Fix migration

docs/configuration.md

@@ -1146,8 +1146,9 @@ via the consumption directory, you can disable the consumer to save resources.
 
 #### [`PAPERLESS_CONSUMER_DELETE_DUPLICATES=<bool>`](#PAPERLESS_CONSUMER_DELETE_DUPLICATES) {#PAPERLESS_CONSUMER_DELETE_DUPLICATES}
 
-: When the consumer detects a duplicate document, it will not touch
+: As of version 3.0 Paperless-ngx allows duplicate documents to be consumed by default, _except_ when
-the original document. This default behavior can be changed here.
+this setting is enabled. When enabled, Paperless will check if a document with the same hash already
+exists in the system and delete the duplicate file from the consumption directory without consuming it.
 
     Defaults to false.
 

src-ui/src/app/components/admin/tasks/tasks.component.html

@@ -97,6 +97,12 @@
                   <br/><em>(<ng-container i18n>click for full output</ng-container>)</em>
                 }
               </ng-template>
+              @if (task.duplicate_documents?.length > 0) {
+                <div class="small text-warning-emphasis d-flex align-items-center gap-1">
+                  <i-bs class="lh-1" width="1em" height="1em" name="exclamation-triangle"></i-bs>
+                  <span i18n>Duplicate(s) detected</span>
+                </div>
+              }
             </td>
           }
           <td class="d-lg-none">

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

@@ -412,9 +412,6 @@ describe('WorkflowEditDialogComponent', () => {
       return newFilter
     }
 
-    const correspondentAny = addFilterOfType(TriggerFilterType.CorrespondentAny)
-    correspondentAny.get('values').setValue([11])
-
     const correspondentIs = addFilterOfType(TriggerFilterType.CorrespondentIs)
     correspondentIs.get('values').setValue(1)
 
@@ -424,18 +421,12 @@ describe('WorkflowEditDialogComponent', () => {
     const documentTypeIs = addFilterOfType(TriggerFilterType.DocumentTypeIs)
     documentTypeIs.get('values').setValue(1)
 
-    const documentTypeAny = addFilterOfType(TriggerFilterType.DocumentTypeAny)
-    documentTypeAny.get('values').setValue([12])
-
     const documentTypeNot = addFilterOfType(TriggerFilterType.DocumentTypeNot)
     documentTypeNot.get('values').setValue([1])
 
     const storagePathIs = addFilterOfType(TriggerFilterType.StoragePathIs)
     storagePathIs.get('values').setValue(1)
 
-    const storagePathAny = addFilterOfType(TriggerFilterType.StoragePathAny)
-    storagePathAny.get('values').setValue([13])
-
     const storagePathNot = addFilterOfType(TriggerFilterType.StoragePathNot)
     storagePathNot.get('values').setValue([1])
 
@@ -450,13 +441,10 @@ describe('WorkflowEditDialogComponent', () => {
     expect(formValues.triggers[0].filter_has_tags).toEqual([1])
     expect(formValues.triggers[0].filter_has_all_tags).toEqual([2, 3])
     expect(formValues.triggers[0].filter_has_not_tags).toEqual([4])
-    expect(formValues.triggers[0].filter_has_any_correspondents).toEqual([11])
     expect(formValues.triggers[0].filter_has_correspondent).toEqual(1)
     expect(formValues.triggers[0].filter_has_not_correspondents).toEqual([1])
-    expect(formValues.triggers[0].filter_has_any_document_types).toEqual([12])
     expect(formValues.triggers[0].filter_has_document_type).toEqual(1)
     expect(formValues.triggers[0].filter_has_not_document_types).toEqual([1])
-    expect(formValues.triggers[0].filter_has_any_storage_paths).toEqual([13])
     expect(formValues.triggers[0].filter_has_storage_path).toEqual(1)
     expect(formValues.triggers[0].filter_has_not_storage_paths).toEqual([1])
     expect(formValues.triggers[0].filter_custom_field_query).toEqual(
@@ -519,22 +507,16 @@ describe('WorkflowEditDialogComponent', () => {
 
     setFilter(TriggerFilterType.TagsAll, 11)
     setFilter(TriggerFilterType.TagsNone, 12)
-    setFilter(TriggerFilterType.CorrespondentAny, 16)
     setFilter(TriggerFilterType.CorrespondentNot, 13)
-    setFilter(TriggerFilterType.DocumentTypeAny, 17)
     setFilter(TriggerFilterType.DocumentTypeNot, 14)
-    setFilter(TriggerFilterType.StoragePathAny, 18)
     setFilter(TriggerFilterType.StoragePathNot, 15)
 
     const formValues = component['getFormValues']()
 
     expect(formValues.triggers[0].filter_has_all_tags).toEqual([11])
     expect(formValues.triggers[0].filter_has_not_tags).toEqual([12])
-    expect(formValues.triggers[0].filter_has_any_correspondents).toEqual([16])
     expect(formValues.triggers[0].filter_has_not_correspondents).toEqual([13])
-    expect(formValues.triggers[0].filter_has_any_document_types).toEqual([17])
     expect(formValues.triggers[0].filter_has_not_document_types).toEqual([14])
-    expect(formValues.triggers[0].filter_has_any_storage_paths).toEqual([18])
     expect(formValues.triggers[0].filter_has_not_storage_paths).toEqual([15])
   })
 
