Last active
September 30, 2020 11:55
-
-
Save quaxsze/bbf2ab4f02b0299bb8e401b069c5e862 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
resources_path="/srv/nfs/datagouv/resources" | |
avatars_path="/srv/nfs/datagouv/avatars" | |
images_path="/srv/nfs/datagouv/images" | |
echo "Processing resources" | |
resources_counter=0 | |
for f in $(find -type f "$resources_path") | |
do | |
foo=${f#"$resources_path/"} | |
if ! grep -Fxq "$foo" resource_fs.txt | |
then | |
echo $f >> resources_deletion.txt | |
if [ $1 == "-d" ] | |
then | |
continue | |
fi | |
rm "$f" | |
(( resources_counter++ )) | |
fi | |
done | |
echo "Resources completed" | |
echo "Resources deletion: ${resources_counter}" | |
echo "Processing avatars" | |
avatars_counter=0 | |
for f in $(find -type f "$avatars_path") | |
do | |
match=0 | |
while read p | |
do | |
if [[ $f == *$p* ]] | |
then | |
match=1 | |
break | |
fi | |
done < avatar_fs.txt | |
if [ $match -eq 0 ] | |
then | |
echo $f >> avatars_deletion.txt | |
if [ $1 == "-d" ] | |
then | |
continue | |
fi | |
rm "$f" | |
(( avatars_counter++ )) | |
fi | |
done | |
echo "Avatars completed" | |
echo "Avatars deletion: ${avatars_counter}" | |
echo "Processing images" | |
images_counter=0 | |
for f in $(find -type f "$images_path") | |
do | |
match=0 | |
while read p | |
do | |
if [[ $f == *$p* ]] | |
then | |
match=1 | |
break | |
fi | |
done < image_fs.txt | |
if [ $match -eq 0 ] | |
then | |
echo $f >> images_deletion.txt | |
if [ $1 == "-d" ] | |
then | |
continue | |
fi | |
rm "$f" | |
(( images_counter++ )) | |
fi | |
done | |
echo "Images completed" | |
echo "Images deletion: ${images_counter}" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from udata.app import create_app | |
from udata.core import init_app | |
from udata.models import Dataset, CommunityResource, Organization, User, Reuse | |
def main(): | |
app = create_app() | |
init_app(app) | |
with app.app_context(): | |
print('Processing resources and community resources.') | |
datasets = Dataset.objects() | |
community_resources = CommunityResource.objects() | |
with open('resource_fs.txt', 'w') as f: | |
for dataset in datasets: | |
for resource in dataset.resources: | |
if resource.url.startswith('https://static.data.gouv.fr'): | |
fs_name = resource.url[38:] | |
f.write(f'{fs_name}\n') | |
for community_resource in community_resources: | |
if community_resource.url.startswith('https://static.data.gouv.fr'): | |
fs_name = community_resource.url[38:] | |
f.write(f'{fs_name}\n') | |
print('Processing organizations logos and users avatars.') | |
orgs = Organization.objects() | |
users = User.objects() | |
with open('avatar_fs.txt', 'w') as f: | |
for org in orgs: | |
if org.logo.filename: | |
split_filename = org.logo.filename.split('.') | |
f.write(f'{split_filename[0]}\n') | |
for user in users: | |
if user.avatar.filename: | |
split_filename = user.avatar.filename.split('.') | |
f.write(f'{split_filename[0]}\n') | |
print('Processing reuses logos.') | |
reuses = Reuse.objects() | |
with open('image_fs.txt', 'w') as f: | |
for reuse in reuses: | |
if reuse.image.filename: | |
split_filename = reuse.image.filename.split('.') | |
f.write(f'{split_filename[0]}\n') | |
print('Completed.') | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment