mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2025-10-10 02:16:12 -05:00
Compare commits
47 Commits
dependabot
...
feature-re
| Author | SHA1 | Date | |
|---|---|---|---|
|
9f8090816f | ||
|
|
495159f0b2 | ||
|
|
33fd8a6579 | ||
|
|
e08e34fb90 | ||
|
|
6164bac66e | ||
|
|
df86882e8e | ||
|
|
1de7c52478 | ||
|
|
9aaaa6f069 | ||
|
|
c3a20b7797 | ||
|
|
476556379b | ||
|
|
e5cafff043 | ||
|
|
8e0d574e99 | ||
|
|
8a5820328e | ||
|
|
809d62a2f4 | ||
|
|
0d87f94b9b | ||
|
|
315b90f8e5 | ||
|
|
47b2d2964b | ||
|
|
e05639ae4e | ||
|
|
f400a8cb2f | ||
|
|
26abcf5612 | ||
|
|
afde52430d | ||
|
|
716f2da652 | ||
|
|
c54073b7c2 | ||
|
|
247e6f39dc | ||
|
|
1e6dfc4481 | ||
|
|
7cc0750066 | ||
|
|
bd6585d3b4 | ||
|
|
717e828a1d | ||
|
|
07381d48e6 | ||
|
|
dd0ffaf312 | ||
|
|
264504affc | ||
|
|
4feedf2add | ||
|
|
2f76cf9831 | ||
|
|
1002d37f6b | ||
|
|
d260a94740 | ||
|
|
88c69b83ea | ||
|
|
2557ee2014 | ||
|
|
3c75deed80 | ||
|
|
d05343c927 | ||
|
|
e7972b7eaf | ||
|
|
75a091cc0d | ||
|
|
dca74803fd | ||
|
|
3cf3d868d0 | ||
|
|
bf4fc6604a | ||
|
|
e8c1eb86fa | ||
|
|
c3dad3cf69 | ||
|
|
811bd66088 |
@@ -1805,3 +1805,23 @@ password. All of these options come from their similarly-named [Django settings]
|
||||
#### [`PAPERLESS_EMAIL_USE_SSL=<bool>`](#PAPERLESS_EMAIL_USE_SSL) {#PAPERLESS_EMAIL_USE_SSL}
|
||||
|
||||
: Defaults to false.
|
||||
|
||||
## Remote OCR
|
||||
|
||||
#### [`PAPERLESS_REMOTE_OCR_ENGINE=<str>`](#PAPERLESS_REMOTE_OCR_ENGINE) {#PAPERLESS_REMOTE_OCR_ENGINE}
|
||||
|
||||
: The remote OCR engine to use. Currently only Azure AI is supported as "azureai".
|
||||
|
||||
Defaults to None, which disables remote OCR.
|
||||
|
||||
#### [`PAPERLESS_REMOTE_OCR_API_KEY=<str>`](#PAPERLESS_REMOTE_OCR_API_KEY) {#PAPERLESS_REMOTE_OCR_API_KEY}
|
||||
|
||||
: The API key to use for the remote OCR engine.
|
||||
|
||||
Defaults to None.
|
||||
|
||||
#### [`PAPERLESS_REMOTE_OCR_ENDPOINT=<str>`](#PAPERLESS_REMOTE_OCR_ENDPOINT) {#PAPERLESS_REMOTE_OCR_ENDPOINT}
|
||||
|
||||
: The endpoint to use for the remote OCR engine. This is required for Azure AI.
|
||||
|
||||
Defaults to None.
|
||||
|
||||
@@ -25,9 +25,10 @@ physical documents into a searchable online archive so you can keep, well, _less
|
||||
## Features
|
||||
|
||||
- **Organize and index** your scanned documents with tags, correspondents, types, and more.
|
||||
- _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way.
|
||||
- _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way, unless you explicitly choose to do so.
|
||||
- Performs **OCR** on your documents, adding searchable and selectable text, even to documents scanned with only images.
|
||||
- Utilizes the open-source Tesseract engine to recognize more than 100 languages.
|
||||
- _New!_ Supports remote OCR with Azure AI (opt-in).
|
||||
- Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals.
|
||||
- Uses machine-learning to automatically add tags, correspondents and document types to your documents.
|
||||
- Supports PDF documents, images, plain text files, Office documents (Word, Excel, PowerPoint, and LibreOffice equivalents)[^1] and more.
|
||||
|
||||
@@ -882,6 +882,21 @@ how regularly you intend to scan documents and use paperless.
|
||||
performed the task associated with the document, move it to the
|
||||
inbox.
|
||||
|
||||
## Remote OCR
|
||||
|
||||
!!! important
|
||||
|
||||
This feature is disabled by default and will always remain strictly "opt-in".
|
||||
|
||||
Paperless-ngx supports performing OCR on documents using remote services. At the moment, this is limited to
|
||||
[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.
|
||||
|
||||
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).
|
||||
|
||||
## Architecture
|
||||
|
||||
Paperless-ngx consists of the following components:
|
||||
|
||||
@@ -15,6 +15,7 @@ classifiers = [
|
||||
# This will allow testing to not install a webserver, mysql, etc
|
||||
|
||||
dependencies = [
|
||||
"azure-ai-documentintelligence>=1.0.2",
|
||||
"babel>=2.17",
|
||||
"bleach~=6.2.0",
|
||||
"celery[redis]~=5.5.1",
|
||||
@@ -26,7 +27,7 @@ dependencies = [
|
||||
# Only patch versions are guaranteed to not introduce breaking changes.
|
||||
"django~=5.2.5",
|
||||
"django-allauth[socialaccount,mfa]~=65.4.0",
|
||||
"django-auditlog~=3.3.0",
|
||||
"django-auditlog~=3.2.1",
|
||||
"django-cachalot~=2.8.0",
|
||||
"django-celery-results~=2.6.0",
|
||||
"django-compression-middleware~=0.5.0",
|
||||
@@ -232,6 +233,7 @@ testpaths = [
|
||||
"src/paperless_tesseract/tests/",
|
||||
"src/paperless_tika/tests",
|
||||
"src/paperless_text/tests/",
|
||||
"src/paperless_remote/tests/",
|
||||
]
|
||||
addopts = [
|
||||
"--pythonwarnings=all",
|
||||
|
||||
@@ -1636,7 +1636,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/admin/tasks/tasks.component.ts</context>
|
||||
<context context-type="linenumber">44</context>
|
||||
<context context-type="linenumber">45</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/admin/trash/trash.component.html</context>
|
||||
@@ -1862,7 +1862,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/admin/tasks/tasks.component.ts</context>
|
||||
<context context-type="linenumber">153</context>
|
||||
<context context-type="linenumber">155</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="2134950584701094962" datatype="html">
|
||||
@@ -1918,63 +1918,77 @@
|
||||
<source>Result</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/admin/tasks/tasks.component.ts</context>
|
||||
<context context-type="linenumber">45</context>
|
||||
<context context-type="linenumber">46</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="5404910960991552159" datatype="html">
|
||||
<source>Dismiss selected</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/admin/tasks/tasks.component.ts</context>
|
||||
<context context-type="linenumber">108</context>
|
||||
<context context-type="linenumber">110</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="8829078752502782653" datatype="html">
|
||||
<source>Dismiss all</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/admin/tasks/tasks.component.ts</context>
|
||||
<context context-type="linenumber">109</context>
|
||||
<context context-type="linenumber">111</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="1323591410517879795" datatype="html">
|
||||
<source>Confirm Dismiss All</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/admin/tasks/tasks.component.ts</context>
|
||||
<context context-type="linenumber">150</context>
|
||||
<context context-type="linenumber">152</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4157200209636243740" datatype="html">
|
||||
<source>Dismiss all <x id="PH" equiv-text="tasks.size"/> tasks?</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/admin/tasks/tasks.component.ts</context>
|
||||
<context context-type="linenumber">151</context>
|
||||
<context context-type="linenumber">153</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="3597309129998924778" datatype="html">
|
||||
<source>Error dismissing tasks</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/admin/tasks/tasks.component.ts</context>
|
||||
<context context-type="linenumber">161</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="2132179171926568807" datatype="html">
|
||||
<source>Error dismissing task</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/admin/tasks/tasks.component.ts</context>
|
||||
<context context-type="linenumber">170</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="9011556615675272238" datatype="html">
|
||||
<source>queued</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/admin/tasks/tasks.component.ts</context>
|
||||
<context context-type="linenumber">236</context>
|
||||
<context context-type="linenumber">246</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6415892379431855826" datatype="html">
|
||||
<source>started</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/admin/tasks/tasks.component.ts</context>
|
||||
<context context-type="linenumber">238</context>
|
||||
<context context-type="linenumber">248</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="7510279840486540181" datatype="html">
|
||||
<source>completed</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/admin/tasks/tasks.component.ts</context>
|
||||
<context context-type="linenumber">240</context>
|
||||
<context context-type="linenumber">250</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4083337005045748464" datatype="html">
|
||||
<source>failed</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/admin/tasks/tasks.component.ts</context>
|
||||
<context context-type="linenumber">242</context>
|
||||
<context context-type="linenumber">252</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="3418677553313974490" datatype="html">
|
||||
@@ -2560,11 +2574,11 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1025</context>
|
||||
<context context-type="linenumber">1028</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1390</context>
|
||||
<context context-type="linenumber">1393</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
@@ -3176,7 +3190,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">978</context>
|
||||
<context context-type="linenumber">981</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
@@ -6654,7 +6668,7 @@
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1389</context>
|
||||
<context context-type="linenumber">1392</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6490688569532630280" datatype="html">
|
||||
@@ -7018,53 +7032,53 @@
|
||||
<source>Error retrieving metadata</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">666</context>
|
||||
<context context-type="linenumber">669</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="3456881259945295697" datatype="html">
|
||||
<source>Error retrieving suggestions.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">695</context>
|
||||
<context context-type="linenumber">698</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="2194092841814123758" datatype="html">
|
||||
<source>Document "<x id="PH" equiv-text="newValues.title"/>" saved successfully.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">867</context>
|
||||
<context context-type="linenumber">870</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">891</context>
|
||||
<context context-type="linenumber">894</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6626387786259219838" datatype="html">
|
||||
<source>Error saving document "<x id="PH" equiv-text="this.document.title"/>"</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">897</context>
|
||||
<context context-type="linenumber">900</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="448882439049417053" datatype="html">
|
||||
<source>Error saving document</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">947</context>
|
||||
