Compare commits

..
Author SHA1 Message Date
shamoon 4be152e570 Add more icons 2026-07-28 13:26:13 -07:00
shamoon 9a7fdda0c4 On doc list too 2026-07-28 13:22:08 -07:00
shamoon 686847a074 Ok now display it everywhere! 2026-07-28 13:20:49 -07:00
shamoon 0d8f760cd2 Also handle in the saved view dialog 2026-07-28 13:20:10 -07:00
shamoon cb3afcd356 Add to management list 2026-07-28 13:19:21 -07:00
shamoon 78e4c716c0 Selects need to work with a string and icon display 2026-07-28 13:19:21 -07:00
shamoon 9fe8a24757 Frontend data classes 2026-07-28 13:16:38 -07:00
shamoon 023c404d29 Backend stuff: add text choice icon field and migration 2026-07-28 13:16:23 -07:00
28 changed files with 435 additions and 227 deletions
+4 -5
View File
@@ -948,11 +948,10 @@ for display in the web interface.
!!! note
The **remote OCR parser** (Azure AI) also honors this setting: when
no archive is requested (`never`, or `auto` with a born-digital PDF),
the remote engine is skipped entirely and locally-extracted text is
used instead, avoiding an unnecessary API call and a duplicate text
layer.
The **remote OCR parser** (Azure AI) always produces a searchable
PDF and stores it as the archive copy, regardless of this setting.
`ARCHIVE_FILE_GENERATION=never` has no effect when the remote
parser handles a document.
#### [`PAPERLESS_OCR_CLEAN=<mode>`](#PAPERLESS_OCR_CLEAN) {#PAPERLESS_OCR_CLEAN}
+4 -5
View File
@@ -187,11 +187,10 @@ PAPERLESS_ARCHIVE_FILE_GENERATION=auto
### Remote OCR parser
If you use the **remote OCR parser** (Azure AI), `ARCHIVE_FILE_GENERATION` is
honored the same way as for the local engine: when no archive is requested
(`never`, or `auto` with a born-digital PDF), the remote engine is skipped
entirely and locally-extracted text is used instead, avoiding an unnecessary
API call and a duplicate text layer.
If you use the **remote OCR parser** (Azure AI), note that it always produces a
searchable PDF and stores it as the archive copy. `ARCHIVE_FILE_GENERATION=never`
has no effect for documents handled by the remote parser - the archive is produced
unconditionally by the remote engine.
## Search Index (Whoosh -> Tantivy)
@@ -111,7 +111,7 @@
routerLinkActive="active" (click)="closeMenu()" [ngbPopover]="view.name"
[disablePopover]="!slimSidebarEnabled" placement="end" container="body" triggers="mouseenter:mouseleave"
popoverClass="popover-slim">
<i-bs class="me-2" name="funnel"></i-bs><span><div class="d-inline-flex view-name"><span class="overflow-hidden" [class.text-wrap]="!slimSidebarEnabled">{{view.name}}</span></div>
<i-bs class="me-2" [name]="view.icon || 'funnel'"></i-bs><span><div class="d-inline-flex view-name"><span class="overflow-hidden" [class.text-wrap]="!slimSidebarEnabled">{{view.name}}</span></div>
@if (showSidebarCounts && !slimSidebarEnabled) {
<span class="badge bg-info text-dark ms-2 d-inline">{{ savedViewService.getDocumentCount(view) }}</span>
}
@@ -36,7 +36,16 @@
(focus)="clearLastSearchTerm()"
(clear)="clearLastSearchTerm()"
(blur)="onBlur()">
<ng-template ng-label-tmp let-item="item">
@if (iconField && item[iconField]) {
<i-bs class="me-2" [name]="item[iconField]"></i-bs>
}
<span [title]="item[bindLabel]">{{item[bindLabel]}}</span>
</ng-template>
<ng-template ng-option-tmp let-item="item">
@if (iconField && item[iconField]) {
<i-bs class="me-2" [name]="item[iconField]"></i-bs>
}
<span [title]="item[bindLabel]">{{item[bindLabel]}}</span>
</ng-template>
</ng-select>
@@ -35,7 +35,7 @@ import { AbstractInputComponent } from '../abstract-input'
NgxBootstrapIconsModule,
],
})
export class SelectComponent extends AbstractInputComponent<number> {
export class SelectComponent extends AbstractInputComponent<number | string> {
constructor() {
super()
this.addItemRef = this.addItem.bind(this)
@@ -100,6 +100,9 @@ export class SelectComponent extends AbstractInputComponent<number> {
@Input()
bindLabel: string = 'name'
@Input()
iconField: string
public searchFn = (term: string, item: any): boolean =>
matchesSearchText(item?.[this.bindLabel], term)
@@ -1,6 +1,7 @@
<pngx-widget-frame
*pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.Document }"
[title]="savedView.name"
[titleIcon]="savedView.icon || 'funnel'"
[loading]="false"
[draggable]="savedView"
>
@@ -8,7 +8,12 @@
<i-bs name="grip-vertical"></i-bs>
</div>
}
<h6 class="card-title mb-0">{{title()}}</h6>
<h6 class="card-title mb-0">
@if (titleIcon()) {
<i-bs class="me-2" [name]="titleIcon()"></i-bs>
}
{{title()}}
</h6>
<ng-content select="[title-badge]"></ng-content>
@if (badge() !== null && badge() !== undefined) {
<span class="badge bg-info text-dark ms-2">{{badge()}}</span>
@@ -16,6 +16,8 @@ export class WidgetFrameComponent implements AfterViewInit {
title = input<string>()
titleIcon = input<string>()
draggable = input<any>()
cardless = input(false)
@@ -97,7 +97,9 @@
<div class="dropdown-menu shadow dropdown-menu-right" ngbDropdownMenu>
@if (!list.activeSavedViewId) {
@for (view of savedViewService.allViews; track view) {
<button ngbDropdownItem (click)="loadViewConfig(view.id)">{{view.name}}</button>
<button ngbDropdownItem (click)="loadViewConfig(view.id)">
<i-bs class="me-2" [name]="view.icon || 'funnel'"></i-bs>{{view.name}}
</button>
}
@if (savedViewService.allViews.length > 0) {
<div class="dropdown-divider"></div>
@@ -457,6 +457,7 @@ export class DocumentListComponent
modal.componentInstance.buttonsEnabled.set(false)
let savedView: SavedView = {
name: formValue.name,
icon: formValue.icon,
filter_rules: this.list.filterRules,
sort_reverse: this.list.sortReverse,
sort_field: this.list.sortField,
@@ -6,6 +6,14 @@
</div>
<div class="modal-body">
<pngx-input-text i18n-title title="Name" formControlName="name" [error]="error()?.name" autocomplete="off"></pngx-input-text>
<pngx-input-select
i18n-title
title="Icon"
formControlName="icon"
[items]="savedViewIcons"
iconField="icon"
[error]="error()?.icon">
</pngx-input-select>
<pngx-input-check i18n-title title="Show in sidebar" formControlName="showInSideBar"></pngx-input-check>
<pngx-input-check i18n-title title="Show on dashboard" formControlName="showOnDashboard"></pngx-input-check>
<pngx-permissions-form accordion="true" formControlName="permissions_form"></pngx-permissions-form>
@@ -9,6 +9,7 @@ import { CheckComponent } from '../../common/input/check/check.component'
import { PermissionsFormComponent } from '../../common/input/permissions/permissions-form/permissions-form.component'
import { PermissionsGroupComponent } from '../../common/input/permissions/permissions-group/permissions-group.component'
import { PermissionsUserComponent } from '../../common/input/permissions/permissions-user/permissions-user.component'
import { SelectComponent } from '../../common/input/select/select.component'
import { TextComponent } from '../../common/input/text/text.component'
import { SaveViewConfigDialogComponent } from './save-view-config-dialog.component'
@@ -40,6 +41,7 @@ describe('SaveViewConfigDialogComponent', () => {
ReactiveFormsModule,
SaveViewConfigDialogComponent,
TextComponent,
SelectComponent,
CheckComponent,
PermissionsFormComponent,
PermissionsUserComponent,
@@ -63,6 +65,7 @@ describe('SaveViewConfigDialogComponent', () => {
expect(component.defaultName()).toEqual(name)
expect(result).toEqual({
name,
icon: 'funnel',
showInSideBar: false,
showOnDashboard: false,
})
@@ -94,6 +97,7 @@ describe('SaveViewConfigDialogComponent', () => {
component.save()
expect(result).toEqual({
name,
icon: 'funnel',
showInSideBar: true,
showOnDashboard: true,
})
@@ -113,6 +117,7 @@ describe('SaveViewConfigDialogComponent', () => {
component.save()
expect(result).toEqual({
name: '',
icon: 'funnel',
showInSideBar: false,
showOnDashboard: false,
permissions_form: permissions,
@@ -13,9 +13,14 @@ import {
ReactiveFormsModule,
} from '@angular/forms'
import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
import {
DEFAULT_SAVED_VIEW_ICON,
SAVED_VIEW_ICONS,
} from 'src/app/data/saved-view-icons'
import { User } from 'src/app/data/user'
import { CheckComponent } from '../../common/input/check/check.component'
import { PermissionsFormComponent } from '../../common/input/permissions/permissions-form/permissions-form.component'
import { SelectComponent } from '../../common/input/select/select.component'
import { TextComponent } from '../../common/input/text/text.component'
@Component({
@@ -24,6 +29,7 @@ import { TextComponent } from '../../common/input/text/text.component'
styleUrls: ['./save-view-config-dialog.component.scss'],
imports: [
CheckComponent,
SelectComponent,
TextComponent,
PermissionsFormComponent,
FormsModule,
@@ -41,6 +47,7 @@ export class SaveViewConfigDialogComponent implements OnInit {
public saveClicked = new EventEmitter()
users: User[]
readonly savedViewIcons = SAVED_VIEW_ICONS
setDefaultName(value: string) {
this.defaultName.set(value)
@@ -49,6 +56,7 @@ export class SaveViewConfigDialogComponent implements OnInit {
saveViewConfigForm = new FormGroup({
name: new FormControl(''),
icon: new FormControl(DEFAULT_SAVED_VIEW_ICON),
showInSideBar: new FormControl(false),
showOnDashboard: new FormControl(false),
permissions_form: new FormControl(null),
@@ -65,6 +73,7 @@ export class SaveViewConfigDialogComponent implements OnInit {
const formValue = this.saveViewConfigForm.value
const saveViewConfig = {
name: formValue.name,
icon: formValue.icon,
showInSideBar: formValue.showInSideBar,
showOnDashboard: formValue.showOnDashboard,
}
@@ -11,10 +11,19 @@
<li class="list-group-item py-3">
<div [formGroupName]="view.id">
<div class="row">
<div class="col">
<div class="col-md">
<pngx-input-text title="Name" formControlName="name"></pngx-input-text>
</div>
<div class="col">
<div class="col-md">
<pngx-input-select
i18n-title
title="Icon"
formControlName="icon"
[items]="savedViewIcons"
iconField="icon">
</pngx-input-select>
</div>
<div class="col-md">
<div class="form-check form-switch mt-3">
<input type="checkbox" class="form-check-input" id="show_on_dashboard_{{view.id}}" formControlName="show_on_dashboard">
<label class="form-check-label" for="show_on_dashboard_{{view.id}}" i18n>Show on dashboard</label>
@@ -25,8 +25,20 @@ import { PageHeaderComponent } from '../../common/page-header/page-header.compon
import { SavedViewsComponent } from './saved-views.component'
const savedViews = [
{ id: 1, name: 'view1', show_in_sidebar: true, show_on_dashboard: true },
{ id: 2, name: 'view2', show_in_sidebar: false, show_on_dashboard: false },
{
id: 1,
name: 'view1',
icon: 'archive',
show_in_sidebar: true,
show_on_dashboard: true,
},
{
id: 2,
name: 'view2',
icon: 'funnel',
show_in_sidebar: false,
show_on_dashboard: false,
},
]
describe('SavedViewsComponent', () => {
@@ -157,6 +169,24 @@ describe('SavedViewsComponent', () => {
expect(patchBody.show_in_sidebar).toBeUndefined()
})
it('should persist a changed icon', () => {
const patchSpy = jest.spyOn(savedViewService, 'patchMany')
const view = savedViews[0]
const iconControl = component.savedViewsForm
.get('savedViews')
.get(view.id.toString())
.get('icon')
iconControl.setValue('bell')
iconControl.markAsDirty()
component.save()
expect(patchSpy.mock.calls[0][0][0]).toMatchObject({
id: view.id,
icon: 'bell',
})
})
it('should persist visibility changes to user settings', () => {
const patchSpy = jest.spyOn(savedViewService, 'patchMany')
const updateVisibilitySpy = jest
@@ -13,6 +13,10 @@ import { BehaviorSubject, Observable, of, switchMap, takeUntil } from 'rxjs'
import { PermissionsDialogComponent } from 'src/app/components/common/permissions-dialog/permissions-dialog.component'
import { DisplayMode } from 'src/app/data/document'
import { SavedView } from 'src/app/data/saved-view'
import {
DEFAULT_SAVED_VIEW_ICON,
SAVED_VIEW_ICONS,
} from 'src/app/data/saved-view-icons'
import { IfPermissionsDirective } from 'src/app/directives/if-permissions.directive'
import {
PermissionAction,
@@ -24,6 +28,7 @@ import { ToastService } from 'src/app/services/toast.service'
import { ConfirmButtonComponent } from '../../common/confirm-button/confirm-button.component'
import { DragDropSelectComponent } from '../../common/input/drag-drop-select/drag-drop-select.component'
import { NumberComponent } from '../../common/input/number/number.component'
import { SelectComponent } from '../../common/input/select/select.component'
import { TextComponent } from '../../common/input/text/text.component'
import { PageHeaderComponent } from '../../common/page-header/page-header.component'
import { LoadingComponentWithPermissions } from '../../loading-component/loading.component'
@@ -35,6 +40,7 @@ import { LoadingComponentWithPermissions } from '../../loading-component/loading
PageHeaderComponent,
ConfirmButtonComponent,
NumberComponent,
SelectComponent,
TextComponent,
IfPermissionsDirective,
DragDropSelectComponent,
@@ -55,6 +61,7 @@ export class SavedViewsComponent
private readonly modalService = inject(NgbModal)
DisplayMode = DisplayMode
readonly savedViewIcons = SAVED_VIEW_ICONS
readonly savedViews = signal<SavedView[]>(undefined)
private savedViewsGroup = new FormGroup({})
@@ -105,6 +112,7 @@ export class SavedViewsComponent
storeData.savedViews[view.id.toString()] = {
id: view.id,
name: view.name,
icon: view.icon ?? DEFAULT_SAVED_VIEW_ICON,
show_on_dashboard: view.show_on_dashboard,
show_in_sidebar: view.show_in_sidebar,
page_size: view.page_size,
@@ -117,6 +125,7 @@ export class SavedViewsComponent
new FormGroup({
id: new FormControl({ value: null, disabled: !canEdit }),
name: new FormControl({ value: null, disabled: !canEdit }),
icon: new FormControl({ value: null, disabled: !canEdit }),
show_on_dashboard: new FormControl({
value: null,
disabled: false,
@@ -195,6 +204,7 @@ export class SavedViewsComponent
const modelFieldsChanged =
group.get('name')?.dirty ||
group.get('icon')?.dirty ||
group.get('page_size')?.dirty ||
group.get('display_mode')?.dirty ||
group.get('display_fields')?.dirty
+89
View File
@@ -0,0 +1,89 @@
export const DEFAULT_SAVED_VIEW_ICON = 'funnel'
export const SAVED_VIEW_ICONS = [
{ id: 'archive', name: $localize`Archive`, icon: 'archive' },
{ id: 'bank', name: $localize`Bank`, icon: 'bank' },
{ id: 'basket', name: $localize`Basket`, icon: 'basket' },
{ id: 'bell', name: $localize`Bell`, icon: 'bell' },
{ id: 'bookmark', name: $localize`Bookmark`, icon: 'bookmark' },
{ id: 'boxes', name: $localize`Boxes`, icon: 'boxes' },
{ id: 'briefcase', name: $localize`Briefcase`, icon: 'briefcase' },
{ id: 'building', name: $localize`Building`, icon: 'building' },
{ id: 'calculator', name: $localize`Calculator`, icon: 'calculator' },
{ id: 'calendar', name: $localize`Calendar`, icon: 'calendar' },
{ id: 'camera', name: $localize`Camera`, icon: 'camera' },
{
id: 'card-checklist',
name: $localize`Checklist`,
icon: 'card-checklist',
},
{ id: 'cash', name: $localize`Cash`, icon: 'cash' },
{ id: 'chat-left-text', name: $localize`Chat`, icon: 'chat-left-text' },
{ id: 'check-circle', name: $localize`Check`, icon: 'check-circle' },
{ id: 'clipboard', name: $localize`Clipboard`, icon: 'clipboard' },
{ id: 'clock-history', name: $localize`Clock`, icon: 'clock-history' },
{ id: 'credit-card', name: $localize`Credit card`, icon: 'credit-card' },
{ id: 'download', name: $localize`Download`, icon: 'download' },
{ id: 'envelope', name: $localize`Envelope`, icon: 'envelope' },
{
id: 'exclamation-triangle',
name: $localize`Warning`,
icon: 'exclamation-triangle',
},
{ id: 'file-earmark', name: $localize`File`, icon: 'file-earmark' },
{
id: 'file-earmark-check',
name: $localize`Checked file`,
icon: 'file-earmark-check',
},
{
id: 'file-earmark-lock',
name: $localize`Locked file`,
icon: 'file-earmark-lock',
},
{
id: 'file-earmark-medical',
name: $localize`Medical file`,
icon: 'file-earmark-medical',
},
{
id: 'file-earmark-person',
name: $localize`Person file`,
icon: 'file-earmark-person',
},
{
id: 'file-earmark-spreadsheet',
name: $localize`Spreadsheet`,
icon: 'file-earmark-spreadsheet',
},
{ id: 'file-text', name: $localize`Text file`, icon: 'file-text' },
{ id: 'files', name: $localize`Files`, icon: 'files' },
{ id: 'folder', name: $localize`Folder`, icon: 'folder' },
{ id: 'funnel', name: $localize`Filter`, icon: 'funnel' },
{ id: 'gear', name: $localize`Gear`, icon: 'gear' },
{ id: 'globe2', name: $localize`Globe`, icon: 'globe2' },
{ id: 'hash', name: $localize`Hash`, icon: 'hash' },
{ id: 'heart', name: $localize`Heart`, icon: 'heart' },
{ id: 'house', name: $localize`House`, icon: 'house' },
{ id: 'inbox', name: $localize`Inbox`, icon: 'inbox' },
{ id: 'journals', name: $localize`Journals`, icon: 'journals' },
{ id: 'list-task', name: $localize`Task list`, icon: 'list-task' },
{ id: 'newspaper', name: $localize`Newspaper`, icon: 'newspaper' },
{ id: 'paperclip', name: $localize`Attachment`, icon: 'paperclip' },
{ id: 'people', name: $localize`People`, icon: 'people' },
{ id: 'person', name: $localize`Person`, icon: 'person' },
{ id: 'printer', name: $localize`Printer`, icon: 'printer' },
{ id: 'receipt', name: $localize`Receipt`, icon: 'receipt' },
{ id: 'safe', name: $localize`Safe`, icon: 'safe' },
{ id: 'search', name: $localize`Search`, icon: 'search' },
{ id: 'send', name: $localize`Send`, icon: 'send' },
{ id: 'shop', name: $localize`Shop`, icon: 'shop' },
{ id: 'stack', name: $localize`Stack`, icon: 'stack' },
{ id: 'stars', name: $localize`Stars`, icon: 'stars' },
{ id: 'tag', name: $localize`Tag`, icon: 'tag' },
{ id: 'tags', name: $localize`Tags`, icon: 'tags' },
{ id: 'telephone', name: $localize`Telephone`, icon: 'telephone' },
{ id: 'truck', name: $localize`Truck`, icon: 'truck' },
{ id: 'upc-scan', name: $localize`Barcode`, icon: 'upc-scan' },
{ id: 'wallet2', name: $localize`Wallet`, icon: 'wallet2' },
]
+2
View File
@@ -5,6 +5,8 @@ import { ObjectWithPermissions } from './object-with-permissions'
export interface SavedView extends ObjectWithPermissions {
name?: string
icon?: string
show_on_dashboard?: boolean
show_in_sidebar?: boolean
+46
View File
@@ -35,19 +35,27 @@ import {
arrowRightShort,
arrowUpRight,
asterisk,
bank,
basket,
bell,
bodyText,
bookmark,
boxArrowUp,
boxArrowUpRight,
boxes,
braces,
briefcase,
building,
calculator,
calendar,
calendarEvent,
calendarEventFill,
camera,
cardChecklist,
cardHeading,
caretDown,
caretUp,
cash,
chatLeftText,
chatSquareDots,
check,
@@ -65,6 +73,7 @@ import {
clipboardCheckFill,
clipboardFill,
clockHistory,
creditCard,
dash,
dashCircle,
diagram3,
@@ -83,9 +92,12 @@ import {
fileEarmarkDiff,
fileEarmarkFill,
fileEarmarkLock,
fileEarmarkMedical,
fileEarmarkMinus,
fileEarmarkPerson,
fileEarmarkPlus,
fileEarmarkRichtext,
fileEarmarkSpreadsheet,
fileText,
files,
filter,
@@ -93,12 +105,15 @@ import {
folderFill,
funnel,
gear,
globe2,
google,
grid,
gripVertical,
hash,
hddStack,
heart,
house,
inbox,
infoCircle,
journals,
link,
@@ -106,7 +121,9 @@ import {
listTask,
listUl,
microsoft,
newspaper,
nodePlus,
paperclip,
pencil,
people,
peopleFill,
@@ -121,9 +138,12 @@ import {
plusCircle,
printer,
questionCircle,
receipt,
safe,
scissors,
search,
send,
shop,
slashCircle,
sliders2Vertical,
sortAlphaDown,
@@ -133,14 +153,17 @@ import {
tag,
tagFill,
tags,
telephone,
textIndentLeft,
textLeft,
threeDots,
threeDotsVertical,
trash,
truck,
uiRadios,
unlock,
upcScan,
wallet2,
windowStack,
x,
xCircle,
@@ -258,15 +281,22 @@ const icons = {
arrowRightShort,
arrowUpRight,
asterisk,
bank,
basket,
bell,
braces,
bodyText,
bookmark,
boxArrowUp,
boxArrowUpRight,
boxes,
briefcase,
building,
calculator,
calendar,
calendarEvent,
calendarEventFill,
camera,
cardChecklist,
cardHeading,
caretDown,
@@ -288,6 +318,8 @@ const icons = {
clipboardCheckFill,
clipboardFill,
clockHistory,
cash,
creditCard,
dash,
dashCircle,
diagram3,
@@ -306,9 +338,12 @@ const icons = {
fileEarmarkDiff,
fileEarmarkFill,
fileEarmarkLock,
fileEarmarkMedical,
fileEarmarkMinus,
fileEarmarkPerson,
fileEarmarkPlus,
fileEarmarkRichtext,
fileEarmarkSpreadsheet,
files,
fileText,
filter,
@@ -316,12 +351,15 @@ const icons = {
folderFill,
funnel,
gear,
globe2,
google,
grid,
gripVertical,
hash,
hddStack,
heart,
house,
inbox,
infoCircle,
journals,
link,
@@ -329,8 +367,10 @@ const icons = {
listTask,
listUl,
microsoft,
newspaper,
nodePlus,
pencil,
paperclip,
people,
peopleFill,
person,
@@ -344,10 +384,13 @@ const icons = {
plusCircle,
printer,
questionCircle,
receipt,
safe,
scissors,
search,
send,
slashCircle,
shop,
sliders2Vertical,
sortAlphaDown,
sortAlphaUpAlt,
@@ -358,12 +401,15 @@ const icons = {
tags,
textIndentLeft,
textLeft,
telephone,
threeDots,
threeDotsVertical,
trash,
truck,
uiRadios,
unlock,
upcScan,
wallet2,
windowStack,
x,
xCircle,
@@ -0,0 +1,79 @@
from django.db import migrations
from django.db import models
class Migration(migrations.Migration):
dependencies = [
("documents", "0022_add_perf_indexes"),
]
operations = [
migrations.AddField(
model_name="savedview",
name="icon",
field=models.CharField(
choices=[
("archive", "Archive"),
("bank", "Bank"),
("basket", "Basket"),
("bell", "Bell"),
("bookmark", "Bookmark"),
("boxes", "Boxes"),
("briefcase", "Briefcase"),
("building", "Building"),
("calculator", "Calculator"),
("calendar", "Calendar"),
("camera", "Camera"),
("card-checklist", "Checklist"),
("cash", "Cash"),
("chat-left-text", "Chat"),
("check-circle", "Check"),
("clipboard", "Clipboard"),
("clock-history", "Clock"),
("credit-card", "Credit card"),
("download", "Download"),
("envelope", "Envelope"),
("exclamation-triangle", "Warning"),
("file-earmark", "File"),
("file-earmark-check", "Checked file"),
("file-earmark-lock", "Locked file"),
("file-earmark-medical", "Medical file"),
("file-earmark-person", "Person file"),
("file-earmark-spreadsheet", "Spreadsheet"),
("file-text", "Text file"),
("files", "Files"),
("folder", "Folder"),
("funnel", "Filter"),
("gear", "Gear"),
("globe2", "Globe"),
("hash", "Hash"),
("heart", "Heart"),
("house", "House"),
("inbox", "Inbox"),
("journals", "Journals"),
("list-task", "Task list"),
("newspaper", "Newspaper"),
("paperclip", "Attachment"),
("people", "People"),
("person", "Person"),
("printer", "Printer"),
("receipt", "Receipt"),
("safe", "Safe"),
("search", "Search"),
("send", "Send"),
("shop", "Shop"),
("stack", "Stack"),
("stars", "Stars"),
("tag", "Tag"),
("tags", "Tags"),
("telephone", "Telephone"),
("truck", "Truck"),
("upc-scan", "Barcode"),
("wallet2", "Wallet"),
],
default="funnel",
max_length=64,
verbose_name="icon",
),
),
]
+69
View File
@@ -519,6 +519,68 @@ class Document(SoftDeleteModel, ModelWithOwner): # type: ignore[django-manager-
class SavedView(ModelWithOwner):
class Icon(models.TextChoices):
ARCHIVE = ("archive", _("Archive"))
BANK = ("bank", _("Bank"))
BASKET = ("basket", _("Basket"))
BELL = ("bell", _("Bell"))
BOOKMARK = ("bookmark", _("Bookmark"))
BOXES = ("boxes", _("Boxes"))
BRIEFCASE = ("briefcase", _("Briefcase"))
BUILDING = ("building", _("Building"))
CALCULATOR = ("calculator", _("Calculator"))
CALENDAR = ("calendar", _("Calendar"))
CAMERA = ("camera", _("Camera"))
CARD_CHECKLIST = ("card-checklist", _("Checklist"))
CASH = ("cash", _("Cash"))
CHAT_LEFT_TEXT = ("chat-left-text", _("Chat"))
CHECK_CIRCLE = ("check-circle", _("Check"))
CLIPBOARD = ("clipboard", _("Clipboard"))
CLOCK_HISTORY = ("clock-history", _("Clock"))
CREDIT_CARD = ("credit-card", _("Credit card"))
DOWNLOAD = ("download", _("Download"))
ENVELOPE = ("envelope", _("Envelope"))
EXCLAMATION_TRIANGLE = ("exclamation-triangle", _("Warning"))
FILE_EARMARK = ("file-earmark", _("File"))
FILE_EARMARK_CHECK = ("file-earmark-check", _("Checked file"))
FILE_EARMARK_LOCK = ("file-earmark-lock", _("Locked file"))
FILE_EARMARK_MEDICAL = ("file-earmark-medical", _("Medical file"))
FILE_EARMARK_PERSON = ("file-earmark-person", _("Person file"))
FILE_EARMARK_SPREADSHEET = (
"file-earmark-spreadsheet",
_("Spreadsheet"),
)
FILE_TEXT = ("file-text", _("Text file"))
FILES = ("files", _("Files"))
FOLDER = ("folder", _("Folder"))
FUNNEL = ("funnel", _("Filter"))
GEAR = ("gear", _("Gear"))
GLOBE = ("globe2", _("Globe"))
HASH = ("hash", _("Hash"))
HEART = ("heart", _("Heart"))
HOUSE = ("house", _("House"))
INBOX = ("inbox", _("Inbox"))
JOURNALS = ("journals", _("Journals"))
LIST_TASK = ("list-task", _("Task list"))
NEWSPAPER = ("newspaper", _("Newspaper"))
PAPERCLIP = ("paperclip", _("Attachment"))
PEOPLE = ("people", _("People"))
PERSON = ("person", _("Person"))
PRINTER = ("printer", _("Printer"))
RECEIPT = ("receipt", _("Receipt"))
SAFE = ("safe", _("Safe"))
SEARCH = ("search", _("Search"))
SEND = ("send", _("Send"))
SHOP = ("shop", _("Shop"))
STACK = ("stack", _("Stack"))
STARS = ("stars", _("Stars"))
TAG = ("tag", _("Tag"))
TAGS = ("tags", _("Tags"))
TELEPHONE = ("telephone", _("Telephone"))
TRUCK = ("truck", _("Truck"))
UPC_SCAN = ("upc-scan", _("Barcode"))
WALLET = ("wallet2", _("Wallet"))
class DisplayMode(models.TextChoices):
TABLE = ("table", _("Table"))
SMALL_CARDS = ("smallCards", _("Small Cards"))
@@ -541,6 +603,13 @@ class SavedView(ModelWithOwner):
name = models.CharField(_("name"), max_length=128)
icon = models.CharField(
_("icon"),
max_length=64,
choices=Icon.choices,
default=Icon.FUNNEL,
)
sort_field = models.CharField(
_("sort field"),
max_length=128,
+1
View File
@@ -1389,6 +1389,7 @@ class SavedViewSerializer(OwnedObjectSerializer):
fields = [
"id",
"name",
"icon",
"sort_field",
"sort_reverse",
"filter_rules",
+10 -1
View File
@@ -2880,18 +2880,20 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
v1 = SavedView.objects.get(name="test")
self.assertEqual(v1.sort_field, "created2")
self.assertEqual(v1.icon, SavedView.Icon.FUNNEL)
self.assertEqual(v1.filter_rules.count(), 1)
self.assertEqual(v1.owner, self.user)
response = self.client.patch(
f"/api/saved_views/{v1.id}/",
{"sort_reverse": True},
{"sort_reverse": True, "icon": SavedView.Icon.RECEIPT},
format="json",
)
v1 = SavedView.objects.get(id=v1.id)
self.assertEqual(response.status_code, status.HTTP_200_OK)
self.assertTrue(v1.sort_reverse)
self.assertEqual(v1.icon, SavedView.Icon.RECEIPT)
self.assertEqual(v1.filter_rules.count(), 1)
view["filter_rules"] = [{"rule_type": 12, "value": "secret"}]
@@ -2911,6 +2913,13 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
v1 = SavedView.objects.get(id=v1.id)
self.assertEqual(v1.filter_rules.count(), 0)
response = self.client.patch(
f"/api/saved_views/{v1.id}/",
{"icon": "not-an-icon"},
format="json",
)
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
def test_saved_view_display_options(self) -> None:
"""
GIVEN:
+7 -33
View File
@@ -3,9 +3,7 @@ Built-in remote-OCR document parser.
Handles documents by sending them to a configured remote OCR engine
(currently Azure AI Vision / Document Intelligence) and retrieving both
the extracted text and a searchable PDF with an embedded text layer. For
born-digital PDFs that need no archive copy, the remote call is skipped
entirely in favor of locally-extracted text (see ``RemoteDocumentParser.parse``).
the extracted text and a searchable PDF with an embedded text layer.
When no engine is configured, ``score()`` returns ``None`` so the parser
is effectively invisible to the registry the tesseract parser handles
@@ -23,8 +21,6 @@ from typing import Self
from django.conf import settings
from paperless.parsers.utils import extract_pdf_text
from paperless.parsers.utils import post_process_text
from paperless.version import __full_version_str__
if TYPE_CHECKING:
@@ -73,11 +69,8 @@ class RemoteDocumentParser:
"""Parse documents via a remote OCR API (currently Azure AI Vision).
This parser sends documents to a remote engine that returns both
extracted text and a searchable PDF with an embedded text layer,
except when ``parse()`` is called with ``produce_archive=False`` for
a PDF, in which case the remote call is skipped and only locally
extracted text is returned (no archive). It does not depend on
Tesseract or ocrmypdf.
extracted text and a searchable PDF with an embedded text layer.
It does not depend on Tesseract or ocrmypdf.
Class attributes
----------------
@@ -166,11 +159,8 @@ class RemoteDocumentParser:
Returns
-------
bool
Always True the remote engine is capable of returning a PDF
with an embedded text layer to serve as the archive copy.
Whether it actually does so for a given document depends on
``produce_archive`` passed to :meth:`parse` (see there for when
the remote engine call, and thus archive generation, is skipped).
Always True the remote engine always returns a PDF with an
embedded text layer that serves as the archive copy.
"""
return True
@@ -227,12 +217,6 @@ class RemoteDocumentParser:
) -> None:
"""Send the document to the remote engine and store results.
When *produce_archive* is False for a PDF, the caller (via
``documents.consumer.should_produce_archive``) has already determined
that the document is born-digital and needs no archive skip the
remote engine entirely rather than re-OCRing it and creating a
duplicate text layer.
Parameters
----------
document_path:
@@ -240,8 +224,8 @@ class RemoteDocumentParser:
mime_type:
Detected MIME type of the document.
produce_archive:
Whether an archive copy is wanted. For PDFs, False skips the
remote engine and uses locally-extracted text instead.
Ignored the remote engine always returns a searchable PDF,
which is stored as the archive copy regardless of this flag.
"""
config = RemoteEngineConfig(
engine=settings.REMOTE_OCR_ENGINE,
@@ -256,16 +240,6 @@ class RemoteDocumentParser:
self._text = ""
return
if not produce_archive and mime_type == "application/pdf":
logger.debug(
"Remote OCR: skipped — no archive requested, "
"using locally-extracted text",
)
self._text = (
post_process_text(extract_pdf_text(document_path, log=logger)) or ""
)
return
if config.engine == "azureai":
self._text = self._azure_ai_vision_parse(document_path, config)
+21 -6
View File
@@ -3,6 +3,7 @@ from __future__ import annotations
import importlib.resources
import logging
import os
import re
import shutil
import tempfile
from pathlib import Path
@@ -24,9 +25,9 @@ from paperless.config import OcrConfig
from paperless.models import CleanChoices
from paperless.models import ModeChoices
from paperless.models import OutputTypeChoices
from paperless.parsers.utils import PDF_TEXT_MIN_LENGTH
from paperless.parsers.utils import extract_pdf_text
from paperless.parsers.utils import pdf_has_digital_text
from paperless.parsers.utils import post_process_text
from paperless.parsers.utils import is_tagged_pdf
from paperless.parsers.utils import read_file_handle_unicode_errors
from paperless.version import __full_version_str__
@@ -509,10 +510,10 @@ class RasterisedDocumentParser:
if mime_type == "application/pdf":
text_original = self.extract_text(None, document_path)
original_has_text = pdf_has_digital_text(
document_path,
text_original,
log=self.log,
has_text = text_original is not None and len(text_original) > 0
original_has_text = has_text and (
is_tagged_pdf(document_path, log=self.log)
or len(text_original) > PDF_TEXT_MIN_LENGTH
)
else:
text_original = None
@@ -657,3 +658,17 @@ class RasterisedDocumentParser:
f"No text was found in {document_path}, the content will be empty.",
)
self.text = ""
def post_process_text(text: str | None) -> str | None:
if not text:
return None
collapsed_spaces = re.sub(r"([^\S\r\n]+)", " ", text)
no_leading_whitespace = re.sub(r"([\n\r]+)([^\S\n\r]+)", "\\1", collapsed_spaces)
no_trailing_whitespace = re.sub(r"([^\S\n\r]+)$", "", no_leading_whitespace)
# TODO: this needs a rework
# replace \0 prevents issues with saving to postgres.
# text may contain \0 when this character is present in PDF files.
return no_trailing_whitespace.strip().replace("\0", " ")
-57
View File
@@ -65,63 +65,6 @@ def is_tagged_pdf(
return False
def pdf_has_digital_text(
path: Path,
text: str | None,
log: logging.Logger | None = None,
) -> bool:
"""Return True if a PDF already has a usable, born-digital text layer.
Combines the tagged-PDF check with an extracted-text length check.
Shared by the tesseract and remote OCR parsers to decide whether
OCR_MODE=auto/off should skip (re-)OCRing a document.
Parameters
----------
path:
Absolute path to the PDF file.
text:
Text already extracted from the PDF (e.g. via ``extract_pdf_text``),
or ``None``.
log:
Logger for warnings. Falls back to the module-level logger when omitted.
Returns
-------
bool
``True`` when the document already contains a text layer.
"""
return is_tagged_pdf(path, log=log) or (
text is not None and len(text) > PDF_TEXT_MIN_LENGTH
)
def post_process_text(text: str | None) -> str | None:
"""Normalise whitespace in extracted OCR/PDF text and strip NUL bytes.
Parameters
----------
text:
Raw extracted text, or ``None``.
Returns
-------
str | None
Cleaned text, or ``None`` when *text* is falsy.
"""
if not text:
return None
collapsed_spaces = re.sub(r"([^\S\r\n]+)", " ", text)
no_leading_whitespace = re.sub(r"([\n\r]+)([^\S\n\r]+)", "\\1", collapsed_spaces)
no_trailing_whitespace = re.sub(r"([^\S\n\r]+)$", "", no_leading_whitespace)
# TODO: this needs a rework
# replace \0 prevents issues with saving to postgres.
# text may contain \0 when this character is present in PDF files.
return no_trailing_whitespace.strip().replace("\0", " ")
def extract_pdf_text(
path: Path,
log: logging.Logger | None = None,
@@ -336,117 +336,6 @@ class TestRemoteParserParse:
assert remote_parser.get_date() is None
# ---------------------------------------------------------------------------
# parse() — produce_archive=False skips the remote engine (PDFs only)
# ---------------------------------------------------------------------------
class TestRemoteParserSkipsWhenNoArchiveWanted:
"""When the caller has already decided no archive is needed for a PDF
(documents.consumer.should_produce_archive), the remote engine call is
skipped entirely in favor of locally-extracted text.
"""
def test_pdf_skips_azure_when_no_archive_requested(
self,
remote_parser: RemoteDocumentParser,
simple_digital_pdf_file: Path,
azure_client: Mock,
) -> None:
"""
GIVEN: produce_archive=False for a PDF
WHEN: parse() is called
THEN: Azure is never invoked, no archive is produced, and text
comes from local pdftotext extraction
"""
remote_parser.parse(
simple_digital_pdf_file,
"application/pdf",
produce_archive=False,
)
azure_client.begin_analyze_document.assert_not_called()
assert remote_parser.get_archive_path() is None
assert remote_parser.get_text() != ""
def test_pdf_no_archive_requested_text_matches_local_extraction(
self,
remote_parser: RemoteDocumentParser,
simple_digital_pdf_file: Path,
azure_client: Mock,
mocker: MockerFixture,
) -> None:
"""
GIVEN: produce_archive=False for a PDF
WHEN: parse() is called
THEN: the returned text is exactly the locally-extracted text,
not anything from the (unused) Azure mock
"""
mocker.patch(
"paperless.parsers.remote.extract_pdf_text",
return_value="Local digital text.",
)
remote_parser.parse(
simple_digital_pdf_file,
"application/pdf",
produce_archive=False,
)
assert remote_parser.get_text() == "Local digital text."
def test_pdf_no_archive_requested_closes_no_client(
self,
remote_parser: RemoteDocumentParser,
simple_digital_pdf_file: Path,
azure_client: Mock,
) -> None:
remote_parser.parse(
simple_digital_pdf_file,
"application/pdf",
produce_archive=False,
)
azure_client.close.assert_not_called()
def test_non_pdf_still_calls_azure_when_no_archive_requested(
self,
remote_parser: RemoteDocumentParser,
simple_digital_pdf_file: Path,
azure_client: Mock,
) -> None:
"""
Images have no local-text fallback, so produce_archive=False does
not skip the remote engine for non-PDF MIME types.
"""
remote_parser.parse(
simple_digital_pdf_file,
"image/png",
produce_archive=False,
)
azure_client.begin_analyze_document.assert_called_once()
assert remote_parser.get_text() == _DEFAULT_TEXT
@pytest.mark.usefixtures("no_engine_settings")
def test_unconfigured_engine_takes_precedence_over_skip(
self,
remote_parser: RemoteDocumentParser,
simple_digital_pdf_file: Path,
) -> None:
"""An unconfigured engine still short-circuits before the
produce_archive check, returning empty text as before.
"""
remote_parser.parse(
simple_digital_pdf_file,
"application/pdf",
produce_archive=False,
)
assert remote_parser.get_text() == ""
assert remote_parser.get_archive_path() is None
# ---------------------------------------------------------------------------
# parse() — Azure failure path
# ---------------------------------------------------------------------------
@@ -21,7 +21,7 @@ from documents.parsers import run_convert
from paperless.models import ModeChoices
from paperless.parsers import ParserProtocol
from paperless.parsers.tesseract import RasterisedDocumentParser
from paperless.parsers.utils import post_process_text
from paperless.parsers.tesseract import post_process_text
if TYPE_CHECKING:
from pathlib import Path