Compare commits

..

9 Commits

Author SHA1 Message Date
Trenton H
02d4fcfe0b Cleans up config formatting 2026-02-23 14:49:08 -08:00
Trenton H
5db46cbc3a Finshes the writeup and migration guide 2026-02-23 14:25:56 -08:00
Trenton H
3c9bbb50b3 Relaxes the typing here 2026-02-23 13:27:19 -08:00
Trenton H
480a406e8a Makes the system checks return multiples, not mashed together 2026-02-23 12:58:06 -08:00
Trenton H
b26546c806 Missing the required parameters 2026-02-23 12:32:27 -08:00
Trenton H
7dc5fdc1d8 Smaller changeset, keep the rest for later 2026-02-23 12:32:27 -08:00
Trenton H
bd1dce2412 Adds the checks for depracated env vars 2026-02-23 12:32:27 -08:00
Trenton H
e9de03303e Moves to the new parser module 2026-02-23 12:32:27 -08:00
Trenton H
d0164e68cf Renames the settings to a module for the next steps 2026-02-23 12:32:27 -08:00
27 changed files with 1072 additions and 1146 deletions

View File

@@ -39,3 +39,6 @@ max_line_length = off
[Dockerfile*]
indent_style = space
[*.toml]
indent_style = space

View File

@@ -700,11 +700,15 @@ src/documents/signals/handlers.py:0: error: Function is missing a type annotatio
src/documents/signals/handlers.py:0: error: Function is missing a type annotation for one or more arguments [no-untyped-def]
src/documents/signals/handlers.py:0: error: Function is missing a type annotation for one or more arguments [no-untyped-def]
src/documents/signals/handlers.py:0: error: Function is missing a type annotation for one or more arguments [no-untyped-def]
src/documents/signals/handlers.py:0: error: Function is missing a type annotation for one or more arguments [no-untyped-def]
src/documents/signals/handlers.py:0: error: Incompatible return value type (got "tuple[DocumentMetadataOverrides | None, str]", expected "tuple[DocumentMetadataOverrides, str] | None") [return-value]
src/documents/signals/handlers.py:0: error: Incompatible types in assignment (expression has type "list[Tag]", variable has type "set[Tag]") [assignment]
src/documents/signals/handlers.py:0: error: Incompatible types in assignment (expression has type "tuple[Any, Any, Any]", variable has type "tuple[Any, Any]") [assignment]
src/documents/signals/handlers.py:0: error: Item "ConsumableDocument" of "Document | ConsumableDocument" has no attribute "refresh_from_db" [union-attr]
src/documents/signals/handlers.py:0: error: Item "ConsumableDocument" of "Document | ConsumableDocument" has no attribute "save" [union-attr]
src/documents/signals/handlers.py:0: error: Item "ConsumableDocument" of "Document | ConsumableDocument" has no attribute "source_path" [union-attr]
src/documents/signals/handlers.py:0: error: Item "ConsumableDocument" of "Document | ConsumableDocument" has no attribute "tags" [union-attr]
src/documents/signals/handlers.py:0: error: Item "ConsumableDocument" of "Document | ConsumableDocument" has no attribute "tags" [union-attr]
src/documents/signals/handlers.py:0: error: Item "ConsumableDocument" of "Document | ConsumableDocument" has no attribute "title" [union-attr]
src/documents/signals/handlers.py:0: error: Item "None" of "Any | None" has no attribute "get" [union-attr]
src/documents/signals/handlers.py:0: error: Item "None" of "Any | None" has no attribute "get" [union-attr]
@@ -2118,6 +2122,7 @@ src/paperless_mail/mail.py:0: error: Function is missing a return type annotatio
src/paperless_mail/mail.py:0: error: Function is missing a return type annotation [no-untyped-def]
src/paperless_mail/mail.py:0: error: Function is missing a return type annotation [no-untyped-def]
src/paperless_mail/mail.py:0: error: Function is missing a return type annotation [no-untyped-def]
src/paperless_mail/mail.py:0: error: Function is missing a return type annotation [no-untyped-def]
src/paperless_mail/mail.py:0: error: Function is missing a type annotation for one or more arguments [no-untyped-def]
src/paperless_mail/mail.py:0: error: Function is missing a type annotation for one or more arguments [no-untyped-def]
src/paperless_mail/mail.py:0: error: Function is missing a type annotation for one or more arguments [no-untyped-def]

