Add content matching to workflow trigger

docs/usage.md

@@ -320,7 +320,8 @@ Workflows allow you to filter by:
 - File path, including wildcards. Note that enabling `PAPERLESS_CONSUMER_RECURSIVE` would allow, for
   example, automatically assigning documents to different owners based on the upload directory.
 - Mail rule. Choosing this option will force 'mail fetch' to be the workflow source.
-- Tags (`Added` and `Updated` triggers only). Will filter for documents with any of the specified tags
+- Content matching (`Added` and `Updated` triggers only). Filter document content using the matching settings.
+- Tags (`Added` and `Updated` triggers only). Filter for documents with any of the specified tags
 - Document type (`Added` and `Updated` triggers only). Filter documents with this doc type
 - Correspondent (`Added` and `Updated` triggers only). Filter documents with this correspondent
 

src-ui/src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.html

@@ -181,6 +181,15 @@
           <pngx-input-text i18n-title title="Filter path" formControlName="filter_path" i18n-hint hint="Apply to documents that match this path. Wildcards specified as * are allowed. Case insensitive.</a>" [error]="error?.filter_path"></pngx-input-text>
           <pngx-input-select i18n-title title="Filter mail rule" [items]="mailRules" [allowNull]="true" formControlName="filter_mailrule" i18n-hint hint="Apply to documents consumed via this mail rule." [error]="error?.filter_mailrule"></pngx-input-select>
         }
+        @if (formGroup.get('type').value === WorkflowTriggerType.DocumentAdded || formGroup.get('type').value === WorkflowTriggerType.DocumentUpdated) {
+          <pngx-input-select i18n-title title="Content matching algorithm" [items]="getMatchingAlgorithms()" formControlName="matching_algorithm"></pngx-input-select>
+          @if (patternRequired) {
+            <pngx-input-text i18n-title title="Content matching pattern" formControlName="match" [error]="error?.match"></pngx-input-text>
+          }
+          @if (patternRequired) {
+            <pngx-input-check i18n-title title="Case insensitive" formControlName="is_insensitive"></pngx-input-check>
+          }
+        }
       </div>
       @if (formGroup.get('type').value === WorkflowTriggerType.DocumentAdded || formGroup.get('type').value === WorkflowTriggerType.DocumentUpdated) {
         <div class="col-md-6">

src-ui/src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.spec.ts

@@ -37,6 +37,7 @@ import {
   WorkflowAction,
   WorkflowActionType,
 } from 'src/app/data/workflow-action'
+import { MATCHING_ALGORITHMS, MATCH_AUTO } from 'src/app/data/matching-model'
 
 const workflow: Workflow = {
   name: 'Workflow 1',
@@ -216,4 +217,10 @@ describe('ConsumptionTemplateEditDialogComponent', () => {
     expect(action1.id).toBeNull()
     expect(action2.id).toBeNull()
   })
+
+  it('should not include auto matching in algorithms', () => {
+    expect(component.getMatchingAlgorithms()).not.toContain(
+      MATCHING_ALGORITHMS.find((a) => a.id === MATCH_AUTO)
+    )
+  })
 })

src-ui/src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts

@@ -26,6 +26,11 @@ import {
   WorkflowActionType,
 } from 'src/app/data/workflow-action'
 import { CdkDragDrop, moveItemInArray } from '@angular/cdk/drag-drop'
+import {
+  MATCHING_ALGORITHMS,
+  MATCH_AUTO,
+  MATCH_NONE,
+} from 'src/app/data/matching-model'
 
 export const DOCUMENT_SOURCE_OPTIONS = [
   {
@@ -64,6 +69,10 @@ export const WORKFLOW_ACTION_OPTIONS = [
   },
 ]
 