<context context-type="linenumber">950</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="8410796510716511826" datatype="html">
|
||||
<source>Do you really want to move the document "<x id="PH" equiv-text="this.document.title"/>" to the trash?</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">979</context>
|
||||
<context context-type="linenumber">982</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="282586936710748252" datatype="html">
|
||||
<source>Documents can be restored prior to permanent deletion.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">980</context>
|
||||
<context context-type="linenumber">983</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
@@ -7075,7 +7089,7 @@
|
||||
<source>Move to trash</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">982</context>
|
||||
<context context-type="linenumber">985</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
@@ -7086,14 +7100,14 @@
|
||||
<source>Error deleting document</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1001</context>
|
||||
<context context-type="linenumber">1004</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="619486176823357521" datatype="html">
|
||||
<source>Reprocess confirm</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1021</context>
|
||||
<context context-type="linenumber">1024</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
|
||||
@@ -7104,81 +7118,81 @@
|
||||
<source>This operation will permanently recreate the archive file for this document.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1022</context>
|
||||
<context context-type="linenumber">1025</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="302054111564709516" datatype="html">
|
||||
<source>The archive file will be re-generated with the current settings.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1023</context>
|
||||
<context context-type="linenumber">1026</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="8251197608401006898" datatype="html">
|
||||
<source>Reprocess operation for "<x id="PH" equiv-text="this.document.title"/>" will begin in the background. Close and re-open or reload this document after the operation has completed to see new content.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1033</context>
|
||||
<context context-type="linenumber">1036</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4409560272830824468" datatype="html">
|
||||
<source>Error executing operation</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1044</context>
|
||||
<context context-type="linenumber">1047</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6030453331794586802" datatype="html">
|
||||
<source>Error downloading document</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1093</context>
|
||||
<context context-type="linenumber">1096</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4458954481601077369" datatype="html">
|
||||
<source>Page Fit</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1170</context>
|
||||
<context context-type="linenumber">1173</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4663705961777238777" datatype="html">
|
||||
<source>PDF edit operation for "<x id="PH" equiv-text="this.document.title"/>" will begin in the background.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1408</context>
|
||||
<context context-type="linenumber">1411</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="9043972994040261999" datatype="html">
|
||||
<source>Error executing PDF edit operation</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1420</context>
|
||||
<context context-type="linenumber">1423</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="3740891324955700797" datatype="html">
|
||||
<source>Print failed.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1452</context>
|
||||
<context context-type="linenumber">1455</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6457245677384603573" datatype="html">
|
||||
<source>Error loading document for printing.</source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1460</context>
|
||||
<context context-type="linenumber">1463</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="6085793215710522488" datatype="html">
|
||||
<source>An error occurred loading tiff: <x id="PH" equiv-text="err.toString()"/></source>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1525</context>
|
||||
<context context-type="linenumber">1528</context>
|
||||
</context-group>
|
||||
<context-group purpose="location">
|
||||
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
|
||||
<context context-type="linenumber">1529</context>
|
||||
<context context-type="linenumber">1532</context>
|
||||
</context-group>
|
||||
</trans-unit>
|
||||
<trans-unit id="4958946940233632319" datatype="html">
|
||||
|
||||
@@ -16,6 +16,7 @@ import {
|
||||
NgbNavItem,
|
||||
} from '@ng-bootstrap/ng-bootstrap'
|
||||
import { allIcons, NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
|
||||
import { throwError } from 'rxjs'
|
||||
import { routes } from 'src/app/app-routing.module'
|
||||
import {
|
||||
PaperlessTask,
|
||||
@@ -28,6 +29,7 @@ import { PermissionsGuard } from 'src/app/guards/permissions.guard'
|
||||
import { CustomDatePipe } from 'src/app/pipes/custom-date.pipe'
|
||||
import { PermissionsService } from 'src/app/services/permissions.service'
|
||||
import { TasksService } from 'src/app/services/tasks.service'
|
||||
import { ToastService } from 'src/app/services/toast.service'
|
||||
import { environment } from 'src/environments/environment'
|
||||
import { ConfirmDialogComponent } from '../../common/confirm-dialog/confirm-dialog.component'
|
||||
import { PageHeaderComponent } from '../../common/page-header/page-header.component'
|
||||
@@ -123,6 +125,7 @@ describe('TasksComponent', () => {
|
||||
let router: Router
|
||||
let httpTestingController: HttpTestingController
|
||||
let reloadSpy
|
||||
let toastService: ToastService
|
||||
|
||||
beforeEach(async () => {
|
||||
TestBed.configureTestingModule({
|
||||
@@ -157,6 +160,7 @@ describe('TasksComponent', () => {
|
||||
httpTestingController = TestBed.inject(HttpTestingController)
|
||||
modalService = TestBed.inject(NgbModal)
|
||||
router = TestBed.inject(Router)
|
||||
toastService = TestBed.inject(ToastService)
|
||||
fixture = TestBed.createComponent(TasksComponent)
|
||||
component = fixture.componentInstance
|
||||
jest.useFakeTimers()
|
||||
@@ -249,6 +253,42 @@ describe('TasksComponent', () => {
|
||||
expect(dismissSpy).toHaveBeenCalledWith(selected)
|
||||
})
|
||||
|
||||
it('should show an error and re-enable modal buttons when dismissing multiple tasks fails', () => {
|
||||
component.selectedTasks = new Set([tasks[0].id, tasks[1].id])
|
||||
const error = new Error('dismiss failed')
|
||||
const toastSpy = jest.spyOn(toastService, 'showError')
|
||||
const dismissSpy = jest
|
||||
.spyOn(tasksService, 'dismissTasks')
|
||||
.mockReturnValue(throwError(() => error))
|
||||
|
||||
let modal: NgbModalRef
|
||||
modalService.activeInstances.subscribe((m) => (modal = m[m.length - 1]))
|
||||
|
||||
component.dismissTasks()
|
||||
expect(modal).not.toBeUndefined()
|
||||
|
||||
modal.componentInstance.confirmClicked.emit()
|
||||
|
||||
expect(dismissSpy).toHaveBeenCalledWith(new Set([tasks[0].id, tasks[1].id]))
|
||||
expect(toastSpy).toHaveBeenCalledWith('Error dismissing tasks', error)
|
||||
expect(modal.componentInstance.buttonsEnabled).toBe(true)
|
||||
expect(component.selectedTasks.size).toBe(0)
|
||||
})
|
||||
|
||||
it('should show an error when dismissing a single task fails', () => {
|
||||
const error = new Error('dismiss failed')
|
||||
const toastSpy = jest.spyOn(toastService, 'showError')
|
||||
const dismissSpy = jest
|
||||
.spyOn(tasksService, 'dismissTasks')
|
||||
.mockReturnValue(throwError(() => error))
|
||||
|
||||
component.dismissTask(tasks[0])
|
||||
|
||||
expect(dismissSpy).toHaveBeenCalledWith(new Set([tasks[0].id]))
|
||||
expect(toastSpy).toHaveBeenCalledWith('Error dismissing task', error)
|
||||
expect(component.selectedTasks.size).toBe(0)
|
||||
})
|
||||
|
||||
it('should support dismiss all tasks', () => {
|
||||
let modal: NgbModalRef
|
||||
modalService.activeInstances.subscribe((m) => (modal = m[m.length - 1]))
|
||||
|
||||
@@ -24,6 +24,7 @@ import { PaperlessTask } from 'src/app/data/paperless-task'
|
||||
import { IfPermissionsDirective } from 'src/app/directives/if-permissions.directive'
|
||||
import { CustomDatePipe } from 'src/app/pipes/custom-date.pipe'
|
||||
import { TasksService } from 'src/app/services/tasks.service'
|
||||
import { ToastService } from 'src/app/services/toast.service'
|
||||
import { ConfirmDialogComponent } from '../../common/confirm-dialog/confirm-dialog.component'
|
||||
import { PageHeaderComponent } from '../../common/page-header/page-header.component'
|
||||
import { LoadingComponentWithPermissions } from '../../loading-component/loading.component'
|
||||
@@ -72,6 +73,7 @@ export class TasksComponent
|
||||
tasksService = inject(TasksService)
|
||||
private modalService = inject(NgbModal)
|
||||
private readonly router = inject(Router)
|
||||
private readonly toastService = inject(ToastService)
|
||||
|
||||
public activeTab: TaskTab
|
||||
public selectedTasks: Set<number> = new Set()
|
||||
@@ -154,11 +156,19 @@ export class TasksComponent
|
||||
modal.componentInstance.confirmClicked.pipe(first()).subscribe(() => {
|
||||
modal.componentInstance.buttonsEnabled = false
|
||||
modal.close()
|
||||
this.tasksService.dismissTasks(tasks)
|
||||
this.tasksService.dismissTasks(tasks).subscribe({
|
||||
error: (e) => {
|
||||
this.toastService.showError($localize`Error dismissing tasks`, e)
|
||||
modal.componentInstance.buttonsEnabled = true
|
||||
},
|
||||
})
|
||||
this.clearSelection()
|
||||
})
|
||||
} else {
|
||||
this.tasksService.dismissTasks(tasks)
|
||||
this.tasksService.dismissTasks(tasks).subscribe({
|
||||
error: (e) =>
|
||||
this.toastService.showError($localize`Error dismissing task`, e),
|
||||
})
|
||||
this.clearSelection()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -41,9 +41,3 @@
|
||||
min-width: 140px;
|
||||
}
|
||||
}
|
||||
|
||||
.btn-group-xs {
|
||||
> .btn {
|
||||
border-radius: 0.15rem;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1212,7 +1212,7 @@ describe('DocumentDetailComponent', () => {
|
||||
it('should support keyboard shortcuts', () => {
|
||||
initNormally()
|
||||
|
||||
jest.spyOn(component, 'hasNext').mockReturnValue(true)
|
||||
const hasNextSpy = jest.spyOn(component, 'hasNext').mockReturnValue(true)
|
||||
const nextSpy = jest.spyOn(component, 'nextDoc')
|
||||
document.dispatchEvent(
|
||||
new KeyboardEvent('keydown', { key: 'arrowright', ctrlKey: true })
|
||||
@@ -1226,21 +1226,32 @@ describe('DocumentDetailComponent', () => {
|
||||
)
|
||||
expect(prevSpy).toHaveBeenCalled()
|
||||
|
||||
jest.spyOn(openDocumentsService, 'isDirty').mockReturnValue(true)
|
||||
const isDirtySpy = jest
|
||||
.spyOn(openDocumentsService, 'isDirty')
|
||||
.mockReturnValue(true)
|
||||
const saveSpy = jest.spyOn(component, 'save')
|
||||
document.dispatchEvent(
|
||||
new KeyboardEvent('keydown', { key: 's', ctrlKey: true })
|
||||
)
|
||||
expect(saveSpy).toHaveBeenCalled()
|
||||
|
||||
jest.spyOn(openDocumentsService, 'isDirty').mockReturnValue(true)
|
||||
jest.spyOn(component, 'hasNext').mockReturnValue(true)
|
||||
hasNextSpy.mockReturnValue(true)
|
||||
const saveNextSpy = jest.spyOn(component, 'saveEditNext')
|
||||
document.dispatchEvent(
|
||||
new KeyboardEvent('keydown', { key: 's', ctrlKey: true, shiftKey: true })
|
||||
)
|
||||
expect(saveNextSpy).toHaveBeenCalled()
|
||||
|
||||
saveSpy.mockClear()
|
||||
saveNextSpy.mockClear()
|
||||
isDirtySpy.mockReturnValue(true)
|
||||
hasNextSpy.mockReturnValue(false)
|
||||
document.dispatchEvent(
|
||||
new KeyboardEvent('keydown', { key: 's', ctrlKey: true, shiftKey: true })
|
||||
)
|
||||
expect(saveNextSpy).not.toHaveBeenCalled()
|
||||
expect(saveSpy).toHaveBeenCalledWith(true)
|
||||
|
||||
const closeSpy = jest.spyOn(component, 'close')
|
||||
document.dispatchEvent(new KeyboardEvent('keydown', { key: 'escape' }))
|
||||
expect(closeSpy).toHaveBeenCalled()
|
||||
|
||||
@@ -615,7 +615,10 @@ export class DocumentDetailComponent
|
||||
})
|
||||
.pipe(takeUntil(this.unsubscribeNotifier))
|
||||
.subscribe(() => {
|
||||
if (this.openDocumentService.isDirty(this.document)) this.saveEditNext()
|
||||
if (this.openDocumentService.isDirty(this.document)) {
|
||||
if (this.hasNext()) this.saveEditNext()
|
||||
else this.save(true)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
@@ -51,7 +51,7 @@ describe('TasksService', () => {
|
||||
})
|
||||
|
||||
it('calls acknowledge_tasks api endpoint on dismiss and reloads', () => {
|
||||
tasksService.dismissTasks(new Set([1, 2, 3]))
|
||||
tasksService.dismissTasks(new Set([1, 2, 3])).subscribe()
|
||||
const req = httpTestingController.expectOne(
|
||||
`${environment.apiBaseUrl}tasks/acknowledge/`
|
||||
)
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import { HttpClient } from '@angular/common/http'
|
||||
import { Injectable, inject } from '@angular/core'
|
||||
import { Observable, Subject } from 'rxjs'
|
||||
import { first, takeUntil } from 'rxjs/operators'
|
||||
import { first, takeUntil, tap } from 'rxjs/operators'
|
||||
import {
|
||||
PaperlessTask,
|
||||
PaperlessTaskName,
|
||||
@@ -68,14 +68,17 @@ export class TasksService {
|
||||
}
|
||||
|
||||
public dismissTasks(task_ids: Set<number>) {
|
||||
this.http
|
||||
return this.http
|
||||
.post(`${this.baseUrl}tasks/acknowledge/`, {
|
||||
tasks: [...task_ids],
|
||||
})
|
||||
.pipe(first())
|
||||
.subscribe((r) => {
|
||||
.pipe(
|
||||
first(),
|
||||
takeUntil(this.unsubscribeNotifer),
|
||||
tap(() => {
|
||||
this.reload()
|
||||
})
|
||||
)
|
||||
}
|
||||
|
||||
public cancelPending(): void {
|
||||
|
||||
@@ -161,3 +161,21 @@ class PaperlessNotePermissions(BasePermission):
|
||||
perms = self.perms_map[request.method]
|
||||
|
||||
return request.user.has_perms(perms)
|
||||
|
||||
|
||||
class AcknowledgeTasksPermissions(BasePermission):
|
||||
"""
|
||||
Permissions class that checks for model permissions for acknowledging tasks.
|
||||
"""
|
||||
|
||||
perms_map = {
|
||||
"POST": ["documents.change_paperlesstask"],
|
||||
}
|
||||
|
||||
def has_permission(self, request, view):
|
||||
if not request.user or not request.user.is_authenticated: # pragma: no cover
|
||||
return False
|
||||
|
||||
perms = self.perms_map.get(request.method, [])
|
||||
|
||||
return request.user.has_perms(perms)
|
||||
|
||||
@@ -135,6 +135,44 @@ class TestTasks(DirectoriesMixin, APITestCase):
|
||||
response = self.client.get(self.ENDPOINT + "?acknowledged=false")
|
||||
self.assertEqual(len(response.data), 0)
|
||||
|
||||
def test_acknowledge_tasks_requires_change_permission(self):
|
||||
"""
|
||||
GIVEN:
|
||||
- A regular user initially without change permissions
|
||||
- A regular user with change permissions
|
||||
WHEN:
|
||||
- API call is made to acknowledge tasks
|
||||
THEN:
|
||||
- The first user is forbidden from acknowledging tasks
|
||||
- The second user is allowed to acknowledge tasks
|
||||
"""
|
||||
regular_user = User.objects.create_user(username="test")
|
||||
self.client.force_authenticate(user=regular_user)
|
||||
|
||||
task = PaperlessTask.objects.create(
|
||||
task_id=str(uuid.uuid4()),
|
||||
task_file_name="task_one.pdf",
|
||||
)
|
||||
|
||||
response = self.client.post(
|
||||
self.ENDPOINT + "acknowledge/",
|
||||
{"tasks": [task.id]},
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
|
||||
|
||||
regular_user2 = User.objects.create_user(username="test2")
|
||||
regular_user2.user_permissions.add(
|
||||
Permission.objects.get(codename="change_paperlesstask"),
|
||||
)
|
||||
regular_user2.save()
|
||||
self.client.force_authenticate(user=regular_user2)
|
||||
|
||||
response = self.client.post(
|
||||
self.ENDPOINT + "acknowledge/",
|
||||
{"tasks": [task.id]},
|
||||
)
|
||||
self.assertEqual(response.status_code, status.HTTP_200_OK)
|
||||
|
||||
def test_tasks_owner_aware(self):
|
||||
"""
|
||||
GIVEN:
|
||||
|
||||
@@ -136,6 +136,7 @@ from documents.models import WorkflowAction
|
||||
from documents.models import WorkflowTrigger
|
||||
from documents.parsers import get_parser_class_for_mime_type
|
||||
from documents.parsers import parse_date_generator
|
||||
from documents.permissions import AcknowledgeTasksPermissions
|
||||
from documents.permissions import PaperlessAdminPermissions
|
||||
from documents.permissions import PaperlessNotePermissions
|
||||
from documents.permissions import PaperlessObjectPermissions
|
||||
@@ -2487,7 +2488,11 @@ class TasksViewSet(ReadOnlyModelViewSet):
|
||||
queryset = PaperlessTask.objects.filter(task_id=task_id)
|
||||
return queryset
|
||||
|
||||
@action(methods=["post"], detail=False)
|
||||
@action(
|
||||
methods=["post"],
|
||||
detail=False,
|
||||
permission_classes=[IsAuthenticated, AcknowledgeTasksPermissions],
|
||||
)
|
||||
def acknowledge(self, request):
|
||||
serializer = AcknowledgeTasksViewSerializer(data=request.data)
|
||||
serializer.is_valid(raise_exception=True)
|
||||
|
||||
@@ -322,6 +322,7 @@ INSTALLED_APPS = [
|
||||
"paperless_tesseract.apps.PaperlessTesseractConfig",
|
||||
"paperless_text.apps.PaperlessTextConfig",
|
||||
"paperless_mail.apps.PaperlessMailConfig",
|
||||
"paperless_remote.apps.PaperlessRemoteParserConfig",
|
||||
"django.contrib.admin",
|
||||
"rest_framework",
|
||||
"rest_framework.authtoken",
|
||||
@@ -1401,3 +1402,10 @@ WEBHOOKS_ALLOW_INTERNAL_REQUESTS = __get_boolean(
|
||||
"PAPERLESS_WEBHOOKS_ALLOW_INTERNAL_REQUESTS",
|
||||
"true",
|
||||
)
|
||||
|
||||
###############################################################################
|
||||
# Remote Parser #
|
||||
###############################################################################
|
||||
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")
