_source_line,
is_leyenda_line,
split_into_paragraphs,
SOURCE_LINE_RE,
)
from content_handlers import (
handle_mermaid_diagram,
handle_code_block,
handle_header,
handle_table,
handle_blockquote,
handle_bullet_list,
handle_numbered_list,
)
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*(.*)$', re.IGNORECASE)
# Accept Leyenda lines with or without markdown bold
LEYENDA_LINE_RE = re.compile(r'^\s*(?:\*{1,2})?Leyenda:(?:\*{1,2})?\s*(.*)$', re.IGNORECASE)
# Global counters for tables and figures
table_counter = 0
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 parse_md_to_html_blocks(md_content, is_anexo=False, counters=None):
"""Convert markdown content to HTML blocks with template styles.
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()
Args:
md_content: Markdown content string
is_anexo: Boolean indicating if processing Anexo section
counters: Dict with table/figure counters. If None, creates new one.
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'<b>\1</b>', text)
# Italic
text = re.sub(r'\*([^*]+)\*', r'<i>\1</i>', text)
# Inline code
text = re.sub(r'`([^`]+)`', r'<span style="font-family:Consolas;font-size:10pt">\1</span>', text)
# Links [text](url) -> <a href="url">text</a>
text = re.sub(r'\[([^\]]+)\]\(([^)]+)\)', r'<a href="\2">\1</a>', text)
return text
def convert_latex_formulas(text):
"""Convert LaTeX formulas to MathML for Word compatibility."""
# Block formulas $$...$$
def convert_block(match):
latex = match.group(1)
try:
mathml = latex_to_mathml(latex, display="block")
return f'<p class=MsoNormal style="text-align:center">{mathml}</p>'
except:
return match.group(0) # Keep original if conversion fails
text = re.sub(r'\$\$([^$]+)\$\$', convert_block, text)
# Inline formulas $...$
def convert_inline(match):
latex = match.group(1)
try:
return latex_to_mathml(latex, display="inline")
except:
return match.group(0)
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_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
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, is_anexo=False):
"""Convert markdown content to HTML blocks with template styles."""
global table_counter, figure_counter, anexo_table_counter, anexo_figure_counter, global_figure_index
Returns:
Tuple of (html_string, counters) where counters is the updated dict
"""
if counters is None:
counters = {
'table': 0,
'figure': 0,
'anexo_table': 0,
'anexo_figure': 0,
'global_figure': 0,
}
html_blocks = []
lines = md_content.split('\n')
@@ -146,346 +72,49 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
# Mermaid diagram - convert to figure with actual image
if line.strip().startswith('```mermaid'):
# 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() == '```':
mermaid_lines.append(lines[i])
i += 1
# Try to extract title from mermaid content (YAML format)
mermaid_content = '\n'.join(mermaid_lines)
# Match title with quotes: title: "Something" or title: 'Something'
title_match = re.search(r'title:\s*["\']([^"\']+)["\']', mermaid_content)
if not title_match:
# Match title without quotes: title: Something
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 {fig_num}"
# 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{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:
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>''')
if os.path.exists(fig_path):
# Read actual image dimensions and scale to fit page width
img = Image.open(fig_path)
orig_w, orig_h = img.size
# Scale to fit max width of 566px (15cm at 96dpi) while preserving aspect ratio
max_width = 566
if orig_w > max_width:
scale = max_width / orig_w
new_w = max_width
new_h = int(orig_h * scale)
else:
new_w, new_h = orig_w, orig_h
# Convert to pt (1px at 96dpi = 0.75pt)
w_pt = new_w * 0.75
h_pt = new_h * 0.75
# 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
# 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
fig_leyenda = 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
# 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)
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>''')
# 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
blocks, i = handle_mermaid_diagram(lines, i, counters, is_anexo)
html_blocks.extend(blocks)
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('&', '&amp;').replace('<', '&lt;').replace('>', '&gt;')
html_blocks.append(f'''<div style="background:#E6F4F9;border-top:solid #0098CD .5pt;border-bottom:solid #0098CD .5pt;padding:8pt 12pt;margin:6pt 0">
