Update api-dashboard3.har

.github/dependabot.yml

@@ -157,9 +157,6 @@ updates:
       postgres:
         patterns:
           - "docker.io/library/postgres*"
-      greenmail:
-        patterns:
-          - "docker.io/greenmail*"
   - package-ecosystem: "pre-commit" # See documentation for possible values
     directory: "/" # Location of package manifests
     schedule:

docker/compose/docker-compose.ci-test.yml

@@ -18,13 +18,13 @@ services:
       - "--log-level=warn"
       - "--log-format=text"
   tika:
-    image: docker.io/apache/tika:3.2.3.0
+    image: docker.io/apache/tika:latest
     hostname: tika
     container_name: tika
     network_mode: host
     restart: unless-stopped
   greenmail:
-    image: docker.io/greenmail/standalone:2.1.8
+    image: greenmail/standalone:2.1.8
     hostname: greenmail
     container_name: greenmail
     environment:

pyproject.toml

@@ -60,7 +60,7 @@ dependencies = [
   "llama-index-llms-openai>=0.6.13",
   "llama-index-vector-stores-faiss>=0.5.2",
   "nltk~=3.9.1",
-  "ocrmypdf~=17.3.0",
+  "ocrmypdf~=16.13.0",
   "openai>=1.76",
   "pathvalidate~=3.3.1",
   "pdf2image~=1.17.0",

src-ui/e2e/dashboard/requests/api-dashboard1.har

@@ -468,7 +468,7 @@
         "time": 0.951,
         "request": {
           "method": "GET",
-          "url": "http://localhost:8000/api/documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__in=9",
+          "url": "http://localhost:8000/api/documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__in=9",
           "httpVersion": "HTTP/1.1",
           "cookies": [],
           "headers": [

src-ui/e2e/dashboard/requests/api-dashboard3.har

@@ -534,7 +534,7 @@
         "time": 0.653,
         "request": {
           "method": "GET",
-          "url": "http://localhost:8000/api/documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=9",
+          "url": "http://localhost:8000/api/documents/?page=1&page_size=10&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=9",
           "httpVersion": "HTTP/1.1",
           "cookies": [],
           "headers": [

src-ui/e2e/document-detail/requests/api-document-detail2.har

@@ -883,7 +883,7 @@
         "time": 0.93,
         "request": {
           "method": "GET",
-          "url": "http://localhost:8000/api/documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=4",
+          "url": "http://localhost:8000/api/documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=4",
           "httpVersion": "HTTP/1.1",
           "cookies": [],
           "headers": [
@@ -961,7 +961,7 @@
         "time": -1,
         "request": {
           "method": "GET",
-          "url": "http://localhost:8000/api/documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=4",
+          "url": "http://localhost:8000/api/documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=4",
           "httpVersion": "HTTP/1.1",
           "cookies": [],
           "headers": [

src-ui/e2e/document-list/document-list.spec.ts

@@ -16,7 +16,7 @@ test('basic filtering', async ({ page }) => {
   await expect(page).toHaveURL(/tags__id__all=9/)
   await expect(page.locator('pngx-document-list')).toHaveText(/8 documents/)
   await page.getByRole('button', { name: 'Document type' }).click()
-  await page.getByRole('menuitem', { name: 'Invoice Test 3' }).click()
+  await page.getByRole('menuitem', { name: /^Invoice Test/ }).click()
   await expect(page).toHaveURL(/document_type__id__in=1/)
   await expect(page.locator('pngx-document-list')).toHaveText(/3 documents/)
   await page.getByRole('button', { name: 'Reset filters' }).first().click()

src-ui/src/app/components/common/filterable-dropdown/filterable-dropdown.component.ts

@@ -20,9 +20,9 @@ import { Subject, filter, takeUntil } from 'rxjs'
 import { NEGATIVE_NULL_FILTER_VALUE } from 'src/app/data/filter-rule-type'
 import { MatchingModel } from 'src/app/data/matching-model'
 import { ObjectWithPermissions } from 'src/app/data/object-with-permissions'
+import { SelectionDataItem } from 'src/app/data/results'
 import { FilterPipe } from 'src/app/pipes/filter.pipe'
 import { HotKeyService } from 'src/app/services/hot-key.service'
-import { SelectionDataItem } from 'src/app/services/rest/document.service'
 import { pngxPopperOptions } from 'src/app/utils/popper-options'
 import { LoadingComponentWithPermissions } from '../../loading-component/loading.component'
 import { ClearableBadgeComponent } from '../clearable-badge/clearable-badge.component'

src-ui/src/app/components/document-list/bulk-editor/bulk-editor.component.spec.ts

@@ -300,7 +300,7 @@ describe('BulkEditorComponent', () => {
       parameters: { add_tags: [101], remove_tags: [] },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -332,7 +332,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -423,7 +423,7 @@ describe('BulkEditorComponent', () => {
       parameters: { correspondent: 101 },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -455,7 +455,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -521,7 +521,7 @@ describe('BulkEditorComponent', () => {
       parameters: { document_type: 101 },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -553,7 +553,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -619,7 +619,7 @@ describe('BulkEditorComponent', () => {
       parameters: { storage_path: 101 },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -651,7 +651,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -717,7 +717,7 @@ describe('BulkEditorComponent', () => {
       parameters: { add_custom_fields: [101], remove_custom_fields: [102] },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -749,7 +749,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -858,7 +858,7 @@ describe('BulkEditorComponent', () => {
       documents: [3, 4],
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -951,7 +951,7 @@ describe('BulkEditorComponent', () => {
       documents: [3, 4],
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -986,7 +986,7 @@ describe('BulkEditorComponent', () => {
       source_mode: 'latest_version',
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1027,7 +1027,7 @@ describe('BulkEditorComponent', () => {
       metadata_document_id: 3,
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1046,7 +1046,7 @@ describe('BulkEditorComponent', () => {
       delete_originals: true,
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1067,7 +1067,7 @@ describe('BulkEditorComponent', () => {
       archive_fallback: true,
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1153,7 +1153,7 @@ describe('BulkEditorComponent', () => {
       },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1460,7 +1460,7 @@ describe('BulkEditorComponent', () => {
     expect(toastServiceShowInfoSpy).toHaveBeenCalled()
     expect(listReloadSpy).toHaveBeenCalled()
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`

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

@@ -16,6 +16,7 @@ import { first, map, Observable, Subject, switchMap, takeUntil } from 'rxjs'
 import { ConfirmDialogComponent } from 'src/app/components/common/confirm-dialog/confirm-dialog.component'
 import { CustomField } from 'src/app/data/custom-field'
 import { MatchingModel } from 'src/app/data/matching-model'
+import { SelectionDataItem } from 'src/app/data/results'
 import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
 import { IfPermissionsDirective } from 'src/app/directives/if-permissions.directive'
 import { DocumentListViewService } from 'src/app/services/document-list-view.service'
@@ -32,7 +33,6 @@ import {
   DocumentBulkEditMethod,
   DocumentService,
   MergeDocumentsRequest,
-  SelectionDataItem,
 } from 'src/app/services/rest/document.service'
 import { SavedViewService } from 'src/app/services/rest/saved-view.service'
 import { ShareLinkBundleService } from 'src/app/services/rest/share-link-bundle.service'

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

@@ -76,6 +76,7 @@ import {
   FILTER_TITLE_CONTENT,
   NEGATIVE_NULL_FILTER_VALUE,
 } from 'src/app/data/filter-rule-type'
+import { SelectionData, SelectionDataItem } from 'src/app/data/results'
 import {
   PermissionAction,
   PermissionType,
@@ -84,11 +85,7 @@ import {
 import { CorrespondentService } from 'src/app/services/rest/correspondent.service'
 import { CustomFieldsService } from 'src/app/services/rest/custom-fields.service'
 import { DocumentTypeService } from 'src/app/services/rest/document-type.service'
-import {
+import { DocumentService } from 'src/app/services/rest/document.service'
-  DocumentService,
-  SelectionData,
-  SelectionDataItem,
-} from 'src/app/services/rest/document.service'
 import { SearchService } from 'src/app/services/rest/search.service'
 import { StoragePathService } from 'src/app/services/rest/storage-path.service'
 import { TagService } from 'src/app/services/rest/tag.service'

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

@@ -1,3 +1,5 @@
+import { Document } from './document'
+
 export interface Results<T> {
   count: number
 
@@ -5,3 +7,20 @@ export interface Results<T> {
 
   all: number[]
 }
+
+export interface SelectionDataItem {
+  id: number
+  document_count: number
+}
+
+export interface SelectionData {
+  selected_storage_paths: SelectionDataItem[]
+  selected_correspondents: SelectionDataItem[]
+  selected_tags: SelectionDataItem[]
+  selected_document_types: SelectionDataItem[]
+  selected_custom_fields: SelectionDataItem[]
+}
+
+export interface DocumentResults extends Results<Document> {
+  selection_data?: SelectionData
+}

src-ui/src/app/services/document-list-view.service.spec.ts

@@ -126,13 +126,10 @@ describe('DocumentListViewService', () => {
     expect(documentListViewService.currentPage).toEqual(1)
     documentListViewService.reload()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(full_results)
-    httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/selection_data/`
-    )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.isReloading).toBeFalsy()
     expect(documentListViewService.activeSavedViewId).toBeNull()
@@ -144,12 +141,12 @@ describe('DocumentListViewService', () => {
   it('should handle error on page request out of range', () => {
     documentListViewService.currentPage = 50
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=50&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=50&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush([], { status: 404, statusText: 'Unexpected error' })
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.currentPage).toEqual(1)
@@ -166,7 +163,7 @@ describe('DocumentListViewService', () => {
     ]
     documentListViewService.setFilterRules(filterRulesAny)
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__in=${tags__id__in}`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__in=${tags__id__in}`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(
@@ -174,13 +171,13 @@ describe('DocumentListViewService', () => {
       { status: 404, statusText: 'Unexpected error' }
     )
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     // reset the list
     documentListViewService.setFilterRules([])
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
   })
 
@@ -188,7 +185,7 @@ describe('DocumentListViewService', () => {
     documentListViewService.currentPage = 1
     documentListViewService.sortField = 'custom_field_999'
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-custom_field_999&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-custom_field_999&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(
@@ -197,7 +194,7 @@ describe('DocumentListViewService', () => {
     )
     // resets itself
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
   })
 
@@ -212,7 +209,7 @@ describe('DocumentListViewService', () => {
     ]
     documentListViewService.setFilterRules(filterRulesAny)
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__in=${tags__id__in}`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__in=${tags__id__in}`
     )
     expect(req.request.method).toEqual('GET')
     req.flush('Generic error', { status: 404, statusText: 'Unexpected error' })
@@ -220,7 +217,7 @@ describe('DocumentListViewService', () => {
     // reset the list
     documentListViewService.setFilterRules([])
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
   })
 