@@ -658,11 +640,8 @@ describe('WorkflowEditDialogComponent', () => {
       filter_has_tags: [],
       filter_has_all_tags: [],
       filter_has_not_tags: [],
-      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: null,
       filter_has_document_type: null,
@@ -720,14 +699,11 @@ describe('WorkflowEditDialogComponent', () => {
     trigger.filter_has_tags = [1]
     trigger.filter_has_all_tags = [2, 3]
     trigger.filter_has_not_tags = [4]
-    trigger.filter_has_any_correspondents = [10] as any
     trigger.filter_has_correspondent = 5 as any
     trigger.filter_has_not_correspondents = [6] as any
     trigger.filter_has_document_type = 7 as any
-    trigger.filter_has_any_document_types = [11] as any
     trigger.filter_has_not_document_types = [8] as any
     trigger.filter_has_storage_path = 9 as any
-    trigger.filter_has_any_storage_paths = [12] as any
     trigger.filter_has_not_storage_paths = [10] as any
     trigger.filter_custom_field_query = JSON.stringify([
       'AND',
@@ -738,8 +714,8 @@ describe('WorkflowEditDialogComponent', () => {
     component.ngOnInit()
     const triggerGroup = component.triggerFields.at(0) as FormGroup
     const filters = component.getFiltersFormArray(triggerGroup)
-    expect(filters.length).toBe(13)
+    expect(filters.length).toBe(10)
-    const customFieldFilter = filters.at(12) as FormGroup
+    const customFieldFilter = filters.at(9) as FormGroup
     expect(customFieldFilter.get('type').value).toBe(
       TriggerFilterType.CustomFieldQuery
     )
@@ -748,27 +724,12 @@ describe('WorkflowEditDialogComponent', () => {
   })
 
   it('should expose select metadata helpers', () => {
-    expect(component.isSelectMultiple(TriggerFilterType.CorrespondentAny)).toBe(
-      true
-    )
     expect(component.isSelectMultiple(TriggerFilterType.CorrespondentNot)).toBe(
       true
     )
     expect(component.isSelectMultiple(TriggerFilterType.CorrespondentIs)).toBe(
       false
     )
-    expect(component.isSelectMultiple(TriggerFilterType.DocumentTypeAny)).toBe(
-      true
-    )
-    expect(component.isSelectMultiple(TriggerFilterType.DocumentTypeIs)).toBe(
-      false
-    )
-    expect(component.isSelectMultiple(TriggerFilterType.StoragePathAny)).toBe(
-      true
-    )
-    expect(component.isSelectMultiple(TriggerFilterType.StoragePathIs)).toBe(
-      false
-    )
 
     component.correspondents = [{ id: 1, name: 'C1' } as any]
     component.documentTypes = [{ id: 2, name: 'DT' } as any]
@@ -780,15 +741,9 @@ describe('WorkflowEditDialogComponent', () => {
     expect(
       component.getFilterSelectItems(TriggerFilterType.DocumentTypeIs)
     ).toEqual(component.documentTypes)
-    expect(
-      component.getFilterSelectItems(TriggerFilterType.DocumentTypeAny)
-    ).toEqual(component.documentTypes)
     expect(
       component.getFilterSelectItems(TriggerFilterType.StoragePathIs)
     ).toEqual(component.storagePaths)
-    expect(
-      component.getFilterSelectItems(TriggerFilterType.StoragePathAny)
-    ).toEqual(component.storagePaths)
     expect(component.getFilterSelectItems(TriggerFilterType.TagsAll)).toEqual(
       []
     )

