Compare commits

..

3 Commits

Author SHA1 Message Date
Trenton H
3ae0b8e219 Fixes logging so I can see it 2026-03-06 12:04:54 -08:00
Trenton H
4a6fd02492 Batch based iteration and bulk updates, with chunked file reading 2026-03-06 11:44:41 -08:00
Trenton H
76fb8f3770 Transitions to SHA256 based checksums 2026-03-06 11:33:33 -08:00
46 changed files with 1127 additions and 1453 deletions

View File

@@ -149,16 +149,15 @@ jobs:
mkdir -p /tmp/digests
digest="${{ steps.build.outputs.digest }}"
echo "digest=${digest}"
echo "${digest}" > "/tmp/digests/digest-${{ matrix.arch }}.txt"
touch "/tmp/digests/${digest#sha256:}"
- name: Upload digest
if: steps.check-push.outputs.should-push == 'true'
uses: actions/upload-artifact@v7.0.0
with:
name: digests-${{ matrix.arch }}
path: /tmp/digests/digest-${{ matrix.arch }}.txt
path: /tmp/digests/*
if-no-files-found: error
retention-days: 1
archive: false
merge-and-push:
name: Merge and Push Manifest
runs-on: ubuntu-24.04
@@ -172,7 +171,7 @@ jobs:
uses: actions/download-artifact@v8.0.0
with:
path: /tmp/digests
pattern: digest-*.txt
pattern: digests-*
merge-multiple: true
- name: List digests
run: |
@@ -218,9 +217,8 @@ jobs:
tags=$(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "${DOCKER_METADATA_OUTPUT_JSON}")
digests=""
for digest_file in digest-*.txt; do
digest=$(cat "${digest_file}")
digests+="${{ env.REGISTRY }}/${REPOSITORY}@${digest} "
for digest in *; do
digests+="${{ env.REGISTRY }}/${REPOSITORY}@sha256:${digest} "
done
echo "Creating manifest with tags: ${tags}"

View File

@@ -2,24 +2,13 @@ name: PR Bot
on:
pull_request_target:
types: [opened]
permissions:
contents: read
pull-requests: write
jobs:
anti-slop:
runs-on: ubuntu-latest
permissions:
contents: read
issues: read
pull-requests: write
steps:
- uses: peakoss/anti-slop@v0.2.1
with:
max-failures: 4
failure-add-pr-labels: 'ai'
pr-bot:
name: Automated PR Bot
runs-on: ubuntu-latest
permissions:
contents: read
pull-requests: write
steps:
- name: Label PR by file path or branch name
# see .github/labeler.yml for the labeler config

View File

@@ -369,38 +369,41 @@ operations, using the endpoint: `/api/bulk_edit_objects/`, which requires a json
## API Versioning
The REST API is versioned.
The REST API is versioned since Paperless-ngx 1.3.0.
- Versioning ensures that changes to the API don't break older
clients.
- Clients specify the specific version of the API they wish to use
with every request and Paperless will handle the request using the
specified API version.
- Even if the underlying data model changes, supported older API
versions continue to serve compatible data.
- If no version is specified, Paperless serves the configured default
API version (currently `10`).
- Supported API versions are currently `9` and `10`.
- Even if the underlying data model changes, older API versions will
always serve compatible data.
- If no version is specified, Paperless will serve version 1 to ensure
compatibility with older clients that do not request a specific API
version.
API versions are specified by submitting an additional HTTP `Accept`
header with every request:
```
Accept: application/json; version=10
Accept: application/json; version=6
```
If an invalid version is specified, Paperless responds with
`406 Not Acceptable` and an error message in the body.
If an invalid version is specified, Paperless 1.3.0 will respond with
"406 Not Acceptable" and an error message in the body. Earlier
versions of Paperless will serve API version 1 regardless of whether a
version is specified via the `Accept` header.
If a client wishes to verify whether it is compatible with any given
server, the following procedure should be performed:
1. Perform an _authenticated_ request against any API endpoint. The
server will add two custom headers to the response:
1. Perform an _authenticated_ request against any API endpoint. If the
server is on version 1.3.0 or newer, the server will add two custom
headers to the response:
```
X-Api-Version: 10
X-Version: <server-version>
X-Api-Version: 2
X-Version: 1.3.0
```
2. Determine whether the client is compatible with this server based on

View File

@@ -1217,7 +1217,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1760</context>
<context context-type="linenumber">1756</context>
</context-group>
</trans-unit>
<trans-unit id="1577733187050997705" datatype="html">
@@ -2090,7 +2090,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">637</context>
<context context-type="linenumber">634</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-version-dropdown/document-version-dropdown.component.html</context>
@@ -2798,11 +2798,11 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1379</context>
<context context-type="linenumber">1376</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">1761</context>
<context context-type="linenumber">1757</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
@@ -3400,7 +3400,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1332</context>
<context context-type="linenumber">1329</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
@@ -3434,46 +3434,39 @@
<context context-type="linenumber">9</context>
</context-group>
</trans-unit>
<trans-unit id="6705735915615634619" datatype="html">
<source>{VAR_PLURAL, plural, =1 {One page} other {<x id="INTERPOLATION"/> pages}}</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
<context context-type="linenumber">25</context>
</context-group>
</trans-unit>
<trans-unit id="7508164375697837821" datatype="html">
<source>Use metadata from:</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
<context context-type="linenumber">34</context>
<context context-type="linenumber">22</context>
</context-group>
</trans-unit>
<trans-unit id="2020403212524346652" datatype="html">
<source>Regenerate all metadata</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
<context context-type="linenumber">36</context>
<context context-type="linenumber">24</context>
</context-group>
</trans-unit>
<trans-unit id="2710430925353472741" datatype="html">
<source>Try to include archive version in merge for non-PDF files</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
<context context-type="linenumber">44</context>
<context context-type="linenumber">32</context>
</context-group>
</trans-unit>
<trans-unit id="5612366187076076264" datatype="html">
<source>Delete original documents after successful merge</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
<context context-type="linenumber">48</context>
<context context-type="linenumber">36</context>
</context-group>
</trans-unit>
<trans-unit id="5138283234724909648" datatype="html">
<source>Note that only PDFs will be included.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
<context context-type="linenumber">51</context>
<context context-type="linenumber">39</context>
</context-group>
</trans-unit>
<trans-unit id="1309641780471803652" datatype="html">
@@ -3512,7 +3505,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1814</context>
<context context-type="linenumber">1808</context>
</context-group>
</trans-unit>
<trans-unit id="6661109599266152398" datatype="html">
@@ -3523,7 +3516,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1815</context>
<context context-type="linenumber">1809</context>
</context-group>
</trans-unit>
<trans-unit id="5162686434580248853" datatype="html">
@@ -3534,7 +3527,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1816</context>
<context context-type="linenumber">1810</context>
</context-group>
</trans-unit>
<trans-unit id="8157388568390631653" datatype="html">
@@ -5495,7 +5488,7 @@
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1336</context>
<context context-type="linenumber">1333</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
@@ -7702,81 +7695,81 @@
<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">411</context>
<context context-type="linenumber">408</context>
</context-group>
</trans-unit>
<trans-unit id="2218903673684131427" datatype="html">
<source>An error occurred loading content: <x id="PH" equiv-text="err.message ?? 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">512,514</context>
<context context-type="linenumber">509,511</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">959,961</context>
<context context-type="linenumber">956,958</context>
</context-group>
</trans-unit>
<trans-unit id="6357361810318120957" datatype="html">
<source>Document was updated</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">632</context>
<context context-type="linenumber">629</context>
</context-group>
</trans-unit>
<trans-unit id="5154064822428631306" datatype="html">
<source>Document was updated at <x id="PH" equiv-text="formattedModified"/>.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">633</context>
<context context-type="linenumber">630</context>
</context-group>
</trans-unit>
<trans-unit id="8462497568316256794" datatype="html">
<source>Reload to discard your local unsaved edits and load the latest remote version.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">634</context>
<context context-type="linenumber">631</context>
</context-group>
</trans-unit>
<trans-unit id="7967484035994732534" datatype="html">
<source>Reload</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">636</context>
<context context-type="linenumber">633</context>
</context-group>
</trans-unit>
<trans-unit id="2907037627372942104" datatype="html">
<source>Document reloaded with latest changes.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">692</context>
<context context-type="linenumber">689</context>
</context-group>
</trans-unit>
<trans-unit id="6435639868943916539" datatype="html">
<source>Document reloaded.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">703</context>
<context context-type="linenumber">700</context>
</context-group>
</trans-unit>
<trans-unit id="6142395741265832184" datatype="html">
<source>Next document</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">805</context>
<context context-type="linenumber">802</context>
</context-group>
</trans-unit>
<trans-unit id="651985345816518480" datatype="html">
<source>Previous document</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">815</context>
<context context-type="linenumber">812</context>
</context-group>
</trans-unit>
<trans-unit id="2885986061416655600" datatype="html">
<source>Close document</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">823</context>
<context context-type="linenumber">820</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/services/open-documents.service.ts</context>
@@ -7787,67 +7780,67 @@
<source>Save document</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">830</context>
<context context-type="linenumber">827</context>
</context-group>
</trans-unit>
<trans-unit id="1784543155727940353" datatype="html">
<source>Save and close / next</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">839</context>
<context context-type="linenumber">836</context>
</context-group>
</trans-unit>
<trans-unit id="7427704425579737895" datatype="html">
<source>Error retrieving version content</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">943</context>
<context context-type="linenumber">940</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">1000</context>
<context context-type="linenumber">997</context>
</context-group>
</trans-unit>
<trans-unit id="2194092841814123758" datatype="html">
<source>Document &quot;<x id="PH" equiv-text="newValues.title"/>&quot; 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">1212</context>
<context context-type="linenumber">1209</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">1239</context>
<context context-type="linenumber">1236</context>
</context-group>
</trans-unit>
<trans-unit id="6626387786259219838" datatype="html">
<source>Error saving document &quot;<x id="PH" equiv-text="this.document.title"/>&quot;</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1245</context>
<context context-type="linenumber">1242</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">1300</context>
<context context-type="linenumber">1297</context>
</context-group>
</trans-unit>
<trans-unit id="8410796510716511826" datatype="html">
<source>Do you really want to move the document &quot;<x id="PH" equiv-text="this.document.title"/>&quot; 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">1333</context>
<context context-type="linenumber">1330</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">1334</context>
<context context-type="linenumber">1331</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
@@ -7858,14 +7851,14 @@
<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">1355</context>
<context context-type="linenumber">1352</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">1375</context>
<context context-type="linenumber">1372</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
@@ -7876,102 +7869,102 @@
<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">1376</context>
<context context-type="linenumber">1373</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">1377</context>
<context context-type="linenumber">1374</context>
</context-group>
</trans-unit>
<trans-unit id="4700389117298802932" datatype="html">
<source>Reprocess operation for &quot;<x id="PH" equiv-text="this.document.title"/>&quot; 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">1387</context>
<context context-type="linenumber">1384</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">1398</context>
<context context-type="linenumber">1395</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">1461</context>
<context context-type="linenumber">1458</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">1541</context>
<context context-type="linenumber">1538</context>
</context-group>
</trans-unit>
<trans-unit id="4663705961777238777" datatype="html">
<source>PDF edit operation for &quot;<x id="PH" equiv-text="this.document.title"/>&quot; 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">1781</context>
<context context-type="linenumber">1775</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">1793</context>
<context context-type="linenumber">1787</context>
</context-group>
</trans-unit>
<trans-unit id="6172690334763056188" datatype="html">
<source>Please enter the current password before attempting to remove it.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1804</context>
<context context-type="linenumber">1798</context>
</context-group>
</trans-unit>
<trans-unit id="968660764814228922" datatype="html">
<source>Password removal operation for &quot;<x id="PH" equiv-text="this.document.title"/>&quot; 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">1838</context>
<context context-type="linenumber">1830</context>
</context-group>
</trans-unit>
<trans-unit id="2282118435712883014" datatype="html">
<source>Error executing password removal operation</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1852</context>
<context context-type="linenumber">1844</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">1891</context>
<context context-type="linenumber">1883</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">1903</context>
<context context-type="linenumber">1895</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">1968</context>
<context context-type="linenumber">1960</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">1972</context>
<context context-type="linenumber">1964</context>
</context-group>
</trans-unit>
<trans-unit id="4958946940233632319" datatype="html">

View File

@@ -10,22 +10,10 @@
<ul class="list-group"
cdkDropList
(cdkDropListDropped)="onDrop($event)">
@for (document of documents; track document.id) {
<li class="list-group-item d-flex align-items-center" cdkDrag>
@for (documentID of documentIDs; track documentID) {
<li class="list-group-item" cdkDrag>
<i-bs name="grip-vertical" class="me-2"></i-bs>
<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>
{{getDocument(documentID)?.title}}
</li>
}
</ul>

View File

@@ -3,14 +3,11 @@ import {
DragDropModule,
moveItemInArray,
} from '@angular/cdk/drag-drop'
import { AsyncPipe } from '@angular/common'
import { Component, OnInit, inject } from '@angular/core'
import { FormsModule, ReactiveFormsModule } from '@angular/forms'
import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
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 { PermissionsService } from 'src/app/services/permissions.service'
import { DocumentService } from 'src/app/services/rest/document.service'
import { ConfirmDialogComponent } from '../confirm-dialog.component'
@@ -20,9 +17,6 @@ import { ConfirmDialogComponent } from '../confirm-dialog.component'
templateUrl: './merge-confirm-dialog.component.html',
styleUrl: './merge-confirm-dialog.component.scss',
imports: [
AsyncPipe,
CorrespondentNamePipe,
CustomDatePipe,
DragDropModule,
FormsModule,
ReactiveFormsModule,

View File

@@ -3,7 +3,6 @@ import { provideHttpClientTesting } from '@angular/common/http/testing'
import { ComponentFixture, TestBed } from '@angular/core/testing'
import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
import { NgxBootstrapIconsModule, allIcons } from 'ngx-bootstrap-icons'
import { DocumentService } from 'src/app/services/rest/document.service'
import { PDFEditorComponent } from './pdf-editor.component'
describe('PDFEditorComponent', () => {
@@ -140,16 +139,4 @@ describe('PDFEditorComponent', () => {
expect(component.pages[1].page).toBe(2)
expect(component.pages[2].page).toBe(3)
})
it('should include selected version in preview source when provided', () => {
const documentService = TestBed.inject(DocumentService)
const previewSpy = jest
.spyOn(documentService, 'getPreviewUrl')
.mockReturnValue('preview-version')
component.documentID = 3
component.versionID = 10
expect(component.pdfSrc).toBe('preview-version')
expect(previewSpy).toHaveBeenCalledWith(3, false, 10)
})
})

View File

@@ -46,7 +46,6 @@ export class PDFEditorComponent extends ConfirmDialogComponent {
activeModal: NgbActiveModal = inject(NgbActiveModal)
documentID: number
versionID?: number
pages: PageOperation[] = []
totalPages = 0
editMode: PdfEditorEditMode = this.settingsService.get(
@@ -56,11 +55,7 @@ export class PDFEditorComponent extends ConfirmDialogComponent {
includeMetadata: boolean = true
get pdfSrc(): string {
return this.documentService.getPreviewUrl(
this.documentID,
false,
this.versionID
)
return this.documentService.getPreviewUrl(this.documentID)
}
pdfLoaded(pdf: PngxPdfDocumentProxy) {

View File

@@ -1661,25 +1661,22 @@ describe('DocumentDetailComponent', () => {
const closeSpy = jest.spyOn(openDocumentsService, 'closeDocument')
const errorSpy = jest.spyOn(toastService, 'showError')
initNormally()
component.selectedVersionId = 10
component.editPdf()
expect(modal).not.toBeUndefined()
modal.componentInstance.documentID = doc.id
expect(modal.componentInstance.versionID).toBe(10)
modal.componentInstance.pages = [{ page: 1, rotate: 0, splitAfter: false }]
modal.componentInstance.confirm()
let req = httpTestingController.expectOne(
`${environment.apiBaseUrl}documents/bulk_edit/`
)
expect(req.request.body).toEqual({
documents: [10],
documents: [doc.id],
method: 'edit_pdf',
parameters: {
operations: [{ page: 1, rotate: 0, doc: 0 }],
delete_original: false,
update_document: false,
include_metadata: true,
source_mode: 'explicit_selection',
},
})
req.error(new ErrorEvent('failed'))
@@ -1701,7 +1698,6 @@ describe('DocumentDetailComponent', () => {
let modal: NgbModalRef
modalService.activeInstances.subscribe((m) => (modal = m[0]))
initNormally()
component.selectedVersionId = 10
component.password = 'secret'
component.removePassword()
const dialog =
@@ -1714,14 +1710,13 @@ describe('DocumentDetailComponent', () => {
`${environment.apiBaseUrl}documents/bulk_edit/`
)
expect(req.request.body).toEqual({
documents: [10],
documents: [doc.id],
method: 'remove_password',
parameters: {
password: 'secret',
update_document: false,
include_metadata: false,
delete_original: true,
source_mode: 'explicit_selection',
},
})
req.flush(true)

