paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2026-01-24 22:39:02 -06:00
Code Issues Packages Projects Releases Wiki Activity

Enhancement: Add 'any of' workflow trigger filters

Browse Source
This commit is contained in:
shamoon
2025-12-17 14:25:58 -08:00
parent 07eb3c4761
commit 5e1fd1dafa
9 changed files with 398 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
src/documents/matching.py
View File

@@ -403,6 +403,18 @@ def existing_document_matches_workflow(
f"Document tags {list(document.tags.all())} include excluded tags {list(trigger_has_not_tags_qs)}",
)
allowed_correspondent_ids = set(
trigger.filter_has_any_correspondents.values_list("id", flat=True),
)
if (
allowed_correspondent_ids
and document.correspondent_id not in allowed_correspondent_ids
):
return (
False,
f"Document correspondent {document.correspondent} is not one of {list(trigger.filter_has_any_correspondents.all())}",
)
# Document correspondent vs trigger has_correspondent
if (
trigger.filter_has_correspondent_id is not None
@@ -424,6 +436,17 @@ def existing_document_matches_workflow(
f"Document correspondent {document.correspondent} is excluded by {list(trigger.filter_has_not_correspondents.all())}",
)
allowed_document_type_ids = set(
trigger.filter_has_any_document_types.values_list("id", flat=True),
)
if allowed_document_type_ids and (
document.document_type_id not in allowed_document_type_ids
):
return (
False,
f"Document doc type {document.document_type} is not one of {list(trigger.filter_has_any_document_types.all())}",
)
# Document document_type vs trigger has_document_type
if (
trigger.filter_has_document_type_id is not None
@@ -445,6 +468,17 @@ def existing_document_matches_workflow(
f"Document doc type {document.document_type} is excluded by {list(trigger.filter_has_not_document_types.all())}",
)
allowed_storage_path_ids = set(
trigger.filter_has_any_storage_paths.values_list("id", flat=True),
)
if allowed_storage_path_ids and (
document.storage_path_id not in allowed_storage_path_ids
):
return (
False,
f"Document storage path {document.storage_path} is not one of {list(trigger.filter_has_any_storage_paths.all())}",
)
# Document storage_path vs trigger has_storage_path
if (
trigger.filter_has_storage_path_id is not None
@@ -532,6 +566,10 @@ def prefilter_documents_by_workflowtrigger(
# Correspondent, DocumentType, etc. filtering
if trigger.filter_has_any_correspondents.exists():
documents = documents.filter(
correspondent__in=trigger.filter_has_any_correspondents.all(),
)
if trigger.filter_has_correspondent is not None:
documents = documents.filter(
correspondent=trigger.filter_has_correspondent,
@@ -541,6 +579,10 @@ def prefilter_documents_by_workflowtrigger(
correspondent__in=trigger.filter_has_not_correspondents.all(),
)
if trigger.filter_has_any_document_types.exists():
documents = documents.filter(
document_type__in=trigger.filter_has_any_document_types.all(),
)
if trigger.filter_has_document_type is not None:
documents = documents.filter(
document_type=trigger.filter_has_document_type,
@@ -550,6 +592,10 @@ def prefilter_documents_by_workflowtrigger(
document_type__in=trigger.filter_has_not_document_types.all(),
)
if trigger.filter_has_any_storage_paths.exists():
documents = documents.filter(
storage_path__in=trigger.filter_has_any_storage_paths.all(),
)
if trigger.filter_has_storage_path is not None:
documents = documents.filter(
storage_path=trigger.filter_has_storage_path,
@@ -604,8 +650,11 @@ def document_matches_workflow(
"filter_has_tags",
"filter_has_all_tags",
"filter_has_not_tags",
"filter_has_any_document_types",
"filter_has_not_document_types",
"filter_has_any_correspondents",
"filter_has_not_correspondents",
"filter_has_any_storage_paths",
"filter_has_not_storage_paths",
)
)

43
src/documents/migrations/1075_workflowtrigger_filter_has_any_correspondents_and_more.py Normal file
View File

@@ -0,0 +1,43 @@
# Generated by Django 5.2.7 on 2025-12-17 22:25
from django.db import migrations
from django.db import models
class Migration(migrations.Migration):
dependencies = [
("documents", "1074_workflowrun_deleted_at_workflowrun_restored_at_and_more"),
]
operations = [
migrations.AddField(
model_name="workflowtrigger",
name="filter_has_any_correspondents",
field=models.ManyToManyField(
blank=True,
related_name="workflowtriggers_has_any_correspondent",
to="documents.correspondent",
verbose_name="has one of these correspondents",
),
),
migrations.AddField(
model_name="workflowtrigger",
name="filter_has_any_document_types",
field=models.ManyToManyField(
blank=True,
related_name="workflowtriggers_has_any_document_type",
to="documents.documenttype",
verbose_name="has one of these document types",
),
),
migrations.AddField(
model_name="workflowtrigger",
name="filter_has_any_storage_paths",
field=models.ManyToManyField(
blank=True,
related_name="workflowtriggers_has_any_storage_path",
to="documents.storagepath",
verbose_name="has one of these storage paths",
),
),
]

21
src/documents/models.py
View File

@@ -1087,6 +1087,13 @@ class WorkflowTrigger(models.Model):
verbose_name=_("has this document type"),
)
filter_has_any_document_types = models.ManyToManyField(
DocumentType,
blank=True,
related_name="workflowtriggers_has_any_document_type",
verbose_name=_("has one of these document types"),
)
filter_has_not_document_types = models.ManyToManyField(
DocumentType,
blank=True,
@@ -1109,6 +1116,13 @@ class WorkflowTrigger(models.Model):
verbose_name=_("does not have these correspondent(s)"),
)
filter_has_any_correspondents = models.ManyToManyField(
Correspondent,
blank=True,
related_name="workflowtriggers_has_any_correspondent",
verbose_name=_("has one of these correspondents"),
)
filter_has_storage_path = models.ForeignKey(
StoragePath,
null=True,
@@ -1117,6 +1131,13 @@ class WorkflowTrigger(models.Model):
verbose_name=_("has this storage path"),
)
filter_has_any_storage_paths = models.ManyToManyField(
StoragePath,
blank=True,
related_name="workflowtriggers_has_any_storage_path",
verbose_name=_("has one of these storage paths"),
)
filter_has_not_storage_paths = models.ManyToManyField(
StoragePath,
blank=True,

27
src/documents/serialisers.py
View File

@@ -2295,8 +2295,11 @@ class WorkflowTriggerSerializer(serializers.ModelSerializer):
"filter_has_all_tags",
"filter_has_not_tags",
"filter_custom_field_query",
"filter_has_any_correspondents",
"filter_has_not_correspondents",
"filter_has_any_document_types",
"filter_has_not_document_types",
"filter_has_any_storage_paths",
"filter_has_not_storage_paths",
"filter_has_correspondent",
"filter_has_document_type",
@@ -2534,14 +2537,26 @@ class WorkflowSerializer(serializers.ModelSerializer):
filter_has_tags = trigger.pop("filter_has_tags", None)
filter_has_all_tags = trigger.pop("filter_has_all_tags", None)
filter_has_not_tags = trigger.pop("filter_has_not_tags", None)
filter_has_any_correspondents = trigger.pop(
"filter_has_any_correspondents",
None,
)
filter_has_not_correspondents = trigger.pop(
"filter_has_not_correspondents",
None,
)
filter_has_any_document_types = trigger.pop(
"filter_has_any_document_types",
None,
)
filter_has_not_document_types = trigger.pop(
"filter_has_not_document_types",
None,
)
filter_has_any_storage_paths = trigger.pop(
"filter_has_any_storage_paths",
None,
)
filter_has_not_storage_paths = trigger.pop(
"filter_has_not_storage_paths",
None,
@@ -2558,14 +2573,26 @@ class WorkflowSerializer(serializers.ModelSerializer):
trigger_instance.filter_has_all_tags.set(filter_has_all_tags)
if filter_has_not_tags is not None:
trigger_instance.filter_has_not_tags.set(filter_has_not_tags)
if filter_has_any_correspondents is not None:
trigger_instance.filter_has_any_correspondents.set(
filter_has_any_correspondents,
)
if filter_has_not_correspondents is not None:
trigger_instance.filter_has_not_correspondents.set(
filter_has_not_correspondents,
)
if filter_has_any_document_types is not None:
trigger_instance.filter_has_any_document_types.set(
filter_has_any_document_types,
)
if filter_has_not_document_types is not None:
trigger_instance.filter_has_not_document_types.set(
filter_has_not_document_types,
)
if filter_has_any_storage_paths is not None:
trigger_instance.filter_has_any_storage_paths.set(
filter_has_any_storage_paths,
)
if filter_has_not_storage_paths is not None:
trigger_instance.filter_has_not_storage_paths.set(
filter_has_not_storage_paths,