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

@@ -145,13 +145,10 @@ export enum TriggerFilterType {
   TagsAny = 'tags_any',
   TagsAll = 'tags_all',
   TagsNone = 'tags_none',
-  CorrespondentAny = 'correspondent_any',
   CorrespondentIs = 'correspondent_is',
   CorrespondentNot = 'correspondent_not',
-  DocumentTypeAny = 'document_type_any',
   DocumentTypeIs = 'document_type_is',
   DocumentTypeNot = 'document_type_not',
-  StoragePathAny = 'storage_path_any',
   StoragePathIs = 'storage_path_is',
   StoragePathNot = 'storage_path_not',
   CustomFieldQuery = 'custom_field_query',
@@ -175,11 +172,8 @@ type TriggerFilterAggregate = {
   filter_has_tags: number[]
   filter_has_all_tags: number[]
   filter_has_not_tags: number[]
-  filter_has_any_correspondents: number[]
   filter_has_not_correspondents: number[]
-  filter_has_any_document_types: number[]
   filter_has_not_document_types: number[]
-  filter_has_any_storage_paths: number[]
   filter_has_not_storage_paths: number[]
   filter_has_correspondent: number | null
   filter_has_document_type: number | null
@@ -225,14 +219,6 @@ const TRIGGER_FILTER_DEFINITIONS: TriggerFilterDefinition[] = [
     allowMultipleEntries: false,
     allowMultipleValues: true,
   },
-  {
-    id: TriggerFilterType.CorrespondentAny,
-    name: $localize`Has any of these correspondents`,
-    inputType: 'select',
-    allowMultipleEntries: false,
-    allowMultipleValues: true,
-    selectItems: 'correspondents',
-  },
   {
     id: TriggerFilterType.CorrespondentIs,
     name: $localize`Has correspondent`,
@@ -257,14 +243,6 @@ const TRIGGER_FILTER_DEFINITIONS: TriggerFilterDefinition[] = [
     allowMultipleValues: false,
     selectItems: 'documentTypes',
   },
-  {
-    id: TriggerFilterType.DocumentTypeAny,
-    name: $localize`Has any of these document types`,
-    inputType: 'select',
-    allowMultipleEntries: false,
-    allowMultipleValues: true,
-    selectItems: 'documentTypes',
-  },
   {
     id: TriggerFilterType.DocumentTypeNot,
     name: $localize`Does not have document types`,
@@ -281,14 +259,6 @@ const TRIGGER_FILTER_DEFINITIONS: TriggerFilterDefinition[] = [
     allowMultipleValues: false,
     selectItems: 'storagePaths',
   },
-  {
-    id: TriggerFilterType.StoragePathAny,
-    name: $localize`Has any of these storage paths`,
-    inputType: 'select',
-    allowMultipleEntries: false,
-    allowMultipleValues: true,
-    selectItems: 'storagePaths',
-  },
   {
     id: TriggerFilterType.StoragePathNot,
     name: $localize`Does not have storage paths`,
@@ -336,15 +306,6 @@ const FILTER_HANDLERS: Record<TriggerFilterType, FilterHandler> = {
     extract: (trigger) => trigger.filter_has_not_tags,
     hasValue: (value) => Array.isArray(value) && value.length > 0,
   },
-  [TriggerFilterType.CorrespondentAny]: {
-    apply: (aggregate, values) => {
-      aggregate.filter_has_any_correspondents = Array.isArray(values)
-        ? [...values]
-        : [values]
-    },
-    extract: (trigger) => trigger.filter_has_any_correspondents,
-    hasValue: (value) => Array.isArray(value) && value.length > 0,
-  },
   [TriggerFilterType.CorrespondentIs]: {
     apply: (aggregate, values) => {
       aggregate.filter_has_correspondent = Array.isArray(values)
@@ -372,15 +333,6 @@ const FILTER_HANDLERS: Record<TriggerFilterType, FilterHandler> = {
     extract: (trigger) => trigger.filter_has_document_type,
     hasValue: (value) => value !== null && value !== undefined,
   },
-  [TriggerFilterType.DocumentTypeAny]: {
-    apply: (aggregate, values) => {
-      aggregate.filter_has_any_document_types = Array.isArray(values)
-        ? [...values]
-        : [values]
-    },
-    extract: (trigger) => trigger.filter_has_any_document_types,
-    hasValue: (value) => Array.isArray(value) && value.length > 0,
-  },
   [TriggerFilterType.DocumentTypeNot]: {
     apply: (aggregate, values) => {
       aggregate.filter_has_not_document_types = Array.isArray(values)
@@ -399,15 +351,6 @@ const FILTER_HANDLERS: Record<TriggerFilterType, FilterHandler> = {
     extract: (trigger) => trigger.filter_has_storage_path,
     hasValue: (value) => value !== null && value !== undefined,
   },
-  [TriggerFilterType.StoragePathAny]: {
-    apply: (aggregate, values) => {
-      aggregate.filter_has_any_storage_paths = Array.isArray(values)
-        ? [...values]
-        : [values]
-    },
-    extract: (trigger) => trigger.filter_has_any_storage_paths,
-    hasValue: (value) => Array.isArray(value) && value.length > 0,
-  },
   [TriggerFilterType.StoragePathNot]: {
     apply: (aggregate, values) => {
       aggregate.filter_has_not_storage_paths = Array.isArray(values)
@@ -699,11 +642,8 @@ export class WorkflowEditDialogComponent
             filter_has_tags: [],
             filter_has_all_tags: [],
             filter_has_not_tags: [],
-            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: null,
             filter_has_document_type: null,
@@ -730,16 +670,10 @@ export class WorkflowEditDialogComponent
           trigger.filter_has_tags = aggregate.filter_has_tags
           trigger.filter_has_all_tags = aggregate.filter_has_all_tags
           trigger.filter_has_not_tags = aggregate.filter_has_not_tags
-          trigger.filter_has_any_correspondents =
-            aggregate.filter_has_any_correspondents
           trigger.filter_has_not_correspondents =
             aggregate.filter_has_not_correspondents
-          trigger.filter_has_any_document_types =
-            aggregate.filter_has_any_document_types
           trigger.filter_has_not_document_types =
             aggregate.filter_has_not_document_types
-          trigger.filter_has_any_storage_paths =
-            aggregate.filter_has_any_storage_paths
           trigger.filter_has_not_storage_paths =
             aggregate.filter_has_not_storage_paths
           trigger.filter_has_correspondent =
@@ -922,11 +856,8 @@ export class WorkflowEditDialogComponent
       case TriggerFilterType.TagsAny:
       case TriggerFilterType.TagsAll:
       case TriggerFilterType.TagsNone:
-      case TriggerFilterType.CorrespondentAny:
       case TriggerFilterType.CorrespondentNot:
-      case TriggerFilterType.DocumentTypeAny:
       case TriggerFilterType.DocumentTypeNot:
-      case TriggerFilterType.StoragePathAny:
       case TriggerFilterType.StoragePathNot:
         return true
       default:
@@ -1248,11 +1179,8 @@ export class WorkflowEditDialogComponent
       filter_has_tags: [],
       filter_has_all_tags: [],
       filter_has_not_tags: [],
-      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_custom_field_query: null,
       filter_has_correspondent: null,

