Merge branch 'dev' into chore/agents-contributing

* Fix: count selection_data from one pass over the filtered documents

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

* Chore: use document type ids in the bulk edit selection_data test

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

* Batch search selection data queries

Co-Authored-By: Codex <267193182+codex@users.noreply.github.com>

---------

Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
Co-authored-by: shamoon <4887959+shamoon@users.noreply.github.com>
Co-authored-by: Codex <267193182+codex@users.noreply.github.com>

.github/actions/apt-install/install.sh

@@ -6,9 +6,9 @@ if [ "${1:-}" = download ]; then
 	download_archive_dir=$2
 	shift 2
 	apt-get update -q
-	apt-get install -q --yes --no-install-recommends --download-only \
+	# Keep apt itself under timeout supervision, including the kill grace period.
+	exec apt-get install -q --yes --no-install-recommends --download-only \
 		-o "Dir::Cache::archives=$download_archive_dir" "$@"
-	exit 0
 fi
 
 SUDO=()
@@ -34,7 +34,8 @@ use_ubuntu_mirrors() {
 
 for attempt in $(seq 1 "$ATTEMPTS"); do
 	echo "::group::apt download attempt ${attempt}/${ATTEMPTS}"
-	if timeout --kill-after=10 "$ATTEMPT_TIMEOUT" "${SUDO[@]}" bash "$0" download "$CACHE_DIR" "${requested_packages[@]}"; then
+	# Run timeout as root so it can signal the root-owned apt processes.
+	if "${SUDO[@]}" timeout --kill-after=10 "$ATTEMPT_TIMEOUT" bash "$0" download "$CACHE_DIR" "${requested_packages[@]}"; then
 		echo "::endgroup::"
 		# Apt handles aliases (e.g. libmagic1 -> libmagic1t64) and dependencies.
 		"${SUDO[@]}" apt-get install -q --yes --no-install-recommends --no-download \

AGENTS.md

@@ -0,0 +1,44 @@
+# Guidance for AI agents
+
+Read [CONTRIBUTING.md](CONTRIBUTING.md) before working on this repository, especially [Use of AI Tools](CONTRIBUTING.md#use-of-ai-tools). These contribution rules apply to all agent-assisted work.
+
+## Contribution boundaries
+
+- Do not open or submit pull requests, including "on behalf of" a human. The project does not accept PRs from AI agents. Prepare local changes for a human to review, verify, and submit personally.
+- The project does not accept PRs that are entirely or mostly AI-derived. Human submission and disclosure do not override this rule.
+- AI-generated content must be clearly disclosed as described in the contributing guidelines. When handing work back to a human, identify what was generated or changed with AI assistance so they can disclose it accurately.
+- Trust matters. Encourage first-time contributors to discuss their proposed change before preparing a PR, especially for large changes or changes involving AI-generated code. New features and enhancements should almost always target an existing feature request with community interest and discussion.
+- The project prefers thoughtful, well-described ideas to AI-generated pull requests. Help contributors describe their problem, use case, desired behavior, and who would benefit. An implementation is not required for a valuable contribution, and a flawed implementation can obscure a useful idea before it receives proper discussion.
+- AI tools have lowered the effort needed to produce a PR, but reviewing and maintaining it still requires substantial work. Encourage discussion of the idea before investing in implementation and review.
+- Issue reports must describe observed behavior, reproduction steps, and relevant logs. Do not add speculative root causes, code analysis, or proposed fixes to agent-generated reports.
+
+## Security reports
+
+- AI-assisted security reports must meet the legitimacy and verification requirements in [SECURITY.md](SECURITY.md#ai-assisted-submissions). A human must verify a real Paperless-ngx code path, concrete reproduction steps, affected versions, and realistic security impact before submission.
+- Account for existing permission checks, configuration requirements, and trust boundaries. Speculation, scanner output, or concerns about third-party software or deployment choices without a demonstrated Paperless-ngx vulnerability do not meet this threshold and may be closed without extended discussion.
+- Disclose AI assistance and use the private vulnerability reporting channel specified in [SECURITY.md](SECURITY.md#reporting-a-vulnerability).
+
+## Working on changes
+
+- Read the relevant code, tests, and documentation before editing. Paperless-ngx is complex: trace interactions between affected components rather than assuming a change is isolated.
+- Keep changes focused on the requested work and follow existing patterns. Avoid unrelated refactoring, formatting, dependency updates, or generated-file changes.
+- Consider effects on permissions, document processing, background tasks, storage, and the API when those areas are involved.
+- Add or update meaningful tests for behavior changes and regressions. Do not weaken tests or checks to make a change pass.
+- Update user or developer documentation when behavior or setup changes.
+- Keep credentials and private documents out of commits, fixtures, logs, and examples.
+
+## Repository and validation
+
+- `src/`: Django back end.
+- `src-ui/`: Angular front end, managed with `pnpm`.
+- `docs/`: Documentation.
+- `docker/` and `scripts/`: Deployment and development tooling.
+- Base functional changes on `dev`; documentation-only changes may target `main`.
+
+Follow [the development documentation](docs/development.md) for environment setup and testing. Common checks after setup are:
+
+- Back end: run `uv run pytest` from `src/` (use a test path to focus on the affected area).
+- Front end: run `pnpm test` and `pnpm lint` from `src-ui/`.
+- Formatting and other pre-commit checks: run `uv run prek run --files <changed-files>` from the repository root.
+
+When handing work back, summarize the changes, the checks actually run and their results, and any remaining uncertainty. Clearly state when a check could not be run; do not claim verification that did not happen. The human contributor must understand and independently verify the contribution before submitting it.

CONTRIBUTING.md

@@ -4,6 +4,18 @@ If you feel like contributing to the project, please do! Bug fixes and improveme
 
 ⚠️ Please note: Pull requests that implement a new feature or enhancement _should almost always target an existing feature request_ with evidence of community interest and discussion. This is in order to balance the work of implementing and maintaining new features / enhancements. Pull requests that are opened without meeting this requirement may not be merged.
 
+## Trust and collaboration
+
+Paperless-ngx places a high value on trust between contributors and maintainers. If you have not contributed before, consider starting with a discussion before preparing a pull request, especially for a large contribution or one involving AI-generated code.
+
+Paperless-ngx is complex, and understanding how its components interact takes time. A change that appears correct in isolation can have consequences elsewhere in the application. Contributors should understand the code they submit, explain how it fits into the project, and work with maintainers through review. Starting with smaller, focused contributions can help build that understanding and trust.
+
+We prefer thoughtful, well-described ideas to AI-generated pull requests. You do not need to supply an implementation for your contribution to be valuable. Explain the problem you have encountered, your use case, the behavior you would like to see, and who would benefit. Concrete examples, alternatives you have considered, and relevant constraints help the community discuss and refine the idea.
+
+AI tools have lowered the effort needed to produce a pull request, but evaluating one still requires substantial maintainer time. Maintainers still need to establish whether the implementation is correct, fits the project, and can be maintained over time.
+
+A flawed implementation can also obscure a good idea: discussion becomes focused on problems with the generated code before the community has considered whether the underlying proposal is useful. Starting with the idea gives it a fair discussion on its own merits and lets contributors and maintainers agree on an approach before investing in implementation and review.
+
 If you want to implement something big:
 
 - As above, please start with a discussion! Maybe something similar is already in development and we can make it happen together.
@@ -61,9 +73,10 @@ This project does not specifically prohibit the use of AI tools or agents _durin
 
 1. Any content — code, pull request descriptions, issue reports or comments — that was generated in whole or in part by an AI tool or agent **must be clearly disclosed as such**. Failing to clearly disclose this is considered a violation of our [Code of Conduct](CODE_OF_CONDUCT.md) and may result in your contributions being closed and further action being taken.
 2. AI-generated code must not violate copyright protections.
-3. We will not accept PRs that are entirely or mostly AI-derived.
-4. Issue reports must describe _observed behavior only_: what happened, how to reproduce it and the relevant logs. Reports generated by an AI agent should not include code analysis, speculation about the root cause or suggest fixes.
-5. Contributors are responsible for everything they submit, regardless of how it was produced. Please do not open issues or PRs you have not verified yourself.
+3. We will not accept PRs opened or submitted by AI agents, including agents acting "on behalf of" a human. A human contributor must personally review, verify, and submit the contribution and take responsibility for it throughout review.
+4. We will not accept PRs that are entirely or mostly AI-derived.
+5. Issue reports must describe _observed behavior only_: what happened, how to reproduce it and the relevant logs. Reports generated by an AI agent should not include code analysis, speculation about the root cause or suggest fixes.
+6. Contributors are responsible for everything they submit, regardless of how it was produced. Please do not open issues or PRs you have not verified yourself.
 
 # Translating Paperless-ngx
 

SECURITY.md

@@ -56,6 +56,9 @@ We may close reports that are:
 
 The following are not generally considered vulnerabilities unless accompanied by a concrete, reproducible impact in Paperless-ngx:
 
+- password length inferred from masked mail-account passwords by users who already have permission to view the account, without disclosure of the password or token itself
+- disclosure limited to document IDs, existence, page counts, checksums, or modification/deletion timestamps, without access to document contents or an unintended privileged action
+- authenticated access to non-secret application settings, such as service endpoint URLs, model names, or configured environment variable names, without disclosure of credentials or secret values
 - large uploads or resource usage that do not bypass documented limits or privileges
 - IDOR / access control claims regarding the ability to attach an un-viewable object to a document. This is expected behavior.
 - claims based solely on the presence of a library, framework feature or code pattern without a working exploit

docker/rootfs/etc/s6-overlay/s6-rc.d/init-compile-bytecode/run

@@ -39,7 +39,6 @@ declare -a scope=(
 	"${site_packages}/allauth"
 	"${site_packages}/drf_spectacular"
 	"${site_packages}/drf_spectacular_sidecar"
-	"${site_packages}/treenode"
 	"${site_packages}/compression_middleware"
 )
 

docs/usage.md

@@ -109,7 +109,7 @@ Think of versions as **file history** for a document.
 Paperless-ngx includes management lists for tags, correspondents, document types
 and more. These areas allow you to view, add, edit, delete and manage permissions
 for these objects. You can also manage saved views, mail accounts, mail rules,
-workflows, [OCR templates](#ocr-templates) and more from the management sections.
+workflows and more from the management sections.
 
 ### Nested Tags
 
@@ -795,84 +795,6 @@ The following custom field types are supported:
 - `Document Link`: reference(s) to other document(s) displayed as links, automatically creates a symmetrical link in reverse
 - `Select`: a pre-defined list of strings from which the user can choose
 
-## OCR Templates {#ocr-templates}
-
-OCR templates read text from fixed areas ("zones") of a document and write it to a
-[custom field](#custom-fields), or to the document's title, archive serial number or created date. They are
-useful for documents that always share the same layout, such as bills from a particular utility. They allow you
-to draw a zone around the account number once, and every new bill gets its account number filled in.
-
-Like tags or document types, each template has a [matching algorithm](advanced_usage.md#matching) that
-decides which documents it automatically applies to (or not), based on their content.
-
-### Creating a template
-
-1. Open **OCR Templates** under "Manage" and choose **Add Template**.
-2. Give the template a name and set up its matching, for example **Any word** with the utility's name. Choose
-   **None** for a template that should only ever be run manually.
-3. Search for a sample document with the layout the template is for. Its pages are shown next to the template
-   settings.
-4. Draw zones on the document. Click a zone to select and edit it.
-5. Choose the field each zone fills.
-6. Use **Test** to run OCR on the selected zone of the sample document and see the text it finds and the value
-   that would be written.
-
-Zones are positioned relative to the sample document's page, so templates work best when the documents they
-match have an identical layout. Keep the matching specific enough that it only catches documents with that
-layout.
-
-### Zone settings
-
-- **Page**: the page the zone is on. Turn on **Last page** for zones that are always on the final page,
-  regardless of how many pages a document has.
-- **OCR language**: the Tesseract languages used to read the zone. Languages other than the defaults must be
-  installed, see [`PAPERLESS_OCR_LANGUAGES`](configuration.md#PAPERLESS_OCR_LANGUAGES).
-- **Transform**: post-processing applied to the text, such as stripping whitespace, keeping only numbers,
-  parsing a date or reading a QR code or barcode instead of text.
-- **Date format**: for the "Parse date" transform, the format of the date using
-  [Python date codes](https://docs.python.org/3/library/datetime.html#format-codes), e.g. `%d.%m.%Y`.
-  Leave it empty to detect the format automatically.
-- **Validation regex**: a regular expression the whole value must match. Values that do not match are not
-  written.
-
-Zones can fill custom fields of type text, long text, URL, date, integer, number, monetary or boolean.
-Document link and select fields are not supported.
-
-### Combining zones
-
-When several zones fill the same field, a **Combined value** setting appears for that field. Use it to arrange
-the zones' values with `{Zone name}` tokens and any text in between, for example `{Start} - {End}`. If it
-is left empty, the values are joined with spaces in zone order.
-
-### When templates run
-
-When a document is added, every enabled template that matches its content runs automatically. A template is
-only used for a document if the document's owner can view the template, so users' templates apply to their own
-documents, and unowned templates apply to everyone's. Templates run in name order, so if two templates fill the
-same field, the later one wins.
-
-Turn off **Enabled** to pause a template without deleting it. Disabled templates never run automatically, but
-can still be run manually.
-
-### Running templates manually
-
-To run templates on documents that are already in Paperless-ngx, open the **Actions** menu on the document
-details page:
-
-- **Run Zone OCR** runs every enabled template that matches the document.
-- The button next to it opens a dialog where you can choose one template to run
-  instead. A template you choose runs even if it does not match the document or is disabled.
-
-The bulk editor's **Run Zone OCR** action opens the same dialog for the selected documents. Bulk runs are
-processed in the background.
-
-!!! warning
-
-    Zone OCR overwrites the fields it fills. A zone that finds no value leaves its field unchanged.
-
-Managing OCR templates requires the OCR template permissions. Running zone OCR on documents requires
-permission to change them, and choosing a template requires permission to view it.
-
 ## PDF Actions
 
 Paperless-ngx supports basic editing operations for PDFs (these operations currently cannot be performed on non-PDF files). When viewing an individual document you can

pyproject.toml

@@ -38,7 +38,6 @@ dependencies = [
   "django-multiselectfield~=1.0.1",
   "django-rich~=2.2.0",
   "django-soft-delete~=1.0.18",
-  "django-treenode>=0.24",
   "djangorestframework~=3.16",
   "drf-spectacular~=0.30",
   "drf-spectacular-sidecar>=2026.10.1,<2026.11",

src-ui/messages.xlf

@@ -6984,7 +6984,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/input/select/select.component.ts</context>
-          <context context-type="linenumber">179</context>
+          <context context-type="linenumber">185</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1880237574877817137" datatype="html">
@@ -7091,7 +7091,7 @@
         <source>Private</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/input/select/select.component.ts</context>
-          <context context-type="linenumber">72</context>
+          <context context-type="linenumber">73</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/tag/tag.component.html</context>
@@ -7114,7 +7114,7 @@
         <source>No items found</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/input/select/select.component.ts</context>
-          <context context-type="linenumber">113</context>
+          <context context-type="linenumber">114</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6541407358060244620" datatype="html">

src-ui/src/app/app-routing.module.ts

@@ -13,7 +13,6 @@ import { DocumentDetailComponent } from './components/document-detail/document-d
 import { DocumentListComponent } from './components/document-list/document-list.component'
 import { DocumentAttributesComponent } from './components/manage/document-attributes/document-attributes.component'
 import { MailComponent } from './components/manage/mail/mail.component'
-import { OcrTemplatesComponent } from './components/manage/ocr-templates/ocr-templates.component'
 import { SavedViewsComponent } from './components/manage/saved-views/saved-views.component'
 import { ShareLinksComponent } from './components/manage/share-links/share-links.component'
 import { WorkflowsComponent } from './components/manage/workflows/workflows.component'
@@ -276,18 +275,6 @@ export const routes: Routes = [
           componentName: 'WorkflowsComponent',
         },
       },
-      {
-        path: 'ocr-templates',
-        component: OcrTemplatesComponent,
-        canActivate: [PermissionsGuard],
-        data: {
-          requiredPermission: {
-            action: PermissionAction.View,
-            type: PermissionType.OcrTemplate,
-          },
-          componentName: 'OcrTemplatesComponent',
-        },
-      },
       {
         path: 'mail',
         component: MailComponent,

src-ui/src/app/components/admin/settings/settings.component.ts

@@ -113,7 +113,6 @@ const sidebarItemLabels: Record<HideableSidebarItemID, string> = {
   [HideableSidebarItemID.SavedViews]: $localize`Saved Views`,
   [HideableSidebarItemID.ShareLinks]: $localize`Share Links`,
   [HideableSidebarItemID.Workflows]: $localize`Workflows`,
-  [HideableSidebarItemID.OcrTemplates]: $localize`OCR Templates`,
   [HideableSidebarItemID.Mail]: $localize`Mail`,
   [HideableSidebarItemID.Documentation]: $localize`Documentation`,
 }

src-ui/src/app/components/app-frame/app-frame.component.html

@@ -289,17 +289,6 @@
                 <pngx-input-switch class="position-absolute top-50 end-0 translate-middle-y me-1" [class.d-none]="slimSidebarEnabled || slimSidebarAnimating()" [compact]="true" title="Workflows" i18n-title [ngModel]="!settingsService.sidebarItemIsHidden(HideableSidebarItemID.Workflows)" (ngModelChange)="toggleSidebarItem(HideableSidebarItemID.Workflows, $event)"></pngx-input-switch>
               }
             </li>
-            <li class="nav-item app-link position-relative" [class.d-none]="settingsService.sidebarItemIsHidden(HideableSidebarItemID.OcrTemplates) && !settingsService.organizingSidebarItems()"
-              *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.OcrTemplate }">
-              <a class="nav-link" [class.opacity-50]="settingsService.sidebarItemIsHidden(HideableSidebarItemID.OcrTemplates)" [class.pe-5]="settingsService.organizingSidebarItems() && !slimSidebarEnabled && !slimSidebarAnimating()" routerLink="ocr-templates" routerLinkActive="active" (click)="closeMenu()"
-                ngbPopover="OCR Templates" i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end"
-                container="body" triggers="mouseenter:mouseleave" popoverClass="popover-slim">
-                <pngx-bs-icon class="me-2" name="bounding-box-circles"></pngx-bs-icon><span class="nav-link-label"><ng-container i18n>OCR Templates</ng-container></span>
-              </a>
-              @if (settingsService.organizingSidebarItems()) {
-                <pngx-input-switch class="position-absolute top-50 end-0 translate-middle-y me-1" [class.d-none]="slimSidebarEnabled || slimSidebarAnimating()" [compact]="true" title="OCR Templates" i18n-title [ngModel]="!settingsService.sidebarItemIsHidden(HideableSidebarItemID.OcrTemplates)" (ngModelChange)="toggleSidebarItem(HideableSidebarItemID.OcrTemplates, $event)"></pngx-input-switch>
-              }
-            </li>
             <li class="nav-item app-link position-relative" [class.d-none]="settingsService.sidebarItemIsHidden(HideableSidebarItemID.Mail) && !settingsService.organizingSidebarItems()" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.MailAccount }"
               tourAnchor="tour.mail">
               <a class="nav-link" [class.opacity-50]="settingsService.sidebarItemIsHidden(HideableSidebarItemID.Mail)" [class.pe-5]="settingsService.organizingSidebarItems() && !slimSidebarEnabled && !slimSidebarAnimating()" routerLink="mail" routerLinkActive="active" (click)="closeMenu()" ngbPopover="Mail"

src-ui/src/app/components/app-frame/app-frame.component.spec.ts

@@ -293,7 +293,6 @@ describe('AppFrameComponent', () => {
       HideableSidebarItemID.Dashboard,
       HideableSidebarItemID.Workflows,
       HideableSidebarItemID.ShareLinks,
-      HideableSidebarItemID.OcrTemplates,
     ])
     fixture.detectChanges()
 
@@ -309,10 +308,6 @@ describe('AppFrameComponent', () => {
       fixture.nativeElement.querySelector('[routerLink="share-links"]')
         .parentElement.classList
     ).toContain('d-none')
-    expect(
-      fixture.nativeElement.querySelector('[routerLink="ocr-templates"]')
-        .parentElement.classList
-    ).toContain('d-none')
     expect(
       fixture.nativeElement.querySelector('[routerLink="mail"]').parentElement
         .classList
@@ -325,21 +320,12 @@ describe('AppFrameComponent', () => {
     ])
     settingsService.sidebarHiddenItemsEditing.set([
       HideableSidebarItemID.Dashboard,
-      HideableSidebarItemID.OcrTemplates,
     ])
     fixture.detectChanges()
 
     expect(
       fixture.nativeElement.querySelectorAll('pngx-input-switch').length
-    ).toBe(7)
-    const ocrTemplatesLink = fixture.nativeElement.querySelector(
-      '[routerLink="ocr-templates"]'
-    )
-    expect(ocrTemplatesLink.parentElement.classList).not.toContain('d-none')
-    expect(ocrTemplatesLink.classList).toContain('opacity-50')
-    expect(
-      ocrTemplatesLink.parentElement.querySelector('pngx-input-switch')
-    ).not.toBeNull()
+    ).toBe(6)
     expect(
       fixture.nativeElement.querySelector('[routerLink="dashboard"]')
         .parentElement.classList

src-ui/src/app/components/common/bootstrap-icon/icons.ts

@@ -16,7 +16,6 @@ import basket from 'bootstrap-icons/icons/basket.svg'
 import bell from 'bootstrap-icons/icons/bell.svg'
 import bodyText from 'bootstrap-icons/icons/body-text.svg'
 import bookmark from 'bootstrap-icons/icons/bookmark.svg'
-import boundingBoxCircles from 'bootstrap-icons/icons/bounding-box-circles.svg'
 import boxArrowInRight from 'bootstrap-icons/icons/box-arrow-in-right.svg'
 import boxArrowUpRight from 'bootstrap-icons/icons/box-arrow-up-right.svg'
 import boxArrowUp from 'bootstrap-icons/icons/box-arrow-up.svg'
@@ -78,7 +77,6 @@ import fileEarmarkMinus from 'bootstrap-icons/icons/file-earmark-minus.svg'
 import fileEarmarkPerson from 'bootstrap-icons/icons/file-earmark-person.svg'
 import fileEarmarkPlus from 'bootstrap-icons/icons/file-earmark-plus.svg'
 import fileEarmarkRichtext from 'bootstrap-icons/icons/file-earmark-richtext.svg'
-import fileEarmarkRuled from 'bootstrap-icons/icons/file-earmark-ruled.svg'
 import fileEarmarkSpreadsheet from 'bootstrap-icons/icons/file-earmark-spreadsheet.svg'
 import fileEarmark from 'bootstrap-icons/icons/file-earmark.svg'
 import fileText from 'bootstrap-icons/icons/file-text.svg'
@@ -132,7 +130,6 @@ import search from 'bootstrap-icons/icons/search.svg'
 import send from 'bootstrap-icons/icons/send.svg'
 import shop from 'bootstrap-icons/icons/shop.svg'
 import slashCircle from 'bootstrap-icons/icons/slash-circle.svg'
-import sliders2 from 'bootstrap-icons/icons/sliders2.svg'
 import sliders2Vertical from 'bootstrap-icons/icons/sliders2-vertical.svg'
 import sortAlphaDown from 'bootstrap-icons/icons/sort-alpha-down.svg'
 import sortAlphaUpAlt from 'bootstrap-icons/icons/sort-alpha-up-alt.svg'
@@ -181,7 +178,6 @@ export const icons: Record<string, string> = {
   braces,
   bodyText,
   bookmark,
-  boundingBoxCircles,
   boxArrowInRight,
   boxArrowUp,
   boxArrowUpRight,
@@ -243,7 +239,6 @@ export const icons: Record<string, string> = {
   fileEarmarkPerson,
   fileEarmarkPlus,
   fileEarmarkRichtext,
-  fileEarmarkRuled,
   fileEarmarkSpreadsheet,
   files,
   fileText,
@@ -295,7 +290,6 @@ export const icons: Record<string, string> = {
   search,
   send,
   slashCircle,
-  sliders2,
   shop,
   sliders2Vertical,
   sortAlphaDown,

src-ui/src/app/components/common/confirm-dialog/zone-ocr-confirm-dialog/zone-ocr-confirm-dialog.component.html

@@ -1,30 +0,0 @@
-<div class="modal-header">
-  <h4 class="modal-title" id="modal-basic-title">{{title}}</h4>
-  <button type="button" class="btn-close" aria-label="Close" (click)="cancel()">
-  </button>
-</div>
-<div class="modal-body">
-  @if (messageBold) {
-    <p class="text-break"><b>{{messageBold}}</b></p>
-  }
-  @if (message) {
-    <p class="text-break" [innerHTML]="message"></p>
-  }
-  <pngx-input-select
-    [items]="templates()"
-    [(ngModel)]="template"
-    [allowNull]="true"
-    title="OCR template"
-    i18n-title
-    placeholder="All matching templates"
-    i18n-placeholder
-  ></pngx-input-select>
-</div>
-<div class="modal-footer">
-  <button type="button" class="btn" [class]="cancelBtnClass" (click)="cancel()" [disabled]="!buttonsEnabled()">
-    <span class="d-inline-block" style="padding-bottom: 1px;">{{cancelBtnCaption}}</span>
-  </button>
-  <button type="button" class="btn" [class]="btnClass" (click)="confirm()" [disabled]="!confirmButtonEnabled || !buttonsEnabled()">
-    {{btnCaption}}
-  </button>
-</div>

src-ui/src/app/components/common/confirm-dialog/zone-ocr-confirm-dialog/zone-ocr-confirm-dialog.component.spec.ts

@@ -1,52 +0,0 @@
-import { provideHttpClient, withInterceptorsFromDi } from '@angular/common/http'
-import { provideHttpClientTesting } from '@angular/common/http/testing'
-import { ComponentFixture, TestBed } from '@angular/core/testing'
-import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
-import { of } from 'rxjs'
-import { MATCH_NONE } from 'src/app/data/matching-model'
-import { OcrTemplate } from 'src/app/data/ocr-template'
-import { OcrTemplateService } from 'src/app/services/rest/ocr-template.service'
-import { ZoneOcrConfirmDialogComponent } from './zone-ocr-confirm-dialog.component'
-
-const templates: OcrTemplate[] = [
-  {
-    id: 1,
-    name: 'Invoices',
-    match: '',
-    matching_algorithm: MATCH_NONE,
-    sample_document: null,
-    source_width: 0,
-    source_height: 0,
-    enabled: true,
-    zones: [],
-  },
-]
-
-describe('ZoneOcrConfirmDialogComponent', () => {
-  let component: ZoneOcrConfirmDialogComponent
-  let fixture: ComponentFixture<ZoneOcrConfirmDialogComponent>
-
-  beforeEach(() => {
-    TestBed.configureTestingModule({
-      providers: [
-        NgbActiveModal,
-        provideHttpClient(withInterceptorsFromDi()),
-        provideHttpClientTesting(),
-      ],
-      imports: [ZoneOcrConfirmDialogComponent],
-    })
-    jest
-      .spyOn(TestBed.inject(OcrTemplateService), 'listAll')
-      .mockReturnValue(of({ count: 1, all: [1], results: templates }))
-
-    fixture = TestBed.createComponent(ZoneOcrConfirmDialogComponent)
-    component = fixture.componentInstance
-    fixture.detectChanges()
-  })
-
-  it('should offer templates and default to all matching templates', () => {
-    expect(component.templates()).toEqual(templates)
-    expect(component.template).toBeNull()
-    expect(fixture.nativeElement.textContent).toContain('OCR template')
-  })
-})

src-ui/src/app/components/common/confirm-dialog/zone-ocr-confirm-dialog/zone-ocr-confirm-dialog.component.ts

@@ -1,31 +0,0 @@
-import { Component, OnInit, inject, signal } from '@angular/core'
-import { FormsModule } from '@angular/forms'
-import { takeUntil } from 'rxjs'
-import { OcrTemplate } from 'src/app/data/ocr-template'
-import { OcrTemplateService } from 'src/app/services/rest/ocr-template.service'
-import { SelectComponent } from '../../input/select/select.component'
-import { ConfirmDialogComponent } from '../confirm-dialog.component'
-
-@Component({
-  selector: 'pngx-zone-ocr-confirm-dialog',
-  templateUrl: './zone-ocr-confirm-dialog.component.html',
-  imports: [FormsModule, SelectComponent],
-})
-export class ZoneOcrConfirmDialogComponent
-  extends ConfirmDialogComponent
-  implements OnInit
-{
-  private readonly ocrTemplateService = inject(OcrTemplateService)
-
-  public readonly templates = signal<OcrTemplate[]>([])
-
-  /** The template to run, or null for every template that matches. */
-  template: number | null = null
-
-  ngOnInit() {
-    this.ocrTemplateService
-      .listAll()
-      .pipe(takeUntil(this.unsubscribeNotifier))
-      .subscribe((r) => this.templates.set(r.results))
-  }
-}

src-ui/src/app/components/common/input/document-link/document-link.component.html

@@ -36,11 +36,11 @@
     [appendTo]="appendTo"
     [loading]="loading()"
     [typeahead]="documentsInput$"
-    (mousedown)="$event.stopImmediatePropagation()"
+    (mousedown)="appendTo && $event.stopImmediatePropagation()"
     (change)="onChange(selectedDocumentIDs)">
     <ng-template ng-label-tmp let-document="item">
       <div class="d-flex align-items-center">
-        @if (!disabled && multiple) {
+        @if (!disabled) {
           <button class="btn p-0 lh-1" (click)="unselect(document)" (mousedown)="$event.stopImmediatePropagation()" type="button" title="Remove link" i18n-title><pngx-bs-icon name="x"></pngx-bs-icon></button>
         }
         @if (document.title) {

src-ui/src/app/components/common/input/document-link/document-link.component.ts

@@ -81,9 +81,6 @@ export class DocumentLinkComponent
   @Input()
   placeholder: string = $localize`Search for documents`
 
-  @Input()
-  multiple: boolean = true
-
   /**
    * Parent for ng-select dropdown, needed to prevent close on click.
    */

src-ui/src/app/components/common/input/select/select.component.spec.ts

@@ -97,6 +97,7 @@ describe('SelectComponent', () => {
     let createNewVal
     component.createNew.subscribe((v) => (createNewVal = v))
     expect(component.allowCreateNew).toBeTruthy()
+    const closeSpy = jest.spyOn(component.ngSelectComponent, 'close')
     component.onSearch({ term: 'foo' })
     component.addItem(undefined)
     expect(createNewVal).toEqual('foo')
@@ -105,6 +106,8 @@ describe('SelectComponent', () => {
     component.onSearch({ term: 'baz' })
     component.clickNew()
     expect(createNewVal).toEqual('baz')
+    // dropdown should close when creating a new item so it isn't left open behind the modal
+    expect(closeSpy).toHaveBeenCalled()
   })
 
   it('should search items by independent normalized terms', () => {

src-ui/src/app/components/common/input/select/select.component.ts

@@ -4,6 +4,7 @@ import {
   forwardRef,
   Input,
   Output,
+  ViewChild,
 } from '@angular/core'
 import {
   FormsModule,
@@ -11,7 +12,7 @@ import {
   ReactiveFormsModule,
 } from '@angular/forms'
 import { RouterModule } from '@angular/router'
-import { NgSelectModule } from '@ng-select/ng-select'
+import { NgSelectComponent, NgSelectModule } from '@ng-select/ng-select'
 import { BootstrapIconComponent } from 'src/app/components/common/bootstrap-icon/bootstrap-icon.component'
 import { matchesSearchText } from 'src/app/utils/text-search'
 import { AbstractInputComponent } from '../abstract-input'
@@ -124,6 +125,9 @@ export class SelectComponent extends AbstractInputComponent<number | string> {
   @Output()
   filterDocuments = new EventEmitter<any[]>()
 
+  @ViewChild(NgSelectComponent)
+  ngSelectComponent: NgSelectComponent
+
   public addItemRef: (name) => void
 
   private _lastSearchTerm: string
@@ -150,11 +154,13 @@ export class SelectComponent extends AbstractInputComponent<number | string> {
     if (name) this.createNew.next(name)
     else this.createNew.next(this._lastSearchTerm)
     this.clearLastSearchTerm()
+    this.ngSelectComponent?.close()
   }
 
   clickNew() {
     this.createNew.next(this._lastSearchTerm)
     this.clearLastSearchTerm()
+    this.ngSelectComponent?.close()
   }
 
   clearLastSearchTerm() {

src-ui/src/app/components/document-detail/document-detail.component.html

@@ -61,22 +61,6 @@
         <pngx-bs-icon name="pencil" class="me-2"></pngx-bs-icon><ng-container i18n>PDF Editor</ng-container>
       </button>
 
-      <div class="d-flex" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.OcrTemplate }">
-        <button ngbDropdownItem (click)="runZoneOcr()" [disabled]="!userCanEdit || networkActive()">
-          <pngx-bs-icon width="1em" height="1em" name="bounding-box-circles" class="me-2"></pngx-bs-icon><span i18n>Run Zone OCR</span>
-        </button>
-        <button
-          ngbDropdownItem
-          class="w-auto flex-shrink-0 px-2"
-          (click)="runZoneOcrWithOptions()"
-          [disabled]="!userCanEdit || networkActive()"
-          title="Choose OCR template"
-          i18n-title
-        >
-          <pngx-bs-icon width="1em" height="1em" name="sliders2"></pngx-bs-icon>
-        </button>
-      </div>
-
       @if (userIsOwner && (requiresPassword || password)) {
         <button ngbDropdownItem (click)="removePassword()" [disabled]="!password">
           <pngx-bs-icon name="unlock" class="me-2"></pngx-bs-icon><ng-container i18n>Remove Password</ng-container>
@@ -106,7 +90,7 @@
 <div class="row">
   <div class="col-md-6 col-xl-5 mb-4">
 
-    <form [formGroup]='documentForm' (ngSubmit)="save()" [attr.inert]="zoneOcrRunning() ? '' : null" [attr.aria-busy]="zoneOcrRunning()">
+    <form [formGroup]='documentForm' (ngSubmit)="save()">
 
       <div class="btn-toolbar mb-1 pb-3 gap-2 row-gap-2 border-bottom">
         <div class="btn-group">

src-ui/src/app/components/document-detail/document-detail.component.spec.ts

@@ -1909,196 +1909,6 @@ describe('DocumentDetailComponent', () => {
     expect(toastSpy).toHaveBeenCalledWith('Document reloaded.')
   })
 
-  it('should run zone OCR, report results and reload the document', () => {
-    component.documentId.set(doc.id)
-    component.document.set(doc)
-    jest.spyOn(documentService, 'runZoneOcr').mockReturnValue(
-      of({
-        results: [
-          { zone: 'Total', value: '102.10' },
-          { zone: 'Due', value: '' },
-        ],
-      } as any)
-    )
-    const loadSpy = jest
-      .spyOn(component as any, 'loadDocument')
-      .mockImplementation(() => {})
-    const notifySpy = jest.spyOn(component.docChangeNotifier, 'next')
-    const toastSpy = jest.spyOn(toastService, 'showInfo')
-    const modalSpy = jest.spyOn(modalService, 'open')
-
-    component.runZoneOcrWithOptions()
-    const dialog = modalSpy.mock.results[0].value.componentInstance
-    expect(dialog.message).toBe(
-      'Fields filled by the template will be overwritten.'
-    )
-    dialog.template = 3
-    dialog.confirmClicked.emit()
-
-    expect(documentService.runZoneOcr).toHaveBeenCalledWith(doc.id, 3)
-    expect(toastSpy).toHaveBeenCalledWith(
-      'Filled 1 of 2 fields. No value found for: Due'
-    )
-    expect(notifySpy).toHaveBeenCalledWith(doc.id)
-    expect(loadSpy).toHaveBeenCalledWith(doc.id, true, expect.any(Function))
-    expect(component.zoneOcrRunning()).toBe(true)
-    loadSpy.mock.calls[0][2]()
-    expect(component.zoneOcrRunning()).toBe(false)
-    expect(component.networkActive()).toBe(false)
-  })
-
-  it('should summarize zone OCR results', () => {
-    component.documentId.set(doc.id)
-    component.document.set(doc)
-    jest.spyOn(component as any, 'loadDocument').mockImplementation(() => {})
-    const runSpy = jest.spyOn(documentService, 'runZoneOcr')
-    const toastSpy = jest.spyOn(toastService, 'showInfo')
-    const modalSpy = jest.spyOn(modalService, 'open')
-
-    runSpy.mockReturnValueOnce(of({ status: 'completed', results: [] }))
-    component.runZoneOcr()
-    expect(modalSpy).not.toHaveBeenCalled()
-    expect(runSpy).toHaveBeenCalledWith(doc.id, null)
-    expect(toastSpy).toHaveBeenLastCalledWith(
-      'Zone OCR found no fields to fill.'
-    )
-
-    component.networkActive.set(false)
-    runSpy.mockReturnValueOnce(
-      of({
-        status: 'completed',
-        results: [
-          { template: 'T', zone: 'Total', custom_field: 'Amount', value: 0 },
-        ],
-      })
-    )
-    component.runZoneOcr()
-    expect(toastSpy).toHaveBeenLastCalledWith('Filled 1 of 1 fields.')
-  })
-
-  it('should confirm before running zone OCR over unsaved changes', () => {
-    component.documentId.set(doc.id)
-    component.document.set({ ...doc, __changedFields: ['title'] })
-    component.documentForm.patchValue({ title: 'Unsaved title' })
-    const runSpy = jest.spyOn(documentService, 'runZoneOcr')
-    const modalSpy = jest.spyOn(modalService, 'open')
-
-    component.runZoneOcr()
-
-    const modal = modalSpy.mock.results[0].value
-    expect(modal.componentInstance.message).toBe(
-      'Running Zone OCR will discard them.'
-    )
-    expect(runSpy).not.toHaveBeenCalled()
-    modal.componentInstance.cancel()
-    expect(runSpy).not.toHaveBeenCalled()
-    expect(component.documentForm.get('title').value).toBe('Unsaved title')
-    expect(component.zoneOcrRunning()).toBe(false)
-  })
-
-  it('should warn about unsaved changes in the zone OCR options dialog', () => {
-    component.documentId.set(doc.id)
-    component.document.set({ ...doc, __changedFields: ['title'] })
-    const runSpy = jest.spyOn(documentService, 'runZoneOcr')
-    const modalSpy = jest.spyOn(modalService, 'open')
-
-    component.runZoneOcrWithOptions()
-
-    const dialog = modalSpy.mock.results[0].value.componentInstance
-    expect(dialog.message).toBe('Running Zone OCR will discard them.')
-    expect(dialog.btnClass).toBe('btn-warning')
-    dialog.cancel()
-    expect(runSpy).not.toHaveBeenCalled()
-    component.networkActive.set(true)
-    component.runZoneOcrWithOptions()
-    expect(modalSpy).toHaveBeenCalledTimes(1)
-  })
-
-  it('should not allow saving or a second zone OCR run while one is running', () => {
-    component.documentId.set(doc.id)
-    component.document.set({ ...doc, __changedFields: ['title'] })
-    const pending = new Subject<any>()
-    const runSpy = jest
-      .spyOn(documentService, 'runZoneOcr')
-      .mockReturnValue(pending)
-    const modalSpy = jest.spyOn(modalService, 'open')
-
-    component.runZoneOcr()
-    modalSpy.mock.results[0].value.componentInstance.confirmClicked.emit()
-
-    expect(runSpy).toHaveBeenCalledWith(doc.id, null)
-    expect(component.zoneOcrRunning()).toBe(true)
-    expect(component.networkActive()).toBe(true)
-    const saveSpy = jest.spyOn(documentService, 'patch')
-    component.save()
-    expect(saveSpy).not.toHaveBeenCalled()
-    component.runZoneOcr()
-    expect(modalSpy).toHaveBeenCalledTimes(1)
-    expect(runSpy).toHaveBeenCalledTimes(1)
-    pending.error(new Error('failed'))
-    expect(component.zoneOcrRunning()).toBe(false)
-    expect(component.networkActive()).toBe(false)
-    expect(component.document().__changedFields).toEqual(['title'])
-  })
-
-  it('should not reload after zone OCR if another document is open', () => {
-    component.documentId.set(doc.id)
-    component.document.set({ ...doc, __changedFields: [] })
-    const pending = new Subject<any>()
-    jest.spyOn(documentService, 'runZoneOcr').mockReturnValue(pending)
-    const loadSpy = jest.spyOn(component as any, 'loadDocument')
-
-    component.runZoneOcr()
-    component.documentId.set(99)
-    pending.next({ results: [] })
-
-    expect(loadSpy).not.toHaveBeenCalled()
-    expect(component.zoneOcrRunning()).toBe(false)
-    pending.complete()
-  })
-
-  it('should keep unsaved changes when zone OCR is skipped', () => {
-    component.documentId.set(doc.id)
-    component.document.set({ ...doc, __changedFields: ['title'] })
-    component.documentForm.patchValue({ title: 'Unsaved title' })
-    const modalSpy = jest.spyOn(modalService, 'open')
-    jest
-      .spyOn(documentService, 'runZoneOcr')
-      .mockReturnValue(of({ status: 'skipped', results: [] }))
-    const loadSpy = jest.spyOn(component as any, 'loadDocument')
-    const infoSpy = jest.spyOn(toastService, 'showInfo')
-
-    component.runZoneOcr()
-    modalSpy.mock.results[0].value.componentInstance.confirm()
-
-    expect(loadSpy).not.toHaveBeenCalled()
-    expect(component.documentForm.get('title').value).toBe('Unsaved title')
-    expect(component.zoneOcrRunning()).toBe(false)
-    expect(component.networkActive()).toBe(false)
-    expect(infoSpy).toHaveBeenCalledWith(
-      'No OCR template applies to this document.'
-    )
-  })
-
-  it('should show an error when zone OCR fails', () => {
-    component.document.set(doc)
-    jest
-      .spyOn(documentService, 'runZoneOcr')
-      .mockReturnValue(throwError(() => new Error('nope')))
-    const loadSpy = jest.spyOn(component as any, 'loadDocument')
-    const errorSpy = jest.spyOn(toastService, 'showError')
-
-    component.runZoneOcr()
-
-    expect(errorSpy).toHaveBeenCalledWith(
-      'Error running zone OCR.',
-      expect.any(Error)
-    )
-    expect(loadSpy).not.toHaveBeenCalled()
-    expect(component.zoneOcrRunning()).toBe(false)
-    expect(component.networkActive()).toBe(false)
-  })
-
   it('should change preview element by render type', () => {
     initNormally()
     component.document.update((document) => ({

src-ui/src/app/components/document-detail/document-detail.component.ts

@@ -64,7 +64,6 @@ import {
   FILTER_STORAGE_PATH,
 } from 'src/app/data/filter-rule-type'
 import { ObjectWithId } from 'src/app/data/object-with-id'
-import { OcrZoneRunResult } from 'src/app/data/ocr-template'
 import { StoragePath } from 'src/app/data/storage-path'
 import { Tag } from 'src/app/data/tag'
 import { SETTINGS_KEYS, SuggestionSource } from 'src/app/data/ui-settings'
@@ -105,7 +104,6 @@ import { DocumentDetailFieldID } from '../admin/settings/settings.component'
 import { ConfirmDialogComponent } from '../common/confirm-dialog/confirm-dialog.component'
 import { PasswordRemovalConfirmDialogComponent } from '../common/confirm-dialog/password-removal-confirm-dialog/password-removal-confirm-dialog.component'
 import { ReprocessConfirmDialogComponent } from '../common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component'
-import { ZoneOcrConfirmDialogComponent } from '../common/confirm-dialog/zone-ocr-confirm-dialog/zone-ocr-confirm-dialog.component'
 import { CustomFieldsDropdownComponent } from '../common/custom-fields-dropdown/custom-fields-dropdown.component'
 import { CorrespondentEditDialogComponent } from '../common/edit-dialog/correspondent-edit-dialog/correspondent-edit-dialog.component'
 import { DocumentTypeEditDialogComponent } from '../common/edit-dialog/document-type-edit-dialog/document-type-edit-dialog.component'
@@ -268,7 +266,6 @@ export class DocumentDetailComponent
   readonly error = signal<any>(undefined)
 
   readonly networkActive = signal(false)
-  readonly zoneOcrRunning = signal(false)
 
   readonly documentId = signal<number>(undefined)
   readonly document = signal<Document>(undefined)
@@ -546,11 +543,7 @@ export class DocumentDetailComponent
       )
   }
 
