Fix: consolidate born-digital PDF detection between archive decision and OCR (#13409)

* Fix: unify born-digital PDF detection between archive decision and OCR

should_produce_archive() and RasterisedDocumentParser.parse() each
reimplemented the "does this PDF have real text" check independently,
using different normalization of pdftotext output. Raw pdftotext output
can be non-empty (whitespace/form-feed layout padding) even when there
is no real content, so the two checks could disagree: consumer.py
treated a tagged-but-textless PDF as born-digital and skipped the
archive, while the parser's own (stricter, normalized) check found no
text and ran OCR anyway, leaving the document with no archive despite
real OCR text (GH #13387).

Both call sites now share one predicate, pdf_born_digital_text() in
paperless/parsers/utils.py, so they can no longer drift apart.

* Fix: restore extract_text seam for born-digital detection in parse()

parse() had switched to calling pdf_born_digital_text() directly for
its initial text/born-digital check, bypassing the parser's own
extract_text instance method. That broke test mockability (tests patch
tesseract_parser.extract_text to control the born-digital decision)
and caused CI failures with mismatched OCR call counts and text.

Split pdf_born_digital_text() into is_born_digital_text(text, path,
log) - a pure decision function - and a thin pdf_born_digital_text()
wrapper for callers without text in hand (consumer.should_produce_archive).
parse() now extracts via self.extract_text(None, document_path) and
passes the result to is_born_digital_text(), restoring the seam with
no change to production behavior.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

* Cleanup: simplify born-digital detection, close #13387 test gap

Simplification pass over the born-digital detection consolidation:
- is_born_digital_text(): drop the has_text temp for an early return.
- consumer.py: standardize the archive-decision log lines on plain
  hyphens (was a mix of em-dash and hyphen) and hoist the duplicated
  text_length computation.
- Parametrize TestPdfBornDigitalText instead of four near-identical
  tests.

Code review follow-up: the existing tests only ever exercised
pdf_born_digital_text() through mocks, so the actual #13387 scenario
(a tagged PDF whose only "text" is layout padding) was never checked
against real pdftotext/pikepdf output - a regression in the
normalize-before-decide logic itself would have gone undetected.
Moved tagged_no_text_pdf_file from parsers/conftest.py up to the
shared paperless/tests/conftest.py (it was previously only visible to
tests under parsers/) and added a non-mocked regression test against
the real sample file.

Also fixed two stale comments in test_consumer.py referencing a
_extract_text_for_archive_check helper that no longer exists.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>

src-ui/src/app/components/app-frame/app-frame.component.html

@@ -111,7 +111,7 @@
                     routerLinkActive="active" (click)="closeMenu()" [ngbPopover]="view.name"
                     [disablePopover]="!slimSidebarEnabled" placement="end" container="body" triggers="mouseenter:mouseleave"
                     popoverClass="popover-slim">
-                    <i-bs class="me-2" [name]="view.icon || 'funnel'"></i-bs><span><div class="d-inline-flex view-name"><span class="overflow-hidden" [class.text-wrap]="!slimSidebarEnabled">{{view.name}}</span></div>
+                    <i-bs class="me-2" name="funnel"></i-bs><span><div class="d-inline-flex view-name"><span class="overflow-hidden" [class.text-wrap]="!slimSidebarEnabled">{{view.name}}</span></div>
                         @if (showSidebarCounts && !slimSidebarEnabled) {
                           <span class="badge bg-info text-dark ms-2 d-inline">{{ savedViewService.getDocumentCount(view) }}</span>
                         }

src-ui/src/app/components/common/input/select/select.component.html

@@ -36,16 +36,7 @@
           (focus)="clearLastSearchTerm()"
           (clear)="clearLastSearchTerm()"
           (blur)="onBlur()">
-          <ng-template ng-label-tmp let-item="item">
-            @if (iconField && item[iconField]) {
-              <i-bs class="me-2" [name]="item[iconField]"></i-bs>
-            }
-            <span [title]="item[bindLabel]">{{item[bindLabel]}}</span>
-          </ng-template>
           <ng-template ng-option-tmp let-item="item">
-              @if (iconField && item[iconField]) {
-                <i-bs class="me-2" [name]="item[iconField]"></i-bs>
-              }
               <span [title]="item[bindLabel]">{{item[bindLabel]}}</span>
           </ng-template>
         </ng-select>

src-ui/src/app/components/common/input/select/select.component.ts

@@ -35,7 +35,7 @@ import { AbstractInputComponent } from '../abstract-input'
     NgxBootstrapIconsModule,
   ],
 })
-export class SelectComponent extends AbstractInputComponent<number | string> {
+export class SelectComponent extends AbstractInputComponent<number> {
   constructor() {
     super()
     this.addItemRef = this.addItem.bind(this)
@@ -100,9 +100,6 @@ export class SelectComponent extends AbstractInputComponent<number | string> {
   @Input()
   bindLabel: string = 'name'
 
-  @Input()
-  iconField: string
-
   public searchFn = (term: string, item: any): boolean =>
     matchesSearchText(item?.[this.bindLabel], term)
 

src-ui/src/app/components/common/pdf-viewer/pdf-viewer.component.spec.ts

@@ -129,13 +129,25 @@ describe('PngxPdfViewerComponent', () => {
     ;(component as any).applyScale()
     expect(viewer.currentScaleValue).toBe(PdfZoomScale.PageFit)
     expect(viewer.currentScale).toBe(2)
+  })
 
+  it('does not reapply scale for page-only changes', async () => {
+    await initComponent()
+
+    const pdf = (component as any).pdf as { numPages: number }
+    pdf.numPages = 3
+    const viewer = (component as any).pdfViewer as PDFViewer
+    viewer.setDocument(pdf)
     const applyScaleSpy = jest.spyOn(component as any, 'applyScale')
     component.page = 2
-    ;(component as any).lastViewerPage = 2
+
-    ;(component as any).applyViewerState()
+    component.ngOnChanges({
+      page: new SimpleChange(1, 2, false),
+    })
+
+    expect(viewer.currentPageNumber).toBe(2)
     expect((component as any).lastViewerPage).toBeUndefined()
-    expect(applyScaleSpy).toHaveBeenCalled()
+    expect(applyScaleSpy).not.toHaveBeenCalled()
   })
 
   it('does not reset the viewer when it is already on the requested page', async () => {

src-ui/src/app/components/common/pdf-viewer/pdf-viewer.component.ts

@@ -116,7 +116,10 @@ export class PngxPdfViewerComponent
       changes['zoomScale'] ||
       changes['rotation']
     ) {
-      this.applyViewerState()
+      // Prevent loop with page / scale application see https://github.com/paperless-ngx/paperless-ngx/issues/13404
+      this.applyViewerState(
+        !!(changes['zoom'] || changes['zoomScale'] || changes['rotation'])
+      )
     }
 
     if (changes['searchQuery']) {
@@ -240,7 +243,7 @@ export class PngxPdfViewerComponent
     }
   }
 
-  private applyViewerState(): void {
+  private applyViewerState(applyScale = true): void {
     if (!this.pdfViewer) {
       return
     }
@@ -264,7 +267,7 @@ export class PngxPdfViewerComponent
     if (this.page === this.lastViewerPage) {
       this.lastViewerPage = undefined
     }
-    if (hasPages) {
+    if (hasPages && applyScale) {
       this.applyScale()
     }
     this.dispatchFindIfReady()

src-ui/src/app/components/dashboard/widgets/saved-view-widget/saved-view-widget.component.html

@@ -1,7 +1,6 @@
 <pngx-widget-frame
   *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.Document }"
   [title]="savedView.name"
-  [titleIcon]="savedView.icon || 'funnel'"
   [loading]="false"
   [draggable]="savedView"
   >

src-ui/src/app/components/dashboard/widgets/widget-frame/widget-frame.component.html

