mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-08-11 05:13:18 +00:00
Compare commits
17
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
f38ce7a41a | ||
|
|
837e79ff22 | ||
|
|
8efe184fdf | ||
|
|
675267b441 | ||
|
|
1e8998f850 | ||
|
|
5b6b2d583d | ||
|
|
667e675be0 | ||
|
|
a00a288b0f | ||
|
|
ca927d2c69 | ||
|
|
f51d4338dc | ||
|
|
95452e79bd | ||
|
|
b74cc9a590 | ||
|
|
e3ac08d6c2 | ||
|
|
3e96ec4c63 | ||
|
|
64565fd6d8 | ||
|
|
aa015423ac | ||
|
|
ead3a46d3b |
+2
-2
@@ -227,6 +227,7 @@ Version-aware endpoints:
|
||||
- `PATCH /api/documents/{id}/`: content updates target the selected version (`?version={version_id}`) or latest version by default; non-content metadata updates target the root document.
|
||||
- `GET /api/documents/{id}/download/`, `GET /api/documents/{id}/preview/`, `GET /api/documents/{id}/thumb/`, `GET /api/documents/{id}/metadata/`: accept `?version={version_id}`.
|
||||
- `POST /api/documents/{id}/update_version/`: uploads a new version using multipart form field `document` and optional `version_label`.
|
||||
- `POST /api/documents/merge_as_versions/`: merges existing top-level documents as versions of a selected root. The JSON body must contain `documents` (at least two document IDs) and `root_document_id` (one of those IDs). When merging one source document, an optional `version_label` may be provided.
|
||||
- `PATCH /api/documents/{id}/versions/{version_id}/`: updates the `version_label` of a specific version.
|
||||
- `DELETE /api/documents/{root_id}/versions/{version_id}/`: deletes a non-root version.
|
||||
|
||||
@@ -301,8 +302,7 @@ The following methods are supported:
|
||||
- `delete`
|
||||
- No `parameters` required
|
||||
- `reprocess`
|
||||
- Optional `parameters`: `{ "remote_ocr": true }` to send the documents to the
|
||||
remote OCR engine, see [Remote OCR](usage.md#remote-ocr). Defaults to false.
|
||||
- No `parameters` required
|
||||
- `set_permissions`
|
||||
- Requires `parameters`:
|
||||
- `"set_permissions": PERMISSIONS_OBJ` (see format [above](#permissions)) and / or
|
||||
|
||||
@@ -2047,18 +2047,6 @@ password. All of these options come from their similarly-named [Django settings]
|
||||
|
||||
Defaults to None.
|
||||
|
||||
#### [`PAPERLESS_REMOTE_OCR_MODE=<str>`](#PAPERLESS_REMOTE_OCR_MODE) {#PAPERLESS_REMOTE_OCR_MODE}
|
||||
|
||||
: Which documents are sent to the remote OCR engine.
|
||||
|
||||
- `always`: every document of a supported file type is sent to the remote
|
||||
engine, bypassing the local OCR engine.
|
||||
- `workflow_only`: documents are processed locally unless a workflow
|
||||
explicitly enables remote OCR for them, letting you use the remote engine
|
||||
selectively.
|
||||
|
||||
Defaults to "always".
|
||||
|
||||
## AI {#ai}
|
||||
|
||||
#### [`PAPERLESS_AI_ENABLED=<bool>`](#PAPERLESS_AI_ENABLED) {#PAPERLESS_AI_ENABLED}
|
||||
|
||||
@@ -456,20 +456,6 @@ def score(
|
||||
return 10
|
||||
```
|
||||
|
||||
**Remote services**
|
||||
|
||||
If your parser sends document content to a remote service, declare it:
|
||||
|
||||
```python
|
||||
class MyCustomParser:
|
||||
uses_remote_service = True
|
||||
```
|
||||
|
||||
Paperless-ngx excludes such parsers when the document being consumed has not
|
||||
been marked for remote processing, so users can keep remote OCR off by default
|
||||
and enable it selectively with a workflow. Parsers that do not declare the
|
||||
attribute are treated as fully local and are always considered.
|
||||
|
||||
**Archive and rendition flags**
|
||||
|
||||
```python
|
||||
|
||||
+3
-51
@@ -99,6 +99,8 @@ Think of versions as **file history** for a document.
|
||||
- By default, search and document content use the latest version.
|
||||
- In document detail, selecting a version switches the preview, file metadata and content (and download etc buttons) to that version.
|
||||
- Deleting a non-root version keeps metadata and falls back to the latest remaining version.
|
||||
- From the document list, select two or more documents and choose **Merge as versions** to combine them under one entry. Select the root document whose metadata and permissions should be retained; the other selected documents become file versions. The root may already have versions, but documents being added as versions must not have version histories of their own.
|
||||
- From a document's **Versions** menu, choose **Existing** to search for another document and add it as a version of the current document.
|
||||
|
||||
### Management Lists
|
||||
|
||||
@@ -648,48 +650,6 @@ happened while it was still encrypted, that original version will likewise be mi
|
||||
**Current limitation**: Passwords are stored as a simple list without descriptions. To handle
|
||||
multiple PDF types with different passwords, create separate workflows for each use case.
|
||||
|
||||
##### Remote OCR {#workflow-action-remote-ocr}
|
||||
|
||||
"Remote OCR" actions send the document to the configured remote OCR engine instead of processing it
|
||||
locally. To use remote OCR selectively, set the [remote OCR mode](configuration.md#PAPERLESS_REMOTE_OCR_MODE)
|
||||
to `workflow_only` then add this action to a workflow that matches only the documents you
|
||||
want sent to the remote engine. See [Remote OCR](#remote-ocr) for the engine setup. The action only works with
|
||||
a **Consumption Started** trigger.
|
||||
|
||||
The action takes no options, its presence is what enables remote OCR for a matching document.
|
||||
|
||||
If the remote engine is not configured, or does not support the document's file type, the document is
|
||||
processed locally instead and a warning is written to the log.
|
||||
|
||||
##### Apply AI Suggestions {#workflow-action-apply-ai-suggestions}
|
||||
|
||||
"Apply AI Suggestions" actions ask the configured AI service for title and metadata suggestions,
|
||||
the same as the AI suggestions shown on the document detail page, except applied automatically and in bulk.
|
||||
It requires [AI features](configuration.md#ai) to be enabled. You can specify:
|
||||
|
||||
- Which suggestions to apply: title, tags, correspondent, document type, storage path and / or created
|
||||
date. Suggestions for fields you did not select are discarded.
|
||||
- Whether to create missing items. By default only tags, correspondents and document types that
|
||||
already exist are assigned and any other suggestion is dropped. With this enabled, suggested items
|
||||
that do not exist are created. Storage paths are never created.
|
||||
- Whether to overwrite existing values. By default a field is only filled in if it is currently empty.
|
||||
Note that documents almost always already have a title and created date, so if you select those you
|
||||
will usually want to enable this too. Tags are an exception: suggested tags are always added and
|
||||
never replace the document's existing tags.
|
||||
|
||||
The action works with every trigger **except Consumption Started**, because suggestions are made from
|
||||
the document's text, which does not exist until after the document has been processed.
|
||||
|
||||
Because the query to the AI service is slow, the action is queued and runs in the background rather
|
||||
than as part of the workflow run itself. The document is updated once the suggestions come back.
|
||||
|
||||
!!! warning
|
||||
|
||||
Every matching document results in a query to the AI service, which may incur costs and have privacy
|
||||
implications. Queries can be slow, so a workflow matching a large number of documents can occupy the
|
||||
task queue, and delay consumption of new documents, etc. Consider narrowing the trigger filters,
|
||||
running in small batches and / or increasing workers.
|
||||
|
||||
#### Workflow placeholders
|
||||
|
||||
Titles and webhook payloads can be generated by workflows using [Jinja templates](https://jinja.palletsprojects.com/en/3.1.x/templates/).
|
||||
@@ -1126,19 +1086,11 @@ Paperless-ngx supports performing OCR on documents using remote services. At the
|
||||
[Microsoft's Azure "Document Intelligence" service](https://azure.microsoft.com/en-us/products/ai-services/ai-document-intelligence).
|
||||
This is of course a paid service (with a free tier) which requires an Azure account and subscription. Azure AI is not affiliated with
|
||||
Paperless-ngx in any way. When enabled, Paperless-ngx will automatically send appropriate documents to Azure for OCR processing, bypassing
|
||||
the local OCR engine. See the [configuration](configuration.md#PAPERLESS_REMOTE_OCR_ENGINE) options for more details. These
|
||||
settings can be supplied as environment variables or via **Application Configuration**.
|
||||
the local OCR engine. See the [configuration](configuration.md#PAPERLESS_REMOTE_OCR_ENGINE) options for more details.
|
||||
|
||||
Additionally, when using a commercial service with this feature, consider both potential costs as well as any associated file size
|
||||
or page limitations (e.g. with a free tier).
|
||||
|
||||
By default, every document of a supported file type is sent to the remote engine. To use it more selectively, set the
|
||||
[remote OCR mode](configuration.md#PAPERLESS_REMOTE_OCR_MODE) to `workflow_only`. Documents are then processed locally
|
||||
unless a [remote OCR workflow action](#workflow-action-remote-ocr) enables it for them, so you can limit the remote
|
||||
engine to particular documents.
|
||||
|
||||
Setting the mode to `workflow_only` also allows the **Reprocess** actions to selectively use remote OCR for individual documents.
|
||||
|
||||
## Architecture
|
||||
|
||||
Paperless-ngx consists of the following components:
|
||||
|
||||
@@ -38,6 +38,7 @@ dependencies = [
|
||||
"django-soft-delete~=1.0.18",
|
||||
"django-treenode>=0.24",
|
||||
"djangorestframework~=3.16",
|
||||
"djangorestframework-guardian~=0.4.0",
|
||||
"drf-spectacular~=0.30",
|
||||
"drf-spectacular-sidecar~=2026.7.1",
|
||||
"drf-writable-nested~=0.7.1",
|
||||
|
||||
+6
-13
@@ -1703,7 +1703,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
|
||||
<context context-type="linenumber">34</context>
|
||||
<context context-type="linenumber">28</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/dashboard/widgets/statistics-widget/statistics-widget.component.html</context>
|
||||
@@ -3279,7 +3279,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
|
||||
<context context-type="linenumber">46</context>
|
||||
<context context-type="linenumber">40</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/dashboard/widgets/statistics-widget/statistics-widget.component.html</context>
|
||||
@@ -7070,39 +7070,32 @@
|
||||
<context context-type="linenumber">143</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="8336346011691074629" datatype="html">
|
||||
<source>No suggestions</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
|
||||
<context context-type="linenumber">11,12</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5320136382998259826" datatype="html">
|
||||
<source>Suggest</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
|
||||
<context context-type="linenumber">13,14</context>
|
||||
<context context-type="linenumber">8,9</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6934085657687954669" datatype="html">
|
||||
<source>Show suggestions</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
|
||||
<context context-type="linenumber">23,24</context>
|
||||
<context context-type="linenumber">17,18</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="3834115140127576673" datatype="html">
|
||||
<source>No novel suggestions</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
|
||||
<context context-type="linenumber">30,31</context>
|
||||
<context context-type="linenumber">24,25</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4369111787961525769" datatype="html">
|
||||
<source>Document Types</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html</context>
|
||||
<context context-type="linenumber">40</context>
|
||||
<context context-type="linenumber">34</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/dashboard/widgets/statistics-widget/statistics-widget.component.html</context>
|
||||
|
||||
+1
-1
@@ -66,5 +66,5 @@
|
||||
"ts-node": "~10.9.1",
|
||||
"typescript": "^6.0.3"
|
||||
},
|
||||
"packageManager": "pnpm@11.15.1"
|
||||
"packageManager": "pnpm@10.26.0"
|
||||
}
|
||||
|
||||
@@ -5,7 +5,6 @@ trustPolicy: no-downgrade
|
||||
trustPolicyExclude:
|
||||
- "chokidar@4.0.3"
|
||||
- "semver@6.3.1 || 5.7.2"
|
||||
blockExoticSubdeps: true
|
||||
allowBuilds:
|
||||
"@parcel/watcher": true
|
||||
canvas: true
|
||||
|
||||
@@ -14,48 +14,43 @@
|
||||
<a ngbNavLink>{{category}}</a>
|
||||
<ng-template ngbNavContent>
|
||||
<div class="p-3">
|
||||
@for (section of getCategorySections(category); track section) {
|
||||
@if (section) {
|
||||
<h5 class="mt-4 mb-3">{{section}}</h5>
|
||||
}
|
||||
<div class="row row-cols-1 row-cols-md-2 row-cols-lg-3 g-2">
|
||||
@for (option of getCategoryOptions(category, section); track option.key) {
|
||||
<div class="col">
|
||||
<div class="card bg-light">
|
||||
<div class="card-body">
|
||||
<div class="card-title d-flex align-items-center">
|
||||
<h6 class="mb-0">
|
||||
{{option.title}}
|
||||
</h6>
|
||||
<a class="btn btn-sm btn-link" title="Read the documentation about this setting" i18n-title [href]="getDocsUrl(option.config_key)" target="_blank" referrerpolicy="no-referrer">
|
||||
<i-bs name="info-circle"></i-bs>
|
||||
</a>
|
||||
@if (isSet(option.key)) {
|
||||
<button type="button" class="btn btn-sm btn-link text-danger ms-auto pe-0" title="Reset" i18n-title (click)="resetOption(option.key)">
|
||||
<i-bs class="me-1" name="x"></i-bs><ng-container i18n>Reset</ng-container>
|
||||
</button>
|
||||
}
|
||||
</div>
|
||||
<div class="mb-n3">
|
||||
@switch (option.type) {
|
||||
@case (ConfigOptionType.Select) { <pngx-input-select [formControlName]="option.key" [error]="errors[option.key]" [items]="option.choices" [allowNull]="true"></pngx-input-select> }
|
||||
@case (ConfigOptionType.Number) { <pngx-input-number [formControlName]="option.key" [error]="errors[option.key]" [showAdd]="false"></pngx-input-number> }
|
||||
@case (ConfigOptionType.Boolean) { <pngx-input-switch [formControlName]="option.key" [error]="errors[option.key]" [showUnsetNote]="true" [horizontal]="true" title="Enable" i18n-title></pngx-input-switch> }
|
||||
@case (ConfigOptionType.String) { <pngx-input-text [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-text> }
|
||||
@case (ConfigOptionType.JSON) { <pngx-input-text [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-text> }
|
||||
@case (ConfigOptionType.File) { <pngx-input-file [formControlName]="option.key" (upload)="uploadFile($event, option.key)" [error]="errors[option.key]"></pngx-input-file> }
|
||||
@case (ConfigOptionType.Password) { <pngx-input-password [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-password> }
|
||||
}
|
||||
</div>
|
||||
@if (option.note) {
|
||||
<div class="form-text fst-italic">{{option.note}}</div>
|
||||
<div class="row row-cols-1 row-cols-md-2 row-cols-lg-3 g-2">
|
||||
@for (option of getCategoryOptions(category); track option.key) {
|
||||
<div class="col">
|
||||
<div class="card bg-light">
|
||||
<div class="card-body">
|
||||
<div class="card-title d-flex align-items-center">
|
||||
<h6 class="mb-0">
|
||||
{{option.title}}
|
||||
</h6>
|
||||
<a class="btn btn-sm btn-link" title="Read the documentation about this setting" i18n-title [href]="getDocsUrl(option.config_key)" target="_blank" referrerpolicy="no-referrer">
|
||||
<i-bs name="info-circle"></i-bs>
|
||||
</a>
|
||||
@if (isSet(option.key)) {
|
||||
<button type="button" class="btn btn-sm btn-link text-danger ms-auto pe-0" title="Reset" i18n-title (click)="resetOption(option.key)">
|
||||
<i-bs class="me-1" name="x"></i-bs><ng-container i18n>Reset</ng-container>
|
||||
</button>
|
||||
}
|
||||
</div>
|
||||
<div class="mb-n3">
|
||||
@switch (option.type) {
|
||||
@case (ConfigOptionType.Select) { <pngx-input-select [formControlName]="option.key" [error]="errors[option.key]" [items]="option.choices" [allowNull]="true"></pngx-input-select> }
|
||||
@case (ConfigOptionType.Number) { <pngx-input-number [formControlName]="option.key" [error]="errors[option.key]" [showAdd]="false"></pngx-input-number> }
|
||||
@case (ConfigOptionType.Boolean) { <pngx-input-switch [formControlName]="option.key" [error]="errors[option.key]" [showUnsetNote]="true" [horizontal]="true" title="Enable" i18n-title></pngx-input-switch> }
|
||||
@case (ConfigOptionType.String) { <pngx-input-text [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-text> }
|
||||
@case (ConfigOptionType.JSON) { <pngx-input-text [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-text> }
|
||||
@case (ConfigOptionType.File) { <pngx-input-file [formControlName]="option.key" (upload)="uploadFile($event, option.key)" [error]="errors[option.key]"></pngx-input-file> }
|
||||
@case (ConfigOptionType.Password) { <pngx-input-password [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-password> }
|
||||
}
|
||||
</div>
|
||||
@if (option.note) {
|
||||
<div class="form-text fst-italic">{{option.note}}</div>
|
||||
}
|
||||
</div>
|
||||
</div>
|
||||
}
|
||||
</div>
|
||||
}
|
||||
</div>
|
||||
}
|
||||
</div>
|
||||
</div>
|
||||
</ng-template>
|
||||
</li>
|
||||
|
||||
@@ -8,11 +8,7 @@ import { NgbModule } from '@ng-bootstrap/ng-bootstrap'
|
||||
import { NgSelectModule } from '@ng-select/ng-select'
|
||||
import { NgxBootstrapIconsModule, allIcons } from 'ngx-bootstrap-icons'
|
||||
import { of, throwError } from 'rxjs'
|
||||
import {
|
||||
ConfigCategory,
|
||||
ConfigSection,
|
||||
OutputTypeConfig,
|
||||
} from 'src/app/data/paperless-config'
|
||||
import { OutputTypeConfig } from 'src/app/data/paperless-config'
|
||||
import { ConfigService } from 'src/app/services/config.service'
|
||||
import { SettingsService } from 'src/app/services/settings.service'
|
||||
import { ToastService } from 'src/app/services/toast.service'
|
||||
@@ -162,24 +158,4 @@ describe('ConfigComponent', () => {
|
||||
component.resetOption('barcodes_enabled')
|
||||
expect(component.configForm.get('barcodes_enabled').value).toBeNull()
|
||||
})
|
||||
|
||||
it('should group options into sections within a category, or not', () => {
|
||||
const sections = component.getCategorySections(ConfigCategory.OCR)
|
||||
expect(sections).toEqual([null, ConfigSection.RemoteOCR])
|
||||
expect(
|
||||
component
|
||||
.getCategoryOptions(ConfigCategory.OCR)
|
||||
.map((option) => option.key)
|
||||
).toContain('output_type')
|
||||
expect(
|
||||
component
|
||||
.getCategoryOptions(ConfigCategory.OCR, ConfigSection.RemoteOCR)
|
||||
.map((option) => option.key)
|
||||
).toEqual([
|
||||
'remote_ocr_engine',
|
||||
'remote_ocr_api_key',
|
||||
'remote_ocr_endpoint',
|
||||
'remote_ocr_mode',
|
||||
])
|
||||
})
|
||||
})
|
||||
|
||||
@@ -74,20 +74,8 @@ export class ConfigComponent
|
||||
return Object.values(ConfigCategory)
|
||||
}
|
||||
|
||||
getCategorySections(category: string): string[] {
|
||||
return [
|
||||
...new Set(
|
||||
PaperlessConfigOptions.filter((o) => o.category === category).map(
|
||||
(o) => o.section ?? null // null means no section
|
||||
)
|
||||
),
|
||||
]
|
||||
}
|
||||
|
||||
getCategoryOptions(category: string, section: string = null): ConfigOption[] {
|
||||
return PaperlessConfigOptions.filter(
|
||||
(o) => o.category === category && (o.section ?? null) === section
|
||||
)
|
||||
getCategoryOptions(category: string): ConfigOption[] {
|
||||
return PaperlessConfigOptions.filter((o) => o.category === category)
|
||||
}
|
||||
|
||||
initialConfig: PaperlessConfig
|
||||
|
||||
+48
@@ -0,0 +1,48 @@
|
||||
<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">
|
||||
<p>{{message}}</p>
|
||||
<div class="form-group">
|
||||
<span class="form-label d-inline-block" i18n>Versions:</span>
|
||||
<ul class="list-group">
|
||||
@for (documentID of versionDocumentIDs(); track documentID) {
|
||||
@let document = getDocument(documentID);
|
||||
@if (document) {
|
||||
<li class="list-group-item d-flex align-items-center">
|
||||
<div class="d-flex flex-column">
|
||||
<div>
|
||||
@if (document.correspondent) {
|
||||
<b>{{document.correspondent | correspondentName | async}}: </b>
|
||||
}{{document.title}}
|
||||
</div>
|
||||
<small class="text-muted">
|
||||
{{document.created | customDate:'mediumDate'}}
|
||||
@if (document.page_count) {
|
||||
| {document.page_count, plural, =1 {One page} other {{{document.page_count}} pages}}
|
||||
}
|
||||
</small>
|
||||
</div>
|
||||
</li>
|
||||
}
|
||||
}
|
||||
</ul>
|
||||
</div>
|
||||
<div class="form-group mt-4">
|
||||
<label class="form-label" for="rootDocumentID" i18n>Root document:</label>
|
||||
<select id="rootDocumentID" class="form-select" [ngModel]="rootDocumentID()" (ngModelChange)="rootDocumentID.set($event)">
|
||||
@for (document of documents(); track document.id) {
|
||||
<option [ngValue]="document.id">{{document.title}}</option>
|
||||
}
|
||||
</select>
|
||||
</div>
|
||||
</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>
|
||||
+56
@@ -0,0 +1,56 @@
|
||||
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 { DocumentService } from 'src/app/services/rest/document.service'
|
||||
import { MergeAsVersionsConfirmDialogComponent } from './merge-as-versions-confirm-dialog.component'
|
||||
|
||||
describe('MergeAsVersionsConfirmDialogComponent', () => {
|
||||
let component: MergeAsVersionsConfirmDialogComponent
|
||||
let fixture: ComponentFixture<MergeAsVersionsConfirmDialogComponent>
|
||||
let documentService: DocumentService
|
||||
|
||||
beforeEach(async () => {
|
||||
await TestBed.configureTestingModule({
|
||||
imports: [MergeAsVersionsConfirmDialogComponent],
|
||||
providers: [
|
||||
NgbActiveModal,
|
||||
provideHttpClient(withInterceptorsFromDi()),
|
||||
provideHttpClientTesting(),
|
||||
],
|
||||
}).compileComponents()
|
||||
|
||||
fixture = TestBed.createComponent(MergeAsVersionsConfirmDialogComponent)
|
||||
documentService = TestBed.inject(DocumentService)
|
||||
component = fixture.componentInstance
|
||||
fixture.detectChanges()
|
||||
})
|
||||
|
||||
it('should fetch selected documents', () => {
|
||||
const documents = [
|
||||
{ id: 1, title: 'Document 1' },
|
||||
{ id: 2, title: 'Document 2' },
|
||||
]
|
||||
jest.spyOn(documentService, 'getFew').mockReturnValue(
|
||||
of({
|
||||
all: [1, 2],
|
||||
count: 2,
|
||||
results: documents,
|
||||
})
|
||||
)
|
||||
component.documentIDs.set([1, 2])
|
||||
|
||||
component.ngOnInit()
|
||||
|
||||
expect(component.documents()).toEqual(documents)
|
||||
expect(documentService.getFew).toHaveBeenCalledWith([1, 2])
|
||||
})
|
||||
|
||||
it('should exclude the root from the draggable documents', () => {
|
||||
component.documentIDs.set([1, 2, 3])
|
||||
component.rootDocumentID.set(2)
|
||||
|
||||
expect(component.versionDocumentIDs()).toEqual([1, 3])
|
||||
})
|
||||
})
|
||||
+41
@@ -0,0 +1,41 @@
|
||||
import { AsyncPipe } from '@angular/common'
|
||||
import { Component, OnInit, computed, inject, signal } from '@angular/core'
|
||||
import { FormsModule } from '@angular/forms'
|
||||
import { takeUntil } from 'rxjs'
|
||||
import { Document } from 'src/app/data/document'
|
||||
import { CorrespondentNamePipe } from 'src/app/pipes/correspondent-name.pipe'
|
||||
import { CustomDatePipe } from 'src/app/pipes/custom-date.pipe'
|
||||
import { DocumentService } from 'src/app/services/rest/document.service'
|
||||
import { ConfirmDialogComponent } from '../confirm-dialog.component'
|
||||
|
||||
@Component({
|
||||
selector: 'pngx-merge-as-versions-confirm-dialog',
|
||||
templateUrl: './merge-as-versions-confirm-dialog.component.html',
|
||||
imports: [AsyncPipe, CorrespondentNamePipe, CustomDatePipe, FormsModule],
|
||||
})
|
||||
export class MergeAsVersionsConfirmDialogComponent
|
||||
extends ConfirmDialogComponent
|
||||
implements OnInit
|
||||
{
|
||||
private readonly documentService = inject(DocumentService)
|
||||
|
||||
readonly documentIDs = signal<number[]>([])
|
||||
readonly documents = signal<Document[]>([])
|
||||
readonly rootDocumentID = signal(-1)
|
||||
readonly versionDocumentIDs = computed(() =>
|
||||
this.documentIDs().filter(
|
||||
(documentID) => documentID !== this.rootDocumentID()
|
||||
)
|
||||
)
|
||||
|
||||
ngOnInit() {
|
||||
this.documentService
|
||||
.getFew(this.documentIDs())
|
||||
.pipe(takeUntil(this.unsubscribeNotifier))
|
||||
.subscribe((response) => this.documents.set(response.results))
|
||||
}
|
||||
|
||||
getDocument(documentID: number): Document {
|
||||
return this.documents().find((document) => document.id === documentID)
|
||||
}
|
||||
}
|
||||
+1
-1
@@ -36,7 +36,7 @@
|
||||
</div>
|
||||
<div class="form-group mt-4">
|
||||
<label class="form-label" for="metadataDocumentID" i18n>Use metadata from:</label>
|
||||
<select class="form-select" [ngModel]="metadataDocumentID()" (ngModelChange)="metadataDocumentID.set($event)">
|
||||
<select id="metadataDocumentID" class="form-select" [ngModel]="metadataDocumentID()" (ngModelChange)="metadataDocumentID.set($event)">
|
||||
<option [ngValue]="-1" i18n>Regenerate all metadata</option>
|
||||
@for (document of documents(); track document.id) {
|
||||
<option [ngValue]="document.id">{{document.title}}</option>
|
||||
|
||||
-28
@@ -1,28 +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="mb-0 text-break" [innerHTML]="message"></p>
|
||||
}
|
||||
@if (showRemoteOcr) {
|
||||
<div class="form-check mt-3">
|
||||
<input class="form-check-input" type="checkbox" id="reprocessRemoteOcr" [(ngModel)]="remoteOcr" />
|
||||
<label class="form-check-label" for="reprocessRemoteOcr" i18n>Use remote OCR</label>
|
||||
<div class="form-text" i18n>Sends the document to the configured remote OCR service, which may incur costs.</div>
|
||||
</div>
|
||||
}
|
||||
</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>
|
||||
-72
@@ -1,72 +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 { RemoteOCRModeConfig } from 'src/app/data/paperless-config'
|
||||
import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
|
||||
import { SettingsService } from 'src/app/services/settings.service'
|
||||
import { ReprocessConfirmDialogComponent } from './reprocess-confirm-dialog.component'
|
||||
|
||||
describe('ReprocessConfirmDialogComponent', () => {
|
||||
let component: ReprocessConfirmDialogComponent
|
||||
let fixture: ComponentFixture<ReprocessConfirmDialogComponent>
|
||||
let settingsService: SettingsService
|
||||
|
||||
const createComponent = (configured: boolean, mode: string) => {
|
||||
settingsService.set(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED, configured)
|
||||
settingsService.set(SETTINGS_KEYS.REMOTE_OCR_MODE, mode)
|
||||
|
||||
fixture = TestBed.createComponent(ReprocessConfirmDialogComponent)
|
||||
component = fixture.componentInstance
|
||||
fixture.detectChanges()
|
||||
}
|
||||
|
||||
beforeEach(async () => {
|
||||
TestBed.configureTestingModule({
|
||||
providers: [
|
||||
NgbActiveModal,
|
||||
provideHttpClient(withInterceptorsFromDi()),
|
||||
provideHttpClientTesting(),
|
||||
],
|
||||
imports: [ReprocessConfirmDialogComponent],
|
||||
}).compileComponents()
|
||||
|
||||
settingsService = TestBed.inject(SettingsService)
|
||||
})
|
||||
|
||||
it('should not request remote OCR by default', () => {
|
||||
createComponent(true, RemoteOCRModeConfig.WORKFLOW_ONLY)
|
||||
|
||||
expect(component.remoteOcr).toBeFalsy()
|
||||
})
|
||||
|
||||
it('should not offer remote OCR when no engine is configured', () => {
|
||||
createComponent(false, RemoteOCRModeConfig.WORKFLOW_ONLY)
|
||||
|
||||
expect(component.showRemoteOcr).toBeFalsy()
|
||||
expect(
|
||||
fixture.nativeElement.querySelector('#reprocessRemoteOcr')
|
||||
).toBeNull()
|
||||
})
|
||||
|
||||
it('should not offer remote OCR when it already handles every document', () => {
|
||||
createComponent(true, RemoteOCRModeConfig.ALWAYS)
|
||||
|
||||
expect(component.showRemoteOcr).toBeFalsy()
|
||||
expect(
|
||||
fixture.nativeElement.querySelector('#reprocessRemoteOcr')
|
||||
).toBeNull()
|
||||
})
|
||||
|
||||
it('should offer remote OCR when configured and selective', () => {
|
||||
createComponent(true, RemoteOCRModeConfig.WORKFLOW_ONLY)
|
||||
|
||||
expect(component.showRemoteOcr).toBeTruthy()
|
||||
const checkbox = fixture.nativeElement.querySelector('#reprocessRemoteOcr')
|
||||
expect(checkbox).not.toBeNull()
|
||||
|
||||
checkbox.click()
|
||||
fixture.detectChanges()
|
||||
expect(component.remoteOcr).toBeTruthy()
|
||||
})
|
||||
})
|
||||
-20
@@ -1,20 +0,0 @@
|
||||
import { Component, inject } from '@angular/core'
|
||||
import { FormsModule } from '@angular/forms'
|
||||
import { SettingsService } from 'src/app/services/settings.service'
|
||||
import { ConfirmDialogComponent } from '../confirm-dialog.component'
|
||||
|
||||
@Component({
|
||||
selector: 'pngx-reprocess-confirm-dialog',
|
||||
templateUrl: './reprocess-confirm-dialog.component.html',
|
||||
imports: [FormsModule],
|
||||
})
|
||||
export class ReprocessConfirmDialogComponent extends ConfirmDialogComponent {
|
||||
private settings = inject(SettingsService)
|
||||
|
||||
remoteOcr: boolean = false
|
||||
|
||||
public get showRemoteOcr(): boolean {
|
||||
// Hidden when it is not configured, or when it already handles every document anyway.
|
||||
return this.settings.remoteOCRIsSelectable
|
||||
}
|
||||
}
|
||||
-46
@@ -455,52 +455,6 @@
|
||||
</div>
|
||||
</div>
|
||||
}
|
||||
@case (WorkflowActionType.RemoteOcr) {
|
||||
<div class="row">
|
||||
<div class="col">
|
||||
<p class="text-muted small" i18n>The document will be sent to the configured remote OCR service. May incur costs.</p>
|
||||
</div>
|
||||
</div>
|
||||
}
|
||||
@case (WorkflowActionType.ApplyAiSuggestions) {
|
||||
<div class="row">
|
||||
<div class="col">
|
||||
<p class="text-muted small" i18n>The document will be sent to the configured AI service for suggestions. Consider costs and privacy.</p>
|
||||
<pngx-input-select
|
||||
i18n-title
|
||||
title="Apply suggestions for"
|
||||
[items]="aiSuggestionFieldOptions"
|
||||
[multiple]="true"
|
||||
formControlName="ai_suggestion_fields"
|
||||
[error]="error?.actions?.[i]?.ai_suggestion_fields"
|
||||
hint="Suggestions for fields that are not selected are discarded."
|
||||
i18n-hint
|
||||
></pngx-input-select>
|
||||
</div>
|
||||
</div>
|
||||
<div class="row">
|
||||
<div class="col-md-6">
|
||||
<pngx-input-switch
|
||||
[horizontal]="true"
|
||||
i18n-title
|
||||
title="Create missing items"
|
||||
formControlName="ai_create_missing"
|
||||
hint="Create suggested tags, correspondents and document types that do not exist yet."
|
||||
i18n-hint
|
||||
></pngx-input-switch>
|
||||
</div>
|
||||
<div class="col-md-6">
|
||||
<pngx-input-switch
|
||||
[horizontal]="true"
|
||||
i18n-title
|
||||
title="Overwrite existing values"
|
||||
formControlName="ai_overwrite_existing"
|
||||
hint="Apply suggestions even if the document already has a value. Tags are always added, never replaced."
|
||||
i18n-hint
|
||||
></pngx-input-switch>
|
||||
</div>
|
||||
</div>
|
||||
}
|
||||
}
|
||||
</div>
|
||||
</ng-template>
|
||||
|
||||
+3
-228
@@ -22,7 +22,6 @@ import {
|
||||
} from 'src/app/data/matching-model'
|
||||
import { Workflow } from 'src/app/data/workflow'
|
||||
import {
|
||||
AISuggestionField,
|
||||
WorkflowAction,
|
||||
WorkflowActionType,
|
||||
} from 'src/app/data/workflow-action'
|
||||
@@ -30,7 +29,6 @@ import {
|
||||
DocumentSource,
|
||||
WorkflowTriggerType,
|
||||
} from 'src/app/data/workflow-trigger'
|
||||
import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
|
||||
import { IfOwnerDirective } from 'src/app/directives/if-owner.directive'
|
||||
import { IfPermissionsDirective } from 'src/app/directives/if-permissions.directive'
|
||||
import { CorrespondentService } from 'src/app/services/rest/correspondent.service'
|
||||
@@ -50,7 +48,6 @@ import { TagsComponent } from '../../input/tags/tags.component'
|
||||
import { TextComponent } from '../../input/text/text.component'
|
||||
import { EditDialogMode } from '../edit-dialog.component'
|
||||
import {
|
||||
AI_SUGGESTION_FIELD_OPTIONS,
|
||||
DOCUMENT_SOURCE_OPTIONS,
|
||||
SCHEDULE_DATE_FIELD_OPTIONS,
|
||||
TriggerFilterType,
|
||||
@@ -227,12 +224,7 @@ describe('WorkflowEditDialogComponent', () => {
|
||||
).toEqual('Document Added')
|
||||
expect(component.getTriggerTypeOptionName(null)).toEqual('')
|
||||
expect(component.sourceOptions).toEqual(DOCUMENT_SOURCE_OPTIONS)
|
||||
// Remote OCR is absent until the workflow has a consumption trigger
|
||||
expect(component.actionTypeOptions).toEqual(
|
||||
WORKFLOW_ACTION_OPTIONS.filter(
|
||||
(a) => a.id !== WorkflowActionType.RemoteOcr
|
||||
)
|
||||
)
|
||||
expect(component.actionTypeOptions).toEqual(WORKFLOW_ACTION_OPTIONS)
|
||||
expect(
|
||||
component.getActionTypeOptionName(WorkflowActionType.Assignment)
|
||||
).toEqual('Assignment')
|
||||
@@ -241,231 +233,14 @@ describe('WorkflowEditDialogComponent', () => {
|
||||
SCHEDULE_DATE_FIELD_OPTIONS
|
||||
)
|
||||
|
||||
// Email, remote OCR and AI all disabled
|
||||
// Email disabled
|
||||
jest.spyOn(settingsService, 'get').mockReturnValue(false)
|
||||
component.ngOnInit()
|
||||
expect(component.actionTypeOptions).toEqual(
|
||||
WORKFLOW_ACTION_OPTIONS.filter(
|
||||
(a) =>
|
||||
a.id !== WorkflowActionType.Email &&
|
||||
a.id !== WorkflowActionType.RemoteOcr &&
|
||||
a.id !== WorkflowActionType.ApplyAiSuggestions
|
||||
)
|
||||
WORKFLOW_ACTION_OPTIONS.filter((a) => a.id !== WorkflowActionType.Email)
|
||||
)
|
||||
})
|
||||
|
||||
it('should offer remote OCR only for consumption workflows', () => {
|
||||
jest.spyOn(settingsService, 'get').mockReturnValue(true)
|
||||
|
||||
// A consumption trigger makes the action reachable
|
||||
component.object = {
|
||||
name: 'Workflow 1',
|
||||
order: 0,
|
||||
enabled: true,
|
||||
triggers: [{ type: WorkflowTriggerType.Consumption }],
|
||||
actions: [],
|
||||
} as Workflow
|
||||
component.ngOnInit()
|
||||
expect(component.actionTypeOptions.map((a) => a.id)).toContain(
|
||||
WorkflowActionType.RemoteOcr
|
||||
)
|
||||
|
||||
// Any other trigger type runs after the document has been parsed
|
||||
component.object = {
|
||||
name: 'Workflow 2',
|
||||
order: 0,
|
||||
enabled: true,
|
||||
triggers: [{ type: WorkflowTriggerType.DocumentAdded }],
|
||||
actions: [],
|
||||
} as Workflow
|
||||
component.ngOnInit()
|
||||
expect(component.actionTypeOptions.map((a) => a.id)).not.toContain(
|
||||
WorkflowActionType.RemoteOcr
|
||||
)
|
||||
})
|
||||
|
||||
it('should offer remote OCR on a trigger added to a new workflow', () => {
|
||||
jest.spyOn(settingsService, 'get').mockReturnValue(true)
|
||||
component.ngOnInit()
|
||||
|
||||
// Nothing for the action to apply to yet
|
||||
expect(component.actionTypeOptions.map((a) => a.id)).not.toContain(
|
||||
WorkflowActionType.RemoteOcr
|
||||
)
|
||||
|
||||
// addTrigger creates the form field with emitEvent false, so the options
|
||||
// have to be computed on read rather than cached from valueChanges
|
||||
component.addTrigger()
|
||||
expect(component.actionTypeOptions.map((a) => a.id)).toContain(
|
||||
WorkflowActionType.RemoteOcr
|
||||
)
|
||||
|
||||
// Switching that trigger to a type that runs after parsing removes it
|
||||
component.triggerFields
|
||||
.at(0)
|
||||
.get('type')
|
||||
.setValue(WorkflowTriggerType.DocumentAdded)
|
||||
expect(component.actionTypeOptions.map((a) => a.id)).not.toContain(
|
||||
WorkflowActionType.RemoteOcr
|
||||
)
|
||||
})
|
||||
|
||||
it('should keep remote OCR listed when an action already uses it', () => {
|
||||
jest.spyOn(settingsService, 'get').mockReturnValue(true)
|
||||
|
||||
// Otherwise changing the trigger would silently blank the selection
|
||||
component.object = {
|
||||
name: 'Workflow 1',
|
||||
order: 0,
|
||||
enabled: true,
|
||||
triggers: [{ type: WorkflowTriggerType.DocumentAdded }],
|
||||
actions: [{ type: WorkflowActionType.RemoteOcr }],
|
||||
} as Workflow
|
||||
component.ngOnInit()
|
||||
|
||||
expect(component.actionTypeOptions.map((a) => a.id)).toContain(
|
||||
WorkflowActionType.RemoteOcr
|
||||
)
|
||||
})
|
||||
|
||||
it('should not offer remote OCR when no engine is configured', () => {
|
||||
jest
|
||||
.spyOn(settingsService, 'get')
|
||||
.mockImplementation((key) => key !== SETTINGS_KEYS.REMOTE_OCR_CONFIGURED)
|
||||
|
||||
component.object = {
|
||||
name: 'Workflow 1',
|
||||
order: 0,
|
||||
enabled: true,
|
||||
triggers: [{ type: WorkflowTriggerType.Consumption }],
|
||||
actions: [],
|
||||
} as Workflow
|
||||
component.ngOnInit()
|
||||
|
||||
expect(component.actionTypeOptions.map((a) => a.id)).not.toContain(
|
||||
WorkflowActionType.RemoteOcr
|
||||
)
|
||||
})
|
||||
|
||||
it('should offer apply AI suggestions unless every trigger is consumption', () => {
|
||||
jest.spyOn(settingsService, 'get').mockReturnValue(true)
|
||||
|
||||
// Consumption runs before the document has been parsed, so there would be
|
||||
// no content to make suggestions from
|
||||
component.object = {
|
||||
name: 'Workflow 1',
|
||||
order: 0,
|
||||
enabled: true,
|
||||
triggers: [{ type: WorkflowTriggerType.Consumption }],
|
||||
actions: [],
|
||||
} as Workflow
|
||||
component.ngOnInit()
|
||||
expect(component.actionTypeOptions.map((a) => a.id)).not.toContain(
|
||||
WorkflowActionType.ApplyAiSuggestions
|
||||
)
|
||||
|
||||
// A second, usable trigger is enough
|
||||
component.object = {
|
||||
name: 'Workflow 2',
|
||||
order: 0,
|
||||
enabled: true,
|
||||
triggers: [
|
||||
{ type: WorkflowTriggerType.Consumption },
|
||||
{ type: WorkflowTriggerType.DocumentAdded },
|
||||
],
|
||||
actions: [],
|
||||
} as Workflow
|
||||
component.ngOnInit()
|
||||
expect(component.actionTypeOptions.map((a) => a.id)).toContain(
|
||||
WorkflowActionType.ApplyAiSuggestions
|
||||
)
|
||||
})
|
||||
|
||||
it('should keep apply AI suggestions listed when an action already uses it', () => {
|
||||
jest.spyOn(settingsService, 'get').mockReturnValue(true)
|
||||
|
||||
// Otherwise changing the trigger would silently blank the selection
|
||||
component.object = {
|
||||
name: 'Workflow 1',
|
||||
order: 0,
|
||||
enabled: true,
|
||||
triggers: [{ type: WorkflowTriggerType.Consumption }],
|
||||
actions: [{ type: WorkflowActionType.ApplyAiSuggestions }],
|
||||
} as Workflow
|
||||
component.ngOnInit()
|
||||
|
||||
expect(component.actionTypeOptions.map((a) => a.id)).toContain(
|
||||
WorkflowActionType.ApplyAiSuggestions
|
||||
)
|
||||
})
|
||||
|
||||
it('should not offer apply AI suggestions when AI is disabled', () => {
|
||||
jest
|
||||
.spyOn(settingsService, 'get')
|
||||
.mockImplementation((key) => key !== SETTINGS_KEYS.AI_ENABLED)
|
||||
|
||||
component.object = {
|
||||
name: 'Workflow 1',
|
||||
order: 0,
|
||||
enabled: true,
|
||||
triggers: [{ type: WorkflowTriggerType.DocumentAdded }],
|
||||
actions: [],
|
||||
} as Workflow
|
||||
component.ngOnInit()
|
||||
|
||||
expect(component.actionTypeOptions.map((a) => a.id)).not.toContain(
|
||||
WorkflowActionType.ApplyAiSuggestions
|
||||
)
|
||||
})
|
||||
|
||||
it('should create form fields for apply AI suggestions options', () => {
|
||||
component.object = {
|
||||
name: 'Workflow 1',
|
||||
order: 0,
|
||||
enabled: true,
|
||||
triggers: [{ type: WorkflowTriggerType.DocumentAdded }],
|
||||
actions: [
|
||||
{
|
||||
type: WorkflowActionType.ApplyAiSuggestions,
|
||||
ai_suggestion_fields: [
|
||||
AISuggestionField.Title,
|
||||
AISuggestionField.Tags,
|
||||
],
|
||||
ai_create_missing: true,
|
||||
ai_overwrite_existing: true,
|
||||
},
|
||||
],
|
||||
} as Workflow
|
||||
component.ngOnInit()
|
||||
|
||||
const action = component.actionFields.at(0)
|
||||
expect(action.get('ai_suggestion_fields').value).toEqual([
|
||||
AISuggestionField.Title,
|
||||
AISuggestionField.Tags,
|
||||
])
|
||||
expect(action.get('ai_create_missing').value).toBeTruthy()
|
||||
expect(action.get('ai_overwrite_existing').value).toBeTruthy()
|
||||
expect(component.aiSuggestionFieldOptions).toEqual(
|
||||
AI_SUGGESTION_FIELD_OPTIONS
|
||||
)
|
||||
})
|
||||
|
||||
it('should default apply AI suggestions options on a new action', () => {
|
||||
component.object = {
|
||||
name: 'Workflow 1',
|
||||
order: 0,
|
||||
enabled: true,
|
||||
triggers: [{ type: WorkflowTriggerType.DocumentAdded }],
|
||||
actions: [],
|
||||
} as Workflow
|
||||
component.addAction()
|
||||
|
||||
const action = component.actionFields.at(component.actionFields.length - 1)
|
||||
expect(action.get('ai_suggestion_fields').value).toEqual([])
|
||||
expect(action.get('ai_create_missing').value).toBeFalsy()
|
||||
expect(action.get('ai_overwrite_existing').value).toBeFalsy()
|
||||
})
|
||||
|
||||
it('should support add and remove triggers and actions', () => {
|
||||
component.object = workflow
|
||||
component.addTrigger()
|
||||
|
||||
+10
-102
@@ -30,7 +30,6 @@ import { StoragePath } from 'src/app/data/storage-path'
|
||||
import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
|
||||
import { Workflow } from 'src/app/data/workflow'
|
||||
import {
|
||||
AISuggestionField,
|
||||
WorkflowAction,
|
||||
WorkflowActionType,
|
||||
} from 'src/app/data/workflow-action'
|
||||
@@ -149,41 +148,6 @@ export const WORKFLOW_ACTION_OPTIONS = [
|
||||
id: WorkflowActionType.MoveToTrash,
|
||||
name: $localize`Move to trash`,
|
||||
},
|
||||
{
|
||||
id: WorkflowActionType.RemoteOcr,
|
||||
name: $localize`Remote OCR`,
|
||||
},
|
||||
{
|
||||
id: WorkflowActionType.ApplyAiSuggestions,
|
||||
name: $localize`Apply AI suggestions`,
|
||||
},
|
||||
]
|
||||
|
||||
export const AI_SUGGESTION_FIELD_OPTIONS = [
|
||||
{
|
||||
id: AISuggestionField.Title,
|
||||
name: $localize`Title`,
|
||||
},
|
||||
{
|
||||
id: AISuggestionField.Tags,
|
||||
name: $localize`Tags`,
|
||||
},
|
||||
{
|
||||
id: AISuggestionField.Correspondent,
|
||||
name: $localize`Correspondent`,
|
||||
},
|
||||
{
|
||||
id: AISuggestionField.DocumentType,
|
||||
name: $localize`Document type`,
|
||||
},
|
||||
{
|
||||
id: AISuggestionField.StoragePath,
|
||||
name: $localize`Storage path`,
|
||||
},
|
||||
{
|
||||
id: AISuggestionField.Created,
|
||||
name: $localize`Created date`,
|
||||
},
|
||||
]
|
||||
|
||||
export enum TriggerFilterType {
|
||||
@@ -540,6 +504,8 @@ export class WorkflowEditDialogComponent
|
||||
|
||||
expandedItem: number = null
|
||||
|
||||
readonly allowedActionTypes = signal([])
|
||||
|
||||
private readonly triggerFilterOptionsMap = new WeakMap<
|
||||
FormArray,
|
||||
TriggerFilterOption[]
|
||||
@@ -582,58 +548,13 @@ export class WorkflowEditDialogComponent
|
||||
this.checkRemovalActionFields.bind(this)
|
||||
)
|
||||
this.checkRemovalActionFields(this.objectForm.value)
|
||||
}
|
||||
|
||||
private allowedActionTypes: typeof WORKFLOW_ACTION_OPTIONS = null
|
||||
|
||||
private getAllowedActionTypes() {
|
||||
let allowed = WORKFLOW_ACTION_OPTIONS
|
||||
|
||||
if (!this.settingsService.get(SETTINGS_KEYS.EMAIL_ENABLED)) {
|
||||
allowed = allowed.filter((a) => a.id !== WorkflowActionType.Email)
|
||||
}
|
||||
|
||||
// Remote OCR is decided before the document is parsed, so it is only
|
||||
// offered for workflows that run at consumption.
|
||||
const formWorkflow: Workflow = this.objectForm?.value
|
||||
const remoteOcrUsable =
|
||||
this.settingsService.get(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED) &&
|
||||
(formWorkflow?.triggers?.some(
|
||||
(trigger) => trigger.type === WorkflowTriggerType.Consumption
|
||||
) ||
|
||||
formWorkflow?.actions?.some(
|
||||
(action) => action.type === WorkflowActionType.RemoteOcr
|
||||
))
|
||||
if (!remoteOcrUsable) {
|
||||
allowed = allowed.filter((a) => a.id !== WorkflowActionType.RemoteOcr)
|
||||
}
|
||||
|
||||
// Only available after consumption. Unlike remote OCR this is hidden only
|
||||
// once every trigger is consumption, so it stays offered on a workflow
|
||||
// that has no triggers yet.
|
||||
const aiSuggestionsUsable =
|
||||
this.settingsService.get(SETTINGS_KEYS.AI_ENABLED) &&
|
||||
(!formWorkflow?.triggers?.length ||
|
||||
formWorkflow.triggers.some(
|
||||
(trigger) => trigger.type !== WorkflowTriggerType.Consumption
|
||||
) ||
|
||||
formWorkflow.actions?.some(
|
||||
(action) => action.type === WorkflowActionType.ApplyAiSuggestions
|
||||
))
|
||||
if (!aiSuggestionsUsable) {
|
||||
allowed = allowed.filter(
|
||||
(a) => a.id !== WorkflowActionType.ApplyAiSuggestions
|
||||
)
|
||||
}
|
||||
|
||||
if (
|
||||
this.allowedActionTypes?.length === allowed.length &&
|
||||
this.allowedActionTypes.every((a, i) => a.id === allowed[i].id)
|
||||
) {
|
||||
return this.allowedActionTypes
|
||||
}
|
||||
this.allowedActionTypes = allowed
|
||||
return allowed
|
||||
this.allowedActionTypes.set(
|
||||
this.settingsService.get(SETTINGS_KEYS.EMAIL_ENABLED)
|
||||
? WORKFLOW_ACTION_OPTIONS
|
||||
: WORKFLOW_ACTION_OPTIONS.filter(
|
||||
(a) => a.id !== WorkflowActionType.Email
|
||||
)
|
||||
)
|
||||
}
|
||||
|
||||
private checkRemovalActionFields(formWorkflow: Workflow) {
|
||||
@@ -1277,11 +1198,6 @@ export class WorkflowEditDialogComponent
|
||||
passwords: new FormControl(
|
||||
this.formatPasswords(action.passwords ?? [])
|
||||
),
|
||||
ai_suggestion_fields: new FormControl(
|
||||
action.ai_suggestion_fields ?? []
|
||||
),
|
||||
ai_create_missing: new FormControl(!!action.ai_create_missing),
|
||||
ai_overwrite_existing: new FormControl(!!action.ai_overwrite_existing),
|
||||
}),
|
||||
{ emitEvent }
|
||||
)
|
||||
@@ -1363,18 +1279,13 @@ export class WorkflowEditDialogComponent
|
||||
|
||||
get actionTypeOptions() {
|
||||
this.settingsService.trackChanges()
|
||||
// Computed on read rather than cached
|
||||
return this.getAllowedActionTypes()
|
||||
return this.allowedActionTypes()
|
||||
}
|
||||
|
||||
getActionTypeOptionName(type: WorkflowActionType): string {
|
||||
return this.actionTypeOptions.find((t) => t.id === type)?.name ?? ''
|
||||
}
|
||||
|
||||
get aiSuggestionFieldOptions() {
|
||||
return AI_SUGGESTION_FIELD_OPTIONS
|
||||
}
|
||||
|
||||
addAction() {
|
||||
if (!this.object) {
|
||||
this.object = Object.assign({}, this.objectForm.value)
|
||||
@@ -1428,9 +1339,6 @@ export class WorkflowEditDialogComponent
|
||||
include_document: false,
|
||||
},
|
||||
passwords: [],
|
||||
ai_suggestion_fields: [],
|
||||
ai_create_missing: false,
|
||||
ai_overwrite_existing: false,
|
||||
}
|
||||
this.object.actions.push(action)
|
||||
this.createActionField(action)
|
||||
|
||||
@@ -151,13 +151,6 @@
|
||||
inset: 0;
|
||||
pointer-events: none;
|
||||
|
||||
& section {
|
||||
position: absolute;
|
||||
text-align: initial;
|
||||
box-sizing: border-box;
|
||||
transform-origin: 0 0;
|
||||
}
|
||||
|
||||
& .annotationTextContent {
|
||||
opacity: 0;
|
||||
}
|
||||
|
||||
@@ -13,7 +13,6 @@ import {
|
||||
ViewChild,
|
||||
} from '@angular/core'
|
||||
import {
|
||||
AnnotationMode,
|
||||
getDocument,
|
||||
GlobalWorkerOptions,
|
||||
PDFDocumentLoadingTask,
|
||||
@@ -222,7 +221,6 @@ export class PngxPdfViewerComponent
|
||||
linkService: this.linkService,
|
||||
findController: this.findController,
|
||||
textLayerMode,
|
||||
annotationMode: AnnotationMode.ENABLE,
|
||||
enableSelectionRendering: false,
|
||||
removePageBorders: true,
|
||||
}
|
||||
|
||||
+2
-8
@@ -2,16 +2,10 @@
|
||||
<button type="button" class="btn btn-sm btn-outline-primary" (click)="clickSuggest()" [disabled]="disabled() || loading() || (suggestions() && !aiEnabled())">
|
||||
@if (loading()) {
|
||||
<div class="spinner-border spinner-border-sm" role="status"></div>
|
||||
} @else if (noSuggestions) {
|
||||
<i-bs width="1.2em" height="1.2em" name="check-circle"></i-bs>
|
||||
} @else {
|
||||
<i-bs width="1.2em" height="1.2em" name="stars"></i-bs>
|
||||
}
|
||||
@if (noSuggestions) {
|
||||
<span class="d-none d-lg-inline ps-1" i18n>No suggestions</span>
|
||||
} @else {
|
||||
<span class="d-none d-lg-inline ps-1" i18n>Suggest</span>
|
||||
}
|
||||
<span class="d-none d-lg-inline ps-1" i18n>Suggest</span>
|
||||
@if (totalSuggestions > 0) {
|
||||
<span class="badge bg-primary ms-2">{{ totalSuggestions }}</span>
|
||||
}
|
||||
@@ -25,7 +19,7 @@
|
||||
|
||||
<div ngbDropdownMenu aria-labelledby="suggestionsDropdown" class="shadow suggestions-dropdown">
|
||||
<div class="list-group list-group-flush small pb-0">
|
||||
@if (totalSuggestions === 0) {
|
||||
@if (!suggestions()?.suggested_tags && !suggestions()?.suggested_document_types && !suggestions()?.suggested_correspondents) {
|
||||
<div class="list-group-item text-muted fst-italic">
|
||||
<small class="text-muted small fst-italic" i18n>No novel suggestions</small>
|
||||
</div>
|
||||
|
||||
-29
@@ -30,34 +30,6 @@ describe('SuggestionsDropdownComponent', () => {
|
||||
expect(component.totalSuggestions).toBe(4)
|
||||
})
|
||||
|
||||
it('should show when a completed request returned no suggestions', () => {
|
||||
fixture.componentRef.setInput('suggestions', {
|
||||
correspondents: [],
|
||||
tags: [],
|
||||
document_types: [],
|
||||
storage_paths: [],
|
||||
dates: [],
|
||||
})
|
||||
fixture.detectChanges()
|
||||
|
||||
expect(component.noSuggestions).toBeTruthy()
|
||||
expect(fixture.nativeElement.textContent).toContain('No suggestions')
|
||||
})
|
||||
|
||||
it('should not show the empty state before a request or with suggestions', () => {
|
||||
expect(component.noSuggestions).toBeFalsy()
|
||||
|
||||
fixture.componentRef.setInput('suggestions', {
|
||||
correspondents: [],
|
||||
tags: [42],
|
||||
document_types: [],
|
||||
storage_paths: [],
|
||||
dates: [],
|
||||
})
|
||||
|
||||
expect(component.noSuggestions).toBeFalsy()
|
||||
})
|
||||
|
||||
it('should emit getSuggestions when clickSuggest is called and suggestions are null', () => {
|
||||
jest.spyOn(component.getSuggestions, 'emit')
|
||||
fixture.componentRef.setInput('suggestions', null)
|
||||
@@ -87,6 +59,5 @@ describe('SuggestionsDropdownComponent', () => {
|
||||
})
|
||||
component.clickSuggest()
|
||||
expect(component.dropdown.open).toBeTruthy()
|
||||
expect(fixture.nativeElement.textContent).toContain('No novel suggestions')
|
||||
})
|
||||
})
|
||||
|
||||
-17
@@ -61,21 +61,4 @@ export class SuggestionsDropdownComponent {
|
||||
this.suggestions()?.suggested_document_types?.length || 0
|
||||
)
|
||||
}
|
||||
|
||||
get noSuggestions(): boolean {
|
||||
const suggestions = this.suggestions()
|
||||
return (
|
||||
suggestions != null &&
|
||||
!suggestions.title &&
|
||||
!suggestions.tags?.length &&
|
||||
!suggestions.suggested_tags?.length &&
|
||||
!suggestions.correspondents?.length &&
|
||||
!suggestions.suggested_correspondents?.length &&
|
||||
!suggestions.document_types?.length &&
|
||||
!suggestions.suggested_document_types?.length &&
|
||||
!suggestions.storage_paths?.length &&
|
||||
!suggestions.suggested_storage_paths?.length &&
|
||||
!suggestions.dates?.length
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -963,24 +963,12 @@ describe('DocumentDetailComponent', () => {
|
||||
component.reprocess()
|
||||
const modalCloseSpy = jest.spyOn(openModal, 'close')
|
||||
openModal.componentInstance.confirmClicked.next()
|
||||
expect(reprocessSpy).toHaveBeenCalledWith({ documents: [doc.id] }, false)
|
||||
expect(reprocessSpy).toHaveBeenCalledWith({ documents: [doc.id] })
|
||||
expect(modalSpy).toHaveBeenCalled()
|
||||
expect(toastSpy).toHaveBeenCalled()
|
||||
expect(modalCloseSpy).toHaveBeenCalled()
|
||||
})
|
||||
|
||||
it('should pass remote OCR choice when reprocessing', () => {
|
||||
initNormally()
|
||||
const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments')
|
||||
reprocessSpy.mockReturnValue(of(true))
|
||||
let openModal: NgbModalRef
|
||||
modalService.activeInstances.subscribe((modal) => (openModal = modal[0]))
|
||||
component.reprocess()
|
||||
openModal.componentInstance.remoteOcr = true
|
||||
openModal.componentInstance.confirmClicked.next()
|
||||
expect(reprocessSpy).toHaveBeenCalledWith({ documents: [doc.id] }, true)
|
||||
})
|
||||
|
||||
it('should show error if redo ocr call fails', () => {
|
||||
initNormally()
|
||||
const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments')
|
||||
|
||||
@@ -97,7 +97,6 @@ import { ISODateAdapter } from 'src/app/utils/ngb-iso-date-adapter'
|
||||
import * as UTIF from 'utif'
|
||||
import { DocumentDetailFieldID } from '../admin/settings/settings.component'
|
||||
import { ConfirmDialogComponent } from '../common/confirm-dialog/confirm-dialog.component'
|
||||
import { ReprocessConfirmDialogComponent } from '../common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component'
|
||||
import { PasswordRemovalConfirmDialogComponent } from '../common/confirm-dialog/password-removal-confirm-dialog/password-removal-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'
|
||||
@@ -1403,7 +1402,7 @@ export class DocumentDetailComponent
|
||||
}
|
||||
|
||||
reprocess() {
|
||||
let modal = this.modalService.open(ReprocessConfirmDialogComponent, {
|
||||
let modal = this.modalService.open(ConfirmDialogComponent, {
|
||||
backdrop: 'static',
|
||||
})
|
||||
modal.componentInstance.title = $localize`Reprocess confirm`
|
||||
@@ -1414,10 +1413,7 @@ export class DocumentDetailComponent
|
||||
modal.componentInstance.confirmClicked.subscribe(() => {
|
||||
modal.componentInstance.buttonsEnabled = false
|
||||
this.documentsService
|
||||
.reprocessDocuments(
|
||||
{ documents: [this.document().id] },
|
||||
modal.componentInstance.remoteOcr
|
||||
)
|
||||
.reprocessDocuments({ documents: [this.document().id] })
|
||||
.subscribe({
|
||||
next: () => {
|
||||
this.toastService.showInfo(
|
||||
|
||||
+18
@@ -0,0 +1,18 @@
|
||||
<div class="modal-header">
|
||||
<h4 class="modal-title" i18n>Add existing document as version</h4>
|
||||
<button type="button" class="btn-close" aria-label="Close" (click)="cancel()"></button>
|
||||
</div>
|
||||
<div class="modal-body">
|
||||
<pngx-input-document-link
|
||||
[(ngModel)]="selectedDocumentIDs"
|
||||
[parentDocumentID]="rootDocumentID"
|
||||
[minimal]="true"
|
||||
placeholder="Search for a document"
|
||||
i18n-placeholder
|
||||
></pngx-input-document-link>
|
||||
<div class="form-text mt-2" i18n>Select one document to add as a version.</div>
|
||||
</div>
|
||||
<div class="modal-footer">
|
||||
<button type="button" class="btn btn-outline-secondary" (click)="cancel()" [disabled]="!buttonsEnabled" i18n>Cancel</button>
|
||||
<button type="button" class="btn btn-primary" (click)="confirm()" [disabled]="!buttonsEnabled || selectedDocumentIDs.length !== 1" i18n>Add version</button>
|
||||
</div>
|
||||
+56
@@ -0,0 +1,56 @@
|
||||
import { ComponentFixture, TestBed } from '@angular/core/testing'
|
||||
import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
|
||||
import { DocumentService } from 'src/app/services/rest/document.service'
|
||||
import { AddExistingDocumentVersionDialogComponent } from './add-existing-document-version-dialog.component'
|
||||
|
||||
describe('AddExistingDocumentVersionDialogComponent', () => {
|
||||
let component: AddExistingDocumentVersionDialogComponent
|
||||
let fixture: ComponentFixture<AddExistingDocumentVersionDialogComponent>
|
||||
let activeModal: jest.Mocked<Pick<NgbActiveModal, 'dismiss'>>
|
||||
|
||||
beforeEach(async () => {
|
||||
activeModal = { dismiss: jest.fn() }
|
||||
await TestBed.configureTestingModule({
|
||||
imports: [AddExistingDocumentVersionDialogComponent],
|
||||
providers: [
|
||||
{
|
||||
provide: NgbActiveModal,
|
||||
useValue: activeModal,
|
||||
},
|
||||
{
|
||||
provide: DocumentService,
|
||||
useValue: {},
|
||||
},
|
||||
],
|
||||
}).compileComponents()
|
||||
|
||||
fixture = TestBed.createComponent(AddExistingDocumentVersionDialogComponent)
|
||||
component = fixture.componentInstance
|
||||
component.rootDocumentID = 3
|
||||
fixture.detectChanges()
|
||||
})
|
||||
|
||||
it('should emit the single selected document', () => {
|
||||
const emitSpy = jest.spyOn(component.confirmClicked, 'emit')
|
||||
component.selectedDocumentIDs = [20]
|
||||
|
||||
component.confirm()
|
||||
|
||||
expect(emitSpy).toHaveBeenCalledWith(20)
|
||||
})
|
||||
|
||||
it('should require exactly one selected document', () => {
|
||||
const emitSpy = jest.spyOn(component.confirmClicked, 'emit')
|
||||
component.selectedDocumentIDs = [20, 21]
|
||||
|
||||
component.confirm()
|
||||
|
||||
expect(emitSpy).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
it('should dismiss on cancel', () => {
|
||||
component.cancel()
|
||||
|
||||
expect(activeModal.dismiss).toHaveBeenCalled()
|
||||
})
|
||||
})
|
||||
+28
@@ -0,0 +1,28 @@
|
||||
import { Component, EventEmitter, Input, Output, inject } from '@angular/core'
|
||||
import { FormsModule } from '@angular/forms'
|
||||
import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
|
||||
import { DocumentLinkComponent } from 'src/app/components/common/input/document-link/document-link.component'
|
||||
|
||||
@Component({
|
||||
selector: 'pngx-add-existing-document-version-dialog',
|
||||
templateUrl: './add-existing-document-version-dialog.component.html',
|
||||
imports: [DocumentLinkComponent, FormsModule],
|
||||
})
|
||||
export class AddExistingDocumentVersionDialogComponent {
|
||||
private readonly activeModal = inject(NgbActiveModal)
|
||||
|
||||
@Input() rootDocumentID: number
|
||||
@Output() confirmClicked = new EventEmitter<number>()
|
||||
|
||||
selectedDocumentIDs: number[] = []
|
||||
buttonsEnabled = true
|
||||
|
||||
confirm(): void {
|
||||
if (this.selectedDocumentIDs.length !== 1) return
|
||||
this.confirmClicked.emit(this.selectedDocumentIDs[0])
|
||||
}
|
||||
|
||||
cancel(): void {
|
||||
this.activeModal.dismiss()
|
||||
}
|
||||
}
|
||||
+20
-7
@@ -24,13 +24,26 @@
|
||||
class="visually-hidden"
|
||||
(change)="onVersionFileSelected($event)"
|
||||
/>
|
||||
<button
|
||||
class="btn btn-sm btn-outline-secondary w-100"
|
||||
(click)="versionFileInput.click()"
|
||||
[disabled]="!userIsOwner || !userCanEdit"
|
||||
>
|
||||
<i-bs name="file-earmark-plus"></i-bs><span class="ps-1" i18n>Add new version</span>
|
||||
</button>
|
||||
<div class="btn-group btn-group-sm w-100">
|
||||
<button
|
||||
class="btn btn-sm btn-outline-secondary w-100"
|
||||
(click)="versionFileInput.click()"
|
||||
[disabled]="!userIsOwner || !userCanEdit"
|
||||
title="Upload a new version"
|
||||
i18n-title
|
||||
>
|
||||
<i-bs name="file-earmark-plus"></i-bs><span class="ps-1" i18n>Upload</span>
|
||||
</button>
|
||||
<button
|
||||
class="btn btn-sm btn-outline-secondary w-100"
|
||||
(click)="addExistingDocumentAsVersion()"
|
||||
[disabled]="!userIsOwner || !userCanEdit"
|
||||
title="Use an existing document"
|
||||
i18n-title
|
||||
>
|
||||
<i-bs name="file-earmark"></i-bs><span class="ps-1" i18n>Existing</span>
|
||||
</button>
|
||||
</div>
|
||||
} @else {
|
||||
@switch (versionUploadState()) {
|
||||
@case (UploadState.Uploading) {
|
||||
|
||||
+52
-1
@@ -1,6 +1,7 @@
|
||||
import { DatePipe } from '@angular/common'
|
||||
import { SimpleChange } from '@angular/core'
|
||||
import { ComponentFixture, TestBed } from '@angular/core/testing'
|
||||
import { NgbModal } from '@ng-bootstrap/ng-bootstrap'
|
||||
import { NgxBootstrapIconsModule, allIcons } from 'ngx-bootstrap-icons'
|
||||
import { Subject, of, throwError } from 'rxjs'
|
||||
import { DocumentVersionInfo } from 'src/app/data/document'
|
||||
@@ -19,12 +20,17 @@ describe('DocumentVersionDropdownComponent', () => {
|
||||
let documentService: jest.Mocked<
|
||||
Pick<
|
||||
DocumentService,
|
||||
'deleteVersion' | 'getVersions' | 'uploadVersion' | 'updateVersionLabel'
|
||||
| 'deleteVersion'
|
||||
| 'getVersions'
|
||||
| 'mergeDocumentsAsVersions'
|
||||
| 'uploadVersion'
|
||||
| 'updateVersionLabel'
|
||||
>
|
||||
>
|
||||
let toastService: jest.Mocked<Pick<ToastService, 'showError' | 'showInfo'>>
|
||||
let finished$: Subject<{ taskId: string }>
|
||||
let failed$: Subject<{ taskId: string; message?: string }>
|
||||
let modalService: jest.Mocked<Pick<NgbModal, 'open'>>
|
||||
|
||||
beforeEach(async () => {
|
||||
finished$ = new Subject<{ taskId: string }>()
|
||||
@@ -32,9 +38,11 @@ describe('DocumentVersionDropdownComponent', () => {
|
||||
documentService = {
|
||||
deleteVersion: jest.fn(),
|
||||
getVersions: jest.fn(),
|
||||
mergeDocumentsAsVersions: jest.fn(),
|
||||
uploadVersion: jest.fn(),
|
||||
updateVersionLabel: jest.fn(),
|
||||
}
|
||||
modalService = { open: jest.fn() }
|
||||
toastService = {
|
||||
showError: jest.fn(),
|
||||
showInfo: jest.fn(),
|
||||
@@ -61,6 +69,10 @@ describe('DocumentVersionDropdownComponent', () => {
|
||||
provide: ToastService,
|
||||
useValue: toastService,
|
||||
},
|
||||
{
|
||||
provide: NgbModal,
|
||||
useValue: modalService,
|
||||
},
|
||||
{
|
||||
provide: WebsocketStatusService,
|
||||
useValue: {
|
||||
@@ -323,4 +335,43 @@ describe('DocumentVersionDropdownComponent', () => {
|
||||
expect(component.editingVersionId).toBeNull()
|
||||
expect(component.versionLabelDraft).toEqual('')
|
||||
})
|
||||
|
||||
it('addExistingDocumentAsVersion should merge with a label and refresh versions', () => {
|
||||
const confirmClicked = new Subject<number>()
|
||||
const modal = {
|
||||
componentInstance: {
|
||||
rootDocumentID: null,
|
||||
buttonsEnabled: true,
|
||||
confirmClicked,
|
||||
},
|
||||
close: jest.fn(),
|
||||
}
|
||||
modalService.open.mockReturnValue(modal as any)
|
||||
documentService.mergeDocumentsAsVersions.mockReturnValue(of({} as any))
|
||||
const versions: DocumentVersionInfo[] = [
|
||||
{ id: 3, is_root: true, checksum: 'aaaa' },
|
||||
{ id: 20, is_root: false, checksum: 'cccc' },
|
||||
]
|
||||
documentService.getVersions.mockReturnValue(of({ id: 3, versions } as any))
|
||||
component.newVersionLabel = ' Imported '
|
||||
const versionsEmitSpy = jest.spyOn(component.versionsUpdated, 'emit')
|
||||
const selectedEmitSpy = jest.spyOn(component.versionSelected, 'emit')
|
||||
|
||||
component.addExistingDocumentAsVersion()
|
||||
expect(modal.componentInstance.rootDocumentID).toEqual(3)
|
||||
confirmClicked.next(20)
|
||||
|
||||
expect(documentService.mergeDocumentsAsVersions).toHaveBeenCalledWith(
|
||||
[3, 20],
|
||||
3,
|
||||
'Imported'
|
||||
)
|
||||
expect(documentService.updateVersionLabel).not.toHaveBeenCalled()
|
||||
expect(documentService.getVersions).toHaveBeenCalledWith(3)
|
||||
expect(versionsEmitSpy).toHaveBeenCalledWith(versions)
|
||||
expect(selectedEmitSpy).toHaveBeenCalledWith(20)
|
||||
expect(component.newVersionLabel).toEqual('')
|
||||
expect(modal.close).toHaveBeenCalled()
|
||||
expect(toastService.showInfo).toHaveBeenCalled()
|
||||
})
|
||||
})
|
||||
|
||||
+53
-1
@@ -11,7 +11,7 @@ import {
|
||||
SimpleChanges,
|
||||
} from '@angular/core'
|
||||
import { FormsModule } from '@angular/forms'
|
||||
import { NgbDropdownModule } from '@ng-bootstrap/ng-bootstrap'
|
||||
import { NgbDropdownModule, NgbModal } from '@ng-bootstrap/ng-bootstrap'
|
||||
import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
|
||||
import { merge, of, Subject } from 'rxjs'
|
||||
import {
|
||||
@@ -33,6 +33,7 @@ import {
|
||||
WebsocketStatusService,
|
||||
} from 'src/app/services/websocket-status.service'
|
||||
import { ConfirmButtonComponent } from '../../common/confirm-button/confirm-button.component'
|
||||
import { AddExistingDocumentVersionDialogComponent } from './add-existing-document-version-dialog/add-existing-document-version-dialog.component'
|
||||
|
||||
@Component({
|
||||
selector: 'pngx-document-version-dropdown',
|
||||
@@ -69,6 +70,7 @@ export class DocumentVersionDropdownComponent implements OnChanges, OnDestroy {
|
||||
private readonly documentsService = inject(DocumentService)
|
||||
private readonly toastService = inject(ToastService)
|
||||
private readonly websocketStatusService = inject(WebsocketStatusService)
|
||||
private readonly modalService = inject(NgbModal)
|
||||
private readonly destroy$ = new Subject<void>()
|
||||
private readonly documentChange$ = new Subject<void>()
|
||||
|
||||
@@ -278,6 +280,56 @@ export class DocumentVersionDropdownComponent implements OnChanges, OnDestroy {
|
||||
})
|
||||
}
|
||||
|
||||
addExistingDocumentAsVersion(): void {
|
||||
const modal = this.modalService.open(
|
||||
AddExistingDocumentVersionDialogComponent,
|
||||
{ backdrop: 'static' }
|
||||
)
|
||||
const dialog =
|
||||
modal.componentInstance as AddExistingDocumentVersionDialogComponent
|
||||
dialog.rootDocumentID = this.documentId
|
||||
dialog.confirmClicked
|
||||
.pipe(takeUntil(this.destroy$), takeUntil(this.documentChange$))
|
||||
.subscribe((existingDocumentID) => {
|
||||
dialog.buttonsEnabled = false
|
||||
const versionLabel = this.newVersionLabel?.trim()
|
||||
this.documentsService
|
||||
.mergeDocumentsAsVersions(
|
||||
[this.documentId, existingDocumentID],
|
||||
this.documentId,
|
||||
versionLabel
|
||||
)
|
||||
.pipe(
|
||||
switchMap(() => this.documentsService.getVersions(this.documentId)),
|
||||
first(),
|
||||
finalize(() => (dialog.buttonsEnabled = true)),
|
||||
takeUntil(this.destroy$),
|
||||
takeUntil(this.documentChange$)
|
||||
)
|
||||
.subscribe({
|
||||
next: (document) => {
|
||||
if (document?.versions) {
|
||||
this.versionsUpdated.emit(document.versions)
|
||||
this.versionSelected.emit(
|
||||
Math.max(...document.versions.map((version) => version.id))
|
||||
)
|
||||
}
|
||||
this.newVersionLabel = ''
|
||||
modal.close()
|
||||
this.toastService.showInfo(
|
||||
$localize`Existing document added as a version.`
|
||||
)
|
||||
},
|
||||
error: (error) => {
|
||||
this.toastService.showError(
|
||||
$localize`Error adding existing document as a version`,
|
||||
error
|
||||
)
|
||||
},
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
clearVersionUploadStatus(): void {
|
||||
this.versionUploadState.set(UploadState.Idle)
|
||||
this.versionUploadError.set(null)
|
||||
|
||||
@@ -95,6 +95,9 @@
|
||||
<button ngbDropdownItem (click)="mergeSelected()" [disabled]="!userCanAdd || list.allSelected || list.selectedCount < 2">
|
||||
<i-bs name="journals" class="me-1"></i-bs><ng-container i18n>Merge</ng-container>
|
||||
</button>
|
||||
<button ngbDropdownItem (click)="mergeSelectedAsVersions()" [disabled]="!userOwnsAll || !userCanEditAll || list.allSelected || list.selectedCount < 2">
|
||||
<i-bs name="journal-bookmark-fill" class="me-1"></i-bs><ng-container i18n>Merge as versions</ng-container>
|
||||
</button>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -1122,7 +1122,6 @@ describe('BulkEditorComponent', () => {
|
||||
req.flush(true)
|
||||
expect(req.request.body).toEqual({
|
||||
documents: [3, 4],
|
||||
remote_ocr: false,
|
||||
})
|
||||
httpTestingController.match(
|
||||
`${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
|
||||
@@ -1249,6 +1248,52 @@ describe('BulkEditorComponent', () => {
|
||||
expect(documentListViewService.selected.size).toEqual(0)
|
||||
})
|
||||
|
||||
it('should support merging documents as versions', () => {
|
||||
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(documentService, 'getFew').mockReturnValue(
|
||||
of({
|
||||
all: [3, 4],
|
||||
count: 2,
|
||||
results: [
|
||||
{ id: 3, title: 'Document 3' },
|
||||
{ id: 4, title: 'Document 4' },
|
||||
],
|
||||
})
|
||||
)
|
||||
jest
|
||||
.spyOn(documentListViewService, 'selected', 'get')
|
||||
.mockReturnValue(new Set([3, 4]))
|
||||
jest
|
||||
.spyOn(permissionsService, 'currentUserHasObjectPermissions')
|
||||
.mockReturnValue(true)
|
||||
jest
|
||||
.spyOn(permissionsService, 'currentUserOwnsObject')
|
||||
.mockReturnValue(true)
|
||||
const mergeAsVersionsSpy = jest
|
||||
.spyOn(documentService, 'mergeDocumentsAsVersions')
|
||||
.mockReturnValue(of(true))
|
||||
fixture.detectChanges()
|
||||
|
||||
component.mergeSelectedAsVersions()
|
||||
expect(modal).not.toBeUndefined()
|
||||
modal.componentInstance.rootDocumentID.set(4)
|
||||
modal.componentInstance.confirm()
|
||||
|
||||
expect(mergeAsVersionsSpy).toHaveBeenCalledWith([3, 4], 4)
|
||||
httpTestingController.match(
|
||||
`${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
|
||||
)
|
||||
httpTestingController.match(
|
||||
`${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
|
||||
)
|
||||
expect(documentListViewService.selected.size).toEqual(0)
|
||||
})
|
||||
|
||||
it('should support bulk download with archive, originals or both and file formatting', () => {
|
||||
jest.spyOn(permissionsService, 'currentUserCan').mockReturnValue(true)
|
||||
jest
|
||||
|
||||
@@ -50,8 +50,8 @@ import { SettingsService } from 'src/app/services/settings.service'
|
||||
import { ToastService } from 'src/app/services/toast.service'
|
||||
import { flattenTags } from 'src/app/utils/flatten-tags'
|
||||
import { queryParamsFromFilterRules } from 'src/app/utils/query-params'
|
||||
import { MergeAsVersionsConfirmDialogComponent } from '../../common/confirm-dialog/merge-as-versions-confirm-dialog/merge-as-versions-confirm-dialog.component'
|
||||
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 { 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'
|
||||
@@ -910,7 +910,7 @@ export class BulkEditorComponent
|
||||
}
|
||||
|
||||
reprocessSelected() {
|
||||
let modal = this.modalService.open(ReprocessConfirmDialogComponent, {
|
||||
let modal = this.modalService.open(ConfirmDialogComponent, {
|
||||
backdrop: 'static',
|
||||
})
|
||||
modal.componentInstance.title = $localize`Reprocess confirm`
|
||||
@@ -924,10 +924,7 @@ export class BulkEditorComponent
|
||||
modal.componentInstance.buttonsEnabled = false
|
||||
this.executeDocumentAction(
|
||||
modal,
|
||||
this.documentService.reprocessDocuments(
|
||||
this.getSelectionQuery(),
|
||||
modal.componentInstance.remoteOcr
|
||||
)
|
||||
this.documentService.reprocessDocuments(this.getSelectionQuery())
|
||||
)
|
||||
})
|
||||
}
|
||||
@@ -1006,6 +1003,34 @@ export class BulkEditorComponent
|
||||
})
|
||||
}
|
||||
|
||||
mergeSelectedAsVersions() {
|
||||
let modal = this.modalService.open(MergeAsVersionsConfirmDialogComponent, {
|
||||
backdrop: 'static',
|
||||
})
|
||||
const mergeDialog =
|
||||
modal.componentInstance as MergeAsVersionsConfirmDialogComponent
|
||||
const documentIDs = Array.from(this.list.selected)
|
||||
mergeDialog.title = $localize`Merge as versions`
|
||||
mergeDialog.message = $localize`The selected documents will become versions of the root document.`
|
||||
mergeDialog.btnCaption = $localize`Proceed`
|
||||
mergeDialog.documentIDs.set(documentIDs)
|
||||
mergeDialog.rootDocumentID.set(documentIDs[0])
|
||||
mergeDialog.confirmClicked
|
||||
.pipe(takeUntil(this.unsubscribeNotifier))
|
||||
.subscribe(() => {
|
||||
mergeDialog.buttonsEnabled = false
|
||||
this.executeDocumentAction(
|
||||
modal,
|
||||
this.documentService.mergeDocumentsAsVersions(
|
||||
mergeDialog.documentIDs(),
|
||||
mergeDialog.rootDocumentID()
|
||||
),
|
||||
{ deleteOriginals: true }
|
||||
)
|
||||
this.toastService.showInfo($localize`Documents merged as versions.`)
|
||||
})
|
||||
}
|
||||
|
||||
public setCustomFieldValues(changedCustomFields: ChangedItems) {
|
||||
const modal = this.modalService.open(CustomFieldsBulkEditDialogComponent, {
|
||||
backdrop: 'static',
|
||||
|
||||
+1
-1
@@ -88,7 +88,7 @@
|
||||
@if (depth > 0) {
|
||||
<div class="indicator"></div>
|
||||
}
|
||||
<button class="btn btn-link ms-0 ps-0 text-start" style="user-select: text;" [disabled]="!userCanEdit(object)" (click)="userCanEdit(object) ? openEditDialog(object) : null; $event.stopPropagation()">{{ object.name }}</button>
|
||||
<button class="btn btn-link ms-0 ps-0 text-start" style="user-select: text;" (click)="userCanEdit(object) ? openEditDialog(object) : null; $event.stopPropagation()">{{ object.name }}</button>
|
||||
</td>
|
||||
<td class="d-none d-sm-table-cell">{{ getMatching(object) }}</td>
|
||||
<td>{{ getDocumentCount(object) }}</td>
|
||||
|
||||
@@ -54,10 +54,6 @@ export const ConfigCategory = {
|
||||
AI: $localize`AI Settings`,
|
||||
}
|
||||
|
||||
export const ConfigSection = {
|
||||
RemoteOCR: $localize`Remote OCR`,
|
||||
}
|
||||
|
||||
export const LLMEmbeddingBackendConfig = {
|
||||
OPENAI_LIKE: 'openai-like',
|
||||
HUGGINGFACE: 'huggingface',
|
||||
@@ -69,15 +65,6 @@ export const LLMBackendConfig = {
|
||||
OLLAMA: 'ollama',
|
||||
}
|
||||
|
||||
export const RemoteOCREngineConfig = {
|
||||
AZURE_AI: 'azureai',
|
||||
}
|
||||
|
||||
export const RemoteOCRModeConfig = {
|
||||
ALWAYS: 'always',
|
||||
WORKFLOW_ONLY: 'workflow_only',
|
||||
}
|
||||
|
||||
export interface ConfigOption {
|
||||
key: string
|
||||
title: string
|
||||
@@ -85,7 +72,6 @@ export interface ConfigOption {
|
||||
choices?: Array<{ id: string; name: string }>
|
||||
config_key?: string
|
||||
category: string
|
||||
section?: string
|
||||
note?: string
|
||||
}
|
||||
|
||||
@@ -195,43 +181,6 @@ export const PaperlessConfigOptions: ConfigOption[] = [
|
||||
config_key: 'PAPERLESS_OCR_USER_ARGS',
|
||||
category: ConfigCategory.OCR,
|
||||
},
|
||||
{
|
||||
key: 'remote_ocr_engine',
|
||||
title: $localize`Remote OCR Engine`,
|
||||
type: ConfigOptionType.Select,
|
||||
choices: mapToItems(RemoteOCREngineConfig),
|
||||
config_key: 'PAPERLESS_REMOTE_OCR_ENGINE',
|
||||
category: ConfigCategory.OCR,
|
||||
section: ConfigSection.RemoteOCR,
|
||||
note: $localize`Enabling remote OCR sends documents to a third-party service for processing. Consider the privacy implications as well as potential costs before enabling.`,
|
||||
},
|
||||
{
|
||||
key: 'remote_ocr_api_key',
|
||||
title: $localize`Remote OCR API Key`,
|
||||
type: ConfigOptionType.Password,
|
||||
config_key: 'PAPERLESS_REMOTE_OCR_API_KEY',
|
||||
category: ConfigCategory.OCR,
|
||||
section: ConfigSection.RemoteOCR,
|
||||
},
|
||||
{
|
||||
key: 'remote_ocr_endpoint',
|
||||
title: $localize`Remote OCR Endpoint`,
|
||||
type: ConfigOptionType.String,
|
||||
config_key: 'PAPERLESS_REMOTE_OCR_ENDPOINT',
|
||||
category: ConfigCategory.OCR,
|
||||
section: ConfigSection.RemoteOCR,
|
||||
note: $localize`Required when using the Azure AI engine.`,
|
||||
},
|
||||
{
|
||||
key: 'remote_ocr_mode',
|
||||
title: $localize`Remote OCR Mode`,
|
||||
type: ConfigOptionType.Select,
|
||||
choices: mapToItems(RemoteOCRModeConfig),
|
||||
config_key: 'PAPERLESS_REMOTE_OCR_MODE',
|
||||
category: ConfigCategory.OCR,
|
||||
section: ConfigSection.RemoteOCR,
|
||||
note: $localize`Which documents are sent to the remote engine. Use 'workflow_only' to keep remote OCR off unless a workflow enables it for a document.`,
|
||||
},
|
||||
{
|
||||
key: 'app_logo',
|
||||
title: $localize`Application Logo`,
|
||||
@@ -449,10 +398,6 @@ export interface PaperlessConfig extends ObjectWithId {
|
||||
barcode_enable_tag: boolean
|
||||
barcode_tag_mapping: object
|
||||
barcode_tag_split: boolean
|
||||
remote_ocr_engine: string
|
||||
remote_ocr_api_key: string
|
||||
remote_ocr_endpoint: string
|
||||
remote_ocr_mode: string
|
||||
ai_enabled: boolean
|
||||
llm_embedding_backend: string
|
||||
llm_embedding_model: string
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
import { PdfEditorEditMode } from '../components/common/pdf-editor/pdf-editor-edit-mode'
|
||||
import { PdfZoomScale } from '../components/common/pdf-viewer/pdf-viewer.types'
|
||||
import { RemoteOCRModeConfig } from './paperless-config'
|
||||
import { User } from './user'
|
||||
|
||||
export interface UiSettings {
|
||||
@@ -95,8 +94,6 @@ export const SETTINGS_KEYS = {
|
||||
OUTLOOK_OAUTH_URL: 'outlook_oauth_url',
|
||||
EMAIL_ENABLED: 'email_enabled',
|
||||
AI_ENABLED: 'ai_enabled',
|
||||
REMOTE_OCR_CONFIGURED: 'remote_ocr:configured',
|
||||
REMOTE_OCR_MODE: 'remote_ocr:mode',
|
||||
}
|
||||
|
||||
export const SETTINGS: UiSetting[] = [
|
||||
@@ -350,14 +347,4 @@ export const SETTINGS: UiSetting[] = [
|
||||
type: 'string',
|
||||
default: PdfEditorEditMode.Create,
|
||||
},
|
||||
{
|
||||
key: SETTINGS_KEYS.REMOTE_OCR_CONFIGURED,
|
||||
type: 'boolean',
|
||||
default: false,
|
||||
},
|
||||
{
|
||||
key: SETTINGS_KEYS.REMOTE_OCR_MODE,
|
||||
type: 'string',
|
||||
default: RemoteOCRModeConfig.ALWAYS,
|
||||
},
|
||||
]
|
||||
|
||||
@@ -7,18 +7,6 @@ export enum WorkflowActionType {
|
||||
Webhook = 4,
|
||||
PasswordRemoval = 5,
|
||||
MoveToTrash = 6,
|
||||
RemoteOcr = 7,
|
||||
ApplyAiSuggestions = 8,
|
||||
}
|
||||
|
||||
// see src/documents/models.py AISuggestionField
|
||||
export enum AISuggestionField {
|
||||
Title = 'title',
|
||||
Tags = 'tags',
|
||||
Correspondent = 'correspondent',
|
||||
DocumentType = 'document_type',
|
||||
StoragePath = 'storage_path',
|
||||
Created = 'created',
|
||||
}
|
||||
|
||||
export interface WorkflowActionEmail extends ObjectWithId {
|
||||
@@ -113,10 +101,4 @@ export interface WorkflowAction extends ObjectWithId {
|
||||
webhook?: WorkflowActionWebhook
|
||||
|
||||
passwords?: string[]
|
||||
|
||||
ai_suggestion_fields?: AISuggestionField[]
|
||||
|
||||
ai_create_missing?: boolean
|
||||
|
||||
ai_overwrite_existing?: boolean
|
||||
}
|
||||
|
||||
@@ -284,21 +284,6 @@ describe(`DocumentService`, () => {
|
||||
expect(req.request.method).toEqual('POST')
|
||||
expect(req.request.body).toEqual({
|
||||
documents: ids,
|
||||
remote_ocr: false,
|
||||
})
|
||||
})
|
||||
|
||||
it('should request remote OCR when reprocessing with it enabled', () => {
|
||||
const ids = [1, 2, 3]
|
||||
subscription = service
|
||||
.reprocessDocuments({ documents: ids }, true)
|
||||
.subscribe()
|
||||
const req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}${endpoint}/reprocess/`
|
||||
)
|
||||
expect(req.request.body).toEqual({
|
||||
documents: ids,
|
||||
remote_ocr: true,
|
||||
})
|
||||
})
|
||||
|
||||
@@ -331,6 +316,34 @@ describe(`DocumentService`, () => {
|
||||
})
|
||||
})
|
||||
|
||||
it('should call appropriate api endpoint for merging documents as versions', () => {
|
||||
const ids = [1, 2, 3]
|
||||
subscription = service.mergeDocumentsAsVersions(ids, 2).subscribe()
|
||||
const req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}${endpoint}/merge_as_versions/`
|
||||
)
|
||||
expect(req.request.method).toEqual('POST')
|
||||
expect(req.request.body).toEqual({
|
||||
documents: ids,
|
||||
root_document_id: 2,
|
||||
})
|
||||
})
|
||||
|
||||
it('should include an optional label when merging one document as a version', () => {
|
||||
const ids = [1, 2]
|
||||
subscription = service
|
||||
.mergeDocumentsAsVersions(ids, 2, 'Imported')
|
||||
.subscribe()
|
||||
const req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}${endpoint}/merge_as_versions/`
|
||||
)
|
||||
expect(req.request.body).toEqual({
|
||||
documents: ids,
|
||||
root_document_id: 2,
|
||||
version_label: 'Imported',
|
||||
})
|
||||
})
|
||||
|
||||
it('should call appropriate api endpoint for edit pdf', () => {
|
||||
const ids = [1]
|
||||
const args = { operations: [{ page: 1, rotate: 90, doc: 0 }] }
|
||||
|
||||
@@ -349,13 +349,9 @@ export class DocumentService extends AbstractPaperlessService<Document> {
|
||||
})
|
||||
}
|
||||
|
||||
reprocessDocuments(
|
||||
selection: DocumentSelectionQuery,
|
||||
remoteOcr: boolean = false
|
||||
) {
|
||||
reprocessDocuments(selection: DocumentSelectionQuery) {
|
||||
return this.http.post(this.getResourceUrl(null, 'reprocess'), {
|
||||
...selection,
|
||||
remote_ocr: remoteOcr,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -378,6 +374,18 @@ export class DocumentService extends AbstractPaperlessService<Document> {
|
||||
})
|
||||
}
|
||||
|
||||
mergeDocumentsAsVersions(
|
||||
ids: number[],
|
||||
rootDocumentId: number,
|
||||
versionLabel?: string
|
||||
) {
|
||||
return this.http.post(this.getResourceUrl(null, 'merge_as_versions'), {
|
||||
documents: ids,
|
||||
root_document_id: rootDocumentId,
|
||||
...(versionLabel ? { version_label: versionLabel } : {}),
|
||||
})
|
||||
}
|
||||
|
||||
editPdfDocuments(ids: number[], request: EditPdfDocumentsRequest) {
|
||||
return this.http.post(this.getResourceUrl(null, 'edit_pdf'), {
|
||||
documents: ids,
|
||||
|
||||
@@ -13,7 +13,6 @@ import { environment } from 'src/environments/environment'
|
||||
import { CustomFieldDataType } from '../data/custom-field'
|
||||
import { DEFAULT_DISPLAY_FIELDS, DisplayField } from '../data/document'
|
||||
import { SavedView } from '../data/saved-view'
|
||||
import { RemoteOCRModeConfig } from '../data/paperless-config'
|
||||
import { SETTINGS_KEYS, UiSettings } from '../data/ui-settings'
|
||||
import { PermissionsService } from './permissions.service'
|
||||
import { CustomFieldsService } from './rest/custom-fields.service'
|
||||
@@ -435,26 +434,4 @@ describe('SettingsService', () => {
|
||||
).name
|
||||
).toEqual(customFields[0].name)
|
||||
})
|
||||
it('should offer remote OCR only when configured and selective', () => {
|
||||
settingsService.set(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED, false)
|
||||
settingsService.set(
|
||||
SETTINGS_KEYS.REMOTE_OCR_MODE,
|
||||
RemoteOCRModeConfig.WORKFLOW_ONLY
|
||||
)
|
||||
expect(settingsService.remoteOCRIsSelectable).toBeFalsy()
|
||||
|
||||
// configured, but already handling every document
|
||||
settingsService.set(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED, true)
|
||||
settingsService.set(
|
||||
SETTINGS_KEYS.REMOTE_OCR_MODE,
|
||||
RemoteOCRModeConfig.ALWAYS
|
||||
)
|
||||
expect(settingsService.remoteOCRIsSelectable).toBeFalsy()
|
||||
|
||||
settingsService.set(
|
||||
SETTINGS_KEYS.REMOTE_OCR_MODE,
|
||||
RemoteOCRModeConfig.WORKFLOW_ONLY
|
||||
)
|
||||
expect(settingsService.remoteOCRIsSelectable).toBeTruthy()
|
||||
})
|
||||
})
|
||||
|
||||
@@ -19,7 +19,6 @@ import {
|
||||
} from 'src/app/utils/color'
|
||||
import { DEFAULT_APP_TITLE, environment } from 'src/environments/environment'
|
||||
import { DEFAULT_DISPLAY_FIELDS, DisplayField } from '../data/document'
|
||||
import { RemoteOCRModeConfig } from '../data/paperless-config'
|
||||
import { SavedView } from '../data/saved-view'
|
||||
import {
|
||||
PAPERLESS_GREEN_HEX,
|
||||
@@ -688,17 +687,6 @@ export class SettingsService {
|
||||
return this.settingIsSet(SETTINGS_KEYS.UPDATE_CHECKING_ENABLED)
|
||||
}
|
||||
|
||||
/**
|
||||
* Offering remote OCR as a choice only makes sense when an engine
|
||||
* is configured but is not already handling every document.
|
||||
*/
|
||||
get remoteOCRIsSelectable(): boolean {
|
||||
return (
|
||||
this.get(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED) &&
|
||||
this.get(SETTINGS_KEYS.REMOTE_OCR_MODE) !== RemoteOCRModeConfig.ALWAYS
|
||||
)
|
||||
}
|
||||
|
||||
offerTour(): boolean {
|
||||
return this.dashboardIsEmpty() && !this.get(SETTINGS_KEYS.TOUR_COMPLETE)
|
||||
}
|
||||
|
||||
@@ -101,6 +101,7 @@ import {
|
||||
house,
|
||||
infoCircle,
|
||||
journals,
|
||||
journalBookmarkFill,
|
||||
link,
|
||||
listNested,
|
||||
listTask,
|
||||
@@ -323,6 +324,7 @@ const icons = {
|
||||
hddStack,
|
||||
house,
|
||||
infoCircle,
|
||||
journalBookmarkFill,
|
||||
journals,
|
||||
link,
|
||||
listNested,
|
||||
|
||||
@@ -19,13 +19,6 @@ export const GlobalWorkerOptions = {
|
||||
workerSrc: '',
|
||||
}
|
||||
|
||||
export const AnnotationMode = {
|
||||
DISABLE: 0,
|
||||
ENABLE: 1,
|
||||
ENABLE_FORMS: 2,
|
||||
ENABLE_STORAGE: 3,
|
||||
}
|
||||
|
||||
export const getDocument = (_src: unknown): PDFDocumentLoadingTask => {
|
||||
return new PDFDocumentLoadingTask(Promise.resolve(new PDFDocumentProxy()))
|
||||
}
|
||||
|
||||
@@ -12,6 +12,7 @@ from celery import group
|
||||
from celery import shared_task
|
||||
from django.conf import settings
|
||||
from django.db import transaction
|
||||
from django.db.models import Max
|
||||
from django.db.models import Q
|
||||
from django.utils import timezone
|
||||
|
||||
@@ -30,6 +31,7 @@ from documents.permissions import set_permissions_for_object
|
||||
from documents.plugins.helpers import DocumentsStatusManager
|
||||
from documents.tasks import bulk_update_documents
|
||||
from documents.tasks import consume_file
|
||||
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
|
||||
from documents.versioning import get_root_document
|
||||
@@ -394,16 +396,10 @@ def delete(doc_ids: list[int]) -> Literal["OK"]:
|
||||
return "OK"
|
||||
|
||||
|
||||
def reprocess(doc_ids: list[int], *, remote_ocr: bool = False) -> Literal["OK"]:
|
||||
"""
|
||||
Re-run parsing for the given documents.
|
||||
|
||||
Consumption workflows do not run here, so ``remote_ocr`` is how the user
|
||||
asks for the remote engine when it is not configured to handle everything.
|
||||
"""
|
||||
def reprocess(doc_ids: list[int]) -> Literal["OK"]:
|
||||
for document_id in doc_ids:
|
||||
update_document_content_maybe_archive_file.apply_async(
|
||||
kwargs={"document_id": document_id, "remote_ocr": remote_ocr},
|
||||
kwargs={"document_id": document_id},
|
||||
headers={"trigger_source": PaperlessTask.TriggerSource.MANUAL},
|
||||
)
|
||||
|
||||
@@ -618,6 +614,77 @@ def merge(
|
||||
return "OK"
|
||||
|
||||
|
||||
def merge_as_versions(
|
||||
doc_ids: list[int],
|
||||
*,
|
||||
root_document_id: int,
|
||||
version_label: str | None = None,
|
||||
) -> Literal["OK"]:
|
||||
with transaction.atomic():
|
||||
documents = list(
|
||||
Document.objects.select_for_update().filter(id__in=doc_ids),
|
||||
)
|
||||
documents_by_id = {document.id: document for document in documents}
|
||||
|
||||
if len(documents) != len(doc_ids):
|
||||
raise ValueError("Some documents do not exist or were specified twice.")
|
||||
if root_document_id not in documents_by_id:
|
||||
raise ValueError("The root document must be selected.")
|
||||
if any(document.root_document_id is not None for document in documents):
|
||||
raise ValueError("Only top-level documents can be merged as versions.")
|
||||
|
||||
source_ids = sorted(doc_id for doc_id in doc_ids if doc_id != root_document_id)
|
||||
if version_label is not None and len(source_ids) != 1:
|
||||
raise ValueError(
|
||||
"A version label can only be set when merging one source document.",
|
||||
)
|
||||
if Document.objects.filter(root_document_id__in=source_ids).exists():
|
||||
raise ValueError(
|
||||
"Documents with existing versions cannot be merged into another document.",
|
||||
)
|
||||
|
||||
root_document = documents_by_id[root_document_id]
|
||||
next_version_index = (
|
||||
Document.global_objects.filter(
|
||||
root_document_id=root_document_id,
|
||||
).aggregate(max_index=Max("version_index"))["max_index"]
|
||||
or 0
|
||||
)
|
||||
|
||||
for source_id in source_ids:
|
||||
source_document = documents_by_id[source_id]
|
||||
next_version_index += 1
|
||||
source_document.root_document = root_document
|
||||
source_document.version_index = next_version_index
|
||||
update_fields = [
|
||||
"root_document",
|
||||
"version_index",
|
||||
"archive_serial_number",
|
||||
]
|
||||
if version_label is not None:
|
||||
source_document.version_label = version_label
|
||||
update_fields.append("version_label")
|
||||
source_document.archive_serial_number = None
|
||||
source_document.save(update_fields=update_fields)
|
||||
|
||||
root_document.modified = timezone.now()
|
||||
root_document.save(update_fields=["modified"])
|
||||
|
||||
for source_id in source_ids:
|
||||
remove_document_from_index.apply_async(args=[source_id])
|
||||
|
||||
bulk_update_documents.apply_async(
|
||||
kwargs={"document_ids": [root_document_id]},
|
||||
headers={"trigger_source": PaperlessTask.TriggerSource.SYSTEM},
|
||||
)
|
||||
|
||||
# And as far as the frontend is concerned, they're deleted
|
||||
status_mgr = DocumentsStatusManager()
|
||||
status_mgr.send_documents_deleted(source_ids)
|
||||
|
||||
return "OK"
|
||||
|
||||
|
||||
def split(
|
||||
doc_ids: list[int],
|
||||
pages: list[list[int]],
|
||||
|
||||
@@ -53,7 +53,6 @@ from documents.utils import copy_basic_file_stats
|
||||
from documents.utils import copy_file_with_basic_stats
|
||||
from documents.utils import run_subprocess
|
||||
from paperless.config import OcrConfig
|
||||
from paperless.config import RemoteOCRConfig
|
||||
from paperless.models import ArchiveFileGenerationChoices
|
||||
from paperless.parsers import ParserContext
|
||||
from paperless.parsers import ParserProtocol
|
||||
@@ -452,19 +451,12 @@ class ConsumerPlugin(
|
||||
except Exception as e:
|
||||
self.log.error(f"Error attempting to clean PDF: {e}")
|
||||
|
||||
# Workflows have already run at this point, so the metadata knows
|
||||
# whether this document was singled out for remote OCR
|
||||
allow_remote = (
|
||||
self.metadata.remote_ocr or RemoteOCRConfig().remote_ocr_by_default
|
||||
)
|
||||
|
||||
# Based on the mime type, get the parser for that type
|
||||
parser_class: type[ParserProtocol] | None = (
|
||||
get_parser_registry().get_parser_for_file(
|
||||
mime_type,
|
||||
self.filename,
|
||||
self.working_copy,
|
||||
allow_remote=allow_remote,
|
||||
)
|
||||
)
|
||||
if not parser_class:
|
||||
@@ -473,16 +465,6 @@ class ConsumerPlugin(
|
||||
f"Unsupported mime type {mime_type}",
|
||||
)
|
||||
|
||||
if self.metadata.remote_ocr and not getattr(
|
||||
parser_class,
|
||||
"uses_remote_service",
|
||||
False,
|
||||
):
|
||||
self.log.warning(
|
||||
"Remote OCR was requested for this document but no remote "
|
||||
"parser is available for it, processing locally instead.",
|
||||
)
|
||||
|
||||
# Notify all listeners that we're going to do some work.
|
||||
|
||||
document_consumption_started.send(
|
||||
|
||||
@@ -34,7 +34,6 @@ class DocumentMetadataOverrides:
|
||||
skip_asn_if_exists: bool = False
|
||||
version_label: str | None = None
|
||||
actor_id: int | None = None
|
||||
remote_ocr: bool = False
|
||||
|
||||
def update(self, other: "DocumentMetadataOverrides") -> "DocumentMetadataOverrides":
|
||||
"""
|
||||
@@ -58,8 +57,6 @@ class DocumentMetadataOverrides:
|
||||
self.actor_id = other.actor_id
|
||||
if other.skip_asn_if_exists:
|
||||
self.skip_asn_if_exists = True
|
||||
if other.remote_ocr:
|
||||
self.remote_ocr = True
|
||||
if other.version_label is not None:
|
||||
self.version_label = other.version_label
|
||||
|
||||
|
||||
+49
-30
@@ -39,6 +39,7 @@ from guardian.utils import get_user_obj_perms_model
|
||||
from rest_framework import serializers
|
||||
from rest_framework.filters import BaseFilterBackend
|
||||
from rest_framework.filters import OrderingFilter
|
||||
from rest_framework_guardian.filters import ObjectPermissionsFilter
|
||||
|
||||
from documents.models import Correspondent
|
||||
from documents.models import CustomField
|
||||
@@ -50,7 +51,7 @@ from documents.models import ShareLink
|
||||
from documents.models import ShareLinkBundle
|
||||
from documents.models import StoragePath
|
||||
from documents.models import Tag
|
||||
from documents.permissions import permitted_object_ids
|
||||
from documents.permissions import permitted_document_ids
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Callable
|
||||
@@ -1027,41 +1028,59 @@ class PaperlessTaskFilterSet(FilterSet):
|
||||
return queryset.exclude(status__in=PaperlessTask.COMPLETE_STATUSES)
|
||||
|
||||
|
||||
class PermittedObjectsFilter(BaseFilterBackend):
|
||||
class ObjectOwnedOrGrantedPermissionsFilter(ObjectPermissionsFilter):
|
||||
"""
|
||||
Filters a queryset down to objects the requesting user owns, are
|
||||
unowned, or (when ``include_granted`` is True) has an explicit
|
||||
user/group guardian permission on. Backed by ``permitted_object_ids``
|
||||
-- a single ``id__in`` subquery, not a join -- so it can't produce
|
||||
duplicate rows even when the base queryset already carries independent
|
||||
joins (e.g. multi-value ``tags__id__all`` filtering), and stays
|
||||
index-friendly at scale instead of falling back to guardian's
|
||||
varchar-cast join.
|
||||
|
||||
Set ``include_granted = False`` on a subclass for endpoints that
|
||||
intentionally only show owned/unowned objects regardless of explicit
|
||||
shares (e.g. ``TrashView``).
|
||||
A filter backend that limits results to those where the requesting user
|
||||
has read object level permissions, owns the objects, or objects without
|
||||
an owner (for backwards compat)
|
||||
"""
|
||||
|
||||
include_granted: bool = True
|
||||
perm_codename: str | None = None
|
||||
|
||||
def filter_queryset(self, request, queryset, view):
|
||||
# Before the superuser and owner-only paths, neither of which consults
|
||||
# permitted_object_ids. Scoped to authenticated users so anonymous
|
||||
# access (AnonymousUser.is_active is False) keeps its existing
|
||||
# unowned-only behaviour.
|
||||
if request.user.is_authenticated and not request.user.is_active:
|
||||
return queryset.none()
|
||||
if request.user.is_superuser:
|
||||
return queryset
|
||||
if not self.include_granted:
|
||||
return queryset.filter(Q(owner=request.user) | Q(owner__isnull=True))
|
||||
model = queryset.model
|
||||
perm = self.perm_codename or f"view_{model._meta.model_name}"
|
||||
return queryset.filter(
|
||||
id__in=permitted_object_ids(request.user, model, perm),
|
||||
)
|
||||
objects_with_perms = super().filter_queryset(request, queryset, view)
|
||||
objects_owned = queryset.filter(owner=request.user)
|
||||
objects_unowned = queryset.filter(owner__isnull=True)
|
||||
return objects_with_perms | objects_owned | objects_unowned
|
||||
|
||||
|
||||
class DocumentPermissionsFilter(BaseFilterBackend):
|
||||
"""
|
||||
A filter backend limiting Document results to those the requesting user
|
||||
owns, are unowned, or has explicit (user- or group-level) view
|
||||
permission on.
|
||||
|
||||
Unlike ``ObjectOwnedOrGrantedPermissionsFilter``, this does not build an
|
||||
``objects_with_perms | objects_owned | objects_unowned`` union of
|
||||
querysets derived from the same base queryset. When that base queryset
|
||||
already carries independent joins on a multi-valued relation (e.g. two
|
||||
separate joins from ``tags__id__all`` filtering on two tags), each
|
||||
OR-ed branch can end up pairing those joins' aliases differently,
|
||||
letting more than one row out of the join's cross product satisfy the
|
||||
combined WHERE -- returning the same document more than once. Filtering
|
||||
via a single ``id__in`` against ``permitted_document_ids`` (a plain
|
||||
subquery, not a join) sidesteps that entirely and is also cheaper than
|
||||
guardian's join-based permission check.
|
||||
"""
|
||||
|
||||
def filter_queryset(self, request, queryset, view):
|
||||
if request.user.is_superuser:
|
||||
return queryset
|
||||
return queryset.filter(id__in=permitted_document_ids(request.user))
|
||||
|
||||
|
||||
class ObjectOwnedPermissionsFilter(ObjectPermissionsFilter):
|
||||
"""
|
||||
A filter backend that limits results to those where the requesting user
|
||||
owns the objects or objects without an owner (for backwards compat)
|
||||
"""
|
||||
|
||||
def filter_queryset(self, request, queryset, view):
|
||||
if request.user.is_superuser:
|
||||
return queryset
|
||||
objects_owned = queryset.filter(owner=request.user)
|
||||
objects_unowned = queryset.filter(owner__isnull=True)
|
||||
return objects_owned | objects_unowned
|
||||
|
||||
|
||||
class DocumentsOrderingFilter(OrderingFilter):
|
||||
|
||||
+14
-10
@@ -19,7 +19,7 @@ from documents.models import StoragePath
|
||||
from documents.models import Tag
|
||||
from documents.models import Workflow
|
||||
from documents.models import WorkflowTrigger
|
||||
from documents.permissions import permitted_object_ids
|
||||
from documents.permissions import get_objects_for_user_owner_aware
|
||||
from documents.regex import safe_regex_search
|
||||
|
||||
if TYPE_CHECKING:
|
||||
@@ -55,8 +55,10 @@ def match_correspondents(document: Document, classifier: DocumentClassifier, use
|
||||
user = document.owner
|
||||
|
||||
if user is not None:
|
||||
correspondents = Correspondent.objects.filter(
|
||||
id__in=permitted_object_ids(user, Correspondent, "view_correspondent"),
|
||||
correspondents = get_objects_for_user_owner_aware(
|
||||
user,
|
||||
"documents.view_correspondent",
|
||||
Correspondent,
|
||||
)
|
||||
else:
|
||||
correspondents = Correspondent.objects.all()
|
||||
@@ -84,8 +86,10 @@ def match_document_types(document: Document, classifier: DocumentClassifier, use
|
||||
user = document.owner
|
||||
|
||||
if user is not None:
|
||||
document_types = DocumentType.objects.filter(
|
||||
id__in=permitted_object_ids(user, DocumentType, "view_documenttype"),
|
||||
document_types = get_objects_for_user_owner_aware(
|
||||
user,
|
||||
"documents.view_documenttype",
|
||||
DocumentType,
|
||||
)
|
||||
else:
|
||||
document_types = DocumentType.objects.all()
|
||||
@@ -112,9 +116,7 @@ def match_tags(document: Document, classifier: DocumentClassifier, user=None):
|
||||
user = document.owner
|
||||
|
||||
if user is not None:
|
||||
tags = Tag.objects.filter(
|
||||
id__in=permitted_object_ids(user, Tag, "view_tag"),
|
||||
)
|
||||
tags = get_objects_for_user_owner_aware(user, "documents.view_tag", Tag)
|
||||
else:
|
||||
tags = Tag.objects.all()
|
||||
|
||||
@@ -143,8 +145,10 @@ def match_storage_paths(document: Document, classifier: DocumentClassifier, user
|
||||
user = document.owner
|
||||
|
||||
if user is not None:
|
||||
storage_paths = StoragePath.objects.filter(
|
||||
id__in=permitted_object_ids(user, StoragePath, "view_storagepath"),
|
||||
storage_paths = get_objects_for_user_owner_aware(
|
||||
user,
|
||||
"documents.view_storagepath",
|
||||
StoragePath,
|
||||
)
|
||||
else:
|
||||
storage_paths = StoragePath.objects.all()
|
||||
|
||||
@@ -1,30 +0,0 @@
|
||||
# Generated by Django 5.2.16 on 2026-08-10 17:27
|
||||
|
||||
from django.db import migrations
|
||||
from django.db import models
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0022_add_perf_indexes"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.AlterField(
|
||||
model_name="workflowaction",
|
||||
name="type",
|
||||
field=models.PositiveSmallIntegerField(
|
||||
choices=[
|
||||
(1, "Assignment"),
|
||||
(2, "Removal"),
|
||||
(3, "Email"),
|
||||
(4, "Webhook"),
|
||||
(5, "Password removal"),
|
||||
(6, "Move to trash"),
|
||||
(7, "Remote OCR"),
|
||||
],
|
||||
default=1,
|
||||
verbose_name="Workflow Action Type",
|
||||
),
|
||||
),
|
||||
]
|
||||
@@ -1,84 +0,0 @@
|
||||
# Generated by Django 5.2.16 on 2026-08-10 18:26
|
||||
|
||||
from django.db import migrations
|
||||
from django.db import models
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0023_alter_workflowaction_type"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.AddField(
|
||||
model_name="workflowaction",
|
||||
name="ai_create_missing",
|
||||
field=models.BooleanField(
|
||||
default=False,
|
||||
help_text="Create suggested tags, correspondents, document types and storage paths that do not already exist instead of skipping them.",
|
||||
verbose_name="create missing objects",
|
||||
),
|
||||
),
|
||||
migrations.AddField(
|
||||
model_name="workflowaction",
|
||||
name="ai_overwrite_existing",
|
||||
field=models.BooleanField(
|
||||
default=False,
|
||||
help_text="Apply suggestions even if the document already has a value for that field. Tags are always added to, never replaced.",
|
||||
verbose_name="overwrite existing values",
|
||||
),
|
||||
),
|
||||
migrations.AddField(
|
||||
model_name="workflowaction",
|
||||
name="ai_suggestion_fields",
|
||||
field=models.JSONField(
|
||||
blank=True,
|
||||
help_text="Which of the AI-suggested fields to apply to the document.",
|
||||
null=True,
|
||||
verbose_name="AI suggestion fields",
|
||||
),
|
||||
),
|
||||
migrations.AlterField(
|
||||
model_name="workflowaction",
|
||||
name="type",
|
||||
field=models.PositiveSmallIntegerField(
|
||||
choices=[
|
||||
(1, "Assignment"),
|
||||
(2, "Removal"),
|
||||
(3, "Email"),
|
||||
(4, "Webhook"),
|
||||
(5, "Password removal"),
|
||||
(6, "Move to trash"),
|
||||
(7, "Remote OCR"),
|
||||
(8, "Apply AI suggestions"),
|
||||
],
|
||||
default=1,
|
||||
verbose_name="Workflow Action Type",
|
||||
),
|
||||
),
|
||||
migrations.AlterField(
|
||||
model_name="paperlesstask",
|
||||
name="task_type",
|
||||
field=models.CharField(
|
||||
choices=[
|
||||
("consume_file", "Consume File"),
|
||||
("train_classifier", "Train Classifier"),
|
||||
("sanity_check", "Sanity Check"),
|
||||
("index_optimize", "Index Optimize"),
|
||||
("mail_fetch", "Mail Fetch"),
|
||||
("llm_index", "LLM Index"),
|
||||
("empty_trash", "Empty Trash"),
|
||||
("check_workflows", "Check Workflows"),
|
||||
("bulk_update", "Bulk Update"),
|
||||
("reprocess_document", "Reprocess Document"),
|
||||
("build_share_link", "Build Share Link"),
|
||||
("bulk_delete", "Bulk Delete"),
|
||||
("apply_ai_suggestions", "Apply AI Suggestions"),
|
||||
],
|
||||
db_index=True,
|
||||
help_text="The kind of work being performed",
|
||||
max_length=50,
|
||||
verbose_name="Task Type",
|
||||
),
|
||||
),
|
||||
]
|
||||
@@ -695,7 +695,6 @@ class PaperlessTask(ModelWithOwner):
|
||||
REPROCESS_DOCUMENT = "reprocess_document", _("Reprocess Document")
|
||||
BUILD_SHARE_LINK = "build_share_link", _("Build Share Link")
|
||||
BULK_DELETE = "bulk_delete", _("Bulk Delete")
|
||||
APPLY_AI_SUGGESTIONS = "apply_ai_suggestions", _("Apply AI Suggestions")
|
||||
|
||||
COMPLETE_STATUSES = (
|
||||
Status.SUCCESS,
|
||||
@@ -1600,22 +1599,6 @@ class WorkflowAction(models.Model):
|
||||
6,
|
||||
_("Move to trash"),
|
||||
)
|
||||
REMOTE_OCR = (
|
||||
7,
|
||||
_("Remote OCR"),
|
||||
)
|
||||
APPLY_AI_SUGGESTIONS = (
|
||||
8,
|
||||
_("Apply AI suggestions"),
|
||||
)
|
||||
|
||||
class AISuggestionField(models.TextChoices):
|
||||
TITLE = ("title", _("Title"))
|
||||
TAGS = ("tags", _("Tags"))
|
||||
CORRESPONDENT = ("correspondent", _("Correspondent"))
|
||||
DOCUMENT_TYPE = ("document_type", _("Document type"))
|
||||
STORAGE_PATH = ("storage_path", _("Storage path"))
|
||||
CREATED = ("created", _("Created date"))
|
||||
|
||||
type = models.PositiveSmallIntegerField(
|
||||
_("Workflow Action Type"),
|
||||
@@ -1854,33 +1837,6 @@ class WorkflowAction(models.Model):
|
||||
),
|
||||
)
|
||||
|
||||
ai_suggestion_fields = models.JSONField(
|
||||
_("AI suggestion fields"),
|
||||
null=True,
|
||||
blank=True,
|
||||
help_text=_(
|
||||
"Which of the AI-suggested fields to apply to the document.",
|
||||
),
|
||||
)
|
||||
|
||||
ai_create_missing = models.BooleanField(
|
||||
_("create missing objects"),
|
||||
default=False,
|
||||
help_text=_(
|
||||
"Create suggested tags, correspondents, document types and storage "
|
||||
"paths that do not already exist instead of skipping them.",
|
||||
),
|
||||
)
|
||||
|
||||
ai_overwrite_existing = models.BooleanField(
|
||||
_("overwrite existing values"),
|
||||
default=False,
|
||||
help_text=_(
|
||||
"Apply suggestions even if the document already has a value for that "
|
||||
"field. Tags are always added to, never replaced.",
|
||||
),
|
||||
)
|
||||
|
||||
class Meta:
|
||||
verbose_name = _("workflow action")
|
||||
verbose_name_plural = _("workflow actions")
|
||||
|
||||
@@ -7,7 +7,6 @@ from django.contrib.contenttypes.models import ContentType
|
||||
from django.db.models import Case
|
||||
from django.db.models import Count
|
||||
from django.db.models import IntegerField
|
||||
from django.db.models import Model
|
||||
from django.db.models import Q
|
||||
from django.db.models import QuerySet
|
||||
from django.db.models import Value
|
||||
@@ -54,15 +53,11 @@ class PaperlessObjectPermissions(DjangoObjectPermissions):
|
||||
|
||||
class PaperlessAdminPermissions(BasePermission):
|
||||
def has_permission(self, request, view):
|
||||
return request.user.is_active and request.user.is_staff
|
||||
return request.user.is_staff
|
||||
|
||||
|
||||
def has_global_statistics_permission(user: User | None) -> bool:
|
||||
if (
|
||||
user is None
|
||||
or not getattr(user, "is_active", False)
|
||||
or not getattr(user, "is_authenticated", False)
|
||||
):
|
||||
if user is None or not getattr(user, "is_authenticated", False):
|
||||
return False
|
||||
|
||||
return getattr(user, "is_superuser", False) or user.has_perm(
|
||||
@@ -71,11 +66,7 @@ def has_global_statistics_permission(user: User | None) -> bool:
|
||||
|
||||
|
||||
def has_system_status_permission(user: User | None) -> bool:
|
||||
if (
|
||||
user is None
|
||||
or not getattr(user, "is_active", False)
|
||||
or not getattr(user, "is_authenticated", False)
|
||||
):
|
||||
if user is None or not getattr(user, "is_authenticated", False):
|
||||
return False
|
||||
|
||||
return (
|
||||
@@ -172,39 +163,30 @@ def set_permissions_for_object(
|
||||
)
|
||||
|
||||
|
||||
def permitted_object_ids(
|
||||
user: User | None,
|
||||
model: type[Model],
|
||||
perm: str,
|
||||
def permitted_document_ids(
|
||||
user,
|
||||
*,
|
||||
perm: str = "view_document",
|
||||
include_deleted: bool = False,
|
||||
) -> QuerySet[int]:
|
||||
):
|
||||
"""
|
||||
Generic version of ``permitted_document_ids`` for any model with an
|
||||
``owner`` field and guardian object-level permissions. ``include_deleted``
|
||||
only has an effect for models exposing a ``global_objects``/``deleted_at``
|
||||
soft-delete pattern (currently only ``Document``); for every other model
|
||||
it is accepted but has no effect, since those models have no soft-delete
|
||||
concept.
|
||||
Return a queryset of document IDs the user has ``perm`` on (default
|
||||
``"view_document"``). By default limited to non-deleted documents; pass
|
||||
``include_deleted=True`` for callers that need to check permission on
|
||||
soft-deleted documents (e.g. trash restore). This intentionally avoids
|
||||
``get_objects_for_user`` to keep the subquery small and index-friendly.
|
||||
"""
|
||||
has_soft_delete = hasattr(model, "global_objects")
|
||||
manager = (
|
||||
model.global_objects if include_deleted and has_soft_delete else model.objects
|
||||
)
|
||||
base_qs = manager.all().only("id", "owner")
|
||||
|
||||
manager = Document.global_objects if include_deleted else Document.objects
|
||||
base_docs = manager.all()
|
||||
base_docs = base_docs.only("id", "owner")
|
||||
|
||||
if user is None or not getattr(user, "is_authenticated", False):
|
||||
return base_qs.filter(owner__isnull=True).values_list("id", flat=True)
|
||||
|
||||
# Deactivated users get nothing, deactivated superusers included, so this
|
||||
# has to come before the superuser shortcut. guardian's
|
||||
# ObjectPermissionChecker denies inactive users, but get_objects_for_user
|
||||
# (the pattern this replaces) does not, so it would not be inherited.
|
||||
if not getattr(user, "is_active", False):
|
||||
return base_qs.none().values_list("id", flat=True)
|
||||
# Just Anonymous user e.g. for drf-spectacular
|
||||
return base_docs.filter(owner__isnull=True).values_list("id", flat=True)
|
||||
|
||||
if getattr(user, "is_superuser", False):
|
||||
return base_qs.values_list("id", flat=True)
|
||||
return base_docs.values_list("id", flat=True)
|
||||
|
||||
# Guardian's UserObjectPermission/GroupObjectPermission always store a bare
|
||||
# codename, but has_perm()-style callers commonly pass the qualified
|
||||
@@ -212,46 +194,31 @@ def permitted_object_ids(
|
||||
# codename, so just drop any prefix rather than silently under-permitting.
|
||||
perm = perm.rsplit(".", 1)[-1]
|
||||
|
||||
content_type = ContentType.objects.get_for_model(model)
|
||||
document_ct = ContentType.objects.get_for_model(Document)
|
||||
perm_filter = {
|
||||
"permission__codename": perm,
|
||||
"permission__content_type": content_type,
|
||||
"permission__content_type": document_ct,
|
||||
}
|
||||
|
||||
user_perm_ids = (
|
||||
user_perm_docs = (
|
||||
UserObjectPermission.objects.filter(user=user, **perm_filter)
|
||||
.annotate(object_pk_int=Cast("object_pk", IntegerField()))
|
||||
.values_list("object_pk_int", flat=True)
|
||||
)
|
||||
group_perm_ids = (
|
||||
|
||||
group_perm_docs = (
|
||||
GroupObjectPermission.objects.filter(group__user=user, **perm_filter)
|
||||
.annotate(object_pk_int=Cast("object_pk", IntegerField()))
|
||||
.values_list("object_pk_int", flat=True)
|
||||
)
|
||||
permitted_ids = user_perm_ids.union(group_perm_ids)
|
||||
|
||||
return base_qs.filter(
|
||||
Q(owner=user) | Q(owner__isnull=True) | Q(id__in=permitted_ids),
|
||||
permitted_documents = user_perm_docs.union(group_perm_docs)
|
||||
|
||||
return base_docs.filter(
|
||||
Q(owner=user) | Q(owner__isnull=True) | Q(id__in=permitted_documents),
|
||||
).values_list("id", flat=True)
|
||||
|
||||
|
||||
def permitted_document_ids(
|
||||
user: User | None,
|
||||
*,
|
||||
perm: str = "view_document",
|
||||
include_deleted: bool = False,
|
||||
) -> QuerySet[int]:
|
||||
"""
|
||||
Document-specific convenience wrapper around ``permitted_object_ids``.
|
||||
Return a queryset of document IDs the user has ``perm`` on (default
|
||||
``"view_document"``). By default limited to non-deleted documents; pass
|
||||
``include_deleted=True`` for callers that need to check permission on
|
||||
soft-deleted documents (e.g. trash restore). This intentionally avoids
|
||||
``get_objects_for_user`` to keep the subquery small and index-friendly.
|
||||
"""
|
||||
return permitted_object_ids(user, Document, perm, include_deleted=include_deleted)
|
||||
|
||||
|
||||
def get_document_count_filter_for_user(user, related_name: str = "documents"):
|
||||
"""
|
||||
Return the Q object used to filter document counts for the given user.
|
||||
@@ -374,13 +341,6 @@ def get_objects_for_user_owner_aware(
|
||||
"""
|
||||
Returns objects the user owns, are unowned, or has explicit perms.
|
||||
When include_deleted is True, soft-deleted items are also included.
|
||||
|
||||
Legacy slow path (guardian-backed, O(n) style permission resolution).
|
||||
Most queryset-filtering call sites have migrated onto
|
||||
``PermittedObjectsFilter``/``permitted_object_ids()``, but this function
|
||||
is kept because production callers still remain. Several callers remain
|
||||
across ``documents/``, ``paperless_mail/``, and ``paperless_ai/`` --
|
||||
grep for this function name before removing it.
|
||||
"""
|
||||
manager = (
|
||||
Model.global_objects
|
||||
@@ -400,15 +360,6 @@ def get_objects_for_user_owner_aware(
|
||||
|
||||
|
||||
def has_perms_owner_aware(user, perms, obj):
|
||||
"""
|
||||
Legacy slow path (guardian-backed) single-object permission check.
|
||||
|
||||
The queryset-filtering side of this migrated onto
|
||||
``PermittedObjectsFilter``/``permitted_object_ids()``, but this
|
||||
single-object check still has many production callers. Several callers
|
||||
remain across ``documents/``, ``paperless_mail/``, and ``paperless_ai/``
|
||||
-- grep for this function name before removing it.
|
||||
"""
|
||||
checker = ObjectPermissionChecker(user)
|
||||
return obj.owner is None or obj.owner == user or checker.has_perm(perms, obj)
|
||||
|
||||
|
||||
@@ -1675,6 +1675,52 @@ class MergeDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin
|
||||
from_webui = serializers.BooleanField(required=False, default=False)
|
||||
|
||||
|
||||
class MergeDocumentsAsVersionsSerializer(DocumentListSerializer):
|
||||
root_document_id = serializers.IntegerField(required=True)
|
||||
version_label = serializers.CharField(
|
||||
required=False,
|
||||
allow_blank=True,
|
||||
allow_null=True,
|
||||
max_length=64,
|
||||
)
|
||||
|
||||
def validate_version_label(self, value):
|
||||
if value is None:
|
||||
return None
|
||||
normalized = value.strip()
|
||||
return normalized or None
|
||||
|
||||
def validate(self, attrs):
|
||||
documents = attrs["documents"]
|
||||
if len(documents) < 2:
|
||||
raise serializers.ValidationError(
|
||||
"At least two documents are required.",
|
||||
)
|
||||
if "version_label" in attrs and len(documents) != 2:
|
||||
raise serializers.ValidationError(
|
||||
"version_label can only be used when merging one source document.",
|
||||
)
|
||||
if attrs["root_document_id"] not in documents:
|
||||
raise serializers.ValidationError(
|
||||
"root_document_id must be one of the selected documents.",
|
||||
)
|
||||
|
||||
selected_documents = Document.objects.filter(id__in=documents)
|
||||
if selected_documents.filter(root_document__isnull=False).exists():
|
||||
raise serializers.ValidationError(
|
||||
"Only top-level documents can be merged as versions.",
|
||||
)
|
||||
|
||||
source_document_ids = set(documents) - {attrs["root_document_id"]}
|
||||
if Document.objects.filter(
|
||||
root_document_id__in=source_document_ids,
|
||||
).exists():
|
||||
raise serializers.ValidationError(
|
||||
"Documents with existing versions cannot be merged into another document.",
|
||||
)
|
||||
return attrs
|
||||
|
||||
|
||||
class EditPdfDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
|
||||
operations = serializers.ListField(required=True)
|
||||
delete_original = serializers.BooleanField(required=False, default=False)
|
||||
@@ -1744,7 +1790,7 @@ class DeleteDocumentsSerializer(DocumentSelectionSerializer):
|
||||
|
||||
|
||||
class ReprocessDocumentsSerializer(DocumentSelectionSerializer):
|
||||
remote_ocr = serializers.BooleanField(required=False, default=False)
|
||||
pass
|
||||
|
||||
|
||||
class BulkEditSerializer(
|
||||
@@ -2086,13 +2132,6 @@ class BulkEditSerializer(
|
||||
f"Page {op['page']} is out of bounds for document with {doc.page_count} pages.",
|
||||
)
|
||||
|
||||
def _validate_parameters_reprocess(self, parameters) -> None:
|
||||
if "remote_ocr" in parameters:
|
||||
if not isinstance(parameters["remote_ocr"], bool):
|
||||
raise serializers.ValidationError("remote_ocr must be a boolean")
|
||||
else:
|
||||
parameters["remote_ocr"] = False
|
||||
|
||||
def validate_parameters_remove_password(self, parameters):
|
||||
if "password" not in parameters:
|
||||
raise serializers.ValidationError("password not specified")
|
||||
@@ -2157,8 +2196,6 @@ class BulkEditSerializer(
|
||||
self._validate_parameters_edit_pdf(parameters, attrs["documents"][0])
|
||||
elif method == bulk_edit.remove_password:
|
||||
self.validate_parameters_remove_password(parameters)
|
||||
elif method == bulk_edit.reprocess:
|
||||
self._validate_parameters_reprocess(parameters)
|
||||
|
||||
return attrs
|
||||
|
||||
@@ -3184,9 +3221,6 @@ class WorkflowActionSerializer(serializers.ModelSerializer[WorkflowAction]):
|
||||
"email",
|
||||
"webhook",
|
||||
"passwords",
|
||||
"ai_suggestion_fields",
|
||||
"ai_create_missing",
|
||||
"ai_overwrite_existing",
|
||||
]
|
||||
|
||||
def validate(self, attrs):
|
||||
@@ -3260,23 +3294,6 @@ class WorkflowActionSerializer(serializers.ModelSerializer[WorkflowAction]):
|
||||
"Passwords are required for password removal actions",
|
||||
)
|
||||
|
||||
if (
|
||||
"type" in attrs
|
||||
and attrs["type"] == WorkflowAction.WorkflowActionType.APPLY_AI_SUGGESTIONS
|
||||
):
|
||||
fields = attrs.get("ai_suggestion_fields")
|
||||
valid_fields = set(WorkflowAction.AISuggestionField.values)
|
||||
if (
|
||||
fields is None
|
||||
or not isinstance(fields, list)
|
||||
or len(fields) == 0
|
||||
or any(field not in valid_fields for field in fields)
|
||||
):
|
||||
raise serializers.ValidationError(
|
||||
"At least one valid field is required for apply AI "
|
||||
f"suggestions actions, options are: {sorted(valid_fields)}",
|
||||
)
|
||||
|
||||
return attrs
|
||||
|
||||
|
||||
@@ -3297,40 +3314,6 @@ class WorkflowSerializer(serializers.ModelSerializer[Workflow]):
|
||||
"actions",
|
||||
]
|
||||
|
||||
def validate(self, attrs):
|
||||
attrs = super().validate(attrs)
|
||||
|
||||
triggers = attrs.get("triggers") or []
|
||||
actions = attrs.get("actions") or []
|
||||
|
||||
# Remote OCR can only work with consumption triggers
|
||||
if any(
|
||||
action.get("type") == WorkflowAction.WorkflowActionType.REMOTE_OCR
|
||||
for action in actions
|
||||
) and not any(
|
||||
trigger.get("type") == WorkflowTrigger.WorkflowTriggerType.CONSUMPTION
|
||||
for trigger in triggers
|
||||
):
|
||||
raise serializers.ValidationError(
|
||||
"Remote OCR actions require a consumption started trigger",
|
||||
)
|
||||
|
||||
# Suggestions are made from the document content, which does not exist
|
||||
# until after consumption has finished
|
||||
if any(
|
||||
action.get("type") == WorkflowAction.WorkflowActionType.APPLY_AI_SUGGESTIONS
|
||||
for action in actions
|
||||
) and not any(
|
||||
trigger.get("type") != WorkflowTrigger.WorkflowTriggerType.CONSUMPTION
|
||||
for trigger in triggers
|
||||
):
|
||||
raise serializers.ValidationError(
|
||||
"Apply AI suggestions actions require a trigger other than "
|
||||
"consumption started",
|
||||
)
|
||||
|
||||
return attrs
|
||||
|
||||
def update_triggers_and_actions(
|
||||
self,
|
||||
instance: Workflow,
|
||||
|
||||
@@ -971,39 +971,6 @@ def run_workflows(
|
||||
)
|
||||
elif action.type == WorkflowAction.WorkflowActionType.MOVE_TO_TRASH:
|
||||
has_move_to_trash_action = True
|
||||
elif action.type == WorkflowAction.WorkflowActionType.REMOTE_OCR:
|
||||
if use_overrides and overrides:
|
||||
overrides.remote_ocr = True
|
||||
else:
|
||||
# If a workflow has a consumption trigger *and* another type,
|
||||
# the document has already been parsed by the time the other one fires
|
||||
logger.debug(
|
||||
"Remote OCR action only applies to consumption "
|
||||
"triggers, ignoring",
|
||||
extra={"group": logging_group},
|
||||
)
|
||||
elif (
|
||||
action.type
|
||||
== WorkflowAction.WorkflowActionType.APPLY_AI_SUGGESTIONS
|
||||
):
|
||||
if use_overrides:
|
||||
# The document has not been parsed yet, so there is no
|
||||
# content for the LLM to make suggestions from
|
||||
logger.debug(
|
||||
"Apply AI suggestions action does not apply to "
|
||||
"consumption triggers, ignoring",
|
||||
extra={"group": logging_group},
|
||||
)
|
||||
else:
|
||||
# Queued rather than run sync
|
||||
from documents.tasks import apply_ai_suggestions
|
||||
|
||||
# kwargs so the PaperlessTask record can note the
|
||||
# document, see _extract_input_data
|
||||
apply_ai_suggestions.delay(
|
||||
action_id=action.pk,
|
||||
document_id=document.pk,
|
||||
)
|
||||
|
||||
if not use_overrides:
|
||||
# limit title to 128 characters
|
||||
@@ -1059,7 +1026,6 @@ TRACKED_TASKS: dict[str, PaperlessTask.TaskType] = {
|
||||
"documents.tasks.update_document_content_maybe_archive_file": PaperlessTask.TaskType.REPROCESS_DOCUMENT,
|
||||
"documents.tasks.build_share_link_bundle": PaperlessTask.TaskType.BUILD_SHARE_LINK,
|
||||
"documents.bulk_edit.delete": PaperlessTask.TaskType.BULK_DELETE,
|
||||
"documents.tasks.apply_ai_suggestions": PaperlessTask.TaskType.APPLY_AI_SUGGESTIONS,
|
||||
}
|
||||
|
||||
_CELERY_STATE_TO_STATUS: dict[str, PaperlessTask.Status] = {
|
||||
@@ -1113,12 +1079,6 @@ def _extract_input_data(
|
||||
return {"account_ids": account_ids}
|
||||
return {}
|
||||
|
||||
if task_type == PaperlessTask.TaskType.APPLY_AI_SUGGESTIONS:
|
||||
document_id = task_kwargs.get("document_id")
|
||||
if document_id is not None:
|
||||
return {"document_id": document_id}
|
||||
return {}
|
||||
|
||||
return {}
|
||||
|
||||
|
||||
|
||||
+1
-49
@@ -66,7 +66,6 @@ from documents.utils import compute_checksum
|
||||
from documents.utils import identity
|
||||
from documents.workflows.utils import get_workflows_for_trigger
|
||||
from paperless.config import AIConfig
|
||||
from paperless.config import RemoteOCRConfig
|
||||
from paperless.logging import consume_task_id
|
||||
from paperless.parsers import ParserContext
|
||||
from paperless.parsers.registry import get_parser_registry
|
||||
@@ -338,17 +337,10 @@ def bulk_update_documents(document_ids) -> None:
|
||||
|
||||
|
||||
@shared_task
|
||||
def update_document_content_maybe_archive_file(
|
||||
document_id,
|
||||
*,
|
||||
remote_ocr: bool = False,
|
||||
) -> None:
|
||||
def update_document_content_maybe_archive_file(document_id) -> None:
|
||||
"""
|
||||
Re-creates OCR content and thumbnail for a document, and archive file if
|
||||
it exists.
|
||||
|
||||
Remote OCR is used only when the engine is configured to handle everything
|
||||
or if explicitly asked for via ``remote_ocr``.
|
||||
"""
|
||||
document = Document.objects.get(id=document_id)
|
||||
|
||||
@@ -358,7 +350,6 @@ def update_document_content_maybe_archive_file(
|
||||
mime_type,
|
||||
document.original_filename or "",
|
||||
document.source_path,
|
||||
allow_remote=remote_ocr or RemoteOCRConfig().remote_ocr_by_default,
|
||||
)
|
||||
|
||||
if not parser_class:
|
||||
@@ -713,45 +704,6 @@ def llmindex_index(
|
||||
)
|
||||
|
||||
|
||||
@shared_task(
|
||||
bind=True,
|
||||
autoretry_for=(Exception,),
|
||||
max_retries=3,
|
||||
retry_backoff=60,
|
||||
retry_backoff_max=600,
|
||||
retry_jitter=True,
|
||||
)
|
||||
def apply_ai_suggestions(self, action_id: int, document_id: int) -> None:
|
||||
"""
|
||||
Deferred "apply AI suggestions" workflow action.
|
||||
"""
|
||||
from documents.models import WorkflowAction
|
||||
from documents.workflows.ai import apply_ai_suggestions_to_document
|
||||
|
||||
try:
|
||||
action = WorkflowAction.objects.get(pk=action_id)
|
||||
document = Document.objects.select_related("owner").get(pk=document_id)
|
||||
except (WorkflowAction.DoesNotExist, Document.DoesNotExist):
|
||||
logger.warning(
|
||||
"Workflow action %s or document %s no longer exists, "
|
||||
"not applying AI suggestions",
|
||||
action_id,
|
||||
document_id,
|
||||
)
|
||||
return
|
||||
|
||||
if not apply_ai_suggestions_to_document(action, document):
|
||||
return
|
||||
|
||||
# No document_updated signal to avoid loop
|
||||
clear_document_caches(document.pk)
|
||||
index_document.delay(document.pk)
|
||||
|
||||
ai_config = AIConfig()
|
||||
if ai_config.llm_index_enabled:
|
||||
update_document_in_llm_index.apply_async(kwargs={"document": document})
|
||||
|
||||
|
||||
@shared_task
|
||||
def update_document_in_llm_index(document) -> None:
|
||||
llm_index_add_or_update_document(document)
|
||||
|
||||
@@ -72,10 +72,6 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
|
||||
"barcode_enable_tag": None,
|
||||
"barcode_tag_mapping": None,
|
||||
"barcode_tag_split": None,
|
||||
"remote_ocr_engine": None,
|
||||
"remote_ocr_api_key": None,
|
||||
"remote_ocr_endpoint": None,
|
||||
"remote_ocr_mode": None,
|
||||
"ai_enabled": False,
|
||||
"llm_embedding_backend": None,
|
||||
"llm_embedding_model": None,
|
||||
@@ -874,49 +870,6 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
|
||||
config.refresh_from_db()
|
||||
self.assertEqual(config.llm_api_key, None)
|
||||
|
||||
def test_update_remote_ocr_api_key(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- Existing config with remote_ocr_api_key specified
|
||||
WHEN:
|
||||
- API to update remote_ocr_api_key is called with all *s
|
||||
- API to update remote_ocr_api_key is called with empty string
|
||||
THEN:
|
||||
- remote_ocr_api_key is unchanged
|
||||
- remote_ocr_api_key is set to None
|
||||
"""
|
||||
config = ApplicationConfiguration.objects.first()
|
||||
assert config is not None
|
||||
config.remote_ocr_api_key = "1234567890"
|
||||
config.save()
|
||||
|
||||
# Test with all *
|
||||
response = self.client.patch(
|
||||
f"{self.ENDPOINT}1/",
|
||||
json.dumps(
|
||||
{
|
||||
"remote_ocr_api_key": "*" * 32,
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
config.refresh_from_db()
|
||||
self.assertEqual(config.remote_ocr_api_key, "1234567890")
|
||||
# Test with empty string
|
||||
response = self.client.patch(
|
||||
f"{self.ENDPOINT}1/",
|
||||
json.dumps(
|
||||
{
|
||||
"remote_ocr_api_key": "",
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
config.refresh_from_db()
|
||||
self.assertEqual(config.remote_ocr_api_key, None)
|
||||
|
||||
def test_enable_ai_index_triggers_update(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
|
||||
@@ -532,29 +532,7 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
m.assert_called_once()
|
||||
args, kwargs = m.call_args
|
||||
self.assertEqual(args[0], [self.doc1.id])
|
||||
self.assertEqual(kwargs, {"remote_ocr": False})
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.reprocess")
|
||||
def test_reprocess_documents_endpoint_remote_ocr(self, m) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- API data to reprocess a document with remote OCR requested
|
||||
WHEN:
|
||||
- API is called
|
||||
THEN:
|
||||
- reprocess is called with remote_ocr=True
|
||||
"""
|
||||
self.setup_mock(m, "reprocess")
|
||||
response = self.client.post(
|
||||
"/api/documents/reprocess/",
|
||||
json.dumps({"documents": [self.doc1.id], "remote_ocr": True}),
|
||||
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, {"remote_ocr": True})
|
||||
self.assertEqual(len(kwargs), 0)
|
||||
|
||||
@mock.patch("documents.serialisers.bulk_edit.set_storage_path")
|
||||
def test_api_set_storage_path(self, m) -> None:
|
||||
@@ -1575,29 +1553,6 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
|
||||
),
|
||||
)
|
||||
|
||||
def test_legacy_bulk_edit_reprocess_invalid_remote_ocr(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- The deprecated bulk_edit endpoint with a non-boolean remote_ocr
|
||||
WHEN:
|
||||
- API is called
|
||||
THEN:
|
||||
- The request is rejected rather than passed through to the task
|
||||
"""
|
||||
response = self.client.post(
|
||||
"/api/documents/bulk_edit/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc1.id],
|
||||
"method": "reprocess",
|
||||
"parameters": {"remote_ocr": "yes please"},
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.edit_pdf")
|
||||
def test_edit_pdf(self, m) -> None:
|
||||
self.setup_mock(m, "edit_pdf")
|
||||
|
||||
@@ -48,6 +48,7 @@ class TestApiSchema(APITestCase):
|
||||
self.assertIn("/api/documents/reprocess/", paths)
|
||||
self.assertIn("/api/documents/rotate/", paths)
|
||||
self.assertIn("/api/documents/merge/", paths)
|
||||
self.assertIn("/api/documents/merge_as_versions/", paths)
|
||||
self.assertIn("/api/documents/edit_pdf/", paths)
|
||||
self.assertIn("/api/documents/remove_password/", paths)
|
||||
|
||||
|
||||
@@ -60,10 +60,6 @@ class TestApiUiSettings(DirectoriesMixin, APITestCase):
|
||||
},
|
||||
"email_enabled": False,
|
||||
"ai_enabled": False,
|
||||
"remote_ocr": {
|
||||
"configured": False,
|
||||
"mode": "always",
|
||||
},
|
||||
},
|
||||
)
|
||||
|
||||
@@ -158,50 +154,6 @@ class TestApiUiSettings(DirectoriesMixin, APITestCase):
|
||||
str(response.data["settings"]),
|
||||
)
|
||||
|
||||
@override_settings(
|
||||
REMOTE_OCR_ENGINE="azureai",
|
||||
REMOTE_OCR_API_KEY="somekey",
|
||||
REMOTE_OCR_ENDPOINT="https://example.cognitiveservices.azure.com",
|
||||
REMOTE_OCR_MODE="workflow_only",
|
||||
)
|
||||
def test_settings_reports_remote_ocr_when_configured(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A fully configured remote OCR engine in workflow_only mode
|
||||
WHEN:
|
||||
- The ui_settings endpoint is called
|
||||
THEN:
|
||||
- The UI is told remote OCR is available and selective, so it can
|
||||
offer it where it would actually change something
|
||||
"""
|
||||
response = self.client.get(self.ENDPOINT, format="json")
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
self.assertEqual(
|
||||
response.data["settings"]["remote_ocr"],
|
||||
{"configured": True, "mode": "workflow_only"},
|
||||
)
|
||||
|
||||
@override_settings(
|
||||
REMOTE_OCR_ENGINE="azureai",
|
||||
REMOTE_OCR_API_KEY=None,
|
||||
REMOTE_OCR_ENDPOINT=None,
|
||||
)
|
||||
def test_settings_reports_remote_ocr_incompletely_configured(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An engine named but missing its endpoint and API key
|
||||
WHEN:
|
||||
- The ui_settings endpoint is called
|
||||
THEN:
|
||||
- It is reported as not configured, matching what the parser
|
||||
registry will actually do
|
||||
"""
|
||||
response = self.client.get(self.ENDPOINT, format="json")
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
self.assertFalse(response.data["settings"]["remote_ocr"]["configured"])
|
||||
|
||||
@override_settings(
|
||||
OAUTH_CALLBACK_BASE_URL="http://localhost:8000",
|
||||
GMAIL_OAUTH_CLIENT_ID="abc123",
|
||||
|
||||
@@ -390,221 +390,6 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
|
||||
|
||||
self.assertEqual(Workflow.objects.count(), 1)
|
||||
|
||||
def test_api_create_remote_ocr_action_requires_consumption_trigger(
|
||||
self,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- API request to create a workflow with a remote OCR action
|
||||
- No consumption started trigger, so the action could never run
|
||||
WHEN:
|
||||
- API is called
|
||||
THEN:
|
||||
- Correct HTTP 400 response
|
||||
- No objects are created
|
||||
"""
|
||||
existing_count = Workflow.objects.count()
|
||||
|
||||
response = self.client.post(
|
||||
self.ENDPOINT,
|
||||
json.dumps(
|
||||
{
|
||||
"name": "Remote OCR too late",
|
||||
"order": 1,
|
||||
"triggers": [
|
||||
{
|
||||
"type": WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
|
||||
},
|
||||
],
|
||||
"actions": [
|
||||
{
|
||||
"type": WorkflowAction.WorkflowActionType.REMOTE_OCR,
|
||||
},
|
||||
],
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertEqual(Workflow.objects.count(), existing_count)
|
||||
|
||||
def test_api_create_remote_ocr_action_with_consumption_trigger(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- API request to create a workflow with a remote OCR action
|
||||
- A consumption started trigger alongside another trigger type
|
||||
WHEN:
|
||||
- API is called
|
||||
THEN:
|
||||
- The workflow is created, the action applies to consumption only
|
||||
"""
|
||||
response = self.client.post(
|
||||
self.ENDPOINT,
|
||||
json.dumps(
|
||||
{
|
||||
"name": "Remote OCR on consume",
|
||||
"order": 1,
|
||||
"triggers": [
|
||||
{
|
||||
"type": WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
|
||||
"filter_filename": "*.pdf",
|
||||
},
|
||||
{
|
||||
"type": WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
|
||||
},
|
||||
],
|
||||
"actions": [
|
||||
{
|
||||
"type": WorkflowAction.WorkflowActionType.REMOTE_OCR,
|
||||
},
|
||||
],
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_201_CREATED)
|
||||
|
||||
def _post_ai_suggestions_workflow(self, *, trigger_types, action: dict):
|
||||
def trigger(trigger_type):
|
||||
# consumption triggers require a filter of their own
|
||||
if trigger_type == WorkflowTrigger.WorkflowTriggerType.CONSUMPTION:
|
||||
return {"type": trigger_type, "filter_filename": "*.pdf"}
|
||||
return {"type": trigger_type}
|
||||
|
||||
return self.client.post(
|
||||
self.ENDPOINT,
|
||||
json.dumps(
|
||||
{
|
||||
"name": "Apply AI suggestions",
|
||||
"order": 1,
|
||||
"triggers": [trigger(t) for t in trigger_types],
|
||||
"actions": [
|
||||
{
|
||||
"type": WorkflowAction.WorkflowActionType.APPLY_AI_SUGGESTIONS,
|
||||
**action,
|
||||
},
|
||||
],
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
def test_api_create_apply_ai_suggestions_action(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- API request to create a workflow with an apply AI suggestions
|
||||
action and a valid set of fields
|
||||
WHEN:
|
||||
- API is called
|
||||
THEN:
|
||||
- The workflow is created with the chosen options
|
||||
"""
|
||||
response = self._post_ai_suggestions_workflow(
|
||||
trigger_types=[WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED],
|
||||
action={
|
||||
"ai_suggestion_fields": ["title", "tags", "correspondent"],
|
||||
"ai_create_missing": True,
|
||||
"ai_overwrite_existing": True,
|
||||
},
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_201_CREATED)
|
||||
action = Workflow.objects.get(name="Apply AI suggestions").actions.first()
|
||||
self.assertEqual(
|
||||
action.ai_suggestion_fields,
|
||||
["title", "tags", "correspondent"],
|
||||
)
|
||||
self.assertTrue(action.ai_create_missing)
|
||||
self.assertTrue(action.ai_overwrite_existing)
|
||||
|
||||
def test_api_create_apply_ai_suggestions_action_requires_fields(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- API request to create an apply AI suggestions action with no
|
||||
fields selected, which could never do anything
|
||||
WHEN:
|
||||
- API is called
|
||||
THEN:
|
||||
- Correct HTTP 400 response
|
||||
- No objects are created
|
||||
"""
|
||||
existing_count = Workflow.objects.count()
|
||||
|
||||
response = self._post_ai_suggestions_workflow(
|
||||
trigger_types=[WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED],
|
||||
action={"ai_suggestion_fields": []},
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertEqual(Workflow.objects.count(), existing_count)
|
||||
|
||||
def test_api_create_apply_ai_suggestions_action_rejects_unknown_field(
|
||||
self,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- API request to create an apply AI suggestions action naming a
|
||||
field that does not exist
|
||||
WHEN:
|
||||
- API is called
|
||||
THEN:
|
||||
- Correct HTTP 400 response
|
||||
"""
|
||||
response = self._post_ai_suggestions_workflow(
|
||||
trigger_types=[WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED],
|
||||
action={"ai_suggestion_fields": ["title", "not_a_field"]},
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
|
||||
def test_api_create_apply_ai_suggestions_action_rejects_consumption_only(
|
||||
self,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- API request to create an apply AI suggestions action whose only
|
||||
trigger is consumption started, so there is no document content
|
||||
to make suggestions from yet
|
||||
WHEN:
|
||||
- API is called
|
||||
THEN:
|
||||
- Correct HTTP 400 response
|
||||
- No objects are created
|
||||
"""
|
||||
existing_count = Workflow.objects.count()
|
||||
|
||||
response = self._post_ai_suggestions_workflow(
|
||||
trigger_types=[WorkflowTrigger.WorkflowTriggerType.CONSUMPTION],
|
||||
action={"ai_suggestion_fields": ["title"]},
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
self.assertEqual(Workflow.objects.count(), existing_count)
|
||||
|
||||
def test_api_create_apply_ai_suggestions_action_allows_extra_consumption_trigger(
|
||||
self,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- API request to create an apply AI suggestions action with a
|
||||
consumption trigger alongside a usable one
|
||||
WHEN:
|
||||
- API is called
|
||||
THEN:
|
||||
- The workflow is created, the action applies to the other trigger
|
||||
"""
|
||||
response = self._post_ai_suggestions_workflow(
|
||||
trigger_types=[
|
||||
WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
|
||||
WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
|
||||
],
|
||||
action={"ai_suggestion_fields": ["title"]},
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_201_CREATED)
|
||||
|
||||
def test_api_create_workflow_trigger_action_empty_fields(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
|
||||
@@ -1782,56 +1782,3 @@ class TestPDFActions(DirectoriesMixin, TestCase):
|
||||
|
||||
self.assertIn("wrong password", str(exc.exception))
|
||||
self.assertIn("Error removing password from document", cm.output[0])
|
||||
|
||||
|
||||
class TestBulkEditReprocess(DirectoriesMixin, TestCase):
|
||||
def setUp(self) -> None:
|
||||
super().setUp()
|
||||
|
||||
self.doc = Document.objects.create(
|
||||
title="test",
|
||||
checksum="A",
|
||||
mime_type="application/pdf",
|
||||
)
|
||||
|
||||
@mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file")
|
||||
def test_reprocess_defaults_to_local(self, mock_task: mock.Mock) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A reprocess request that says nothing about remote OCR
|
||||
WHEN:
|
||||
- reprocess is called
|
||||
THEN:
|
||||
- The task is queued without asking for the remote engine
|
||||
"""
|
||||
result = bulk_edit.reprocess([self.doc.id])
|
||||
|
||||
self.assertEqual(result, "OK")
|
||||
mock_task.apply_async.assert_called_once()
|
||||
_, kwargs = mock_task.apply_async.call_args
|
||||
self.assertEqual(
|
||||
kwargs["kwargs"],
|
||||
{"document_id": self.doc.id, "remote_ocr": False},
|
||||
)
|
||||
|
||||
@mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file")
|
||||
def test_reprocess_passes_remote_ocr(self, mock_task: mock.Mock) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A reprocess request that explicitly asks for remote OCR
|
||||
WHEN:
|
||||
- reprocess is called
|
||||
THEN:
|
||||
- The request is forwarded to the task for every document
|
||||
"""
|
||||
other = Document.objects.create(
|
||||
title="test2",
|
||||
checksum="B",
|
||||
mime_type="application/pdf",
|
||||
)
|
||||
|
||||
bulk_edit.reprocess([self.doc.id, other.id], remote_ocr=True)
|
||||
|
||||
self.assertEqual(mock_task.apply_async.call_count, 2)
|
||||
for call in mock_task.apply_async.call_args_list:
|
||||
self.assertTrue(call.kwargs["kwargs"]["remote_ocr"])
|
||||
|
||||
@@ -1559,72 +1559,6 @@ class PostConsumeTestCase(DirectoriesMixin, GetConsumerMixin, TestCase):
|
||||
consumer.run_post_consume_script(doc)
|
||||
|
||||
|
||||
class TestConsumerRemoteOCR(
|
||||
DirectoriesMixin,
|
||||
FileSystemAssertsMixin,
|
||||
GetConsumerMixin,
|
||||
TestCase,
|
||||
):
|
||||
"""
|
||||
The consumer resolves the remote OCR mode and the per-document request from
|
||||
workflows into the allow_remote flag it hands to the parser registry.
|
||||
"""
|
||||
|
||||
def setUp(self) -> None:
|
||||
super().setUp()
|
||||
|
||||
patcher = mock.patch("documents.consumer.get_parser_registry")
|
||||
self.mock_registry = patcher.start()
|
||||
self.mock_registry.return_value.get_parser_for_file.return_value = DummyParser
|
||||
self.addCleanup(patcher.stop)
|
||||
|
||||
def _consume(self, *, overrides: DocumentMetadataOverrides | None = None) -> bool:
|
||||
src = (
|
||||
Path(__file__).parent
|
||||
/ "samples"
|
||||
/ "documents"
|
||||
/ "originals"
|
||||
/ "0000001.pdf"
|
||||
)
|
||||
dst = self.dirs.scratch_dir / "sample.pdf"
|
||||
shutil.copy(src, dst)
|
||||
|
||||
with self.get_consumer(dst, overrides=overrides) as consumer:
|
||||
consumer.run()
|
||||
|
||||
_, kwargs = self.mock_registry.return_value.get_parser_for_file.call_args
|
||||
return kwargs["allow_remote"]
|
||||
|
||||
@override_settings(REMOTE_OCR_MODE="always")
|
||||
def test_always_mode_allows_remote(self) -> None:
|
||||
"""
|
||||
GIVEN: Remote OCR mode is 'always'.
|
||||
WHEN: A document is consumed without any workflow asking for it.
|
||||
THEN: The registry is allowed to pick the remote parser.
|
||||
"""
|
||||
self.assertTrue(self._consume())
|
||||
|
||||
@override_settings(REMOTE_OCR_MODE="workflow_only")
|
||||
def test_workflow_only_mode_denies_remote_by_default(self) -> None:
|
||||
"""
|
||||
GIVEN: Remote OCR mode is 'workflow_only'.
|
||||
WHEN: A document is consumed and nothing asked for remote OCR.
|
||||
THEN: The remote parser is excluded.
|
||||
"""
|
||||
self.assertFalse(self._consume())
|
||||
|
||||
@override_settings(REMOTE_OCR_MODE="workflow_only")
|
||||
def test_workflow_only_mode_allows_remote_when_requested(self) -> None:
|
||||
"""
|
||||
GIVEN: Remote OCR mode is 'workflow_only'.
|
||||
WHEN: A workflow set remote_ocr on the metadata overrides.
|
||||
THEN: The registry is allowed to pick the remote parser.
|
||||
"""
|
||||
self.assertTrue(
|
||||
self._consume(overrides=DocumentMetadataOverrides(remote_ocr=True)),
|
||||
)
|
||||
|
||||
|
||||
class TestMetadataOverrides(TestCase):
|
||||
def test_update_skip_asn_if_exists(self) -> None:
|
||||
base = DocumentMetadataOverrides()
|
||||
@@ -1632,20 +1566,6 @@ class TestMetadataOverrides(TestCase):
|
||||
base.update(incoming)
|
||||
self.assertTrue(base.skip_asn_if_exists)
|
||||
|
||||
def test_update_remote_ocr(self) -> None:
|
||||
base = DocumentMetadataOverrides()
|
||||
base.update(DocumentMetadataOverrides(remote_ocr=True))
|
||||
self.assertTrue(base.remote_ocr)
|
||||
|
||||
def test_update_remote_ocr_is_not_unset(self) -> None:
|
||||
"""
|
||||
A later workflow that says nothing must not undo an earlier one that
|
||||
asked for remote OCR.
|
||||
"""
|
||||
base = DocumentMetadataOverrides(remote_ocr=True)
|
||||
base.update(DocumentMetadataOverrides())
|
||||
self.assertTrue(base.remote_ocr)
|
||||
|
||||
def test_update_actor_and_version_label(self) -> None:
|
||||
base = DocumentMetadataOverrides(
|
||||
actor_id=1,
|
||||
|
||||
@@ -0,0 +1,402 @@
|
||||
import json
|
||||
from unittest import mock
|
||||
|
||||
from django.contrib.auth.models import Permission
|
||||
from django.contrib.auth.models import User
|
||||
from django.test import TestCase
|
||||
from rest_framework import status
|
||||
from rest_framework.test import APITestCase
|
||||
|
||||
from documents.bulk_edit import merge_as_versions
|
||||
from documents.models import Document
|
||||
from documents.serialisers import MergeDocumentsAsVersionsSerializer
|
||||
|
||||
|
||||
class TestMergeDocumentsAsVersionsSerializer(TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.doc1 = Document.objects.create(checksum="A", title="A")
|
||||
self.doc2 = Document.objects.create(checksum="B", title="B")
|
||||
self.doc3 = Document.objects.create(checksum="C", title="C")
|
||||
|
||||
def test_accepts_selected_root_document(self) -> None:
|
||||
serializer = MergeDocumentsAsVersionsSerializer(
|
||||
data={
|
||||
"documents": [self.doc1.id, self.doc2.id, self.doc3.id],
|
||||
"root_document_id": self.doc2.id,
|
||||
},
|
||||
)
|
||||
|
||||
self.assertTrue(serializer.is_valid(), serializer.errors)
|
||||
self.assertEqual(
|
||||
serializer.validated_data,
|
||||
{
|
||||
"documents": [self.doc1.id, self.doc2.id, self.doc3.id],
|
||||
"root_document_id": self.doc2.id,
|
||||
},
|
||||
)
|
||||
|
||||
def test_requires_at_least_two_documents(self) -> None:
|
||||
serializer = MergeDocumentsAsVersionsSerializer(
|
||||
data={
|
||||
"documents": [self.doc1.id],
|
||||
"root_document_id": self.doc1.id,
|
||||
},
|
||||
)
|
||||
|
||||
self.assertFalse(serializer.is_valid())
|
||||
self.assertEqual(
|
||||
serializer.errors["non_field_errors"][0],
|
||||
"At least two documents are required.",
|
||||
)
|
||||
|
||||
def test_accepts_version_label_for_one_source_document(self) -> None:
|
||||
serializer = MergeDocumentsAsVersionsSerializer(
|
||||
data={
|
||||
"documents": [self.doc1.id, self.doc2.id],
|
||||
"root_document_id": self.doc1.id,
|
||||
"version_label": " Imported ",
|
||||
},
|
||||
)
|
||||
|
||||
self.assertTrue(serializer.is_valid(), serializer.errors)
|
||||
self.assertEqual(serializer.validated_data["version_label"], "Imported")
|
||||
|
||||
def test_rejects_version_label_for_multiple_source_documents(self) -> None:
|
||||
serializer = MergeDocumentsAsVersionsSerializer(
|
||||
data={
|
||||
"documents": [self.doc1.id, self.doc2.id, self.doc3.id],
|
||||
"root_document_id": self.doc1.id,
|
||||
"version_label": "Imported",
|
||||
},
|
||||
)
|
||||
|
||||
self.assertFalse(serializer.is_valid())
|
||||
self.assertEqual(
|
||||
serializer.errors["non_field_errors"][0],
|
||||
"version_label can only be used when merging one source document.",
|
||||
)
|
||||
|
||||
def test_requires_root_document_to_be_selected(self) -> None:
|
||||
serializer = MergeDocumentsAsVersionsSerializer(
|
||||
data={
|
||||
"documents": [self.doc1.id, self.doc2.id],
|
||||
"root_document_id": self.doc3.id,
|
||||
},
|
||||
)
|
||||
|
||||
self.assertFalse(serializer.is_valid())
|
||||
self.assertEqual(
|
||||
serializer.errors["non_field_errors"][0],
|
||||
"root_document_id must be one of the selected documents.",
|
||||
)
|
||||
|
||||
def test_rejects_duplicate_documents(self) -> None:
|
||||
serializer = MergeDocumentsAsVersionsSerializer(
|
||||
data={
|
||||
"documents": [self.doc1.id, self.doc1.id],
|
||||
"root_document_id": self.doc1.id,
|
||||
},
|
||||
)
|
||||
|
||||
self.assertFalse(serializer.is_valid())
|
||||
self.assertIn("documents", serializer.errors)
|
||||
|
||||
def test_rejects_selected_version(self) -> None:
|
||||
version = Document.objects.create(
|
||||
checksum="D",
|
||||
title="D",
|
||||
root_document=self.doc1,
|
||||
version_index=1,
|
||||
)
|
||||
serializer = MergeDocumentsAsVersionsSerializer(
|
||||
data={
|
||||
"documents": [version.id, self.doc2.id],
|
||||
"root_document_id": self.doc2.id,
|
||||
},
|
||||
)
|
||||
|
||||
self.assertFalse(serializer.is_valid())
|
||||
self.assertEqual(
|
||||
serializer.errors["non_field_errors"][0],
|
||||
"Only top-level documents can be merged as versions.",
|
||||
)
|
||||
|
||||
def test_rejects_source_document_with_versions(self) -> None:
|
||||
Document.objects.create(
|
||||
checksum="D",
|
||||
title="D",
|
||||
root_document=self.doc1,
|
||||
version_index=1,
|
||||
)
|
||||
serializer = MergeDocumentsAsVersionsSerializer(
|
||||
data={
|
||||
"documents": [self.doc1.id, self.doc2.id],
|
||||
"root_document_id": self.doc2.id,
|
||||
},
|
||||
)
|
||||
|
||||
self.assertFalse(serializer.is_valid())
|
||||
self.assertEqual(
|
||||
serializer.errors["non_field_errors"][0],
|
||||
"Documents with existing versions cannot be merged into another document.",
|
||||
)
|
||||
|
||||
def test_allows_root_document_with_versions(self) -> None:
|
||||
Document.objects.create(
|
||||
checksum="D",
|
||||
title="D",
|
||||
root_document=self.doc1,
|
||||
version_index=1,
|
||||
)
|
||||
serializer = MergeDocumentsAsVersionsSerializer(
|
||||
data={
|
||||
"documents": [self.doc1.id, self.doc2.id],
|
||||
"root_document_id": self.doc1.id,
|
||||
},
|
||||
)
|
||||
|
||||
self.assertTrue(serializer.is_valid(), serializer.errors)
|
||||
|
||||
|
||||
class TestMergeDocumentsAsVersions(TestCase):
|
||||
@mock.patch("documents.bulk_edit.DocumentsStatusManager")
|
||||
@mock.patch("documents.bulk_edit.bulk_update_documents.apply_async")
|
||||
@mock.patch("documents.bulk_edit.remove_document_from_index.apply_async")
|
||||
def test_merges_documents_in_creation_order(
|
||||
self,
|
||||
remove_from_index_mock,
|
||||
bulk_update_mock,
|
||||
status_manager_mock,
|
||||
) -> None:
|
||||
root = Document.objects.create(checksum="A", title="Root")
|
||||
existing_version = Document.objects.create(
|
||||
checksum="B",
|
||||
title="Existing version",
|
||||
root_document=root,
|
||||
version_index=3,
|
||||
)
|
||||
source1 = Document.objects.create(
|
||||
checksum="C",
|
||||
title="Source 1",
|
||||
archive_serial_number=1,
|
||||
)
|
||||
source2 = Document.objects.create(
|
||||
checksum="D",
|
||||
title="Source 2",
|
||||
archive_serial_number=2,
|
||||
)
|
||||
original_modified = root.modified
|
||||
|
||||
result = merge_as_versions(
|
||||
[source2.id, root.id, source1.id],
|
||||
root_document_id=root.id,
|
||||
)
|
||||
|
||||
self.assertEqual(result, "OK")
|
||||
source1.refresh_from_db()
|
||||
source2.refresh_from_db()
|
||||
root.refresh_from_db()
|
||||
self.assertEqual(source2.root_document_id, root.id)
|
||||
self.assertEqual(source2.version_index, 5)
|
||||
self.assertEqual(source1.root_document_id, root.id)
|
||||
self.assertEqual(source1.version_index, 4)
|
||||
self.assertIsNone(source1.archive_serial_number)
|
||||
self.assertIsNone(source2.archive_serial_number)
|
||||
self.assertGreater(root.modified, original_modified)
|
||||
self.assertEqual(existing_version.root_document_id, root.id)
|
||||
|
||||
self.assertEqual(
|
||||
[call.kwargs["args"] for call in remove_from_index_mock.call_args_list],
|
||||
[[source1.id], [source2.id]],
|
||||
)
|
||||
bulk_update_mock.assert_called_once_with(
|
||||
kwargs={"document_ids": [root.id]},
|
||||
headers={"trigger_source": "system"},
|
||||
)
|
||||
status_manager_mock.return_value.send_documents_deleted.assert_called_once_with(
|
||||
[source1.id, source2.id],
|
||||
)
|
||||
|
||||
@mock.patch("documents.bulk_edit.DocumentsStatusManager")
|
||||
@mock.patch("documents.bulk_edit.bulk_update_documents.apply_async")
|
||||
@mock.patch("documents.bulk_edit.remove_document_from_index.apply_async")
|
||||
def test_sets_version_label_for_one_source_document(
|
||||
self,
|
||||
_remove_from_index_mock,
|
||||
_bulk_update_mock,
|
||||
_status_manager_mock,
|
||||
) -> None:
|
||||
root = Document.objects.create(checksum="A", title="Root")
|
||||
source = Document.objects.create(checksum="B", title="Source")
|
||||
|
||||
merge_as_versions(
|
||||
[root.id, source.id],
|
||||
root_document_id=root.id,
|
||||
version_label="Imported",
|
||||
)
|
||||
|
||||
source.refresh_from_db()
|
||||
self.assertEqual(source.version_label, "Imported")
|
||||
|
||||
@mock.patch("documents.bulk_edit.DocumentsStatusManager")
|
||||
@mock.patch("documents.bulk_edit.bulk_update_documents.apply_async")
|
||||
@mock.patch("documents.bulk_edit.remove_document_from_index.apply_async")
|
||||
def test_rejects_source_document_with_versions(
|
||||
self,
|
||||
remove_from_index_mock,
|
||||
bulk_update_mock,
|
||||
status_manager_mock,
|
||||
) -> None:
|
||||
source = Document.objects.create(checksum="A", title="Source")
|
||||
Document.objects.create(
|
||||
checksum="B",
|
||||
title="Source version",
|
||||
root_document=source,
|
||||
version_index=1,
|
||||
)
|
||||
root = Document.objects.create(checksum="C", title="Root")
|
||||
|
||||
with self.assertRaisesRegex(ValueError, "existing versions"):
|
||||
merge_as_versions(
|
||||
[source.id, root.id],
|
||||
root_document_id=root.id,
|
||||
)
|
||||
|
||||
source.refresh_from_db()
|
||||
self.assertIsNone(source.root_document_id)
|
||||
remove_from_index_mock.assert_not_called()
|
||||
bulk_update_mock.assert_not_called()
|
||||
status_manager_mock.assert_not_called()
|
||||
|
||||
|
||||
class TestMergeDocumentsAsVersionsAPI(APITestCase):
|
||||
def setUp(self) -> None:
|
||||
self.user = User.objects.create_user(username="user")
|
||||
self.user.user_permissions.add(
|
||||
Permission.objects.get(codename="change_document"),
|
||||
Permission.objects.get(codename="view_document"),
|
||||
)
|
||||
self.doc1 = Document.objects.create(
|
||||
checksum="A",
|
||||
title="A",
|
||||
owner=self.user,
|
||||
)
|
||||
self.doc2 = Document.objects.create(
|
||||
checksum="B",
|
||||
title="B",
|
||||
owner=self.user,
|
||||
)
|
||||
self.client.force_authenticate(user=self.user)
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.merge_as_versions")
|
||||
def test_merges_documents_as_versions(self, merge_mock) -> None:
|
||||
merge_mock.return_value = "OK"
|
||||
merge_mock.__name__ = "merge_as_versions"
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/merge_as_versions/",
|
||||
json.dumps(
|
||||
{
|
||||
"documents": [self.doc1.id, self.doc2.id],
|
||||
"root_document_id": self.doc2.id,
|
||||
"version_label": "Imported",
|
||||
},
|
||||
),
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
self.assertEqual(response.data, {"result": "OK"})
|
||||
merge_mock.assert_called_once_with(
|
||||
[self.doc1.id, self.doc2.id],
|
||||
root_document_id=self.doc2.id,
|
||||
version_label="Imported",
|
||||
)
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.merge_as_versions")
|
||||
def test_requires_change_permission(self, merge_mock) -> None:
|
||||
merge_mock.__name__ = "merge_as_versions"
|
||||
user = User.objects.create_user(username="no-change")
|
||||
self.doc1.owner = user
|
||||
self.doc1.save()
|
||||
self.doc2.owner = user
|
||||
self.doc2.save()
|
||||
self.client.force_authenticate(user=user)
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/merge_as_versions/",
|
||||
{
|
||||
"documents": [self.doc1.id, self.doc2.id],
|
||||
"root_document_id": self.doc1.id,
|
||||
},
|
||||
format="json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
|
||||
merge_mock.assert_not_called()
|
||||
|
||||
@mock.patch("documents.views.bulk_edit.merge_as_versions")
|
||||
def test_rejects_unselected_root(self, merge_mock) -> None:
|
||||
doc3 = Document.objects.create(
|
||||
checksum="C",
|
||||
title="C",
|
||||
owner=self.user,
|
||||
)
|
||||
|
||||
response = self.client.post(
|
||||
"/api/documents/merge_as_versions/",
|
||||
{
|
||||
"documents": [self.doc1.id, self.doc2.id],
|
||||
"root_document_id": doc3.id,
|
||||
},
|
||||
format="json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
merge_mock.assert_not_called()
|
||||
|
||||
@mock.patch("documents.bulk_edit.DocumentsStatusManager")
|
||||
@mock.patch("documents.bulk_edit.bulk_update_documents.apply_async")
|
||||
@mock.patch("documents.bulk_edit.remove_document_from_index.apply_async")
|
||||
def test_merges_and_returns_documents_as_versions(
|
||||
self,
|
||||
remove_from_index_mock,
|
||||
bulk_update_mock,
|
||||
status_manager_mock,
|
||||
) -> None:
|
||||
response = self.client.post(
|
||||
"/api/documents/merge_as_versions/",
|
||||
{
|
||||
"documents": [self.doc1.id, self.doc2.id],
|
||||
"root_document_id": self.doc2.id,
|
||||
"version_label": "Imported",
|
||||
},
|
||||
format="json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
self.doc1.refresh_from_db()
|
||||
self.assertEqual(self.doc1.root_document_id, self.doc2.id)
|
||||
self.assertEqual(self.doc1.version_label, "Imported")
|
||||
|
||||
detail_response = self.client.get(
|
||||
f"/api/documents/{self.doc2.id}/?fields=id,versions",
|
||||
)
|
||||
self.assertEqual(detail_response.status_code, status.HTTP_200_OK)
|
||||
versions = detail_response.data["versions"]
|
||||
self.assertEqual(
|
||||
{version["id"] for version in versions},
|
||||
{self.doc1.id, self.doc2.id},
|
||||
)
|
||||
self.assertEqual(
|
||||
[version["id"] for version in versions if version["is_root"]],
|
||||
[self.doc2.id],
|
||||
)
|
||||
remove_from_index_mock.assert_called_once_with(args=[self.doc1.id])
|
||||
bulk_update_mock.assert_called_once_with(
|
||||
kwargs={"document_ids": [self.doc2.id]},
|
||||
headers={"trigger_source": "system"},
|
||||
)
|
||||
status_manager_mock.return_value.send_documents_deleted.assert_called_once_with(
|
||||
[self.doc1.id],
|
||||
)
|
||||
@@ -12,22 +12,9 @@ from django.test import override_settings
|
||||
from guardian.shortcuts import assign_perm
|
||||
from rest_framework.test import APIClient
|
||||
|
||||
from documents.matching import match_correspondents
|
||||
from documents.matching import match_document_types
|
||||
from documents.matching import match_storage_paths
|
||||
from documents.matching import match_tags
|
||||
from documents.models import Correspondent
|
||||
from documents.models import DocumentType
|
||||
from documents.models import StoragePath
|
||||
from documents.models import Tag
|
||||
from documents.permissions import permitted_document_ids
|
||||
from documents.permissions import permitted_object_ids
|
||||
from documents.serialisers import _get_viewable_duplicates
|
||||
from documents.tests.factories import CorrespondentFactory
|
||||
from documents.tests.factories import DocumentFactory
|
||||
from documents.tests.factories import DocumentTypeFactory
|
||||
from documents.tests.factories import StoragePathFactory
|
||||
from documents.tests.factories import TagFactory
|
||||
|
||||
|
||||
def assert_visible_document_ids(actual_ids, *, expected_visible, expected_hidden):
|
||||
@@ -444,342 +431,3 @@ class TestTrashRestorePermissionBoundary:
|
||||
format="json",
|
||||
)
|
||||
assert response.status_code == HTTPStatus.OK
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestTrashViewExcludesExplicitlyGrantedDocuments:
|
||||
"""
|
||||
Regression test pinning TrashView's use of
|
||||
``_TrashPermittedObjectsFilter`` (``include_granted = False``). If that
|
||||
flag were ever flipped to the default ``True``, or the subclass removed
|
||||
in favor of the base ``PermittedObjectsFilter``, a trashed document
|
||||
would leak into ``/api/trash/`` results for any user holding an
|
||||
explicit guardian grant on it, even though they are neither the owner
|
||||
nor a superuser.
|
||||
"""
|
||||
|
||||
def test_explicit_grant_does_not_leak_trashed_document(self, rest_api_client):
|
||||
owner = User.objects.create_user(username="trash_owner")
|
||||
grantee = User.objects.create_user(username="trash_grantee")
|
||||
doc = DocumentFactory(owner=owner)
|
||||
doc.delete() # soft delete
|
||||
assign_perm("view_document", grantee, doc)
|
||||
|
||||
rest_api_client.force_authenticate(user=grantee)
|
||||
response = rest_api_client.get("/api/trash/")
|
||||
|
||||
assert response.status_code == HTTPStatus.OK
|
||||
result_ids = {result["id"] for result in response.data["results"]}
|
||||
assert doc.pk not in result_ids
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@pytest.mark.parametrize(
|
||||
("model", "factory", "perm"),
|
||||
[
|
||||
(Tag, TagFactory, "view_tag"),
|
||||
(Correspondent, CorrespondentFactory, "view_correspondent"),
|
||||
(DocumentType, DocumentTypeFactory, "view_documenttype"),
|
||||
(StoragePath, StoragePathFactory, "view_storagepath"),
|
||||
],
|
||||
)
|
||||
class TestPermittedObjectIdsGenericModels:
|
||||
def test_owner_sees_own_object(self, model, factory, perm):
|
||||
owner = User.objects.create_user(username=f"owner_{model.__name__}")
|
||||
stranger = User.objects.create_user(username=f"stranger_{model.__name__}")
|
||||
owned = factory(owner=owner)
|
||||
strangers = factory(owner=stranger)
|
||||
|
||||
assert_visible_document_ids(
|
||||
permitted_object_ids(owner, model, perm),
|
||||
expected_visible=[owned.pk],
|
||||
expected_hidden=[strangers.pk],
|
||||
)
|
||||
|
||||
@pytest.mark.parametrize("is_superuser", [False, True])
|
||||
def test_inactive_user_sees_nothing(self, model, factory, perm, is_superuser):
|
||||
suffix = f"{model.__name__}_{is_superuser}"
|
||||
user = User.objects.create_user(
|
||||
username=f"inactive_{suffix}",
|
||||
is_active=False,
|
||||
is_superuser=is_superuser,
|
||||
)
|
||||
other = User.objects.create_user(username=f"other_{suffix}")
|
||||
granted = factory(owner=other)
|
||||
assign_perm(perm, user, granted)
|
||||
|
||||
assert_visible_document_ids(
|
||||
permitted_object_ids(user, model, perm),
|
||||
expected_visible=[],
|
||||
expected_hidden=[
|
||||
factory(owner=None).pk,
|
||||
factory(owner=user).pk,
|
||||
granted.pk,
|
||||
],
|
||||
)
|
||||
|
||||
def test_unowned_object_visible_to_everyone(self, model, factory, perm):
|
||||
user = User.objects.create_user(username=f"user_{model.__name__}")
|
||||
unowned = factory(owner=None)
|
||||
|
||||
assert_visible_document_ids(
|
||||
permitted_object_ids(user, model, perm),
|
||||
expected_visible=[unowned.pk],
|
||||
expected_hidden=[],
|
||||
)
|
||||
|
||||
def test_explicit_permission_grants_visibility(self, model, factory, perm):
|
||||
owner = User.objects.create_user(username=f"owner2_{model.__name__}")
|
||||
grantee = User.objects.create_user(username=f"grantee_{model.__name__}")
|
||||
stranger = User.objects.create_user(username=f"stranger2_{model.__name__}")
|
||||
shared = factory(owner=owner)
|
||||
not_shared = factory(owner=owner)
|
||||
assign_perm(perm, grantee, shared)
|
||||
|
||||
assert_visible_document_ids(
|
||||
permitted_object_ids(grantee, model, perm),
|
||||
expected_visible=[shared.pk],
|
||||
expected_hidden=[not_shared.pk],
|
||||
)
|
||||
assert_visible_document_ids(
|
||||
permitted_object_ids(stranger, model, perm),
|
||||
expected_visible=[],
|
||||
expected_hidden=[shared.pk, not_shared.pk],
|
||||
)
|
||||
|
||||
def test_group_permission_grants_visibility_to_members_only(
|
||||
self,
|
||||
model,
|
||||
factory,
|
||||
perm,
|
||||
):
|
||||
owner = User.objects.create_user(username=f"owner3_{model.__name__}")
|
||||
member = User.objects.create_user(username=f"member_{model.__name__}")
|
||||
non_member = User.objects.create_user(username=f"nonmember_{model.__name__}")
|
||||
group = Group.objects.create(name=f"group_{model.__name__}")
|
||||
member.groups.add(group)
|
||||
shared = factory(owner=owner)
|
||||
assign_perm(perm, group, shared)
|
||||
|
||||
assert_visible_document_ids(
|
||||
permitted_object_ids(member, model, perm),
|
||||
expected_visible=[shared.pk],
|
||||
expected_hidden=[],
|
||||
)
|
||||
assert_visible_document_ids(
|
||||
permitted_object_ids(non_member, model, perm),
|
||||
expected_visible=[],
|
||||
expected_hidden=[shared.pk],
|
||||
)
|
||||
|
||||
def test_superuser_sees_everything(self, model, factory, perm):
|
||||
superuser = User.objects.create_superuser(username=f"root_{model.__name__}")
|
||||
owner = User.objects.create_user(username=f"owner4_{model.__name__}")
|
||||
obj = factory(owner=owner)
|
||||
|
||||
assert_visible_document_ids(
|
||||
permitted_object_ids(superuser, model, perm),
|
||||
expected_visible=[obj.pk],
|
||||
expected_hidden=[],
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestMatchingRespectsObjectPermissions:
|
||||
def test_match_tags_only_considers_tags_visible_to_user(self):
|
||||
owner = User.objects.create_user(username="tag_owner")
|
||||
classifying_user = User.objects.create_user(username="classifier_user")
|
||||
visible_tag = TagFactory(
|
||||
owner=owner,
|
||||
match="invoice",
|
||||
matching_algorithm=Tag.MATCH_LITERAL,
|
||||
)
|
||||
hidden_tag = TagFactory(
|
||||
owner=owner,
|
||||
match="invoice",
|
||||
matching_algorithm=Tag.MATCH_LITERAL,
|
||||
)
|
||||
assign_perm("view_tag", classifying_user, visible_tag)
|
||||
doc = DocumentFactory(owner=classifying_user, content="an invoice document")
|
||||
|
||||
matched = match_tags(doc, classifier=None, user=classifying_user)
|
||||
matched_ids = {t.pk for t in matched}
|
||||
assert visible_tag.pk in matched_ids
|
||||
assert hidden_tag.pk not in matched_ids
|
||||
|
||||
def test_match_correspondents_only_considers_correspondents_visible_to_user(self):
|
||||
owner = User.objects.create_user(username="correspondent_owner")
|
||||
classifying_user = User.objects.create_user(username="classifier_user2")
|
||||
visible_correspondent = CorrespondentFactory(
|
||||
owner=owner,
|
||||
match="invoice",
|
||||
matching_algorithm=Correspondent.MATCH_LITERAL,
|
||||
)
|
||||
hidden_correspondent = CorrespondentFactory(
|
||||
owner=owner,
|
||||
match="invoice",
|
||||
matching_algorithm=Correspondent.MATCH_LITERAL,
|
||||
)
|
||||
assign_perm("view_correspondent", classifying_user, visible_correspondent)
|
||||
doc = DocumentFactory(owner=classifying_user, content="an invoice document")
|
||||
|
||||
matched = match_correspondents(doc, classifier=None, user=classifying_user)
|
||||
matched_ids = {c.pk for c in matched}
|
||||
assert visible_correspondent.pk in matched_ids
|
||||
assert hidden_correspondent.pk not in matched_ids
|
||||
|
||||
def test_match_document_types_only_considers_document_types_visible_to_user(self):
|
||||
owner = User.objects.create_user(username="document_type_owner")
|
||||
classifying_user = User.objects.create_user(username="classifier_user3")
|
||||
visible_document_type = DocumentTypeFactory(
|
||||
owner=owner,
|
||||
match="invoice",
|
||||
matching_algorithm=DocumentType.MATCH_LITERAL,
|
||||
)
|
||||
hidden_document_type = DocumentTypeFactory(
|
||||
owner=owner,
|
||||
match="invoice",
|
||||
matching_algorithm=DocumentType.MATCH_LITERAL,
|
||||
)
|
||||
assign_perm("view_documenttype", classifying_user, visible_document_type)
|
||||
doc = DocumentFactory(owner=classifying_user, content="an invoice document")
|
||||
|
||||
matched = match_document_types(doc, classifier=None, user=classifying_user)
|
||||
matched_ids = {dt.pk for dt in matched}
|
||||
assert visible_document_type.pk in matched_ids
|
||||
assert hidden_document_type.pk not in matched_ids
|
||||
|
||||
def test_match_storage_paths_only_considers_storage_paths_visible_to_user(self):
|
||||
owner = User.objects.create_user(username="storage_path_owner")
|
||||
classifying_user = User.objects.create_user(username="classifier_user4")
|
||||
visible_storage_path = StoragePathFactory(
|
||||
owner=owner,
|
||||
match="invoice",
|
||||
matching_algorithm=StoragePath.MATCH_LITERAL,
|
||||
)
|
||||
hidden_storage_path = StoragePathFactory(
|
||||
owner=owner,
|
||||
match="invoice",
|
||||
matching_algorithm=StoragePath.MATCH_LITERAL,
|
||||
)
|
||||
assign_perm("view_storagepath", classifying_user, visible_storage_path)
|
||||
doc = DocumentFactory(owner=classifying_user, content="an invoice document")
|
||||
|
||||
matched = match_storage_paths(doc, classifier=None, user=classifying_user)
|
||||
matched_ids = {sp.pk for sp in matched}
|
||||
assert visible_storage_path.pk in matched_ids
|
||||
assert hidden_storage_path.pk not in matched_ids
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestBulkEditObjectsApplyToAllPermissionBoundary:
|
||||
def test_apply_to_all_tags_excludes_unpermitted_tag(self, rest_api_client):
|
||||
owner = User.objects.create_user(username="tags_owner")
|
||||
requester = User.objects.create_user(username="tags_requester")
|
||||
# grant the global change_tag permission so the object-level
|
||||
# filtering (not the global has_perm check) is what's under test
|
||||
requester.user_permissions.add(
|
||||
Permission.objects.get(codename="change_tag"),
|
||||
)
|
||||
rest_api_client.force_authenticate(user=requester)
|
||||
visible = TagFactory(owner=owner)
|
||||
hidden = TagFactory(owner=owner)
|
||||
assign_perm("view_tag", requester, visible)
|
||||
assign_perm("change_tag", requester, visible)
|
||||
|
||||
response = rest_api_client.post(
|
||||
"/api/bulk_edit_objects/",
|
||||
{
|
||||
"object_type": "tags",
|
||||
"operation": "set_permissions",
|
||||
"all": True,
|
||||
"filters": {},
|
||||
"owner": requester.pk,
|
||||
},
|
||||
format="json",
|
||||
)
|
||||
assert response.status_code == HTTPStatus.OK
|
||||
|
||||
# The apply_to_all dispatch must resolve permitted objects up front:
|
||||
# the visible tag (object-level change_tag granted) gets its owner
|
||||
# reassigned, while the hidden tag (no object-level grant) is
|
||||
# excluded entirely and keeps its original owner.
|
||||
visible.refresh_from_db()
|
||||
hidden.refresh_from_db()
|
||||
assert visible.owner == requester
|
||||
assert hidden.owner == owner
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestBulkEditObjectsTagDescendantPartialPermission:
|
||||
def test_apply_to_all_descendant_expansion_respects_per_object_permissions(
|
||||
self,
|
||||
rest_api_client,
|
||||
):
|
||||
"""
|
||||
GIVEN:
|
||||
- A tag hierarchy (parent -> permitted_child, unpermitted_child)
|
||||
- A non-superuser requester with object-level change_tag granted
|
||||
on the parent and on only ONE of the two children
|
||||
WHEN:
|
||||
- bulk_edit_objects is called with all=True and a filter that
|
||||
matches only the root (parent) tag, engaging the
|
||||
tag-descendant-expansion logic in BulkEditObjectsView.post
|
||||
THEN:
|
||||
- The descendant expansion only pulls in descendants the
|
||||
requester actually has permission on: the permitted child's
|
||||
owner is reassigned alongside the parent's, while the
|
||||
unpermitted child keeps its original owner. This pins that the
|
||||
expansion checks per-object permissions (editable_ids), not
|
||||
merely "is a descendant of a filter match".
|
||||
|
||||
NOTE: this uses ``set_permissions`` (owner reassignment) rather than
|
||||
``delete`` as the operation, because Tag.tn_parent (django-treenode)
|
||||
cascades deletes to descendants at the database/ORM level regardless
|
||||
of which tags the view resolved into ``objs`` -- a delete-based test
|
||||
would pass/fail based on FK cascade behavior, not on whether the
|
||||
descendant-expansion logic itself respected per-object permissions.
|
||||
"""
|
||||
owner = User.objects.create_user(username="tag_hierarchy_owner")
|
||||
requester = User.objects.create_user(username="tag_hierarchy_requester")
|
||||
# global change_tag permission so the has_perm() gate passes and the
|
||||
# object-level permitted_object_ids filtering is what's under test
|
||||
requester.user_permissions.add(
|
||||
Permission.objects.get(codename="change_tag"),
|
||||
)
|
||||
rest_api_client.force_authenticate(user=requester)
|
||||
|
||||
parent = TagFactory(owner=owner, name="parent-tag")
|
||||
permitted_child = TagFactory(
|
||||
owner=owner,
|
||||
name="permitted-child-tag",
|
||||
tn_parent=parent,
|
||||
)
|
||||
unpermitted_child = TagFactory(
|
||||
owner=owner,
|
||||
name="unpermitted-child-tag",
|
||||
tn_parent=parent,
|
||||
)
|
||||
assign_perm("change_tag", requester, parent)
|
||||
assign_perm("change_tag", requester, permitted_child)
|
||||
# unpermitted_child is intentionally NOT granted change_tag
|
||||
|
||||
response = rest_api_client.post(
|
||||
"/api/bulk_edit_objects/",
|
||||
{
|
||||
"object_type": "tags",
|
||||
"operation": "set_permissions",
|
||||
"all": True,
|
||||
"filters": {"is_root": True},
|
||||
"owner": requester.pk,
|
||||
},
|
||||
format="json",
|
||||
)
|
||||
assert response.status_code == HTTPStatus.OK
|
||||
|
||||
parent.refresh_from_db()
|
||||
permitted_child.refresh_from_db()
|
||||
unpermitted_child.refresh_from_db()
|
||||
assert parent.owner == requester
|
||||
assert permitted_child.owner == requester
|
||||
assert unpermitted_child.owner == owner
|
||||
|
||||
@@ -1,111 +0,0 @@
|
||||
import pytest
|
||||
from django.contrib.auth.models import User
|
||||
from guardian.shortcuts import assign_perm
|
||||
from rest_framework.test import APIRequestFactory
|
||||
|
||||
from documents.filters import PermittedObjectsFilter
|
||||
from documents.models import Tag
|
||||
from documents.tests.factories import TagFactory
|
||||
|
||||
|
||||
class _DummyView:
|
||||
queryset = Tag.objects.all()
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestPermittedObjectsFilter:
|
||||
def test_superuser_bypasses_filtering_entirely(self):
|
||||
superuser = User.objects.create_superuser(username="root")
|
||||
owner = User.objects.create_user(username="owner")
|
||||
TagFactory(owner=owner)
|
||||
request = APIRequestFactory().get("/")
|
||||
request.user = superuser
|
||||
|
||||
result = PermittedObjectsFilter().filter_queryset(
|
||||
request,
|
||||
Tag.objects.all(),
|
||||
_DummyView(),
|
||||
)
|
||||
assert result.count() == Tag.objects.count()
|
||||
|
||||
def test_non_superuser_sees_only_owned_unowned_and_granted(self):
|
||||
owner = User.objects.create_user(username="owner")
|
||||
grantee = User.objects.create_user(username="grantee")
|
||||
owned = TagFactory(owner=grantee)
|
||||
unowned = TagFactory(owner=None)
|
||||
granted = TagFactory(owner=owner)
|
||||
hidden = TagFactory(owner=owner)
|
||||
assign_perm("view_tag", grantee, granted)
|
||||
request = APIRequestFactory().get("/")
|
||||
request.user = grantee
|
||||
|
||||
result = PermittedObjectsFilter().filter_queryset(
|
||||
request,
|
||||
Tag.objects.all(),
|
||||
_DummyView(),
|
||||
)
|
||||
visible_ids = set(result.values_list("id", flat=True))
|
||||
assert visible_ids == {owned.pk, unowned.pk, granted.pk}
|
||||
assert hidden.pk not in visible_ids
|
||||
|
||||
def test_include_granted_false_excludes_explicitly_shared_objects(self):
|
||||
owner = User.objects.create_user(username="owner2")
|
||||
grantee = User.objects.create_user(username="grantee2")
|
||||
owned = TagFactory(owner=grantee)
|
||||
granted = TagFactory(owner=owner)
|
||||
assign_perm("view_tag", grantee, granted)
|
||||
request = APIRequestFactory().get("/")
|
||||
request.user = grantee
|
||||
|
||||
class _OwnerOnlyFilter(PermittedObjectsFilter):
|
||||
include_granted = False
|
||||
|
||||
result = _OwnerOnlyFilter().filter_queryset(
|
||||
request,
|
||||
Tag.objects.all(),
|
||||
_DummyView(),
|
||||
)
|
||||
visible_ids = set(result.values_list("id", flat=True))
|
||||
assert visible_ids == {owned.pk}
|
||||
assert granted.pk not in visible_ids
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
("username", "is_superuser"),
|
||||
[("inactive", False), ("inactive_super", True)],
|
||||
)
|
||||
def test_inactive_user_sees_nothing(self, username: str, *, is_superuser: bool):
|
||||
user = User.objects.create_user(
|
||||
username=username,
|
||||
is_active=False,
|
||||
is_superuser=is_superuser,
|
||||
)
|
||||
TagFactory(owner=None)
|
||||
TagFactory(owner=user)
|
||||
granted = TagFactory(owner=User.objects.create_user(username=f"o_{username}"))
|
||||
assign_perm("view_tag", user, granted)
|
||||
request = APIRequestFactory().get("/")
|
||||
request.user = user
|
||||
|
||||
result = PermittedObjectsFilter().filter_queryset(
|
||||
request,
|
||||
Tag.objects.all(),
|
||||
_DummyView(),
|
||||
)
|
||||
assert result.count() == 0
|
||||
|
||||
def test_inactive_user_sees_nothing_with_include_granted_false(self):
|
||||
user = User.objects.create_user(username="inactive_owner", is_active=False)
|
||||
TagFactory(owner=user)
|
||||
TagFactory(owner=None)
|
||||
request = APIRequestFactory().get("/")
|
||||
request.user = user
|
||||
|
||||
class _OwnerOnlyFilter(PermittedObjectsFilter):
|
||||
include_granted = False
|
||||
|
||||
result = _OwnerOnlyFilter().filter_queryset(
|
||||
request,
|
||||
Tag.objects.all(),
|
||||
_DummyView(),
|
||||
)
|
||||
assert result.count() == 0
|
||||
@@ -385,25 +385,6 @@ class TestTaskFailureHandler:
|
||||
task_failure_handler(task_id=None, exception=ValueError("x"), traceback=None)
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestApplyAiSuggestionsTracking:
|
||||
def test_records_the_document_it_is_for(self) -> None:
|
||||
"""
|
||||
The action queues one task per document, so the tracked record notes
|
||||
which document it is for -- otherwise a bulk run is an indistinguishable
|
||||
wall of identical entries in the tasks list.
|
||||
"""
|
||||
task_id = send_publish(
|
||||
"documents.tasks.apply_ai_suggestions",
|
||||
(),
|
||||
{"action_id": 1, "document_id": 42},
|
||||
)
|
||||
|
||||
task = PaperlessTask.objects.get(task_id=task_id)
|
||||
assert task.task_type == PaperlessTask.TaskType.APPLY_AI_SUGGESTIONS
|
||||
assert task.input_data == {"document_id": 42}
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestTaskRevokedHandler:
|
||||
def test_marks_task_revoked(self, mocker: pytest_mock.MockerFixture) -> None:
|
||||
|
||||
@@ -14,7 +14,6 @@ from documents.models import Correspondent
|
||||
from documents.models import Document
|
||||
from documents.models import DocumentType
|
||||
from documents.models import Tag
|
||||
from documents.models import WorkflowAction
|
||||
from documents.sanity_checker import SanityCheckFailedException
|
||||
from documents.sanity_checker import SanityCheckMessages
|
||||
from documents.tests.test_classifier import dummy_preprocess
|
||||
@@ -288,45 +287,6 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
|
||||
self.assertNotEqual(Document.objects.get(pk=doc.pk).content, "test")
|
||||
|
||||
|
||||
class TestUpdateContentRemoteOCR(DirectoriesMixin, TestCase):
|
||||
"""
|
||||
Consumption workflows do not run on reprocess, so the remote parser is
|
||||
used only in 'always' mode or when the caller explicitly asks for it.
|
||||
"""
|
||||
|
||||
def setUp(self) -> None:
|
||||
super().setUp()
|
||||
|
||||
patcher = mock.patch("documents.tasks.get_parser_registry")
|
||||
self.mock_registry = patcher.start()
|
||||
self.mock_registry.return_value.get_parser_for_file.return_value = None
|
||||
self.addCleanup(patcher.stop)
|
||||
|
||||
self.doc = Document.objects.create(
|
||||
title="test",
|
||||
content="my document",
|
||||
checksum="wow",
|
||||
mime_type="application/pdf",
|
||||
)
|
||||
|
||||
def _allow_remote(self, **kwargs) -> bool:
|
||||
tasks.update_document_content_maybe_archive_file(self.doc.pk, **kwargs)
|
||||
_, call_kwargs = self.mock_registry.return_value.get_parser_for_file.call_args
|
||||
return call_kwargs["allow_remote"]
|
||||
|
||||
@override_settings(REMOTE_OCR_MODE="always")
|
||||
def test_always_mode_allows_remote(self) -> None:
|
||||
self.assertTrue(self._allow_remote())
|
||||
|
||||
@override_settings(REMOTE_OCR_MODE="workflow_only")
|
||||
def test_workflow_only_mode_denies_remote_by_default(self) -> None:
|
||||
self.assertFalse(self._allow_remote())
|
||||
|
||||
@override_settings(REMOTE_OCR_MODE="workflow_only")
|
||||
def test_workflow_only_mode_allows_remote_when_requested(self) -> None:
|
||||
self.assertTrue(self._allow_remote(remote_ocr=True))
|
||||
|
||||
|
||||
class TestAIIndex(DirectoriesMixin, TestCase):
|
||||
@override_settings(
|
||||
AI_ENABLED=True,
|
||||
@@ -448,110 +408,3 @@ class TestAIIndex(DirectoriesMixin, TestCase):
|
||||
rebuild=False,
|
||||
document_ids=doc_ids,
|
||||
)
|
||||
|
||||
|
||||
class TestApplyAISuggestionsTask(DirectoriesMixin, TestCase):
|
||||
def setUp(self) -> None:
|
||||
super().setUp()
|
||||
self.doc = Document.objects.create(
|
||||
title="doc",
|
||||
content="content",
|
||||
checksum="apply-ai-suggestions",
|
||||
)
|
||||
self.action = WorkflowAction.objects.create(
|
||||
type=WorkflowAction.WorkflowActionType.APPLY_AI_SUGGESTIONS,
|
||||
ai_suggestion_fields=[WorkflowAction.AISuggestionField.TITLE],
|
||||
)
|
||||
|
||||
def test_reindexes_without_sending_document_updated(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An apply AI suggestions action that changes the document
|
||||
WHEN:
|
||||
- The task runs
|
||||
THEN:
|
||||
- The search index and caches are refreshed directly, deliberately
|
||||
not via the document_updated signal: that re-runs updated
|
||||
workflows, which for this action means queueing another LLM
|
||||
query for a document it just changed, forever
|
||||
"""
|
||||
with (
|
||||
mock.patch(
|
||||
"documents.workflows.ai.apply_ai_suggestions_to_document",
|
||||
return_value=["title"],
|
||||
),
|
||||
mock.patch("documents.tasks.index_document") as index_document,
|
||||
mock.patch("documents.tasks.clear_document_caches") as clear_caches,
|
||||
mock.patch("documents.tasks.document_updated") as document_updated,
|
||||
):
|
||||
tasks.apply_ai_suggestions(self.action.pk, self.doc.pk)
|
||||
|
||||
index_document.delay.assert_called_once_with(self.doc.pk)
|
||||
clear_caches.assert_called_once_with(self.doc.pk)
|
||||
document_updated.send.assert_not_called()
|
||||
|
||||
def test_no_changes_skips_reindex(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An apply AI suggestions action that changes nothing
|
||||
WHEN:
|
||||
- The task runs
|
||||
THEN:
|
||||
- No reindexing work is queued
|
||||
"""
|
||||
with (
|
||||
mock.patch(
|
||||
"documents.workflows.ai.apply_ai_suggestions_to_document",
|
||||
return_value=[],
|
||||
),
|
||||
mock.patch("documents.tasks.index_document") as index_document,
|
||||
):
|
||||
tasks.apply_ai_suggestions(self.action.pk, self.doc.pk)
|
||||
|
||||
index_document.delay.assert_not_called()
|
||||
|
||||
@override_settings(AI_ENABLED=True, LLM_EMBEDDING_BACKEND="huggingface")
|
||||
def test_updates_llm_index_when_enabled(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An apply AI suggestions action that changes the document
|
||||
- The LLM index is enabled
|
||||
WHEN:
|
||||
- The task runs
|
||||
THEN:
|
||||
- The document is updated in the LLM index too
|
||||
"""
|
||||
with (
|
||||
mock.patch(
|
||||
"documents.workflows.ai.apply_ai_suggestions_to_document",
|
||||
return_value=["title"],
|
||||
),
|
||||
mock.patch("documents.tasks.index_document"),
|
||||
mock.patch(
|
||||
"documents.tasks.update_document_in_llm_index",
|
||||
) as update_in_llm_index,
|
||||
):
|
||||
tasks.apply_ai_suggestions(self.action.pk, self.doc.pk)
|
||||
|
||||
update_in_llm_index.apply_async.assert_called_once()
|
||||
|
||||
def test_deleted_document_is_a_noop(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A document that was deleted between the workflow running and the
|
||||
queued task starting
|
||||
WHEN:
|
||||
- The task runs
|
||||
THEN:
|
||||
- It logs and exits rather than raising
|
||||
"""
|
||||
with (
|
||||
mock.patch(
|
||||
"documents.workflows.ai.apply_ai_suggestions_to_document",
|
||||
) as apply_suggestions,
|
||||
self.assertLogs("paperless.tasks", level="WARNING") as cm,
|
||||
):
|
||||
tasks.apply_ai_suggestions(self.action.pk, self.doc.pk + 1000)
|
||||
|
||||
apply_suggestions.assert_not_called()
|
||||
self.assertIn("no longer exists", "".join(cm.output))
|
||||
|
||||
@@ -31,9 +31,7 @@ from documents.file_handling import create_source_path_directory
|
||||
from documents.file_handling import generate_filename
|
||||
from documents.file_handling import generate_unique_filename
|
||||
from documents.signals.handlers import run_workflows
|
||||
from documents.workflows.ai import apply_ai_suggestions_to_document
|
||||
from documents.workflows.webhooks import send_webhook
|
||||
from paperless_ai.exceptions import LLMTimeoutError
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from django.db.models import QuerySet
|
||||
@@ -5362,493 +5360,3 @@ class TestDateWorkflowLocalization(
|
||||
document = Document.objects.first()
|
||||
assert document is not None
|
||||
assert document.title == expected_title
|
||||
|
||||
|
||||
class TestRemoteOCRWorkflowAction(DirectoriesMixin, SampleDirMixin, APITestCase):
|
||||
def _make_workflow(self, trigger_type) -> None:
|
||||
trigger = WorkflowTrigger.objects.create(type=trigger_type)
|
||||
action = WorkflowAction.objects.create(
|
||||
type=WorkflowAction.WorkflowActionType.REMOTE_OCR,
|
||||
)
|
||||
w = Workflow.objects.create(name="Remote OCR", order=0)
|
||||
w.triggers.add(trigger)
|
||||
w.actions.add(action)
|
||||
w.save()
|
||||
|
||||
def test_consumption_trigger_requests_remote_ocr(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A consumption workflow with a remote OCR action
|
||||
WHEN:
|
||||
- A matching document is consumed
|
||||
THEN:
|
||||
- The overrides ask for remote OCR, which is what the consumer
|
||||
reads when choosing a parser
|
||||
"""
|
||||
self._make_workflow(WorkflowTrigger.WorkflowTriggerType.CONSUMPTION)
|
||||
|
||||
test_file = shutil.copy(
|
||||
self.SAMPLE_DIR / "simple.pdf",
|
||||
self.dirs.scratch_dir / "simple.pdf",
|
||||
)
|
||||
overrides = DocumentMetadataOverrides()
|
||||
|
||||
run_workflows(
|
||||
WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
|
||||
ConsumableDocument(
|
||||
source=DocumentSource.ConsumeFolder,
|
||||
original_file=test_file,
|
||||
),
|
||||
overrides=overrides,
|
||||
)
|
||||
|
||||
self.assertTrue(overrides.remote_ocr)
|
||||
|
||||
def test_other_trigger_types_are_ignored(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A workflow with a remote OCR action that also has a
|
||||
non-consumption trigger, which is a valid combination
|
||||
WHEN:
|
||||
- The non-consumption trigger fires
|
||||
THEN:
|
||||
- The action is skipped, since the document has already been
|
||||
parsed by this point
|
||||
"""
|
||||
trigger = WorkflowTrigger.objects.create(
|
||||
type=WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
|
||||
)
|
||||
updated_trigger = WorkflowTrigger.objects.create(
|
||||
type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
|
||||
)
|
||||
action = WorkflowAction.objects.create(
|
||||
type=WorkflowAction.WorkflowActionType.REMOTE_OCR,
|
||||
)
|
||||
w = Workflow.objects.create(name="Remote OCR", order=0)
|
||||
w.triggers.add(trigger, updated_trigger)
|
||||
w.actions.add(action)
|
||||
w.save()
|
||||
|
||||
doc = Document.objects.create(
|
||||
title="sample test",
|
||||
original_filename="sample.pdf",
|
||||
)
|
||||
|
||||
with self.assertLogs("paperless.handlers", level="DEBUG") as cm:
|
||||
run_workflows(
|
||||
WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
|
||||
doc,
|
||||
)
|
||||
|
||||
self.assertIn("only applies to consumption triggers", "".join(cm.output))
|
||||
|
||||
|
||||
SUGGESTIONS = {
|
||||
"title": "Suggested Title",
|
||||
"tags": ["Existing Tag", "Suggested Tag"],
|
||||
"correspondents": ["Existing Correspondent", "Suggested Correspondent"],
|
||||
"document_types": ["Suggested Document Type"],
|
||||
"storage_paths": ["Suggested Storage Path"],
|
||||
"dates": ["2024-03-05"],
|
||||
}
|
||||
|
||||
ALL_SUGGESTION_FIELDS = [
|
||||
WorkflowAction.AISuggestionField.TITLE,
|
||||
WorkflowAction.AISuggestionField.TAGS,
|
||||
WorkflowAction.AISuggestionField.CORRESPONDENT,
|
||||
WorkflowAction.AISuggestionField.DOCUMENT_TYPE,
|
||||
WorkflowAction.AISuggestionField.STORAGE_PATH,
|
||||
WorkflowAction.AISuggestionField.CREATED,
|
||||
]
|
||||
|
||||
|
||||
@override_settings(AI_ENABLED=True)
|
||||
class TestApplyAISuggestionsWorkflowAction(
|
||||
DirectoriesMixin,
|
||||
SampleDirMixin,
|
||||
APITestCase,
|
||||
):
|
||||
def setUp(self) -> None:
|
||||
super().setUp()
|
||||
self.user = User.objects.create(username="ai-user")
|
||||
self.doc = Document.objects.create(
|
||||
title="original.pdf",
|
||||
content="the document content",
|
||||
checksum="ai-suggestions-checksum",
|
||||
mime_type="application/pdf",
|
||||
created=datetime.date(2020, 1, 1),
|
||||
owner=self.user,
|
||||
)
|
||||
|
||||
def make_action(self, **kwargs) -> WorkflowAction:
|
||||
return WorkflowAction.objects.create(
|
||||
type=WorkflowAction.WorkflowActionType.APPLY_AI_SUGGESTIONS,
|
||||
ai_suggestion_fields=kwargs.pop(
|
||||
"ai_suggestion_fields",
|
||||
ALL_SUGGESTION_FIELDS,
|
||||
),
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
def make_workflow(self, action: WorkflowAction, trigger_type) -> Workflow:
|
||||
trigger = WorkflowTrigger.objects.create(type=trigger_type)
|
||||
w = Workflow.objects.create(name="Apply AI suggestions", order=0)
|
||||
w.triggers.add(trigger)
|
||||
w.actions.add(action)
|
||||
w.save()
|
||||
return w
|
||||
|
||||
def apply(self, action: WorkflowAction) -> list[str]:
|
||||
with mock.patch(
|
||||
"documents.workflows.ai.get_ai_document_classification",
|
||||
return_value=SUGGESTIONS,
|
||||
):
|
||||
changed = apply_ai_suggestions_to_document(action, self.doc)
|
||||
self.doc.refresh_from_db()
|
||||
return changed
|
||||
|
||||
def test_document_added_trigger_queues_task(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A document added workflow with an apply AI suggestions action
|
||||
WHEN:
|
||||
- A matching document is added
|
||||
THEN:
|
||||
- The work is queued rather than run inline, so a slow LLM query
|
||||
cannot stall the rest of the workflow run
|
||||
"""
|
||||
action = self.make_action()
|
||||
self.make_workflow(action, WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED)
|
||||
|
||||
with mock.patch("documents.tasks.apply_ai_suggestions.delay") as delay:
|
||||
run_workflows(
|
||||
WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
|
||||
self.doc,
|
||||
)
|
||||
|
||||
delay.assert_called_once_with(action_id=action.pk, document_id=self.doc.pk)
|
||||
|
||||
def test_consumption_trigger_is_ignored(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A workflow with an apply AI suggestions action and a consumption
|
||||
trigger alongside a valid one
|
||||
WHEN:
|
||||
- The consumption trigger fires
|
||||
THEN:
|
||||
- The action is skipped, since the document has not been parsed
|
||||
yet and so has no content to make suggestions from
|
||||
"""
|
||||
action = self.make_action()
|
||||
w = self.make_workflow(
|
||||
action,
|
||||
WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
|
||||
)
|
||||
w.triggers.add(
|
||||
WorkflowTrigger.objects.create(
|
||||
type=WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
|
||||
),
|
||||
)
|
||||
|
||||
test_file = shutil.copy(
|
||||
self.SAMPLE_DIR / "simple.pdf",
|
||||
self.dirs.scratch_dir / "simple.pdf",
|
||||
)
|
||||
|
||||
with (
|
||||
mock.patch("documents.tasks.apply_ai_suggestions.delay") as delay,
|
||||
self.assertLogs("paperless.handlers", level="DEBUG") as cm,
|
||||
):
|
||||
run_workflows(
|
||||
WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
|
||||
ConsumableDocument(
|
||||
source=DocumentSource.ConsumeFolder,
|
||||
original_file=test_file,
|
||||
),
|
||||
overrides=DocumentMetadataOverrides(),
|
||||
)
|
||||
|
||||
delay.assert_not_called()
|
||||
self.assertIn("does not apply to consumption triggers", "".join(cm.output))
|
||||
|
||||
def test_no_selected_fields_does_nothing(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An action with no suggestion fields selected
|
||||
WHEN:
|
||||
- The action is applied
|
||||
THEN:
|
||||
- Nothing is changed and it is logged
|
||||
"""
|
||||
action = self.make_action(ai_suggestion_fields=[])
|
||||
|
||||
with self.assertLogs("paperless.workflows.ai", level="WARNING") as cm:
|
||||
changed = self.apply(action)
|
||||
|
||||
self.assertEqual(changed, [])
|
||||
self.assertIn("no AI suggestion fields selected", "".join(cm.output))
|
||||
|
||||
@override_settings(AI_ENABLED=False)
|
||||
def test_ai_disabled_does_nothing(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An action on an install where AI has since been disabled
|
||||
WHEN:
|
||||
- The action is applied
|
||||
THEN:
|
||||
- Nothing is changed and it is logged
|
||||
"""
|
||||
action = self.make_action()
|
||||
|
||||
with self.assertLogs("paperless.workflows.ai", level="ERROR") as cm:
|
||||
changed = self.apply(action)
|
||||
|
||||
self.assertEqual(changed, [])
|
||||
self.assertIn("AI is not enabled", "".join(cm.output))
|
||||
|
||||
def test_invalid_configuration_leaves_document_untouched(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An AI backend that is misconfigured
|
||||
WHEN:
|
||||
- The action is applied
|
||||
THEN:
|
||||
- The failure is logged and the document is left alone. It is not
|
||||
re-raised, because retrying will not fix a bad configuration
|
||||
"""
|
||||
action = self.make_action()
|
||||
|
||||
with (
|
||||
mock.patch(
|
||||
"documents.workflows.ai.get_ai_document_classification",
|
||||
side_effect=ValueError("nope"),
|
||||
),
|
||||
self.assertLogs("paperless.workflows.ai", level="ERROR") as cm,
|
||||
):
|
||||
changed = apply_ai_suggestions_to_document(action, self.doc)
|
||||
|
||||
self.assertEqual(changed, [])
|
||||
self.doc.refresh_from_db()
|
||||
self.assertEqual(self.doc.title, "original.pdf")
|
||||
self.assertIn("Invalid AI configuration", "".join(cm.output))
|
||||
|
||||
def test_transient_llm_failure_is_raised_for_retry(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An LLM backend that times out, or rate limits the request
|
||||
WHEN:
|
||||
- The action is applied
|
||||
THEN:
|
||||
- The error propagates so the queued task can back off and retry,
|
||||
rather than silently dropping this document's suggestions
|
||||
"""
|
||||
action = self.make_action()
|
||||
|
||||
with (
|
||||
mock.patch(
|
||||
"documents.workflows.ai.get_ai_document_classification",
|
||||
side_effect=LLMTimeoutError(),
|
||||
),
|
||||
self.assertRaises(LLMTimeoutError),
|
||||
):
|
||||
apply_ai_suggestions_to_document(action, self.doc)
|
||||
|
||||
self.doc.refresh_from_db()
|
||||
self.assertEqual(self.doc.title, "original.pdf")
|
||||
|
||||
def test_only_matching_objects_are_applied(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An action without create missing, and only some of the suggested
|
||||
objects existing
|
||||
WHEN:
|
||||
- The action is applied
|
||||
THEN:
|
||||
- Only the existing objects are assigned, unmatched suggestions are
|
||||
dropped rather than creating anything
|
||||
"""
|
||||
tag = Tag.objects.create(name="Existing Tag", owner=self.user)
|
||||
correspondent = Correspondent.objects.create(
|
||||
name="Existing Correspondent",
|
||||
owner=self.user,
|
||||
)
|
||||
action = self.make_action(ai_overwrite_existing=True)
|
||||
|
||||
changed = self.apply(action)
|
||||
|
||||
self.assertEqual(self.doc.correspondent, correspondent)
|
||||
self.assertEqual(list(self.doc.tags.all()), [tag])
|
||||
# Nothing matched for these and create missing is off
|
||||
self.assertIsNone(self.doc.document_type)
|
||||
self.assertIsNone(self.doc.storage_path)
|
||||
self.assertNotIn("document_type", changed)
|
||||
self.assertEqual(Tag.objects.count(), 1)
|
||||
self.assertEqual(Correspondent.objects.count(), 1)
|
||||
|
||||
def test_create_missing_creates_objects_owned_by_document_owner(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An action with create missing enabled
|
||||
WHEN:
|
||||
- The action is applied and suggestions match nothing
|
||||
THEN:
|
||||
- Tags, correspondents and document types are created, owned by the
|
||||
document owner so they stay private to them
|
||||
- Storage paths are never created, since a path template cannot be
|
||||
inferred from a name
|
||||
"""
|
||||
action = self.make_action(
|
||||
ai_create_missing=True,
|
||||
ai_overwrite_existing=True,
|
||||
)
|
||||
|
||||
changed = self.apply(action)
|
||||
|
||||
self.assertEqual(
|
||||
sorted(t.name for t in self.doc.tags.all()),
|
||||
["Existing Tag", "Suggested Tag"],
|
||||
)
|
||||
self.assertEqual(self.doc.correspondent.name, "Existing Correspondent")
|
||||
self.assertEqual(self.doc.correspondent.owner, self.user)
|
||||
self.assertEqual(self.doc.document_type.name, "Suggested Document Type")
|
||||
self.assertEqual(self.doc.document_type.owner, self.user)
|
||||
|
||||
self.assertIsNone(self.doc.storage_path)
|
||||
self.assertFalse(StoragePath.objects.exists())
|
||||
self.assertNotIn("storage_path", changed)
|
||||
|
||||
def test_overwrite_disabled_keeps_existing_values(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An action without overwrite existing
|
||||
- A document that already has a title, created date and
|
||||
correspondent
|
||||
WHEN:
|
||||
- The action is applied
|
||||
THEN:
|
||||
- The existing values are kept, only the empty document type is
|
||||
filled in
|
||||
"""
|
||||
existing = Correspondent.objects.create(name="Mine", owner=self.user)
|
||||
self.doc.correspondent = existing
|
||||
self.doc.save()
|
||||
action = self.make_action(ai_create_missing=True)
|
||||
|
||||
changed = self.apply(action)
|
||||
|
||||
self.assertEqual(self.doc.title, "original.pdf")
|
||||
self.assertEqual(self.doc.created, datetime.date(2020, 1, 1))
|
||||
self.assertEqual(self.doc.correspondent, existing)
|
||||
self.assertEqual(self.doc.document_type.name, "Suggested Document Type")
|
||||
self.assertNotIn("title", changed)
|
||||
self.assertNotIn("correspondent", changed)
|
||||
|
||||
def test_overwrite_enabled_replaces_existing_values(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An action with overwrite existing
|
||||
- A document that already has a title and created date
|
||||
WHEN:
|
||||
- The action is applied
|
||||
THEN:
|
||||
- The suggested values replace them
|
||||
"""
|
||||
action = self.make_action(
|
||||
ai_create_missing=True,
|
||||
ai_overwrite_existing=True,
|
||||
)
|
||||
|
||||
changed = self.apply(action)
|
||||
|
||||
self.assertEqual(self.doc.title, "Suggested Title")
|
||||
self.assertEqual(self.doc.created, datetime.date(2024, 3, 5))
|
||||
self.assertIn("title", changed)
|
||||
self.assertIn("created", changed)
|
||||
|
||||
def test_tags_are_added_not_replaced(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A document that already has a tag unrelated to the suggestions
|
||||
WHEN:
|
||||
- The action is applied with overwrite existing enabled
|
||||
THEN:
|
||||
- The existing tag is kept, since suggested tags are always
|
||||
additive regardless of the overwrite setting
|
||||
"""
|
||||
kept = Tag.objects.create(name="Do Not Remove", owner=self.user)
|
||||
self.doc.tags.add(kept)
|
||||
Tag.objects.create(name="Existing Tag", owner=self.user)
|
||||
action = self.make_action(ai_overwrite_existing=True)
|
||||
|
||||
self.apply(action)
|
||||
|
||||
self.assertEqual(
|
||||
sorted(t.name for t in self.doc.tags.all()),
|
||||
["Do Not Remove", "Existing Tag"],
|
||||
)
|
||||
|
||||
def test_unselected_fields_are_untouched(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An action that only selects the title
|
||||
WHEN:
|
||||
- The action is applied
|
||||
THEN:
|
||||
- Only the title changes, even though the LLM suggested everything
|
||||
"""
|
||||
action = self.make_action(
|
||||
ai_suggestion_fields=[WorkflowAction.AISuggestionField.TITLE],
|
||||
ai_create_missing=True,
|
||||
ai_overwrite_existing=True,
|
||||
)
|
||||
|
||||
changed = self.apply(action)
|
||||
|
||||
self.assertEqual(changed, ["title"])
|
||||
self.assertEqual(self.doc.title, "Suggested Title")
|
||||
self.assertEqual(self.doc.tags.count(), 0)
|
||||
self.assertIsNone(self.doc.correspondent)
|
||||
self.assertEqual(self.doc.created, datetime.date(2020, 1, 1))
|
||||
|
||||
def test_another_users_private_objects_are_not_matched(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A suggested tag name that exists, but is owned by someone else
|
||||
WHEN:
|
||||
- The action is applied
|
||||
THEN:
|
||||
- It is not assigned, because the document owner cannot see it
|
||||
"""
|
||||
other = User.objects.create(username="someone-else")