-  private loadDocument(
-    documentId: number,
-    forceRemote: boolean = false,
-    onComplete?: () => void
-  ): void {
+  private loadDocument(documentId: number, forceRemote: boolean = false): void {
     let redirectedToRoot = false
     this.closeIncomingUpdateModal()
     this.pendingIncomingUpdate = null
@@ -607,8 +600,7 @@ export class DocumentDetailComponent
         }),
         first(),
         takeUntil(this.unsubscribeNotifier),
-        takeUntil(this.docChangeNotifier),
-        finalize(() => onComplete?.())
+        takeUntil(this.docChangeNotifier)
       )
       .subscribe({
         next: (doc) => {
@@ -1342,7 +1334,6 @@ export class DocumentDetailComponent
   }
 
   save(close: boolean = false, savedCallback: () => void = null) {
-    if (this.zoneOcrRunning()) return
     this.networkActive.set(true)
     ;(document.activeElement as HTMLElement)?.dispatchEvent(new Event('change'))
     this.documentsService
@@ -1568,107 +1559,6 @@ export class DocumentDetailComponent
     })
   }
 
-  /** Runs every template that matches, confirming only over unsaved changes. */
-  runZoneOcr() {
-    if (this.networkActive()) return
-    const documentId = this.documentId()
-    if (!this.hasLocalEdits(this.document())) {
-      this.executeZoneOcr(documentId, null)
-      return
-    }
-    const modal = this.modalService.open(ConfirmDialogComponent, {
-      backdrop: 'static',
-    })
-    modal.componentInstance.title = $localize`Run Zone OCR`
-    modal.componentInstance.messageBold = $localize`You have unsaved changes.`
-    modal.componentInstance.message = $localize`Running Zone OCR will discard them.`
-    modal.componentInstance.btnClass = 'btn-warning'
-    modal.componentInstance.btnCaption = $localize`Run Zone OCR`
-    modal.componentInstance.confirmClicked
-      .pipe(first(), takeUntil(this.unsubscribeNotifier))
-      .subscribe(() => {
-        modal.close()
-        if (this.documentId() === documentId && !this.networkActive()) {
-          this.executeZoneOcr(documentId, null)
-        }
-      })
-  }
-
-  /** Opens the dialog to pick which template to run. */
-  runZoneOcrWithOptions() {
-    if (this.networkActive()) return
-    const documentId = this.documentId()
-    const modal = this.modalService.open(ZoneOcrConfirmDialogComponent, {
-      backdrop: 'static',
-    })
-    const dialog = modal.componentInstance as ZoneOcrConfirmDialogComponent
-    dialog.title = $localize`Run Zone OCR`
-    dialog.btnCaption = $localize`Run Zone OCR`
-    if (this.hasLocalEdits(this.document())) {
-      dialog.messageBold = $localize`You have unsaved changes.`
-      dialog.message = $localize`Running Zone OCR will discard them.`
-      dialog.btnClass = 'btn-warning'
-    } else {
-      dialog.message = $localize`Fields filled by the template will be overwritten.`
-    }
-    dialog.confirmClicked
-      .pipe(first(), takeUntil(this.unsubscribeNotifier))
-      .subscribe(() => {
-        modal.close()
-        if (this.documentId() === documentId && !this.networkActive()) {
-          this.executeZoneOcr(documentId, dialog.template)
-        }
-      })
-  }
-
-  private executeZoneOcr(documentId: number, templateId: number | null) {
-    this.zoneOcrRunning.set(true)
-    this.networkActive.set(true)
-    this.documentsService
-      .runZoneOcr(documentId, templateId)
-      .pipe(takeUntil(this.unsubscribeNotifier))
-      .subscribe({
-        next: (response) => {
-          if (
-            this.documentId() !== documentId ||
-            response.status === 'skipped'
-          ) {
-            this.finishZoneOcr()
-            if (response.status === 'skipped') {
-              this.toastService.showInfo(
-                $localize`No OCR template applies to this document.`
-              )
-            }
-            return
-          }
-          this.toastService.showInfo(this.zoneOcrSummary(response.results))
-          this.docChangeNotifier.next(documentId)
-          this.loadDocument(documentId, true, () => this.finishZoneOcr())
-        },
-        error: (error) => {
-          this.finishZoneOcr()
-          this.toastService.showError($localize`Error running zone OCR.`, error)
-        },
-      })
-  }
-
-  private zoneOcrSummary(results: OcrZoneRunResult[]): string {
-    if (!results.length) return $localize`Zone OCR found no fields to fill.`
-    const missed = results
-      .filter((result) => !`${result.value ?? ''}`.trim())
-      .map((result) => result.zone)
-    const filled = results.length - missed.length
-    return missed.length
-      ? $localize`Filled ${filled} of ${results.length} fields. No value found for: ${missed.join(', ')}`
-      : $localize`Filled ${filled} of ${results.length} fields.`
-  }
-
-  private finishZoneOcr() {
-    this.zoneOcrRunning.set(false)
-    this.networkActive.set(false)
-    this.flushPendingIncomingUpdate()
-  }
-
   private getSelectedNonLatestVersionId(): number | null {
     const versions = this.document()?.versions ?? []
     if (!versions.length || !this.selectedVersionId()) {

src-ui/src/app/components/document-list/bulk-editor/bulk-editor.component.html

@@ -98,11 +98,6 @@
           <button ngbDropdownItem (click)="mergeSelectedAsVersions()" [disabled]="!userOwnsAll || !userCanEditAll || !userCanDelete || list.allSelected || list.selectedCount < 2">
             <pngx-bs-icon name="journal-bookmark-fill" class="me-2"></pngx-bs-icon><ng-container i18n>Merge as versions</ng-container>
           </button>
-          @if (permissionService.currentUserCan(PermissionAction.View, PermissionType.OcrTemplate)) {
-            <button ngbDropdownItem (click)="runZoneOcrSelected()" [disabled]="!userCanEditAll">
-              <pngx-bs-icon name="bounding-box-circles" class="me-2"></pngx-bs-icon><ng-container i18n>Run Zone OCR</ng-container>
-            </button>
-          }
         </div>
       </div>
     </div>

src-ui/src/app/components/document-list/bulk-editor/bulk-editor.component.spec.ts

@@ -1285,53 +1285,6 @@ describe('BulkEditorComponent', () => {
     ) // listAllFilteredIds
   })
 
-  it('should support run zone ocr', () => {
-    let modal: NgbModalRef
-    modalService.activeInstances.subscribe((m) => (modal = m[0]))
-    jest.spyOn(permissionsService, 'currentUserCan').mockReturnValue(true)
-    jest
-      .spyOn(documentListViewService, 'documents', 'get')
-      .mockReturnValue([{ id: 3 }, { id: 4 }])
-    jest
-      .spyOn(documentListViewService, 'selected', 'get')
-      .mockReturnValue(new Set([3, 4]))
-    jest
-      .spyOn(permissionsService, 'currentUserHasObjectPermissions')
-      .mockReturnValue(true)
-    fixture.detectChanges()
-    component.runZoneOcrSelected()
-    expect(modal).not.toBeUndefined()
-    modal.componentInstance.confirm()
-    let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/run_zone_ocr/`
-    )
-    req.flush(true)
-    expect(req.request.body).toEqual({
-      documents: [3, 4],
-    })
-
-    component.runZoneOcrSelected()
-    modal.componentInstance.template = 3
-    modal.componentInstance.confirm()
-    req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/run_zone_ocr/`
-    )
-    req.flush(true)
-    expect(req.request.body).toEqual({
-      documents: [3, 4],
-      template: 3,
-    })
-    httpTestingController.match(
-      `${environment.apiBaseUrl}ocr_templates/?page=1&page_size=100000`
-    ) // template list
-    httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
-    ) // list reload
-    httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
-    ) // listAllFilteredIds
-  })
-
   it('should support rotate', () => {
     let modal: NgbModalRef
     modalService.activeInstances.subscribe((m) => (modal = m[0]))

src-ui/src/app/components/document-list/bulk-editor/bulk-editor.component.ts

@@ -64,7 +64,6 @@ import { MergeAsVersionsConfirmDialogComponent } from '../../common/confirm-dial
 import { MergeConfirmDialogComponent } from '../../common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component'
 import { ReprocessConfirmDialogComponent } from '../../common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component'
 import { RotateConfirmDialogComponent } from '../../common/confirm-dialog/rotate-confirm-dialog/rotate-confirm-dialog.component'
-import { ZoneOcrConfirmDialogComponent } from '../../common/confirm-dialog/zone-ocr-confirm-dialog/zone-ocr-confirm-dialog.component'
 import { CorrespondentEditDialogComponent } from '../../common/edit-dialog/correspondent-edit-dialog/correspondent-edit-dialog.component'
 import { CustomFieldEditDialogComponent } from '../../common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component'
 import { DocumentTypeEditDialogComponent } from '../../common/edit-dialog/document-type-edit-dialog/document-type-edit-dialog.component'
@@ -967,30 +966,6 @@ export class BulkEditorComponent
       })
   }
 
-  runZoneOcrSelected() {
-    const modal = this.modalService.open(ZoneOcrConfirmDialogComponent, {
-      backdrop: 'static',
-    })
-    const dialog = modal.componentInstance as ZoneOcrConfirmDialogComponent
-    dialog.title = $localize`Run zone OCR confirm`
-    dialog.messageBold = $localize`This operation will run zone OCR on ${this.getSelectionSize()} selected document(s).`
-    dialog.message = $localize`Fields filled by the template will be overwritten.`
-    dialog.btnClass = 'btn-warning'
-    dialog.btnCaption = $localize`Proceed`
-    dialog.confirmClicked
-      .pipe(takeUntil(this.unsubscribeNotifier))
-      .subscribe(() => {
-        dialog.buttonsEnabled.set(false)
-        this.executeDocumentAction(
-          modal,
-          this.documentService.runZoneOcrDocuments(
-            this.getSelectionQuery(),
-            dialog.template
-          )
-        )
-      })
-  }
-
   setPermissions() {
     let modal = this.modalService.open(PermissionsDialogComponent, {
       backdrop: 'static',

src-ui/src/app/components/manage/ocr-templates/ocr-template-editor/ocr-template-editor-zone-list/ocr-template-editor-zone-list.component.html

@@ -1,36 +0,0 @@
-@if (zones.length === 0) {
-  <p class="text-muted" i18n>No zones yet. Drag anywhere on the sample document to create one.</p>
-} @else {
-  <div class="list-group">
-    @for (zone of zones; track $index; let i = $index) {
-      <div class="list-group-item list-group-item-action d-flex align-items-center gap-3 position-relative">
-        <span class="p-2 rounded flex-shrink-0" [style.background-color]="zoneColor(i)" aria-hidden="true"></span>
-        <div class="flex-grow-1 text-truncate">
-          <button type="button" class="btn btn-link p-0 fw-semibold text-reset text-decoration-none text-truncate mw-100 stretched-link" (click)="zoneSelected.emit(i)">{{ zone.name }}</button>
-          @if (!hasField(zone)) {
-            <div class="small text-warning text-truncate">
-              <pngx-bs-icon name="exclamation-triangle" class="me-1" aria-hidden="true"></pngx-bs-icon><span i18n>No field selected</span>
-            </div>
-          } @else {
-            <div class="small text-muted text-truncate">
-              {{ getZoneTargetName(zone) }}
-              @if (isCombined(zone)) {
-                <pngx-bs-icon name="braces" class="ms-1" title="Combined with other zones" i18n-title></pngx-bs-icon>
-              }
-            </div>
-          }
-        </div>
-        <small class="text-muted text-nowrap">
-          @if (zone.page === -1) {
-            <ng-container i18n>Last page</ng-container>
-          } @else {
-            <ng-container i18n>Page {{ zone.page ?? 1 }}</ng-container>
-          }
-        </small>
-        <button type="button" class="btn btn-sm btn-link text-danger position-relative z-2" (click)="zoneRemoved.emit(i)" title="Delete zone" i18n-title aria-label="Delete zone" i18n-aria-label>
-          <pngx-bs-icon name="trash"></pngx-bs-icon>
-        </button>
-      </div>
-    }
-  </div>
-}

src-ui/src/app/components/manage/ocr-templates/ocr-template-editor/ocr-template-editor-zone-list/ocr-template-editor-zone-list.component.spec.ts

@@ -1,115 +0,0 @@
-import { ComponentFixture, TestBed } from '@angular/core/testing'
-import { BootstrapIconComponent } from 'src/app/components/common/bootstrap-icon/bootstrap-icon.component'
-import { CustomField } from 'src/app/data/custom-field'
-import {
-  OcrTemplateZone,
-  OcrZoneTarget,
-  OcrZoneTransform,
-} from 'src/app/data/ocr-template'
-import { OcrTemplateEditorZoneListComponent } from './ocr-template-editor-zone-list.component'
-
-function zone(overrides: Partial<OcrTemplateZone> = {}): OcrTemplateZone {
-  return {
-    name: 'Zone 1',
-    target: OcrZoneTarget.CustomField,
-    custom_field: 7,
-    x: 10,
-    y: 20,
-    width: 30,
-    height: 40,
-    page: 1,
-    ocr_language: 'eng',
-    transform: OcrZoneTransform.Strip,
-    validation_regex: '',
-    order: 0,
-    ...overrides,
-  }
-}
-
-describe('OcrTemplateEditorZoneListComponent', () => {
-  let fixture: ComponentFixture<OcrTemplateEditorZoneListComponent>
-  let component: OcrTemplateEditorZoneListComponent
-
-  beforeEach(async () => {
-    await TestBed.configureTestingModule({
-      imports: [OcrTemplateEditorZoneListComponent, BootstrapIconComponent],
-    }).compileComponents()
-
-    fixture = TestBed.createComponent(OcrTemplateEditorZoneListComponent)
-    component = fixture.componentInstance
-  })
-
-  it('shows empty state when no zones are defined', () => {
-    fixture.detectChanges()
-
-    expect(fixture.nativeElement.textContent).toContain('No zones yet')
-  })
-
-  it('renders zone name, target, and page', () => {
-    component.zones = [zone(), zone({ name: 'Zone 2', page: -1 })]
-    component.customFields = [{ id: 7, name: 'Invoice Number' } as CustomField]
-    fixture.detectChanges()
-
-    const text = fixture.nativeElement.textContent
-    expect(text).toContain('Zone 1')
-    expect(text).toContain('Invoice Number')
-    expect(text).toContain('Page 1')
-    expect(text).toContain('Last page')
-  })
-
-  it('marks zones that share a field', () => {
-    component.zones = [
-      zone(),
-      zone({ name: 'Zone 2' }),
-      zone({ name: 'Zone 3', custom_field: 8 }),
-    ]
-    fixture.detectChanges()
-
-    expect(component.isCombined(component.zones[0])).toBe(true)
-    expect(component.isCombined(component.zones[2])).toBe(false)
-    expect(
-      fixture.nativeElement.querySelectorAll(
-        '[title="Combined with other zones"]'
-      )
-    ).toHaveLength(2)
-  })
-
-  it('warns only for zones without a field and clears the warning when assigned', () => {
-    component.zones = [
-      zone({ custom_field: null }),
-      zone({ target: OcrZoneTarget.Title, custom_field: null }),
-      zone(),
-    ]
-    fixture.detectChanges()
-
-    const warnings = () =>
-      fixture.nativeElement.querySelectorAll('.text-warning')
-    expect(warnings()).toHaveLength(1)
-    expect(warnings()[0].textContent).toContain('No field selected')
-
-    component.zones[0].custom_field = 7
-    fixture.componentRef.setInput('zones', [...component.zones])
-    fixture.detectChanges()
-    expect(warnings()).toHaveLength(0)
-  })
-
-  it('emits select and remove events', () => {
-    component.zones = [zone()]
-    const selectSpy = jest.spyOn(component.zoneSelected, 'emit')
-    const removeSpy = jest.spyOn(component.zoneRemoved, 'emit')
-    fixture.detectChanges()
-
-    const buttons = fixture.nativeElement.querySelectorAll('button')
-    buttons[0].click()
-    buttons[1].click()
-
-    expect(selectSpy).toHaveBeenCalledWith(0)
-    expect(removeSpy).toHaveBeenCalledWith(0)
-  })
-
-  it('does not label an unknown built-in target', () => {
-    expect(
-      component.getZoneTargetName(zone({ target: 'unknown' as OcrZoneTarget }))
-    ).toBe('')
-  })
-})

src-ui/src/app/components/manage/ocr-templates/ocr-template-editor/ocr-template-editor-zone-list/ocr-template-editor-zone-list.component.ts

@@ -1,50 +0,0 @@
-import { Component, EventEmitter, Input, Output } from '@angular/core'
-import { BootstrapIconComponent } from 'src/app/components/common/bootstrap-icon/bootstrap-icon.component'
-import { CustomField } from 'src/app/data/custom-field'
-import {
-  getZoneFieldKey,
-  OCR_BUILTIN_TARGETS,
-  OcrTemplateZone,
-  OcrZoneTarget,
-} from 'src/app/data/ocr-template'
-import { getZoneColor } from '../zone-geometry'
-
-@Component({
-  selector: 'pngx-ocr-template-zone-list',
-  imports: [BootstrapIconComponent],
-  templateUrl: './ocr-template-editor-zone-list.component.html',
-})
-export class OcrTemplateEditorZoneListComponent {
-  @Input() zones: OcrTemplateZone[] = []
-  @Input() customFields: CustomField[] = []
-
-  @Output() public readonly zoneSelected = new EventEmitter<number>()
-  @Output() public readonly zoneRemoved = new EventEmitter<number>()
-
-  public readonly zoneColor = getZoneColor
-
-  hasField(zone: OcrTemplateZone): boolean {
-    return getZoneFieldKey(zone) !== null
-  }
-
-  isCombined(zone: OcrTemplateZone): boolean {
-    const key = getZoneFieldKey(zone)
-    return (
-      key !== null &&
-      this.zones.filter((z) => getZoneFieldKey(z) === key).length > 1
-    )
-  }
-
-  getZoneTargetName(zone: OcrTemplateZone): string {
-    if (zone.target === OcrZoneTarget.CustomField) {
-      return (
-        this.customFields.find((field) => field.id === zone.custom_field)
-          ?.name ?? ''
-      )
-    }
-    return (
-      OCR_BUILTIN_TARGETS.find((target) => target.id === zone.target)?.name ??
-      ''
-    )
-  }
-}

src-ui/src/app/components/manage/ocr-templates/ocr-template-editor/ocr-template-editor.component.html

@@ -1,313 +0,0 @@
-<div class="modal-header">
-  <h4 class="modal-title" id="ocr-template-editor-title">{{ dialogTitle }}</h4>
-  @if (template.id) {
-    <span class="badge bg-primary text-primary-text-contrast ms-2">ID: {{ template.id }}</span>
-  }
-  <button type="button" class="btn-close" (click)="activeModal.dismiss()" [disabled]="saving()" aria-label="Close" i18n-aria-label></button>
-</div>
-
-<div class="modal-body d-flex flex-column">
-  <div class="row gx-3 editor-layout flex-grow-1 flex-lg-nowrap" [attr.inert]="saving() ? '' : null" [attr.aria-busy]="saving()">
-    <div class="col-lg-4 mb-3 mb-lg-0 overflow-auto">
-      <ul ngbNav #nav="ngbNav" [(activeId)]="activeTab" class="nav-underline flex-nowrap flex-md-wrap overflow-auto">
-        <li ngbNavItem="template">
-          <a ngbNavLink i18n>Template</a>
-          <ng-template ngbNavContent>
-            <div class="row mb-3">
-              <div class="col-9">
-                <pngx-input-text [(ngModel)]="template.name" title="Template name" i18n-title></pngx-input-text>
-              </div>
-              <div class="col-3">
-                <pngx-input-switch [(ngModel)]="template.enabled" title="Enabled" i18n-title></pngx-input-switch>
-              </div>
-            </div>
-
-            <pngx-input-select [(ngModel)]="template.matching_algorithm" [items]="matchingAlgorithms" title="Matching algorithm" i18n-title></pngx-input-select>
-            @if (patternRequired) {
-              <pngx-input-text [(ngModel)]="template.match" title="Matching pattern" i18n-title></pngx-input-text>
-              <pngx-input-check [(ngModel)]="template.is_insensitive" title="Case insensitive" i18n-title></pngx-input-check>
-            }
-
-            <div *pngxIfOwner="object">
-              <hr />
-              <pngx-permissions-form [users]="users()" [accordion]="true" [(ngModel)]="permissionsForm"></pngx-permissions-form>
-            </div>
-
-          </ng-template>
-        </li>
-
-        <li ngbNavItem="zones">
-          <a ngbNavLink><ng-container i18n>Zones</ng-container> <span class="badge bg-primary ms-2">{{ template.zones.length }}</span></a>
-          <ng-template ngbNavContent>
-            @if (selectedZone; as zone) {
-              <div class="d-flex align-items-center gap-2 mb-3">
-                <button type="button" class="btn btn-sm btn-link px-0 me-auto" (click)="deselectZone()">
-                  <pngx-bs-icon name="arrow-left" class="me-1"></pngx-bs-icon><ng-container i18n>All zones</ng-container>
-                </button>
-                <button type="button" class="btn btn-sm btn-outline-primary" (click)="testZone()" [disabled]="!previewDocId || zoneTesting">
-                  @if (zoneTesting) {
-                    <span class="spinner-border spinner-border-sm me-1" aria-hidden="true"></span>
-                  } @else {
-                    <pngx-bs-icon name="play-fill" class="me-1"></pngx-bs-icon>
-                  }
-                  <ng-container i18n>Test</ng-container>
-                </button>
-                <button type="button" class="btn btn-sm btn-outline-danger" (click)="removeZone(selectedZoneIndex)" title="Delete zone" i18n-title aria-label="Delete zone" i18n-aria-label>
-                  <pngx-bs-icon name="trash"></pngx-bs-icon>
-                </button>
-              </div>
-
-              @if (zoneTestResult; as result) {
-                @if (result.error) {
-                  <div class="alert alert-warning py-2 mb-3 small" role="alert">{{ result.error }}</div>
-                } @else {
-                  <dl class="row small border rounded mx-0 py-2 mb-3">
-                    <dt class="col-4" i18n>OCR text</dt>
-                    <dd class="col-8">
-                      @if (result.raw_text) {
-                        <code>{{ result.raw_text }}</code>
-                      } @else {
-                        <span class="text-muted" i18n>Nothing detected</span>
-                      }
-                    </dd>
-                    <dt class="col-4" i18n>Value</dt>
-                    <dd class="col-8" [class.mb-0]="!result.regex">
-                      @if (result.value) {
-                        <code>{{ result.value }}</code>
-                      } @else {
-                        <span class="text-muted" i18n>Empty</span>
-                      }
-                    </dd>
-                    @if (result.regex) {
-                      <dt class="col-4" i18n>Validation</dt>
-                      <dd class="col-8 mb-0">
-                        @if (result.regex_match) {
-                          <span class="badge bg-success" i18n>Regex matches</span>
-                        } @else {
-                          <span class="badge bg-danger" i18n>Regex does not match</span>
-                        }
-                      </dd>
-                    }
-                  </dl>
-                }
-              }
-
-              <pngx-input-text [ngModel]="zone.name" (ngModelChange)="renameZone(zone, $event)" title="Name" i18n-title></pngx-input-text>
-
-              <pngx-input-select
-                [items]="fieldItems()"
-                [ngModel]="zoneFieldValue(zone)"
-                (ngModelChange)="setZoneField(zone, $event)"
-                (createNew)="createField($event)"
-                title="Field"
-                i18n-title
-                placeholder="Choose a field"
-                i18n-placeholder
-                hint="Where the extracted value is written."
-                i18n-hint
-              ></pngx-input-select>
-
-              @if (isFieldShared(zone)) {
-                <pngx-input-text
-                  [ngModel]="getCombineFormat(zone)"
-                  (ngModelChange)="setCombineFormat(zone, $event)"
-                  [placeholder]="defaultCombineFormat(zone)"
-                  title="Combined value"
-                  i18n-title
-                  hint="Several zones write to this field. Set the format or leave empty to join them with spaces."
-                  i18n-hint
-                ></pngx-input-text>
-                <div class="d-flex flex-wrap gap-1 mt-n2 mb-3">
-                  @for (z of zonesForField(zone); track z) {
-                    <button type="button" class="btn btn-sm btn-outline-secondary font-monospace" (click)="insertCombineToken(zone, z)">{{ '{' + z.name + '}' }}</button>
-                  }
-                </div>
-              }
-
-              <div class="row align-items-end">
-                <div class="col">
-                  @if (!isLastPageZone(zone)) {
-                    <pngx-input-number [(ngModel)]="zone.page" [showAdd]="false" title="Page" i18n-title></pngx-input-number>
-                  }
-                </div>
-                <div class="col-auto">
-                  <pngx-input-switch [ngModel]="isLastPageZone(zone)" (ngModelChange)="setLastPageZone(zone, $event)" [horizontal]="true" title="Last page" i18n-title></pngx-input-switch>
-                </div>
-              </div>
-
-              <h6 class="border-top pt-3 mt-1 mb-3" i18n>Processing</h6>
-
-              <pngx-input-select
-                [items]="languageOptions"
-                [multiple]="true"
-                [ngModel]="ocrLanguageArray(zone)"
-                (ngModelChange)="setOcrLanguages(zone, $event)"
-                title="OCR language"
-                i18n-title
-                placeholder="Select languages"
-                i18n-placeholder
-              ></pngx-input-select>
-
-              <pngx-input-select [items]="transformOptions" [(ngModel)]="zone.transform" title="Transform" i18n-title></pngx-input-select>
-
-              @if (zone.transform === OcrZoneTransform.Date) {
-                <pngx-input-text
-                  [(ngModel)]="zone.date_format"
-                  title="Date format"
-                  i18n-title
-                  placeholder="Auto-detect"
-                  i18n-placeholder
-                  hint="Python date codes, e.g. %d.%m.%Y. Leave empty to detect the format automatically."
-                  i18n-hint
-                ></pngx-input-text>
-              }
-
-              <pngx-input-text [(ngModel)]="zone.validation_regex" title="Validation regex" i18n-title placeholder="\d{2}\.\d{2}\.\d{4}" hint="The value must match this pattern to be applied." i18n-hint></pngx-input-text>
-            } @else {
-              <pngx-ocr-template-zone-list
-                [zones]="template.zones"
-                [customFields]="customFields()"
-                (zoneSelected)="selectZone($event)"
-                (zoneRemoved)="removeZone($event)"
-              ></pngx-ocr-template-zone-list>
-            }
-          </ng-template>
-        </li>
-      </ul>
-
-      <div [ngbNavOutlet]="nav" class="mt-3"></div>
-    </div>
-
-    <div class="col-lg-8 d-flex flex-column">
-      <div class="d-flex flex-wrap gap-2 mb-2 flex-shrink-0">
-        <pngx-input-document-link
-          class="flex-grow-1"
-          [ngModel]="sampleDocumentIds"
-          (ngModelChange)="setSampleDocument($event)"
-          [minimal]="true"
-          [multiple]="false"
-          placeholder="Search for a sample document"
-          i18n-placeholder
-        ></pngx-input-document-link>
-        @if (previewDocId) {
-          <div class="input-group w-auto flex-nowrap">
-            <input class="form-control flex-grow-0 preview-page-input" type="number" min="1" [max]="previewPageCount()" [(ngModel)]="previewPageDisplay" [disabled]="!pageLoaded()" aria-label="Page" i18n-aria-label />
-            <span class="input-group-text" i18n>of {{ previewPageCount() ?? '?' }}</span>
-          </div>
-          <fieldset class="input-group w-auto flex-nowrap" aria-label="Zoom" i18n-aria-label>
-            <button type="button" class="btn btn-outline-secondary" aria-label="Zoom out" i18n-aria-label [disabled]="!pageLoaded() || zoom <= 0.5" (click)="zoomOut()"><pngx-bs-icon name="dash"></pngx-bs-icon></button>
-            <button type="button" class="btn btn-outline-secondary preview-zoom" title="Reset zoom" i18n-title [disabled]="!pageLoaded()" (click)="resetZoom()">{{ zoom | percent: '1.0-0' }}</button>
-            <button type="button" class="btn btn-outline-secondary" aria-label="Zoom in" i18n-aria-label [disabled]="!pageLoaded() || zoom >= 4" (click)="zoomIn()"><pngx-bs-icon name="plus"></pngx-bs-icon></button>
-          </fieldset>
-        }
-      </div>
-      <div class="flex-grow-1 overflow-hidden">
-        <div class="h-100 overflow-auto border" [attr.aria-busy]="previewDocId && !pageLoaded()">
-          @if (pageFailed()) {
-            <div class="py-5 px-3 text-center" role="alert">
-              <pngx-bs-icon name="exclamation-triangle" width="32" height="32" class="text-warning"></pngx-bs-icon>
-              <p class="my-3" i18n>Could not load this page.</p>
-              <button type="button" class="btn btn-sm btn-outline-secondary" (click)="setSampleDocument(sampleDocumentIds)"><pngx-bs-icon name="arrow-clockwise" class="me-1"></pngx-bs-icon><span i18n>Retry</span></button>
-            </div>
-          } @else if (previewDocId) {
-            <div class="position-relative" [class.d-none]="!pageLoaded()" [style.width.%]="zoom * 100">
-              <img
-                #pageImage
-                [src]="pageImageUrl"
-                (load)="onImageLoad()"
-                (error)="onImageError()"
-                alt="Sample document page"
-                i18n-alt
-                class="d-block w-100"
-                crossorigin="use-credentials"
-              />
-              @if (pageLoaded()) {
-                <svg
-                  #zoneOverlay
-                  class="zone-overlay position-absolute top-0 start-0 w-100 h-100"
-                  [attr.viewBox]="overlayViewBox()"
-                  preserveAspectRatio="none"
-                  [style.cursor]="overlayCursor"
-                  (pointerdown)="onOverlayPointerDown($event)"
-                  (pointermove)="onOverlayPointerMove($event)"
-                  (pointerup)="onOverlayPointerUp($event)"
-                  (pointercancel)="onOverlayPointerCancel($event)"
-                  (lostpointercapture)="onOverlayPointerCancel($event)"
-                  aria-label="Zone overlay" i18n-aria-label
-                >
-                  @for (zone of template.zones; track $index; let i = $index) {
-                    @if (zoneDisplayRect(i); as rect) {
-                      <g>
-                        <rect
-                          class="zone-rect"
-                          [class.zone-rect-selected]="selectedZoneIndex === i"
-                          [attr.x]="rect.x"
-                          [attr.y]="rect.y"
-                          [attr.width]="rect.w"
-                          [attr.height]="rect.h"
-                          [attr.stroke]="zoneColor(i)"
-                          [attr.fill]="zoneColor(i)"
-                        ></rect>
-                        <text
-                          class="zone-label fw-semibold pe-none"
-                          [attr.x]="rect.x + overlayUnitSize(6)"
-                          [attr.y]="zoneLabelY(rect)"
-                          [attr.font-size]="overlayFontSize()"
-                          [attr.fill]="zoneColor(i)"
-                        >{{ zoneLabel(zone, i) }}</text>
-
-                        @if (selectedZoneIndex === i) {
-                          @for (handle of resizeHandles(rect); track handle.handle) {
-                            <rect
-                              class="zone-resize-handle"
-                              [attr.x]="handle.x - overlayHandleSize() / 2"
-                              [attr.y]="handle.y - overlayHandleSize() / 2"
-                              [attr.width]="overlayHandleSize()"
-                              [attr.height]="overlayHandleSize()"
-                              [attr.fill]="zoneColor(i)"
-                            ></rect>
-                          }
-                        }
-                      </g>
-                    }
-                  }
-
-                  @if (drawingRect(); as rect) {
-                    <rect
-                      class="zone-drawing-rect"
-                      [attr.x]="rect.x"
-                      [attr.y]="rect.y"
-                      [attr.width]="rect.w"
-                      [attr.height]="rect.h"
-                    ></rect>
-                  }
-                </svg>
-              }
-            </div>
-            @if (!pageLoaded()) {
-              <div class="p-5 d-flex justify-content-center align-items-center">
-                <output class="spinner-border">
-                  <span class="visually-hidden" i18n>Loading page...</span>
-                </output>
-              </div>
-            }
-          } @else {
-            <div class="py-5 px-3 text-center text-muted">
-              <pngx-bs-icon name="file-text" width="32" height="32"></pngx-bs-icon>
-              <p class="mt-3 mb-0" i18n>No sample document selected.</p>
-            </div>
-          }
-        </div>
-      </div>
-    </div>
-  </div>
-</div>
-<div class="modal-footer">
-  <button type="button" class="btn btn-outline-secondary" (click)="activeModal.dismiss()" [disabled]="saving()" i18n>Cancel</button>
-  <button type="button" class="btn btn-primary" (click)="save()" [disabled]="saving() || !isDirty">
-    @if (saving()) {
-      <span class="spinner-border spinner-border-sm me-1" aria-hidden="true"></span>
-    }
-    <span i18n>Save</span>
-  </button>
-</div>

src-ui/src/app/components/manage/ocr-templates/ocr-template-editor/ocr-template-editor.component.scss

@@ -1,64 +0,0 @@
-:host {
-  display: flex;
-  flex-direction: column;
-  min-height: 0;
-}
-
-@media (min-width: 992px) {
-  .modal-body {
-    overflow: hidden;
-  }
-
-  .editor-layout {
-    min-height: 0;
-  }
-}
-
-.preview-page-input {
-  width: 3.5rem;
-}
-
-.preview-zoom {
-  min-width: 4rem;
-}
-
-.zone-overlay {
-  touch-action: none;
-}
-
-.zone-rect,
-.zone-drawing-rect {
-  vector-effect: non-scaling-stroke;
-}
-
-.zone-rect {
-  fill-opacity: 0.2;
-  stroke-width: 2;
-}
-
-.zone-rect-selected {
-  stroke-width: 3;
-}
-
-.zone-label {
-  font-family: var(--bs-font-sans-serif);
-  paint-order: stroke;
-  stroke: #fff;
-  stroke-linejoin: round;
-  stroke-width: 4px;
-  vector-effect: non-scaling-stroke;
-}
-
-.zone-resize-handle {
-  stroke: #fff;
-  stroke-width: 1;
-  vector-effect: non-scaling-stroke;
-}
-
-.zone-drawing-rect {
-  fill: var(--bs-primary);
-  fill-opacity: 0.2;
-  stroke: var(--bs-primary);
-  stroke-dasharray: 5 5;
-  stroke-width: 2;
-}

src-ui/src/app/components/manage/ocr-templates/ocr-template-editor/ocr-template-editor.component.spec.ts

