[importers] Fix scale file checker

vrobbler/apps/scrobbles/importers/webdav.py

@@ -507,7 +507,12 @@ def scan_webdav_for_ebird(webdav_client, user_id):
 
 
 def scan_webdav_for_scale(webdav_client, user_id):
-    """Download .csv files from WebDAV var/scale/ and queue imports for new files."""
+    """Download .csv files from WebDAV var/scale/ and queue imports for new files.
+
+    Because the scale CSV always has the same filename but grows by appending
+    rows, we detect changes by downloading the file and comparing its content
+    hash against the last completed import, rather than checking the filename.
+    """
     from scrobbles.models import ScaleCSVImport
     from scrobbles.tasks import process_scale_csv_import
 
@@ -530,28 +535,41 @@ def scan_webdav_for_scale(webdav_client, user_id):
         return 0
 
     new_imports = 0
-    already_imported = set(
-        ScaleCSVImport.objects.filter(user_id=user_id).values_list(
-            "original_filename", flat=True
-        )
-    )
 
     for fname in files:
         fname = os.path.basename(fname)
         if not fname.lower().endswith(".csv"):
             continue
-        if fname in already_imported:
-            logger.debug(f"Skipping already-imported {fname}")
-            continue
 
         tmp = tempfile.NamedTemporaryFile(delete=False, suffix=fname)
         try:
             webdav_client.download_sync(
                 remote_path=f"{scale_path}/{fname}", local_path=tmp.name
             )
+
+            new_hash = get_file_md5_hash(tmp.name)
+
+            last_import = (
+                ScaleCSVImport.objects.filter(
+                    user_id=user_id,
+                    original_filename=fname,
+                    processed_finished__isnull=False,
+                )
+                .order_by("-processed_finished")
+                .first()
+            )
+            if last_import and last_import.file_hash == new_hash:
+                logger.debug(
+                    "Scale CSV %s unchanged (hash match), skipping",
+                    fname,
+                    extra={"user_id": user_id, "hash": new_hash},
+                )
+                continue
+
             imp = ScaleCSVImport.objects.create(
                 user_id=user_id,
                 original_filename=fname,
+                file_hash=new_hash,
             )
             with open(tmp.name, "rb") as f:
                 imp.csv_file.save(fname, f, save=True)