mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-07-29 23:34:56 +00:00
Compare commits
11
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
  stumpylogandClaude Sonnet 5
|
7d9ba34582 | ||
|
stumpylogandClaude Sonnet 5
|
91c3d9caab | ||
  shamoonandGitHub
|
668fa77428 | ||
|
shamoonandGitHub
|
5bd72014a6 | ||
|
Trenton HandGitHub
|
bbb9c86ba4 | ||
 GitHub Actions
|
09c9fa03cf | ||
|
shamoonandGitHub
|
04779d72bb | ||
|
Trenton HandGitHub
|
1b32b9d678 | ||
|
Trenton HandGitHub
|
12d318deff | ||
  |
9c98f30d3f | ||
|
shamoonandGitHub
|
6a1d7b1bca |
@@ -620,6 +620,34 @@ no other workflow will be executed on the document.
|
||||
If a "Move to Trash" action is executed in a consume pipeline, the consumption
|
||||
will be aborted and the file will be deleted.
|
||||
|
||||
##### Password Removal {#workflow-action-password-removal}
|
||||
|
||||
"Password Removal" actions attempt to remove password protection from encrypted PDF documents. You can specify:
|
||||
|
||||
- One or more passwords to try, separated by commas or new lines
|
||||
- Each password is tried in order until one successfully unlocks the document
|
||||
|
||||
Password removal never modifies a file in place. Instead, once a working password is found, the
|
||||
decrypted content is consumed as a new [document version](#document-file-versions), leaving the
|
||||
original (still encrypted) version in the document's version history.
|
||||
|
||||
**Consumption Started**: because this trigger fires before the document exists yet, the password
|
||||
removal itself is deferred until after the initial consumption of the encrypted file has completed.
|
||||
OCR engines cannot process an encrypted PDF, so this first version is typically stored with no
|
||||
extracted text (unless the file already contained extractable text outside of OCR). Immediately
|
||||
afterwards, the password is removed and the decrypted file is automatically re-consumed as a second,
|
||||
new version of the same document, this time with normal OCR/text extraction applied. In other words,
|
||||
a password-protected file added with this trigger will briefly exist as an un-OCR'd version before
|
||||
the properly processed version is created.
|
||||
|
||||
**Document Added**, **Document Updated**, **Scheduled**: these triggers run against a document that
|
||||
already exists, so password removal happens immediately: the decrypted content is queued for
|
||||
consumption as a new version right away. Note that if the document's initial consumption also
|
||||
happened while it was still encrypted, that original version will likewise be missing OCR text.
|
||||
|
||||
**Current limitation**: Passwords are stored as a simple list without descriptions. To handle
|
||||
multiple PDF types with different passwords, create separate workflows for each use case.
|
||||
|
||||
#### Workflow placeholders
|
||||
|
||||
Titles and webhook payloads can be generated by workflows using [Jinja templates](https://jinja.palletsprojects.com/en/3.1.x/templates/).
|
||||
|
||||
+35
-35
@@ -659,7 +659,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">445</context>
|
||||
<context context-type="linenumber">449</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/custom-fields-bulk-edit-dialog/custom-fields-bulk-edit-dialog.component.html</context>
|
||||
@@ -831,7 +831,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">464</context>
|
||||
<context context-type="linenumber">468</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/document-list.component.html</context>
|
||||
@@ -1355,7 +1355,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">390</context>
|
||||
<context context-type="linenumber">394</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.html</context>
|
||||
@@ -1596,7 +1596,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">165</context>
|
||||
<context context-type="linenumber">169</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="2691296884221415710" datatype="html">
|
||||
@@ -1607,7 +1607,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">170</context>
|
||||
<context context-type="linenumber">174</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.html</context>
|
||||
@@ -1638,7 +1638,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">174</context>
|
||||
<context context-type="linenumber">178</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.html</context>
|
||||
@@ -1669,7 +1669,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">178</context>
|
||||
<context context-type="linenumber">182</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.html</context>
|
||||
@@ -4914,7 +4914,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">356</context>
|
||||
<context context-type="linenumber">360</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="8057014866157903311" datatype="html">
|
||||
@@ -7760,14 +7760,14 @@
|
||||
<source>Details</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">160</context>
|
||||
<context context-type="linenumber">164</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5701618810648052610" datatype="html">
|
||||
<source>Title</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">163</context>
|
||||
<context context-type="linenumber">167</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/document-list.component.html</context>
|
||||
@@ -7790,14 +7790,14 @@
|
||||
<source>Date created</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">167</context>
|
||||
<context context-type="linenumber">171</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5607669932062416162" datatype="html">
|
||||
<source>Default</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">179</context>
|
||||
<context context-type="linenumber">183</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/manage/saved-views/saved-views.component.html</context>
|
||||
@@ -7808,14 +7808,14 @@
|
||||
<source>Content</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">286</context>
|
||||
<context context-type="linenumber">290</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="218403386307979629" datatype="html">
|
||||
<source>Metadata</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">295</context>
|
||||
<context context-type="linenumber">299</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/metadata-collapse/metadata-collapse.component.ts</context>
|
||||
@@ -7826,147 +7826,147 @@
|
||||
<source>Date modified</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">302</context>
|
||||
<context context-type="linenumber">306</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6392918669949841614" datatype="html">
|
||||
<source>Date added</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">306</context>
|
||||
<context context-type="linenumber">310</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="146828917013192897" datatype="html">
|
||||
<source>Media filename</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">310</context>
|
||||
<context context-type="linenumber">314</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4500855521601039868" datatype="html">
|
||||
<source>Original filename</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">314</context>
|
||||
<context context-type="linenumber">318</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="2659735245739197634" datatype="html">
|
||||
<source>Original SHA256 checksum</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">318</context>
|
||||
<context context-type="linenumber">322</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5888243105821763422" datatype="html">
|
||||
<source>Original file size</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">322</context>
|
||||
<context context-type="linenumber">326</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="2696647325713149563" datatype="html">
|
||||
<source>Original mime type</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">326</context>
|
||||
<context context-type="linenumber">330</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6714358112223607756" datatype="html">
|
||||
<source>Archive SHA256 checksum</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">331</context>
|
||||
<context context-type="linenumber">335</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6033581412811562084" datatype="html">
|
||||
<source>Archive file size</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">337</context>
|
||||
<context context-type="linenumber">341</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6992781481378431874" datatype="html">
|
||||
<source>Original document metadata</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">346</context>
|
||||
<context context-type="linenumber">350</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="2846565152091361585" datatype="html">
|
||||
<source>Archived document metadata</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">349</context>
|
||||
<context context-type="linenumber">353</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="7206723502037428235" datatype="html">
|
||||
<source>Notes <x id="START_BLOCK_IF" equiv-text="@if (document()?.notes.length) {"/><x id="START_TAG_SPAN" ctype="x-span" equiv-text="<span class="badge text-bg-secondary ms-1">"/><x id="INTERPOLATION" equiv-text="length}}"/><x id="CLOSE_TAG_SPAN" ctype="x-span"/><x id="CLOSE_BLOCK_IF" equiv-text="}"/></source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">368,371</context>
|
||||
<context context-type="linenumber">372,375</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="186236568870281953" datatype="html">
|
||||
<source>History</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">379</context>
|
||||
<context context-type="linenumber">383</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="8236092845697214347" datatype="html">
|
||||
<source> Duplicates <x id="START_TAG_SPAN" ctype="x-span" equiv-text="<span class="badge text-bg-secondary ms-1">"/><x id="INTERPOLATION" equiv-text="cate_documents.length }}"/><x id="CLOSE_TAG_SPAN" ctype="x-span"/></source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">401,405</context>
|
||||
<context context-type="linenumber">405,409</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6449374629822973702" datatype="html">
|
||||
<source>Duplicate documents detected:</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">407</context>
|
||||
<context context-type="linenumber">411</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="14058600336670816" datatype="html">
|
||||
<source>In trash</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">418</context>
|
||||
<context context-type="linenumber">422</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5129524307369213584" datatype="html">
|
||||
<source>Save & next</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">447</context>
|
||||
<context context-type="linenumber">451</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4910102545766233758" datatype="html">
|
||||
<source>Save & close</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">449</context>
|
||||
<context context-type="linenumber">453</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="3823219296477075982" datatype="html">
|
||||
<source>Discard</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">451</context>
|
||||
<context context-type="linenumber">455</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="1309556917227148591" datatype="html">
|
||||
<source>Document loading...</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">459</context>
|
||||
<context context-type="linenumber">463</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="8191371354890763172" datatype="html">
|
||||
<source>Enter Password</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">513</context>
|
||||
<context context-type="linenumber">517</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5758784066858623886" datatype="html">
|
||||
|
||||
@@ -129,13 +129,25 @@ describe('PngxPdfViewerComponent', () => {
|
||||
;(component as any).applyScale()
|
||||
expect(viewer.currentScaleValue).toBe(PdfZoomScale.PageFit)
|
||||
expect(viewer.currentScale).toBe(2)
|
||||
})
|
||||
|
||||
it('does not reapply scale for page-only changes', async () => {
|
||||
await initComponent()
|
||||
|
||||
const pdf = (component as any).pdf as { numPages: number }
|
||||
pdf.numPages = 3
|
||||
const viewer = (component as any).pdfViewer as PDFViewer
|
||||
viewer.setDocument(pdf)
|
||||
const applyScaleSpy = jest.spyOn(component as any, 'applyScale')
|
||||
component.page = 2
|
||||
;(component as any).lastViewerPage = 2
|
||||
;(component as any).applyViewerState()
|
||||
|
||||
component.ngOnChanges({
|
||||
page: new SimpleChange(1, 2, false),
|
||||
})
|
||||
|
||||
expect(viewer.currentPageNumber).toBe(2)
|
||||
expect((component as any).lastViewerPage).toBeUndefined()
|
||||
expect(applyScaleSpy).toHaveBeenCalled()
|
||||
expect(applyScaleSpy).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
it('does not reset the viewer when it is already on the requested page', async () => {
|
||||
|
||||
@@ -116,7 +116,10 @@ export class PngxPdfViewerComponent
|
||||
changes['zoomScale'] ||
|
||||
changes['rotation']
|
||||
) {
|
||||
this.applyViewerState()
|
||||
// Prevent loop with page / scale application see https://github.com/paperless-ngx/paperless-ngx/issues/13404
|
||||
this.applyViewerState(
|
||||
!!(changes['zoom'] || changes['zoomScale'] || changes['rotation'])
|
||||
)
|
||||
}
|
||||
|
||||
if (changes['searchQuery']) {
|
||||
@@ -240,7 +243,7 @@ export class PngxPdfViewerComponent
|
||||
}
|
||||
}
|
||||
|
||||
private applyViewerState(): void {
|
||||
private applyViewerState(applyScale = true): void {
|
||||
if (!this.pdfViewer) {
|
||||
return
|
||||
}
|
||||
@@ -264,7 +267,7 @@ export class PngxPdfViewerComponent
|
||||
if (this.page === this.lastViewerPage) {
|
||||
this.lastViewerPage = undefined
|
||||
}
|
||||
if (hasPages) {
|
||||
if (hasPages && applyScale) {
|
||||
this.applyScale()
|
||||
}
|
||||
this.dispatchFindIfReady()
|
||||
|
||||
@@ -113,8 +113,8 @@
|
||||
|
||||
<form [formGroup]='documentForm' (ngSubmit)="save()">
|
||||
|
||||
<div class="btn-toolbar mb-1 border-bottom">
|
||||
<div class="btn-group pb-3">
|
||||
<div class="btn-toolbar justify-content-end mb-1 pb-3 gap-2 row-gap-2 border-bottom">
|
||||
<div class="btn-group me-auto">
|
||||
<button type="button" class="btn btn-sm btn-outline-secondary" i18n-title title="Close" (click)="close()">
|
||||
<i-bs width="1.2em" height="1.2em" name="x"></i-bs>
|
||||
</button>
|
||||
@@ -127,32 +127,36 @@
|
||||
</div>
|
||||
|
||||
<ng-container *pngxIfPermissions="{ action: PermissionAction.Change, type: PermissionType.Document }">
|
||||
<div class="btn-group pb-3 ms-auto">
|
||||
<pngx-suggestions-dropdown *pngxIfPermissions="{ action: PermissionAction.Change, type: PermissionType.Document }"
|
||||
[disabled]="!userCanEdit || suggestionsLoading()"
|
||||
[loading]="suggestionsLoading()"
|
||||
[suggestions]="suggestions()"
|
||||
[aiEnabled]="aiEnabled"
|
||||
(getSuggestions)="getSuggestions()"
|
||||
(addTag)="createTag($event)"
|
||||
(addDocumentType)="createDocumentType($event)"
|
||||
(addCorrespondent)="createCorrespondent($event)">
|
||||
</pngx-suggestions-dropdown>
|
||||
<div class="d-flex gap-2">
|
||||
<div class="btn-group">
|
||||
<pngx-suggestions-dropdown *pngxIfPermissions="{ action: PermissionAction.Change, type: PermissionType.Document }"
|
||||
[disabled]="!userCanEdit || suggestionsLoading()"
|
||||
[loading]="suggestionsLoading()"
|
||||
[suggestions]="suggestions()"
|
||||
[aiEnabled]="aiEnabled"
|
||||
(getSuggestions)="getSuggestions()"
|
||||
(addTag)="createTag($event)"
|
||||
(addDocumentType)="createDocumentType($event)"
|
||||
(addCorrespondent)="createCorrespondent($event)">
|
||||
</pngx-suggestions-dropdown>
|
||||
</div>
|
||||
|
||||
<div class="btn-group">
|
||||
<pngx-custom-fields-dropdown
|
||||
*pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.CustomField }"
|
||||
[documentId]="documentId()"
|
||||
[disabled]="!userCanEdit"
|
||||
[existingFields]="document()?.custom_fields"
|
||||
(created)="refreshCustomFields()"
|
||||
(added)="addField($event)">
|
||||
</pngx-custom-fields-dropdown>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="btn-group pb-3 ms-2">
|
||||
<pngx-custom-fields-dropdown
|
||||
*pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.CustomField }"
|
||||
[documentId]="documentId()"
|
||||
[disabled]="!userCanEdit"
|
||||
[existingFields]="document()?.custom_fields"
|
||||
(created)="refreshCustomFields()"
|
||||
(added)="addField($event)">
|
||||
</pngx-custom-fields-dropdown>
|
||||
<div class="ps-3">
|
||||
<ng-container *ngTemplateOutlet="saveButtons"></ng-container>
|
||||
</div>
|
||||
</ng-container>
|
||||
|
||||
<ng-container *ngTemplateOutlet="saveButtons"></ng-container>
|
||||
</div>
|
||||
|
||||
<ul ngbNav #nav="ngbNav" class="nav-underline flex-nowrap flex-md-wrap overflow-auto" (navChange)="onNavChange($event)" [activeId]="activeNavID()" (activeIdChange)="activeNavID.set($event)">
|
||||
@@ -276,7 +280,7 @@
|
||||
}
|
||||
</div>
|
||||
|
||||
<div class="d-flex border-top pt-3">
|
||||
<div class="d-flex justify-content-end border-top pt-3">
|
||||
<ng-container *ngTemplateOutlet="saveButtons"></ng-container>
|
||||
</div>
|
||||
</ng-template>
|
||||
@@ -440,7 +444,7 @@
|
||||
</div>
|
||||
|
||||
<ng-template #saveButtons>
|
||||
<div class="btn-group pb-3 ms-4">
|
||||
<div class="btn-group">
|
||||
<ng-container *pngxIfPermissions="{ action: PermissionAction.Change, type: PermissionType.Document }">
|
||||
<button type="submit" class="order-3 btn btn-sm btn-primary" i18n [disabled]="!userCanEdit || networkActive() || (isDirty$ | async) !== true">Save</button>
|
||||
@if (hasNext()) {
|
||||
|
||||
@@ -36,6 +36,9 @@ def send_email(
|
||||
|
||||
TODO: re-evaluate this pending https://code.djangoproject.com/ticket/35581 / https://github.com/django/django/pull/18966
|
||||
"""
|
||||
if "\r" in subject or "\n" in subject:
|
||||
subject = " ".join(line.strip(" \t") for line in subject.splitlines())
|
||||
|
||||
email = EmailMessage(
|
||||
subject=subject,
|
||||
body=body,
|
||||
|
||||
@@ -386,10 +386,19 @@ class Command(CryptMixin, PaperlessCommand):
|
||||
raise DeserializationError(
|
||||
f"{model.__name__} has no updatable fields; PK-only models are not supported by the importer",
|
||||
)
|
||||
# MySQL/MariaDB support upserts via ON DUPLICATE KEY UPDATE but,
|
||||
# unlike PostgreSQL/SQLite, cannot target a specific unique field
|
||||
# for the conflict -- passing unique_fields there raises
|
||||
# NotSupportedError.
|
||||
unique_fields = (
|
||||
[model._meta.pk.attname]
|
||||
if connection.features.supports_update_conflicts_with_target
|
||||
else None
|
||||
)
|
||||
model.objects.bulk_create( # type: ignore[attr-defined]
|
||||
instances,
|
||||
update_conflicts=True,
|
||||
unique_fields=[model._meta.pk.attname],
|
||||
unique_fields=unique_fields,
|
||||
update_fields=update_fields,
|
||||
)
|
||||
loaded_models.add(model)
|
||||
|
||||
@@ -43,8 +43,16 @@ def _fmt(dt: datetime) -> str:
|
||||
|
||||
|
||||
def _iso_range(lo: datetime, hi: datetime) -> str:
|
||||
"""Format a [lo TO hi] range string in ISO 8601 for Tantivy query syntax."""
|
||||
return f"[{_fmt(lo)} TO {_fmt(hi)}]"
|
||||
"""
|
||||
Format a half-open ``[lo TO hi)`` range in ISO 8601 for Tantivy query syntax.
|
||||
|
||||
``hi`` is always the exclusive ceiling of a computed period (the start of
|
||||
the *next* day/week/month/quarter/year), so the closing bracket must be
|
||||
the Tantivy exclusive-range brace ``}`` rather than ``]`` — otherwise the
|
||||
first instant of the following period (e.g. the 1st of next month) is
|
||||
incorrectly included in the match.
|
||||
"""
|
||||
return f"[{_fmt(lo)} TO {_fmt(hi)}}}"
|
||||
|
||||
|
||||
def _quarter_start(d: date) -> date:
|
||||
|
||||
@@ -566,6 +566,17 @@ def translate_range(field: str, lo: str, hi: str, tz: tzinfo) -> str:
|
||||
lo_pair, hi_pair = hi_pair, lo_pair
|
||||
|
||||
lo_iso = _fmt(lo_pair[0]) if lo_pair is not None else OPEN_LO
|
||||
hi_iso = _fmt(hi_pair[1]) if hi_pair is not None else OPEN_HI
|
||||
|
||||
return f"{field}:[{lo_iso} TO {hi_iso}]"
|
||||
# A bound resolves to (floor, ceil) where floor == ceil for an exact instant
|
||||
# (a full ISO datetime, "now", or a "+/-N unit" offset) and floor != ceil for
|
||||
# a coarser period token (year/month/day precision). Only the latter needs a
|
||||
# half-open close: its ceil is the start of the *next* period and must be
|
||||
# excluded, or that instant (e.g. the 1st of next month) wrongly matches.
|
||||
if hi_pair is not None:
|
||||
hi_iso = _fmt(hi_pair[1])
|
||||
hi_close = "]" if hi_pair[0] == hi_pair[1] else "}"
|
||||
else:
|
||||
hi_iso = OPEN_HI
|
||||
hi_close = "]"
|
||||
|
||||
return f"{field}:[{lo_iso} TO {hi_iso}{hi_close}"
|
||||
|
||||
@@ -1134,6 +1134,11 @@ def before_task_publish_handler(
|
||||
return
|
||||
|
||||
try:
|
||||
# Close stale connections without disrupting a transaction publishing a task
|
||||
for connection in connections.all(initialized_only=True):
|
||||
if not connection.in_atomic_block:
|
||||
connection.close_if_unusable_or_obsolete()
|
||||
|
||||
_, task_kwargs, _ = body
|
||||
task_id = headers["id"]
|
||||
|
||||
|
||||
@@ -32,7 +32,9 @@ AUCKLAND = ZoneInfo("Pacific/Auckland") # UTC+13 in southern-hemisphere summer
|
||||
|
||||
|
||||
def _range(result: str, field: str) -> tuple[str, str]:
|
||||
m = re.search(rf"{field}:\[(.+?) TO (.+?)\]", result)
|
||||
# Half-open period ranges close with "}" (exclusive); exact-instant ranges
|
||||
# (full ISO datetimes, "now", relative offsets) close with "]" (inclusive).
|
||||
m = re.search(rf"{field}:\[(.+?) TO (.+?)[\]}}]", result)
|
||||
assert m, f"No range for {field!r} in: {result!r}"
|
||||
return m.group(1), m.group(2)
|
||||
|
||||
|
||||
@@ -214,27 +214,27 @@ class TestTranslateScalar:
|
||||
(
|
||||
"created",
|
||||
"2020",
|
||||
"created:[2020-01-01T00:00:00Z TO 2021-01-01T00:00:00Z]",
|
||||
"created:[2020-01-01T00:00:00Z TO 2021-01-01T00:00:00Z}",
|
||||
),
|
||||
(
|
||||
"created",
|
||||
"202003",
|
||||
"created:[2020-03-01T00:00:00Z TO 2020-04-01T00:00:00Z]",
|
||||
"created:[2020-03-01T00:00:00Z TO 2020-04-01T00:00:00Z}",
|
||||
),
|
||||
(
|
||||
"created",
|
||||
"20200115",
|
||||
"created:[2020-01-15T00:00:00Z TO 2020-01-16T00:00:00Z]",
|
||||
"created:[2020-01-15T00:00:00Z TO 2020-01-16T00:00:00Z}",
|
||||
),
|
||||
(
|
||||
"created",
|
||||
"2020-01-15",
|
||||
"created:[2020-01-15T00:00:00Z TO 2020-01-16T00:00:00Z]",
|
||||
"created:[2020-01-15T00:00:00Z TO 2020-01-16T00:00:00Z}",
|
||||
),
|
||||
(
|
||||
"created",
|
||||
"2020-03",
|
||||
"created:[2020-03-01T00:00:00Z TO 2020-04-01T00:00:00Z]",
|
||||
"created:[2020-03-01T00:00:00Z TO 2020-04-01T00:00:00Z}",
|
||||
),
|
||||
],
|
||||
)
|
||||
@@ -248,9 +248,9 @@ class TestTranslateScalar:
|
||||
assert exc_info.value.value == "202023"
|
||||
|
||||
def test_keyword_delegates(self) -> None:
|
||||
# keyword path produces a range; just assert it is a created range
|
||||
# keyword path produces a half-open range; just assert it is a created range
|
||||
out = translate_scalar("created", "today", UTC)
|
||||
assert out.startswith("created:[") and out.endswith("]")
|
||||
assert out.startswith("created:[") and out.endswith("}")
|
||||
|
||||
def test_14digit_compact_datetime(self) -> None:
|
||||
out = translate_scalar("created", "20240115120000", UTC)
|
||||
@@ -279,21 +279,21 @@ class TestTranslateRange:
|
||||
@pytest.mark.parametrize(
|
||||
("lo", "hi", "expected"),
|
||||
[
|
||||
("2005", "2009", "created:[2005-01-01T00:00:00Z TO 2010-01-01T00:00:00Z]"),
|
||||
("2005", "2009", "created:[2005-01-01T00:00:00Z TO 2010-01-01T00:00:00Z}"),
|
||||
(
|
||||
"202001",
|
||||
"202006",
|
||||
"created:[2020-01-01T00:00:00Z TO 2020-07-01T00:00:00Z]",
|
||||
"created:[2020-01-01T00:00:00Z TO 2020-07-01T00:00:00Z}",
|
||||
),
|
||||
(
|
||||
"20200101",
|
||||
"20201231",
|
||||
"created:[2020-01-01T00:00:00Z TO 2021-01-01T00:00:00Z]",
|
||||
"created:[2020-01-01T00:00:00Z TO 2021-01-01T00:00:00Z}",
|
||||
),
|
||||
(
|
||||
"2020-01-01",
|
||||
"2020-12-31",
|
||||
"created:[2020-01-01T00:00:00Z TO 2021-01-01T00:00:00Z]",
|
||||
"created:[2020-01-01T00:00:00Z TO 2021-01-01T00:00:00Z}",
|
||||
),
|
||||
],
|
||||
)
|
||||
@@ -302,7 +302,7 @@ class TestTranslateRange:
|
||||
|
||||
def test_reversed_swaps(self):
|
||||
assert translate_range("created", "2009", "2005", UTC) == (
|
||||
"created:[2005-01-01T00:00:00Z TO 2010-01-01T00:00:00Z]"
|
||||
"created:[2005-01-01T00:00:00Z TO 2010-01-01T00:00:00Z}"
|
||||
)
|
||||
|
||||
def test_open_upper(self):
|
||||
@@ -311,7 +311,7 @@ class TestTranslateRange:
|
||||
|
||||
def test_open_lower(self):
|
||||
out = translate_range("created", "", "2020", UTC)
|
||||
assert out == f"created:[{OPEN_LO} TO 2021-01-01T00:00:00Z]"
|
||||
assert out == f"created:[{OPEN_LO} TO 2021-01-01T00:00:00Z}}"
|
||||
|
||||
def test_invalid_bound_raises(self):
|
||||
with pytest.raises(InvalidDateQuery) as exc_info:
|
||||
@@ -334,16 +334,16 @@ class TestTranslateQuery:
|
||||
[
|
||||
(
|
||||
"created:2020",
|
||||
"created:[2020-01-01T00:00:00Z TO 2021-01-01T00:00:00Z]",
|
||||
"created:[2020-01-01T00:00:00Z TO 2021-01-01T00:00:00Z}",
|
||||
),
|
||||
("tag:foo,bar", "tag:foo AND tag:bar"),
|
||||
# 'type' is a user-facing alias rewritten to 'document_type' (the real schema field)
|
||||
("tag:foo,type:bar", "tag:foo AND document_type:bar"),
|
||||
(
|
||||
"created:[2020 TO 2021],added:[2022 TO 2023]",
|
||||
"created:[2020-01-01T00:00:00Z TO 2022-01-01T00:00:00Z]"
|
||||
"created:[2020-01-01T00:00:00Z TO 2022-01-01T00:00:00Z}"
|
||||
" AND "
|
||||
"added:[2022-01-01T00:00:00Z TO 2024-01-01T00:00:00Z]",
|
||||
"added:[2022-01-01T00:00:00Z TO 2024-01-01T00:00:00Z}",
|
||||
),
|
||||
# correspondent is not multi-value: comma stays literal inside the value
|
||||
("correspondent:foo,bar", "correspondent:foo,bar"),
|
||||
@@ -506,7 +506,7 @@ class TestOperatorNormalization:
|
||||
def test_date_range_preserved(self) -> None:
|
||||
out = translate_query("created:[2020 TO 2021]", UTC)
|
||||
# Must not corrupt the ISO range
|
||||
assert out == "created:[2020-01-01T00:00:00Z TO 2022-01-01T00:00:00Z]"
|
||||
assert out == "created:[2020-01-01T00:00:00Z TO 2022-01-01T00:00:00Z}"
|
||||
|
||||
def test_date_scalar_with_or(self) -> None:
|
||||
out = translate_query("created:2020 OR foo", UTC)
|
||||
@@ -581,42 +581,42 @@ class TestKeywordDateResolution:
|
||||
[
|
||||
pytest.param(
|
||||
"today",
|
||||
"created:[2026-03-28T00:00:00Z TO 2026-03-29T00:00:00Z]",
|
||||
"created:[2026-03-28T00:00:00Z TO 2026-03-29T00:00:00Z}",
|
||||
id="today",
|
||||
),
|
||||
pytest.param(
|
||||
"yesterday",
|
||||
"created:[2026-03-27T00:00:00Z TO 2026-03-28T00:00:00Z]",
|
||||
"created:[2026-03-27T00:00:00Z TO 2026-03-28T00:00:00Z}",
|
||||
id="yesterday",
|
||||
),
|
||||
pytest.param(
|
||||
"previous week",
|
||||
"created:[2026-03-16T00:00:00Z TO 2026-03-23T00:00:00Z]",
|
||||
"created:[2026-03-16T00:00:00Z TO 2026-03-23T00:00:00Z}",
|
||||
id="previous-week",
|
||||
),
|
||||
pytest.param(
|
||||
"this month",
|
||||
"created:[2026-03-01T00:00:00Z TO 2026-04-01T00:00:00Z]",
|
||||
"created:[2026-03-01T00:00:00Z TO 2026-04-01T00:00:00Z}",
|
||||
id="this-month",
|
||||
),
|
||||
pytest.param(
|
||||
"previous month",
|
||||
"created:[2026-02-01T00:00:00Z TO 2026-03-01T00:00:00Z]",
|
||||
"created:[2026-02-01T00:00:00Z TO 2026-03-01T00:00:00Z}",
|
||||
id="previous-month",
|
||||
),
|
||||
pytest.param(
|
||||
"this year",
|
||||
"created:[2026-01-01T00:00:00Z TO 2027-01-01T00:00:00Z]",
|
||||
"created:[2026-01-01T00:00:00Z TO 2027-01-01T00:00:00Z}",
|
||||
id="this-year",
|
||||
),
|
||||
pytest.param(
|
||||
"previous year",
|
||||
"created:[2025-01-01T00:00:00Z TO 2026-01-01T00:00:00Z]",
|
||||
"created:[2025-01-01T00:00:00Z TO 2026-01-01T00:00:00Z}",
|
||||
id="previous-year",
|
||||
),
|
||||
pytest.param(
|
||||
"previous quarter",
|
||||
"created:[2025-10-01T00:00:00Z TO 2026-01-01T00:00:00Z]",
|
||||
"created:[2025-10-01T00:00:00Z TO 2026-01-01T00:00:00Z}",
|
||||
id="previous-quarter",
|
||||
),
|
||||
],
|
||||
@@ -637,42 +637,42 @@ class TestKeywordDateResolution:
|
||||
[
|
||||
pytest.param(
|
||||
"today",
|
||||
"added:[2026-03-27T15:00:00Z TO 2026-03-28T15:00:00Z]",
|
||||
"added:[2026-03-27T15:00:00Z TO 2026-03-28T15:00:00Z}",
|
||||
id="today",
|
||||
),
|
||||
pytest.param(
|
||||
"yesterday",
|
||||
"added:[2026-03-26T15:00:00Z TO 2026-03-27T15:00:00Z]",
|
||||
"added:[2026-03-26T15:00:00Z TO 2026-03-27T15:00:00Z}",
|
||||
id="yesterday",
|
||||
),
|
||||
pytest.param(
|
||||
"previous week",
|
||||
"added:[2026-03-15T15:00:00Z TO 2026-03-22T15:00:00Z]",
|
||||
"added:[2026-03-15T15:00:00Z TO 2026-03-22T15:00:00Z}",
|
||||
id="previous-week",
|
||||
),
|
||||
pytest.param(
|
||||
"this month",
|
||||
"added:[2026-02-28T15:00:00Z TO 2026-03-31T15:00:00Z]",
|
||||
"added:[2026-02-28T15:00:00Z TO 2026-03-31T15:00:00Z}",
|
||||
id="this-month",
|
||||
),
|
||||
pytest.param(
|
||||
"previous month",
|
||||
"added:[2026-01-31T15:00:00Z TO 2026-02-28T15:00:00Z]",
|
||||
"added:[2026-01-31T15:00:00Z TO 2026-02-28T15:00:00Z}",
|
||||
id="previous-month",
|
||||
),
|
||||
pytest.param(
|
||||
"this year",
|
||||
"added:[2025-12-31T15:00:00Z TO 2026-12-31T15:00:00Z]",
|
||||
"added:[2025-12-31T15:00:00Z TO 2026-12-31T15:00:00Z}",
|
||||
id="this-year",
|
||||
),
|
||||
pytest.param(
|
||||
"previous year",
|
||||
"added:[2024-12-31T15:00:00Z TO 2025-12-31T15:00:00Z]",
|
||||
"added:[2024-12-31T15:00:00Z TO 2025-12-31T15:00:00Z}",
|
||||
id="previous-year",
|
||||
),
|
||||
pytest.param(
|
||||
"previous quarter",
|
||||
"added:[2025-09-30T15:00:00Z TO 2025-12-31T15:00:00Z]",
|
||||
"added:[2025-09-30T15:00:00Z TO 2025-12-31T15:00:00Z}",
|
||||
id="previous-quarter",
|
||||
),
|
||||
],
|
||||
@@ -719,7 +719,7 @@ class TestISODatetimeBounds:
|
||||
def test_translate_query_text_before_comma_separated_date_clause(self) -> None:
|
||||
result = translate_query("schäfersee,created:previous year", UTC)
|
||||
assert result == (
|
||||
"schäfersee AND created:[2025-01-01T00:00:00Z TO 2026-01-01T00:00:00Z]"
|
||||
"schäfersee AND created:[2025-01-01T00:00:00Z TO 2026-01-01T00:00:00Z}"
|
||||
)
|
||||
|
||||
def test_invalid_iso_datetime_raises(self) -> None:
|
||||
|
||||
@@ -75,7 +75,7 @@ class TestEmail(DirectoriesMixin, SampleDirMixin, APITestCase):
|
||||
{
|
||||
"documents": [self.doc1.pk, self.doc2.pk],
|
||||
"addresses": "hello@paperless-ngx.com,test@example.com",
|
||||
"subject": "Bulk email test",
|
||||
"subject": "Bulk email\n test",
|
||||
"message": "Here are your documents",
|
||||
},
|
||||
),
|
||||
|
||||
@@ -720,6 +720,48 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
|
||||
self.assertEqual(results[0]["id"], 3)
|
||||
self.assertEqual(results[0]["title"], "bank statement 3")
|
||||
|
||||
def test_search_added_previous_month_excludes_next_period_start(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- One document added at the last instant of last month
|
||||
- One document added exactly at the first instant of this month
|
||||
WHEN:
|
||||
- Query for documents added in the previous month
|
||||
THEN:
|
||||
- Only the document from last month is returned; the document dated
|
||||
exactly at the start of this month (the exclusive upper bound of
|
||||
the range) is not
|
||||
"""
|
||||
d1 = DocumentFactory.create(
|
||||
title="end of last month",
|
||||
content="last instant of last month",
|
||||
checksum="A",
|
||||
pk=1,
|
||||
added=timezone.make_aware(datetime.datetime(2024, 1, 31, 23, 59, 59)),
|
||||
)
|
||||
d2 = DocumentFactory.create(
|
||||
title="start of this month",
|
||||
content="first instant of this month",
|
||||
checksum="B",
|
||||
pk=2,
|
||||
added=timezone.make_aware(datetime.datetime(2024, 2, 1, 0, 0, 0)),
|
||||
)
|
||||
|
||||
backend = get_backend()
|
||||
backend.add_or_update(d1)
|
||||
backend.add_or_update(d2)
|
||||
|
||||
with time_machine.travel(
|
||||
timezone.make_aware(datetime.datetime(2024, 2, 15, 12, 0, 0)),
|
||||
tick=False,
|
||||
):
|
||||
response = self.client.get("/api/documents/?query=added:previous month")
|
||||
results = response.data["results"]
|
||||
|
||||
self.assertEqual(len(results), 1)
|
||||
self.assertEqual(results[0]["id"], 1)
|
||||
self.assertEqual(results[0]["title"], "end of last month")
|
||||
|
||||
def test_search_added_invalid_date(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
|
||||
@@ -56,6 +56,32 @@ def send_publish(
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestBeforeTaskPublishHandler:
|
||||
@mock.patch("documents.signals.handlers.connections.all")
|
||||
def test_closes_old_connections_outside_atomic_blocks(
|
||||
self,
|
||||
connections_all,
|
||||
) -> None:
|
||||
connection = mock.Mock(in_atomic_block=False)
|
||||
connections_all.return_value = [connection]
|
||||
|
||||
task_id = send_publish("documents.tasks.train_classifier", (), {})
|
||||
|
||||
connection.close_if_unusable_or_obsolete.assert_called_once_with()
|
||||
assert PaperlessTask.objects.filter(task_id=task_id).exists()
|
||||
|
||||
@mock.patch("documents.signals.handlers.connections.all")
|
||||
def test_keeps_connections_open_inside_atomic_blocks(
|
||||
self,
|
||||
connections_all,
|
||||
) -> None:
|
||||
connection = mock.Mock(in_atomic_block=True)
|
||||
connections_all.return_value = [connection]
|
||||
|
||||
task_id = send_publish("documents.tasks.train_classifier", (), {})
|
||||
|
||||
connection.close_if_unusable_or_obsolete.assert_not_called()
|
||||
assert PaperlessTask.objects.filter(task_id=task_id).exists()
|
||||
|
||||
def test_creates_task_for_consume_file(
|
||||
self,
|
||||
consume_input_doc,
|
||||
|
||||
@@ -0,0 +1,229 @@
|
||||
"""Thin gateways over the plain relational side tables that sit alongside the
|
||||
vec0 table. Each method takes the sqlite3.Connection to operate on
|
||||
explicitly, rather than owning one -- the store swaps connections during
|
||||
compact()/migration, and migrations always work across two connections
|
||||
(src_conn, dst_conn) at once.
|
||||
|
||||
PRECONDITION: Callers must set conn.row_factory = sqlite3.Row before passing a
|
||||
connection to any of these gateways' read methods. The read methods across all
|
||||
three classes (DocumentChunksTable.chunk_ids_for_document, IndexMetaTable._get,
|
||||
DocumentMetaTable.all_modified_times, DocumentMetaTable.copy_all) use
|
||||
row["column_name"] dictionary-style indexing, which requires sqlite3.Row as the
|
||||
row factory -- without it, sqlite3.Row is not set, rows are returned as plain
|
||||
tuples, and tuple indices must be integers, raising TypeError.
|
||||
"""
|
||||
|
||||
import sqlite3
|
||||
from collections.abc import Iterable
|
||||
from typing import NamedTuple
|
||||
|
||||
|
||||
class ChunkRow(NamedTuple):
|
||||
chunk_id: str
|
||||
document_id: int
|
||||
|
||||
|
||||
class DocumentMetaRow(NamedTuple):
|
||||
document_id: int
|
||||
modified: str
|
||||
|
||||
|
||||
class DocumentChunksTable:
|
||||
"""chunk_id -> document_id, indexed by document_id. Gives O(1)
|
||||
per-document chunk lookup that vec0's own document_id metadata column
|
||||
cannot (see PaperlessSqliteVecVectorStore._delete_chunks_by_document_id).
|
||||
"""
|
||||
|
||||
@staticmethod
|
||||
def create(conn: sqlite3.Connection) -> None:
|
||||
conn.execute(
|
||||
"CREATE TABLE IF NOT EXISTS document_chunks "
|
||||
"(chunk_id TEXT PRIMARY KEY, document_id INTEGER NOT NULL)",
|
||||
)
|
||||
conn.execute(
|
||||
"CREATE INDEX IF NOT EXISTS idx_document_chunks_document_id "
|
||||
"ON document_chunks (document_id)",
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def insert_many(conn: sqlite3.Connection, rows: Iterable[ChunkRow]) -> None:
|
||||
"""rows must already be batch-bounded by the caller (e.g. vec0's own
|
||||
fetchmany() loop) -- this never reads, so it can't itself introduce
|
||||
an unbounded scan, but a whole-table iterable defeats the point."""
|
||||
conn.executemany(
|
||||
"INSERT INTO document_chunks (chunk_id, document_id) VALUES (?, ?)",
|
||||
rows,
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def chunk_ids_for_document(
|
||||
conn: sqlite3.Connection,
|
||||
document_id: int,
|
||||
) -> list[str]:
|
||||
return [
|
||||
row["chunk_id"]
|
||||
for row in conn.execute(
|
||||
"SELECT chunk_id FROM document_chunks WHERE document_id = ?",
|
||||
(document_id,),
|
||||
).fetchall()
|
||||
]
|
||||
|
||||
@staticmethod
|
||||
def delete_for_document(conn: sqlite3.Connection, document_id: int) -> None:
|
||||
conn.execute(
|
||||
"DELETE FROM document_chunks WHERE document_id = ?",
|
||||
(document_id,),
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def delete_all(conn: sqlite3.Connection) -> None:
|
||||
conn.execute("DELETE FROM document_chunks")
|
||||
|
||||
@staticmethod
|
||||
def count(conn: sqlite3.Connection) -> int:
|
||||
"""Cheap stand-in for vec0's own row count -- see compact()."""
|
||||
return conn.execute("SELECT count(*) FROM document_chunks").fetchone()[0]
|
||||
|
||||
|
||||
class DocumentMetaTable:
|
||||
"""document_id -> modified, one row per document. Lives outside vec0
|
||||
because vec0 only inlines TEXT metadata up to 12 bytes and `modified`
|
||||
(an ISO timestamp) is always longer.
|
||||
"""
|
||||
|
||||
@staticmethod
|
||||
def create(conn: sqlite3.Connection) -> None:
|
||||
conn.execute(
|
||||
"CREATE TABLE IF NOT EXISTS document_meta "
|
||||
"(document_id INTEGER PRIMARY KEY, modified TEXT NOT NULL)",
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def upsert_many(
|
||||
conn: sqlite3.Connection,
|
||||
rows: Iterable[DocumentMetaRow],
|
||||
) -> None:
|
||||
conn.executemany(
|
||||
"INSERT INTO document_meta (document_id, modified) VALUES (?, ?) "
|
||||
"ON CONFLICT(document_id) DO UPDATE SET modified = excluded.modified",
|
||||
rows,
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def delete_for_document(conn: sqlite3.Connection, document_id: int) -> None:
|
||||
conn.execute(
|
||||
"DELETE FROM document_meta WHERE document_id = ?",
|
||||
(document_id,),
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def delete_all(conn: sqlite3.Connection) -> None:
|
||||
conn.execute("DELETE FROM document_meta")
|
||||
|
||||
@staticmethod
|
||||
def copy_all(
|
||||
src_conn: sqlite3.Connection,
|
||||
dst_conn: sqlite3.Connection,
|
||||
batch_size: int,
|
||||
) -> None:
|
||||
"""Stream document_meta from src_conn into dst_conn in bounded
|
||||
batches. The *only* sanctioned way to move this table across
|
||||
connections (compact()/migrations) -- an unbounded fetchall here
|
||||
would defeat the same OOM-avoidance the vec0 row copy already relies
|
||||
on. batch_size has no default: forces the call site to think about
|
||||
it (pass COMPACT_BATCH_SIZE)."""
|
||||
cursor = src_conn.execute(
|
||||
"SELECT document_id, modified FROM document_meta",
|
||||
)
|
||||
while batch := cursor.fetchmany(batch_size):
|
||||
DocumentMetaTable.upsert_many(
|
||||
dst_conn,
|
||||
(DocumentMetaRow(r["document_id"], r["modified"]) for r in batch),
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def all_modified_times(conn: sqlite3.Connection) -> dict[str, str]:
|
||||
"""Full document_id -> modified map, for get_modified_times()'s
|
||||
public API only. One unbounded read by design (existing behavior).
|
||||
Never use this for cross-connection copying; see copy_all()."""
|
||||
return {
|
||||
str(row["document_id"]): str(row["modified"] or "")
|
||||
for row in conn.execute(
|
||||
"SELECT document_id, modified FROM document_meta",
|
||||
)
|
||||
}
|
||||
|
||||
|
||||
class IndexMetaTable:
|
||||
"""Typed accessors over index_meta's key/value rows -- replaces
|
||||
PaperlessSqliteVecVectorStore._meta_get_on/_meta_set_on, which returned
|
||||
untyped str | None regardless of whether the key held an int (dim,
|
||||
schema_version, total_inserts) or a string (embed_model).
|
||||
"""
|
||||
|
||||
@staticmethod
|
||||
def create(conn: sqlite3.Connection) -> None:
|
||||
conn.execute(
|
||||
"CREATE TABLE IF NOT EXISTS index_meta (key TEXT PRIMARY KEY, value TEXT)",
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _get(conn: sqlite3.Connection, key: str) -> str | None:
|
||||
row = conn.execute(
|
||||
"SELECT value FROM index_meta WHERE key = ?",
|
||||
(key,),
|
||||
).fetchone()
|
||||
return row["value"] if row else None
|
||||
|
||||
@staticmethod
|
||||
def _set(conn: sqlite3.Connection, key: str, value: str) -> None:
|
||||
conn.execute(
|
||||
"INSERT INTO index_meta (key, value) VALUES (?, ?) "
|
||||
"ON CONFLICT(key) DO UPDATE SET value = excluded.value",
|
||||
(key, value),
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def get_dim(conn: sqlite3.Connection) -> int | None:
|
||||
value = IndexMetaTable._get(conn, "dim")
|
||||
return int(value) if value is not None else None
|
||||
|
||||
@staticmethod
|
||||
def set_dim(conn: sqlite3.Connection, dim: int) -> None:
|
||||
IndexMetaTable._set(conn, "dim", str(dim))
|
||||
|
||||
@staticmethod
|
||||
def get_embed_model(conn: sqlite3.Connection) -> str | None:
|
||||
return IndexMetaTable._get(conn, "embed_model")
|
||||
|
||||
@staticmethod
|
||||
def set_embed_model(conn: sqlite3.Connection, name: str) -> None:
|
||||
IndexMetaTable._set(conn, "embed_model", name)
|
||||
|
||||
@staticmethod
|
||||
def get_schema_version(conn: sqlite3.Connection) -> int | None:
|
||||
value = IndexMetaTable._get(conn, "schema_version")
|
||||
return int(value) if value is not None else None
|
||||
|
||||
@staticmethod
|
||||
def set_schema_version(conn: sqlite3.Connection, version: int) -> None:
|
||||
IndexMetaTable._set(conn, "schema_version", str(version))
|
||||
|
||||
@staticmethod
|
||||
def get_total_inserts(conn: sqlite3.Connection) -> int:
|
||||
value = IndexMetaTable._get(conn, "total_inserts")
|
||||
return int(value) if value is not None else 0
|
||||
|
||||
@staticmethod
|
||||
def increment_total_inserts(conn: sqlite3.Connection, count: int) -> None:
|
||||
current = IndexMetaTable.get_total_inserts(conn)
|
||||
IndexMetaTable._set(conn, "total_inserts", str(current + count))
|
||||
|
||||
@staticmethod
|
||||
def reset_total_inserts(conn: sqlite3.Connection, count: int) -> None:
|
||||
"""Set total_inserts to an absolute value -- distinct from
|
||||
increment_total_inserts(): used by compact()'s rebuild and by
|
||||
m0001_v1_to_v2 after copying live rows into a fresh file, where
|
||||
total_inserts must become exactly the live row count, not add to
|
||||
whatever the source file's counter held."""
|
||||
IndexMetaTable._set(conn, "total_inserts", str(count))
|
||||
@@ -0,0 +1,306 @@
|
||||
import sqlite3
|
||||
from collections.abc import Generator
|
||||
|
||||
import pytest
|
||||
|
||||
from paperless_ai.tables import ChunkRow
|
||||
from paperless_ai.tables import DocumentChunksTable
|
||||
from paperless_ai.tables import DocumentMetaRow
|
||||
from paperless_ai.tables import DocumentMetaTable
|
||||
from paperless_ai.tables import IndexMetaTable
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def conn() -> Generator[sqlite3.Connection, None, None]:
|
||||
connection = sqlite3.connect(":memory:")
|
||||
connection.row_factory = sqlite3.Row
|
||||
try:
|
||||
yield connection
|
||||
finally:
|
||||
connection.close()
|
||||
|
||||
|
||||
class TestDocumentChunksTable:
|
||||
def test_create_is_idempotent(self, conn: sqlite3.Connection) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A bare sqlite3 connection
|
||||
WHEN:
|
||||
- create() is called, a row is inserted, then create() is called again
|
||||
THEN:
|
||||
- No error is raised and the row survives uncorrupted
|
||||
"""
|
||||
DocumentChunksTable.create(conn)
|
||||
DocumentChunksTable.insert_many(conn, [ChunkRow("c1", 1)])
|
||||
DocumentChunksTable.create(conn)
|
||||
assert DocumentChunksTable.chunk_ids_for_document(conn, 1) == ["c1"]
|
||||
|
||||
def test_insert_many_then_lookup_by_document_id(
|
||||
self,
|
||||
conn: sqlite3.Connection,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An empty document_chunks table
|
||||
WHEN:
|
||||
- Two chunks for document 1 and one for document 2 are inserted
|
||||
THEN:
|
||||
- chunk_ids_for_document returns exactly the matching chunk ids
|
||||
"""
|
||||
DocumentChunksTable.create(conn)
|
||||
DocumentChunksTable.insert_many(
|
||||
conn,
|
||||
[ChunkRow("c1", 1), ChunkRow("c2", 1), ChunkRow("c3", 2)],
|
||||
)
|
||||
assert sorted(DocumentChunksTable.chunk_ids_for_document(conn, 1)) == [
|
||||
"c1",
|
||||
"c2",
|
||||
]
|
||||
assert DocumentChunksTable.chunk_ids_for_document(conn, 2) == ["c3"]
|
||||
assert DocumentChunksTable.chunk_ids_for_document(conn, 999) == []
|
||||
|
||||
def test_delete_for_document_removes_only_that_document(
|
||||
self,
|
||||
conn: sqlite3.Connection,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- Chunks for two different documents
|
||||
WHEN:
|
||||
- delete_for_document() is called for one of them
|
||||
THEN:
|
||||
- Only that document's chunks are removed
|
||||
"""
|
||||
DocumentChunksTable.create(conn)
|
||||
DocumentChunksTable.insert_many(
|
||||
conn,
|
||||
[ChunkRow("c1", 1), ChunkRow("c2", 2)],
|
||||
)
|
||||
DocumentChunksTable.delete_for_document(conn, 1)
|
||||
assert DocumentChunksTable.chunk_ids_for_document(conn, 1) == []
|
||||
assert DocumentChunksTable.chunk_ids_for_document(conn, 2) == ["c2"]
|
||||
|
||||
def test_delete_all_clears_every_row(self, conn: sqlite3.Connection) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- Chunks for multiple documents
|
||||
WHEN:
|
||||
- delete_all() is called
|
||||
THEN:
|
||||
- count() returns 0
|
||||
"""
|
||||
DocumentChunksTable.create(conn)
|
||||
DocumentChunksTable.insert_many(
|
||||
conn,
|
||||
[ChunkRow("c1", 1), ChunkRow("c2", 2)],
|
||||
)
|
||||
DocumentChunksTable.delete_all(conn)
|
||||
assert DocumentChunksTable.count(conn) == 0
|
||||
|
||||
def test_count_reflects_live_rows(self, conn: sqlite3.Connection) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An empty document_chunks table
|
||||
WHEN:
|
||||
- Rows are inserted then one document's rows are deleted
|
||||
THEN:
|
||||
- count() reflects the remaining row count
|
||||
"""
|
||||
DocumentChunksTable.create(conn)
|
||||
DocumentChunksTable.insert_many(
|
||||
conn,
|
||||
[ChunkRow("c1", 1), ChunkRow("c2", 1), ChunkRow("c3", 2)],
|
||||
)
|
||||
assert DocumentChunksTable.count(conn) == 3
|
||||
DocumentChunksTable.delete_for_document(conn, 1)
|
||||
assert DocumentChunksTable.count(conn) == 1
|
||||
|
||||
|
||||
class TestDocumentMetaTable:
|
||||
def test_upsert_many_then_all_modified_times(
|
||||
self,
|
||||
conn: sqlite3.Connection,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An empty document_meta table
|
||||
WHEN:
|
||||
- Two documents' modified timestamps are upserted
|
||||
THEN:
|
||||
- all_modified_times() returns both, keyed by str(document_id)
|
||||
"""
|
||||
DocumentMetaTable.create(conn)
|
||||
DocumentMetaTable.upsert_many(
|
||||
