Initial crack

This commit is contained in:
shamoon
2025-10-07 09:20:37 -07:00
parent 33fd8a6579
commit 1fed785c7d
10 changed files with 448 additions and 6 deletions

View File

@@ -360,10 +360,9 @@ def existing_document_matches_workflow(
)
trigger_matched = False
# Document tags vs trigger has_tags
if (
trigger.filter_has_tags.all().count() > 0
and document.tags.filter(
# Document tags vs trigger has_tags (any of)
if trigger.filter_has_tags.all().count() > 0 and (
document.tags.filter(
id__in=trigger.filter_has_tags.all().values_list("id"),
).count()
== 0
@@ -374,6 +373,36 @@ def existing_document_matches_workflow(
)
trigger_matched = False
# Document tags vs trigger has_all_tags (all of)
if trigger.filter_has_all_tags.all().count() > 0 and trigger_matched:
required_tag_ids = set(
trigger.filter_has_all_tags.all().values_list("id", flat=True),
)
document_tag_ids = set(
document.tags.all().values_list("id", flat=True),
)
missing_tags = required_tag_ids - document_tag_ids
if missing_tags:
reason = (
f"Document tags {document.tags.all()} do not contain all of"
f" {trigger.filter_has_all_tags.all()}",
)
trigger_matched = False
# Document tags vs trigger has_not_tags (none of)
if (
trigger.filter_has_not_tags.all().count() > 0
and trigger_matched
and document.tags.filter(
id__in=trigger.filter_has_not_tags.all().values_list("id"),
).exists()
):
reason = (
f"Document tags {document.tags.all()} include excluded tags"
f" {trigger.filter_has_not_tags.all()}",
)
trigger_matched = False
# Document correspondent vs trigger has_correspondent
if (
trigger.filter_has_correspondent is not None
@@ -438,6 +467,16 @@ def prefilter_documents_by_workflowtrigger(
tags__in=trigger.filter_has_tags.all(),
).distinct()
if trigger.filter_has_all_tags.all().count() > 0:
for tag_id in trigger.filter_has_all_tags.all().values_list("id", flat=True):
documents = documents.filter(tags__id=tag_id)
documents = documents.distinct()
if trigger.filter_has_not_tags.all().count() > 0:
documents = documents.exclude(
tags__in=trigger.filter_has_not_tags.all(),
).distinct()
if trigger.filter_has_correspondent is not None:
documents = documents.filter(
correspondent=trigger.filter_has_correspondent,

View File

@@ -0,0 +1,33 @@
# Generated by Django 5.2.6 on 2025-10-07 16:09
from django.db import migrations
from django.db import models
class Migration(migrations.Migration):
dependencies = [
("documents", "1071_tag_tn_ancestors_count_tag_tn_ancestors_pks_and_more"),
]
operations = [
migrations.AddField(
model_name="workflowtrigger",
name="filter_has_all_tags",
field=models.ManyToManyField(
blank=True,
related_name="workflowtriggers_has_all",
to="documents.tag",
verbose_name="has all of these tag(s)",
),
),
migrations.AddField(
model_name="workflowtrigger",
name="filter_has_not_tags",
field=models.ManyToManyField(
blank=True,
related_name="workflowtriggers_has_not",
to="documents.tag",
verbose_name="does not have these tag(s)",
),
),
]

View File

@@ -1065,6 +1065,20 @@ class WorkflowTrigger(models.Model):
verbose_name=_("has these tag(s)"),
)
filter_has_all_tags = models.ManyToManyField(
Tag,
blank=True,
related_name="workflowtriggers_has_all",
verbose_name=_("has all of these tag(s)"),
)
filter_has_not_tags = models.ManyToManyField(
Tag,
blank=True,
related_name="workflowtriggers_has_not",
verbose_name=_("does not have these tag(s)"),
)
filter_has_document_type = models.ForeignKey(
DocumentType,
null=True,

View File

@@ -2194,6 +2194,8 @@ class WorkflowTriggerSerializer(serializers.ModelSerializer):
"match",
"is_insensitive",
"filter_has_tags",
"filter_has_all_tags",
"filter_has_not_tags",
"filter_has_correspondent",
"filter_has_document_type",
"filter_has_storage_path",
@@ -2414,6 +2416,8 @@ class WorkflowSerializer(serializers.ModelSerializer):
if triggers is not None and triggers is not serializers.empty:
for trigger in triggers:
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)
# Convert sources to strings to handle django-multiselectfield v1.0 changes
WorkflowTriggerSerializer.normalize_workflow_trigger_sources(trigger)
trigger_instance, _ = WorkflowTrigger.objects.update_or_create(
@@ -2422,6 +2426,10 @@ class WorkflowSerializer(serializers.ModelSerializer):
)
if filter_has_tags is not None:
trigger_instance.filter_has_tags.set(filter_has_tags)
if filter_has_all_tags is not None:
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)
set_triggers.append(trigger_instance)
if actions is not None and actions is not serializers.empty:

View File

@@ -184,6 +184,8 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
"filter_filename": "*",
"filter_path": "*/samples/*",
"filter_has_tags": [self.t1.id],
"filter_has_all_tags": [self.t2.id],
"filter_has_not_tags": [self.t3.id],
"filter_has_document_type": self.dt.id,
"filter_has_correspondent": self.c.id,
"filter_has_storage_path": self.sp.id,
@@ -223,6 +225,20 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
)
self.assertEqual(response.status_code, status.HTTP_201_CREATED)
self.assertEqual(Workflow.objects.count(), 2)
workflow = Workflow.objects.get(name="Workflow 2")
trigger = workflow.triggers.first()
self.assertSetEqual(
set(trigger.filter_has_tags.values_list("id", flat=True)),
{self.t1.id},
)
self.assertSetEqual(
set(trigger.filter_has_all_tags.values_list("id", flat=True)),
{self.t2.id},
)
self.assertSetEqual(
set(trigger.filter_has_not_tags.values_list("id", flat=True)),
{self.t3.id},
)
def test_api_create_invalid_workflow_trigger(self):
"""
@@ -376,6 +392,8 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
{
"type": WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
"filter_has_tags": [self.t1.id],
"filter_has_all_tags": [self.t2.id],
"filter_has_not_tags": [self.t3.id],
"filter_has_correspondent": self.c.id,
"filter_has_document_type": self.dt.id,
},
@@ -393,6 +411,14 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
workflow = Workflow.objects.get(id=response.data["id"])
self.assertEqual(workflow.name, "Workflow Updated")
self.assertEqual(workflow.triggers.first().filter_has_tags.first(), self.t1)
self.assertEqual(
workflow.triggers.first().filter_has_all_tags.first(),
self.t2,
)
self.assertEqual(
workflow.triggers.first().filter_has_not_tags.first(),
self.t3,
)
self.assertEqual(workflow.actions.first().assign_title, "Action New Title")
def test_api_update_workflow_no_trigger_actions(self):

View File

@@ -1083,6 +1083,82 @@ class TestWorkflows(
expected_str = f"Document tags {doc.tags.all()} do not include {trigger.filter_has_tags.all()}"
self.assertIn(expected_str, cm.output[1])
def test_document_added_no_match_all_tags(self):
trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
)
trigger.filter_has_all_tags.set([self.t1, self.t2])
action = WorkflowAction.objects.create(
assign_title="Doc assign owner",
assign_owner=self.user2,
)
w = Workflow.objects.create(
name="Workflow 1",
order=0,
)
w.triggers.add(trigger)
w.actions.add(action)
w.save()
doc = Document.objects.create(
title="sample test",
correspondent=self.c,
original_filename="sample.pdf",
)
doc.tags.set([self.t1])
doc.save()
with self.assertLogs("paperless.matching", level="DEBUG") as cm:
document_consumption_finished.send(
sender=self.__class__,
document=doc,
)
expected_str = f"Document did not match {w}"
self.assertIn(expected_str, cm.output[0])
expected_str = (
f"Document tags {doc.tags.all()} do not contain all of"
f" {trigger.filter_has_all_tags.all()}"
)
self.assertIn(expected_str, cm.output[1])
def test_document_added_excluded_tags(self):
trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
)
trigger.filter_has_not_tags.set([self.t3])
action = WorkflowAction.objects.create(
assign_title="Doc assign owner",
assign_owner=self.user2,
)
w = Workflow.objects.create(
name="Workflow 1",
order=0,
)
w.triggers.add(trigger)
w.actions.add(action)
w.save()
doc = Document.objects.create(
title="sample test",
correspondent=self.c,
original_filename="sample.pdf",
)
doc.tags.set([self.t3])
doc.save()
with self.assertLogs("paperless.matching", level="DEBUG") as cm:
document_consumption_finished.send(
sender=self.__class__,
document=doc,
)
expected_str = f"Document did not match {w}"
self.assertIn(expected_str, cm.output[0])
expected_str = (
f"Document tags {doc.tags.all()} include excluded tags"
f" {trigger.filter_has_not_tags.all()}"
)
self.assertIn(expected_str, cm.output[1])
def test_document_added_no_match_doctype(self):
trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,