@@ -8,12 +8,7 @@
               <i-bs name="grip-vertical"></i-bs>
             </div>
           }
-          <h6 class="card-title mb-0">
+          <h6 class="card-title mb-0">{{title()}}</h6>
-            @if (titleIcon()) {
-              <i-bs class="me-2" [name]="titleIcon()"></i-bs>
-            }
-            {{title()}}
-          </h6>
           <ng-content select="[title-badge]"></ng-content>
           @if (badge() !== null && badge() !== undefined) {
             <span class="badge bg-info text-dark ms-2">{{badge()}}</span>

src-ui/src/app/components/dashboard/widgets/widget-frame/widget-frame.component.ts

@@ -16,8 +16,6 @@ export class WidgetFrameComponent implements AfterViewInit {
 
   title = input<string>()
 
-  titleIcon = input<string>()
-
   draggable = input<any>()
 
   cardless = input(false)

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

@@ -97,9 +97,7 @@
     <div class="dropdown-menu shadow dropdown-menu-right" ngbDropdownMenu>
       @if (!list.activeSavedViewId) {
         @for (view of savedViewService.allViews; track view) {
-          <button ngbDropdownItem (click)="loadViewConfig(view.id)">
+          <button ngbDropdownItem (click)="loadViewConfig(view.id)">{{view.name}}</button>
-            <i-bs class="me-2" [name]="view.icon || 'funnel'"></i-bs>{{view.name}}
-          </button>
         }
         @if (savedViewService.allViews.length > 0) {
           <div class="dropdown-divider"></div>

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

@@ -457,7 +457,6 @@ export class DocumentListComponent
       modal.componentInstance.buttonsEnabled.set(false)
       let savedView: SavedView = {
         name: formValue.name,
-        icon: formValue.icon,
         filter_rules: this.list.filterRules,
         sort_reverse: this.list.sortReverse,
         sort_field: this.list.sortField,

src-ui/src/app/components/document-list/save-view-config-dialog/save-view-config-dialog.component.html

@@ -6,14 +6,6 @@
   </div>
   <div class="modal-body">
     <pngx-input-text i18n-title title="Name" formControlName="name" [error]="error()?.name" autocomplete="off"></pngx-input-text>
-    <pngx-input-select
-      i18n-title
-      title="Icon"
-      formControlName="icon"
-      [items]="savedViewIcons"
-      iconField="icon"
-      [error]="error()?.icon">
-    </pngx-input-select>
     <pngx-input-check i18n-title title="Show in sidebar" formControlName="showInSideBar"></pngx-input-check>
     <pngx-input-check i18n-title title="Show on dashboard" formControlName="showOnDashboard"></pngx-input-check>
     <pngx-permissions-form accordion="true" formControlName="permissions_form"></pngx-permissions-form>

src-ui/src/app/components/document-list/save-view-config-dialog/save-view-config-dialog.component.spec.ts

@@ -9,7 +9,6 @@ import { CheckComponent } from '../../common/input/check/check.component'
 import { PermissionsFormComponent } from '../../common/input/permissions/permissions-form/permissions-form.component'
 import { PermissionsGroupComponent } from '../../common/input/permissions/permissions-group/permissions-group.component'
 import { PermissionsUserComponent } from '../../common/input/permissions/permissions-user/permissions-user.component'
-import { SelectComponent } from '../../common/input/select/select.component'
 import { TextComponent } from '../../common/input/text/text.component'
 import { SaveViewConfigDialogComponent } from './save-view-config-dialog.component'
 
@@ -41,7 +40,6 @@ describe('SaveViewConfigDialogComponent', () => {
         ReactiveFormsModule,
         SaveViewConfigDialogComponent,
         TextComponent,
-        SelectComponent,
         CheckComponent,
         PermissionsFormComponent,
         PermissionsUserComponent,
@@ -65,7 +63,6 @@ describe('SaveViewConfigDialogComponent', () => {
     expect(component.defaultName()).toEqual(name)
     expect(result).toEqual({
       name,
-      icon: 'funnel',
       showInSideBar: false,
       showOnDashboard: false,
     })
@@ -97,7 +94,6 @@ describe('SaveViewConfigDialogComponent', () => {
     component.save()
     expect(result).toEqual({
       name,
-      icon: 'funnel',
       showInSideBar: true,
       showOnDashboard: true,
     })
@@ -117,7 +113,6 @@ describe('SaveViewConfigDialogComponent', () => {
     component.save()
     expect(result).toEqual({
       name: '',
-      icon: 'funnel',
       showInSideBar: false,
       showOnDashboard: false,
       permissions_form: permissions,

src-ui/src/app/components/document-list/save-view-config-dialog/save-view-config-dialog.component.ts

@@ -13,14 +13,9 @@ import {
   ReactiveFormsModule,
 } from '@angular/forms'
 import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
-import {
-  DEFAULT_SAVED_VIEW_ICON,
-  SAVED_VIEW_ICONS,
-} from 'src/app/data/saved-view-icons'
 import { User } from 'src/app/data/user'
 import { CheckComponent } from '../../common/input/check/check.component'
 import { PermissionsFormComponent } from '../../common/input/permissions/permissions-form/permissions-form.component'
-import { SelectComponent } from '../../common/input/select/select.component'
 import { TextComponent } from '../../common/input/text/text.component'
 
 @Component({
@@ -29,7 +24,6 @@ import { TextComponent } from '../../common/input/text/text.component'
   styleUrls: ['./save-view-config-dialog.component.scss'],
   imports: [
     CheckComponent,
-    SelectComponent,
     TextComponent,
     PermissionsFormComponent,
     FormsModule,
@@ -47,7 +41,6 @@ export class SaveViewConfigDialogComponent implements OnInit {
   public saveClicked = new EventEmitter()
 
   users: User[]
-  readonly savedViewIcons = SAVED_VIEW_ICONS
 
   setDefaultName(value: string) {
     this.defaultName.set(value)
@@ -56,7 +49,6 @@ export class SaveViewConfigDialogComponent implements OnInit {
 
   saveViewConfigForm = new FormGroup({
     name: new FormControl(''),
-    icon: new FormControl(DEFAULT_SAVED_VIEW_ICON),
     showInSideBar: new FormControl(false),
     showOnDashboard: new FormControl(false),
     permissions_form: new FormControl(null),
@@ -73,7 +65,6 @@ export class SaveViewConfigDialogComponent implements OnInit {
     const formValue = this.saveViewConfigForm.value
     const saveViewConfig = {
       name: formValue.name,
-      icon: formValue.icon,
       showInSideBar: formValue.showInSideBar,
       showOnDashboard: formValue.showOnDashboard,
     }

src-ui/src/app/components/manage/saved-views/saved-views.component.html

@@ -11,19 +11,10 @@
       <li class="list-group-item py-3">
       <div [formGroupName]="view.id">
         <div class="row">
-          <div class="col-md">
+          <div class="col">
             <pngx-input-text title="Name" formControlName="name"></pngx-input-text>
           </div>
-          <div class="col-md">
+          <div class="col">
-            <pngx-input-select
-              i18n-title
-              title="Icon"
-              formControlName="icon"
-              [items]="savedViewIcons"
-              iconField="icon">
-            </pngx-input-select>
-          </div>
-          <div class="col-md">
             <div class="form-check form-switch mt-3">
               <input type="checkbox" class="form-check-input" id="show_on_dashboard_{{view.id}}" formControlName="show_on_dashboard">
               <label class="form-check-label" for="show_on_dashboard_{{view.id}}" i18n>Show on dashboard</label>

src-ui/src/app/components/manage/saved-views/saved-views.component.spec.ts

@@ -25,20 +25,8 @@ import { PageHeaderComponent } from '../../common/page-header/page-header.compon
 import { SavedViewsComponent } from './saved-views.component'
 
 const savedViews = [
-  {
+  { id: 1, name: 'view1', show_in_sidebar: true, show_on_dashboard: true },
-    id: 1,
+  { id: 2, name: 'view2', show_in_sidebar: false, show_on_dashboard: false },
-    name: 'view1',
-    icon: 'archive',
-    show_in_sidebar: true,
-    show_on_dashboard: true,
-  },
-  {
-    id: 2,
-    name: 'view2',
-    icon: 'funnel',
-    show_in_sidebar: false,
-    show_on_dashboard: false,
-  },
 ]
 
 describe('SavedViewsComponent', () => {
@@ -169,24 +157,6 @@ describe('SavedViewsComponent', () => {
     expect(patchBody.show_in_sidebar).toBeUndefined()
   })
 