|
||||
Tag.objects.create(name="Existing Tag", owner=other)
|
||||
action = self.make_action(
|
||||
ai_suggestion_fields=[WorkflowAction.AISuggestionField.TAGS],
|
||||
)
|
||||
|
||||
self.apply(action)
|
||||
|
||||
self.assertEqual(self.doc.tags.count(), 0)
|
||||
|
||||
def test_unparsable_dates_are_skipped(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- Suggested dates that are not all valid
|
||||
WHEN:
|
||||
- The action is applied
|
||||
THEN:
|
||||
- The first usable date is applied and the rest ignored
|
||||
"""
|
||||
action = self.make_action(
|
||||
ai_suggestion_fields=[WorkflowAction.AISuggestionField.CREATED],
|
||||
ai_overwrite_existing=True,
|
||||
)
|
||||
|
||||
with mock.patch(
|
||||
"documents.workflows.ai.get_ai_document_classification",
|
||||
return_value={**SUGGESTIONS, "dates": ["not a date", "2019-07-04"]},
|
||||
):
|
||||
changed = apply_ai_suggestions_to_document(action, self.doc)
|
||||
|
||||
self.doc.refresh_from_db()
|
||||
self.assertEqual(changed, ["created"])
|
||||
self.assertEqual(self.doc.created, datetime.date(2019, 7, 4))
|
||||
|
||||
+63
-38
@@ -133,10 +133,12 @@ from documents.file_handling import format_filename
|
||||
from documents.filters import CorrespondentFilterSet
|
||||
from documents.filters import CustomFieldFilterSet
|
||||
from documents.filters import DocumentFilterSet
|
||||
from documents.filters import DocumentPermissionsFilter
|
||||
from documents.filters import DocumentsOrderingFilter
|
||||
from documents.filters import DocumentTypeFilterSet
|
||||
from documents.filters import ObjectOwnedOrGrantedPermissionsFilter
|
||||
from documents.filters import ObjectOwnedPermissionsFilter
|
||||
from documents.filters import PaperlessTaskFilterSet
|
||||
from documents.filters import PermittedObjectsFilter
|
||||
from documents.filters import ShareLinkBundleFilterSet
|
||||
from documents.filters import ShareLinkFilterSet
|
||||
from documents.filters import StoragePathFilterSet
|
||||
@@ -176,7 +178,6 @@ from documents.permissions import has_global_statistics_permission
|
||||
from documents.permissions import has_perms_owner_aware
|
||||
from documents.permissions import has_system_status_permission
|
||||
from documents.permissions import permitted_document_ids
|
||||
from documents.permissions import permitted_object_ids
|
||||
from documents.permissions import set_permissions_for_object
|
||||
from documents.plugins.date_parsing import get_date_parser
|
||||
from documents.schema import generate_object_with_permissions_schema
|
||||
@@ -195,6 +196,7 @@ from documents.serialisers import DocumentVersionLabelSerializer
|
||||
from documents.serialisers import DocumentVersionSerializer
|
||||
from documents.serialisers import EditPdfDocumentsSerializer
|
||||
from documents.serialisers import EmailSerializer
|
||||
from documents.serialisers import MergeDocumentsAsVersionsSerializer
|
||||
from documents.serialisers import MergeDocumentsSerializer
|
||||
from documents.serialisers import NotesSerializer
|
||||
from documents.serialisers import PostDocumentSerializer
|
||||
@@ -236,15 +238,12 @@ from paperless import version
|
||||
from paperless.celery import app as celery_app
|
||||
from paperless.config import AIConfig
|
||||
from paperless.config import GeneralConfig
|
||||
from paperless.config import RemoteOCRConfig
|
||||
from paperless.models import ApplicationConfiguration
|
||||
from paperless.parsers.registry import get_parser_registry
|
||||
from paperless.parsers.remote import RemoteEngineConfig
|
||||
from paperless.serialisers import GroupSerializer
|
||||
from paperless.serialisers import UserSerializer
|
||||
from paperless.views import StandardPagination
|
||||
from paperless_ai.ai_classifier import get_ai_document_classification
|
||||
from paperless_ai.ai_classifier import get_llm_output_language
|
||||
from paperless_ai.chat import stream_chat_with_documents
|
||||
from paperless_ai.exceptions import LLMTimeoutError
|
||||
from paperless_ai.matching import extract_unmatched_names
|
||||
@@ -552,7 +551,7 @@ class CorrespondentViewSet(
|
||||
filter_backends = (
|
||||
DjangoFilterBackend,
|
||||
OrderingFilter,
|
||||
PermittedObjectsFilter,
|
||||
ObjectOwnedOrGrantedPermissionsFilter,
|
||||
)
|
||||
filterset_class = CorrespondentFilterSet
|
||||
ordering_fields = (
|
||||
@@ -593,7 +592,7 @@ class TagViewSet(PermissionsAwareDocumentCountMixin, ModelViewSet[Tag]):
|
||||
filter_backends = (
|
||||
DjangoFilterBackend,
|
||||
OrderingFilter,
|
||||
PermittedObjectsFilter,
|
||||
ObjectOwnedOrGrantedPermissionsFilter,
|
||||
)
|
||||
filterset_class = TagFilterSet
|
||||
ordering_fields = ("color", "name", "matching_algorithm", "match", "document_count")
|
||||
@@ -656,6 +655,20 @@ class TagViewSet(PermissionsAwareDocumentCountMixin, ModelViewSet[Tag]):
|
||||
update_document_parent_tags(tag, new_parent)
|
||||
|
||||
|
||||
def _get_llm_output_language(ai_config: AIConfig, request) -> str | None:
|
||||
output_language = ai_config.llm_output_language
|
||||
if (
|
||||
not output_language
|
||||
and hasattr(request.user, "ui_settings")
|
||||
and isinstance(
|
||||
request.user.ui_settings.settings,
|
||||
dict,
|
||||
)
|
||||
):
|
||||
output_language = request.user.ui_settings.settings.get("language")
|
||||
return output_language
|
||||
|
||||
|
||||
@extend_schema_view(**generate_object_with_permissions_schema(DocumentTypeSerializer))
|
||||
class DocumentTypeViewSet(
|
||||
PermissionsAwareDocumentCountMixin,
|
||||
@@ -671,7 +684,7 @@ class DocumentTypeViewSet(
|
||||
filter_backends = (
|
||||
DjangoFilterBackend,
|
||||
OrderingFilter,
|
||||
PermittedObjectsFilter,
|
||||
ObjectOwnedOrGrantedPermissionsFilter,
|
||||
)
|
||||
filterset_class = DocumentTypeFilterSet
|
||||
ordering_fields = ("name", "matching_algorithm", "match", "document_count")
|
||||
@@ -975,7 +988,7 @@ class DocumentViewSet(
|
||||
DjangoFilterBackend,
|
||||
SearchFilter,
|
||||
DocumentsOrderingFilter,
|
||||
PermittedObjectsFilter,
|
||||
DocumentPermissionsFilter,
|
||||
)
|
||||
filterset_class = DocumentFilterSet
|
||||
search_fields = ("title", "correspondent__name", "effective_content")
|
||||
@@ -1517,10 +1530,7 @@ class DocumentViewSet(
|
||||
if not ai_config.ai_enabled:
|
||||
return HttpResponseBadRequest("AI is required for this feature")
|
||||
|
||||
output_language = get_llm_output_language(
|
||||
ai_config=ai_config,
|
||||
user=request.user,
|
||||
)
|
||||
output_language = _get_llm_output_language(ai_config=ai_config, request=request)
|
||||
llm_cache_backend = ":".join(
|
||||
part
|
||||
for part in (
|
||||
@@ -2265,10 +2275,7 @@ class ChatStreamingView(GenericAPIView[Any]):
|
||||
id__in=permitted_document_ids(request.user),
|
||||
)
|
||||
|
||||
output_language = get_llm_output_language(
|
||||
ai_config=ai_config,
|
||||
user=request.user,
|
||||
)
|
||||
output_language = _get_llm_output_language(ai_config=ai_config, request=request)
|
||||
|
||||
response = StreamingHttpResponse(
|
||||
stream_chat_with_documents(
|
||||
@@ -2667,7 +2674,7 @@ class SavedViewViewSet(BulkPermissionMixin, PassUserMixin, ModelViewSet[SavedVie
|
||||
permission_classes = (IsAuthenticated, PaperlessObjectPermissions)
|
||||
filter_backends = (
|
||||
OrderingFilter,
|
||||
PermittedObjectsFilter,
|
||||
ObjectOwnedOrGrantedPermissionsFilter,
|
||||
)
|
||||
ordering_fields = ("name",)
|
||||
|
||||
@@ -2802,6 +2809,7 @@ class DocumentOperationPermissionMixin(PassUserMixin, DocumentSelectionMixin):
|
||||
bulk_edit.rotate,
|
||||
bulk_edit.delete_pages,
|
||||
bulk_edit.edit_pdf,
|
||||
bulk_edit.merge_as_versions,
|
||||
bulk_edit.remove_password,
|
||||
]
|
||||
)
|
||||
@@ -3088,6 +3096,33 @@ class MergeDocumentsView(DocumentOperationPermissionMixin):
|
||||
)
|
||||
|
||||
|
||||
@extend_schema_view(
|
||||
post=extend_schema(
|
||||
operation_id="documents_merge_as_versions",
|
||||
description="Merge selected documents as versions of a chosen root document",
|
||||
responses={
|
||||
200: inline_serializer(
|
||||
name="MergeDocumentsAsVersionsResult",
|
||||
fields={
|
||||
"result": serializers.CharField(),
|
||||
},
|
||||
),
|
||||
},
|
||||
),
|
||||
)
|
||||
class MergeDocumentsAsVersionsView(DocumentOperationPermissionMixin):
|
||||
serializer_class = MergeDocumentsAsVersionsSerializer
|
||||
|
||||
def post(self, request, *args, **kwargs):
|
||||
serializer = self.get_serializer(data=request.data)
|
||||
serializer.is_valid(raise_exception=True)
|
||||
return self._execute_document_action(
|
||||
method=bulk_edit.merge_as_versions,
|
||||
validated_data=serializer.validated_data,
|
||||
operation_label="document merge as versions",
|
||||
)
|
||||
|
||||
|
||||
@extend_schema_view(
|
||||
post=extend_schema(
|
||||
operation_id="documents_delete",
|
||||
@@ -3914,7 +3949,7 @@ class StoragePathViewSet(PermissionsAwareDocumentCountMixin, ModelViewSet[Storag
|
||||
filter_backends = (
|
||||
DjangoFilterBackend,
|
||||
OrderingFilter,
|
||||
PermittedObjectsFilter,
|
||||
ObjectOwnedOrGrantedPermissionsFilter,
|
||||
)
|
||||
filterset_class = StoragePathFilterSet
|
||||
ordering_fields = ("name", "path", "matching_algorithm", "match", "document_count")
|
||||
@@ -4005,11 +4040,6 @@ class UiSettingsView(GenericAPIView[Any]):
|
||||
|
||||
ui_settings["auditlog_enabled"] = settings.AUDIT_LOG_ENABLED
|
||||
|
||||
ui_settings["remote_ocr"] = {
|
||||
"configured": RemoteEngineConfig.from_app_config().engine_is_valid(),
|
||||
"mode": RemoteOCRConfig().remote_ocr_mode,
|
||||
}
|
||||
|
||||
if settings.GMAIL_OAUTH_ENABLED or settings.OUTLOOK_OAUTH_ENABLED:
|
||||
manager = PaperlessMailOAuth2Manager()
|
||||
if settings.GMAIL_OAUTH_ENABLED:
|
||||
@@ -4450,7 +4480,7 @@ class ShareLinkViewSet(
|
||||
filter_backends = (
|
||||
DjangoFilterBackend,
|
||||
OrderingFilter,
|
||||
PermittedObjectsFilter,
|
||||
ObjectOwnedOrGrantedPermissionsFilter,
|
||||
)
|
||||
filterset_class = ShareLinkFilterSet
|
||||
ordering_fields = ("created", "expiration", "document")
|
||||
@@ -4480,7 +4510,7 @@ class ShareLinkBundleViewSet(PassUserMixin, ModelViewSet[ShareLinkBundle]):
|
||||
filter_backends = (
|
||||
DjangoFilterBackend,
|
||||
OrderingFilter,
|
||||
PermittedObjectsFilter,
|
||||
ObjectOwnedOrGrantedPermissionsFilter,
|
||||
)
|
||||
filterset_class = ShareLinkBundleFilterSet
|
||||
ordering_fields = ("created", "expiration", "status")
|
||||
@@ -4763,8 +4793,10 @@ class BulkEditObjectsView(PassUserMixin):
|
||||
"document_types": DocumentTypeFilterSet,
|
||||
"storage_paths": StoragePathFilterSet,
|
||||
}[object_type]
|
||||
user_permitted_objects = object_class.objects.filter(
|
||||
id__in=permitted_object_ids(user, object_class, perm_codename),
|
||||
user_permitted_objects = get_objects_for_user_owner_aware(
|
||||
user,
|
||||
perm_codename,
|
||||
object_class,
|
||||
)
|
||||
objs = filterset_class(
|
||||
data=filters,
|
||||
@@ -4789,11 +4821,8 @@ class BulkEditObjectsView(PassUserMixin):
|
||||
|
||||
if not user.is_superuser:
|
||||
perm = f"documents.{perm_codename}"
|
||||
has_perms = (
|
||||
user.has_perm(perm)
|
||||
and not objs.exclude(
|
||||
pk__in=permitted_object_ids(user, object_class, perm_codename),
|
||||
).exists()
|
||||
has_perms = user.has_perm(perm) and all(
|
||||
has_perms_owner_aware(user, perm_codename, obj) for obj in objs
|
||||
)
|
||||
|
||||
if not has_perms:
|
||||
@@ -5294,11 +5323,7 @@ class SystemStatusView(PassUserMixin):
|
||||
class TrashView(ListModelMixin, PassUserMixin):
|
||||
permission_classes = (IsAuthenticated,)
|
||||
serializer_class = TrashSerializer
|
||||
|
||||
class _TrashPermittedObjectsFilter(PermittedObjectsFilter):
|
||||
include_granted = False
|
||||
|
||||
filter_backends = (_TrashPermittedObjectsFilter,)
|
||||
filter_backends = (ObjectOwnedPermissionsFilter,)
|
||||
pagination_class = StandardPagination
|
||||
|
||||
model = Document
|
||||
|
||||
@@ -1,241 +0,0 @@
|
||||
import logging
|
||||
from datetime import date
|
||||
from datetime import datetime
|
||||
|
||||
from django.contrib.auth.models import User
|
||||
|
||||
from documents.models import Correspondent
|
||||
from documents.models import Document
|
||||
from documents.models import DocumentType
|
||||
from documents.models import StoragePath
|
||||
from documents.models import Tag
|
||||
from documents.models import WorkflowAction
|
||||
from paperless.config import AIConfig
|
||||
from paperless_ai.ai_classifier import get_ai_document_classification
|
||||
from paperless_ai.ai_classifier import get_llm_output_language
|
||||
from paperless_ai.matching import extract_unmatched_names
|
||||
from paperless_ai.matching import match_correspondents_by_name
|
||||
from paperless_ai.matching import match_document_types_by_name
|
||||
from paperless_ai.matching import match_storage_paths_by_name
|
||||
from paperless_ai.matching import match_tags_by_name
|
||||
|
||||
logger = logging.getLogger("paperless.workflows.ai")
|
||||
|
||||
AISuggestionField = WorkflowAction.AISuggestionField
|
||||
|
||||
# Tags use m2m relation instead
|
||||
DIRECT_FIELDS: dict[str, str] = {
|
||||
AISuggestionField.TITLE: "title",
|
||||
AISuggestionField.CORRESPONDENT: "correspondent",
|
||||
AISuggestionField.DOCUMENT_TYPE: "document_type",
|
||||
AISuggestionField.STORAGE_PATH: "storage_path",
|
||||
AISuggestionField.CREATED: "created",
|
||||
}
|
||||
|
||||
|
||||
def resolve_date(dates: list[str]) -> date | None:
|
||||
"""
|
||||
First usable date out of the suggestions, which are expected as
|
||||
YYYY-MM-DD. Document.created is a DateField, so only one can be applied.
|
||||
"""
|
||||
for value in dates:
|
||||
try:
|
||||
return datetime.strptime(value, "%Y-%m-%d").date()
|
||||
except (TypeError, ValueError):
|
||||
logger.debug("Ignoring unparsable suggested date %s", value)
|
||||
return None
|
||||
|
||||
|
||||
def resolve_object(
|
||||
model,
|
||||
names: list[str],
|
||||
matched: list,
|
||||
*,
|
||||
create_missing: bool,
|
||||
owner: User | None,
|
||||
):
|
||||
"""
|
||||
Single object from a suggestion list. The best match if there was one, else
|
||||
optionally a newly-created object. StoragePaths are excluded.
|
||||
"""
|
||||
if matched:
|
||||
return matched[0]
|
||||
|
||||
if not create_missing or model is StoragePath:
|
||||
return None
|
||||
|
||||
unmatched = extract_unmatched_names(names, matched)
|
||||
if not unmatched:
|
||||
return None
|
||||
|
||||
# (name, owner) is what MatchingModel is unique on
|
||||
obj, created = model.objects.get_or_create(
|
||||
name=unmatched[0][:128],
|
||||
owner=owner,
|
||||
)
|
||||
if created:
|
||||
logger.info("Created %s '%s' from AI suggestion", model.__name__, obj.name)
|
||||
return obj
|
||||
|
||||
|
||||
def resolve_tags(
|
||||
names: list[str],
|
||||
matched: list[Tag],
|
||||
*,
|
||||
create_missing: bool,
|
||||
owner: User | None,
|
||||
) -> list[Tag]:
|
||||
"""
|
||||
Matched tags, plus newly created ones if create_missing is set.
|
||||
"""
|
||||
tags = list(matched)
|
||||
if not create_missing:
|
||||
return tags
|
||||
|
||||
for name in extract_unmatched_names(names, matched):
|
||||
tag, created = Tag.objects.get_or_create(
|
||||
name=name[:128],
|
||||
owner=owner,
|
||||
)
|
||||
if created:
|
||||
logger.info("Created tag '%s' from AI suggestion", tag.name)
|
||||
tags.append(tag)
|
||||
return tags
|
||||
|
||||
|
||||
def apply_ai_suggestions_to_document(
|
||||
action: WorkflowAction,
|
||||
document: Document,
|
||||
logging_group=None,
|
||||
) -> list[str]:
|
||||
"""
|
||||
Get suggestions about `document` and write the chosen fields.
|
||||
|
||||
Returns the names of the fields that were actually changed.
|
||||
"""
|
||||
selected = set(action.ai_suggestion_fields or [])
|
||||
if not selected:
|
||||
logger.warning(
|
||||
"Workflow action %s has no AI suggestion fields selected, skipping",
|
||||
action.pk,
|
||||
extra={"group": logging_group},
|
||||
)
|
||||
return []
|
||||
|
||||
ai_config = AIConfig()
|
||||
if not ai_config.ai_enabled:
|
||||
logger.error(
|
||||
"AI is not enabled, cannot apply AI suggestions for document %s",
|
||||
document.pk,
|
||||
extra={"group": logging_group},
|
||||
)
|
||||
return []
|
||||
|
||||
# Workflows run without a user, so we use the document owner
|
||||
owner = document.owner
|
||||
|
||||
try:
|
||||
suggestions = get_ai_document_classification(
|
||||
document,
|
||||
owner,
|
||||
get_llm_output_language(ai_config, owner),
|
||||
)
|
||||
except ValueError:
|
||||
# A bad AI config will not fix itself, so swallow it rather than
|
||||
# letting the caller retry. Timeouts, rate limits, network errors etc
|
||||
# propagate so the queued task can back off and try again.
|
||||
logger.exception(
|
||||
"Invalid AI configuration, cannot get suggestions for document %s",
|
||||
document.pk,
|
||||
extra={"group": logging_group},
|
||||
)
|
||||
return []
|
||||
|
||||
overwrite = action.ai_overwrite_existing
|
||||
create_missing = action.ai_create_missing
|
||||
updated_fields: list[str] = []
|
||||
|
||||
def should_set(field: str) -> bool:
|
||||
# The field is selected and (overwrite or it's empty)
|
||||
return field in selected and (
|
||||
overwrite or getattr(document, DIRECT_FIELDS[field]) in (None, "")
|
||||
)
|
||||
|
||||
if should_set(AISuggestionField.TITLE):
|
||||
title = (suggestions.get("title") or "").strip()
|
||||
if title:
|
||||
# title is capped at 128 characters
|
||||
document.title = title[:128]
|
||||
updated_fields.append("title")
|
||||
|
||||
if should_set(AISuggestionField.CORRESPONDENT):
|
||||
names = suggestions.get("correspondents", [])
|
||||
correspondent = resolve_object(
|
||||
Correspondent,
|
||||
names,
|
||||
match_correspondents_by_name(names, owner),
|
||||
create_missing=create_missing,
|
||||
owner=owner,
|
||||
)
|
||||
if correspondent:
|
||||
document.correspondent = correspondent
|
||||
updated_fields.append("correspondent")
|
||||
|
||||
if should_set(AISuggestionField.DOCUMENT_TYPE):
|
||||
names = suggestions.get("document_types", [])
|
||||
document_type = resolve_object(
|
||||
DocumentType,
|
||||
names,
|
||||
match_document_types_by_name(names, owner),
|
||||
create_missing=create_missing,
|
||||
owner=owner,
|
||||
)
|
||||
if document_type:
|
||||
document.document_type = document_type
|
||||
updated_fields.append("document_type")
|
||||
|
||||
if should_set(AISuggestionField.STORAGE_PATH):
|
||||
names = suggestions.get("storage_paths", [])
|
||||
storage_path = resolve_object(
|
||||
StoragePath,
|
||||
names,
|
||||
match_storage_paths_by_name(names, owner),
|
||||
create_missing=create_missing,
|
||||
owner=owner,
|
||||
)
|
||||
if storage_path:
|
||||
document.storage_path = storage_path
|
||||
updated_fields.append("storage_path")
|
||||
|
||||
if should_set(AISuggestionField.CREATED):
|
||||
created = resolve_date(suggestions.get("dates", []))
|
||||
if created:
|
||||
document.created = created
|
||||
updated_fields.append("created")
|
||||
|
||||
if updated_fields:
|
||||
# save fields and update modified
|
||||
document.save(update_fields=[*updated_fields, "modified"])
|
||||
|
||||
if AISuggestionField.TAGS in selected:
|
||||
names = suggestions.get("tags", [])
|
||||
tags = resolve_tags(
|
||||
names,
|
||||
match_tags_by_name(names, owner),
|
||||
create_missing=create_missing,
|
||||
owner=owner,
|
||||
)
|
||||
if tags:
|
||||
# Suggested tags are always added, so overwrite_existing
|
||||
# does not really apply here
|
||||
document.add_nested_tags(tags)
|
||||
updated_fields.append("tags")
|
||||
|
||||
logger.info(
|
||||
"Applied AI suggestions %s to document %s",
|
||||
updated_fields or "(none)",
|
||||
document.pk,
|
||||
extra={"group": logging_group},
|
||||
)
|
||||
|
||||
return updated_fields
|
||||
@@ -2,7 +2,7 @@ msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: paperless-ngx\n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2026-08-10 02:25+0000\n"
|
||||
"POT-Creation-Date: 2026-08-07 20:00+0000\n"
|
||||
"PO-Revision-Date: 2022-02-17 04:17\n"
|
||||
"Last-Translator: \n"
|
||||
"Language-Team: English\n"
|
||||
@@ -21,39 +21,39 @@ msgstr ""
|
||||
msgid "Documents"
|
||||
msgstr ""
|
||||
|
||||
#: documents/filters.py:471
|
||||
#: documents/filters.py:472
|
||||
msgid "Value must be valid JSON."
|
||||
msgstr ""
|
||||
|
||||
#: documents/filters.py:490
|
||||
#: documents/filters.py:491
|
||||
msgid "Invalid custom field query expression"
|
||||
msgstr ""
|
||||
|
||||
#: documents/filters.py:500
|
||||
#: documents/filters.py:501
|
||||
msgid "Invalid expression list. Must be nonempty."
|
||||
msgstr ""
|
||||
|
||||
#: documents/filters.py:521
|
||||
#: documents/filters.py:522
|
||||
msgid "Invalid logical operator {op!r}"
|
||||
msgstr ""
|
||||
|
||||
#: documents/filters.py:535
|
||||
#: documents/filters.py:536
|
||||
msgid "Maximum number of query conditions exceeded."
|
||||
msgstr ""
|
||||
|
||||
#: documents/filters.py:599
|
||||
#: documents/filters.py:600
|
||||
msgid "{name!r} is not a valid custom field."
|
||||
msgstr ""
|
||||
|
||||
#: documents/filters.py:636
|
||||
#: documents/filters.py:637
|
||||
msgid "{data_type} does not support query expr {expr!r}."
|
||||
msgstr ""
|
||||
|
||||
#: documents/filters.py:755 documents/models.py:136
|
||||
#: documents/filters.py:756 documents/models.py:136
|
||||
msgid "Maximum nesting depth exceeded."
|
||||
msgstr ""
|
||||
|
||||
#: documents/filters.py:1079
|
||||
#: documents/filters.py:1098
|
||||
msgid "Custom field not found"
|
||||
msgstr ""
|
||||
|
||||
@@ -1352,7 +1352,7 @@ msgid "workflow runs"
|
||||
msgstr ""
|
||||
|
||||
#: documents/serialisers.py:521 documents/serialisers.py:873
|
||||
#: documents/serialisers.py:2767 documents/views.py:299 documents/views.py:2555
|
||||
#: documents/serialisers.py:2767 documents/views.py:300 documents/views.py:2556
|
||||
#: paperless_mail/serialisers.py:155
|
||||
msgid "Insufficient permissions."
|
||||
msgstr ""
|
||||
@@ -1393,7 +1393,7 @@ msgstr ""
|
||||
msgid "Duplicate document identifiers are not allowed."
|
||||
msgstr ""
|
||||
|
||||
#: documents/serialisers.py:2853 documents/views.py:4509
|
||||
#: documents/serialisers.py:2853 documents/views.py:4510
|
||||
#, python-format
|
||||
msgid "Documents not found: %(ids)s"
|
||||
msgstr ""
|
||||
@@ -1661,36 +1661,36 @@ msgstr ""
|
||||
msgid "Unable to parse URI {value}"
|
||||
msgstr ""
|
||||
|
||||
#: documents/views.py:292 documents/views.py:2552
|
||||
#: documents/views.py:293 documents/views.py:2553
|
||||
msgid "Invalid more_like_id"
|
||||
msgstr ""
|
||||
|
||||
#: documents/views.py:1566
|
||||
#: documents/views.py:1567
|
||||
msgid "Invalid AI configuration."
|
||||
msgstr ""
|
||||
|
||||
#: documents/views.py:1575
|
||||
#: documents/views.py:1576
|
||||
msgid "AI backend request timed out."
|
||||
msgstr ""
|
||||
|
||||
#: documents/views.py:2377 documents/views.py:2698
|
||||
#: documents/views.py:2378 documents/views.py:2699
|
||||
msgid "Specify only one of text, title_search, query, or more_like_id."
|
||||
msgstr ""
|
||||
|
||||
#: documents/views.py:4522
|
||||
#: documents/views.py:4523
|
||||
#, python-format
|
||||
msgid "Insufficient permissions to share document %(id)s."
|
||||
msgstr ""
|
||||
|
||||
#: documents/views.py:4568
|
||||
#: documents/views.py:4569
|
||||
msgid "Bundle is already being processed."
|
||||
msgstr ""
|
||||
|
||||
#: documents/views.py:4629
|
||||
#: documents/views.py:4630
|
||||
msgid "The share link bundle is still being prepared. Please try again later."
|
||||
msgstr ""
|
||||
|
||||
#: documents/views.py:4639
|
||||
#: documents/views.py:4640
|
||||
msgid "The share link bundle is unavailable."
|
||||
msgstr ""
|
||||
|
||||
|
||||
@@ -19,10 +19,7 @@ class AutoLoginMiddleware(MiddlewareMixin):
|
||||
if request.path.startswith("/api/token/") and request.method == "POST":
|
||||
return None
|
||||
try:
|
||||
request.user = User.objects.get(
|
||||
username=settings.AUTO_LOGIN_USERNAME,
|
||||
is_active=True,
|
||||
)
|
||||
request.user = User.objects.get(username=settings.AUTO_LOGIN_USERNAME)
|
||||
auth.login(
|
||||
request=request,
|
||||
user=request.user,
|
||||
|
||||
+3
-17
@@ -339,30 +339,16 @@ def check_deprecated_v2_ocr_env_vars(
|
||||
|
||||
@register()
|
||||
def check_remote_parser_configured(app_configs: Any, **kwargs: Any) -> list[Error]:
|
||||
# Import here because checks.py runs before the app registry is ready
|
||||
from paperless.models import RemoteOCRMode
|
||||
|
||||
errors = []
|
||||
|
||||
if settings.REMOTE_OCR_ENGINE == "azureai" and not (
|
||||
settings.REMOTE_OCR_ENDPOINT and settings.REMOTE_OCR_API_KEY
|
||||
):
|
||||
errors.append(
|
||||
return [
|
||||
Error(
|
||||
"Azure AI remote parser requires endpoint and API key to be configured.",
|
||||
),
|
||||
)
|
||||
]
|
||||
|
||||
valid_modes = {mode.value for mode in RemoteOCRMode}
|
||||
if settings.REMOTE_OCR_MODE not in valid_modes:
|
||||
errors.append(
|
||||
Error(
|
||||
f"PAPERLESS_REMOTE_OCR_MODE is set to {settings.REMOTE_OCR_MODE!r}, "
|
||||
f"expected one of {sorted(valid_modes)}.",
|
||||
),
|
||||
)
|
||||
|
||||
return errors
|
||||
return []
|
||||
|
||||
|
||||
def get_tesseract_langs():
|
||||
|
||||
@@ -9,7 +9,6 @@ from paperless.models import CleanChoices
|
||||
from paperless.models import ColorConvertChoices
|
||||
from paperless.models import ModeChoices
|
||||
from paperless.models import OutputTypeChoices
|
||||
from paperless.models import RemoteOCRMode
|
||||
|
||||
|
||||
@dataclasses.dataclass
|
||||
@@ -186,45 +185,6 @@ class GeneralConfig(BaseConfig):
|
||||
self.app_logo = app_config.app_logo.url if app_config.app_logo else None
|
||||
|
||||
|
||||
@dataclasses.dataclass
|
||||
class RemoteOCRConfig(BaseConfig):
|
||||
"""
|
||||
Settings for the remote (cloud) OCR parser
|
||||
"""
|
||||
|
||||
remote_ocr_engine: str | None = dataclasses.field(init=False)
|
||||
remote_ocr_api_key: str | None = dataclasses.field(init=False)
|
||||
remote_ocr_endpoint: str | None = dataclasses.field(init=False)
|
||||
remote_ocr_mode: RemoteOCRMode = dataclasses.field(init=False)
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
app_config = self._get_config_instance()
|
||||
|
||||
self.remote_ocr_engine = (
|
||||
app_config.remote_ocr_engine or settings.REMOTE_OCR_ENGINE
|
||||
)
|
||||
self.remote_ocr_api_key = (
|
||||
app_config.remote_ocr_api_key or settings.REMOTE_OCR_API_KEY
|
||||
)
|
||||
self.remote_ocr_endpoint = (
|
||||
app_config.remote_ocr_endpoint or settings.REMOTE_OCR_ENDPOINT
|
||||
)
|
||||
self.remote_ocr_mode = app_config.remote_ocr_mode or RemoteOCRMode(
|
||||
settings.REMOTE_OCR_MODE,
|
||||
)
|
||||
|
||||
@property
|
||||
def remote_ocr_by_default(self) -> bool:
|
||||
"""
|
||||
Whether every supported document goes to the remote engine.
|
||||
|
||||
When False the remote engine is used only for documents that
|
||||
explicitly asked for it, i.e. a workflow matched during consumption or
|
||||
the user ticked the box when reprocessing.
|
||||
"""
|
||||
return self.remote_ocr_mode == RemoteOCRMode.ALWAYS
|
||||
|
||||
|
||||
@dataclasses.dataclass
|
||||
class AIConfig(BaseConfig):
|
||||
"""
|
||||
|
||||
@@ -1,44 +0,0 @@
|
||||
# Generated by Django 5.2.16 on 2026-08-10 14:37
|
||||
|
||||
from django.db import migrations
|
||||
from django.db import models
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("paperless", "0013_applicationconfiguration_llm_request_timeout"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.AddField(
|
||||
model_name="applicationconfiguration",
|
||||
name="remote_ocr_api_key",
|
||||
field=models.CharField(
|
||||
blank=True,
|
||||
max_length=1024,
|
||||
null=True,
|
||||
verbose_name="Sets the remote OCR API key",
|
||||
),
|
||||
),
|
||||
migrations.AddField(
|
||||
model_name="applicationconfiguration",
|
||||
name="remote_ocr_endpoint",
|
||||
field=models.CharField(
|
||||
blank=True,
|
||||
max_length=256,
|
||||
null=True,
|
||||
verbose_name="Sets the remote OCR endpoint",
|
||||
),
|
||||
),
|
||||
migrations.AddField(
|
||||
model_name="applicationconfiguration",
|
||||
name="remote_ocr_engine",
|
||||
field=models.CharField(
|
||||
blank=True,
|
||||
choices=[("azureai", "Azure AI Document Intelligence")],
|
||||
max_length=32,
|
||||
null=True,
|
||||
verbose_name="Sets the remote OCR engine",
|
||||
),
|
||||
),
|
||||
]
|
||||
@@ -1,27 +0,0 @@
|
||||
# Generated by Django 5.2.16 on 2026-08-10 15:43
|
||||
|
||||
from django.db import migrations
|
||||
from django.db import models
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("paperless", "0014_applicationconfiguration_remote_ocr_api_key_and_more"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.AddField(
|
||||
model_name="applicationconfiguration",
|
||||
name="remote_ocr_mode",
|
||||
field=models.CharField(
|
||||
blank=True,
|
||||
choices=[
|
||||
("always", "All supported documents"),
|
||||
("workflow_only", "Only when a workflow enables it"),
|
||||
],
|
||||
max_length=32,
|
||||
null=True,
|
||||
verbose_name="Sets which documents are sent to the remote OCR engine",
|
||||
),
|
||||
),
|
||||
]
|
||||
@@ -74,23 +74,6 @@ class ColorConvertChoices(models.TextChoices):
|
||||
CMYK = ("CMYK", _("CMYK"))
|
||||
|
||||
|
||||
class RemoteOCREngine(models.TextChoices):
|
||||
"""
|
||||
Matches to PAPERLESS_REMOTE_OCR_ENGINE
|
||||
"""
|
||||
|
||||
AZURE_AI = ("azureai", _("Azure AI Document Intelligence"))
|
||||
|
||||
|
||||
class RemoteOCRMode(models.TextChoices):
|
||||
"""
|
||||
Matches to PAPERLESS_REMOTE_OCR_MODE
|
||||
"""
|
||||
|
||||
ALWAYS = ("always", _("All supported documents"))
|
||||
WORKFLOW_ONLY = ("workflow_only", _("Only when a workflow enables it"))
|
||||
|
||||
|
||||
class LLMEmbeddingBackend(models.TextChoices):
|
||||
OPENAI_LIKE = ("openai-like", _("OpenAI-compatible"))
|
||||
HUGGINGFACE = ("huggingface", _("Huggingface"))
|
||||
@@ -303,44 +286,6 @@ class ApplicationConfiguration(AbstractSingletonModel):
|
||||
null=True,
|
||||
)
|
||||
|
||||
"""
|
||||
Settings for the remote OCR parser
|
||||
"""
|
||||
|
||||
# PAPERLESS_REMOTE_OCR_ENGINE
|
||||
remote_ocr_engine = models.CharField(
|
||||
verbose_name=_("Sets the remote OCR engine"),
|
||||
blank=True,
|
||||
null=True,
|
||||
max_length=32,
|
||||
choices=RemoteOCREngine.choices,
|
||||
)
|
||||
|
||||
# PAPERLESS_REMOTE_OCR_API_KEY
|
||||
remote_ocr_api_key = models.CharField(
|
||||
verbose_name=_("Sets the remote OCR API key"),
|
||||
blank=True,
|
||||
null=True,
|
||||
max_length=1024,
|
||||
)
|
||||
|
||||
# PAPERLESS_REMOTE_OCR_ENDPOINT
|
||||
remote_ocr_endpoint = models.CharField(
|
||||
verbose_name=_("Sets the remote OCR endpoint"),
|
||||
blank=True,
|
||||
null=True,
|
||||
max_length=256,
|
||||
)
|
||||
|
||||
# PAPERLESS_REMOTE_OCR_MODE
|
||||
remote_ocr_mode = models.CharField(
|
||||
verbose_name=_("Sets which documents are sent to the remote OCR engine"),
|
||||
blank=True,
|
||||
null=True,
|
||||
max_length=32,
|
||||
choices=RemoteOCRMode.choices,
|
||||
)
|
||||
|
||||
"""
|
||||
AI related settings
|
||||
"""
|
||||
|
||||
@@ -134,11 +134,6 @@ class ParserProtocol(Protocol):
|
||||
Author or organisation name.