@@ -229,7 +226,7 @@ describe('DocumentListViewService', () => {
     expect(documentListViewService.sortReverse).toBeTruthy()
     documentListViewService.setSort('added', false)
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=added&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=added&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.sortField).toEqual('added')
@@ -237,12 +234,12 @@ describe('DocumentListViewService', () => {
 
     documentListViewService.sortField = 'created'
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=created&truncate_content=true&include_selection_data=true`
     )
     expect(documentListViewService.sortField).toEqual('created')
     documentListViewService.sortReverse = true
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.sortReverse).toBeTruthy()
@@ -262,7 +259,7 @@ describe('DocumentListViewService', () => {
     const req = httpTestingController.expectOne(
       `${environment.apiBaseUrl}documents/?page=${page}&page_size=${
         documentListViewService.pageSize
-      }&ordering=${reverse ? '-' : ''}${sort}&truncate_content=true`
+      }&ordering=${reverse ? '-' : ''}${sort}&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.currentPage).toEqual(page)
@@ -279,7 +276,7 @@ describe('DocumentListViewService', () => {
     }
     documentListViewService.loadFromQueryParams(convertToParamMap(params))
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-added&truncate_content=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-added&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.filterRules).toEqual([
@@ -289,15 +286,12 @@ describe('DocumentListViewService', () => {
       },
     ])
     req.flush(full_results)
-    httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/selection_data/`
-    )
   })
 
   it('should use filter rules to update query params', () => {
     documentListViewService.setFilterRules(filterRules)
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-created&truncate_content=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
     )
     expect(req.request.method).toEqual('GET')
   })
@@ -306,34 +300,26 @@ describe('DocumentListViewService', () => {
     documentListViewService.currentPage = 2
     let req = httpTestingController.expectOne((request) =>
       request.urlWithParams.startsWith(
-        `${environment.apiBaseUrl}documents/?page=2&page_size=50&ordering=-created&truncate_content=true`
+        `${environment.apiBaseUrl}documents/?page=2&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
       )
     )
     expect(req.request.method).toEqual('GET')
     req.flush(full_results)
-    req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/selection_data/`
-    )
-    req.flush([])
 
     documentListViewService.setFilterRules(filterRules, true)
 
     const filteredReqs = httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
     )
     expect(filteredReqs).toHaveLength(1)
     filteredReqs[0].flush(full_results)
-    req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/selection_data/`
-    )
-    req.flush([])
     expect(documentListViewService.currentPage).toEqual(1)
   })
 
   it('should support quick filter', () => {
     documentListViewService.quickFilter(filterRules)
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-created&truncate_content=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
     )
     expect(req.request.method).toEqual('GET')
   })
@@ -356,21 +342,21 @@ describe('DocumentListViewService', () => {
       convertToParamMap(params)
     )
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=${page}&page_size=${documentListViewService.pageSize}&ordering=-added&truncate_content=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=${page}&page_size=${documentListViewService.pageSize}&ordering=-added&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
     )
     expect(req.request.method).toEqual('GET')
     // reset the list
     documentListViewService.currentPage = 1
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-added&truncate_content=true&tags__id__all=9`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-added&truncate_content=true&include_selection_data=true&tags__id__all=9`
     )
     documentListViewService.setFilterRules([])
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-added&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-added&truncate_content=true&include_selection_data=true`
     )
     documentListViewService.sortField = 'created'
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     documentListViewService.activateSavedView(null)
   })
@@ -378,21 +364,18 @@ describe('DocumentListViewService', () => {
   it('should support navigating next / previous', () => {
     documentListViewService.setFilterRules([])
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(documentListViewService.currentPage).toEqual(1)
     documentListViewService.pageSize = 3
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush({
       count: 3,
       results: documents.slice(0, 3),
     })
-    httpTestingController
-      .expectOne(`${environment.apiBaseUrl}documents/selection_data/`)
-      .flush([])
     expect(documentListViewService.hasNext(documents[0].id)).toBeTruthy()
     expect(documentListViewService.hasPrevious(documents[0].id)).toBeFalsy()
     documentListViewService.getNext(documents[0].id).subscribe((docId) => {
@@ -439,7 +422,7 @@ describe('DocumentListViewService', () => {
     expect(documentListViewService.currentPage).toEqual(1)
     documentListViewService.pageSize = 3
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     jest
       .spyOn(documentListViewService, 'getLastPage')
@@ -454,7 +437,7 @@ describe('DocumentListViewService', () => {
     expect(reloadSpy).toHaveBeenCalled()
     expect(documentListViewService.currentPage).toEqual(2)
     const reqs = httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=2&page_size=3&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=2&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(reqs.length).toBeGreaterThan(0)
   })
@@ -489,11 +472,11 @@ describe('DocumentListViewService', () => {
       .mockReturnValue(documents)
     documentListViewService.currentPage = 2
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=2&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=2&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     documentListViewService.pageSize = 3
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=2&page_size=3&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=2&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     const reloadSpy = jest.spyOn(documentListViewService, 'reload')
     documentListViewService.getPrevious(1).subscribe({
@@ -503,7 +486,7 @@ describe('DocumentListViewService', () => {
     expect(reloadSpy).toHaveBeenCalled()
     expect(documentListViewService.currentPage).toEqual(1)
     const reqs = httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(reqs.length).toBeGreaterThan(0)
   })
@@ -516,13 +499,10 @@ describe('DocumentListViewService', () => {
   it('should support select a document', () => {
     documentListViewService.reload()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(full_results)
-    httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/selection_data/`
-    )
     documentListViewService.toggleSelected(documents[0])
     expect(documentListViewService.isSelected(documents[0])).toBeTruthy()
     documentListViewService.toggleSelected(documents[0])
@@ -544,16 +524,13 @@ describe('DocumentListViewService', () => {
   it('should support select page', () => {
     documentListViewService.pageSize = 3
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush({
       count: 3,
       results: documents.slice(0, 3),
     })
-    httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/selection_data/`
-    )
     documentListViewService.selectPage()
     expect(documentListViewService.selected.size).toEqual(3)
     expect(documentListViewService.isSelected(documents[5])).toBeFalsy()
@@ -562,13 +539,10 @@ describe('DocumentListViewService', () => {
   it('should support select range', () => {
     documentListViewService.reload()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(full_results)
-    httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/selection_data/`
-    )
     documentListViewService.toggleSelected(documents[0])
     expect(documentListViewService.isSelected(documents[0])).toBeTruthy()
     documentListViewService.selectRangeTo(documents[2])
@@ -588,7 +562,7 @@ describe('DocumentListViewService', () => {
 
     documentListViewService.setFilterRules(filterRules)
     httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=9`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=9`
     )
     const reqs = httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id&tags__id__all=9`
@@ -604,7 +578,7 @@ describe('DocumentListViewService', () => {
     const cancelSpy = jest.spyOn(documentListViewService, 'cancelPending')
     documentListViewService.reload()
     httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=9`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=9`
     )
     expect(cancelSpy).toHaveBeenCalled()
   })
@@ -623,7 +597,7 @@ describe('DocumentListViewService', () => {
     documentListViewService.setFilterRules([])
     expect(documentListViewService.sortField).toEqual('created')
     httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
   })
 
@@ -650,11 +624,11 @@ describe('DocumentListViewService', () => {
     expect(localStorageSpy).toHaveBeenCalled()
     // reload triggered
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     documentListViewService.displayFields = null
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(documentListViewService.displayFields).toEqual(
       DEFAULT_DISPLAY_FIELDS.filter((f) => f.id !== DisplayField.ADDED).map(
@@ -694,7 +668,7 @@ describe('DocumentListViewService', () => {
   it('should generate quick filter URL preserving default state', () => {
     documentListViewService.reload()
     httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     const urlTree = documentListViewService.getQuickFilterUrl(filterRules)
     expect(urlTree).toBeDefined()

src-ui/src/app/services/document-list-view.service.ts

@@ -1,6 +1,6 @@
 import { Injectable, inject } from '@angular/core'
 import { ParamMap, Router, UrlTree } from '@angular/router'
-import { Observable, Subject, first, takeUntil } from 'rxjs'
+import { Observable, Subject, takeUntil } from 'rxjs'
 import {
   DEFAULT_DISPLAY_FIELDS,
   DisplayField,
@@ -8,6 +8,7 @@ import {
   Document,
 } from '../data/document'
 import { FilterRule } from '../data/filter-rule'
+import { DocumentResults, SelectionData } from '../data/results'
 import { SavedView } from '../data/saved-view'
 import { DOCUMENT_LIST_SERVICE } from '../data/storage-keys'
 import { SETTINGS_KEYS } from '../data/ui-settings'
@@ -17,7 +18,7 @@ import {
   isFullTextFilterRule,
 } from '../utils/filter-rules'
 import { paramsFromViewState, paramsToViewState } from '../utils/query-params'
-import { DocumentService, SelectionData } from './rest/document.service'
+import { DocumentService } from './rest/document.service'
 import { SettingsService } from './settings.service'
 
 const LIST_DEFAULT_DISPLAY_FIELDS: DisplayField[] = DEFAULT_DISPLAY_FIELDS.map(
@@ -260,27 +261,17 @@ export class DocumentListViewService {
         activeListViewState.sortField,
         activeListViewState.sortReverse,
         activeListViewState.filterRules,
-        { truncate_content: true }
+        { truncate_content: true, include_selection_data: true }
       )
       .pipe(takeUntil(this.unsubscribeNotifier))
       .subscribe({
         next: (result) => {
+          const resultWithSelectionData = result as DocumentResults
           this.initialized = true
           this.isReloading = false
           activeListViewState.collectionSize = result.count
           activeListViewState.documents = result.results
-
+          this.selectionData = resultWithSelectionData.selection_data ?? null
-          this.documentService
-            .getSelectionData(result.all)
-            .pipe(first())
-            .subscribe({
-              next: (selectionData) => {
-                this.selectionData = selectionData
-              },
-              error: () => {
-                this.selectionData = null
-              },
-            })
 
           if (updateQueryParams && !this._activeSavedViewId) {
             let base = ['/documents']

src-ui/src/app/services/rest/document.service.ts

@@ -12,7 +12,7 @@ import {
 import { DocumentMetadata } from 'src/app/data/document-metadata'
 import { DocumentSuggestions } from 'src/app/data/document-suggestions'
 import { FilterRule } from 'src/app/data/filter-rule'
-import { Results } from 'src/app/data/results'
+import { Results, SelectionData } from 'src/app/data/results'
 import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
 import { queryParamsFromFilterRules } from '../../utils/query-params'
 import {
@@ -24,19 +24,6 @@ import { SettingsService } from '../settings.service'
 import { AbstractPaperlessService } from './abstract-paperless-service'
 import { CustomFieldsService } from './custom-fields.service'
 
-export interface SelectionDataItem {
-  id: number
-  document_count: number
-}
-
-export interface SelectionData {
-  selected_storage_paths: SelectionDataItem[]
-  selected_correspondents: SelectionDataItem[]
-  selected_tags: SelectionDataItem[]
-  selected_document_types: SelectionDataItem[]
-  selected_custom_fields: SelectionDataItem[]
-}
-
 export enum BulkEditSourceMode {
   LATEST_VERSION = 'latest_version',
   EXPLICIT_SELECTION = 'explicit_selection',

src/documents/consumer.py

@@ -52,7 +52,6 @@ from documents.utils import copy_basic_file_stats
 from documents.utils import copy_file_with_basic_stats
 from documents.utils import run_subprocess
 from paperless.parsers.text import TextDocumentParser
-from paperless.parsers.tika import TikaDocumentParser
 from paperless_mail.parsers import MailDocumentParser
 
 LOGGING_NAME: Final[str] = "paperless.consumer"
@@ -68,7 +67,7 @@ def _parser_cleanup(parser: DocumentParser) -> None:
 
     TODO(stumpylog): Remove me in the future
     """
-    if isinstance(parser, (TextDocumentParser, TikaDocumentParser)):
+    if isinstance(parser, TextDocumentParser):
         parser.__exit__(None, None, None)
     else:
         parser.cleanup()
@@ -449,12 +448,6 @@ class ConsumerPlugin(
             progress_callback=progress_callback,
         )
 
-        # New-style parsers use __enter__/__exit__ for resource management.
-        # _parser_cleanup (below) handles __exit__; call __enter__ here.
-        # TODO(stumpylog): Remove me in the future
-        if isinstance(document_parser, (TextDocumentParser, TikaDocumentParser)):
-            document_parser.__enter__()
-
         self.log.debug(f"Parser: {type(document_parser).__name__}")
 