<pre style="font-family:Consolas,monospace;font-size:9pt;color:#333333;margin:0;white-space:pre-wrap;word-wrap:break-word">{code}</pre>
</div>''')
blocks, i = handle_code_block(lines, i)
html_blocks.extend(blocks)
continue
# Headers
if line.startswith('#'):
header_html = handle_header(line, is_anexo)
if header_html is not None:
html_blocks.append(header_html)
i += 1
continue
# Headers - ## becomes h2, ### becomes h3
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"><b><span lang=ES style="text-transform:none">{text}</span></b></h4>')
i += 1
continue
elif line.startswith('###'):
text = line.lstrip('#').strip()
# 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()
# 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('#'):
# Skip h1 - we keep the original
i += 1
continue
# Table - check for table title pattern first
# Table
if '|' in line and i + 1 < len(lines) and '---' in lines[i + 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
alt_title = None # Alternative title from **bold text:** pattern
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.startswith('**') and prev_line.endswith(':**'):
# Alternative: **Bold title:** pattern (for informal tables)
alt_title = re.sub(r'\*+', '', prev_line).rstrip(':').strip()
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 (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)
# Word TOC looks for text with Caption style - anchor must be outside main caption text
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()
elif alt_title:
# Use alternative title from **bold text:** pattern
clean_title = alt_title
else:
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:
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>''')
# Build table HTML with APA style (horizontal lines only, no vertical)
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]]
table_html += '<tr>'
for cell in cells:
if j == 0:
# Header row: top and bottom border, bold text
table_html += f'<td style="border-top:solid windowtext 1.0pt;border-bottom:solid windowtext 1.0pt;border-left:none;border-right:none;padding:5px"><p class=MsoNormal style="margin:0;text-align:center"><b><span lang=ES>{md_to_html_para(cell)}</span></b></p></td>'
elif j == len(table_lines) - 1:
# Last row: bottom border only
table_html += f'<td style="border-top:none;border-bottom:solid windowtext 1.0pt;border-left:none;border-right:none;padding:5px"><p class=MsoNormal style="margin:0;text-align:center"><span lang=ES>{md_to_html_para(cell)}</span></p></td>'
else:
# Middle rows: no borders
table_html += f'<td style="border:none;padding:5px"><p class=MsoNormal style="margin:0;text-align:center"><span lang=ES>{md_to_html_para(cell)}</span></p></td>'
table_html += '</tr>'
table_html += '</table></div>'
html_blocks.append(table_html)
# 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>')
# 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>')
blocks, i = handle_table(lines, i, counters, is_anexo)
html_blocks.extend(blocks)
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'<p class=MsoQuote><i><span lang=ES>{md_to_html_para(quote_text)}</span></i></p>')
blocks, i = handle_blockquote(lines, i)
html_blocks.extend(blocks)
continue
# Bullet list (handle blank lines between items)
# Bullet list
if re.match(r'^[\-\*\+]\s', line):
# 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)
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>')
blocks, i = handle_bullet_list(lines, i)
html_blocks.extend(blocks)
continue
# Numbered list (handle blank lines between items)
# Numbered list
if re.match(r'^\d+\.\s', line):
# 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)
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>')
blocks, i = handle_numbered_list(lines, i)
html_blocks.extend(blocks)
continue
# Skip lines that are just table/figure titles (they'll be handled with the table/figure)
# Skip lines that are just table/figure titles
if line.strip().startswith('**Tabla') or line.strip().startswith('*Tabla'):
i += 1
continue
@@ -514,12 +143,23 @@ def parse_md_to_html_blocks(md_content, is_anexo=False):
else:
html_blocks.append(f'<p class=MsoNormal><span lang=ES>{md_to_html_para(para_text)}</span></p>')
return '\n\n'.join(html_blocks)
return '\n\n'.join(html_blocks), counters
def extract_section_content(md_content, is_anexo=False):
"""Extract content from markdown, skipping the first # header."""
def extract_section_content(md_content, is_anexo=False, counters=None):
"""Extract content from markdown, skipping the first # header.