+const TRIGGER_MATCHING_ALGORITHMS = MATCHING_ALGORITHMS.filter(
+  (a) => a.id !== MATCH_AUTO
+)
+
 @Component({
   selector: 'pngx-workflow-edit-dialog',
   templateUrl: './workflow-edit-dialog.component.html',
@@ -141,6 +150,11 @@ export class WorkflowEditDialogComponent
     })
   }
 
+  getMatchingAlgorithms() {
+    // No auto matching
+    return TRIGGER_MATCHING_ALGORITHMS
+  }
+
   ngOnInit(): void {
     super.ngOnInit()
     this.updateTriggerActionFields()
@@ -165,6 +179,9 @@ export class WorkflowEditDialogComponent
           filter_filename: new FormControl(trigger.filter_filename),
           filter_path: new FormControl(trigger.filter_path),
           filter_mailrule: new FormControl(trigger.filter_mailrule),
+          matching_algorithm: new FormControl(MATCH_NONE),
+          match: new FormControl(''),
+          is_insensitive: new FormControl(true),
           filter_has_tags: new FormControl(trigger.filter_has_tags),
           filter_has_correspondent: new FormControl(
             trigger.filter_has_correspondent

src-ui/src/app/data/workflow-trigger.ts

@@ -23,6 +23,12 @@ export interface WorkflowTrigger extends ObjectWithId {
 
   filter_mailrule?: number // MailRule.id
 
+  match?: string
+
+  matching_algorithm?: number
+
+  is_insensitive?: boolean
+
   filter_has_tags?: number[] // Tag.id[]
 
   filter_has_correspondent?: number // Correspondent.id

src/documents/matching.py

@@ -21,9 +21,13 @@ logger = logging.getLogger("paperless.matching")
 
 def log_reason(matching_model: MatchingModel, document: Document, reason: str):
     class_name = type(matching_model).__name__
+    name = (
+        matching_model.name
+        if hasattr(matching_model, "name")
+        else matching_model.__str__()
+    )
     logger.debug(
-        f"{class_name} {matching_model.name} matched on document "
+        f"{class_name} {name} matched on document {document} because {reason}",
-        f"{document} because {reason}",
     )
 
 
@@ -318,6 +322,15 @@ def document_matches_workflow(
             ):
                 # document is type Document
 
+                if (
+                    trigger.matching_algorithm > MatchingModel.MATCH_NONE
+                    and not matches(trigger, document)
+                ):
+                    log_match_failure(
+                        f"Document content matching settings for algorithm '{trigger.matching_algorithm}' did not match",
+                    )
+                    trigger_matched = False
+
                 # Document has_tags vs document tags
                 if (
                     trigger.filter_has_tags.all().count() > 0

src/documents/migrations/1044_workflow_workflowaction_workflowtrigger_and_more.py

@@ -407,6 +407,29 @@ class Migration(migrations.Migration):
                         verbose_name="filter documents from this mail rule",
                     ),
                 ),
+                (
+                    "matching_algorithm",
+                    models.PositiveIntegerField(
+                        choices=[
+                            (0, "None"),
+                            (1, "Any word"),
+                            (2, "All words"),
+                            (3, "Exact match"),
+                            (4, "Regular expression"),
+                            (5, "Fuzzy word"),
+                        ],
+                        default=0,
+                        verbose_name="matching algorithm",
+                    ),
+                ),
+                (
+                    "match",
+                    models.CharField(blank=True, max_length=256, verbose_name="match"),
+                ),
+                (
+                    "is_insensitive",
+                    models.BooleanField(default=True, verbose_name="is insensitive"),
+                ),
                 (
                     "filter_has_tags",
                     models.ManyToManyField(

src/documents/models.py

@@ -889,6 +889,15 @@ if settings.AUDIT_LOG_ENABLED:
 