View File

@@ -74,10 +74,7 @@ import {
import { CorrespondentService } from 'src/app/services/rest/correspondent.service'
import { CustomFieldsService } from 'src/app/services/rest/custom-fields.service'
import { DocumentTypeService } from 'src/app/services/rest/document-type.service'
import {
BulkEditSourceMode,
DocumentService,
} from 'src/app/services/rest/document.service'
import { DocumentService } from 'src/app/services/rest/document.service'
import { SavedViewService } from 'src/app/services/rest/saved-view.service'
import { StoragePathService } from 'src/app/services/rest/storage-path.service'
import { TagService } from 'src/app/services/rest/tag.service'
@@ -1756,23 +1753,20 @@ export class DocumentDetailComponent
size: 'xl',
scrollable: true,
})
const sourceDocumentId = this.selectedVersionId ?? this.document.id
modal.componentInstance.title = $localize`PDF Editor`
modal.componentInstance.btnCaption = $localize`Proceed`
modal.componentInstance.documentID = this.document.id
modal.componentInstance.versionID = sourceDocumentId
modal.componentInstance.confirmClicked
.pipe(takeUntil(this.unsubscribeNotifier))
.subscribe(() => {
modal.componentInstance.buttonsEnabled = false
this.documentsService
.bulkEdit([sourceDocumentId], 'edit_pdf', {
.bulkEdit([this.document.id], 'edit_pdf', {
operations: modal.componentInstance.getOperations(),
delete_original: modal.componentInstance.deleteOriginal,
update_document:
modal.componentInstance.editMode == PdfEditorEditMode.Update,
include_metadata: modal.componentInstance.includeMetadata,
source_mode: BulkEditSourceMode.EXPLICIT_SELECTION,
})
.pipe(first(), takeUntil(this.unsubscribeNotifier))
.subscribe({
@@ -1818,18 +1812,16 @@ export class DocumentDetailComponent
modal.componentInstance.confirmClicked
.pipe(takeUntil(this.unsubscribeNotifier))
.subscribe(() => {
const sourceDocumentId = this.selectedVersionId ?? this.document.id
const dialog =
modal.componentInstance as PasswordRemovalConfirmDialogComponent
dialog.buttonsEnabled = false
this.networkActive = true
this.documentsService
.bulkEdit([sourceDocumentId], 'remove_password', {
.bulkEdit([this.document.id], 'remove_password', {
password: this.password,
update_document: dialog.updateDocument,
include_metadata: dialog.includeMetadata,
delete_original: dialog.deleteOriginal,
source_mode: BulkEditSourceMode.EXPLICIT_SELECTION,
})
.pipe(first(), takeUntil(this.unsubscribeNotifier))
.subscribe({

View File

@@ -37,11 +37,6 @@ export interface SelectionData {
selected_custom_fields: SelectionDataItem[]
}
export enum BulkEditSourceMode {
LATEST_VERSION = 'latest_version',
EXPLICIT_SELECTION = 'explicit_selection',
}
@Injectable({
providedIn: 'root',
})

View File

@@ -29,21 +29,12 @@ from documents.plugins.helpers import DocumentsStatusManager
from documents.tasks import bulk_update_documents
from documents.tasks import consume_file
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
if TYPE_CHECKING:
from django.contrib.auth.models import User
logger: logging.Logger = logging.getLogger("paperless.bulk_edit")
SourceMode = Literal["latest_version", "explicit_selection"]
class SourceModeChoices:
LATEST_VERSION: SourceMode = "latest_version"
EXPLICIT_SELECTION: SourceMode = "explicit_selection"
@shared_task(bind=True)
def restore_archive_serial_numbers_task(
@@ -81,21 +72,46 @@ def restore_archive_serial_numbers(backup: dict[int, int | None]) -> None:
logger.info(f"Restored archive serial numbers for documents {list(backup.keys())}")
def _resolve_root_and_source_doc(
doc: Document,
*,
source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
) -> tuple[Document, Document]:
root_doc = get_root_document(doc)
def _get_root_ids_by_doc_id(doc_ids: list[int]) -> dict[int, int]:
"""
Resolve each provided document id to its root document id.
if source_mode == SourceModeChoices.EXPLICIT_SELECTION:
return root_doc, doc
- If the id is already a root document: root id is itself.
- If the id is a version document: root id is its `root_document_id`.
"""
qs = Document.objects.filter(id__in=doc_ids).only("id", "root_document_id")
return {doc.id: doc.root_document_id or doc.id for doc in qs}
# Version IDs are explicit by default, only a selected root resolves to latest
if doc.root_document_id is not None:
return root_doc, doc
return root_doc, get_latest_version_for_root(root_doc)
def _get_root_and_current_docs_by_root_id(
root_ids: set[int],
) -> tuple[dict[int, Document], dict[int, Document]]:
"""
Returns:
- root_docs: root_id -> root Document
- current_docs: root_id -> newest version Document (or root if none)
"""
root_docs = {
doc.id: doc
for doc in Document.objects.filter(id__in=root_ids).select_related(
"owner",
)
}
latest_versions_by_root_id: dict[int, Document] = {}
for version_doc in Document.objects.filter(root_document_id__in=root_ids).order_by(
"root_document_id",
"-id",
):
root_id = version_doc.root_document_id
if root_id is None:
continue
latest_versions_by_root_id.setdefault(root_id, version_doc)
current_docs: dict[int, Document] = {
root_id: latest_versions_by_root_id.get(root_id, root_docs[root_id])
for root_id in root_docs
}
return root_docs, current_docs
def set_correspondent(
@@ -405,32 +421,21 @@ def rotate(
doc_ids: list[int],
degrees: int,
*,
source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
user: User | None = None,
) -> Literal["OK"]:
logger.info(
f"Attempting to rotate {len(doc_ids)} documents by {degrees} degrees.",
)
docs_by_id = {
doc.id: doc
for doc in Document.objects.select_related("root_document").filter(
id__in=doc_ids,
)
}
docs_by_root_id: dict[int, tuple[Document, Document]] = {}
for doc_id in doc_ids:
doc = docs_by_id.get(doc_id)
if doc is None:
continue
root_doc, source_doc = _resolve_root_and_source_doc(
doc,
source_mode=source_mode,
)
docs_by_root_id.setdefault(root_doc.id, (root_doc, source_doc))
doc_to_root_id = _get_root_ids_by_doc_id(doc_ids)
root_ids = set(doc_to_root_id.values())
root_docs_by_id, current_docs_by_root_id = _get_root_and_current_docs_by_root_id(
root_ids,
)
import pikepdf
for root_doc, source_doc in docs_by_root_id.values():
for root_id in root_ids:
root_doc = root_docs_by_id[root_id]
source_doc = current_docs_by_root_id[root_id]
if source_doc.mime_type != "application/pdf":
logger.warning(
f"Document {root_doc.id} is not a PDF, skipping rotation.",
@@ -476,14 +481,12 @@ def merge(
metadata_document_id: int | None = None,
delete_originals: bool = False,
archive_fallback: bool = False,
source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
user: User | None = None,
) -> Literal["OK"]:
logger.info(
f"Attempting to merge {len(doc_ids)} documents into a single document.",
)
qs = Document.objects.select_related("root_document").filter(id__in=doc_ids)
docs_by_id = {doc.id: doc for doc in qs}
qs = Document.objects.filter(id__in=doc_ids)
affected_docs: list[int] = []
import pikepdf
@@ -492,20 +495,14 @@ def merge(
handoff_asn: int | None = None
# use doc_ids to preserve order
for doc_id in doc_ids:
doc = docs_by_id.get(doc_id)
if doc is None:
continue
_, source_doc = _resolve_root_and_source_doc(
doc,
source_mode=source_mode,
)
doc = qs.get(id=doc_id)
try:
doc_path = (
source_doc.archive_path
doc.archive_path
if archive_fallback
and source_doc.mime_type != "application/pdf"
and source_doc.has_archive_version
else source_doc.source_path
and doc.mime_type != "application/pdf"
and doc.has_archive_version
else doc.source_path
)
with pikepdf.open(str(doc_path)) as pdf:
version = max(version, pdf.pdf_version)
@@ -587,23 +584,18 @@ def split(
pages: list[list[int]],
*,
delete_originals: bool = False,
source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
user: User | None = None,
) -> Literal["OK"]:
logger.info(
f"Attempting to split document {doc_ids[0]} into {len(pages)} documents",
)
doc = Document.objects.select_related("root_document").get(id=doc_ids[0])
_, source_doc = _resolve_root_and_source_doc(
doc,
source_mode=source_mode,
)
doc = Document.objects.get(id=doc_ids[0])
import pikepdf
consume_tasks = []
try:
with pikepdf.open(source_doc.source_path) as pdf:
with pikepdf.open(doc.source_path) as pdf:
for idx, split_doc in enumerate(pages):
dst: pikepdf.Pdf = pikepdf.new()
for page in split_doc:
@@ -667,17 +659,25 @@ def delete_pages(
doc_ids: list[int],
pages: list[int],
*,
source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
user: User | None = None,
) -> Literal["OK"]:
logger.info(
f"Attempting to delete pages {pages} from {len(doc_ids)} documents",
)
doc = Document.objects.select_related("root_document").get(id=doc_ids[0])
root_doc, source_doc = _resolve_root_and_source_doc(
doc,
source_mode=source_mode,
root_doc: Document
if doc.root_document_id is None or doc.root_document is None:
root_doc = doc
else:
root_doc = doc.root_document
source_doc = (
Document.objects.filter(Q(id=root_doc.id) | Q(root_document=root_doc))
.order_by("-id")
.first()
)
if source_doc is None:
source_doc = root_doc
pages = sorted(pages) # sort pages to avoid index issues
import pikepdf
@@ -722,7 +722,6 @@ def edit_pdf(
delete_original: bool = False,
update_document: bool = False,
include_metadata: bool = True,
source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
user: User | None = None,
) -> Literal["OK"]:
"""
@@ -737,10 +736,19 @@ def edit_pdf(
f"Editing PDF of document {doc_ids[0]} with {len(operations)} operations",
)
doc = Document.objects.select_related("root_document").get(id=doc_ids[0])
root_doc, source_doc = _resolve_root_and_source_doc(
doc,
source_mode=source_mode,
root_doc: Document
if doc.root_document_id is None or doc.root_document is None:
root_doc = doc
else:
root_doc = doc.root_document
source_doc = (
Document.objects.filter(Q(id=root_doc.id) | Q(root_document=root_doc))
.order_by("-id")
.first()
)
if source_doc is None:
source_doc = root_doc
import pikepdf
pdf_docs: list[pikepdf.Pdf] = []
@@ -851,7 +859,6 @@ def remove_password(
update_document: bool = False,
delete_original: bool = False,
include_metadata: bool = True,
source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
user: User | None = None,
) -> Literal["OK"]:
"""
@@ -861,10 +868,19 @@ def remove_password(
for doc_id in doc_ids:
doc = Document.objects.select_related("root_document").get(id=doc_id)
root_doc, source_doc = _resolve_root_and_source_doc(
doc,
source_mode=source_mode,
root_doc: Document
if doc.root_document_id is None or doc.root_document is None:
root_doc = doc
else:
root_doc = doc.root_document
source_doc = (
Document.objects.filter(Q(id=root_doc.id) | Q(root_document=root_doc))
.order_by("-id")
.first()
)
if source_doc is None:
source_doc = root_doc
try:
logger.info(
f"Attempting password removal from document {doc_ids[0]}",

View File

@@ -1,5 +1,4 @@
import datetime
import hashlib
import os
import tempfile
from enum import StrEnum
@@ -48,6 +47,7 @@ from documents.signals import document_consumption_started
from documents.signals import document_updated
from documents.signals.handlers import run_workflows
from documents.templating.workflows import parse_w_workflow_placeholders
from documents.utils import compute_checksum
from documents.utils import copy_basic_file_stats
from documents.utils import copy_file_with_basic_stats
from documents.utils import run_subprocess
@@ -196,9 +196,7 @@ class ConsumerPlugin(
version_doc = Document(
root_document=root_doc_frozen,
version_index=next_version_index + 1,
checksum=hashlib.md5(
file_for_checksum.read_bytes(),
).hexdigest(),
checksum=compute_checksum(file_for_checksum),
content=text or "",
page_count=page_count,
mime_type=mime_type,
@@ -656,10 +654,9 @@ class ConsumerPlugin(
document.archive_path,
)
with Path(archive_path).open("rb") as f:
document.archive_checksum = hashlib.md5(
f.read(),
).hexdigest()
document.archive_checksum = compute_checksum(
Path(archive_path),
)
# Don't save with the lock active. Saving will cause the file
# renaming logic to acquire the lock as well.
@@ -800,7 +797,7 @@ class ConsumerPlugin(
title=title[:127],
content=text,
mime_type=mime_type,
checksum=hashlib.md5(file_for_checksum.read_bytes()).hexdigest(),
checksum=compute_checksum(file_for_checksum),
created=create_date,
modified=create_date,
page_count=page_count,
@@ -917,10 +914,9 @@ class ConsumerPreflightPlugin(
def pre_check_duplicate(self) -> None:
"""
Using the MD5 of the file, check this exact file doesn't already exist
Using the SHA256 of the file, check this exact file doesn't already exist
"""
with Path(self.input_doc.original_file).open("rb") as f:
checksum = hashlib.md5(f.read()).hexdigest()
checksum = compute_checksum(Path(self.input_doc.original_file))
existing_doc = Document.global_objects.filter(
Q(checksum=checksum) | Q(archive_checksum=checksum),
)