         # Parse the document. This may take some time.
@@ -483,7 +476,7 @@ class ConsumerPlugin(
                     self.filename,
                     self.input_doc.mailrule_id,
                 )
-            elif isinstance(document_parser, (TextDocumentParser, TikaDocumentParser)):
+            elif isinstance(document_parser, TextDocumentParser):
                 # TODO(stumpylog): Remove me in the future
                 document_parser.parse(self.working_copy, mime_type)
             else:
@@ -496,7 +489,7 @@ class ConsumerPlugin(
                 ProgressStatusOptions.WORKING,
                 ConsumerStatusShortMessage.GENERATING_THUMBNAIL,
             )
-            if isinstance(document_parser, (TextDocumentParser, TikaDocumentParser)):
+            if isinstance(document_parser, TextDocumentParser):
                 # TODO(stumpylog): Remove me in the future
                 thumbnail = document_parser.get_thumbnail(self.working_copy, mime_type)
             else:

src/documents/tests/test_api_documents.py

@@ -1144,6 +1144,56 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
         self.assertEqual(len(response.data["all"]), 50)
         self.assertCountEqual(response.data["all"], [d.id for d in docs])
 
+    def test_list_with_include_selection_data(self) -> None:
+        correspondent = Correspondent.objects.create(name="c1")
+        doc_type = DocumentType.objects.create(name="dt1")
+        storage_path = StoragePath.objects.create(name="sp1")
+        tag = Tag.objects.create(name="tag")
+
+        matching_doc = Document.objects.create(
+            checksum="A",
+            correspondent=correspondent,
+            document_type=doc_type,
+            storage_path=storage_path,
+        )
+        matching_doc.tags.add(tag)
+
+        non_matching_doc = Document.objects.create(checksum="B")
+        non_matching_doc.tags.add(Tag.objects.create(name="other"))
+
+        response = self.client.get(
+            f"/api/documents/?tags__id__in={tag.id}&include_selection_data=true",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertIn("selection_data", response.data)
+
+        selected_correspondent = next(
+            item
+            for item in response.data["selection_data"]["selected_correspondents"]
+            if item["id"] == correspondent.id
+        )
+        selected_tag = next(
+            item
+            for item in response.data["selection_data"]["selected_tags"]
+            if item["id"] == tag.id
+        )
+        selected_type = next(
+            item
+            for item in response.data["selection_data"]["selected_document_types"]
+            if item["id"] == doc_type.id
+        )
+        selected_storage_path = next(
+            item
+            for item in response.data["selection_data"]["selected_storage_paths"]
+            if item["id"] == storage_path.id
+        )
+
+        self.assertEqual(selected_correspondent["document_count"], 1)
+        self.assertEqual(selected_tag["document_count"], 1)
+        self.assertEqual(selected_type["document_count"], 1)
+        self.assertEqual(selected_storage_path["document_count"], 1)
+
     def test_statistics(self) -> None:
         doc1 = Document.objects.create(
             title="none1",

src/documents/tests/test_api_search.py

@@ -89,6 +89,46 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         self.assertEqual(len(results), 0)
         self.assertCountEqual(response.data["all"], [])
 
+    def test_search_with_include_selection_data(self) -> None:
+        correspondent = Correspondent.objects.create(name="c1")
+        doc_type = DocumentType.objects.create(name="dt1")
+        storage_path = StoragePath.objects.create(name="sp1")
+        tag = Tag.objects.create(name="tag")
+
+        matching_doc = Document.objects.create(
+            title="bank statement",
+            content="bank content",
+            checksum="A",
+            correspondent=correspondent,
+            document_type=doc_type,
+            storage_path=storage_path,
+        )
+        matching_doc.tags.add(tag)
+
+        with AsyncWriter(index.open_index()) as writer:
+            index.update_document(writer, matching_doc)
+
+        response = self.client.get(
+            "/api/documents/?query=bank&include_selection_data=true",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertIn("selection_data", response.data)
+
+        selected_correspondent = next(
+            item
+            for item in response.data["selection_data"]["selected_correspondents"]
+            if item["id"] == correspondent.id
+        )
+        selected_tag = next(
+            item
+            for item in response.data["selection_data"]["selected_tags"]
+            if item["id"] == tag.id
+        )
+
+        self.assertEqual(selected_correspondent["document_count"], 1)
+        self.assertEqual(selected_tag["document_count"], 1)
+
     def test_search_custom_field_ordering(self) -> None:
         custom_field = CustomField.objects.create(
             name="Sortable field",

src/documents/tests/test_parsers.py

@@ -10,8 +10,8 @@ from documents.parsers import get_parser_class_for_mime_type
 from documents.parsers import get_supported_file_extensions
 from documents.parsers import is_file_ext_supported
 from paperless.parsers.text import TextDocumentParser
-from paperless.parsers.tika import TikaDocumentParser
 from paperless_tesseract.parsers import RasterisedDocumentParser
+from paperless_tika.parsers import TikaDocumentParser
 
 
 class TestParserDiscovery(TestCase):

src/documents/views.py

@@ -7,7 +7,6 @@ import tempfile
 import zipfile
 from collections import defaultdict
 from collections import deque
-from contextlib import nullcontext
 from datetime import datetime
 from pathlib import Path
 from time import mktime
@@ -226,7 +225,6 @@ from paperless.celery import app as celery_app
 from paperless.config import AIConfig
 from paperless.config import GeneralConfig
 from paperless.models import ApplicationConfiguration
-from paperless.parsers import ParserProtocol
 from paperless.serialisers import GroupSerializer
 from paperless.serialisers import UserSerializer
 from paperless.views import StandardPagination
@@ -837,6 +835,61 @@ class DocumentViewSet(
         "custom_field_",
     )
 
+    def _get_selection_data_for_queryset(self, queryset):
+        correspondents = Correspondent.objects.annotate(
+            document_count=Count(
+                "documents",
+                filter=Q(documents__in=queryset),
+                distinct=True,
+            ),
+        )
+        tags = Tag.objects.annotate(
+            document_count=Count(
+                "documents",
+                filter=Q(documents__in=queryset),
+                distinct=True,
+            ),
+        )
+        document_types = DocumentType.objects.annotate(
+            document_count=Count(
+                "documents",
+                filter=Q(documents__in=queryset),
+                distinct=True,
+            ),
+        )
+        storage_paths = StoragePath.objects.annotate(
+            document_count=Count(
+                "documents",
+                filter=Q(documents__in=queryset),
+                distinct=True,
+            ),
+        )
+        custom_fields = CustomField.objects.annotate(
+            document_count=Count(
+                "fields__document",
+                filter=Q(fields__document__in=queryset),
+                distinct=True,
+            ),
+        )
+
+        return {
+            "selected_correspondents": [
+                {"id": t.id, "document_count": t.document_count} for t in correspondents
+            ],
+            "selected_tags": [
+                {"id": t.id, "document_count": t.document_count} for t in tags
+            ],
+            "selected_document_types": [
+                {"id": t.id, "document_count": t.document_count} for t in document_types
+            ],
+            "selected_storage_paths": [
+                {"id": t.id, "document_count": t.document_count} for t in storage_paths
+            ],
+            "selected_custom_fields": [
+                {"id": t.id, "document_count": t.document_count} for t in custom_fields
+            ],
+        }
+
     def get_queryset(self):
         latest_version_content = Subquery(
             Document.objects.filter(root_document=OuterRef("pk"))
@@ -984,6 +1037,25 @@ class DocumentViewSet(
 
         return response
 
+    def list(self, request, *args, **kwargs):
+        if not get_boolean(
+            str(request.query_params.get("include_selection_data", "false")),
+        ):
+            return super().list(request, *args, **kwargs)
+
+        queryset = self.filter_queryset(self.get_queryset())
+        selection_data = self._get_selection_data_for_queryset(queryset)
+
+        page = self.paginate_queryset(queryset)
+        if page is not None:
+            serializer = self.get_serializer(page, many=True)
+            response = self.get_paginated_response(serializer.data)
+            response.data["selection_data"] = selection_data
+            return response
+
+        serializer = self.get_serializer(queryset, many=True)
+        return Response({"results": serializer.data, "selection_data": selection_data})
+
     def destroy(self, request, *args, **kwargs):
         from documents import index
 
@@ -1086,11 +1158,9 @@ class DocumentViewSet(
         parser_class = get_parser_class_for_mime_type(mime_type)
         if parser_class:
             parser = parser_class(progress_callback=None, logging_group=None)
-            cm = parser if isinstance(parser, ParserProtocol) else nullcontext(parser)
 
             try:
-                with cm:
+                return parser.extract_metadata(file, mime_type)
-                    return parser.extract_metadata(file, mime_type)
             except Exception:  # pragma: no cover
                 logger.exception(f"Issue getting metadata for {file}")
                 # TODO: cover GPG errors, remove later.
@@ -2006,6 +2076,21 @@ class UnifiedSearchViewSet(DocumentViewSet):
                         else None
                     )
 
+                    if get_boolean(
+                        str(
+                            request.query_params.get(
+                                "include_selection_data",
+                                "false",
+                            ),
+                        ),
+                    ):
+                        result_ids = response.data.get("all", [])
+                        response.data["selection_data"] = (
+                            self._get_selection_data_for_queryset(
+                                Document.objects.filter(pk__in=result_ids),
+                            )
+                        )
+
                     return response
             except NotFound:
                 raise

src/paperless/parsers/registry.py

@@ -194,10 +194,8 @@ class ParserRegistry:
         at runtime regardless of registration order.
         """
         from paperless.parsers.text import TextDocumentParser
-        from paperless.parsers.tika import TikaDocumentParser
 
         self.register_builtin(TextDocumentParser)
-        self.register_builtin(TikaDocumentParser)
 
