From ea343b1ca4d1b5fc3d1d3c92775be04df20f7b7a Mon Sep 17 00:00:00 2001
From: Trenton Holmes <797416+stumpylog@users.noreply.github.com>
Date: Thu, 21 Mar 2024 18:35:27 -0700
Subject: [PATCH] Clear the cache keys more aggressivly when a document is
 highly likely to be changing

---
 src/documents/caching.py          | 18 +++++++++++++-----
 src/documents/signals/handlers.py |  5 +++--
 src/documents/tasks.py            |  4 ++++
 3 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/src/documents/caching.py b/src/documents/caching.py
index a1f20d086..9abd3bc65 100644
--- a/src/documents/caching.py
+++ b/src/documents/caching.py
@@ -189,13 +189,21 @@ def refresh_metadata_cache(
     cache.touch(doc_key, timeout)
 
 
-def clear_metadata_cache(document_id: int) -> None:
-    doc_key = get_metadata_cache_key(document_id)
-    cache.delete(doc_key)
-
-
 def get_thumbnail_modified_key(document_id: int) -> str:
     """
     Builds the key to store a thumbnail's timestamp
     """
     return f"doc_{document_id}_thumbnail_modified"
+
+
+def clear_document_caches(document_id: int) -> None:
+    """
+    Removes all cached items for the given document
+    """
+    cache.delete_many(
+        [
+            get_suggestion_cache_key(document_id),
+            get_metadata_cache_key(document_id),
+            get_thumbnail_modified_key(document_id),
+        ],
+    )
diff --git a/src/documents/signals/handlers.py b/src/documents/signals/handlers.py
index 85e8126c1..cdfedcb4c 100644
--- a/src/documents/signals/handlers.py
+++ b/src/documents/signals/handlers.py
@@ -23,7 +23,7 @@ from filelock import FileLock
 from guardian.shortcuts import remove_perm
 
 from documents import matching
-from documents.caching import clear_metadata_cache
+from documents.caching import clear_document_caches
 from documents.classifier import DocumentClassifier
 from documents.consumer import parse_doc_title_w_placeholders
 from documents.file_handling import create_source_path_directory
@@ -439,7 +439,8 @@ def update_filename_and_move_files(sender, instance: Document, **kwargs):
                 archive_filename=instance.archive_filename,
                 modified=timezone.now(),
             )
-            clear_metadata_cache(instance.pk)
+            # Clear any caching for this document.  Slightly overkill, but not terrible
+            clear_document_caches(instance.pk)
 
         except (OSError, DatabaseError, CannotMoveFilesException) as e:
             logger.warning(f"Exception during file handling: {e}")
diff --git a/src/documents/tasks.py b/src/documents/tasks.py
index a83c2e6cd..0ab55ac45 100644
--- a/src/documents/tasks.py
+++ b/src/documents/tasks.py
@@ -18,6 +18,7 @@ from whoosh.writing import AsyncWriter
 from documents import index
 from documents import sanity_checker
 from documents.barcodes import BarcodePlugin
+from documents.caching import clear_document_caches
 from documents.classifier import DocumentClassifier
 from documents.classifier import load_classifier
 from documents.consumer import Consumer
@@ -213,6 +214,7 @@ def bulk_update_documents(document_ids):
     ix = index.open_index()
 
     for doc in documents:
+        clear_document_caches(doc.pk)
         document_updated.send(
             sender=None,
             document=doc,
@@ -305,6 +307,8 @@ def update_document_archive_file(document_id):
             with index.open_index_writer() as writer:
                 index.update_document(writer, document)
 
+            clear_document_caches(document.pk)
+
     except Exception:
         logger.exception(
             f"Error while parsing document {document} (ID: {document_id})",