Compare commits

...
41 changed files with 845 additions and 15 deletions
+2 -1
View File
@@ -301,7 +301,8 @@ The following methods are supported:
- `delete` - `delete`
- No `parameters` required - No `parameters` required
- `reprocess` - `reprocess`
- No `parameters` required - Optional `parameters`: `{ "remote_ocr": true }` to send the documents to the
remote OCR engine, see [Remote OCR](usage.md#remote-ocr). Defaults to false.
- `set_permissions` - `set_permissions`
- Requires `parameters`: - Requires `parameters`:
- `"set_permissions": PERMISSIONS_OBJ` (see format [above](#permissions)) and / or - `"set_permissions": PERMISSIONS_OBJ` (see format [above](#permissions)) and / or
+12
View File
@@ -2047,6 +2047,18 @@ password. All of these options come from their similarly-named [Django settings]
Defaults to None. Defaults to None.
#### [`PAPERLESS_REMOTE_OCR_MODE=<str>`](#PAPERLESS_REMOTE_OCR_MODE) {#PAPERLESS_REMOTE_OCR_MODE}
: Which documents are sent to the remote OCR engine.
- `always`: every document of a supported file type is sent to the remote
engine, bypassing the local OCR engine.
- `workflow_only`: documents are processed locally unless a workflow
explicitly enables remote OCR for them, letting you use the remote engine
selectively.
Defaults to "always".
## AI {#ai} ## AI {#ai}
#### [`PAPERLESS_AI_ENABLED=<bool>`](#PAPERLESS_AI_ENABLED) {#PAPERLESS_AI_ENABLED} #### [`PAPERLESS_AI_ENABLED=<bool>`](#PAPERLESS_AI_ENABLED) {#PAPERLESS_AI_ENABLED}
+14
View File
@@ -456,6 +456,20 @@ def score(
return 10 return 10
``` ```
**Remote services**
If your parser sends document content to a remote service, declare it:
```python
class MyCustomParser:
uses_remote_service = True
```
Paperless-ngx excludes such parsers when the document being consumed has not
been marked for remote processing, so users can keep remote OCR off by default
and enable it selectively with a workflow. Parsers that do not declare the
attribute are treated as fully local and are always considered.
**Archive and rendition flags** **Archive and rendition flags**
```python ```python
+6
View File
@@ -1090,6 +1090,12 @@ settings can be supplied as environment variables or via **Application Configura
Additionally, when using a commercial service with this feature, consider both potential costs as well as any associated file size Additionally, when using a commercial service with this feature, consider both potential costs as well as any associated file size
or page limitations (e.g. with a free tier). or page limitations (e.g. with a free tier).
By default, every document of a supported file type is sent to the remote engine. To use it more selectively, set the
[remote OCR mode](configuration.md#PAPERLESS_REMOTE_OCR_MODE) to `workflow_only`. Documents are then processed locally
unless a workflow explicitly enables remote OCR for them, so you can limit the remote engine to particular documents.
Setting the mode to `workflow_only` also allows the **Reprocess** actions to selectively use remote OCR for individual documents.
## Architecture ## Architecture
Paperless-ngx consists of the following components: Paperless-ngx consists of the following components:
@@ -179,6 +179,7 @@ describe('ConfigComponent', () => {
'remote_ocr_engine', 'remote_ocr_engine',
'remote_ocr_api_key', 'remote_ocr_api_key',
'remote_ocr_endpoint', 'remote_ocr_endpoint',
'remote_ocr_mode',
]) ])
}) })
}) })
@@ -0,0 +1,28 @@
<div class="modal-header">
<h4 class="modal-title" id="modal-basic-title">{{title}}</h4>
<button type="button" class="btn-close" aria-label="Close" (click)="cancel()">
</button>
</div>
<div class="modal-body">
@if (messageBold) {
<p class="text-break"><b>{{messageBold}}</b></p>
}
@if (message) {
<p class="mb-0 text-break" [innerHTML]="message"></p>
}
@if (showRemoteOcr) {
<div class="form-check mt-3">
<input class="form-check-input" type="checkbox" id="reprocessRemoteOcr" [(ngModel)]="remoteOcr" />
<label class="form-check-label" for="reprocessRemoteOcr" i18n>Use remote OCR</label>
<div class="form-text" i18n>Sends the document to the configured remote OCR service, which may incur costs.</div>
</div>
}
</div>
<div class="modal-footer">
<button type="button" class="btn" [class]="cancelBtnClass" (click)="cancel()" [disabled]="!buttonsEnabled">
<span class="d-inline-block" style="padding-bottom: 1px;">{{cancelBtnCaption}}</span>
</button>
<button type="button" class="btn" [class]="btnClass" (click)="confirm()" [disabled]="!confirmButtonEnabled || !buttonsEnabled">
{{btnCaption}}
</button>
</div>
@@ -0,0 +1,72 @@
import { provideHttpClient, withInterceptorsFromDi } from '@angular/common/http'
import { provideHttpClientTesting } from '@angular/common/http/testing'
import { ComponentFixture, TestBed } from '@angular/core/testing'
import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
import { RemoteOCRModeConfig } from 'src/app/data/paperless-config'
import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
import { SettingsService } from 'src/app/services/settings.service'
import { ReprocessConfirmDialogComponent } from './reprocess-confirm-dialog.component'
describe('ReprocessConfirmDialogComponent', () => {
let component: ReprocessConfirmDialogComponent
let fixture: ComponentFixture<ReprocessConfirmDialogComponent>
let settingsService: SettingsService
const createComponent = (configured: boolean, mode: string) => {
settingsService.set(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED, configured)
settingsService.set(SETTINGS_KEYS.REMOTE_OCR_MODE, mode)
fixture = TestBed.createComponent(ReprocessConfirmDialogComponent)
component = fixture.componentInstance
fixture.detectChanges()
}
beforeEach(async () => {
TestBed.configureTestingModule({
providers: [
NgbActiveModal,
provideHttpClient(withInterceptorsFromDi()),
provideHttpClientTesting(),
],
imports: [ReprocessConfirmDialogComponent],
}).compileComponents()
settingsService = TestBed.inject(SettingsService)
})
it('should not request remote OCR by default', () => {
createComponent(true, RemoteOCRModeConfig.WORKFLOW_ONLY)
expect(component.remoteOcr).toBeFalsy()
})
it('should not offer remote OCR when no engine is configured', () => {
createComponent(false, RemoteOCRModeConfig.WORKFLOW_ONLY)
expect(component.showRemoteOcr).toBeFalsy()
expect(
fixture.nativeElement.querySelector('#reprocessRemoteOcr')
).toBeNull()
})
it('should not offer remote OCR when it already handles every document', () => {
createComponent(true, RemoteOCRModeConfig.ALWAYS)
expect(component.showRemoteOcr).toBeFalsy()
expect(
fixture.nativeElement.querySelector('#reprocessRemoteOcr')
).toBeNull()
})
it('should offer remote OCR when configured and selective', () => {
createComponent(true, RemoteOCRModeConfig.WORKFLOW_ONLY)
expect(component.showRemoteOcr).toBeTruthy()
const checkbox = fixture.nativeElement.querySelector('#reprocessRemoteOcr')
expect(checkbox).not.toBeNull()
checkbox.click()
fixture.detectChanges()
expect(component.remoteOcr).toBeTruthy()
})
})
@@ -0,0 +1,20 @@
import { Component, inject } from '@angular/core'
import { FormsModule } from '@angular/forms'
import { SettingsService } from 'src/app/services/settings.service'
import { ConfirmDialogComponent } from '../confirm-dialog.component'
@Component({
selector: 'pngx-reprocess-confirm-dialog',
templateUrl: './reprocess-confirm-dialog.component.html',
imports: [FormsModule],
})
export class ReprocessConfirmDialogComponent extends ConfirmDialogComponent {
private settings = inject(SettingsService)
remoteOcr: boolean = false
public get showRemoteOcr(): boolean {
// Hidden when it is not configured, or when it already handles every document anyway.
return this.settings.remoteOCRIsSelectable
}
}
@@ -963,12 +963,24 @@ describe('DocumentDetailComponent', () => {
component.reprocess() component.reprocess()
const modalCloseSpy = jest.spyOn(openModal, 'close') const modalCloseSpy = jest.spyOn(openModal, 'close')
openModal.componentInstance.confirmClicked.next() openModal.componentInstance.confirmClicked.next()
expect(reprocessSpy).toHaveBeenCalledWith({ documents: [doc.id] }) expect(reprocessSpy).toHaveBeenCalledWith({ documents: [doc.id] }, false)
expect(modalSpy).toHaveBeenCalled() expect(modalSpy).toHaveBeenCalled()
expect(toastSpy).toHaveBeenCalled() expect(toastSpy).toHaveBeenCalled()
expect(modalCloseSpy).toHaveBeenCalled() expect(modalCloseSpy).toHaveBeenCalled()
}) })
it('should pass remote OCR choice when reprocessing', () => {
initNormally()
const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments')
reprocessSpy.mockReturnValue(of(true))
let openModal: NgbModalRef
modalService.activeInstances.subscribe((modal) => (openModal = modal[0]))
component.reprocess()
openModal.componentInstance.remoteOcr = true
openModal.componentInstance.confirmClicked.next()
expect(reprocessSpy).toHaveBeenCalledWith({ documents: [doc.id] }, true)
})
it('should show error if redo ocr call fails', () => { it('should show error if redo ocr call fails', () => {
initNormally() initNormally()
const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments') const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments')
@@ -97,6 +97,7 @@ import { ISODateAdapter } from 'src/app/utils/ngb-iso-date-adapter'
import * as UTIF from 'utif' import * as UTIF from 'utif'
import { DocumentDetailFieldID } from '../admin/settings/settings.component' import { DocumentDetailFieldID } from '../admin/settings/settings.component'
import { ConfirmDialogComponent } from '../common/confirm-dialog/confirm-dialog.component' import { ConfirmDialogComponent } from '../common/confirm-dialog/confirm-dialog.component'
import { ReprocessConfirmDialogComponent } from '../common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component'
import { PasswordRemovalConfirmDialogComponent } from '../common/confirm-dialog/password-removal-confirm-dialog/password-removal-confirm-dialog.component' import { PasswordRemovalConfirmDialogComponent } from '../common/confirm-dialog/password-removal-confirm-dialog/password-removal-confirm-dialog.component'
import { CustomFieldsDropdownComponent } from '../common/custom-fields-dropdown/custom-fields-dropdown.component' import { CustomFieldsDropdownComponent } from '../common/custom-fields-dropdown/custom-fields-dropdown.component'
import { CorrespondentEditDialogComponent } from '../common/edit-dialog/correspondent-edit-dialog/correspondent-edit-dialog.component' import { CorrespondentEditDialogComponent } from '../common/edit-dialog/correspondent-edit-dialog/correspondent-edit-dialog.component'
@@ -1402,7 +1403,7 @@ export class DocumentDetailComponent
} }
reprocess() { reprocess() {
let modal = this.modalService.open(ConfirmDialogComponent, { let modal = this.modalService.open(ReprocessConfirmDialogComponent, {
backdrop: 'static', backdrop: 'static',
}) })
modal.componentInstance.title = $localize`Reprocess confirm` modal.componentInstance.title = $localize`Reprocess confirm`
@@ -1413,7 +1414,10 @@ export class DocumentDetailComponent
modal.componentInstance.confirmClicked.subscribe(() => { modal.componentInstance.confirmClicked.subscribe(() => {
modal.componentInstance.buttonsEnabled = false modal.componentInstance.buttonsEnabled = false
this.documentsService this.documentsService
.reprocessDocuments({ documents: [this.document().id] }) .reprocessDocuments(
{ documents: [this.document().id] },
modal.componentInstance.remoteOcr
)
.subscribe({ .subscribe({
next: () => { next: () => {
this.toastService.showInfo( this.toastService.showInfo(
@@ -1122,6 +1122,7 @@ describe('BulkEditorComponent', () => {
req.flush(true) req.flush(true)
expect(req.request.body).toEqual({ expect(req.request.body).toEqual({
documents: [3, 4], documents: [3, 4],
remote_ocr: false,
}) })
httpTestingController.match( httpTestingController.match(
`${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true` `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
@@ -51,6 +51,7 @@ import { ToastService } from 'src/app/services/toast.service'
import { flattenTags } from 'src/app/utils/flatten-tags' import { flattenTags } from 'src/app/utils/flatten-tags'
import { queryParamsFromFilterRules } from 'src/app/utils/query-params' import { queryParamsFromFilterRules } from 'src/app/utils/query-params'
import { MergeConfirmDialogComponent } from '../../common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component' import { MergeConfirmDialogComponent } from '../../common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component'
import { ReprocessConfirmDialogComponent } from '../../common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component'
import { RotateConfirmDialogComponent } from '../../common/confirm-dialog/rotate-confirm-dialog/rotate-confirm-dialog.component' import { RotateConfirmDialogComponent } from '../../common/confirm-dialog/rotate-confirm-dialog/rotate-confirm-dialog.component'
import { CorrespondentEditDialogComponent } from '../../common/edit-dialog/correspondent-edit-dialog/correspondent-edit-dialog.component' import { CorrespondentEditDialogComponent } from '../../common/edit-dialog/correspondent-edit-dialog/correspondent-edit-dialog.component'
import { CustomFieldEditDialogComponent } from '../../common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component' import { CustomFieldEditDialogComponent } from '../../common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component'
@@ -909,7 +910,7 @@ export class BulkEditorComponent
} }
reprocessSelected() { reprocessSelected() {
let modal = this.modalService.open(ConfirmDialogComponent, { let modal = this.modalService.open(ReprocessConfirmDialogComponent, {
backdrop: 'static', backdrop: 'static',
}) })
modal.componentInstance.title = $localize`Reprocess confirm` modal.componentInstance.title = $localize`Reprocess confirm`
@@ -923,7 +924,10 @@ export class BulkEditorComponent
modal.componentInstance.buttonsEnabled = false modal.componentInstance.buttonsEnabled = false
this.executeDocumentAction( this.executeDocumentAction(
modal, modal,
this.documentService.reprocessDocuments(this.getSelectionQuery()) this.documentService.reprocessDocuments(
this.getSelectionQuery(),
modal.componentInstance.remoteOcr
)
) )
}) })
} }
+16
View File
@@ -73,6 +73,11 @@ export const RemoteOCREngineConfig = {
AZURE_AI: 'azureai', AZURE_AI: 'azureai',
} }
export const RemoteOCRModeConfig = {
ALWAYS: 'always',
WORKFLOW_ONLY: 'workflow_only',
}
export interface ConfigOption { export interface ConfigOption {
key: string key: string
title: string title: string
@@ -217,6 +222,16 @@ export const PaperlessConfigOptions: ConfigOption[] = [
section: ConfigSection.RemoteOCR, section: ConfigSection.RemoteOCR,
note: $localize`Required when using the Azure AI engine.`, note: $localize`Required when using the Azure AI engine.`,
}, },
{
key: 'remote_ocr_mode',
title: $localize`Remote OCR Mode`,
type: ConfigOptionType.Select,
choices: mapToItems(RemoteOCRModeConfig),
config_key: 'PAPERLESS_REMOTE_OCR_MODE',
category: ConfigCategory.OCR,
section: ConfigSection.RemoteOCR,
note: $localize`Which documents are sent to the remote engine. Use 'workflow_only' to keep remote OCR off unless a workflow enables it for a document.`,
},
{ {
key: 'app_logo', key: 'app_logo',
title: $localize`Application Logo`, title: $localize`Application Logo`,
@@ -437,6 +452,7 @@ export interface PaperlessConfig extends ObjectWithId {
remote_ocr_engine: string remote_ocr_engine: string
remote_ocr_api_key: string remote_ocr_api_key: string
remote_ocr_endpoint: string remote_ocr_endpoint: string
remote_ocr_mode: string
ai_enabled: boolean ai_enabled: boolean
llm_embedding_backend: string llm_embedding_backend: string
llm_embedding_model: string llm_embedding_model: string
+13
View File
@@ -1,5 +1,6 @@
import { PdfEditorEditMode } from '../components/common/pdf-editor/pdf-editor-edit-mode' import { PdfEditorEditMode } from '../components/common/pdf-editor/pdf-editor-edit-mode'
import { PdfZoomScale } from '../components/common/pdf-viewer/pdf-viewer.types' import { PdfZoomScale } from '../components/common/pdf-viewer/pdf-viewer.types'
import { RemoteOCRModeConfig } from './paperless-config'
import { User } from './user' import { User } from './user'
export interface UiSettings { export interface UiSettings {
@@ -94,6 +95,8 @@ export const SETTINGS_KEYS = {
OUTLOOK_OAUTH_URL: 'outlook_oauth_url', OUTLOOK_OAUTH_URL: 'outlook_oauth_url',
EMAIL_ENABLED: 'email_enabled', EMAIL_ENABLED: 'email_enabled',
AI_ENABLED: 'ai_enabled', AI_ENABLED: 'ai_enabled',
REMOTE_OCR_CONFIGURED: 'remote_ocr:configured',
REMOTE_OCR_MODE: 'remote_ocr:mode',
} }
export const SETTINGS: UiSetting[] = [ export const SETTINGS: UiSetting[] = [
@@ -347,4 +350,14 @@ export const SETTINGS: UiSetting[] = [
type: 'string', type: 'string',
default: PdfEditorEditMode.Create, default: PdfEditorEditMode.Create,
}, },
{
key: SETTINGS_KEYS.REMOTE_OCR_CONFIGURED,
type: 'boolean',
default: false,
},
{
key: SETTINGS_KEYS.REMOTE_OCR_MODE,
type: 'string',
default: RemoteOCRModeConfig.ALWAYS,
},
] ]
@@ -284,6 +284,21 @@ describe(`DocumentService`, () => {
expect(req.request.method).toEqual('POST') expect(req.request.method).toEqual('POST')
expect(req.request.body).toEqual({ expect(req.request.body).toEqual({
documents: ids, documents: ids,
remote_ocr: false,
})
})
it('should request remote OCR when reprocessing with it enabled', () => {
const ids = [1, 2, 3]
subscription = service
.reprocessDocuments({ documents: ids }, true)
.subscribe()
const req = httpTestingController.expectOne(
`${environment.apiBaseUrl}${endpoint}/reprocess/`
)
expect(req.request.body).toEqual({
documents: ids,
remote_ocr: true,
}) })
}) })
@@ -349,9 +349,13 @@ export class DocumentService extends AbstractPaperlessService<Document> {
}) })
} }
reprocessDocuments(selection: DocumentSelectionQuery) { reprocessDocuments(
selection: DocumentSelectionQuery,
remoteOcr: boolean = false
) {
return this.http.post(this.getResourceUrl(null, 'reprocess'), { return this.http.post(this.getResourceUrl(null, 'reprocess'), {
...selection, ...selection,
remote_ocr: remoteOcr,
}) })
} }
@@ -13,6 +13,7 @@ import { environment } from 'src/environments/environment'
import { CustomFieldDataType } from '../data/custom-field' import { CustomFieldDataType } from '../data/custom-field'
import { DEFAULT_DISPLAY_FIELDS, DisplayField } from '../data/document' import { DEFAULT_DISPLAY_FIELDS, DisplayField } from '../data/document'
import { SavedView } from '../data/saved-view' import { SavedView } from '../data/saved-view'
import { RemoteOCRModeConfig } from '../data/paperless-config'
import { SETTINGS_KEYS, UiSettings } from '../data/ui-settings' import { SETTINGS_KEYS, UiSettings } from '../data/ui-settings'
import { PermissionsService } from './permissions.service' import { PermissionsService } from './permissions.service'
import { CustomFieldsService } from './rest/custom-fields.service' import { CustomFieldsService } from './rest/custom-fields.service'
@@ -434,4 +435,26 @@ describe('SettingsService', () => {
).name ).name
).toEqual(customFields[0].name) ).toEqual(customFields[0].name)
}) })
it('should offer remote OCR only when configured and selective', () => {
settingsService.set(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED, false)
settingsService.set(
SETTINGS_KEYS.REMOTE_OCR_MODE,
RemoteOCRModeConfig.WORKFLOW_ONLY
)
expect(settingsService.remoteOCRIsSelectable).toBeFalsy()
// configured, but already handling every document
settingsService.set(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED, true)
settingsService.set(
SETTINGS_KEYS.REMOTE_OCR_MODE,
RemoteOCRModeConfig.ALWAYS
)
expect(settingsService.remoteOCRIsSelectable).toBeFalsy()
settingsService.set(
SETTINGS_KEYS.REMOTE_OCR_MODE,
RemoteOCRModeConfig.WORKFLOW_ONLY
)
expect(settingsService.remoteOCRIsSelectable).toBeTruthy()
})
}) })
@@ -19,6 +19,7 @@ import {
} from 'src/app/utils/color' } from 'src/app/utils/color'
import { DEFAULT_APP_TITLE, environment } from 'src/environments/environment' import { DEFAULT_APP_TITLE, environment } from 'src/environments/environment'
import { DEFAULT_DISPLAY_FIELDS, DisplayField } from '../data/document' import { DEFAULT_DISPLAY_FIELDS, DisplayField } from '../data/document'
import { RemoteOCRModeConfig } from '../data/paperless-config'
import { SavedView } from '../data/saved-view' import { SavedView } from '../data/saved-view'
import { import {
PAPERLESS_GREEN_HEX, PAPERLESS_GREEN_HEX,
@@ -687,6 +688,17 @@ export class SettingsService {
return this.settingIsSet(SETTINGS_KEYS.UPDATE_CHECKING_ENABLED) return this.settingIsSet(SETTINGS_KEYS.UPDATE_CHECKING_ENABLED)
} }
/**
* Offering remote OCR as a choice only makes sense when an engine
* is configured but is not already handling every document.
*/
get remoteOCRIsSelectable(): boolean {
return (
this.get(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED) &&
this.get(SETTINGS_KEYS.REMOTE_OCR_MODE) !== RemoteOCRModeConfig.ALWAYS
)
}
offerTour(): boolean { offerTour(): boolean {
return this.dashboardIsEmpty() && !this.get(SETTINGS_KEYS.TOUR_COMPLETE) return this.dashboardIsEmpty() && !this.get(SETTINGS_KEYS.TOUR_COMPLETE)
} }
+8 -2
View File
@@ -394,10 +394,16 @@ def delete(doc_ids: list[int]) -> Literal["OK"]:
return "OK" return "OK"
def reprocess(doc_ids: list[int]) -> Literal["OK"]: def reprocess(doc_ids: list[int], *, remote_ocr: bool = False) -> Literal["OK"]:
"""
Re-run parsing for the given documents.
Consumption workflows do not run here, so ``remote_ocr`` is how the user
asks for the remote engine when it is not configured to handle everything.
"""
for document_id in doc_ids: for document_id in doc_ids:
update_document_content_maybe_archive_file.apply_async( update_document_content_maybe_archive_file.apply_async(
kwargs={"document_id": document_id}, kwargs={"document_id": document_id, "remote_ocr": remote_ocr},
headers={"trigger_source": PaperlessTask.TriggerSource.MANUAL}, headers={"trigger_source": PaperlessTask.TriggerSource.MANUAL},
) )
+8
View File
@@ -53,6 +53,7 @@ from documents.utils import copy_basic_file_stats
from documents.utils import copy_file_with_basic_stats from documents.utils import copy_file_with_basic_stats
from documents.utils import run_subprocess from documents.utils import run_subprocess
from paperless.config import OcrConfig from paperless.config import OcrConfig
from paperless.config import RemoteOCRConfig
from paperless.models import ArchiveFileGenerationChoices from paperless.models import ArchiveFileGenerationChoices
from paperless.parsers import ParserContext from paperless.parsers import ParserContext
from paperless.parsers import ParserProtocol from paperless.parsers import ParserProtocol
@@ -451,12 +452,19 @@ class ConsumerPlugin(
except Exception as e: except Exception as e:
self.log.error(f"Error attempting to clean PDF: {e}") self.log.error(f"Error attempting to clean PDF: {e}")
# Workflows have already run at this point, so the metadata knows
# whether this document was singled out for remote OCR
allow_remote = (
self.metadata.remote_ocr or RemoteOCRConfig().remote_ocr_by_default
)
# Based on the mime type, get the parser for that type # Based on the mime type, get the parser for that type
parser_class: type[ParserProtocol] | None = ( parser_class: type[ParserProtocol] | None = (
get_parser_registry().get_parser_for_file( get_parser_registry().get_parser_for_file(
mime_type, mime_type,
self.filename, self.filename,
self.working_copy, self.working_copy,
allow_remote=allow_remote,
) )
) )
if not parser_class: if not parser_class:
+3
View File
@@ -34,6 +34,7 @@ class DocumentMetadataOverrides:
skip_asn_if_exists: bool = False skip_asn_if_exists: bool = False
version_label: str | None = None version_label: str | None = None
actor_id: int | None = None actor_id: int | None = None
remote_ocr: bool = False
def update(self, other: "DocumentMetadataOverrides") -> "DocumentMetadataOverrides": def update(self, other: "DocumentMetadataOverrides") -> "DocumentMetadataOverrides":
""" """
@@ -57,6 +58,8 @@ class DocumentMetadataOverrides:
self.actor_id = other.actor_id self.actor_id = other.actor_id
if other.skip_asn_if_exists: if other.skip_asn_if_exists:
self.skip_asn_if_exists = True self.skip_asn_if_exists = True
if other.remote_ocr:
self.remote_ocr = True
if other.version_label is not None: if other.version_label is not None:
self.version_label = other.version_label self.version_label = other.version_label
+10 -1
View File
@@ -1744,7 +1744,7 @@ class DeleteDocumentsSerializer(DocumentSelectionSerializer):
class ReprocessDocumentsSerializer(DocumentSelectionSerializer): class ReprocessDocumentsSerializer(DocumentSelectionSerializer):
pass remote_ocr = serializers.BooleanField(required=False, default=False)
class BulkEditSerializer( class BulkEditSerializer(
@@ -2086,6 +2086,13 @@ class BulkEditSerializer(
f"Page {op['page']} is out of bounds for document with {doc.page_count} pages.", f"Page {op['page']} is out of bounds for document with {doc.page_count} pages.",
) )
def _validate_parameters_reprocess(self, parameters) -> None:
if "remote_ocr" in parameters:
if not isinstance(parameters["remote_ocr"], bool):
raise serializers.ValidationError("remote_ocr must be a boolean")
else:
parameters["remote_ocr"] = False
def validate_parameters_remove_password(self, parameters): def validate_parameters_remove_password(self, parameters):
if "password" not in parameters: if "password" not in parameters:
raise serializers.ValidationError("password not specified") raise serializers.ValidationError("password not specified")
@@ -2150,6 +2157,8 @@ class BulkEditSerializer(
self._validate_parameters_edit_pdf(parameters, attrs["documents"][0]) self._validate_parameters_edit_pdf(parameters, attrs["documents"][0])
elif method == bulk_edit.remove_password: elif method == bulk_edit.remove_password:
self.validate_parameters_remove_password(parameters) self.validate_parameters_remove_password(parameters)
elif method == bulk_edit.reprocess:
self._validate_parameters_reprocess(parameters)
return attrs return attrs
+10 -1
View File
@@ -66,6 +66,7 @@ from documents.utils import compute_checksum
from documents.utils import identity from documents.utils import identity
from documents.workflows.utils import get_workflows_for_trigger from documents.workflows.utils import get_workflows_for_trigger
from paperless.config import AIConfig from paperless.config import AIConfig
from paperless.config import RemoteOCRConfig
from paperless.logging import consume_task_id from paperless.logging import consume_task_id
from paperless.parsers import ParserContext from paperless.parsers import ParserContext
from paperless.parsers.registry import get_parser_registry from paperless.parsers.registry import get_parser_registry
@@ -337,10 +338,17 @@ def bulk_update_documents(document_ids) -> None:
@shared_task @shared_task
def update_document_content_maybe_archive_file(document_id) -> None: def update_document_content_maybe_archive_file(
document_id,
*,
remote_ocr: bool = False,
) -> None:
""" """
Re-creates OCR content and thumbnail for a document, and archive file if Re-creates OCR content and thumbnail for a document, and archive file if
it exists. it exists.
Remote OCR is used only when the engine is configured to handle everything
or if explicitly asked for via ``remote_ocr``.
""" """
document = Document.objects.get(id=document_id) document = Document.objects.get(id=document_id)
@@ -350,6 +358,7 @@ def update_document_content_maybe_archive_file(document_id) -> None:
mime_type, mime_type,
document.original_filename or "", document.original_filename or "",
document.source_path, document.source_path,
allow_remote=remote_ocr or RemoteOCRConfig().remote_ocr_by_default,
) )
if not parser_class: if not parser_class:
@@ -75,6 +75,7 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
"remote_ocr_engine": None, "remote_ocr_engine": None,
"remote_ocr_api_key": None, "remote_ocr_api_key": None,
"remote_ocr_endpoint": None, "remote_ocr_endpoint": None,
"remote_ocr_mode": None,
"ai_enabled": False, "ai_enabled": False,
"llm_embedding_backend": None, "llm_embedding_backend": None,
"llm_embedding_model": None, "llm_embedding_model": None,
+46 -1
View File
@@ -532,7 +532,29 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
m.assert_called_once() m.assert_called_once()
args, kwargs = m.call_args args, kwargs = m.call_args
self.assertEqual(args[0], [self.doc1.id]) self.assertEqual(args[0], [self.doc1.id])
self.assertEqual(len(kwargs), 0) self.assertEqual(kwargs, {"remote_ocr": False})
@mock.patch("documents.views.bulk_edit.reprocess")
def test_reprocess_documents_endpoint_remote_ocr(self, m) -> None:
"""
GIVEN:
- API data to reprocess a document with remote OCR requested
WHEN:
- API is called
THEN:
- reprocess is called with remote_ocr=True
"""
self.setup_mock(m, "reprocess")
response = self.client.post(
"/api/documents/reprocess/",
json.dumps({"documents": [self.doc1.id], "remote_ocr": True}),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_200_OK)
m.assert_called_once()
args, kwargs = m.call_args
self.assertEqual(args[0], [self.doc1.id])
self.assertEqual(kwargs, {"remote_ocr": True})
@mock.patch("documents.serialisers.bulk_edit.set_storage_path") @mock.patch("documents.serialisers.bulk_edit.set_storage_path")
def test_api_set_storage_path(self, m) -> None: def test_api_set_storage_path(self, m) -> None:
@@ -1553,6 +1575,29 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
), ),
) )
def test_legacy_bulk_edit_reprocess_invalid_remote_ocr(self) -> None:
"""
GIVEN:
- The deprecated bulk_edit endpoint with a non-boolean remote_ocr
WHEN:
- API is called
THEN:
- The request is rejected rather than passed through to the task
"""
response = self.client.post(
"/api/documents/bulk_edit/",
json.dumps(
{
"documents": [self.doc1.id],
"method": "reprocess",
"parameters": {"remote_ocr": "yes please"},
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
@mock.patch("documents.views.bulk_edit.edit_pdf") @mock.patch("documents.views.bulk_edit.edit_pdf")
def test_edit_pdf(self, m) -> None: def test_edit_pdf(self, m) -> None:
self.setup_mock(m, "edit_pdf") self.setup_mock(m, "edit_pdf")
@@ -60,6 +60,10 @@ class TestApiUiSettings(DirectoriesMixin, APITestCase):
}, },
"email_enabled": False, "email_enabled": False,
"ai_enabled": False, "ai_enabled": False,
"remote_ocr": {
"configured": False,
"mode": "always",
},
}, },
) )
@@ -154,6 +158,50 @@ class TestApiUiSettings(DirectoriesMixin, APITestCase):
str(response.data["settings"]), str(response.data["settings"]),
) )
@override_settings(
REMOTE_OCR_ENGINE="azureai",
REMOTE_OCR_API_KEY="somekey",
REMOTE_OCR_ENDPOINT="https://example.cognitiveservices.azure.com",
REMOTE_OCR_MODE="workflow_only",
)
def test_settings_reports_remote_ocr_when_configured(self) -> None:
"""
GIVEN:
- A fully configured remote OCR engine in workflow_only mode
WHEN:
- The ui_settings endpoint is called
THEN:
- The UI is told remote OCR is available and selective, so it can
offer it where it would actually change something
"""
response = self.client.get(self.ENDPOINT, format="json")
self.assertEqual(response.status_code, status.HTTP_200_OK)
self.assertEqual(
response.data["settings"]["remote_ocr"],
{"configured": True, "mode": "workflow_only"},
)
@override_settings(
REMOTE_OCR_ENGINE="azureai",
REMOTE_OCR_API_KEY=None,
REMOTE_OCR_ENDPOINT=None,
)
def test_settings_reports_remote_ocr_incompletely_configured(self) -> None:
"""
GIVEN:
- An engine named but missing its endpoint and API key
WHEN:
- The ui_settings endpoint is called
THEN:
- It is reported as not configured, matching what the parser
registry will actually do
"""
response = self.client.get(self.ENDPOINT, format="json")
self.assertEqual(response.status_code, status.HTTP_200_OK)
self.assertFalse(response.data["settings"]["remote_ocr"]["configured"])
@override_settings( @override_settings(
OAUTH_CALLBACK_BASE_URL="http://localhost:8000", OAUTH_CALLBACK_BASE_URL="http://localhost:8000",
GMAIL_OAUTH_CLIENT_ID="abc123", GMAIL_OAUTH_CLIENT_ID="abc123",
+53
View File
@@ -1782,3 +1782,56 @@ class TestPDFActions(DirectoriesMixin, TestCase):
self.assertIn("wrong password", str(exc.exception)) self.assertIn("wrong password", str(exc.exception))
self.assertIn("Error removing password from document", cm.output[0]) self.assertIn("Error removing password from document", cm.output[0])
class TestBulkEditReprocess(DirectoriesMixin, TestCase):
def setUp(self) -> None:
super().setUp()
self.doc = Document.objects.create(
title="test",
checksum="A",
mime_type="application/pdf",
)
@mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file")
def test_reprocess_defaults_to_local(self, mock_task: mock.Mock) -> None:
"""
GIVEN:
- A reprocess request that says nothing about remote OCR
WHEN:
- reprocess is called
THEN:
- The task is queued without asking for the remote engine
"""
result = bulk_edit.reprocess([self.doc.id])
self.assertEqual(result, "OK")
mock_task.apply_async.assert_called_once()
_, kwargs = mock_task.apply_async.call_args
self.assertEqual(
kwargs["kwargs"],
{"document_id": self.doc.id, "remote_ocr": False},
)
@mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file")
def test_reprocess_passes_remote_ocr(self, mock_task: mock.Mock) -> None:
"""
GIVEN:
- A reprocess request that explicitly asks for remote OCR
WHEN:
- reprocess is called
THEN:
- The request is forwarded to the task for every document
"""
other = Document.objects.create(
title="test2",
checksum="B",
mime_type="application/pdf",
)
bulk_edit.reprocess([self.doc.id, other.id], remote_ocr=True)
self.assertEqual(mock_task.apply_async.call_count, 2)
for call in mock_task.apply_async.call_args_list:
self.assertTrue(call.kwargs["kwargs"]["remote_ocr"])
+80
View File
@@ -1559,6 +1559,72 @@ class PostConsumeTestCase(DirectoriesMixin, GetConsumerMixin, TestCase):
consumer.run_post_consume_script(doc) consumer.run_post_consume_script(doc)
class TestConsumerRemoteOCR(
DirectoriesMixin,
FileSystemAssertsMixin,
GetConsumerMixin,
TestCase,
):
"""
The consumer resolves the remote OCR mode and the per-document request from
workflows into the allow_remote flag it hands to the parser registry.
"""
def setUp(self) -> None:
super().setUp()
patcher = mock.patch("documents.consumer.get_parser_registry")
self.mock_registry = patcher.start()
self.mock_registry.return_value.get_parser_for_file.return_value = DummyParser
self.addCleanup(patcher.stop)
def _consume(self, *, overrides: DocumentMetadataOverrides | None = None) -> bool:
src = (
Path(__file__).parent
/ "samples"
/ "documents"
/ "originals"
/ "0000001.pdf"
)
dst = self.dirs.scratch_dir / "sample.pdf"
shutil.copy(src, dst)
with self.get_consumer(dst, overrides=overrides) as consumer:
consumer.run()
_, kwargs = self.mock_registry.return_value.get_parser_for_file.call_args
return kwargs["allow_remote"]
@override_settings(REMOTE_OCR_MODE="always")
def test_always_mode_allows_remote(self) -> None:
"""
GIVEN: Remote OCR mode is 'always'.
WHEN: A document is consumed without any workflow asking for it.
THEN: The registry is allowed to pick the remote parser.
"""
self.assertTrue(self._consume())
@override_settings(REMOTE_OCR_MODE="workflow_only")
def test_workflow_only_mode_denies_remote_by_default(self) -> None:
"""
GIVEN: Remote OCR mode is 'workflow_only'.
WHEN: A document is consumed and nothing asked for remote OCR.
THEN: The remote parser is excluded.
"""
self.assertFalse(self._consume())
@override_settings(REMOTE_OCR_MODE="workflow_only")
def test_workflow_only_mode_allows_remote_when_requested(self) -> None:
"""
GIVEN: Remote OCR mode is 'workflow_only'.
WHEN: A workflow set remote_ocr on the metadata overrides.
THEN: The registry is allowed to pick the remote parser.