@@ -1,875 +0,0 @@
-import { provideHttpClient, withInterceptorsFromDi } from '@angular/common/http'
-import { provideHttpClientTesting } from '@angular/common/http/testing'
-import { ElementRef } from '@angular/core'
-import { ComponentFixture, TestBed } from '@angular/core/testing'
-import { By } from '@angular/platform-browser'
-import { NgbActiveModal, NgbModal } from '@ng-bootstrap/ng-bootstrap'
-import { BootstrapIconComponent } from 'src/app/components/common/bootstrap-icon/bootstrap-icon.component'
-import { of, Subject, throwError } from 'rxjs'
-import { PermissionsFormComponent } from 'src/app/components/common/input/permissions/permissions-form/permissions-form.component'
-import { CustomField, CustomFieldDataType } from 'src/app/data/custom-field'
-import { Document } from 'src/app/data/document'
-import {
-  MATCH_ANY,
-  MATCH_AUTO,
-  MATCH_LITERAL,
-  MATCH_NONE,
-} from 'src/app/data/matching-model'
-import {
-  OcrTemplate,
-  OcrTemplateZone,
-  OcrZoneTarget,
-  OcrZoneTestResult,
-  OcrZoneTransform,
-} from 'src/app/data/ocr-template'
-import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
-import { User } from 'src/app/data/user'
-import { PermissionsService } from 'src/app/services/permissions.service'
-import { CustomFieldsService } from 'src/app/services/rest/custom-fields.service'
-import { DocumentService } from 'src/app/services/rest/document.service'
-import { OcrTemplateService } from 'src/app/services/rest/ocr-template.service'
-import { UserService } from 'src/app/services/rest/user.service'
-import { SettingsService } from 'src/app/services/settings.service'
-import { ToastService } from 'src/app/services/toast.service'
-import { OcrTemplateEditorComponent } from './ocr-template-editor.component'
-
-const customFields: CustomField[] = [
-  { id: 1, name: 'Invoice number', data_type: CustomFieldDataType.String },
-  { id: 2, name: 'Status', data_type: CustomFieldDataType.Select },
-]
-
-function zone(overrides: Partial<OcrTemplateZone> = {}): OcrTemplateZone {
-  return {
-    name: 'Invoice number',
-    target: OcrZoneTarget.CustomField,
-    custom_field: 1,
-    x: 100,
-    y: 100,
-    width: 200,
-    height: 100,
-    page: 1,
-    ocr_language: 'eng',
-    transform: OcrZoneTransform.Strip,
-    validation_regex: '',
-    order: 0,
-    ...overrides,
-  }
-}
-
-function pointer(x: number, y: number, pointerId = 1): PointerEvent {
-  return Object.assign(
-    new MouseEvent('pointermove', { clientX: x, clientY: y, button: 0 }),
-    { pointerId }
-  ) as PointerEvent
-}
-
-describe('OcrTemplateEditorComponent', () => {
-  let component: OcrTemplateEditorComponent
-  let fixture: ComponentFixture<OcrTemplateEditorComponent>
-  let documentService: DocumentService
-  let templateService: OcrTemplateService
-  let modalService: NgbModal
-  const activeModal = { close: jest.fn(), dismiss: jest.fn() }
-
-  beforeEach(() => {
-    TestBed.configureTestingModule({
-      imports: [BootstrapIconComponent, OcrTemplateEditorComponent],
-      providers: [
-        { provide: NgbActiveModal, useValue: activeModal },
-        provideHttpClient(withInterceptorsFromDi()),
-        provideHttpClientTesting(),
-      ],
-    })
-    jest
-      .spyOn(TestBed.inject(CustomFieldsService), 'listAll')
-      .mockReturnValue(of({ count: 2, all: [1, 2], results: customFields }))
-    jest
-      .spyOn(TestBed.inject(UserService), 'listAll')
-      .mockReturnValue(of({ count: 0, all: [], results: [] }))
-    TestBed.inject(PermissionsService).initialize([], { id: 1 } as User)
-    documentService = TestBed.inject(DocumentService)
-    jest
-      .spyOn(documentService, 'get')
-      .mockReturnValue(of({ id: 5, page_count: 3 }))
-    templateService = TestBed.inject(OcrTemplateService)
-    modalService = TestBed.inject(NgbModal)
-    activeModal.close.mockReset()
-    fixture = TestBed.createComponent(OcrTemplateEditorComponent)
-    component = fixture.componentInstance
-  })
-
-  function prepareOverlay() {
-    const image = document.createElement('img')
-    Object.defineProperties(image, {
-      naturalWidth: { value: 1000 },
-      naturalHeight: { value: 1000 },
-      clientWidth: { value: 1000 },
-    })
-    const overlay = document.createElementNS(
-      'http://www.w3.org/2000/svg',
-      'svg'
-    )
-    Object.assign(overlay, {
-      getScreenCTM: () => ({ inverse: () => ({}) }),
-      createSVGPoint: () => ({
-        x: 0,
-        y: 0,
-        matrixTransform() {
-          return { x: this.x, y: this.y }
-        },
-      }),
-      setPointerCapture: jest.fn(),
-      hasPointerCapture: () => true,
-      releasePointerCapture: jest.fn(),
-    })
-    component.imageRef = new ElementRef(image)
-    component.overlayRef = new ElementRef(overlay)
-    component.pageLoaded.set(true)
-  }
-
-  function fieldDialog() {
-    const dialog = {
-      dialogMode: { set: jest.fn() },
-      object: null,
-      succeeded: new Subject<CustomField>(),
-      failed: new Subject(),
-    }
-    jest
-      .spyOn(modalService, 'open')
-      .mockReturnValue({ componentInstance: dialog } as any)
-    return dialog
-  }
-
-  it('updates screen-sized overlay units when the preview image resizes', () => {
-    let resize: ResizeObserverCallback
-    const observer = {
-      observe: jest.fn(),
-      unobserve: jest.fn(),
-      disconnect: jest.fn(),
-    }
-    const resizeObserver = jest
-      .spyOn(globalThis, 'ResizeObserver')
-      .mockImplementation((callback) => {
-        resize = callback
-        return observer
-      })
-    const image = document.createElement('img')
-    const ref = new ElementRef(image)
-    component.pageImage = ref
-    expect(observer.observe).toHaveBeenCalledWith(image)
-    resize([], observer)
-    expect(component.overlayUnitSize(8)).toBe(8)
-
-    Object.defineProperties(image, {
-      naturalWidth: { value: 1000 },
-      clientWidth: { value: 500 },
-    })
-    resize([], observer)
-    expect(component.overlayUnitSize(8)).toBe(16)
-    expect(component.overlayFontSize()).toBe(24)
-
-    component.pageImage = undefined
-    expect(observer.disconnect).toHaveBeenCalledTimes(1)
-    fixture.destroy()
-    expect(observer.disconnect).toHaveBeenCalledTimes(2)
-    resizeObserver.mockRestore()
-  })
-
-  it('renders loaded image dimensions, zone labels, and selection handles', () => {
-    component.object = {
-      ...component.template,
-      id: 3,
-      sample_document: 5,
-      zones: [zone()],
-    }
-    component.selectedZoneIndex = 0
-    fixture.detectChanges()
-    const image = fixture.nativeElement.querySelector('img')
-    Object.defineProperties(image, {
-      naturalWidth: { value: 1000 },
-      naturalHeight: { value: 1500 },
-    })
-    image.dispatchEvent(new Event('load'))
-    fixture.detectChanges()
-
-    expect(component.template).toMatchObject({
-      source_width: 1000,
-      source_height: 1500,
-    })
-    expect(
-      fixture.nativeElement
-        .querySelector('.zone-overlay')
-        .getAttribute('viewBox')
-    ).toBe('0 0 1000 1500')
-    expect(
-      fixture.nativeElement.querySelector('.zone-label').textContent
-    ).toContain('Invoice number')
-    expect(
-      fixture.nativeElement.querySelectorAll('.zone-resize-handle')
-    ).toHaveLength(8)
-    expect(component.zoneLabel(zone({ name: '' }), 2)).toBe('Zone 3')
-    expect(component.zoneLabelY({ x: 0, y: 0, w: 100, h: 100 })).toBe(14)
-  })
-
-  it('offers the supported language and transform choices', () => {
-    expect(component.languageOptions.map((option) => option.id)).toContain(
-      'eng'
-    )
-    expect(component.transformOptions.map((option) => option.id)).toEqual(
-      Object.values(OcrZoneTransform)
-    )
-  })
-
-  it('clamps page navigation and supports one-based page input', () => {
-    component.setSampleDocument([5])
-    component.previewPageDisplay = 2
-    expect(component.previewPage).toBe(1)
-    expect(component.previewPageDisplay).toBe(2)
-    expect(component.pageImageUrl).toContain('/5/1/')
-    component.pageLoaded.set(true)
-    component.goToPage(1)
-    expect(component.pageLoaded()).toBe(true)
-    component.goToPage(Infinity)
-    component.goToPage(NaN)
-    expect(component.previewPage).toBe(1)
-    component.goToPage(99)
-    expect(component.previewPage).toBe(2)
-    expect(component.pageLoaded()).toBe(false)
-    component.goToPage(-5)
-    expect(component.previewPage).toBe(0)
-    component.previewPageCount.set(null)
-    component.goToPage(4.7)
-    expect(component.previewPage).toBe(4)
-  })
-
-  it('limits zoom and resets it to the original size', () => {
-    for (let i = 0; i < 20; i++) component.zoomIn()
-    expect(component.zoom).toBe(4)
-    for (let i = 0; i < 20; i++) component.zoomOut()
-    expect(component.zoom).toBe(0.5)
-    component.resetZoom()
-    expect(component.zoom).toBe(1)
-  })
-
-  it('moves last-page zones to the last page and can pin them to a page', () => {
-    component.setSampleDocument([5])
-    const selected = zone()
-    component.template.zones = [selected]
-    expect(component.isLastPageZone(selected)).toBe(false)
-    component.setLastPageZone(selected, true)
-    expect(selected.page).toBe(-1)
-    expect(component.isLastPageZone(selected)).toBe(true)
-    component.selectZone(0)
-    expect(component.previewPage).toBe(2)
-    component.setLastPageZone(selected, false)
-    expect(selected.page).toBe(3)
-  })
-
-  it('ignores page-count errors from a previous sample document', () => {
-    const pending = new Subject<Document>()
-    jest
-      .spyOn(documentService, 'get')
-      .mockReturnValueOnce(pending)
-      .mockReturnValueOnce(of({ id: 6 }))
-    component.setSampleDocument([5])
-    component.setSampleDocument([6])
-    pending.error(new Error('Old document failed'))
-    expect(component.pageFailed()).toBe(false)
-    expect(component.previewPageCount()).toBeNull()
-  })
-
-  it('ignores non-primary, unloaded, and saving pointer gestures', () => {
-    prepareOverlay()
-    component.onOverlayPointerDown(
-      new MouseEvent('pointerdown', { button: 2 }) as PointerEvent
-    )
-    expect(component.drawingRect()).toBeNull()
-    component.pageLoaded.set(false)
-    component.onOverlayPointerDown(pointer(100, 100))
-    expect(component.drawingRect()).toBeNull()
-    component.pageLoaded.set(true)
-    component.saving.set(true)
-    component.onOverlayPointerDown(pointer(100, 100))
-    expect(component.drawingRect()).toBeNull()
-  })
-
-  it('ignores pointer events when the SVG coordinate transform is unavailable', () => {
-    component.onOverlayPointerDown(pointer(100, 100))
-    expect(component.drawingRect()).toBeNull()
-    prepareOverlay()
-    jest
-      .spyOn(component.overlayRef.nativeElement, 'getScreenCTM')
-      .mockReturnValue(null)
-    component.onOverlayPointerDown(pointer(100, 100))
-    component.onOverlayPointerMove(pointer(200, 200))
-    expect(component.drawingRect()).toBeNull()
-  })
-
-  it('updates a drawing only for its captured pointer', () => {
-    prepareOverlay()
-    component.onOverlayPointerDown(pointer(100, 100))
-    component.onOverlayPointerDown(pointer(500, 500, 2))
-    component.onOverlayPointerMove(pointer(900, 900, 2))
-    expect(component.drawingRect()).toEqual({ x: 100, y: 100, w: 0, h: 0 })
-    component.onOverlayPointerMove(pointer(250, 200))
-    expect(component.drawingRect()).toEqual({ x: 100, y: 100, w: 150, h: 100 })
-    component.onOverlayPointerUp(pointer(250, 200))
-    expect(component.template.zones[0]).toMatchObject({
-      x: 100,
-      y: 100,
-      width: 150,
-      height: 100,
-    })
-  })
-
-  it('resizes a selected zone using its corner handle', () => {
-    prepareOverlay()
-    const selected = zone()
-    component.template.zones = [selected]
-    component.selectZone(0)
-    component.onOverlayPointerDown(pointer(100, 100))
-    component.onOverlayPointerMove(pointer(50, 75))
-    component.onOverlayPointerUp(pointer(60, 80))
-    expect(selected).toMatchObject({ x: 60, y: 80, width: 240, height: 120 })
-    expect(component.template.zones).toHaveLength(1)
-  })
-
-  it('shows the appropriate cursor over handles, zones, and empty space', () => {
-    prepareOverlay()
-    component.template.zones = [zone()]
-    component.onOverlayPointerMove(pointer(150, 150))
-    expect(component.overlayCursor).toBe('move')
-    component.selectZone(0)
-    component.onOverlayPointerMove(pointer(100, 100))
-    expect(component.overlayCursor).toBe('nw-resize')
-    component.onOverlayPointerMove(pointer(500, 500))
-    expect(component.overlayCursor).toBe('crosshair')
-    component.template.zones[0].page = 2
-    component.onOverlayPointerMove(pointer(100, 100))
-    expect(component.zoneDisplayRect(0)).toBeNull()
-    expect(component.overlayCursor).toBe('crosshair')
-  })
-
-  it('cancels only the captured pointer and tolerates an already-lost capture', () => {
-    prepareOverlay()
-    component.onOverlayPointerCancel(pointer(100, 100))
-    component.onOverlayPointerDown(pointer(100, 100))
-    component.onOverlayPointerCancel(pointer(150, 150, 2))
-    expect(component.drawingRect()).not.toBeNull()
-    jest
-      .spyOn(component.overlayRef.nativeElement, 'hasPointerCapture')
-      .mockReturnValue(false)
-    component.onOverlayPointerCancel(pointer(150, 150))
-    expect(component.drawingRect()).toBeNull()
-    expect(
-      component.overlayRef.nativeElement.releasePointerCapture
-    ).not.toHaveBeenCalled()
-    expect(component.template.zones).toEqual([])
-  })
-
-  it('preserves the selected zone when an earlier or later zone is removed', () => {
-    component.template.zones = [zone(), zone(), zone(), zone()]
-    component.selectZone(1)
-    const selected = component.selectedZone
-    component.removeZone(3)
-    expect(component.selectedZone).toBe(selected)
-    component.removeZone(0)
-    expect(component.selectedZoneIndex).toBe(0)
-    expect(component.selectedZone).toBe(selected)
-    component.selectZone(99)
-    expect(component.selectedZone).toBeNull()
-  })
-
-  it('does not test zones without a selection or a sample document', () => {
-    const test = jest.spyOn(templateService, 'testZone')
-    component.testZone()
-    component.template.zones = [zone()]
-    component.selectZone(0)
-    component.testZone()
-    expect(test).not.toHaveBeenCalled()
-  })
-
-  it.each([
-    {
-      response: { error: { error: 'OCR unavailable' } },
-      message: 'OCR unavailable',
-    },
-    { response: new Error('Network failure'), message: 'Test failed' },
-  ])('shows zone-test errors: $message', ({ response, message }) => {
-    component.template.zones = [zone({ page: undefined })]
-    component.selectZone(0)
-    component.setSampleDocument([5])
-    jest
-      .spyOn(templateService, 'testZone')
-      .mockReturnValue(throwError(() => response))
-    component.testZone()
-    expect(component.zoneTestResult).toEqual({ error: message })
-    expect(component.zoneTesting).toBe(false)
-    expect(templateService.testZone).toHaveBeenCalledWith(
-      5,
-      expect.objectContaining({ page: 1 })
-    )
-  })
-
-  it('switches between built-in targets, custom fields, and an unassigned field', () => {
-    const selected = zone()
-    expect(component.zoneFieldValue(selected)).toBe(1)
-    component.setZoneField(selected, OcrZoneTarget.Title)
-    expect(component.zoneFieldValue(selected)).toBe(OcrZoneTarget.Title)
-    expect(selected.custom_field).toBeNull()
-    component.setZoneField(selected, 7)
-    expect(selected).toMatchObject({
-      target: OcrZoneTarget.CustomField,
-      custom_field: 7,
-    })
-    component.setZoneField(selected, null)
-    expect(component.zoneFieldValue(selected)).toBeNull()
-    expect(component.zonesForField(selected)).toEqual([])
-    component.setCombineFormat(selected, 'Ignored')
-    expect(component.template.combine_formats).toEqual({})
-  })
-
-  it('creates combine formats when absent and leaves implicit formats alone on rename', () => {
-    const selected = zone({ target: OcrZoneTarget.Title, custom_field: null })
-    component.template.combine_formats = undefined
-    component.renameZone(selected, 'Renamed')
-    expect(selected.name).toBe('Renamed')
-    expect(component.getCombineFormat(selected)).toBe('')
-    component.setCombineFormat(selected, '{Renamed} ')
-    component.insertCombineToken(selected, selected)
-    expect(component.template.combine_formats).toEqual({
-      title: '{Renamed} {Renamed}',
-    })
-  })
-
-  it('saves templates without combine formats', () => {
-    component.template.combine_formats = undefined
-    fixture.detectChanges()
-    expect(component.isDirty).toBe(false)
-    jest
-      .spyOn(templateService, 'create')
-      .mockReturnValue(of(component.template))
-    component.save()
-    expect(component.template.combine_formats).toBeUndefined()
-  })
-
-  it('does not assign unsupported custom field types and surfaces creation failures', () => {
-    component.template.zones = [zone({ custom_field: null })]
-    component.selectZone(0)
-    const dialog = fieldDialog()
-    const error = jest.spyOn(TestBed.inject(ToastService), 'showError')
-    component.createField('Status')
-    expect(dialog.object).toEqual({ name: 'Status' })
-    dialog.succeeded.next(customFields[1])
-    expect(component.selectedZone.custom_field).toBeNull()
-    const failure = new Error('Could not save')
-    dialog.failed.next(failure)
-    expect(error).toHaveBeenCalledWith('Error saving field.', failure)
-  })
-
-  it('refreshes field choices when a field is created without a selected zone', () => {
-    const dialog = fieldDialog()
-    component.createField('Total')
-    dialog.succeeded.next(customFields[0])
-    expect(component.customFields()).toEqual(customFields)
-    expect(component.selectedZone).toBeNull()
-  })
-
-  it('should edit a copy of the template and load its sample document', () => {
-    const original: OcrTemplate = {
-      ...component.template,
-      id: 3,
-      name: 'Invoices',
-      match: 'Northwind',
-      matching_algorithm: MATCH_LITERAL,
-      sample_document: 5,
-      zones: [zone()],
-      combine_formats: { '1': '{Invoice number}' },
-    }
-    component.object = original
-    fixture.detectChanges()
-
-    expect(component.dialogTitle).toEqual('Edit OCR Template')
-    expect(component.previewDocId).toEqual(5)
-    expect(component.previewPageCount()).toEqual(3)
-    expect(component.pageImageUrl).toContain('document-page-image/5/0/')
-    expect(component.template.match).toEqual('Northwind')
-    expect(component.isDirty).toBeFalsy()
-
-    component.template.zones[0].x = 500
-    component.template.combine_formats['1'] = 'Edited'
-    expect(original.zones[0].x).toEqual(100)
-    expect(original.combine_formats['1']).toEqual('{Invoice number}')
-  })
-
-  it('should offer every matching algorithm except automatic', () => {
-    expect(component.matchingAlgorithms.map((a) => a.id)).not.toContain(
-      MATCH_AUTO
-    )
-    expect(component.template.matching_algorithm).toEqual(MATCH_ANY)
-    expect(component.patternRequired).toBeTruthy()
-
-    component.template.matching_algorithm = MATCH_NONE
-    expect(component.patternRequired).toBeFalsy()
-  })
-
-  it('should initialize new template permissions from saved defaults', () => {
-    const defaults = {
-      [SETTINGS_KEYS.DEFAULT_PERMS_OWNER]: 1,
-      [SETTINGS_KEYS.DEFAULT_PERMS_VIEW_USERS]: [2],
-      [SETTINGS_KEYS.DEFAULT_PERMS_VIEW_GROUPS]: [3],
-      [SETTINGS_KEYS.DEFAULT_PERMS_EDIT_USERS]: [],
-      [SETTINGS_KEYS.DEFAULT_PERMS_EDIT_GROUPS]: [4],
-    }
-    jest
-      .spyOn(TestBed.inject(SettingsService), 'get')
-      .mockImplementation((key) => defaults[key])
-    fixture.detectChanges()
-    expect(component.permissionsForm).toEqual({
-      owner: 1,
-      set_permissions: {
-        view: { users: [2], groups: [3] },
-        change: { users: [], groups: [4] },
-      },
-    })
-    expect(
-      fixture.debugElement.query(By.directive(PermissionsFormComponent))
-    ).toBeTruthy()
-    expect(component.isDirty).toBe(false)
-    const create = jest
-      .spyOn(templateService, 'create')
-      .mockReturnValue(of({ ...component.template, id: 3 }))
-    component.save()
-    expect(create).toHaveBeenCalledWith(
-      expect.objectContaining(component.permissionsForm)
-    )
-  })
-
-  it('should copy existing permissions and track changes without mutating the list item', () => {
-    component.object = {
-      ...component.template,
-      id: 3,
-      owner: 1,
-      permissions: {
-        view: { users: [2], groups: [] },
-        change: { users: [], groups: [3] },
-      },
-    }
-    fixture.detectChanges()
-    expect(component.permissionsForm.owner).toBe(1)
-    expect(component.isDirty).toBe(false)
-    component.permissionsForm.set_permissions.view.users.push(4)
-    expect(component.isDirty).toBe(true)
-    expect(component.object.permissions.view.users).toEqual([2])
-    const update = jest
-      .spyOn(templateService, 'update')
-      .mockReturnValue(of(component.template))
-    component.save()
-    expect(update).toHaveBeenCalledWith(
-      expect.objectContaining({
-        owner: 1,
-        set_permissions: {
-          view: { users: [2, 4], groups: [] },
-          change: { users: [], groups: [3] },
-        },
-      })
-    )
-  })
-
-  it('should hide sharing controls and omit permission changes for a shared editor', () => {
-    component.object = {
-      ...component.template,
-      id: 3,
-      owner: 2,
-      user_can_change: true,
-    }
-    fixture.detectChanges()
-    expect(
-      fixture.debugElement.query(By.directive(PermissionsFormComponent))
-    ).toBeNull()
-    component.permissionsForm = {
-      owner: 1,
-      set_permissions: { view: { users: [1] } },
-    }
-    const update = jest
-      .spyOn(templateService, 'update')
-      .mockReturnValue(of(component.template))
-    component.save()
-    expect(update.mock.calls[0][0].owner).toBe(2)
-    expect(update.mock.calls[0][0]).not.toHaveProperty('set_permissions')
-  })
-
-  it('should keep only the last picked sample document', () => {
-    component.setSampleDocument([5, 6])
-    expect(component.sampleDocumentIds).toEqual([6])
-
-    component.setSampleDocument([])
-    expect(component.previewDocId).toBeNull()
-    expect(component.pageImageUrl).toBeNull()
-  })
-
-  it('should ignore a stale sample document response', () => {
-    const pending = new Subject<Document>()
-    jest.spyOn(documentService, 'get').mockReturnValueOnce(pending)
-    component.setSampleDocument([5])
-    component.setSampleDocument([6])
-    pending.next({ id: 5, page_count: 99 })
-
-    expect(component.previewPageCount()).toEqual(3)
-  })
-
-  it('should show a failed page and retry it', () => {
-    jest
-      .spyOn(documentService, 'get')
-      .mockReturnValueOnce(throwError(() => new Error('offline')))
-    component.setSampleDocument([5])
-    expect(component.pageFailed()).toBeTruthy()
-
-    component.setSampleDocument(component.sampleDocumentIds)
-    expect(component.pageFailed()).toBeFalsy()
-
-    component.onImageError()
-    expect(component.pageFailed()).toBeTruthy()
-  })
-
-  it('should support create and update', () => {
-    const createSpy = jest
-      .spyOn(templateService, 'create')
-      .mockReturnValue(of({ ...component.template, id: 3 }))
-    const updateSpy = jest
-      .spyOn(templateService, 'update')
-      .mockReturnValue(of(component.template))
-    const succeededSpy = jest.spyOn(component.succeeded, 'emit')
-
-    component.save()
-    expect(createSpy).toHaveBeenCalled()
-    expect(succeededSpy).toHaveBeenCalledWith({ ...component.template, id: 3 })
-    expect(activeModal.close).toHaveBeenCalled()
-
-    component.saving.set(false)
-    component.template.id = 3
-    component.save()
-    expect(updateSpy).toHaveBeenCalledWith(component.template)
-  })
-
-  it('should emit failed and allow editing again after a failed save', () => {
-    prepareOverlay()
-    component.template.zones = [zone()]
-    const pending = new Subject<OcrTemplate>()
-    jest.spyOn(templateService, 'create').mockReturnValue(pending)
-    const failedSpy = jest.spyOn(component.failed, 'emit')
-    component.onOverlayPointerDown(pointer(150, 150))
-
-    component.save()
-    component.save()
-    expect(templateService.create).toHaveBeenCalledTimes(1)
-    component.onOverlayPointerMove(pointer(250, 250))
-    component.onOverlayPointerUp(pointer(250, 250))
-    expect(component.template.zones[0].x).toEqual(100)
-
-    pending.error(new Error('Save failed'))
-    expect(failedSpy).toHaveBeenCalled()
-    expect(component.saving()).toBeFalsy()
-    component.onOverlayPointerDown(pointer(150, 150))
-    component.onOverlayPointerUp(pointer(250, 250))
-    expect(component.template.zones[0].x).toEqual(200)
-  })
-
-  it('should track unsaved changes', () => {
-    fixture.detectChanges()
-    expect(component.isDirty).toBeFalsy()
-
-    component.template.combine_formats = { '1': '' }
-    expect(component.isDirty).toBeFalsy()
-
-    component.template.name = 'Invoices'
-    expect(component.isDirty).toBeTruthy()
-    component.template.name = ''
-    expect(component.isDirty).toBeFalsy()
-
-    component.setSampleDocument([5])
-    expect(component.isDirty).toBeTruthy()
-  })
-
-  it('should draw a zone with no field in empty space', () => {
-    prepareOverlay()
-    component.onOverlayPointerDown(pointer(100, 100))
-    component.onOverlayPointerUp(pointer(1200, 250))
-
-    expect(component.template.zones[0]).toMatchObject({
-      x: 100,
-      y: 100,
-      width: 900,
-      height: 150,
-      custom_field: null,
-    })
-    expect(component.selectedZoneIndex).toEqual(0)
-  })
-
-  it('should clear the selection on a click in empty space', () => {
-    prepareOverlay()
-    component.template.zones = [zone()]
-    component.selectZone(0)
-    component.onOverlayPointerDown(pointer(600, 600))
-    component.onOverlayPointerUp(pointer(602, 601))
-
-    expect(component.template.zones).toHaveLength(1)
-    expect(component.selectedZoneIndex).toBeNull()
-  })
-
-  it('should move a zone when dragging on it', () => {
-    prepareOverlay()
-    component.template.zones = [zone()]
-    component.onOverlayPointerDown(pointer(150, 150))
-    component.onOverlayPointerUp(pointer(250, 200))
-
-    expect(component.template.zones).toHaveLength(1)
-    expect(component.template.zones[0]).toMatchObject({ x: 200, y: 150 })
-  })
-
-  it('should cancel a drawing on escape and ignore other pointers', () => {
-    prepareOverlay()
-    component.onOverlayPointerDown(pointer(100, 100))
-    component.onOverlayPointerUp(pointer(300, 200, 2))
-    expect(component.drawingRect()).not.toBeNull()
-
-    component.cancelDrawing()
-    component.onOverlayPointerUp(pointer(300, 200))
-    expect(component.template.zones).toEqual([])
-  })
-
-  it('should open a zone in the zones tab and go back to the list', () => {
-    component.template.zones = [zone(), zone()]
-    component.selectZone(1)
-    expect(component.activeTab).toEqual('zones')
-    expect(component.selectedZone).toBe(component.template.zones[1])
-
-    component.deselectZone()
-    expect(component.selectedZone).toBeNull()
-
-    component.selectZone(0)
-    component.removeZone(0)
-    expect(component.template.zones).toHaveLength(1)
-    expect(component.selectedZone).toBeNull()
-  })
-
-  it('should only offer custom fields OCR can write to', () => {
-    fixture.detectChanges()
-    expect(component.fieldItems().map((item) => item.id)).toEqual([
-      OcrZoneTarget.Title,
-      OcrZoneTarget.Asn,
-      OcrZoneTarget.Created,
-      1,
-    ])
-  })
-
-  it('should create a custom field and assign it to the zone', () => {
-    const succeeded = new Subject<CustomField>()
-    const dialog = {
-      dialogMode: { set: jest.fn() },
-      object: null,
-      succeeded,
-      failed: new Subject(),
-    }
-    jest
-      .spyOn(modalService, 'open')
-      .mockReturnValue({ componentInstance: dialog } as any)
-    component.template.zones = [zone({ custom_field: null })]
-    component.selectZone(0)
-
-    component.createField()
-    expect(dialog.object).toEqual({ name: 'Invoice number' })
-    succeeded.next(customFields[0])
-
-    expect(component.template.zones[0].custom_field).toEqual(1)
-  })
-
-  it('should build and prune combine formats', () => {
-    const first = zone({ name: 'First' })
-    const second = zone({ name: 'Second' })
-    const other = zone({ name: 'Other', custom_field: 2 })
-    component.template.zones = [first, second, other]
-    component.template.combine_formats = { '2': '{Other}' }
-
-    expect(component.isFieldShared(first)).toBeTruthy()
-    expect(component.isFieldShared(other)).toBeFalsy()
-    expect(component.defaultCombineFormat(first)).toEqual('{First} {Second}')
-
-    component.insertCombineToken(first, second)
-    component.insertCombineToken(first, first)
-    expect(component.getCombineFormat(second)).toEqual('{Second} {First}')
-
-    jest.spyOn(templateService, 'create').mockReturnValue(of(null))
-    component.save()
-    expect(component.template.combine_formats).toEqual({
-      '1': '{Second} {First}',
-    })
-  })
-
-  it('should update exact tokens when a zone is renamed', () => {
-    const first = zone({ name: 'First [value]' })
-    component.template.zones = [first, zone({ name: 'Second' })]
-    component.template.combine_formats = {
-      '1': 'First [value]: {First [value]} / { First [value] } / {Second} / {First [value] extra}',
-      '2': '{First [value]}',
-    }
-
-    component.renameZone(first, '')
-    component.renameZone(first, 'Invoice number')
-
-    expect(first.name).toEqual('Invoice number')
-    expect(component.template.combine_formats).toEqual({
-      '1': 'First [value]: {Invoice number} / {Invoice number} / {Second} / {First [value] extra}',
-      '2': '{First [value]}',
-    })
-  })
-
-  it('should keep the language array stable until the value changes', () => {
-    const selected = zone({ ocr_language: 'deu+eng' })
-    const languages = component.ocrLanguageArray(selected)
-    expect(languages).toEqual(['deu', 'eng'])
-    expect(component.ocrLanguageArray(selected)).toBe(languages)
-
-    component.setOcrLanguages(selected, ['fra'])
-    expect(selected.ocr_language).toEqual('fra')
-    expect(component.ocrLanguageArray(selected)).toEqual(['fra'])
-
-    component.setOcrLanguages(selected, null)
-    expect(component.ocrLanguageArray(selected)).toEqual([])
-  })
-
-  it('should hide a test result once the zone changes', () => {
-    const selected = zone()
-    component.template.zones = [selected]
-    component.selectZone(0)
-    component.setSampleDocument([5])
-    jest
-      .spyOn(templateService, 'testZone')
-      .mockReturnValue(of({ value: '123' }))
-
-    component.testZone()
-    expect(component.zoneTestResult.value).toEqual('123')
-
-    selected.transform = OcrZoneTransform.Numeric
-    expect(component.zoneTestResult).toBeNull()
-  })
-
-  it('should drop a pending test when the zone or sample document changes', () => {
-    const pending = new Subject<OcrZoneTestResult>()
-    component.template.zones = [zone(), zone()]
-    component.selectZone(0)
-    component.setSampleDocument([5])
-    jest.spyOn(templateService, 'testZone').mockReturnValue(pending)
-
-    component.testZone()
-    expect(component.zoneTesting).toBeTruthy()
-    component.selectZone(1)
-    pending.next({ value: 'Old zone' })
-    expect(component.zoneTestResult).toBeNull()
-
-    component.testZone()
-    component.setSampleDocument([])
-    pending.next({ value: 'Old document' })
-    expect(component.zoneTestResult).toBeNull()
-  })
-})

src-ui/src/app/components/manage/ocr-templates/ocr-template-editor/ocr-template-editor.component.ts

@@ -1,963 +0,0 @@
-import { CommonModule } from '@angular/common'
-import {
-  Component,
-  computed,
-  ElementRef,
-  EventEmitter,
-  HostListener,
-  inject,
-  Input,
-  OnDestroy,
-  OnInit,
-  Output,
-  signal,
-  ViewChild,
-} from '@angular/core'
-import { FormsModule } from '@angular/forms'
-import {
-  NgbActiveModal,
-  NgbModal,
-  NgbNavModule,
-} from '@ng-bootstrap/ng-bootstrap'
-import { BootstrapIconComponent } from 'src/app/components/common/bootstrap-icon/bootstrap-icon.component'
-import { Subject, takeUntil } from 'rxjs'
-import { CustomFieldEditDialogComponent } from 'src/app/components/common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component'
-import { EditDialogMode } from 'src/app/components/common/edit-dialog/edit-dialog.component'
-import { DocumentLinkComponent } from 'src/app/components/common/input/document-link/document-link.component'
-import { CheckComponent } from 'src/app/components/common/input/check/check.component'
-import { NumberComponent } from 'src/app/components/common/input/number/number.component'
-import {
-  PermissionsFormComponent,
-  PermissionsFormObject,
-} from 'src/app/components/common/input/permissions/permissions-form/permissions-form.component'
-import { SelectComponent } from 'src/app/components/common/input/select/select.component'
-import { SwitchComponent } from 'src/app/components/common/input/switch/switch.component'
-import { TextComponent } from 'src/app/components/common/input/text/text.component'
-import { CustomField } from 'src/app/data/custom-field'
-import {
-  MATCH_ANY,
-  MATCH_AUTO,
-  MATCH_NONE,
-  MATCHING_ALGORITHMS,
-} from 'src/app/data/matching-model'
-import {
-  DEFAULT_OCR_ZONE_LANGUAGE,
-  getZoneFieldKey,
-  OCR_BUILTIN_TARGETS,
-  OCR_SUPPORTED_FIELD_TYPES,
-  OcrTemplate,
-  OcrTemplateZone,
-  OcrZoneTarget,
-  OcrZoneTestResult,
-  OcrZoneTransform,
-  ZoneTestRequest,
-} from 'src/app/data/ocr-template'
-import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
-import { User } from 'src/app/data/user'
-import { IfOwnerDirective } from 'src/app/directives/if-owner.directive'
-import { PermissionsService } from 'src/app/services/permissions.service'
-import { CustomFieldsService } from 'src/app/services/rest/custom-fields.service'
-import { DocumentService } from 'src/app/services/rest/document.service'
-import { OcrTemplateService } from 'src/app/services/rest/ocr-template.service'
-import { UserService } from 'src/app/services/rest/user.service'
-import { SettingsService } from 'src/app/services/settings.service'
-import { ToastService } from 'src/app/services/toast.service'
-import { OcrTemplateEditorZoneListComponent } from './ocr-template-editor-zone-list/ocr-template-editor-zone-list.component'
-import {
-  DisplayRect,
-  DrawingRect,
-  findHandleAt,
-  findZoneAt,
-  getResizeHandles,
-  getZoneColor,
-  getZoneDisplayRect,
-  getZonePage,
-  HANDLE_SIZE,
-  isZoneOnPage,
-  MIN_ZONE_SIZE,
-  MoveStart,
-  moveZone,
-  Point,
-  ResizeHandle,
-  resizeZone,
-} from './zone-geometry'
-
-type ActiveTab = 'template' | 'zones'
-type ZoneFieldSelection = OcrZoneTarget | number | null
-type OverlayInteraction =
-  | { kind: 'idle' }
-  | { kind: 'drawing'; pointerId: number; rect: DrawingRect }
-  | { kind: 'moving'; pointerId: number; zoneIndex: number; start: MoveStart }
-  | {
-      kind: 'resizing'
-      pointerId: number
-      zoneIndex: number
-      handle: ResizeHandle
-    }
-interface ZoneTest {
-  zone: OcrTemplateZone
-  /** The sample document and zone settings the result was produced from. */
-  key: string
-  result: OcrZoneTestResult | null
-}
-
-export const ZONE_TRANSFORM_OPTIONS = [
-  { id: OcrZoneTransform.None, name: $localize`None` },
-  { id: OcrZoneTransform.Strip, name: $localize`Strip whitespace` },
-  { id: OcrZoneTransform.Uppercase, name: $localize`Uppercase` },
-  { id: OcrZoneTransform.Lowercase, name: $localize`Lowercase` },
-  { id: OcrZoneTransform.Numeric, name: $localize`Numeric only` },
-  {
-    id: OcrZoneTransform.StripPunctuation,
-    name: $localize`Remove leading/trailing punctuation`,
-  },
-  { id: OcrZoneTransform.Date, name: $localize`Parse date` },
-  { id: OcrZoneTransform.QrCode, name: $localize`Read QR/barcode` },
-]
-
-export const ZONE_LANGUAGE_OPTIONS = [
-  { id: 'eng', name: $localize`English` },
-  { id: 'deu', name: $localize`German` },
-  { id: 'fra', name: $localize`French` },
-  { id: 'ita', name: $localize`Italian` },
-  { id: 'spa', name: $localize`Spanish` },
-  { id: 'por', name: $localize`Portuguese` },
-  { id: 'nld', name: $localize`Dutch` },
-]
-
-const TEMPLATE_MATCHING_ALGORITHMS = MATCHING_ALGORITHMS.filter(
-  (algorithm) => algorithm.id !== MATCH_AUTO
-)
-
-const NO_OVERLAY_INTERACTION: OverlayInteraction = { kind: 'idle' }
-const RESIZE_CURSOR: Record<ResizeHandle, string> = {
-  nw: 'nw-resize',
-  ne: 'ne-resize',
-  sw: 'sw-resize',
-  se: 'se-resize',
-  n: 'n-resize',
-  s: 's-resize',
-  w: 'w-resize',
-  e: 'e-resize',
-}
-
-@Component({
-  selector: 'pngx-ocr-template-editor',
-  imports: [
-    DocumentLinkComponent,
-    NumberComponent,
-    TextComponent,
-    CheckComponent,
-    SelectComponent,
-    SwitchComponent,
-    CommonModule,
-    FormsModule,
-    NgbNavModule,
-    BootstrapIconComponent,
-    OcrTemplateEditorZoneListComponent,
-    PermissionsFormComponent,
-    IfOwnerDirective,
-  ],
-  templateUrl: './ocr-template-editor.component.html',
-  styleUrls: ['./ocr-template-editor.component.scss'],
-})
-export class OcrTemplateEditorComponent implements OnInit, OnDestroy {
-  public readonly activeModal = inject(NgbActiveModal)
-  private readonly templateService = inject(OcrTemplateService)
-  private readonly customFieldsService = inject(CustomFieldsService)
-  private readonly documentService = inject(DocumentService)
-  private readonly toastService = inject(ToastService)
-  private readonly modalService = inject(NgbModal)
-  private readonly userService = inject(UserService)
-  private readonly settingsService = inject(SettingsService)
-  private readonly permissionsService = inject(PermissionsService)
-  private readonly destroy$ = new Subject<void>()
-  private readonly cancelZoneTest$ = new Subject<void>()
-
-  @Input() object: OcrTemplate
-  @Output() public readonly succeeded = new EventEmitter<OcrTemplate>()
-  @Output() public readonly failed = new EventEmitter()
-
-  @ViewChild('zoneOverlay') overlayRef: ElementRef<SVGSVGElement>
-  imageRef: ElementRef<HTMLImageElement>
-  private previewResizeObserver: ResizeObserver | null = null
-  private readonly overlayScale = signal(1)
-
-  @ViewChild('pageImage')
-  set pageImage(ref: ElementRef<HTMLImageElement> | undefined) {
-    this.previewResizeObserver?.disconnect()
-    this.imageRef = ref
-    if (!ref) return
-    this.previewResizeObserver = new ResizeObserver(() => {
-      const image = ref.nativeElement
-      if (image.naturalWidth && image.clientWidth) {
-        this.overlayScale.set(image.naturalWidth / image.clientWidth)
-      }
-    })
-    this.previewResizeObserver.observe(ref.nativeElement)
-  }
-
-  template: OcrTemplate = {
-    id: null,
-    name: '',
-    match: '',
-    matching_algorithm: MATCH_ANY,
-    is_insensitive: true,
-    sample_document: null,
-    source_width: 0,
-    source_height: 0,
-    enabled: true,
-    combine_formats: {},
-    zones: [],
-  }
-
-  public readonly customFields = signal<CustomField[]>([])
-  public readonly fieldItems = computed<
-    { id: ZoneFieldSelection; name: string }[]
-  >(() => [
-    ...OCR_BUILTIN_TARGETS,
-    ...this.customFields()
-      .filter((field) => OCR_SUPPORTED_FIELD_TYPES.includes(field.data_type))
-      .map((field) => ({ id: field.id, name: field.name })),
-  ])
-  public readonly users = signal<User[]>([])
-  permissionsForm: PermissionsFormObject = {}
-  public readonly OcrZoneTransform = OcrZoneTransform
-  public readonly saving = signal(false)
-
-  /** Bound to the document picker, which works with id arrays. */
-  sampleDocumentIds: number[] = []
-  previewPage = 0
-  public readonly previewPageCount = signal<number | null>(null)
-  public readonly pageLoaded = signal(false)
-  public readonly pageFailed = signal(false)
-  zoom = 1
-
-  get previewDocId(): number | null {
-    return this.sampleDocumentIds[0] ?? null
-  }
-
-  get pageImageUrl(): string | null {
-    return this.previewDocId
-      ? this.templateService.getPageImageUrl(
-          this.previewDocId,
-          this.previewPage
-        )
-      : null
-  }
-
-  get transformOptions() {
-    return ZONE_TRANSFORM_OPTIONS
-  }
-
-  get languageOptions() {
-    return ZONE_LANGUAGE_OPTIONS
-  }
-
-  get matchingAlgorithms() {
-    return TEMPLATE_MATCHING_ALGORITHMS
-  }
-
-  get patternRequired(): boolean {
-    return (
-      this.template.matching_algorithm !== MATCH_AUTO &&
-      this.template.matching_algorithm !== MATCH_NONE
-    )
-  }
-
-  public get previewPageDisplay(): number {
-    return this.previewPage + 1
-  }
-
-  public set previewPageDisplay(value: number) {
-    this.goToPage(value - 1)
-  }
-
-  activeTab: ActiveTab = 'template'
-
-  selectedZoneIndex: number | null = null
-  private overlayInteraction: OverlayInteraction = NO_OVERLAY_INTERACTION
-  overlayCursor = 'crosshair'
-
-  private readonly zoneTest = signal<ZoneTest | null>(null)
-
-  get zoneTestResult(): OcrZoneTestResult | null {
-    return this.isCurrentZoneTest() ? this.zoneTest().result : null
-  }
-
-  get zoneTesting(): boolean {
-    return this.isCurrentZoneTest() && this.zoneTest().result === null
-  }
-
-  get selectedZone(): OcrTemplateZone | null {
-    return this.selectedZoneIndex !== null
-      ? (this.template.zones[this.selectedZoneIndex] ?? null)
-      : null
-  }
-
-  private initialState = ''
-
-  get isDirty(): boolean {
-    return this.editorState() !== this.initialState
-  }
-
-  private editorState(): string {
-    const formats = Object.entries(this.template.combine_formats ?? {}).filter(
-      ([, format]) => format
-    )
-    return JSON.stringify({
-      ...this.template,
-      combine_formats: Object.fromEntries(formats),
-      sample_document: this.previewDocId ?? null,
-      permissions_form: this.permissionsForm,
-    })
-  }
-
-  get dialogTitle(): string {
-    return this.template.id
-      ? $localize`Edit OCR Template`
-      : $localize`New OCR Template`
-  }
-
-  ngOnInit() {
-    this.userService
-      .listAll()
-      .pipe(takeUntil(this.destroy$))
-      .subscribe((r) => this.users.set(r.results))
-    this.customFieldsService
-      .listAll()
-      .pipe(takeUntil(this.destroy$))
-      .subscribe((r) => {
-        this.customFields.set(r.results)
-      })
-
-    if (this.object) {
-      this.template = {
-        ...this.object,
-        zones: this.object.zones.map((zone) => ({ ...zone })),
-        combine_formats: { ...this.object.combine_formats },
-      }
-      if (this.template.sample_document) {
-        this.setSampleDocument([this.template.sample_document])
-      }
-    }
-    const permissions = this.object?.permissions
-    this.permissionsForm = this.object
-      ? {
-          owner: this.object.owner,
-          set_permissions: {
-            view: {
-              users: [...(permissions?.view.users ?? [])],
-              groups: [...(permissions?.view.groups ?? [])],
-            },
-            change: {
-              users: [...(permissions?.change.users ?? [])],
-              groups: [...(permissions?.change.groups ?? [])],
-            },
-          },
-        }
-      : {
-          owner: this.settingsService.get(SETTINGS_KEYS.DEFAULT_PERMS_OWNER),
-          set_permissions: {
-            view: {
-              users: this.settingsService.get(
-                SETTINGS_KEYS.DEFAULT_PERMS_VIEW_USERS
-              ),
-              groups: this.settingsService.get(
-                SETTINGS_KEYS.DEFAULT_PERMS_VIEW_GROUPS
-              ),
-            },
-            change: {
-              users: this.settingsService.get(
-                SETTINGS_KEYS.DEFAULT_PERMS_EDIT_USERS
-              ),
-              groups: this.settingsService.get(
-                SETTINGS_KEYS.DEFAULT_PERMS_EDIT_GROUPS
-              ),
-            },
-          },
-        }
-    this.initialState = this.editorState()
-  }
-
-  setSampleDocument(ids: number[]) {
-    const id = ids.at(-1)
-    this.sampleDocumentIds = id ? [id] : []
-    this.previewPage = 0
-    this.previewPageCount.set(null)
-    this.resetPage()
-    if (!id) return
-    this.documentService
-      .get(id)
-      .pipe(takeUntil(this.destroy$))
-      .subscribe({
-        next: (doc) => {
-          if (this.previewDocId !== id) return
-          this.previewPageCount.set(doc.page_count ?? null)
-        },
-        error: () => {
-          if (this.previewDocId === id) this.pageFailed.set(true)
-        },
-      })
-  }
-
-  private resetPage() {
-    this.stopOverlayInteraction()
-    this.clearZoneTest()
-    this.pageLoaded.set(false)
-    this.pageFailed.set(false)
-  }
-
-  goToPage(page: number) {
-    if (!Number.isFinite(page)) return
-    const pageCount = this.previewPageCount()
-    const max = pageCount ? pageCount - 1 : page
-    const clamped = Math.max(0, Math.min(Math.trunc(page), max))
-    if (clamped === this.previewPage) return
-    this.previewPage = clamped
-    this.resetPage()
-  }
-
-  zoomIn() {
-    this.zoom = Math.min(4, Math.round((this.zoom + 0.25) * 100) / 100)
-  }
-
-  zoomOut() {
-    this.zoom = Math.max(0.5, Math.round((this.zoom - 0.25) * 100) / 100)
-  }
-
-  resetZoom() {
-    this.zoom = 1
-  }
-
-  zonePage(zone: OcrTemplateZone): number {
-    return getZonePage(zone, this.previewPage, this.previewPageCount())
-  }
-
-  isLastPageZone(zone: OcrTemplateZone): boolean {
-    return zone.page === -1
-  }
-
-  setLastPageZone(zone: OcrTemplateZone, lastPage: boolean) {
-    zone.page = lastPage ? -1 : this.previewPage + 1
-  }
-
-  private isOnCurrentPage(zone: OcrTemplateZone): boolean {
-    return isZoneOnPage(zone, this.previewPage, this.previewPageCount())
-  }
-
-  onImageLoad() {
-    this.pageLoaded.set(true)
-    const img = this.imageRef.nativeElement
-    this.template.source_width = img.naturalWidth
-    this.template.source_height = img.naturalHeight
-  }
-
-  onImageError() {
-    this.stopOverlayInteraction()
-    this.pageFailed.set(true)
-  }
-
-  @HostListener('document:keydown.escape')
-  cancelDrawing() {
-    this.stopOverlayInteraction()
-  }
-
-  onOverlayPointerDown(event: PointerEvent) {
-    if (this.saving()) return
-    if (event.button !== 0 || this.overlayInteraction.kind !== 'idle') return
-    const point = this.svgPointFromEvent(event)
-    if (!this.pageLoaded() || !point) return
-    event.preventDefault()
-
-    if (this.selectedZoneIndex !== null) {
-      const handle = this.handleAt(point, this.selectedZoneIndex)
-      if (handle) {
-        this.overlayInteraction = {
-          kind: 'resizing',
-          pointerId: event.pointerId,
-          zoneIndex: this.selectedZoneIndex,
-          handle,
-        }
-        this.overlayRef.nativeElement.setPointerCapture(event.pointerId)
-        return
-      }
-    }
-
-    const clickedIdx = this.zoneIndexAt(point)
-    if (clickedIdx !== null) {
-      this.selectZone(clickedIdx)
-      const zone = this.template.zones[clickedIdx]
-      this.overlayInteraction = {
-        kind: 'moving',
-        pointerId: event.pointerId,
-        zoneIndex: clickedIdx,
-        start: {
-          mouseX: point.x,
-          mouseY: point.y,
-          zoneX: zone.x,
-          zoneY: zone.y,
-        },
-      }
-      this.overlayRef.nativeElement.setPointerCapture(event.pointerId)
-      return
-    }
-
-    // Empty space: start drawing a new zone. A click without a drag just clears
-    // the selection (see onOverlayPointerUp).
-    this.clearZoneTest()
-    this.selectedZoneIndex = null
-    this.overlayInteraction = {
-      kind: 'drawing',
-      pointerId: event.pointerId,
-      rect: {
-        startX: point.x,
-        startY: point.y,
-        endX: point.x,
-        endY: point.y,
-      },
-    }
-    this.overlayRef.nativeElement.setPointerCapture(event.pointerId)
-  }
-
-  onOverlayPointerMove(event: PointerEvent) {
-    if (
-      this.overlayInteraction.kind !== 'idle' &&
-      this.overlayInteraction.pointerId !== event.pointerId
-    )
-      return
-    const point = this.svgPointFromEvent(event)
-    if (!point) return
-
-    if (this.overlayInteraction.kind === 'resizing') {
-      resizeZone(
-        this.template.zones[this.overlayInteraction.zoneIndex],
-        this.overlayInteraction.handle,
-        point,
-        this.imageNaturalSize()
-      )
-      return
-    }
-
-    if (this.overlayInteraction.kind === 'moving') {
-      moveZone(
-        this.template.zones[this.overlayInteraction.zoneIndex],
-        point,
-        this.overlayInteraction.start,
-        this.imageNaturalSize()
-      )
-      return
-    }
-
-    if (this.overlayInteraction.kind === 'drawing') {
-      this.overlayInteraction.rect.endX = point.x
-      this.overlayInteraction.rect.endY = point.y
-      return
-    }
-
-    this.updateOverlayCursor(point)
-  }
-
-  private updateOverlayCursor(point: Point) {
-    if (this.selectedZoneIndex !== null) {
-      const handle = this.handleAt(point, this.selectedZoneIndex)
-      if (handle) {
-        this.overlayCursor = RESIZE_CURSOR[handle]
-        return
-      }
-    }
-    this.overlayCursor = this.zoneIndexAt(point) !== null ? 'move' : 'crosshair'
-  }
-
-  onOverlayPointerUp(event: PointerEvent) {
-    if (this.overlayInteraction.kind === 'idle') return
-    if (this.overlayInteraction.pointerId !== event.pointerId) return
-    this.onOverlayPointerMove(event)
-    const interaction = this.overlayInteraction
-    this.stopOverlayInteraction()
-    if (interaction.kind !== 'drawing') return
-
-    const rect = this.sourceRectFromDrawing(interaction.rect)
-
-    // Ignore tiny accidental clicks.
-    if (rect.w < MIN_ZONE_SIZE || rect.h < MIN_ZONE_SIZE) {
-      return
-    }
-
-    this.template.zones.push(this.createZoneFromRect(rect))
-    this.selectZone(this.template.zones.length - 1)
-  }
-
-  private createZoneFromRect(rect: DisplayRect): OcrTemplateZone {
-    const imageSize = this.imageNaturalSize()
-    return {
-      name: `Zone ${this.template.zones.length + 1}`,
-      target: OcrZoneTarget.CustomField,
-      custom_field: null,
-      x: rect.x,
-      y: rect.y,
-      width: rect.w,
-      height: rect.h,
-      page: this.previewPageDisplay,
-      ocr_language: DEFAULT_OCR_ZONE_LANGUAGE,
-      transform: OcrZoneTransform.Strip,
-      date_format: '',
-      validation_regex: '',
-      order: this.template.zones.length,
-      zone_source_width: imageSize.width,
-      zone_source_height: imageSize.height,
-    }
-  }
-
-  onOverlayPointerCancel(event: PointerEvent) {
-    if (this.overlayInteraction.kind === 'idle') return
-    if (this.overlayInteraction.pointerId !== event.pointerId) return
-    this.stopOverlayInteraction()
-  }
-
-  private stopOverlayInteraction() {
-    const interaction = this.overlayInteraction
-    this.overlayInteraction = NO_OVERLAY_INTERACTION
-    this.overlayCursor = 'crosshair'
-    const overlay = this.overlayRef?.nativeElement
-    if (
-      interaction.kind !== 'idle' &&
-      overlay?.hasPointerCapture(interaction.pointerId)
-    ) {
-      overlay.releasePointerCapture(interaction.pointerId)
-    }
-  }
-
-  drawingRect(): DisplayRect | null {
-    return this.overlayInteraction.kind === 'drawing'
-      ? this.displayRectFromDrawing(this.overlayInteraction.rect)
-      : null
-  }
-
-  /** The zone's rectangle on the overlay, or null if it's on another page. */
-  zoneDisplayRect(zoneIndex: number): DisplayRect | null {
-    const zone = this.template.zones[zoneIndex]
-    if (!this.isOnCurrentPage(zone)) return null
-    return getZoneDisplayRect(zone, this.imageNaturalSize())
-  }
-
-  private handleAt(point: Point, zoneIndex: number): ResizeHandle | null {
-    const rect = this.zoneDisplayRect(zoneIndex)
-    return rect ? findHandleAt(point, rect, this.overlayHandleSize()) : null
-  }
-
-  private zoneIndexAt(point: Point): number | null {
-    return findZoneAt(
-      point,
-      this.template.zones,
-      this.previewPage,
-      this.previewPageCount(),
-      this.imageNaturalSize()
-    )
-  }
-
-  overlayViewBox(): string {
-    const imageSize = this.imageNaturalSize()
-    return `0 0 ${imageSize.width} ${imageSize.height}`
-  }
-
-  public readonly zoneColor = getZoneColor
-
-  zoneLabel(zone: OcrTemplateZone, index: number): string {
-    return zone.name || `Zone ${index + 1}`
-  }
-
-  zoneLabelY(rect: DisplayRect): number {
-    return Math.max(this.overlayUnitSize(14), rect.y - this.overlayUnitSize(4))
-  }
-
-  public readonly resizeHandles = getResizeHandles
-
-  overlayHandleSize(): number {
-    return this.overlayUnitSize(HANDLE_SIZE)
-  }
-
-  overlayFontSize(): number {
-    return this.overlayUnitSize(12)
-  }
-
-  overlayUnitSize(screenPixels: number): number {
-    return screenPixels * this.overlayScale()
-  }
-
-  private svgPointFromEvent(event: MouseEvent): Point | null {
-    const svg = this.overlayRef?.nativeElement
-    const matrix = svg?.getScreenCTM()
-    if (!svg || !matrix) return null
-
-    const point = svg.createSVGPoint()
-    point.x = event.clientX
-    point.y = event.clientY
-
-    const svgPoint = point.matrixTransform(matrix.inverse())
-    const size = this.imageNaturalSize()
-    return {
-      x: Math.max(0, Math.min(svgPoint.x, size.width)),
-      y: Math.max(0, Math.min(svgPoint.y, size.height)),
-    }
-  }
-
-  private displayRectFromDrawing(rect: DrawingRect): DisplayRect {
-    return {
-      x: Math.min(rect.startX, rect.endX),
-      y: Math.min(rect.startY, rect.endY),
-      w: Math.abs(rect.endX - rect.startX),
-      h: Math.abs(rect.endY - rect.startY),
-    }
-  }
-
-  private sourceRectFromDrawing(rect: DrawingRect): DisplayRect {
-    const displayRect = this.displayRectFromDrawing(rect)
-    return {
-      x: Math.round(displayRect.x),
-      y: Math.round(displayRect.y),
-      w: Math.round(displayRect.w),
-      h: Math.round(displayRect.h),
-    }
-  }
-
-  private imageNaturalSize() {
-    const img = this.imageRef.nativeElement
-    return { width: img.naturalWidth, height: img.naturalHeight }
-  }
-
-  removeZone(index: number) {
-    this.stopOverlayInteraction()
-    this.clearZoneTest()
-    this.template.zones.splice(index, 1)
-    if (this.selectedZoneIndex === index) {
-      this.selectedZoneIndex = null
-    } else if (this.selectedZoneIndex > index) {
-      this.selectedZoneIndex--
-    }
-  }
-
-  selectZone(index: number) {
-    this.selectedZoneIndex = index
-    this.activeTab = 'zones'
-    this.clearZoneTest()
-    const zone = this.template.zones[index]
-    if (zone) {
-      this.goToPage(this.zonePage(zone) - 1)
-    }
-  }
-
-  deselectZone() {
-    this.selectedZoneIndex = null
-    this.clearZoneTest()
-  }
-
-  testZone() {
-    const zone = this.selectedZone
-    if (!zone || !this.previewDocId) return
-    this.clearZoneTest()
-    const test: ZoneTest = { zone, key: this.zoneTestKey(zone), result: null }
-    this.zoneTest.set(test)
-    this.templateService
-      .testZone(this.previewDocId, this.zoneTestRequest(zone))
-      .pipe(takeUntil(this.destroy$), takeUntil(this.cancelZoneTest$))
-      .subscribe({
-        next: (res) => this.zoneTest.set({ ...test, result: res }),
-        error: (err) =>
-          this.zoneTest.set({
-            ...test,
-            result: { error: err.error?.error || $localize`Test failed` },
-          }),
-      })
-  }
-
-  private clearZoneTest() {
-    this.cancelZoneTest$.next()
-    this.zoneTest.set(null)
-  }
-
-  /** A result is stale once its zone, settings or sample document change. */
-  private isCurrentZoneTest(): boolean {
-    const test = this.zoneTest()
-    return (
-      test?.zone === this.selectedZone &&
-      test.key === this.zoneTestKey(test.zone)
-    )
-  }
-
-  private zoneTestKey(zone: OcrTemplateZone): string {
-    return JSON.stringify([this.previewDocId, this.zoneTestRequest(zone)])
-  }
-
-  private zoneTestRequest(zone: OcrTemplateZone): ZoneTestRequest {
-    return {
-      name: zone.name,
-      x: zone.x,
-      y: zone.y,
-      width: zone.width,
-      height: zone.height,
-      page: zone.page ?? 1,
-      ocr_language: zone.ocr_language,
-      transform: zone.transform,
-      date_format: zone.date_format,
-      validation_regex: zone.validation_regex,
-      zone_source_width: zone.zone_source_width,
-      zone_source_height: zone.zone_source_height,
-    }
-  }
-
-  save() {
-    if (this.saving()) return
-    this.stopOverlayInteraction()
-    this.saving.set(true)
-    this.pruneCombineFormats()
-    this.template.sample_document = this.previewDocId
-    const payload = this.permissionsService.currentUserOwnsObject(this.object)
-      ? { ...this.template, ...this.permissionsForm }
-      : this.template
-    const obs = this.template.id
-      ? this.templateService.update(payload)
-      : this.templateService.create(payload)
-
-    obs.pipe(takeUntil(this.destroy$)).subscribe({
-      next: (saved) => {
-        this.activeModal.close()
-        this.succeeded.emit(saved)
-      },
-      error: (e) => {
-        this.saving.set(false)
-        this.failed.emit(e)
-      },
-    })
-  }
-
-  // ng-select needs a stable array between change detection runs, so the
-  // split language list is cached per zone until ocr_language changes.
-  private readonly ocrLanguageCache = new WeakMap<
-    OcrTemplateZone,
-    { language: string; languages: string[] }
-  >()
-
-  ocrLanguageArray(zone: OcrTemplateZone): string[] {
-    const language = zone.ocr_language || ''
-    const cached = this.ocrLanguageCache.get(zone)
-    if (cached?.language === language) return cached.languages
-    const languages = language.split('+').filter(Boolean)
-    this.ocrLanguageCache.set(zone, { language, languages })
-    return languages
-  }
-
-  setOcrLanguages(zone: OcrTemplateZone, langs: string[]) {
-    zone.ocr_language = (langs ?? []).join('+')
-  }
-
-  /** The field select's value: a built-in target, or a custom field id. */
-  zoneFieldValue(zone: OcrTemplateZone): ZoneFieldSelection {
-    return zone.target === OcrZoneTarget.CustomField
-      ? zone.custom_field
-      : zone.target
-  }
-
-  setZoneField(zone: OcrTemplateZone, value: ZoneFieldSelection) {
-    if (typeof value === 'string') {
-      zone.target = value
-      zone.custom_field = null
-    } else {
-      zone.target = OcrZoneTarget.CustomField
-      zone.custom_field = value
-    }
-  }
-
-  zonesForField(zone: OcrTemplateZone): OcrTemplateZone[] {
-    const key = getZoneFieldKey(zone)
-    if (!key) return []
-    return this.template.zones.filter((z) => getZoneFieldKey(z) === key)
-  }
-
-  isFieldShared(zone: OcrTemplateZone): boolean {
-    return this.zonesForField(zone).length > 1
-  }
-
-  renameZone(zone: OcrTemplateZone, name: string) {
-    const oldName = zone.name.trim()
-    const format = this.getCombineFormat(zone)
-    if (format) {
-      this.setCombineFormat(
-        zone,
-        format.replace(/\{([^{}]*)\}/g, (token, tokenName: string) =>
-          tokenName.trim() === oldName ? `{${name}}` : token
-        )
-      )
-    }
-    zone.name = name
-  }
-
-  getCombineFormat(zone: OcrTemplateZone): string {
-    return this.template.combine_formats?.[getZoneFieldKey(zone)] ?? ''
-  }
-
-  setCombineFormat(zone: OcrTemplateZone, value: string) {
-    const key = getZoneFieldKey(zone)
-    if (!key) return
-    this.template.combine_formats ??= {}
-    this.template.combine_formats[key] = value
-  }
-
-  defaultCombineFormat(zone: OcrTemplateZone): string {
-    return this.zonesForField(zone)
-      .map((z) => `{${z.name}}`)
-      .join(' ')
-  }
-
-  insertCombineToken(zone: OcrTemplateZone, tokenZone: OcrTemplateZone) {
-    const current = this.getCombineFormat(zone)
-    const sep = current && !current.endsWith(' ') ? ' ' : ''
-    this.setCombineFormat(zone, `${current}${sep}{${tokenZone.name}}`)
-  }
-
-  /** Drop formats that are empty or whose field no longer has several zones. */
-  private pruneCombineFormats() {
-    const formats = this.template.combine_formats
-    if (!formats) return
-    const keys = this.template.zones.map(getZoneFieldKey)
-    for (const [key, format] of Object.entries(formats)) {
-      if (!format || keys.filter((k) => k === key).length < 2) {
-        delete formats[key]
-      }
-    }
-  }
-
-  createField(name?: string) {
-    const zone = this.selectedZone
-    const modal = this.modalService.open(CustomFieldEditDialogComponent)
-    modal.componentInstance.dialogMode.set(EditDialogMode.CREATE)
-    modal.componentInstance.object = { name: name || zone?.name }
-    modal.componentInstance.succeeded
-      .pipe(takeUntil(this.destroy$))
-      .subscribe((field: CustomField) => {
-        this.toastService.showSuccess($localize`Saved field "${field.name}".`)
-        this.customFieldsService.clearCache()
-        this.customFieldsService
-          .listAll()
-          .pipe(takeUntil(this.destroy$))
-          .subscribe((r) => {
-            if (zone && OCR_SUPPORTED_FIELD_TYPES.includes(field.data_type)) {
-              this.setZoneField(zone, field.id)
-            }
-            this.customFields.set(r.results)
-          })
-      })
-    modal.componentInstance.failed
-      .pipe(takeUntil(this.destroy$))
-      .subscribe((e) => {
-        this.toastService.showError($localize`Error saving field.`, e)
-      })
-  }
-
-  ngOnDestroy() {
-    this.previewResizeObserver?.disconnect()
-    this.cancelZoneTest$.complete()
-    this.destroy$.next()
-    this.destroy$.complete()
-  }
-}

src-ui/src/app/components/manage/ocr-templates/ocr-template-editor/zone-geometry.spec.ts

@@ -1,197 +0,0 @@
-import {
-  OcrTemplateZone,
-  OcrZoneTarget,
-  OcrZoneTransform,
-} from 'src/app/data/ocr-template'
-import {
-  findHandleAt,
-  findZoneAt,
-  getResizeHandles,
-  getZoneDisplayRect,
-  getZonePage,
-  isZoneOnPage,
-  moveZone,
-  resizeZone,
-} from './zone-geometry'
-
-function zone(overrides: Partial<OcrTemplateZone> = {}): OcrTemplateZone {
-  return {
-    name: 'Zone',
-    target: OcrZoneTarget.CustomField,
-    custom_field: 1,
-    x: 100,
-    y: 200,
-    width: 300,
-    height: 400,
-    page: 1,
-    ocr_language: 'eng',
-    transform: OcrZoneTransform.Strip,
-    validation_regex: '',
-    order: 0,
-    ...overrides,
-  }
-}
-
-describe('OCR template editor geometry', () => {
-  it('normalizes zone pages', () => {
-    expect(getZonePage(zone({ page: 2 }), 0, 5)).toBe(2)
-    expect(getZonePage(zone({ page: -1 }), 0, 5)).toBe(5)
-    expect(getZonePage(zone({ page: -1 }), 2, null)).toBe(3)
-    expect(getZonePage(zone({ page: 0 }), 0, 5)).toBe(1)
-    expect(getZonePage(zone({ page: undefined }), 0, 5)).toBe(1)
-  })
-
-  it('checks whether a zone is on the current preview page', () => {
-    expect(isZoneOnPage(zone({ page: 2 }), 1, 5)).toBe(true)
-    expect(isZoneOnPage(zone({ page: 2 }), 0, 5)).toBe(false)
-    expect(isZoneOnPage(zone({ page: -1 }), 4, 5)).toBe(true)
-  })
-
-  it('uses natural image coordinates when source dimensions are unset', () => {
-    expect(
-      getZoneDisplayRect(zone({ x: 100, y: 200, width: 300, height: 400 }), {
-        width: 1000,
-        height: 2000,
-      })
-    ).toEqual({ x: 100, y: 200, w: 300, h: 400 })
-  })
-
-  it('uses per-zone source dimensions when present', () => {
-    expect(
-      getZoneDisplayRect(
-        zone({
-          x: 100,
-          y: 100,
-          width: 100,
-          height: 100,
-          zone_source_width: 1000,
-          zone_source_height: 1000,
-        }),
-        { width: 500, height: 750 }
-      )
-    ).toEqual({ x: 50, y: 75, w: 50, h: 75 })
-  })
-
-  it('finds zones from topmost to bottommost on the current page', () => {
-    const zones = [
-      zone({ name: 'first', x: 0, y: 0, width: 100, height: 100, page: 1 }),
-      zone({ name: 'second', x: 0, y: 0, width: 50, height: 50, page: 1 }),
-      zone({ name: 'third', x: 0, y: 0, width: 50, height: 50, page: 2 }),
-    ]
-
-    expect(
-      findZoneAt({ x: 25, y: 25 }, zones, 0, 2, { width: 100, height: 100 })
-    ).toBe(1)
-  })
-
-  it('finds resize handles around a display rect', () => {
-    const rect = { x: 10, y: 20, w: 100, h: 200 }
-
-    expect(findHandleAt({ x: 10, y: 20 }, rect)).toBe('nw')
-    expect(findHandleAt({ x: 110, y: 220 }, rect)).toBe('se')
-    expect(findHandleAt({ x: 60, y: 20 }, rect)).toBe('n')
-    expect(findHandleAt({ x: 90, y: 160 }, rect)).toBeNull()
-    expect(findHandleAt({ x: 19, y: 20 }, rect, 8)).toBeNull()
-    expect(findHandleAt({ x: 19, y: 20 }, rect, 10)).toBe('nw')
-  })
-
-  it('returns no zone when the point is outside every rectangle', () => {
-    expect(
-      findZoneAt({ x: 900, y: 900 }, [zone()], 0, 1, {
-        width: 1000,
-        height: 1000,
-      })
-    ).toBeNull()
-  })
-
-  it('resizes north-west edges while keeping the opposite corner fixed', () => {
-    const z = zone({ x: 100, y: 200, width: 300, height: 400 })
-    resizeZone(z, 'nw', { x: 50, y: 100 }, { width: 1000, height: 1000 })
-    expect(z).toMatchObject({ x: 50, y: 100, width: 350, height: 500 })
-    resizeZone(z, 'nw', { x: 900, y: 900 }, { width: 1000, height: 1000 })
-    expect(z).toMatchObject({ x: 390, y: 590, width: 10, height: 10 })
-  })
-
-  it('clamps resized north-west edges to the source image bounds', () => {
-    const z = zone({
-      x: 50,
-      y: 50,
-      width: 100,
-      height: 100,
-      zone_source_width: 200,
-      zone_source_height: 300,
-    })
-    resizeZone(z, 'nw', { x: -50, y: -50 }, { width: 400, height: 600 })
-    expect(z).toMatchObject({ x: 0, y: 0, width: 150, height: 150 })
-  })
-
-  it('uses the rendered handle positions for hit testing', () => {
-    const rect = { x: 10, y: 20, w: 100, h: 200 }
-    const handles = getResizeHandles(rect)
-
-    expect(handles).toEqual([
-      { handle: 'nw', x: 10, y: 20 },
-      { handle: 'n', x: 60, y: 20 },
-      { handle: 'ne', x: 110, y: 20 },
-      { handle: 'w', x: 10, y: 120 },
-      { handle: 'e', x: 110, y: 120 },
-      { handle: 'sw', x: 10, y: 220 },
-      { handle: 's', x: 60, y: 220 },
-      { handle: 'se', x: 110, y: 220 },
-    ])
-    for (const marker of handles) {
-      expect(findHandleAt(marker, rect)).toBe(marker.handle)
-    }
-  })
-
-  it('moves zones without leaving source image bounds', () => {
-    const z = zone({ x: 50, y: 50, width: 100, height: 100 })
-
-    moveZone(
-      z,
-      { x: 500, y: 500 },
-      { mouseX: 50, mouseY: 50, zoneX: 50, zoneY: 50 },
-      { width: 500, height: 500 }
-    )
-
-    expect(z.x).toBe(400)
-    expect(z.y).toBe(400)
-  })
-
-  it('resizes zones without leaving source image bounds', () => {
-    const z = zone({
-      x: 50,
-      y: 50,
-      width: 100,
-      height: 100,
-      zone_source_width: 200,
-      zone_source_height: 200,
-    })
-
-    resizeZone(z, 'se', { x: 500, y: 500 }, { width: 500, height: 500 })
-
-    expect(z.width).toBe(150)
-    expect(z.height).toBe(150)
-  })
-
-  it('moves zones in their original source coordinates on a different-size preview', () => {
-    const z = zone({
-      x: 50,
-      y: 50,
-      width: 100,
-      height: 100,
-      zone_source_width: 1000,
-      zone_source_height: 2000,
-    })
-
-    moveZone(
-      z,
-      { x: 75, y: 75 },
-      { mouseX: 25, mouseY: 25, zoneX: 50, zoneY: 50 },
-      { width: 500, height: 500 }
-    )
-
-    expect(z.x).toBe(150)
-    expect(z.y).toBe(250)
-  })
-})

src-ui/src/app/components/manage/ocr-templates/ocr-template-editor/zone-geometry.ts

@@ -1,204 +0,0 @@
-import { OcrTemplateZone } from 'src/app/data/ocr-template'
-
-export interface DrawingRect {
-  startX: number
-  startY: number
-  endX: number
-  endY: number
-}
-
-export interface Dimensions {
-  width: number
-  height: number
-}
-
-export interface Point {
-  x: number
-  y: number
-}
-
-export interface DisplayRect {
-  x: number
-  y: number
-  w: number
-  h: number
-}
-
-export interface MoveStart {
-  mouseX: number
-  mouseY: number
-  zoneX: number
-  zoneY: number
-}
-
-export type ResizeHandle = 'n' | 's' | 'e' | 'w' | 'ne' | 'nw' | 'se' | 'sw'
-
-export interface ResizeHandleMarker extends Point {
-  handle: ResizeHandle
-}
-
-export const HANDLE_SIZE = 8
-export const MIN_ZONE_SIZE = 10
-
-const ZONE_COLORS = [
-  '#4f8ff7',
-  '#ff6b6b',
-  '#51cf66',
-  '#ffd43b',
-  '#cc5de8',
-  '#ff922b',
-  '#20c997',
-  '#e599f7',
-]
-
-/** Outline color for a zone, shared by the preview overlay and the zone list. */
-export function getZoneColor(index: number): string {
-  return ZONE_COLORS[index % ZONE_COLORS.length]
-}
-
-export function getZonePage(
-  zone: OcrTemplateZone,
-  previewPage: number,
-  previewPageCount: number | null
-): number {
-  const page = zone.page ?? 1
-  if (page === -1) return previewPageCount ?? previewPage + 1
-  return Math.max(page, 1)
-}
-
-export function isZoneOnPage(
-  zone: OcrTemplateZone,
-  previewPage: number,
-  previewPageCount: number | null
-): boolean {
-  return getZonePage(zone, previewPage, previewPageCount) === previewPage + 1
-}
-
-function getZoneSourceSize(
-  zone: OcrTemplateZone,
-  imageSize: Dimensions
-): Dimensions {
-  return {
-    width: zone.zone_source_width || imageSize.width,
-    height: zone.zone_source_height || imageSize.height,
-  }
-}
-
-export function getZoneDisplayRect(
-  zone: OcrTemplateZone,
-  imageSize: Dimensions
-): DisplayRect {
-  const sourceSize = getZoneSourceSize(zone, imageSize)
-  // The SVG viewBox uses the preview image's natural dimensions.
-  const scaleX = imageSize.width / sourceSize.width
-  const scaleY = imageSize.height / sourceSize.height
-
-  return {
-    x: zone.x * scaleX,
-    y: zone.y * scaleY,
-    w: zone.width * scaleX,
-    h: zone.height * scaleY,
-  }
-}
-
-export function getResizeHandles(rect: DisplayRect): ResizeHandleMarker[] {
-  return [
-    { handle: 'nw', x: rect.x, y: rect.y },
-    { handle: 'n', x: rect.x + rect.w / 2, y: rect.y },
-    { handle: 'ne', x: rect.x + rect.w, y: rect.y },
-    { handle: 'w', x: rect.x, y: rect.y + rect.h / 2 },
-    { handle: 'e', x: rect.x + rect.w, y: rect.y + rect.h / 2 },
-    { handle: 'sw', x: rect.x, y: rect.y + rect.h },
-    { handle: 's', x: rect.x + rect.w / 2, y: rect.y + rect.h },
-    { handle: 'se', x: rect.x + rect.w, y: rect.y + rect.h },
-  ]
-}
-
-export function findHandleAt(
-  point: Point,
-  rect: DisplayRect,
-  handleSize = HANDLE_SIZE
-): ResizeHandle | null {
-  return (
-    getResizeHandles(rect).find(
-      ({ x, y }) =>
-        Math.abs(point.x - x) <= handleSize &&
-        Math.abs(point.y - y) <= handleSize
-    )?.handle ?? null
-  )
-}
-
-export function findZoneAt(
-  point: Point,
-  zones: OcrTemplateZone[],
-  previewPage: number,
-  previewPageCount: number | null,
-  imageSize: Dimensions
-): number | null {
-  for (let i = zones.length - 1; i >= 0; i--) {
-    const zone = zones[i]
-    if (!isZoneOnPage(zone, previewPage, previewPageCount)) continue
-    const rect = getZoneDisplayRect(zone, imageSize)
-
-    if (
-      point.x >= rect.x &&
-      point.x <= rect.x + rect.w &&
-      point.y >= rect.y &&
-      point.y <= rect.y + rect.h
-    ) {
-      return i
-    }
-  }
-
-  return null
-}
-
-export function moveZone(
-  zone: OcrTemplateZone,
-  point: Point,
-  moveStart: MoveStart,
-  imageSize: Dimensions
-) {
-  const sourceSize = getZoneSourceSize(zone, imageSize)
-  const scaleX = sourceSize.width / imageSize.width
-  const scaleY = sourceSize.height / imageSize.height
-  const dx = Math.round((point.x - moveStart.mouseX) * scaleX)
-  const dy = Math.round((point.y - moveStart.mouseY) * scaleY)
-
-  zone.x = clamp(moveStart.zoneX + dx, 0, sourceSize.width - zone.width)
-  zone.y = clamp(moveStart.zoneY + dy, 0, sourceSize.height - zone.height)
-}
-
-export function resizeZone(
-  zone: OcrTemplateZone,
-  handle: ResizeHandle,
-  point: Point,
-  imageSize: Dimensions
-) {
-  const sourceSize = getZoneSourceSize(zone, imageSize)
-  const scaleX = sourceSize.width / imageSize.width
-  const scaleY = sourceSize.height / imageSize.height
-  const imageX = clamp(Math.round(point.x * scaleX), 0, sourceSize.width)
-  const imageY = clamp(Math.round(point.y * scaleY), 0, sourceSize.height)
-
-  if (handle.includes('w')) {
-    const right = Math.min(zone.x + zone.width, sourceSize.width)
-    zone.x = clamp(imageX, 0, right - MIN_ZONE_SIZE)
-    zone.width = right - zone.x
-  }
-  if (handle.includes('e')) {
-    zone.width = Math.max(MIN_ZONE_SIZE, imageX - zone.x)
-  }
-  if (handle.includes('n')) {
-    const bottom = Math.min(zone.y + zone.height, sourceSize.height)
-    zone.y = clamp(imageY, 0, bottom - MIN_ZONE_SIZE)
-    zone.height = bottom - zone.y
-  }
-  if (handle.includes('s')) {
-    zone.height = Math.max(MIN_ZONE_SIZE, imageY - zone.y)
-  }
-}
-
-function clamp(value: number, min: number, max: number): number {
-  return Math.max(min, Math.min(value, max))
-}

src-ui/src/app/components/manage/ocr-templates/ocr-templates.component.html

@@ -1,75 +0,0 @@
-<pngx-page-header
-  title="OCR Templates"
-  i18n-title
-  info="Define extraction zones on document types to automatically populate custom fields via OCR."
-  i18n-info
-  >
-  <button type="button" class="btn btn-sm btn-outline-primary" (click)="editTemplate()" *pngxIfPermissions="{ action: PermissionAction.Add, type: PermissionType.OcrTemplate }">
-    <pngx-bs-icon name="plus-circle" class="me-1"></pngx-bs-icon><ng-container i18n>Add Template</ng-container>
-  </button>
-</pngx-page-header>
-
-<ul class="list-group">
-
-  <li class="list-group-item">
-    <div class="row">
-      <div class="col" i18n>Name</div>
-      <div class="col d-none d-sm-flex" i18n>Matching</div>
-      <div class="col d-none d-sm-flex" i18n>Zones</div>
-      <div class="col" i18n>Status</div>
-      <div class="col" i18n>Actions</div>
-    </div>
-  </li>
-
-  @if (loading() && templates().length === 0) {
-    <li class="list-group-item">
-      <output class="spinner-border spinner-border-sm me-2"></output>
-      <ng-container i18n>Loading...</ng-container>
-    </li>
-  }
-
-  @for (template of templates(); track template.id) {
-    <li class="list-group-item">
-      <div class="row fade" [class.show]="show()">
-        <div class="col d-flex align-items-center"><button class="btn btn-link p-0 text-start" type="button" (click)="editTemplate(template)" [disabled]="!userCanEdit(template)">{{template.name}}</button></div>
-        <div class="col d-flex align-items-center d-none d-sm-flex">{{getMatching(template)}}</div>
-        <div class="col d-flex align-items-center d-none d-sm-flex"><code>{{template.zones.length}}</code></div>
-        <div class="col d-flex align-items-center">
-          <div class="form-check form-switch mb-0">
-            <input type="checkbox" class="form-check-input cursor-pointer" [id]="template.id+'_enable'" [(ngModel)]="template.enabled" (change)="toggleTemplateEnabled(template)" [disabled]="!userCanEdit(template)" *pngxIfPermissions="{ action: PermissionAction.Change, type: PermissionType.OcrTemplate }">
-            <label class="form-check-label cursor-pointer" [for]="template.id+'_enable'">
-              <code> @if(template.enabled) { <ng-container i18n>Enabled</ng-container> } @else { <span i18n class="text-muted">Disabled</span> }</code>
-            </label>
-          </div>
-        </div>
-        <div class="col">
-
-          <div class="btn-group d-block d-sm-none">
-            <div ngbDropdown container="body" class="d-inline-block">
-              <button type="button" class="btn btn-link" id="actionsMenuMobile{{template.id}}" (click)="$event.stopPropagation()" ngbDropdownToggle>
-                <pngx-bs-icon name="three-dots-vertical"></pngx-bs-icon>
-              </button>
-              <div ngbDropdownMenu aria-labelledby="actionsMenuMobile{{template.id}}">
-                <button (click)="editTemplate(template)" [disabled]="!userCanEdit(template)" *pngxIfPermissions="{ action: PermissionAction.Change, type: PermissionType.OcrTemplate }" ngbDropdownItem i18n>Edit</button>
-                <button (click)="deleteTemplate(template)" [disabled]="!permissionsService.currentUserOwnsObject(template)" *pngxIfPermissions="{ action: PermissionAction.Delete, type: PermissionType.OcrTemplate }" ngbDropdownItem i18n>Delete</button>
-              </div>
-            </div>
-          </div>
-          <div class="btn-toolbar d-none d-sm-flex gap-2" role="toolbar">
-            <div class="btn-group">
-              <button *pngxIfPermissions="{ action: PermissionAction.Change, type: PermissionType.OcrTemplate }" [disabled]="!userCanEdit(template)" class="btn btn-sm btn-outline-secondary" type="button" (click)="editTemplate(template)">
-                <pngx-bs-icon width="1em" height="1em" name="pencil" class="me-1"></pngx-bs-icon><ng-container i18n>Edit</ng-container>
-              </button>
-              <button *pngxIfPermissions="{ action: PermissionAction.Delete, type: PermissionType.OcrTemplate }" [disabled]="!permissionsService.currentUserOwnsObject(template)" class="btn btn-sm btn-outline-danger" type="button" (click)="deleteTemplate(template)">
-                <pngx-bs-icon width="1em" height="1em" name="trash" class="me-1"></pngx-bs-icon><ng-container i18n>Delete</ng-container>
-              </button>
-            </div>
-          </div>
-        </div>
-      </div>
-    </li>
-  }
-  @if (!loading() && templates().length === 0) {
-    <li class="list-group-item" [class.show]="show()" i18n>No OCR templates defined.</li>
-  }
-</ul>

src-ui/src/app/components/manage/ocr-templates/ocr-templates.component.spec.ts

@@ -1,300 +0,0 @@
-import { provideHttpClient, withInterceptorsFromDi } from '@angular/common/http'
-import { provideHttpClientTesting } from '@angular/common/http/testing'
-import { ComponentFixture, TestBed } from '@angular/core/testing'
-import { By } from '@angular/platform-browser'
-import { NgbModal, NgbModalRef } from '@ng-bootstrap/ng-bootstrap'
-import { of, throwError } from 'rxjs'
-import { MATCH_LITERAL, MATCH_NONE } from 'src/app/data/matching-model'
-import { OcrTemplate } from 'src/app/data/ocr-template'
-import { User } from 'src/app/data/user'
-import { DirtyFormGuard } from 'src/app/guards/dirty-form.guard'
-import { PermissionsService } from 'src/app/services/permissions.service'
-import { OcrTemplateService } from 'src/app/services/rest/ocr-template.service'
-import { UserService } from 'src/app/services/rest/user.service'
-import { ToastService } from 'src/app/services/toast.service'
-import { ConfirmDialogComponent } from '../../common/confirm-dialog/confirm-dialog.component'
-import { OcrTemplateEditorComponent } from './ocr-template-editor/ocr-template-editor.component'
-import { OcrTemplatesComponent } from './ocr-templates.component'
-import { BootstrapIconComponent } from 'src/app/components/common/bootstrap-icon/bootstrap-icon.component'
-
-const templates: OcrTemplate[] = [
-  {
-    id: 1,
-    name: 'Invoices',
-    match: 'Northwind',
-    matching_algorithm: MATCH_LITERAL,
-    sample_document: null,
-    source_width: 0,
-    source_height: 0,
-    enabled: true,
-    zones: [],
-  },
-]
-
-describe('OcrTemplatesComponent', () => {
-  let component: OcrTemplatesComponent
-  let fixture: ComponentFixture<OcrTemplatesComponent>
-  let ocrTemplateService: OcrTemplateService
-  let modalService: NgbModal
-  let toastService: ToastService
-  let modal: NgbModalRef
-
-  beforeEach(() => {
-    TestBed.configureTestingModule({
-      imports: [OcrTemplatesComponent, BootstrapIconComponent],
-      providers: [
-        provideHttpClient(withInterceptorsFromDi()),
-        provideHttpClientTesting(),
-      ],
-    })
-
-    TestBed.inject(PermissionsService).initialize(
-      [
-        'view_ocrtemplate',
-        'add_ocrtemplate',
-        'change_ocrtemplate',
-        'delete_ocrtemplate',
-      ],
-      { id: 1, groups: [], is_superuser: false } as User
-    )
-    jest
-      .spyOn(TestBed.inject(UserService), 'listAll')
-      .mockReturnValue(of({ count: 0, all: [], results: [] }))
-
-    ocrTemplateService = TestBed.inject(OcrTemplateService)
-    jest
-      .spyOn(ocrTemplateService, 'listAll')
-      .mockReturnValue(of({ count: 1, all: [1], results: templates }))
-    modalService = TestBed.inject(NgbModal)
-    modalService.activeInstances.subscribe((m) => (modal = m[m.length - 1]))
-    toastService = TestBed.inject(ToastService)
-    fixture = TestBed.createComponent(OcrTemplatesComponent)
-    component = fixture.componentInstance
-    fixture.detectChanges()
-  })
-
-  afterEach(() => modalService.dismissAll())
-
-  it('should show templates with their matching', () => {
-    const text = fixture.nativeElement.textContent
-    expect(text).toContain('Invoices')
-    expect(text).toContain('Exact match: Northwind')
-
-    expect(
-      component.getMatching({ ...templates[0], matching_algorithm: MATCH_NONE })
-    ).toEqual('None')
-    expect(component.getMatching({ ...templates[0], match: '' })).toEqual('-')
-  })
-
-  it.each([
-    {
-      name: 'owned',
-      owner: 1,
-      user_can_change: true,
-      editable: true,
-      deletable: true,
-    },
-    {
-      name: 'unowned',
-      owner: null,
-      user_can_change: true,
-      editable: true,
-      deletable: true,
-    },
-    {
-      name: 'view-only shared',
-      owner: 2,
-      user_can_change: false,
-      editable: false,
-      deletable: false,
-    },
-    {
-      name: 'editable shared',
-      owner: 2,
-      user_can_change: true,
-      editable: true,
-      deletable: false,
-    },
-  ])(
-    'should respect permissions for $name templates',
-    async ({ owner, user_can_change, editable, deletable }) => {
-      const template = { ...templates[0], owner, user_can_change }
-      component.templates.set([template])
-      fixture.detectChanges()
-      await fixture.whenStable()
-
-      expect(fixture.nativeElement.querySelector('.text-start').disabled).toBe(
-        !editable
-      )
-      expect(
-        fixture.nativeElement.querySelector('.form-switch input').disabled
-      ).toBe(!editable)
-      const buttons = Array.from<HTMLButtonElement>(
-        fixture.nativeElement.querySelectorAll('button')
-      )
-      for (const button of buttons.filter(
-        (button) => button.textContent.trim() === 'Edit'
-      )) {
-        expect(button.disabled).toBe(!editable)
-      }
-      for (const button of buttons.filter(
-        (button) => button.textContent.trim() === 'Delete'
-      )) {
-        expect(button.disabled).toBe(!deletable)
-      }
-    }
-  )
-
-  it('should allow a superuser to manage another users template', () => {
-    TestBed.inject(PermissionsService).initialize([], {
-      id: 1,
-      is_superuser: true,
-    } as User)
-    component.templates.set([
-      { ...templates[0], owner: 2, user_can_change: false },
-    ])
-    fixture.detectChanges()
-    expect(fixture.nativeElement.querySelector('.text-start').disabled).toBe(
-      false
-    )
-    expect(
-      fixture.nativeElement.querySelector('.btn-outline-danger').disabled
-    ).toBe(false)
-  })
-
-  it('should not open mutation dialogs or patch a view-only template', () => {
-    const template = { ...templates[0], owner: 2, user_can_change: false }
-    const open = jest.spyOn(modalService, 'open')
-    const patch = jest.spyOn(ocrTemplateService, 'patch')
-    component.editTemplate(template)
-    component.toggleTemplateEnabled(template)
-    component.deleteTemplate(template)
-    expect(open).not.toHaveBeenCalled()
-    expect(patch).not.toHaveBeenCalled()
-  })
-
-  it('should require global edit permission even for an owned template', () => {
-    TestBed.inject(PermissionsService).initialize(['view_ocrtemplate'], {
-      id: 1,
-    } as User)
-    fixture.destroy()
-    fixture = TestBed.createComponent(OcrTemplatesComponent)
-    component = fixture.componentInstance
-    fixture.detectChanges()
-    expect(fixture.nativeElement.querySelector('.text-start').disabled).toBe(
-      true
-    )
-    expect(fixture.nativeElement.querySelector('.form-switch input')).toBeNull()
-  })
-
-  it('should support create, show notification on error / success', () => {
-    const toastErrorSpy = jest.spyOn(toastService, 'showError')
-    const toastSuccessSpy = jest.spyOn(toastService, 'showSuccess')
-    const reloadSpy = jest.spyOn(component, 'reload')
-
-    fixture.debugElement
-      .queryAll(By.css('pngx-page-header button'))
-      .find((button) => button.nativeElement.textContent.includes('Add'))
-      .triggerEventHandler('click')
-
-    const editor = modal.componentInstance as OcrTemplateEditorComponent
-    expect(editor).toBeInstanceOf(OcrTemplateEditorComponent)
-    expect(editor.object).toBeUndefined()
-
-    editor.failed.emit({ error: 'error creating template' })
-    expect(toastErrorSpy).toHaveBeenCalled()
-    expect(reloadSpy).not.toHaveBeenCalled()
-
-    editor.succeeded.emit(templates[0])
-    expect(toastSuccessSpy).toHaveBeenCalled()
-    expect(reloadSpy).toHaveBeenCalled()
-  })
-
-  it('should pass the template to the editor', () => {
-    component.editTemplate(templates[0])
-    expect(modal.componentInstance.object).toBe(templates[0])
-  })
-
-  it('should confirm closing the editor with unsaved changes', async () => {
-    const confirmSpy = jest
-      .spyOn(TestBed.inject(DirtyFormGuard), 'confirmChanges')
-      .mockReturnValue(of(false))
-    component.editTemplate()
-    const editor = modal.componentInstance as OcrTemplateEditorComponent
-    editor.ngOnInit()
-
-    modal.dismiss()
-    await fixture.whenStable()
-    expect(confirmSpy).not.toHaveBeenCalled()
-
-    component.editTemplate()
-    const dirtyEditor = modal.componentInstance as OcrTemplateEditorComponent
-    dirtyEditor.ngOnInit()
-    dirtyEditor.template.name = 'Changed'
-    modal.dismiss()
-    await fixture.whenStable()
-    expect(confirmSpy).toHaveBeenCalled()
-    expect(modalService.hasOpenModals()).toBe(true)
-
-    dirtyEditor.saving.set(true)
-    confirmSpy.mockClear()
-    modal.dismiss()
-    await fixture.whenStable()
-    expect(confirmSpy).not.toHaveBeenCalled()
-    expect(modalService.hasOpenModals()).toBe(true)
-  })
-
-  it('should only send the enabled flag when toggling', () => {
-    const patchSpy = jest
-      .spyOn(ocrTemplateService, 'patch')
-      .mockReturnValueOnce(throwError(() => new Error('error toggling')))
-      .mockReturnValueOnce(of(templates[0]))
-    const toastErrorSpy = jest.spyOn(toastService, 'showError')
-    const toastSuccessSpy = jest.spyOn(toastService, 'showSuccess')
-    const reloadSpy = jest.spyOn(component, 'reload')
-
-    const toggle = fixture.debugElement.query(By.css('.form-switch input'))
-    toggle.nativeElement.click()
-    expect(patchSpy).toHaveBeenCalledWith({ id: 1, enabled: false })
-    expect(toastErrorSpy).toHaveBeenCalled()
-    expect(reloadSpy).toHaveBeenCalledTimes(1)
-
-    component.toggleTemplateEnabled(templates[0])
-    expect(toastSuccessSpy).toHaveBeenCalled()
-    expect(reloadSpy).toHaveBeenCalledTimes(2)
-  })
-
-  it('should support delete, show notification on error / success', () => {
-    const toastErrorSpy = jest.spyOn(toastService, 'showError')
-    const toastSuccessSpy = jest.spyOn(toastService, 'showSuccess')
-    const deleteSpy = jest.spyOn(ocrTemplateService, 'delete')
-    const reloadSpy = jest.spyOn(component, 'reload')
-
-    component.deleteTemplate(templates[0])
-    const dialog = modal.componentInstance as ConfirmDialogComponent
-
-    deleteSpy.mockReturnValueOnce(throwError(() => new Error('error deleting')))
-    dialog.confirmClicked.emit()
-    expect(toastErrorSpy).toHaveBeenCalled()
-    expect(dialog.buttonsEnabled()).toBe(true)
-    expect(reloadSpy).not.toHaveBeenCalled()
-
-    deleteSpy.mockReturnValueOnce(of(true))
-    dialog.confirmClicked.emit()
-    expect(toastSuccessSpy).toHaveBeenCalled()
-    expect(reloadSpy).toHaveBeenCalled()
-  })
-
-  it.each([true, false])(
-    'reports the enabled state %s after the update succeeds',
-    (enabled) => {
-      const template = { ...templates[0], enabled }
-      jest.spyOn(ocrTemplateService, 'patch').mockReturnValue(of(template))
-      const toast = jest.spyOn(toastService, 'showSuccess')
-      component.toggleTemplateEnabled(template)
-      expect(toast).toHaveBeenCalledWith(
-        `${enabled ? 'Enabled' : 'Disabled'} OCR template "${template.name}"`
-      )
-    }
-  )
-})

src-ui/src/app/components/manage/ocr-templates/ocr-templates.component.ts

@@ -1,185 +0,0 @@
-import { Component, OnInit, inject, signal } from '@angular/core'
-import { FormsModule } from '@angular/forms'
-import { NgbDropdownModule, NgbModal } from '@ng-bootstrap/ng-bootstrap'
-import { BootstrapIconComponent } from 'src/app/components/common/bootstrap-icon/bootstrap-icon.component'
-import { firstValueFrom, takeUntil, tap } from 'rxjs'
-import { MATCH_NONE, MATCHING_ALGORITHMS } from 'src/app/data/matching-model'
-import { OcrTemplate } from 'src/app/data/ocr-template'
-import { IfPermissionsDirective } from 'src/app/directives/if-permissions.directive'
-import { DirtyFormGuard } from 'src/app/guards/dirty-form.guard'
-import {
-  PermissionAction,
-  PermissionType,
-  PermissionsService,
-} from 'src/app/services/permissions.service'
-import { OcrTemplateService } from 'src/app/services/rest/ocr-template.service'
-import { ToastService } from 'src/app/services/toast.service'
-import { ConfirmDialogComponent } from '../../common/confirm-dialog/confirm-dialog.component'
-import { PageHeaderComponent } from '../../common/page-header/page-header.component'
-import { LoadingComponentWithPermissions } from '../../loading-component/loading.component'
-import { OcrTemplateEditorComponent } from './ocr-template-editor/ocr-template-editor.component'
-
-@Component({
-  selector: 'pngx-ocr-templates',
-  templateUrl: './ocr-templates.component.html',
-  imports: [
-    PageHeaderComponent,
-    IfPermissionsDirective,
-    FormsModule,
-    NgbDropdownModule,
-    BootstrapIconComponent,
-  ],
-})
-export class OcrTemplatesComponent
-  extends LoadingComponentWithPermissions
-  implements OnInit
-{
-  private readonly ocrTemplateService = inject(OcrTemplateService)
-  public readonly permissionsService = inject(PermissionsService)
-  private readonly modalService = inject(NgbModal)
-  private readonly dirtyFormGuard = inject(DirtyFormGuard)
-  private readonly toastService = inject(ToastService)
-
-  public readonly templates = signal<OcrTemplate[]>([])
-
-  ngOnInit() {
-    this.reload()
-  }
-
-  reload() {
-    this.loading.set(true)
-    this.ocrTemplateService
-      .listAll()
-      .pipe(
-        takeUntil(this.unsubscribeNotifier),
-        tap((r) => this.templates.set(r.results))
-      )
-      .subscribe(() => {
-        this.show.set(true)
-        this.loading.set(false)
-      })
-  }
-
-  getMatching(template: OcrTemplate): string {
-    if (template.matching_algorithm === MATCH_NONE) {
-      return $localize`None`
-    }
-    if (!template.match) {
-      return '-'
-    }
-    const algorithm = MATCHING_ALGORITHMS.find(
-      (a) => a.id === template.matching_algorithm
-    )
-    return `${algorithm?.shortName}: ${template.match}`
-  }
-
-  editTemplate(template?: OcrTemplate) {
-    if (template && !this.userCanEdit(template)) return
-    const modal = this.modalService.open(OcrTemplateEditorComponent, {
-      backdrop: 'static',
-      keyboard: false,
-      size: 'xxl',
-      fullscreen: 'lg',
-      scrollable: true,
-      ariaLabelledBy: 'ocr-template-editor-title',
-      beforeDismiss: () => {
-        const editor: OcrTemplateEditorComponent = modal.componentInstance
-        if (editor.saving()) return false
-        if (!editor.isDirty) return true
-        return firstValueFrom(
-          this.dirtyFormGuard.confirmChanges(undefined, $localize`Close`)
-        )
-      },
-    })
-    modal.componentInstance.object = template
-    modal.componentInstance.succeeded
-      .pipe(takeUntil(this.unsubscribeNotifier))
-      .subscribe((saved: OcrTemplate) => {
-        this.toastService.showSuccess(
-          $localize`Saved OCR template "${saved.name}".`
-        )
-        this.ocrTemplateService.clearCache()
-        this.reload()
-      })
-    modal.componentInstance.failed
-      .pipe(takeUntil(this.unsubscribeNotifier))
-      .subscribe((e) => {
-        this.toastService.showError($localize`Error saving OCR template.`, e)
-      })
-  }
-
-  toggleTemplateEnabled(template: OcrTemplate) {
-    if (!this.userCanEdit(template)) return
-    this.ocrTemplateService
-      .patch({ id: template.id, enabled: template.enabled } as OcrTemplate)
-      .subscribe({
-        next: () => {
-          this.toastService.showSuccess(
-            template.enabled
-              ? $localize`Enabled OCR template "${template.name}"`
-              : $localize`Disabled OCR template "${template.name}"`
-          )
-          this.reload()
-        },
-        error: (e) => {
-          this.toastService.showError(
-            $localize`Error toggling OCR template "${template.name}".`,
-            e
-          )
-          this.reload()
-        },
-      })
-  }
-
-  deleteTemplate(template: OcrTemplate) {
-    if (
-      !this.permissionsService.currentUserCan(
-        PermissionAction.Delete,
-        PermissionType.OcrTemplate
-      ) ||
-      !this.permissionsService.currentUserOwnsObject(template)
-    )
-      return
-    const modal = this.modalService.open(ConfirmDialogComponent, {
-      backdrop: 'static',
-    })
-    modal.componentInstance.title = $localize`Confirm delete OCR template`
-    modal.componentInstance.messageBold = $localize`This operation will permanently delete this OCR template.`
-    modal.componentInstance.message = $localize`This operation cannot be undone.`
-    modal.componentInstance.btnClass = 'btn-danger'
-    modal.componentInstance.btnCaption = $localize`Proceed`
-    modal.componentInstance.confirmClicked.subscribe(() => {
-      modal.componentInstance.buttonsEnabled.set(false)
-      this.ocrTemplateService.delete(template).subscribe({
-        next: () => {
-          modal.close()
-          this.toastService.showSuccess(
-            $localize`Deleted OCR template "${template.name}".`
-          )
-          this.ocrTemplateService.clearCache()
-          this.reload()
-        },
-        error: (e) => {
-          modal.componentInstance.buttonsEnabled.set(true)
-          this.toastService.showError(
-            $localize`Error deleting OCR template "${template.name}".`,
-            e
-          )
-        },
-      })
-    })
-  }
-
-  userCanEdit(template: OcrTemplate): boolean {
-    return (
-      this.permissionsService.currentUserCan(
-        PermissionAction.Change,
-        PermissionType.OcrTemplate
-      ) &&
-      this.permissionsService.currentUserHasObjectPermissions(
-        PermissionAction.Change,
-        template
-      )
-    )
-  }
-}

src-ui/src/app/data/ocr-template.ts

@@ -1,115 +0,0 @@
-import { CustomFieldDataType } from './custom-field'
-import { MatchingModel } from './matching-model'
-import { ObjectWithPermissions } from './object-with-permissions'
-
-export enum OcrZoneTarget {
-  CustomField = 'custom_field',
-  Title = 'title',
-  Asn = 'asn',
-  Created = 'created',
-}
-
-export enum OcrZoneTransform {
-  None = 'none',
-  Strip = 'strip',
-  Uppercase = 'uppercase',
-  Lowercase = 'lowercase',
-  Numeric = 'numeric',
-  StripPunctuation = 'strip_punctuation',
-  Date = 'date',
-  QrCode = 'qr_code',
-}
-
-export const DEFAULT_OCR_ZONE_LANGUAGE = 'eng'
-
-/** The field a zone writes to, keyed by OcrTemplate.combine_formats. */
-export function getZoneFieldKey(zone: OcrTemplateZone): string | null {
-  if (zone.target !== OcrZoneTarget.CustomField) return zone.target
-  return zone.custom_field === null ? null : String(zone.custom_field)
-}
-
-/** Custom field types zone OCR can write to. See models.py OCR_SUPPORTED_FIELD_TYPES. */
-export const OCR_SUPPORTED_FIELD_TYPES: CustomFieldDataType[] = [
-  CustomFieldDataType.String,
-  CustomFieldDataType.Url,
-  CustomFieldDataType.Date,
-  CustomFieldDataType.Integer,
-  CustomFieldDataType.Float,
-  CustomFieldDataType.Monetary,
-  CustomFieldDataType.LongText,
-  CustomFieldDataType.Boolean,
-]
-
-export const OCR_BUILTIN_TARGETS = [
-  { id: OcrZoneTarget.Title, name: $localize`Title` },
-  { id: OcrZoneTarget.Asn, name: $localize`Archive serial number` },
-  { id: OcrZoneTarget.Created, name: $localize`Date created` },
-]
-
-export interface OcrTemplateZone {
-  id?: number
-  name: string
-  target: OcrZoneTarget
-  custom_field: number | null
-  page?: number
-  x: number
-  y: number
-  width: number
-  height: number
-  ocr_language: string
-  transform: OcrZoneTransform
-  date_format?: string
-  validation_regex: string
-  order: number
-  zone_source_width?: number
-  zone_source_height?: number
-}
-
-export interface OcrTemplate extends MatchingModel, ObjectWithPermissions {
-  name: string
-  sample_document: number | null
-  source_width: number
-  source_height: number
-  enabled: boolean
-  combine_formats?: Record<string, string>
-  created?: string
-  updated?: string
-  zones: OcrTemplateZone[]
-}
-
-export interface ZoneTestRequest {
-  name: string
-  x: number
-  y: number
-  width: number
-  height: number
-  page: number
-  ocr_language: string
-  transform: OcrZoneTransform
-  date_format?: string
-  validation_regex: string
-  zone_source_width?: number
-  zone_source_height?: number
-}
-
-export interface OcrZoneTestResult {
-  raw_text?: string | null
-  value?: string | null
-  regex?: string
-  regex_match?: boolean | null
-  error?: string
-}
-
-export interface OcrZoneRunResult {
-  template: string
-  zone: string
-  custom_field: string
-  value: string | number | boolean | null
-  reason?: string | null
-}
-
-export interface OcrZoneRunResponse {
-  status: 'completed' | 'skipped'
-  reason?: 'no_template'
-  results: OcrZoneRunResult[]
-}

src-ui/src/app/data/ui-settings.ts

@@ -35,7 +35,6 @@ export enum HideableSidebarItemID {
   SavedViews = 'saved_views',
   ShareLinks = 'share_links',
   Workflows = 'workflows',
-  OcrTemplates = 'ocr_templates',
   Mail = 'mail',
   Documentation = 'documentation',
 }

src-ui/src/app/guards/dirty-form.guard.ts

@@ -3,16 +3,12 @@ import { NgbModal } from '@ng-bootstrap/ng-bootstrap'
 import { DirtyCheckGuard } from '@ngneat/dirty-check-forms'
 import { Observable, Subject } from 'rxjs'
 import { ConfirmDialogComponent } from 'src/app/components/common/confirm-dialog/confirm-dialog.component'
-import { ActivatedRouteSnapshot } from '@angular/router'
 
 @Injectable({ providedIn: 'root' })
 export class DirtyFormGuard extends DirtyCheckGuard {
   private modalService = inject(NgbModal)
 
-  confirmChanges(
-    _currentRoute?: ActivatedRouteSnapshot,
-    leaveLabel: string = $localize`Leave page`
-  ): Observable<boolean> {
+  confirmChanges(): Observable<boolean> {
     let modal = this.modalService.open(ConfirmDialogComponent, {
       backdrop: 'static',
     })
@@ -20,7 +16,7 @@ export class DirtyFormGuard extends DirtyCheckGuard {
     modal.componentInstance.messageBold = $localize`You have unsaved changes.`
     modal.componentInstance.message = $localize`Are you sure you want to leave?`
     modal.componentInstance.btnClass = 'btn-warning'
-    modal.componentInstance.btnCaption = leaveLabel
+    modal.componentInstance.btnCaption = $localize`Leave page`
     modal.componentInstance.confirmClicked.subscribe(() => {
       modal.componentInstance.buttonsEnabled.set(false)
       modal.close()

src-ui/src/app/services/permissions.service.spec.ts

@@ -283,10 +283,6 @@ describe('PermissionsService', () => {
         'view_workflow',
         'change_workflow',
         'delete_workflow',
-        'add_ocrtemplate',
-        'view_ocrtemplate',
-        'change_ocrtemplate',
-        'delete_ocrtemplate',
         'add_customfield',
         'view_customfield',
         'change_customfield',

src-ui/src/app/services/permissions.service.ts

@@ -29,7 +29,6 @@ export enum PermissionType {
   ShareLinkBundle = '%s_sharelinkbundle',
   CustomField = '%s_customfield',
   Workflow = '%s_workflow',
-  OcrTemplate = '%s_ocrtemplate',
   ProcessedMail = '%s_processedmail',
   GlobalStatistics = '%s_global_statistics',
   SystemMonitoring = '%s_system_monitoring',

src-ui/src/app/services/rest/document.service.spec.ts

@@ -563,20 +563,6 @@ describe(`DocumentService`, () => {
 
     req.flush('task-id')
   })
-
-  it('should call appropriate api endpoint for running zone OCR', () => {
-    const url = `${environment.apiBaseUrl}${endpoint}/${documents[0].id}/run-zone-ocr/`
-    subscription = service.runZoneOcr(documents[0].id).subscribe()
-    let req = httpTestingController.expectOne(url)
-    expect(req.request.method).toEqual('POST')
-    expect(req.request.body).toEqual({})
-    req.flush({ status: 'completed', results: [] })
-
-    subscription = service.runZoneOcr(documents[0].id, 3).subscribe()
-    req = httpTestingController.expectOne(url)
-    expect(req.request.body).toEqual({ template: 3 })
-    req.flush({ status: 'completed', results: [] })
-  })
 })
 
 it('should construct sort fields respecting permissions', () => {

src-ui/src/app/services/rest/document.service.ts

@@ -12,7 +12,6 @@ import {
 import { DocumentMetadata } from 'src/app/data/document-metadata'
 import { DocumentSuggestions } from 'src/app/data/document-suggestions'
 import { FilterRule } from 'src/app/data/filter-rule'
-import { OcrZoneRunResponse } from 'src/app/data/ocr-template'
 import { Results, SelectionData } from 'src/app/data/results'
 import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
 import { queryParamsFromFilterRules } from '../../utils/query-params'
@@ -361,26 +360,6 @@ export class DocumentService extends AbstractPaperlessService<Document> {
     })
   }
 
-  runZoneOcrDocuments(
-    selection: DocumentSelectionQuery,
-    templateId: number | null = null
-  ) {
-    return this.http.post(this.getResourceUrl(null, 'run_zone_ocr'), {
-      ...selection,
-      ...(templateId ? { template: templateId } : {}),
-    })
-  }
-
-  runZoneOcr(
-    id: number,
-    templateId: number | null = null
-  ): Observable<OcrZoneRunResponse> {
-    return this.http.post<OcrZoneRunResponse>(
-      this.getResourceUrl(id, 'run-zone-ocr'),
-      templateId ? { template: templateId } : {}
-    )
-  }
-
   rotateDocuments(
     selection: DocumentSelectionQuery,
     degrees: number,

src-ui/src/app/services/rest/ocr-template.service.spec.ts

@@ -1,78 +0,0 @@
-import { provideHttpClient } from '@angular/common/http'
-import {
-  HttpTestingController,
-  provideHttpClientTesting,
-} from '@angular/common/http/testing'
-import { TestBed } from '@angular/core/testing'
-import { OcrZoneTransform, ZoneTestRequest } from 'src/app/data/ocr-template'
-import { environment } from 'src/environments/environment'
-import { OcrTemplateService } from './ocr-template.service'
-
-describe('OcrTemplateService', () => {
-  let service: OcrTemplateService
-  let http: HttpTestingController
-
-  beforeEach(() => {
-    TestBed.configureTestingModule({
-      providers: [provideHttpClient(), provideHttpClientTesting()],
-    })
-    service = TestBed.inject(OcrTemplateService)
-    http = TestBed.inject(HttpTestingController)
-  })
-
-  afterEach(() => http.verify())
-
-  it('builds page image URLs with zero-based page numbers', () => {
-    expect(service.getPageImageUrl(12, 0)).toBe(
-      `${environment.apiBaseUrl}ocr_templates/document-page-image/12/0/`
-    )
-    expect(service.getPageImageUrl(12, 2)).toBe(
-      `${environment.apiBaseUrl}ocr_templates/document-page-image/12/2/`
-    )
-  })
-
-  it('posts a zone test and returns the extraction result', () => {
-    const zone: ZoneTestRequest = {
-      name: 'Total',
-      x: 10,
-      y: 20,
-      width: 100,
-      height: 50,
-      page: -1,
-      ocr_language: 'eng',
-      transform: OcrZoneTransform.Numeric,
-      validation_regex: '\\d+',
-      zone_source_width: 1000,
-      zone_source_height: 1500,
-    }
-    const result = {
-      raw_text: 'Total: 123',
-      value: '123',
-      regex: '\\d+',
-      regex_match: true,
-    }
-    const next = jest.fn()
-    service.testZone(12, zone).subscribe(next)
-    const request = http.expectOne(
-      `${environment.apiBaseUrl}ocr_templates/test-zone/`
-    )
-    expect(request.request.method).toBe('POST')
-    expect(request.request.body).toEqual({ document: 12, zone })
-    request.flush(result)
-    expect(next).toHaveBeenCalledWith(result)
-  })
-
-  it('passes zone-test failures to the caller', () => {
-    const error = jest.fn()
-    service.testZone(12, {} as ZoneTestRequest).subscribe({ error })
-    http
-      .expectOne(`${environment.apiBaseUrl}ocr_templates/test-zone/`)
-      .flush(
-        { error: 'Invalid zone' },
-        { status: 400, statusText: 'Bad Request' }
-      )
-    expect(error).toHaveBeenCalledWith(
-      expect.objectContaining({ status: 400, error: { error: 'Invalid zone' } })
-    )
-  })
-})

src-ui/src/app/services/rest/ocr-template.service.ts

@@ -1,30 +0,0 @@
-import { Injectable } from '@angular/core'
-import { Observable } from 'rxjs'
-import {
-  OcrTemplate,
-  OcrZoneTestResult,
-  ZoneTestRequest,
-} from '../../data/ocr-template'
-import { AbstractPaperlessService } from './abstract-paperless-service'
-
-@Injectable({ providedIn: 'root' })
-export class OcrTemplateService extends AbstractPaperlessService<OcrTemplate> {
-  constructor() {
-    super()
-    this.resourceName = 'ocr_templates'
-  }
-
-  getPageImageUrl(docId: number, page: number): string {
-    return `${this.baseUrl}${this.resourceName}/document-page-image/${docId}/${page}/`
-  }
-
-  testZone(
-    docId: number,
-    zone: ZoneTestRequest
-  ): Observable<OcrZoneTestResult> {
-    return this.http.post<OcrZoneTestResult>(
-      `${this.baseUrl}${this.resourceName}/test-zone/`,
-      { document: docId, zone }
-    )
-  }
-}

src-ui/src/styles.scss

@@ -691,12 +691,6 @@ table.table {
   }
 }
 
-@media (min-width: 992px) {
-  .modal-xxl {
-    --bs-modal-width: min(1440px, calc(100vw - 2 * var(--bs-modal-margin)));
-  }
-}
-
 .toast {
   --bs-toast-max-width: var(--pngx-toast-max-width);
 }

src/documents/admin.py

@@ -1,7 +1,6 @@
 from django.conf import settings
 from django.contrib import admin
 from guardian.admin import GuardedModelAdmin
-from treenode.admin import TreeNodeModelAdmin
 
 from documents.models import Correspondent
 from documents.models import CustomField
@@ -29,7 +28,7 @@ class CorrespondentAdmin(GuardedModelAdmin):
     list_editable = ("match", "matching_algorithm")
 
 
-class TagAdmin(GuardedModelAdmin, TreeNodeModelAdmin):
+class TagAdmin(GuardedModelAdmin):
     list_display = ("name", "color", "match", "matching_algorithm")
     list_filter = ("matching_algorithm",)
     list_editable = ("color", "match", "matching_algorithm")

src/documents/apps.py

@@ -15,7 +15,6 @@ class DocumentsConfig(AppConfig):
         from documents.signals.handlers import add_to_index
         from documents.signals.handlers import run_workflows_added
         from documents.signals.handlers import run_workflows_updated
-        from documents.signals.handlers import run_zone_ocr_extraction
         from documents.signals.handlers import send_websocket_document_updated
         from documents.signals.handlers import set_correspondent
         from documents.signals.handlers import set_document_type
@@ -30,8 +29,6 @@ class DocumentsConfig(AppConfig):
         document_consumption_finished.connect(run_workflows_added)
         document_consumption_finished.connect(add_to_index)
         document_consumption_finished.connect(add_or_update_document_in_llm_index)
-        document_consumption_finished.connect(run_zone_ocr_extraction)
-
         document_updated.connect(run_workflows_updated)
         document_updated.connect(send_websocket_document_updated)
         document_updated.connect(add_or_update_document_in_llm_index)

src/documents/bulk_edit.py

@@ -33,7 +33,6 @@ from documents.models import CustomField
 from documents.models import CustomFieldInstance
 from documents.models import Document
 from documents.models import DocumentType
-from documents.models import OcrTemplate
 from documents.models import PaperlessTask
 from documents.models import StoragePath
 from documents.models import Tag
@@ -42,7 +41,6 @@ from documents.permissions import set_permissions_for_objects
 from documents.plugins.helpers import DocumentsStatusManager
 from documents.tasks import bulk_update_documents
 from documents.tasks import consume_file
-from documents.tasks import extract_zones
 from documents.tasks import remove_document_from_index
 from documents.tasks import update_document_content_maybe_archive_file
 from documents.versioning import get_latest_version_for_root
@@ -257,19 +255,13 @@ def modify_tags(
     affected_docs = list(qs.values_list("pk", flat=True))
     DocumentTagRelationship = Document.tags.through
 
-    # add with all ancestors
-    expanded_add_tags: set[int] = set()
-    add_tag_objects = Tag.objects.filter(pk__in=add_tags)
-    for t in add_tag_objects:
-        expanded_add_tags.add(int(t.id))
-        expanded_add_tags.update(int(pk) for pk in t.get_ancestors_pks())
-
-    # remove with all descendants
-    expanded_remove_tags: set[int] = set()
-    remove_tag_objects = Tag.objects.filter(pk__in=remove_tags)
-    for t in remove_tag_objects:
-        expanded_remove_tags.add(int(t.id))
-        expanded_remove_tags.update(int(pk) for pk in t.get_descendants_pks())
+    hierarchy = Tag.get_hierarchy()
+    expanded_add_tags = hierarchy.with_ancestors(
+        Tag.objects.filter(pk__in=add_tags).values_list("pk", flat=True),
+    )
+    expanded_remove_tags = hierarchy.with_descendants(
+        Tag.objects.filter(pk__in=remove_tags).values_list("pk", flat=True),
+    )
 
     with transaction.atomic():
         if expanded_remove_tags:
@@ -1199,22 +1191,3 @@ def remove_doclink(
         target_doc_field_instance.value.remove(document.id)
         target_doc_field_instance.save()
     Document.objects.filter(id=target_doc_id).update(modified=timezone.now())
-
-
-def run_zone_ocr(
-    doc_ids: list[int],
-    *,
-    template: OcrTemplate | None = None,
-) -> Literal["OK"]:
-    """
-    Queue zone OCR for the given documents, with the given template or with the
-    templates that match each document's content when its task runs.
-    """
-    template_id = template.pk if template is not None else None
-    for document_id in doc_ids:
-        extract_zones.apply_async(
-            kwargs={"document_id": document_id, "template_id": template_id},
-            headers={"trigger_source": PaperlessTask.TriggerSource.MANUAL},
-        )
-
-    return "OK"

src/documents/management/commands/document_importer.py

@@ -108,6 +108,24 @@ def _deserialize_record(
         ) from e
 
     for field_name, field_value in record.get("fields", {}).items():
+        # Older exports include django-treenode's derived bookkeeping. The
+        # parent FK is authoritative; accept only these known removed fields.
+        if Model is Tag and field_name in {
+            "tn_ancestors_count",
+            "tn_ancestors_pks",
+            "tn_children_count",
+            "tn_children_pks",
+            "tn_depth",
+            "tn_descendants_count",
+            "tn_descendants_pks",
+            "tn_index",
+            "tn_level",
+            "tn_order",
+            "tn_priority",
+            "tn_siblings_count",
+            "tn_siblings_pks",
+        }:
+            continue
         field = Model._meta.get_field(field_name)
         remote = field.remote_field
 

src/documents/migrations/0028_ocrtemplate_ocrtemplatezone.py

@@ -1,311 +0,0 @@
-# Generated by Django 5.2.17 on 2026-10-20 20:29
-
-import django.core.validators
-import django.db.models.deletion
-import django.utils.timezone
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0027_documentbarcode"),
-        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
-    ]
-
-    operations = [
-        migrations.CreateModel(
-            name="OcrTemplate",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                ("name", models.CharField(max_length=128, verbose_name="name")),
-                (
-                    "match",
-                    models.CharField(blank=True, max_length=256, verbose_name="match"),
-                ),
-                (
-                    "matching_algorithm",
-                    models.PositiveSmallIntegerField(
-                        choices=[
-                            (0, "None"),
-                            (1, "Any word"),
-                            (2, "All words"),
-                            (3, "Exact match"),
-                            (4, "Regular expression"),
-                            (5, "Fuzzy word"),
-                            (6, "Automatic"),
-                        ],
-                        default=1,
-                        verbose_name="matching algorithm",
-                    ),
-                ),
-                (
-                    "is_insensitive",
-                    models.BooleanField(default=True, verbose_name="is insensitive"),
-                ),
-                (
-                    "source_width",
-                    models.PositiveIntegerField(
-                        help_text="Width of the image the zones were drawn on (px)",
-                        validators=[django.core.validators.MinValueValidator(1)],
-                        verbose_name="source width",
-                    ),
-                ),
-                (
-                    "source_height",
-                    models.PositiveIntegerField(
-                        help_text="Height of the image the zones were drawn on (px)",
-                        validators=[django.core.validators.MinValueValidator(1)],
-                        verbose_name="source height",
-                    ),
-                ),
-                ("enabled", models.BooleanField(default=True, verbose_name="enabled")),
-                (
-                    "combine_formats",
-                    models.JSONField(
-                        blank=True,
-                        default=dict,
-                        help_text="Per-target format strings for combining several zones into one field, keyed by target (custom field id, or 'title'/'asn'/'created'). Tokens like {Zone Name} are replaced with that zone's value.",
-                        verbose_name="combine formats",
-                    ),
-                ),
-                (
-                    "created",
-                    models.DateTimeField(
-                        db_index=True,
-                        default=django.utils.timezone.now,
-                        editable=False,
-                        verbose_name="created",
-                    ),
-                ),
-                (
-                    "updated",
-                    models.DateTimeField(auto_now=True, verbose_name="updated"),
-                ),
-                (
-                    "owner",
-                    models.ForeignKey(
-                        blank=True,
-                        default=None,
-                        null=True,
-                        on_delete=django.db.models.deletion.SET_NULL,
-                        to=settings.AUTH_USER_MODEL,
-                        verbose_name="owner",
-                    ),
-                ),
-                (
-                    "sample_document",
-                    models.ForeignKey(
-                        blank=True,
-                        help_text="Document used for previewing zones in the editor",
-                        null=True,
-                        on_delete=django.db.models.deletion.SET_NULL,
-                        related_name="+",
-                        to="documents.document",
-                        verbose_name="sample document",
-                    ),
-                ),
-            ],
-            options={
-                "verbose_name": "OCR template",
-                "verbose_name_plural": "OCR templates",
-                "ordering": ("name",),
-                "abstract": False,
-            },
-        ),
-        migrations.CreateModel(
-            name="OcrTemplateZone",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                (
-                    "name",
-                    models.CharField(
-                        help_text="Descriptive name for this zone (e.g. 'Invoice Number')",
-                        max_length=128,
-                        verbose_name="zone name",
-                    ),
-                ),
-                (
-                    "target",
-                    models.CharField(
-                        choices=[
-                            ("custom_field", "Custom field"),
-                            ("title", "Title"),
-                            ("asn", "Archive serial number"),
-                            ("created", "Date created"),
-                        ],
-                        default="custom_field",
-                        help_text="Where the extracted value is written: a custom field, or a built-in document field (title, ASN, created date)",
-                        max_length=20,
-                        verbose_name="target",
-                    ),
-                ),
-                (
-                    "page",
-                    models.IntegerField(
-                        blank=True,
-                        help_text="Page (1 = first, -1 = last; blank uses the template default)",
-                        null=True,
-                        verbose_name="page",
-                    ),
-                ),
-                (
-                    "x",
-                    models.PositiveIntegerField(
-                        help_text="Left edge (px)",
-                        verbose_name="x",
-                    ),
-                ),
-                (
-                    "y",
-                    models.PositiveIntegerField(
-                        help_text="Top edge (px)",
-                        verbose_name="y",
-                    ),
-                ),
-                (
-                    "width",
-                    models.PositiveIntegerField(
-                        help_text="Zone width (px)",
-                        validators=[django.core.validators.MinValueValidator(1)],
-                        verbose_name="width",
-                    ),
-                ),
-                (
-                    "height",
-                    models.PositiveIntegerField(
-                        help_text="Zone height (px)",
-                        validators=[django.core.validators.MinValueValidator(1)],
-                        verbose_name="height",
-                    ),
-                ),
-                (
-                    "zone_source_width",
-                    models.PositiveIntegerField(
-                        blank=True,
-                        help_text="Width of the page image this zone was drawn on (px). Falls back to template source_width if unset.",
-                        null=True,
-                        verbose_name="zone source width",
-                    ),
-                ),
-                (
-                    "zone_source_height",
-                    models.PositiveIntegerField(
-                        blank=True,
-                        help_text="Height of the page image this zone was drawn on (px). Falls back to template source_height if unset.",
-                        null=True,
-                        verbose_name="zone source height",
-                    ),
-                ),
-                (
-                    "ocr_language",
-                    models.CharField(
-                        default="eng",
-                        help_text="Tesseract language code(s), e.g. 'deu+eng'",
-                        max_length=20,
-                        verbose_name="OCR language",
-                    ),
-                ),
-                (
-                    "transform",
-                    models.CharField(
-                        choices=[
-                            ("none", "None"),
-                            ("strip", "Strip whitespace"),
-                            ("uppercase", "Uppercase"),
-                            ("lowercase", "Lowercase"),
-                            ("numeric", "Numeric only"),
-                            (
-                                "strip_punctuation",
-                                "Remove leading/trailing punctuation",
-                            ),
-                            ("date", "Parse date"),
-                            ("qr_code", "Read QR/barcode"),
-                        ],
-                        default="strip",
-                        max_length=20,
-                        verbose_name="transform",
-                    ),
-                ),
-                (
-                    "date_format",
-                    models.CharField(
-                        blank=True,
-                        default="",
-                        help_text="Python strptime format for the 'Parse date' transform (e.g. %d.%m.%Y). Blank = auto-detect.",
-                        max_length=64,
-                        verbose_name="date format",
-                    ),
-                ),
-                (
-                    "validation_regex",
-                    models.CharField(
-                        blank=True,
-                        default="",
-                        help_text="Optional regex pattern — extracted text is only accepted if it matches",
-                        max_length=256,
-                        verbose_name="validation regex",
-                    ),
-                ),
-                ("order", models.PositiveIntegerField(default=0, verbose_name="order")),
-                (
-                    "custom_field",
-                    models.ForeignKey(
-                        blank=True,
-                        help_text="Target custom field (only used when target is 'custom_field')",
-                        null=True,
-                        on_delete=django.db.models.deletion.CASCADE,
-                        related_name="ocr_zones",
-                        to="documents.customfield",
-                        verbose_name="custom field",
-                    ),
-                ),
-                (
-                    "template",
-                    models.ForeignKey(
-                        on_delete=django.db.models.deletion.CASCADE,
-                        related_name="zones",
-                        to="documents.ocrtemplate",
-                        verbose_name="template",
-                    ),
-                ),
-            ],
-            options={
-                "verbose_name": "OCR template zone",
-                "verbose_name_plural": "OCR template zones",
-                "ordering": ("template", "order"),
-            },
-        ),
-        migrations.AddConstraint(
-            model_name="ocrtemplate",
-            constraint=models.UniqueConstraint(
-                fields=("name", "owner"),
-                name="documents_ocrtemplate_unique_name_owner",
-            ),
-        ),
-        migrations.AddConstraint(
-            model_name="ocrtemplate",
-            constraint=models.UniqueConstraint(
-                condition=models.Q(("owner__isnull", True)),
-                fields=("name",),
-                name="documents_ocrtemplate_name_uniq",
-            ),
-        ),
-    ]

src/documents/migrations/0028_replace_tag_tree_fields.py

@@ -0,0 +1,64 @@
+# Generated by Django 5.2.17 on 2026-10-28 22:54
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0027_documentbarcode"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_ancestors_count",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_ancestors_pks",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_children_count",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_children_pks",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_depth",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_descendants_count",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_descendants_pks",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_index",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_level",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_order",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_priority",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_siblings_count",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_siblings_pks",
+        ),
+    ]

src/documents/models.py

@@ -1,6 +1,7 @@
 import datetime
 import uuid
 from pathlib import Path
+from typing import TYPE_CHECKING
 from typing import Final
 
 import pathvalidate
@@ -14,7 +15,6 @@ from django.db import models
 from django.utils import timezone
 from django.utils.translation import gettext_lazy as _
 from multiselectfield import MultiSelectField
-from treenode.models import TreeNodeModel
 
 if settings.AUDIT_LOG_ENABLED:
     from auditlog.registry import auditlog
@@ -29,6 +29,9 @@ from django_softdelete.models import SoftDeleteModel
 from documents.data_models import DocumentSource
 from documents.parsers import get_default_file_extension
 
+if TYPE_CHECKING:
+    from documents.tag_hierarchy import TagHierarchy
+
 
 class ModelWithOwner(models.Model):
     owner = models.ForeignKey(
@@ -100,7 +103,17 @@ class Correspondent(MatchingModel):
         verbose_name_plural = _("correspondents")
 
 
-class Tag(MatchingModel, TreeNodeModel):
+class Tag(MatchingModel):
+    # Keep the existing column and reverse relation during the transition.
+    tn_parent = models.ForeignKey(
+        "self",
+        blank=True,
+        null=True,
+        on_delete=models.CASCADE,
+        related_name="tn_children",
+        verbose_name=_("Parent"),
+    )
+
     color = models.CharField(_("color"), max_length=7, default="#a6cee3")
     # Maximum allowed nesting depth for tags (root = 1, max depth = 5)
     MAX_NESTING_DEPTH: Final[int] = 5
@@ -114,27 +127,72 @@ class Tag(MatchingModel, TreeNodeModel):
         ),
     )
 
-    class Meta(MatchingModel.Meta, TreeNodeModel.Meta):
+    class Meta(MatchingModel.Meta):
         verbose_name = _("tag")
         verbose_name_plural = _("tags")
 
+    @classmethod
+    def get_hierarchy(cls) -> "TagHierarchy":
+        """Read the tag hierarchy in one query, ready to use across multiple tags."""
+        from documents.tag_hierarchy import TagHierarchy
+
+        return TagHierarchy(cls.objects.values_list("pk", "tn_parent_id"))
+
+    @property
+    def parent_pk(self) -> int | None:
+        return self.tn_parent_id
+
+    def get_parent(self) -> "Tag | None":
+        return self.tn_parent
+
+    def get_ancestors_pks(self) -> list[int]:
+        """Return ancestor IDs ordered from root to parent.
+
+        Each call reads the full hierarchy. Use Tag.get_hierarchy() once and
+        reuse it when working with several tags.
+        """
+        return self.get_hierarchy().ancestors(self.tn_parent_id)
+
+    def get_ancestors(self) -> list["Tag"]:
+        """Return ancestors ordered from root to parent.
+
+        Each call reads the full hierarchy. Use Tag.get_hierarchy() once and
+        reuse it when working with several tags.
+        """
+        ids = self.get_ancestors_pks()
+        tags = self.__class__.objects.in_bulk(ids)
+        return [tags[pk] for pk in ids]
+
+    def get_descendants_pks(self) -> set[int]:
+        """Return all descendant IDs.
+
+        Each call reads the full hierarchy. Use Tag.get_hierarchy() once and
+        reuse it when working with several tags.
+        """
+        return self.get_hierarchy().descendants([self.pk])
+
+    def get_descendants(self) -> "models.QuerySet[Tag]":
+        """Return a queryset of all descendants.
+
+        Each call reads the full hierarchy. Use Tag.get_hierarchy() once and
+        reuse it when working with several tags.
+        """
+        return self.__class__.objects.filter(pk__in=self.get_descendants_pks())
+
+    def get_children_queryset(self) -> "models.QuerySet[Tag]":
+        return self.__class__.objects.filter(tn_parent_id=self.pk)
+
     def clean(self) -> None:
-        # Prevent self-parenting and assigning a descendant as parent
-        parent = self.get_parent()
-        if parent == self:
-            raise ValidationError({"parent": _("Cannot set itself as parent.")})
-        if parent and self.pk is not None and self.is_ancestor_of(parent):
-            raise ValidationError({"parent": _("Cannot set parent to a descendant.")})
-
-        # Enforce maximum nesting depth
-        new_parent_depth = 0
-        if parent:
-            new_parent_depth = parent.get_ancestors_count() + 1
-
-        height = 0 if self.pk is None else self.get_depth()
-        deepest_new_depth = (new_parent_depth + 1) + height
-        if deepest_new_depth > self.MAX_NESTING_DEPTH:
-            raise ValidationError({"parent": _("Maximum nesting depth exceeded.")})
+        hierarchy = self.get_hierarchy()
+        if self.pk is not None and self.tn_parent_id == self.pk:
+            raise ValidationError({"tn_parent": _("Cannot set itself as parent.")})
+        ancestors = hierarchy.ancestors(self.tn_parent_id)
+        if self.pk is not None and self.pk in ancestors:
+            raise ValidationError(
+                {"tn_parent": _("Cannot set parent to a descendant.")},
+            )
+        if len(ancestors) + 1 + hierarchy.height(self.pk) > self.MAX_NESTING_DEPTH:
+            raise ValidationError({"tn_parent": _("Maximum nesting depth exceeded.")})
 
         return super().clean()
 
@@ -539,10 +597,7 @@ class Document(SoftDeleteModel, ModelWithOwner):  # type: ignore[django-manager-
         return self.created
 
     def add_nested_tags(self, tags) -> None:
-        tag_ids = set()
-        for tag in tags:
-            tag_ids.add(tag.id)
-            tag_ids.update(tag.get_ancestors_pks())
+        tag_ids = Tag.get_hierarchy().with_ancestors(tag.pk for tag in tags)
 
         tags_to_add = self.tags.model.objects.filter(id__in=tag_ids)
         self.tags.add(*tags_to_add)
@@ -2149,215 +2204,3 @@ class WorkflowRun(SoftDeleteModel):
 
     def __str__(self) -> str:
         return f"WorkflowRun of {self.workflow} at {self.run_at} on {self.document}"
-
-
-class OcrTemplate(MatchingModel):
-    """Matching rules and extraction zones for documents with a common layout."""
-
-    source_width = models.PositiveIntegerField(
-        _("source width"),
-        validators=[MinValueValidator(1)],
-        help_text=_("Width of the image the zones were drawn on (px)"),
-    )
-
-    source_height = models.PositiveIntegerField(
-        _("source height"),
-        validators=[MinValueValidator(1)],
-        help_text=_("Height of the image the zones were drawn on (px)"),
-    )
-
-    sample_document = models.ForeignKey(
-        "documents.Document",
-        on_delete=models.SET_NULL,
-        null=True,
-        blank=True,
-        related_name="+",
-        verbose_name=_("sample document"),
-        help_text=_("Document used for previewing zones in the editor"),
-    )
-
-    enabled = models.BooleanField(_("enabled"), default=True)
-
-    combine_formats = models.JSONField(
-        _("combine formats"),
-        default=dict,
-        blank=True,
-        help_text=_(
-            "Per-target format strings for combining several zones into one "
-            "field, keyed by target (custom field id, or 'title'/'asn'/'created'). "
-            "Tokens like {Zone Name} are replaced with that zone's value.",
-        ),
-    )
-
-    created = models.DateTimeField(
-        _("created"),
-        default=timezone.now,
-        db_index=True,
-        editable=False,
-    )
-
-    updated = models.DateTimeField(
-        _("updated"),
-        auto_now=True,
-    )
-
-    class Meta(MatchingModel.Meta):
-        verbose_name = _("OCR template")
-        verbose_name_plural = _("OCR templates")
-
-
-class OcrTemplateZone(models.Model):
-    """A page region and the field its extracted value is written to."""
-
-    template = models.ForeignKey(
-        OcrTemplate,
-        on_delete=models.CASCADE,
-        related_name="zones",
-        verbose_name=_("template"),
-    )
-
-    name = models.CharField(
-        _("zone name"),
-        max_length=128,
-        help_text=_("Descriptive name for this zone (e.g. 'Invoice Number')"),
-    )
-
-    class TargetType(models.TextChoices):
-        CUSTOM_FIELD = ("custom_field", _("Custom field"))
-        TITLE = ("title", _("Title"))
-        ASN = ("asn", _("Archive serial number"))
-        CREATED = ("created", _("Date created"))
-
-    target = models.CharField(
-        _("target"),
-        max_length=20,
-        choices=TargetType.choices,
-        default=TargetType.CUSTOM_FIELD,
-        help_text=_(
-            "Where the extracted value is written: a custom field, or a "
-            "built-in document field (title, ASN, created date)",
-        ),
-    )
-
-    custom_field = models.ForeignKey(
-        "documents.CustomField",
-        on_delete=models.CASCADE,
-        related_name="ocr_zones",
-        verbose_name=_("custom field"),
-        null=True,
-        blank=True,
-        help_text=_("Target custom field (only used when target is 'custom_field')"),
-    )
-
-    page = models.IntegerField(
-        _("page"),
-        null=True,
-        blank=True,
-        help_text=_("Page (1 = first, -1 = last; blank uses the template default)"),
-    )
-
-    x = models.PositiveIntegerField(_("x"), help_text=_("Left edge (px)"))
-    y = models.PositiveIntegerField(_("y"), help_text=_("Top edge (px)"))
-    width = models.PositiveIntegerField(
-        _("width"),
-        validators=[MinValueValidator(1)],
-        help_text=_("Zone width (px)"),
-    )
-    height = models.PositiveIntegerField(
-        _("height"),
-        validators=[MinValueValidator(1)],
-        help_text=_("Zone height (px)"),
-    )
-
-    # Mixed-size PDFs need each zone's original page dimensions for scaling.
-    zone_source_width = models.PositiveIntegerField(
-        _("zone source width"),
-        null=True,
-        blank=True,
-        help_text=_(
-            "Width of the page image this zone was drawn on (px). "
-            "Falls back to template source_width if unset.",
-        ),
-    )
-    zone_source_height = models.PositiveIntegerField(
-        _("zone source height"),
-        null=True,
-        blank=True,
-        help_text=_(
-            "Height of the page image this zone was drawn on (px). "
-            "Falls back to template source_height if unset.",
-        ),
-    )
-
-    ocr_language = models.CharField(
-        _("OCR language"),
-        max_length=20,
-        default="eng",
-        help_text=_("Tesseract language code(s), e.g. 'deu+eng'"),
-    )
-
-    class TransformType(models.TextChoices):
-        NONE = ("none", _("None"))
-        STRIP = ("strip", _("Strip whitespace"))
-        UPPERCASE = ("uppercase", _("Uppercase"))
-        LOWERCASE = ("lowercase", _("Lowercase"))
-        NUMERIC = ("numeric", _("Numeric only"))
-        STRIP_PUNCTUATION = (
-            "strip_punctuation",
-            _("Remove leading/trailing punctuation"),
-        )
-        DATE = ("date", _("Parse date"))
-        QR_CODE = ("qr_code", _("Read QR/barcode"))
-
-    transform = models.CharField(
-        _("transform"),
-        max_length=20,
-        choices=TransformType.choices,
-        default=TransformType.STRIP,
-    )
-
-    date_format = models.CharField(
-        _("date format"),
-        max_length=64,
-        blank=True,
-        default="",
-        help_text=_(
-            "Python strptime format for the 'Parse date' transform "
-            "(e.g. %d.%m.%Y). Blank = auto-detect.",
-        ),
-    )
-
-    validation_regex = models.CharField(
-        _("validation regex"),
-        max_length=256,
-        blank=True,
-        default="",
-        help_text=_(
-            "Optional regex pattern — extracted text is only accepted if it matches",
-        ),
-    )
-
-    order = models.PositiveIntegerField(_("order"), default=0)
-
-    class Meta:
-        ordering = ("template", "order")
-        verbose_name = _("OCR template zone")
-        verbose_name_plural = _("OCR template zones")
-
-    def __str__(self) -> str:
-        return f"{self.template.name} -> {self.name}"
-
-
-# Document links and select fields require object references, not OCR text.
-OCR_SUPPORTED_FIELD_TYPES = frozenset(
-    {
-        CustomField.FieldDataType.STRING,
-        CustomField.FieldDataType.URL,
-        CustomField.FieldDataType.DATE,
-        CustomField.FieldDataType.INT,
-        CustomField.FieldDataType.FLOAT,
-        CustomField.FieldDataType.MONETARY,
-        CustomField.FieldDataType.LONG_TEXT,
-        CustomField.FieldDataType.BOOL,
-    },
-)

src/documents/permissions.py

@@ -31,6 +31,7 @@ from guardian.core import ObjectPermissionChecker
 from guardian.models import GroupObjectPermission
 from guardian.models import UserObjectPermission
 from rest_framework.permissions import BasePermission
+from rest_framework.permissions import DjangoModelPermissions
 from rest_framework.permissions import DjangoObjectPermissions
 
 from documents.models import Document
@@ -63,6 +64,17 @@ class PermissionGranteesUpdate(TypedDict, total=False):
 PermissionsSpec: TypeAlias = Mapping[PermissionAction, PermissionGranteesUpdate]
 
 
+class PaperlessModelPermissions(DjangoModelPermissions):
+    """Require basic global model permissions."""
+
+    perms_map = {
+        **DjangoModelPermissions.perms_map,
+        "GET": ["%(app_label)s.view_%(model_name)s"],
+        "OPTIONS": ["%(app_label)s.view_%(model_name)s"],
+        "HEAD": ["%(app_label)s.view_%(model_name)s"],
+    }
+
+
 class PaperlessObjectPermissions(DjangoObjectPermissions):
     """
     A permissions backend that checks for object-level permissions
@@ -576,12 +588,9 @@ def annotate_document_count_by_ids(
                        or CustomFieldInstance)
         related_object_field: field on the relation pointing back to queryset pk
         document_ids: the document ids to count against -- a concrete list/set,
-                       or a simple (already resolved) queryset of ids. Callers
-                       that need this filtered by a complex condition (e.g. a
-                       permission check) should resolve it to a concrete list
-                       first if the same ids will be reused across multiple
-                       calls, rather than passing the complex queryset itself
-                       into each -- see ``_get_selection_data_for_queryset``.
+                       or a simple (already resolved) queryset of ids. Keep
+                       the list small: it is embedded in the statement as
+                       literal parameters.
         target_field: field on the relation pointing to Document id
     """
 

src/documents/regex.py

@@ -77,33 +77,6 @@ def safe_regex_match(pattern: str, text: str, *, flags: int = 0):
         return None
 
 
-def safe_regex_fullmatch(pattern: str, text: str, *, flags: int = 0):
-    """
-    Run a regex full match with a timeout. Returns a match object or None.
-    Validation errors and timeouts are logged and treated as no match.
-    """
-
-    try:
-        validate_regex_pattern(pattern)
-        compiled = regex.compile(pattern, flags=flags)
-    except (regex.error, ValueError) as exc:
-        logger.exception(
-            "Error while processing regular expression %s: %s",
-            textwrap.shorten(pattern, width=80, placeholder="…"),
-            exc,
-        )
-        return None
-
-    try:
-        return compiled.fullmatch(text, timeout=REGEX_TIMEOUT_SECONDS)
-    except TimeoutError:
-        logger.warning(
-            "Regular expression matching timed out for pattern %s",
-            textwrap.shorten(pattern, width=80, placeholder="…"),
-        )
-        return None
-
-
 def safe_regex_sub(pattern: str, repl: str, text: str, *, flags: int = 0) -> str | None:
     """
     Run a regex substitution with a timeout. Returns the substituted string,

src/documents/serialisers.py

@@ -23,7 +23,6 @@ from django.core.validators import MaxValueValidator
 from django.core.validators import MinValueValidator
 from django.core.validators import RegexValidator
 from django.core.validators import integer_validator
-from django.db import transaction
 from django.db.models import Count
 from django.db.models import Q
 from django.db.models.functions import Lower
@@ -55,7 +54,6 @@ if settings.AUDIT_LOG_ENABLED:
 from documents import bulk_edit
 from documents.data_models import DocumentSource
 from documents.filters import CustomFieldQueryParser
-from documents.models import OCR_SUPPORTED_FIELD_TYPES
 from documents.models import Correspondent
 from documents.models import CustomField
 from documents.models import CustomFieldInstance
@@ -64,8 +62,6 @@ from documents.models import DocumentBarcode
 from documents.models import DocumentType
 from documents.models import MatchingModel
 from documents.models import Note
-from documents.models import OcrTemplate
-from documents.models import OcrTemplateZone
 from documents.models import PaperlessTask
 from documents.models import SavedView
 from documents.models import SavedViewFilterRule
@@ -593,7 +589,7 @@ class TagSerializer(MatchingModelSerializer, OwnedObjectSerializer):
 
     text_color = serializers.SerializerMethodField()
 
-    # map to treenode's tn_parent
+    # Preserve the public API parent field.
     parent = serializers.PrimaryKeyRelatedField(
         queryset=Tag.objects.all(),
         allow_null=True,
@@ -696,7 +692,9 @@ class TagSerializer(MatchingModelSerializer, OwnedObjectSerializer):
                 self.instance.clean()
             except ValidationError as e:
                 logger.debug("Tag parent validation failed: %s", e)
-                raise e
+                raise serializers.ValidationError(
+                    {"parent": e.message_dict["tn_parent"]},
+                ) from e
             finally:
                 self.instance.tn_parent = original_parent
         else:
@@ -706,7 +704,9 @@ class TagSerializer(MatchingModelSerializer, OwnedObjectSerializer):
                 temp.clean()
             except ValidationError as e:
                 logger.debug("Tag parent validation failed: %s", e)
-                raise e
+                raise serializers.ValidationError(
+                    {"parent": e.message_dict["tn_parent"]},
+                ) from e
 
         return super().validate(attrs)
 
@@ -1202,61 +1202,35 @@ class DocumentSerializer(
                             doc_id,
                         )
         if "tags" in validated_data:
-            # Respect tag hierarchy on updates:
-            # - Adding a child adds its ancestors
-            # - Removing a parent removes all its descendants
-            prev_tags = set(instance.tags.all())
-            requested_tags = set(validated_data["tags"])
+            hierarchy = Tag.get_hierarchy()
+            previous_ids = set(instance.tags.values_list("pk", flat=True))
+            requested_ids = {tag.pk for tag in validated_data["tags"]}
+            required_ids = hierarchy.with_ancestors(requested_ids - previous_ids)
+            blocked_ids = hierarchy.with_descendants(previous_ids - requested_ids)
+            blocked_ids.difference_update(required_ids)
+            final_ids = hierarchy.with_ancestors(requested_ids) - blocked_ids
+            validated_data["tags"] = list(Tag.objects.filter(pk__in=final_ids))
 
-            # Tags newly added in this update and the ancestors they require
-            added_tags = requested_tags - prev_tags
-            required_by_add_tags = set(added_tags)
-            for t in added_tags:
-                required_by_add_tags.update(t.get_ancestors())
-
-            # Tags being removed in this update and all descendants, except
-            # those required by a tag that is being added in this same update
-            removed_tags = prev_tags - requested_tags
-            blocked_tags = set(removed_tags)
-            for t in removed_tags:
-                blocked_tags.update(t.get_descendants())
-            blocked_tags.difference_update(required_by_add_tags)
-
-            # Add all parent tags
-            final_tags = set(requested_tags)
-            for t in requested_tags:
-                final_tags.update(t.get_ancestors())
-
-            # Drop removed parents and their descendants
-            final_tags.difference_update(blocked_tags)
-
-            validated_data["tags"] = list(final_tags)
         if validated_data.get("remove_inbox_tags"):
-            current_tag_ids = {t.pk for t in instance.tags.all()}
+            hierarchy = Tag.get_hierarchy()
             tags = (
                 validated_data["tags"]
                 if "tags" in validated_data
                 else list(instance.tags.all())
             )
-
-            # Tags newly added in this update, plus their ancestors, are kept
-            keep_ids: set[int] = set()
-            for tag in tags:
-                if tag.pk not in current_tag_ids:
-                    keep_ids.add(tag.pk)
-                    keep_ids.update(int(pk) for pk in tag.get_ancestors_pks())
-
-            # Remove inbox tags and their descendants, except those being kept
-            remove_ids: set[int] = set()
-            for inbox_tag in (
+            current_ids = set(instance.tags.values_list("pk", flat=True))
+            keep_ids = hierarchy.with_ancestors(
+                tag.pk for tag in tags if tag.pk not in current_ids
+            )
+            inbox_ids = (
                 Tag.objects.filter(is_inbox_tag=True)
-                .exclude(pk__in=keep_ids)
-                .only("pk", "tn_descendants_pks")
-            ):
-                remove_ids.add(inbox_tag.pk)
-                remove_ids.update(int(pk) for pk in inbox_tag.get_descendants_pks())
-
-            validated_data["tags"] = [t for t in tags if t.pk not in remove_ids]
+                .exclude(
+                    pk__in=keep_ids,
+                )
+                .values_list("pk", flat=True)
+            )
+            remove_ids = hierarchy.with_descendants(inbox_ids) - keep_ids
+            validated_data["tags"] = [tag for tag in tags if tag.pk not in remove_ids]
 
         if settings.AUDIT_LOG_ENABLED:
             with set_actor(self.user):
@@ -1825,18 +1799,6 @@ class ReprocessDocumentsSerializer(DocumentSelectionSerializer):
     remote_ocr = serializers.BooleanField(required=False, default=False)
 
 
-class RunZoneOcrSerializer(serializers.Serializer):
-    template = serializers.PrimaryKeyRelatedField(
-        queryset=OcrTemplate.objects.prefetch_related("zones", "zones__custom_field"),
-        required=False,
-        allow_null=True,
-    )
-
-
-class RunZoneOcrDocumentsSerializer(DocumentSelectionSerializer, RunZoneOcrSerializer):
-    pass
-
-
 class BulkEditSerializer(
     SerializerWithPerms,
     DocumentSelectionSerializer,
@@ -3714,181 +3676,3 @@ class StoragePathTestSerializer(SerializerWithPerms):
             document_field.queryset = Document.objects.filter(
                 id__in=permitted_document_ids(user),
             )
-
-
-class OcrTemplateZoneSerializer(serializers.ModelSerializer):
-    class Meta:
-        model = OcrTemplateZone
-        fields = [
-            "id",
-            "name",
-            "target",
-            "custom_field",
-            "page",
-            "x",
-            "y",
-            "width",
-            "height",
-            "ocr_language",
-            "transform",
-            "date_format",
-            "order",
-            "zone_source_width",
-            "zone_source_height",
-            "validation_regex",
-        ]
-
-    def validate_custom_field(self, value):
-        if value is None:
-            return value
-        if value.data_type not in OCR_SUPPORTED_FIELD_TYPES:
-            raise serializers.ValidationError(
-                f"Custom field type '{value.data_type}' is not supported for OCR extraction. "
-                f"Use string, integer, float, date, monetary, boolean, URL, or long text.",
-            )
-        return value
-
-    def validate_page(self, value):
-        if value is not None and value != -1 and value < 1:
-            raise serializers.ValidationError(
-                "Page must be positive or -1 for the last page.",
-            )
-        return value
-
-    def validate(self, data):
-        # A template PATCH still replaces each zone in full.
-        if self.root.partial:
-            for name, field in self.fields.items():
-                if field.required and name not in data:
-                    raise serializers.ValidationError(
-                        {name: field.error_messages["required"]},
-                    )
-        return data
-
-
-class OcrTemplateZoneTestSerializer(OcrTemplateZoneSerializer):
-    name = serializers.CharField(default="test")
-    x = serializers.IntegerField(min_value=0, default=0)
-    y = serializers.IntegerField(min_value=0, default=0)
-    width = serializers.IntegerField(min_value=2)
-    height = serializers.IntegerField(min_value=2)
-
-    class Meta(OcrTemplateZoneSerializer.Meta):
-        fields = [
-            "name",
-            "x",
-            "y",
-            "width",
-            "height",
-            "page",
-            "ocr_language",
-            "transform",
-            "date_format",
-            "validation_regex",
-            "zone_source_width",
-            "zone_source_height",
-        ]
-        extra_kwargs = {
-            "zone_source_width": {"min_value": 1},
-            "zone_source_height": {"min_value": 1},
-        }
-
-
-class OcrTemplateTestSerializer(serializers.Serializer):
-    document = serializers.PrimaryKeyRelatedField(
-        queryset=Document.objects.select_related("root_document__owner"),
-    )
-    zone = OcrTemplateZoneTestSerializer()
-
-
-class OcrTemplateSerializer(MatchingModelSerializer, OwnedObjectSerializer):
-    zones = OcrTemplateZoneSerializer(many=True, required=False)
-    combine_formats = serializers.DictField(
-        child=serializers.CharField(allow_blank=True, trim_whitespace=False),
-        required=False,
-    )
-
-    # Templates are never assigned to documents
-    slug = None
-    document_count = None
-
-    class Meta:
-        model = OcrTemplate
-        fields = [
-            "id",
-            "name",
-            "match",
-            "matching_algorithm",
-            "is_insensitive",
-            "source_width",
-            "source_height",
-            "sample_document",
-            "enabled",
-            "combine_formats",
-            "created",
-            "updated",
-            "zones",
-            "owner",
-            "permissions",
-            "user_can_change",
-            "set_permissions",
-        ]
-        read_only_fields = ["created", "updated"]
-
-    def validate_matching_algorithm(self, value):
-        if value == MatchingModel.MATCH_AUTO:
-            raise serializers.ValidationError(
-                "Automatic matching is not supported for OCR templates.",
-            )
-        return value
-
-    def validate(self, data):
-        data = super().validate(data)
-        zones = data.get("zones", [])
-        if (
-            self.instance
-            and "zones" not in data
-            and ("source_width" in data or "source_height" in data)
-        ):
-            zones = self.instance.zones.values()
-        source_width = data.get(
-            "source_width",
-            getattr(self.instance, "source_width", None),
-        )
-        source_height = data.get(
-            "source_height",
-            getattr(self.instance, "source_height", None),
-        )
-        for zone in zones:
-            width = zone.get("zone_source_width") or source_width
-            height = zone.get("zone_source_height") or source_height
-            if (
-                zone.get("x", 0) + zone.get("width", 0) > width
-                or zone.get("y", 0) + zone.get("height", 0) > height
-            ):
-                raise serializers.ValidationError(
-                    {
-                        "zones": f"Zone '{zone.get('name', '?')}' extends beyond its source dimensions.",
-                    },
-                )
-        return data
-
-    @transaction.atomic
-    def create(self, validated_data):
-        zones_data = validated_data.pop("zones", [])
-        template = super().create(validated_data)
-        for zone_data in zones_data:
-            OcrTemplateZone.objects.create(template=template, **zone_data)
-        return template
-
-    @transaction.atomic
-    def update(self, instance, validated_data):
-        zones_data = validated_data.pop("zones", None)
-        instance = super().update(instance, validated_data)
-
-        if zones_data is not None:
-            instance.zones.all().delete()
-            for zone_data in zones_data:
-                OcrTemplateZone.objects.create(template=instance, **zone_data)
-
-        return instance

src/documents/signals/handlers.py

@@ -1412,19 +1412,6 @@ def close_connection_pool_on_worker_init(**kwargs) -> None:
             conn.close_pool()
 
 
-def run_zone_ocr_extraction(sender, document, original_file=None, **kwargs):
-    """Apply matching templates without failing consumption if extraction fails."""
-    try:
-        from documents.zone_ocr import run_zone_extraction
-
-        run_zone_extraction(document, Path(original_file) if original_file else None)
-    except Exception:
-        logger.exception(
-            "Zone OCR extraction failed for document %s",
-            document.pk,
-        )
-
-
 @worker_process_shutdown.connect
 def close_connection_pool_on_worker_shutdown(**kwargs) -> None:  # pragma: no cover
     """

src/documents/tag_hierarchy.py

@@ -0,0 +1,61 @@
+"""An operation-local snapshot of tag edges, with no persistent derived fields.
+
+Never cache this globally: tasks, bulk updates and other processes can change
+parents. Callers traversing multiple tags should share one snapshot.
+"""
+
+from collections import defaultdict
+from collections.abc import Iterable
+
+
+class TagHierarchy:
+    def __init__(self, edges: Iterable[tuple[int, int | None]]) -> None:
+        self.parents = dict(edges)
+        self.children: dict[int | None, list[int]] = defaultdict(list)
+        for pk, parent in self.parents.items():
+            self.children[parent].append(pk)
+
+    def ancestors(self, parent_id: int | None) -> list[int]:
+        result = []
+        seen = set()
+        while parent_id is not None and parent_id not in seen:
+            seen.add(parent_id)
+            result.append(parent_id)
+            parent_id = self.parents.get(parent_id)
+        return result[::-1]
+
+    def with_ancestors(self, roots: Iterable[int]) -> set[int]:
+        result = set(roots)
+        for pk in list(result):
+            result.update(self.ancestors(self.parents.get(pk)))
+        return result
+
+    def with_descendants(self, roots: Iterable[int]) -> set[int]:
+        roots = set(roots)
+        return roots | self.descendants(roots)
+
+    def descendants(self, roots: Iterable[int]) -> set[int]:
+        roots = {pk for pk in roots if pk is not None}
+        seen = set(roots)
+        pending = list(roots)
+        while pending:
+            for child in self.children.get(pending.pop(), ()):
+                if child not in seen:
+                    seen.add(child)
+                    pending.append(child)
+        return seen - roots
+
+    def height(self, pk: int | None) -> int:
+        if pk is None:
+            return 0
+        seen = {pk}
+        pending = [(pk, 0)]
+        height = 0
+        while pending:
+            parent, depth = pending.pop()
+            height = max(height, depth)
+            for child in self.children.get(parent, ()):
+                if child not in seen:
+                    seen.add(child)
+                    pending.append((child, depth + 1))
+        return height

src/documents/tasks.py

@@ -47,7 +47,6 @@ from documents.models import CustomFieldInstance
 from documents.models import Document
 from documents.models import DocumentBarcode
 from documents.models import DocumentType
-from documents.models import OcrTemplate
 from documents.models import PaperlessTask
 from documents.models import ShareLink
 from documents.models import ShareLinkBundle
@@ -70,7 +69,6 @@ from documents.utils import compute_checksum
 from documents.utils import identity
 from documents.versioning import annotate_effective_content
 from documents.workflows.utils import get_workflows_for_trigger
-from documents.zone_ocr import run_zone_extraction
 from paperless.config import AIConfig
 from paperless.config import BarcodeConfig
 from paperless.config import RemoteOCRConfig
@@ -369,31 +367,6 @@ def _read_barcodes_for_reprocess(document: Document) -> list[StoredBarcode] | No
         return None
 
 
-@shared_task
-def extract_zones(document_id: int, template_id: int | None = None) -> None:
-    """
-    Run an OCR template against a stored document, or every template that
-    matches it when no template is given.
-    """
-    document = Document.objects.get(id=document_id)
-    if template_id is None:
-        run_zone_extraction(document, None)
-        return
-
-    try:
-        template = OcrTemplate.objects.prefetch_related(
-            "zones",
-            "zones__custom_field",
-        ).get(id=template_id)
-    except OcrTemplate.DoesNotExist:
-        logger.warning(
-            "OCR template %s no longer exists, not running zone OCR",
-            template_id,
-        )
-        return
-    run_zone_extraction(document, None, templates=[template])
-
-
 @shared_task
 def update_document_content_maybe_archive_file(
     document_id,

src/documents/tests/test_api_app_config.py

@@ -15,6 +15,7 @@ from paperless.models import ColorConvertChoices
 from paperless_testing.dirs import DirectoriesMixin
 from paperless_testing.factories import UserFactory
 from paperless_testing.http import read_streaming_response
+from paperless_testing.permissions import grant_global
 
 
 class TestApiAppConfig(DirectoriesMixin, APITestCase):
@@ -26,6 +27,67 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
         user = UserFactory(username="temp_admin", superuser=True)
         self.client.force_authenticate(user=user)
 
+    def test_api_read_config_requires_view_permission(self) -> None:
+        for permissions in (
+            (),
+            ("change_applicationconfiguration",),
+            ("view_document",),
+        ):
+            user = UserFactory()
+            grant_global(user, *permissions)
+            self.client.force_authenticate(user=user)
+
+            for endpoint in (self.ENDPOINT, f"{self.ENDPOINT}1/"):
+                for method in ("get", "head", "options"):
+                    with self.subTest(
+                        permissions=permissions,
+                        endpoint=endpoint,
+                        method=method,
+                    ):
+                        response = getattr(self.client, method)(endpoint)
+                        self.assertEqual(
+                            response.status_code,
+                            status.HTTP_403_FORBIDDEN,
+                        )
+
+    def test_api_read_config_with_view_permission(self) -> None:
+        user = UserFactory()
+        grant_global(user, "view_applicationconfiguration")
+        self.client.force_authenticate(user=user)
+
+        for endpoint in (self.ENDPOINT, f"{self.ENDPOINT}1/"):
+            for method in ("get", "head", "options"):
+                with self.subTest(endpoint=endpoint, method=method):
+                    response = getattr(self.client, method)(endpoint)
+                    self.assertEqual(response.status_code, status.HTTP_200_OK)
+
+    def test_api_view_config_permission_does_not_allow_writes(self) -> None:
+        user = UserFactory()
+        grant_global(user, "view_applicationconfiguration")
+        self.client.force_authenticate(user=user)
+
+        for method in ("put", "patch", "delete"):
+            with self.subTest(method=method):
+                response = getattr(self.client, method)(f"{self.ENDPOINT}1/")
+                self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
+
+    def test_api_change_config_permission_allows_updates(self) -> None:
+        user = UserFactory()
+        grant_global(user, "change_applicationconfiguration")
+        self.client.force_authenticate(user=user)
+
+        response = self.client.patch(
+            f"{self.ENDPOINT}1/",
+            {"app_title": "Updated title"},
+            format="json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertEqual(
+            ApplicationConfiguration.objects.get().app_title,
+            "Updated title",
+        )
+
     def test_api_get_config(self) -> None:
         """
         GIVEN:

src/documents/tests/test_api_bulk_edit.py

@@ -12,7 +12,6 @@ from documents.models import CustomField
 from documents.models import CustomFieldInstance
 from documents.models import Document
 from documents.models import DocumentType
-from documents.models import OcrTemplate
 from documents.models import StoragePath
 from documents.models import Tag
 from paperless_testing.dirs import DirectoriesMixin
@@ -584,87 +583,6 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(args[0], [self.doc1.id])
         self.assertEqual(kwargs, {"remote_ocr": True})
 
-    @mock.patch("documents.views.bulk_edit.run_zone_ocr")
-    def test_run_zone_ocr_documents_endpoint(self, m) -> None:
-        """
-        GIVEN:
-            - API data to run zone OCR on a document
-        WHEN:
-            - API is called
-        THEN:
-            - run_zone_ocr is called with the document
-        """
-        self.setup_mock(m, "run_zone_ocr")
-        response = self.client.post(
-            "/api/documents/run_zone_ocr/",
-            json.dumps({"documents": [self.doc1.id]}),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        m.assert_called_once()
-        args, kwargs = m.call_args
-        self.assertEqual(args[0], [self.doc1.id])
-        self.assertEqual(kwargs, {})
-
-    @mock.patch("documents.views.bulk_edit.run_zone_ocr")
-    def test_run_zone_ocr_documents_endpoint_with_template(self, m) -> None:
-        """
-        GIVEN:
-            - API data to run a chosen OCR template on a document
-        WHEN:
-            - API is called
-        THEN:
-            - run_zone_ocr is called with the template
-        """
-        self.setup_mock(m, "run_zone_ocr")
-        template = OcrTemplate.objects.create(
-            name="Bills",
-            source_width=100,
-            source_height=100,
-        )
-        response = self.client.post(
-            "/api/documents/run_zone_ocr/",
-            json.dumps({"documents": [self.doc1.id], "template": template.pk}),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        m.assert_called_once()
-        args, kwargs = m.call_args
-        self.assertEqual(args[0], [self.doc1.id])
-        self.assertEqual(kwargs, {"template": template})
-
-    @mock.patch("documents.views.bulk_edit.run_zone_ocr")
-    def test_run_zone_ocr_documents_endpoint_rejects_private_template(
-        self,
-        m,
-    ) -> None:
-        """
-        GIVEN:
-            - A user who can change the documents but not view the template
-        WHEN:
-            - API is called with that template
-        THEN:
-            - The whole request is refused
-        """
-        user = UserFactory(username="editor")
-        grant_global(user, "view_document", "change_document")
-        template = OcrTemplate.objects.create(
-            name="Private",
-            owner=UserFactory(username="other"),
-            source_width=100,
-            source_height=100,
-        )
-        self.client.force_authenticate(user=user)
-
-        response = self.client.post(
-            "/api/documents/run_zone_ocr/",
-            json.dumps({"documents": [self.doc1.id], "template": template.pk}),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
-        m.assert_not_called()
-
     @mock.patch("documents.serialisers.bulk_edit.set_storage_path")
     def test_api_set_storage_path(self, m) -> None:
         """
@@ -1223,8 +1141,8 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertCountEqual(
             response.data["selected_document_types"],
             [
-                {"id": self.c1.id, "document_count": 1},
-                {"id": self.c2.id, "document_count": 0},
+                {"id": self.dt1.id, "document_count": 1},
+                {"id": self.dt2.id, "document_count": 0},
             ],
         )
 

src/documents/tests/test_api_documents.py

@@ -49,6 +49,7 @@ from documents.models import WorkflowTrigger
 from documents.search import get_backend
 from documents.signals.handlers import run_workflows
 from documents.tests.utils import ConsumeTaskMixin
+from documents.views import DocumentViewSet
 from paperless_testing.dirs import DirectoriesMixin
 from paperless_testing.factories import DocumentFactory
 from paperless_testing.factories import TagFactory
@@ -1755,12 +1756,113 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         }
         self.assertEqual(counts_by_field[custom_field.id], 1)
 
+    def test_selection_data_counts_with_shared_by_filter(self) -> None:
+        """
+        GIVEN:
+            - Several documents owned by one user with the same correspondent
+              and document type, only one of which is shared
+        WHEN:
+            - Requesting the document list filtered by shared_by__id with
+              include_selection_data=true
+        THEN:
+            - Counts reflect only the shared document, not every document the
+              owner has with that correspondent or document type, regardless of
+              the batch size
+        """
+        owner = User.objects.create_user(username="owner")
+        other = User.objects.create_user(username="other")
+        correspondent = Correspondent.objects.create(name="c1")
+        doc_type = DocumentType.objects.create(name="dt1")
+        tag = Tag.objects.create(name="tag")
+        docs = [
+            Document.objects.create(
+                checksum=str(i),
+                owner=owner,
+                correspondent=correspondent,
+                document_type=doc_type,
+            )
+            for i in range(3)
+        ]
+        for doc in docs:
+            doc.tags.add(tag)
+        grant_object(other, docs[0], "view_document")
+
+        for batch_size in (10_000, 1):
+            with (
+                self.subTest(batch_size=batch_size),
+                mock.patch.object(
+                    DocumentViewSet,
+                    "selection_data_batch_size",
+                    batch_size,
+                ),
+            ):
+                response = self.client.get(
+                    f"/api/documents/?shared_by__id={owner.id}"
+                    "&include_selection_data=true",
+                )
+
+                self.assertEqual(response.status_code, status.HTTP_200_OK)
+                self.assertEqual(response.data["count"], 1)
+                selection_data = response.data["selection_data"]
+                for key, obj in (
+                    ("selected_correspondents", correspondent),
+                    ("selected_document_types", doc_type),
+                    ("selected_tags", tag),
+                ):
+                    counts = {
+                        item["id"]: item["document_count"]
+                        for item in selection_data[key]
+                    }
+                    self.assertEqual(counts[obj.id], 1, key)
+
+    def test_selection_data_counts_documents_once_when_filter_joins(self) -> None:
+        """
+        GIVEN:
+            - A document matching a multi-valued filter through two tags
+        WHEN:
+            - Requesting the document list with include_selection_data=true
+        THEN:
+            - The document is counted once per correspondent, not once per
+              matching tag, regardless of the batch size
+        """
+        correspondent = Correspondent.objects.create(name="c1")
+        tag_a = Tag.objects.create(name="a")
+        tag_b = Tag.objects.create(name="b")
+        both = Document.objects.create(checksum="1", correspondent=correspondent)
+        both.tags.add(tag_a, tag_b)
+        only_a = Document.objects.create(checksum="2", correspondent=correspondent)
+        only_a.tags.add(tag_a)
+
+        for batch_size in (10_000, 1):
+            with (
+                self.subTest(batch_size=batch_size),
+                mock.patch.object(
+                    DocumentViewSet,
+                    "selection_data_batch_size",
+                    batch_size,
+                ),
+            ):
+                response = self.client.get(
+                    f"/api/documents/?tags__id__in={tag_a.id},{tag_b.id}"
+                    "&include_selection_data=true",
+                )
+
+                self.assertEqual(response.status_code, status.HTTP_200_OK)
+                counts = {
+                    item["id"]: item["document_count"]
+                    for item in response.data["selection_data"][
+                        "selected_correspondents"
+                    ]
+                }
+                self.assertEqual(counts[correspondent.id], 2)
+
     def test_statistics(self) -> None:
         doc1 = Document.objects.create(
             title="none1",
             checksum="A",
             mime_type="application/pdf",
             content="abc",
+            archive_serial_number=42,
         )
         Document.objects.create(
             title="none2",
@@ -1804,6 +1906,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         self.assertEqual(response.data["correspondent_count"], 2)
         self.assertEqual(response.data["document_type_count"], 1)
         self.assertEqual(response.data["storage_path_count"], 2)
+        self.assertEqual(response.data["current_asn"], 42)
 
     def test_statistics_excludes_document_versions(self) -> None:
         root = Document.objects.create(
@@ -1811,6 +1914,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             checksum="A",
             mime_type="application/pdf",
             content="root",
+            archive_serial_number=42,
         )
         version = Document.objects.create(
             title="version",
@@ -1819,6 +1923,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             content="version",
             root_document=root,
             version_index=1,
+            archive_serial_number=99,
         )
         tag_inbox = Tag.objects.create(name="t1", is_inbox_tag=True)
         version.tags.add(tag_inbox)
@@ -1829,6 +1934,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         self.assertEqual(response.data["documents_total"], 1)
         self.assertEqual(response.data["documents_inbox"], 0)
         self.assertEqual(response.data["character_count"], 4)
+        self.assertEqual(response.data["current_asn"], 42)
         self.assertEqual(
             response.data["document_file_type_counts"][0]["mime_type_count"],
             1,
@@ -1842,6 +1948,45 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         self.assertEqual(response.data["documents_inbox"], None)
         self.assertEqual(response.data["inbox_tags"], None)
 
+    def test_statistics_current_asn_respects_document_permissions(self) -> None:
+        viewer = UserFactory()
+        grant_global(viewer, "view_document")
+        DocumentFactory(owner=viewer, archive_serial_number=12)
+        shared = DocumentFactory(owner=self.user, archive_serial_number=23)
+        grant_object(viewer, shared, "view_document")
+        DocumentFactory(owner=self.user, archive_serial_number=99)
+
+        self.client.force_authenticate(user=viewer)
+        response = self.client.get("/api/statistics/")
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertEqual(response.data["current_asn"], 23)
+
+    def test_statistics_current_asn_without_visible_documents(self) -> None:
+        DocumentFactory(owner=self.user, archive_serial_number=99)
+
+        for permissions in ((), ("view_document",)):
+            viewer = UserFactory()
+            grant_global(viewer, *permissions)
+            self.client.force_authenticate(user=viewer)
+
+            with self.subTest(permissions=permissions):
+                response = self.client.get("/api/statistics/")
+
+                self.assertEqual(response.status_code, status.HTTP_200_OK)
+                self.assertEqual(response.data["current_asn"], 0)
+
+    def test_statistics_current_asn_with_global_statistics_permission(self) -> None:
+        viewer = UserFactory()
+        grant_global(viewer, "view_global_statistics")
+        DocumentFactory(owner=self.user, archive_serial_number=99)
+
+        self.client.force_authenticate(user=viewer)
+        response = self.client.get("/api/statistics/")
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertEqual(response.data["current_asn"], 99)
+
     def test_statistics_multiple_users(self) -> None:
         """
         GIVEN:

src/documents/tests/test_api_search.py

@@ -25,6 +25,7 @@ from documents.models import Tag
 from documents.models import Workflow
 from documents.search import get_backend
 from documents.search import reset_backend
+from documents.views import DocumentViewSet
 from paperless_mail.models import MailAccount
 from paperless_mail.models import MailRule
 from paperless_testing.dirs import DirectoriesMixin
@@ -345,38 +346,39 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         storage_path = StoragePath.objects.create(name="sp1")
         tag = Tag.objects.create(name="tag")
 
-        matching_doc = Document.objects.create(
-            title="bank statement",
-            content="bank content",
-            checksum="A",
-            correspondent=correspondent,
-            document_type=doc_type,
-            storage_path=storage_path,
-        )
-        matching_doc.tags.add(tag)
+        for checksum, title in (
+            ("A", "bank statement"),
+            ("B", "bank account"),
+            ("C", "credit card"),
+        ):
+            doc = Document.objects.create(
+                title=title,
+                checksum=checksum,
+                correspondent=correspondent,
+                document_type=doc_type,
+                storage_path=storage_path,
+            )
+            doc.tags.add(tag)
+            get_backend().add_or_update(doc)
 
-        get_backend().add_or_update(matching_doc)
-
-        response = self.client.get(
-            "/api/documents/?query=bank&include_selection_data=true",
-        )
+        with mock.patch.object(DocumentViewSet, "selection_data_batch_size", 1):
+            response = self.client.get(
+                "/api/documents/?query=bank&page_size=1&include_selection_data=true",
+            )
 
         self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertIn("selection_data", response.data)
-
-        selected_correspondent = next(
-            item
-            for item in response.data["selection_data"]["selected_correspondents"]
-            if item["id"] == correspondent.id
-        )
-        selected_tag = next(
-            item
-            for item in response.data["selection_data"]["selected_tags"]
-            if item["id"] == tag.id
-        )
-
-        self.assertEqual(selected_correspondent["document_count"], 1)
-        self.assertEqual(selected_tag["document_count"], 1)
+        self.assertEqual(response.data["count"], 2)
+        self.assertEqual(len(response.data["results"]), 1)
+        for key, pk in (
+            ("selected_correspondents", correspondent.pk),
+            ("selected_document_types", doc_type.pk),
+            ("selected_storage_paths", storage_path.pk),
+            ("selected_tags", tag.pk),
+        ):
+            self.assertEqual(
+                response.data["selection_data"][key],
+                [{"id": pk, "document_count": 2}],
+            )
 
     def test_search_custom_field_ordering(self) -> None:
         custom_field = CustomField.objects.create(

src/documents/tests/test_bulk_edit.py

@@ -21,13 +21,11 @@ from documents.models import CustomField
 from documents.models import CustomFieldInstance
 from documents.models import Document
 from documents.models import DocumentType
-from documents.models import OcrTemplate
 from documents.models import StoragePath
 from documents.models import Tag
 from documents.pdf_ops import PageSpec
 from documents.permissions import PermissionsSpec
 from documents.permissions import set_permissions_for_objects
-from documents.tasks import extract_zones
 from paperless_testing.dirs import DirectoriesMixin
 from paperless_testing.factories import DocumentFactory
 from paperless_testing.permissions import grant_object
@@ -1876,111 +1874,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         self.assertIn("Error removing password from document", cm.output[0])
 
 
-@pytest.mark.django_db
-class TestBulkEditRunZoneOcr:
-    @pytest.fixture
-    def mock_task(self, mocker: MockerFixture) -> mock.MagicMock:
-        return mocker.patch("documents.bulk_edit.extract_zones")
-
-    def test_queues_every_selected_document(
-        self,
-        mock_task: mock.MagicMock,
-    ) -> None:
-        """
-        GIVEN:
-            - Selected documents
-        WHEN:
-            - run_zone_ocr is called with them
-        THEN:
-            - Each document is queued once, templates are matched when its
-              task runs
-        """
-        docs = DocumentFactory.create_batch(2)
-
-        result = bulk_edit.run_zone_ocr([doc.id for doc in docs])
-
-        assert result == "OK"
-        assert [
-            call.kwargs["kwargs"] for call in mock_task.apply_async.call_args_list
-        ] == [{"document_id": doc.id, "template_id": None} for doc in docs]
-
-    def test_queues_the_chosen_template(self, mock_task: mock.MagicMock) -> None:
-        """
-        GIVEN:
-            - A chosen OCR template
-        WHEN:
-            - run_zone_ocr is called with it
-        THEN:
-            - The template is queued with the document
-        """
-        doc = DocumentFactory()
-        template = OcrTemplate.objects.create(
-            name="Bills",
-            source_width=100,
-            source_height=100,
-        )
-
-        bulk_edit.run_zone_ocr([doc.id], template=template)
-
-        assert mock_task.apply_async.call_args.kwargs["kwargs"] == {
-            "document_id": doc.id,
-            "template_id": template.pk,
-        }
-
-    def test_task_runs_extraction(self, mocker: MockerFixture) -> None:
-        """
-        GIVEN:
-            - A queued zone OCR task
-        WHEN:
-            - The task runs
-        THEN:
-            - Zone extraction runs on the stored document
-        """
-        extract = mocker.patch("documents.tasks.run_zone_extraction")
-        doc = DocumentFactory()
-
-        extract_zones(doc.id)
-
-        extract.assert_called_once_with(doc, None)
-
-    def test_task_runs_the_chosen_template(self, mocker: MockerFixture) -> None:
-        """
-        GIVEN:
-            - A queued zone OCR task with a chosen template
-        WHEN:
-            - The task runs
-        THEN:
-            - Zone extraction runs with only that template
-        """
-        extract = mocker.patch("documents.tasks.run_zone_extraction")
-        doc = DocumentFactory()
-        template = OcrTemplate.objects.create(
-            name="Bills",
-            source_width=100,
-            source_height=100,
-        )
-
-        extract_zones(doc.id, template.pk)
-
-        extract.assert_called_once_with(doc, None, templates=[template])
-
-    def test_task_skips_a_deleted_template(self, mocker: MockerFixture) -> None:
-        """
-        GIVEN:
-            - A template deleted between queueing and running
-        WHEN:
-            - The task runs
-        THEN:
-            - Nothing is extracted
-        """
-        extract = mocker.patch("documents.tasks.run_zone_extraction")
-        doc = DocumentFactory()
-
-        extract_zones(doc.id, 999)
-
-        extract.assert_not_called()
-
-
 @pytest.mark.django_db
 class TestBulkEditReprocess:
     @pytest.fixture

src/documents/tests/test_regex.py

@@ -4,7 +4,6 @@ from django.conf import settings
 from pytest_mock import MockerFixture
 
 from documents.regex import safe_regex_finditer
-from documents.regex import safe_regex_fullmatch
 from documents.regex import safe_regex_match
 from documents.regex import safe_regex_search
 from documents.regex import safe_regex_sub
@@ -27,7 +26,7 @@ class TestValidateRegexPattern:
 
 
 class TestSafeRegexSearchAndMatch:
-    """Tests for safe_regex_search, _match and _fullmatch (same contract)."""
+    """Tests for safe_regex_search and safe_regex_match (same contract)."""
 
     @pytest.mark.parametrize(
         ("func", "pattern", "text", "expected_group"),
@@ -46,13 +45,6 @@ class TestSafeRegexSearchAndMatch:
                 "123",
                 id="match-match-found",
             ),
-            pytest.param(
-                safe_regex_fullmatch,
-                r"\d+",
-                "123",
-                "123",
-                id="fullmatch-match-found",
-            ),
         ],
     )
     def test_match_found(self, func, pattern, text, expected_group) -> None:
@@ -65,12 +57,6 @@ class TestSafeRegexSearchAndMatch:
         [
             pytest.param(safe_regex_search, r"\d+", "abcdef", id="search-no-match"),
             pytest.param(safe_regex_match, r"\d+", "abc123", id="match-no-match"),
-            pytest.param(
-                safe_regex_fullmatch,
-                r"\d+",
-                "123abc",
-                id="fullmatch-no-match",
-            ),
         ],
     )
     def test_no_match(self, func, pattern, text) -> None:
@@ -81,7 +67,6 @@ class TestSafeRegexSearchAndMatch:
         [
             pytest.param(safe_regex_search, id="search"),
             pytest.param(safe_regex_match, id="match"),
-            pytest.param(safe_regex_fullmatch, id="fullmatch"),
         ],
     )
     def test_invalid_pattern_returns_none(self, func) -> None:
@@ -92,7 +77,6 @@ class TestSafeRegexSearchAndMatch:
         [
             pytest.param(safe_regex_search, id="search"),
             pytest.param(safe_regex_match, id="match"),
-            pytest.param(safe_regex_fullmatch, id="fullmatch"),
         ],
     )
     def test_flags_respected(self, func) -> None:
@@ -103,7 +87,6 @@ class TestSafeRegexSearchAndMatch:
         [
             pytest.param(safe_regex_search, "search", id="search"),
             pytest.param(safe_regex_match, "match", id="match"),
-            pytest.param(safe_regex_fullmatch, "fullmatch", id="fullmatch"),
         ],
     )
     def test_timeout_returns_none(

src/documents/tests/test_tag_adjacency.py

@@ -0,0 +1,123 @@
+from typing import TYPE_CHECKING
+
+import pytest
+from django.core.exceptions import FieldDoesNotExist
+from django.db import connection
+from django.test.utils import CaptureQueriesContext
+
+from documents.management.commands.document_importer import _deserialize_record
+from documents.models import Tag
+from documents.tag_hierarchy import TagHierarchy
+from paperless_testing.factories import TagFactory
+from paperless_testing.migrations import TestMigrations
+
+if TYPE_CHECKING:
+    from django.apps.registry import Apps
+    from pytest_django.fixtures import DjangoAssertNumQueries
+
+
+@pytest.mark.django_db
+class TestTagAdjacency:
+    def test_held_instance_uses_current_parent_edges(self) -> None:
+        """Descendant lookups reflect parent changes made after loading a tag."""
+        first = TagFactory(name="First")
+        second = TagFactory(name="Second")
+        child = TagFactory(name="Child", tn_parent=first)
+        Tag.objects.filter(pk=child.pk).update(tn_parent=second)
+        assert first.get_descendants_pks() == set()
+        assert second.get_descendants_pks() == {child.pk}
+
+    def test_queryset_delete_preserves_cascade(self) -> None:
+        """Deleting a parent through a queryset deletes only its subtree."""
+        root = TagFactory(name="Root")
+        child = TagFactory(name="Child", tn_parent=root)
+        TagFactory(name="Grandchild", tn_parent=child)
+        survivor = TagFactory(name="Other root")
+        Tag.objects.filter(pk=root.pk).delete()
+        assert list(Tag.objects.values_list("pk", flat=True)) == [survivor.pk]
+
+    def test_flat_writes_do_not_update_other_tags(self) -> None:
+        """Creating and renaming flat tags never rewrite unrelated tag rows."""
+        TagFactory.create_batch(100)
+        with CaptureQueriesContext(connection) as queries:
+            new = TagFactory(name="New")
+        assert not any(q["sql"].startswith("UPDATE") for q in queries)
+        with CaptureQueriesContext(connection) as queries:
+            new.name = "Renamed"
+            new.save()
+        tag_updates = [
+            q["sql"] for q in queries if q["sql"].startswith('UPDATE "documents_tag"')
+        ]
+        assert len(tag_updates) == 1
+        assert 'WHERE "documents_tag"."id" =' in tag_updates[0]
+
+    def test_batch_snapshot_is_one_query_and_includes_overlapping_roots(
+        self,
+        django_assert_num_queries: "DjangoAssertNumQueries",
+    ) -> None:
+        """One edge query supports multiple traversals with overlapping roots."""
+        root = TagFactory(name="Root")
+        child = TagFactory(name="Child", tn_parent=root)
+        leaf = TagFactory(name="Leaf", tn_parent=child)
+        with django_assert_num_queries(1):
+            hierarchy = Tag.get_hierarchy()
+            assert hierarchy.with_ancestors([leaf.pk]) == {root.pk, child.pk, leaf.pk}
+            assert hierarchy.with_descendants([root.pk, child.pk]) == {
+                root.pk,
+                child.pk,
+                leaf.pk,
+            }
+        assert hierarchy.height(None) == 0
+
+    def test_legacy_export_fields_are_ignored_but_parent_is_preserved(self) -> None:
+        """Legacy bookkeeping is ignored while parent links and field checks survive."""
+        model, tag, m2m = _deserialize_record(
+            {
+                "model": "documents.tag",
+                "pk": 2,
+                "fields": {
+                    "name": "Child",
+                    "tn_parent": 1,
+                    "tn_order": 3,
+                    "tn_siblings_pks": "4,5",
+                    "tn_descendants_pks": "6",
+                },
+            },
+        )
+        assert model is Tag
+        assert tag.tn_parent_id == 1
+        assert tag.name == "Child"
+        assert not m2m
+        with pytest.raises(FieldDoesNotExist):
+            _deserialize_record(
+                {"model": "documents.tag", "pk": 3, "fields": {"tn_typo": "bad"}},
+            )
+
+    def test_malformed_cycles_terminate(self) -> None:
+        """Traversal terminates even when stored parent edges contain a cycle."""
+        hierarchy = TagHierarchy([(1, 2), (2, 1)])
+        assert hierarchy.with_descendants([1]) == {1, 2}
+        assert set(hierarchy.ancestors(2)) == {1, 2}
+
+
+class TestTagAdjacencyMigration(TestMigrations):
+    migrate_from = "0027_documentbarcode"
+    migrate_to = "0028_replace_tag_tree_fields"
+
+    def setUpBeforeMigration(self, apps: "Apps") -> None:
+        """Seed parent links using the model from the pre-migration state."""
+        tag = apps.get_model("documents", "Tag")
+        root = tag.objects.create(name="Root")
+        child = tag.objects.create(name="Child", tn_parent=root)
+        self.edges = [(root.pk, None), (child.pk, root.pk)]
+
+    def test_parent_edges_survive(self) -> None:
+        """Removing derived tree columns preserves the existing parent links."""
+        tag = self.apps.get_model("documents", "Tag")
+        assert (
+            list(tag.objects.order_by("pk").values_list("pk", "tn_parent_id"))
+            == self.edges
+        )
+        assert {
+            field.name for field in tag._meta.fields if field.name.startswith("tn_")
+        } == {"tn_parent"}

src/documents/tests/test_task_signals.py

@@ -13,52 +13,14 @@ from documents.data_models import DocumentMetadataOverrides
 from documents.data_models import DocumentSource
 from documents.models import PaperlessTask
 from documents.signals.handlers import before_task_publish_handler
-from documents.signals.handlers import run_zone_ocr_extraction
 from documents.signals.handlers import task_failure_handler
 from documents.signals.handlers import task_postrun_handler
 from documents.signals.handlers import task_prerun_handler
 from documents.signals.handlers import task_revoked_handler
-from paperless_testing.factories import DocumentFactory
 from paperless_testing.factories import PaperlessTaskFactory
 from paperless_testing.factories import UserFactory
 
 
-@pytest.mark.django_db
-@pytest.mark.parametrize(
-    "original_file",
-    [None, "/tmp/original.pdf", Path("/tmp/original.pdf")],
-)
-def test_consumption_runs_zone_extraction(
-    original_file,
-    mocker: pytest_mock.MockerFixture,
-):
-    extract = mocker.patch("documents.zone_ocr.run_zone_extraction")
-    document = DocumentFactory()
-
-    run_zone_ocr_extraction(sender=None, document=document, original_file=original_file)
-
-    extract.assert_called_once_with(
-        document,
-        Path(original_file) if original_file else None,
-    )
-
-
-@pytest.mark.django_db
-def test_zone_extraction_failure_does_not_fail_consumption(
-    mocker: pytest_mock.MockerFixture,
-    caplog,
-):
-    mocker.patch(
-        "documents.zone_ocr.run_zone_extraction",
-        side_effect=RuntimeError("OCR failed"),
-    )
-    document = DocumentFactory()
-
-    run_zone_ocr_extraction(sender=None, document=document)
-
-    assert f"Zone OCR extraction failed for document {document.pk}" in caplog.text
-
-
 @pytest.fixture
 def consume_input_doc():
     doc = mock.MagicMock(spec=ConsumableDocument)

src/documents/views.py

@@ -3,15 +3,15 @@ import logging
 import os
 import platform
 import re
-import subprocess
 import tempfile
 import zipfile
+from collections import Counter
 from collections import deque
 from collections.abc import Callable
-from dataclasses import asdict
 from datetime import datetime
 from datetime import timedelta
 from http import HTTPStatus
+from itertools import islice
 from pathlib import Path
 from time import mktime
 from time import sleep
@@ -154,8 +154,6 @@ from documents.models import CustomFieldInstance
 from documents.models import Document
 from documents.models import DocumentType
 from documents.models import Note
-from documents.models import OcrTemplate
-from documents.models import OcrTemplateZone
 from documents.models import PaperlessTask
 from documents.models import SavedView
 from documents.models import ShareLink
@@ -172,7 +170,6 @@ from documents.permissions import PaperlessNotePermissions
 from documents.permissions import PaperlessObjectPermissions
 from documents.permissions import TrashPermissions
 from documents.permissions import ViewDocumentsPermissions
-from documents.permissions import annotate_document_count_by_ids
 from documents.permissions import annotate_document_count_for_related_queryset
 from documents.permissions import get_document_count_filter_for_user
 from documents.permissions import get_permission_grantees
@@ -185,7 +182,6 @@ from documents.permissions import restrict_queryset_to_visible
 from documents.permissions import set_permissions_for_objects
 from documents.permissions import user_is_unrestricted
 from documents.plugins.date_parsing import get_date_parser
-from documents.regex import safe_regex_fullmatch
 from documents.schema import generate_object_with_permissions_schema
 from documents.search import SearchHit
 from documents.serialisers import AcknowledgeTasksViewSerializer
@@ -206,15 +202,11 @@ from documents.serialisers import EmailSerializer
 from documents.serialisers import MergeDocumentsAsVersionsSerializer
 from documents.serialisers import MergeDocumentsSerializer
 from documents.serialisers import NotesSerializer
-from documents.serialisers import OcrTemplateSerializer
-from documents.serialisers import OcrTemplateTestSerializer
 from documents.serialisers import PostDocumentSerializer
 from documents.serialisers import RemovePasswordDocumentsSerializer
 from documents.serialisers import ReprocessDocumentsSerializer
 from documents.serialisers import RotateDocumentsSerializer
 from documents.serialisers import RunTaskSerializer
-from documents.serialisers import RunZoneOcrDocumentsSerializer
-from documents.serialisers import RunZoneOcrSerializer
 from documents.serialisers import SavedViewSerializer
 from documents.serialisers import SearchResultSerializer
 from documents.serialisers import SerializerWithPerms
@@ -641,7 +633,7 @@ class TagViewSet(PermissionsAwareDocumentCountMixin, ModelViewSet[Tag]):
         queryset = queryset.order_by(*ordering)
 
         all_tags = list(queryset)
-        descendant_pks = {pk for tag in all_tags for pk in tag.get_descendants_pks()}
+        descendant_pks = Tag.get_hierarchy().descendants(t.pk for t in all_tags)
 
         if descendant_pks:
             user = getattr(getattr(self, "request", None), "user", None)
@@ -1023,71 +1015,80 @@ class DocumentViewSet(
         "custom_field_",
     )
 
-    def _get_selection_data_for_queryset(self, queryset):
-        # Resolve once instead of once per model below. `queryset` can carry an
-        # arbitrarily expensive WHERE clause (user filters plus the permission
-        # filter); re-embedding it as a subquery inside 5 separate Count(...)
-        # calls forces the database to re-evaluate that whole thing 5 times, and
-        # -- for FK relations especially -- can defeat semi-join planning
-        # entirely at scale. A concrete id list is cheap to reuse.
-        # order_by() drops the default/user ordering -- irrelevant for a plain
-        # id list, but left in place it forces a sort over the full filtered
-        # set before the ids can even be collected.
-        document_ids = list(queryset.order_by().values_list("pk", flat=True))
+    # Bound the IN clauses used for search results and through-table lookups.
+    selection_data_batch_size = 10_000
 
-        correspondents = Correspondent.objects.annotate(
-            document_count=Count(
-                "documents",
-                filter=Q(documents__id__in=document_ids),
-                distinct=True,
-            ),
-        )
-        document_types = DocumentType.objects.annotate(
-            document_count=Count(
-                "documents",
-                filter=Q(documents__id__in=document_ids),
-                distinct=True,
-            ),
-        )
-        storage_paths = StoragePath.objects.annotate(
-            document_count=Count(
-                "documents",
-                filter=Q(documents__id__in=document_ids),
-                distinct=True,
-            ),
-        )
-        # Tag and CustomField reach Document through an M2M/through-model table;
-        # a plain Count(filter=...) there is a much more expensive plan than the
-        # FK relations above once the bridge table is large -- see
-        # annotate_document_count_by_ids() for why.
-        tags = annotate_document_count_by_ids(
-            Tag.objects.all(),
-            through_model=Document.tags.through,
-            related_object_field="tag_id",
-            document_ids=document_ids,
-        )
-        custom_fields = annotate_document_count_by_ids(
-            CustomField.objects.all(),
-            through_model=CustomFieldInstance,
-            related_object_field="field_id",
-            document_ids=document_ids,
+    def _get_selection_data_for_queryset(
+        self,
+        queryset: QuerySet[Document],
+        *,
+        search_ids: list[int] | None = None,
+    ) -> dict[str, list[dict[str, int]]]:
+        # Keep permission and filter predicates at document granularity.
+        # Reusing the filtered queryset as a subquery for each count is slow.
+        rows = (
+            queryset.order_by()
+            .prefetch_related(None)
+            .values_list(
+                "pk",
+                "correspondent_id",
+                "document_type_id",
+                "storage_path_id",
+            )
         )
+        batch_size = self.selection_data_batch_size
+
+        def document_rows():
+            if search_ids is None:
+                yield from rows.iterator()
+            else:
+                for start in range(0, len(search_ids), batch_size):
+                    yield from rows.filter(
+                        pk__in=search_ids[start : start + batch_size],
+                    ).iterator()
+
+        correspondents: Counter[int | None] = Counter()
+        document_types: Counter[int | None] = Counter()
+        storage_paths: Counter[int | None] = Counter()
+        document_ids: set[int] = set()
+        for pk, correspondent, document_type, storage_path in document_rows():
+            # Filters that join multi-valued relations can repeat a document.
+            if pk in document_ids:
+                continue
+            document_ids.add(pk)
+            correspondents[correspondent] += 1
+            document_types[document_type] += 1
+            storage_paths[storage_path] += 1
+
+        tags: Counter[int | None] = Counter()
+        custom_fields: Counter[int | None] = Counter()
+        ids = iter(document_ids)
+        while batch := list(islice(ids, batch_size)):
+            for model, field, counts in (
+                (Document.tags.through, "tag_id", tags),
+                (CustomFieldInstance, "field_id", custom_fields),
+            ):
+                counts.update(
+                    dict(
+                        model.objects.filter(document_id__in=batch)
+                        .order_by()
+                        .values_list(field)
+                        .annotate(document_count=Count("document_id")),
+                    ),
+                )
+
+        def selection(model: type[Model], counts: Counter[int | None]):
+            return [
+                {"id": pk, "document_count": counts[pk]}
+                for pk in model._default_manager.values_list("pk", flat=True)
+            ]
+
         return {
-            "selected_correspondents": [
-                {"id": t.id, "document_count": t.document_count} for t in correspondents
-            ],
-            "selected_tags": [
-                {"id": t.id, "document_count": t.document_count} for t in tags
-            ],
-            "selected_document_types": [
-                {"id": t.id, "document_count": t.document_count} for t in document_types
-            ],
-            "selected_storage_paths": [
-                {"id": t.id, "document_count": t.document_count} for t in storage_paths
-            ],
-            "selected_custom_fields": [
-                {"id": t.id, "document_count": t.document_count} for t in custom_fields
-            ],
+            "selected_correspondents": selection(Correspondent, correspondents),
+            "selected_tags": selection(Tag, tags),
+            "selected_document_types": selection(DocumentType, document_types),
+            "selected_storage_paths": selection(StoragePath, storage_paths),
+            "selected_custom_fields": selection(CustomField, custom_fields),
         }
 
     @classmethod
@@ -2249,76 +2250,6 @@ class DocumentViewSet(
             raise Http404
         return version_doc
 
-    @extend_schema(
-        operation_id="documents_run_zone_ocr",
-        request=RunZoneOcrSerializer,
-        responses=inline_serializer(
-            name="RunZoneOcrResult",
-            fields={
-                "status": serializers.ChoiceField(choices=["completed", "skipped"]),
-                "reason": serializers.ChoiceField(
-                    choices=["no_template"],
-                    required=False,
-                ),
-                "results": serializers.ListField(child=serializers.DictField()),
-            },
-        ),
-    )
-    @action(
-        methods=["post"],
-        detail=True,
-        url_path="run-zone-ocr",
-        permission_classes=[IsAuthenticated],
-    )
-    def run_zone_ocr(self, request, pk=None):
-        """
-        Run zone-based OCR extraction on this document, with the given template
-        or with every template that matches it.
-        """
-        serializer = RunZoneOcrSerializer(data=request.data)
-        serializer.is_valid(raise_exception=True)
-        template = serializer.validated_data.get("template")
-
-        document = get_object_or_404(
-            Document.objects.select_related("root_document__owner"),
-            pk=pk,
-        )
-        if not request.user.has_perm(
-            "documents.change_document",
-        ) or not has_perms_owner_aware(request.user, "change_document", document):
-            return HttpResponseForbidden("Insufficient permissions")
-
-        if template is not None and not has_perms_owner_aware(
-            request.user,
-            "view_ocrtemplate",
-            template,
-        ):
-            return HttpResponseForbidden("Insufficient permissions")
-
-        from documents.zone_ocr import get_templates_for_document
-
-        templates = (
-            [template] if template is not None else get_templates_for_document(document)
-        )
-        if not templates:
-            return Response(
-                {"status": "skipped", "reason": "no_template", "results": []},
-            )
-
-        doc_path = document.archive_path or document.source_path
-        if not doc_path or not Path(doc_path).is_file():
-            return Response(
-                {"error": "Document file not found"},
-                status=status.HTTP_404_NOT_FOUND,
-            )
-
-        from documents.zone_ocr import run_zone_extraction
-
-        results = run_zone_extraction(document, None, templates=templates)
-        return Response(
-            {"status": "completed", "results": [asdict(result) for result in results]},
-        )
-
     @extend_schema(
         operation_id="documents_delete_version",
         parameters=[
@@ -2804,13 +2735,10 @@ class UnifiedSearchViewSet(DocumentViewSet):
                 if get_boolean(
                     str(request.query_params.get("include_selection_data", "false")),
                 ):
-                    # NOTE: pk__in=ordered_ids generates a large SQL IN clause
-                    # for big result sets.  Acceptable today but may need a temp
-                    # table or chunked approach if selection_data becomes slow
-                    # at scale (tens of thousands of matching documents).
                     response.data["selection_data"] = (
                         self._get_selection_data_for_queryset(
-                            filtered_qs.filter(pk__in=result.ordered_ids),
+                            filtered_qs,
+                            search_ids=result.ordered_ids,
                         )
                     )
                 return response
@@ -3485,40 +3413,6 @@ class ReprocessDocumentsView(DocumentOperationPermissionMixin):
         )
 
 
-@extend_schema_view(
-    post=extend_schema(
-        operation_id="documents_run_zone_ocr_bulk",
-        description="Run OCR template zone extraction on selected documents",
-        responses={
-            200: inline_serializer(
-                name="RunZoneOcrDocumentsResult",
-                fields={
-                    "result": serializers.CharField(),
-                },
-            ),
-        },
-    ),
-)
-class RunZoneOcrDocumentsView(DocumentOperationPermissionMixin):
-    serializer_class = RunZoneOcrDocumentsSerializer
-
-    def post(self, request, *args, **kwargs):
-        serializer = self.get_serializer(data=request.data)
-        serializer.is_valid(raise_exception=True)
-        template = serializer.validated_data.get("template")
-        if template is not None and not has_perms_owner_aware(
-            request.user,
-            "view_ocrtemplate",
-            template,
-        ):
-            return HttpResponseForbidden("Insufficient permissions")
-        return self._execute_document_action(
-            method=bulk_edit.run_zone_ocr,
-            validated_data=serializer.validated_data,
-            operation_label="document zone OCR",
-        )
-
-
 @extend_schema_view(
     post=extend_schema(
         operation_id="documents_edit_pdf",
@@ -4184,7 +4078,7 @@ class StatisticsView(GenericAPIView[Any]):
             for row in mime_type_stats
         ]
 