View File

@@ -51,137 +51,163 @@ matcher.
### Database
By default, Paperless uses **SQLite** with a database stored at `data/db.sqlite3`.
To switch to **PostgreSQL** or **MariaDB**, set [`PAPERLESS_DBHOST`](#PAPERLESS_DBHOST) and optionally configure other
database-related environment variables.
For multi-user or higher-throughput deployments, **PostgreSQL** (recommended) or
**MariaDB** can be used instead by setting [`PAPERLESS_DBENGINE`](#PAPERLESS_DBENGINE)
and the relevant connection variables.
#### [`PAPERLESS_DBENGINE=<engine>`](#PAPERLESS_DBENGINE) {#PAPERLESS_DBENGINE}
: Specifies the database engine to use. Accepted values are `sqlite`, `postgresql`,
and `mariadb`.
Defaults to `sqlite` if not set.
PostgreSQL and MariaDB both require [`PAPERLESS_DBHOST`](#PAPERLESS_DBHOST) to be
set. SQLite does not use any other connection variables; the database file is always
located at `<PAPERLESS_DATA_DIR>/db.sqlite3`.
!!! warning
Using MariaDB comes with some caveats.
See [MySQL Caveats](advanced_usage.md#mysql-caveats).
#### [`PAPERLESS_DBHOST=<hostname>`](#PAPERLESS_DBHOST) {#PAPERLESS_DBHOST}
: If unset, Paperless uses **SQLite** by default.
Set `PAPERLESS_DBHOST` to switch to PostgreSQL or MariaDB instead.
#### [`PAPERLESS_DBENGINE=<engine_name>`](#PAPERLESS_DBENGINE) {#PAPERLESS_DBENGINE}
: Optional. Specifies the database engine to use when connecting to a remote database.
Available options are `postgresql` and `mariadb`.
Defaults to `postgresql` if `PAPERLESS_DBHOST` is set.
!!! warning
Using MariaDB comes with some caveats. See [MySQL Caveats](advanced_usage.md#mysql-caveats).
: Hostname of the PostgreSQL or MariaDB database server. Required when
`PAPERLESS_DBENGINE` is `postgresql` or `mariadb`.
#### [`PAPERLESS_DBPORT=<port>`](#PAPERLESS_DBPORT) {#PAPERLESS_DBPORT}
: Port to use when connecting to PostgreSQL or MariaDB.
Default is `5432` for PostgreSQL and `3306` for MariaDB.
Defaults to `5432` for PostgreSQL and `3306` for MariaDB.
#### [`PAPERLESS_DBNAME=<name>`](#PAPERLESS_DBNAME) {#PAPERLESS_DBNAME}
: Name of the database to connect to when using PostgreSQL or MariaDB.
: Name of the PostgreSQL or MariaDB database to connect to.
Defaults to "paperless".
Defaults to `paperless`.
#### [`PAPERLESS_DBUSER=<name>`](#PAPERLESS_DBUSER) {#PAPERLESS_DBUSER}
#### [`PAPERLESS_DBUSER=<user>`](#PAPERLESS_DBUSER) {#PAPERLESS_DBUSER}
: Username for authenticating with the PostgreSQL or MariaDB database.
Defaults to "paperless".
Defaults to `paperless`.
#### [`PAPERLESS_DBPASS=<password>`](#PAPERLESS_DBPASS) {#PAPERLESS_DBPASS}
: Password for the PostgreSQL or MariaDB database user.
Defaults to "paperless".
Defaults to `paperless`.
#### [`PAPERLESS_DBSSLMODE=<mode>`](#PAPERLESS_DBSSLMODE) {#PAPERLESS_DBSSLMODE}
#### [`PAPERLESS_DB_OPTIONS=<options>`](#PAPERLESS_DB_OPTIONS) {#PAPERLESS_DB_OPTIONS}
: SSL mode to use when connecting to PostgreSQL or MariaDB.
: Advanced database connection options as a semicolon-delimited key-value string.
Keys and values are separated by `=`. Dot-notation produces nested option
dictionaries; for example, `pool.max_size=20` sets
`OPTIONS["pool"]["max_size"] = 20`.
See [the official documentation about
sslmode for PostgreSQL](https://www.postgresql.org/docs/current/libpq-ssl.html).
Options specified here are merged over the engine defaults. Unrecognised keys
are passed through to the underlying database driver without validation, so a
typo will be silently ignored rather than producing an error.
See [the official documentation about
sslmode for MySQL and MariaDB](https://dev.mysql.com/doc/refman/8.0/en/connection-options.html#option_general_ssl-mode).
Refer to your database driver's documentation for the full set of accepted keys:
*Note*: SSL mode values differ between PostgreSQL and MariaDB.
- PostgreSQL: [libpq connection parameters](https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-PARAMKEYWORDS)
- MariaDB: [MariaDB Connector/Python](https://mariadb.com/kb/en/mariadb-connector-python/)
- SQLite: [SQLite PRAGMA statements](https://www.sqlite.org/pragma.html)
Default is `prefer` for PostgreSQL and `PREFERRED` for MariaDB.
**Examples:**
#### [`PAPERLESS_DBSSLROOTCERT=<ca-path>`](#PAPERLESS_DBSSLROOTCERT) {#PAPERLESS_DBSSLROOTCERT}
```bash
# PostgreSQL: require SSL, set a custom CA certificate, and limit the pool size
PAPERLESS_DB_OPTIONS="sslmode=require;sslrootcert=/certs/ca.pem;pool.max_size=5"
: Path to the SSL root certificate used to verify the database server.
# MariaDB: require SSL with a custom CA certificate
PAPERLESS_DB_OPTIONS="ssl_mode=REQUIRED;ssl.ca=/certs/ca.pem"
See [the official documentation about
sslmode for PostgreSQL](https://www.postgresql.org/docs/current/libpq-ssl.html).
Changes the location of `root.crt`.
# PostgreSQL: set a connection timeout
PAPERLESS_DB_OPTIONS="connect_timeout=10"
```
