From 79d3bc86155a6258eb11f43553a12343eb8c2f93 Mon Sep 17 00:00:00 2001 From: Sleeps Date: Wed, 7 Oct 2026 13:52:44 +0100 Subject: [PATCH] Persist and page detailed index reports --- scene_search/index_jobs.py | 127 ++++++++++++++++++++++++++++++++++--- 1 file changed, 119 insertions(+), 8 deletions(-) diff --git a/scene_search/index_jobs.py b/scene_search/index_jobs.py index 8bb6cf2..df8ed62 100644 --- a/scene_search/index_jobs.py +++ b/scene_search/index_jobs.py @@ -6,6 +6,7 @@ from datetime import datetime, timezone from typing import Any from .database import connect, init_db +from .index_report import load_index_report, save_index_report from .jellyfin_index import ( build_jellyfin_client, index_libraries, @@ -40,6 +41,39 @@ class IndexJobManager: with self._state_lock: return deepcopy(self._state) + def report( + self, + *, + category: str | None = None, + offset: int = 0, + limit: int = 200, + ) -> dict[str, Any]: + report = load_index_report() + items = list(report.get("items") or []) + if category: + items = [ + item + for item in items + if str(item.get("status") or "") == category + ] + + total = len(items) + page = items[offset:offset + limit] + return { + "available": bool(report.get("available", False)), + "kind": report.get("kind"), + "status": report.get("status"), + "started_at": report.get("started_at"), + "finished_at": report.get("finished_at"), + "error": report.get("error"), + "summary": report.get("summary") or {}, + "category": category, + "offset": offset, + "limit": limit, + "total": total, + "items": page, + } + def libraries(self) -> list[dict[str, Any]]: client = build_jellyfin_client() libraries = client.media_folders() @@ -92,7 +126,9 @@ class IndexJobManager: for value in library_ids if str(value).strip() } + started_at = datetime.now(timezone.utc).isoformat() result = reconcile_selected_libraries(selected_ids) + removed_items = list(result.pop("removed_items", []) or []) removed_ids = [ str(value) for value in (result.get("removed_library_ids") or []) @@ -104,6 +140,26 @@ class IndexJobManager: + ", ".join(removed_ids) + f" ({int(result.get('removed_media') or 0)} media item(s))" ) + + finished_at = datetime.now(timezone.utc).isoformat() + save_index_report( + { + "available": True, + "kind": "library_selection", + "status": "complete", + "started_at": started_at, + "finished_at": finished_at, + "error": None, + "summary": { + "indexed": 0, + "skipped": 0, + "failed": 0, + "pruned": int(result.get("removed_media") or 0), + "removed_libraries": int(result.get("removed_libraries") or 0), + }, + "items": removed_items, + } + ) return result def start(self, library_ids: list[str], *, force: bool = False) -> dict[str, Any]: @@ -208,8 +264,11 @@ class IndexJobManager: selected_ids: set[str], force: bool, ) -> None: + report_items: list[dict[str, object]] = [] + started_at = str(self.status().get("started_at") or datetime.now(timezone.utc).isoformat()) try: removed = reconcile_selected_libraries(selected_ids) + report_items.extend(list(removed.pop("removed_items", []) or [])) removed_ids = [ str(value) for value in (removed.get("removed_library_ids") or []) @@ -229,17 +288,34 @@ class IndexJobManager: ) if not libraries: + finished_at = datetime.now(timezone.utc).isoformat() + summary = { + "library_total": 0, + "indexed": 0, + "skipped": 0, + "failed": 0, + "pruned": int(removed.get("removed_media") or 0), + "removed_libraries": int(removed.get("removed_libraries") or 0), + } self._progress( { "running": False, "stage": "complete", - "finished_at": datetime.now(timezone.utc).isoformat(), + "finished_at": finished_at, "documents_processed": 0, - "library_total": 0, - "indexed": 0, - "skipped": 0, - "failed": 0, - "pruned": int(removed.get("removed_media") or 0), + **summary, + } + ) + save_index_report( + { + "available": True, + "kind": "index", + "status": "complete", + "started_at": started_at, + "finished_at": finished_at, + "error": None, + "summary": summary, + "items": report_items, } ) return @@ -253,6 +329,7 @@ class IndexJobManager: embedder=embedder, force=force, progress=self._progress, + report_items=report_items, ) retained_index_changed = ( int(summary.get("indexed") or 0) > 0 @@ -276,22 +353,56 @@ class IndexJobManager: "skipping full Meilisearch rebuild." ) + finished_at = datetime.now(timezone.utc).isoformat() self._progress( { "running": False, "stage": "complete", - "finished_at": datetime.now(timezone.utc).isoformat(), + "finished_at": finished_at, "documents_processed": documents, "full_meili_rebuild": retained_index_changed, **summary, } ) + save_index_report( + { + "available": True, + "kind": "index", + "status": "complete", + "started_at": started_at, + "finished_at": finished_at, + "error": None, + "summary": { + **summary, + "documents_processed": documents, + "full_meili_rebuild": retained_index_changed, + }, + "items": report_items, + } + ) except Exception as exc: + finished_at = datetime.now(timezone.utc).isoformat() self._progress( { "running": False, "stage": "failed", - "finished_at": datetime.now(timezone.utc).isoformat(), + "finished_at": finished_at, "error": str(exc), } ) + save_index_report( + { + "available": True, + "kind": "index", + "status": "failed", + "started_at": started_at, + "finished_at": finished_at, + "error": str(exc), + "summary": { + "indexed": sum(1 for item in report_items if item.get("status") == "indexed"), + "failed": sum(1 for item in report_items if item.get("status") == "failed"), + "pruned": sum(1 for item in report_items if item.get("status") == "removed"), + }, + "items": report_items, + } + )