src-ui/src/app/components/document-detail/document-detail.component.html

@@ -370,6 +370,37 @@
             </ng-template>
           </li>
         }
+
+        @if (document?.duplicate_documents?.length) {
+          <li [ngbNavItem]="DocumentDetailNavIDs.Duplicates">
+            <a class="text-nowrap" ngbNavLink i18n>
+              Duplicates
+              <span class="badge text-bg-secondary ms-1">{{ document.duplicate_documents.length }}</span>
+            </a>
+            <ng-template ngbNavContent>
+              <div class="d-flex flex-column gap-2">
+                <div class="fst-italic" i18n>Duplicate documents detected:</div>
+                <div class="list-group">
+                  @for (duplicate of document.duplicate_documents; track duplicate.id) {
+                    <a
+                      class="list-group-item list-group-item-action d-flex justify-content-between align-items-center"
+                      [routerLink]="['/documents', duplicate.id, 'details']"
+                      [class.disabled]="duplicate.deleted_at"
+                    >
+                      <span class="d-flex align-items-center gap-2">
+                        <span>{{ duplicate.title || ('#' + duplicate.id) }}</span>
+                        @if (duplicate.deleted_at) {
+                          <span class="badge text-bg-secondary" i18n>In trash</span>
+                        }
+                      </span>
+                      <span class="text-secondary">#{{ duplicate.id }}</span>
+                    </a>
+                  }
+                </div>
+              </div>
+            </ng-template>
+          </li>
+        }
       </ul>
 
       <div [ngbNavOutlet]="nav" class="mt-3"></div>

src-ui/src/app/components/document-detail/document-detail.component.spec.ts

@@ -301,16 +301,16 @@ describe('DocumentDetailComponent', () => {
       .spyOn(openDocumentsService, 'openDocument')
       .mockReturnValueOnce(of(true))
     fixture.detectChanges()
-    expect(component.activeNavID).toEqual(5) // DocumentDetailNavIDs.Notes
+    expect(component.activeNavID).toEqual(component.DocumentDetailNavIDs.Notes)
   })
 
   it('should change url on tab switch', () => {
     initNormally()
     const navigateSpy = jest.spyOn(router, 'navigate')
-    component.nav.select(5)
+    component.nav.select(component.DocumentDetailNavIDs.Notes)
     component.nav.navChange.next({
       activeId: 1,
-      nextId: 5,
+      nextId: component.DocumentDetailNavIDs.Notes,
       preventDefault: () => {},
     })
     fixture.detectChanges()
@@ -352,6 +352,18 @@ describe('DocumentDetailComponent', () => {
     expect(component.document).toEqual(doc)
   })
 
+  it('should fall back to details tab when duplicates tab is active but no duplicates', () => {
+    initNormally()
+    component.activeNavID = component.DocumentDetailNavIDs.Duplicates
+    const noDupDoc = { ...doc, duplicate_documents: [] }
+
+    component.updateComponent(noDupDoc)
+
+    expect(component.activeNavID).toEqual(
+      component.DocumentDetailNavIDs.Details
+    )
+  })
+
   it('should load already-opened document via param', () => {
     initNormally()
     jest.spyOn(documentService, 'get').mockReturnValueOnce(of(doc))
@@ -367,6 +379,38 @@ describe('DocumentDetailComponent', () => {
     expect(component.document).toEqual(doc)
   })
 
+  it('should update cached open document duplicates when reloading an open doc', () => {
+    const openDoc = { ...doc, duplicate_documents: [{ id: 1, title: 'Old' }] }
+    const updatedDuplicates = [
+      { id: 2, title: 'Newer duplicate', deleted_at: null },
+    ]
+    jest
+      .spyOn(activatedRoute, 'paramMap', 'get')
+      .mockReturnValue(of(convertToParamMap({ id: 3, section: 'details' })))
+    jest.spyOn(documentService, 'get').mockReturnValue(
+      of({
+        ...doc,
+        modified: new Date('2024-01-02T00:00:00Z'),
+        duplicate_documents: updatedDuplicates,
+      })
+    )
+    jest.spyOn(openDocumentsService, 'getOpenDocument').mockReturnValue(openDoc)
+    const saveSpy = jest.spyOn(openDocumentsService, 'save')
+    jest.spyOn(openDocumentsService, 'openDocument').mockReturnValue(of(true))
+    jest.spyOn(customFieldsService, 'listAll').mockReturnValue(
+      of({
+        count: customFields.length,
+        all: customFields.map((f) => f.id),
+        results: customFields,
+      })
+    )
+
+    fixture.detectChanges()
+
+    expect(openDoc.duplicate_documents).toEqual(updatedDuplicates)
+    expect(saveSpy).toHaveBeenCalled()
+  })
+
   it('should disable form if user cannot edit', () => {
     currentUserHasObjectPermissions = false
     initNormally()