Args:
md_content: Markdown content string
is_anexo: Boolean indicating if processing Anexo section
counters: Dict with table/figure counters
Returns:
Tuple of (html_string, counters)
"""
md_content = re.sub(r'^#\s+[^\n]+\n+', '', md_content, count=1)
return parse_md_to_html_blocks(md_content, is_anexo=is_anexo)
return parse_md_to_html_blocks(md_content, is_anexo=is_anexo, counters=counters)
def find_section_element(soup, keyword):
"""Find element containing keyword (h1 or special paragraph classes)."""
@@ -540,6 +180,7 @@ def find_section_element(soup, keyword):
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
@@ -553,6 +194,7 @@ def remove_elements_between(start_elem, end_elem):
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()
@@ -566,20 +208,11 @@ def format_references(refs_content):
# Apply markdown formatting
formatted = md_to_html_para(line)
# Use MsoBibliography style with hanging indent (36pt indent, -36pt text-indent)
# Use MsoBibliography style with hanging indent
refs_html += f'''<p class=MsoBibliography style="margin-left:36.0pt;text-indent:-36.0pt"><span lang=ES>{formatted}</span></p>\n'''
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"""
@@ -610,16 +243,21 @@ def extract_resumen_parts(resumen_content):
return spanish_text, spanish_keywords, english_text, english_keywords
def main():
global table_counter, figure_counter, anexo_table_counter, anexo_figure_counter
# Initialize counters dict (replaces global counters)
counters = {
'table': 0,
'figure': 0,
'anexo_table': 0,
'anexo_figure': 0,
'global_figure': 0,
}
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',
@@ -652,7 +290,6 @@ def main():
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:
@@ -666,7 +303,6 @@ def main():
if hasattr(elem, 'decompose'):
elem.decompose()
# 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>
@@ -681,11 +317,9 @@ def main():
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)
@@ -698,7 +332,6 @@ def main():
if hasattr(elem, 'decompose'):
elem.decompose()
# 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>
@@ -721,31 +354,24 @@ def main():
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)
# Clear old figure/table index entries
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 <a> 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()
@@ -754,24 +380,20 @@ def main():
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():
@@ -782,7 +404,7 @@ def main():
print(" ✓ Removed template table example")
break
# Define chapters with their keywords and next chapter keywords
# Define chapters
chapters = [
('Introducción', 'intro', 'Contexto'),
('Contexto', 'contexto', 'Objetivos'),
@@ -795,16 +417,12 @@ def main():
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_content_html, counters = extract_section_content(docs[doc_key], counters=counters)
new_soup = BeautifulSoup(new_content_html, 'html.parser')
insert_point = start_elem
for new_elem in reversed(list(new_soup.children)):
@@ -844,20 +462,20 @@ def main():
current.extract()
current = next_elem
anexo_content = extract_section_content(docs['anexo'], is_anexo=True)
anexo_content, counters = extract_section_content(docs['anexo'], is_anexo=True, counters=counters)
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 + {anexo_table_counter} Anexo tables, {figure_counter} figures + {anexo_figure_counter} Anexo figures processed")
print(f"\nSummary: {counters['table']} tables + {counters['anexo_table']} Anexo tables, {counters['figure']} figures + {counters['anexo_figure']} Anexo figures processed")
print("Saving modified template...")
output_html = str(soup)
write_file(TEMPLATE_OUTPUT, output_html)
# Copy template support files (header.htm, images, etc.)
# Copy template support files
support_files_src = os.path.join(BASE_DIR, 'instructions/plantilla_individual_files')
support_files_dst = os.path.join(BASE_DIR, 'thesis_output/plantilla_individual_files')
if os.path.exists(support_files_src):
@@ -874,5 +492,6 @@ def main():
print(" - This will regenerate: Índice de contenidos, Índice de figuras, Índice de tablas")
print("4. Save as .docx")
if __name__ == '__main__':
main()