     # ------------------------------------------------------------------
     # Discovery

src/paperless/parsers/tika.py

@@ -1,440 +0,0 @@
-"""
-Built-in Tika document parser.
-
-Handles Office documents (DOCX, ODT, XLS, XLSX, PPT, PPTX, RTF, etc.) by
-sending them to an Apache Tika server for text extraction and a Gotenberg
-server for PDF conversion.  Because the source formats cannot be rendered by
-a browser natively, the parser always produces a PDF rendition for display.
-"""
-
-from __future__ import annotations
-
-import logging
-import shutil
-import tempfile
-from contextlib import ExitStack
-from pathlib import Path
-from typing import TYPE_CHECKING
-from typing import Self
-
-import httpx
-from django.conf import settings
-from django.utils import timezone
-from gotenberg_client import GotenbergClient
-from gotenberg_client.options import PdfAFormat
-from tika_client import TikaClient
-
-from documents.parsers import ParseError
-from documents.parsers import make_thumbnail_from_pdf
-from paperless.config import OutputTypeConfig
-from paperless.models import OutputTypeChoices
-from paperless.version import __full_version_str__
-
-if TYPE_CHECKING:
-    import datetime
-    from types import TracebackType
-
-    from paperless.parsers import MetadataEntry
-
-logger = logging.getLogger("paperless.parsing.tika")
-
-_SUPPORTED_MIME_TYPES: dict[str, str] = {
-    "application/msword": ".doc",
-    "application/vnd.openxmlformats-officedocument.wordprocessingml.document": ".docx",
-    "application/vnd.ms-excel": ".xls",
-    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": ".xlsx",
-    "application/vnd.ms-powerpoint": ".ppt",
-    "application/vnd.openxmlformats-officedocument.presentationml.presentation": ".pptx",
-    "application/vnd.openxmlformats-officedocument.presentationml.slideshow": ".ppsx",
-    "application/vnd.oasis.opendocument.presentation": ".odp",
-    "application/vnd.oasis.opendocument.spreadsheet": ".ods",
-    "application/vnd.oasis.opendocument.text": ".odt",
-    "application/vnd.oasis.opendocument.graphics": ".odg",
-    "text/rtf": ".rtf",
-}
-
-
-class TikaDocumentParser:
-    """Parse Office documents via Apache Tika and Gotenberg for Paperless-ngx.
-
-    Text extraction is handled by the Tika server.  PDF conversion for display
-    is handled by Gotenberg (LibreOffice route).  Because the source formats
-    cannot be rendered by a browser natively, ``requires_pdf_rendition`` is
-    True and the PDF is always produced regardless of the ``produce_archive``
-    flag passed to ``parse``.
-
-    Both ``TikaClient`` and ``GotenbergClient`` are opened once in
-    ``__enter__`` via an ``ExitStack`` and shared across ``parse``,
-    ``extract_metadata``, and ``_convert_to_pdf`` calls, then closed via
-    ``ExitStack.close()`` in ``__exit__``.  The parser must always be used
-    as a context manager.
-
-    Class attributes
-    ----------------
-    name : str
-        Human-readable parser name.
-    version : str
-        Semantic version string, kept in sync with Paperless-ngx releases.
-    author : str
-        Maintainer name.
-    url : str
-        Issue tracker / source URL.
-    """
-
-    name: str = "Paperless-ngx Tika Parser"
-    version: str = __full_version_str__
-    author: str = "Paperless-ngx Contributors"
-    url: str = "https://github.com/paperless-ngx/paperless-ngx"
-
-    # ------------------------------------------------------------------
-    # Class methods
-    # ------------------------------------------------------------------
-
-    @classmethod
-    def supported_mime_types(cls) -> dict[str, str]:
-        """Return the MIME types this parser handles.
-
-        Returns
-        -------
-        dict[str, str]
-            Mapping of MIME type to preferred file extension.
-        """
-        return _SUPPORTED_MIME_TYPES
-
-    @classmethod
-    def score(
-        cls,
-        mime_type: str,
-        filename: str,
-        path: Path | None = None,
-    ) -> int | None:
-        """Return the priority score for handling this file.
-
-        Returns ``None`` when Tika integration is disabled so the registry
-        skips this parser entirely.
-
-        Parameters
-        ----------
-        mime_type:
-            Detected MIME type of the file.
-        filename:
-            Original filename including extension.
-        path:
-            Optional filesystem path. Not inspected by this parser.
-
-        Returns
-        -------
-        int | None
-            10 if TIKA_ENABLED and the MIME type is supported, otherwise None.
-        """
-        if not settings.TIKA_ENABLED:
-            return None
-        if mime_type in _SUPPORTED_MIME_TYPES:
-            return 10
-        return None
-
-    # ------------------------------------------------------------------
-    # Properties
-    # ------------------------------------------------------------------
-
-    @property
-    def can_produce_archive(self) -> bool:
-        """Whether this parser can produce a searchable PDF archive copy.
-
-        Returns
-        -------
-        bool
-            Always False — Tika produces a display PDF, not an OCR archive.
-        """
-        return False
-
-    @property
-    def requires_pdf_rendition(self) -> bool:
-        """Whether the parser must produce a PDF for the frontend to display.
-
-        Returns
-        -------
-        bool
-            Always True — Office formats cannot be rendered natively in a
-            browser, so a PDF conversion is always required for display.
-        """
-        return True
-
-    # ------------------------------------------------------------------
-    # Lifecycle
-    # ------------------------------------------------------------------
-
-    def __init__(self, logging_group: object = None) -> None:
-        settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
-        self._tempdir = Path(
-            tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR),
-        )
-        self._text: str | None = None
-        self._date: datetime.datetime | None = None
-        self._archive_path: Path | None = None
-        self._exit_stack = ExitStack()
-        self._tika_client: TikaClient | None = None
-        self._gotenberg_client: GotenbergClient | None = None
-
-    def __enter__(self) -> Self:
-        self._tika_client = self._exit_stack.enter_context(
-            TikaClient(
-                tika_url=settings.TIKA_ENDPOINT,
-                timeout=settings.CELERY_TASK_TIME_LIMIT,
-            ),
-        )
-        self._gotenberg_client = self._exit_stack.enter_context(
-            GotenbergClient(
-                host=settings.TIKA_GOTENBERG_ENDPOINT,
-                timeout=settings.CELERY_TASK_TIME_LIMIT,
-            ),
-        )
-        return self
-
-    def __exit__(
-        self,
-        exc_type: type[BaseException] | None,
-        exc_val: BaseException | None,
-        exc_tb: TracebackType | None,
-    ) -> None:
-        self._exit_stack.close()
-        logger.debug("Cleaning up temporary directory %s", self._tempdir)
-        shutil.rmtree(self._tempdir, ignore_errors=True)
-
-    # ------------------------------------------------------------------
-    # Core parsing interface
-    # ------------------------------------------------------------------
-
-    def parse(
-        self,
-        document_path: Path,
-        mime_type: str,
-        *,
-        produce_archive: bool = True,
-    ) -> None:
-        """Send the document to Tika for text extraction and Gotenberg for PDF.
-
-        Because ``requires_pdf_rendition`` is True the PDF conversion is
-        always performed — the ``produce_archive`` flag is intentionally
-        ignored.
-
-        Parameters
-        ----------
-        document_path:
-            Absolute path to the document file to parse.
-        mime_type:
-            Detected MIME type of the document.
-        produce_archive:
-            Accepted for protocol compatibility but ignored; the PDF rendition
-            is always produced since the source format cannot be displayed
-            natively in the browser.
-
-        Raises
-        ------
-        documents.parsers.ParseError
-            If Tika or Gotenberg returns an error.
-        """
-        if TYPE_CHECKING:
-            assert self._tika_client is not None
-
-        logger.info("Sending %s to Tika server", document_path)
-
-        try:
-            try:
-                parsed = self._tika_client.tika.as_text.from_file(
-                    document_path,
-                    mime_type,
-                )
-            except httpx.HTTPStatusError as err:
-                # Workaround https://issues.apache.org/jira/browse/TIKA-4110
-                # Tika fails with some files as multi-part form data
-                if err.response.status_code == httpx.codes.INTERNAL_SERVER_ERROR:
-                    parsed = self._tika_client.tika.as_text.from_buffer(
-                        document_path.read_bytes(),
-                        mime_type,
-                    )
-                else:  # pragma: no cover
-                    raise
-        except Exception as err:
-            raise ParseError(
-                f"Could not parse {document_path} with tika server at "
-                f"{settings.TIKA_ENDPOINT}: {err}",
-            ) from err
-
-        self._text = parsed.content
-        if self._text is not None:
-            self._text = self._text.strip()
-
-        self._date = parsed.created
-        if self._date is not None and timezone.is_naive(self._date):
-            self._date = timezone.make_aware(self._date)
-
-        # Always convert — requires_pdf_rendition=True means the browser
-        # cannot display the source format natively.
-        self._archive_path = self._convert_to_pdf(document_path)
-
-    # ------------------------------------------------------------------
-    # Result accessors
-    # ------------------------------------------------------------------
-
-    def get_text(self) -> str | None:
-        """Return the plain-text content extracted during parse.
-
-        Returns
-        -------
-        str | None
-            Extracted text, or None if parse has not been called yet.
-        """
-        return self._text
-
-    def get_date(self) -> datetime.datetime | None:
-        """Return the document date detected during parse.
-
-        Returns
-        -------
-        datetime.datetime | None
-            Creation date from Tika metadata, or None if not detected.
-        """
-        return self._date
-
-    def get_archive_path(self) -> Path | None:
-        """Return the path to the generated PDF rendition, or None.
-
-        Returns
-        -------
-        Path | None
-            Path to the PDF produced by Gotenberg, or None if parse has not
-            been called yet.
-        """
-        return self._archive_path
-
-    # ------------------------------------------------------------------
-    # Thumbnail and metadata
-    # ------------------------------------------------------------------
-
-    def get_thumbnail(self, document_path: Path, mime_type: str) -> Path:
-        """Generate a thumbnail from the PDF rendition of the document.
-
-        Converts the document to PDF first if not already done.
-
-        Parameters
-        ----------
-        document_path:
-            Absolute path to the source document.
-        mime_type:
-            Detected MIME type of the document.
-
-        Returns
-        -------
-        Path
-            Path to the generated WebP thumbnail inside the temporary directory.
-        """
-        if self._archive_path is None:
-            self._archive_path = self._convert_to_pdf(document_path)
-        return make_thumbnail_from_pdf(self._archive_path, self._tempdir)
-
-    def get_page_count(
-        self,
-        document_path: Path,
-        mime_type: str,
-    ) -> int | None:
-        """Return the number of pages in the document.
-
-        Returns
-        -------
-        int | None
-            Always None — page count is not available from Tika.
-        """
-        return None
-
-    def extract_metadata(
-        self,
-        document_path: Path,
-        mime_type: str,
-    ) -> list[MetadataEntry]:
-        """Extract format-specific metadata via the Tika metadata endpoint.
-
-        Returns
-        -------
-        list[MetadataEntry]
-            All key/value pairs returned by Tika, or ``[]`` on error.
-        """
-        if TYPE_CHECKING:
-            assert self._tika_client is not None
-
-        try:
-            parsed = self._tika_client.metadata.from_file(document_path, mime_type)
-            return [
-                {
-                    "namespace": "",
-                    "prefix": "",
-                    "key": key,
-                    "value": parsed.data[key],
-                }
-                for key in parsed.data
-            ]
-        except Exception as e:
-            logger.warning(
-                "Error while fetching document metadata for %s: %s",
-                document_path,
-                e,
-            )
-            return []
-
-    # ------------------------------------------------------------------
-    # Private helpers
-    # ------------------------------------------------------------------
-
-    def _convert_to_pdf(self, document_path: Path) -> Path:
-        """Convert the document to PDF using Gotenberg's LibreOffice route.
-
-        Parameters
-        ----------
-        document_path:
-            Absolute path to the source document.
-
-        Returns
-        -------
-        Path
-            Path to the generated PDF inside the temporary directory.
-
-        Raises
-        ------
-        documents.parsers.ParseError
-            If Gotenberg returns an error.
-        """
-        if TYPE_CHECKING:
-            assert self._gotenberg_client is not None
-
-        pdf_path = self._tempdir / "convert.pdf"
-
-        logger.info("Converting %s to PDF as %s", document_path, pdf_path)
-
-        with self._gotenberg_client.libre_office.to_pdf() as route:
-            # Set the output format of the resulting PDF.
-            # OutputTypeConfig reads the database-stored ApplicationConfiguration
-            # first, then falls back to the PAPERLESS_OCR_OUTPUT_TYPE env var.
-            output_type = OutputTypeConfig().output_type
-            if output_type in {
-                OutputTypeChoices.PDF_A,
-                OutputTypeChoices.PDF_A2,
-            }:
-                route.pdf_format(PdfAFormat.A2b)
-            elif output_type == OutputTypeChoices.PDF_A1:
-                logger.warning(
-                    "Gotenberg does not support PDF/A-1a, choosing PDF/A-2b instead",
-                )
-                route.pdf_format(PdfAFormat.A2b)
-            elif output_type == OutputTypeChoices.PDF_A3:
-                route.pdf_format(PdfAFormat.A3b)
-
-            route.convert(document_path)
-
-            try:
-                response = route.run()
-                pdf_path.write_bytes(response.content)
-                return pdf_path
-            except Exception as err:
-                raise ParseError(
-                    f"Error while converting document to PDF: {err}",
-                ) from err

src/paperless/tests/parsers/conftest.py

@@ -11,7 +11,6 @@ from typing import TYPE_CHECKING
 import pytest
 
 from paperless.parsers.text import TextDocumentParser
-from paperless.parsers.tika import TikaDocumentParser
 