src-ui/src/app/components/document-detail/document-detail.component.ts

@@ -8,7 +8,7 @@ import {
   FormsModule,
   ReactiveFormsModule,
 } from '@angular/forms'
-import { ActivatedRoute, Router } from '@angular/router'
+import { ActivatedRoute, Router, RouterModule } from '@angular/router'
 import {
   NgbDateStruct,
   NgbDropdownModule,
@@ -124,6 +124,7 @@ enum DocumentDetailNavIDs {
   Notes = 5,
   Permissions = 6,
   History = 7,
+  Duplicates = 8,
 }
 
 enum ContentRenderType {
@@ -181,6 +182,7 @@ export enum ZoomSetting {
     NgxBootstrapIconsModule,
     PdfViewerModule,
     TextAreaComponent,
+    RouterModule,
   ],
 })
 export class DocumentDetailComponent
@@ -454,6 +456,11 @@ export class DocumentDetailComponent
           const openDocument = this.openDocumentService.getOpenDocument(
             this.documentId
           )
+          // update duplicate documents if present
+          if (openDocument && doc?.duplicate_documents) {
+            openDocument.duplicate_documents = doc.duplicate_documents
+            this.openDocumentService.save()
+          }
           const useDoc = openDocument || doc
           if (openDocument) {
             if (
@@ -704,6 +711,13 @@ export class DocumentDetailComponent
     }
     this.title = this.documentTitlePipe.transform(doc.title)
     this.prepareForm(doc)
+
+    if (
+      this.activeNavID === DocumentDetailNavIDs.Duplicates &&
+      !doc?.duplicate_documents?.length
+    ) {
+      this.activeNavID = DocumentDetailNavIDs.Details
+    }
   }
 
   get customFieldFormFields(): FormArray {

src-ui/src/app/data/document.ts

@@ -159,6 +159,8 @@ export interface Document extends ObjectWithPermissions {
 
   page_count?: number
 
+  duplicate_documents?: Document[]
+
   // Frontend only
   __changedFields?: string[]
 }

src-ui/src/app/data/paperless-task.ts

@@ -1,3 +1,4 @@
+import { Document } from './document'
 import { ObjectWithId } from './object-with-id'
 
 export enum PaperlessTaskType {
@@ -42,5 +43,7 @@ export interface PaperlessTask extends ObjectWithId {
 
   related_document?: number
 
+  duplicate_documents?: Document[]
+
   owner?: number
 }

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

@@ -44,16 +44,10 @@ export interface WorkflowTrigger extends ObjectWithId {
 
   filter_has_not_tags?: number[] // Tag.id[]
 
-  filter_has_any_correspondents?: number[] // Correspondent.id[]
-
   filter_has_not_correspondents?: number[] // Correspondent.id[]
 
-  filter_has_any_document_types?: number[] // DocumentType.id[]
-
   filter_has_not_document_types?: number[] // DocumentType.id[]
 
-  filter_has_any_storage_paths?: number[] // StoragePath.id[]
-
   filter_has_not_storage_paths?: number[] // StoragePath.id[]
 
   filter_custom_field_query?: string

src/documents/consumer.py

@@ -779,19 +779,45 @@ class ConsumerPreflightPlugin(
             Q(checksum=checksum) | Q(archive_checksum=checksum),
         )
         if existing_doc.exists():
-            msg = ConsumerStatusShortMessage.DOCUMENT_ALREADY_EXISTS
+            existing_doc = existing_doc.order_by("-created")
-            log_msg = f"Not consuming {self.filename}: It is a duplicate of {existing_doc.get().title} (#{existing_doc.get().pk})."
+            duplicates_in_trash = existing_doc.filter(deleted_at__isnull=False)
+            log_msg = (
+                f"Consuming duplicate {self.filename}: "
+                f"{existing_doc.count()} existing document(s) share the same content."
+            )
 
-            if existing_doc.first().deleted_at is not None:
+            if duplicates_in_trash.exists():
-                msg = ConsumerStatusShortMessage.DOCUMENT_ALREADY_EXISTS_IN_TRASH
+                log_msg += " Note: at least one existing document is in the trash."
-                log_msg += " Note: existing document is in the trash."
+
+            self.log.warning(log_msg)
 
