[books] Fix list page_data for old book scrobbles

PROJECT.org

@@ -88,7 +88,7 @@ fetching and simple saving.
 *** Metadata sources
 **** Scraper
 
-* Backlog [1/16] :vrobbler:project:personal:
+* Backlog [2/17] :vrobbler:project:personal:
 ** TODO [#C] Create small utility to clean up tracks scrobbled with wonky playback times :vrobbler:personal:bug:music:scrobbles:
 :PROPERTIES:
 :ID:       702462cf-d54b-48c6-8a7c-78b8de751deb
@@ -544,6 +544,26 @@ log a warning and move on.
 We should have a global view `/favorites/` that shows the logged in users's
 favorited media objects.
 
+** DONE [#A] Fix book scrobbles where page_data is a list :bug:books:scrobbles:
+:PROPERTIES:
+:ID:       35b323fa-ccc0-4009-b227-8a0f12bbd469
+:END:
+
+*** Description
+
+Comic scrobbling is currently kind of janky. Most of the problems boil down to them
+storing saved page data in a list of dicts rather than a dict keyed off of the page number that
+was read.
+
+We need to adjust comic scrobbling to use a dict of pages keyed off the page number, and also
+write a migration script that runs as a data migration to update any book scrobbles that may
+have page_data as a list.
+
+*** Example data
+#+begin_src python
+{"notes": null, "page_end": 27, "page_data": [{"notes": null, "end_ts": 1771815895, "duration": 14, "start_ts": 1771815881, "description": null, "page_number": "1"}, {"notes": null, "end_ts": 1771815908, "duration": 13, "start_ts": 1771815895, "description": null, "page_number": "1"}, {"notes": null, "end_ts": 1771815913, "duration": 5, "start_ts": 1771815908, "description": null, "page_number": "2"}, {"notes": null, "end_ts": 1771815933, "duration": 20, "start_ts": 1771815913, "description": null, "page_number": "3"}, {"notes": null, "end_ts": 1771815945, "duration": 12, "start_ts": 1771815933, "description": null, "page_number": "4"}, {"notes": null, "end_ts": 1771815983, "duration": 38, "start_ts": 1771815945, "description": null, "page_number": "5"}, {"notes": null, "end_ts": 1771816007, "duration": 24, "start_ts": 1771815983, "description": null, "page_number": "6"}, {"notes": null, "end_ts": 1771816011, "duration": 4, "start_ts": 1771816007, "description": null, "page_number": "7"}, {"notes": null, "end_ts": 1771816013, "duration": 2, "start_ts": 1771816011, "description": null, "page_number": "8"}, {"notes": null, "end_ts": 1771816052, "duration": 39, "start_ts": 1771816013, "description": null, "page_number": "7"}, {"notes": null, "end_ts": 1771816127, "duration": 75, "start_ts": 1771816052, "description": null, "page_number": "8"}, {"notes": null, "end_ts": 1771816134, "duration": 7, "start_ts": 1771816127, "description": null, "page_number": "9"}, {"notes": null, "end_ts": 1771816196, "duration": 62, "start_ts": 1771816134, "description": null, "page_number": "10"}, {"notes": null, "end_ts": 1771816262, "duration": 66, "start_ts": 1771816196, "description": null, "page_number": "11"}, {"notes": null, "end_ts": 1771816293, "duration": 31, "start_ts": 1771816262, "description": null, "page_number": "12"}, {"notes": null, "end_ts": 1771816322, "duration": 29, "start_ts": 1771816293, "description": null, "page_number": "13"}, {"notes": null, "end_ts": 1771816330, "duration": 8, "start_ts": 1771816322, "description": null, "page_number": "14"}, {"notes": null, "end_ts": 1771816368, "duration": 38, "start_ts": 1771816330, "description": null, "page_number": "15"}, {"notes": null, "end_ts": 1771816388, "duration": 20, "start_ts": 1771816368, "description": null, "page_number": "16"}, {"notes": null, "end_ts": 1771816482, "duration": 94, "start_ts": 1771816388, "description": null, "page_number": "17"}, {"notes": null, "end_ts": 1771816550, "duration": 68, "start_ts": 1771816482, "description": null, "page_number": "18"}, {"notes": null, "end_ts": 1771816567, "duration": 17, "start_ts": 1771816550, "description": null, "page_number": "19"}, {"notes": null, "end_ts": 1771816586, "duration": 19, "start_ts": 1771816567, "description": null, "page_number": "20"}, {"notes": null, "end_ts": 1771816597, "duration": 11, "start_ts": 1771816586, "description": null, "page_number": "21"}, {"notes": null, "end_ts": 1771816616, "duration": 19, "start_ts": 1771816597, "description": null, "page_number": "22"}, {"notes": null, "end_ts": 1771816640, "duration": 24, "start_ts": 1771816616, "description": null, "page_number": "23"}, {"notes": null, "end_ts": 1771816690, "duration": 50, "start_ts": 1771816640, "description": null, "page_number": "24"}, {"notes": null, "end_ts": 1771816702, "duration": 12, "start_ts": 1771816690, "description": null, "page_number": "25"}, {"notes": null, "end_ts": 1771816823, "duration": 121, "start_ts": 1771816702, "description": null, "page_number": "26"}, {"notes": null, "end_ts": null, "duration": null, "start_ts": 1771816823, "description": null, "page_number": "27"}], "page_start": 1, "pages_read": 27, "resume_url": null, "description": null, "koreader_hash": null, "long_play_complete": false}
+
+#+end_src
 ** DONE [#A] Lichess imports do not set default visbility :boardgames:bug:importers:lichess:
 :PROPERTIES:
 :ID:       a78f7c72-a20a-8db2-cde0-d92a731d4fba

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", [])
+                    page_data = scrobble.log.get("page_data", {})
-                    if page_list:
+                    if page_data:
-                        for page in page_list:
+                        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(
+                    page_data[read_log_page] = BookPageLogData(
-                        BookPageLogData(
+                        page_number=read_log_page,
-                            page_number=read_log_page,
+                        start_ts=int(timezone.now().timestamp()),
-                            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=[
+                page_data={
-                    BookPageLogData(
+                    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")
+                valid_pages = sorted(int(k) for k in page_data.keys())
-                return
+                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)
+                if valid_pages:
-
+                    self.log["page_start"] = min(valid_pages)
-            valid_pages = []
+                    self.log["page_end"] = max(valid_pages)
-            for page in page_data:
+                    self.log["pages_read"] = len(set(valid_pages))
-                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))
         else:
             page_start = self.log.get("page_start")
             page_end = self.log.get("page_end")