-        current_asn = Document.objects.aggregate(
+        current_asn = documents.aggregate(
             Max("archive_serial_number", default=0),
         ).get(
             "archive_serial_number__max",
@@ -5191,12 +5085,7 @@ class BulkEditObjectsView(PassUserMixin):
             if object_type == "tags":
                 editable_ids = set(user_permitted_objects.values_list("pk", flat=True))
                 all_ids = set(objs.values_list("pk", flat=True))
-                for tag in objs:
-                    all_ids.update(
-                        descendant.pk
-                        for descendant in tag.get_descendants()
-                        if descendant.pk in editable_ids
-                    )
+                all_ids.update(Tag.get_hierarchy().descendants(all_ids) & editable_ids)
                 objs = object_class.objects.filter(pk__in=all_ids)
             objs = objs.select_related("owner")
             object_ids = list(objs.values_list("pk", flat=True))
@@ -5821,141 +5710,3 @@ def serve_logo(request: HttpRequest, filename: str | None = None) -> FileRespons
         filename=logo_name,
         as_attachment=True,
     )
-
-
-class OcrTemplateViewSet(BulkPermissionMixin, PassUserMixin, ModelViewSet[OcrTemplate]):
-    """CRUD for OCR templates with zone definitions."""
-
-    model = OcrTemplate
-
-    queryset = (
-        OcrTemplate.objects.select_related("owner")
-        .prefetch_related(
-            "zones",
-            "zones__custom_field",
-        )
-        .order_by("name")
-    )
-    serializer_class = OcrTemplateSerializer
-    pagination_class = StandardPagination
-    permission_classes = (IsAuthenticated, PaperlessObjectPermissions)
-    filter_backends = (
-        OrderingFilter,
-        PermittedObjectsFilter,
-    )
-    ordering_fields = ("name",)
-
-    @action(
-        detail=False,
-        methods=["get"],
-        url_path=r"document-page-image/(?P<doc_id>[0-9]+)/(?P<page>[0-9]+)",
-    )
-    def document_page_image(self, request, doc_id=None, page=None):
-        """Render a page for the template editor's zone overlay."""
-        document = get_object_or_404(
-            Document.objects.select_related("root_document__owner"),
-            pk=doc_id,
-        )
-
-        if not has_perms_owner_aware(request.user, "view_document", document):
-            return HttpResponseForbidden("Insufficient permissions")
-
-        page_num = int(page)
-
-        if document.page_count and page_num >= document.page_count:
-            raise Http404(
-                f"Page {page_num} out of range (document has {document.page_count} pages)",
-            )
-
-        doc_path = document.archive_path or document.source_path
-        if not doc_path or not Path(doc_path).is_file():
-            raise Http404("Document file not found")
-
-        if document.mime_type and document.mime_type.startswith("image/"):
-            content = Path(doc_path).read_bytes()
-            return HttpResponse(content, content_type=document.mime_type)
-
-        with tempfile.TemporaryDirectory(dir=settings.SCRATCH_DIR) as tmp_dir:
-            output_prefix = Path(tmp_dir) / "page"
-            try:
-                subprocess.run(
-                    [
-                        "pdftoppm",
-                        "-png",
-                        "-r",
-                        "150",
-                        "-f",
-                        str(page_num + 1),
-                        "-l",
-                        str(page_num + 1),
-                        str(doc_path),
-                        str(output_prefix),
-                    ],
-                    check=True,
-                    capture_output=True,
-                    timeout=30,
-                )
-            except (subprocess.CalledProcessError, subprocess.TimeoutExpired) as error:
-                logger.warning(
-                    "Failed to render page %s of document %s: %s",
-                    page_num,
-                    document.pk,
-                    error,
-                )
-                raise Http404("Failed to render page") from error
-            except FileNotFoundError as error:
-                logger.warning("pdftoppm is not available")
-                raise Http404("Failed to render page") from error
-
-            rendered = sorted(Path(tmp_dir).glob("page-*.png"))
-            if not rendered:
-                raise Http404("No rendered page found")
-
-            content = rendered[0].read_bytes()
-
-        return HttpResponse(content, content_type="image/png")
-
-    @extend_schema(request=OcrTemplateTestSerializer)
-    @action(detail=False, methods=["post"], url_path="test-zone")
-    def test_zone(self, request):
-        """Extract an ad-hoc zone without changing the document."""
-        from documents.zone_ocr import extract_zone_preview
-
-        serializer = OcrTemplateTestSerializer(data=request.data)
-        serializer.is_valid(raise_exception=True)
-        document = serializer.validated_data["document"]
-
-        if not has_perms_owner_aware(request.user, "view_document", document):
-            return HttpResponseForbidden("Insufficient permissions")
-
-        doc_path = document.archive_path or document.source_path
-        if not doc_path or not Path(doc_path).is_file():
-            return Response(
-                {"error": "Document file not found"},
-                status=status.HTTP_404_NOT_FOUND,
-            )
-
-        zone = OcrTemplateZone(**serializer.validated_data["zone"])
-
-        result = extract_zone_preview(
-            Path(doc_path),
-            zone,
-            zone.zone_source_width or 0,
-            zone.zone_source_height or 0,
-            document.page_count,
-        )
-
-        regex_match = None
-        if zone.validation_regex and result.get("value") is not None:
-            regex_match = (
-                safe_regex_fullmatch(zone.validation_regex, result["value"]) is not None
-            )
-
-        return Response(
-            {
-                "raw_text": result.get("raw_text"),
-                "value": result.get("value"),
-                "regex": zone.validation_regex,
-                "regex_match": regex_match,
-            },
-        )

src/documents/workflows/mutations.py

@@ -6,6 +6,7 @@ from guardian.shortcuts import remove_perm
 from documents.data_models import DocumentMetadataOverrides
 from documents.models import CustomFieldInstance
 from documents.models import Document
+from documents.models import Tag
 from documents.models import WorkflowAction
 from documents.permissions import PermissionsSpec
 from documents.permissions import set_permissions_for_objects
@@ -134,10 +135,9 @@ def apply_assignment_to_overrides(
     if action.has_assign_tags:
         if overrides.tag_ids is None:
             overrides.tag_ids = []
-        tag_ids_to_add: set[int] = set()
-        for tag in action.assign_tags.all():
-            tag_ids_to_add.add(tag.pk)
-            tag_ids_to_add.update(int(pk) for pk in tag.get_ancestors_pks())
+        tag_ids_to_add = Tag.get_hierarchy().with_ancestors(
+            tag.pk for tag in action.assign_tags.all()
+        )
 
         overrides.tag_ids = list(set(overrides.tag_ids) | tag_ids_to_add)
 
@@ -216,10 +216,9 @@ def apply_removal_to_document(
     if action.remove_all_tags:
         Document.objects.get(pk=document.pk).tags.clear()
     else:
-        tag_ids_to_remove: set[int] = set()
-        for tag in action.remove_tags.all():
-            tag_ids_to_remove.add(tag.pk)
-            tag_ids_to_remove.update(int(pk) for pk in tag.get_descendants_pks())
+        tag_ids_to_remove = Tag.get_hierarchy().with_descendants(
+            tag.pk for tag in action.remove_tags.all()
+        )
 
         if tag_ids_to_remove:
             Document.objects.get(pk=document.pk).tags.remove(*tag_ids_to_remove)
@@ -297,10 +296,9 @@ def apply_removal_to_overrides(
     if action.remove_all_tags:
         overrides.tag_ids = None
     elif overrides.tag_ids:
-        tag_ids_to_remove: set[int] = set()
-        for tag in action.remove_tags.all():
-            tag_ids_to_remove.add(tag.pk)
-            tag_ids_to_remove.update(int(pk) for pk in tag.get_descendants_pks())
+        tag_ids_to_remove = Tag.get_hierarchy().with_descendants(
+            tag.pk for tag in action.remove_tags.all()
+        )
 
         overrides.tag_ids = [t for t in overrides.tag_ids if t not in tag_ids_to_remove]
 

src/documents/zone_ocr.py

@@ -1,672 +0,0 @@
-from __future__ import annotations
-
-import logging
-import math
-import re
-import string
-import subprocess
-import tempfile
-from dataclasses import dataclass
-from datetime import date
-from datetime import datetime
-from decimal import Decimal
-from decimal import InvalidOperation
-from pathlib import Path
-
-import dateparser
-import magic
-import zxingcpp
-from django.conf import settings
-from django.core.exceptions import ValidationError
-from django.db import transaction
-from PIL import Image
-
-from documents.matching import matches
-from documents.models import CustomField
-from documents.models import CustomFieldInstance
-from documents.models import Document
-from documents.models import OcrTemplate
-from documents.models import OcrTemplateZone
-from documents.permissions import permitted_object_ids
-from documents.regex import safe_regex_fullmatch
-from documents.versioning import get_root_document
-
-logger = logging.getLogger("paperless.zone_ocr")
-
-
-@dataclass(frozen=True)
-class ZoneExtraction:
-    raw_text: str | None = None
-    value: str | None = None
-
-
-@dataclass(frozen=True)
-class FieldUpdate:
-    field_name: str
-    value: object
-    custom_field: CustomField | None = None
-
-
-@dataclass
-class ZoneOcrResult:
-    template: str
-    zone: str
-    custom_field: str
-    value: object = None
-    reason: str | None = None
-
-
-def _zone_result(
-    template: OcrTemplate,
-    zone: OcrTemplateZone,
-    *,
-    value: object = None,
-    reason: str | None = None,
-) -> ZoneOcrResult:
-    if zone.target == OcrTemplateZone.TargetType.CUSTOM_FIELD:
-        label = zone.custom_field.name if zone.custom_field_id else "(no field)"
-    else:
-        label = {"title": "Title", "asn": "ASN", "created": "Created"}[zone.target]
-    return ZoneOcrResult(template.name, zone.name, label, value, reason)
-
-
-def get_templates_for_document(document: Document) -> list[OcrTemplate]:
-    """
-    The enabled templates that match the document's content and that its owner
-    can view, the same rule as matching. A version is owned through its root
-    document.
-    """
-    owner = get_root_document(document).owner
-    templates = (
-        OcrTemplate.objects.filter(
-            enabled=True,
-            id__in=permitted_object_ids(owner, OcrTemplate, "view_ocrtemplate"),
-        )
-        .order_by("name", "pk")
-        .prefetch_related("zones", "zones__custom_field")
-    )
-    return [template for template in templates if matches(template, document)]
-
-
-def run_zone_extraction(
-    document: Document,
-    original_file: Path | None,
-    templates: list[OcrTemplate] | None = None,
-) -> list[ZoneOcrResult]:
-    """
-    Run zone-based OCR extraction for the given templates, or for every
-    template that matches the document when none are given.
-    """
-    if templates is None:
-        templates = get_templates_for_document(document)
-    if not templates:
-        return []
-
-    doc_path = _resolve_doc_path(document, original_file)
-    if doc_path is None:
-        logger.warning(
-            "Zone OCR: no accessible file for document %d",
-            document.pk,
-        )
-        return [
-            _zone_result(template, zone, reason="missing_file")
-            for template in templates
-            for zone in template.zones.all()
-        ]
-
-    template_zones = [(template, list(template.zones.all())) for template in templates]
-    pages = {
-        _resolve_page_idx(zone.page, document.page_count)
-        for _, zones in template_zones
-        for zone in zones
-    }
-    if not pages:
-        return []
-    results = []
-    with tempfile.TemporaryDirectory(dir=settings.SCRATCH_DIR) as tmp_dir:
-        tmp_path = Path(tmp_dir)
-        page_images = _render_pages(doc_path, pages, tmp_path, document.page_count)
-        for template, zones in template_zones:
-            try:
-                results.extend(
-                    _process_template(document, page_images, template, zones, tmp_path),
-                )
-            except Exception:
-                # One failed template must not prevent the remaining templates from running.
-                logger.exception(
-                    "Zone OCR: error processing template '%s' for document %d",
-                    template.name,
-                    document.pk,
-                )
-                results.extend(
-                    _zone_result(template, zone, reason="template_failed")
-                    for zone in zones
-                )
-    return results
-
-
-def _resolve_doc_path(
-    document: Document,
-    original_file: Path | None,
-) -> Path | None:
-    """Prefer the archive, then the source, then the ingestion signal's file."""
-    candidates = []
-    if document.has_archive_version:
-        candidates.append(document.archive_path)
-    candidates.append(document.source_path)
-    if original_file is not None:
-        candidates.append(original_file)
-
-    for path in candidates:
-        if path is not None and Path(path).is_file():
-            return Path(path)
-    return None
-
-
-def _resolve_page_idx(page_value: int | None, page_count: int | None) -> int:
-    """Resolve a 1-based page or -1 (last page), defaulting to the first page."""
-    if page_value == -1:
-        return max((page_count or 1) - 1, 0)
-    return max((page_value or 1) - 1, 0)
-
-
-def _process_template(
-    document: Document,
-    page_images: dict[int, Path],
-    template: OcrTemplate,
-    zones: list[OcrTemplateZone],
-    tmp_path: Path,
-) -> list[ZoneOcrResult]:
-    """Extract and combine zone values before applying a template's updates."""
-    grouped: dict[str, list[tuple[OcrTemplateZone, ZoneOcrResult]]] = {}
-    results = []
-    for zone in zones:
-        page_idx = _resolve_page_idx(zone.page, document.page_count)
-        extracted = None
-        reason = "missing_page"
-        if page_idx in page_images:
-            extraction = _extract_zone(
-                page_images[page_idx],
-                zone,
-                zone.zone_source_width or template.source_width,
-                zone.zone_source_height or template.source_height,
-                tmp_path,
-            )
-            extracted = extraction.value
-            reason = None if extracted else "no_value"
-        if (
-            extracted is not None
-            and zone.validation_regex
-            and not safe_regex_fullmatch(zone.validation_regex, extracted)
-        ):
-            reason = "regex_mismatch"
-        result = _zone_result(
-            template,
-            zone,
-            value=extracted if reason is None else None,
-            reason=reason,
-        )
-        results.append(result)
-        grouped.setdefault(_field_key(zone), []).append((zone, result))
-
-    updates = []
-    combine_formats = template.combine_formats or {}
-    for key, field_zones in grouped.items():
-        accepted = [result for _, result in field_zones if result.reason is None]
-        if not accepted:
-            continue
-        value = _combine_field_value(
-            combine_formats.get(key, ""),
-            [(zone.name, result.value) for zone, result in field_zones],
-        )
-        target_zone = field_zones[0][0]
-        update = _prepare_field_update(target_zone, value) if value else None
-        if update is not None:
-            updates.append(update)
-        for result in accepted:
-            result.value = update.value if update else None
-            if update is None:
-                result.reason = (
-                    "unassigned" if key == "custom_field" else "invalid_value"
-                )
-    _apply_field_updates(document, updates)
-    return results
-
-
-def _field_key(zone: OcrTemplateZone) -> str:
-    """Use the same target keys as the editor's combination formats."""
-    target = zone.target
-    if target == OcrTemplateZone.TargetType.CUSTOM_FIELD and zone.custom_field_id:
-        return str(zone.custom_field_id)
-    return target
-
-
-def _combine_field_value(
-    fmt: str,
-    field_zones: list[tuple[str, str | None]],
-) -> str:
-    """Combine the OCR values of all zones targeting one field.
-
-    With a format string, `{Zone Name}` tokens are replaced by that zone's value
-    and literal text is kept; separators left dangling by an empty token are
-    cleaned up. Without a format, the zone values are joined in order by a space.
-    """
-    values = {name: value or "" for name, value in field_zones}
-
-    if not fmt:
-        return " ".join(value for _, value in field_zones if value).strip()
-
-    def _replace(match: re.Match) -> str:
-        return values.get(match.group(1).strip(), "")
-
-    combined = re.sub(r"\{([^{}]+)\}", _replace, fmt)
-    # Tidy up separators an empty token may have left behind.
-    combined = re.sub(r"\s{2,}", " ", combined)
-    combined = re.sub(r"([^\w\s])\s*\1+", r"\1", combined)
-    return combined.strip().strip("-/.,;:| \t")
-
-
-def _render_pages(
-    doc_path: Path,
-    pages: set[int],
-    tmp_dir: Path,
-    page_count: int | None,
-) -> dict[int, Path]:
-    """Render specific PDF pages as PNG images using pdftoppm (poppler-utils)."""
-    result: dict[int, Path] = {}
-    mime = _detect_mime(doc_path)
-
-    if mime and mime.startswith("image/"):
-        if 0 in pages:
-            result[0] = doc_path
-        return result
-
-    for actual_page in sorted(pages):
-        if actual_page < 0 or (page_count and actual_page >= page_count):
-            continue
-
-        output_prefix = tmp_dir / f"page_{actual_page}"
-        try:
-            subprocess.run(
-                [
-                    "pdftoppm",
-                    "-png",
-                    "-singlefile",
-                    "-r",
-                    "300",
-                    "-f",
-                    str(actual_page + 1),  # pdftoppm is 1-indexed
-                    "-l",
-                    str(actual_page + 1),
-                    str(doc_path),
-                    str(output_prefix),
-                ],
-                check=True,
-                capture_output=True,
-                timeout=60,
-            )
-        except subprocess.TimeoutExpired:
-            logger.error("Zone OCR: pdftoppm timed out for page %d", actual_page)
-            continue
-        except subprocess.CalledProcessError as e:
-            logger.error(
-                "Zone OCR: pdftoppm failed for page %d: %s",
-                actual_page,
-                e.stderr.decode(errors="replace") if e.stderr else str(e),
-            )
-            continue
-        except FileNotFoundError:
-            logger.error("Zone OCR: pdftoppm not found")
-            return result
-
-        rendered = output_prefix.with_suffix(".png")
-        if rendered.is_file():
-            result[actual_page] = rendered
-
-    return result
-
-
-def _crop_zone(
-    page_img: Path,
-    zone: OcrTemplateZone,
-    source_width: int,
-    source_height: int,
-) -> Image.Image | None:
-    """Crop a zone from the page image and return the PIL Image."""
-    try:
-        with Image.open(page_img) as img:
-            img_width, img_height = img.size
-            if not source_width or not source_height:
-                source_width, source_height = img.size
-
-            scale_x = img_width / source_width
-            scale_y = img_height / source_height
-
-            crop_left = int(zone.x * scale_x)
-            crop_top = int(zone.y * scale_y)
-            crop_right = int((zone.x + zone.width) * scale_x)
-            crop_bottom = int((zone.y + zone.height) * scale_y)
-
-            # Clamp to the image so an oversized zone can't crop out of bounds.
-            crop_left = max(0, min(crop_left, img_width))
-            crop_top = max(0, min(crop_top, img_height))
-            crop_right = min(crop_right, img_width)
-            crop_bottom = min(crop_bottom, img_height)
-
-            if crop_right - crop_left < 2 or crop_bottom - crop_top < 2:
-                logger.warning("Zone OCR: crop too small for zone '%s'", zone.name)
-                return None
-
-            return img.crop((crop_left, crop_top, crop_right, crop_bottom))
-    except (OSError, ValueError, Image.DecompressionBombError):
-        logger.exception("Zone OCR: crop failed for zone '%s'", zone.name)
-        return None
-
-
-def _read_barcode(cropped: Image.Image, zone_name: str) -> str | None:
-    """Read QR/barcode from a cropped image using zxingcpp."""
-    try:
-        results = zxingcpp.read_barcodes(cropped)
-        return results[0].text if results else None
-    except (RuntimeError, ValueError, TypeError):
-        logger.exception("Zone OCR: barcode read failed for zone '%s'", zone_name)
-        return None
-
-
-def _ocr_text(cropped: Image.Image, zone: OcrTemplateZone, tmp_dir: Path) -> str | None:
-    """OCR a cropped image with Tesseract."""
-    crop_path = tmp_dir / f"zone_{zone.pk}.png"
-    cropped.save(crop_path)
-
-    try:
-        proc = subprocess.run(
-            [
-                "tesseract",
-                str(crop_path),
-                "stdout",
-                "-l",
-                zone.ocr_language,
-                "--psm",
-                "6",  # Assume uniform block of text
-            ],
-            capture_output=True,
-            text=True,
-            timeout=30,
-            check=True,
-        )
-        return proc.stdout.strip() or None
-    except subprocess.TimeoutExpired:
-        logger.error("Zone OCR: Tesseract timed out for zone '%s'", zone.name)
-        return None
-    except subprocess.CalledProcessError as e:
-        logger.error(
-            "Zone OCR: Tesseract failed for zone '%s': %s",
-            zone.name,
-            e.stderr[:200] if e.stderr else str(e),
-        )
-        return None
-    except FileNotFoundError:
-        logger.error("Zone OCR: Tesseract not found")
-        return None
-
-
-def _extract_zone(
-    page_img: Path,
-    zone: OcrTemplateZone,
-    source_width: int,
-    source_height: int,
-    tmp_dir: Path,
-) -> ZoneExtraction:
-    """Read and transform a zone, retaining the text for the editor's preview."""
-    cropped = _crop_zone(page_img, zone, source_width, source_height)
-    if cropped is None:
-        return ZoneExtraction()
-
-    try:
-        raw_text = (
-            _read_barcode(cropped, zone.name)
-            if zone.transform == OcrTemplateZone.TransformType.QR_CODE
-            else _ocr_text(cropped, zone, tmp_dir)
-        )
-    finally:
-        cropped.close()
-    return ZoneExtraction(
-        raw_text=raw_text,
-        value=_apply_transform(raw_text, zone.transform, zone.date_format)
-        if raw_text
-        else None,
-    )
-
-
-def extract_zone_preview(
-    doc_path: Path,
-    zone: OcrTemplateZone,
-    source_width: int,
-    source_height: int,
-    page_count: int | None,
-) -> dict:
-    """Extract a zone without writing its value to the document."""
-    page_idx = _resolve_page_idx(zone.page, page_count)
-    with tempfile.TemporaryDirectory(dir=settings.SCRATCH_DIR) as tmp_dir:
-        tmp_path = Path(tmp_dir)
-        page_images = _render_pages(doc_path, {page_idx}, tmp_path, page_count)
-        if page_idx not in page_images:
-            return {"raw_text": None, "value": None}
-
-        result = _extract_zone(
-            page_images[page_idx],
-            zone,
-            source_width,
-            source_height,
-            tmp_path,
-        )
-        return {"raw_text": result.raw_text, "value": result.value}
-
-
-def _parse_iso_date(text: str) -> date | None:
-    match = re.search(r"\d{4}-\d{2}-\d{2}", text)
-    return date.fromisoformat(match[0]) if match else None
-
-
-def _parse_date(text: str, fmt: str = "") -> date | None:
-    """Try the zone's date format, ISO dates, then automatic date detection."""
-    if fmt:
-        try:
-            return datetime.strptime(text, fmt).date()
-        except ValueError:
-            pass
-    try:
-        iso_date = _parse_iso_date(text)
-    except ValueError:
-        iso_date = None
-    if iso_date is not None:
-        return iso_date
-    try:
-        parsed = dateparser.parse(
-            text,
-            settings={
-                "PREFER_DAY_OF_MONTH": "first",
-                "RETURN_AS_TIMEZONE_AWARE": False,
-            },
-        )
-        if parsed:
-            return parsed.date()
-    except (ValueError, OverflowError):
-        logger.debug("Zone OCR: date parsing failed")
-    return None
-
-
-def _apply_transform(text: str, transform: str, date_format: str = "") -> str:
-    """Apply post-processing transform to extracted text."""
-    text = text.strip()
-    if not text:
-        return text
-
-    if transform in ("strip", "none"):
-        return text
-    elif transform == "date":
-        parsed = _parse_date(text, date_format)
-        return parsed.isoformat() if parsed else text
-    elif transform == "uppercase":
-        return text.upper()
-    elif transform == "lowercase":
-        return text.lower()
-    elif transform == "numeric":
-        result = re.sub(r"[^\d.,\-]", "", text)
-        return result if result else text
-    elif transform == "strip_punctuation":
-        return text.strip(string.punctuation + " \t\r\n")
-    return text
-
-
-def _prepare_field_update(
-    zone: OcrTemplateZone,
-    value: str,
-) -> FieldUpdate | None:
-    """Convert extracted text and enforce the destination field's constraints."""
-    custom_field = None
-    if zone.target == OcrTemplateZone.TargetType.CUSTOM_FIELD:
-        if not zone.custom_field_id:
-            return None
-        custom_field = zone.custom_field
-        field_name = CustomFieldInstance.get_value_field_name(custom_field.data_type)
-        typed_value = _convert_value(value, custom_field.data_type)
-        model = CustomFieldInstance
-    elif zone.target == OcrTemplateZone.TargetType.TITLE:
-        field_name, typed_value = "title", value[:128]
-        model = Document
-    elif zone.target == OcrTemplateZone.TargetType.ASN:
-        digits = re.sub(r"[^\d]", "", value)
-        field_name = "archive_serial_number"
-        typed_value = int(digits) if digits else None
-        model = Document
-    elif zone.target == OcrTemplateZone.TargetType.CREATED:
-        field_name, typed_value = "created", _parse_date(value)
-        model = Document
-    else:
-        return None
-    if typed_value is None:
-        return None
-    try:
-        typed_value = model._meta.get_field(field_name).clean(typed_value, None)
-    except ValidationError:
-        logger.info("Zone OCR: invalid value for zone '%s'", zone.name)
-        return None
-    return FieldUpdate(field_name, typed_value, custom_field)
-
-
-def _apply_field_updates(document: Document, updates: list[FieldUpdate]) -> None:
-    builtin_values = {
-        update.field_name: update.value
-        for update in updates
-        if update.custom_field is None
-    }
-    original_values = {name: getattr(document, name) for name in builtin_values}
-    try:
-        with transaction.atomic():
-            for update in updates:
-                if update.custom_field is not None:
-                    CustomFieldInstance.objects.update_or_create(
-                        document=document,
-                        field=update.custom_field,
-                        defaults={update.field_name: update.value},
-                    )
-            if builtin_values:
-                for name, value in builtin_values.items():
-                    setattr(document, name, value)
-                document.save(update_fields=list(builtin_values))
-    except Exception:
-        # Database rollback does not restore attributes on the model instance.
-        for name, value in original_values.items():
-            setattr(document, name, value)
-        raise
-
-
-def _normalize_number(value: str) -> str:
-    cleaned = re.sub(r"[^\d.,\-]", "", value)
-    # When both separators occur, the rightmost one is the decimal separator.
-    if "," in cleaned and "." in cleaned:
-        if cleaned.rindex(",") > cleaned.rindex("."):
-            cleaned = cleaned.replace(".", "").replace(",", ".")
-        else:
-            cleaned = cleaned.replace(",", "")
-    else:
-        cleaned = cleaned.replace(",", ".")
-    Decimal(cleaned)
-    return cleaned
-
-
-def _convert_value(value: str, data_type: str) -> object | None:
-    """Convert an extracted OCR string to the appropriate type for the custom field."""
-    if not value:
-        return None
-
-    try:
-        if data_type in (
-            CustomField.FieldDataType.STRING,
-            CustomField.FieldDataType.URL,
-        ):
-            return value[:128]
-
-        elif data_type == CustomField.FieldDataType.LONG_TEXT:
-            return value
-
-        elif data_type == CustomField.FieldDataType.INT:
-            digits = re.sub(r"[^\d\-]", "", value)
-            digits = digits.lstrip("-")
-            if not digits:
-                return None
-            if value.strip().startswith("-"):
-                digits = "-" + digits
-            return int(digits)
-
-        elif data_type == CustomField.FieldDataType.FLOAT:
-            number = float(_normalize_number(value))
-            return number if math.isfinite(number) else None
-
-        elif data_type == CustomField.FieldDataType.DATE:
-            parsed = _parse_iso_date(value)
-            return parsed.isoformat() if parsed else None
-
-        elif data_type == CustomField.FieldDataType.MONETARY:
-            return _normalize_number(value)
-
-        elif data_type == CustomField.FieldDataType.BOOL:
-            lower = value.lower().strip()
-            if lower in ("true", "yes", "1", "ja", "oui", "si", "x"):
-                return True
-            elif lower in ("false", "no", "0", "nein", "non"):
-                return False
-            return None
-
-        else:
-            logger.debug(
-                "Zone OCR: unsupported custom field type %s for OCR extraction",
-                data_type,
-            )
-            return None
-
-    except (ValueError, InvalidOperation):
-        logger.info("Zone OCR: could not convert value to %s", data_type)
-        return None
-
-
-def _detect_mime(path: Path) -> str | None:
-    """Detect MIME type of a file."""
-    try:
-        return magic.from_file(str(path), mime=True)
-    except (OSError, magic.MagicException):
-        logger.debug("Zone OCR: magic failed for %s, falling back to extension", path)
-
-    suffix = path.suffix.lower()
-    return {
-        ".pdf": "application/pdf",
-        ".png": "image/png",
-        ".jpg": "image/jpeg",
-        ".jpeg": "image/jpeg",
-        ".tiff": "image/tiff",
-        ".tif": "image/tiff",
-        ".webp": "image/webp",
-        ".bmp": "image/bmp",
-        ".gif": "image/gif",
-    }.get(suffix)

src/paperless/settings/__init__.py

@@ -157,7 +157,6 @@ INSTALLED_APPS = [
     "allauth.headless",
     "drf_spectacular",
     "drf_spectacular_sidecar",
-    "treenode",
     *env_apps,
 ]
 

src/paperless/urls.py

@@ -30,13 +30,11 @@ from documents.views import IndexView
 from documents.views import LogViewSet
 from documents.views import MergeDocumentsAsVersionsView
 from documents.views import MergeDocumentsView
-from documents.views import OcrTemplateViewSet
 from documents.views import PostDocumentView
 from documents.views import RemoteVersionView
 from documents.views import RemovePasswordDocumentsView
 from documents.views import ReprocessDocumentsView
 from documents.views import RotateDocumentsView
-from documents.views import RunZoneOcrDocumentsView
 from documents.views import SavedViewViewSet
 from documents.views import SearchAutoCompleteView
 from documents.views import SelectionDataView
@@ -92,7 +90,6 @@ api_router.register(r"workflow_triggers", WorkflowTriggerViewSet)
 api_router.register(r"workflow_actions", WorkflowActionViewSet)
 api_router.register(r"workflows", WorkflowViewSet)
 api_router.register(r"custom_fields", CustomFieldViewSet)
-api_router.register(r"ocr_templates", OcrTemplateViewSet)
 api_router.register(r"config", ApplicationConfigurationViewSet)
 api_router.register(r"processed_mail", ProcessedMailViewSet)
 
@@ -169,11 +166,6 @@ urlpatterns = [
                                 ReprocessDocumentsView.as_view(),
                                 name="reprocess_documents",
                             ),
-                            re_path(
-                                "^run_zone_ocr/",
-                                RunZoneOcrDocumentsView.as_view(),
-                                name="run_zone_ocr_documents",
-                            ),
                             re_path(
                                 "^rotate/",
                                 RotateDocumentsView.as_view(),

src/paperless/views.py

@@ -32,13 +32,13 @@ from rest_framework.fields import BooleanField
 from rest_framework.filters import OrderingFilter
 from rest_framework.generics import GenericAPIView
 from rest_framework.pagination import PageNumberPagination
-from rest_framework.permissions import DjangoModelPermissions
 from rest_framework.permissions import IsAuthenticated
 from rest_framework.response import Response
 from rest_framework.throttling import ScopedRateThrottle
 from rest_framework.viewsets import ModelViewSet
 
 from documents.models import PaperlessTask
+from documents.permissions import PaperlessModelPermissions
 from documents.permissions import PaperlessObjectPermissions
 from documents.tasks import llmindex_index
 from paperless.filters import GroupFilterSet
@@ -414,7 +414,7 @@ class ApplicationConfigurationViewSet(ModelViewSet[ApplicationConfiguration]):
     queryset = ApplicationConfiguration.objects
 
     serializer_class = ApplicationConfigurationSerializer
-    permission_classes = (IsAuthenticated, DjangoModelPermissions)
+    permission_classes = (IsAuthenticated, PaperlessModelPermissions)
 
     @extend_schema(exclude=True)
     def create(self, request, *args, **kwargs):

src/paperless_ai/tests/test_vector_store.py

@@ -20,8 +20,10 @@ from paperless_ai.tables import DocumentChunksTable
 from paperless_ai.tables import DocumentMetaTable
 from paperless_ai.vector_store import _MAX_IN_VALUES
 from paperless_ai.vector_store import DB_FILENAME
+from paperless_ai.vector_store import DB_PAGE_SIZE
 from paperless_ai.vector_store import DEFAULT_TABLE_NAME
 from paperless_ai.vector_store import SCHEMA_VERSION
+from paperless_ai.vector_store import VEC0_CHUNK_SIZE
 from paperless_ai.vector_store import PaperlessSqliteVecVectorStore
 from paperless_ai.vector_store import _build_where
 from paperless_ai.vector_store import _pack
@@ -1128,3 +1130,127 @@ class TestV1ToV2Migration:
         assert "DocumentChunksTable.create" not in source
         assert "DocumentMetaTable.create" not in source
         assert "_create_vec_table(" not in source
+
+
+LEGACY_PAGE_SIZE = 4096
+
+
+def vec_table_sql(db_path: Path) -> str:
+    conn = sqlite3.connect(db_path)
+    try:
+        return conn.execute(
+            "SELECT sql FROM sqlite_master WHERE name = ?",
+            (DEFAULT_TABLE_NAME,),
+        ).fetchone()[0]
+    finally:
+        conn.close()
+
+
+def page_size_of(db_path: Path) -> int:
+    conn = sqlite3.connect(db_path)
+    try:
+        return conn.execute("PRAGMA page_size").fetchone()[0]
+    finally:
+        conn.close()
+
+
+def create_legacy_vec_table(conn: sqlite3.Connection, dim: int) -> None:
+    """The table definition from before chunk_size was set explicitly."""
+    conn.execute(
+        f"CREATE VIRTUAL TABLE {DEFAULT_TABLE_NAME} USING vec0("
+        "id TEXT PRIMARY KEY, document_id INTEGER, +node_content TEXT, "
+        f"embedding float[{dim}] distance_metric=cosine)",
+    )
+
+
+@pytest.fixture
+def legacy_page_size_db(tmp_path: Path) -> Path:
+    """An existing index file created before the page size was set."""
+    db_path = tmp_path / DB_FILENAME
+    conn = sqlite3.connect(db_path)
+    conn.execute(f"PRAGMA page_size={LEGACY_PAGE_SIZE}")
+    conn.execute("CREATE TABLE _seed(x)")
+    conn.execute("DROP TABLE _seed")
+    conn.close()
+    assert page_size_of(db_path) == LEGACY_PAGE_SIZE
+    return db_path
+
+
+class TestVecChunkSize:
+    def test_new_table_uses_configured_chunk_size(
+        self,
+        store: PaperlessSqliteVecVectorStore,
+        tmp_path: Path,
+    ) -> None:
+        """
+        GIVEN an empty store
+        WHEN the first document is indexed and the vec0 table is created
+        THEN the table definition carries the configured chunk size
+        """
+        store.upsert_document(1, [make_node("1-a", 1)])
+
+        assert f"chunk_size={VEC0_CHUNK_SIZE}" in vec_table_sql(tmp_path / DB_FILENAME)
+
+    def test_compact_moves_legacy_table_to_configured_chunk_size(
+        self,
+        store: PaperlessSqliteVecVectorStore,
+        tmp_path: Path,
+        mocker: MockerFixture,
+    ) -> None:
+        """
+        GIVEN an index whose vec0 table was created with the default chunk size
+        WHEN the index is compacted
+        THEN the rebuilt table uses the configured chunk size
+        AND no indexed chunks are lost
+        """
+        legacy = mocker.patch.object(
+            PaperlessSqliteVecVectorStore,
+            "_create_vec_table",
+            staticmethod(create_legacy_vec_table),
+        )
+        store.upsert_document(1, [make_node("1-a", 1), make_node("1-b", 1)])
+        store.upsert_document(2, [make_node("2-a", 2)])
+        mocker.stop(legacy)
+        assert "chunk_size" not in vec_table_sql(tmp_path / DB_FILENAME)
+
+        store.compact(force=True)
+
+        assert f"chunk_size={VEC0_CHUNK_SIZE}" in vec_table_sql(tmp_path / DB_FILENAME)
+        assert DocumentChunksTable.count(store.client) == 3
+
+
+class TestIndexPageSize:
+    def test_new_index_file_uses_configured_page_size(
+        self,
+        store: PaperlessSqliteVecVectorStore,
+        tmp_path: Path,
+    ) -> None:
+        """
+        GIVEN no existing index file
+        WHEN a store is opened and a document is indexed
+        THEN the database file uses the configured page size
+        """
+        store.upsert_document(1, [make_node("1-a", 1)])
+
+        assert page_size_of(tmp_path / DB_FILENAME) == DB_PAGE_SIZE
+
+    def test_compact_moves_legacy_file_to_configured_page_size(
+        self,
+        legacy_page_size_db: Path,
+    ) -> None:
+        """
+        GIVEN an existing index file created with a different page size
+        WHEN the index is compacted
+        THEN the rebuilt file uses the configured page size
+        AND no indexed chunks are lost
+        """
+        with PaperlessSqliteVecVectorStore(
+            uri=str(legacy_page_size_db.parent),
+        ) as store:
+            store.upsert_document(1, [make_node("1-a", 1), make_node("1-b", 1)])
+            assert page_size_of(legacy_page_size_db) == LEGACY_PAGE_SIZE
+
+            store.compact(force=True)
+
+            assert page_size_of(legacy_page_size_db) == DB_PAGE_SIZE
+            assert DocumentChunksTable.count(store.client) == 2

src/paperless_ai/vector_store.py

@@ -47,6 +47,20 @@ SCHEMA_VERSION = 2
 # a rebuild copies the live rows into a fresh table.
 COMPACT_BLOAT_RATIO = 2.0
 
+# Rows per vec0 vector chunk (vec0's default is 1024, which makes each chunk a
+# multi-megabyte blob). On spinning disks, inserts and re-indexing were dozens
+# of times faster with small chunks, at no cost in query speed or file size.
+# Only applies to tables created from here on; an existing index picks it up
+# the next time it is rebuilt (compact or rebuild).
+VEC0_CHUNK_SIZE = 32
+
+# SQLite page size for the index file, in bytes. With the small vec0 chunks above,
+# 64 KiB pages made cold scans about 35% faster and warm ones about 45% faster,
+# at the cost of a larger write-ahead log (up to about 70 MB). Only takes effect
+# on a newly created file, so like the chunk size it reaches an existing index
+# when it is rebuilt.
+DB_PAGE_SIZE = 65536
+
 # Number of rows fetched/copied per batch whenever this module streams rows
 # instead of materializing them all at once, keeping memory bounded regardless
 # of index size -- used by compact()'s rebuild, m0001_v1_to_v2's migration
@@ -222,6 +236,7 @@ class PaperlessSqliteVecVectorStore(BasePydanticVectorStore):
         conn.enable_load_extension(True)  # noqa: FBT003
         sqlite_vec.load(conn)
         conn.enable_load_extension(False)  # noqa: FBT003
+        conn.execute(f"PRAGMA page_size={DB_PAGE_SIZE}")
         conn.execute("PRAGMA journal_mode=WAL")
         conn.execute("PRAGMA synchronous=NORMAL")
         IndexMetaTable.create(conn)
@@ -329,7 +344,8 @@ class PaperlessSqliteVecVectorStore(BasePydanticVectorStore):
             + " +node_content TEXT,"
             + " embedding float["
             + str(int(dim))
-            + "] distance_metric=cosine"
+            + "] distance_metric=cosine, chunk_size="
+            + str(VEC0_CHUNK_SIZE)
             + ")",
         )
 

uv.lock

@@ -1210,15 +1210,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/99/c3/305a9f7611c0dc96d2a638bc3a67bdcde5a7faa5f4669188db018b8af6fc/django_stubs_ext-6.1.1-py3-none-any.whl", hash = "sha256:64aebb7ce2c327a4a2b75207d67034e879fd7edf027c93487be69da363dc79fa", size = 10853, upload-time = "2026-09-14T08:45:51.289Z" },
 ]
 
-[[package]]
-name = "django-treenode"
-version = "0.25.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/cb/2b/09f04b44b3583a911ae4f5d0e3360a23d529704c9e9115fce2520b7d4420/django_treenode-0.25.0.tar.gz", hash = "sha256:d14d0eb3571c227ce11147210d62a8f87b568bbb30fa76a5be9b9e6d514157c3", size = 29951, upload-time = "2026-08-26T00:20:13.489Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/e1/ac/2140e8c20e2a47457ec23302273527d3430bf5c09edb8940d74c0725c138/django_treenode-0.25.0-py3-none-any.whl", hash = "sha256:f47caab5440420870b6287602b3ee401ca354416d44b24ab97579be5ea658927", size = 22343, upload-time = "2026-08-26T00:20:12.078Z" },
-]
-
 [[package]]
 name = "djangorestframework"
 version = "3.18.3"
@@ -3107,7 +3098,6 @@ dependencies = [
     { name = "django-multiselectfield" },
     { name = "django-rich" },
     { name = "django-soft-delete" },
-    { name = "django-treenode" },
     { name = "djangorestframework" },
     { name = "drf-spectacular" },
     { name = "drf-spectacular-sidecar" },
@@ -3258,7 +3248,6 @@ requires-dist = [
     { name = "django-multiselectfield", specifier = "~=1.0.1" },
     { name = "django-rich", specifier = "~=2.2.0" },
     { name = "django-soft-delete", specifier = "~=1.0.18" },
-    { name = "django-treenode", specifier = ">=0.24" },
     { name = "djangorestframework", specifier = "~=3.16" },
     { name = "drf-spectacular", specifier = "~=0.30" },
     { name = "drf-spectacular-sidecar", specifier = ">=2026.10.1,<2026.11" },