View File

@@ -3,6 +3,7 @@ import json
import os
import shutil
import tempfile
from itertools import chain
from itertools import islice
from pathlib import Path
from typing import TYPE_CHECKING
@@ -57,6 +58,7 @@ from documents.models import WorkflowTrigger
from documents.settings import EXPORTER_ARCHIVE_NAME
from documents.settings import EXPORTER_FILE_NAME
from documents.settings import EXPORTER_THUMBNAIL_NAME
from documents.utils import compute_checksum
from documents.utils import copy_file_with_basic_stats
from paperless import version
from paperless.models import ApplicationConfiguration
@@ -80,87 +82,6 @@ def serialize_queryset_batched(
yield serializers.serialize("python", chunk)
class StreamingManifestWriter:
"""Incrementally writes a JSON array to a file, one record at a time.
Writes to <target>.tmp first; on close(), optionally BLAKE2b-compares
with the existing file (--compare-json) and renames or discards accordingly.
On exception, discard() deletes the tmp file and leaves the original intact.
"""
def __init__(
self,
path: Path,
*,
compare_json: bool = False,
files_in_export_dir: "set[Path] | None" = None,
) -> None:
self._path = path.resolve()
self._tmp_path = self._path.with_suffix(self._path.suffix + ".tmp")
self._compare_json = compare_json
self._files_in_export_dir: set[Path] = (
files_in_export_dir if files_in_export_dir is not None else set()
)
self._file = None
self._first = True
def open(self) -> None:
self._path.parent.mkdir(parents=True, exist_ok=True)
self._file = self._tmp_path.open("w", encoding="utf-8")
self._file.write("[")
self._first = True
def write_record(self, record: dict) -> None:
if not self._first:
self._file.write(",\n")
else:
self._first = False
self._file.write(
json.dumps(record, cls=DjangoJSONEncoder, indent=2, ensure_ascii=False),
)
def write_batch(self, records: list[dict]) -> None:
for record in records:
self.write_record(record)
def close(self) -> None:
if self._file is None:
return
self._file.write("\n]")
self._file.close()
self._file = None
self._finalize()
def discard(self) -> None:
if self._file is not None:
self._file.close()
self._file = None
if self._tmp_path.exists():
self._tmp_path.unlink()
def _finalize(self) -> None:
"""Compare with existing file (if --compare-json) then rename or discard tmp."""
if self._path in self._files_in_export_dir:
self._files_in_export_dir.remove(self._path)
if self._compare_json:
existing_hash = hashlib.blake2b(self._path.read_bytes()).hexdigest()
new_hash = hashlib.blake2b(self._tmp_path.read_bytes()).hexdigest()
if existing_hash == new_hash:
self._tmp_path.unlink()
return
self._tmp_path.rename(self._path)
def __enter__(self) -> "StreamingManifestWriter":
self.open()
return self
def __exit__(self, exc_type, exc_val, exc_tb) -> None:
if exc_type is not None:
self.discard()
else:
self.close()
class Command(CryptMixin, BaseCommand):
help = (
"Decrypt and rename all files in our collection into a given target "
@@ -402,83 +323,95 @@ class Command(CryptMixin, BaseCommand):
if settings.AUDIT_LOG_ENABLED:
manifest_key_to_object_query["log_entries"] = LogEntry.objects.all()
# Crypto setup before streaming begins
if self.passphrase:
self.setup_crypto(passphrase=self.passphrase)
elif MailAccount.objects.count() > 0 or SocialToken.objects.count() > 0:
self.stdout.write(
self.style.NOTICE(
"No passphrase was given, sensitive fields will be in plaintext",
),
)
with transaction.atomic():
manifest_dict = {}
document_manifest: list[dict] = []
manifest_path = (self.target / "manifest.json").resolve()
with StreamingManifestWriter(
manifest_path,
compare_json=self.compare_json,
files_in_export_dir=self.files_in_export_dir,
) as writer:
with transaction.atomic():
for key, qs in manifest_key_to_object_query.items():
if key == "documents":
# Accumulate for file-copy loop; written to manifest after
for batch in serialize_queryset_batched(
qs,
# Build an overall manifest
for key, object_query in manifest_key_to_object_query.items():
manifest_dict[key] = list(
chain.from_iterable(
serialize_queryset_batched(
object_query,
batch_size=self.batch_size,
):
for record in batch:
self._encrypt_record_inline(record)
document_manifest.extend(batch)
elif self.split_manifest and key in (
"notes",
"custom_field_instances",
):
# Written per-document in _write_split_manifest
pass
else:
for batch in serialize_queryset_batched(
qs,
batch_size=self.batch_size,
):
for record in batch:
self._encrypt_record_inline(record)
writer.write_batch(batch)
document_map: dict[int, Document] = {
d.pk: d for d in Document.objects.order_by("id")
}
# 3. Export files from each document
for document_dict in tqdm.tqdm(
document_manifest,
total=len(document_manifest),
disable=self.no_progress_bar,
):
document = document_map[document_dict["pk"]]
# 3.1. generate a unique filename
base_name = self.generate_base_name(document)
# 3.2. write filenames into manifest
original_target, thumbnail_target, archive_target = (
self.generate_document_targets(document, base_name, document_dict)
),
),
)
# 3.3. write files to target folder
if not self.data_only:
self.copy_document_files(
document,
original_target,
thumbnail_target,
archive_target,
)
self.encrypt_secret_fields(manifest_dict)
if self.split_manifest:
self._write_split_manifest(document_dict, document, base_name)
else:
writer.write_record(document_dict)
# These are treated specially and included in the per-document manifest
# if that setting is enabled. Otherwise, they are just exported to the bulk
# manifest
document_map: dict[int, Document] = {
d.pk: d for d in manifest_key_to_object_query["documents"]
}
document_manifest = manifest_dict["documents"]
# 3. Export files from each document
for index, document_dict in tqdm.tqdm(
enumerate(document_manifest),
total=len(document_manifest),
disable=self.no_progress_bar,
):
document = document_map[document_dict["pk"]]
# 3.1. generate a unique filename
base_name = self.generate_base_name(document)
# 3.2. write filenames into manifest
original_target, thumbnail_target, archive_target = (
self.generate_document_targets(document, base_name, document_dict)
)
# 3.3. write files to target folder
if not self.data_only:
self.copy_document_files(
document,
original_target,
thumbnail_target,
archive_target,
)
if self.split_manifest:
manifest_name = base_name.with_name(f"{base_name.stem}-manifest.json")
if self.use_folder_prefix:
manifest_name = Path("json") / manifest_name
manifest_name = (self.target / manifest_name).resolve()
manifest_name.parent.mkdir(parents=True, exist_ok=True)
content = [document_manifest[index]]
content += list(
filter(
lambda d: d["fields"]["document"] == document_dict["pk"],
manifest_dict["notes"],
),
)
content += list(
filter(
lambda d: d["fields"]["document"] == document_dict["pk"],
manifest_dict["custom_field_instances"],
),
)
self.check_and_write_json(
content,
manifest_name,
)
# These were exported already
if self.split_manifest:
del manifest_dict["documents"]
del manifest_dict["notes"]
del manifest_dict["custom_field_instances"]
# 4.1 write primary manifest to target folder
manifest = []
for key, item in manifest_dict.items():
manifest.extend(item)
manifest_path = (self.target / "manifest.json").resolve()
self.check_and_write_json(
manifest,
manifest_path,
)
# 4.2 write version information to target folder
extra_metadata_path = (self.target / "metadata.json").resolve()
@@ -600,42 +533,6 @@ class Command(CryptMixin, BaseCommand):
archive_target,
)
def _encrypt_record_inline(self, record: dict) -> None:
"""Encrypt sensitive fields in a single record, if passphrase is set."""
if not self.passphrase:
return
fields = self.CRYPT_FIELDS_BY_MODEL.get(record.get("model", ""))
if fields:
for field in fields:
if record["fields"].get(field):
record["fields"][field] = self.encrypt_string(
value=record["fields"][field],
)
def _write_split_manifest(
self,
document_dict: dict,
document: Document,
base_name: Path,
) -> None:
"""Write per-document manifest file for --split-manifest mode."""
content = [document_dict]
content.extend(
serializers.serialize("python", Note.objects.filter(document=document)),
)
content.extend(
serializers.serialize(
"python",
CustomFieldInstance.objects.filter(document=document),
),
)
manifest_name = base_name.with_name(f"{base_name.stem}-manifest.json")
if self.use_folder_prefix:
manifest_name = Path("json") / manifest_name
manifest_name = (self.target / manifest_name).resolve()
manifest_name.parent.mkdir(parents=True, exist_ok=True)
self.check_and_write_json(content, manifest_name)
def check_and_write_json(
self,
content: list[dict] | dict,
@@ -653,14 +550,14 @@ class Command(CryptMixin, BaseCommand):
if target in self.files_in_export_dir:
self.files_in_export_dir.remove(target)
if self.compare_json:
target_checksum = hashlib.blake2b(target.read_bytes()).hexdigest()
target_checksum = compute_checksum(target)
src_str = json.dumps(
content,
cls=DjangoJSONEncoder,
indent=2,
ensure_ascii=False,
)
src_checksum = hashlib.blake2b(src_str.encode("utf-8")).hexdigest()
src_checksum = hashlib.sha256(src_str.encode("utf-8")).hexdigest()
if src_checksum == target_checksum:
perform_write = False
@@ -696,7 +593,7 @@ class Command(CryptMixin, BaseCommand):
source_stat = source.stat()
target_stat = target.stat()
if self.compare_checksums and source_checksum:
target_checksum = hashlib.md5(target.read_bytes()).hexdigest()
target_checksum = compute_checksum(target)
perform_copy = target_checksum != source_checksum
elif (
source_stat.st_mtime != target_stat.st_mtime
@@ -710,3 +607,28 @@ class Command(CryptMixin, BaseCommand):
if perform_copy:
target.parent.mkdir(parents=True, exist_ok=True)
copy_file_with_basic_stats(source, target)
def encrypt_secret_fields(self, manifest: dict) -> None:
"""
Encrypts certain fields in the export. Currently limited to the mail account password
"""
if self.passphrase:
self.setup_crypto(passphrase=self.passphrase)
for crypt_config in self.CRYPT_FIELDS:
exporter_key = crypt_config["exporter_key"]
crypt_fields = crypt_config["fields"]
for manifest_record in manifest[exporter_key]:
for field in crypt_fields:
if manifest_record["fields"][field]:
manifest_record["fields"][field] = self.encrypt_string(
value=manifest_record["fields"][field],
)
elif MailAccount.objects.count() > 0 or SocialToken.objects.count() > 0:
self.stdout.write(
self.style.NOTICE(
"No passphrase was given, sensitive fields will be in plaintext",
),
)

View File

@@ -71,7 +71,7 @@ class CryptMixin:
key_size = 32
kdf_algorithm = "pbkdf2_sha256"
CRYPT_FIELDS: list[CryptFields] = [
CRYPT_FIELDS: CryptFields = [
{
"exporter_key": "mail_accounts",
"model_name": "paperless_mail.mailaccount",
@@ -89,10 +89,6 @@ class CryptMixin:
],
},
]
# O(1) lookup for per-record encryption; derived from CRYPT_FIELDS at class definition time
CRYPT_FIELDS_BY_MODEL: dict[str, list[str]] = {
cfg["model_name"]: cfg["fields"] for cfg in CRYPT_FIELDS
}
def get_crypt_params(self) -> dict[str, dict[str, str | int]]:
return {

View File

@@ -0,0 +1,130 @@
import hashlib
import logging
from pathlib import Path
from django.conf import settings
from django.db import migrations
from django.db import models
logger = logging.getLogger("paperless.migrations")
_CHUNK_SIZE = 65536 # 64 KiB — avoids loading entire files into memory
_BATCH_SIZE = 500 # documents per bulk_update call
_PROGRESS_INTERVAL = 500 # log a progress line every N documents
def _sha256(path: Path) -> str:
h = hashlib.sha256()
with path.open("rb") as fh:
while chunk := fh.read(_CHUNK_SIZE):
h.update(chunk)
return h.hexdigest()
def recompute_checksums(apps, schema_editor):
"""Recompute all document checksums from MD5 to SHA256."""
Document = apps.get_model("documents", "Document")
total = Document.objects.count()
if total == 0:
return
logger.info("Recomputing SHA-256 checksums for %d document(s)...", total)
batch: list = []
processed = 0
for doc in Document.objects.only(
"pk",
"filename",
"checksum",
"archive_filename",
"archive_checksum",
).iterator(chunk_size=_BATCH_SIZE):
updated_fields: list[str] = []
# Reconstruct source path the same way Document.source_path does
fname = str(doc.filename) if doc.filename else f"{doc.pk:07}.pdf"
source_path = (settings.ORIGINALS_DIR / Path(fname)).resolve()
if source_path.exists():
doc.checksum = _sha256(source_path)
updated_fields.append("checksum")
else:
logger.warning(
"Document %s: original file %s not found, checksum not updated.",
doc.pk,
source_path,
)
# Mirror Document.has_archive_version: archive_filename is not None
if doc.archive_filename is not None:
archive_path = (
settings.ARCHIVE_DIR / Path(str(doc.archive_filename))
).resolve()
if archive_path.exists():
doc.archive_checksum = _sha256(archive_path)
updated_fields.append("archive_checksum")
else:
logger.warning(
"Document %s: archive file %s not found, checksum not updated.",
doc.pk,
archive_path,
)
if updated_fields:
batch.append(doc)
processed += 1
if len(batch) >= _BATCH_SIZE:
Document.objects.bulk_update(batch, ["checksum", "archive_checksum"])
batch.clear()
if processed % _PROGRESS_INTERVAL == 0:
logger.info(
"SHA-256 checksum progress: %d/%d (%d%%)",
processed,
total,
processed * 100 // total,
)
if batch:
Document.objects.bulk_update(batch, ["checksum", "archive_checksum"])
logger.info(
"SHA-256 checksum recomputation complete: %d document(s) processed.",
total,
)
class Migration(migrations.Migration):
dependencies = [
("documents", "0016_document_version_index_and_more"),
]
operations = [
migrations.AlterField(
model_name="document",
name="checksum",
field=models.CharField(
editable=False,
help_text="The checksum of the original document.",
max_length=64,
verbose_name="checksum",
),
),
migrations.AlterField(
model_name="document",
name="archive_checksum",
field=models.CharField(
blank=True,
editable=False,
help_text="The checksum of the archived document.",
max_length=64,
null=True,
verbose_name="archive checksum",
),
),
migrations.RunPython(recompute_checksums, migrations.RunPython.noop),
]

View File

@@ -216,14 +216,14 @@ class Document(SoftDeleteModel, ModelWithOwner): # type: ignore[django-manager-
checksum = models.CharField(
_("checksum"),
max_length=32,
max_length=64,
editable=False,
help_text=_("The checksum of the original document."),
)
archive_checksum = models.CharField(
_("archive checksum"),
max_length=32,
max_length=64,
editable=False,
blank=True,
null=True,

View File

@@ -11,7 +11,6 @@ is an identity function that adds no overhead.
from __future__ import annotations
import hashlib
import logging
import uuid
from collections import defaultdict
@@ -30,6 +29,7 @@ from django.utils import timezone
from documents.models import Document
from documents.models import PaperlessTask
from documents.utils import compute_checksum
from paperless.config import GeneralConfig
logger = logging.getLogger("paperless.sanity_checker")
@@ -218,7 +218,7 @@ def _check_original(
present_files.discard(source_path)
try:
checksum = hashlib.md5(source_path.read_bytes()).hexdigest()
checksum = compute_checksum(source_path)
except OSError as e:
messages.error(doc.pk, f"Cannot read original file of document: {e}")
else:
@@ -255,7 +255,7 @@ def _check_archive(
present_files.discard(archive_path)
try:
checksum = hashlib.md5(archive_path.read_bytes()).hexdigest()
checksum = compute_checksum(archive_path)
except OSError as e:
messages.error(
doc.pk,