|
||||
|
||||
4
src/paperless_remote/__init__.py
Normal file
4
src/paperless_remote/__init__.py
Normal file
@@ -0,0 +1,4 @@
|
||||
# this is here so that django finds the checks.
|
||||
from paperless_remote.checks import check_remote_parser_configured
|
||||
|
||||
__all__ = ["check_remote_parser_configured"]
|
||||
14
src/paperless_remote/apps.py
Normal file
14
src/paperless_remote/apps.py
Normal file
@@ -0,0 +1,14 @@
|
||||
from django.apps import AppConfig
|
||||
|
||||
from paperless_remote.signals import remote_consumer_declaration
|
||||
|
||||
|
||||
class PaperlessRemoteParserConfig(AppConfig):
|
||||
name = "paperless_remote"
|
||||
|
||||
def ready(self):
|
||||
from documents.signals import document_consumer_declaration
|
||||
|
||||
document_consumer_declaration.connect(remote_consumer_declaration)
|
||||
|
||||
AppConfig.ready(self)
|
||||
17
src/paperless_remote/checks.py
Normal file
17
src/paperless_remote/checks.py
Normal file
@@ -0,0 +1,17 @@
|
||||
from django.conf import settings
|
||||
from django.core.checks import Error
|
||||
from django.core.checks import register
|
||||
|
||||
|
||||
@register()
|
||||
def check_remote_parser_configured(app_configs, **kwargs):
|
||||
if settings.REMOTE_OCR_ENGINE == "azureai" and not (
|
||||
settings.REMOTE_OCR_ENDPOINT and settings.REMOTE_OCR_API_KEY
|
||||
):
|
||||
return [
|
||||
Error(
|
||||
"Azure AI remote parser requires endpoint and API key to be configured.",
|
||||
),
|
||||
]
|
||||
|
||||
return []
|
||||
113
src/paperless_remote/parsers.py
Normal file
113
src/paperless_remote/parsers.py
Normal file
@@ -0,0 +1,113 @@
|
||||
from pathlib import Path
|
||||
|
||||
from django.conf import settings
|
||||
|
||||
from paperless_tesseract.parsers import RasterisedDocumentParser
|
||||
|
||||
|
||||
class RemoteEngineConfig:
|
||||
def __init__(
|
||||
self,
|
||||
engine: str,
|
||||
api_key: str | None = None,
|
||||
endpoint: str | None = None,
|
||||
):
|
||||
self.engine = engine
|
||||
self.api_key = api_key
|
||||
self.endpoint = endpoint
|
||||
|
||||
def engine_is_valid(self):
|
||||
valid = self.engine in ["azureai"] and self.api_key is not None
|
||||
if self.engine == "azureai":
|
||||
valid = valid and self.endpoint is not None
|
||||
return valid
|
||||
|
||||
|
||||
class RemoteDocumentParser(RasterisedDocumentParser):
|
||||
"""
|
||||
This parser uses a remote OCR engine to parse documents. Currently, it supports Azure AI Vision
|
||||
as this is the only service that provides a remote OCR API with text-embedded PDF output.
|
||||
"""
|
||||
|
||||
logging_name = "paperless.parsing.remote"
|
||||
|
||||
def get_settings(self) -> RemoteEngineConfig:
|
||||
"""
|
||||
Returns the configuration for the remote OCR engine, loaded from Django settings.
|
||||
"""
|
||||
return RemoteEngineConfig(
|
||||
engine=settings.REMOTE_OCR_ENGINE,
|
||||
api_key=settings.REMOTE_OCR_API_KEY,
|
||||
endpoint=settings.REMOTE_OCR_ENDPOINT,
|
||||
)
|
||||
|
||||
def supported_mime_types(self):
|
||||
if self.settings.engine_is_valid():
|
||||
return {
|
||||
"application/pdf": ".pdf",
|
||||
"image/png": ".png",
|
||||
"image/jpeg": ".jpg",
|
||||
"image/tiff": ".tiff",
|
||||
"image/bmp": ".bmp",
|
||||
"image/gif": ".gif",
|
||||
"image/webp": ".webp",
|
||||
}
|
||||
else:
|
||||
return {}
|
||||
|
||||
def azure_ai_vision_parse(
|
||||
self,
|
||||
file: Path,
|
||||
) -> str | None:
|
||||
"""
|
||||
Uses Azure AI Vision to parse the document and return the text content.
|
||||
It requests a searchable PDF output with embedded text.
|
||||
The PDF is saved to the archive_path attribute.
|
||||
Returns the text content extracted from the document.
|
||||
If the parsing fails, it returns None.
|
||||
"""
|
||||
from azure.ai.documentintelligence import DocumentIntelligenceClient
|
||||
from azure.ai.documentintelligence.models import AnalyzeDocumentRequest
|
||||
from azure.ai.documentintelligence.models import AnalyzeOutputOption
|
||||
from azure.ai.documentintelligence.models import DocumentContentFormat
|
||||
from azure.core.credentials import AzureKeyCredential
|
||||
|
||||
client = DocumentIntelligenceClient(
|
||||
endpoint=self.settings.endpoint,
|
||||
credential=AzureKeyCredential(self.settings.api_key),
|
||||
)
|
||||
|
||||
with file.open("rb") as f:
|
||||
analyze_request = AnalyzeDocumentRequest(bytes_source=f.read())
|
||||
poller = client.begin_analyze_document(
|
||||
model_id="prebuilt-read",
|
||||
body=analyze_request,
|
||||
output_content_format=DocumentContentFormat.TEXT,
|
||||
output=[AnalyzeOutputOption.PDF], # request searchable PDF output
|
||||
content_type="application/json",
|
||||
)
|
||||
|
||||
poller.wait()
|
||||
result_id = poller.details["operation_id"]
|
||||
result = poller.result()
|
||||
|
||||
# Download the PDF with embedded text
|
||||
self.archive_path = self.tempdir / "archive.pdf"
|
||||
with self.archive_path.open("wb") as f:
|
||||
for chunk in client.get_analyze_result_pdf(
|
||||
model_id="prebuilt-read",
|
||||
result_id=result_id,
|
||||
):
|
||||
f.write(chunk)
|
||||
|
||||
client.close()
|
||||
return result.content
|
||||
|
||||
def parse(self, document_path: Path, mime_type, file_name=None):
|
||||
if not self.settings.engine_is_valid():
|
||||
self.log.warning(
|
||||
"No valid remote parser engine is configured, content will be empty.",
|
||||
)
|
||||
self.text = ""
|
||||
elif self.settings.engine == "azureai":
|
||||
self.text = self.azure_ai_vision_parse(document_path)
|
||||
18
src/paperless_remote/signals.py
Normal file
18
src/paperless_remote/signals.py
Normal file
@@ -0,0 +1,18 @@
|
||||
def get_parser(*args, **kwargs):
|
||||
from paperless_remote.parsers import RemoteDocumentParser
|
||||
|
||||
return RemoteDocumentParser(*args, **kwargs)
|
||||
|
||||
|
||||
def get_supported_mime_types():
|
||||
from paperless_remote.parsers import RemoteDocumentParser
|
||||
|
||||
return RemoteDocumentParser(None).supported_mime_types()
|
||||
|
||||
|
||||
def remote_consumer_declaration(sender, **kwargs):
|
||||
return {
|
||||
"parser": get_parser,
|
||||
"weight": 5,
|
||||
"mime_types": get_supported_mime_types(),
|
||||
}
|
||||
0
src/paperless_remote/tests/__init__.py
Normal file
0
src/paperless_remote/tests/__init__.py
Normal file
BIN
src/paperless_remote/tests/samples/simple-digital.pdf
Normal file
BIN
src/paperless_remote/tests/samples/simple-digital.pdf
Normal file
Binary file not shown.