-  it('should persist a changed icon', () => {
-    const patchSpy = jest.spyOn(savedViewService, 'patchMany')
-    const view = savedViews[0]
-    const iconControl = component.savedViewsForm
-      .get('savedViews')
-      .get(view.id.toString())
-      .get('icon')
-
-    iconControl.setValue('bell')
-    iconControl.markAsDirty()
-    component.save()
-
-    expect(patchSpy.mock.calls[0][0][0]).toMatchObject({
-      id: view.id,
-      icon: 'bell',
-    })
-  })
-
   it('should persist visibility changes to user settings', () => {
     const patchSpy = jest.spyOn(savedViewService, 'patchMany')
     const updateVisibilitySpy = jest

src-ui/src/app/components/manage/saved-views/saved-views.component.ts

@@ -13,10 +13,6 @@ import { BehaviorSubject, Observable, of, switchMap, takeUntil } from 'rxjs'
 import { PermissionsDialogComponent } from 'src/app/components/common/permissions-dialog/permissions-dialog.component'
 import { DisplayMode } from 'src/app/data/document'
 import { SavedView } from 'src/app/data/saved-view'
-import {
-  DEFAULT_SAVED_VIEW_ICON,
-  SAVED_VIEW_ICONS,
-} from 'src/app/data/saved-view-icons'
 import { IfPermissionsDirective } from 'src/app/directives/if-permissions.directive'
 import {
   PermissionAction,
@@ -28,7 +24,6 @@ import { ToastService } from 'src/app/services/toast.service'
 import { ConfirmButtonComponent } from '../../common/confirm-button/confirm-button.component'
 import { DragDropSelectComponent } from '../../common/input/drag-drop-select/drag-drop-select.component'
 import { NumberComponent } from '../../common/input/number/number.component'
-import { SelectComponent } from '../../common/input/select/select.component'
 import { TextComponent } from '../../common/input/text/text.component'
 import { PageHeaderComponent } from '../../common/page-header/page-header.component'
 import { LoadingComponentWithPermissions } from '../../loading-component/loading.component'
@@ -40,7 +35,6 @@ import { LoadingComponentWithPermissions } from '../../loading-component/loading
     PageHeaderComponent,
     ConfirmButtonComponent,
     NumberComponent,
-    SelectComponent,
     TextComponent,
     IfPermissionsDirective,
     DragDropSelectComponent,
@@ -61,7 +55,6 @@ export class SavedViewsComponent
   private readonly modalService = inject(NgbModal)
 
   DisplayMode = DisplayMode
-  readonly savedViewIcons = SAVED_VIEW_ICONS
 
   readonly savedViews = signal<SavedView[]>(undefined)
   private savedViewsGroup = new FormGroup({})
@@ -112,7 +105,6 @@ export class SavedViewsComponent
       storeData.savedViews[view.id.toString()] = {
         id: view.id,
         name: view.name,
-        icon: view.icon ?? DEFAULT_SAVED_VIEW_ICON,
         show_on_dashboard: view.show_on_dashboard,
         show_in_sidebar: view.show_in_sidebar,
         page_size: view.page_size,
@@ -125,7 +117,6 @@ export class SavedViewsComponent
         new FormGroup({
           id: new FormControl({ value: null, disabled: !canEdit }),
           name: new FormControl({ value: null, disabled: !canEdit }),
-          icon: new FormControl({ value: null, disabled: !canEdit }),
           show_on_dashboard: new FormControl({
             value: null,
             disabled: false,
@@ -204,7 +195,6 @@ export class SavedViewsComponent
 
       const modelFieldsChanged =
         group.get('name')?.dirty ||
-        group.get('icon')?.dirty ||
         group.get('page_size')?.dirty ||
         group.get('display_mode')?.dirty ||
         group.get('display_fields')?.dirty

src-ui/src/app/data/saved-view-icons.ts

@@ -1,89 +0,0 @@
-export const DEFAULT_SAVED_VIEW_ICON = 'funnel'
-
-export const SAVED_VIEW_ICONS = [
-  { id: 'archive', name: $localize`Archive`, icon: 'archive' },
-  { id: 'bank', name: $localize`Bank`, icon: 'bank' },
-  { id: 'basket', name: $localize`Basket`, icon: 'basket' },
-  { id: 'bell', name: $localize`Bell`, icon: 'bell' },
-  { id: 'bookmark', name: $localize`Bookmark`, icon: 'bookmark' },
-  { id: 'boxes', name: $localize`Boxes`, icon: 'boxes' },
-  { id: 'briefcase', name: $localize`Briefcase`, icon: 'briefcase' },
-  { id: 'building', name: $localize`Building`, icon: 'building' },
-  { id: 'calculator', name: $localize`Calculator`, icon: 'calculator' },
-  { id: 'calendar', name: $localize`Calendar`, icon: 'calendar' },
-  { id: 'camera', name: $localize`Camera`, icon: 'camera' },
-  {
-    id: 'card-checklist',
-    name: $localize`Checklist`,
-    icon: 'card-checklist',
-  },
-  { id: 'cash', name: $localize`Cash`, icon: 'cash' },
-  { id: 'chat-left-text', name: $localize`Chat`, icon: 'chat-left-text' },
-  { id: 'check-circle', name: $localize`Check`, icon: 'check-circle' },
-  { id: 'clipboard', name: $localize`Clipboard`, icon: 'clipboard' },
-  { id: 'clock-history', name: $localize`Clock`, icon: 'clock-history' },
-  { id: 'credit-card', name: $localize`Credit card`, icon: 'credit-card' },
-  { id: 'download', name: $localize`Download`, icon: 'download' },
-  { id: 'envelope', name: $localize`Envelope`, icon: 'envelope' },
-  {
-    id: 'exclamation-triangle',
-    name: $localize`Warning`,
-    icon: 'exclamation-triangle',
-  },
-  { id: 'file-earmark', name: $localize`File`, icon: 'file-earmark' },
-  {
-    id: 'file-earmark-check',
-    name: $localize`Checked file`,
-    icon: 'file-earmark-check',
-  },
-  {
-    id: 'file-earmark-lock',
-    name: $localize`Locked file`,
-    icon: 'file-earmark-lock',
-  },
-  {
-    id: 'file-earmark-medical',
-    name: $localize`Medical file`,
-    icon: 'file-earmark-medical',
-  },
-  {
-    id: 'file-earmark-person',
-    name: $localize`Person file`,
-    icon: 'file-earmark-person',
-  },
-  {
-    id: 'file-earmark-spreadsheet',
-    name: $localize`Spreadsheet`,
-    icon: 'file-earmark-spreadsheet',
-  },
-  { id: 'file-text', name: $localize`Text file`, icon: 'file-text' },
-  { id: 'files', name: $localize`Files`, icon: 'files' },
-  { id: 'folder', name: $localize`Folder`, icon: 'folder' },
-  { id: 'funnel', name: $localize`Filter`, icon: 'funnel' },
-  { id: 'gear', name: $localize`Gear`, icon: 'gear' },
-  { id: 'globe2', name: $localize`Globe`, icon: 'globe2' },
-  { id: 'hash', name: $localize`Hash`, icon: 'hash' },
-  { id: 'heart', name: $localize`Heart`, icon: 'heart' },
-  { id: 'house', name: $localize`House`, icon: 'house' },
-  { id: 'inbox', name: $localize`Inbox`, icon: 'inbox' },
-  { id: 'journals', name: $localize`Journals`, icon: 'journals' },
-  { id: 'list-task', name: $localize`Task list`, icon: 'list-task' },
-  { id: 'newspaper', name: $localize`Newspaper`, icon: 'newspaper' },
-  { id: 'paperclip', name: $localize`Attachment`, icon: 'paperclip' },
-  { id: 'people', name: $localize`People`, icon: 'people' },
-  { id: 'person', name: $localize`Person`, icon: 'person' },
-  { id: 'printer', name: $localize`Printer`, icon: 'printer' },
-  { id: 'receipt', name: $localize`Receipt`, icon: 'receipt' },
-  { id: 'safe', name: $localize`Safe`, icon: 'safe' },
-  { id: 'search', name: $localize`Search`, icon: 'search' },
-  { id: 'send', name: $localize`Send`, icon: 'send' },
-  { id: 'shop', name: $localize`Shop`, icon: 'shop' },
-  { id: 'stack', name: $localize`Stack`, icon: 'stack' },
-  { id: 'stars', name: $localize`Stars`, icon: 'stars' },
-  { id: 'tag', name: $localize`Tag`, icon: 'tag' },
-  { id: 'tags', name: $localize`Tags`, icon: 'tags' },
-  { id: 'telephone', name: $localize`Telephone`, icon: 'telephone' },
-  { id: 'truck', name: $localize`Truck`, icon: 'truck' },
-  { id: 'upc-scan', name: $localize`Barcode`, icon: 'upc-scan' },
-  { id: 'wallet2', name: $localize`Wallet`, icon: 'wallet2' },
-]

