paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2026-01-08 21:24:26 -06:00
Code Issues Packages Projects Releases Wiki Activity

Performance: avoid unnecessary filename operations on bulk custom field updates (#11558)

Browse Source
This commit is contained in:
shamoon
2025-12-12 07:50:51 -08:00
committed by GitHub
parent 3f81b432ec
commit 3b4d958b97
2 changed files with 117 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
src/documents/signals/handlers.py
View File

@@ -28,6 +28,7 @@ from documents import matching
from documents.caching import clear_document_caches
from documents.file_handling import create_source_path_directory
from documents.file_handling import delete_empty_directories
from documents.file_handling import generate_filename
from documents.file_handling import generate_unique_filename
from documents.models import CustomField
from documents.models import CustomFieldInstance
@@ -42,6 +43,7 @@ from documents.models import WorkflowAction
from documents.models import WorkflowRun
from documents.models import WorkflowTrigger
from documents.permissions import get_objects_for_user_owner_aware
from documents.templating.utils import convert_format_str_to_template_format
from documents.workflows.actions import build_workflow_action_context
from documents.workflows.actions import execute_email_action
from documents.workflows.actions import execute_webhook_action
@@ -389,6 +391,19 @@ class CannotMoveFilesException(Exception):
pass
def _filename_template_uses_custom_fields(doc: Document) -> bool:
template = None
if doc.storage_path is not None:
template = doc.storage_path.path
elif settings.FILENAME_FORMAT is not None:
template = convert_format_str_to_template_format(settings.FILENAME_FORMAT)
if not template:
return False
return "custom_fields" in template
# should be disabled in /src/documents/management/commands/document_importer.py handle
@receiver(models.signals.post_save, sender=CustomFieldInstance, weak=False)
@receiver(models.signals.m2m_changed, sender=Document.tags.through, weak=False)
@@ -399,6 +414,8 @@ def update_filename_and_move_files(
**kwargs,
):
if isinstance(instance, CustomFieldInstance):
if not _filename_template_uses_custom_fields(instance.document):
return
instance = instance.document
def validate_move(instance, old_path: Path, new_path: Path):
@@ -436,21 +453,47 @@ def update_filename_and_move_files(
old_filename = instance.filename
old_source_path = instance.source_path
candidate_filename = generate_filename(instance)
candidate_source_path = (
settings.ORIGINALS_DIR / candidate_filename
).resolve()
if candidate_filename == Path(old_filename):
new_filename = Path(old_filename)
elif (
candidate_source_path.exists()
and candidate_source_path != old_source_path
):
# Only fall back to unique search when there is an actual conflict
new_filename = generate_unique_filename(instance)
else:
new_filename = candidate_filename
# Need to convert to string to be able to save it to the db
instance.filename = str(generate_unique_filename(instance))
instance.filename = str(new_filename)
move_original = old_filename != instance.filename
old_archive_filename = instance.archive_filename
old_archive_path = instance.archive_path
if instance.has_archive_version:
# Need to convert to string to be able to save it to the db
instance.archive_filename = str(
generate_unique_filename(
archive_candidate = generate_filename(instance, archive_filename=True)
archive_candidate_path = (
settings.ARCHIVE_DIR / archive_candidate
).resolve()
if archive_candidate == Path(old_archive_filename):
new_archive_filename = Path(old_archive_filename)
elif (
archive_candidate_path.exists()
and archive_candidate_path != old_archive_path
):
new_archive_filename = generate_unique_filename(
instance,
archive_filename=True,
),
)
)
else:
new_archive_filename = archive_candidate
instance.archive_filename = str(new_archive_filename)
move_archive = old_archive_filename != instance.archive_filename
else: