Compare commits

..

3 Commits

Author SHA1 Message Date
Trenton H
3ae0b8e219 Fixes logging so I can see it 2026-03-06 12:04:54 -08:00
Trenton H
4a6fd02492 Batch based iteration and bulk updates, with chunked file reading 2026-03-06 11:44:41 -08:00
Trenton H
76fb8f3770 Transitions to SHA256 based checksums 2026-03-06 11:33:33 -08:00
25 changed files with 352 additions and 541 deletions

View File

@@ -59,7 +59,7 @@ 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",

View File

@@ -1217,7 +1217,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1760</context>
<context context-type="linenumber">1756</context>
</context-group>
</trans-unit>
<trans-unit id="1577733187050997705" datatype="html">
@@ -2090,7 +2090,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">637</context>
<context context-type="linenumber">634</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-version-dropdown/document-version-dropdown.component.html</context>
@@ -2798,11 +2798,11 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1379</context>
<context context-type="linenumber">1376</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1761</context>
<context context-type="linenumber">1757</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
@@ -3400,7 +3400,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1332</context>
<context context-type="linenumber">1329</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
@@ -3505,7 +3505,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1814</context>
<context context-type="linenumber">1808</context>
</context-group>
</trans-unit>
<trans-unit id="6661109599266152398" datatype="html">
@@ -3516,7 +3516,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1815</context>
<context context-type="linenumber">1809</context>
</context-group>
</trans-unit>
<trans-unit id="5162686434580248853" datatype="html">
@@ -3527,7 +3527,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1816</context>
<context context-type="linenumber">1810</context>
</context-group>
</trans-unit>
<trans-unit id="8157388568390631653" datatype="html">
@@ -5488,7 +5488,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1336</context>
<context context-type="linenumber">1333</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
@@ -7695,81 +7695,81 @@
<source>Error retrieving metadata</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">411</context>
<context context-type="linenumber">408</context>
</context-group>
</trans-unit>
<trans-unit id="2218903673684131427" datatype="html">
<source>An error occurred loading content: <x id="PH" equiv-text="err.message ?? err.toString()"/></source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">512,514</context>
<context context-type="linenumber">509,511</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">959,961</context>
<context context-type="linenumber">956,958</context>
</context-group>
</trans-unit>
<trans-unit id="6357361810318120957" datatype="html">
<source>Document was updated</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">632</context>
<context context-type="linenumber">629</context>
</context-group>
</trans-unit>
<trans-unit id="5154064822428631306" datatype="html">
<source>Document was updated at <x id="PH" equiv-text="formattedModified"/>.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">633</context>
<context context-type="linenumber">630</context>
</context-group>
</trans-unit>
<trans-unit id="8462497568316256794" datatype="html">
<source>Reload to discard your local unsaved edits and load the latest remote version.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">634</context>
<context context-type="linenumber">631</context>
</context-group>
</trans-unit>
<trans-unit id="7967484035994732534" datatype="html">
<source>Reload</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">636</context>
<context context-type="linenumber">633</context>
</context-group>
</trans-unit>
<trans-unit id="2907037627372942104" datatype="html">
<source>Document reloaded with latest changes.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">692</context>
<context context-type="linenumber">689</context>
</context-group>
</trans-unit>
<trans-unit id="6435639868943916539" datatype="html">
<source>Document reloaded.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">703</context>
<context context-type="linenumber">700</context>
</context-group>
</trans-unit>
<trans-unit id="6142395741265832184" datatype="html">
<source>Next document</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">805</context>
<context context-type="linenumber">802</context>
</context-group>
</trans-unit>
<trans-unit id="651985345816518480" datatype="html">
<source>Previous document</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">815</context>
<context context-type="linenumber">812</context>
</context-group>
</trans-unit>
<trans-unit id="2885986061416655600" datatype="html">
<source>Close document</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">823</context>
<context context-type="linenumber">820</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/services/open-documents.service.ts</context>
@@ -7780,67 +7780,67 @@
<source>Save document</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">830</context>
<context context-type="linenumber">827</context>
</context-group>
</trans-unit>
<trans-unit id="1784543155727940353" datatype="html">
<source>Save and close / next</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">839</context>
<context context-type="linenumber">836</context>
</context-group>
</trans-unit>
<trans-unit id="7427704425579737895" datatype="html">
<source>Error retrieving version content</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">943</context>
<context context-type="linenumber">940</context>
</context-group>
</trans-unit>
<trans-unit id="3456881259945295697" datatype="html">
<source>Error retrieving suggestions.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1000</context>
<context context-type="linenumber">997</context>
</context-group>
</trans-unit>
<trans-unit id="2194092841814123758" datatype="html">
<source>Document &quot;<x id="PH" equiv-text="newValues.title"/>&quot; saved successfully.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1212</context>
<context context-type="linenumber">1209</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1239</context>
<context context-type="linenumber">1236</context>
</context-group>
</trans-unit>
<trans-unit id="6626387786259219838" datatype="html">
<source>Error saving document &quot;<x id="PH" equiv-text="this.document.title"/>&quot;</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1245</context>
<context context-type="linenumber">1242</context>
</context-group>
</trans-unit>
<trans-unit id="448882439049417053" datatype="html">
<source>Error saving document</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1300</context>
<context context-type="linenumber">1297</context>
</context-group>
</trans-unit>
<trans-unit id="8410796510716511826" datatype="html">
<source>Do you really want to move the document &quot;<x id="PH" equiv-text="this.document.title"/>&quot; to the trash?</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1333</context>
<context context-type="linenumber">1330</context>
</context-group>
</trans-unit>
<trans-unit id="282586936710748252" datatype="html">
<source>Documents can be restored prior to permanent deletion.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1334</context>
<context context-type="linenumber">1331</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
@@ -7851,14 +7851,14 @@
<source>Error deleting document</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1355</context>
<context context-type="linenumber">1352</context>
</context-group>
</trans-unit>
<trans-unit id="619486176823357521" datatype="html">
<source>Reprocess confirm</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1375</context>
<context context-type="linenumber">1372</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
@@ -7869,102 +7869,102 @@
<source>This operation will permanently recreate the archive file for this document.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1376</context>
<context context-type="linenumber">1373</context>
</context-group>
</trans-unit>
<trans-unit id="302054111564709516" datatype="html">
<source>The archive file will be re-generated with the current settings.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1377</context>
<context context-type="linenumber">1374</context>
</context-group>
</trans-unit>
<trans-unit id="4700389117298802932" datatype="html">
<source>Reprocess operation for &quot;<x id="PH" equiv-text="this.document.title"/>&quot; will begin in the background.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1387</context>
<context context-type="linenumber">1384</context>
</context-group>
</trans-unit>
<trans-unit id="4409560272830824468" datatype="html">
<source>Error executing operation</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1398</context>
<context context-type="linenumber">1395</context>
</context-group>
</trans-unit>
<trans-unit id="6030453331794586802" datatype="html">
<source>Error downloading document</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1461</context>
<context context-type="linenumber">1458</context>
</context-group>
</trans-unit>
<trans-unit id="4458954481601077369" datatype="html">
<source>Page Fit</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1541</context>
<context context-type="linenumber">1538</context>
</context-group>
</trans-unit>
<trans-unit id="4663705961777238777" datatype="html">
<source>PDF edit operation for &quot;<x id="PH" equiv-text="this.document.title"/>&quot; will begin in the background.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1781</context>
<context context-type="linenumber">1775</context>
</context-group>
</trans-unit>
<trans-unit id="9043972994040261999" datatype="html">
<source>Error executing PDF edit operation</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1793</context>
<context context-type="linenumber">1787</context>
</context-group>
</trans-unit>
<trans-unit id="6172690334763056188" datatype="html">
<source>Please enter the current password before attempting to remove it.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1804</context>
<context context-type="linenumber">1798</context>
</context-group>
</trans-unit>
<trans-unit id="968660764814228922" datatype="html">
<source>Password removal operation for &quot;<x id="PH" equiv-text="this.document.title"/>&quot; will begin in the background.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1838</context>
<context context-type="linenumber">1830</context>
</context-group>
</trans-unit>
<trans-unit id="2282118435712883014" datatype="html">
<source>Error executing password removal operation</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1852</context>
<context context-type="linenumber">1844</context>
</context-group>
</trans-unit>
<trans-unit id="3740891324955700797" datatype="html">
<source>Print failed.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1891</context>
<context context-type="linenumber">1883</context>
</context-group>
</trans-unit>
<trans-unit id="6457245677384603573" datatype="html">
<source>Error loading document for printing.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1903</context>
<context context-type="linenumber">1895</context>
</context-group>
</trans-unit>
<trans-unit id="6085793215710522488" datatype="html">
<source>An error occurred loading tiff: <x id="PH" equiv-text="err.toString()"/></source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1968</context>
<context context-type="linenumber">1960</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1972</context>
<context context-type="linenumber">1964</context>
</context-group>
</trans-unit>
<trans-unit id="4958946940233632319" datatype="html">

View File

@@ -3,7 +3,6 @@ import { provideHttpClientTesting } from '@angular/common/http/testing'
import { ComponentFixture, TestBed } from '@angular/core/testing'
import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
import { NgxBootstrapIconsModule, allIcons } from 'ngx-bootstrap-icons'
import { DocumentService } from 'src/app/services/rest/document.service'
import { PDFEditorComponent } from './pdf-editor.component'
describe('PDFEditorComponent', () => {
@@ -140,16 +139,4 @@ describe('PDFEditorComponent', () => {
expect(component.pages[1].page).toBe(2)
expect(component.pages[2].page).toBe(3)
})
it('should include selected version in preview source when provided', () => {
const documentService = TestBed.inject(DocumentService)
const previewSpy = jest
.spyOn(documentService, 'getPreviewUrl')
.mockReturnValue('preview-version')
component.documentID = 3
component.versionID = 10
expect(component.pdfSrc).toBe('preview-version')
expect(previewSpy).toHaveBeenCalledWith(3, false, 10)
})
})

View File

@@ -46,7 +46,6 @@ export class PDFEditorComponent extends ConfirmDialogComponent {
activeModal: NgbActiveModal = inject(NgbActiveModal)
documentID: number
versionID?: number
pages: PageOperation[] = []
totalPages = 0
editMode: PdfEditorEditMode = this.settingsService.get(
@@ -56,11 +55,7 @@ export class PDFEditorComponent extends ConfirmDialogComponent {
includeMetadata: boolean = true
get pdfSrc(): string {
return this.documentService.getPreviewUrl(
this.documentID,
false,
this.versionID
)
return this.documentService.getPreviewUrl(this.documentID)
}
pdfLoaded(pdf: PngxPdfDocumentProxy) {

View File

@@ -1661,25 +1661,22 @@ describe('DocumentDetailComponent', () => {
const closeSpy = jest.spyOn(openDocumentsService, 'closeDocument')
const errorSpy = jest.spyOn(toastService, 'showError')
initNormally()
component.selectedVersionId = 10
component.editPdf()
expect(modal).not.toBeUndefined()
modal.componentInstance.documentID = doc.id
expect(modal.componentInstance.versionID).toBe(10)
modal.componentInstance.pages = [{ page: 1, rotate: 0, splitAfter: false }]
modal.componentInstance.confirm()
let req = httpTestingController.expectOne(
`${environment.apiBaseUrl}documents/bulk_edit/`
)
expect(req.request.body).toEqual({
documents: [10],
documents: [doc.id],
method: 'edit_pdf',
parameters: {
operations: [{ page: 1, rotate: 0, doc: 0 }],
delete_original: false,
update_document: false,
include_metadata: true,
source_mode: 'explicit_selection',
},
})
req.error(new ErrorEvent('failed'))
@@ -1701,7 +1698,6 @@ describe('DocumentDetailComponent', () => {
let modal: NgbModalRef
modalService.activeInstances.subscribe((m) => (modal = m[0]))
initNormally()
component.selectedVersionId = 10
component.password = 'secret'
component.removePassword()
const dialog =
@@ -1714,14 +1710,13 @@ describe('DocumentDetailComponent', () => {
`${environment.apiBaseUrl}documents/bulk_edit/`
)
expect(req.request.body).toEqual({
documents: [10],
documents: [doc.id],
method: 'remove_password',
parameters: {
password: 'secret',
update_document: false,
include_metadata: false,
delete_original: true,
source_mode: 'explicit_selection',
},
})
req.flush(true)

View File

@@ -74,10 +74,7 @@ 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 {
BulkEditSourceMode,
DocumentService,
} from 'src/app/services/rest/document.service'
import { DocumentService } from 'src/app/services/rest/document.service'
import { SavedViewService } from 'src/app/services/rest/saved-view.service'
import { StoragePathService } from 'src/app/services/rest/storage-path.service'
import { TagService } from 'src/app/services/rest/tag.service'
@@ -1756,23 +1753,20 @@ export class DocumentDetailComponent
size: 'xl',
scrollable: true,
})
const sourceDocumentId = this.selectedVersionId ?? this.document.id
modal.componentInstance.title = $localize`PDF Editor`
modal.componentInstance.btnCaption = $localize`Proceed`
modal.componentInstance.documentID = this.document.id
modal.componentInstance.versionID = sourceDocumentId
modal.componentInstance.confirmClicked
.pipe(takeUntil(this.unsubscribeNotifier))
.subscribe(() => {
modal.componentInstance.buttonsEnabled = false
this.documentsService
.bulkEdit([sourceDocumentId], 'edit_pdf', {
.bulkEdit([this.document.id], 'edit_pdf', {
operations: modal.componentInstance.getOperations(),
delete_original: modal.componentInstance.deleteOriginal,
update_document:
modal.componentInstance.editMode == PdfEditorEditMode.Update,
include_metadata: modal.componentInstance.includeMetadata,
source_mode: BulkEditSourceMode.EXPLICIT_SELECTION,
})
.pipe(first(), takeUntil(this.unsubscribeNotifier))
.subscribe({
@@ -1818,18 +1812,16 @@ export class DocumentDetailComponent
modal.componentInstance.confirmClicked
.pipe(takeUntil(this.unsubscribeNotifier))
.subscribe(() => {
const sourceDocumentId = this.selectedVersionId ?? this.document.id
const dialog =
modal.componentInstance as PasswordRemovalConfirmDialogComponent
dialog.buttonsEnabled = false
this.networkActive = true
this.documentsService
.bulkEdit([sourceDocumentId], 'remove_password', {
.bulkEdit([this.document.id], 'remove_password', {
password: this.password,
update_document: dialog.updateDocument,
include_metadata: dialog.includeMetadata,
delete_original: dialog.deleteOriginal,
source_mode: BulkEditSourceMode.EXPLICIT_SELECTION,
})
.pipe(first(), takeUntil(this.unsubscribeNotifier))
.subscribe({

View File

@@ -37,11 +37,6 @@ export interface SelectionData {
selected_custom_fields: SelectionDataItem[]
}
export enum BulkEditSourceMode {
LATEST_VERSION = 'latest_version',
EXPLICIT_SELECTION = 'explicit_selection',
}
@Injectable({
providedIn: 'root',
})

View File

@@ -29,21 +29,12 @@ from documents.plugins.helpers import DocumentsStatusManager
from documents.tasks import bulk_update_documents
from documents.tasks import consume_file
from documents.tasks import update_document_content_maybe_archive_file
from documents.versioning import get_latest_version_for_root
from documents.versioning import get_root_document
if TYPE_CHECKING:
from django.contrib.auth.models import User
logger: logging.Logger = logging.getLogger("paperless.bulk_edit")
SourceMode = Literal["latest_version", "explicit_selection"]
class SourceModeChoices:
LATEST_VERSION: SourceMode = "latest_version"
EXPLICIT_SELECTION: SourceMode = "explicit_selection"
@shared_task(bind=True)
def restore_archive_serial_numbers_task(
@@ -81,21 +72,46 @@ def restore_archive_serial_numbers(backup: dict[int, int | None]) -> None:
logger.info(f"Restored archive serial numbers for documents {list(backup.keys())}")
def _resolve_root_and_source_doc(
doc: Document,
*,
source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
) -> tuple[Document, Document]:
root_doc = get_root_document(doc)
def _get_root_ids_by_doc_id(doc_ids: list[int]) -> dict[int, int]:
"""
Resolve each provided document id to its root document id.
if source_mode == SourceModeChoices.EXPLICIT_SELECTION:
return root_doc, doc
- If the id is already a root document: root id is itself.
- If the id is a version document: root id is its `root_document_id`.
"""
qs = Document.objects.filter(id__in=doc_ids).only("id", "root_document_id")
return {doc.id: doc.root_document_id or doc.id for doc in qs}
# Version IDs are explicit by default, only a selected root resolves to latest
if doc.root_document_id is not None:
return root_doc, doc
return root_doc, get_latest_version_for_root(root_doc)
def _get_root_and_current_docs_by_root_id(
root_ids: set[int],
) -> tuple[dict[int, Document], dict[int, Document]]:
"""
Returns:
- root_docs: root_id -> root Document
- current_docs: root_id -> newest version Document (or root if none)
"""
root_docs = {
doc.id: doc
for doc in Document.objects.filter(id__in=root_ids).select_related(
"owner",
)
}
latest_versions_by_root_id: dict[int, Document] = {}
for version_doc in Document.objects.filter(root_document_id__in=root_ids).order_by(
"root_document_id",
"-id",
):
root_id = version_doc.root_document_id
if root_id is None:
continue
latest_versions_by_root_id.setdefault(root_id, version_doc)
current_docs: dict[int, Document] = {
root_id: latest_versions_by_root_id.get(root_id, root_docs[root_id])
for root_id in root_docs
}
return root_docs, current_docs
def set_correspondent(
@@ -405,32 +421,21 @@ def rotate(
doc_ids: list[int],
degrees: int,
*,
source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
user: User | None = None,
) -> Literal["OK"]:
logger.info(
f"Attempting to rotate {len(doc_ids)} documents by {degrees} degrees.",
)
docs_by_id = {
doc.id: doc
for doc in Document.objects.select_related("root_document").filter(
id__in=doc_ids,
)
}
docs_by_root_id: dict[int, tuple[Document, Document]] = {}
for doc_id in doc_ids:
doc = docs_by_id.get(doc_id)
if doc is None:
continue
root_doc, source_doc = _resolve_root_and_source_doc(
doc,
source_mode=source_mode,
)
docs_by_root_id.setdefault(root_doc.id, (root_doc, source_doc))
doc_to_root_id = _get_root_ids_by_doc_id(doc_ids)
root_ids = set(doc_to_root_id.values())
root_docs_by_id, current_docs_by_root_id = _get_root_and_current_docs_by_root_id(
root_ids,
)
import pikepdf
for root_doc, source_doc in docs_by_root_id.values():
for root_id in root_ids:
root_doc = root_docs_by_id[root_id]
source_doc = current_docs_by_root_id[root_id]
if source_doc.mime_type != "application/pdf":
logger.warning(
f"Document {root_doc.id} is not a PDF, skipping rotation.",
@@ -476,14 +481,12 @@ def merge(
metadata_document_id: int | None = None,
delete_originals: bool = False,
archive_fallback: bool = False,
source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
user: User | None = None,
) -> Literal["OK"]:
logger.info(
f"Attempting to merge {len(doc_ids)} documents into a single document.",
)
qs = Document.objects.select_related("root_document").filter(id__in=doc_ids)
docs_by_id = {doc.id: doc for doc in qs}
qs = Document.objects.filter(id__in=doc_ids)
affected_docs: list[int] = []
import pikepdf
@@ -492,20 +495,14 @@ def merge(
handoff_asn: int | None = None
# use doc_ids to preserve order
for doc_id in doc_ids:
doc = docs_by_id.get(doc_id)
if doc is None:
continue
_, source_doc = _resolve_root_and_source_doc(
doc,
source_mode=source_mode,
)
doc = qs.get(id=doc_id)
try:
doc_path = (
source_doc.archive_path
doc.archive_path
if archive_fallback
and source_doc.mime_type != "application/pdf"
and source_doc.has_archive_version
else source_doc.source_path
and doc.mime_type != "application/pdf"
and doc.has_archive_version
else doc.source_path
)
with pikepdf.open(str(doc_path)) as pdf:
version = max(version, pdf.pdf_version)
@@ -587,23 +584,18 @@ def split(
pages: list[list[int]],
*,
delete_originals: bool = False,
source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
user: User | None = None,
) -> Literal["OK"]:
logger.info(
f"Attempting to split document {doc_ids[0]} into {len(pages)} documents",
)
doc = Document.objects.select_related("root_document").get(id=doc_ids[0])
_, source_doc = _resolve_root_and_source_doc(
doc,
source_mode=source_mode,
)
doc = Document.objects.get(id=doc_ids[0])
import pikepdf
consume_tasks = []
try:
with pikepdf.open(source_doc.source_path) as pdf:
with pikepdf.open(doc.source_path) as pdf:
for idx, split_doc in enumerate(pages):
dst: pikepdf.Pdf = pikepdf.new()
for page in split_doc:
@@ -667,17 +659,25 @@ def delete_pages(
doc_ids: list[int],
pages: list[int],
*,
source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
user: User | None = None,
) -> Literal["OK"]:
logger.info(
f"Attempting to delete pages {pages} from {len(doc_ids)} documents",
)
doc = Document.objects.select_related("root_document").get(id=doc_ids[0])
root_doc, source_doc = _resolve_root_and_source_doc(
doc,
source_mode=source_mode,
root_doc: Document
if doc.root_document_id is None or doc.root_document is None:
root_doc = doc
else:
root_doc = doc.root_document
source_doc = (
Document.objects.filter(Q(id=root_doc.id) | Q(root_document=root_doc))
.order_by("-id")
.first()
)
if source_doc is None:
source_doc = root_doc
pages = sorted(pages) # sort pages to avoid index issues
import pikepdf
@@ -722,7 +722,6 @@ def edit_pdf(
delete_original: bool = False,
update_document: bool = False,
include_metadata: bool = True,
source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
user: User | None = None,
) -> Literal["OK"]:
"""
@@ -737,10 +736,19 @@ def edit_pdf(
f"Editing PDF of document {doc_ids[0]} with {len(operations)} operations",
)
doc = Document.objects.select_related("root_document").get(id=doc_ids[0])
root_doc, source_doc = _resolve_root_and_source_doc(
doc,
source_mode=source_mode,
root_doc: Document
if doc.root_document_id is None or doc.root_document is None:
root_doc = doc
else:
root_doc = doc.root_document
source_doc = (
Document.objects.filter(Q(id=root_doc.id) | Q(root_document=root_doc))
.order_by("-id")
.first()
)
if source_doc is None:
source_doc = root_doc
import pikepdf
pdf_docs: list[pikepdf.Pdf] = []
@@ -851,7 +859,6 @@ def remove_password(
update_document: bool = False,
delete_original: bool = False,
include_metadata: bool = True,
source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
user: User | None = None,
) -> Literal["OK"]:
"""
@@ -861,10 +868,19 @@ def remove_password(
for doc_id in doc_ids:
doc = Document.objects.select_related("root_document").get(id=doc_id)
root_doc, source_doc = _resolve_root_and_source_doc(
doc,
source_mode=source_mode,
root_doc: Document
if doc.root_document_id is None or doc.root_document is None:
root_doc = doc
else:
root_doc = doc.root_document
source_doc = (
Document.objects.filter(Q(id=root_doc.id) | Q(root_document=root_doc))
.order_by("-id")
.first()
)
if source_doc is None:
source_doc = root_doc
try:
logger.info(
f"Attempting password removal from document {doc_ids[0]}",

View File

@@ -1,5 +1,4 @@
import datetime
import hashlib
import os
import tempfile
from enum import StrEnum
@@ -48,6 +47,7 @@ from documents.signals import document_consumption_started
from documents.signals import document_updated
from documents.signals.handlers import run_workflows
from documents.templating.workflows import parse_w_workflow_placeholders
from documents.utils import compute_checksum
from documents.utils import copy_basic_file_stats
from documents.utils import copy_file_with_basic_stats
from documents.utils import run_subprocess
@@ -196,9 +196,7 @@ class ConsumerPlugin(
version_doc = Document(
root_document=root_doc_frozen,
version_index=next_version_index + 1,
checksum=hashlib.md5(
file_for_checksum.read_bytes(),
).hexdigest(),
checksum=compute_checksum(file_for_checksum),
content=text or "",
page_count=page_count,
mime_type=mime_type,
@@ -656,10 +654,9 @@ class ConsumerPlugin(
document.archive_path,
)
with Path(archive_path).open("rb") as f:
document.archive_checksum = hashlib.md5(
f.read(),
).hexdigest()
document.archive_checksum = compute_checksum(
Path(archive_path),
)
# Don't save with the lock active. Saving will cause the file
# renaming logic to acquire the lock as well.
@@ -800,7 +797,7 @@ class ConsumerPlugin(
title=title[:127],
content=text,
mime_type=mime_type,
checksum=hashlib.md5(file_for_checksum.read_bytes()).hexdigest(),
checksum=compute_checksum(file_for_checksum),
created=create_date,
modified=create_date,
page_count=page_count,
@@ -917,10 +914,9 @@ class ConsumerPreflightPlugin(
def pre_check_duplicate(self) -> None:
"""
Using the MD5 of the file, check this exact file doesn't already exist
Using the SHA256 of the file, check this exact file doesn't already exist
"""
with Path(self.input_doc.original_file).open("rb") as f:
checksum = hashlib.md5(f.read()).hexdigest()
checksum = compute_checksum(Path(self.input_doc.original_file))
existing_doc = Document.global_objects.filter(
Q(checksum=checksum) | Q(archive_checksum=checksum),
)