src-ui/src/app/data/saved-view.ts

@@ -5,8 +5,6 @@ import { ObjectWithPermissions } from './object-with-permissions'
 export interface SavedView extends ObjectWithPermissions {
   name?: string
 
-  icon?: string
-
   show_on_dashboard?: boolean
 
   show_in_sidebar?: boolean

src-ui/src/main.ts

@@ -35,27 +35,19 @@ import {
   arrowRightShort,
   arrowUpRight,
   asterisk,
-  bank,
-  basket,
   bell,
   bodyText,
-  bookmark,
   boxArrowUp,
   boxArrowUpRight,
   boxes,
   braces,
-  briefcase,
-  building,
-  calculator,
   calendar,
   calendarEvent,
   calendarEventFill,
-  camera,
   cardChecklist,
   cardHeading,
   caretDown,
   caretUp,
-  cash,
   chatLeftText,
   chatSquareDots,
   check,
@@ -73,7 +65,6 @@ import {
   clipboardCheckFill,
   clipboardFill,
   clockHistory,
-  creditCard,
   dash,
   dashCircle,
   diagram3,
@@ -92,12 +83,9 @@ import {
   fileEarmarkDiff,
   fileEarmarkFill,
   fileEarmarkLock,
-  fileEarmarkMedical,
   fileEarmarkMinus,
-  fileEarmarkPerson,
   fileEarmarkPlus,
   fileEarmarkRichtext,
-  fileEarmarkSpreadsheet,
   fileText,
   files,
   filter,
@@ -105,15 +93,12 @@ import {
   folderFill,
   funnel,
   gear,
-  globe2,
   google,
   grid,
   gripVertical,
   hash,
   hddStack,
-  heart,
   house,
-  inbox,
   infoCircle,
   journals,
   link,
@@ -121,9 +106,7 @@ import {
   listTask,
   listUl,
   microsoft,
-  newspaper,
   nodePlus,
-  paperclip,
   pencil,
   people,
   peopleFill,
@@ -138,12 +121,9 @@ import {
   plusCircle,
   printer,
   questionCircle,
-  receipt,
-  safe,
   scissors,
   search,
   send,
-  shop,
   slashCircle,
   sliders2Vertical,
   sortAlphaDown,
@@ -153,17 +133,14 @@ import {
   tag,
   tagFill,
   tags,
-  telephone,
   textIndentLeft,
   textLeft,
   threeDots,
   threeDotsVertical,
   trash,
-  truck,
   uiRadios,
   unlock,
   upcScan,
-  wallet2,
   windowStack,
   x,
   xCircle,
@@ -281,22 +258,15 @@ const icons = {
   arrowRightShort,
   arrowUpRight,
   asterisk,
-  bank,
-  basket,
   bell,
   braces,
   bodyText,
-  bookmark,
   boxArrowUp,
   boxArrowUpRight,
   boxes,
-  briefcase,
-  building,
-  calculator,
   calendar,
   calendarEvent,
   calendarEventFill,
-  camera,
   cardChecklist,
   cardHeading,
   caretDown,
@@ -318,8 +288,6 @@ const icons = {
   clipboardCheckFill,
   clipboardFill,
   clockHistory,
-  cash,
-  creditCard,
   dash,
   dashCircle,
   diagram3,
@@ -338,12 +306,9 @@ const icons = {
   fileEarmarkDiff,
   fileEarmarkFill,
   fileEarmarkLock,
-  fileEarmarkMedical,
   fileEarmarkMinus,
-  fileEarmarkPerson,
   fileEarmarkPlus,
   fileEarmarkRichtext,
-  fileEarmarkSpreadsheet,
   files,
   fileText,
   filter,
@@ -351,15 +316,12 @@ const icons = {
   folderFill,
   funnel,
   gear,
-  globe2,
   google,
   grid,
   gripVertical,
   hash,
   hddStack,
-  heart,
   house,
-  inbox,
   infoCircle,
   journals,
   link,
@@ -367,10 +329,8 @@ const icons = {
   listTask,
   listUl,
   microsoft,
-  newspaper,
   nodePlus,
   pencil,
-  paperclip,
   people,
   peopleFill,
   person,
@@ -384,13 +344,10 @@ const icons = {
   plusCircle,
   printer,
   questionCircle,
-  receipt,
-  safe,
   scissors,
   search,
   send,
   slashCircle,
-  shop,
   sliders2Vertical,
   sortAlphaDown,
   sortAlphaUpAlt,
@@ -401,15 +358,12 @@ const icons = {
   tags,
   textIndentLeft,
   textLeft,
-  telephone,
   threeDots,
   threeDotsVertical,
   trash,
-  truck,
   uiRadios,
   unlock,
   upcScan,
-  wallet2,
   windowStack,
   x,
   xCircle,

src/documents/consumer.py

@@ -57,9 +57,7 @@ from paperless.models import ArchiveFileGenerationChoices
 from paperless.parsers import ParserContext
 from paperless.parsers import ParserProtocol
 from paperless.parsers.registry import get_parser_registry
-from paperless.parsers.utils import PDF_TEXT_MIN_LENGTH
+from paperless.parsers.utils import pdf_born_digital_text
-from paperless.parsers.utils import extract_pdf_text
-from paperless.parsers.utils import is_tagged_pdf
 
 LOGGING_NAME: Final[str] = "paperless.consumer"
 
@@ -138,53 +136,45 @@ def should_produce_archive(
 
     # Must produce a PDF so the frontend can display the original format at all.
     if parser.requires_pdf_rendition:
-        _log.debug("Archive: yes — parser requires PDF rendition for frontend display")
+        _log.debug("Archive: yes - parser requires PDF rendition for frontend display")
         return True
 