 if TYPE_CHECKING:
     from collections.abc import Generator
@@ -75,86 +74,3 @@ def text_parser() -> Generator[TextDocumentParser, None, None]:
     """
     with TextDocumentParser() as parser:
         yield parser
-
-
-# ------------------------------------------------------------------
-# Tika parser sample files
-# ------------------------------------------------------------------
-
-
-@pytest.fixture(scope="session")
-def tika_samples_dir(samples_dir: Path) -> Path:
-    """Absolute path to the Tika parser sample files directory.
-
-    Returns
-    -------
-    Path
-        ``<samples_dir>/tika/``
-    """
-    return samples_dir / "tika"
-
-
-@pytest.fixture(scope="session")
-def sample_odt_file(tika_samples_dir: Path) -> Path:
-    """Path to a sample ODT file.
-
-    Returns
-    -------
-    Path
-        Absolute path to ``tika/sample.odt``.
-    """
-    return tika_samples_dir / "sample.odt"
-
-
-@pytest.fixture(scope="session")
-def sample_docx_file(tika_samples_dir: Path) -> Path:
-    """Path to a sample DOCX file.
-
-    Returns
-    -------
-    Path
-        Absolute path to ``tika/sample.docx``.
-    """
-    return tika_samples_dir / "sample.docx"
-
-
-@pytest.fixture(scope="session")
-def sample_doc_file(tika_samples_dir: Path) -> Path:
-    """Path to a sample DOC file.
-
-    Returns
-    -------
-    Path
-        Absolute path to ``tika/sample.doc``.
-    """
-    return tika_samples_dir / "sample.doc"
-
-
-@pytest.fixture(scope="session")
-def sample_broken_odt(tika_samples_dir: Path) -> Path:
-    """Path to a broken ODT file that triggers the multi-part fallback.
-
-    Returns
-    -------
-    Path
-        Absolute path to ``tika/multi-part-broken.odt``.
-    """
-    return tika_samples_dir / "multi-part-broken.odt"
-
-
-# ------------------------------------------------------------------
-# Tika parser instance
-# ------------------------------------------------------------------
-
-
-@pytest.fixture()
-def tika_parser() -> Generator[TikaDocumentParser, None, None]:
-    """Yield a TikaDocumentParser and clean up its temporary directory afterwards.
-
-    Yields
-    ------
-    TikaDocumentParser
-        A ready-to-use parser instance.
-    """
-    with TikaDocumentParser() as parser:
-        yield parser

src/paperless_tesseract/parsers.py

@@ -221,7 +221,7 @@ class RasterisedDocumentParser(DocumentParser):
         if TYPE_CHECKING:
             assert isinstance(self.settings, OcrConfig)
         ocrmypdf_args = {
-            "input_file_or_options": input_file,
+            "input_file": input_file,
             "output_file": output_file,
             # need to use threads, since this will be run in daemonized
             # processes via the task library.
@@ -285,7 +285,7 @@ class RasterisedDocumentParser(DocumentParser):
                     "for compatibility with img2pdf",
                 )
                 # Replace the input file with the non-alpha
-                ocrmypdf_args["input_file_or_options"] = self.remove_alpha(input_file)
+                ocrmypdf_args["input_file"] = self.remove_alpha(input_file)
 
             if dpi:
                 self.log.debug(f"Detected DPI for image {input_file}: {dpi}")

src/paperless_tesseract/tests/test_parser.py

@@ -778,7 +778,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
             safe_fallback=False,
         )
 
-        self.assertEqual(params["input_file_or_options"], "input.pdf")
+        self.assertEqual(params["input_file"], "input.pdf")
         self.assertEqual(params["output_file"], "output.pdf")
         self.assertEqual(params["sidecar"], "sidecar.txt")
 

src/paperless_text/signals.py

@@ -1,12 +1,10 @@
 def get_parser(*args, **kwargs):
     from paperless.parsers.text import TextDocumentParser
 
-    # TextDocumentParser accepts logging_group for constructor compatibility but
+    # The new TextDocumentParser does not accept the legacy logging_group /
-    # does not store or use it (no legacy DocumentParser base class).
+    # progress_callback kwargs injected by the old signal-based consumer.
-    # progress_callback is also not used.  Both may arrive as a positional arg
+    # These are dropped here; Phase 4 will replace this signal path with the
-    # (consumer) or a keyword arg (views); *args absorbs the positional form,
+    # new ParserRegistry so the shim can be removed at that point.
-    # kwargs.pop handles the keyword form.  Phase 4 will replace this signal
-    # path with the new ParserRegistry so the shim can be removed at that point.
     kwargs.pop("logging_group", None)
     kwargs.pop("progress_callback", None)
     return TextDocumentParser()

src/paperless_tika/parsers.py

@@ -0,0 +1,136 @@
+from pathlib import Path
+
+import httpx
+from django.conf import settings
+from django.utils import timezone
+from gotenberg_client import GotenbergClient
+from gotenberg_client.options import PdfAFormat
+from tika_client import TikaClient
+
+from documents.parsers import DocumentParser
+from documents.parsers import ParseError
+from documents.parsers import make_thumbnail_from_pdf
+from paperless.config import OutputTypeConfig
+from paperless.models import OutputTypeChoices
+
+
+class TikaDocumentParser(DocumentParser):
+    """
+    This parser sends documents to a local tika server
+    """
+
+    logging_name = "paperless.parsing.tika"
+
+    def get_thumbnail(self, document_path, mime_type, file_name=None):
+        if not self.archive_path:
+            self.archive_path = self.convert_to_pdf(document_path, file_name)
+
+        return make_thumbnail_from_pdf(
+            self.archive_path,
+            self.tempdir,
+            self.logging_group,
+        )
+
+    def extract_metadata(self, document_path, mime_type):
+        try:
+            with TikaClient(
+                tika_url=settings.TIKA_ENDPOINT,
+                timeout=settings.CELERY_TASK_TIME_LIMIT,
+            ) as client:
+                parsed = client.metadata.from_file(document_path, mime_type)
+                return [
+                    {
+                        "namespace": "",
+                        "prefix": "",
+                        "key": key,
+                        "value": parsed.data[key],
+                    }
+                    for key in parsed.data
+                ]
+        except Exception as e:
+            self.log.warning(
+                f"Error while fetching document metadata for {document_path}: {e}",
+            )
+            return []
+
+    def parse(self, document_path: Path, mime_type: str, file_name=None) -> None:
+        self.log.info(f"Sending {document_path} to Tika server")
+
+        try:
+            with TikaClient(
+                tika_url=settings.TIKA_ENDPOINT,
+                timeout=settings.CELERY_TASK_TIME_LIMIT,
+            ) as client:
+                try:
+                    parsed = client.tika.as_text.from_file(document_path, mime_type)
+                except httpx.HTTPStatusError as err:
+                    # Workaround https://issues.apache.org/jira/browse/TIKA-4110
+                    # Tika fails with some files as multi-part form data
+                    if err.response.status_code == httpx.codes.INTERNAL_SERVER_ERROR:
+                        parsed = client.tika.as_text.from_buffer(
+                            document_path.read_bytes(),
+                            mime_type,
+                        )
+                    else:  # pragma: no cover
+                        raise
+        except Exception as err:
+            raise ParseError(
+                f"Could not parse {document_path} with tika server at "
+                f"{settings.TIKA_ENDPOINT}: {err}",
+            ) from err
+
+        self.text = parsed.content
+        if self.text is not None:
+            self.text = self.text.strip()
+
+        self.date = parsed.created
+        if self.date is not None and timezone.is_naive(self.date):
+            self.date = timezone.make_aware(self.date)
+
+        self.archive_path = self.convert_to_pdf(document_path, file_name)
+
+    def convert_to_pdf(self, document_path: Path, file_name):
+        pdf_path = Path(self.tempdir) / "convert.pdf"
+
+        self.log.info(f"Converting {document_path} to PDF as {pdf_path}")
+
+        with (
+            GotenbergClient(
+                host=settings.TIKA_GOTENBERG_ENDPOINT,
+                timeout=settings.CELERY_TASK_TIME_LIMIT,
+            ) as client,
+            client.libre_office.to_pdf() as route,
+        ):
+            # Set the output format of the resulting PDF
+            if settings.OCR_OUTPUT_TYPE in {
+                OutputTypeChoices.PDF_A,
+                OutputTypeChoices.PDF_A2,
+            }:
+                route.pdf_format(PdfAFormat.A2b)
+            elif settings.OCR_OUTPUT_TYPE == OutputTypeChoices.PDF_A1:
+                self.log.warning(
+                    "Gotenberg does not support PDF/A-1a, choosing PDF/A-2b instead",
+                )
+                route.pdf_format(PdfAFormat.A2b)
+            elif settings.OCR_OUTPUT_TYPE == OutputTypeChoices.PDF_A3:
+                route.pdf_format(PdfAFormat.A3b)
+
+            route.convert(document_path)
+
+            try:
+                response = route.run()
+
+                pdf_path.write_bytes(response.content)
+
+                return pdf_path
+
+            except Exception as err:
+                raise ParseError(
+                    f"Error while converting document to PDF: {err}",
+                ) from err
+
+    def get_settings(self) -> OutputTypeConfig:
+        """
+        This parser only uses the PDF output type configuration currently
+        """
+        return OutputTypeConfig()

src/paperless_tika/signals.py

@@ -1,15 +1,7 @@
 def get_parser(*args, **kwargs):
-    from paperless.parsers.tika import TikaDocumentParser
+    from paperless_tika.parsers import TikaDocumentParser
 
-    # TikaDocumentParser accepts logging_group for constructor compatibility but
+    return TikaDocumentParser(*args, **kwargs)
-    # does not store or use it (no legacy DocumentParser base class).
-    # progress_callback is also not used.  Both may arrive as a positional arg
-    # (consumer) or a keyword arg (views); *args absorbs the positional form,
-    # kwargs.pop handles the keyword form.  Phase 4 will replace this signal
-    # path with the new ParserRegistry so the shim can be removed at that point.
-    kwargs.pop("logging_group", None)
-    kwargs.pop("progress_callback", None)
-    return TikaDocumentParser()
 
 
 def tika_consumer_declaration(sender, **kwargs):

src/paperless_tika/tests/conftest.py

@@ -0,0 +1,41 @@
+from collections.abc import Generator
+from pathlib import Path
+
+import pytest
+
+from paperless_tika.parsers import TikaDocumentParser
+
+
+@pytest.fixture()
+def tika_parser() -> Generator[TikaDocumentParser, None, None]:
+    try:
+        parser = TikaDocumentParser(logging_group=None)
+        yield parser
+    finally:
+        # TODO(stumpylog): Cleanup once all parsers are handled
+        parser.cleanup()
+
+
+@pytest.fixture(scope="session")
+def sample_dir() -> Path:
+    return (Path(__file__).parent / Path("samples")).resolve()
+
+
+@pytest.fixture(scope="session")
+def sample_odt_file(sample_dir: Path) -> Path:
+    return sample_dir / "sample.odt"
+
+
+@pytest.fixture(scope="session")
+def sample_docx_file(sample_dir: Path) -> Path:
+    return sample_dir / "sample.docx"
+
+
+@pytest.fixture(scope="session")
+def sample_doc_file(sample_dir: Path) -> Path:
+    return sample_dir / "sample.doc"
+
+
+@pytest.fixture(scope="session")
+def sample_broken_odt(sample_dir: Path) -> Path:
+    return sample_dir / "multi-part-broken.odt"

src/paperless_tika/tests/test_live_tika.py

@@ -4,7 +4,7 @@ from pathlib import Path
 import pytest
 
 from documents.tests.utils import util_call_with_backoff
-from paperless.parsers.tika import TikaDocumentParser
+from paperless_tika.parsers import TikaDocumentParser
 
 
 @pytest.mark.skipif(
@@ -42,15 +42,14 @@ class TestTikaParserAgainstServer:
         )
 
         assert (
-            tika_parser.get_text()
+            tika_parser.text
             == "This is an ODT test document, created September 14, 2022"
         )
-        archive = tika_parser.get_archive_path()
+        assert tika_parser.archive_path is not None
-        assert archive is not None
+        assert b"PDF-" in tika_parser.archive_path.read_bytes()[:10]
-        assert b"PDF-" in archive.read_bytes()[:10]
 