See [the official documentation about
sslmode for MySQL and MariaDB](https://dev.mysql.com/doc/refman/8.0/en/connection-options.html#option_general_ssl-ca).
!!! note "PostgreSQL connection pooling"
Pool size is controlled via `pool.min_size` and `pool.max_size`. When
configuring pooling, ensure your PostgreSQL `max_connections` is large enough
to handle all pool connections across all workers:
`(web_workers + celery_workers) * pool.max_size + safety_margin`.
Defaults to unset, using the standard location in the home directory.
#### ~~[`PAPERLESS_DBSSLMODE`](#PAPERLESS_DBSSLMODE)~~ {#PAPERLESS_DBSSLMODE}
#### [`PAPERLESS_DBSSLCERT=<client-cert-path>`](#PAPERLESS_DBSSLCERT) {#PAPERLESS_DBSSLCERT}
!!! failure "Removed in v3"
Use [`PAPERLESS_DB_OPTIONS`](#PAPERLESS_DB_OPTIONS) instead.
: Path to the client SSL certificate used when connecting securely.
```bash
# PostgreSQL
PAPERLESS_DB_OPTIONS="sslmode=require"
See [the official documentation about
sslmode for PostgreSQL](https://www.postgresql.org/docs/current/libpq-ssl.html).
# MariaDB
PAPERLESS_DB_OPTIONS="ssl_mode=REQUIRED"
```
See [the official documentation about
sslmode for MySQL and MariaDB](https://dev.mysql.com/doc/refman/8.0/en/connection-options.html#option_general_ssl-cert).
#### ~~[`PAPERLESS_DBSSLROOTCERT`](#PAPERLESS_DBSSLROOTCERT)~~ {#PAPERLESS_DBSSLROOTCERT}
Changes the location of `postgresql.crt`.
!!! failure "Removed in v3"
Use [`PAPERLESS_DB_OPTIONS`](#PAPERLESS_DB_OPTIONS) instead.
Defaults to unset, using the standard location in the home directory.
```bash
# PostgreSQL
PAPERLESS_DB_OPTIONS="sslrootcert=/path/to/ca.pem"
#### [`PAPERLESS_DBSSLKEY=<client-cert-key>`](#PAPERLESS_DBSSLKEY) {#PAPERLESS_DBSSLKEY}
# MariaDB
PAPERLESS_DB_OPTIONS="ssl.ca=/path/to/ca.pem"
```
: Path to the client SSL private key used when connecting securely.
#### ~~[`PAPERLESS_DBSSLCERT`](#PAPERLESS_DBSSLCERT)~~ {#PAPERLESS_DBSSLCERT}
See [the official documentation about
sslmode for PostgreSQL](https://www.postgresql.org/docs/current/libpq-ssl.html).
!!! failure "Removed in v3"
Use [`PAPERLESS_DB_OPTIONS`](#PAPERLESS_DB_OPTIONS) instead.
See [the official documentation about
sslmode for MySQL and MariaDB](https://dev.mysql.com/doc/refman/8.0/en/connection-options.html#option_general_ssl-key).
```bash
# PostgreSQL
PAPERLESS_DB_OPTIONS="sslcert=/path/to/client.crt"
Changes the location of `postgresql.key`.
# MariaDB
PAPERLESS_DB_OPTIONS="ssl.cert=/path/to/client.crt"
```
Defaults to unset, using the standard location in the home directory.
#### ~~[`PAPERLESS_DBSSLKEY`](#PAPERLESS_DBSSLKEY)~~ {#PAPERLESS_DBSSLKEY}
#### [`PAPERLESS_DB_TIMEOUT=<int>`](#PAPERLESS_DB_TIMEOUT) {#PAPERLESS_DB_TIMEOUT}
!!! failure "Removed in v3"
Use [`PAPERLESS_DB_OPTIONS`](#PAPERLESS_DB_OPTIONS) instead.
: Sets how long a database connection should wait before timing out.
```bash
# PostgreSQL
PAPERLESS_DB_OPTIONS="sslkey=/path/to/client.key"
For SQLite, this sets how long to wait if the database is locked.
For PostgreSQL or MariaDB, this sets the connection timeout.
# MariaDB
PAPERLESS_DB_OPTIONS="ssl.key=/path/to/client.key"
```
Defaults to unset, which uses Djangos built-in defaults.
#### ~~[`PAPERLESS_DB_TIMEOUT`](#PAPERLESS_DB_TIMEOUT)~~ {#PAPERLESS_DB_TIMEOUT}
#### [`PAPERLESS_DB_POOLSIZE=<int>`](#PAPERLESS_DB_POOLSIZE) {#PAPERLESS_DB_POOLSIZE}
!!! failure "Removed in v3"
Use [`PAPERLESS_DB_OPTIONS`](#PAPERLESS_DB_OPTIONS) instead.
: Defines the maximum number of database connections to keep in the pool.
```bash
# SQLite
PAPERLESS_DB_OPTIONS="timeout=30"
Only applies to PostgreSQL. This setting is ignored for other database engines.
# PostgreSQL or MariaDB
PAPERLESS_DB_OPTIONS="connect_timeout=30"
```
The value must be greater than or equal to 1 to be used.
Defaults to unset, which disables connection pooling.
#### ~~[`PAPERLESS_DB_POOLSIZE`](#PAPERLESS_DB_POOLSIZE)~~ {#PAPERLESS_DB_POOLSIZE}
!!! note
!!! failure "Removed in v3"
Use [`PAPERLESS_DB_OPTIONS`](#PAPERLESS_DB_OPTIONS) instead.
A pool of 8-10 connections per worker is typically sufficient.
If you encounter error messages such as `couldn't get a connection`
or database connection timeouts, you probably need to increase the pool size.
!!! warning
Make sure your PostgreSQL `max_connections` setting is large enough to handle the connection pools:
`(NB_PAPERLESS_WORKERS + NB_CELERY_WORKERS) × POOL_SIZE + SAFETY_MARGIN`. For example, with
4 Paperless workers and 2 Celery workers, and a pool size of 8:``(4 + 2) × 8 + 10 = 58`,
so `max_connections = 60` (or even more) is appropriate.
This assumes only Paperless-ngx connects to your PostgreSQL instance. If you have other applications,
you should increase `max_connections` accordingly.
```bash
PAPERLESS_DB_OPTIONS="pool.max_size=10"
```
#### [`PAPERLESS_DB_READ_CACHE_ENABLED=<bool>`](#PAPERLESS_DB_READ_CACHE_ENABLED) {#PAPERLESS_DB_READ_CACHE_ENABLED}