conn,
|
||||
[
|
||||
DocumentMetaRow(1, "2026-01-01T00:00:00"),
|
||||
DocumentMetaRow(2, "2026-02-02T00:00:00"),
|
||||
],
|
||||
)
|
||||
assert DocumentMetaTable.all_modified_times(conn) == {
|
||||
"1": "2026-01-01T00:00:00",
|
||||
"2": "2026-02-02T00:00:00",
|
||||
}
|
||||
|
||||
def test_upsert_many_overwrites_existing_value(
|
||||
self,
|
||||
conn: sqlite3.Connection,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A document_meta row for document 1
|
||||
WHEN:
|
||||
- upsert_many() is called again with a new modified value for
|
||||
the same document_id
|
||||
THEN:
|
||||
- The stored value is replaced, not duplicated
|
||||
"""
|
||||
DocumentMetaTable.create(conn)
|
||||
DocumentMetaTable.upsert_many(conn, [DocumentMetaRow(1, "old")])
|
||||
DocumentMetaTable.upsert_many(conn, [DocumentMetaRow(1, "new")])
|
||||
assert DocumentMetaTable.all_modified_times(conn) == {"1": "new"}
|
||||
|
||||
def test_delete_for_document_removes_only_that_row(
|
||||
self,
|
||||
conn: sqlite3.Connection,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- document_meta rows for two documents
|
||||
WHEN:
|
||||
- delete_for_document() is called for one of them
|
||||
THEN:
|
||||
- Only that document's row is removed
|
||||
"""
|
||||
DocumentMetaTable.create(conn)
|
||||
DocumentMetaTable.upsert_many(
|
||||
conn,
|
||||
[DocumentMetaRow(1, "a"), DocumentMetaRow(2, "b")],
|
||||
)
|
||||
DocumentMetaTable.delete_for_document(conn, 1)
|
||||
assert DocumentMetaTable.all_modified_times(conn) == {"2": "b"}
|
||||
|
||||
def test_delete_all_clears_every_row(self, conn: sqlite3.Connection) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- document_meta rows for multiple documents
|
||||
WHEN:
|
||||
- delete_all() is called
|
||||
THEN:
|
||||
- all_modified_times() returns an empty dict
|
||||
"""
|
||||
DocumentMetaTable.create(conn)
|
||||
DocumentMetaTable.upsert_many(
|
||||
conn,
|
||||
[DocumentMetaRow(1, "a"), DocumentMetaRow(2, "b")],
|
||||
)
|
||||
DocumentMetaTable.delete_all(conn)
|
||||
assert DocumentMetaTable.all_modified_times(conn) == {}
|
||||
|
||||
def test_copy_all_streams_every_row_to_destination(
|
||||
self,
|
||||
conn: sqlite3.Connection,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A source connection with document_meta rows for 5 documents
|
||||
- A separate, empty destination connection
|
||||
WHEN:
|
||||
- copy_all() is called with a batch size smaller than the row
|
||||
count, forcing multiple fetchmany() cycles
|
||||
THEN:
|
||||
- Every row is present on the destination connection
|
||||
"""
|
||||
DocumentMetaTable.create(conn)
|
||||
DocumentMetaTable.upsert_many(
|
||||
conn,
|
||||
[DocumentMetaRow(i, f"modified-{i}") for i in range(5)],
|
||||
)
|
||||
dst_conn = sqlite3.connect(":memory:")
|
||||
dst_conn.row_factory = sqlite3.Row
|
||||
try:
|
||||
DocumentMetaTable.create(dst_conn)
|
||||
DocumentMetaTable.copy_all(conn, dst_conn, batch_size=2)
|
||||
assert DocumentMetaTable.all_modified_times(dst_conn) == {
|
||||
str(i): f"modified-{i}" for i in range(5)
|
||||
}
|
||||
finally:
|
||||
dst_conn.close()
|
||||
|
||||
|
||||
class TestIndexMetaTable:
|
||||
@pytest.mark.parametrize(
|
||||
("setter_name", "getter_name", "value"),
|
||||
[
|
||||
("set_dim", "get_dim", 384),
|
||||
("set_embed_model", "get_embed_model", "model-a"),
|
||||
("set_schema_version", "get_schema_version", 2),
|
||||
],
|
||||
)
|
||||
def test_typed_accessor_roundtrip(
|
||||
self,
|
||||
conn: sqlite3.Connection,
|
||||
setter_name: str,
|
||||
getter_name: str,
|
||||
value: int | str,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An empty index_meta table
|
||||
WHEN:
|
||||
- A typed accessor's setter is called then the getter is read back
|
||||
THEN:
|
||||
- The same value is returned, correctly typed (int or str)
|
||||
"""
|
||||
IndexMetaTable.create(conn)
|
||||
getter = getattr(IndexMetaTable, getter_name)
|
||||
setter = getattr(IndexMetaTable, setter_name)
|
||||
assert getter(conn) is None
|
||||
setter(conn, value)
|
||||
assert getter(conn) == value
|
||||
|
||||
def test_total_inserts_starts_at_zero(self, conn: sqlite3.Connection) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An empty index_meta table
|
||||
WHEN:
|
||||
- get_total_inserts() is read before anything is set
|
||||
THEN:
|
||||
- 0 is returned
|
||||
"""
|
||||
IndexMetaTable.create(conn)
|
||||
assert IndexMetaTable.get_total_inserts(conn) == 0
|
||||
|
||||
def test_increment_total_inserts_accumulates(
|
||||
self,
|
||||
conn: sqlite3.Connection,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An empty index_meta table
|
||||
WHEN:
|
||||
- increment_total_inserts() is called twice
|
||||
THEN:
|
||||
- get_total_inserts() returns the running sum
|
||||
"""
|
||||
IndexMetaTable.create(conn)
|
||||
IndexMetaTable.increment_total_inserts(conn, 5)
|
||||
IndexMetaTable.increment_total_inserts(conn, 3)
|
||||
assert IndexMetaTable.get_total_inserts(conn) == 8
|
||||
|
||||
def test_reset_total_inserts_sets_absolute_value(
|
||||
self,
|
||||
conn: sqlite3.Connection,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A total_inserts counter already at a high value
|
||||
WHEN:
|
||||
- reset_total_inserts() is called with a lower value
|
||||
THEN:
|
||||
- get_total_inserts() returns exactly that value, not a sum
|
||||
"""
|
||||
IndexMetaTable.create(conn)
|
||||
IndexMetaTable.increment_total_inserts(conn, 100)
|
||||
IndexMetaTable.reset_total_inserts(conn, 7)
|
||||
assert IndexMetaTable.get_total_inserts(conn) == 7
|
||||
@@ -3735,15 +3735,15 @@ crypto = [
|
||||
|
||||
[[package]]
|
||||
name = "pymdown-extensions"
|
||||
version = "10.21.3"
|
||||
version = "11.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "markdown", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "pyyaml", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/9e/26/d1015444da4d952a1ca487a236b522eb979766f0295a0bd0c5fc089989a9/pymdown_extensions-10.21.3.tar.gz", hash = "sha256:72cfcf55f07aea0d4af2c4f11dd4e52466ddfb1bb819673146398e0bd3a77354", size = 854140, upload-time = "2026-05-13T12:57:32.267Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/47/67/f1e79672a5f91985577c7984c9709ca110e4fd37fe7fd167b60422e6ccc2/pymdown_extensions-11.0.tar.gz", hash = "sha256:8269cef0247f9e2d0a62fcea10860aba05c1cbab5470fd4b63230b96434dc589", size = 857049, upload-time = "2026-06-23T02:27:45.146Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/7e/85/545a951eecc270fcd688288c600017e2050a1aacb56c711d208586d3e470/pymdown_extensions-10.21.3-py3-none-any.whl", hash = "sha256:d7a5d08014fc571e80ca21dd6f854e31f94c489800350564d55d15b3c41e76b6", size = 269002, upload-time = "2026-05-13T12:57:30.296Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/af/b6/1ae53367e28b9cffa3be7574e13fbe4589694272fd47710fbdbafd3d63c6/pymdown_extensions-11.0-py3-none-any.whl", hash = "sha256:fbc4acb641814fa9d17521bbd21a5240ef739a662f11c06330c4b78c93e954d6", size = 269415, upload-time = "2026-06-23T02:27:43.826Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
||||
Reference in New Issue
Block a user