         # TODO: Unsure what can set the Creation-Date field in a document, enable when possible
-        # self.assertEqual(tika_parser.get_date(), datetime.datetime(2022, 9, 14))
+        # self.assertEqual(tika_parser.date, datetime.datetime(2022, 9, 14))
 
     def test_basic_parse_docx(
         self,
@@ -75,15 +74,14 @@ class TestTikaParserAgainstServer:
         )
 
         assert (
-            tika_parser.get_text()
+            tika_parser.text
             == "This is an DOCX test document, also made September 14, 2022"
         )
-        archive = tika_parser.get_archive_path()
+        assert tika_parser.archive_path is not None
-        assert archive is not None
+        with Path(tika_parser.archive_path).open("rb") as f:
-        with archive.open("rb") as f:
             assert b"PDF-" in f.read()[:10]
 
-        # self.assertEqual(tika_parser.get_date(), datetime.datetime(2022, 9, 14))
+        # self.assertEqual(tika_parser.date, datetime.datetime(2022, 9, 14))
 
     def test_basic_parse_doc(
         self,
@@ -104,12 +102,13 @@ class TestTikaParserAgainstServer:
             [sample_doc_file, "application/msword"],
         )
 
-        text = tika_parser.get_text()
+        assert tika_parser.text is not None
-        assert text is not None
+        assert (
-        assert "This is a test document, saved in the older .doc format" in text
+            "This is a test document, saved in the older .doc format"
-        archive = tika_parser.get_archive_path()
+            in tika_parser.text
-        assert archive is not None
+        )
-        with archive.open("rb") as f:
+        assert tika_parser.archive_path is not None
+        with Path(tika_parser.archive_path).open("rb") as f:
             assert b"PDF-" in f.read()[:10]
 
     def test_tika_fails_multi_part(
@@ -134,7 +133,6 @@ class TestTikaParserAgainstServer:
             [sample_broken_odt, "application/vnd.oasis.opendocument.text"],
         )
 
-        archive = tika_parser.get_archive_path()
+        assert tika_parser.archive_path is not None
-        assert archive is not None
+        with Path(tika_parser.archive_path).open("rb") as f:
-        with archive.open("rb") as f:
             assert b"PDF-" in f.read()[:10]

src/paperless_tika/tests/test_tika_parser.py

@@ -9,56 +9,7 @@ from pytest_django.fixtures import SettingsWrapper
 from pytest_httpx import HTTPXMock
 
 from documents.parsers import ParseError
-from paperless.parsers import ParserProtocol
+from paperless_tika.parsers import TikaDocumentParser
-from paperless.parsers.tika import TikaDocumentParser
-
-
-class TestTikaParserRegistryInterface:
-    """Verify that TikaDocumentParser satisfies the ParserProtocol contract."""
-
-    def test_satisfies_parser_protocol(self) -> None:
-        assert isinstance(TikaDocumentParser(), ParserProtocol)
-
-    def test_supported_mime_types_is_classmethod(self) -> None:
-        mime_types = TikaDocumentParser.supported_mime_types()
-        assert isinstance(mime_types, dict)
-        assert len(mime_types) > 0
-
-    def test_score_returns_none_when_tika_disabled(
-        self,
-        settings: SettingsWrapper,
-    ) -> None:
-        settings.TIKA_ENABLED = False
-        result = TikaDocumentParser.score(
-            "application/vnd.oasis.opendocument.text",
-            "sample.odt",
-        )
-        assert result is None
-
-    def test_score_returns_int_when_tika_enabled(
-        self,
-        settings: SettingsWrapper,
-    ) -> None:
-        settings.TIKA_ENABLED = True
-        result = TikaDocumentParser.score(
-            "application/vnd.oasis.opendocument.text",
-            "sample.odt",
-        )
-        assert isinstance(result, int)
-
-    def test_score_returns_none_for_unsupported_mime(
-        self,
-        settings: SettingsWrapper,
-    ) -> None:
-        settings.TIKA_ENABLED = True
-        result = TikaDocumentParser.score("application/pdf", "doc.pdf")
-        assert result is None
-
-    def test_can_produce_archive_is_false(self) -> None:
-        assert TikaDocumentParser().can_produce_archive is False
-
-    def test_requires_pdf_rendition_is_true(self) -> None:
-        assert TikaDocumentParser().requires_pdf_rendition is True
 
 
 @pytest.mark.django_db()
@@ -85,12 +36,12 @@ class TestTikaParser:
 
         tika_parser.parse(sample_odt_file, "application/vnd.oasis.opendocument.text")
 
-        assert tika_parser.get_text() == "the content"
+        assert tika_parser.text == "the content"
-        assert tika_parser.get_archive_path() is not None
+        assert tika_parser.archive_path is not None
-        with Path(tika_parser.get_archive_path()).open("rb") as f:
+        with Path(tika_parser.archive_path).open("rb") as f:
             assert f.read() == b"PDF document"
 
-        assert tika_parser.get_date() == datetime.datetime(
+        assert tika_parser.date == datetime.datetime(
             2020,
             11,
             21,
@@ -138,7 +89,7 @@ class TestTikaParser:
         httpx_mock.add_response(status_code=HTTPStatus.INTERNAL_SERVER_ERROR)
 
         with pytest.raises(ParseError):
-            tika_parser._convert_to_pdf(sample_odt_file)
+            tika_parser.convert_to_pdf(sample_odt_file, None)
 
     @pytest.mark.parametrize(
         ("setting_value", "expected_form_value"),
@@ -155,6 +106,7 @@ class TestTikaParser:
         expected_form_value: str,
         httpx_mock: HTTPXMock,
         settings: SettingsWrapper,
+        tika_parser: TikaDocumentParser,
         sample_odt_file: Path,
     ) -> None:
         """
@@ -165,8 +117,6 @@ class TestTikaParser:
         THEN:
             - Request to Gotenberg contains the expected PDF/A format string
         """
-        # Parser must be created after the setting is changed so that
-        # OutputTypeConfig reads the correct value at __init__ time.
         settings.OCR_OUTPUT_TYPE = setting_value
         httpx_mock.add_response(
             status_code=codes.OK,
@@ -174,8 +124,7 @@ class TestTikaParser:
             method="POST",
         )
 
-        with TikaDocumentParser() as parser:
+        tika_parser.convert_to_pdf(sample_odt_file, None)
-            parser._convert_to_pdf(sample_odt_file)
 
         request = httpx_mock.get_request()
 

uv.lock

@@ -831,15 +831,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/2d/82/e5d2c1c67d19841e9edc74954c827444ae826978499bde3dfc1d007c8c11/deepmerge-2.0-py3-none-any.whl", hash = "sha256:6de9ce507115cff0bed95ff0ce9ecc31088ef50cbdf09bc90a09349a318b3d00", size = 13475, upload-time = "2024-08-30T05:31:48.659Z" },
 ]
 
-[[package]]
-name = "defusedxml"
-version = "0.7.1"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/0f/d5/c66da9b79e5bdb124974bfe172b4daf3c984ebd9c2a06e2b8a4dc7331c72/defusedxml-0.7.1.tar.gz", hash = "sha256:1bb3032db185915b62d7c6209c5a8792be6a32ab2fedacc84e01b52c51aa3e69", size = 75520, upload-time = "2021-03-08T10:59:26.269Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/07/6c/aa3f2f849e01cb6a001cd8554a88d4c77c5c1a31c95bdf1cf9301e6d9ef4/defusedxml-0.7.1-py2.py3-none-any.whl", hash = "sha256:a352e7e428770286cc899e2542b6cdaedb2b4953ff269a210103ec58f6198a61", size = 25604, upload-time = "2021-03-08T10:59:24.45Z" },
-]
-
 [[package]]
 name = "deprecated"
 version = "1.3.1"
@@ -1292,59 +1283,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a6/ff/ee2f67c0ff146ec98b5df1df637b2bc2d17beeb05df9f427a67bd7a7d79c/flower-2.0.1-py2.py3-none-any.whl", hash = "sha256:9db2c621eeefbc844c8dd88be64aef61e84e2deb29b271e02ab2b5b9f01068e2", size = 383553, upload-time = "2023-08-13T14:37:41.552Z" },
 ]
 