View File

@@ -703,6 +703,15 @@ class StoragePathField(serializers.PrimaryKeyRelatedField):
class CustomFieldSerializer(serializers.ModelSerializer):
def __init__(self, *args, **kwargs):
context = kwargs.get("context")
self.api_version = int(
context.get("request").version
if context and context.get("request")
else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
)
super().__init__(*args, **kwargs)
data_type = serializers.ChoiceField(
choices=CustomField.FieldDataType,
read_only=False,
@@ -782,6 +791,38 @@ class CustomFieldSerializer(serializers.ModelSerializer):
)
return super().validate(attrs)
def to_internal_value(self, data):
ret = super().to_internal_value(data)
if (
self.api_version < 7
and ret.get("data_type", "") == CustomField.FieldDataType.SELECT
and isinstance(ret.get("extra_data", {}).get("select_options"), list)
):
ret["extra_data"]["select_options"] = [
{
"label": option,
"id": get_random_string(length=16),
}
for option in ret["extra_data"]["select_options"]
]
return ret
def to_representation(self, instance):
ret = super().to_representation(instance)
if (
self.api_version < 7
and instance.data_type == CustomField.FieldDataType.SELECT
):
# Convert the select options with ids to a list of strings
ret["extra_data"]["select_options"] = [
option["label"] for option in ret["extra_data"]["select_options"]
]
return ret
class ReadWriteSerializerMethodField(serializers.SerializerMethodField):
"""
@@ -896,6 +937,50 @@ class CustomFieldInstanceSerializer(serializers.ModelSerializer):
return data
def get_api_version(self):
return int(
self.context.get("request").version
if self.context.get("request")
else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
)
def to_internal_value(self, data):
ret = super().to_internal_value(data)
if (
self.get_api_version() < 7
and ret.get("field").data_type == CustomField.FieldDataType.SELECT
and ret.get("value") is not None
):
# Convert the index of the option in the field.extra_data["select_options"]
# list to the options unique id
ret["value"] = ret.get("field").extra_data["select_options"][ret["value"]][
"id"
]
return ret
def to_representation(self, instance):
ret = super().to_representation(instance)
if (
self.get_api_version() < 7
and instance.field.data_type == CustomField.FieldDataType.SELECT
):
# return the index of the option in the field.extra_data["select_options"] list
ret["value"] = next(
(
idx
for idx, option in enumerate(
instance.field.extra_data["select_options"],
)
if option["id"] == instance.value
),
None,
)
return ret
class Meta:
model = CustomFieldInstance
fields = [
@@ -919,6 +1004,20 @@ class NotesSerializer(serializers.ModelSerializer):
fields = ["id", "note", "created", "user"]
ordering = ["-created"]
def to_representation(self, instance):
ret = super().to_representation(instance)
request = self.context.get("request")
api_version = int(
request.version if request else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
)
if api_version < 8 and "user" in ret:
user_id = ret["user"]["id"]
ret["user"] = user_id
return ret
def _get_viewable_duplicates(
document: Document,
@@ -1073,6 +1172,22 @@ class DocumentSerializer(
doc["content"] = getattr(instance, "effective_content") or ""
if self.truncate_content and "content" in self.fields:
doc["content"] = doc.get("content")[0:550]
request = self.context.get("request")
api_version = int(
request.version if request else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
)
if api_version < 9 and "created" in self.fields:
# provide created as a datetime for backwards compatibility
from django.utils import timezone
doc["created"] = timezone.make_aware(
datetime.combine(
instance.created,
datetime.min.time(),
),
).isoformat()
return doc
def to_internal_value(self, data):
@@ -1325,124 +1440,6 @@ class SavedViewSerializer(OwnedObjectSerializer):
"set_permissions",
]
def _get_api_version(self) -> int:
request = self.context.get("request")
return int(
request.version if request else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
)
def _update_legacy_visibility_preferences(
self,
saved_view_id: int,
*,
show_on_dashboard: bool | None,
show_in_sidebar: bool | None,
) -> UiSettings | None:
if show_on_dashboard is None and show_in_sidebar is None:
return None
request = self.context.get("request")
user = request.user if request else self.user
if user is None:
return None
ui_settings, _ = UiSettings.objects.get_or_create(
user=user,
defaults={"settings": {}},
)
current_settings = (
ui_settings.settings if isinstance(ui_settings.settings, dict) else {}
)
current_settings = dict(current_settings)
saved_views_settings = current_settings.get("saved_views")
if isinstance(saved_views_settings, dict):
saved_views_settings = dict(saved_views_settings)
else:
saved_views_settings = {}
dashboard_ids = {
int(raw_id)
for raw_id in saved_views_settings.get("dashboard_views_visible_ids", [])
if str(raw_id).isdigit()
}
sidebar_ids = {
int(raw_id)
for raw_id in saved_views_settings.get("sidebar_views_visible_ids", [])
if str(raw_id).isdigit()
}
if show_on_dashboard is not None:
if show_on_dashboard:
dashboard_ids.add(saved_view_id)
else:
dashboard_ids.discard(saved_view_id)
if show_in_sidebar is not None:
if show_in_sidebar:
sidebar_ids.add(saved_view_id)
else:
sidebar_ids.discard(saved_view_id)
saved_views_settings["dashboard_views_visible_ids"] = sorted(dashboard_ids)
saved_views_settings["sidebar_views_visible_ids"] = sorted(sidebar_ids)
current_settings["saved_views"] = saved_views_settings
ui_settings.settings = current_settings
ui_settings.save(update_fields=["settings"])
return ui_settings
def to_representation(self, instance):
# TODO: remove this and related backwards compatibility code when API v9 is dropped
ret = super().to_representation(instance)
request = self.context.get("request")
api_version = self._get_api_version()
if api_version < 10:
dashboard_ids = set()
sidebar_ids = set()
user = request.user if request else None
if user is not None and hasattr(user, "ui_settings"):
ui_settings = user.ui_settings.settings or None
saved_views = None
if isinstance(ui_settings, dict):
saved_views = ui_settings.get("saved_views", {})
if isinstance(saved_views, dict):
dashboard_ids = set(
saved_views.get("dashboard_views_visible_ids", []),
)
sidebar_ids = set(
saved_views.get("sidebar_views_visible_ids", []),
)
ret["show_on_dashboard"] = instance.id in dashboard_ids
ret["show_in_sidebar"] = instance.id in sidebar_ids
return ret
def to_internal_value(self, data):
# TODO: remove this and related backwards compatibility code when API v9 is dropped
api_version = self._get_api_version()
if api_version >= 10:
return super().to_internal_value(data)
normalized_data = data.copy()
legacy_visibility_fields = {}
boolean_field = serializers.BooleanField()
for field_name in ("show_on_dashboard", "show_in_sidebar"):
if field_name in normalized_data:
try:
legacy_visibility_fields[field_name] = (
boolean_field.to_internal_value(
normalized_data.get(field_name),
)
)
except serializers.ValidationError as exc:
raise serializers.ValidationError({field_name: exc.detail})
del normalized_data[field_name]
ret = super().to_internal_value(normalized_data)
ret.update(legacy_visibility_fields)
return ret
def validate(self, attrs):
attrs = super().validate(attrs)
if "display_fields" in attrs and attrs["display_fields"] is not None:
@@ -1462,9 +1459,6 @@ class SavedViewSerializer(OwnedObjectSerializer):
return attrs
def update(self, instance, validated_data):
request = self.context.get("request")
show_on_dashboard = validated_data.pop("show_on_dashboard", None)
show_in_sidebar = validated_data.pop("show_in_sidebar", None)
if "filter_rules" in validated_data:
rules_data = validated_data.pop("filter_rules")
else:
@@ -1486,19 +1480,9 @@ class SavedViewSerializer(OwnedObjectSerializer):
SavedViewFilterRule.objects.filter(saved_view=instance).delete()
for rule_data in rules_data:
SavedViewFilterRule.objects.create(saved_view=instance, **rule_data)
ui_settings = self._update_legacy_visibility_preferences(
instance.id,
show_on_dashboard=show_on_dashboard,
show_in_sidebar=show_in_sidebar,
)
if request is not None and ui_settings is not None:
request.user.ui_settings = ui_settings
return instance
def create(self, validated_data):
request = self.context.get("request")
show_on_dashboard = validated_data.pop("show_on_dashboard", None)
show_in_sidebar = validated_data.pop("show_in_sidebar", None)
rules_data = validated_data.pop("filter_rules")
if "user" in validated_data:
# backwards compatibility
@@ -1506,13 +1490,6 @@ class SavedViewSerializer(OwnedObjectSerializer):
saved_view = super().create(validated_data)
for rule_data in rules_data:
SavedViewFilterRule.objects.create(saved_view=saved_view, **rule_data)
ui_settings = self._update_legacy_visibility_preferences(
saved_view.id,
show_on_dashboard=show_on_dashboard,
show_in_sidebar=show_in_sidebar,
)
if request is not None and ui_settings is not None:
request.user.ui_settings = ui_settings
return saved_view
@@ -1746,15 +1723,6 @@ class BulkEditSerializer(
except ValueError:
raise serializers.ValidationError("invalid rotation degrees")
def _validate_source_mode(self, parameters) -> None:
source_mode = parameters.get(
"source_mode",
bulk_edit.SourceModeChoices.LATEST_VERSION,
)
if source_mode not in bulk_edit.SourceModeChoices.__dict__.values():
raise serializers.ValidationError("Invalid source_mode")
parameters["source_mode"] = source_mode
def _validate_parameters_split(self, parameters) -> None:
if "pages" not in parameters:
raise serializers.ValidationError("pages not specified")
@@ -1855,9 +1823,6 @@ class BulkEditSerializer(
method = attrs["method"]
parameters = attrs["parameters"]
if "source_mode" in parameters:
self._validate_source_mode(parameters)
if method == bulk_edit.set_correspondent:
self._validate_parameters_correspondent(parameters)
elif method == bulk_edit.set_document_type:

View File

@@ -1,5 +1,4 @@
import datetime
import hashlib
import logging
import shutil
import uuid
@@ -63,6 +62,7 @@ from documents.signals import document_updated
from documents.signals.handlers import cleanup_document_deletion
from documents.signals.handlers import run_workflows
from documents.signals.handlers import send_websocket_document_updated
from documents.utils import compute_checksum
from documents.workflows.utils import get_workflows_for_trigger
from paperless.config import AIConfig
from paperless_ai.indexing import llm_index_add_or_update_document
@@ -323,8 +323,7 @@ def update_document_content_maybe_archive_file(document_id) -> None:
with transaction.atomic():
oldDocument = Document.objects.get(pk=document.pk)
if parser.get_archive_path():
with Path(parser.get_archive_path()).open("rb") as f:
checksum = hashlib.md5(f.read()).hexdigest()
checksum = compute_checksum(Path(parser.get_archive_path()))
# I'm going to save first so that in case the file move
# fails, the database is rolled back.
# We also don't use save() since that triggers the filehandling

View File

@@ -82,8 +82,8 @@ def sample_doc(
return DocumentFactory(
title="test",
checksum="42995833e01aea9b3edee44bbfdd7ce1",
archive_checksum="62acb0bcbfbcaa62ca6ad3668e4e404b",
checksum="1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
archive_checksum="706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
content="test content",
pk=1,
filename="0000001.pdf",

View File

@@ -60,7 +60,7 @@ class DocumentFactory(DjangoModelFactory):
model = Document
title = factory.Faker("sentence", nb_words=4)
checksum = factory.Faker("md5")
checksum = factory.Faker("sha256")
content = factory.Faker("paragraph")
correspondent = None
document_type = None

View File

@@ -1395,10 +1395,7 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
{
"documents": [self.doc2.id],
"method": "edit_pdf",
"parameters": {
"operations": [{"page": 1}],
"source_mode": "explicit_selection",
},
"parameters": {"operations": [{"page": 1}]},
},
),
content_type="application/json",
@@ -1410,7 +1407,6 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
args, kwargs = m.call_args
self.assertCountEqual(args[0], [self.doc2.id])
self.assertEqual(kwargs["operations"], [{"page": 1}])
self.assertEqual(kwargs["source_mode"], "explicit_selection")
self.assertEqual(kwargs["user"], self.user)
def test_edit_pdf_invalid_params(self) -> None:
@@ -1576,24 +1572,6 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
response.content,
)
# invalid source mode
response = self.client.post(
"/api/documents/bulk_edit/",
json.dumps(
{
"documents": [self.doc2.id],
"method": "edit_pdf",
"parameters": {
"operations": [{"page": 1}],
"source_mode": "not_a_mode",
},
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
self.assertIn(b"Invalid source_mode", response.content)
@mock.patch("documents.serialisers.bulk_edit.edit_pdf")
def test_edit_pdf_page_out_of_bounds(self, m) -> None:
"""

View File

@@ -323,6 +323,113 @@ class TestCustomFieldsAPI(DirectoriesMixin, APITestCase):
mock_delay.assert_called_once_with(cf_select)
def test_custom_field_select_old_version(self) -> None:
"""
GIVEN:
- Nothing
WHEN:
- API post request is made for custom fields with api version header < 7
- API get request is made for custom fields with api version header < 7
THEN:
- The select options are created with unique ids
- The select options are returned in the old format
"""
resp = self.client.post(
self.ENDPOINT,
headers={"Accept": "application/json; version=6"},
data=json.dumps(
{
"data_type": "select",
"name": "Select Field",
"extra_data": {
"select_options": [
"Option 1",
"Option 2",
],
},
},
),
content_type="application/json",
)
self.assertEqual(resp.status_code, status.HTTP_201_CREATED)
field = CustomField.objects.get(name="Select Field")
self.assertEqual(
field.extra_data["select_options"],
[
{"label": "Option 1", "id": ANY},
{"label": "Option 2", "id": ANY},
],
)
resp = self.client.get(
f"{self.ENDPOINT}{field.id}/",
headers={"Accept": "application/json; version=6"},
)
self.assertEqual(resp.status_code, status.HTTP_200_OK)
data = resp.json()
self.assertEqual(
data["extra_data"]["select_options"],
[
"Option 1",
"Option 2",
],
)
def test_custom_field_select_value_old_version(self) -> None:
"""
GIVEN:
- Existing document with custom field select
WHEN:
- API post request is made to add the field for document with api version header < 7
- API get request is made for document with api version header < 7
THEN:
- The select value is returned in the old format, the index of the option
"""
custom_field_select = CustomField.objects.create(
name="Select Field",
data_type=CustomField.FieldDataType.SELECT,
extra_data={
"select_options": [
{"label": "Option 1", "id": "abc-123"},
{"label": "Option 2", "id": "def-456"},
],
},
)
doc = Document.objects.create(
title="WOW",
content="the content",
checksum="123",
mime_type="application/pdf",
)
resp = self.client.patch(
f"/api/documents/{doc.id}/",
headers={"Accept": "application/json; version=6"},
data=json.dumps(
{
"custom_fields": [
{"field": custom_field_select.id, "value": 1},
],
},
),
content_type="application/json",
)
self.assertEqual(resp.status_code, status.HTTP_200_OK)
doc.refresh_from_db()
self.assertEqual(doc.custom_fields.first().value, "def-456")
resp = self.client.get(
f"/api/documents/{doc.id}/",
headers={"Accept": "application/json; version=6"},
)
self.assertEqual(resp.status_code, status.HTTP_200_OK)
data = resp.json()
self.assertEqual(data["custom_fields"][0]["value"], 1)
def test_create_custom_field_monetary_validation(self) -> None:
"""
GIVEN:

View File

@@ -41,7 +41,6 @@ from documents.models import SavedView
from documents.models import ShareLink
from documents.models import StoragePath
from documents.models import Tag
from documents.models import UiSettings
from documents.models import Workflow
from documents.models import WorkflowAction
from documents.models import WorkflowTrigger
@@ -177,7 +176,7 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
results = response.data["results"]
self.assertEqual(len(results[0]), 0)
def test_document_fields_respects_created(self) -> None:
def test_document_fields_api_version_8_respects_created(self) -> None:
Document.objects.create(
title="legacy",
checksum="123",
@@ -187,6 +186,7 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
response = self.client.get(
"/api/documents/?fields=id",
headers={"Accept": "application/json; version=8"},
format="json",
)
self.assertEqual(response.status_code, status.HTTP_200_OK)
@@ -196,22 +196,25 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
response = self.client.get(
"/api/documents/?fields=id,created",
headers={"Accept": "application/json; version=8"},
format="json",
)
self.assertEqual(response.status_code, status.HTTP_200_OK)
results = response.data["results"]
self.assertIn("id", results[0])
self.assertIn("created", results[0])
self.assertEqual(results[0]["created"], "2024-01-15")
self.assertRegex(results[0]["created"], r"^2024-01-15T00:00:00.*$")
def test_document_created_format(self) -> None:
def test_document_legacy_created_format(self) -> None:
"""
GIVEN:
- Existing document
WHEN:
- Document is requested
- Document is requested with api version ≥ 9
- Document is requested with api version < 9
THEN:
- Document created field is returned as date
- Document created field is returned as datetime
"""
doc = Document.objects.create(
title="none",
@@ -222,6 +225,14 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
response = self.client.get(
f"/api/documents/{doc.pk}/",
headers={"Accept": "application/json; version=8"},
)
self.assertEqual(response.status_code, status.HTTP_200_OK)
self.assertRegex(response.data["created"], r"^2023-01-01T00:00:00.*$")
response = self.client.get(
f"/api/documents/{doc.pk}/",
headers={"Accept": "application/json; version=9"},
)
self.assertEqual(response.status_code, status.HTTP_200_OK)
self.assertEqual(response.data["created"], "2023-01-01")
@@ -2189,205 +2200,6 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
self.assertEqual(response.status_code, status.HTTP_200_OK)
self.assertEqual(response.data["count"], 0)
def test_saved_view_api_version_backward_compatibility(self) -> None:
"""
GIVEN:
- Saved views and UiSettings with visibility preferences
WHEN:
- API request with version=9 (legacy)
- API request with version=10 (current)
THEN:
- Version 9 returns show_on_dashboard and show_in_sidebar from UiSettings
- Version 10 omits these fields (moved to UiSettings)
"""
v1 = SavedView.objects.create(
owner=self.user,
name="dashboard_view",
sort_field="created",
)
v2 = SavedView.objects.create(
owner=self.user,
name="sidebar_view",
sort_field="created",
)
v3 = SavedView.objects.create(
owner=self.user,
name="hidden_view",
sort_field="created",
)
UiSettings.objects.update_or_create(
user=self.user,
defaults={
"settings": {
"saved_views": {
"dashboard_views_visible_ids": [v1.id],
"sidebar_views_visible_ids": [v2.id],
},
},
},
)
response_v9 = self.client.get(
"/api/saved_views/",
headers={"Accept": "application/json; version=9"},
format="json",
)
self.assertEqual(response_v9.status_code, status.HTTP_200_OK)
results_v9 = {r["id"]: r for r in response_v9.data["results"]}
self.assertIn("show_on_dashboard", results_v9[v1.id])
self.assertIn("show_in_sidebar", results_v9[v1.id])
self.assertTrue(results_v9[v1.id]["show_on_dashboard"])
self.assertFalse(results_v9[v1.id]["show_in_sidebar"])
self.assertTrue(results_v9[v2.id]["show_in_sidebar"])
self.assertFalse(results_v9[v2.id]["show_on_dashboard"])
self.assertFalse(results_v9[v3.id]["show_on_dashboard"])
self.assertFalse(results_v9[v3.id]["show_in_sidebar"])
response_v10 = self.client.get(
"/api/saved_views/",
headers={"Accept": "application/json; version=10"},
format="json",
)
self.assertEqual(response_v10.status_code, status.HTTP_200_OK)
results_v10 = {r["id"]: r for r in response_v10.data["results"]}
self.assertNotIn("show_on_dashboard", results_v10[v1.id])
self.assertNotIn("show_in_sidebar", results_v10[v1.id])
def test_saved_view_api_version_9_user_without_ui_settings(self) -> None:
"""
GIVEN:
- User with no UiSettings and a saved view
WHEN:
- API request with version=9
THEN:
- show_on_dashboard and show_in_sidebar are False (default)
"""
SavedView.objects.create(
owner=self.user,
name="test_view",
sort_field="created",
)
UiSettings.objects.filter(user=self.user).delete()
response = self.client.get(
"/api/saved_views/",
headers={"Accept": "application/json; version=9"},
format="json",
)
self.assertEqual(response.status_code, status.HTTP_200_OK)
result = response.data["results"][0]
self.assertFalse(result["show_on_dashboard"])
self.assertFalse(result["show_in_sidebar"])
def test_saved_view_api_version_9_create_writes_visibility_to_ui_settings(
self,
) -> None:
"""
GIVEN:
- No UiSettings for the current user
WHEN:
- A saved view is created through API version 9 with visibility flags
THEN:
- Visibility is persisted in UiSettings.saved_views
"""
UiSettings.objects.filter(user=self.user).delete()
response = self.client.post(
"/api/saved_views/",
{
"name": "legacy-v9-create",
"sort_field": "created",
"filter_rules": [],
"show_on_dashboard": True,
"show_in_sidebar": False,
},
headers={"Accept": "application/json; version=9"},
format="json",
)
self.assertEqual(response.status_code, status.HTTP_201_CREATED)
self.assertTrue(response.data["show_on_dashboard"])
self.assertFalse(response.data["show_in_sidebar"])
self.user.refresh_from_db()
self.assertTrue(hasattr(self.user, "ui_settings"))
saved_view_settings = self.user.ui_settings.settings["saved_views"]
self.assertListEqual(
saved_view_settings["dashboard_views_visible_ids"],
[response.data["id"]],
)
self.assertListEqual(saved_view_settings["sidebar_views_visible_ids"], [])
def test_saved_view_api_version_9_patch_writes_visibility_to_ui_settings(
self,
) -> None:
"""
GIVEN:
- Existing saved views and UiSettings visibility ids
WHEN:
- A saved view is updated through API version 9 visibility flags
THEN:
- The per-user UiSettings visibility ids are updated
"""
v1 = SavedView.objects.create(
owner=self.user,
name="legacy-v9-patch-1",
sort_field="created",
)
v2 = SavedView.objects.create(
owner=self.user,
name="legacy-v9-patch-2",
sort_field="created",
)
UiSettings.objects.update_or_create(
user=self.user,
defaults={
"settings": {
"saved_views": {
"dashboard_views_visible_ids": [v1.id],
"sidebar_views_visible_ids": [v1.id, v2.id],
},
},
},
)
response = self.client.patch(
f"/api/saved_views/{v1.id}/",
{
"show_on_dashboard": False,
},
headers={"Accept": "application/json; version=9"},
format="json",
)
self.assertEqual(response.status_code, status.HTTP_200_OK)
self.assertFalse(response.data["show_on_dashboard"])
self.assertTrue(response.data["show_in_sidebar"])
self.user.refresh_from_db()
saved_view_settings = self.user.ui_settings.settings["saved_views"]
self.assertListEqual(saved_view_settings["dashboard_views_visible_ids"], [])
self.assertListEqual(
saved_view_settings["sidebar_views_visible_ids"],
[v1.id, v2.id],
)
response = self.client.patch(
f"/api/saved_views/{v1.id}/",
{
"show_in_sidebar": False,
},
headers={"Accept": "application/json; version=9"},
format="json",
)
self.assertEqual(response.status_code, status.HTTP_200_OK)
self.assertFalse(response.data["show_on_dashboard"])
self.assertFalse(response.data["show_in_sidebar"])
self.user.refresh_from_db()
saved_view_settings = self.user.ui_settings.settings["saved_views"]
self.assertListEqual(saved_view_settings["dashboard_views_visible_ids"], [])
self.assertListEqual(saved_view_settings["sidebar_views_visible_ids"], [v2.id])
def test_saved_view_create_update_patch(self) -> None:
User.objects.create_user("user1")
@@ -2791,6 +2603,26 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
},
)
def test_docnote_serializer_v7(self) -> None:
doc = Document.objects.create(
title="test",
mime_type="application/pdf",
content="this is a document which will have notes!",
)
Note.objects.create(
note="This is a note.",
document=doc,
user=self.user,
)
self.assertEqual(
self.client.get(
f"/api/documents/{doc.pk}/",
headers={"Accept": "application/json; version=7"},
format="json",
).data["notes"][0]["user"],
self.user.id,
)
def test_create_note(self) -> None:
"""
GIVEN:
@@ -3559,13 +3391,14 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
)
class TestDocumentApiTagColors(DirectoriesMixin, APITestCase):
class TestDocumentApiV2(DirectoriesMixin, APITestCase):
def setUp(self) -> None:
super().setUp()
self.user = User.objects.create_superuser(username="temp_admin")
self.client.force_authenticate(user=self.user)
self.client.defaults["HTTP_ACCEPT"] = "application/json; version=2"
def test_tag_validate_color(self) -> None:
self.assertEqual(