             if settings.CONSUMER_DELETE_DUPLICATES:
+                duplicate = existing_doc.first()
+                duplicate_label = (
+                    duplicate.title
+                    or duplicate.original_filename
+                    or (Path(duplicate.filename).name if duplicate.filename else None)
+                    or str(duplicate.pk)
+                )
+
                 Path(self.input_doc.original_file).unlink()
-            self._fail(
+
-                msg,
+                failure_msg = (
-                log_msg,
+                    f"Not consuming {self.filename}: "
-            )
+                    f"It is a duplicate of {duplicate_label} (#{duplicate.pk})"
+                )
+                status_msg = ConsumerStatusShortMessage.DOCUMENT_ALREADY_EXISTS
+
+                if duplicates_in_trash.exists():
+                    status_msg = (
+                        ConsumerStatusShortMessage.DOCUMENT_ALREADY_EXISTS_IN_TRASH
+                    )
+                    failure_msg += " Note: existing document is in the trash."
+
+                self._fail(
+                    status_msg,
+                    failure_msg,
+                )
 
     def pre_check_directories(self):
         """

src/documents/matching.py

@@ -403,18 +403,6 @@ 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
@@ -436,17 +424,6 @@ 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
@@ -468,17 +445,6 @@ 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
@@ -566,10 +532,6 @@ 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,
@@ -579,10 +541,6 @@ 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,
@@ -592,10 +550,6 @@ 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,
@@ -650,11 +604,8 @@ 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",
         )
     )

src/documents/migrations/0005_alter_document_checksum_unique.py

@@ -0,0 +1,23 @@
+# Generated by Django 5.2.7 on 2026-01-14 17:45
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0004_remove_document_storage_type"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="document",
+            name="checksum",
+            field=models.CharField(
+                editable=False,
+                max_length=32,
+                verbose_name="checksum",
+                help_text="The checksum of the original document.",
+            ),
+        ),
+    ]

src/documents/migrations/0005_workflowtrigger_filter_has_any_correspondents_and_more.py

@@ -1,43 +0,0 @@
-# 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", "0004_remove_document_storage_type"),
-    ]
-
-    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",
-            ),
-        ),
-    ]

src/documents/models.py

@@ -205,7 +205,6 @@ class Document(SoftDeleteModel, ModelWithOwner):
         _("checksum"),
         max_length=32,
         editable=False,
-        unique=True,
         help_text=_("The checksum of the original document."),
     )
 
@@ -1066,13 +1065,6 @@ 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,
@@ -1095,13 +1087,6 @@ 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,
@@ -1110,13 +1095,6 @@ 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,

src/documents/permissions.py

@@ -148,13 +148,29 @@ def get_document_count_filter_for_user(user):
     )
 
 
-def get_objects_for_user_owner_aware(user, perms, Model) -> QuerySet:
+def get_objects_for_user_owner_aware(
-    objects_owned = Model.objects.filter(owner=user)
+    user,
-    objects_unowned = Model.objects.filter(owner__isnull=True)
+    perms,
+    Model,
+    *,
+    include_deleted=False,
+) -> QuerySet:
+    """
+    Returns objects the user owns, are unowned, or has explicit perms.
+    When include_deleted is True, soft-deleted items are also included.
+    """
+    manager = (
+        Model.global_objects
+        if include_deleted and hasattr(Model, "global_objects")
+        else Model.objects
+    )
+
+    objects_owned = manager.filter(owner=user)
+    objects_unowned = manager.filter(owner__isnull=True)
     objects_with_perms = get_objects_for_user(
         user=user,
         perms=perms,
-        klass=Model,
+        klass=manager.all(),
         accept_global_perms=False,
     )
     return objects_owned | objects_unowned | objects_with_perms

src/documents/serialisers.py

@@ -23,6 +23,7 @@ from django.core.validators import MinValueValidator
 from django.core.validators import RegexValidator
 from django.core.validators import integer_validator
 from django.db.models import Count
+from django.db.models import Q
 from django.db.models.functions import Lower
 from django.utils.crypto import get_random_string
 from django.utils.dateparse import parse_datetime
@@ -72,6 +73,7 @@ from documents.models import WorkflowTrigger
 from documents.parsers import is_mime_type_supported
 from documents.permissions import get_document_count_filter_for_user
 from documents.permissions import get_groups_with_only_permission
+from documents.permissions import get_objects_for_user_owner_aware
 from documents.permissions import set_permissions_for_object
 from documents.regex import validate_regex_pattern
 from documents.templating.filepath import validate_filepath_template_and_render
@@ -1014,6 +1016,29 @@ class NotesSerializer(serializers.ModelSerializer):
         return ret
 
 
+def _get_viewable_duplicates(document: Document, user: User | None):
+    checksums = {document.checksum}
+    if document.archive_checksum:
+        checksums.add(document.archive_checksum)
+    duplicates = Document.global_objects.filter(
+        Q(checksum__in=checksums) | Q(archive_checksum__in=checksums),
+    ).exclude(pk=document.pk)
+    duplicates = duplicates.order_by("-created")
+    allowed = get_objects_for_user_owner_aware(
+        user,
+        "documents.view_document",
+        Document,
+        include_deleted=True,
+    )
+    return duplicates.filter(id__in=allowed.values_list("id", flat=True))
+
+
+class DuplicateDocumentSummarySerializer(serializers.Serializer):
+    id = serializers.IntegerField()
+    title = serializers.CharField()
+    deleted_at = serializers.DateTimeField(allow_null=True)
+
+
 @extend_schema_serializer(
     deprecate_fields=["created_date"],
 )
@@ -1031,6 +1056,7 @@ class DocumentSerializer(
     archived_file_name = SerializerMethodField()
     created_date = serializers.DateField(required=False)
     page_count = SerializerMethodField()
+    duplicate_documents = SerializerMethodField()
 
     notes = NotesSerializer(many=True, required=False, read_only=True)
 