-[[package]]
-name = "fonttools"
-version = "4.62.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/5a/96/686339e0fda8142b7ebed39af53f4a5694602a729662f42a6209e3be91d0/fonttools-4.62.0.tar.gz", hash = "sha256:0dc477c12b8076b4eb9af2e440421b0433ffa9e1dcb39e0640a6c94665ed1098", size = 3579521, upload-time = "2026-03-09T16:50:06.217Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/e4/33/63d79ca41020dd460b51f1e0f58ad1ff0a36b7bcbdf8f3971d52836581e9/fonttools-4.62.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:196cafef9aeec5258425bd31a4e9a414b2ee0d1557bca184d7923d3d3bcd90f9", size = 2870816, upload-time = "2026-03-09T16:48:32.39Z" },
-    { url = "https://files.pythonhosted.org/packages/c0/7a/9aeec114bc9fc00d757a41f092f7107863d372e684a5b5724c043654477c/fonttools-4.62.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:153afc3012ff8761b1733e8fbe5d98623409774c44ffd88fbcb780e240c11d13", size = 2416127, upload-time = "2026-03-09T16:48:34.627Z" },
-    { url = "https://files.pythonhosted.org/packages/5a/71/12cfd8ae0478b7158ffa8850786781f67e73c00fd897ef9d053415c5f88b/fonttools-4.62.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:13b663fb197334de84db790353d59da2a7288fd14e9be329f5debc63ec0500a5", size = 5100678, upload-time = "2026-03-09T16:48:36.454Z" },
-    { url = "https://files.pythonhosted.org/packages/8a/d7/8e4845993ee233c2023d11babe9b3dae7d30333da1d792eeccebcb77baab/fonttools-4.62.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:591220d5333264b1df0d3285adbdfe2af4f6a45bbf9ca2b485f97c9f577c49ff", size = 5070859, upload-time = "2026-03-09T16:48:38.786Z" },
-    { url = "https://files.pythonhosted.org/packages/ae/a0/287ae04cd883a52e7bb1d92dfc4997dcffb54173761c751106845fa9e316/fonttools-4.62.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:579f35c121528a50c96bf6fcb6a393e81e7f896d4326bf40e379f1c971603db9", size = 5076689, upload-time = "2026-03-09T16:48:41.886Z" },
-    { url = "https://files.pythonhosted.org/packages/6d/4e/a2377ad26c36fcd3e671a1c316ea5ed83107de1588e2d897a98349363bc7/fonttools-4.62.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:44956b003151d5a289eba6c71fe590d63509267c37e26de1766ba15d9c589582", size = 5202053, upload-time = "2026-03-09T16:48:43.867Z" },
-    { url = "https://files.pythonhosted.org/packages/ab/9d/7ad1ffc080619f67d0b1e0fa6a0578f0be077404f13fd8e448d1616a94a3/fonttools-4.62.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:22bde4dc12a9e09b5ced77f3b5053d96cf10c4976c6ac0dee293418ef289d221", size = 2870004, upload-time = "2026-03-09T16:48:50.837Z" },
-    { url = "https://files.pythonhosted.org/packages/4d/8b/ba59069a490f61b737e064c3129453dbd28ee38e81d56af0d04d7e6b4de4/fonttools-4.62.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:7199c73b326bad892f1cb53ffdd002128bfd58a89b8f662204fbf1daf8d62e85", size = 2414662, upload-time = "2026-03-09T16:48:53.295Z" },
-    { url = "https://files.pythonhosted.org/packages/8c/8c/c52a4310de58deeac7e9ea800892aec09b00bb3eb0c53265b31ec02be115/fonttools-4.62.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d732938633681d6e2324e601b79e93f7f72395ec8681f9cdae5a8c08bc167e72", size = 5032975, upload-time = "2026-03-09T16:48:55.718Z" },
-    { url = "https://files.pythonhosted.org/packages/0b/a1/d16318232964d786907b9b3613b8409f74cf0be2da400854509d3a864e43/fonttools-4.62.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:31a804c16d76038cc4e3826e07678efb0a02dc4f15396ea8e07088adbfb2578e", size = 4988544, upload-time = "2026-03-09T16:48:57.715Z" },
-    { url = "https://files.pythonhosted.org/packages/b2/8d/7e745ca3e65852adc5e52a83dc213fe1b07d61cb5b394970fcd4b1199d1e/fonttools-4.62.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:090e74ac86e68c20150e665ef8e7e0c20cb9f8b395302c9419fa2e4d332c3b51", size = 4971296, upload-time = "2026-03-09T16:48:59.678Z" },
-    { url = "https://files.pythonhosted.org/packages/e6/d4/b717a4874175146029ca1517e85474b1af80c9d9a306fc3161e71485eea5/fonttools-4.62.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:8f086120e8be9e99ca1288aa5ce519833f93fe0ec6ebad2380c1dee18781f0b5", size = 5122503, upload-time = "2026-03-09T16:49:02.464Z" },
-    { url = "https://files.pythonhosted.org/packages/82/c7/985c1670aa6d82ef270f04cde11394c168f2002700353bd2bde405e59b8f/fonttools-4.62.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:274c8b8a87e439faf565d3bcd3f9f9e31bca7740755776a4a90a4bfeaa722efa", size = 2864929, upload-time = "2026-03-09T16:49:09.331Z" },
-    { url = "https://files.pythonhosted.org/packages/c1/dc/c409c8ceec0d3119e9ab0b7b1a2e3c76d1f4d66e4a9db5c59e6b7652e7df/fonttools-4.62.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:93e27131a5a0ae82aaadcffe309b1bae195f6711689722af026862bede05c07c", size = 2412586, upload-time = "2026-03-09T16:49:11.378Z" },
-    { url = "https://files.pythonhosted.org/packages/5f/ac/8e300dbf7b4d135287c261ffd92ede02d9f48f0d2db14665fbc8b059588a/fonttools-4.62.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:83c6524c5b93bad9c2939d88e619fedc62e913c19e673f25d5ab74e7a5d074e5", size = 5013708, upload-time = "2026-03-09T16:49:14.063Z" },
-    { url = "https://files.pythonhosted.org/packages/fb/bc/60d93477b653eeb1ddf5f9ec34be689b79234d82dbdded269ac0252715b8/fonttools-4.62.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:106aec9226f9498fc5345125ff7200842c01eda273ae038f5049b0916907acee", size = 4964355, upload-time = "2026-03-09T16:49:16.515Z" },
-    { url = "https://files.pythonhosted.org/packages/cb/eb/6dc62bcc3c3598c28a3ecb77e69018869c3e109bd83031d4973c059d318b/fonttools-4.62.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:15d86b96c79013320f13bc1b15f94789edb376c0a2d22fb6088f33637e8dfcbc", size = 4953472, upload-time = "2026-03-09T16:49:18.494Z" },
-    { url = "https://files.pythonhosted.org/packages/82/b3/3af7592d9b254b7b7fec018135f8776bfa0d1ad335476c2791b1334dc5e4/fonttools-4.62.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:4f16c07e5250d5d71d0f990a59460bc5620c3cc456121f2cfb5b60475699905f", size = 5094701, upload-time = "2026-03-09T16:49:21.67Z" },
-    { url = "https://files.pythonhosted.org/packages/1a/64/61f69298aa6e7c363dcf00dd6371a654676900abe27d1effd1a74b43e5d0/fonttools-4.62.0-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:4fa5a9c716e2f75ef34b5a5c2ca0ee4848d795daa7e6792bf30fd4abf8993449", size = 2864222, upload-time = "2026-03-09T16:49:28.285Z" },
-    { url = "https://files.pythonhosted.org/packages/c6/57/6b08756fe4455336b1fe160ab3c11fccc90768ccb6ee03fb0b45851aace4/fonttools-4.62.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:625f5cbeb0b8f4e42343eaeb4bc2786718ddd84760a2f5e55fdd3db049047c00", size = 2410674, upload-time = "2026-03-09T16:49:30.504Z" },
-    { url = "https://files.pythonhosted.org/packages/6f/86/db65b63bb1b824b63e602e9be21b18741ddc99bcf5a7850f9181159ae107/fonttools-4.62.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6247e58b96b982709cd569a91a2ba935d406dccf17b6aa615afaed37ac3856aa", size = 4999387, upload-time = "2026-03-09T16:49:32.593Z" },
-    { url = "https://files.pythonhosted.org/packages/86/c8/c6669e42d2f4efd60d38a3252cebbb28851f968890efb2b9b15f9d1092b0/fonttools-4.62.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:840632ea9c1eab7b7f01c369e408c0721c287dfd7500ab937398430689852fd1", size = 4912506, upload-time = "2026-03-09T16:49:34.927Z" },
-    { url = "https://files.pythonhosted.org/packages/2e/49/0ae552aa098edd0ec548413fbf818f52ceb70535016215094a5ce9bf8f70/fonttools-4.62.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:28a9ea2a7467a816d1bec22658b0cce4443ac60abac3e293bdee78beb74588f3", size = 4951202, upload-time = "2026-03-09T16:49:37.1Z" },
-    { url = "https://files.pythonhosted.org/packages/71/65/ae38fc8a4cea6f162d74cf11f58e9aeef1baa7d0e3d1376dabd336c129e5/fonttools-4.62.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:5ae611294f768d413949fd12693a8cba0e6332fbc1e07aba60121be35eac68d0", size = 5060758, upload-time = "2026-03-09T16:49:39.464Z" },
-    { url = "https://files.pythonhosted.org/packages/f8/65/f47f9b3db1ec156a1f222f1089ba076b2cc9ee1d024a8b0a60c54258517e/fonttools-4.62.0-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:0361a7d41d86937f1f752717c19f719d0fde064d3011038f9f19bdf5fc2f5c95", size = 2947079, upload-time = "2026-03-09T16:49:46.471Z" },
-    { url = "https://files.pythonhosted.org/packages/52/73/bc62e5058a0c22cf02b1e0169ef0c3ca6c3247216d719f95bead3c05a991/fonttools-4.62.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:d4108c12773b3c97aa592311557c405d5b4fc03db2b969ed928fcf68e7b3c887", size = 2448802, upload-time = "2026-03-09T16:49:48.328Z" },
-    { url = "https://files.pythonhosted.org/packages/2b/df/bfaa0e845884935355670e6e68f137185ab87295f8bc838db575e4a66064/fonttools-4.62.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b448075f32708e8fb377fe7687f769a5f51a027172c591ba9a58693631b077a8", size = 5137378, upload-time = "2026-03-09T16:49:50.223Z" },
-    { url = "https://files.pythonhosted.org/packages/32/32/04f616979a18b48b52e634988b93d847b6346260faf85ecccaf7e2e9057f/fonttools-4.62.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e5f1fa8cc9f1a56a3e33ee6b954d6d9235e6b9d11eb7a6c9dfe2c2f829dc24db", size = 4920714, upload-time = "2026-03-09T16:49:53.172Z" },
-    { url = "https://files.pythonhosted.org/packages/3b/2e/274e16689c1dfee5c68302cd7c444213cfddd23cf4620374419625037ec6/fonttools-4.62.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:f8c8ea812f82db1e884b9cdb663080453e28f0f9a1f5027a5adb59c4cc8d38d1", size = 5016012, upload-time = "2026-03-09T16:49:55.762Z" },
-    { url = "https://files.pythonhosted.org/packages/7f/0c/b08117270626e7117ac2f89d732fdd4386ec37d2ab3a944462d29e6f89a1/fonttools-4.62.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:03c6068adfdc67c565d217e92386b1cdd951abd4240d65180cec62fa74ba31b2", size = 5042766, upload-time = "2026-03-09T16:49:57.726Z" },
-    { url = "https://files.pythonhosted.org/packages/9c/57/c2487c281dde03abb2dec244fd67059b8d118bd30a653cbf69e94084cb23/fonttools-4.62.0-py3-none-any.whl", hash = "sha256:75064f19a10c50c74b336aa5ebe7b1f89fd0fb5255807bfd4b0c6317098f4af3", size = 1152427, upload-time = "2026-03-09T16:50:04.074Z" },
-]
-
-[[package]]
-name = "fpdf2"
-version = "2.8.7"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "defusedxml", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "fonttools", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "pillow", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/27/f2/72feae0b2827ed38013e4307b14f95bf0b3d124adfef4d38a7d57533f7be/fpdf2-2.8.7.tar.gz", hash = "sha256:7060ccee5a9c7ab0a271fb765a36a23639f83ef8996c34e3d46af0a17ede57f9", size = 362351, upload-time = "2026-02-28T05:39:16.456Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/66/0a/cf50ecffa1e3747ed9380a3adfc829259f1f86b3fdbd9e505af789003141/fpdf2-2.8.7-py3-none-any.whl", hash = "sha256:d391fc508a3ce02fc43a577c830cda4fe6f37646f2d143d489839940932fbc19", size = 327056, upload-time = "2026-02-28T05:39:14.619Z" },
-]
-
 [[package]]
 name = "frozenlist"
 version = "1.8.0"
@@ -2784,11 +2722,10 @@ wheels = [
 
 [[package]]
 name = "ocrmypdf"
-version = "17.3.0"
+version = "16.13.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "deprecation", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "fpdf2", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "img2pdf", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "packaging", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "pdfminer-six", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2796,14 +2733,11 @@ dependencies = [
     { name = "pikepdf", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "pillow", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "pluggy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "pydantic", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "pypdfium2", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "rich", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "uharfbuzz", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/fa/fe/60bdc79529be1ad8b151d426ed2020d5ac90328c54e9ba92bd808e1535c1/ocrmypdf-17.3.0.tar.gz", hash = "sha256:4022f13aad3f405e330056a07aa8bd63714b48b414693831b56e2cf2c325f52d", size = 7378015, upload-time = "2026-02-21T09:30:07.207Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/8c/52/be1aaece0703a736757d8957c0d4f19c37561054169b501eb0e7132f15e5/ocrmypdf-16.13.0.tar.gz", hash = "sha256:29d37e915234ce717374863a9cc5dd32d29e063dfe60c51380dda71254c88248", size = 7042247, upload-time = "2025-12-24T07:58:35.86Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/3d/b1/b7ae057a1bcb1495067ee3c4d48c1ce5fc66addd9492307c5a0ff799a7f2/ocrmypdf-17.3.0-py3-none-any.whl", hash = "sha256:c8882e7864954d3db6bcee49cc9f261b65bff66b7e5925eb68a1c281f41cad23", size = 488130, upload-time = "2026-02-21T09:30:05.236Z" },
+    { url = "https://files.pythonhosted.org/packages/41/b1/e2e7ad98de0d3ee05b44dbc3f78ccb158a620f3add82d00c85490120e7f2/ocrmypdf-16.13.0-py3-none-any.whl", hash = "sha256:fad8a6f7cc52cdc6225095c401a1766c778c47efe9f1e854ae4dc64a550a3d37", size = 165377, upload-time = "2025-12-24T07:58:33.925Z" },
 ]
 
 [[package]]
@@ -3044,7 +2978,7 @@ requires-dist = [
     { name = "llama-index-vector-stores-faiss", specifier = ">=0.5.2" },
     { name = "mysqlclient", marker = "extra == 'mariadb'", specifier = "~=2.2.7" },
     { name = "nltk", specifier = "~=3.9.1" },
-    { name = "ocrmypdf", specifier = "~=17.3.0" },
+    { name = "ocrmypdf", specifier = "~=16.13.0" },
     { name = "openai", specifier = ">=1.76" },
     { name = "pathvalidate", specifier = "~=3.3.1" },
     { name = "pdf2image", specifier = "~=1.17.0" },
@@ -3721,30 +3655,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/d1/81/ef2b1dfd1862567d573a4fdbc9f969067621764fbb74338496840a1d2977/pyopenssl-25.3.0-py3-none-any.whl", hash = "sha256:1fda6fc034d5e3d179d39e59c1895c9faeaf40a79de5fc4cbbfbe0d36f4a77b6", size = 57268, upload-time = "2025-09-17T00:32:19.474Z" },
 ]
 
