MastersThesis/generate_mermaid_figures.py

#!/usr/bin/env python3
"""Extract Mermaid diagrams from markdown files and convert to PNG images."""

import os
import re
import subprocess
import json

BASE_DIR = '/Users/sergio/Desktop/MastersThesis'
DOCS_DIR = os.path.join(BASE_DIR, 'docs')
OUTPUT_DIR = os.path.join(BASE_DIR, 'thesis_output/figures')
MMDC = os.path.join(BASE_DIR, 'node_modules/.bin/mmdc')

def extract_mermaid_diagrams():
    """Extract all mermaid diagrams from markdown files."""
    diagrams = []

    md_files = [
        '02_contexto_estado_arte.md',
        '03_objetivos_metodologia.md',
        '04_desarrollo_especifico.md',
    ]

    for md_file in md_files:
        filepath = os.path.join(DOCS_DIR, md_file)
        if not os.path.exists(filepath):
            continue

        with open(filepath, 'r', encoding='utf-8') as f:
            content = f.read()

        # Find all mermaid blocks
        pattern = r'```mermaid\n(.*?)```'
        matches = re.findall(pattern, content, re.DOTALL)

        for i, mermaid_code in enumerate(matches):
            # Try to extract title
            title_match = re.search(r'title\s+["\']?([^"\'"\n]+)["\']?', mermaid_code)
            title = title_match.group(1).strip() if title_match else f"Diagrama de {md_file}"

            diagrams.append({
                'source': md_file,
                'code': mermaid_code.strip(),
                'title': title,
                'index': len(diagrams) + 1
            })

    return diagrams

def convert_to_png(diagrams):
    """Convert mermaid diagrams to PNG using mmdc."""
    os.makedirs(OUTPUT_DIR, exist_ok=True)

    generated = []

    for diagram in diagrams:
        # Write mermaid code to temp file
        temp_file = os.path.join(OUTPUT_DIR, f'temp_{diagram["index"]}.mmd')
        output_file = os.path.join(OUTPUT_DIR, f'figura_{diagram["index"]}.png')

        with open(temp_file, 'w', encoding='utf-8') as f:
            f.write(diagram['code'])

        # Convert using mmdc with higher resolution for better readability
        try:
            result = subprocess.run(
                [MMDC, '-i', temp_file, '-o', output_file, '-b', 'white', '-w', '1600', '-s', '2'],
                capture_output=True,
                text=True,
                timeout=60
            )

            if os.path.exists(output_file):
                print(f"✓ Generated: figura_{diagram['index']}.png - {diagram['title']}")
                generated.append({
                    'file': f'figura_{diagram["index"]}.png',
                    'title': diagram['title'],
                    'index': diagram['index']
                })
            else:
                print(f"✗ Failed: figura_{diagram['index']}.png - {result.stderr}")
        except subprocess.TimeoutExpired:
            print(f"✗ Timeout: figura_{diagram['index']}.png")
        except Exception as e:
            print(f"✗ Error: figura_{diagram['index']}.png - {e}")

        # Clean up temp file
        if os.path.exists(temp_file):
            os.remove(temp_file)

    return generated

def main():
    print("Extracting Mermaid diagrams from markdown files...")
    diagrams = extract_mermaid_diagrams()
    print(f"Found {len(diagrams)} diagrams\n")

    print("Converting to PNG images...")
    generated = convert_to_png(diagrams)

    print(f"\n✓ Generated {len(generated)} figures in {OUTPUT_DIR}")

    # Save manifest for apply_content.py to use
    manifest_file = os.path.join(OUTPUT_DIR, 'figures_manifest.json')
    with open(manifest_file, 'w', encoding='utf-8') as f:
        json.dump(generated, f, indent=2, ensure_ascii=False)
    print(f"✓ Saved manifest to {manifest_file}")

if __name__ == '__main__':
    main()