View File

@@ -58,6 +58,7 @@ from documents.models import WorkflowTrigger
from documents.settings import EXPORTER_ARCHIVE_NAME
from documents.settings import EXPORTER_FILE_NAME
from documents.settings import EXPORTER_THUMBNAIL_NAME
from documents.utils import compute_checksum
from documents.utils import copy_file_with_basic_stats
from paperless import version
from paperless.models import ApplicationConfiguration
@@ -549,14 +550,14 @@ class Command(CryptMixin, BaseCommand):
if target in self.files_in_export_dir:
self.files_in_export_dir.remove(target)
if self.compare_json:
target_checksum = hashlib.md5(target.read_bytes()).hexdigest()
target_checksum = compute_checksum(target)
src_str = json.dumps(
content,
cls=DjangoJSONEncoder,
indent=2,
ensure_ascii=False,
)
src_checksum = hashlib.md5(src_str.encode("utf-8")).hexdigest()
src_checksum = hashlib.sha256(src_str.encode("utf-8")).hexdigest()
if src_checksum == target_checksum:
perform_write = False
@@ -592,7 +593,7 @@ class Command(CryptMixin, BaseCommand):
source_stat = source.stat()
target_stat = target.stat()
if self.compare_checksums and source_checksum:
target_checksum = hashlib.md5(target.read_bytes()).hexdigest()
target_checksum = compute_checksum(target)
perform_copy = target_checksum != source_checksum
elif (
source_stat.st_mtime != target_stat.st_mtime

View File

@@ -0,0 +1,130 @@
import hashlib
import logging
from pathlib import Path
from django.conf import settings
from django.db import migrations
from django.db import models
logger = logging.getLogger("paperless.migrations")
_CHUNK_SIZE = 65536 # 64 KiB — avoids loading entire files into memory
_BATCH_SIZE = 500 # documents per bulk_update call
_PROGRESS_INTERVAL = 500 # log a progress line every N documents
def _sha256(path: Path) -> str:
h = hashlib.sha256()
with path.open("rb") as fh:
while chunk := fh.read(_CHUNK_SIZE):
h.update(chunk)
return h.hexdigest()
def recompute_checksums(apps, schema_editor):
"""Recompute all document checksums from MD5 to SHA256."""
Document = apps.get_model("documents", "Document")
total = Document.objects.count()
if total == 0:
return
logger.info("Recomputing SHA-256 checksums for %d document(s)...", total)
batch: list = []
processed = 0
for doc in Document.objects.only(
"pk",
"filename",
"checksum",
"archive_filename",
"archive_checksum",
).iterator(chunk_size=_BATCH_SIZE):
updated_fields: list[str] = []
# Reconstruct source path the same way Document.source_path does
fname = str(doc.filename) if doc.filename else f"{doc.pk:07}.pdf"
source_path = (settings.ORIGINALS_DIR / Path(fname)).resolve()
if source_path.exists():
doc.checksum = _sha256(source_path)
updated_fields.append("checksum")
else:
logger.warning(
"Document %s: original file %s not found, checksum not updated.",
doc.pk,
source_path,
)
# Mirror Document.has_archive_version: archive_filename is not None
if doc.archive_filename is not None:
archive_path = (
settings.ARCHIVE_DIR / Path(str(doc.archive_filename))
).resolve()
if archive_path.exists():
doc.archive_checksum = _sha256(archive_path)
updated_fields.append("archive_checksum")
else:
logger.warning(
"Document %s: archive file %s not found, checksum not updated.",
doc.pk,
archive_path,
)
if updated_fields:
batch.append(doc)
processed += 1
if len(batch) >= _BATCH_SIZE:
Document.objects.bulk_update(batch, ["checksum", "archive_checksum"])
batch.clear()
if processed % _PROGRESS_INTERVAL == 0:
logger.info(
"SHA-256 checksum progress: %d/%d (%d%%)",
processed,
total,
processed * 100 // total,
)
if batch:
Document.objects.bulk_update(batch, ["checksum", "archive_checksum"])
logger.info(
"SHA-256 checksum recomputation complete: %d document(s) processed.",
total,
)
class Migration(migrations.Migration):
dependencies = [
("documents", "0016_document_version_index_and_more"),
]
operations = [
migrations.AlterField(
model_name="document",
name="checksum",
field=models.CharField(
editable=False,
help_text="The checksum of the original document.",
max_length=64,
verbose_name="checksum",
),
),
migrations.AlterField(
model_name="document",
name="archive_checksum",
field=models.CharField(
blank=True,
editable=False,
help_text="The checksum of the archived document.",
max_length=64,
null=True,
verbose_name="archive checksum",
),
),
migrations.RunPython(recompute_checksums, migrations.RunPython.noop),
]

View File

@@ -216,14 +216,14 @@ class Document(SoftDeleteModel, ModelWithOwner): # type: ignore[django-manager-
checksum = models.CharField(
_("checksum"),
max_length=32,
max_length=64,
editable=False,
help_text=_("The checksum of the original document."),
)
archive_checksum = models.CharField(
_("archive checksum"),
max_length=32,
max_length=64,
editable=False,
blank=True,
null=True,

View File

@@ -11,7 +11,6 @@ is an identity function that adds no overhead.
from __future__ import annotations
import hashlib
import logging
import uuid
from collections import defaultdict
@@ -30,6 +29,7 @@ from django.utils import timezone
from documents.models import Document
from documents.models import PaperlessTask
from documents.utils import compute_checksum
from paperless.config import GeneralConfig
logger = logging.getLogger("paperless.sanity_checker")
@@ -218,7 +218,7 @@ def _check_original(
present_files.discard(source_path)
try:
checksum = hashlib.md5(source_path.read_bytes()).hexdigest()
checksum = compute_checksum(source_path)
except OSError as e:
messages.error(doc.pk, f"Cannot read original file of document: {e}")
else:
@@ -255,7 +255,7 @@ def _check_archive(
present_files.discard(archive_path)
try:
checksum = hashlib.md5(archive_path.read_bytes()).hexdigest()
checksum = compute_checksum(archive_path)
except OSError as e:
messages.error(
doc.pk,

View File

@@ -1723,15 +1723,6 @@ class BulkEditSerializer(
except ValueError:
raise serializers.ValidationError("invalid rotation degrees")
def _validate_source_mode(self, parameters) -> None:
source_mode = parameters.get(
"source_mode",
bulk_edit.SourceModeChoices.LATEST_VERSION,
)
if source_mode not in bulk_edit.SourceModeChoices.__dict__.values():
raise serializers.ValidationError("Invalid source_mode")
parameters["source_mode"] = source_mode
def _validate_parameters_split(self, parameters) -> None:
if "pages" not in parameters:
raise serializers.ValidationError("pages not specified")
@@ -1832,9 +1823,6 @@ class BulkEditSerializer(
method = attrs["method"]
parameters = attrs["parameters"]
if "source_mode" in parameters:
self._validate_source_mode(parameters)
if method == bulk_edit.set_correspondent:
self._validate_parameters_correspondent(parameters)
elif method == bulk_edit.set_document_type:

View File

@@ -1,5 +1,4 @@
import datetime
import hashlib
import logging
import shutil
import uuid
@@ -63,6 +62,7 @@ from documents.signals import document_updated
from documents.signals.handlers import cleanup_document_deletion
from documents.signals.handlers import run_workflows
from documents.signals.handlers import send_websocket_document_updated
from documents.utils import compute_checksum
from documents.workflows.utils import get_workflows_for_trigger
from paperless.config import AIConfig
from paperless_ai.indexing import llm_index_add_or_update_document
@@ -323,8 +323,7 @@ def update_document_content_maybe_archive_file(document_id) -> None:
with transaction.atomic():
oldDocument = Document.objects.get(pk=document.pk)
if parser.get_archive_path():
with Path(parser.get_archive_path()).open("rb") as f:
checksum = hashlib.md5(f.read()).hexdigest()
checksum = compute_checksum(Path(parser.get_archive_path()))
# I'm going to save first so that in case the file move
# fails, the database is rolled back.
# We also don't use save() since that triggers the filehandling

View File

@@ -82,8 +82,8 @@ def sample_doc(
return DocumentFactory(
title="test",
checksum="42995833e01aea9b3edee44bbfdd7ce1",
archive_checksum="62acb0bcbfbcaa62ca6ad3668e4e404b",
checksum="1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
archive_checksum="706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
content="test content",
pk=1,
filename="0000001.pdf",

View File

@@ -60,7 +60,7 @@ class DocumentFactory(DjangoModelFactory):
model = Document
title = factory.Faker("sentence", nb_words=4)
checksum = factory.Faker("md5")
checksum = factory.Faker("sha256")
content = factory.Faker("paragraph")
correspondent = None
document_type = None

View File

@@ -1395,10 +1395,7 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
{
"documents": [self.doc2.id],
"method": "edit_pdf",
"parameters": {
"operations": [{"page": 1}],
"source_mode": "explicit_selection",
},
"parameters": {"operations": [{"page": 1}]},
},
),
content_type="application/json",
@@ -1410,7 +1407,6 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
args, kwargs = m.call_args
self.assertCountEqual(args[0], [self.doc2.id])
self.assertEqual(kwargs["operations"], [{"page": 1}])
self.assertEqual(kwargs["source_mode"], "explicit_selection")
self.assertEqual(kwargs["user"], self.user)
def test_edit_pdf_invalid_params(self) -> None:
@@ -1576,24 +1572,6 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
response.content,
)
# invalid source mode
response = self.client.post(
"/api/documents/bulk_edit/",
json.dumps(
{
"documents": [self.doc2.id],
"method": "edit_pdf",
"parameters": {
"operations": [{"page": 1}],
"source_mode": "not_a_mode",
},
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
self.assertIn(b"Invalid source_mode", response.content)
@mock.patch("documents.serialisers.bulk_edit.edit_pdf")
def test_edit_pdf_page_out_of_bounds(self, m) -> None:
"""

View File

@@ -405,9 +405,7 @@ class TestBulkEdit(DirectoriesMixin, TestCase):
self.assertTrue(Document.objects.filter(id=self.doc1.id).exists())
self.assertFalse(Document.objects.filter(id=version.id).exists())
def test_resolve_root_and_source_doc_latest_version_prefers_newest_version(
self,
) -> None:
def test_get_root_and_current_doc_mapping(self) -> None:
version1 = Document.objects.create(
checksum="B-v1",
title="B version 1",
@@ -419,14 +417,18 @@ class TestBulkEdit(DirectoriesMixin, TestCase):
root_document=self.doc2,
)
root_doc, source_doc = bulk_edit._resolve_root_and_source_doc(
self.doc2,
source_mode="latest_version",
root_ids_by_doc_id = bulk_edit._get_root_ids_by_doc_id(
[self.doc2.id, version1.id, version2.id],
)
self.assertEqual(root_ids_by_doc_id[self.doc2.id], self.doc2.id)
self.assertEqual(root_ids_by_doc_id[version1.id], self.doc2.id)
self.assertEqual(root_ids_by_doc_id[version2.id], self.doc2.id)
self.assertEqual(root_doc.id, self.doc2.id)
self.assertEqual(source_doc.id, version2.id)
self.assertNotEqual(source_doc.id, version1.id)
root_docs, current_docs = bulk_edit._get_root_and_current_docs_by_root_id(
{self.doc2.id},
)
self.assertEqual(root_docs[self.doc2.id].id, self.doc2.id)
self.assertEqual(current_docs[self.doc2.id].id, version2.id)
@mock.patch("documents.tasks.bulk_update_documents.delay")
def test_set_permissions(self, m) -> None:
@@ -660,33 +662,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
self.assertEqual(result, "OK")
@mock.patch("pikepdf.open")
@mock.patch("documents.tasks.consume_file.s")
def test_merge_uses_latest_version_source_for_root_selection(
self,
mock_consume_file,
mock_open_pdf,
) -> None:
version_file = self.dirs.scratch_dir / "sample2_version_merge.pdf"
shutil.copy(self.doc2.source_path, version_file)
version = Document.objects.create(
checksum="B-v1",
title="B version 1",
root_document=self.doc2,
filename=version_file,
mime_type="application/pdf",
)
fake_pdf = mock.MagicMock()
fake_pdf.pdf_version = "1.7"
fake_pdf.pages = [mock.Mock()]
mock_open_pdf.return_value.__enter__.return_value = fake_pdf
result = bulk_edit.merge([self.doc2.id])
self.assertEqual(result, "OK")
mock_open_pdf.assert_called_once_with(str(version.source_path))
mock_consume_file.assert_not_called()
@mock.patch("documents.bulk_edit.delete.si")
@mock.patch("documents.tasks.consume_file.s")
def test_merge_and_delete_originals(
@@ -895,36 +870,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
self.assertEqual(result, "OK")
@mock.patch("documents.bulk_edit.group")
@mock.patch("pikepdf.open")
@mock.patch("documents.tasks.consume_file.s")
def test_split_uses_latest_version_source_for_root_selection(
self,
mock_consume_file,
mock_open_pdf,
mock_group,
) -> None:
version_file = self.dirs.scratch_dir / "sample2_version_split.pdf"
shutil.copy(self.doc2.source_path, version_file)
version = Document.objects.create(
checksum="B-v1",
title="B version 1",
root_document=self.doc2,
filename=version_file,
mime_type="application/pdf",
)
fake_pdf = mock.MagicMock()
fake_pdf.pages = [mock.Mock(), mock.Mock()]
mock_open_pdf.return_value.__enter__.return_value = fake_pdf
mock_group.return_value.delay.return_value = None
result = bulk_edit.split([self.doc2.id], [[1], [2]])
self.assertEqual(result, "OK")
mock_open_pdf.assert_called_once_with(version.source_path)
mock_consume_file.assert_not_called()
mock_group.return_value.delay.assert_not_called()
@mock.patch("documents.bulk_edit.delete.si")
@mock.patch("documents.tasks.consume_file.s")
@mock.patch("documents.bulk_edit.chord")
@@ -1096,34 +1041,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
self.assertIsNotNone(overrides)
self.assertEqual(result, "OK")
@mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
@mock.patch("documents.tasks.consume_file.delay")
@mock.patch("pikepdf.open")
def test_rotate_explicit_selection_uses_root_source_when_root_selected(
self,
mock_open,
mock_consume_delay,
mock_magic,
):
Document.objects.create(
checksum="B-v1",
title="B version 1",
root_document=self.doc2,
)
fake_pdf = mock.MagicMock()
fake_pdf.pages = [mock.Mock()]
mock_open.return_value.__enter__.return_value = fake_pdf
result = bulk_edit.rotate(
[self.doc2.id],
90,
source_mode="explicit_selection",
)
self.assertEqual(result, "OK")
mock_open.assert_called_once_with(self.doc2.source_path)
mock_consume_delay.assert_called_once()
@mock.patch("documents.tasks.consume_file.delay")
@mock.patch("pikepdf.Pdf.save")
@mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
@@ -1148,34 +1065,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
self.assertIsNotNone(overrides)
self.assertEqual(result, "OK")
@mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
@mock.patch("documents.tasks.consume_file.delay")
@mock.patch("pikepdf.open")
def test_delete_pages_explicit_selection_uses_root_source_when_root_selected(
self,
mock_open,
mock_consume_delay,
mock_magic,
):
Document.objects.create(
checksum="B-v1",
title="B version 1",
root_document=self.doc2,
)
fake_pdf = mock.MagicMock()
fake_pdf.pages = [mock.Mock(), mock.Mock()]
mock_open.return_value.__enter__.return_value = fake_pdf
result = bulk_edit.delete_pages(
[self.doc2.id],
[1],
source_mode="explicit_selection",
)
self.assertEqual(result, "OK")
mock_open.assert_called_once_with(self.doc2.source_path)
mock_consume_delay.assert_called_once()
@mock.patch("documents.tasks.consume_file.delay")
@mock.patch("pikepdf.Pdf.save")
def test_delete_pages_with_error(self, mock_pdf_save, mock_consume_delay):
@@ -1324,40 +1213,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
self.assertTrue(str(consumable.original_file).endswith("_edited.pdf"))
self.assertIsNotNone(overrides)
@mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
@mock.patch("documents.tasks.consume_file.delay")
@mock.patch("pikepdf.new")
@mock.patch("pikepdf.open")
def test_edit_pdf_explicit_selection_uses_root_source_when_root_selected(
self,
mock_open,
mock_new,
mock_consume_delay,
mock_magic,
):
Document.objects.create(
checksum="B-v1",
title="B version 1",
root_document=self.doc2,
)
fake_pdf = mock.MagicMock()
fake_pdf.pages = [mock.Mock()]
mock_open.return_value.__enter__.return_value = fake_pdf
output_pdf = mock.MagicMock()
output_pdf.pages = []
mock_new.return_value = output_pdf
result = bulk_edit.edit_pdf(
[self.doc2.id],
operations=[{"page": 1}],
update_document=True,
source_mode="explicit_selection",
)
self.assertEqual(result, "OK")
mock_open.assert_called_once_with(self.doc2.source_path)
mock_consume_delay.assert_called_once()
@mock.patch("documents.bulk_edit.group")
@mock.patch("documents.tasks.consume_file.s")
def test_edit_pdf_without_metadata(
@@ -1478,34 +1333,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
self.assertEqual(consumable.root_document_id, doc.id)
self.assertIsNotNone(overrides)
@mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
@mock.patch("documents.tasks.consume_file.delay")
@mock.patch("pikepdf.open")
def test_remove_password_explicit_selection_uses_root_source_when_root_selected(
self,
mock_open,
mock_consume_delay,
mock_magic,
) -> None:
Document.objects.create(
checksum="A-v1",
title="A version 1",
root_document=self.doc1,
)
fake_pdf = mock.MagicMock()
mock_open.return_value.__enter__.return_value = fake_pdf
result = bulk_edit.remove_password(
[self.doc1.id],
password="secret",
update_document=True,
source_mode="explicit_selection",
)
self.assertEqual(result, "OK")
mock_open.assert_called_once_with(self.doc1.source_path, password="secret")
mock_consume_delay.assert_called_once()
@mock.patch("documents.bulk_edit.chord")
@mock.patch("documents.bulk_edit.group")
@mock.patch("documents.tasks.consume_file.s")

View File

@@ -245,8 +245,14 @@ class TestConsumer(
self.assertIsFile(document.archive_path)
self.assertEqual(document.checksum, "42995833e01aea9b3edee44bbfdd7ce1")
self.assertEqual(document.archive_checksum, "62acb0bcbfbcaa62ca6ad3668e4e404b")
self.assertEqual(
document.checksum,
"1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
)
self.assertEqual(
document.archive_checksum,
"706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
)
self.assertIsNotFile(filename)

View File

@@ -63,8 +63,8 @@ class TestExportImport(
self.d1 = Document.objects.create(
content="Content",
checksum="42995833e01aea9b3edee44bbfdd7ce1",
archive_checksum="62acb0bcbfbcaa62ca6ad3668e4e404b",
checksum="1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
archive_checksum="706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
title="wow1",
filename="0000001.pdf",
mime_type="application/pdf",
@@ -72,21 +72,21 @@ class TestExportImport(
)
self.d2 = Document.objects.create(
content="Content",
checksum="9c9691e51741c1f4f41a20896af31770",
checksum="550d1bae0f746d4f7c6be07054eb20cc2f11988a58ef64ceae45e98f85e92a5b",
title="wow2",
filename="0000002.pdf",
mime_type="application/pdf",
)
self.d3 = Document.objects.create(
content="Content",
checksum="d38d7ed02e988e072caf924e0f3fcb76",
checksum="f1ba6b7ff8548214a75adec228f5468a14fe187f445bc0b9485cbf1c35b15915",
title="wow2",
filename="0000003.pdf",
mime_type="application/pdf",
)
self.d4 = Document.objects.create(
content="Content",
checksum="82186aaa94f0b98697d704b90fd1c072",
checksum="a81b16b6b313cfd7e60eb7b12598d1343b58622b4030cfa19a2724a02e98db1b",
title="wow_dec",
filename="0000004.pdf",
mime_type="application/pdf",
@@ -240,7 +240,7 @@ class TestExportImport(
)
with Path(fname).open("rb") as f:
checksum = hashlib.md5(f.read()).hexdigest()
checksum = hashlib.sha256(f.read()).hexdigest()
self.assertEqual(checksum, element["fields"]["checksum"])
# Generated field "content_length" should not be exported,
@@ -254,7 +254,7 @@ class TestExportImport(
self.assertIsFile(fname)
with Path(fname).open("rb") as f:
checksum = hashlib.md5(f.read()).hexdigest()
checksum = hashlib.sha256(f.read()).hexdigest()
self.assertEqual(checksum, element["fields"]["archive_checksum"])
elif element["model"] == "documents.note":

View File

@@ -260,8 +260,8 @@ class TestCommandImport(
Document.objects.create(
content="Content",
checksum="42995833e01aea9b3edee44bbfdd7ce1",
archive_checksum="62acb0bcbfbcaa62ca6ad3668e4e404b",
checksum="1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
archive_checksum="706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
title="wow1",
filename="0000001.pdf",
mime_type="application/pdf",

View File

@@ -1,3 +1,4 @@
import hashlib
import logging
import shutil
from os import utime
@@ -128,3 +129,15 @@ def get_boolean(boolstr: str) -> bool:
Return a boolean value from a string representation.
"""
return bool(boolstr.lower() in ("yes", "y", "1", "t", "true"))
def compute_checksum(path: Path, chunk_size: int = 65536) -> str:
"""
Return the SHA256 hex digest of the file at *path*, reading in chunks
of *chunk_size* bytes to avoid loading the entire file into memory.
"""
h = hashlib.sha256()
with path.open("rb") as f:
while chunk := f.read(chunk_size):
h.update(chunk)
return h.hexdigest()

View File

@@ -2,7 +2,7 @@ msgid ""
msgstr ""
"Project-Id-Version: paperless-ngx\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2026-03-06 20:00+0000\n"
"POT-Creation-Date: 2026-03-04 23:29+0000\n"
"PO-Revision-Date: 2022-02-17 04:17\n"
"Last-Translator: \n"
"Language-Team: English\n"
@@ -1299,7 +1299,7 @@ msgstr ""
msgid "workflow runs"
msgstr ""
#: documents/serialisers.py:463 documents/serialisers.py:2344
#: documents/serialisers.py:463 documents/serialisers.py:2332
msgid "Insufficient permissions."
msgstr ""
@@ -1307,39 +1307,39 @@ msgstr ""
msgid "Invalid color."
msgstr ""
#: documents/serialisers.py:1967
#: documents/serialisers.py:1955
#, python-format
msgid "File type %(type)s not supported"
msgstr ""
#: documents/serialisers.py:2011
#: documents/serialisers.py:1999
#, python-format
msgid "Custom field id must be an integer: %(id)s"
msgstr ""
#: documents/serialisers.py:2018
#: documents/serialisers.py:2006
#, python-format
msgid "Custom field with id %(id)s does not exist"
msgstr ""
#: documents/serialisers.py:2035 documents/serialisers.py:2045
#: documents/serialisers.py:2023 documents/serialisers.py:2033
msgid ""
"Custom fields must be a list of integers or an object mapping ids to values."
msgstr ""
#: documents/serialisers.py:2040
#: documents/serialisers.py:2028
msgid "Some custom fields don't exist or were specified twice."
msgstr ""
#: documents/serialisers.py:2187
#: documents/serialisers.py:2175
msgid "Invalid variable detected."
msgstr ""
#: documents/serialisers.py:2400
#: documents/serialisers.py:2388
msgid "Duplicate document identifiers are not allowed."
msgstr ""
#: documents/serialisers.py:2430 documents/views.py:3328
#: documents/serialisers.py:2418 documents/views.py:3328
#, python-format
msgid "Documents not found: %(ids)s"
msgstr ""