"""
self.assertTrue(
self._consume(overrides=DocumentMetadataOverrides(remote_ocr=True)),
)
class TestMetadataOverrides(TestCase): class TestMetadataOverrides(TestCase):
def test_update_skip_asn_if_exists(self) -> None: def test_update_skip_asn_if_exists(self) -> None:
base = DocumentMetadataOverrides() base = DocumentMetadataOverrides()
@@ -1566,6 +1632,20 @@ class TestMetadataOverrides(TestCase):
base.update(incoming) base.update(incoming)
self.assertTrue(base.skip_asn_if_exists) self.assertTrue(base.skip_asn_if_exists)
def test_update_remote_ocr(self) -> None:
base = DocumentMetadataOverrides()
base.update(DocumentMetadataOverrides(remote_ocr=True))
self.assertTrue(base.remote_ocr)
def test_update_remote_ocr_is_not_unset(self) -> None:
"""
A later workflow that says nothing must not undo an earlier one that
asked for remote OCR.
"""
base = DocumentMetadataOverrides(remote_ocr=True)
base.update(DocumentMetadataOverrides())
self.assertTrue(base.remote_ocr)
def test_update_actor_and_version_label(self) -> None: def test_update_actor_and_version_label(self) -> None:
base = DocumentMetadataOverrides( base = DocumentMetadataOverrides(
actor_id=1, actor_id=1,
+39
View File
@@ -287,6 +287,45 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
self.assertNotEqual(Document.objects.get(pk=doc.pk).content, "test") self.assertNotEqual(Document.objects.get(pk=doc.pk).content, "test")
class TestUpdateContentRemoteOCR(DirectoriesMixin, TestCase):
"""
Consumption workflows do not run on reprocess, so the remote parser is
used only in 'always' mode or when the caller explicitly asks for it.
"""
def setUp(self) -> None:
super().setUp()
patcher = mock.patch("documents.tasks.get_parser_registry")
self.mock_registry = patcher.start()
self.mock_registry.return_value.get_parser_for_file.return_value = None
self.addCleanup(patcher.stop)
self.doc = Document.objects.create(
title="test",
content="my document",
checksum="wow",
mime_type="application/pdf",
)
def _allow_remote(self, **kwargs) -> bool:
tasks.update_document_content_maybe_archive_file(self.doc.pk, **kwargs)
_, call_kwargs = self.mock_registry.return_value.get_parser_for_file.call_args
return call_kwargs["allow_remote"]
@override_settings(REMOTE_OCR_MODE="always")
def test_always_mode_allows_remote(self) -> None:
self.assertTrue(self._allow_remote())
@override_settings(REMOTE_OCR_MODE="workflow_only")
def test_workflow_only_mode_denies_remote_by_default(self) -> None:
self.assertFalse(self._allow_remote())
@override_settings(REMOTE_OCR_MODE="workflow_only")
def test_workflow_only_mode_allows_remote_when_requested(self) -> None:
self.assertTrue(self._allow_remote(remote_ocr=True))
class TestAIIndex(DirectoriesMixin, TestCase): class TestAIIndex(DirectoriesMixin, TestCase):
@override_settings( @override_settings(
AI_ENABLED=True, AI_ENABLED=True,
+7
View File
@@ -236,8 +236,10 @@ from paperless import version
from paperless.celery import app as celery_app from paperless.celery import app as celery_app
from paperless.config import AIConfig from paperless.config import AIConfig
from paperless.config import GeneralConfig from paperless.config import GeneralConfig
from paperless.config import RemoteOCRConfig
from paperless.models import ApplicationConfiguration from paperless.models import ApplicationConfiguration
from paperless.parsers.registry import get_parser_registry from paperless.parsers.registry import get_parser_registry
from paperless.parsers.remote import RemoteEngineConfig
from paperless.serialisers import GroupSerializer from paperless.serialisers import GroupSerializer
from paperless.serialisers import UserSerializer from paperless.serialisers import UserSerializer
from paperless.views import StandardPagination from paperless.views import StandardPagination
@@ -4010,6 +4012,11 @@ class UiSettingsView(GenericAPIView[Any]):
ui_settings["auditlog_enabled"] = settings.AUDIT_LOG_ENABLED ui_settings["auditlog_enabled"] = settings.AUDIT_LOG_ENABLED
ui_settings["remote_ocr"] = {
"configured": RemoteEngineConfig.from_app_config().engine_is_valid(),
"mode": RemoteOCRConfig().remote_ocr_mode,
}
if settings.GMAIL_OAUTH_ENABLED or settings.OUTLOOK_OAUTH_ENABLED: if settings.GMAIL_OAUTH_ENABLED or settings.OUTLOOK_OAUTH_ENABLED:
manager = PaperlessMailOAuth2Manager() manager = PaperlessMailOAuth2Manager()
if settings.GMAIL_OAUTH_ENABLED: if settings.GMAIL_OAUTH_ENABLED:
+17 -3
View File
@@ -339,16 +339,30 @@ def check_deprecated_v2_ocr_env_vars(
@register() @register()
def check_remote_parser_configured(app_configs: Any, **kwargs: Any) -> list[Error]: def check_remote_parser_configured(app_configs: Any, **kwargs: Any) -> list[Error]:
# Import here because checks.py runs before the app registry is ready
from paperless.models import RemoteOCRMode
errors = []
if settings.REMOTE_OCR_ENGINE == "azureai" and not ( if settings.REMOTE_OCR_ENGINE == "azureai" and not (
settings.REMOTE_OCR_ENDPOINT and settings.REMOTE_OCR_API_KEY settings.REMOTE_OCR_ENDPOINT and settings.REMOTE_OCR_API_KEY
): ):
return [ errors.append(
Error( Error(
"Azure AI remote parser requires endpoint and API key to be configured.", "Azure AI remote parser requires endpoint and API key to be configured.",
), ),
] )
return [] valid_modes = {mode.value for mode in RemoteOCRMode}
if settings.REMOTE_OCR_MODE not in valid_modes:
errors.append(
Error(
f"PAPERLESS_REMOTE_OCR_MODE is set to {settings.REMOTE_OCR_MODE!r}, "
f"expected one of {sorted(valid_modes)}.",
),
)
return errors
def get_tesseract_langs(): def get_tesseract_langs():
+16
View File
@@ -9,6 +9,7 @@ from paperless.models import CleanChoices
from paperless.models import ColorConvertChoices from paperless.models import ColorConvertChoices
from paperless.models import ModeChoices from paperless.models import ModeChoices
from paperless.models import OutputTypeChoices from paperless.models import OutputTypeChoices
from paperless.models import RemoteOCRMode
@dataclasses.dataclass @dataclasses.dataclass
@@ -194,6 +195,7 @@ class RemoteOCRConfig(BaseConfig):
remote_ocr_engine: str | None = dataclasses.field(init=False) remote_ocr_engine: str | None = dataclasses.field(init=False)
remote_ocr_api_key: str | None = dataclasses.field(init=False) remote_ocr_api_key: str | None = dataclasses.field(init=False)
remote_ocr_endpoint: str | None = dataclasses.field(init=False) remote_ocr_endpoint: str | None = dataclasses.field(init=False)
remote_ocr_mode: RemoteOCRMode = dataclasses.field(init=False)
def __post_init__(self) -> None: def __post_init__(self) -> None:
app_config = self._get_config_instance() app_config = self._get_config_instance()
@@ -207,6 +209,20 @@ class RemoteOCRConfig(BaseConfig):
self.remote_ocr_endpoint = ( self.remote_ocr_endpoint = (
app_config.remote_ocr_endpoint or settings.REMOTE_OCR_ENDPOINT app_config.remote_ocr_endpoint or settings.REMOTE_OCR_ENDPOINT
) )
self.remote_ocr_mode = app_config.remote_ocr_mode or RemoteOCRMode(
settings.REMOTE_OCR_MODE,
)
@property
def remote_ocr_by_default(self) -> bool:
"""
Whether every supported document goes to the remote engine.
