sergio
f5d1032e41
Some checks failed
build_docker / build_cpu (pull_request) Successful in 5m16s
build_docker / build_easyocr_gpu (pull_request) Has been cancelled
build_docker / build_doctr (pull_request) Has been cancelled
build_docker / build_doctr_gpu (pull_request) Has been cancelled
build_docker / build_raytune (pull_request) Has been cancelled
build_docker / build_gpu (pull_request) Has been cancelled
build_docker / build_easyocr (pull_request) Has been cancelled
build_docker / essential (pull_request) Successful in 1s
116 lines
4.0 KiB
Python
116 lines
4.0 KiB
Python
#!/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 = os.path.dirname(os.path.abspath(__file__))
|
|
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',
|
|
'07_anexo_a.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 from YAML front matter
|
|
# Match title with quotes: title: "Something" or title: 'Something'
|
|
title_match = re.search(r'title:\s*["\']([^"\']+)["\']', mermaid_code)
|
|
if not title_match:
|
|
# Match title without quotes: title: Something
|
|
title_match = re.search(r'title:\s*([^"\'\n]+)', mermaid_code)
|
|
title = title_match.group(1).strip() if title_match else f"Diagrama {len(diagrams) + 1}"
|
|
|
|
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 high resolution for clarity
|
|
try:
|
|
result = subprocess.run(
|
|
[MMDC, '-i', temp_file, '-o', output_file, '-b', 'white', '-w', '1600', '-s', '3'],
|
|
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()
|