     # Parser cannot produce an archive (e.g. TextDocumentParser).
     if not parser.can_produce_archive:
-        _log.debug("Archive: no — parser cannot produce archives")
+        _log.debug("Archive: no - parser cannot produce archives")
         return False
 
     generation = OcrConfig().archive_file_generation
 
     if generation == ArchiveFileGenerationChoices.ALWAYS:
-        _log.debug("Archive: yes — ARCHIVE_FILE_GENERATION=always")
+        _log.debug("Archive: yes - ARCHIVE_FILE_GENERATION=always")
         return True
     if generation == ArchiveFileGenerationChoices.NEVER:
-        _log.debug("Archive: no — ARCHIVE_FILE_GENERATION=never")
+        _log.debug("Archive: no - ARCHIVE_FILE_GENERATION=never")
         return False
 
     # auto: produce archives for scanned/image documents; skip for born-digital PDFs.
     if mime_type.startswith("image/"):
-        _log.debug("Archive: yes — image document, ARCHIVE_FILE_GENERATION=auto")
+        _log.debug("Archive: yes - image document, ARCHIVE_FILE_GENERATION=auto")
         return True
     if mime_type == "application/pdf":
-        text = extract_pdf_text(document_path)
+        text, born_digital = pdf_born_digital_text(document_path, log=_log)
-        has_text = text is not None and len(text) > 0
+        text_length = len(text) if text else 0
-        if has_text and is_tagged_pdf(document_path):
+        if born_digital:
             _log.debug(
-                "Archive: no — born-digital PDF (structure tags detected),"
+                "Archive: no - born-digital PDF (text_length=%d),"
                 " ARCHIVE_FILE_GENERATION=auto",
+                text_length,
             )
             return False
-        if text is None or len(text) <= PDF_TEXT_MIN_LENGTH:
-            _log.debug(
-                "Archive: yes — scanned PDF (text_length=%d ≤ %d),"
-                " ARCHIVE_FILE_GENERATION=auto",
-                len(text) if text else 0,
-                PDF_TEXT_MIN_LENGTH,
-            )
-            return True
         _log.debug(
-            "Archive: no — born-digital PDF (text_length=%d > %d),"
+            "Archive: yes - scanned/textless PDF (text_length=%d),"
             " ARCHIVE_FILE_GENERATION=auto",
-            len(text),
+            text_length,
-            PDF_TEXT_MIN_LENGTH,
         )
-        return False
+        return True
     _log.debug(
-        "Archive: no — MIME type %r not eligible for auto archive generation",
+        "Archive: no - MIME type %r not eligible for auto archive generation",
         mime_type,
     )
     return False

src/documents/mail.py

@@ -36,6 +36,9 @@ def send_email(
 
     TODO: re-evaluate this pending https://code.djangoproject.com/ticket/35581 / https://github.com/django/django/pull/18966
     """
+    if "\r" in subject or "\n" in subject:
+        subject = " ".join(line.strip(" \t") for line in subject.splitlines())
+
     email = EmailMessage(
         subject=subject,
         body=body,

src/documents/management/commands/document_importer.py

@@ -386,10 +386,19 @@ class Command(CryptMixin, PaperlessCommand):
                 raise DeserializationError(
                     f"{model.__name__} has no updatable fields; PK-only models are not supported by the importer",
                 )
+            # MySQL/MariaDB support upserts via ON DUPLICATE KEY UPDATE but,
+            # unlike PostgreSQL/SQLite, cannot target a specific unique field
+            # for the conflict -- passing unique_fields there raises
+            # NotSupportedError.
+            unique_fields = (
+                [model._meta.pk.attname]
+                if connection.features.supports_update_conflicts_with_target
+                else None
+            )
             model.objects.bulk_create(  # type: ignore[attr-defined]
                 instances,
                 update_conflicts=True,
-                unique_fields=[model._meta.pk.attname],
+                unique_fields=unique_fields,
                 update_fields=update_fields,
             )
             loaded_models.add(model)

src/documents/migrations/0023_savedview_icon.py

@@ -1,79 +0,0 @@
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0022_add_perf_indexes"),
-    ]
-
-    operations = [
-        migrations.AddField(
-            model_name="savedview",
-            name="icon",
-            field=models.CharField(
-                choices=[
-                    ("archive", "Archive"),
-                    ("bank", "Bank"),
-                    ("basket", "Basket"),
-                    ("bell", "Bell"),
-                    ("bookmark", "Bookmark"),
-                    ("boxes", "Boxes"),
-                    ("briefcase", "Briefcase"),
-                    ("building", "Building"),
-                    ("calculator", "Calculator"),
-                    ("calendar", "Calendar"),
-                    ("camera", "Camera"),
-                    ("card-checklist", "Checklist"),
-                    ("cash", "Cash"),
-                    ("chat-left-text", "Chat"),
-                    ("check-circle", "Check"),
-                    ("clipboard", "Clipboard"),
-                    ("clock-history", "Clock"),
-                    ("credit-card", "Credit card"),
-                    ("download", "Download"),
-                    ("envelope", "Envelope"),
-                    ("exclamation-triangle", "Warning"),
-                    ("file-earmark", "File"),
-                    ("file-earmark-check", "Checked file"),
-                    ("file-earmark-lock", "Locked file"),
-                    ("file-earmark-medical", "Medical file"),
-                    ("file-earmark-person", "Person file"),
-                    ("file-earmark-spreadsheet", "Spreadsheet"),
-                    ("file-text", "Text file"),
-                    ("files", "Files"),
-                    ("folder", "Folder"),
-                    ("funnel", "Filter"),
-                    ("gear", "Gear"),
-                    ("globe2", "Globe"),
-                    ("hash", "Hash"),
-                    ("heart", "Heart"),
-                    ("house", "House"),
-                    ("inbox", "Inbox"),
-                    ("journals", "Journals"),
-                    ("list-task", "Task list"),
-                    ("newspaper", "Newspaper"),
-                    ("paperclip", "Attachment"),
-                    ("people", "People"),
-                    ("person", "Person"),
-                    ("printer", "Printer"),
-                    ("receipt", "Receipt"),
-                    ("safe", "Safe"),
-                    ("search", "Search"),
-                    ("send", "Send"),
-                    ("shop", "Shop"),
-                    ("stack", "Stack"),
-                    ("stars", "Stars"),
-                    ("tag", "Tag"),
-                    ("tags", "Tags"),
-                    ("telephone", "Telephone"),
-                    ("truck", "Truck"),
-                    ("upc-scan", "Barcode"),
-                    ("wallet2", "Wallet"),
-                ],
-                default="funnel",
-                max_length=64,
-                verbose_name="icon",
-            ),
-        ),
-    ]

src/documents/models.py

@@ -519,68 +519,6 @@ class Document(SoftDeleteModel, ModelWithOwner):  # type: ignore[django-manager-
 