View File

@@ -48,3 +48,58 @@ The `CONSUMER_BARCODE_SCANNER` setting has been removed. zxing-cpp is now the on
reliability.
- The `libzbar0` / `libzbar-dev` system packages are no longer required and can be removed from any custom Docker
images or host installations.
## Database Engine
`PAPERLESS_DBENGINE` is now required to use PostgreSQL or MariaDB. Previously, the
engine was inferred from the presence of `PAPERLESS_DBHOST`, with `PAPERLESS_DBENGINE`
only needed to select MariaDB over PostgreSQL.
SQLite users require no changes, though they may explicitly set their engine if desired.
#### Action Required
PostgreSQL and MariaDB users must add `PAPERLESS_DBENGINE` to their environment:
```yaml
# v2 (PostgreSQL inferred from PAPERLESS_DBHOST)
PAPERLESS_DBHOST: postgres
# v3 (engine must be explicit)
PAPERLESS_DBENGINE: postgresql
PAPERLESS_DBHOST: postgres
```
See [`PAPERLESS_DBENGINE`](configuration.md#PAPERLESS_DBENGINE) for accepted values.
## Database Advanced Options
The individual SSL, timeout, and pooling variables have been removed in favour of a
single [`PAPERLESS_DB_OPTIONS`](configuration.md#PAPERLESS_DB_OPTIONS) string. This
consolidates a growing set of engine-specific variables into one place, and allows
any option supported by the underlying database driver to be set without requiring a
dedicated environment variable for each.
The removed variables and their replacements are:
| Removed Variable | Replacement in `PAPERLESS_DB_OPTIONS` |
| ------------------------- | ---------------------------------------------------------------------------- |
| `PAPERLESS_DBSSLMODE` | `sslmode=<value>` (PostgreSQL) or `ssl_mode=<value>` (MariaDB) |
| `PAPERLESS_DBSSLROOTCERT` | `sslrootcert=<path>` (PostgreSQL) or `ssl.ca=<path>` (MariaDB) |
| `PAPERLESS_DBSSLCERT` | `sslcert=<path>` (PostgreSQL) or `ssl.cert=<path>` (MariaDB) |
| `PAPERLESS_DBSSLKEY` | `sslkey=<path>` (PostgreSQL) or `ssl.key=<path>` (MariaDB) |
| `PAPERLESS_DB_POOLSIZE` | `pool.max_size=<value>` (PostgreSQL only) |
| `PAPERLESS_DB_TIMEOUT` | `timeout=<value>` (SQLite) or `connect_timeout=<value>` (PostgreSQL/MariaDB) |
The deprecated variables will continue to function for now but will be removed in a
future release. A deprecation warning is logged at startup for each deprecated variable
that is still set.
#### Action Required
Users with any of the deprecated variables set should migrate to `PAPERLESS_DB_OPTIONS`.
Multiple options are combined in a single value:
```bash
PAPERLESS_DB_OPTIONS="sslmode=require;sslrootcert=/certs/ca.pem;pool.max_size=10"
```

View File

@@ -564,18 +564,6 @@ For security reasons, webhooks can be limited to specific ports and disallowed f
[configuration settings](configuration.md#workflow-webhooks) to change this behavior. If you are allowing non-admins to create workflows,
you may want to adjust these settings to prevent abuse.
##### Move to Trash {#workflow-action-move-to-trash}
"Move to Trash" actions move the document to the trash. The document can be restored
from the trash until the trash is emptied (after the configured delay or manually).
The "Move to Trash" action will always be executed at the end of the workflow run,
regardless of its position in the action list. After a "Move to Trash" action is executed
no other workflow will be executed on the document.
If a "Move to Trash" action is executed in a consume pipeline, the consumption
will be aborted and the file will be deleted.
#### Workflow placeholders
Titles and webhook payloads can be generated by workflows using [Jinja templates](https://jinja.palletsprojects.com/en/3.1.x/templates/).

View File

@@ -5355,13 +5355,6 @@
<context context-type="linenumber">445</context>
</context-group>
</trans-unit>
<trans-unit id="7902569198692046993" datatype="html">
<source>The document will be moved to the trash at the end of the workflow run.</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.html</context>
<context context-type="linenumber">454</context>
</context-group>
</trans-unit>
<trans-unit id="4626030417479279989" datatype="html">
<source>Consume Folder</source>
<context-group purpose="location">
@@ -5464,124 +5457,109 @@
<context context-type="linenumber">144</context>
</context-group>
</trans-unit>
<trans-unit id="2048798344356757326" datatype="html">
<source>Move to trash</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">148</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">1087</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
<context context-type="linenumber">760</context>
</context-group>
</trans-unit>
<trans-unit id="4522609911791833187" datatype="html">
<source>Has any of these tags</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">217</context>
<context context-type="linenumber">213</context>
</context-group>
</trans-unit>
<trans-unit id="4166903555074156852" datatype="html">
<source>Has all of these tags</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">224</context>
<context context-type="linenumber">220</context>
</context-group>
</trans-unit>
<trans-unit id="6624363795312783141" datatype="html">
<source>Does not have these tags</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">231</context>
<context context-type="linenumber">227</context>
</context-group>
</trans-unit>
<trans-unit id="7168528512669831184" datatype="html">
<source>Has any of these correspondents</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">238</context>
<context context-type="linenumber">234</context>
</context-group>
</trans-unit>
<trans-unit id="5281365940563983618" datatype="html">
<source>Has correspondent</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">246</context>
<context context-type="linenumber">242</context>
</context-group>
</trans-unit>
<trans-unit id="6884498632428600393" datatype="html">
<source>Does not have correspondents</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">254</context>
<context context-type="linenumber">250</context>
</context-group>
</trans-unit>
<trans-unit id="4806713133917046341" datatype="html">
<source>Has document type</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">262</context>
<context context-type="linenumber">258</context>
</context-group>
</trans-unit>
<trans-unit id="8801397520369995032" datatype="html">
<source>Has any of these document types</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">270</context>
<context context-type="linenumber">266</context>
</context-group>
</trans-unit>
<trans-unit id="1507843981661822403" datatype="html">
<source>Does not have document types</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">278</context>
<context context-type="linenumber">274</context>
</context-group>
</trans-unit>
<trans-unit id="4277260190522078330" datatype="html">
<source>Has storage path</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">286</context>
<context context-type="linenumber">282</context>
</context-group>
</trans-unit>
<trans-unit id="8858580062214623097" datatype="html">
<source>Has any of these storage paths</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">294</context>
<context context-type="linenumber">290</context>
</context-group>
</trans-unit>
<trans-unit id="6070943364927280151" datatype="html">
<source>Does not have storage paths</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">302</context>
<context context-type="linenumber">298</context>
</context-group>
</trans-unit>
<trans-unit id="6250799006816371860" datatype="html">
<source>Matches custom field query</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">310</context>
<context context-type="linenumber">306</context>
</context-group>
</trans-unit>
<trans-unit id="3138206142174978019" datatype="html">
<source>Create new workflow</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">539</context>
<context context-type="linenumber">535</context>
</context-group>
</trans-unit>
<trans-unit id="5996779210524133604" datatype="html">
<source>Edit workflow</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts</context>
<context context-type="linenumber">543</context>
<context context-type="linenumber">539</context>
</context-group>
</trans-unit>
<trans-unit id="5457837313196342910" datatype="html">
@@ -7795,6 +7773,17 @@
<context context-type="linenumber">758</context>
</context-group>
</trans-unit>
<trans-unit id="2048798344356757326" datatype="html">
<source>Move to trash</source>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
<context context-type="linenumber">1087</context>
</context-group>
<context-group purpose="location">
<context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
<context context-type="linenumber">760</context>
</context-group>
</trans-unit>
<trans-unit id="7295637485862454066" datatype="html">
<source>Error deleting document</source>
<context-group purpose="location">