30
src/documents/tests/test_api_workflows.py
View File

@@ -186,8 +186,11 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
"filter_has_tags": [self.t1.id],
"filter_has_all_tags": [self.t2.id],
"filter_has_not_tags": [self.t3.id],
"filter_has_any_correspondents": [self.c.id],
"filter_has_not_correspondents": [self.c2.id],
"filter_has_any_document_types": [self.dt.id],
"filter_has_not_document_types": [self.dt2.id],
"filter_has_any_storage_paths": [self.sp.id],
"filter_has_not_storage_paths": [self.sp2.id],
"filter_custom_field_query": json.dumps(
[
@@ -248,14 +251,26 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
set(trigger.filter_has_not_tags.values_list("id", flat=True)),
{self.t3.id},
)
self.assertSetEqual(
set(trigger.filter_has_any_correspondents.values_list("id", flat=True)),
{self.c.id},
)
self.assertSetEqual(
set(trigger.filter_has_not_correspondents.values_list("id", flat=True)),
{self.c2.id},
)
self.assertSetEqual(
set(trigger.filter_has_any_document_types.values_list("id", flat=True)),
{self.dt.id},
)
self.assertSetEqual(
set(trigger.filter_has_not_document_types.values_list("id", flat=True)),
{self.dt2.id},
)
self.assertSetEqual(
set(trigger.filter_has_any_storage_paths.values_list("id", flat=True)),
{self.sp.id},
)
self.assertSetEqual(
set(trigger.filter_has_not_storage_paths.values_list("id", flat=True)),
{self.sp2.id},
@@ -419,8 +434,11 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
"filter_has_tags": [self.t1.id],
"filter_has_all_tags": [self.t2.id],
"filter_has_not_tags": [self.t3.id],
"filter_has_any_correspondents": [self.c.id],
"filter_has_not_correspondents": [self.c2.id],
"filter_has_any_document_types": [self.dt.id],
"filter_has_not_document_types": [self.dt2.id],
"filter_has_any_storage_paths": [self.sp.id],
"filter_has_not_storage_paths": [self.sp2.id],
"filter_custom_field_query": json.dumps(
["AND", [[self.cf1.id, "exact", "value"]]],
@@ -450,14 +468,26 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
workflow.triggers.first().filter_has_not_tags.first(),
self.t3,
)
self.assertEqual(
workflow.triggers.first().filter_has_any_correspondents.first(),
self.c,
)
self.assertEqual(
workflow.triggers.first().filter_has_not_correspondents.first(),
self.c2,
)
self.assertEqual(
workflow.triggers.first().filter_has_any_document_types.first(),
self.dt,
)
self.assertEqual(
workflow.triggers.first().filter_has_not_document_types.first(),
self.dt2,
)
self.assertEqual(
workflow.triggers.first().filter_has_any_storage_paths.first(),
self.sp,
)
self.assertEqual(
workflow.triggers.first().filter_has_not_storage_paths.first(),
self.sp2,

103
src/documents/tests/test_workflows.py
View File

@@ -1276,6 +1276,76 @@ class TestWorkflows(
)
self.assertIn(expected_str, cm.output[1])
def test_document_added_any_filters(self):
trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
)
trigger.filter_has_any_correspondents.set([self.c])
trigger.filter_has_any_document_types.set([self.dt])
trigger.filter_has_any_storage_paths.set([self.sp])
matching_doc = Document.objects.create(
title="sample test",
correspondent=self.c,
document_type=self.dt,
storage_path=self.sp,
original_filename="sample.pdf",
checksum="checksum-any-match",
)
matched, reason = existing_document_matches_workflow(matching_doc, trigger)
self.assertTrue(matched)
self.assertIsNone(reason)
wrong_correspondent = Document.objects.create(
title="wrong correspondent",
correspondent=self.c2,
document_type=self.dt,
storage_path=self.sp,
original_filename="sample2.pdf",
)
matched, reason = existing_document_matches_workflow(
wrong_correspondent,
trigger,
)
self.assertFalse(matched)
self.assertIn("correspondent", reason)
other_document_type = DocumentType.objects.create(name="Other")
wrong_document_type = Document.objects.create(
title="wrong doc type",
correspondent=self.c,
document_type=other_document_type,
storage_path=self.sp,
original_filename="sample3.pdf",
checksum="checksum-wrong-doc-type",
)
matched, reason = existing_document_matches_workflow(
wrong_document_type,
trigger,
)
self.assertFalse(matched)
self.assertIn("doc type", reason)
other_storage_path = StoragePath.objects.create(
name="Other path",
path="/other/",
)
wrong_storage_path = Document.objects.create(
title="wrong storage",
correspondent=self.c,
document_type=self.dt,
storage_path=other_storage_path,
original_filename="sample4.pdf",
checksum="checksum-wrong-storage-path",
)
matched, reason = existing_document_matches_workflow(
wrong_storage_path,
trigger,
)
self.assertFalse(matched)
self.assertIn("storage path", reason)
def test_document_added_custom_field_query_no_match(self):
trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
@@ -1384,6 +1454,39 @@ class TestWorkflows(
self.assertIn(doc1, filtered)
self.assertNotIn(doc2, filtered)
def test_prefilter_documents_any_filters(self):
trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
)
trigger.filter_has_any_correspondents.set([self.c])
trigger.filter_has_any_document_types.set([self.dt])
trigger.filter_has_any_storage_paths.set([self.sp])
allowed_document = Document.objects.create(
title="allowed",
correspondent=self.c,
document_type=self.dt,
storage_path=self.sp,
original_filename="doc-allowed.pdf",
checksum="checksum-any-allowed",
)
blocked_document = Document.objects.create(
title="blocked",
correspondent=self.c2,
document_type=self.dt,
storage_path=self.sp,
original_filename="doc-blocked.pdf",
checksum="checksum-any-blocked",
)
filtered = prefilter_documents_by_workflowtrigger(
Document.objects.all(),
trigger,
)
self.assertIn(allowed_document, filtered)
self.assertNotIn(blocked_document, filtered)
def test_consumption_trigger_requires_filter_configuration(self):
serializer = WorkflowTriggerSerializer(
data={