mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-08-30 22:47:15 +00:00
Compare commits
10
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 shamoon
|
4c9cc18165 | ||
|
shamoon
|
784c87a10d | ||
|
shamoon
|
699d856286 | ||
 GitHub Actions
|
b20d707f2a | ||
|
shamoon
|
fa6e481224 | ||
|
GitHub Actions
|
aba32fbd57 | ||
|
shamoon
|
d371085699 | ||
|
shamoon
|
14b6a41b88 | ||
|
shamoon
|
8af3e69084 | ||
|
shamoon
|
1d23a9550c |
+53
-46
@@ -662,7 +662,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">449,450</context>
|
||||
<context context-type="linenumber">453,454</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>
|
||||
@@ -727,11 +727,11 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
|
||||
<context context-type="linenumber">318</context>
|
||||
<context context-type="linenumber">319</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
|
||||
<context context-type="linenumber">320</context>
|
||||
<context context-type="linenumber">321</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="2272120016352772836" datatype="html">
|
||||
@@ -838,7 +838,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">468</context>
|
||||
<context context-type="linenumber">472</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/document-list.component.html</context>
|
||||
@@ -1362,7 +1362,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">394,395</context>
|
||||
<context context-type="linenumber">398,399</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.html</context>
|
||||
@@ -1611,7 +1611,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">169</context>
|
||||
<context context-type="linenumber">173</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="2691296884221415710" datatype="html">
|
||||
@@ -1626,7 +1626,7 @@
|
||||
</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>
|
||||
@@ -1661,7 +1661,7 @@
|
||||
</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>
|
||||
@@ -1696,7 +1696,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">182</context>
|
||||
<context context-type="linenumber">186</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.html</context>
|
||||
@@ -3330,11 +3330,11 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
|
||||
<context context-type="linenumber">326,327</context>
|
||||
<context context-type="linenumber">327,328</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
|
||||
<context context-type="linenumber">329</context>
|
||||
<context context-type="linenumber">330</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="472206565520537964" datatype="html">
|
||||
@@ -3492,49 +3492,49 @@
|
||||
<source>GitHub</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
|
||||
<context context-type="linenumber">336</context>
|
||||
<context context-type="linenumber">337</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4112664765954374539" datatype="html">
|
||||
<source>is available.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
|
||||
<context context-type="linenumber">346</context>
|
||||
<context context-type="linenumber">347</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="1175891574282637937" datatype="html">
|
||||
<source>Click to view.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
|
||||
<context context-type="linenumber">346</context>
|
||||
<context context-type="linenumber">347</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="9811291095862612" datatype="html">
|
||||
<source>Paperless-ngx can automatically check for updates</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
|
||||
<context context-type="linenumber">350</context>
|
||||
<context context-type="linenumber">351</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="894819944961861800" datatype="html">
|
||||
<source> How does this work? </source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
|
||||
<context context-type="linenumber">358</context>
|
||||
<context context-type="linenumber">359</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="509090351011426949" datatype="html">
|
||||
<source>Update available</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
|
||||
<context context-type="linenumber">370</context>
|
||||
<context context-type="linenumber">371</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="1329827712962827905" datatype="html">
|
||||
<source>Configure update checking</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
|
||||
<context context-type="linenumber">375</context>
|
||||
<context context-type="linenumber">376</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="1542489069631984294" datatype="html">
|
||||
@@ -5227,7 +5227,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">360,361</context>
|
||||
<context context-type="linenumber">364,365</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="8057014866157903311" datatype="html">
|
||||
@@ -6134,7 +6134,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">167</context>
|
||||
<context context-type="linenumber">171</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/document-list.component.html</context>
|
||||
@@ -7627,6 +7627,13 @@
|
||||
<context context-type="linenumber">120</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5700628356844396417" datatype="html">
|
||||
<source>{VAR_PLURAL, plural, =1 {1 existing value suggested below} other {<x id="INTERPOLATION"/> existing values suggested below}}</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
|
||||
<context context-type="linenumber">53</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="9180110319941008393" datatype="html">
|
||||
<source>Environment</source>
|
||||
<context-group purpose="location">
|
||||
@@ -8314,21 +8321,21 @@
|
||||
<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">164,165</context>
|
||||
<context context-type="linenumber">168,169</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5114742157723900905" datatype="html">
|
||||
<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">171</context>
|
||||
<context context-type="linenumber">175</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">183</context>
|
||||
<context context-type="linenumber">187</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/manage/saved-views/saved-views.component.html</context>
|
||||
@@ -8339,14 +8346,14 @@
|
||||
<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">290,291</context>
|
||||
<context context-type="linenumber">294,295</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">299,300</context>
|
||||
<context context-type="linenumber">303,304</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/metadata-collapse/metadata-collapse.component.ts</context>
|
||||
@@ -8357,147 +8364,147 @@
|
||||
<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">306,307</context>
|
||||
<context context-type="linenumber">310,311</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">310,311</context>
|
||||
<context context-type="linenumber">314,315</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">314,315</context>
|
||||
<context context-type="linenumber">318,319</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">318,319</context>
|
||||
<context context-type="linenumber">322,323</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">322,323</context>
|
||||
<context context-type="linenumber">326,327</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">326,327</context>
|
||||
<context context-type="linenumber">330,331</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">330,331</context>
|
||||
<context context-type="linenumber">334,335</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">335,336</context>
|
||||
<context context-type="linenumber">339,340</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">341,342</context>
|
||||
<context context-type="linenumber">345,346</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">350</context>
|
||||
<context context-type="linenumber">354</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">353</context>
|
||||
<context context-type="linenumber">357</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="{{document().notes.length}}"/><x id="CLOSE_TAG_SPAN" ctype="x-span" equiv-text="</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">372,375</context>
|
||||
<context context-type="linenumber">376,379</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">383,384</context>
|
||||
<context context-type="linenumber">387,388</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="{{ document().duplicate_documents.length }}"/><x id="CLOSE_TAG_SPAN" ctype="x-span" equiv-text="</span>"/></source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.html</context>
|
||||
<context context-type="linenumber">406,409</context>
|
||||
<context context-type="linenumber">410,413</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">411,412</context>
|
||||
<context context-type="linenumber">415,416</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">422,423</context>
|
||||
<context context-type="linenumber">426,427</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">451</context>
|
||||
<context context-type="linenumber">455</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">453</context>
|
||||
<context context-type="linenumber">457</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">455,456</context>
|
||||
<context context-type="linenumber">459,460</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">463</context>
|
||||
<context context-type="linenumber">467</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">517</context>
|
||||
<context context-type="linenumber">521</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5758784066858623886" datatype="html">
|
||||
|
||||
@@ -73,7 +73,7 @@
|
||||
<div class="container-fluid">
|
||||
<div class="row">
|
||||
<nav id="sidebarMenu" class="d-md-block bg-light sidebar collapse"
|
||||
[ngClass]="slimSidebarEnabled ? 'slim' : 'col-md-3 col-lg-2 col-xxxl-1'" [class.animating]="slimSidebarAnimating()"
|
||||
[ngClass]="slimSidebarEnabled ? 'slim' : 'expanded'" [class.animating]="slimSidebarAnimating()"
|
||||
[ngbCollapse]="isMenuCollapsed()">
|
||||
@if (canSaveSettings) {
|
||||
<button class="btn btn-sm btn-dark sidebar-slim-toggler" (click)="toggleSlimSidebar()" [aria-label]="slimSidebarEnabled ? 'Expand sidebar' : 'Collapse sidebar'" i18n-aria-label>
|
||||
@@ -90,7 +90,7 @@
|
||||
<a class="nav-link" routerLink="dashboard" routerLinkActive="active" (click)="closeMenu()"
|
||||
ngbPopover="Dashboard" i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end"
|
||||
container="body" triggers="mouseenter:mouseleave" popoverClass="popover-slim">
|
||||
<i-bs class="me-2" name="house"></i-bs><span><ng-container i18n>Dashboard</ng-container></span>
|
||||
<i-bs class="me-2" name="house"></i-bs><span class="nav-link-label"><ng-container i18n>Dashboard</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
<li class="nav-item app-link" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.Document }">
|
||||
@@ -99,7 +99,7 @@
|
||||
(click)="closeMenu()"
|
||||
ngbPopover="Documents" i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end"
|
||||
container="body" triggers="mouseenter:mouseleave" popoverClass="popover-slim">
|
||||
<i-bs class="me-2" name="files"></i-bs><span><ng-container i18n>Documents</ng-container></span>
|
||||
<i-bs class="me-2" name="files"></i-bs><span class="nav-link-label"><ng-container i18n>Documents</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
@@ -170,7 +170,7 @@
|
||||
[class.text-truncate]="!slimSidebarEnabled" (click)="closeAll()"
|
||||
ngbPopover="Close all" i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end"
|
||||
container="body" triggers="mouseenter:mouseleave" popoverClass="popover-slim">
|
||||
<i-bs class="me-2" name="x"></i-bs><span><ng-container i18n>Close all</ng-container></span>
|
||||
<i-bs class="me-2" name="x"></i-bs><span class="nav-link-label"><ng-container i18n>Close all</ng-container></span>
|
||||
</button>
|
||||
</li>
|
||||
}
|
||||
@@ -189,7 +189,7 @@
|
||||
[routerLinkActiveOptions]="{ exact: !(slimSidebarEnabled || attributesSectionsCollapsed) }" (click)="closeMenu()"
|
||||
ngbPopover="Attributes" i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end"
|
||||
container="body" triggers="mouseenter:mouseleave" popoverClass="popover-slim">
|
||||
<i-bs name="stack"></i-bs><span class="ms-2"><ng-container i18n>Attributes</ng-container></span>
|
||||
<i-bs name="stack"></i-bs><span class="nav-link-label ms-2"><ng-container i18n>Attributes</ng-container></span>
|
||||
</a>
|
||||
@if (!slimSidebarEnabled && canSaveSettings) {
|
||||
<button
|
||||
@@ -210,27 +210,27 @@
|
||||
<ul class="nav flex-column">
|
||||
<li class="nav-item app-link" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.Tag }">
|
||||
<a class="nav-link" routerLink="attributes/tags" routerLinkActive="active" (click)="closeMenu()">
|
||||
<i-bs class="me-2" name="tags"></i-bs><span><ng-container i18n>Tags</ng-container></span>
|
||||
<i-bs class="me-2" name="tags"></i-bs><span class="nav-link-label"><ng-container i18n>Tags</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
<li class="nav-item app-link" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.Correspondent }">
|
||||
<a class="nav-link" routerLink="attributes/correspondents" routerLinkActive="active" (click)="closeMenu()">
|
||||
<i-bs class="me-2" name="person"></i-bs><span><ng-container i18n>Correspondents</ng-container></span>
|
||||
<i-bs class="me-2" name="person"></i-bs><span class="nav-link-label"><ng-container i18n>Correspondents</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
<li class="nav-item app-link" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.DocumentType }">
|
||||
<a class="nav-link" routerLink="attributes/documenttypes" routerLinkActive="active" (click)="closeMenu()">
|
||||
<i-bs class="me-2" name="hash"></i-bs><span><ng-container i18n>Document types</ng-container></span>
|
||||
<i-bs class="me-2" name="hash"></i-bs><span class="nav-link-label"><ng-container i18n>Document types</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
<li class="nav-item app-link" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.StoragePath }">
|
||||
<a class="nav-link" routerLink="attributes/storagepaths" routerLinkActive="active" (click)="closeMenu()">
|
||||
<i-bs class="me-2" name="folder"></i-bs><span><ng-container i18n>Storage paths</ng-container></span>
|
||||
<i-bs class="me-2" name="folder"></i-bs><span class="nav-link-label"><ng-container i18n>Storage paths</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
<li class="nav-item app-link" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.CustomField }">
|
||||
<a class="nav-link" routerLink="attributes/customfields" routerLinkActive="active" (click)="closeMenu()">
|
||||
<i-bs class="me-2" name="ui-radios"></i-bs><span><ng-container i18n>Custom fields</ng-container></span>
|
||||
<i-bs class="me-2" name="ui-radios"></i-bs><span class="nav-link-label"><ng-container i18n>Custom fields</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
@@ -241,7 +241,7 @@
|
||||
<a class="nav-link" routerLink="savedviews" routerLinkActive="active" (click)="closeMenu()"
|
||||
ngbPopover="Saved Views" i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end"
|
||||
container="body" triggers="mouseenter:mouseleave" popoverClass="popover-slim">
|
||||
<i-bs class="me-2" name="window-stack"></i-bs><span><ng-container i18n>Saved Views</ng-container></span>
|
||||
<i-bs class="me-2" name="window-stack"></i-bs><span class="nav-link-label"><ng-container i18n>Saved Views</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
<li class="nav-item app-link"
|
||||
@@ -250,7 +250,7 @@
|
||||
<a class="nav-link" routerLink="workflows" routerLinkActive="active" (click)="closeMenu()"
|
||||
ngbPopover="Workflows" i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end"
|
||||
container="body" triggers="mouseenter:mouseleave" popoverClass="popover-slim">
|
||||
<i-bs class="me-2" name="boxes"></i-bs><span><ng-container i18n>Workflows</ng-container></span>
|
||||
<i-bs class="me-2" name="boxes"></i-bs><span class="nav-link-label"><ng-container i18n>Workflows</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
<li class="nav-item app-link" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.MailAccount }"
|
||||
@@ -258,14 +258,14 @@
|
||||
<a class="nav-link" routerLink="mail" routerLinkActive="active" (click)="closeMenu()" ngbPopover="Mail"
|
||||
i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end" container="body"
|
||||
triggers="mouseenter:mouseleave" popoverClass="popover-slim">
|
||||
<i-bs class="me-2" name="envelope"></i-bs><span><ng-container i18n>Mail</ng-container></span>
|
||||
<i-bs class="me-2" name="envelope"></i-bs><span class="nav-link-label"><ng-container i18n>Mail</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
<li class="nav-item app-link" *pngxIfPermissions="{ action: PermissionAction.Delete, type: PermissionType.Document }">
|
||||
<a class="nav-link" routerLink="trash" routerLinkActive="active" (click)="closeMenu()" ngbPopover="Trash"
|
||||
i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end" container="body"
|
||||
triggers="mouseenter:mouseleave" popoverClass="popover-slim">
|
||||
<i-bs class="me-2" name="trash"></i-bs><span><ng-container i18n>Trash</ng-container></span>
|
||||
<i-bs class="me-2" name="trash"></i-bs><span class="nav-link-label"><ng-container i18n>Trash</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
@@ -281,21 +281,21 @@
|
||||
<a class="nav-link" routerLink="settings" routerLinkActive="active" (click)="closeMenu()"
|
||||
ngbPopover="Settings" i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end"
|
||||
container="body" triggers="mouseenter:mouseleave" popoverClass="popover-slim">
|
||||
<i-bs class="me-2" name="gear"></i-bs><span><ng-container i18n>Settings</ng-container></span>
|
||||
<i-bs class="me-2" name="gear"></i-bs><span class="nav-link-label"><ng-container i18n>Settings</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
<li class="nav-item app-link" *pngxIfPermissions="{ action: PermissionAction.Change, type: PermissionType.AppConfig }">
|
||||
<a class="nav-link" routerLink="config" routerLinkActive="active" (click)="closeMenu()"
|
||||
ngbPopover="Configuration" i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end"
|
||||
container="body" triggers="mouseenter:mouseleave" popoverClass="popover-slim">
|
||||
<i-bs class="me-2" name="sliders2-vertical"></i-bs><span><ng-container i18n>Configuration</ng-container></span>
|
||||
<i-bs class="me-2" name="sliders2-vertical"></i-bs><span class="nav-link-label"><ng-container i18n>Configuration</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
<li class="nav-item app-link" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.User }">
|
||||
<a class="nav-link" routerLink="usersgroups" routerLinkActive="active" (click)="closeMenu()"
|
||||
ngbPopover="Users & Groups" i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end"
|
||||
container="body" triggers="mouseenter:mouseleave" popoverClass="popover-slim">
|
||||
<i-bs class="me-2" name="people"></i-bs><span><ng-container i18n>Users & Groups</ng-container></span>
|
||||
<i-bs class="me-2" name="people"></i-bs><span class="nav-link-label"><ng-container i18n>Users & Groups</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
<li class="nav-item app-link"
|
||||
@@ -304,9 +304,10 @@
|
||||
<a class="nav-link" routerLink="tasks" routerLinkActive="active" (click)="closeMenu()"
|
||||
ngbPopover="Tasks" i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end"
|
||||
container="body" triggers="mouseenter:mouseleave" popoverClass="popover-slim">
|
||||
<i-bs class="me-2" name="list-task"></i-bs><span><ng-container i18n>Tasks</ng-container>@if (tasksService.needsAttentionTasks.length > 0) {
|
||||
<span><span class="badge bg-danger ms-2 d-inline">{{tasksService.needsAttentionTasks.length}}</span></span>
|
||||
}</span>
|
||||
<i-bs class="me-2" name="list-task"></i-bs><span class="nav-link-label"><ng-container i18n>Tasks</ng-container></span>
|
||||
@if (tasksService.needsAttentionTasks.length > 0 && !slimSidebarEnabled) {
|
||||
<span class="badge bg-danger ms-2 d-inline flex-shrink-0">{{tasksService.needsAttentionTasks.length}}</span>
|
||||
}
|
||||
@if (tasksService.needsAttentionTasks.length > 0 && slimSidebarEnabled) {
|
||||
<span class="badge bg-danger position-absolute top-0 end-0 d-none d-md-block">{{tasksService.needsAttentionTasks.length}}</span>
|
||||
}
|
||||
@@ -317,7 +318,7 @@
|
||||
<a class="nav-link" routerLink="logs" routerLinkActive="active" (click)="closeMenu()" ngbPopover="Logs"
|
||||
i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end" container="body"
|
||||
triggers="mouseenter:mouseleave" popoverClass="popover-slim">
|
||||
<i-bs class="me-2" name="text-left"></i-bs><span><ng-container i18n>Logs</ng-container></span>
|
||||
<i-bs class="me-2" name="text-left"></i-bs><span class="nav-link-label"><ng-container i18n>Logs</ng-container></span>
|
||||
</a>
|
||||
</li>
|
||||
}
|
||||
@@ -388,7 +389,7 @@
|
||||
</nav>
|
||||
|
||||
<main role="main" class="ms-sm-auto px-md-4" [class.mobile-search-hidden]="mobileSearchHidden()"
|
||||
[ngClass]="slimSidebarEnabled ? 'col-slim' : 'col-md-9 col-lg-10 col-xxxl-11'">
|
||||
[ngClass]="slimSidebarEnabled ? 'col-slim' : 'col-sidebar-expanded'">
|
||||
<router-outlet></router-outlet>
|
||||
</main>
|
||||
</div>
|
||||
|
||||
@@ -11,6 +11,7 @@
|
||||
border-right: 1px solid color-mix(in srgb, var(--bs-border-color) 65%, transparent);
|
||||
overflow-y: auto;
|
||||
--pngx-sidebar-width: 100%;
|
||||
width: var(--pngx-sidebar-width);
|
||||
max-width: var(--pngx-sidebar-width);
|
||||
transition: all .2s ease;
|
||||
|
||||
@@ -32,17 +33,10 @@
|
||||
display: none !important;
|
||||
}
|
||||
|
||||
// These come from the col-* classes for non-slim sidebar, needed for animation
|
||||
@media (min-width: 768px) {
|
||||
--pngx-sidebar-width: 25%;
|
||||
}
|
||||
|
||||
@media (min-width: 992px) {
|
||||
--pngx-sidebar-width: 16.66666667%;
|
||||
}
|
||||
|
||||
@media (min-width: 2400px) {
|
||||
--pngx-sidebar-width: 8.33333333%;
|
||||
&.expanded {
|
||||
--pngx-sidebar-width: var(--pngx-sidebar-expanded-width);
|
||||
}
|
||||
}
|
||||
}
|
||||
@media (max-width: 767.98px) {
|
||||
@@ -260,6 +254,26 @@ main {
|
||||
}
|
||||
}
|
||||
|
||||
.sidebar .nav-link:has(> .nav-link-label) {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
min-width: 0;
|
||||
|
||||
> i-bs {
|
||||
flex: 0 0 auto;
|
||||
}
|
||||
|
||||
> .nav-link-label {
|
||||
min-width: 0;
|
||||
overflow: hidden;
|
||||
text-overflow: ellipsis;
|
||||
}
|
||||
}
|
||||
|
||||
.sidebar:not(.slim):not(.animating) .nav-link > .nav-link-label {
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
.sidebar .nav-anchor, .sidebar .nav-label {
|
||||
padding: .25rem .7rem;
|
||||
}
|
||||
@@ -385,7 +399,7 @@ main {
|
||||
}
|
||||
|
||||
::ng-deep .navbar-official-logo {
|
||||
will-change: filter; // Safari repaints the whole navbar on filter change without this
|
||||
will-change: filter; // prevent resizing the filter region on hover and nudging the logo a pixel
|
||||
filter: drop-shadow(0 1px 2px rgba(var(--pngx-navbar-brand-shadow-rgb), .3));
|
||||
transition: filter .15s ease-in-out;
|
||||
|
||||
@@ -398,6 +412,8 @@ main {
|
||||
width: 1.65rem;
|
||||
height: 1.65rem;
|
||||
flex: 0 0 auto;
|
||||
will-change: filter; // prevent resizing the filter region on hover and nudging the logo a pixel
|
||||
filter: drop-shadow(0 2px 3px rgba(var(--pngx-navbar-brand-shadow-rgb), 0));
|
||||
transition: filter .15s ease-in-out;
|
||||
}
|
||||
|
||||
@@ -430,6 +446,8 @@ main {
|
||||
max-width: 5rem;
|
||||
flex: 0 0 auto;
|
||||
object-fit: contain;
|
||||
will-change: filter; // prevent resizing the filter region on hover and nudging the logo a pixel
|
||||
filter: drop-shadow(0 2px 3px rgba(var(--pngx-navbar-brand-shadow-rgb), 0));
|
||||
transition: filter .15s ease-in-out, transform .15s ease-in-out;
|
||||
}
|
||||
|
||||
|
||||
+9
-4
@@ -25,29 +25,34 @@
|
||||
|
||||
<div ngbDropdownMenu aria-labelledby="suggestionsDropdown" class="shadow suggestions-dropdown">
|
||||
<div class="list-group list-group-flush small pb-0">
|
||||
@if (totalSuggestions === 0) {
|
||||
@if (novelSuggestions === 0 && reusableSuggestions === 0) {
|
||||
<div class="list-group-item text-muted fst-italic">
|
||||
<small class="text-muted small fst-italic" i18n>No novel suggestions</small>
|
||||
</div>
|
||||
}
|
||||
@if (suggestions()?.suggested_tags.length > 0) {
|
||||
@if (suggestions()?.suggested_tags?.length > 0) {
|
||||
<small class="list-group-item text-uppercase text-muted small"><i-bs class="me-2" name="tags"></i-bs><ng-container i18n>Tags</ng-container></small>
|
||||
@for (tag of suggestions().suggested_tags; track tag) {
|
||||
<button type="button" class="list-group-item list-group-item-action bg-light" (click)="addTag.emit(tag)">{{ tag }}</button>
|
||||
}
|
||||
}
|
||||
@if (suggestions()?.suggested_document_types.length > 0) {
|
||||
@if (suggestions()?.suggested_document_types?.length > 0) {
|
||||
<div class="list-group-item text-uppercase text-muted small"><i-bs class="me-2" name="hash"></i-bs><ng-container i18n>Document Types</ng-container></div>
|
||||
@for (type of suggestions().suggested_document_types; track type) {
|
||||
<button type="button" class="list-group-item list-group-item-action bg-light" (click)="addDocumentType.emit(type)">{{ type }}</button>
|
||||
}
|
||||
}
|
||||
@if (suggestions()?.suggested_correspondents.length > 0) {
|
||||
@if (suggestions()?.suggested_correspondents?.length > 0) {
|
||||
<div class="list-group-item text-uppercase text-muted small"><i-bs class="me-2" name="person"></i-bs><ng-container i18n>Correspondents</ng-container></div>
|
||||
@for (correspondent of suggestions().suggested_correspondents; track correspondent) {
|
||||
<button type="button" class="list-group-item list-group-item-action bg-light" (click)="addCorrespondent.emit(correspondent)">{{ correspondent }}</button>
|
||||
}
|
||||
}
|
||||
@if (reusableSuggestions > 0) {
|
||||
<div class="list-group-item text-muted fst-italic">
|
||||
<small class="text-muted small fst-italic" i18n>{reusableSuggestions, plural, =1 {1 existing value suggested below} other {{{reusableSuggestions}} existing values suggested below}}</small>
|
||||
</div>
|
||||
}
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
+101
-1
@@ -21,15 +21,115 @@ describe('SuggestionsDropdownComponent', () => {
|
||||
fixture.detectChanges()
|
||||
})
|
||||
|
||||
it('should calculate totalSuggestions', () => {
|
||||
it('should exclude suggested storage path names from totalSuggestions', () => {
|
||||
fixture.componentRef.setInput('suggestions', {
|
||||
suggested_correspondents: ['John Doe'],
|
||||
suggested_tags: ['Tag1', 'Tag2'],
|
||||
suggested_document_types: ['Type1'],
|
||||
suggested_storage_paths: ['Finance/Invoices'],
|
||||
})
|
||||
expect(component.totalSuggestions).toBe(4)
|
||||
})
|
||||
|
||||
it('should count suggestions when a category is absent from the response', () => {
|
||||
fixture.componentRef.setInput('suggestions', {
|
||||
suggested_tags: ['Tag1'],
|
||||
})
|
||||
expect(component.totalSuggestions).toBe(1)
|
||||
})
|
||||
|
||||
it('should count reused values the document does not have yet', () => {
|
||||
fixture.componentRef.setInput('suggestions', {
|
||||
tags: [1, 2, 3],
|
||||
correspondents: [10],
|
||||
document_types: [20],
|
||||
suggested_tags: ['NewTag'],
|
||||
})
|
||||
fixture.componentRef.setInput('appliedTags', [2])
|
||||
fixture.componentRef.setInput('appliedDocumentType', 20)
|
||||
|
||||
// tags 1 and 3 are not applied yet, correspondent 10 is not set, tag 2 and
|
||||
// document type 20 already are.
|
||||
expect(component.reusableSuggestions).toBe(3)
|
||||
expect(component.novelSuggestions).toBe(1)
|
||||
expect(component.totalSuggestions).toBe(4)
|
||||
})
|
||||
|
||||
it('should not count reused values that are already applied', () => {
|
||||
fixture.componentRef.setInput('suggestions', {
|
||||
tags: [1],
|
||||
correspondents: [10],
|
||||
document_types: [20],
|
||||
})
|
||||
fixture.componentRef.setInput('appliedTags', [1])
|
||||
fixture.componentRef.setInput('appliedCorrespondent', 10)
|
||||
fixture.componentRef.setInput('appliedDocumentType', 20)
|
||||
|
||||
expect(component.totalSuggestions).toBe(0)
|
||||
})
|
||||
|
||||
it('should point at the fields when suggestions are all reused', () => {
|
||||
// The dropdown lists only values to create, so a response made entirely of
|
||||
// reused existing objects used to render as "No novel suggestions".
|
||||
fixture.componentRef.setInput('aiEnabled', true)
|
||||
fixture.componentRef.setInput('suggestions', {
|
||||
tags: [1, 2],
|
||||
suggested_tags: [],
|
||||
suggested_correspondents: [],
|
||||
suggested_document_types: [],
|
||||
})
|
||||
fixture.detectChanges()
|
||||
component.clickSuggest()
|
||||
fixture.detectChanges()
|
||||
|
||||
expect(fixture.nativeElement.textContent).toContain(
|
||||
'2 existing values suggested below'
|
||||
)
|
||||
expect(fixture.nativeElement.textContent).not.toContain(
|
||||
'No novel suggestions'
|
||||
)
|
||||
})
|
||||
|
||||
it('should account for reused values alongside values to create', () => {
|
||||
// The badge counts both, but only the novel names are listed here, so the
|
||||
// dropdown has to say where the rest of the count came from.
|
||||
fixture.componentRef.setInput('aiEnabled', true)
|
||||
fixture.componentRef.setInput('suggestions', {
|
||||
tags: [6, 3],
|
||||
suggested_tags: ['Arbitration', 'New York'],
|
||||
suggested_correspondents: [],
|
||||
suggested_document_types: [],
|
||||
})
|
||||
fixture.detectChanges()
|
||||
component.clickSuggest()
|
||||
fixture.detectChanges()
|
||||
|
||||
expect(component.totalSuggestions).toBe(4)
|
||||
expect(fixture.nativeElement.textContent).toContain('Arbitration')
|
||||
expect(fixture.nativeElement.textContent).toContain(
|
||||
'2 existing values suggested below'
|
||||
)
|
||||
})
|
||||
|
||||
it('should count classic (non-AI) suggestions, which are ids only', () => {
|
||||
// /api/documents/{id}/suggestions/ returns only id arrays and no
|
||||
// suggested_* keys at all, so every one of its suggestions is a reused
|
||||
// existing object - including storage paths.
|
||||
fixture.componentRef.setInput('suggestions', {
|
||||
correspondents: [4],
|
||||
tags: [6, 3],
|
||||
document_types: [2],
|
||||
storage_paths: [7],
|
||||
dates: ['2005-01-01'],
|
||||
})
|
||||
|
||||
expect(component.novelSuggestions).toBe(0)
|
||||
expect(component.totalSuggestions).toBe(5)
|
||||
|
||||
fixture.componentRef.setInput('appliedStoragePath', 7)
|
||||
expect(component.totalSuggestions).toBe(4)
|
||||
})
|
||||
|
||||
it('should show when a completed request returned no suggestions', () => {
|
||||
fixture.componentRef.setInput('suggestions', {
|
||||
correspondents: [],
|
||||
|
||||
+41
-4
@@ -25,6 +25,11 @@ export class SuggestionsDropdownComponent {
|
||||
readonly loading = input(false)
|
||||
readonly disabled = input(false)
|
||||
|
||||
readonly appliedTags = input<number[]>([])
|
||||
readonly appliedCorrespondent = input<number>(null)
|
||||
readonly appliedDocumentType = input<number>(null)
|
||||
readonly appliedStoragePath = input<number>(null)
|
||||
|
||||
@Output()
|
||||
getSuggestions: EventEmitter<SuggestionsDropdownComponent> =
|
||||
new EventEmitter()
|
||||
@@ -54,14 +59,46 @@ export class SuggestionsDropdownComponent {
|
||||
}
|
||||
}
|
||||
|
||||
get totalSuggestions(): number {
|
||||
get novelSuggestions(): number {
|
||||
return (
|
||||
this.suggestions()?.suggested_correspondents?.length +
|
||||
this.suggestions()?.suggested_tags?.length +
|
||||
this.suggestions()?.suggested_document_types?.length || 0
|
||||
(this.suggestions()?.suggested_correspondents?.length ?? 0) +
|
||||
(this.suggestions()?.suggested_tags?.length ?? 0) +
|
||||
(this.suggestions()?.suggested_document_types?.length ?? 0)
|
||||
)
|
||||
}
|
||||
|
||||
get reusableSuggestions(): number {
|
||||
const correspondent = this.appliedCorrespondent()
|
||||
const documentType = this.appliedDocumentType()
|
||||
const storagePath = this.appliedStoragePath()
|
||||
// Storage paths count here but not in novelSuggestions: an existing one
|
||||
// can be applied from the field, a suggested name cannot create one.
|
||||
return (
|
||||
this.countUnapplied(this.suggestions()?.tags, this.appliedTags()) +
|
||||
this.countUnapplied(
|
||||
this.suggestions()?.correspondents,
|
||||
correspondent ? [correspondent] : []
|
||||
) +
|
||||
this.countUnapplied(
|
||||
this.suggestions()?.document_types,
|
||||
documentType ? [documentType] : []
|
||||
) +
|
||||
this.countUnapplied(
|
||||
this.suggestions()?.storage_paths,
|
||||
storagePath ? [storagePath] : []
|
||||
)
|
||||
)
|
||||
}
|
||||
|
||||
get totalSuggestions(): number {
|
||||
return this.novelSuggestions + this.reusableSuggestions
|
||||
}
|
||||
|
||||
private countUnapplied(suggested: number[], applied: number[]): number {
|
||||
return (suggested ?? []).filter((id) => !(applied ?? []).includes(id))
|
||||
.length
|
||||
}
|
||||
|
||||
get noSuggestions(): boolean {
|
||||
const suggestions = this.suggestions()
|
||||
return (
|
||||
|
||||
+1
-1
@@ -9,7 +9,7 @@
|
||||
<input type="file" class="visually-hidden" (change)="onFileSelected($event)" multiple #fileUpload>
|
||||
</form>
|
||||
@if (getStatus().length > 0) {
|
||||
<div class="fixed-bottom p-2 p-md-4 d-flex justify-content-end pe-none consumer-status-list" [ngClass]="slimSidebarEnabled ? 'col-slim' : 'offset-md-3 offset-lg-2'">
|
||||
<div class="fixed-bottom p-2 p-md-4 d-flex justify-content-end pe-none consumer-status-list" [ngClass]="slimSidebarEnabled ? 'col-slim' : 'offset-sidebar-expanded'">
|
||||
<div class="col col-lg-4 col-xl-3 ps-0 pe-0 ps-lg-3 pe-lg-0 pe-auto overflow-y-scroll">
|
||||
<div class="card shadow-sm consumer-status-card">
|
||||
<div class="card-body">
|
||||
|
||||
@@ -134,6 +134,10 @@
|
||||
[loading]="suggestionsLoading()"
|
||||
[suggestions]="suggestions()"
|
||||
[aiEnabled]="aiEnabled"
|
||||
[appliedTags]="documentForm.value.tags"
|
||||
[appliedCorrespondent]="documentForm.value.correspondent"
|
||||
[appliedDocumentType]="documentForm.value.document_type"
|
||||
[appliedStoragePath]="documentForm.value.storage_path"
|
||||
(getSuggestions)="getSuggestions()"
|
||||
(addTag)="createTag($event)"
|
||||
(addDocumentType)="createDocumentType($event)"
|
||||
|
||||
@@ -12,9 +12,11 @@
|
||||
margin-right: 0 !important;
|
||||
}
|
||||
|
||||
main.col-lg-10 {
|
||||
main {
|
||||
max-width: 100%;
|
||||
flex-basis: 100%;
|
||||
width: 100% !important;
|
||||
padding-left: 0 !important;
|
||||
display: block;
|
||||
}
|
||||
|
||||
|
||||
+10
-11
@@ -52,20 +52,10 @@ $grid-breakpoints: (
|
||||
}
|
||||
}
|
||||
|
||||
@media (min-width: 2400px) {
|
||||
.col-xxxl-1 {
|
||||
flex: 0 0 auto;
|
||||
width: 8.33333333%;
|
||||
}
|
||||
.col-xxxl-11 {
|
||||
flex: 0 0 auto;
|
||||
width:91.66666667%
|
||||
}
|
||||
}
|
||||
|
||||
// Paperless-ngx styles
|
||||
body {
|
||||
--pngx-body-font-size: 0.875rem;
|
||||
--pngx-sidebar-expanded-width: clamp(15rem, 16.66666667vw, 20rem);
|
||||
font-size: var(--pngx-body-font-size);
|
||||
height: 100vh;
|
||||
letter-spacing: -0.005em;
|
||||
@@ -107,6 +97,15 @@ body {
|
||||
.col-slim {
|
||||
padding-left: calc(56px + $grid-gutter-width) !important;
|
||||
}
|
||||
|
||||
.col-sidebar-expanded {
|
||||
flex: 0 0 auto;
|
||||
width: calc(100% - var(--pngx-sidebar-expanded-width));
|
||||
}
|
||||
|
||||
.offset-sidebar-expanded {
|
||||
margin-left: var(--pngx-sidebar-expanded-width);
|
||||
}
|
||||
}
|
||||
|
||||
svg.logo {
|
||||
|
||||
@@ -45,14 +45,16 @@ CLASSIFIER_HASH_KEY: Final[str] = "classifier_hash"
|
||||
CLASSIFIER_MODIFIED_KEY: Final[str] = "classifier_modified"
|
||||
# Marker distinguishing LLM suggestions from classifier-generated ones (whose
|
||||
# FORMAT_VERSION lives in a much lower range - see DocumentClassifier). Bump
|
||||
# this whenever the *shape* of the cached `suggestions` dict changes, so a
|
||||
# cache entry written by a previous release can never be read back by code
|
||||
# that expects a different shape:
|
||||
# this whenever cached suggestions must not be reused, including changes to
|
||||
# their shape or interpretation, so a previous release's result cannot leak
|
||||
# incompatible or obsolete behavior into the new one:
|
||||
# 1000 - initial LLM suggestions cache (flat lists of resolved object ids
|
||||
# per taxonomy field)
|
||||
# 1001 - suggestions reshaped to {"existing_ids": [...], "new_names":
|
||||
# [...]} per taxonomy field (#13676)
|
||||
LLM_CACHE_CLASSIFIER_VERSION: Final[int] = 1001
|
||||
# 1002 - names are always generated and optional candidate mappings are
|
||||
# validated separately, so candidate-anchored 1001 results are stale
|
||||
LLM_CACHE_CLASSIFIER_VERSION: Final[int] = 1002
|
||||
|
||||
CACHE_1_MINUTE: Final[int] = 60
|
||||
CACHE_5_MINUTES: Final[int] = 5 * CACHE_1_MINUTE
|
||||
|
||||
@@ -1,18 +1,17 @@
|
||||
import json
|
||||
import logging
|
||||
|
||||
from django.conf import settings
|
||||
from django.contrib.auth.models import User
|
||||
|
||||
from documents.models import Document
|
||||
from documents.permissions import permitted_object_ids
|
||||
from documents.permissions import restrict_queryset_to_visible
|
||||
from documents.permissions import user_is_unrestricted
|
||||
from documents.permissions import get_objects_for_user_owner_aware
|
||||
from paperless.config import AIConfig
|
||||
from paperless_ai.base_model import ClassificationSuggestions
|
||||
from paperless_ai.base_model import TaxonomyChoiceDict
|
||||
from paperless_ai.base_model import classification_suggestions_to_model
|
||||
from paperless_ai.client import AIClient
|
||||
from paperless_ai.db import db_connection_released
|
||||
from paperless_ai.indexing import _node_document_ids
|
||||
from paperless_ai.indexing import retrieve_similar_nodes
|
||||
from paperless_ai.indexing import truncate_content
|
||||
from paperless_ai.prompts.context import ClassificationPromptContext
|
||||
@@ -20,9 +19,7 @@ from paperless_ai.prompts.context import LocalizationPromptContext
|
||||
from paperless_ai.prompts.context import RagContextPromptContext
|
||||
from paperless_ai.prompts.render import render_prompt
|
||||
from paperless_ai.taxonomy import AssignedMetadata
|
||||
from paperless_ai.taxonomy import SimilarDocument
|
||||
from paperless_ai.taxonomy import TaxonomyCandidates
|
||||
from paperless_ai.taxonomy import _node_document_weights
|
||||
from paperless_ai.taxonomy import build_taxonomy_candidates
|
||||
from paperless_ai.taxonomy import empty_taxonomy_candidates
|
||||
from paperless_ai.taxonomy import format_taxonomy_for_prompt
|
||||
@@ -42,48 +39,6 @@ logger = logging.getLogger("paperless_ai.rag_classifier")
|
||||
TAXONOMY_CANDIDATE_TOP_K = 15
|
||||
|
||||
|
||||
def _fulltext_similar_documents(
|
||||
document: Document,
|
||||
user: User | None,
|
||||
top_k: int,
|
||||
) -> list[SimilarDocument]:
|
||||
"""Rank-based fallback when no embedding backend is configured. Uses
|
||||
Tantivy's "More Like This" (term-overlap similarity) instead of vector
|
||||
similarity - cruder, but far better than no candidates at all.
|
||||
more_like_this_ids returns only a ranked ID list, no scores, so weight is
|
||||
synthesized from rank (descending from top_k) rather than claiming a
|
||||
similarity magnitude that doesn't exist. An unrestricted user (none, or an
|
||||
active superuser - see user_is_unrestricted) is normalized to ``None``
|
||||
before calling, since the backend's permission filter has no superuser
|
||||
short-circuit of its own. Results are re-checked with
|
||||
restrict_queryset_to_visible() since Tantivy's indexed permission fields
|
||||
lag the DB via async reindexing.
|
||||
"""
|
||||
from documents.search import get_backend
|
||||
|
||||
unrestricted = user_is_unrestricted(user)
|
||||
search_user = None if unrestricted else user
|
||||
backend = get_backend()
|
||||
similar_ids = backend.more_like_this_ids(
|
||||
document.pk,
|
||||
user=search_user,
|
||||
limit=top_k,
|
||||
)
|
||||
if not unrestricted:
|
||||
allowed_ids = set(
|
||||
restrict_queryset_to_visible(
|
||||
Document.objects.filter(pk__in=similar_ids),
|
||||
user,
|
||||
"view_document",
|
||||
).values_list("pk", flat=True),
|
||||
)
|
||||
similar_ids = [doc_id for doc_id in similar_ids if doc_id in allowed_ids]
|
||||
return [
|
||||
SimilarDocument(document_id=doc_id, weight=float(top_k - rank))
|
||||
for rank, doc_id in enumerate(similar_ids)
|
||||
]
|
||||
|
||||
|
||||
def get_language_name(language_code: str) -> str:
|
||||
normalized_language_code = language_code.lower()
|
||||
for code, name in settings.LANGUAGES:
|
||||
@@ -112,7 +67,6 @@ def build_prompt_without_rag(
|
||||
document: Document,
|
||||
config: AIConfig,
|
||||
candidates: TaxonomyCandidates | None = None,
|
||||
assigned: AssignedMetadata | None = None,
|
||||
) -> str:
|
||||
filename = document.filename or ""
|
||||
content = truncate_content(
|
||||
@@ -122,9 +76,7 @@ def build_prompt_without_rag(
|
||||
)
|
||||
|
||||
taxonomy_block = (
|
||||
format_taxonomy_for_prompt(candidates, assigned)
|
||||
if candidates is not None and assigned is not None
|
||||
else ""
|
||||
format_taxonomy_for_prompt(candidates) if candidates is not None else ""
|
||||
)
|
||||
has_candidates = candidates is not None and any(candidates.values())
|
||||
|
||||
@@ -142,14 +94,12 @@ def build_prompt_with_rag(
|
||||
document: Document,
|
||||
config: AIConfig,
|
||||
candidates: TaxonomyCandidates | None = None,
|
||||
assigned: AssignedMetadata | None = None,
|
||||
context: str = "",
|
||||
) -> str:
|
||||
base_prompt = build_prompt_without_rag(
|
||||
document,
|
||||
config,
|
||||
candidates=candidates,
|
||||
assigned=assigned,
|
||||
)
|
||||
truncated_context = truncate_content(
|
||||
context,
|
||||
@@ -169,20 +119,16 @@ def build_localization_prompt(
|
||||
suggestions: ClassificationSuggestions,
|
||||
output_language: str,
|
||||
) -> str:
|
||||
"""``suggestions`` is the full nested-shape result of parse_ai_response
|
||||
(each taxonomy field a ``{"existing_ids": [...], "new_names": [...]}``
|
||||
dict) - passed through as-is so the model receives and returns the exact
|
||||
DocumentClassifierSchema shape run_llm_query() always parses against.
|
||||
Only each field's new_names (never existing_ids, which are plain
|
||||
resolved-object IDs, not text) and title get used from the response; see
|
||||
get_ai_document_classification's merge step, which always keeps the
|
||||
*original* existing_ids regardless of what the model echoes back here.
|
||||
"""Render internal suggestions in the same flat shape the model returns.
|
||||
Only the name fields and title are used from the localized response; the
|
||||
merge step always keeps the original ID fields.
|
||||
"""
|
||||
language_name = get_language_name(output_language)
|
||||
model_suggestions = classification_suggestions_to_model(suggestions)
|
||||
return render_prompt(
|
||||
LocalizationPromptContext(
|
||||
language_name=language_name,
|
||||
suggestions_json=json.dumps(suggestions, ensure_ascii=False),
|
||||
suggestions_json=model_suggestions.model_dump_json(),
|
||||
),
|
||||
)
|
||||
|
||||
@@ -192,53 +138,44 @@ def get_taxonomy_context(
|
||||
user: User | None = None,
|
||||
max_docs: int = 5,
|
||||
) -> tuple[TaxonomyCandidates, AssignedMetadata, str]:
|
||||
"""One retrieval feeds both taxonomy candidates and RAG text context. Uses
|
||||
vector similarity when an embedding backend is configured, otherwise
|
||||
falls back to Tantivy full-text "More Like This" similarity - see
|
||||
_fulltext_similar_documents. On any retrieval failure, degrades to empty
|
||||
candidates/context rather than propagating the exception - neither a
|
||||
vector-store outage nor a search-index issue should block classification,
|
||||
only its context-assisted enrichment.
|
||||
"""One retrieval feeds both taxonomy candidates and RAG text context.
|
||||
On any retrieval failure, degrades to empty candidates/context rather than
|
||||
propagating the exception - a vector-store outage should not block
|
||||
classification, only its RAG-assisted enrichment.
|
||||
"""
|
||||
assigned = get_assigned_metadata(document, user)
|
||||
ai_config = AIConfig()
|
||||
try:
|
||||
if ai_config.llm_embedding_backend:
|
||||
# None means "no restriction" to retrieve_similar_nodes. An
|
||||
# unrestricted user (no user at all, or an active superuser -- see
|
||||
# user_is_unrestricted) can see every document, so skip
|
||||
# materializing every visible pk into a Python list and passing it
|
||||
# through as an IN filter: for a large library that is a wasted
|
||||
# quadratic scan in the vector store at best, and past ~32,763
|
||||
# documents a hard sqlite3.OperationalError (SQLite's
|
||||
# bound-parameter limit) at worst.
|
||||
# permitted_object_ids() has its own superuser shortcut that would
|
||||
# return every Document's id anyway, so this changes nothing about
|
||||
# which documents are considered -- only how we get there.
|
||||
visible_document_ids = (
|
||||
None
|
||||
if user_is_unrestricted(user)
|
||||
else list(permitted_object_ids(user, Document, "view_document"))
|
||||
)
|
||||
nodes = retrieve_similar_nodes(
|
||||
document,
|
||||
top_k=TAXONOMY_CANDIDATE_TOP_K,
|
||||
document_ids=visible_document_ids,
|
||||
)
|
||||
similar_documents = _node_document_weights(nodes)
|
||||
else:
|
||||
# See _fulltext_similar_documents: it applies its own permission
|
||||
# filter via `user`, so no visible-document-id list is needed here.
|
||||
similar_documents = _fulltext_similar_documents(
|
||||
document,
|
||||
user,
|
||||
top_k=TAXONOMY_CANDIDATE_TOP_K,
|
||||
# None means "no restriction" to retrieve_similar_nodes. A superuser
|
||||
# (like no user at all) can see every document, so skip materializing
|
||||
# every visible pk into a Python list and passing it through as an IN
|
||||
# filter: for a large library that is a wasted quadratic scan in the
|
||||
# vector store at best, and past ~32,763 documents a hard
|
||||
# sqlite3.OperationalError (SQLite's bound-parameter limit) at worst.
|
||||
# get_objects_for_user_owner_aware() would return every Document for a
|
||||
# superuser anyway (guardian's own with_superuser shortcut), so this
|
||||
# changes nothing about which documents are considered -- only how we
|
||||
# get there.
|
||||
visible_document_ids = (
|
||||
None
|
||||
if user is None or user.is_superuser
|
||||
else list(
|
||||
get_objects_for_user_owner_aware(
|
||||
user,
|
||||
"view_document",
|
||||
Document,
|
||||
).values_list("pk", flat=True),
|
||||
)
|
||||
)
|
||||
nodes = retrieve_similar_nodes(
|
||||
document,
|
||||
top_k=TAXONOMY_CANDIDATE_TOP_K,
|
||||
document_ids=visible_document_ids,
|
||||
)
|
||||
|
||||
candidates = build_taxonomy_candidates(similar_documents, user)
|
||||
candidates = build_taxonomy_candidates(nodes, user)
|
||||
|
||||
# similar_documents is already ordered by descending weight; don't lose it.
|
||||
similar_document_ids = [s["document_id"] for s in similar_documents]
|
||||
# ``nodes`` are already ordered by descending vector similarity; don't lose it.
|
||||
similar_document_ids = list(dict.fromkeys(_node_document_ids(nodes)))
|
||||
similar_documents_by_id = Document.objects.in_bulk(similar_document_ids)
|
||||
similar_docs = [
|
||||
similar_documents_by_id[document_id]
|
||||
@@ -252,8 +189,8 @@ def get_taxonomy_context(
|
||||
context_blocks.append(f"TITLE: {title}\n{text}")
|
||||
except Exception:
|
||||
logger.exception(
|
||||
"Failed to retrieve similar-document context for document %s; "
|
||||
"continuing without taxonomy candidates or similar-document context.",
|
||||
"Failed to retrieve RAG neighbours for document %s; continuing "
|
||||
"without taxonomy candidates or similar-document context.",
|
||||
document.pk,
|
||||
)
|
||||
return empty_taxonomy_candidates(), assigned, ""
|
||||
@@ -262,11 +199,9 @@ def get_taxonomy_context(
|
||||
|
||||
|
||||
def parse_ai_response(raw: dict) -> ClassificationSuggestions:
|
||||
"""``raw`` is AIClient.run_llm_query()'s return value - already a
|
||||
DocumentClassifierSchema.model_dump(), so every key below is always
|
||||
present with the right shape; this only exists to give the rest of the
|
||||
module a named, typed boundary instead of passing the client's bare dict
|
||||
straight through everywhere.
|
||||
"""``raw`` is AIClient.run_llm_query()'s validated internal-shape result.
|
||||
This gives the rest of the module a named, typed boundary instead of
|
||||
passing the client's bare dict straight through everywhere.
|
||||
"""
|
||||
|
||||
def _choice(value: dict | None) -> TaxonomyChoiceDict:
|
||||
@@ -329,6 +264,22 @@ def _restrict_to_shown_candidates(
|
||||
)
|
||||
|
||||
|
||||
def _candidate_id_allowlist(
|
||||
candidates: TaxonomyCandidates,
|
||||
) -> dict[str, set[int]]:
|
||||
"""Candidate IDs grouped by category for validating model mappings."""
|
||||
return {
|
||||
"tags": {candidate["id"] for candidate in candidates["tags"]},
|
||||
"document_types": {
|
||||
candidate["id"] for candidate in candidates["document_types"]
|
||||
},
|
||||
"correspondents": {
|
||||
candidate["id"] for candidate in candidates["correspondents"]
|
||||
},
|
||||
"storage_paths": {candidate["id"] for candidate in candidates["storage_paths"]},
|
||||
}
|
||||
|
||||
|
||||
def get_ai_document_classification(
|
||||
document: Document,
|
||||
user: User | None = None,
|
||||
@@ -336,20 +287,26 @@ def get_ai_document_classification(
|
||||
) -> ClassificationSuggestions:
|
||||
ai_config = AIConfig()
|
||||
|
||||
candidates, assigned, context = get_taxonomy_context(document, user)
|
||||
prompt = build_prompt_with_rag(
|
||||
document,
|
||||
ai_config,
|
||||
candidates=candidates,
|
||||
assigned=assigned,
|
||||
context=context,
|
||||
)
|
||||
if ai_config.llm_embedding_backend:
|
||||
candidates, _assigned, context = get_taxonomy_context(document, user)
|
||||
prompt = build_prompt_with_rag(
|
||||
document,
|
||||
ai_config,
|
||||
candidates=candidates,
|
||||
context=context,
|
||||
)
|
||||
else:
|
||||
candidates = empty_taxonomy_candidates()
|
||||
prompt = build_prompt_without_rag(document, ai_config, candidates=candidates)
|
||||
|
||||
client = AIClient()
|
||||
# Hand the pooled DB connection back while the (slow) LLM query runs so it
|
||||
# is not pinned for the call's duration; see paperless_ai.db and #12976.
|
||||
with db_connection_released():
|
||||
result = client.run_llm_query(prompt)
|
||||
result = client.run_llm_query(
|
||||
prompt,
|
||||
allowed_candidate_ids=_candidate_id_allowlist(candidates),
|
||||
)
|
||||
suggestions = _restrict_to_shown_candidates(
|
||||
parse_ai_response(result),
|
||||
candidates,
|
||||
|
||||
+202
-73
@@ -31,38 +31,9 @@ def _truncate_to_field_limit(value: Any, field: FieldInfo) -> Any:
|
||||
)
|
||||
|
||||
|
||||
# Docstrings and field descriptions on both models below are serialized into
|
||||
# the schema handed to the LLM, so write them for the model. Code comments
|
||||
# should go here only.
|
||||
class TaxonomyChoice(BaseModel):
|
||||
"""One field's suggestions: existing values to reuse, plus new ones to create."""
|
||||
|
||||
existing_ids: list[int] = Field(
|
||||
default_factory=list,
|
||||
max_length=MAX_EXISTING_IDS,
|
||||
description=(
|
||||
"IDs from the candidate list shown in the prompt that clearly "
|
||||
"represent values you would suggest for this field. Never invent "
|
||||
"an ID, select a weak match merely because it exists, or use an "
|
||||
"ID when no candidates are shown."
|
||||
),
|
||||
)
|
||||
new_names: list[str] = Field(
|
||||
default_factory=list,
|
||||
max_length=MAX_NEW_NAMES,
|
||||
description=(
|
||||
"Names for clearly supported values that no shown candidate "
|
||||
"represents. When a candidate represents the same value, use its "
|
||||
"ID instead so an existing value is not duplicated under a new name."
|
||||
),
|
||||
)
|
||||
|
||||
@field_validator("existing_ids", "new_names", mode="before")
|
||||
@classmethod
|
||||
def _truncate(cls, value: Any, info: ValidationInfo) -> Any:
|
||||
return _truncate_to_field_limit(value, cls.model_fields[info.field_name])
|
||||
|
||||
|
||||
# This model is serialized into the schema handed to the LLM, so its docstring
|
||||
# and field descriptions are instructions for the model. Keep implementation
|
||||
# details in code comments instead.
|
||||
class DocumentClassifierSchema(BaseModel):
|
||||
"""Classification suggestions for a single document."""
|
||||
|
||||
@@ -73,36 +44,111 @@ class DocumentClassifierSchema(BaseModel):
|
||||
f"{MAX_TITLE_LENGTH} characters."
|
||||
),
|
||||
)
|
||||
tags: TaxonomyChoice = Field(
|
||||
default_factory=TaxonomyChoice,
|
||||
tags: list[str] = Field(
|
||||
default_factory=list,
|
||||
max_length=MAX_NEW_NAMES,
|
||||
description=(
|
||||
"Topic labels describing what this document is about. A document "
|
||||
"may have several, e.g. 'Insurance', 'Car', 'Warranty'."
|
||||
"All topic labels you would suggest from the document itself, e.g. "
|
||||
"'Insurance', 'Car', 'Warranty'. Always include every suggested "
|
||||
"name here, even when it matches an available tag."
|
||||
),
|
||||
)
|
||||
correspondents: TaxonomyChoice = Field(
|
||||
default_factory=TaxonomyChoice,
|
||||
matched_tags: list[str] = Field(
|
||||
default_factory=list,
|
||||
max_length=MAX_NEW_NAMES,
|
||||
description=(
|
||||
"The person, institution or company this document originates "
|
||||
"from, or was sent to. Not every party merely mentioned in the "
|
||||
"text, and not the subject of the document."
|
||||
"Names copied exactly from tags that mean the same thing as an "
|
||||
"available tag. Align each name by position with tag_ids."
|
||||
),
|
||||
)
|
||||
document_types: TaxonomyChoice = Field(
|
||||
default_factory=TaxonomyChoice,
|
||||
tag_ids: list[int] = Field(
|
||||
default_factory=list,
|
||||
max_length=MAX_EXISTING_IDS,
|
||||
description=(
|
||||
"What kind of document this is, e.g. 'Invoice', 'Contract', "
|
||||
"'Bank Statement', 'Letter'. Never its subject matter and never "
|
||||
"who sent it."
|
||||
"Available tag IDs matching matched_tags, in the same order. "
|
||||
"Only use IDs shown in the prompt."
|
||||
),
|
||||
)
|
||||
storage_paths: TaxonomyChoice = Field(
|
||||
default_factory=TaxonomyChoice,
|
||||
correspondents: list[str] = Field(
|
||||
default_factory=list,
|
||||
max_length=MAX_NEW_NAMES,
|
||||
description=(
|
||||
"A folder-style filing location for this document, e.g. "
|
||||
"All people, institutions or companies you would suggest as who "
|
||||
"this document is from or was sent to, not every party merely "
|
||||
"mentioned. Always include every suggested name here, even when it "
|
||||
"matches an available correspondent."
|
||||
),
|
||||
)
|
||||
matched_correspondents: list[str] = Field(
|
||||
default_factory=list,
|
||||
max_length=MAX_NEW_NAMES,
|
||||
description=(
|
||||
"Names copied exactly from correspondents that identify the same "
|
||||
"entity as an available correspondent. Align each name by position "
|
||||
"with correspondent_ids."
|
||||
),
|
||||
)
|
||||
correspondent_ids: list[int] = Field(
|
||||
default_factory=list,
|
||||
max_length=MAX_EXISTING_IDS,
|
||||
description=(
|
||||
"Available correspondent IDs matching matched_correspondents, in "
|
||||
"the same order. Only use IDs shown in the prompt."
|
||||
),
|
||||
)
|
||||
document_types: list[str] = Field(
|
||||
default_factory=list,
|
||||
max_length=MAX_NEW_NAMES,
|
||||
description=(
|
||||
"All names describing what kind of document this is, e.g. 'Invoice', "
|
||||
"'Contract', 'Bank Statement', 'Letter'. Never use its subject or "
|
||||
"sender as a document type. Always include every suggested name "
|
||||
"here, even when it matches an available document type."
|
||||
),
|
||||
)
|
||||
matched_document_types: list[str] = Field(
|
||||
default_factory=list,
|
||||
max_length=MAX_NEW_NAMES,
|
||||
description=(
|
||||
"Names copied exactly from document_types that mean the same thing "
|
||||
"as an available document type. Align each name by position with "
|
||||
"document_type_ids."
|
||||
),
|
||||
)
|
||||
document_type_ids: list[int] = Field(
|
||||
default_factory=list,
|
||||
max_length=MAX_EXISTING_IDS,
|
||||
description=(
|
||||
"Available document type IDs matching matched_document_types, in "
|
||||
"the same order. Only use IDs shown in the prompt."
|
||||
),
|
||||
)
|
||||
storage_paths: list[str] = Field(
|
||||
default_factory=list,
|
||||
max_length=MAX_NEW_NAMES,
|
||||
description=(
|
||||
"All folder-style filing locations you would suggest, e.g. "
|
||||
"'Finance/Invoices'. Leave empty unless a filing location is "
|
||||
"clearly implied - never put tags, document types or "
|
||||
"correspondents here."
|
||||
"correspondents here. Always include every suggested name here, "
|
||||
"even when it matches an available storage path."
|
||||
),
|
||||
)
|
||||
matched_storage_paths: list[str] = Field(
|
||||
default_factory=list,
|
||||
max_length=MAX_NEW_NAMES,
|
||||
description=(
|
||||
"Names copied exactly from storage_paths that mean the same filing "
|
||||
"location as an available storage path. Align each name by position "
|
||||
"with storage_path_ids."
|
||||
),
|
||||
)
|
||||
storage_path_ids: list[int] = Field(
|
||||
default_factory=list,
|
||||
max_length=MAX_EXISTING_IDS,
|
||||
description=(
|
||||
"Available storage path IDs matching matched_storage_paths, in the "
|
||||
"same order. Only use IDs shown in the prompt."
|
||||
),
|
||||
)
|
||||
dates: list[str] = Field(
|
||||
@@ -115,41 +161,37 @@ class DocumentClassifierSchema(BaseModel):
|
||||
),
|
||||
)
|
||||
|
||||
@field_validator("title", "dates", mode="before")
|
||||
@field_validator(
|
||||
"title",
|
||||
"tags",
|
||||
"matched_tags",
|
||||
"tag_ids",
|
||||
"correspondents",
|
||||
"matched_correspondents",
|
||||
"correspondent_ids",
|
||||
"document_types",
|
||||
"matched_document_types",
|
||||
"document_type_ids",
|
||||
"storage_paths",
|
||||
"matched_storage_paths",
|
||||
"storage_path_ids",
|
||||
"dates",
|
||||
mode="before",
|
||||
)
|
||||
@classmethod
|
||||
def _truncate(cls, value: Any, info: ValidationInfo) -> Any:
|
||||
return _truncate_to_field_limit(value, cls.model_fields[info.field_name])
|
||||
|
||||
@classmethod
|
||||
def model_json_schema(cls, *args: Any, **kwargs: Any) -> dict[str, Any]:
|
||||
"""Inline TaxonomyChoice for backends that reject JSON Schema refs."""
|
||||
schema = super().model_json_schema(*args, **kwargs)
|
||||
taxonomy_choice = schema.pop("$defs")["TaxonomyChoice"]
|
||||
for field in ("tags", "correspondents", "document_types", "storage_paths"):
|
||||
# Pydantic emits a field's description as a sibling of its $ref;
|
||||
# those keys must survive and win over the shared definition.
|
||||
siblings = {
|
||||
key: value
|
||||
for key, value in schema["properties"][field].items()
|
||||
if key != "$ref"
|
||||
}
|
||||
schema["properties"][field] = taxonomy_choice | siblings
|
||||
return schema
|
||||
|
||||
|
||||
class TaxonomyChoiceDict(TypedDict):
|
||||
"""Plain-dict counterpart of TaxonomyChoice - what
|
||||
TaxonomyChoice.model_dump() actually produces, typed for callers that
|
||||
work with the dumped dict rather than the pydantic instance."""
|
||||
"""Internal representation of names and existing IDs for one taxonomy."""
|
||||
|
||||
existing_ids: list[int]
|
||||
new_names: list[str]
|
||||
|
||||
|
||||
class ClassificationSuggestions(TypedDict):
|
||||
"""Plain-dict counterpart of DocumentClassifierSchema.model_dump() -
|
||||
the shape threaded through parse_ai_response, build_localization_prompt,
|
||||
get_ai_document_classification, and the ai_suggestions view."""
|
||||
"""Internal shape used after the flat LLM response is validated."""
|
||||
|
||||
title: str
|
||||
tags: TaxonomyChoiceDict
|
||||
@@ -157,3 +199,90 @@ class ClassificationSuggestions(TypedDict):
|
||||
document_types: TaxonomyChoiceDict
|
||||
storage_paths: TaxonomyChoiceDict
|
||||
dates: list[str]
|
||||
|
||||
|
||||
def model_to_classification_suggestions(
|
||||
model: DocumentClassifierSchema,
|
||||
allowed_candidate_ids: dict[str, set[int]] | None = None,
|
||||
) -> ClassificationSuggestions:
|
||||
"""Validate optional candidate mappings and convert to the internal shape.
|
||||
|
||||
A mapping is accepted only when its name is copied from the model's own
|
||||
complete suggestion list and its ID was actually shown for that category.
|
||||
Invalid or unpaired mappings leave the original name untouched.
|
||||
"""
|
||||
allowed_candidate_ids = allowed_candidate_ids or {}
|
||||
|
||||
def _choice(
|
||||
names: list[str],
|
||||
matched_names: list[str],
|
||||
ids: list[int],
|
||||
category: str,
|
||||
) -> TaxonomyChoiceDict:
|
||||
remaining_names = list(names)
|
||||
existing_ids: list[int] = []
|
||||
allowed_ids = allowed_candidate_ids.get(category, set())
|
||||
for name, object_id in zip(matched_names, ids, strict=False):
|
||||
if (
|
||||
name not in remaining_names
|
||||
or object_id not in allowed_ids
|
||||
or object_id in existing_ids
|
||||
):
|
||||
continue
|
||||
remaining_names.remove(name)
|
||||
existing_ids.append(object_id)
|
||||
return TaxonomyChoiceDict(
|
||||
existing_ids=existing_ids,
|
||||
new_names=remaining_names,
|
||||
)
|
||||
|
||||
return ClassificationSuggestions(
|
||||
title=model.title,
|
||||
tags=_choice(
|
||||
model.tags,
|
||||
model.matched_tags,
|
||||
model.tag_ids,
|
||||
"tags",
|
||||
),
|
||||
correspondents=_choice(
|
||||
model.correspondents,
|
||||
model.matched_correspondents,
|
||||
model.correspondent_ids,
|
||||
"correspondents",
|
||||
),
|
||||
document_types=_choice(
|
||||
model.document_types,
|
||||
model.matched_document_types,
|
||||
model.document_type_ids,
|
||||
"document_types",
|
||||
),
|
||||
storage_paths=_choice(
|
||||
model.storage_paths,
|
||||
model.matched_storage_paths,
|
||||
model.storage_path_ids,
|
||||
"storage_paths",
|
||||
),
|
||||
dates=model.dates,
|
||||
)
|
||||
|
||||
|
||||
def classification_suggestions_to_model(
|
||||
suggestions: ClassificationSuggestions,
|
||||
) -> DocumentClassifierSchema:
|
||||
"""Convert internal suggestions to the flat shape used for localization."""
|
||||
return DocumentClassifierSchema(
|
||||
title=suggestions["title"],
|
||||
tags=suggestions["tags"]["new_names"],
|
||||
matched_tags=[],
|
||||
tag_ids=[],
|
||||
correspondents=suggestions["correspondents"]["new_names"],
|
||||
matched_correspondents=[],
|
||||
correspondent_ids=[],
|
||||
document_types=suggestions["document_types"]["new_names"],
|
||||
matched_document_types=[],
|
||||
document_type_ids=[],
|
||||
storage_paths=suggestions["storage_paths"]["new_names"],
|
||||
matched_storage_paths=[],
|
||||
storage_path_ids=[],
|
||||
dates=suggestions["dates"],
|
||||
)
|
||||
|
||||
@@ -19,7 +19,9 @@ from paperless.network import PinnedHostHTTPTransport
|
||||
from paperless.network import create_pinned_async_httpx_client
|
||||
from paperless.network import create_pinned_httpx_client
|
||||
from paperless.network import validate_outbound_http_url
|
||||
from paperless_ai.base_model import ClassificationSuggestions
|
||||
from paperless_ai.base_model import DocumentClassifierSchema
|
||||
from paperless_ai.base_model import model_to_classification_suggestions
|
||||
from paperless_ai.exceptions import LLMTimeoutError
|
||||
|
||||
logger = logging.getLogger("paperless_ai.client")
|
||||
@@ -115,7 +117,12 @@ class AIClient:
|
||||
else:
|
||||
raise ValueError(f"Unsupported LLM backend: {self.settings.llm_backend}")
|
||||
|
||||
def run_llm_query(self, prompt: str) -> str:
|
||||
def run_llm_query(
|
||||
self,
|
||||
prompt: str,
|
||||
*,
|
||||
allowed_candidate_ids: dict[str, set[int]] | None = None,
|
||||
) -> ClassificationSuggestions:
|
||||
logger.debug(
|
||||
"Running LLM query against %s with model %s",
|
||||
self.settings.llm_backend,
|
||||
@@ -134,7 +141,10 @@ class AIClient:
|
||||
)
|
||||
logger.debug("LLM query result: %s", result)
|
||||
parsed = DocumentClassifierSchema(**json.loads(result.message.content))
|
||||
return parsed.model_dump()
|
||||
return model_to_classification_suggestions(
|
||||
parsed,
|
||||
allowed_candidate_ids,
|
||||
)
|
||||
|
||||
from llama_index.core.program.function_program import get_function_tool
|
||||
|
||||
@@ -153,7 +163,10 @@ class AIClient:
|
||||
)
|
||||
logger.debug("LLM query result: %s", tool_calls)
|
||||
parsed = DocumentClassifierSchema(**tool_calls[0].tool_kwargs)
|
||||
return parsed.model_dump()
|
||||
return model_to_classification_suggestions(
|
||||
parsed,
|
||||
allowed_candidate_ids,
|
||||
)
|
||||
|
||||
@contextmanager
|
||||
def _normalize_timeouts(self) -> Iterator[None]:
|
||||
|
||||
@@ -13,10 +13,7 @@ Analyze the following document and fill in these fields:
|
||||
- dates: up to 3 relevant dates in YYYY-MM-DD format
|
||||
{% if has_candidates %}
|
||||
|
||||
For tags, correspondents, document types, and storage paths: first decide whether there is a useful, well-supported suggestion. If an available candidate clearly represents that suggestion, put its id in existing_ids instead of duplicating it in new_names. If no candidate represents the suggestion, put its name in new_names. Do not choose a weak candidate merely because it exists.
|
||||
{% else %}
|
||||
|
||||
No candidates are shown for this document, so leave every existing_ids list empty and put each suggestion's name in new_names.
|
||||
First produce the complete name suggestions from the document itself in tags, correspondents, document_types, and storage_paths. Always include every suggested name in those fields, even when an available candidate represents the same value. Then, as a separate reconciliation step, copy each name that means the same thing as an available candidate into the matching matched_* field and put that candidate's ID at the same position in the corresponding *_ids field. Candidates must not create, replace, or suppress suggestions. Do not match a candidate that is merely related.
|
||||
{% endif %}
|
||||
|
||||
Filename:
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
You are localizing document classification suggestions for display in Paperless-ngx.
|
||||
|
||||
Rewrite only the "title" field and each taxonomy field's "new_names" list in {{ language_name }}. Leave every "existing_ids" list exactly as given - these are database identifiers, not text, and are not used from your response even if changed.
|
||||
Rewrite only the "title", "tags", "document_types", and "storage_paths" fields in {{ language_name }}.
|
||||
|
||||
Do not translate correspondents or dates.
|
||||
Preserve proper nouns, organization names, product names, and exact official document names. Translate generic category words when a {{ language_name }} equivalent exists.
|
||||
|
||||
@@ -33,11 +33,6 @@ class TaxonomyCandidate(TypedDict):
|
||||
weight: float
|
||||
|
||||
|
||||
class SimilarDocument(TypedDict):
|
||||
document_id: int
|
||||
weight: float
|
||||
|
||||
|
||||
class TaxonomyCandidates(TypedDict):
|
||||
tags: list[TaxonomyCandidate]
|
||||
document_types: list[TaxonomyCandidate]
|
||||
@@ -110,10 +105,10 @@ def get_assigned_metadata(document: Document, user: User | None) -> AssignedMeta
|
||||
)
|
||||
|
||||
|
||||
def _node_document_weights(nodes: list["NodeWithScore"]) -> list[SimilarDocument]:
|
||||
"""Sum each node's similarity score into its document_id (a document can
|
||||
appear via multiple chunks/nodes) and return one SimilarDocument per
|
||||
distinct document_id."""
|
||||
def _node_document_weights(nodes: list["NodeWithScore"]) -> dict[int, float]:
|
||||
"""document_id -> that node's similarity score, summed if a document_id
|
||||
appears more than once across the retrieved nodes (e.g. multiple chunks
|
||||
of the same source document)."""
|
||||
weights: dict[int, float] = defaultdict(float)
|
||||
for node in nodes:
|
||||
document_id = node.metadata.get("document_id")
|
||||
@@ -126,14 +121,7 @@ def _node_document_weights(nodes: list["NodeWithScore"]) -> list[SimilarDocument
|
||||
weights[int(document_id)] += float(node.score or 0.0)
|
||||
except (TypeError, ValueError): # pragma: no cover
|
||||
continue
|
||||
return sorted(
|
||||
(
|
||||
SimilarDocument(document_id=document_id, weight=weight)
|
||||
for document_id, weight in weights.items()
|
||||
),
|
||||
key=lambda similar: similar["weight"],
|
||||
reverse=True,
|
||||
)
|
||||
return weights
|
||||
|
||||
|
||||
def _visible_ranked_candidates(
|
||||
@@ -169,25 +157,20 @@ def _visible_ranked_candidates(
|
||||
|
||||
|
||||
def build_taxonomy_candidates(
|
||||
similar_documents: list[SimilarDocument],
|
||||
nodes: list["NodeWithScore"],
|
||||
user: User | None,
|
||||
) -> TaxonomyCandidates:
|
||||
"""Resolve each similar document's id to a live Document, read its
|
||||
*current* tags/type/correspondent/storage_path via the ORM (never any
|
||||
possibly-stale names an adapter's source might have cached), weight each
|
||||
distinct taxonomy object by aggregate similarity weight, permission-filter
|
||||
"""Resolve each neighbour node's document_id to a live Document, read its
|
||||
*current* tags/type/correspondent/storage_path via the ORM (never the
|
||||
possibly-stale names cached in vector-index node metadata), weight each
|
||||
distinct taxonomy object by aggregate neighbour similarity, permission-filter
|
||||
against what ``user`` can see, and return each category ranked by weight
|
||||
and capped. ``similar_documents`` may come from either the vector-RAG
|
||||
adapter or the full-text fallback adapter - both produce this same shape.
|
||||
and capped.
|
||||
"""
|
||||
if not similar_documents:
|
||||
return empty_taxonomy_candidates()
|
||||
|
||||
# Both adapters guarantee at most one SimilarDocument per document_id, so
|
||||
# this never silently drops a duplicate's weight.
|
||||
document_weights: dict[int, float] = {
|
||||
s["document_id"]: s["weight"] for s in similar_documents
|
||||
}
|
||||
document_weights = _node_document_weights(nodes)
|
||||
if not document_weights:
|
||||
return empty_taxonomy_candidates()
|
||||
|
||||
# Only .tags.all() needs prefetching (a reverse M2M, one extra query for
|
||||
# the whole batch). document_type/correspondent/storage_path are read
|
||||
@@ -262,7 +245,7 @@ def _assigned_block(assigned: AssignedMetadata) -> str:
|
||||
|
||||
def format_taxonomy_for_prompt(
|
||||
candidates: TaxonomyCandidates,
|
||||
assigned: AssignedMetadata,
|
||||
assigned: AssignedMetadata | None = None,
|
||||
) -> str:
|
||||
"""Render assigned metadata and ranked candidates as labelled prompt
|
||||
blocks. Candidate names are untrusted, user-controlled data, so they are
|
||||
@@ -272,7 +255,7 @@ def format_taxonomy_for_prompt(
|
||||
is nothing to say (no assigned metadata and no candidates), so callers can
|
||||
treat the result the same as no hints at all.
|
||||
"""
|
||||
has_assigned = any(
|
||||
has_assigned = assigned is not None and any(
|
||||
[
|
||||
assigned["tags"],
|
||||
assigned["document_type"],
|
||||
@@ -288,7 +271,11 @@ def format_taxonomy_for_prompt(
|
||||
|
||||
return render_prompt(
|
||||
TaxonomyBlockPromptContext(
|
||||
assigned_block=_assigned_block(assigned) if has_assigned else "",
|
||||
assigned_block=(
|
||||
_assigned_block(assigned)
|
||||
if assigned is not None and has_assigned
|
||||
else ""
|
||||
),
|
||||
candidate_payload_json=(
|
||||
json.dumps(candidate_payload, ensure_ascii=False)
|
||||
if candidate_payload
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
import datetime
|
||||
from collections.abc import Generator
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import MagicMock
|
||||
from unittest.mock import patch
|
||||
@@ -9,13 +8,10 @@ import pytest_mock
|
||||
from django.test import override_settings
|
||||
|
||||
from documents.models import Document
|
||||
from documents.search import TantivyBackend
|
||||
from documents.tests.factories import DocumentFactory
|
||||
from documents.tests.factories import TagFactory
|
||||
from documents.tests.factories import UserFactory
|
||||
from paperless.config import AIConfig
|
||||
from paperless_ai.ai_classifier import TAXONOMY_CANDIDATE_TOP_K
|
||||
from paperless_ai.ai_classifier import _fulltext_similar_documents
|
||||
from paperless_ai.ai_classifier import _restrict_to_shown_candidates
|
||||
from paperless_ai.ai_classifier import build_localization_prompt
|
||||
from paperless_ai.ai_classifier import build_prompt_with_rag
|
||||
@@ -25,7 +21,6 @@ from paperless_ai.ai_classifier import get_language_name
|
||||
from paperless_ai.ai_classifier import get_taxonomy_context
|
||||
from paperless_ai.base_model import ClassificationSuggestions
|
||||
from paperless_ai.base_model import TaxonomyChoiceDict
|
||||
from paperless_ai.taxonomy import SimilarDocument
|
||||
from paperless_ai.taxonomy import TaxonomyCandidate
|
||||
from paperless_ai.taxonomy import TaxonomyCandidates
|
||||
from paperless_ai.taxonomy import empty_taxonomy_candidates
|
||||
@@ -180,6 +175,7 @@ def test_get_ai_document_classification_failure(mock_run_llm_query, mock_documen
|
||||
@pytest.mark.django_db
|
||||
@patch("paperless_ai.client.AIClient.run_llm_query")
|
||||
@patch("paperless_ai.ai_classifier.build_prompt_with_rag")
|
||||
@patch("paperless_ai.ai_classifier.build_taxonomy_candidates")
|
||||
@patch("paperless_ai.ai_classifier.retrieve_similar_nodes")
|
||||
@override_settings(
|
||||
LLM_EMBEDDING_BACKEND="huggingface",
|
||||
@@ -189,6 +185,7 @@ def test_get_ai_document_classification_failure(mock_run_llm_query, mock_documen
|
||||
)
|
||||
def test_use_rag_if_configured(
|
||||
mock_retrieve,
|
||||
mock_build_candidates,
|
||||
mock_build_prompt_with_rag,
|
||||
mock_run_llm_query,
|
||||
mock_document,
|
||||
@@ -200,20 +197,39 @@ def test_use_rag_if_configured(
|
||||
- get_ai_document_classification() is called
|
||||
THEN:
|
||||
- The RAG-augmented prompt builder is used
|
||||
- Classification and candidate reconciliation happen in one LLM call
|
||||
- Only candidate IDs from the permission-filtered candidate set are allowed
|
||||
"""
|
||||
mock_retrieve.return_value = []
|
||||
mock_build_candidates.return_value = TaxonomyCandidates(
|
||||
tags=[TaxonomyCandidate(id=12, name="Contractor", weight=1.0)],
|
||||
document_types=[],
|
||||
correspondents=[],
|
||||
storage_paths=[],
|
||||
)
|
||||
mock_build_prompt_with_rag.return_value = "Prompt with RAG"
|
||||
mock_run_llm_query.return_value = NESTED_SUGGESTIONS
|
||||
get_ai_document_classification(mock_document)
|
||||
mock_build_prompt_with_rag.assert_called_once()
|
||||
mock_run_llm_query.assert_called_once_with(
|
||||
"Prompt with RAG",
|
||||
allowed_candidate_ids={
|
||||
"tags": {12},
|
||||
"document_types": set(),
|
||||
"correspondents": set(),
|
||||
"storage_paths": set(),
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@patch("paperless_ai.client.AIClient.run_llm_query")
|
||||
@patch("paperless_ai.ai_classifier.build_prompt_with_rag")
|
||||
@patch("paperless_ai.ai_classifier.build_prompt_without_rag")
|
||||
@patch("paperless_ai.ai_classifier.AIConfig")
|
||||
@override_settings(LLM_BACKEND="ollama", LLM_MODEL="some_model")
|
||||
def test_use_rag_prompt_even_without_embedding_backend(
|
||||
mock_build_prompt_with_rag,
|
||||
def test_use_without_rag_if_not_configured(
|
||||
mock_ai_config,
|
||||
mock_build_prompt_without_rag,
|
||||
mock_run_llm_query,
|
||||
mock_document,
|
||||
):
|
||||
@@ -223,13 +239,13 @@ def test_use_rag_prompt_even_without_embedding_backend(
|
||||
WHEN:
|
||||
- get_ai_document_classification() is called
|
||||
THEN:
|
||||
- The RAG-context prompt builder is still used (fed by the full-text
|
||||
fallback's context/candidates instead of the vector store's)
|
||||
- The non-RAG prompt builder is used
|
||||
"""
|
||||
mock_build_prompt_with_rag.return_value = "Prompt with RAG"
|
||||
mock_ai_config.return_value.llm_embedding_backend = None
|
||||
mock_build_prompt_without_rag.return_value = "Prompt without RAG"
|
||||
mock_run_llm_query.return_value = NESTED_SUGGESTIONS
|
||||
get_ai_document_classification(mock_document)
|
||||
mock_build_prompt_with_rag.assert_called_once()
|
||||
mock_build_prompt_without_rag.assert_called_once()
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@@ -248,7 +264,7 @@ def test_prompt_with_without_rag(mock_document):
|
||||
THEN:
|
||||
- build_prompt_without_rag() has no similar-documents section
|
||||
- build_prompt_with_rag() includes the similar-documents context
|
||||
- build_localization_prompt() asks to rewrite only new_names/title and
|
||||
- build_localization_prompt() asks to rewrite only names/title and
|
||||
not to translate correspondents or dates
|
||||
"""
|
||||
config = AIConfig()
|
||||
@@ -267,6 +283,7 @@ def test_prompt_with_without_rag(mock_document):
|
||||
prompt = build_localization_prompt(NESTED_SUGGESTIONS, output_language="de-de")
|
||||
assert "Rewrite only the" in prompt
|
||||
assert "Do not translate correspondents or dates" in prompt
|
||||
assert '"tag_ids":[]' in prompt
|
||||
|
||||
|
||||
def test_get_language_name_falls_back_to_language_code():
|
||||
@@ -307,7 +324,6 @@ def test_build_localization_prompt_preserves_unicode_characters():
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@override_settings(LLM_EMBEDDING_BACKEND="huggingface")
|
||||
def test_get_taxonomy_context_assembles_rag_text_and_candidates():
|
||||
"""
|
||||
GIVEN:
|
||||
@@ -349,7 +365,6 @@ def test_get_taxonomy_context_assembles_rag_text_and_candidates():
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@override_settings(LLM_EMBEDDING_BACKEND="huggingface")
|
||||
def test_get_taxonomy_context_preserves_similarity_order_and_distinct_documents():
|
||||
"""
|
||||
GIVEN:
|
||||
@@ -420,7 +435,6 @@ def test_get_taxonomy_context_preserves_similarity_order_and_distinct_documents(
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@override_settings(LLM_EMBEDDING_BACKEND="huggingface")
|
||||
def test_get_taxonomy_context_no_similar_docs():
|
||||
"""
|
||||
GIVEN:
|
||||
@@ -444,67 +458,6 @@ def test_get_taxonomy_context_no_similar_docs():
|
||||
}
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_get_taxonomy_context_uses_fulltext_fallback_when_no_embedding_backend(
|
||||
mocker: pytest_mock.MockerFixture,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- No LLM embedding backend is configured (the default test settings)
|
||||
WHEN:
|
||||
- get_taxonomy_context() is called
|
||||
THEN:
|
||||
- _fulltext_similar_documents() is called with the document, the user
|
||||
and TAXONOMY_CANDIDATE_TOP_K
|
||||
- retrieve_similar_nodes() (the vector path) is never called
|
||||
"""
|
||||
document = DocumentFactory.create(content="Some content")
|
||||
mock_fulltext = mocker.patch(
|
||||
"paperless_ai.ai_classifier._fulltext_similar_documents",
|
||||
return_value=[],
|
||||
)
|
||||
mock_retrieve = mocker.patch("paperless_ai.ai_classifier.retrieve_similar_nodes")
|
||||
|
||||
get_taxonomy_context(document, user=None)
|
||||
|
||||
mock_fulltext.assert_called_once_with(
|
||||
document,
|
||||
None,
|
||||
top_k=TAXONOMY_CANDIDATE_TOP_K,
|
||||
)
|
||||
mock_retrieve.assert_not_called()
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@override_settings(LLM_EMBEDDING_BACKEND="huggingface")
|
||||
def test_get_taxonomy_context_uses_vector_path_when_embedding_backend_configured(
|
||||
mocker: pytest_mock.MockerFixture,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An LLM embedding backend is configured
|
||||
WHEN:
|
||||
- get_taxonomy_context() is called
|
||||
THEN:
|
||||
- retrieve_similar_nodes() (the vector path) is called
|
||||
- _fulltext_similar_documents() (the no-embedding-backend fallback)
|
||||
is never called
|
||||
"""
|
||||
document = DocumentFactory.create(content="Some content")
|
||||
mock_retrieve = mocker.patch(
|
||||
"paperless_ai.ai_classifier.retrieve_similar_nodes",
|
||||
return_value=[],
|
||||
)
|
||||
mock_fulltext = mocker.patch(
|
||||
"paperless_ai.ai_classifier._fulltext_similar_documents",
|
||||
)
|
||||
|
||||
get_taxonomy_context(document, user=None)
|
||||
|
||||
mock_retrieve.assert_called_once()
|
||||
mock_fulltext.assert_not_called()
|
||||
|
||||
|
||||
class TestGetTaxonomyContextVisibility:
|
||||
"""get_taxonomy_context must not materialize every visible document id
|
||||
for a user who can already see the whole library: a superuser (like no
|
||||
@@ -517,7 +470,6 @@ class TestGetTaxonomyContextVisibility:
|
||||
"""
|
||||
|
||||
@pytest.mark.django_db
|
||||
@override_settings(LLM_EMBEDDING_BACKEND="huggingface")
|
||||
def test_skips_permission_lookup_for_superuser(
|
||||
self,
|
||||
mocker: pytest_mock.MockerFixture,
|
||||
@@ -536,18 +488,17 @@ class TestGetTaxonomyContextVisibility:
|
||||
"paperless_ai.ai_classifier.retrieve_similar_nodes",
|
||||
return_value=[],
|
||||
)
|
||||
mock_permitted = mocker.patch(
|
||||
"paperless_ai.ai_classifier.permitted_object_ids",
|
||||
mock_get_objects = mocker.patch(
|
||||
"paperless_ai.ai_classifier.get_objects_for_user_owner_aware",
|
||||
)
|
||||
user = UserFactory.create(is_superuser=True)
|
||||
|
||||
get_taxonomy_context(document, user)
|
||||
|
||||
mock_permitted.assert_not_called()
|
||||
mock_get_objects.assert_not_called()
|
||||
assert mock_retrieve.call_args.kwargs["document_ids"] is None
|
||||
|
||||
@pytest.mark.django_db
|
||||
@override_settings(LLM_EMBEDDING_BACKEND="huggingface")
|
||||
def test_skips_permission_lookup_when_no_user(
|
||||
self,
|
||||
mocker: pytest_mock.MockerFixture,
|
||||
@@ -566,17 +517,16 @@ class TestGetTaxonomyContextVisibility:
|
||||
"paperless_ai.ai_classifier.retrieve_similar_nodes",
|
||||
return_value=[],
|
||||
)
|
||||
mock_permitted = mocker.patch(
|
||||
"paperless_ai.ai_classifier.permitted_object_ids",
|
||||
mock_get_objects = mocker.patch(
|
||||
"paperless_ai.ai_classifier.get_objects_for_user_owner_aware",
|
||||
)
|
||||
|
||||
get_taxonomy_context(document, None)
|
||||
|
||||
mock_permitted.assert_not_called()
|
||||
mock_get_objects.assert_not_called()
|
||||
assert mock_retrieve.call_args.kwargs["document_ids"] is None
|
||||
|
||||
@pytest.mark.django_db
|
||||
@override_settings(LLM_EMBEDDING_BACKEND="huggingface")
|
||||
def test_restricts_to_visible_documents_for_non_superuser(
|
||||
self,
|
||||
mocker: pytest_mock.MockerFixture,
|
||||
@@ -587,7 +537,7 @@ class TestGetTaxonomyContextVisibility:
|
||||
WHEN:
|
||||
- get_taxonomy_context() is called
|
||||
THEN:
|
||||
- The user's permitted document ids are looked up and passed to
|
||||
- The user's visible document ids are looked up and passed to
|
||||
retrieve_similar_nodes() as a restriction
|
||||
"""
|
||||
document = DocumentFactory.create(content="Some content")
|
||||
@@ -595,186 +545,21 @@ class TestGetTaxonomyContextVisibility:
|
||||
"paperless_ai.ai_classifier.retrieve_similar_nodes",
|
||||
return_value=[],
|
||||
)
|
||||
mock_permitted = mocker.patch(
|
||||
"paperless_ai.ai_classifier.permitted_object_ids",
|
||||
return_value=[1, 2, 3],
|
||||
mock_queryset = mocker.MagicMock()
|
||||
mock_queryset.values_list.return_value = [1, 2, 3]
|
||||
mock_get_objects = mocker.patch(
|
||||
"paperless_ai.ai_classifier.get_objects_for_user_owner_aware",
|
||||
return_value=mock_queryset,
|
||||
)
|
||||
user = UserFactory.create(is_superuser=False)
|
||||
|
||||
get_taxonomy_context(document, user)
|
||||
|
||||
mock_permitted.assert_called_once_with(user, Document, "view_document")
|
||||
mock_get_objects.assert_called_once_with(user, "view_document", Document)
|
||||
assert mock_retrieve.call_args.kwargs["document_ids"] == [1, 2, 3]
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestFulltextSimilarDocuments:
|
||||
"""_fulltext_similar_documents is the no-embedding-backend fallback: it
|
||||
asks the Tantivy full-text index for "More Like This" neighbours instead
|
||||
of the vector store, and synthesizes a rank-based weight since Tantivy's
|
||||
more_like_this_ids returns only an ordered id list, no scores.
|
||||
"""
|
||||
|
||||
@pytest.fixture
|
||||
def fulltext_backend(
|
||||
self,
|
||||
mocker: pytest_mock.MockerFixture,
|
||||
) -> Generator[TantivyBackend, None, None]:
|
||||
"""An in-memory Tantivy backend, wired up as the module-level
|
||||
singleton _fulltext_similar_documents resolves via get_backend()."""
|
||||
backend = TantivyBackend(path=None)
|
||||
backend.open()
|
||||
mocker.patch("documents.search.get_backend", return_value=backend)
|
||||
try:
|
||||
yield backend
|
||||
finally:
|
||||
backend.close()
|
||||
|
||||
def test_ranks_by_rank_based_weight_descending(
|
||||
self,
|
||||
fulltext_backend: TantivyBackend,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A source document and two similar documents indexed in Tantivy
|
||||
WHEN:
|
||||
- _fulltext_similar_documents() is called
|
||||
THEN:
|
||||
- Each result's weight reflects its rank (first result weighted
|
||||
higher than the second), not a raw similarity score
|
||||
"""
|
||||
source = DocumentFactory.create(content="quarterly financial report details")
|
||||
first = DocumentFactory.create(content="quarterly financial report details")
|
||||
second = DocumentFactory.create(content="financial report")
|
||||
for doc in (source, first, second):
|
||||
fulltext_backend.add_or_update(doc)
|
||||
|
||||
result = _fulltext_similar_documents(source, user=None, top_k=5)
|
||||
|
||||
assert len(result) == 2
|
||||
weight_by_id = {s["document_id"]: s["weight"] for s in result}
|
||||
assert weight_by_id[first.pk] > weight_by_id[second.pk]
|
||||
|
||||
def test_excludes_source_document(
|
||||
self,
|
||||
fulltext_backend: TantivyBackend,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A source document indexed in Tantivy with no other documents
|
||||
WHEN:
|
||||
- _fulltext_similar_documents() is called
|
||||
THEN:
|
||||
- An empty list is returned - the source document is never its
|
||||
own similar document
|
||||
"""
|
||||
source = DocumentFactory.create(content="unique unrelated content")
|
||||
fulltext_backend.add_or_update(source)
|
||||
|
||||
result = _fulltext_similar_documents(source, user=None, top_k=5)
|
||||
|
||||
assert result == []
|
||||
|
||||
def test_empty_index_returns_empty_list(
|
||||
self,
|
||||
fulltext_backend: TantivyBackend,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A document that has never been indexed (fresh/empty Tantivy index)
|
||||
WHEN:
|
||||
- _fulltext_similar_documents() is called
|
||||
THEN:
|
||||
- An empty list is returned rather than raising
|
||||
"""
|
||||
source = DocumentFactory.create(content="never indexed")
|
||||
|
||||
result = _fulltext_similar_documents(source, user=None, top_k=5)
|
||||
|
||||
assert result == []
|
||||
|
||||
def test_respects_top_k_limit(
|
||||
self,
|
||||
fulltext_backend: TantivyBackend,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A source document and four similar documents indexed
|
||||
WHEN:
|
||||
- _fulltext_similar_documents() is called with top_k=2
|
||||
THEN:
|
||||
- At most 2 results are returned
|
||||
"""
|
||||
source = DocumentFactory.create(content="shared overlapping keyword text")
|
||||
fulltext_backend.add_or_update(source)
|
||||
for _ in range(4):
|
||||
fulltext_backend.add_or_update(
|
||||
DocumentFactory.create(content="shared overlapping keyword text"),
|
||||
)
|
||||
|
||||
result = _fulltext_similar_documents(source, user=None, top_k=2)
|
||||
|
||||
assert len(result) == 2
|
||||
|
||||
def test_result_shape_is_similar_document(
|
||||
self,
|
||||
fulltext_backend: TantivyBackend,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A source document and one similar document indexed
|
||||
WHEN:
|
||||
- _fulltext_similar_documents() is called
|
||||
THEN:
|
||||
- Each result is a SimilarDocument (document_id + weight only)
|
||||
"""
|
||||
source = DocumentFactory.create(content="shared content phrase")
|
||||
other = DocumentFactory.create(content="shared content phrase")
|
||||
fulltext_backend.add_or_update(source)
|
||||
fulltext_backend.add_or_update(other)
|
||||
|
||||
result = _fulltext_similar_documents(source, user=None, top_k=5)
|
||||
|
||||
# rank 0 (the only/best result) with top_k=5 -> weight = top_k - rank = 5.0,
|
||||
# per the "first result gets top_k, the last gets 1" formula.
|
||||
assert result == [SimilarDocument(document_id=other.pk, weight=5.0)]
|
||||
|
||||
def test_superuser_sees_other_users_documents(
|
||||
self,
|
||||
fulltext_backend: TantivyBackend,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A source document owned by one user and a similar document
|
||||
owned by a different user, with no sharing between them
|
||||
WHEN:
|
||||
- _fulltext_similar_documents() is called with a superuser
|
||||
THEN:
|
||||
- The other user's document is still returned as a similar
|
||||
document - a superuser must not be narrowed by the backend's
|
||||
owner-based permission filter
|
||||
"""
|
||||
owner = UserFactory.create()
|
||||
other_owner = UserFactory.create()
|
||||
superuser = UserFactory.create(is_superuser=True)
|
||||
source = DocumentFactory.create(
|
||||
content="shared content phrase",
|
||||
owner=owner,
|
||||
)
|
||||
other = DocumentFactory.create(
|
||||
content="shared content phrase",
|
||||
owner=other_owner,
|
||||
)
|
||||
fulltext_backend.add_or_update(source)
|
||||
fulltext_backend.add_or_update(other)
|
||||
|
||||
result = _fulltext_similar_documents(source, user=superuser, top_k=5)
|
||||
|
||||
assert [s["document_id"] for s in result] == [other.pk]
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@override_settings(LLM_EMBEDDING_BACKEND="huggingface")
|
||||
@patch("paperless_ai.ai_classifier.retrieve_similar_nodes")
|
||||
def test_get_taxonomy_context_retrieval_failure_degrades_to_no_hints(mock_retrieve):
|
||||
"""
|
||||
@@ -801,7 +586,6 @@ def test_get_taxonomy_context_retrieval_failure_degrades_to_no_hints(mock_retrie
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@override_settings(LLM_EMBEDDING_BACKEND="huggingface")
|
||||
@patch("paperless_ai.ai_classifier.build_taxonomy_candidates")
|
||||
@patch("paperless_ai.ai_classifier.retrieve_similar_nodes")
|
||||
def test_get_taxonomy_context_candidate_building_failure_degrades_to_no_hints(
|
||||
@@ -841,10 +625,11 @@ def test_build_prompt_without_rag_includes_taxonomy_block():
|
||||
GIVEN:
|
||||
- Non-empty taxonomy candidates
|
||||
WHEN:
|
||||
- build_prompt_without_rag() is called with candidates and assigned metadata
|
||||
- build_prompt_without_rag() is called with candidates
|
||||
THEN:
|
||||
- The candidate's id and the existing_ids/new_names instructions appear
|
||||
- Candidates are presented as deduplication options, not requirements
|
||||
- The candidate and single-call reconciliation instructions appear
|
||||
- Complete name suggestions remain mandatory
|
||||
- Assigned metadata is not included
|
||||
"""
|
||||
document = DocumentFactory.create(content="Some content")
|
||||
config = AIConfig()
|
||||
@@ -854,40 +639,31 @@ def test_build_prompt_without_rag_includes_taxonomy_block():
|
||||
"correspondents": [],
|
||||
"storage_paths": [],
|
||||
}
|
||||
assigned = {
|
||||
"tags": [],
|
||||
"document_type": None,
|
||||
"correspondent": None,
|
||||
"storage_path": None,
|
||||
}
|
||||
|
||||
prompt = build_prompt_without_rag(
|
||||
document,
|
||||
config,
|
||||
candidates=candidates,
|
||||
assigned=assigned,
|
||||
)
|
||||
|
||||
assert '"id": 12' in prompt
|
||||
assert "existing_ids" in prompt
|
||||
assert "new_names" in prompt
|
||||
assert "not requirements" in prompt
|
||||
assert "weak candidate" in prompt
|
||||
assert "Always include every suggested name" in prompt
|
||||
assert "matched_*" in prompt
|
||||
assert "corresponding *_ids" in prompt
|
||||
assert "Candidates must not create, replace, or suppress suggestions" in prompt
|
||||
assert "already assigned" not in prompt
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_build_prompt_without_rag_identical_when_no_hints():
|
||||
def test_build_prompt_without_rag_identical_when_no_candidates():
|
||||
"""
|
||||
GIVEN:
|
||||
- Empty taxonomy candidates and empty assigned metadata
|
||||
- Empty taxonomy candidates
|
||||
WHEN:
|
||||
- build_prompt_without_rag() is called with those empty values, and
|
||||
separately with no candidates/assigned at all
|
||||
separately with no candidates at all
|
||||
THEN:
|
||||
- Both prompts are identical
|
||||
- Neither carries the "Available ..." candidate block or the
|
||||
id-vs-name routing instruction
|
||||
- Both still tell the model to leave existing_ids empty
|
||||
- Neither carries candidate reconciliation instructions
|
||||
"""
|
||||
document = DocumentFactory.create(content="Some content")
|
||||
config = AIConfig()
|
||||
@@ -897,67 +673,37 @@ def test_build_prompt_without_rag_identical_when_no_hints():
|
||||
"correspondents": [],
|
||||
"storage_paths": [],
|
||||
}
|
||||
empty_assigned = {
|
||||
"tags": [],
|
||||
"document_type": None,
|
||||
"correspondent": None,
|
||||
"storage_path": None,
|
||||
}
|
||||
|
||||
with_empty_hints = build_prompt_without_rag(
|
||||
document,
|
||||
config,
|
||||
candidates=empty_candidates,
|
||||
assigned=empty_assigned,
|
||||
)
|
||||
with_no_hints = build_prompt_without_rag(document, config)
|
||||
|
||||
assert with_empty_hints == with_no_hints
|
||||
assert "Available " not in with_no_hints
|
||||
assert "put its id in existing_ids" not in with_no_hints
|
||||
assert "leave every existing_ids list empty" in with_no_hints
|
||||
assert "matched_*" not in with_no_hints
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_build_prompt_without_rag_tells_model_to_skip_ids_when_no_candidates():
|
||||
def test_build_prompt_without_rag_never_includes_assigned_metadata():
|
||||
"""
|
||||
GIVEN:
|
||||
- Assigned metadata but empty taxonomy candidates
|
||||
- A document with assigned taxonomy metadata
|
||||
WHEN:
|
||||
- build_prompt_without_rag() is called with candidates and assigned metadata
|
||||
- build_prompt_without_rag() is called
|
||||
THEN:
|
||||
- The assigned-metadata block appears (taxonomy_block is non-empty)
|
||||
- The prompt tells the model to leave existing_ids empty
|
||||
|
||||
Staying silent about existing_ids here is not enough: the response schema
|
||||
advertises the field whatever the prompt says, and models fill it with
|
||||
placeholder ids that resolve to real but unrelated objects (#13831).