 
 class SavedView(ModelWithOwner):
-    class Icon(models.TextChoices):
-        ARCHIVE = ("archive", _("Archive"))
-        BANK = ("bank", _("Bank"))
-        BASKET = ("basket", _("Basket"))
-        BELL = ("bell", _("Bell"))
-        BOOKMARK = ("bookmark", _("Bookmark"))
-        BOXES = ("boxes", _("Boxes"))
-        BRIEFCASE = ("briefcase", _("Briefcase"))
-        BUILDING = ("building", _("Building"))
-        CALCULATOR = ("calculator", _("Calculator"))
-        CALENDAR = ("calendar", _("Calendar"))
-        CAMERA = ("camera", _("Camera"))
-        CARD_CHECKLIST = ("card-checklist", _("Checklist"))
-        CASH = ("cash", _("Cash"))
-        CHAT_LEFT_TEXT = ("chat-left-text", _("Chat"))
-        CHECK_CIRCLE = ("check-circle", _("Check"))
-        CLIPBOARD = ("clipboard", _("Clipboard"))
-        CLOCK_HISTORY = ("clock-history", _("Clock"))
-        CREDIT_CARD = ("credit-card", _("Credit card"))
-        DOWNLOAD = ("download", _("Download"))
-        ENVELOPE = ("envelope", _("Envelope"))
-        EXCLAMATION_TRIANGLE = ("exclamation-triangle", _("Warning"))
-        FILE_EARMARK = ("file-earmark", _("File"))
-        FILE_EARMARK_CHECK = ("file-earmark-check", _("Checked file"))
-        FILE_EARMARK_LOCK = ("file-earmark-lock", _("Locked file"))
-        FILE_EARMARK_MEDICAL = ("file-earmark-medical", _("Medical file"))
-        FILE_EARMARK_PERSON = ("file-earmark-person", _("Person file"))
-        FILE_EARMARK_SPREADSHEET = (
-            "file-earmark-spreadsheet",
-            _("Spreadsheet"),
-        )
-        FILE_TEXT = ("file-text", _("Text file"))
-        FILES = ("files", _("Files"))
-        FOLDER = ("folder", _("Folder"))
-        FUNNEL = ("funnel", _("Filter"))
-        GEAR = ("gear", _("Gear"))
-        GLOBE = ("globe2", _("Globe"))
-        HASH = ("hash", _("Hash"))
-        HEART = ("heart", _("Heart"))
-        HOUSE = ("house", _("House"))
-        INBOX = ("inbox", _("Inbox"))
-        JOURNALS = ("journals", _("Journals"))
-        LIST_TASK = ("list-task", _("Task list"))
-        NEWSPAPER = ("newspaper", _("Newspaper"))
-        PAPERCLIP = ("paperclip", _("Attachment"))
-        PEOPLE = ("people", _("People"))
-        PERSON = ("person", _("Person"))
-        PRINTER = ("printer", _("Printer"))
-        RECEIPT = ("receipt", _("Receipt"))
-        SAFE = ("safe", _("Safe"))
-        SEARCH = ("search", _("Search"))
-        SEND = ("send", _("Send"))
-        SHOP = ("shop", _("Shop"))
-        STACK = ("stack", _("Stack"))
-        STARS = ("stars", _("Stars"))
-        TAG = ("tag", _("Tag"))
-        TAGS = ("tags", _("Tags"))
-        TELEPHONE = ("telephone", _("Telephone"))
-        TRUCK = ("truck", _("Truck"))
-        UPC_SCAN = ("upc-scan", _("Barcode"))
-        WALLET = ("wallet2", _("Wallet"))
-
     class DisplayMode(models.TextChoices):
         TABLE = ("table", _("Table"))
         SMALL_CARDS = ("smallCards", _("Small Cards"))
@@ -603,13 +541,6 @@ class SavedView(ModelWithOwner):
 
     name = models.CharField(_("name"), max_length=128)
 
-    icon = models.CharField(
-        _("icon"),
-        max_length=64,
-        choices=Icon.choices,
-        default=Icon.FUNNEL,
-    )
-
     sort_field = models.CharField(
         _("sort field"),
         max_length=128,

src/documents/serialisers.py

@@ -1389,7 +1389,6 @@ class SavedViewSerializer(OwnedObjectSerializer):
         fields = [
             "id",
             "name",
-            "icon",
             "sort_field",
             "sort_reverse",
             "filter_rules",

src/documents/tests/test_api_documents.py

@@ -2880,20 +2880,18 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
 
         v1 = SavedView.objects.get(name="test")
         self.assertEqual(v1.sort_field, "created2")
-        self.assertEqual(v1.icon, SavedView.Icon.FUNNEL)
         self.assertEqual(v1.filter_rules.count(), 1)
         self.assertEqual(v1.owner, self.user)
 
         response = self.client.patch(
             f"/api/saved_views/{v1.id}/",
-            {"sort_reverse": True, "icon": SavedView.Icon.RECEIPT},
+            {"sort_reverse": True},
             format="json",
         )
 
         v1 = SavedView.objects.get(id=v1.id)
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         self.assertTrue(v1.sort_reverse)
-        self.assertEqual(v1.icon, SavedView.Icon.RECEIPT)
         self.assertEqual(v1.filter_rules.count(), 1)
 
         view["filter_rules"] = [{"rule_type": 12, "value": "secret"}]
@@ -2913,13 +2911,6 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         v1 = SavedView.objects.get(id=v1.id)
         self.assertEqual(v1.filter_rules.count(), 0)
 
-        response = self.client.patch(
-            f"/api/saved_views/{v1.id}/",
-            {"icon": "not-an-icon"},
-            format="json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-
     def test_saved_view_display_options(self) -> None:
         """
         GIVEN:

src/documents/tests/test_api_email.py

@@ -75,7 +75,7 @@ class TestEmail(DirectoriesMixin, SampleDirMixin, APITestCase):
                 {
                     "documents": [self.doc1.pk, self.doc2.pk],
                     "addresses": "hello@paperless-ngx.com,test@example.com",
-                    "subject": "Bulk email test",
+                    "subject": "Bulk email\n test",
                     "message": "Here are your documents",
                 },
             ),

src/documents/tests/test_consumer.py

@@ -1329,7 +1329,7 @@ class PreConsumeTestCase(DirectoriesMixin, GetConsumerMixin, TestCase):
         with self.get_consumer(self.test_file) as c:
             c.run()
             # Verify no pre-consume script subprocess was invoked
-            # (run_subprocess may still be called by _extract_text_for_archive_check)
+            # (run_subprocess may still be called by pdf_born_digital_text via pdftotext)
             script_calls = [
                 call
                 for call in m.call_args_list
@@ -1354,7 +1354,7 @@ class PreConsumeTestCase(DirectoriesMixin, GetConsumerMixin, TestCase):
                     self.assertTrue(m.called)
 
                     # Find the call that invoked the pre-consume script
-                    # (run_subprocess may also be called by _extract_text_for_archive_check)
+                    # (run_subprocess may also be called by pdf_born_digital_text via pdftotext)
                     script_call = next(
                         call
                         for call in m.call_args_list

src/documents/tests/test_consumer_archive.py

@@ -134,60 +134,32 @@ class TestShouldProduceArchive:
         assert should_produce_archive(parser, mime, Path("/tmp/doc")) is expected
 