115
uv.lock generated
View File

@@ -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 = "4.61.1"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/ec/ca/cf17b88a8df95691275a3d77dc0a5ad9907f328ae53acbe6795da1b2f5ed/fonttools-4.61.1.tar.gz", hash = "sha256:6675329885c44657f826ef01d9e4fb33b9158e9d93c537d84ad8399539bc6f69", size = 3565756, upload-time = "2025-12-12T17:31:24.246Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/69/12/bf9f4eaa2fad039356cc627587e30ed008c03f1cebd3034376b5ee8d1d44/fonttools-4.61.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:c6604b735bb12fef8e0efd5578c9fb5d3d8532d5001ea13a19cddf295673ee09", size = 2852213, upload-time = "2025-12-12T17:29:46.675Z" },
{ url = "https://files.pythonhosted.org/packages/ac/49/4138d1acb6261499bedde1c07f8c2605d1d8f9d77a151e5507fd3ef084b6/fonttools-4.61.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5ce02f38a754f207f2f06557523cd39a06438ba3aafc0639c477ac409fc64e37", size = 2401689, upload-time = "2025-12-12T17:29:48.769Z" },
{ url = "https://files.pythonhosted.org/packages/e5/fe/e6ce0fe20a40e03aef906af60aa87668696f9e4802fa283627d0b5ed777f/fonttools-4.61.1-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:77efb033d8d7ff233385f30c62c7c79271c8885d5c9657d967ede124671bbdfb", size = 5058809, upload-time = "2025-12-12T17:29:51.701Z" },
{ url = "https://files.pythonhosted.org/packages/79/61/1ca198af22f7dd22c17ab86e9024ed3c06299cfdb08170640e9996d501a0/fonttools-4.61.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:75c1a6dfac6abd407634420c93864a1e274ebc1c7531346d9254c0d8f6ca00f9", size = 5036039, upload-time = "2025-12-12T17:29:53.659Z" },
{ url = "https://files.pythonhosted.org/packages/99/cc/fa1801e408586b5fce4da9f5455af8d770f4fc57391cd5da7256bb364d38/fonttools-4.61.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:0de30bfe7745c0d1ffa2b0b7048fb7123ad0d71107e10ee090fa0b16b9452e87", size = 5034714, upload-time = "2025-12-12T17:29:55.592Z" },
{ url = "https://files.pythonhosted.org/packages/bf/aa/b7aeafe65adb1b0a925f8f25725e09f078c635bc22754f3fecb7456955b0/fonttools-4.61.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:58b0ee0ab5b1fc9921eccfe11d1435added19d6494dde14e323f25ad2bc30c56", size = 5158648, upload-time = "2025-12-12T17:29:57.861Z" },
{ url = "https://files.pythonhosted.org/packages/6f/16/7decaa24a1bd3a70c607b2e29f0adc6159f36a7e40eaba59846414765fd4/fonttools-4.61.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:f3cb4a569029b9f291f88aafc927dd53683757e640081ca8c412781ea144565e", size = 2851593, upload-time = "2025-12-12T17:30:04.225Z" },
{ url = "https://files.pythonhosted.org/packages/94/98/3c4cb97c64713a8cf499b3245c3bf9a2b8fd16a3e375feff2aed78f96259/fonttools-4.61.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:41a7170d042e8c0024703ed13b71893519a1a6d6e18e933e3ec7507a2c26a4b2", size = 2400231, upload-time = "2025-12-12T17:30:06.47Z" },
{ url = "https://files.pythonhosted.org/packages/b7/37/82dbef0f6342eb01f54bca073ac1498433d6ce71e50c3c3282b655733b31/fonttools-4.61.1-cp312-cp312-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:10d88e55330e092940584774ee5e8a6971b01fc2f4d3466a1d6c158230880796", size = 4954103, upload-time = "2025-12-12T17:30:08.432Z" },
{ url = "https://files.pythonhosted.org/packages/6c/44/f3aeac0fa98e7ad527f479e161aca6c3a1e47bb6996b053d45226fe37bf2/fonttools-4.61.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:15acc09befd16a0fb8a8f62bc147e1a82817542d72184acca9ce6e0aeda9fa6d", size = 5004295, upload-time = "2025-12-12T17:30:10.56Z" },
{ url = "https://files.pythonhosted.org/packages/14/e8/7424ced75473983b964d09f6747fa09f054a6d656f60e9ac9324cf40c743/fonttools-4.61.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e6bcdf33aec38d16508ce61fd81838f24c83c90a1d1b8c68982857038673d6b8", size = 4944109, upload-time = "2025-12-12T17:30:12.874Z" },
{ url = "https://files.pythonhosted.org/packages/c8/8b/6391b257fa3d0b553d73e778f953a2f0154292a7a7a085e2374b111e5410/fonttools-4.61.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:5fade934607a523614726119164ff621e8c30e8fa1ffffbbd358662056ba69f0", size = 5093598, upload-time = "2025-12-12T17:30:15.79Z" },
{ url = "https://files.pythonhosted.org/packages/4b/cf/00ba28b0990982530addb8dc3e9e6f2fa9cb5c20df2abdda7baa755e8fe1/fonttools-4.61.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:8c56c488ab471628ff3bfa80964372fc13504ece601e0d97a78ee74126b2045c", size = 2846454, upload-time = "2025-12-12T17:30:24.938Z" },
{ url = "https://files.pythonhosted.org/packages/5a/ca/468c9a8446a2103ae645d14fee3f610567b7042aba85031c1c65e3ef7471/fonttools-4.61.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:dc492779501fa723b04d0ab1f5be046797fee17d27700476edc7ee9ae535a61e", size = 2398191, upload-time = "2025-12-12T17:30:27.343Z" },
{ url = "https://files.pythonhosted.org/packages/a3/4b/d67eedaed19def5967fade3297fed8161b25ba94699efc124b14fb68cdbc/fonttools-4.61.1-cp313-cp313-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:64102ca87e84261419c3747a0d20f396eb024bdbeb04c2bfb37e2891f5fadcb5", size = 4928410, upload-time = "2025-12-12T17:30:29.771Z" },
{ url = "https://files.pythonhosted.org/packages/b0/8d/6fb3494dfe61a46258cd93d979cf4725ded4eb46c2a4ca35e4490d84daea/fonttools-4.61.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4c1b526c8d3f615a7b1867f38a9410849c8f4aef078535742198e942fba0e9bd", size = 4984460, upload-time = "2025-12-12T17:30:32.073Z" },
{ url = "https://files.pythonhosted.org/packages/f7/f1/a47f1d30b3dc00d75e7af762652d4cbc3dff5c2697a0dbd5203c81afd9c3/fonttools-4.61.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:41ed4b5ec103bd306bb68f81dc166e77409e5209443e5773cb4ed837bcc9b0d3", size = 4925800, upload-time = "2025-12-12T17:30:34.339Z" },
{ url = "https://files.pythonhosted.org/packages/a7/01/e6ae64a0981076e8a66906fab01539799546181e32a37a0257b77e4aa88b/fonttools-4.61.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:b501c862d4901792adaec7c25b1ecc749e2662543f68bb194c42ba18d6eec98d", size = 5067859, upload-time = "2025-12-12T17:30:36.593Z" },
{ url = "https://files.pythonhosted.org/packages/32/8f/4e7bf82c0cbb738d3c2206c920ca34ca74ef9dabde779030145d28665104/fonttools-4.61.1-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:fff4f534200a04b4a36e7ae3cb74493afe807b517a09e99cb4faa89a34ed6ecd", size = 2846094, upload-time = "2025-12-12T17:30:43.511Z" },
{ url = "https://files.pythonhosted.org/packages/71/09/d44e45d0a4f3a651f23a1e9d42de43bc643cce2971b19e784cc67d823676/fonttools-4.61.1-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:d9203500f7c63545b4ce3799319fe4d9feb1a1b89b28d3cb5abd11b9dd64147e", size = 2396589, upload-time = "2025-12-12T17:30:45.681Z" },
{ url = "https://files.pythonhosted.org/packages/89/18/58c64cafcf8eb677a99ef593121f719e6dcbdb7d1c594ae5a10d4997ca8a/fonttools-4.61.1-cp314-cp314-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:fa646ecec9528bef693415c79a86e733c70a4965dd938e9a226b0fc64c9d2e6c", size = 4877892, upload-time = "2025-12-12T17:30:47.709Z" },
{ url = "https://files.pythonhosted.org/packages/8a/ec/9e6b38c7ba1e09eb51db849d5450f4c05b7e78481f662c3b79dbde6f3d04/fonttools-4.61.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:11f35ad7805edba3aac1a3710d104592df59f4b957e30108ae0ba6c10b11dd75", size = 4972884, upload-time = "2025-12-12T17:30:49.656Z" },
{ url = "https://files.pythonhosted.org/packages/5e/87/b5339da8e0256734ba0dbbf5b6cdebb1dd79b01dc8c270989b7bcd465541/fonttools-4.61.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:b931ae8f62db78861b0ff1ac017851764602288575d65b8e8ff1963fed419063", size = 4924405, upload-time = "2025-12-12T17:30:51.735Z" },
{ url = "https://files.pythonhosted.org/packages/0b/47/e3409f1e1e69c073a3a6fd8cb886eb18c0bae0ee13db2c8d5e7f8495e8b7/fonttools-4.61.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:b148b56f5de675ee16d45e769e69f87623a4944f7443850bf9a9376e628a89d2", size = 5035553, upload-time = "2025-12-12T17:30:54.823Z" },