When False the remote engine is used only for documents that
explicitly asked for it, i.e. a workflow matched during consumption or
the user ticked the box when reprocessing.
"""
return self.remote_ocr_mode == RemoteOCRMode.ALWAYS
@dataclasses.dataclass @dataclasses.dataclass
@@ -0,0 +1,27 @@
# Generated by Django 5.2.16 on 2026-08-10 15:43
from django.db import migrations
from django.db import models
class Migration(migrations.Migration):
dependencies = [
("paperless", "0014_applicationconfiguration_remote_ocr_api_key_and_more"),
]
operations = [
migrations.AddField(
model_name="applicationconfiguration",
name="remote_ocr_mode",
field=models.CharField(
blank=True,
choices=[
("always", "All supported documents"),
("workflow_only", "Only when a workflow enables it"),
],
max_length=32,
null=True,
verbose_name="Sets which documents are sent to the remote OCR engine",
),
),
]
+18
View File
@@ -82,6 +82,15 @@ class RemoteOCREngine(models.TextChoices):
AZURE_AI = ("azureai", _("Azure AI Document Intelligence")) AZURE_AI = ("azureai", _("Azure AI Document Intelligence"))
class RemoteOCRMode(models.TextChoices):
"""
Matches to PAPERLESS_REMOTE_OCR_MODE
"""
ALWAYS = ("always", _("All supported documents"))
WORKFLOW_ONLY = ("workflow_only", _("Only when a workflow enables it"))
class LLMEmbeddingBackend(models.TextChoices): class LLMEmbeddingBackend(models.TextChoices):
OPENAI_LIKE = ("openai-like", _("OpenAI-compatible")) OPENAI_LIKE = ("openai-like", _("OpenAI-compatible"))
HUGGINGFACE = ("huggingface", _("Huggingface")) HUGGINGFACE = ("huggingface", _("Huggingface"))
@@ -323,6 +332,15 @@ class ApplicationConfiguration(AbstractSingletonModel):
max_length=256, max_length=256,
) )
# PAPERLESS_REMOTE_OCR_MODE
remote_ocr_mode = models.CharField(
verbose_name=_("Sets which documents are sent to the remote OCR engine"),
blank=True,
null=True,
max_length=32,
choices=RemoteOCRMode.choices,
)
""" """
AI related settings AI related settings
""" """
+9
View File
@@ -134,6 +134,11 @@ class ParserProtocol(Protocol):
Author or organisation name. Author or organisation name.
url : str url : str
URL for documentation, source code, or issue tracker. URL for documentation, source code, or issue tracker.
Parsers that send document content to a remote service should additionally
set ``uses_remote_service = True`` so the registry can exclude them when
remote processing has not been requested for a document. The attribute is
optional so a parser that omits it is treated as fully local.
""" """
# ------------------------------------------------------------------ # ------------------------------------------------------------------
@@ -145,6 +150,10 @@ class ParserProtocol(Protocol):
author: str author: str
url: str url: str
# NOTE: uses_remote_service is not declared here, the registry reads it
# with getattr(cls, ..., False) for backwards-compatibility with existing
# parsers
# ------------------------------------------------------------------ # ------------------------------------------------------------------
# Class methods # Class methods
# ------------------------------------------------------------------ # ------------------------------------------------------------------
+14
View File
@@ -334,6 +334,8 @@ class ParserRegistry:
mime_type: str, mime_type: str,
filename: str, filename: str,
path: Path | None = None, path: Path | None = None,
*,
allow_remote: bool = True,
) -> type[ParserProtocol] | None: ) -> type[ParserProtocol] | None:
"""Return the best parser class for the given file, or None. """Return the best parser class for the given file, or None.
@@ -359,6 +361,11 @@ class ParserRegistry:
path: path:
Optional filesystem path to the file. Forwarded to each Optional filesystem path to the file. Forwarded to each
parser's score method. parser's score method.
allow_remote:
When False, parsers that declare ``uses_remote_service = True``
are excluded from consideration, so a document is never sent to
a remote service. Parsers that do not declare the attribute
are treated as local and are always considered.
Returns Returns
------- -------
@@ -374,6 +381,13 @@ class ParserRegistry:
if mime_type not in parser_class.supported_mime_types(): if mime_type not in parser_class.supported_mime_types():
continue continue
if not allow_remote and getattr(
parser_class,
"uses_remote_service",
False,
):
continue
score = parser_class.score(mime_type, filename, path) score = parser_class.score(mime_type, filename, path)
if score is None: if score is None:
continue continue
+5
View File
@@ -95,6 +95,9 @@ class RemoteDocumentParser:
Maintainer name. Maintainer name.
url : str url : str
Issue tracker / source URL. Issue tracker / source URL.
uses_remote_service : bool
Content is sent to a remote service, True so that the registry
can skip this parser if remote processing was not requested.
""" """
name: str = "Paperless-ngx Remote OCR Parser" name: str = "Paperless-ngx Remote OCR Parser"
@@ -102,6 +105,8 @@ class RemoteDocumentParser:
author: str = "Paperless-ngx Contributors" author: str = "Paperless-ngx Contributors"
url: str = "https://github.com/paperless-ngx/paperless-ngx" url: str = "https://github.com/paperless-ngx/paperless-ngx"
uses_remote_service: bool = True
# ------------------------------------------------------------------ # ------------------------------------------------------------------
# Class methods # Class methods
# ------------------------------------------------------------------ # ------------------------------------------------------------------
+1
View File
@@ -1197,6 +1197,7 @@ WEBHOOKS_ALLOW_INTERNAL_REQUESTS = get_bool_from_env(
REMOTE_OCR_ENGINE = os.getenv("PAPERLESS_REMOTE_OCR_ENGINE") REMOTE_OCR_ENGINE = os.getenv("PAPERLESS_REMOTE_OCR_ENGINE")
REMOTE_OCR_API_KEY = os.getenv("PAPERLESS_REMOTE_OCR_API_KEY") REMOTE_OCR_API_KEY = os.getenv("PAPERLESS_REMOTE_OCR_API_KEY")
REMOTE_OCR_ENDPOINT = os.getenv("PAPERLESS_REMOTE_OCR_ENDPOINT") REMOTE_OCR_ENDPOINT = os.getenv("PAPERLESS_REMOTE_OCR_ENDPOINT")
REMOTE_OCR_MODE = os.getenv("PAPERLESS_REMOTE_OCR_MODE", "always")
################################################################################ ################################################################################
# AI Settings # # AI Settings #
+17
View File
@@ -655,6 +655,23 @@ class TestRemoteParserChecks:
in msg.msg in msg.msg
) )
def test_valid_mode(self, settings: SettingsWrapper) -> None:
settings.REMOTE_OCR_ENGINE = None
settings.REMOTE_OCR_MODE = "workflow_only"
msgs = check_remote_parser_configured(None)
assert len(msgs) == 0
def test_invalid_mode(self, settings: SettingsWrapper) -> None:
settings.REMOTE_OCR_ENGINE = None
settings.REMOTE_OCR_MODE = "sometimes"
msgs = check_remote_parser_configured(None)
assert len(msgs) == 1
assert "PAPERLESS_REMOTE_OCR_MODE is set to 'sometimes'" in msgs[0].msg
class TestTesseractChecks: class TestTesseractChecks:
def test_default_language(self) -> None: def test_default_language(self) -> None:
+118
View File
@@ -468,6 +468,124 @@ class TestParserRegistryGetParserForFile:
assert result is AcceptingBuiltin assert result is AcceptingBuiltin
class TestParserRegistryRemoteParsers:
"""Verify the allow_remote filter in ParserRegistry.get_parser_for_file()."""