     @pytest.mark.parametrize(
-        ("extracted_text", "expected"),
+        ("born_digital", "expected"),
         [
-            pytest.param(
+            pytest.param(True, False, id="born-digital-skips-archive"),
-                "This is a born-digital PDF with lots of text content. " * 10,
+            pytest.param(False, True, id="not-born-digital-produces-archive"),
-                False,
-                id="born-digital-long-text-skips-archive",
-            ),
-            pytest.param(None, True, id="no-text-scanned-produces-archive"),
-            pytest.param("tiny", True, id="short-text-treated-as-scanned"),
         ],
     )
     def test_auto_pdf_archive_decision(
         self,
         mocker: MockerFixture,
         settings,
-        extracted_text: str | None,
+        born_digital: bool,  # noqa: FBT001
         expected: bool,  # noqa: FBT001
     ) -> None:
+        """Archive decision tracks pdf_born_digital_text()'s verdict exactly.
+
+        should_produce_archive() defers entirely to pdf_born_digital_text()
+        for the has-real-text decision, so both callers of that predicate
+        (this function and RasterisedDocumentParser.parse()) always agree.
+        """
         settings.ARCHIVE_FILE_GENERATION = "auto"
-        mocker.patch("documents.consumer.is_tagged_pdf", return_value=False)
+        mocker.patch(
-        mocker.patch("documents.consumer.extract_pdf_text", return_value=extracted_text)
+            "documents.consumer.pdf_born_digital_text",
+            return_value=("some text", born_digital),
+        )
         parser = _parser_instance(can_produce=True, requires_rendition=False)
         assert (
             should_produce_archive(parser, "application/pdf", Path("/tmp/doc.pdf"))
             is expected
         )
-
-    def test_tagged_pdf_skips_archive_in_auto_mode(
-        self,
-        mocker: MockerFixture,
-        settings,
-    ) -> None:
-        """Tagged PDFs (e.g. Word exports) with real text are treated as born-digital, even below PDF_TEXT_MIN_LENGTH."""
-        settings.ARCHIVE_FILE_GENERATION = "auto"
-        mocker.patch("documents.consumer.is_tagged_pdf", return_value=True)
-        mocker.patch("documents.consumer.extract_pdf_text", return_value="tiny")
-        parser = _parser_instance(can_produce=True, requires_rendition=False)
-        assert (
-            should_produce_archive(parser, "application/pdf", Path("/tmp/doc.pdf"))
-            is False
-        )
-
-    def test_tagged_pdf_without_text_produces_archive(
-        self,
-        mocker: MockerFixture,
-        settings,
-    ) -> None:
-        """A tagged PDF with no actual extractable text (e.g. some scanner firmware) is not
-        trusted as born-digital — the tag alone must not bypass OCR."""
-        settings.ARCHIVE_FILE_GENERATION = "auto"
-        mocker.patch("documents.consumer.is_tagged_pdf", return_value=True)
-        mocker.patch("documents.consumer.extract_pdf_text", return_value=None)
-        parser = _parser_instance(can_produce=True, requires_rendition=False)
-        assert (
-            should_produce_archive(parser, "application/pdf", Path("/tmp/doc.pdf"))
-            is True
-        )

src/paperless/parsers/tesseract.py

@@ -3,7 +3,6 @@ from __future__ import annotations
 import importlib.resources
 import logging
 import os
-import re
 import shutil
 import tempfile
 from pathlib import Path
@@ -25,9 +24,9 @@ from paperless.config import OcrConfig
 from paperless.models import CleanChoices
 from paperless.models import ModeChoices
 from paperless.models import OutputTypeChoices
-from paperless.parsers.utils import PDF_TEXT_MIN_LENGTH
 from paperless.parsers.utils import extract_pdf_text
-from paperless.parsers.utils import is_tagged_pdf
+from paperless.parsers.utils import is_born_digital_text
+from paperless.parsers.utils import post_process_text
 from paperless.parsers.utils import read_file_handle_unicode_errors
 from paperless.version import __full_version_str__
 
@@ -510,10 +509,10 @@ class RasterisedDocumentParser:
 
         if mime_type == "application/pdf":
             text_original = self.extract_text(None, document_path)
-            has_text = text_original is not None and len(text_original) > 0
+            original_has_text = is_born_digital_text(
-            original_has_text = has_text and (
+                text_original,
-                is_tagged_pdf(document_path, log=self.log)
+                document_path,
-                or len(text_original) > PDF_TEXT_MIN_LENGTH
+                log=self.log,
             )
         else:
             text_original = None
@@ -658,17 +657,3 @@ class RasterisedDocumentParser:
                     f"No text was found in {document_path}, the content will be empty.",
                 )
                 self.text = ""
-
-
-def post_process_text(text: str | None) -> str | None:
-    if not text:
-        return None
-
-    collapsed_spaces = re.sub(r"([^\S\r\n]+)", " ", text)
-    no_leading_whitespace = re.sub(r"([\n\r]+)([^\S\n\r]+)", "\\1", collapsed_spaces)
-    no_trailing_whitespace = re.sub(r"([^\S\n\r]+)$", "", no_leading_whitespace)
-
-    # TODO: this needs a rework
-    # replace \0 prevents issues with saving to postgres.
-    # text may contain \0 when this character is present in PDF files.
-    return no_trailing_whitespace.strip().replace("\0", " ")

src/paperless/parsers/utils.py

@@ -111,6 +111,88 @@ def extract_pdf_text(
         return None
 
 
+def post_process_text(text: str | None) -> str | None:
+    """Normalize extracted PDF/OCR text: collapse whitespace, strip padding.
+
+    Returns ``None`` for ``None`` or whitespace-only input, so callers can
+    treat "no text" and "only layout padding" the same way.
+    """
+    if not text:
+        return None
+
+    collapsed_spaces = re.sub(r"([^\S\r\n]+)", " ", text)
+    no_leading_whitespace = re.sub(r"([\n\r]+)([^\S\n\r]+)", "\\1", collapsed_spaces)
+    no_trailing_whitespace = re.sub(r"([^\S\n\r]+)$", "", no_leading_whitespace)
+
+    # replace \0 prevents issues with saving to postgres.
+    # text may contain \0 when this character is present in PDF files.
+    result = no_trailing_whitespace.strip().replace("\0", " ")
+    return result or None
+
+
+def is_born_digital_text(
+    text: str | None,
+    path: Path,
+    log: logging.Logger | None = None,
+) -> bool:
+    """Decide whether already-extracted, normalized PDF text counts as born-digital.
+
+    This is the single source of truth for "does this PDF already have real
+    text", used both to decide whether to produce an archive file and to
+    decide whether OCR can be skipped. Both decisions must agree, or a
+    tagged-but-textless PDF can end up with no archive AND a forced OCR pass
+    (see GH #13387): raw ``pdftotext -layout`` output can be non-empty
+    (whitespace/form-feed padding) even when there is no real content, so
+    *text* must already be normalized via :func:`post_process_text`, not the
+    raw extraction.
+
+    Parameters
+    ----------
+    text:
+        The normalized extracted text (or ``None``) to evaluate.
+    path:
+        Absolute path to the PDF file, used for the tagged-PDF check.
+    log:
+        Logger for warnings.  Falls back to the module-level logger when omitted.
+
+    Returns
+    -------
+    bool
+        Whether the PDF counts as born-digital (has real text, and is either
+        tagged or exceeds ``PDF_TEXT_MIN_LENGTH``).
+    """
+    if not text:
+        return False
+    return is_tagged_pdf(path, log=log) or len(text) > PDF_TEXT_MIN_LENGTH
+
+
+def pdf_born_digital_text(
+    path: Path,
+    log: logging.Logger | None = None,
+) -> tuple[str | None, bool]:
+    """Extract a PDF's text and decide whether it should be treated as born-digital.
+
+    Convenience wrapper around :func:`is_born_digital_text` for callers that
+    don't already have the PDF's text extracted (e.g. the archive-generation
+    decision, which runs before any parser has touched the file).
+
+    Parameters
+    ----------
+    path:
+        Absolute path to the PDF file.
+    log:
+        Logger for warnings.  Falls back to the module-level logger when omitted.
+
+    Returns
+    -------
+    tuple[str | None, bool]
+        The normalized extracted text (or ``None``), and whether the PDF
+        counts as born-digital.
+    """
+    text = post_process_text(extract_pdf_text(path, log=log))
+    return text, is_born_digital_text(text, path, log=log)
+
+
 def read_file_handle_unicode_errors(
     filepath: Path,
     log: logging.Logger | None = None,

src/paperless/tests/conftest.py

@@ -36,6 +36,23 @@ def samples_dir() -> Path:
     return (Path(__file__).parent / "samples").resolve()
 