{ url = "https://files.pythonhosted.org/packages/39/5c/908ad78e46c61c3e3ed70c3b58ff82ab48437faf84ec84f109592cabbd9f/fonttools-4.61.1-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:e76ce097e3c57c4bcb67c5aa24a0ecdbd9f74ea9219997a707a4061fbe2707aa", size = 2929571, upload-time = "2025-12-12T17:31:02.574Z" },
{ url = "https://files.pythonhosted.org/packages/bd/41/975804132c6dea64cdbfbaa59f3518a21c137a10cccf962805b301ac6ab2/fonttools-4.61.1-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:9cfef3ab326780c04d6646f68d4b4742aae222e8b8ea1d627c74e38afcbc9d91", size = 2435317, upload-time = "2025-12-12T17:31:04.974Z" },
{ url = "https://files.pythonhosted.org/packages/b0/5a/aef2a0a8daf1ebaae4cfd83f84186d4a72ee08fd6a8451289fcd03ffa8a4/fonttools-4.61.1-cp314-cp314t-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:a75c301f96db737e1c5ed5fd7d77d9c34466de16095a266509e13da09751bd19", size = 4882124, upload-time = "2025-12-12T17:31:07.456Z" },
{ url = "https://files.pythonhosted.org/packages/80/33/d6db3485b645b81cea538c9d1c9219d5805f0877fda18777add4671c5240/fonttools-4.61.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:91669ccac46bbc1d09e9273546181919064e8df73488ea087dcac3e2968df9ba", size = 5100391, upload-time = "2025-12-12T17:31:09.732Z" },
{ url = "https://files.pythonhosted.org/packages/6c/d6/675ba631454043c75fcf76f0ca5463eac8eb0666ea1d7badae5fea001155/fonttools-4.61.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:c33ab3ca9d3ccd581d58e989d67554e42d8d4ded94ab3ade3508455fe70e65f7", size = 4978800, upload-time = "2025-12-12T17:31:11.681Z" },
{ url = "https://files.pythonhosted.org/packages/7f/33/d3ec753d547a8d2bdaedd390d4a814e8d5b45a093d558f025c6b990b554c/fonttools-4.61.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:664c5a68ec406f6b1547946683008576ef8b38275608e1cee6c061828171c118", size = 5006426, upload-time = "2025-12-12T17:31:13.764Z" },
{ url = "https://files.pythonhosted.org/packages/c7/4e/ce75a57ff3aebf6fc1f4e9d508b8e5810618a33d900ad6c19eb30b290b97/fonttools-4.61.1-py3-none-any.whl", hash = "sha256:17d2bf5d541add43822bcf0c43d7d847b160c9bb01d15d5007d84e2217aaa371", size = 1148996, upload-time = "2025-12-12T17:31:21.03Z" },
]
[[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"
@@ -2717,11 +2655,10 @@ 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'" },
@@ -2729,14 +2666,11 @@ 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]]
@@ -2975,7 +2909,7 @@ 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" },
@@ -3652,30 +3586,6 @@ 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 = "5.5.0"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/fb/f6/42f5f1b9beb7e036f5532832b9c590fd107c52a78f704302c03bc6793954/pypdfium2-5.5.0.tar.gz", hash = "sha256:3283c61f54c3c546d140da201ef48a51c18b0ad54293091a010029ac13ece23a", size = 270502, upload-time = "2026-02-18T23:22:37.643Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/bc/a9/379ec56c4481f39f0e37a7ce42f4844e6ddd7662571922e2b348105960ab/pypdfium2-5.5.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:0770bd3f0be5c68443fc4017e43b1b1fe8f36877481cab70fd29b68b2c362e1b", size = 2815036, upload-time = "2026-02-18T23:22:00.288Z" },
{ url = "https://files.pythonhosted.org/packages/91/a4/b0cc01aaae1fdf1ca4e080cc55bb432f5a2234f33209a602bc498a47850d/pypdfium2-5.5.0-py3-none-macosx_11_0_x86_64.whl", hash = "sha256:5ab41a3b9953d9be44be35c36a2340f1d67c602db98a0d6f70006610871ae43a", size = 2948686, upload-time = "2026-02-18T23:22:02.213Z" },
{ url = "https://files.pythonhosted.org/packages/26/99/25a0c71b551d100b505c618910afec0df402b230e087078c8078f8b1fcff/pypdfium2-5.5.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2492a22c3126a004cee2fa208ea4aa03ede2c7e205d05814934ab18f83d073e9", size = 2977311, upload-time = "2026-02-18T23:22:03.603Z" },
{ url = "https://files.pythonhosted.org/packages/85/64/691e21539566f7a0521295948b5589d2fdfe3df5acab9c29ff410633a839/pypdfium2-5.5.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:83ff93e08b1fadb00040564e2eccc99147fc1a632ba5daff745126b373d78446", size = 2762449, upload-time = "2026-02-18T23:22:05.044Z" },
{ url = "https://files.pythonhosted.org/packages/74/b1/9af288557291e2964bf5ffd460b7ed1090fcb8c54addfd6c7c5deb9ba7c7/pypdfium2-5.5.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b7e85de3332bedf8e5f157c248063b4eaf968660e1e490353b6e581d9f96a4c6", size = 3074851, upload-time = "2026-02-18T23:22:07.431Z" },
{ url = "https://files.pythonhosted.org/packages/a4/1e/c61fddbdea5ea1ba478dc7ecc9d68069d17b858e5fed04e4e071811f0858/pypdfium2-5.5.0-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e258365f34b6e334bb415e44dd9b1ee78a6e525bf854a1e74af67af7ede7555b", size = 3423003, upload-time = "2026-02-18T23:22:09.749Z" },
{ url = "https://files.pythonhosted.org/packages/36/5f/d2eb58c54abba3a6c3bc4c297b3a11348dd4b4deb073f1aa8a872a298278/pypdfium2-5.5.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bec21d833404ca771f02fa5cefb0b73e2148f05cbdb3b5b9989bdd51d9b5cbac", size = 3002104, upload-time = "2026-02-18T23:22:12.035Z" },
{ url = "https://files.pythonhosted.org/packages/1c/33/87423eec4f5d4287d5a1726dbb9f06fb1f1aebc38ff75dcff817c492769d/pypdfium2-5.5.0-py3-none-manylinux_2_27_s390x.manylinux_2_28_s390x.whl", hash = "sha256:1dd6ccbe1b5e2e778e8b021e47f9485b4fd42eaa6c9bdda2631641724e1fcc04", size = 3097209, upload-time = "2026-02-18T23:22:13.809Z" },
{ url = "https://files.pythonhosted.org/packages/97/0a/a3fd71f00838bba7922691107219bee67f50fbda6d12df330ef485a97848/pypdfium2-5.5.0-py3-none-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:da3eada345570cec5e34872d1472d4ac542f0e650ccdb6c2eac08ae1a5f07c82", size = 2965027, upload-time = "2026-02-18T23:22:16.324Z" },
{ url = "https://files.pythonhosted.org/packages/75/4a/2181260bd8a0b1b30ac50b7fd6ee3366e04f3a9f1c29351d882652da7fa7/pypdfium2-5.5.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:a087fb4088c7433fd3d78833dbe42cfb66df3d5ac98e3edf66110520fb33c0f0", size = 4131431, upload-time = "2026-02-18T23:22:18.469Z" },
{ url = "https://files.pythonhosted.org/packages/15/bb/3ccf481191346eda11c0c208bd4e46f8de019ae7d9e9c1b660633f0bb3f4/pypdfium2-5.5.0-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:e6418cdc500ef85a90319f9bc7f1c54fc133460379f509429403225d8a4c157f", size = 3747468, upload-time = "2026-02-18T23:22:20.679Z" },
{ url = "https://files.pythonhosted.org/packages/15/51/17e50ec72cf2235ac18d9cbe907859501c769d3e964818fefac6a3e10727/pypdfium2-5.5.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:8f7b66eedfac26eb2df4b00936e081b0a1c76fb8ee1c12639d85c2e73b0769ef", size = 4337579, upload-time = "2026-02-18T23:22:23.245Z" },
{ url = "https://files.pythonhosted.org/packages/c6/e4/f9bdf06f4d3f1e56eff9d997392a00a4b66cbc9c20f33934c4edc2a7943f/pypdfium2-5.5.0-py3-none-musllinux_1_2_ppc64le.whl", hash = "sha256:faea3246591ce2ea6218cd06679071275e3c65f11c3f5c9091eb7fb07610af6a", size = 4376104, upload-time = "2026-02-18T23:22:25.337Z" },
{ url = "https://files.pythonhosted.org/packages/8c/20/06baf1f5d494e035f50fc895fa1da5ed652d03ecc59aeb3aabb0daa5adfc/pypdfium2-5.5.0-py3-none-musllinux_1_2_riscv64.whl", hash = "sha256:aba26d404b51a9de3d3e80c867a95c71abf1c79552001ae22707451e59186b3d", size = 3929824, upload-time = "2026-02-18T23:22:26.889Z" },
{ url = "https://files.pythonhosted.org/packages/3a/01/28940e54e6936674e9a05eb58ccce7c54d8e2ac81cd84ec0b76e7d32a010/pypdfium2-5.5.0-py3-none-musllinux_1_2_s390x.whl", hash = "sha256:e0fa8f81679e6e71f26806f4db853571ee6435dc3bde7a46acdd182ef886a5b9", size = 4270200, upload-time = "2026-02-18T23:22:28.668Z" },
{ url = "https://files.pythonhosted.org/packages/cb/d4/1f36c505a3770aad9a88c895a46d61fd4c0535f79548f02c93b97ff89604/pypdfium2-5.5.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:ee22df3376d350eeb64d2002a1071e3a02c0d874c557a3cd8229a8fc572cdaac", size = 4180794, upload-time = "2026-02-18T23:22:30.11Z" },
]
[[package]]
name = "pyrefly"
version = "0.54.0"
@@ -5162,23 +5072,6 @@ 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"