View File

@@ -448,13 +448,6 @@
</div>
</div>
}
@case (WorkflowActionType.MoveToTrash) {
<div class="row">
<div class="col">
<p class="text-muted small" i18n>The document will be moved to the trash at the end of the workflow run.</p>
</div>
</div>
}
}
</div>
</ng-template>

View File

@@ -143,10 +143,6 @@ export const WORKFLOW_ACTION_OPTIONS = [
id: WorkflowActionType.PasswordRemoval,
name: $localize`Password removal`,
},
{
id: WorkflowActionType.MoveToTrash,
name: $localize`Move to trash`,
},
]
export enum TriggerFilterType {

View File

@@ -6,7 +6,6 @@ export enum WorkflowActionType {
Email = 3,
Webhook = 4,
PasswordRemoval = 5,
MoveToTrash = 6,
}
export interface WorkflowActionEmail extends ObjectWithId {

View File

@@ -1,29 +0,0 @@
# Generated by Django 5.2.11 on 2026-02-14 19:19
from django.db import migrations
from django.db import models
class Migration(migrations.Migration):
dependencies = [
("documents", "0011_optimize_integer_field_sizes"),
]
operations = [
migrations.AlterField(
model_name="workflowaction",
name="type",
field=models.PositiveSmallIntegerField(
choices=[
(1, "Assignment"),
(2, "Removal"),
(3, "Email"),
(4, "Webhook"),
(5, "Password removal"),
(6, "Move to trash"),
],
default=1,
verbose_name="Workflow Action Type",
),
),
]

View File

@@ -1409,10 +1409,6 @@ class WorkflowAction(models.Model):
5,
_("Password removal"),
)
MOVE_TO_TRASH = (
6,
_("Move to trash"),
)
type = models.PositiveSmallIntegerField(
_("Workflow Action Type"),