|
||||
- Assigned metadata is absent so it cannot anchor classification
|
||||
"""
|
||||
document = DocumentFactory.create(content="Some content")
|
||||
config = AIConfig()
|
||||
empty_candidates = {
|
||||
"tags": [],
|
||||
"document_types": [],
|
||||
"correspondents": [],
|
||||
"storage_paths": [],
|
||||
}
|
||||
assigned = {
|
||||
"tags": ["Bloodwork"],
|
||||
"document_type": None,
|
||||
"correspondent": None,
|
||||
"storage_path": None,
|
||||
}
|
||||
assigned_tag = TagFactory.create(name="Bloodwork")
|
||||
document.tags.add(assigned_tag)
|
||||
|
||||
prompt = build_prompt_without_rag(
|
||||
document,
|
||||
config,
|
||||
candidates=empty_candidates,
|
||||
assigned=assigned,
|
||||
)
|
||||
prompt = build_prompt_without_rag(document, config)
|
||||
|
||||
assert "already assigned" in prompt
|
||||
assert "No candidates are shown" in prompt
|
||||
assert "leave every existing_ids list empty" in prompt
|
||||
assert "Bloodwork" not in prompt
|
||||
assert "already assigned" not in prompt
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
|
||||
@@ -1,13 +1,13 @@
|
||||
import json
|
||||
|
||||
from paperless_ai.base_model import MAX_DATES
|
||||
from paperless_ai.base_model import MAX_EXISTING_IDS
|
||||
from paperless_ai.base_model import MAX_NEW_NAMES
|
||||
from paperless_ai.base_model import MAX_TITLE_LENGTH
|
||||
from paperless_ai.base_model import ClassificationSuggestions
|
||||
from paperless_ai.base_model import DocumentClassifierSchema
|
||||
from paperless_ai.base_model import TaxonomyChoice
|
||||
from paperless_ai.base_model import TaxonomyChoiceDict
|
||||
from paperless_ai.base_model import classification_suggestions_to_model
|
||||
from paperless_ai.base_model import model_to_classification_suggestions
|
||||
|
||||
|
||||
def test_document_classifier_schema_declared_defaults():
|
||||
@@ -18,29 +18,116 @@ def test_document_classifier_schema_declared_defaults():
|
||||
WHEN:
|
||||
- The schema is dumped to a dict via model_dump()
|
||||
THEN:
|
||||
- Every taxonomy field dumps as an empty existing_ids/new_names
|
||||
dict, and dates dumps as an empty list
|
||||
- Every optional name field, and dates, dump as empty lists
|
||||
|
||||
This is the one project-owned fact worth pinning down here: which
|
||||
defaults this schema declares for a partial LLM response (see
|
||||
client.py's DocumentClassifierSchema(**json.loads(...)) call sites,
|
||||
which construct from whatever subset of fields the backend actually
|
||||
returned). It deliberately hardcodes the expected literal rather than
|
||||
re-deriving it from TaxonomyChoice()/[] - pydantic's own
|
||||
default_factory machinery is not this project's to re-test, and a
|
||||
test that recomputes the expected value from the model under test
|
||||
can't ever catch a wrong default.
|
||||
The model may omit optional fields, so the schema must provide the complete
|
||||
empty shape expected by the conversion and matching pipeline.
|
||||
"""
|
||||
schema = DocumentClassifierSchema(title="Test Title")
|
||||
|
||||
dumped = schema.model_dump()
|
||||
|
||||
empty_choice = {"existing_ids": [], "new_names": []}
|
||||
assert dumped["tags"] == empty_choice
|
||||
assert dumped["correspondents"] == empty_choice
|
||||
assert dumped["document_types"] == empty_choice
|
||||
assert dumped["storage_paths"] == empty_choice
|
||||
assert dumped["dates"] == []
|
||||
assert dumped == {
|
||||
"title": "Test Title",
|
||||
"tags": [],
|
||||
"matched_tags": [],
|
||||
"tag_ids": [],
|
||||
"correspondents": [],
|
||||
"matched_correspondents": [],
|
||||
"correspondent_ids": [],
|
||||
"document_types": [],
|
||||
"matched_document_types": [],
|
||||
"document_type_ids": [],
|
||||
"storage_paths": [],
|
||||
"matched_storage_paths": [],
|
||||
"storage_path_ids": [],
|
||||
"dates": [],
|
||||
}
|
||||
|
||||
|
||||
def test_model_response_converts_names_to_internal_taxonomy_choices():
|
||||
"""
|
||||
GIVEN:
|
||||
- A model response containing taxonomy names
|
||||
WHEN:
|
||||
- It is converted to Paperless' internal suggestion representation
|
||||
THEN:
|
||||
- Names enter the internal taxonomy representation as new names
|
||||
- Existing IDs remain empty for deterministic application-side matching
|
||||
"""
|
||||
parsed = DocumentClassifierSchema(
|
||||
title="Electricity Bill",
|
||||
tags=["Utilities", "Electricity"],
|
||||
correspondents=["Power Company"],
|
||||
document_types=["Utility Bill"],
|
||||
storage_paths=["Finance/Utilities"],
|
||||
)
|
||||
suggestions = model_to_classification_suggestions(parsed)
|
||||
|
||||
assert suggestions["tags"] == {
|
||||
"existing_ids": [],
|
||||
"new_names": ["Utilities", "Electricity"],
|
||||
}
|
||||
assert suggestions["correspondents"] == {
|
||||
"existing_ids": [],
|
||||
"new_names": ["Power Company"],
|
||||
}
|
||||
assert suggestions["document_types"] == {
|
||||
"existing_ids": [],
|
||||
"new_names": ["Utility Bill"],
|
||||
}
|
||||
assert suggestions["storage_paths"] == {
|
||||
"existing_ids": [],
|
||||
"new_names": ["Finance/Utilities"],
|
||||
}
|
||||
|
||||
|
||||
def test_valid_candidate_mappings_replace_only_the_matched_names():
|
||||
parsed = DocumentClassifierSchema(
|
||||
title="Electricity Bill",
|
||||
tags=["Utilities", "Electricity"],
|
||||
matched_tags=["Utilities"],
|
||||
tag_ids=[12],
|
||||
correspondents=["Power Company"],
|
||||
matched_correspondents=["Power Company"],
|
||||
correspondent_ids=[23],
|
||||
)
|
||||
|
||||
suggestions = model_to_classification_suggestions(
|
||||
parsed,
|
||||
{
|
||||
"tags": {12},
|
||||
"correspondents": {23},
|
||||
},
|
||||
)
|
||||
|
||||
assert suggestions["tags"] == {
|
||||
"existing_ids": [12],
|
||||
"new_names": ["Electricity"],
|
||||
}
|
||||
assert suggestions["correspondents"] == {
|
||||
"existing_ids": [23],
|
||||
"new_names": [],
|
||||
}
|
||||
|
||||
|
||||
def test_invalid_or_unpaired_candidate_mappings_do_not_remove_names():
|
||||
parsed = DocumentClassifierSchema(
|
||||
title="Electricity Bill",
|
||||
tags=["Utilities", "Electricity", "Energy"],
|
||||
matched_tags=["Invented", "Utilities", "Electricity"],
|
||||
tag_ids=[12, 999],
|
||||
)
|
||||
|
||||
suggestions = model_to_classification_suggestions(
|
||||
parsed,
|
||||
{"tags": {12}},
|
||||
)
|
||||
|
||||
assert suggestions["tags"] == {
|
||||
"existing_ids": [],
|
||||
"new_names": ["Utilities", "Electricity", "Energy"],
|
||||
}
|
||||
|
||||
|
||||
def test_document_classifier_schema_json_schema_is_self_contained():
|
||||
@@ -50,23 +137,20 @@ def test_document_classifier_schema_json_schema_is_self_contained():
|
||||
WHEN:
|
||||
- Its JSON schema is generated via model_json_schema()
|
||||
THEN:
|
||||
- No $defs section and no $ref at any depth survives in the schema
|
||||
- Each taxonomy property carries existing_ids/new_names inline
|
||||
- The schema contains no definitions, references, or nested objects
|
||||
- Every response field is a scalar or flat array
|
||||
|
||||
Regression guard: Google's function-declaration schema rejects the $ref
|
||||
Pydantic normally emits for the nested TaxonomyChoice model.
|
||||
This keeps the function declaration compatible with backends that reject
|
||||
JSON Schema references and with smaller models that struggle with nesting.
|
||||
"""
|
||||
schema = DocumentClassifierSchema.model_json_schema()
|
||||
|
||||
assert "$defs" not in schema
|
||||
assert "$ref" not in json.dumps(schema)
|
||||
for field in ("tags", "correspondents", "document_types", "storage_paths"):
|
||||
field_schema = schema["properties"][field]
|
||||
assert "$ref" not in field_schema
|
||||
assert set(field_schema["properties"].keys()) == {
|
||||
"existing_ids",
|
||||
"new_names",
|
||||
}
|
||||
assert all(
|
||||
field_schema.get("type") != "object"
|
||||
for field_schema in schema["properties"].values()
|
||||
)
|
||||
|
||||
|
||||
def test_every_field_describes_itself_to_the_model():
|
||||
@@ -76,8 +160,7 @@ def test_every_field_describes_itself_to_the_model():
|
||||
WHEN:
|
||||
- Its JSON schema is generated via model_json_schema()
|
||||
THEN:
|
||||
- Every property, and every property of each inlined TaxonomyChoice,
|
||||
carries a non-empty description
|
||||
- Every property carries a non-empty description
|
||||
|
||||
In tool-calling mode the schema is most of what tells the model how to
|
||||
fill these fields; on field names alone, small models can bin tags and
|
||||
@@ -86,48 +169,14 @@ def test_every_field_describes_itself_to_the_model():
|
||||
schema = DocumentClassifierSchema.model_json_schema()
|
||||
|
||||
undescribed = [
|
||||
f"{owner}.{name}"
|
||||
for owner, definition in [
|
||||
("DocumentClassifierSchema", schema),
|
||||
*(
|
||||
(name, prop)
|
||||
for name, prop in schema["properties"].items()
|
||||
if prop.get("type") == "object"
|
||||
),
|
||||
]
|
||||
for name, prop in definition.get("properties", {}).items()
|
||||
name
|
||||
for name, prop in schema["properties"].items()
|
||||
if not prop.get("description")
|
||||
]
|
||||
|
||||
assert undescribed == []
|
||||
|
||||
|
||||
def test_inlining_keeps_each_taxonomy_fields_own_description():
|
||||
"""
|
||||
GIVEN:
|
||||
- The DocumentClassifierSchema pydantic model
|
||||
WHEN:
|
||||
- Its JSON schema is generated via model_json_schema()
|
||||
THEN:
|
||||
- Each taxonomy field keeps its own description, not the shared one
|
||||
- The inlined TaxonomyChoice properties survive underneath it
|
||||
|
||||
Pydantic emits a field's description as a sibling of its $ref, so
|
||||
replacing the property outright collapses all four onto TaxonomyChoice's
|
||||
docstring - which still passes a "has a description" check.
|
||||
"""
|
||||
properties = DocumentClassifierSchema.model_json_schema()["properties"]
|
||||
|
||||
taxonomy_fields = ("tags", "correspondents", "document_types", "storage_paths")
|
||||
descriptions = {
|
||||
field: properties[field]["description"] for field in taxonomy_fields
|
||||
}
|
||||
|
||||
assert len(set(descriptions.values())) == len(taxonomy_fields)
|
||||
for field in taxonomy_fields:
|
||||
assert properties[field]["properties"]["existing_ids"]["description"]
|
||||
|
||||
|
||||
def test_every_sequence_in_the_emitted_schema_is_bounded():
|
||||
"""
|
||||
GIVEN:
|
||||
@@ -135,22 +184,13 @@ def test_every_sequence_in_the_emitted_schema_is_bounded():
|
||||
WHEN:
|
||||
- Its JSON schema is generated via model_json_schema()
|
||||
THEN:
|
||||
- Every array property in the schema, including those on each
|
||||
inlined TaxonomyChoice, carries a maxItems
|
||||
- Every array property in the schema carries a maxItems
|
||||
"""
|
||||
schema = DocumentClassifierSchema.model_json_schema()
|
||||
|
||||
unbounded = [
|
||||
f"{owner}.{name}"
|
||||
for owner, definition in [
|
||||
("DocumentClassifierSchema", schema),
|
||||
*(
|
||||
(name, prop)
|
||||
for name, prop in schema["properties"].items()
|
||||
if prop.get("type") == "object"
|
||||
),
|
||||
]
|
||||
for name, prop in definition.get("properties", {}).items()
|
||||
name
|
||||
for name, prop in schema["properties"].items()
|
||||
if prop.get("type") == "array" and "maxItems" not in prop
|
||||
]
|
||||
|
||||
@@ -182,17 +222,13 @@ def test_over_long_response_is_truncated_rather_than_rejected():
|
||||
"""
|
||||
parsed = DocumentClassifierSchema(
|
||||
title="T" * (MAX_TITLE_LENGTH + 50),
|
||||
tags=TaxonomyChoice(
|
||||
existing_ids=list(range(MAX_EXISTING_IDS + 20)),
|
||||
new_names=["n"] * (MAX_NEW_NAMES + 20),
|
||||
),
|
||||
tags=["n"] * (MAX_NEW_NAMES + 20),
|
||||
dates=[f"2016-{month:02d}-01" for month in range(1, 13)],
|
||||
)
|
||||
|
||||
assert len(parsed.title) == MAX_TITLE_LENGTH
|
||||
assert len(parsed.dates) == MAX_DATES
|
||||
assert len(parsed.tags.existing_ids) == MAX_EXISTING_IDS
|
||||
assert len(parsed.tags.new_names) == MAX_NEW_NAMES
|
||||
assert len(parsed.tags) == MAX_NEW_NAMES
|
||||
|
||||
|
||||
def test_truncation_keeps_the_earliest_entries():
|
||||
@@ -212,24 +248,66 @@ def test_truncation_keeps_the_earliest_entries():
|
||||
assert parsed.dates == ["2016-10-01", "2016-09-01", "2016-08-01"]
|
||||
|
||||
|
||||
def test_model_dump_matches_typed_dict_keys():
|
||||
def test_model_conversion_matches_internal_typed_dict_keys():
|
||||
"""
|
||||
GIVEN:
|
||||
- A DocumentClassifierSchema instance
|
||||
WHEN:
|
||||
- It is dumped to a dict via model_dump()
|
||||
- It is converted to ClassificationSuggestions
|
||||
THEN:
|
||||
- The dumped dict's keys exactly match ClassificationSuggestions'
|
||||
- The converted dict's keys exactly match ClassificationSuggestions'
|
||||
declared keys
|
||||
- The dumped tags dict's keys exactly match TaxonomyChoiceDict's
|
||||
- The converted tags dict's keys exactly match TaxonomyChoiceDict's
|
||||
declared keys
|
||||
"""