View File

@@ -152,7 +152,7 @@ class TestCustomFieldsSearch(DirectoriesMixin, APITestCase):
context={
"request": types.SimpleNamespace(
method="GET",
version="9",
version="7",
),
},
)

View File

@@ -405,9 +405,7 @@ class TestBulkEdit(DirectoriesMixin, TestCase):
self.assertTrue(Document.objects.filter(id=self.doc1.id).exists())
self.assertFalse(Document.objects.filter(id=version.id).exists())
def test_resolve_root_and_source_doc_latest_version_prefers_newest_version(
self,
) -> None:
def test_get_root_and_current_doc_mapping(self) -> None:
version1 = Document.objects.create(
checksum="B-v1",
title="B version 1",
@@ -419,14 +417,18 @@ class TestBulkEdit(DirectoriesMixin, TestCase):
root_document=self.doc2,
)
root_doc, source_doc = bulk_edit._resolve_root_and_source_doc(
self.doc2,
source_mode="latest_version",
root_ids_by_doc_id = bulk_edit._get_root_ids_by_doc_id(
[self.doc2.id, version1.id, version2.id],
)
self.assertEqual(root_ids_by_doc_id[self.doc2.id], self.doc2.id)
self.assertEqual(root_ids_by_doc_id[version1.id], self.doc2.id)
self.assertEqual(root_ids_by_doc_id[version2.id], self.doc2.id)
self.assertEqual(root_doc.id, self.doc2.id)
self.assertEqual(source_doc.id, version2.id)
self.assertNotEqual(source_doc.id, version1.id)
root_docs, current_docs = bulk_edit._get_root_and_current_docs_by_root_id(
{self.doc2.id},
)
self.assertEqual(root_docs[self.doc2.id].id, self.doc2.id)
self.assertEqual(current_docs[self.doc2.id].id, version2.id)
@mock.patch("documents.tasks.bulk_update_documents.delay")
def test_set_permissions(self, m) -> None:
@@ -660,33 +662,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
self.assertEqual(result, "OK")
@mock.patch("pikepdf.open")
@mock.patch("documents.tasks.consume_file.s")
def test_merge_uses_latest_version_source_for_root_selection(
self,
mock_consume_file,
mock_open_pdf,
) -> None:
version_file = self.dirs.scratch_dir / "sample2_version_merge.pdf"
shutil.copy(self.doc2.source_path, version_file)
version = Document.objects.create(
checksum="B-v1",
title="B version 1",
root_document=self.doc2,
filename=version_file,
mime_type="application/pdf",
)
fake_pdf = mock.MagicMock()
fake_pdf.pdf_version = "1.7"
fake_pdf.pages = [mock.Mock()]
mock_open_pdf.return_value.__enter__.return_value = fake_pdf
result = bulk_edit.merge([self.doc2.id])
self.assertEqual(result, "OK")
mock_open_pdf.assert_called_once_with(str(version.source_path))
mock_consume_file.assert_not_called()
@mock.patch("documents.bulk_edit.delete.si")
@mock.patch("documents.tasks.consume_file.s")
def test_merge_and_delete_originals(
@@ -895,36 +870,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
self.assertEqual(result, "OK")
@mock.patch("documents.bulk_edit.group")
@mock.patch("pikepdf.open")
@mock.patch("documents.tasks.consume_file.s")
def test_split_uses_latest_version_source_for_root_selection(
self,
mock_consume_file,
mock_open_pdf,
mock_group,
) -> None:
version_file = self.dirs.scratch_dir / "sample2_version_split.pdf"
shutil.copy(self.doc2.source_path, version_file)
version = Document.objects.create(
checksum="B-v1",
title="B version 1",
root_document=self.doc2,
filename=version_file,
mime_type="application/pdf",
)
fake_pdf = mock.MagicMock()
fake_pdf.pages = [mock.Mock(), mock.Mock()]
mock_open_pdf.return_value.__enter__.return_value = fake_pdf
mock_group.return_value.delay.return_value = None
result = bulk_edit.split([self.doc2.id], [[1], [2]])
self.assertEqual(result, "OK")
mock_open_pdf.assert_called_once_with(version.source_path)
mock_consume_file.assert_not_called()
mock_group.return_value.delay.assert_not_called()
@mock.patch("documents.bulk_edit.delete.si")
@mock.patch("documents.tasks.consume_file.s")
@mock.patch("documents.bulk_edit.chord")
@@ -1096,34 +1041,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
self.assertIsNotNone(overrides)
self.assertEqual(result, "OK")
@mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
@mock.patch("documents.tasks.consume_file.delay")
@mock.patch("pikepdf.open")
def test_rotate_explicit_selection_uses_root_source_when_root_selected(
self,
mock_open,
mock_consume_delay,
mock_magic,
):
Document.objects.create(
checksum="B-v1",
title="B version 1",
root_document=self.doc2,
)
fake_pdf = mock.MagicMock()
fake_pdf.pages = [mock.Mock()]
mock_open.return_value.__enter__.return_value = fake_pdf
result = bulk_edit.rotate(
[self.doc2.id],
90,
source_mode="explicit_selection",
)
self.assertEqual(result, "OK")
mock_open.assert_called_once_with(self.doc2.source_path)
mock_consume_delay.assert_called_once()
@mock.patch("documents.tasks.consume_file.delay")
@mock.patch("pikepdf.Pdf.save")
@mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
@@ -1148,34 +1065,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
self.assertIsNotNone(overrides)
self.assertEqual(result, "OK")
@mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
@mock.patch("documents.tasks.consume_file.delay")
@mock.patch("pikepdf.open")
def test_delete_pages_explicit_selection_uses_root_source_when_root_selected(
self,
mock_open,
mock_consume_delay,
mock_magic,
):
Document.objects.create(
checksum="B-v1",
title="B version 1",
root_document=self.doc2,
)
fake_pdf = mock.MagicMock()
fake_pdf.pages = [mock.Mock(), mock.Mock()]
mock_open.return_value.__enter__.return_value = fake_pdf
result = bulk_edit.delete_pages(
[self.doc2.id],
[1],
source_mode="explicit_selection",
)
self.assertEqual(result, "OK")
mock_open.assert_called_once_with(self.doc2.source_path)
mock_consume_delay.assert_called_once()
@mock.patch("documents.tasks.consume_file.delay")
@mock.patch("pikepdf.Pdf.save")
def test_delete_pages_with_error(self, mock_pdf_save, mock_consume_delay):
@@ -1324,40 +1213,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
self.assertTrue(str(consumable.original_file).endswith("_edited.pdf"))
self.assertIsNotNone(overrides)
@mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
@mock.patch("documents.tasks.consume_file.delay")
@mock.patch("pikepdf.new")
@mock.patch("pikepdf.open")
def test_edit_pdf_explicit_selection_uses_root_source_when_root_selected(
self,
mock_open,
mock_new,
mock_consume_delay,
mock_magic,
):
Document.objects.create(
checksum="B-v1",
title="B version 1",
root_document=self.doc2,
)
fake_pdf = mock.MagicMock()
fake_pdf.pages = [mock.Mock()]
mock_open.return_value.__enter__.return_value = fake_pdf
output_pdf = mock.MagicMock()
output_pdf.pages = []
mock_new.return_value = output_pdf
result = bulk_edit.edit_pdf(
[self.doc2.id],
operations=[{"page": 1}],
update_document=True,
source_mode="explicit_selection",
)
self.assertEqual(result, "OK")
mock_open.assert_called_once_with(self.doc2.source_path)
mock_consume_delay.assert_called_once()
@mock.patch("documents.bulk_edit.group")
@mock.patch("documents.tasks.consume_file.s")
def test_edit_pdf_without_metadata(
@@ -1478,34 +1333,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
self.assertEqual(consumable.root_document_id, doc.id)
self.assertIsNotNone(overrides)
@mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
@mock.patch("documents.tasks.consume_file.delay")
@mock.patch("pikepdf.open")
def test_remove_password_explicit_selection_uses_root_source_when_root_selected(
self,
mock_open,
mock_consume_delay,
mock_magic,
) -> None:
Document.objects.create(
checksum="A-v1",
title="A version 1",
root_document=self.doc1,
)
fake_pdf = mock.MagicMock()
mock_open.return_value.__enter__.return_value = fake_pdf
result = bulk_edit.remove_password(
[self.doc1.id],
password="secret",
update_document=True,
source_mode="explicit_selection",
)
self.assertEqual(result, "OK")
mock_open.assert_called_once_with(self.doc1.source_path, password="secret")
mock_consume_delay.assert_called_once()
@mock.patch("documents.bulk_edit.chord")
@mock.patch("documents.bulk_edit.group")
@mock.patch("documents.tasks.consume_file.s")

View File

@@ -245,8 +245,14 @@ class TestConsumer(
self.assertIsFile(document.archive_path)
self.assertEqual(document.checksum, "42995833e01aea9b3edee44bbfdd7ce1")
self.assertEqual(document.archive_checksum, "62acb0bcbfbcaa62ca6ad3668e4e404b")
self.assertEqual(
document.checksum,
"1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
)
self.assertEqual(
document.archive_checksum,
"706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
)
self.assertIsNotFile(filename)

View File

@@ -63,8 +63,8 @@ class TestExportImport(
self.d1 = Document.objects.create(
content="Content",
checksum="42995833e01aea9b3edee44bbfdd7ce1",
archive_checksum="62acb0bcbfbcaa62ca6ad3668e4e404b",
checksum="1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
archive_checksum="706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
title="wow1",
filename="0000001.pdf",
mime_type="application/pdf",
@@ -72,21 +72,21 @@ class TestExportImport(
)
self.d2 = Document.objects.create(
content="Content",
checksum="9c9691e51741c1f4f41a20896af31770",
checksum="550d1bae0f746d4f7c6be07054eb20cc2f11988a58ef64ceae45e98f85e92a5b",
title="wow2",
filename="0000002.pdf",
mime_type="application/pdf",
)
self.d3 = Document.objects.create(
content="Content",
checksum="d38d7ed02e988e072caf924e0f3fcb76",
checksum="f1ba6b7ff8548214a75adec228f5468a14fe187f445bc0b9485cbf1c35b15915",
title="wow2",
filename="0000003.pdf",
mime_type="application/pdf",
)
self.d4 = Document.objects.create(
content="Content",
checksum="82186aaa94f0b98697d704b90fd1c072",
checksum="a81b16b6b313cfd7e60eb7b12598d1343b58622b4030cfa19a2724a02e98db1b",
title="wow_dec",
filename="0000004.pdf",
mime_type="application/pdf",
@@ -240,7 +240,7 @@ class TestExportImport(
)
with Path(fname).open("rb") as f:
checksum = hashlib.md5(f.read()).hexdigest()
checksum = hashlib.sha256(f.read()).hexdigest()
self.assertEqual(checksum, element["fields"]["checksum"])
# Generated field "content_length" should not be exported,
@@ -254,7 +254,7 @@ class TestExportImport(
self.assertIsFile(fname)
with Path(fname).open("rb") as f:
checksum = hashlib.md5(f.read()).hexdigest()
checksum = hashlib.sha256(f.read()).hexdigest()
self.assertEqual(checksum, element["fields"]["archive_checksum"])
elif element["model"] == "documents.note":
@@ -753,31 +753,6 @@ class TestExportImport(
call_command("document_importer", "--no-progress-bar", self.target)
self.assertEqual(Document.objects.count(), 4)
def test_folder_prefix_with_split(self) -> None:
"""
GIVEN:
- Request to export documents to directory
WHEN:
- Option use_folder_prefix is used
- Option split manifest is used
THEN:
- Documents can be imported again
"""
shutil.rmtree(Path(self.dirs.media_dir) / "documents")
shutil.copytree(
Path(__file__).parent / "samples" / "documents",
Path(self.dirs.media_dir) / "documents",
)
self._do_export(use_folder_prefix=True, split_manifest=True)
with paperless_environment():
self.assertEqual(Document.objects.count(), 4)
Document.objects.all().delete()
self.assertEqual(Document.objects.count(), 0)
call_command("document_importer", "--no-progress-bar", self.target)
self.assertEqual(Document.objects.count(), 4)
def test_import_db_transaction_failed(self) -> None:
"""
GIVEN:

View File

@@ -260,8 +260,8 @@ class TestCommandImport(
Document.objects.create(
content="Content",
checksum="42995833e01aea9b3edee44bbfdd7ce1",
archive_checksum="62acb0bcbfbcaa62ca6ad3668e4e404b",
checksum="1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
archive_checksum="706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
title="wow1",
filename="0000001.pdf",
mime_type="application/pdf",

View File

@@ -1,3 +1,4 @@
import hashlib
import logging
import shutil
from os import utime
@@ -128,3 +129,15 @@ def get_boolean(boolstr: str) -> bool:
Return a boolean value from a string representation.
"""
return bool(boolstr.lower() in ("yes", "y", "1", "t", "true"))
def compute_checksum(path: Path, chunk_size: int = 65536) -> str:
"""
Return the SHA256 hex digest of the file at *path*, reading in chunks
of *chunk_size* bytes to avoid loading the entire file into memory.
"""
h = hashlib.sha256()
with path.open("rb") as f:
while chunk := f.read(chunk_size):
h.update(chunk)
return h.hexdigest()

View File

@@ -2,7 +2,7 @@ msgid ""
msgstr ""
"Project-Id-Version: paperless-ngx\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2026-03-09 01:51+0000\n"
"POT-Creation-Date: 2026-03-04 23:29+0000\n"
"PO-Revision-Date: 2022-02-17 04:17\n"
"Last-Translator: \n"
"Language-Team: English\n"
@@ -1299,7 +1299,7 @@ msgstr ""
msgid "workflow runs"
msgstr ""
#: documents/serialisers.py:463 documents/serialisers.py:2482
#: documents/serialisers.py:463 documents/serialisers.py:2332
msgid "Insufficient permissions."
msgstr ""
@@ -1307,39 +1307,39 @@ msgstr ""
msgid "Invalid color."
msgstr ""
#: documents/serialisers.py:2105
#: documents/serialisers.py:1955
#, python-format
msgid "File type %(type)s not supported"
msgstr ""
#: documents/serialisers.py:2149
#: documents/serialisers.py:1999
#, python-format
msgid "Custom field id must be an integer: %(id)s"
msgstr ""
#: documents/serialisers.py:2156
#: documents/serialisers.py:2006
#, python-format
msgid "Custom field with id %(id)s does not exist"
msgstr ""
#: documents/serialisers.py:2173 documents/serialisers.py:2183
#: documents/serialisers.py:2023 documents/serialisers.py:2033
msgid ""
"Custom fields must be a list of integers or an object mapping ids to values."
msgstr ""
#: documents/serialisers.py:2178
#: documents/serialisers.py:2028
msgid "Some custom fields don't exist or were specified twice."
msgstr ""
#: documents/serialisers.py:2325
#: documents/serialisers.py:2175
msgid "Invalid variable detected."
msgstr ""
#: documents/serialisers.py:2538
#: documents/serialisers.py:2388
msgid "Duplicate document identifiers are not allowed."
msgstr ""
#: documents/serialisers.py:2568 documents/views.py:3328
#: documents/serialisers.py:2418 documents/views.py:3328
#, python-format
msgid "Documents not found: %(ids)s"
msgstr ""

View File

@@ -379,7 +379,7 @@ REST_FRAMEWORK = {
"DEFAULT_VERSION": "10", # match src-ui/src/environments/environment.prod.ts
# Make sure these are ordered and that the most recent version appears
# last. See api.md#api-versioning when adding new versions.
"ALLOWED_VERSIONS": ["9", "10"],
"ALLOWED_VERSIONS": ["2", "3", "4", "5", "6", "7", "8", "9", "10"],
# DRF Spectacular default schema
"DEFAULT_SCHEMA_CLASS": "drf_spectacular.openapi.AutoSchema",
}

View File

@@ -1,100 +1,107 @@
import logging
from unittest import mock
import pytest
from allauth.account.adapter import get_adapter
from allauth.core import context
from allauth.socialaccount.adapter import get_adapter as get_social_adapter
from django.conf import settings
from django.contrib.auth.models import AnonymousUser
from django.contrib.auth.models import Group
from django.contrib.auth.models import User
from django.forms import ValidationError
from django.http import HttpRequest
from django.test import TestCase
from django.test import override_settings
from django.urls import reverse
from pytest_django.fixtures import SettingsWrapper
from pytest_mock import MockerFixture
from rest_framework.authtoken.models import Token
from paperless.adapter import DrfTokenStrategy
@pytest.mark.django_db
class TestCustomAccountAdapter:
def test_is_open_for_signup(self, settings: SettingsWrapper) -> None:
class TestCustomAccountAdapter(TestCase):
def test_is_open_for_signup(self) -> None:
adapter = get_adapter()
# With no accounts, signups should be allowed
assert adapter.is_open_for_signup(None)
self.assertTrue(adapter.is_open_for_signup(None))
User.objects.create_user("testuser")
# Test when ACCOUNT_ALLOW_SIGNUPS is True
settings.ACCOUNT_ALLOW_SIGNUPS = True
assert adapter.is_open_for_signup(None)
self.assertTrue(adapter.is_open_for_signup(None))
# Test when ACCOUNT_ALLOW_SIGNUPS is False
settings.ACCOUNT_ALLOW_SIGNUPS = False
assert not adapter.is_open_for_signup(None)
self.assertFalse(adapter.is_open_for_signup(None))
def test_is_safe_url(self, settings: SettingsWrapper) -> None:
def test_is_safe_url(self) -> None:
request = HttpRequest()
request.get_host = lambda: "example.com"
request.get_host = mock.Mock(return_value="example.com")
with context.request_context(request):
adapter = get_adapter()
with override_settings(ALLOWED_HOSTS=["*"]):
# True because request host is same
url = "https://example.com"
self.assertTrue(adapter.is_safe_url(url))
settings.ALLOWED_HOSTS = ["*"]
# True because request host is same
assert adapter.is_safe_url("https://example.com")
url = "https://evil.com"
# False despite wildcard because request host is different
assert not adapter.is_safe_url("https://evil.com")
self.assertFalse(adapter.is_safe_url(url))
settings.ALLOWED_HOSTS = ["example.com"]
url = "https://example.com"
# True because request host is same
assert adapter.is_safe_url("https://example.com")
self.assertTrue(adapter.is_safe_url(url))
settings.ALLOWED_HOSTS = ["*", "example.com"]
url = "//evil.com"
# False because request host is not in allowed hosts
assert not adapter.is_safe_url("//evil.com")
self.assertFalse(adapter.is_safe_url(url))
def test_pre_authenticate(
self,
settings: SettingsWrapper,
mocker: MockerFixture,
) -> None:
mocker.patch("allauth.core.internal.ratelimit.consume", return_value=True)
@mock.patch("allauth.core.internal.ratelimit.consume", return_value=True)
def test_pre_authenticate(self, mock_consume) -> None:
adapter = get_adapter()
request = HttpRequest()
request.get_host = lambda: "example.com"
request.get_host = mock.Mock(return_value="example.com")
settings.DISABLE_REGULAR_LOGIN = False
adapter.pre_authenticate(request)
settings.DISABLE_REGULAR_LOGIN = True
with pytest.raises(ValidationError):
with self.assertRaises(ValidationError):
adapter.pre_authenticate(request)
def test_get_reset_password_from_key_url(self, settings: SettingsWrapper) -> None:
def test_get_reset_password_from_key_url(self) -> None:
request = HttpRequest()
request.get_host = lambda: "foo.org"
request.get_host = mock.Mock(return_value="foo.org")
with context.request_context(request):
adapter = get_adapter()
settings.PAPERLESS_URL = None
settings.ACCOUNT_DEFAULT_HTTP_PROTOCOL = "https"
expected_url = f"https://foo.org{reverse('account_reset_password_from_key', kwargs={'uidb36': 'UID', 'key': 'KEY'})}"
assert adapter.get_reset_password_from_key_url("UID-KEY") == expected_url
# Test when PAPERLESS_URL is None
with override_settings(
PAPERLESS_URL=None,
ACCOUNT_DEFAULT_HTTP_PROTOCOL="https",
):
expected_url = f"https://foo.org{reverse('account_reset_password_from_key', kwargs={'uidb36': 'UID', 'key': 'KEY'})}"
self.assertEqual(
adapter.get_reset_password_from_key_url("UID-KEY"),
expected_url,
)
settings.PAPERLESS_URL = "https://bar.com"
expected_url = f"https://bar.com{reverse('account_reset_password_from_key', kwargs={'uidb36': 'UID', 'key': 'KEY'})}"
assert adapter.get_reset_password_from_key_url("UID-KEY") == expected_url
# Test when PAPERLESS_URL is not None
with override_settings(PAPERLESS_URL="https://bar.com"):
expected_url = f"https://bar.com{reverse('account_reset_password_from_key', kwargs={'uidb36': 'UID', 'key': 'KEY'})}"
self.assertEqual(
adapter.get_reset_password_from_key_url("UID-KEY"),
expected_url,
)
def test_save_user_adds_groups(
self,
settings: SettingsWrapper,
mocker: MockerFixture,
) -> None:
settings.ACCOUNT_DEFAULT_GROUPS = ["group1", "group2"]
@override_settings(ACCOUNT_DEFAULT_GROUPS=["group1", "group2"])
def test_save_user_adds_groups(self) -> None:
Group.objects.create(name="group1")
user = User.objects.create_user("testuser")
adapter = get_adapter()
form = mocker.MagicMock(
form = mock.Mock(
cleaned_data={
"username": "testuser",
"email": "user@example.com",
@@ -103,81 +110,88 @@ class TestCustomAccountAdapter:
user = adapter.save_user(HttpRequest(), user, form, commit=True)
assert user.groups.count() == 1
assert user.groups.filter(name="group1").exists()
assert not user.groups.filter(name="group2").exists()
self.assertEqual(user.groups.count(), 1)
self.assertTrue(user.groups.filter(name="group1").exists())
self.assertFalse(user.groups.filter(name="group2").exists())
def test_fresh_install_save_creates_superuser(self, mocker: MockerFixture) -> None:
def test_fresh_install_save_creates_superuser(self) -> None:
adapter = get_adapter()
form = mocker.MagicMock(
form = mock.Mock(
cleaned_data={
"username": "testuser",
"email": "user@paperless-ngx.com",
},
)
user = adapter.save_user(HttpRequest(), User(), form, commit=True)
assert user.is_superuser
self.assertTrue(user.is_superuser)
form = mocker.MagicMock(
# Next time, it should not create a superuser
form = mock.Mock(
cleaned_data={
"username": "testuser2",
"email": "user2@paperless-ngx.com",
},
)
user2 = adapter.save_user(HttpRequest(), User(), form, commit=True)
assert not user2.is_superuser
self.assertFalse(user2.is_superuser)
class TestCustomSocialAccountAdapter:
@pytest.mark.django_db
def test_is_open_for_signup(self, settings: SettingsWrapper) -> None:
class TestCustomSocialAccountAdapter(TestCase):
def test_is_open_for_signup(self) -> None:
adapter = get_social_adapter()
# Test when SOCIALACCOUNT_ALLOW_SIGNUPS is True
settings.SOCIALACCOUNT_ALLOW_SIGNUPS = True
assert adapter.is_open_for_signup(None, None)
self.assertTrue(adapter.is_open_for_signup(None, None))
# Test when SOCIALACCOUNT_ALLOW_SIGNUPS is False
settings.SOCIALACCOUNT_ALLOW_SIGNUPS = False
assert not adapter.is_open_for_signup(None, None)
self.assertFalse(adapter.is_open_for_signup(None, None))
def test_get_connect_redirect_url(self) -> None:
adapter = get_social_adapter()
assert adapter.get_connect_redirect_url(None, None) == reverse("base")
request = None
socialaccount = None
@pytest.mark.django_db
def test_save_user_adds_groups(
self,
settings: SettingsWrapper,
mocker: MockerFixture,
) -> None:
settings.SOCIAL_ACCOUNT_DEFAULT_GROUPS = ["group1", "group2"]
# Test the default URL
expected_url = reverse("base")
self.assertEqual(
adapter.get_connect_redirect_url(request, socialaccount),
expected_url,
)
@override_settings(SOCIAL_ACCOUNT_DEFAULT_GROUPS=["group1", "group2"])
def test_save_user_adds_groups(self) -> None:
Group.objects.create(name="group1")
adapter = get_social_adapter()
request = HttpRequest()
user = User.objects.create_user("testuser")
sociallogin = mocker.MagicMock(user=user)
sociallogin = mock.Mock(
user=user,
)
user = adapter.save_user(HttpRequest(), sociallogin, None)
user = adapter.save_user(request, sociallogin, None)
assert user.groups.count() == 1
assert user.groups.filter(name="group1").exists()
assert not user.groups.filter(name="group2").exists()
self.assertEqual(user.groups.count(), 1)
self.assertTrue(user.groups.filter(name="group1").exists())
self.assertFalse(user.groups.filter(name="group2").exists())
def test_error_logged_on_authentication_error(
self,
caplog: pytest.LogCaptureFixture,
) -> None:
def test_error_logged_on_authentication_error(self) -> None:
adapter = get_social_adapter()
with caplog.at_level(logging.INFO, logger="paperless.auth"):
request = HttpRequest()
with self.assertLogs("paperless.auth", level="INFO") as log_cm:
adapter.on_authentication_error(
HttpRequest(),
request,
provider="test-provider",
error="Error",
exception="Test authentication error",
)
assert any("Test authentication error" in msg for msg in caplog.messages)
self.assertTrue(
any("Test authentication error" in message for message in log_cm.output),
)
@pytest.mark.django_db
class TestDrfTokenStrategy:
class TestDrfTokenStrategy(TestCase):
def test_create_access_token_creates_new_token(self) -> None:
"""
GIVEN:
@@ -187,6 +201,7 @@ class TestDrfTokenStrategy:
THEN:
- A new token is created and its key is returned
"""
user = User.objects.create_user("testuser")
request = HttpRequest()
request.user = user
@@ -194,9 +209,13 @@ class TestDrfTokenStrategy:
strategy = DrfTokenStrategy()
token_key = strategy.create_access_token(request)
assert token_key is not None
assert Token.objects.filter(user=user).exists()
assert token_key == Token.objects.get(user=user).key
# Verify a token was created
self.assertIsNotNone(token_key)
self.assertTrue(Token.objects.filter(user=user).exists())
# Verify the returned key matches the created token
token = Token.objects.get(user=user)
self.assertEqual(token_key, token.key)
def test_create_access_token_returns_existing_token(self) -> None:
"""
@@ -207,6 +226,7 @@ class TestDrfTokenStrategy:
THEN:
- The same token key is returned (no new token created)
"""
user = User.objects.create_user("testuser")
existing_token = Token.objects.create(user=user)
@@ -216,8 +236,11 @@ class TestDrfTokenStrategy:
strategy = DrfTokenStrategy()
token_key = strategy.create_access_token(request)
assert token_key == existing_token.key
assert Token.objects.filter(user=user).count() == 1
# Verify the existing token key is returned
self.assertEqual(token_key, existing_token.key)
# Verify only one token exists (no duplicate created)
self.assertEqual(Token.objects.filter(user=user).count(), 1)
def test_create_access_token_returns_none_for_unauthenticated_user(self) -> None:
"""
@@ -228,11 +251,12 @@ class TestDrfTokenStrategy:
THEN:
- None is returned and no token is created
"""
request = HttpRequest()
request.user = AnonymousUser()
strategy = DrfTokenStrategy()
token_key = strategy.create_access_token(request)
assert token_key is None
assert Token.objects.count() == 0
self.assertIsNone(token_key)
self.assertEqual(Token.objects.count(), 0)

