#!/usr/bin/env python3
"""
Script pour générer un PDF complet de toute la documentation MkDocs.
Utilise weasyprint pour convertir le HTML en PDF.
"""
import os
import re
import subprocess
import tempfile
import shutil
from pathlib import Path
from typing import List, Dict, Any
import yaml
class SafeLineLoader(yaml.SafeLoader):
"""Loader YAML qui ignore les tags Python non supportés"""
pass
# Ignorer les tags Python custom (pour les extensions MkDocs)
SafeLineLoader.add_multi_constructor('tag:yaml.org,2002:python/', lambda loader, suffix, node: None)
def parse_nav(nav: List, docs_dir: Path, prefix: str = "") -> List[Path]:
"""Parse la navigation MkDocs et retourne la liste ordonnée des fichiers MD"""
files = []
for item in nav:
if isinstance(item, str):
# Fichier simple ou dossier
path = docs_dir / item
if path.is_file() and path.suffix == '.md':
files.append(path)
elif path.is_dir():
# C'est un dossier, récupérer tous les fichiers MD
files.extend(sorted(path.rglob('*.md')))
elif item.endswith('/'):
# Référence à un dossier (ex: bdd/)
dir_path = docs_dir / item.rstrip('/')
if dir_path.is_dir():
files.extend(sorted(dir_path.rglob('*.md')))
elif isinstance(item, dict):
for title, value in item.items():
if isinstance(value, str):
# Fichier avec titre ou dossier
path = docs_dir / value
if path.is_file() and path.suffix == '.md':
files.append(path)
elif path.is_dir():
files.extend(sorted(path.rglob('*.md')))
elif value.endswith('/'):
dir_path = docs_dir / value.rstrip('/')
if dir_path.is_dir():
files.extend(sorted(dir_path.rglob('*.md')))
elif isinstance(value, list):
# Sous-section
files.extend(parse_nav(value, docs_dir, prefix + " "))
return files
def get_all_md_files(docs_dir: Path, mkdocs_config: Dict[str, Any]) -> List[Path]:
"""Récupère tous les fichiers MD dans l'ordre de navigation"""
if 'nav' in mkdocs_config:
return parse_nav(mkdocs_config['nav'], docs_dir)
else:
# Pas de nav, récupérer tous les fichiers MD
return sorted(docs_dir.rglob('*.md'))
def preprocess_markdown(content: str, file_path: Path, docs_dir: Path) -> str:
"""Prétraite le Markdown pour le PDF"""
# Convertir les liens relatifs
def fix_link(match):
link = match.group(2)
if link.startswith('http'):
return match.group(0)
# Convertir les liens .md en ancres
if link.endswith('.md'):
link = link[:-3]
return f'[{match.group(1)}](#{link})'
content = re.sub(r'\[([^\]]+)\]\(([^)]+)\)', fix_link, content)
# Supprimer les admonitions MkDocs et les convertir en blockquotes
# !!! type "title" -> blockquote
content = re.sub(
r'!!! (\w+) "([^"]+)"\n\n((?: .+\n)+)',
lambda m: f'> **{m.group(2)}**\n>\n' + '\n'.join(f'> {line[4:]}' for line in m.group(3).split('\n') if line),
content
)
# ??? type "title" -> blockquote (collapsible)
content = re.sub(
r'\?\?\??\+? (\w+) "([^"]+)"\n\n((?: .+\n)+)',
lambda m: f'> **{m.group(2)}**\n>\n' + '\n'.join(f'> {line[4:]}' for line in m.group(3).split('\n') if line),
content
)
return content
def create_combined_markdown(files: List[Path], docs_dir: Path, output_path: Path) -> None:
"""Combine tous les fichiers MD en un seul"""
combined = []
# Page de titre
combined.append("# Documentation RoadWave\n\n")
combined.append("---\n\n")
combined.append("## Table des matières\n\n")
# Générer la table des matières
toc_entries = []
for f in files:
with open(f, 'r', encoding='utf-8') as file:
content = file.read()
# Extraire le titre H1
title_match = re.search(r'^# (.+)$', content, re.MULTILINE)
if title_match:
title = title_match.group(1)
anchor = re.sub(r'[^\w\s-]', '', title.lower()).replace(' ', '-')
toc_entries.append(f"- [{title}](#{anchor})")
combined.append('\n'.join(toc_entries))
combined.append("\n\n---\n\n")
combined.append('\n\n')
# Ajouter chaque fichier
for f in files:
with open(f, 'r', encoding='utf-8') as file:
content = file.read()
# Prétraiter
content = preprocess_markdown(content, f, docs_dir)
combined.append(content)
combined.append("\n\n")
combined.append('\n\n')
with open(output_path, 'w', encoding='utf-8') as f:
f.write('\n'.join(combined))
def markdown_to_html(md_path: Path, html_path: Path) -> None:
"""Convertit Markdown en HTML avec styles"""
import markdown
from markdown.extensions.tables import TableExtension
from markdown.extensions.fenced_code import FencedCodeExtension
from markdown.extensions.toc import TocExtension
with open(md_path, 'r', encoding='utf-8') as f:
md_content = f.read()
# Convertir en HTML
md = markdown.Markdown(extensions=[
'tables',
'fenced_code',
'toc',
'attr_list',
'md_in_html'
])
html_content = md.convert(md_content)
# Template HTML avec styles
html_template = f'''
Documentation RoadWave
{html_content}
'''
with open(html_path, 'w', encoding='utf-8') as f:
f.write(html_template)
def html_to_pdf(html_path: Path, pdf_path: Path) -> None:
"""Convertit HTML en PDF avec weasyprint"""
from weasyprint import HTML, CSS
print(f" Conversion HTML → PDF...")
HTML(filename=str(html_path)).write_pdf(str(pdf_path))
def main():
"""Point d'entrée principal"""
project_root = Path(__file__).parent.parent
docs_dir = project_root / 'docs'
mkdocs_path = project_root / 'mkdocs.yml'
output_dir = project_root / 'output'
output_dir.mkdir(exist_ok=True)
print("📄 Génération du PDF de la documentation RoadWave...")
# Charger la config MkDocs
with open(mkdocs_path, 'r', encoding='utf-8') as f:
mkdocs_config = yaml.load(f, Loader=SafeLineLoader)
# Récupérer tous les fichiers MD
print(" Collecte des fichiers Markdown...")
md_files = get_all_md_files(docs_dir, mkdocs_config)
print(f" → {len(md_files)} fichiers trouvés")
# Créer un fichier MD combiné
combined_md = output_dir / 'documentation_complete.md'
print(" Combinaison des fichiers...")
create_combined_markdown(md_files, docs_dir, combined_md)
# Convertir en HTML
html_path = output_dir / 'documentation_complete.html'
print(" Conversion Markdown → HTML...")
markdown_to_html(combined_md, html_path)
# Convertir en PDF
pdf_path = output_dir / 'RoadWave_Documentation.pdf'
html_to_pdf(html_path, pdf_path)
print(f"\n✅ PDF généré: {pdf_path}")
print(f" Taille: {pdf_path.stat().st_size / 1024 / 1024:.2f} MB")
if __name__ == '__main__':
main()