|
||||
# TaxonomyChoiceDict/ClassificationSuggestions are the static-typing
|
||||
# counterparts of TaxonomyChoice/DocumentClassifierSchema - this pins
|
||||
# down that .model_dump()'s actual runtime keys are exactly what the
|
||||
# TypedDicts declare, so the two don't silently drift apart.
|
||||
schema = DocumentClassifierSchema(title="T", tags=TaxonomyChoice(existing_ids=[1]))
|
||||
dumped = schema.model_dump()
|
||||
schema = DocumentClassifierSchema(title="T", tags=["Tag"])
|
||||
suggestions = model_to_classification_suggestions(schema)
|
||||
|
||||
assert set(dumped.keys()) == set(ClassificationSuggestions.__annotations__.keys())
|
||||
assert set(dumped["tags"].keys()) == set(TaxonomyChoiceDict.__annotations__.keys())
|
||||
assert set(suggestions.keys()) == set(
|
||||
ClassificationSuggestions.__annotations__.keys(),
|
||||
)
|
||||
assert set(suggestions["tags"].keys()) == set(
|
||||
TaxonomyChoiceDict.__annotations__.keys(),
|
||||
)
|
||||
|
||||
|
||||
def test_internal_suggestions_convert_to_names_only_model():
|
||||
suggestions = ClassificationSuggestions(
|
||||
title="Electricity Bill",
|
||||
tags=TaxonomyChoiceDict(existing_ids=[1], new_names=["Utilities"]),
|
||||
correspondents=TaxonomyChoiceDict(
|
||||
existing_ids=[2],
|
||||
new_names=["Power Company"],
|
||||
),
|
||||
document_types=TaxonomyChoiceDict(
|
||||
existing_ids=[3],
|
||||
new_names=["Utility Bill"],
|
||||
),
|
||||
storage_paths=TaxonomyChoiceDict(
|
||||
existing_ids=[4],
|
||||
new_names=["Finance/Utilities"],
|
||||
),
|
||||
dates=["2026-08-30"],
|
||||
)
|
||||
|
||||
model = classification_suggestions_to_model(suggestions)
|
||||
|
||||
converted = model_to_classification_suggestions(model)
|
||||
|
||||
assert converted == ClassificationSuggestions(
|
||||
title="Electricity Bill",
|
||||
tags=TaxonomyChoiceDict(existing_ids=[], new_names=["Utilities"]),
|
||||
correspondents=TaxonomyChoiceDict(
|
||||
existing_ids=[],
|
||||
new_names=["Power Company"],
|
||||
),
|
||||
document_types=TaxonomyChoiceDict(
|
||||
existing_ids=[],
|
||||
new_names=["Utility Bill"],
|
||||
),
|
||||
storage_paths=TaxonomyChoiceDict(
|
||||
existing_ids=[],
|
||||
new_names=["Finance/Utilities"],
|
||||
),
|
||||
dates=["2026-08-30"],
|
||||
)
|
||||
|
||||
@@ -123,19 +123,24 @@ def test_run_llm_query_ollama_uses_structured_json(mock_ai_config, mock_ollama_l
|
||||
mock_llm_instance.chat.return_value.message.content = json.dumps(
|
||||
{
|
||||
"title": "Test Title",
|
||||
"tags": {"existing_ids": [1], "new_names": ["document"]},
|
||||
"correspondents": {"existing_ids": [], "new_names": ["John Doe"]},
|
||||
"document_types": {"existing_ids": [], "new_names": ["report"]},
|
||||
"storage_paths": {"existing_ids": [], "new_names": ["Reports"]},
|
||||
"tags": ["document"],
|
||||
"matched_tags": ["document"],
|
||||
"tag_ids": [1],
|
||||
"correspondents": ["John Doe"],
|
||||
"document_types": ["report"],
|
||||
"storage_paths": ["Reports"],
|
||||
"dates": ["2023-01-01"],
|
||||
},
|
||||
)
|
||||
|
||||
client = AIClient()
|
||||
result = client.run_llm_query("test_prompt")
|
||||
result = client.run_llm_query(
|
||||
"test_prompt",
|
||||
allowed_candidate_ids={"tags": {1}},
|
||||
)
|
||||
|
||||
assert result["title"] == "Test Title"
|
||||
assert result["tags"] == {"existing_ids": [1], "new_names": ["document"]}
|
||||
assert result["tags"] == {"existing_ids": [1], "new_names": []}
|
||||
mock_llm_instance.chat.assert_called_once_with(
|
||||
[ANY],
|
||||
format=ANY,
|
||||
@@ -156,10 +161,12 @@ def test_run_llm_query_openai_uses_tools(mock_ai_config, mock_openai_llm):
|
||||
tool_name="DocumentClassifierSchema",
|
||||
tool_kwargs={
|
||||
"title": "Test Title",
|
||||
"tags": {"existing_ids": [1], "new_names": ["document"]},
|
||||
"correspondents": {"existing_ids": [], "new_names": ["John Doe"]},
|
||||
"document_types": {"existing_ids": [], "new_names": ["report"]},
|
||||
"storage_paths": {"existing_ids": [], "new_names": ["Reports"]},
|
||||
"tags": ["document"],
|
||||
"matched_tags": ["document"],
|
||||
"tag_ids": [1],
|
||||
"correspondents": ["John Doe"],
|
||||
"document_types": ["report"],
|
||||
"storage_paths": ["Reports"],
|
||||
"dates": ["2023-01-01"],
|
||||
},
|
||||
)
|
||||
@@ -168,10 +175,13 @@ def test_run_llm_query_openai_uses_tools(mock_ai_config, mock_openai_llm):
|
||||
mock_llm_instance.get_tool_calls_from_response.return_value = [tool_selection]
|
||||
|
||||
client = AIClient()
|
||||
result = client.run_llm_query("test_prompt")
|
||||
result = client.run_llm_query(
|
||||
"test_prompt",
|
||||
allowed_candidate_ids={"tags": {1}},
|
||||
)
|
||||
|
||||
assert result["title"] == "Test Title"
|
||||
assert result["tags"] == {"existing_ids": [1], "new_names": ["document"]}
|
||||
assert result["tags"] == {"existing_ids": [1], "new_names": []}
|
||||
mock_llm_instance.chat_with_tools.assert_called_once()
|
||||
|
||||
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
import json
|
||||
from types import SimpleNamespace
|
||||
|
||||
import pytest
|
||||
import pytest_mock
|
||||
@@ -10,7 +11,6 @@ from documents.tests.factories import StoragePathFactory
|
||||
from documents.tests.factories import TagFactory
|
||||
from documents.tests.factories import UserFactory
|
||||
from paperless_ai.taxonomy import AssignedMetadata
|
||||
from paperless_ai.taxonomy import SimilarDocument
|
||||
from paperless_ai.taxonomy import TaxonomyCandidates
|
||||
from paperless_ai.taxonomy import build_taxonomy_candidates
|
||||
from paperless_ai.taxonomy import format_taxonomy_for_prompt
|
||||
@@ -132,8 +132,9 @@ class TestGetAssignedMetadata:
|
||||
assert result["tags"] == ["Owned By Someone Else"]
|
||||
|
||||
|
||||
def make_similar(document_id: int, weight: float) -> SimilarDocument:
|
||||
return SimilarDocument(document_id=document_id, weight=weight)
|
||||
def make_node(document_id: int, score: float) -> SimpleNamespace:
|
||||
"""A stand-in for NodeWithScore: only ``.metadata``/``.score`` are read."""
|
||||
return SimpleNamespace(metadata={"document_id": str(document_id)}, score=score)
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@@ -169,9 +170,9 @@ class TestBuildTaxonomyCandidates:
|
||||
doc_a.tags.add(tag)
|
||||
doc_b = DocumentFactory.create()
|
||||
doc_b.tags.add(tag)
|
||||
similar_documents = [make_similar(doc_a.pk, 0.9), make_similar(doc_b.pk, 0.4)]
|
||||
nodes = [make_node(doc_a.pk, 0.9), make_node(doc_b.pk, 0.4)]
|
||||
|
||||
result = build_taxonomy_candidates(similar_documents, user=None)
|
||||
result = build_taxonomy_candidates(nodes, user=None)
|
||||
|
||||
assert len(result["tags"]) == 1
|
||||
assert result["tags"][0]["id"] == tag.pk
|
||||
@@ -196,9 +197,9 @@ class TestBuildTaxonomyCandidates:
|
||||
document.tags.add(tag)
|
||||
tag.name = "New Name"
|
||||
tag.save()
|
||||
similar_documents = [make_similar(document.pk, 0.5)]
|
||||
nodes = [make_node(document.pk, 0.5)]
|
||||
|
||||
result = build_taxonomy_candidates(similar_documents, user=None)
|
||||
result = build_taxonomy_candidates(nodes, user=None)
|
||||
|
||||
assert result["tags"][0]["name"] == "New Name"
|
||||
|
||||
@@ -218,9 +219,9 @@ class TestBuildTaxonomyCandidates:
|
||||
document = DocumentFactory.create()
|
||||
document.tags.add(tag)
|
||||
tag.delete()
|
||||
similar_documents = [make_similar(document.pk, 0.5)]
|
||||
nodes = [make_node(document.pk, 0.5)]
|
||||
|
||||
result = build_taxonomy_candidates(similar_documents, user=None)
|
||||
result = build_taxonomy_candidates(nodes, user=None)
|
||||
|
||||
assert result["tags"] == []
|
||||
|
||||
@@ -239,12 +240,9 @@ class TestBuildTaxonomyCandidates:
|
||||
strong_doc.tags.add(strong_tag)
|
||||
weak_doc = DocumentFactory.create()
|
||||
weak_doc.tags.add(weak_tag)
|
||||
similar_documents = [
|
||||
make_similar(strong_doc.pk, 0.9),
|
||||
make_similar(weak_doc.pk, 0.1),
|
||||
]
|
||||
nodes = [make_node(strong_doc.pk, 0.9), make_node(weak_doc.pk, 0.1)]
|
||||
|
||||
result = build_taxonomy_candidates(similar_documents, user=None)
|
||||
result = build_taxonomy_candidates(nodes, user=None)
|
||||
|
||||
assert [c["name"] for c in result["tags"]] == ["Strong", "Weak"]
|
||||
|
||||
@@ -260,9 +258,9 @@ class TestBuildTaxonomyCandidates:
|
||||
document = DocumentFactory.create()
|
||||
for i in range(15):
|
||||
document.tags.add(TagFactory.create(name=f"Tag{i}"))
|
||||
similar_documents = [make_similar(document.pk, 0.5)]
|
||||
nodes = [make_node(document.pk, 0.5)]
|
||||
|
||||
result = build_taxonomy_candidates(similar_documents, user=None)
|
||||
result = build_taxonomy_candidates(nodes, user=None)
|
||||
|
||||
assert len(result["tags"]) == 10
|
||||
|
||||
@@ -276,12 +274,12 @@ class TestBuildTaxonomyCandidates:
|
||||
- Only 5 correspondents are returned
|
||||
"""
|
||||
correspondents = CorrespondentFactory.create_batch(7)
|
||||
similar_documents = [
|
||||
make_similar(DocumentFactory.create(correspondent=c).pk, 0.5)
|
||||
nodes = [
|
||||
make_node(DocumentFactory.create(correspondent=c).pk, 0.5)
|
||||
for c in correspondents
|
||||
]
|
||||
|
||||
result = build_taxonomy_candidates(similar_documents, user=None)
|
||||
result = build_taxonomy_candidates(nodes, user=None)
|
||||
|
||||
assert len(result["correspondents"]) == 5
|
||||
|
||||
@@ -296,9 +294,9 @@ class TestBuildTaxonomyCandidates:
|
||||
"""
|
||||
document_type = DocumentTypeFactory.create(name="Invoice")
|
||||
document = DocumentFactory.create(document_type=document_type)
|
||||
similar_documents = [make_similar(document.pk, 0.5)]
|
||||
nodes = [make_node(document.pk, 0.5)]
|
||||
|
||||
result = build_taxonomy_candidates(similar_documents, user=None)
|
||||
result = build_taxonomy_candidates(nodes, user=None)
|
||||
|
||||
assert len(result["document_types"]) == 1
|
||||
assert result["document_types"][0]["id"] == document_type.pk
|
||||
@@ -314,12 +312,12 @@ class TestBuildTaxonomyCandidates:
|
||||
- Only 5 document_types are returned
|
||||
"""
|
||||
document_types = DocumentTypeFactory.create_batch(7)
|
||||
similar_documents = [
|
||||
make_similar(DocumentFactory.create(document_type=dt).pk, 0.5)
|
||||
nodes = [
|
||||
make_node(DocumentFactory.create(document_type=dt).pk, 0.5)
|
||||
for dt in document_types
|
||||
]
|
||||
|
||||
result = build_taxonomy_candidates(similar_documents, user=None)
|
||||
result = build_taxonomy_candidates(nodes, user=None)
|
||||
|
||||
assert len(result["document_types"]) == 5
|
||||
|
||||
@@ -334,9 +332,9 @@ class TestBuildTaxonomyCandidates:
|
||||
"""
|
||||
storage_path = StoragePathFactory.create(name="Invoices")
|
||||
document = DocumentFactory.create(storage_path=storage_path)
|
||||
similar_documents = [make_similar(document.pk, 0.5)]
|
||||
nodes = [make_node(document.pk, 0.5)]
|
||||
|
||||
result = build_taxonomy_candidates(similar_documents, user=None)
|
||||
result = build_taxonomy_candidates(nodes, user=None)
|
||||
|
||||
assert len(result["storage_paths"]) == 1
|
||||
assert result["storage_paths"][0]["id"] == storage_path.pk
|
||||
@@ -352,12 +350,12 @@ class TestBuildTaxonomyCandidates:
|
||||
- Only 5 storage_paths are returned
|
||||
"""
|
||||
storage_paths = StoragePathFactory.create_batch(7)
|
||||
similar_documents = [
|
||||
make_similar(DocumentFactory.create(storage_path=sp).pk, 0.5)
|
||||
nodes = [
|
||||
make_node(DocumentFactory.create(storage_path=sp).pk, 0.5)
|
||||
for sp in storage_paths
|
||||
]
|
||||
|
||||
result = build_taxonomy_candidates(similar_documents, user=None)
|
||||
result = build_taxonomy_candidates(nodes, user=None)
|
||||
|
||||
assert len(result["storage_paths"]) == 5
|
||||
|
||||
@@ -377,14 +375,14 @@ class TestBuildTaxonomyCandidates:
|
||||
tag = TagFactory.create(name="Restricted")
|
||||
document = DocumentFactory.create()
|
||||
document.tags.add(tag)
|
||||
similar_documents = [make_similar(document.pk, 0.5)]
|
||||
nodes = [make_node(document.pk, 0.5)]
|
||||
user = UserFactory.create()
|
||||
mocker.patch(
|
||||
"documents.permissions.permitted_object_ids",
|
||||
return_value=[], # user cannot see this tag
|
||||
)
|
||||
|
||||
result = build_taxonomy_candidates(similar_documents, user=user)
|
||||
result = build_taxonomy_candidates(nodes, user=user)
|
||||
|
||||
assert result["tags"] == []
|
||||
|
||||
@@ -414,10 +412,10 @@ class TestBuildTaxonomyCandidates:
|
||||
tag.save()
|
||||
document = DocumentFactory.create()
|
||||
document.tags.add(tag)
|
||||
similar_documents = [make_similar(document.pk, 0.5)]
|
||||
nodes = [make_node(document.pk, 0.5)]
|
||||
spy = mocker.patch("documents.permissions.permitted_object_ids")
|
||||
|
||||
result = build_taxonomy_candidates(similar_documents, user=None)
|
||||
result = build_taxonomy_candidates(nodes, user=None)
|
||||
|
||||
assert result["tags"][0]["name"] == "Owned"
|
||||
spy.assert_not_called()
|
||||
|
||||
Reference in New Issue
Block a user