[books] Fix list page_data for old book scrobbles

vrobbler/apps/scrobbles/migrations/0096_convert_book_page_data_to_dict.py

@@ -0,0 +1,35 @@
+from django.db import migrations
+
+
+def convert_page_data_to_dict(apps, schema_editor):
+    Scrobble = apps.get_model("scrobbles", "Scrobble")
+    for scrobble in Scrobble.objects.filter(media_type="Book").exclude(
+        log__page_data=None
+    ):
+        page_data = scrobble.log.get("page_data")
+        if isinstance(page_data, list):
+            new_page_data = {}
+            for entry in page_data:
+                page_num = entry.get("page_number")
+                if page_num is not None:
+                    try:
+                        page_num = int(page_num)
+                    except (ValueError, TypeError):
+                        continue
+                    new_page_data[page_num] = entry
+            scrobble.log["page_data"] = new_page_data
+            scrobble.save(update_fields=["log"])
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("scrobbles", "0095_backfill_null_visibility"),
+    ]
+
+    operations = [
+        migrations.RunPython(
+            convert_page_data_to_dict,
+            reverse_code=migrations.RunPython.noop,
+        ),
+    ]

vrobbler/apps/scrobbles/models.py

@@ -1412,20 +1412,18 @@ class Scrobble(TimeStampedModel):
                 or scrobble_data["playback_status"] == "stopped"
             ):
                 if read_log_page:
-                    page_list = scrobble.log.get("page_data", [])
-                    if page_list:
-                        for page in page_list:
+                    page_data = scrobble.log.get("page_data", {})
+                    if page_data:
+                        for page_num, page in page_data.items():
                             if not page.get("end_ts", None):
                                 page["end_ts"] = int(timezone.now().timestamp())
                                 page["duration"] = page["end_ts"] - page.get("start_ts")
 
-                    page_list.append(
-                        BookPageLogData(
-                            page_number=read_log_page,
-                            start_ts=int(timezone.now().timestamp()),
-                        )
+                    page_data[read_log_page] = BookPageLogData(
+                        page_number=read_log_page,
+                        start_ts=int(timezone.now().timestamp()),
                     )
-                    scrobble.log["page_data"] = page_list
+                    scrobble.log["page_data"] = page_data
                     scrobble.save(update_fields=["log"])
                 elif "log" in scrobble_data.keys() and scrobble.log:
                     scrobble_data["log"] = scrobble.log | scrobble_data["log"]
@@ -1436,12 +1434,12 @@ class Scrobble(TimeStampedModel):
 
         if read_log_page:
             scrobble_data["log"] = BookLogData(
-                page_data=[
-                    BookPageLogData(
+                page_data={
+                    read_log_page: BookPageLogData(
                         page_number=read_log_page,
                         start_ts=int(timezone.now().timestamp()),
                     )
-                ]
+                }
             )
 
         logger.info(
@@ -1783,30 +1781,24 @@ class Scrobble(TimeStampedModel):
         page_data = self.log.get("page_data")
 
         if page_data:
-            # --- Sort safely by numeric page_number ---
-            def safe_page_number(entry):
-                try:
-                    return int(getattr("page_number", entry), 0)
-                except (ValueError, TypeError):
-                    return float("inf")
-
             if isinstance(page_data, dict):
-                logger.warning("Page data is dict, migrate koreader data")
-                return
+                valid_pages = sorted(int(k) for k in page_data.keys())
+                if valid_pages:
+                    self.log["page_start"] = min(valid_pages)
+                    self.log["page_end"] = max(valid_pages)
+                    self.log["pages_read"] = len(set(valid_pages))
+            elif isinstance(page_data, list):
+                valid_pages = []
+                for page in page_data:
+                    try:
+                        valid_pages.append(int(page["page_number"]))
+                    except (ValueError, TypeError):
+                        continue
 
-            page_data.sort(key=safe_page_number)
-
-            valid_pages = []
-            for page in page_data:
-                try:
-                    valid_pages.append(int(page["page_number"]))
-                except (ValueError, TypeError):
-                    continue
-
-            if valid_pages:
-                self.log["page_start"] = min(valid_pages)
-                self.log["page_end"] = max(valid_pages)
-                self.log["pages_read"] = len(set(valid_pages))
+                if valid_pages:
+                    self.log["page_start"] = min(valid_pages)
+                    self.log["page_end"] = max(valid_pages)
+                    self.log["pages_read"] = len(set(valid_pages))
         else:
             page_start = self.log.get("page_start")
             page_end = self.log.get("page_end")