tykayn/orgmode-to-gemini-blog
1
0
Fork 0
mirror of https://forge.chapril.org/tykayn/orgmode-to-gemini-blog synced 2025-06-20 09:04:42 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

do not recreate not modified files already built by default

Browse source
This commit is contained in:
Tykayn 2025-02-23 20:09:39 +01:00 • committed by tykayn
parent e1f8bf93e0
commit 17e935a3ca
3 changed files with 36 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

36
linking_articles_prev_next.py
View file

@ -95,6 +95,8 @@ Navigation:
if generate_linkings_json :
count_articles = len(os.listdir(directory))
counter=0
rebuild_counter = 0
pandoc_runs_counter = 0
print(f"Génération des liens entre articles pour {count_articles} articles")
print(f"run_pandoc: {run_pandoc}")
@ -128,10 +130,15 @@ if generate_linkings_json :
gemini_content = ''
html_content = ''
# Vérifier l'existence du fichier HTML pour déterminer last_html_build
html_path = f"html_websites/{args.blog}/{annee}/{slug}/index.html"
last_html_build = None
html_path = f"html-websites/{args.blog}/{annee}/{slug}/index.html"
last_html_build_time = None
if os.path.exists(html_path):
last_html_build = time.ctime(os.path.getmtime(html_path))
# Obtenir la date de création du fichier HTML
last_html_build_time = os.path.getctime(html_path)
print(f"last_html_build: {last_html_build_time} : {html_path}")
else:
print(f"----------- last_html_build html_path: {html_path} n'existe pas")
# Vérifier l'existence du fichier Gemini pour déterminer last_gemini_build
gemini_path = f"gemini-capsules/{args.blog}/{slug}.gmi"
last_gemini_build = None
@ -144,21 +151,32 @@ if generate_linkings_json :
last_build_time = time.mktime(time.strptime(last_gemini_build))
rebuild_this_article_gemini = file_modified_time > last_build_time
else:
rebuild_this_article_gemini = True
# Vérifier si l'article doit être reconstruit en comparant les dates de modification
rebuild_this_article_html = False
if last_html_build:
if last_html_build_time:
file_modified_time = os.path.getmtime(file_path)
last_build_time = time.mktime(time.strptime(last_html_build))
rebuild_this_article_html = file_modified_time > last_build_time
print(f"--------- file_modified_time: {file_path} : {file_modified_time}")
# Obtenir l'heure de dernière modification du fichier HTML
rebuild_this_article_html = file_modified_time > last_html_build_time
# print(f"--------- article modifié après le build de son rendu html: {file_path}, {rebuild_this_article_html}")
else:
# si il n'y a pas de fichier html, on le construit pour la première fois
print('on reconstruit le html de l\'article', file_name)
rebuild_this_article_html = True
if rebuild_this_article_html:
rebuild_counter += 1
if run_pandoc and rebuild_this_article_html:
# convertir le contenu d'article org vers html
print(f"{time.strftime('%H:%M:%S')} : Conversion de {file_name} en html")
print(f"BRRRRRRRRRRRR pandoc time {time.strftime('%H:%M:%S')} : Conversion de {file_name} en html")
html_content = pypandoc.convert_text(content_without_h1, 'html', format='org')
pandoc_runs_counter += 1
else:
html_content = content_without_h1
@ -184,13 +202,15 @@ if generate_linkings_json :
'title': title,
'next': None,
'previous': None,
'last_html_build': last_html_build,
'last_html_build': last_html_build_time,
'last_gemini_build': last_gemini_build,
'org_content': content, # Contenu Org original
'html_content_without_h1': re.sub(r'<h1>.*?</h1>', '', html_content), # Contenu HTML converti sans le titre de premier niveau
'html_content': html_content # Contenu first_picture_urlHTML converti
}
print(f"======= Nombre d'articles reconstruits: {rebuild_counter}")
print(f"======= Nombre de runs de pandoc: {pandoc_runs_counter}")
# Trier les basenames par ordre décroissant
sorted_basenames = sorted(files_dict.keys(), reverse=True)
print(len(sorted_basenames), 'articles trouvés')