View File

@@ -48,7 +48,6 @@ from documents.permissions import get_objects_for_user_owner_aware
from documents.templating.utils import convert_format_str_to_template_format
from documents.workflows.actions import build_workflow_action_context
from documents.workflows.actions import execute_email_action
from documents.workflows.actions import execute_move_to_trash_action
from documents.workflows.actions import execute_password_removal_action
from documents.workflows.actions import execute_webhook_action
from documents.workflows.mutations import apply_assignment_to_document
@@ -59,8 +58,6 @@ from documents.workflows.utils import get_workflows_for_trigger
from paperless.config import AIConfig
if TYPE_CHECKING:
import uuid
from documents.classifier import DocumentClassifier
from documents.data_models import ConsumableDocument
from documents.data_models import DocumentMetadataOverrides
@@ -730,7 +727,7 @@ def add_to_index(sender, document, **kwargs) -> None:
def run_workflows_added(
sender,
document: Document,
logging_group: uuid.UUID | None = None,
logging_group=None,
original_file=None,
**kwargs,
) -> None:
@@ -746,7 +743,7 @@ def run_workflows_added(
def run_workflows_updated(
sender,
document: Document,
logging_group: uuid.UUID | None = None,
logging_group=None,
**kwargs,
) -> None:
run_workflows(
@@ -760,7 +757,7 @@ def run_workflows(
trigger_type: WorkflowTrigger.WorkflowTriggerType,
document: Document | ConsumableDocument,
workflow_to_run: Workflow | None = None,
logging_group: uuid.UUID | None = None,
logging_group=None,
overrides: DocumentMetadataOverrides | None = None,
original_file: Path | None = None,
) -> tuple[DocumentMetadataOverrides, str] | None:
@@ -786,33 +783,14 @@ def run_workflows(
for workflow in workflows:
if not use_overrides:
if TYPE_CHECKING:
assert isinstance(document, Document)
try:
# This can be called from bulk_update_documents, which may be running multiple times
# Refresh this so the matching data is fresh and instance fields are re-freshed
# Otherwise, this instance might be behind and overwrite the work another process did
document.refresh_from_db()
doc_tag_ids = list(document.tags.values_list("pk", flat=True))
except Document.DoesNotExist:
# Document was hard deleted by a previous workflow or another process
logger.info(
"Document no longer exists, skipping remaining workflows",
extra={"group": logging_group},
)
break
# Check if document was soft deleted (moved to trash)
if document.is_deleted:
logger.info(
"Document was moved to trash, skipping remaining workflows",
extra={"group": logging_group},
)
break
# This can be called from bulk_update_documents, which may be running multiple times
# Refresh this so the matching data is fresh and instance fields are re-freshed
# Otherwise, this instance might be behind and overwrite the work another process did
document.refresh_from_db()
doc_tag_ids = list(document.tags.values_list("pk", flat=True))
if matching.document_matches_workflow(document, workflow, trigger_type):
action: WorkflowAction
has_move_to_trash_action = False
for action in workflow.actions.order_by("order", "pk"):
message = f"Applying {action} from {workflow}"
if not use_overrides:
@@ -856,8 +834,6 @@ def run_workflows(
)
elif action.type == WorkflowAction.WorkflowActionType.PASSWORD_REMOVAL:
execute_password_removal_action(action, document, logging_group)
elif action.type == WorkflowAction.WorkflowActionType.MOVE_TO_TRASH:
has_move_to_trash_action = True
if not use_overrides:
# limit title to 128 characters
@@ -872,12 +848,7 @@ def run_workflows(
document=document if not use_overrides else None,
)
if has_move_to_trash_action:
execute_move_to_trash_action(action, document, logging_group)
if use_overrides:
if TYPE_CHECKING:
assert overrides is not None
return overrides, "\n".join(messages)

View File

@@ -896,210 +896,3 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
"Passwords are required",
str(response.data["non_field_errors"][0]),
)
def test_trash_action_validation(self) -> None:
"""
GIVEN:
- API request to create a workflow with a trash action
WHEN:
- API is called
THEN:
- Correct HTTP response
"""
response = self.client.post(
self.ENDPOINT,
json.dumps(
{
"name": "Workflow 2",
"order": 1,
"triggers": [
{
"type": WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
"sources": [DocumentSource.ApiUpload],
"filter_filename": "*",
},
],
"actions": [
{
"type": WorkflowAction.WorkflowActionType.MOVE_TO_TRASH,
},
],
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_201_CREATED)
response = self.client.post(
self.ENDPOINT,
json.dumps(
{
"name": "Workflow 3",
"order": 2,
"triggers": [
{
"type": WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
"sources": [DocumentSource.ApiUpload],
"filter_filename": "*",
},
],
"actions": [
{
"type": WorkflowAction.WorkflowActionType.MOVE_TO_TRASH,
},
],
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_201_CREATED)
def test_trash_action_as_last_action_valid(self) -> None:
"""
GIVEN:
- API request to create a workflow with multiple actions
- Move to trash action is the last action
WHEN:
- API is called
THEN:
- Workflow is created successfully
"""
response = self.client.post(
self.ENDPOINT,
json.dumps(
{
"name": "Workflow with Move to Trash Last",
"order": 1,
"triggers": [
{
"type": WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
"sources": [DocumentSource.ApiUpload],
"filter_filename": "*",
},
],
"actions": [
{
"type": WorkflowAction.WorkflowActionType.ASSIGNMENT,
"assign_title": "Assigned Title",
},
{
"type": WorkflowAction.WorkflowActionType.REMOVAL,
"remove_all_tags": True,
},
{
"type": WorkflowAction.WorkflowActionType.MOVE_TO_TRASH,
},
],
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_201_CREATED)
def test_update_workflow_add_trash_at_end_valid(self) -> None:
"""
GIVEN:
- Existing workflow without trash action
WHEN:
- PATCH to add trash action at end
THEN:
- HTTP 200 success
"""
response = self.client.post(
self.ENDPOINT,
json.dumps(
{
"name": "Workflow to Add Move to Trash",
"order": 1,
"triggers": [
{
"type": WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
"sources": [DocumentSource.ApiUpload],
"filter_filename": "*",
},
],
"actions": [
{
"type": WorkflowAction.WorkflowActionType.ASSIGNMENT,
"assign_title": "First Action",
},
],
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_201_CREATED)
workflow_id = response.data["id"]
response = self.client.patch(
f"{self.ENDPOINT}{workflow_id}/",
json.dumps(
{
"actions": [
{
"type": WorkflowAction.WorkflowActionType.ASSIGNMENT,
"assign_title": "First Action",
},
{
"type": WorkflowAction.WorkflowActionType.MOVE_TO_TRASH,
},
],
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_200_OK)
def test_update_workflow_remove_trash_action_valid(self) -> None:
"""
GIVEN:
- Existing workflow with trash action
WHEN:
- PATCH to remove trash action
THEN:
- HTTP 200 success
"""
response = self.client.post(
self.ENDPOINT,
json.dumps(
{
"name": "Workflow to Remove move to trash",
"order": 1,
"triggers": [
{
"type": WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
"sources": [DocumentSource.ApiUpload],
"filter_filename": "*",
},
],
"actions": [
{
"type": WorkflowAction.WorkflowActionType.ASSIGNMENT,
"assign_title": "First Action",
},
{
"type": WorkflowAction.WorkflowActionType.MOVE_TO_TRASH,
},
],
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_201_CREATED)
workflow_id = response.data["id"]
response = self.client.patch(
f"{self.ENDPOINT}{workflow_id}/",
json.dumps(
{
"actions": [
{
"type": WorkflowAction.WorkflowActionType.ASSIGNMENT,
"assign_title": "Only Action",
},
],
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_200_OK)