@staticmethod
def _remote_parser_cls() -> type:
class RemoteParser:
name = "remote"
version = "1.0"
author = "A"
url = "https://example.com/remote"
uses_remote_service = True
@classmethod
def supported_mime_types(cls):
return {"text/plain": ".txt"}
@classmethod
def score(cls, mime_type, filename, path=None):
return 20
return RemoteParser
def test_remote_parser_wins_when_remote_allowed(
self,
dummy_parser_cls: type,
) -> None:
"""
GIVEN: A remote parser scoring 20 and a local parser scoring 10.
WHEN: get_parser_for_file() is called with allow_remote=True.
THEN: The remote parser is returned.
"""
remote_parser_cls = self._remote_parser_cls()
registry = ParserRegistry()
registry.register_builtin(dummy_parser_cls)
registry.register_builtin(remote_parser_cls)
result = registry.get_parser_for_file(
"text/plain",
"readme.txt",
allow_remote=True,
)
assert result is remote_parser_cls
def test_remote_parser_skipped_when_remote_not_allowed(
self,
dummy_parser_cls: type,
) -> None:
"""
GIVEN: A remote parser scoring 20 and a local parser scoring 10.
WHEN: get_parser_for_file() is called with allow_remote=False.
THEN: The local parser is returned despite its lower score.
"""
registry = ParserRegistry()
registry.register_builtin(dummy_parser_cls)
registry.register_builtin(self._remote_parser_cls())
result = registry.get_parser_for_file(
"text/plain",
"readme.txt",
allow_remote=False,
)
assert result is dummy_parser_cls
def test_no_parser_when_only_remote_available_and_not_allowed(self) -> None:
"""
GIVEN: A registry whose only candidate declares uses_remote_service.
WHEN: get_parser_for_file() is called with allow_remote=False.
THEN: None is returned the remote parser is never used as a
fallback when remote processing was not requested.
"""
registry = ParserRegistry()
registry.register_builtin(self._remote_parser_cls())
result = registry.get_parser_for_file(
"text/plain",
"readme.txt",
allow_remote=False,
)
assert result is None
def test_parser_without_attribute_treated_as_local(
self,
dummy_parser_cls: type,
) -> None:
"""
GIVEN: A third-party parser predating uses_remote_service, so it does
not declare the attribute at all.
WHEN: get_parser_for_file() is called with allow_remote=False.
THEN: It is still considered, i.e. treated as fully local, rather
than raising AttributeError.
"""
assert not hasattr(dummy_parser_cls, "uses_remote_service")
registry = ParserRegistry()
registry.register_builtin(dummy_parser_cls)
result = registry.get_parser_for_file(
"text/plain",
"readme.txt",
allow_remote=False,
)
assert result is dummy_parser_cls
def test_remote_allowed_by_default(self) -> None:
"""
GIVEN: A registry containing only a remote parser.
WHEN: get_parser_for_file() is called without allow_remote.
THEN: The remote parser is returned callers that do not opt in to
the filter keep the previous behaviour.
"""
remote_parser_cls = self._remote_parser_cls()
registry = ParserRegistry()
registry.register_builtin(remote_parser_cls)
result = registry.get_parser_for_file("text/plain", "readme.txt")
assert result is remote_parser_cls
class TestDiscover: class TestDiscover:
"""Verify entrypoint discovery in ParserRegistry.discover().""" """Verify entrypoint discovery in ParserRegistry.discover()."""
@@ -8,6 +8,7 @@ import pytest
from django.test import override_settings from django.test import override_settings
from paperless.config import RemoteOCRConfig from paperless.config import RemoteOCRConfig
from paperless.models import RemoteOCRMode
if TYPE_CHECKING: if TYPE_CHECKING:
from unittest.mock import MagicMock from unittest.mock import MagicMock
@@ -20,6 +21,7 @@ def null_app_config(mocker) -> MagicMock:
remote_ocr_engine=None, remote_ocr_engine=None,
remote_ocr_api_key=None, remote_ocr_api_key=None,
remote_ocr_endpoint=None, remote_ocr_endpoint=None,
remote_ocr_mode=None,
) )
@@ -47,10 +49,12 @@ class TestRemoteOCRConfig:
REMOTE_OCR_ENGINE="azureai", REMOTE_OCR_ENGINE="azureai",
REMOTE_OCR_API_KEY="env-key", REMOTE_OCR_API_KEY="env-key",
REMOTE_OCR_ENDPOINT="https://env.cognitiveservices.azure.com", REMOTE_OCR_ENDPOINT="https://env.cognitiveservices.azure.com",
REMOTE_OCR_MODE=RemoteOCRMode.WORKFLOW_ONLY,
) )
assert cfg.remote_ocr_engine == "azureai" assert cfg.remote_ocr_engine == "azureai"
assert cfg.remote_ocr_api_key == "env-key" assert cfg.remote_ocr_api_key == "env-key"
assert cfg.remote_ocr_endpoint == "https://env.cognitiveservices.azure.com" assert cfg.remote_ocr_endpoint == "https://env.cognitiveservices.azure.com"
assert cfg.remote_ocr_mode == RemoteOCRMode.WORKFLOW_ONLY
def test_app_config_takes_precedence( def test_app_config_takes_precedence(
self, self,
@@ -61,16 +65,19 @@ class TestRemoteOCRConfig:
remote_ocr_engine="azureai", remote_ocr_engine="azureai",
remote_ocr_api_key="db-key", remote_ocr_api_key="db-key",
remote_ocr_endpoint="https://db.cognitiveservices.azure.com", remote_ocr_endpoint="https://db.cognitiveservices.azure.com",
remote_ocr_mode=RemoteOCRMode.WORKFLOW_ONLY,
) )
cfg = make_remote_ocr_config( cfg = make_remote_ocr_config(
app_config, app_config,
REMOTE_OCR_ENGINE=None, REMOTE_OCR_ENGINE=None,
REMOTE_OCR_API_KEY="env-key", REMOTE_OCR_API_KEY="env-key",
REMOTE_OCR_ENDPOINT="https://env.cognitiveservices.azure.com", REMOTE_OCR_ENDPOINT="https://env.cognitiveservices.azure.com",
REMOTE_OCR_MODE=RemoteOCRMode.ALWAYS,
) )
assert cfg.remote_ocr_engine == "azureai" assert cfg.remote_ocr_engine == "azureai"
assert cfg.remote_ocr_api_key == "db-key" assert cfg.remote_ocr_api_key == "db-key"
assert cfg.remote_ocr_endpoint == "https://db.cognitiveservices.azure.com" assert cfg.remote_ocr_endpoint == "https://db.cognitiveservices.azure.com"
assert cfg.remote_ocr_mode == RemoteOCRMode.WORKFLOW_ONLY
def test_unset_everywhere( def test_unset_everywhere(
self, self,
@@ -86,3 +93,21 @@ class TestRemoteOCRConfig:
assert cfg.remote_ocr_engine is None assert cfg.remote_ocr_engine is None
assert cfg.remote_ocr_api_key is None assert cfg.remote_ocr_api_key is None
assert cfg.remote_ocr_endpoint is None assert cfg.remote_ocr_endpoint is None
class TestRemoteOCRByDefault:
def test_always_mode(self, make_remote_ocr_config, null_app_config) -> None:
cfg = make_remote_ocr_config(
null_app_config,
REMOTE_OCR_MODE=RemoteOCRMode.ALWAYS,
)
assert cfg.remote_ocr_by_default is True
def test_workflow_only_mode(self, make_remote_ocr_config, null_app_config) -> None:
cfg = make_remote_ocr_config(
null_app_config,
REMOTE_OCR_MODE=RemoteOCRMode.WORKFLOW_ONLY,
)
assert cfg.remote_ocr_by_default is False