View File

@@ -1,15 +1,16 @@
import os
from collections.abc import Callable
from dataclasses import dataclass
from pathlib import Path
from unittest import mock
import pytest
from django.core.checks import Error
from django.core.checks import Warning
from pytest_django.fixtures import SettingsWrapper
from django.test import TestCase
from django.test import override_settings
from pytest_mock import MockerFixture
from documents.tests.utils import DirectoriesMixin
from documents.tests.utils import FileSystemAssertsMixin
from paperless.checks import audit_log_check
from paperless.checks import binaries_check
from paperless.checks import check_deprecated_db_settings
@@ -19,84 +20,54 @@ from paperless.checks import paths_check
from paperless.checks import settings_values_check
@dataclass(frozen=True, slots=True)
class PaperlessTestDirs:
data_dir: Path
media_dir: Path
consumption_dir: Path
# TODO: consolidate with documents/tests/conftest.py PaperlessDirs/paperless_dirs
# once the paperless and documents test suites are ready to share fixtures.
@pytest.fixture()
def directories(tmp_path: Path, settings: SettingsWrapper) -> PaperlessTestDirs:
data_dir = tmp_path / "data"
media_dir = tmp_path / "media"
consumption_dir = tmp_path / "consumption"
for d in (data_dir, media_dir, consumption_dir):
d.mkdir()
settings.DATA_DIR = data_dir
settings.MEDIA_ROOT = media_dir
settings.CONSUMPTION_DIR = consumption_dir
return PaperlessTestDirs(
data_dir=data_dir,
media_dir=media_dir,
consumption_dir=consumption_dir,
)
class TestChecks:
class TestChecks(DirectoriesMixin, TestCase):
def test_binaries(self) -> None:
assert binaries_check(None) == []
self.assertEqual(binaries_check(None), [])
def test_binaries_fail(self, settings: SettingsWrapper) -> None:
settings.CONVERT_BINARY = "uuuhh"
assert len(binaries_check(None)) == 1
@override_settings(CONVERT_BINARY="uuuhh")
def test_binaries_fail(self) -> None:
self.assertEqual(len(binaries_check(None)), 1)
@pytest.mark.usefixtures("directories")
def test_paths_check(self) -> None:
assert paths_check(None) == []
self.assertEqual(paths_check(None), [])
def test_paths_check_dont_exist(self, settings: SettingsWrapper) -> None:
settings.MEDIA_ROOT = Path("uuh")
settings.DATA_DIR = Path("whatever")
settings.CONSUMPTION_DIR = Path("idontcare")
@override_settings(
MEDIA_ROOT=Path("uuh"),
DATA_DIR=Path("whatever"),
CONSUMPTION_DIR=Path("idontcare"),
)
def test_paths_check_dont_exist(self) -> None:
msgs = paths_check(None)
self.assertEqual(len(msgs), 3, str(msgs))
for msg in msgs:
self.assertTrue(msg.msg.endswith("is set but doesn't exist."))
def test_paths_check_no_access(self) -> None:
Path(self.dirs.data_dir).chmod(0o000)
Path(self.dirs.media_dir).chmod(0o000)
Path(self.dirs.consumption_dir).chmod(0o000)
self.addCleanup(os.chmod, self.dirs.data_dir, 0o777)
self.addCleanup(os.chmod, self.dirs.media_dir, 0o777)
self.addCleanup(os.chmod, self.dirs.consumption_dir, 0o777)
msgs = paths_check(None)
self.assertEqual(len(msgs), 3)
assert len(msgs) == 3, str(msgs)
for msg in msgs:
assert msg.msg.endswith("is set but doesn't exist.")
self.assertTrue(msg.msg.endswith("is not writeable"))
def test_paths_check_no_access(self, directories: PaperlessTestDirs) -> None:
directories.data_dir.chmod(0o000)
directories.media_dir.chmod(0o000)
directories.consumption_dir.chmod(0o000)
@override_settings(DEBUG=False)
def test_debug_disabled(self) -> None:
self.assertEqual(debug_mode_check(None), [])
try:
msgs = paths_check(None)
finally:
directories.data_dir.chmod(0o777)
directories.media_dir.chmod(0o777)
directories.consumption_dir.chmod(0o777)
assert len(msgs) == 3
for msg in msgs:
assert msg.msg.endswith("is not writeable")
def test_debug_disabled(self, settings: SettingsWrapper) -> None:
settings.DEBUG = False
assert debug_mode_check(None) == []
def test_debug_enabled(self, settings: SettingsWrapper) -> None:
settings.DEBUG = True
assert len(debug_mode_check(None)) == 1
@override_settings(DEBUG=True)
def test_debug_enabled(self) -> None:
self.assertEqual(len(debug_mode_check(None)), 1)
class TestSettingsChecksAgainstDefaults:
class TestSettingsChecksAgainstDefaults(DirectoriesMixin, TestCase):
def test_all_valid(self) -> None:
"""
GIVEN:
@@ -107,71 +78,104 @@ class TestSettingsChecksAgainstDefaults:
- No system check errors reported
"""
msgs = settings_values_check(None)
assert len(msgs) == 0
self.assertEqual(len(msgs), 0)
class TestOcrSettingsChecks:
@pytest.mark.parametrize(
("setting", "value", "expected_msg"),
[
pytest.param(
"OCR_OUTPUT_TYPE",
"notapdf",
'OCR output type "notapdf"',
id="invalid-output-type",
),
pytest.param(
"OCR_MODE",
"makeitso",
'OCR output mode "makeitso"',
id="invalid-mode",
),
pytest.param(
"OCR_MODE",
"skip_noarchive",
"deprecated",
id="deprecated-mode",
),
pytest.param(
"OCR_SKIP_ARCHIVE_FILE",
"invalid",
'OCR_SKIP_ARCHIVE_FILE setting "invalid"',
id="invalid-skip-archive-file",
),
pytest.param(
"OCR_CLEAN",
"cleanme",
'OCR clean mode "cleanme"',
id="invalid-clean",
),
],
)
def test_invalid_setting_produces_one_error(
self,
settings: SettingsWrapper,
setting: str,
value: str,
expected_msg: str,
) -> None:
class TestOcrSettingsChecks(DirectoriesMixin, TestCase):
@override_settings(OCR_OUTPUT_TYPE="notapdf")
def test_invalid_output_type(self) -> None:
"""
GIVEN:
- Default settings
- One OCR setting is set to an invalid value
- OCR output type is invalid
WHEN:
- Settings are validated
THEN:
- Exactly one system check error is reported containing the expected message
- system check error reported for OCR output type
"""
setattr(settings, setting, value)
msgs = settings_values_check(None)
self.assertEqual(len(msgs), 1)
assert len(msgs) == 1
assert expected_msg in msgs[0].msg
msg = msgs[0]
self.assertIn('OCR output type "notapdf"', msg.msg)
@override_settings(OCR_MODE="makeitso")
def test_invalid_ocr_type(self) -> None:
"""
GIVEN:
- Default settings
- OCR type is invalid
WHEN:
- Settings are validated
THEN:
- system check error reported for OCR type
"""
msgs = settings_values_check(None)
self.assertEqual(len(msgs), 1)
msg = msgs[0]
self.assertIn('OCR output mode "makeitso"', msg.msg)
@override_settings(OCR_MODE="skip_noarchive")
def test_deprecated_ocr_type(self) -> None:
"""
GIVEN:
- Default settings
- OCR type is deprecated
WHEN:
- Settings are validated
THEN:
- deprecation warning reported for OCR type
"""
msgs = settings_values_check(None)
self.assertEqual(len(msgs), 1)
msg = msgs[0]
self.assertIn("deprecated", msg.msg)
@override_settings(OCR_SKIP_ARCHIVE_FILE="invalid")
def test_invalid_ocr_skip_archive_file(self) -> None:
"""
GIVEN:
- Default settings
- OCR_SKIP_ARCHIVE_FILE is invalid
WHEN:
- Settings are validated
THEN:
- system check error reported for OCR_SKIP_ARCHIVE_FILE
"""
msgs = settings_values_check(None)
self.assertEqual(len(msgs), 1)
msg = msgs[0]
self.assertIn('OCR_SKIP_ARCHIVE_FILE setting "invalid"', msg.msg)
@override_settings(OCR_CLEAN="cleanme")
def test_invalid_ocr_clean(self) -> None:
"""
GIVEN:
- Default settings
- OCR cleaning type is invalid
WHEN:
- Settings are validated
THEN:
- system check error reported for OCR cleaning type
"""
msgs = settings_values_check(None)
self.assertEqual(len(msgs), 1)
msg = msgs[0]
self.assertIn('OCR clean mode "cleanme"', msg.msg)
class TestTimezoneSettingsChecks:
def test_invalid_timezone(self, settings: SettingsWrapper) -> None:
class TestTimezoneSettingsChecks(DirectoriesMixin, TestCase):
@override_settings(TIME_ZONE="TheMoon\\MyCrater")
def test_invalid_timezone(self) -> None:
"""
GIVEN:
- Default settings
@@ -181,16 +185,17 @@ class TestTimezoneSettingsChecks:
THEN:
- system check error reported for timezone
"""
settings.TIME_ZONE = "TheMoon\\MyCrater"
msgs = settings_values_check(None)
self.assertEqual(len(msgs), 1)
assert len(msgs) == 1
assert 'Timezone "TheMoon\\MyCrater"' in msgs[0].msg
msg = msgs[0]
self.assertIn('Timezone "TheMoon\\MyCrater"', msg.msg)
class TestEmailCertSettingsChecks:
def test_not_valid_file(self, settings: SettingsWrapper) -> None:
class TestEmailCertSettingsChecks(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
@override_settings(EMAIL_CERTIFICATE_FILE=Path("/tmp/not_actually_here.pem"))
def test_not_valid_file(self) -> None:
"""
GIVEN:
- Default settings
@@ -200,22 +205,19 @@ class TestEmailCertSettingsChecks:
THEN:
- system check error reported for email certificate
"""
cert_path = Path("/tmp/not_actually_here.pem")
assert not cert_path.is_file()
settings.EMAIL_CERTIFICATE_FILE = cert_path
self.assertIsNotFile("/tmp/not_actually_here.pem")
msgs = settings_values_check(None)
assert len(msgs) == 1
assert "Email cert /tmp/not_actually_here.pem is not a file" in msgs[0].msg
self.assertEqual(len(msgs), 1)
msg = msgs[0]
self.assertIn("Email cert /tmp/not_actually_here.pem is not a file", msg.msg)
class TestAuditLogChecks:
def test_was_enabled_once(
self,
settings: SettingsWrapper,
mocker: MockerFixture,
) -> None:
class TestAuditLogChecks(TestCase):
def test_was_enabled_once(self) -> None:
"""
GIVEN:
- Audit log is not enabled
@@ -224,18 +226,23 @@ class TestAuditLogChecks:
THEN:
- system check error reported for disabling audit log
"""
settings.AUDIT_LOG_ENABLED = False
introspect_mock = mocker.MagicMock()
introspect_mock = mock.MagicMock()
introspect_mock.introspection.table_names.return_value = ["auditlog_logentry"]
mocker.patch.dict(
"paperless.checks.connections",
{"default": introspect_mock},
)
with override_settings(AUDIT_LOG_ENABLED=False):
with mock.patch.dict(
"paperless.checks.connections",
{"default": introspect_mock},
):
msgs = audit_log_check(None)
msgs = audit_log_check(None)
self.assertEqual(len(msgs), 1)
assert len(msgs) == 1
assert "auditlog table was found but audit log is disabled." in msgs[0].msg
msg = msgs[0]
self.assertIn(
("auditlog table was found but audit log is disabled."),
msg.msg,
)
DEPRECATED_VARS: dict[str, str] = {
@@ -264,16 +271,20 @@ class TestDeprecatedDbSettings:
@pytest.mark.parametrize(
("env_var", "db_option_key"),
[
pytest.param("PAPERLESS_DB_TIMEOUT", "timeout", id="db-timeout"),
pytest.param(
"PAPERLESS_DB_POOLSIZE",
"pool.min_size / pool.max_size",
id="db-poolsize",
),
pytest.param("PAPERLESS_DBSSLMODE", "sslmode", id="ssl-mode"),
pytest.param("PAPERLESS_DBSSLROOTCERT", "sslrootcert", id="ssl-rootcert"),
pytest.param("PAPERLESS_DBSSLCERT", "sslcert", id="ssl-cert"),
pytest.param("PAPERLESS_DBSSLKEY", "sslkey", id="ssl-key"),
("PAPERLESS_DB_TIMEOUT", "timeout"),
("PAPERLESS_DB_POOLSIZE", "pool.min_size / pool.max_size"),
("PAPERLESS_DBSSLMODE", "sslmode"),
("PAPERLESS_DBSSLROOTCERT", "sslrootcert"),
("PAPERLESS_DBSSLCERT", "sslcert"),
("PAPERLESS_DBSSLKEY", "sslkey"),
],
ids=[
"db-timeout",
"db-poolsize",
"ssl-mode",
"ssl-rootcert",
"ssl-cert",
"ssl-key",
],
)
def test_single_deprecated_var_produces_one_warning(
@@ -392,10 +403,7 @@ class TestV3MinimumUpgradeVersionCheck:
"""Test suite for check_v3_minimum_upgrade_version system check."""
@pytest.fixture
def build_conn_mock(
self,
mocker: MockerFixture,
) -> Callable[[list[str], list[str]], mock.MagicMock]:
def build_conn_mock(self, mocker: MockerFixture):
"""Factory fixture that builds a connections['default'] mock.
Usage::
@@ -415,7 +423,7 @@ class TestV3MinimumUpgradeVersionCheck:
def test_no_migrations_table_fresh_install(
self,
mocker: MockerFixture,
build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
build_conn_mock,
) -> None:
"""
GIVEN:
@@ -434,7 +442,7 @@ class TestV3MinimumUpgradeVersionCheck:
def test_no_documents_migrations_fresh_install(
self,
mocker: MockerFixture,
build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
build_conn_mock,
) -> None:
"""
GIVEN:
@@ -453,7 +461,7 @@ class TestV3MinimumUpgradeVersionCheck:
def test_v3_state_with_0001_squashed(
self,
mocker: MockerFixture,
build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
build_conn_mock,
) -> None:
"""
GIVEN:
@@ -477,7 +485,7 @@ class TestV3MinimumUpgradeVersionCheck:
def test_v3_state_with_0002_squashed_only(
self,
mocker: MockerFixture,
build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
build_conn_mock,
) -> None:
"""
GIVEN:
@@ -496,7 +504,7 @@ class TestV3MinimumUpgradeVersionCheck:
def test_v2_20_9_state_ready_to_upgrade(
self,
mocker: MockerFixture,
build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
build_conn_mock,
) -> None:
"""
GIVEN:
@@ -523,7 +531,7 @@ class TestV3MinimumUpgradeVersionCheck:
def test_v2_20_8_raises_error(
self,
mocker: MockerFixture,
build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
build_conn_mock,
) -> None:
"""
GIVEN:
@@ -550,7 +558,7 @@ class TestV3MinimumUpgradeVersionCheck:
def test_very_old_version_raises_error(
self,
mocker: MockerFixture,
build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
build_conn_mock,
) -> None:
"""
GIVEN:
@@ -577,7 +585,7 @@ class TestV3MinimumUpgradeVersionCheck:
def test_error_hint_mentions_v2_20_9(
self,
mocker: MockerFixture,
build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
build_conn_mock,
) -> None:
"""
GIVEN:

View File

@@ -9,50 +9,35 @@ from paperless.utils import ocr_to_dateparser_languages
@pytest.mark.parametrize(
("ocr_language", "expected"),
[
pytest.param("eng", ["en"], id="single-language"),
pytest.param("fra+ita+lao", ["fr", "it", "lo"], id="multiple-languages"),
pytest.param("fil", ["fil"], id="no-two-letter-equivalent"),
pytest.param(
"aze_cyrl+srp_latn",
["az-Cyrl", "sr-Latn"],
id="script-supported-by-dateparser",
),
pytest.param(
"deu_frak",
["de"],
id="script-not-supported-falls-back-to-language",
),
pytest.param(
"chi_tra+chi_sim",
["zh"],
id="chinese-variants-collapse-to-general",
),
pytest.param(
"eng+unsupported_language+por",
["en", "pt"],
id="unsupported-language-skipped",
),
pytest.param(
"unsupported1+unsupported2",
[],
id="all-unsupported-returns-empty",
),
pytest.param("eng+eng", ["en"], id="duplicates-deduplicated"),
pytest.param(
"ita_unknownscript",
["it"],
id="unknown-script-falls-back-to-language",
),
# One language
("eng", ["en"]),
# Multiple languages
("fra+ita+lao", ["fr", "it", "lo"]),
# Languages that don't have a two-letter equivalent
("fil", ["fil"]),
# Languages with a script part supported by dateparser
("aze_cyrl+srp_latn", ["az-Cyrl", "sr-Latn"]),
# Languages with a script part not supported by dateparser
# In this case, default to the language without script
("deu_frak", ["de"]),
# Traditional and simplified chinese don't have the same name in dateparser,
# so they're converted to the general chinese language
("chi_tra+chi_sim", ["zh"]),
# If a language is not supported by dateparser, fallback to the supported ones
("eng+unsupported_language+por", ["en", "pt"]),
# If no language is supported, fallback to default
("unsupported1+unsupported2", []),
# Duplicate languages, should not duplicate in result
("eng+eng", ["en"]),
# Language with script, but script is not mapped
("ita_unknownscript", ["it"]),
],
)
def test_ocr_to_dateparser_languages(ocr_language: str, expected: list[str]) -> None:
def test_ocr_to_dateparser_languages(ocr_language, expected):
assert sorted(ocr_to_dateparser_languages(ocr_language)) == sorted(expected)
def test_ocr_to_dateparser_languages_exception(
monkeypatch: pytest.MonkeyPatch,
caplog: pytest.LogCaptureFixture,
) -> None:
def test_ocr_to_dateparser_languages_exception(monkeypatch, caplog):
# Patch LocaleDataLoader.get_locale_map to raise an exception
class DummyLoader:
def get_locale_map(self, locales=None):