24
src/paperless_remote/tests/test_checks.py
Normal file
24
src/paperless_remote/tests/test_checks.py
Normal file
@@ -0,0 +1,24 @@
|
||||
from unittest import TestCase
|
||||
|
||||
from django.test import override_settings
|
||||
|
||||
from paperless_remote import check_remote_parser_configured
|
||||
|
||||
|
||||
class TestChecks(TestCase):
|
||||
@override_settings(REMOTE_OCR_ENGINE=None)
|
||||
def test_no_engine(self):
|
||||
msgs = check_remote_parser_configured(None)
|
||||
self.assertEqual(len(msgs), 0)
|
||||
|
||||
@override_settings(REMOTE_OCR_ENGINE="azureai")
|
||||
@override_settings(REMOTE_OCR_API_KEY="somekey")
|
||||
@override_settings(REMOTE_OCR_ENDPOINT=None)
|
||||
def test_azure_no_endpoint(self):
|
||||
msgs = check_remote_parser_configured(None)
|
||||
self.assertEqual(len(msgs), 1)
|
||||
self.assertTrue(
|
||||
msgs[0].msg.startswith(
|
||||
"Azure AI remote parser requires endpoint and API key to be configured.",
|
||||
),
|
||||
)
|
||||
101
src/paperless_remote/tests/test_parser.py
Normal file
101
src/paperless_remote/tests/test_parser.py
Normal file
@@ -0,0 +1,101 @@
|
||||
import uuid
|
||||
from pathlib import Path
|
||||
from unittest import mock
|
||||
|
||||
from django.test import TestCase
|
||||
from django.test import override_settings
|
||||
|
||||
from documents.tests.utils import DirectoriesMixin
|
||||
from documents.tests.utils import FileSystemAssertsMixin
|
||||
from paperless_remote.parsers import RemoteDocumentParser
|
||||
from paperless_remote.signals import get_parser
|
||||
|
||||
|
||||
class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
|
||||
SAMPLE_FILES = Path(__file__).resolve().parent / "samples"
|
||||
|
||||
def assertContainsStrings(self, content: str, strings: list[str]):
|
||||
# Asserts that all strings appear in content, in the given order.
|
||||
indices = []
|
||||
for s in strings:
|
||||
if s in content:
|
||||
indices.append(content.index(s))
|
||||
else:
|
||||
self.fail(f"'{s}' is not in '{content}'")
|
||||
self.assertListEqual(indices, sorted(indices))
|
||||
|
||||
@mock.patch("paperless_tesseract.parsers.run_subprocess")
|
||||
@mock.patch("azure.ai.documentintelligence.DocumentIntelligenceClient")
|
||||
def test_get_text_with_azure(self, mock_client_cls, mock_subprocess):
|
||||
# Arrange mock Azure client
|
||||
mock_client = mock.Mock()
|
||||
mock_client_cls.return_value = mock_client
|
||||
|
||||
# Simulate poller result and its `.details`
|
||||
mock_poller = mock.Mock()
|
||||
mock_poller.wait.return_value = None
|
||||
mock_poller.details = {"operation_id": "fake-op-id"}
|
||||
mock_client.begin_analyze_document.return_value = mock_poller
|
||||
mock_poller.result.return_value.content = "This is a test document."
|
||||
|
||||
# Return dummy PDF bytes
|
||||
mock_client.get_analyze_result_pdf.return_value = [
|
||||
b"%PDF-",
|
||||
b"1.7 ",
|
||||
b"FAKEPDF",
|
||||
]
|
||||
|
||||
# Simulate pdftotext by writing dummy text to sidecar file
|
||||
def fake_run(cmd, *args, **kwargs):
|
||||
with Path(cmd[-1]).open("w", encoding="utf-8") as f:
|
||||
f.write("This is a test document.")
|
||||
|
||||
mock_subprocess.side_effect = fake_run
|
||||
|
||||
with override_settings(
|
||||
REMOTE_OCR_ENGINE="azureai",
|
||||
REMOTE_OCR_API_KEY="somekey",
|
||||
REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
|
||||
):
|
||||
parser = get_parser(uuid.uuid4())
|
||||
parser.parse(
|
||||
self.SAMPLE_FILES / "simple-digital.pdf",
|
||||
"application/pdf",
|
||||
)
|
||||
|
||||
self.assertContainsStrings(
|
||||
parser.text.strip(),
|
||||
["This is a test document."],
|
||||
)
|
||||
|
||||
@override_settings(
|
||||
REMOTE_OCR_ENGINE="azureai",
|
||||
REMOTE_OCR_API_KEY="key",
|
||||
REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
|
||||
)
|
||||
def test_supported_mime_types_valid_config(self):
|
||||
parser = RemoteDocumentParser(uuid.uuid4())
|
||||
expected_types = {
|
||||
"application/pdf": ".pdf",
|
||||
"image/png": ".png",
|
||||
"image/jpeg": ".jpg",
|
||||
"image/tiff": ".tiff",
|
||||
"image/bmp": ".bmp",
|
||||
"image/gif": ".gif",
|
||||
"image/webp": ".webp",
|
||||
}
|
||||
self.assertEqual(parser.supported_mime_types(), expected_types)
|
||||
|
||||
def test_supported_mime_types_invalid_config(self):
|
||||
parser = get_parser(uuid.uuid4())
|
||||
self.assertEqual(parser.supported_mime_types(), {})
|
||||
|
||||
@override_settings(
|
||||
REMOTE_OCR_ENGINE=None,
|
||||
REMOTE_OCR_API_KEY=None,
|
||||
REMOTE_OCR_ENDPOINT=None,
|
||||
)
|
||||
def test_parse_with_invalid_config(self):
|
||||
parser = get_parser(uuid.uuid4())
|
||||
parser.parse(self.SAMPLE_FILES / "simple-digital.pdf", "application/pdf")
|
||||
self.assertEqual(parser.text, "")
|
||||
47
uv.lock
generated
47
uv.lock
generated
@@ -95,6 +95,34 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/02/ff/1175b0b7371e46244032d43a56862d0af455823b5280a50c63d99cc50f18/automat-25.4.16-py3-none-any.whl", hash = "sha256:04e9bce696a8d5671ee698005af6e5a9fa15354140a87f4870744604dcdd3ba1", size = 42842, upload-time = "2025-04-16T20:12:14.447Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "azure-ai-documentintelligence"
|
||||