 
 class WorkflowTrigger(models.Model):
+    class WorkflowTriggerMatching(models.IntegerChoices):
+        # No auto matching
+        NONE = MatchingModel.MATCH_NONE, _("None")
+        ANY = MatchingModel.MATCH_ANY, _("Any word")
+        ALL = MatchingModel.MATCH_ALL, _("All words")
+        LITERAL = MatchingModel.MATCH_LITERAL, _("Exact match")
+        REGEX = MatchingModel.MATCH_REGEX, _("Regular expression")
+        FUZZY = MatchingModel.MATCH_FUZZY, _("Fuzzy word")
+
     class WorkflowTriggerType(models.IntegerChoices):
         CONSUMPTION = 1, _("Consumption")
         DOCUMENT_ADDED = 2, _("Document Added")
@@ -943,6 +952,16 @@ class WorkflowTrigger(models.Model):
         verbose_name=_("filter documents from this mail rule"),
     )
 
+    match = models.CharField(_("match"), max_length=256, blank=True)
+
+    matching_algorithm = models.PositiveIntegerField(
+        _("matching algorithm"),
+        choices=WorkflowTriggerMatching.choices,
+        default=WorkflowTriggerMatching.NONE,
+    )
+
+    is_insensitive = models.BooleanField(_("is insensitive"), default=True)
+
     filter_has_tags = models.ManyToManyField(
         Tag,
         blank=True,

src/documents/serialisers.py

@@ -1302,6 +1302,9 @@ class WorkflowTriggerSerializer(serializers.ModelSerializer):
             "filter_path",
             "filter_filename",
             "filter_mailrule",
+            "matching_algorithm",
+            "match",
+            "is_insensitive",
             "filter_has_tags",
             "filter_has_correspondent",
             "filter_has_document_type",

src/documents/tests/test_workflows.py

@@ -16,6 +16,7 @@ from documents.models import Correspondent
 from documents.models import CustomField
 from documents.models import Document
 from documents.models import DocumentType
+from documents.models import MatchingModel
 from documents.models import StoragePath
 from documents.models import Tag
 from documents.models import Workflow
@@ -742,6 +743,81 @@ class TestWorkflows(DirectoriesMixin, FileSystemAssertsMixin, APITestCase):
             expected_str = f"Document filename {doc.original_filename} does not match"
             self.assertIn(expected_str, cm.output[1])
 
+    def test_document_added_match_content_matching(self):
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
+            matching_algorithm=MatchingModel.MATCH_LITERAL,
+            match="foo",
+            is_insensitive=True,
+        )
+        action = WorkflowAction.objects.create(
+            assign_title="Doc content matching worked",
+            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",
+            content="Hello world foo bar",
+        )
+
+        with self.assertLogs("paperless.matching", level="DEBUG") as cm:
+            document_consumption_finished.send(
+                sender=self.__class__,
+                document=doc,
+            )
+            expected_str = f"WorkflowTrigger {trigger} matched on document"
+            expected_str2 = 'because it contains this string: "foo"'
+            self.assertIn(expected_str, cm.output[0])
+            self.assertIn(expected_str2, cm.output[0])
+            expected_str = f"Document matched {trigger} from {w}"
+            self.assertIn(expected_str, cm.output[1])
+
+    def test_document_added_no_match_content_matching(self):
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
+            matching_algorithm=MatchingModel.MATCH_LITERAL,
+            match="foo",
+            is_insensitive=True,
+        )
+        action = WorkflowAction.objects.create(
+            assign_title="Doc content matching worked",
+            assign_owner=self.user2,
+        )
+        action.save()
+        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",
+            content="Hello world bar",
+        )
+
+        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 content matching settings for algorithm '{trigger.matching_algorithm}' did not match"
+            self.assertIn(expected_str, cm.output[1])
+
     def test_document_added_no_match_tags(self):
         trigger = WorkflowTrigger.objects.create(
             type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
@@ -751,7 +827,6 @@ class TestWorkflows(DirectoriesMixin, FileSystemAssertsMixin, APITestCase):
             assign_title="Doc assign owner",
             assign_owner=self.user2,
         )
-        action.save()
         w = Workflow.objects.create(
             name="Workflow 1",
             order=0,