Fix #781: Added a `check_inplace_files` management command to remove purge the database from references to in-place imported files that don't exist on disk anymore

api/funkwhale_api/music/management/commands/check_inplace_files.py

@@ -0,0 +1,76 @@
+import os
+from argparse import RawTextHelpFormatter
+
+from django.core.management.base import BaseCommand
+
+from django.db import transaction
+
+from funkwhale_api.music import models
+
+
+def progress(buffer, count, total, status=""):
+    bar_len = 60
+    filled_len = int(round(bar_len * count / float(total)))
+
+    bar = "=" * filled_len + "-" * (bar_len - filled_len)
+
+    buffer.write("[%s] %s/%s ...%s\r" % (bar, count, total, status))
+    buffer.flush()
+
+
+class Command(BaseCommand):
+    help = """
+    Loop through all in-place imported files in the database, and verify
+    that the corresponding files are present on the filesystem. If some files are not
+    found and --no-dry-run is specified, the corresponding database objects will be deleted.
+    """
+
+    def create_parser(self, *args, **kwargs):
+        parser = super().create_parser(*args, **kwargs)
+        parser.formatter_class = RawTextHelpFormatter
+        return parser
+
+    def add_arguments(self, parser):
+        parser.add_argument(
+            "--no-dry-run",
+            action="store_false",
+            dest="dry_run",
+            default=True,
+            help="Disable dry run mode and apply pruning for real on the database",
+        )
+
+    @transaction.atomic
+    def handle(self, *args, **options):
+        candidates = models.Upload.objects.filter(source__startswith="file://")
+        candidates = candidates.filter(audio_file__in=["", None])
+        total = candidates.count()
+        self.stdout.write("Checking {} in-place imported files…".format(total))
+
+        missing = []
+        for i, row in enumerate(candidates.values("id", "source")):
+            path = row["source"].replace("file://", "")
+            progress(self.stdout, i + 1, total)
+            if not os.path.exists(path):
+                missing.append((path, row["id"]))
+
+        if missing:
+            for path, _ in missing:
+                self.stdout.write("  {}".format(path))
+            self.stdout.write(
+                "The previous {} paths are referenced in database, but not found on disk!".format(
+                    len(missing)
+                )
+            )
+
+        else:
+            self.stdout.write("All in-place imports have a matching on-disk file")
+            return
+
+        to_delete = candidates.filter(pk__in=[id for _, id in missing])
+        if options["dry_run"]:
+            self.stdout.write(
+                "Nothing was deleted, rerun this command with --no-dry-run to apply the changes"
+            )
+        else:
+            self.stdout.write("Deleting {} uploads…".format(to_delete.count()))
+            to_delete.delete()

api/tests/music/test_commands.py

@@ -1,6 +1,7 @@
 import os
 import pytest
 
+from funkwhale_api.music.management.commands import check_inplace_files
 from funkwhale_api.music.management.commands import fix_uploads
 from funkwhale_api.music.management.commands import prune_library
 
@@ -150,3 +151,35 @@ def test_prune_library(factories, mocker):
 
     for o in [not_prunable_track, not_prunable_album, not_prunable_artist]:
         o.refresh_from_db()
+
+
+def test_check_inplace_files_dry_run(factories, tmpfile):
+    prunable = factories["music.Upload"](source="file:///notfound", audio_file=None)
+    not_prunable = factories["music.Upload"](
+        source="file://{}".format(tmpfile.name), audio_file=None
+    )
+    c = check_inplace_files.Command()
+    c.handle(dry_run=True)
+
+    for u in [prunable, not_prunable]:
+        # nothing pruned, because dry run
+        u.refresh_from_db()
+
+
+def test_check_inplace_files_no_dry_run(factories, tmpfile):
+    prunable = factories["music.Upload"](source="file:///notfound", audio_file=None)
+    not_prunable = [
+        factories["music.Upload"](
+            source="file://{}".format(tmpfile.name), audio_file=None
+        ),
+        factories["music.Upload"](source="upload://"),
+        factories["music.Upload"](source="https://"),
+    ]
+    c = check_inplace_files.Command()
+    c.handle(dry_run=False)
+
+    with pytest.raises(prunable.DoesNotExist):
+        prunable.refresh_from_db()
+
+    for u in not_prunable:
+        u.refresh_from_db()

changes/changelog.d/781.enhancement

@@ -0,0 +1 @@
+Added a `check_inplace_files` management command to remove purge the database from references to in-place imported files that don't exist on disk anymore (#781)

changes/notes.rst

@@ -51,5 +51,16 @@ Users are often surprised by Funkwhale's tendency to keep track, album and artis
 metadata even if no associated files exist.
 
 To help with that, we now offer a ``prune_library`` management command you can run
-to purge your database from obsolete entry. `Please refer to our documentation
+to purge your database from obsolete entries. `Please refer to our documentation
 for usage instructions <https://docs.funkwhale.audio/admin/commands.html#pruning-library>`_.
+
+Check in-place files command
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+When using in-place import with a living audio library, you'll quite often rename or
+remove files from the file system. Unfortunately, Funkwhale keeps a reference to those
+files in the database, which results in unplayable tracks.
+
+To help with that, we now offer a ``check_inplace_files`` management command you can run
+to purge your database from obsolete files. `Please refer to our documentation
+for usage instructions <https://docs.funkwhale.audio/admin/commands.html#remove-obsolete-files-from-database>`_.

docs/admin/commands.rst

@@ -55,3 +55,28 @@ the changes on the database.
     history by default. If you want to include those in the pruning process as well,
     add the corresponding ``--ignore-favorites``, ``--ignore-playlists`` and ``--ignore-listenings``
     flags.
+
+Remove obsolete files from database
+-----------------------------------
+
+When importing using the :ref:`in-place method <in-place-import>`, if you move or remove
+in-place imported files on disk, Funkwhale will still have a reference to those files and won't
+be able to serve them properly.
+
+To help with that, whenever you remove or move files that were previously imported
+with the ``--in-place`` flag, you can run the following command::
+
+    python manage.py check_inplace_files
+
+This command will loop through all the database objects that reference
+an in-place imported file, check that the file is accessible on disk,
+or delete the database object if it's not.
+
+Once you have reviewed the output and are comfortable with the changes, you should rerun
+the command with the ``--no-dry-run`` flag to disable dry run mode and actually delete the
+database objects.
+
+.. warning::
+
+    Running this command with ``--no-dry-run`` is irreversible. Unless you have a backup,
+    there will be no way to retrieve the deleted data.