|
||||
url : str
|
||||
URL for documentation, source code, or issue tracker.
|
||||
|
||||
Parsers that send document content to a remote service should additionally
|
||||
set ``uses_remote_service = True`` so the registry can exclude them when
|
||||
remote processing has not been requested for a document. The attribute is
|
||||
optional so a parser that omits it is treated as fully local.
|
||||
"""
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
@@ -150,10 +145,6 @@ class ParserProtocol(Protocol):
|
||||
author: str
|
||||
url: str
|
||||
|
||||
# NOTE: uses_remote_service is not declared here, the registry reads it
|
||||
# with getattr(cls, ..., False) for backwards-compatibility with existing
|
||||
# parsers
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Class methods
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@@ -334,8 +334,6 @@ class ParserRegistry:
|
||||
mime_type: str,
|
||||
filename: str,
|
||||
path: Path | None = None,
|
||||
*,
|
||||
allow_remote: bool = True,
|
||||
) -> type[ParserProtocol] | None:
|
||||
"""Return the best parser class for the given file, or None.
|
||||
|
||||
@@ -361,11 +359,6 @@ class ParserRegistry:
|
||||
path:
|
||||
Optional filesystem path to the file. Forwarded to each
|
||||
parser's score method.
|
||||
allow_remote:
|
||||
When False, parsers that declare ``uses_remote_service = True``
|
||||
are excluded from consideration, so a document is never sent to
|
||||
a remote service. Parsers that do not declare the attribute
|
||||
are treated as local and are always considered.
|
||||
|
||||
Returns
|
||||
-------
|
||||
@@ -381,13 +374,6 @@ class ParserRegistry:
|
||||
if mime_type not in parser_class.supported_mime_types():
|
||||
continue
|
||||
|
||||
if not allow_remote and getattr(
|
||||
parser_class,
|
||||
"uses_remote_service",
|
||||
False,
|
||||
):
|
||||
continue
|
||||
|
||||
score = parser_class.score(mime_type, filename, path)
|
||||
if score is None:
|
||||
continue
|
||||
|
||||
@@ -57,18 +57,6 @@ class RemoteEngineConfig:
|
||||
self.api_key = api_key
|
||||
self.endpoint = endpoint
|
||||
|
||||
@classmethod
|
||||
def from_app_config(cls) -> Self:
|
||||
"""Build the config from the app config, falling back to the env."""
|
||||
from paperless.config import RemoteOCRConfig
|
||||
|
||||
app_config = RemoteOCRConfig()
|
||||
return cls(
|
||||
engine=app_config.remote_ocr_engine,
|
||||
api_key=app_config.remote_ocr_api_key,
|
||||
endpoint=app_config.remote_ocr_endpoint,
|
||||
)
|
||||
|
||||
def engine_is_valid(self) -> bool:
|
||||
"""Return True when the engine is known and fully configured."""
|
||||
return (
|
||||
@@ -95,9 +83,6 @@ class RemoteDocumentParser:
|
||||
Maintainer name.
|
||||
url : str
|
||||
Issue tracker / source URL.
|
||||
uses_remote_service : bool
|
||||
Content is sent to a remote service, True so that the registry
|
||||
can skip this parser if remote processing was not requested.
|
||||
"""
|
||||
|
||||
name: str = "Paperless-ngx Remote OCR Parser"
|
||||
@@ -105,8 +90,6 @@ class RemoteDocumentParser:
|
||||
author: str = "Paperless-ngx Contributors"
|
||||
url: str = "https://github.com/paperless-ngx/paperless-ngx"
|
||||
|
||||
uses_remote_service: bool = True
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Class methods
|
||||
# ------------------------------------------------------------------
|
||||
@@ -155,7 +138,11 @@ class RemoteDocumentParser:
|
||||
20 when the remote engine is configured and the MIME type is
|
||||
supported, otherwise None.
|
||||
"""
|
||||
config = RemoteEngineConfig.from_app_config()
|
||||
config = RemoteEngineConfig(
|
||||
engine=settings.REMOTE_OCR_ENGINE,
|
||||
api_key=settings.REMOTE_OCR_API_KEY,
|
||||
endpoint=settings.REMOTE_OCR_ENDPOINT,
|
||||
)
|
||||
if not config.engine_is_valid():
|
||||
return None
|
||||
if mime_type not in _SUPPORTED_MIME_TYPES:
|
||||
@@ -241,7 +228,11 @@ class RemoteDocumentParser:
|
||||
Ignored — the remote engine always returns a searchable PDF,
|
||||
which is stored as the archive copy regardless of this flag.
|
||||
"""
|
||||
config = RemoteEngineConfig.from_app_config()
|
||||
config = RemoteEngineConfig(
|
||||
engine=settings.REMOTE_OCR_ENGINE,
|
||||
api_key=settings.REMOTE_OCR_API_KEY,
|
||||
endpoint=settings.REMOTE_OCR_ENDPOINT,
|
||||
)
|
||||
|
||||
if not config.engine_is_valid():
|
||||
logger.warning(
|
||||
|
||||
@@ -217,15 +217,7 @@ class ApplicationConfigurationSerializer(
|
||||
llm_api_key = ObfuscatedPasswordField(
|
||||
required=False,
|
||||
allow_null=True,
|
||||
max_length=1024,
|
||||
)
|
||||
remote_ocr_api_key = ObfuscatedPasswordField(
|
||||
required=False,
|
||||
allow_null=True,
|
||||
max_length=1024,
|
||||
)
|
||||
|
||||
OBFUSCATED_FIELDS = ("llm_api_key", "remote_ocr_api_key")
|
||||
|
||||
def run_validation(self, data):
|
||||
# Empty strings treated as None to avoid unexpected behavior
|
||||
@@ -237,13 +229,11 @@ class ApplicationConfigurationSerializer(
|
||||
data["language"] = None
|
||||
if "llm_output_language" in data and data["llm_output_language"] == "":
|
||||
data["llm_output_language"] = None
|
||||
for field in self.OBFUSCATED_FIELDS:
|
||||
if field in data and data[field] is not None:
|
||||
if data[field] == "":
|
||||
data[field] = None
|
||||
# Not a real value, don't overwrite the stored one
|
||||
elif len(data[field].replace("*", "")) == 0:
|
||||
del data[field]
|
||||
if "llm_api_key" in data and data["llm_api_key"] is not None:
|
||||
if data["llm_api_key"] == "":
|
||||
data["llm_api_key"] = None
|
||||
elif len(data["llm_api_key"].replace("*", "")) == 0:
|
||||
del data["llm_api_key"]
|
||||
return super().run_validation(data)
|
||||
|
||||
def update(self, instance, validated_data):
|
||||
|
||||
@@ -1197,7 +1197,6 @@ WEBHOOKS_ALLOW_INTERNAL_REQUESTS = get_bool_from_env(
|
||||
REMOTE_OCR_ENGINE = os.getenv("PAPERLESS_REMOTE_OCR_ENGINE")
|
||||
REMOTE_OCR_API_KEY = os.getenv("PAPERLESS_REMOTE_OCR_API_KEY")
|
||||
REMOTE_OCR_ENDPOINT = os.getenv("PAPERLESS_REMOTE_OCR_ENDPOINT")
|
||||
REMOTE_OCR_MODE = os.getenv("PAPERLESS_REMOTE_OCR_MODE", "always")
|
||||
|
||||
################################################################################
|
||||
# AI Settings #
|
||||
|
||||
@@ -21,7 +21,6 @@ from unittest.mock import Mock
|
||||
import pytest
|
||||
|
||||
from documents.parsers import ParseError
|
||||
from paperless.models import ApplicationConfiguration
|
||||
from paperless.parsers import ParserContext
|
||||
from paperless.parsers import ParserProtocol
|
||||
from paperless.parsers.remote import RemoteDocumentParser
|
||||
@@ -34,10 +33,6 @@ if TYPE_CHECKING:
|
||||
from pytest_mock import MockerFixture
|
||||
|
||||
|
||||
# Remote ocr config from ApplicationConfiguration needs DB access
|
||||
pytestmark = pytest.mark.django_db
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Module-local fixtures
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -232,18 +227,6 @@ class TestRemoteParserScore:
|
||||
score = RemoteDocumentParser.score("application/pdf", "doc.pdf")
|
||||
assert score is not None and score > 10
|
||||
|
||||
@pytest.mark.usefixtures("no_engine_settings")
|
||||
def test_score_uses_app_config_when_env_unset(self) -> None:
|
||||
"""The app config alone is enough to activate the parser."""
|
||||
config = ApplicationConfiguration.objects.first()
|
||||
assert config is not None
|
||||
config.remote_ocr_engine = "azureai"
|
||||
config.remote_ocr_api_key = "app-config-key"
|
||||
config.remote_ocr_endpoint = "https://config.cognitiveservices.azure.com"
|
||||
config.save()
|
||||
|
||||
assert RemoteDocumentParser.score("application/pdf", "doc.pdf") == 20
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Properties
|
||||
|
||||
@@ -1277,8 +1277,6 @@ class TestParserFileTypes:
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
# Remote ocr config from ApplicationConfiguration needs DB access
|
||||
@pytest.mark.django_db
|
||||
class TestRasterisedDocumentParserRegistry:
|
||||
def test_registered_in_defaults(self) -> None:
|
||||
from paperless.parsers.registry import ParserRegistry
|
||||
|
||||
@@ -1,53 +0,0 @@
|
||||
from django.contrib.auth.models import AnonymousUser
|
||||
from django.contrib.auth.models import User
|
||||
from django.test import RequestFactory
|
||||
from django.test import TestCase
|
||||
from django.test import override_settings
|
||||
|
||||
from paperless.auth import AutoLoginMiddleware
|
||||
|
||||
|
||||
@override_settings(AUTO_LOGIN_USERNAME="autologin")
|
||||
class TestAutoLoginMiddleware(TestCase):
|
||||
def setUp(self) -> None:
|
||||
super().setUp()
|
||||
self.factory = RequestFactory()
|
||||
self.middleware = AutoLoginMiddleware(lambda request: None)
|
||||
|
||||
def _process(self, request):
|
||||
# login() needs a session to write to
|
||||
request.session = self.client.session
|
||||
self.middleware.process_request(request)
|
||||
return request
|
||||
|
||||
def test_active_user_is_logged_in(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- AUTO_LOGIN_USERNAME names an active user
|
||||
WHEN:
|
||||
- A request is processed by the middleware
|
||||
THEN:
|
||||
- That user is attached to the request
|
||||
"""
|
||||
user = User.objects.create_user(username="autologin")
|
||||
|
||||
request = self._process(self.factory.get("/"))
|
||||
|
||||
self.assertEqual(request.user, user)
|
||||
|
||||
def test_deactivated_user_is_not_logged_in(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- AUTO_LOGIN_USERNAME names a user who has been deactivated
|
||||
WHEN:
|
||||
- A request is processed by the middleware
|
||||
THEN:
|
||||
- The request is left anonymous rather than authenticated as them
|
||||
"""
|
||||
User.objects.create_user(username="autologin", is_active=False)
|
||||
|
||||
request = self.factory.get("/")
|
||||
request.user = AnonymousUser()
|
||||
self._process(request)
|
||||
|
||||
self.assertFalse(request.user.is_authenticated)
|
||||
@@ -655,23 +655,6 @@ class TestRemoteParserChecks:
|
||||
in msg.msg
|
||||
)
|
||||
|
||||
def test_valid_mode(self, settings: SettingsWrapper) -> None:
|
||||
settings.REMOTE_OCR_ENGINE = None
|
||||
settings.REMOTE_OCR_MODE = "workflow_only"
|
||||
|
||||
msgs = check_remote_parser_configured(None)
|
||||
|
||||
assert len(msgs) == 0
|
||||
|
||||
def test_invalid_mode(self, settings: SettingsWrapper) -> None:
|
||||
settings.REMOTE_OCR_ENGINE = None
|
||||
settings.REMOTE_OCR_MODE = "sometimes"
|
||||
|
||||
msgs = check_remote_parser_configured(None)
|
||||
|
||||
assert len(msgs) == 1
|
||||
assert "PAPERLESS_REMOTE_OCR_MODE is set to 'sometimes'" in msgs[0].msg
|
||||
|
||||
|
||||
class TestTesseractChecks:
|
||||
def test_default_language(self) -> None:
|
||||
|
||||
@@ -468,124 +468,6 @@ class TestParserRegistryGetParserForFile:
|
||||
assert result is AcceptingBuiltin
|
||||
|
||||
|
||||
class TestParserRegistryRemoteParsers:
|
||||
"""Verify the allow_remote filter in ParserRegistry.get_parser_for_file()."""
|
||||
|
||||
@staticmethod
|
||||
def _remote_parser_cls() -> type:
|
||||
class RemoteParser:
|
||||
name = "remote"
|
||||
version = "1.0"
|
||||
author = "A"
|
||||
url = "https://example.com/remote"
|
||||
uses_remote_service = True
|
||||
|
||||
@classmethod
|
||||
def supported_mime_types(cls):
|
||||
return {"text/plain": ".txt"}
|
||||
|
||||
@classmethod
|
||||
def score(cls, mime_type, filename, path=None):
|
||||
return 20
|
||||
|
||||
return RemoteParser
|
||||
|
||||
def test_remote_parser_wins_when_remote_allowed(
|
||||
self,
|
||||
dummy_parser_cls: type,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: A remote parser scoring 20 and a local parser scoring 10.
|
||||
WHEN: get_parser_for_file() is called with allow_remote=True.
|
||||
THEN: The remote parser is returned.
|
||||
"""
|
||||
remote_parser_cls = self._remote_parser_cls()
|
||||
registry = ParserRegistry()
|
||||
registry.register_builtin(dummy_parser_cls)
|
||||
registry.register_builtin(remote_parser_cls)
|
||||
|
||||
result = registry.get_parser_for_file(
|
||||
"text/plain",
|
||||
"readme.txt",
|
||||
allow_remote=True,
|
||||
)
|
||||
assert result is remote_parser_cls
|
||||
|
||||
def test_remote_parser_skipped_when_remote_not_allowed(
|
||||
self,
|
||||
dummy_parser_cls: type,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: A remote parser scoring 20 and a local parser scoring 10.
|
||||
WHEN: get_parser_for_file() is called with allow_remote=False.
|
||||
THEN: The local parser is returned despite its lower score.
|
||||
"""
|
||||
registry = ParserRegistry()
|
||||
registry.register_builtin(dummy_parser_cls)
|
||||
registry.register_builtin(self._remote_parser_cls())
|
||||
|
||||
result = registry.get_parser_for_file(
|
||||
"text/plain",
|
||||
"readme.txt",
|
||||
allow_remote=False,
|
||||
)
|
||||
assert result is dummy_parser_cls
|
||||
|
||||
def test_no_parser_when_only_remote_available_and_not_allowed(self) -> None:
|
||||
"""
|
||||
GIVEN: A registry whose only candidate declares uses_remote_service.
|
||||
WHEN: get_parser_for_file() is called with allow_remote=False.
|
||||
THEN: None is returned — the remote parser is never used as a
|
||||
fallback when remote processing was not requested.
|
||||
"""
|
||||
registry = ParserRegistry()
|
||||
registry.register_builtin(self._remote_parser_cls())
|
||||
|
||||
result = registry.get_parser_for_file(
|
||||
"text/plain",
|
||||
"readme.txt",
|
||||
allow_remote=False,
|
||||
)
|
||||
assert result is None
|
||||
|
||||
def test_parser_without_attribute_treated_as_local(
|
||||
self,
|
||||
dummy_parser_cls: type,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN: A third-party parser predating uses_remote_service, so it does
|
||||
not declare the attribute at all.
|
||||
WHEN: get_parser_for_file() is called with allow_remote=False.
|
||||
THEN: It is still considered, i.e. treated as fully local, rather
|
||||
than raising AttributeError.
|
||||
"""
|
||||
assert not hasattr(dummy_parser_cls, "uses_remote_service")
|
||||
|
||||
registry = ParserRegistry()
|
||||
registry.register_builtin(dummy_parser_cls)
|
||||
|
||||
result = registry.get_parser_for_file(
|
||||
"text/plain",
|
||||
"readme.txt",
|
||||
allow_remote=False,
|
||||
)
|
||||
assert result is dummy_parser_cls
|
||||
|
||||
def test_remote_allowed_by_default(self) -> None:
|
||||
"""
|
||||
GIVEN: A registry containing only a remote parser.
|
||||
WHEN: get_parser_for_file() is called without allow_remote.
|
||||
THEN: The remote parser is returned — callers that do not opt in to
|
||||
the filter keep the previous behaviour.
|
||||
"""
|
||||
remote_parser_cls = self._remote_parser_cls()
|
||||
registry = ParserRegistry()
|
||||
registry.register_builtin(remote_parser_cls)
|
||||
|
||||
result = registry.get_parser_for_file("text/plain", "readme.txt")
|
||||
assert result is remote_parser_cls
|
||||
|
||||
|
||||
class TestDiscover:
|
||||
"""Verify entrypoint discovery in ParserRegistry.discover()."""
|
||||
|
||||
|
||||
@@ -1,113 +0,0 @@
|
||||
"""Tests for RemoteOCRConfig precedence between app config and Django settings."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import pytest
|
||||
from django.test import override_settings
|
||||
|
||||
from paperless.config import RemoteOCRConfig
|
||||
from paperless.models import RemoteOCRMode
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def null_app_config(mocker) -> MagicMock:
|
||||
"""Mock ApplicationConfiguration with all fields None → falls back to Django settings."""
|
||||
return mocker.MagicMock(
|
||||
remote_ocr_engine=None,
|
||||
remote_ocr_api_key=None,
|
||||
remote_ocr_endpoint=None,
|
||||
remote_ocr_mode=None,
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def make_remote_ocr_config(mocker):
|
||||
def _make(app_config, **django_settings_overrides):
|
||||
mocker.patch(
|
||||
"paperless.config.BaseConfig._get_config_instance",
|
||||
return_value=app_config,
|
||||
)
|
||||
with override_settings(**django_settings_overrides):
|
||||
return RemoteOCRConfig()
|
||||
|
||||
return _make
|
||||
|
||||
|
||||
class TestRemoteOCRConfig:
|
||||
def test_falls_back_to_settings(
|
||||
self,
|
||||
make_remote_ocr_config,
|
||||
null_app_config,
|
||||
) -> None:
|
||||
cfg = make_remote_ocr_config(
|
||||
null_app_config,
|
||||
REMOTE_OCR_ENGINE="azureai",
|
||||
REMOTE_OCR_API_KEY="env-key",
|
||||
REMOTE_OCR_ENDPOINT="https://env.cognitiveservices.azure.com",
|
||||
REMOTE_OCR_MODE=RemoteOCRMode.WORKFLOW_ONLY,
|
||||
)
|
||||
assert cfg.remote_ocr_engine == "azureai"
|
||||
assert cfg.remote_ocr_api_key == "env-key"
|
||||
assert cfg.remote_ocr_endpoint == "https://env.cognitiveservices.azure.com"
|
||||
assert cfg.remote_ocr_mode == RemoteOCRMode.WORKFLOW_ONLY
|
||||
|
||||
def test_app_config_takes_precedence(
|
||||
self,
|
||||
make_remote_ocr_config,
|
||||
mocker,
|
||||
) -> None:
|
||||
app_config = mocker.MagicMock(
|
||||
remote_ocr_engine="azureai",
|
||||
remote_ocr_api_key="db-key",
|
||||
remote_ocr_endpoint="https://db.cognitiveservices.azure.com",
|
||||
remote_ocr_mode=RemoteOCRMode.WORKFLOW_ONLY,
|
||||
)
|
||||
cfg = make_remote_ocr_config(
|
||||
app_config,
|
||||
REMOTE_OCR_ENGINE=None,
|
||||
REMOTE_OCR_API_KEY="env-key",
|
||||
REMOTE_OCR_ENDPOINT="https://env.cognitiveservices.azure.com",
|
||||
REMOTE_OCR_MODE=RemoteOCRMode.ALWAYS,
|
||||
)
|
||||
assert cfg.remote_ocr_engine == "azureai"
|
||||
assert cfg.remote_ocr_api_key == "db-key"
|
||||
assert cfg.remote_ocr_endpoint == "https://db.cognitiveservices.azure.com"
|
||||
assert cfg.remote_ocr_mode == RemoteOCRMode.WORKFLOW_ONLY
|
||||
|
||||
def test_unset_everywhere(
|
||||
self,
|
||||
make_remote_ocr_config,
|
||||
null_app_config,
|
||||
) -> None:
|
||||
cfg = make_remote_ocr_config(
|
||||
null_app_config,
|
||||
REMOTE_OCR_ENGINE=None,
|
||||
REMOTE_OCR_API_KEY=None,
|
||||
REMOTE_OCR_ENDPOINT=None,
|
||||
)
|
||||
assert cfg.remote_ocr_engine is None
|
||||
assert cfg.remote_ocr_api_key is None
|
||||
assert cfg.remote_ocr_endpoint is None
|
||||
|
||||
|
||||
class TestRemoteOCRByDefault:
|
||||
def test_always_mode(self, make_remote_ocr_config, null_app_config) -> None:
|
||||
cfg = make_remote_ocr_config(
|
||||
null_app_config,
|
||||
REMOTE_OCR_MODE=RemoteOCRMode.ALWAYS,
|
||||
)
|
||||
|
||||
assert cfg.remote_ocr_by_default is True
|
||||
|
||||
def test_workflow_only_mode(self, make_remote_ocr_config, null_app_config) -> None:
|
||||
cfg = make_remote_ocr_config(
|
||||
null_app_config,
|
||||
REMOTE_OCR_MODE=RemoteOCRMode.WORKFLOW_ONLY,
|
||||
)
|
||||
|
||||
assert cfg.remote_ocr_by_default is False
|
||||
@@ -27,6 +27,7 @@ from documents.views import EditPdfDocumentsView
|
||||
from documents.views import GlobalSearchView
|
||||
from documents.views import IndexView
|
||||
from documents.views import LogViewSet
|
||||
from documents.views import MergeDocumentsAsVersionsView
|
||||
from documents.views import MergeDocumentsView
|
||||
from documents.views import PostDocumentView
|
||||
from documents.views import RemoteVersionView
|
||||
@@ -172,6 +173,11 @@ urlpatterns = [
|
||||
MergeDocumentsView.as_view(),
|
||||
name="merge_documents",
|
||||
),
|
||||
re_path(
|
||||
"^merge_as_versions/",
|
||||
MergeDocumentsAsVersionsView.as_view(),
|
||||
name="merge_documents_as_versions",
|
||||
),
|
||||
re_path(
|
||||
"^edit_pdf/",
|
||||
EditPdfDocumentsView.as_view(),
|
||||
|
||||
@@ -23,22 +23,6 @@ def get_language_name(language_code: str) -> str:
|
||||
return language_code
|
||||
|
||||
|
||||
def get_llm_output_language(ai_config: AIConfig, user: User | None) -> str | None:
|
||||
"""
|
||||
Language to localize LLM output into: the configured language, falling back
|
||||
to the user's own UI language when unset.
|
||||
"""
|
||||
output_language = ai_config.llm_output_language
|
||||
if (
|
||||
not output_language
|
||||
and user is not None
|
||||
and hasattr(user, "ui_settings")
|
||||
and isinstance(user.ui_settings.settings, dict)
|
||||
):
|
||||
output_language = user.ui_settings.settings.get("language")
|
||||
return output_language
|
||||
|
||||
|
||||
def build_prompt_without_rag(
|
||||
document: Document,
|
||||
config: AIConfig,
|
||||
|
||||
@@ -8,48 +8,45 @@ from documents.models import Correspondent
|
||||
from documents.models import DocumentType
|
||||
from documents.models import StoragePath
|
||||
from documents.models import Tag
|
||||
from documents.permissions import permitted_object_ids
|
||||
from documents.permissions import get_objects_for_user_owner_aware
|
||||
|
||||
MATCH_THRESHOLD = 0.8
|
||||
|
||||
logger = logging.getLogger("paperless_ai.matching")
|
||||
|
||||
# Note: with a None user, e.g. a workflow acting on an unowned document,
|
||||
# permitted_object_ids returns unowned objects only, so it won't return
|
||||
# someone's private tag.
|
||||
|
||||
|
||||
def match_tags_by_name(names: list[str], user: User | None) -> list[Tag]:
|
||||
queryset = Tag.objects.filter(id__in=permitted_object_ids(user, Tag, "view_tag"))
|
||||
return _match_names_to_queryset(names, queryset, "name")
|
||||
|
||||
|
||||
def match_correspondents_by_name(
|
||||
names: list[str],
|
||||
user: User | None,
|
||||
) -> list[Correspondent]:
|
||||
queryset = Correspondent.objects.filter(
|
||||
id__in=permitted_object_ids(user, Correspondent, "view_correspondent"),
|
||||
def match_tags_by_name(names: list[str], user: User) -> list[Tag]:
|
||||
queryset = get_objects_for_user_owner_aware(
|
||||
user,
|
||||
["view_tag"],
|
||||
Tag,
|
||||
)
|
||||
return _match_names_to_queryset(names, queryset, "name")
|
||||
|
||||
|
||||
def match_document_types_by_name(
|
||||
names: list[str],
|
||||
user: User | None,
|
||||
) -> list[DocumentType]:
|
||||
queryset = DocumentType.objects.filter(
|
||||
id__in=permitted_object_ids(user, DocumentType, "view_documenttype"),
|
||||
def match_correspondents_by_name(names: list[str], user: User) -> list[Correspondent]:
|
||||
queryset = get_objects_for_user_owner_aware(
|
||||
user,
|
||||
["view_correspondent"],
|
||||
Correspondent,
|
||||
)
|
||||
return _match_names_to_queryset(names, queryset, "name")
|
||||
|
||||
|
||||
def match_storage_paths_by_name(
|
||||
names: list[str],
|
||||
user: User | None,
|
||||
) -> list[StoragePath]:
|
||||
queryset = StoragePath.objects.filter(
|
||||
id__in=permitted_object_ids(user, StoragePath, "view_storagepath"),
|
||||
def match_document_types_by_name(names: list[str], user: User) -> list[DocumentType]:
|
||||
queryset = get_objects_for_user_owner_aware(
|
||||
user,
|
||||
["view_documenttype"],
|
||||
DocumentType,
|
||||
)
|
||||
return _match_names_to_queryset(names, queryset, "name")
|
||||
|
||||
|
||||
def match_storage_paths_by_name(names: list[str], user: User) -> list[StoragePath]:
|
||||
queryset = get_objects_for_user_owner_aware(
|
||||
user,
|
||||
["view_storagepath"],
|
||||
StoragePath,
|
||||
)
|
||||
return _match_names_to_queryset(names, queryset, "name")
|
||||
|
||||
|
||||
@@ -1,3 +1,5 @@
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
from django.test import TestCase
|
||||
|
||||
@@ -30,25 +32,33 @@ class TestAIMatching(TestCase):
|
||||
self.storage_path1 = StoragePath.objects.create(name="Test Storage Path 1")
|
||||
self.storage_path2 = StoragePath.objects.create(name="Test Storage Path 2")
|
||||
|
||||
def test_match_tags_by_name(self) -> None:
|
||||
@patch("paperless_ai.matching.get_objects_for_user_owner_aware")
|
||||
def test_match_tags_by_name(self, mock_get_objects) -> None:
|
||||
mock_get_objects.return_value = Tag.objects.all()
|
||||
names = ["Test Tag 1", "Nonexistent Tag"]
|
||||
result = match_tags_by_name(names, user=None)
|
||||
self.assertEqual(len(result), 1)
|
||||
self.assertEqual(result[0].name, "Test Tag 1")
|
||||
|
||||
def test_match_correspondents_by_name(self) -> None:
|
||||
@patch("paperless_ai.matching.get_objects_for_user_owner_aware")
|
||||
def test_match_correspondents_by_name(self, mock_get_objects) -> None:
|
||||
mock_get_objects.return_value = Correspondent.objects.all()
|
||||
names = ["Test Correspondent 1", "Nonexistent Correspondent"]
|
||||
result = match_correspondents_by_name(names, user=None)
|
||||
self.assertEqual(len(result), 1)
|
||||
self.assertEqual(result[0].name, "Test Correspondent 1")
|
||||
|
||||
def test_match_document_types_by_name(self) -> None:
|
||||
@patch("paperless_ai.matching.get_objects_for_user_owner_aware")
|
||||
def test_match_document_types_by_name(self, mock_get_objects) -> None:
|
||||
mock_get_objects.return_value = DocumentType.objects.all()
|
||||
names = ["Test Document Type 1", "Nonexistent Document Type"]
|
||||
result = match_document_types_by_name(names, user=None)
|
||||
self.assertEqual(len(result), 1)
|
||||
self.assertEqual(result[0].name, "Test Document Type 1")
|
||||
|
||||
def test_match_storage_paths_by_name(self) -> None:
|
||||
@patch("paperless_ai.matching.get_objects_for_user_owner_aware")
|
||||
def test_match_storage_paths_by_name(self, mock_get_objects) -> None:
|
||||
mock_get_objects.return_value = StoragePath.objects.all()
|
||||
names = ["Test Storage Path 1", "Nonexistent Storage Path"]
|
||||
result = match_storage_paths_by_name(names, user=None)
|
||||
self.assertEqual(len(result), 1)
|
||||
@@ -60,12 +70,16 @@ class TestAIMatching(TestCase):
|
||||
unmatched_names = extract_unmatched_names(llm_names, matched_objects)
|
||||
self.assertEqual(unmatched_names, ["Nonexistent Tag"])
|
||||
|
||||
def test_match_tags_by_name_with_empty_names(self) -> None:
|
||||
@patch("paperless_ai.matching.get_objects_for_user_owner_aware")
|
||||
def test_match_tags_by_name_with_empty_names(self, mock_get_objects) -> None:
|
||||
mock_get_objects.return_value = Tag.objects.all()
|
||||
names = [None, "", " "]
|
||||
result = match_tags_by_name(names, user=None)
|
||||
self.assertEqual(result, [])
|
||||
|
||||
def test_match_tags_with_fuzzy_matching(self) -> None:
|
||||
@patch("paperless_ai.matching.get_objects_for_user_owner_aware")
|
||||
def test_match_tags_with_fuzzy_matching(self, mock_get_objects) -> None:
|
||||
mock_get_objects.return_value = Tag.objects.all()
|
||||
names = ["Test Taag 1", "Teest Tag 2"]
|
||||
result = match_tags_by_name(names, user=None)
|
||||
self.assertEqual(len(result), 2)
|
||||
|
||||
@@ -757,30 +757,3 @@ class TestAPIProcessedMails(DirectoriesMixin, APITestCase):
|
||||
format="json",
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
|
||||
|
||||
def test_bulk_delete_processed_mails_rejects_mixed_batch_atomically(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A permitted processed mail and one the user may not delete
|
||||
WHEN:
|
||||
- API call bulk deletes both in a single request
|
||||
THEN:
|
||||
- The request is rejected and neither mail is deleted
|
||||
"""
|
||||
user2 = User.objects.create_user(username="temp_admin2")
|
||||
rule = MailRuleFactory()
|
||||
# Created first so it sorts ahead of the forbidden mail, i.e. the
|
||||
# permission check has to cover the whole batch before deleting rather
|
||||
# than rejecting only once it reaches the forbidden one.
|
||||
pm_owned = ProcessedMailFactory(rule=rule, owner=self.user)
|
||||
pm_forbidden = ProcessedMailFactory(rule=rule, owner=user2)
|
||||
|
||||
response = self.client.post(
|
||||
f"{self.ENDPOINT}bulk_delete/",
|
||||
data={"mail_ids": [pm_owned.id, pm_forbidden.id]},
|
||||
format="json",
|
||||
)
|
||||
|
||||
self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
|
||||
self.assertTrue(ProcessedMail.objects.filter(id=pm_owned.id).exists())
|
||||
self.assertTrue(ProcessedMail.objects.filter(id=pm_forbidden.id).exists())
|
||||
|
||||
@@ -23,11 +23,10 @@ from rest_framework.response import Response
|
||||
from rest_framework.viewsets import ModelViewSet
|
||||
from rest_framework.viewsets import ReadOnlyModelViewSet
|
||||
|
||||
from documents.filters import PermittedObjectsFilter
|
||||
from documents.filters import ObjectOwnedOrGrantedPermissionsFilter
|
||||
from documents.models import PaperlessTask
|
||||
from documents.permissions import PaperlessObjectPermissions
|
||||
from documents.permissions import has_perms_owner_aware
|
||||
from documents.permissions import permitted_object_ids
|
||||
from documents.views import PassUserMixin
|
||||
from paperless.views import StandardPagination
|
||||
from paperless_mail.filters import ProcessedMailFilterSet
|
||||
@@ -76,7 +75,7 @@ class MailAccountViewSet(PassUserMixin, ModelViewSet[MailAccount]):
|
||||
serializer_class = MailAccountSerializer
|
||||
pagination_class = StandardPagination
|
||||
permission_classes = (IsAuthenticated, PaperlessObjectPermissions)
|
||||
filter_backends = (PermittedObjectsFilter,)
|
||||
filter_backends = (ObjectOwnedOrGrantedPermissionsFilter,)
|
||||
|
||||
def get_permissions(self):
|
||||
if self.action == "test":
|
||||
@@ -198,7 +197,7 @@ class ProcessedMailViewSet(PassUserMixin, ReadOnlyModelViewSet[ProcessedMail]):
|
||||
filter_backends = (
|
||||
DjangoFilterBackend,
|
||||
OrderingFilter,
|
||||
PermittedObjectsFilter,
|
||||
ObjectOwnedOrGrantedPermissionsFilter,
|
||||
)
|
||||
filterset_class = ProcessedMailFilterSet
|
||||
|
||||
@@ -212,17 +211,10 @@ class ProcessedMailViewSet(PassUserMixin, ReadOnlyModelViewSet[ProcessedMail]):
|
||||
):
|
||||
return HttpResponseBadRequest("mail_ids must be a list of integers")
|
||||
mails = ProcessedMail.objects.filter(id__in=mail_ids)
|
||||
# Check every id up front so an unpermitted one rejects the whole
|
||||
# request rather than deleting the mails ahead of it first.
|
||||
if mails.exclude(
|
||||
pk__in=permitted_object_ids(
|
||||
request.user,
|
||||
ProcessedMail,
|
||||
"delete_processedmail",
|
||||
),
|
||||
).exists():
|
||||
return HttpResponseForbidden("Insufficient permissions")
|
||||
mails.delete()
|
||||
for mail in mails:
|
||||
if not has_perms_owner_aware(request.user, "delete_processedmail", mail):
|
||||
return HttpResponseForbidden("Insufficient permissions")
|
||||
mail.delete()
|
||||
return Response({"result": "OK", "deleted_mail_ids": mail_ids})
|
||||
|
||||
|
||||
@@ -233,7 +225,7 @@ class MailRuleViewSet(PassUserMixin, ModelViewSet[MailRule]):
|
||||
serializer_class = MailRuleSerializer
|
||||
pagination_class = StandardPagination
|
||||
permission_classes = (IsAuthenticated, PaperlessObjectPermissions)
|
||||
filter_backends = (PermittedObjectsFilter,)
|
||||
filter_backends = (ObjectOwnedOrGrantedPermissionsFilter,)
|
||||
|
||||
|
||||
@extend_schema_view(
|
||||
|
||||
Reference in New Issue
Block a user