From e8771df78d87868d193ce8c25d67da85eb5fd941 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Fran=C3=A7ois=20Poulain?= <fpoulain@metrodore.fr>
Date: Tue, 4 Aug 2020 10:53:21 +0200
Subject: [PATCH] feat(convert): rend paresseux le download des logos

---
 drupal2spip_lal/base/convert.py               | 19 +++++++++++--------
 .../base/management/commands/import.py        |  7 ++++++-
 2 files changed, 17 insertions(+), 9 deletions(-)

diff --git a/drupal2spip_lal/base/convert.py b/drupal2spip_lal/base/convert.py
index ca5ab3d..cfaf83c 100644
--- a/drupal2spip_lal/base/convert.py
+++ b/drupal2spip_lal/base/convert.py
@@ -53,7 +53,7 @@ def strong_to_dl(html):
     return '\n'.join(r)
 
 
-def fetch_and_remove_logo(article):
+def fetch_and_remove_logo(article, force_download):
     def fetch_logo(src):
         """
         SPIP gère les logos à la façon d'un hack : un fichier dans IMG nommé
@@ -63,11 +63,11 @@ def fetch_and_remove_logo(article):
         filename = 'arton{}.{}'.format(article.pk, ext)
         path = os.path.join(settings.SPIP_LOGO_DIR, filename)
 
-        r = request.get(src, stream=True)
-
-        with open(path, 'wb') as fd:
-            for chunk in r.iter_content(chunk_size=128):
-                fd.write(chunk)
+        if not os.access(path, os.R_OK) or force_download:
+            r = request.get(src, stream=True)
+            with open(path, 'wb') as fd:
+                for chunk in r.iter_content(chunk_size=128):
+                    fd.write(chunk)
 
     def remove_img(img):
         has_siblings = [
@@ -100,12 +100,15 @@ def sanitarize_html(html):
     return soup.prettify(formatter="html5")
 
 
-def convert_node(node, update=False):
+def convert_node(node, options):
     """
     Le point d'entrée fonctionnel c'est les Urls.
     On se base donc là dessus pour vérifier si l'import
     est à faire ou pas ou encore à upgrader.
     """
+    update = options.get('update', False)
+    force_download = options.get('force_download', False)
+
     node_urls = drupal.UrlAlias.objects.filter(src='node/{}'.format(node.pk))
 
     spip_urls = spip.Urls.objects.filter(
@@ -169,7 +172,7 @@ def convert_node(node, update=False):
             auteur=auteur, id_objet=article.pk, objet='article'
         )
 
-        fetch_and_remove_logo(article)
+        fetch_and_remove_logo(article, force_download)
 
         for term_node in node.termnode_set.all():
             groupe, _ = spip.GroupesMots.objects.get_or_create(
diff --git a/drupal2spip_lal/base/management/commands/import.py b/drupal2spip_lal/base/management/commands/import.py
index 9cedb68..83a243b 100644
--- a/drupal2spip_lal/base/management/commands/import.py
+++ b/drupal2spip_lal/base/management/commands/import.py
@@ -19,9 +19,14 @@ class Command(BaseCommand):
             action='store_true',
             help='Force existing articles to be updated. Default is skip.',
         )
+        parser.add_argument(
+            '--force-download',
+            action='store_true',
+            help='Force existing ressources to be downloaded. Default is skip.',
+        )
 
     def handle(self, **options):
         [
-            convert_node(n, update=options.get('update', False))
+            convert_node(n, options)
             for n in Node.objects.filter(pk__in=options.get('node', []))
         ]