@@ -1056,6 +1082,16 @@ class DocumentSerializer(
     def get_page_count(self, obj) -> int | None:
         return obj.page_count
 
+    @extend_schema_field(DuplicateDocumentSummarySerializer(many=True))
+    def get_duplicate_documents(self, obj):
+        view = self.context.get("view")
+        if view and getattr(view, "action", None) != "retrieve":
+            return []
+        request = self.context.get("request")
+        user = request.user if request else None
+        duplicates = _get_viewable_duplicates(obj, user)
+        return list(duplicates.values("id", "title", "deleted_at"))
+
     def get_original_file_name(self, obj) -> str | None:
         return obj.original_filename
 
@@ -1233,6 +1269,7 @@ class DocumentSerializer(
             "archive_serial_number",
             "original_file_name",
             "archived_file_name",
+            "duplicate_documents",
             "owner",
             "permissions",
             "user_can_change",
@@ -2094,10 +2131,12 @@ class TasksViewSerializer(OwnedObjectSerializer):
             "result",
             "acknowledged",
             "related_document",
+            "duplicate_documents",
             "owner",
         )
 
     related_document = serializers.SerializerMethodField()
+    duplicate_documents = serializers.SerializerMethodField()
     created_doc_re = re.compile(r"New document id (\d+) created")
     duplicate_doc_re = re.compile(r"It is a duplicate of .* \(#(\d+)\)")
 
@@ -2122,6 +2161,17 @@ class TasksViewSerializer(OwnedObjectSerializer):
 
         return result
 
+    @extend_schema_field(DuplicateDocumentSummarySerializer(many=True))
+    def get_duplicate_documents(self, obj):
+        related_document = self.get_related_document(obj)
+        request = self.context.get("request")
+        user = request.user if request else None
+        document = Document.global_objects.filter(pk=related_document).first()
+        if not related_document or not user or not document:
+            return []
+        duplicates = _get_viewable_duplicates(document, user)
+        return list(duplicates.values("id", "title", "deleted_at"))
+
 
 class RunTaskViewSerializer(serializers.Serializer):
     task_name = serializers.ChoiceField(
@@ -2299,11 +2349,8 @@ 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",
@@ -2541,26 +2588,14 @@ 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,
@@ -2577,26 +2612,14 @@ 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,

src/documents/tests/test_api_tasks.py

@@ -7,6 +7,7 @@ from django.contrib.auth.models import User
 from rest_framework import status
 from rest_framework.test import APITestCase
 
+from documents.models import Document
 from documents.models import PaperlessTask
 from documents.tests.utils import DirectoriesMixin
 from documents.views import TasksViewSet
@@ -258,7 +259,7 @@ class TestTasks(DirectoriesMixin, APITestCase):
             task_id=str(uuid.uuid4()),
             task_file_name="task_one.pdf",
             status=celery.states.FAILURE,
-            result="test.pdf: Not consuming test.pdf: It is a duplicate.",
+            result="test.pdf: Unexpected error during ingestion.",
         )
 
         response = self.client.get(self.ENDPOINT)
@@ -270,7 +271,7 @@ class TestTasks(DirectoriesMixin, APITestCase):
 
         self.assertEqual(
             returned_data["result"],
-            "test.pdf: Not consuming test.pdf: It is a duplicate.",
+            "test.pdf: Unexpected error during ingestion.",
         )
 
     def test_task_name_webui(self):
@@ -325,20 +326,34 @@ class TestTasks(DirectoriesMixin, APITestCase):
 
         self.assertEqual(returned_data["task_file_name"], "anothertest.pdf")
 
-    def test_task_result_failed_duplicate_includes_related_doc(self):
+    def test_task_result_duplicate_warning_includes_count(self):
         """
         GIVEN:
-            - A celery task failed with a duplicate error
+            - A celery task succeeds, but a duplicate exists
         WHEN:
             - API call is made to get tasks
         THEN:
-            - The returned data includes a related document link
+            - The returned data includes duplicate warning metadata
         """
+        checksum = "duplicate-checksum"
+        Document.objects.create(
+            title="Existing",
+            content="",
+            mime_type="application/pdf",
+            checksum=checksum,
+        )
+        created_doc = Document.objects.create(
+            title="Created",
+            content="",
+            mime_type="application/pdf",
+            checksum=checksum,
+            archive_checksum="another-checksum",
+        )
         PaperlessTask.objects.create(
             task_id=str(uuid.uuid4()),
             task_file_name="task_one.pdf",
-            status=celery.states.FAILURE,
+            status=celery.states.SUCCESS,
-            result="Not consuming task_one.pdf: It is a duplicate of task_one_existing.pdf (#1234).",
+            result=f"Success. New document id {created_doc.pk} created",
         )
 
         response = self.client.get(self.ENDPOINT)
@@ -348,7 +363,7 @@ class TestTasks(DirectoriesMixin, APITestCase):
 
         returned_data = response.data[0]
 