-[[package]]
-name = "pypdfium2"
-version = "5.6.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/3b/01/be763b9081c7eb823196e7d13d9c145bf75ac43f3c1466de81c21c24b381/pypdfium2-5.6.0.tar.gz", hash = "sha256:bcb9368acfe3547054698abbdae68ba0cbd2d3bda8e8ee437e061deef061976d", size = 270714, upload-time = "2026-03-08T01:05:06.5Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/6e/f6/9f9e190fe0e5a6b86b82f83bd8b5d3490348766062381140ca5cad8e00b1/pypdfium2-5.6.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:e468c38997573f0e86f03273c2c1fbdea999de52ba43fee96acaa2f6b2ad35f7", size = 3412541, upload-time = "2026-03-08T01:04:25.45Z" },
-    { url = "https://files.pythonhosted.org/packages/ee/8d/e57492cb2228ba56ed57de1ff044c8ac114b46905f8b1445c33299ba0488/pypdfium2-5.6.0-py3-none-macosx_11_0_x86_64.whl", hash = "sha256:ad3abddc5805424f962e383253ccad6a0d1d2ebd86afa9a9e1b9ca659773cd0d", size = 3592320, upload-time = "2026-03-08T01:04:27.509Z" },
-    { url = "https://files.pythonhosted.org/packages/f9/8a/8ab82e33e9c551494cbe1526ea250ca8cc4e9e98d6a4fc6b6f8d959aa1d1/pypdfium2-5.6.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f6b5eb9eae5c45076395454522ca26add72ba8bd1fe473e1e4721aa58521470c", size = 3596450, upload-time = "2026-03-08T01:04:29.183Z" },
-    { url = "https://files.pythonhosted.org/packages/f5/b5/602a792282312ccb158cc63849528079d94b0a11efdc61f2a359edfb41e9/pypdfium2-5.6.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:258624da8ef45cdc426e11b33e9d83f9fb723c1c201c6e0f4ab5a85966c6b876", size = 3325442, upload-time = "2026-03-08T01:04:30.886Z" },
-    { url = "https://files.pythonhosted.org/packages/81/1f/9e48ec05ed8d19d736c2d1f23c1bd0f20673f02ef846a2576c69e237f15d/pypdfium2-5.6.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e9367451c8a00931d6612db0822525a18c06f649d562cd323a719e46ac19c9bb", size = 3727434, upload-time = "2026-03-08T01:04:33.619Z" },
-    { url = "https://files.pythonhosted.org/packages/33/90/0efd020928b4edbd65f4f3c2af0c84e20b43a3ada8fa6d04f999a97afe7a/pypdfium2-5.6.0-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a757869f891eac1cc1372e38a4aa01adac8abc8fe2a8a4e2ebf50595e3bf5937", size = 4139029, upload-time = "2026-03-08T01:04:36.08Z" },
-    { url = "https://files.pythonhosted.org/packages/ff/49/a640b288a48dab1752281dd9b72c0679fccea107874e80a65a606b00efa9/pypdfium2-5.6.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:515be355222cc57ae9e62cd5c7c350b8e0c863efc539f80c7d75e2811ba45cb6", size = 3646387, upload-time = "2026-03-08T01:04:38.151Z" },
-    { url = "https://files.pythonhosted.org/packages/b0/3b/a344c19c01021eeb5d830c102e4fc9b1602f19c04aa7d11abbe2d188fd8e/pypdfium2-5.6.0-py3-none-manylinux_2_27_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d1c4753c7caf7d004211d7f57a21f10d127f5e0e5510a14d24bc073e7220a3ea", size = 3097212, upload-time = "2026-03-08T01:04:40.776Z" },
-    { url = "https://files.pythonhosted.org/packages/50/96/e48e13789ace22aeb9b7510904a1b1493ec588196e11bbacc122da330b3d/pypdfium2-5.6.0-py3-none-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:c49729090281fdd85775fb8912c10bd19e99178efaa98f145ab06e7ce68554d2", size = 2965026, upload-time = "2026-03-08T01:04:42.857Z" },
-    { url = "https://files.pythonhosted.org/packages/cb/06/3100e44d4935f73af8f5d633d3bd40f0d36d606027085a0ef1f0566a6320/pypdfium2-5.6.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:a4a1749a8d4afd62924a8d95cfa4f2e26fc32957ce34ac3b674be6f127ed252e", size = 4131431, upload-time = "2026-03-08T01:04:44.982Z" },
-    { url = "https://files.pythonhosted.org/packages/64/ef/d8df63569ce9a66c8496057782eb8af78e0d28667922d62ec958434e3d4b/pypdfium2-5.6.0-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:36469ebd0fdffb7130ce45ed9c44f8232d91571c89eb851bd1633c64b6f6114f", size = 3747469, upload-time = "2026-03-08T01:04:46.702Z" },
-    { url = "https://files.pythonhosted.org/packages/a6/47/fd2c6a67a49fade1acd719fbd11f7c375e7219912923ef2de0ea0ac1544e/pypdfium2-5.6.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:9da900df09be3cf546b637a127a7b6428fb22d705951d731269e25fd3adef457", size = 4337578, upload-time = "2026-03-08T01:04:49.007Z" },
-    { url = "https://files.pythonhosted.org/packages/6b/f5/836c83e54b01e09478c4d6bf4912651d6053c932250fcee953f5c72d8e4a/pypdfium2-5.6.0-py3-none-musllinux_1_2_ppc64le.whl", hash = "sha256:45fccd5622233c5ec91a885770ae7dd4004d4320ac05a4ad8fa03a66dea40244", size = 4376104, upload-time = "2026-03-08T01:04:51.04Z" },
-    { url = "https://files.pythonhosted.org/packages/6e/7f/b940b6a1664daf8f9bad87c6c99b84effa3611615b8708d10392dc33036c/pypdfium2-5.6.0-py3-none-musllinux_1_2_riscv64.whl", hash = "sha256:282dc030e767cd61bd0299f9d581052b91188e2b87561489057a8e7963e7e0cb", size = 3929824, upload-time = "2026-03-08T01:04:53.544Z" },
-    { url = "https://files.pythonhosted.org/packages/88/79/00267d92a6a58c229e364d474f5698efe446e0c7f4f152f58d0138715e99/pypdfium2-5.6.0-py3-none-musllinux_1_2_s390x.whl", hash = "sha256:a1c1dfe950382c76a7bba1ba160ec5e40df8dd26b04a1124ae268fda55bc4cbe", size = 4270201, upload-time = "2026-03-08T01:04:55.81Z" },
-    { url = "https://files.pythonhosted.org/packages/e1/ab/b127f38aba41746bdf9ace15ba08411d7ef6ecba1326d529ba414eb1ed50/pypdfium2-5.6.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:43b0341ca6feb6c92e4b7a9eb4813e5466f5f5e8b6baeb14df0a94d5f312c00b", size = 4180793, upload-time = "2026-03-08T01:04:57.961Z" },
-]
-
 [[package]]
 name = "pyrefly"
 version = "0.55.0"
@@ -5233,23 +5143,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b1/5e/512aeb40fd819f4660d00f96f5c7371ee36fc8c6b605128c5ee59e0b28c6/u_msgpack_python-2.8.0-py2.py3-none-any.whl", hash = "sha256:1d853d33e78b72c4228a2025b4db28cda81214076e5b0422ed0ae1b1b2bb586a", size = 10590, upload-time = "2023-05-18T09:28:10.323Z" },
 ]
 
-[[package]]
-name = "uharfbuzz"
-version = "0.53.3"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/1c/8d/7c82298bfa5c96f018541661bc2ccdf90dfe397bb2724db46725bf495466/uharfbuzz-0.53.3.tar.gz", hash = "sha256:9a87175c14d1361322ce2a3504e63c6b66062934a5edf47266aed5b33416806c", size = 1714488, upload-time = "2026-01-24T13:10:43.693Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/51/88/5df9337adb60d7b1ad150b162bbc5c56d783d15546714085d92b9531f8f3/uharfbuzz-0.53.3-cp310-abi3-macosx_10_9_universal2.whl", hash = "sha256:d977e41a501d9e8af3f2c329d75031037ee79634bc29ca3872e9115c44e67d25", size = 2722639, upload-time = "2026-01-24T13:10:22.436Z" },
-    { url = "https://files.pythonhosted.org/packages/39/c4/8b4b050e77d6cb9a84af509e5796734f0e687bd02ad11757a581bd6f197d/uharfbuzz-0.53.3-cp310-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:21d512c94aa992691aaf5b433deaca7e51f4ea54c68b99f535974073364f806f", size = 1647506, upload-time = "2026-01-24T13:10:24.16Z" },
-    { url = "https://files.pythonhosted.org/packages/30/ff/8e7cf78d525604f3e0a43b9468263fcf2acb5d208a3979c3bfa8dc61112d/uharfbuzz-0.53.3-cp310-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:dca9a2e071c0c59ba8f382356f31a2518ac3dc7cc77e4f3519defc454c5b9a97", size = 1706448, upload-time = "2026-01-24T13:10:25.729Z" },
-    { url = "https://files.pythonhosted.org/packages/9b/a0/739471cdd52723ecc9fc80f36fb92c706a87265dc258521c1b14d99414f7/uharfbuzz-0.53.3-cp310-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:1191a74ddcf18ec721161b6b33a8ab31b0c6a2b15c6724a9b663127bf7f07d2e", size = 2664628, upload-time = "2026-01-24T13:10:27.814Z" },
-    { url = "https://files.pythonhosted.org/packages/ae/4a/63a81e9eef922b9f26bd948b518b73704d01a8d8e83324b2f99084ab7af0/uharfbuzz-0.53.3-cp310-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:35ec3b600b3f63e7659792f9bd43e1ffb389d3d2aac8285f269d11efbe04787d", size = 2757384, upload-time = "2026-01-24T13:10:29.669Z" },
-    { url = "https://files.pythonhosted.org/packages/e2/d2/27be1201488323d0ff0c99fb966a0522b2736f79bd5a5b7b99526fca3d98/uharfbuzz-0.53.3-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:6f0ad2812303d2c7ccff596fd6c9d5629874f3a83f30255e11639c9b7ba4e89d", size = 1335822, upload-time = "2026-01-24T13:10:34.774Z" },
-    { url = "https://files.pythonhosted.org/packages/70/99/53e39bcd4dec5981eb70a6a76285a862c8a76b80cd52e8f40fe51adab032/uharfbuzz-0.53.3-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:757d9ed1841912e8f229319f335cf7dd25a2fd377e444bda9deb720617192e12", size = 1237560, upload-time = "2026-01-24T13:10:36.971Z" },
-    { url = "https://files.pythonhosted.org/packages/aa/2b/04d8cde466acfe70373d4f489da5c6eab0aba07d50442dd21217cb0fd167/uharfbuzz-0.53.3-pp311-pypy311_pp73-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5d3a0b824811bd1be129356818e6cdbf0e4b056bb60aa9a5eb270bff9d21f24c", size = 1497923, upload-time = "2026-01-24T13:10:38.743Z" },
-    { url = "https://files.pythonhosted.org/packages/f3/01/a250521491bc995609275e0062c552b16f437a3ce15de83250176245093e/uharfbuzz-0.53.3-pp311-pypy311_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9211d798b2921a99b8c34e810676137f66372d3b5447765b72d969bdfa6abe6a", size = 1556794, upload-time = "2026-01-24T13:10:40.262Z" },
-]
-
 [[package]]
 name = "ujson"
 version = "5.11.0"