version = "1.0.2"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "azure-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "isodate", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/44/7b/8115cd713e2caa5e44def85f2b7ebd02a74ae74d7113ba20bdd41fd6dd80/azure_ai_documentintelligence-1.0.2.tar.gz", hash = "sha256:4d75a2513f2839365ebabc0e0e1772f5601b3a8c9a71e75da12440da13b63484", size = 170940 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/d9/75/c9ec040f23082f54ffb1977ff8f364c2d21c79a640a13d1c1809e7fd6b1a/azure_ai_documentintelligence-1.0.2-py3-none-any.whl", hash = "sha256:e1fb446abbdeccc9759d897898a0fe13141ed29f9ad11fc705f951925822ed59", size = 106005 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "azure-core"
|
||||
version = "1.33.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "requests", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "six", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/75/aa/7c9db8edd626f1a7d99d09ef7926f6f4fb34d5f9fa00dc394afdfe8e2a80/azure_core-1.33.0.tar.gz", hash = "sha256:f367aa07b5e3005fec2c1e184b882b0b039910733907d001c20fb08ebb8c0eb9", size = 295633 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/07/b7/76b7e144aa53bd206bf1ce34fa75350472c3f69bf30e5c8c18bc9881035d/azure_core-1.33.0-py3-none-any.whl", hash = "sha256:9b5b6d0223a1d38c37500e6971118c1e0f13f54951e6893968b38910bc9cda8f", size = 207071 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "babel"
|
||||
version = "2.17.0"
|
||||
@@ -710,15 +738,15 @@ socialaccount = [
|
||||
|
||||
[[package]]
|
||||
name = "django-auditlog"
|
||||
version = "3.3.0"
|
||||
version = "3.2.1"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "django", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "python-dateutil", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/37/d8/ddd1c653ffb7ed1984596420982e32a0b163a0be316721a801a54dcbf016/django_auditlog-3.3.0.tar.gz", hash = "sha256:01331a0e7bb1a8ff7573311b486c88f3d0c431c388f5a1e4a9b6b26911dd79b8", size = 85941, upload-time = "2025-10-02T17:16:27.591Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/e1/46/9da1d94493832fa18d2f6324a76d387fa232001593866987a96047709f4e/django_auditlog-3.2.1.tar.gz", hash = "sha256:63a4c9f7793e94eed804bc31a04d9b0b58244b1d280e2ed273c8b406bff1f779", size = 72926, upload-time = "2025-07-03T20:08:17.734Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/f3/bc/6e1b503d1755ab09cff6480cb088def073f1303165ab59b1a09247a2e756/django_auditlog-3.3.0-py3-none-any.whl", hash = "sha256:ab0f0f556a7107ac01c8fa87137bdfbb2b6f0debf70f7753169d9a40673d2636", size = 39676, upload-time = "2025-10-02T17:15:42.922Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a7/06/67296d050a72dcd76f57f220df621cb27e5b9282ba7ad0f5f74870dce241/django_auditlog-3.2.1-py3-none-any.whl", hash = "sha256:99603ca9d015f7e9b062b1c34f3e0826a3ce6ae6e5950c81bb7e663f7802a899", size = 38330, upload-time = "2025-07-03T20:07:51.735Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -1451,6 +1479,15 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/c7/fc/4e5a141c3f7c7bed550ac1f69e599e92b6be449dd4677ec09f325cad0955/inotifyrecursive-0.3.5-py3-none-any.whl", hash = "sha256:7e5f4a2e1dc2bef0efa3b5f6b339c41fb4599055a2b54909d020e9e932cc8d2f", size = 8009, upload-time = "2020-11-20T12:38:46.981Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "isodate"
|
||||
version = "0.7.2"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/54/4d/e940025e2ce31a8ce1202635910747e5a87cc3a6a6bb2d00973375014749/isodate-0.7.2.tar.gz", hash = "sha256:4cd1aa0f43ca76f4a6c6c0292a85f40b35ec2e43e315b59f06e6d32171a953e6", size = 29705 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/15/aa/0aca39a37d3c7eb941ba736ede56d689e7be91cab5d9ca846bde3999eba6/isodate-0.7.2-py3-none-any.whl", hash = "sha256:28009937d8031054830160fce6d409ed342816b543597cece116d966c6d99e15", size = 22320 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "jinja2"
|
||||
version = "3.1.6"
|
||||
@@ -2119,6 +2156,7 @@ name = "paperless-ngx"
|
||||
version = "2.18.4"
|
||||
source = { virtual = "." }
|
||||
dependencies = [
|
||||
{ name = "azure-ai-documentintelligence", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "babel", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "bleach", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "celery", extra = ["redis"], marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
@@ -2255,6 +2293,7 @@ typing = [
|
||||
|
||||
[package.metadata]
|
||||
requires-dist = [
|
||||
{ name = "azure-ai-documentintelligence", specifier = ">=1.0.2" },
|
||||
{ name = "babel", specifier = ">=2.17" },
|
||||
{ name = "bleach", specifier = "~=6.2.0" },
|
||||
{ name = "celery", extras = ["redis"], specifier = "~=5.5.1" },
|
||||
@@ -2264,7 +2303,7 @@ requires-dist = [
|
||||
{ name = "dateparser", specifier = "~=1.2" },
|
||||
{ name = "django", specifier = "~=5.2.5" },
|
||||
{ name = "django-allauth", extras = ["socialaccount", "mfa"], specifier = "~=65.4.0" },
|
||||
{ name = "django-auditlog", specifier = "~=3.3.0" },
|
||||
{ name = "django-auditlog", specifier = "~=3.2.1" },
|
||||
{ name = "django-cachalot", specifier = "~=2.8.0" },
|
||||
{ name = "django-celery-results", specifier = "~=2.6.0" },
|
||||
{ name = "django-compression-middleware", specifier = "~=0.5.0" },
|
||||
|
||||
Reference in New Issue
Block a user