Basic start of soft delete

Currently blocked by https://github.com/san4ezy/django_softdelete/pull/30

Pipfile

@@ -17,6 +17,7 @@ django-extensions = "*"
 django-filter = "~=24.2"
 django-guardian = "*"
 django-multiselectfield = "*"
+django-soft-delete = "*"
 djangorestframework = "==3.14.0"
 djangorestframework-guardian = "*"
 drf-writable-nested = "*"

Pipfile.lock

@@ -540,6 +540,15 @@
             "index": "pypi",
             "version": "==0.1.12"
         },
+        "django-soft-delete": {
+            "hashes": [
+                "sha256:2b28ab95d18847ea301c46f6f172ea878490fdf12261c697ec7e44b9d652f866",
+                "sha256:5afe70c0f5ce066c0e287c39806fb949ab66e73305a11b88d4c533247f3b96f0"
+            ],
+            "index": "pypi",
+            "markers": "python_version >= '3.6'",
+            "version": "==1.0.12"
+        },
         "djangorestframework": {
             "hashes": [
                 "sha256:579a333e6256b09489cbe0a067e66abe55c6595d8926be6b99423786334350c8",

docs/configuration.md

@@ -1362,6 +1362,20 @@ processing. This only has an effect if
 
     Defaults to false.
 
+## Trash
+
+#### [`EMPTY_TRASH_DELAY=<num>`](#EMPTY_TRASH_DELAY) {#EMPTY_TRASH_DELAY}
+
+: Sets how long in days objects remain in the 'trash' before they are permanently deleted.
+
+    Defaults to 30 days, minimum of 1 day.
+
+#### [`PAPERLESS_EMPTY_TRASH_TASK_CRON=<cron expression>`](#PAPERLESS_EMPTY_TRASH_TASK_CRON) {#PAPERLESS_EMPTY_TRASH_TASK_CRON}
+
+: Configures the schedule to empty the trash of expired deleted objects.
+
+    Defaults to `0 1 * * *`, once per day.
+
 ## Binaries
 
 There are a few external software packages that Paperless expects to

src/documents/migrations/1047_correspondent_deleted_at_correspondent_restored_at_and_more.py

@@ -0,0 +1,84 @@
+# Generated by Django 4.2.11 on 2024-04-22 20:44
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("documents", "1046_workflowaction_remove_all_correspondents_and_more"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="correspondent",
+            name="deleted_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="correspondent",
+            name="restored_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="document",
+            name="deleted_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="document",
+            name="restored_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="documenttype",
+            name="deleted_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="documenttype",
+            name="restored_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="savedview",
+            name="deleted_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="savedview",
+            name="restored_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="storagepath",
+            name="deleted_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="storagepath",
+            name="restored_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="tag",
+            name="deleted_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="tag",
+            name="restored_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="workflow",
+            name="deleted_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="workflow",
+            name="restored_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+    ]

src/documents/models.py

@@ -23,11 +23,13 @@ from multiselectfield import MultiSelectField
 if settings.AUDIT_LOG_ENABLED:
     from auditlog.registry import auditlog
 
+from django_softdelete.models import SoftDeleteModel
+
 from documents.data_models import DocumentSource
 from documents.parsers import get_default_file_extension
 
 
-class ModelWithOwner(models.Model):
+class ModelWithOwner(SoftDeleteModel):
     owner = models.ForeignKey(
         User,
         blank=True,
@@ -1262,7 +1264,7 @@ class WorkflowAction(models.Model):
         return f"WorkflowAction {self.pk}"
 
 
-class Workflow(models.Model):
+class Workflow(SoftDeleteModel):
     name = models.CharField(_("name"), max_length=256, unique=True)
 
     order = models.IntegerField(_("order"), default=0)

src/documents/signals/handlers.py

@@ -1,6 +1,7 @@
 import logging
 import os
 import shutil
+from datetime import timedelta
 from typing import Optional
 
 from celery import states
@@ -302,7 +303,13 @@ def set_storage_path(
 
 
 @receiver(models.signals.post_delete, sender=Document)
-def cleanup_document_deletion(sender, instance, using, **kwargs):
+def cleanup_document_deletion(sender, instance, **kwargs):
+    now = timezone.localtime(timezone.now())
+    if now - instance.deleted_at < timedelta(days=settings.EMPTY_TRASH_DELAY):
+        logger.info(
+            f"Detected soft delete of {instance!s}. Deferring cleanup.",
+        )
+        return
     with FileLock(settings.MEDIA_LOCK):
         if settings.TRASH_DIR:
             # Find a non-conflicting filename in case a document with the same

src/paperless/settings.py

@@ -207,6 +207,19 @@ def _parse_beat_schedule() -> dict:
                 "expires": ((7.0 * 24.0) - 1.0) * 60.0 * 60.0,
             },
         },
+        {
+            "name": "Empty trash",
+            "env_key": "PAPERLESS_EMPTY_TRASH_TASK_CRON",
+            # Default daily at 01:00
+            "env_default": "0 1 * * *",
+            "task": "documents.tasks.sanity_check",
+            "options": {
+                # 1 hour before default schedule sends again
+                "expires": 23.0
+                * 60.0
+                * 60.0,
+            },
+        },
     ]
     for task in tasks:
         # Either get the environment setting or use the default
@@ -1148,3 +1161,9 @@ EMAIL_SUBJECT_PREFIX: Final[str] = "[Paperless-ngx] "
 if DEBUG:  # pragma: no cover
     EMAIL_BACKEND = "django.core.mail.backends.filebased.EmailBackend"
     EMAIL_FILE_PATH = BASE_DIR / "sent_emails"
+
+
+###############################################################################
+# Soft Delete
+###############################################################################
+EMPTY_TRASH_DELAY = max(__get_int("PAPERLESS_SOFT_DELETE_DELAY", 30), 1)

src/paperless_mail/migrations/0024_mailaccount_deleted_at_mailaccount_restored_at_and_more.py

@@ -0,0 +1,44 @@
+# Generated by Django 4.2.11 on 2024-04-22 20:44
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("paperless_mail", "0023_remove_mailrule_filter_attachment_filename_and_more"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="mailaccount",
+            name="deleted_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="mailaccount",
+            name="restored_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="mailrule",
+            name="deleted_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="mailrule",
+            name="restored_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="processedmail",
+            name="deleted_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="processedmail",
+            name="restored_at",
+            field=models.DateTimeField(blank=True, null=True),
+        ),
+    ]