View File

@@ -1,31 +1,24 @@
import tempfile
from pathlib import Path
from django.test import Client
from pytest_django.fixtures import SettingsWrapper
from django.test import override_settings
def test_favicon_view(
client: Client,
tmp_path: Path,
settings: SettingsWrapper,
) -> None:
favicon_path = tmp_path / "paperless" / "img" / "favicon.ico"
favicon_path.parent.mkdir(parents=True)
favicon_path.write_bytes(b"FAKE ICON DATA")
def test_favicon_view(client):
with tempfile.TemporaryDirectory() as tmpdir:
static_dir = Path(tmpdir)
favicon_path = static_dir / "paperless" / "img" / "favicon.ico"
favicon_path.parent.mkdir(parents=True, exist_ok=True)
favicon_path.write_bytes(b"FAKE ICON DATA")
settings.STATIC_ROOT = tmp_path
response = client.get("/favicon.ico")
assert response.status_code == 200
assert response["Content-Type"] == "image/x-icon"
assert b"".join(response.streaming_content) == b"FAKE ICON DATA"
with override_settings(STATIC_ROOT=static_dir):
response = client.get("/favicon.ico")
assert response.status_code == 200
assert response["Content-Type"] == "image/x-icon"
assert b"".join(response.streaming_content) == b"FAKE ICON DATA"
def test_favicon_view_missing_file(
client: Client,
tmp_path: Path,
settings: SettingsWrapper,
) -> None:
settings.STATIC_ROOT = tmp_path
response = client.get("/favicon.ico")
assert response.status_code == 404
def test_favicon_view_missing_file(client):
with override_settings(STATIC_ROOT=Path(tempfile.mkdtemp())):
response = client.get("/favicon.ico")
assert response.status_code == 404

View File

@@ -1,4 +1,4 @@
from pydantic import BaseModel
from llama_index.core.bridge.pydantic import BaseModel
class DocumentClassifierSchema(BaseModel):

View File

@@ -1,6 +1,10 @@
import logging
import sys
from llama_index.core import VectorStoreIndex
from llama_index.core.prompts import PromptTemplate
from llama_index.core.query_engine import RetrieverQueryEngine
from documents.models import Document
from paperless_ai.client import AIClient
from paperless_ai.indexing import load_or_build_index
@@ -10,13 +14,15 @@ logger = logging.getLogger("paperless_ai.chat")
MAX_SINGLE_DOC_CONTEXT_CHARS = 15000
SINGLE_DOC_SNIPPET_CHARS = 800
CHAT_PROMPT_TMPL = """Context information is below.
CHAT_PROMPT_TMPL = PromptTemplate(
template="""Context information is below.
---------------------
{context_str}
---------------------
Given the context information and not prior knowledge, answer the query.
Query: {query_str}
Answer:"""
Answer:""",
)
def stream_chat_with_documents(query_str: str, documents: list[Document]):
@@ -37,10 +43,6 @@ def stream_chat_with_documents(query_str: str, documents: list[Document]):
yield "Sorry, I couldn't find any content to answer your question."
return
from llama_index.core import VectorStoreIndex
from llama_index.core.prompts import PromptTemplate
from llama_index.core.query_engine import RetrieverQueryEngine
local_index = VectorStoreIndex(nodes=nodes)
retriever = local_index.as_retriever(
similarity_top_k=3 if len(documents) == 1 else 5,
@@ -83,8 +85,7 @@ def stream_chat_with_documents(query_str: str, documents: list[Document]):
for node in top_nodes
)
prompt_template = PromptTemplate(template=CHAT_PROMPT_TMPL)
prompt = prompt_template.partial_format(
prompt = CHAT_PROMPT_TMPL.partial_format(
context_str=context,
query_str=query_str,
).format(llm=client.llm)

View File

@@ -1,10 +1,9 @@
import logging
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from llama_index.core.llms import ChatMessage
from llama_index.llms.ollama import Ollama
from llama_index.llms.openai import OpenAI
from llama_index.core.llms import ChatMessage
from llama_index.core.program.function_program import get_function_tool
from llama_index.llms.ollama import Ollama
from llama_index.llms.openai import OpenAI
from paperless.config import AIConfig
from paperless_ai.base_model import DocumentClassifierSchema
@@ -21,18 +20,14 @@ class AIClient:
self.settings = AIConfig()
self.llm = self.get_llm()
def get_llm(self) -> "Ollama | OpenAI":
def get_llm(self) -> Ollama | OpenAI:
if self.settings.llm_backend == "ollama":
from llama_index.llms.ollama import Ollama
return Ollama(
model=self.settings.llm_model or "llama3.1",
base_url=self.settings.llm_endpoint or "http://localhost:11434",
request_timeout=120,
)
elif self.settings.llm_backend == "openai":
from llama_index.llms.openai import OpenAI
return OpenAI(
model=self.settings.llm_model or "gpt-3.5-turbo",
api_base=self.settings.llm_endpoint or None,
@@ -48,9 +43,6 @@ class AIClient:
self.settings.llm_model,
)
from llama_index.core.llms import ChatMessage
from llama_index.core.program.function_program import get_function_tool
user_msg = ChatMessage(role="user", content=prompt)
tool = get_function_tool(DocumentClassifierSchema)
result = self.llm.chat_with_tools(
@@ -66,7 +58,7 @@ class AIClient:
parsed = DocumentClassifierSchema(**tool_calls[0].tool_kwargs)
return parsed.model_dump()
def run_chat(self, messages: list["ChatMessage"]) -> str:
def run_chat(self, messages: list[ChatMessage]) -> str:
logger.debug(
"Running chat query against %s with model %s",
self.settings.llm_backend,

View File

@@ -1,12 +1,13 @@
import json
from typing import TYPE_CHECKING
from django.conf import settings
if TYPE_CHECKING:
from pathlib import Path
from llama_index.core.base.embeddings.base import BaseEmbedding
from django.conf import settings
from llama_index.core.base.embeddings.base import BaseEmbedding
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.embeddings.openai import OpenAIEmbedding
from documents.models import Document
from documents.models import Note
@@ -14,21 +15,17 @@ from paperless.config import AIConfig
from paperless.models import LLMEmbeddingBackend
def get_embedding_model() -> "BaseEmbedding":
def get_embedding_model() -> BaseEmbedding:
config = AIConfig()
match config.llm_embedding_backend:
case LLMEmbeddingBackend.OPENAI:
from llama_index.embeddings.openai import OpenAIEmbedding
return OpenAIEmbedding(
model=config.llm_embedding_model or "text-embedding-3-small",
api_key=config.llm_api_key,
api_base=config.llm_endpoint or None,
)
case LLMEmbeddingBackend.HUGGINGFACE:
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
return HuggingFaceEmbedding(
model_name=config.llm_embedding_model
or "sentence-transformers/all-MiniLM-L6-v2",

View File

@@ -4,12 +4,26 @@ from collections.abc import Callable
from collections.abc import Iterable
from datetime import timedelta
from pathlib import Path
from typing import TYPE_CHECKING
from typing import TypeVar
import faiss
import llama_index.core.settings as llama_settings
from celery import states
from django.conf import settings
from django.utils import timezone
from llama_index.core import Document as LlamaDocument
from llama_index.core import StorageContext
from llama_index.core import VectorStoreIndex
from llama_index.core import load_index_from_storage
from llama_index.core.indices.prompt_helper import PromptHelper
from llama_index.core.node_parser import SimpleNodeParser
from llama_index.core.prompts import PromptTemplate
from llama_index.core.retrievers import VectorIndexRetriever
from llama_index.core.schema import BaseNode
from llama_index.core.storage.docstore import SimpleDocumentStore
from llama_index.core.storage.index_store import SimpleIndexStore
from llama_index.core.text_splitter import TokenTextSplitter
from llama_index.vector_stores.faiss import FaissVectorStore
from documents.models import Document
from documents.models import PaperlessTask
@@ -20,10 +34,6 @@ from paperless_ai.embedding import get_embedding_model
_T = TypeVar("_T")
IterWrapper = Callable[[Iterable[_T]], Iterable[_T]]
if TYPE_CHECKING:
from llama_index.core import VectorStoreIndex
from llama_index.core.schema import BaseNode
def _identity(iterable: Iterable[_T]) -> Iterable[_T]:
return iterable
@@ -65,23 +75,12 @@ def get_or_create_storage_context(*, rebuild=False):
settings.LLM_INDEX_DIR.mkdir(parents=True, exist_ok=True)
if rebuild or not settings.LLM_INDEX_DIR.exists():
import faiss
from llama_index.core import StorageContext
from llama_index.core.storage.docstore import SimpleDocumentStore
from llama_index.core.storage.index_store import SimpleIndexStore
from llama_index.vector_stores.faiss import FaissVectorStore
embedding_dim = get_embedding_dim()
faiss_index = faiss.IndexFlatL2(embedding_dim)
vector_store = FaissVectorStore(faiss_index=faiss_index)
docstore = SimpleDocumentStore()
index_store = SimpleIndexStore()
else:
from llama_index.core import StorageContext
from llama_index.core.storage.docstore import SimpleDocumentStore
from llama_index.core.storage.index_store import SimpleIndexStore
from llama_index.vector_stores.faiss import FaissVectorStore
vector_store = FaissVectorStore.from_persist_dir(settings.LLM_INDEX_DIR)
docstore = SimpleDocumentStore.from_persist_dir(settings.LLM_INDEX_DIR)
index_store = SimpleIndexStore.from_persist_dir(settings.LLM_INDEX_DIR)
@@ -94,7 +93,7 @@ def get_or_create_storage_context(*, rebuild=False):
)
def build_document_node(document: Document) -> list["BaseNode"]:
def build_document_node(document: Document) -> list[BaseNode]:
"""
Given a Document, returns parsed Nodes ready for indexing.
"""
@@ -113,9 +112,6 @@ def build_document_node(document: Document) -> list["BaseNode"]:
"added": document.added.isoformat() if document.added else None,
"modified": document.modified.isoformat(),
}
from llama_index.core import Document as LlamaDocument
from llama_index.core.node_parser import SimpleNodeParser
doc = LlamaDocument(text=text, metadata=metadata)
parser = SimpleNodeParser()
return parser.get_nodes_from_documents([doc])
@@ -126,10 +122,6 @@ def load_or_build_index(nodes=None):
Load an existing VectorStoreIndex if present,
or build a new one using provided nodes if storage is empty.
"""
import llama_index.core.settings as llama_settings
from llama_index.core import VectorStoreIndex
from llama_index.core import load_index_from_storage
embed_model = get_embedding_model()
llama_settings.Settings.embed_model = embed_model
storage_context = get_or_create_storage_context()
@@ -151,7 +143,7 @@ def load_or_build_index(nodes=None):
)
def remove_document_docstore_nodes(document: Document, index: "VectorStoreIndex"):
def remove_document_docstore_nodes(document: Document, index: VectorStoreIndex):
"""
Removes existing documents from docstore for a given document from the index.
This is necessary because FAISS IndexFlatL2 is append-only.
@@ -182,8 +174,6 @@ def update_llm_index(
"""
Rebuild or update the LLM index.
"""
from llama_index.core import VectorStoreIndex
nodes = []
documents = Document.objects.all()
@@ -197,8 +187,6 @@ def update_llm_index(
(settings.LLM_INDEX_DIR / "meta.json").unlink(missing_ok=True)
# Rebuild index from scratch
logger.info("Rebuilding LLM index.")
import llama_index.core.settings as llama_settings
embed_model = get_embedding_model()
llama_settings.Settings.embed_model = embed_model
storage_context = get_or_create_storage_context(rebuild=True)
@@ -283,10 +271,6 @@ def llm_index_remove_document(document: Document):
def truncate_content(content: str) -> str:
from llama_index.core.indices.prompt_helper import PromptHelper
from llama_index.core.prompts import PromptTemplate
from llama_index.core.text_splitter import TokenTextSplitter
prompt_helper = PromptHelper(
context_window=8192,
num_output=512,
@@ -331,8 +315,6 @@ def query_similar_documents(
else None
)
from llama_index.core.retrievers import VectorIndexRetriever
retriever = VectorIndexRetriever(
index=index,
similarity_top_k=top_k,

View File

@@ -181,11 +181,11 @@ def test_load_or_build_index_builds_when_nodes_given(
) -> None:
with (
patch(
"llama_index.core.load_index_from_storage",
"paperless_ai.indexing.load_index_from_storage",
side_effect=ValueError("Index not found"),
),
patch(
"llama_index.core.VectorStoreIndex",
"paperless_ai.indexing.VectorStoreIndex",
return_value=MagicMock(),
) as mock_index_cls,
patch(
@@ -206,7 +206,7 @@ def test_load_or_build_index_raises_exception_when_no_nodes(
) -> None:
with (
patch(
"llama_index.core.load_index_from_storage",
"paperless_ai.indexing.load_index_from_storage",
side_effect=ValueError("Index not found"),
),
patch(
@@ -225,11 +225,11 @@ def test_load_or_build_index_succeeds_when_nodes_given(
) -> None:
with (
patch(
"llama_index.core.load_index_from_storage",
"paperless_ai.indexing.load_index_from_storage",
side_effect=ValueError("Index not found"),
),
patch(
"llama_index.core.VectorStoreIndex",
"paperless_ai.indexing.VectorStoreIndex",
return_value=MagicMock(),
) as mock_index_cls,
patch(
@@ -334,7 +334,7 @@ def test_query_similar_documents(
patch(
"paperless_ai.indexing.vector_store_file_exists",
) as mock_vector_store_exists,
patch("llama_index.core.retrievers.VectorIndexRetriever") as mock_retriever_cls,
patch("paperless_ai.indexing.VectorIndexRetriever") as mock_retriever_cls,
patch("paperless_ai.indexing.Document.objects.filter") as mock_filter,
):
mock_storage.return_value = MagicMock()

View File

@@ -45,7 +45,7 @@ def test_stream_chat_with_one_document_full_content(mock_document) -> None:
patch("paperless_ai.chat.AIClient") as mock_client_cls,
patch("paperless_ai.chat.load_or_build_index") as mock_load_index,
patch(
"llama_index.core.query_engine.RetrieverQueryEngine.from_args",
"paperless_ai.chat.RetrieverQueryEngine.from_args",
) as mock_query_engine_cls,
):
mock_client = MagicMock()
@@ -76,7 +76,7 @@ def test_stream_chat_with_multiple_documents_retrieval(patch_embed_nodes) -> Non
patch("paperless_ai.chat.AIClient") as mock_client_cls,
patch("paperless_ai.chat.load_or_build_index") as mock_load_index,
patch(
"llama_index.core.query_engine.RetrieverQueryEngine.from_args",
"paperless_ai.chat.RetrieverQueryEngine.from_args",
) as mock_query_engine_cls,
patch.object(VectorStoreIndex, "as_retriever") as mock_as_retriever,
):

View File

@@ -18,13 +18,13 @@ def mock_ai_config():
@pytest.fixture
def mock_ollama_llm():
with patch("llama_index.llms.ollama.Ollama") as MockOllama:
with patch("paperless_ai.client.Ollama") as MockOllama:
yield MockOllama
@pytest.fixture
def mock_openai_llm():
with patch("llama_index.llms.openai.OpenAI") as MockOpenAI:
with patch("paperless_ai.client.OpenAI") as MockOpenAI:
yield MockOpenAI

View File

@@ -67,7 +67,7 @@ def test_get_embedding_model_openai(mock_ai_config):
mock_ai_config.return_value.llm_api_key = "test_api_key"
mock_ai_config.return_value.llm_endpoint = "http://test-url"
with patch("llama_index.embeddings.openai.OpenAIEmbedding") as MockOpenAIEmbedding:
with patch("paperless_ai.embedding.OpenAIEmbedding") as MockOpenAIEmbedding:
model = get_embedding_model()
MockOpenAIEmbedding.assert_called_once_with(
model="text-embedding-3-small",
@@ -84,7 +84,7 @@ def test_get_embedding_model_huggingface(mock_ai_config):
)
with patch(
"llama_index.embeddings.huggingface.HuggingFaceEmbedding",
"paperless_ai.embedding.HuggingFaceEmbedding",
) as MockHuggingFaceEmbedding:
model = get_embedding_model()
MockHuggingFaceEmbedding.assert_called_once_with(