-        self.assertEqual(returned_data["related_document"], "1234")
+        self.assertEqual(returned_data["related_document"], str(created_doc.pk))
 
     def test_run_train_classifier_task(self):
         """

src/documents/tests/test_api_workflows.py

@@ -186,11 +186,8 @@ 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(
                                 [
@@ -251,26 +248,14 @@ 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},
@@ -434,11 +419,8 @@ 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"]]],
@@ -468,26 +450,14 @@ 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,

src/documents/tests/test_consumer.py

@@ -485,21 +485,21 @@ class TestConsumer(
         with self.get_consumer(self.get_test_file()) as consumer:
             consumer.run()
 
-        with self.assertRaisesMessage(ConsumerError, "It is a duplicate"):
+        with self.get_consumer(self.get_test_file()) as consumer:
-            with self.get_consumer(self.get_test_file()) as consumer:
+            consumer.run()
-                consumer.run()
 
-        self._assert_first_last_send_progress(last_status="FAILED")
+        self.assertEqual(Document.objects.count(), 2)
+        self._assert_first_last_send_progress()
 
     def testDuplicates2(self):
         with self.get_consumer(self.get_test_file()) as consumer:
             consumer.run()
 
-        with self.assertRaisesMessage(ConsumerError, "It is a duplicate"):
+        with self.get_consumer(self.get_test_archive_file()) as consumer:
-            with self.get_consumer(self.get_test_archive_file()) as consumer:
+            consumer.run()
-                consumer.run()
 
-        self._assert_first_last_send_progress(last_status="FAILED")
+        self.assertEqual(Document.objects.count(), 2)
+        self._assert_first_last_send_progress()
 
     def testDuplicates3(self):
         with self.get_consumer(self.get_test_archive_file()) as consumer:
@@ -513,9 +513,10 @@ class TestConsumer(
 
         Document.objects.all().delete()
 
-        with self.assertRaisesMessage(ConsumerError, "document is in the trash"):
+        with self.get_consumer(self.get_test_file()) as consumer:
-            with self.get_consumer(self.get_test_file()) as consumer:
+            consumer.run()
-                consumer.run()
+
+        self.assertEqual(Document.objects.count(), 1)
 
     def testAsnExists(self):
         with self.get_consumer(
@@ -718,12 +719,45 @@ class TestConsumer(
         dst = self.get_test_file()
         self.assertIsFile(dst)
 
-        with self.assertRaises(ConsumerError):
+        expected_message = (
+            f"{dst.name}: Not consuming {dst.name}: "
+            f"It is a duplicate of {document.title} (#{document.pk})"
+        )
+
+        with self.assertRaisesMessage(ConsumerError, expected_message):
             with self.get_consumer(dst) as consumer:
                 consumer.run()
 
         self.assertIsNotFile(dst)
-        self._assert_first_last_send_progress(last_status="FAILED")
+        self.assertEqual(Document.objects.count(), 1)
+        self._assert_first_last_send_progress(last_status=ProgressStatusOptions.FAILED)
+
+    @override_settings(CONSUMER_DELETE_DUPLICATES=True)
+    def test_delete_duplicate_in_trash(self):
+        dst = self.get_test_file()
+        with self.get_consumer(dst) as consumer:
+            consumer.run()
+
+        # Move the existing document to trash
+        document = Document.objects.first()
+        document.delete()
+
+        dst = self.get_test_file()
+        self.assertIsFile(dst)
+
+        expected_message = (
+            f"{dst.name}: Not consuming {dst.name}: "
+            f"It is a duplicate of {document.title} (#{document.pk})"
+            f" Note: existing document is in the trash."
+        )
+
+        with self.assertRaisesMessage(ConsumerError, expected_message):
+            with self.get_consumer(dst) as consumer:
+                consumer.run()
+
+        self.assertIsNotFile(dst)
+        self.assertEqual(Document.global_objects.count(), 1)
+        self.assertEqual(Document.objects.count(), 0)
 
     @override_settings(CONSUMER_DELETE_DUPLICATES=False)
     def test_no_delete_duplicate(self):
@@ -743,15 +777,12 @@ class TestConsumer(
         dst = self.get_test_file()
         self.assertIsFile(dst)
 
-        with self.assertRaisesRegex(
+        with self.get_consumer(dst) as consumer:
-            ConsumerError,
+            consumer.run()
-            r"sample\.pdf: Not consuming sample\.pdf: It is a duplicate of sample \(#\d+\)",
-        ):
-            with self.get_consumer(dst) as consumer:
-                consumer.run()
 
-        self.assertIsFile(dst)
+        self.assertIsNotFile(dst)
-        self._assert_first_last_send_progress(last_status="FAILED")
+        self.assertEqual(Document.objects.count(), 2)
+        self._assert_first_last_send_progress()
 
     @override_settings(FILENAME_FORMAT="{title}")
     @mock.patch("documents.parsers.document_consumer_declaration.send")

src/documents/tests/test_workflows.py

@@ -1276,76 +1276,6 @@ 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,
@@ -1454,39 +1384,6 @@ 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={