 
+@pytest.fixture(scope="session")
+def tagged_no_text_pdf_file(samples_dir: Path) -> Path:
+    """Path to a tagged PDF whose only "text" is pdftotext layout padding.
+
+    Reproduces GH #13387: ``/MarkInfo /Marked true`` is set, but the only
+    extractable content is a form-feed byte, not real text. Lives here
+    rather than in parsers/conftest.py so both parser tests and
+    paperless/tests/test_parser_utils.py can use it.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/tagged-but-no-text.pdf``.
+    """
+    return samples_dir / "tesseract" / "tagged-but-no-text.pdf"
+
+
 @pytest.fixture(autouse=True)
 def clean_registry() -> Generator[None, None, None]:
     """Reset the parser registry before and after every test.

src/paperless/tests/parsers/test_tesseract_parser.py

@@ -21,7 +21,7 @@ from documents.parsers import run_convert
 from paperless.models import ModeChoices
 from paperless.parsers import ParserProtocol
 from paperless.parsers.tesseract import RasterisedDocumentParser
-from paperless.parsers.tesseract import post_process_text
+from paperless.parsers.utils import is_tagged_pdf
 
 if TYPE_CHECKING:
     from pathlib import Path
@@ -151,36 +151,6 @@ class TestRasterisedDocumentParserLifecycle:
         assert tempdir is not None and not tempdir.exists()
 
 
-# ---------------------------------------------------------------------------
-# post_process_text
-# ---------------------------------------------------------------------------
-
-
-class TestPostProcessText:
-    @pytest.mark.parametrize(
-        ("source", "expected"),
-        [
-            pytest.param(
-                "simple     string",
-                "simple string",
-                id="collapse-spaces",
-            ),
-            pytest.param(
-                "simple    newline\n   testing string",
-                "simple newline\ntesting string",
-                id="preserve-newline",
-            ),
-            pytest.param(
-                "utf-8   строка с пробелами в конце  ",  # noqa: RUF001
-                "utf-8 строка с пробелами в конце",  # noqa: RUF001
-                id="utf8-trailing-spaces",
-            ),
-        ],
-    )
-    def test_post_process_text(self, source: str, expected: str) -> None:
-        assert post_process_text(source) == expected
-
-
 # ---------------------------------------------------------------------------
 # Page count
 # ---------------------------------------------------------------------------
@@ -910,25 +880,25 @@ class TestSkipArchive:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        tagged_no_text_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
-            - A PDF that reports itself as tagged (/MarkInfo /Marked true) but
+            - A real PDF that reports itself as tagged (/MarkInfo /Marked
-              has no actual extractable text (some scanner firmware produces
+              true) but whose only pdftotext output is layout padding (a
-              this — see GitHub issue #13349)
+              lone form-feed byte), not real text (see GitHub issue #13387,
+              originally reported against #13349's tagged-PDF handling)
             - Mode: auto, produce_archive=False
         WHEN:
             - Document is parsed
         THEN:
             - The tag alone is not trusted as "has text"; OCRmyPDF still runs
         """
+        assert is_tagged_pdf(tagged_no_text_pdf_file) is True
         tesseract_parser.settings.mode = ModeChoices.AUTO
-        mocker.patch("paperless.parsers.tesseract.is_tagged_pdf", return_value=True)
-        mocker.patch.object(tesseract_parser, "extract_text", return_value=None)
         mock_ocr = mocker.patch("ocrmypdf.ocr")
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-images.pdf",
+            tagged_no_text_pdf_file,
             "application/pdf",
             produce_archive=False,
         )

src/paperless/tests/test_parser_utils.py

@@ -4,10 +4,18 @@ from __future__ import annotations
 
 import codecs
 from pathlib import Path
+from typing import TYPE_CHECKING
+
+import pytest
 
 from paperless.parsers.utils import is_tagged_pdf
+from paperless.parsers.utils import pdf_born_digital_text
+from paperless.parsers.utils import post_process_text
 from paperless.parsers.utils import read_file_handle_unicode_errors
 
+if TYPE_CHECKING:
+    from pytest_mock import MockerFixture
+
 SAMPLES = Path(__file__).parent / "samples" / "tesseract"
 
 
@@ -60,3 +68,105 @@ class TestIsTaggedPdf:
         bad = tmp_path / "bad.pdf"
         bad.write_bytes(b"not a pdf")
         assert is_tagged_pdf(bad) is False
+
+
+class TestPostProcessText:
+    @pytest.mark.parametrize(
+        ("source", "expected"),
+        [
+            pytest.param(
+                "simple     string",
+                "simple string",
+                id="collapse-spaces",
+            ),
+            pytest.param(
+                "simple    newline\n   testing string",
+                "simple newline\ntesting string",
+                id="preserve-newline",
+            ),
+            pytest.param(
+                "utf-8   строка с пробелами в конце  ",  # noqa: RUF001
+                "utf-8 строка с пробелами в конце",  # noqa: RUF001
+                id="utf8-trailing-spaces",
+            ),
+            pytest.param(None, None, id="none-input"),
+            pytest.param("", None, id="empty-string"),
+            pytest.param("   \n\x0c  \n ", None, id="whitespace-and-formfeed-only"),
+        ],
+    )
+    def test_post_process_text(
+        self,
+        source: str | None,
+        expected: str | None,
+    ) -> None:
+        assert post_process_text(source) == expected
+
+
+class TestPdfBornDigitalText:
+    """Regression coverage for GH #13387.
+
+    should_produce_archive() and RasterisedDocumentParser.parse() must agree
+    on whether a PDF has real text, so both go through this one function.
+    """
+
+    @pytest.mark.parametrize(
+        ("extracted", "tagged", "expected_text", "expected_born_digital"),
+        [
+            pytest.param("tiny", True, "tiny", True, id="tagged-with-real-text"),
+            pytest.param("tiny", False, "tiny", False, id="untagged-below-min-length"),
+            pytest.param(
+                "x" * 51,
+                False,
+                "x" * 51,
+                True,
+                id="untagged-above-min-length",
+            ),
+            pytest.param(None, True, None, False, id="tagged-but-no-text"),
+        ],
+    )
+    def test_born_digital_decision(
+        self,
+        mocker: MockerFixture,
+        tmp_path: Path,
+        extracted: str | None,
+        tagged: bool,  # noqa: FBT001
+        expected_text: str | None,
+        expected_born_digital: bool,  # noqa: FBT001
+    ) -> None:
+        """
+        GIVEN:
+            - A PDF whose pdftotext output and /MarkInfo tag status vary
+        WHEN:
+            - pdf_born_digital_text() is called
+        THEN:
+            - The normalized text and born-digital verdict match; the tag
+              alone never counts as "has text"
+        """
+        mocker.patch(
+            "paperless.parsers.utils.extract_pdf_text",
+            return_value=extracted,
+        )
+        mocker.patch("paperless.parsers.utils.is_tagged_pdf", return_value=tagged)
+        text, born_digital = pdf_born_digital_text(tmp_path / "doc.pdf")
+        assert text == expected_text
+        assert born_digital is expected_born_digital
+
+    def test_tagged_but_textless_pdf_is_not_born_digital(
+        self,
+        tagged_no_text_pdf_file: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - A real PDF that is tagged (/MarkInfo /Marked true) but whose
+              only "text" is layout padding (a stray form-feed byte)
+        WHEN:
+            - pdf_born_digital_text() is called with no mocking
+        THEN:
+            - The normalized text is None and the PDF is not treated as
+              born-digital. The raw, unnormalized pdftotext output is
+              non-empty for this file, which is exactly what caused the
+              archive decision to disagree with the OCR decision in #13387.
+        """
+        text, born_digital = pdf_born_digital_text(tagged_no_text_pdf_file)
+        assert text is None
+        assert born_digital is False