View File

@@ -3,11 +3,9 @@ import json
import shutil
import socket
import tempfile
from collections.abc import Callable
from datetime import timedelta
from pathlib import Path
from typing import TYPE_CHECKING
from typing import Any
from unittest import mock
import pytest
@@ -57,7 +55,6 @@ from documents.models import WorkflowActionEmail
from documents.models import WorkflowActionWebhook
from documents.models import WorkflowRun
from documents.models import WorkflowTrigger
from documents.plugins.base import StopConsumeTaskError
from documents.serialisers import WorkflowTriggerSerializer
from documents.signals import document_consumption_finished
from documents.tests.utils import DirectoriesMixin
@@ -3917,427 +3914,6 @@ class TestWorkflows(
)
assert mock_remove_password.call_count == 2
def test_workflow_trash_action_soft_delete(self):
"""
GIVEN:
- Document updated workflow with delete action
WHEN:
- Document that matches is updated
THEN:
- Document is moved to trash (soft deleted)
"""
trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
)
action = WorkflowAction.objects.create(
type=WorkflowAction.WorkflowActionType.MOVE_TO_TRASH,
)
w = Workflow.objects.create(
name="Workflow 1",
order=0,
)
w.triggers.add(trigger)
w.actions.add(action)
w.save()
doc = Document.objects.create(
title="sample test",
correspondent=self.c,
original_filename="sample.pdf",
)
self.assertEqual(Document.objects.count(), 1)
self.assertEqual(Document.deleted_objects.count(), 0)
run_workflows(WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED, doc)
self.assertEqual(Document.objects.count(), 0)
self.assertEqual(Document.deleted_objects.count(), 1)
@override_settings(
PAPERLESS_EMAIL_HOST="localhost",
EMAIL_ENABLED=True,
PAPERLESS_URL="http://localhost:8000",
)
@mock.patch("django.core.mail.message.EmailMessage.send")
def test_workflow_trash_with_email_action(self, mock_email_send):
"""
GIVEN:
- Workflow with email action, then move to trash action
WHEN:
- Document matches and workflow runs
THEN:
- Email is sent first
- Document is moved to trash (soft deleted)
"""
mock_email_send.return_value = 1
trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
)
email_action = WorkflowActionEmail.objects.create(
subject="Document deleted: {doc_title}",
body="Document {doc_title} will be deleted",
to="user@example.com",
include_document=False,
)
email_workflow_action = WorkflowAction.objects.create(
type=WorkflowAction.WorkflowActionType.EMAIL,
email=email_action,
)
trash_workflow_action = WorkflowAction.objects.create(
type=WorkflowAction.WorkflowActionType.MOVE_TO_TRASH,
)
w = Workflow.objects.create(
name="Workflow with email then move to trash",
order=0,
)
w.triggers.add(trigger)
w.actions.add(email_workflow_action, trash_workflow_action)
w.save()
doc = Document.objects.create(
title="sample test",
correspondent=self.c,
original_filename="sample.pdf",
)
self.assertEqual(Document.objects.count(), 1)
self.assertEqual(Document.deleted_objects.count(), 0)
run_workflows(WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED, doc)
mock_email_send.assert_called_once()
self.assertEqual(Document.objects.count(), 0)
self.assertEqual(Document.deleted_objects.count(), 1)
@override_settings(
PAPERLESS_URL="http://localhost:8000",
)
@mock.patch("documents.workflows.webhooks.send_webhook.delay")
def test_workflow_trash_with_webhook_action(self, mock_webhook_delay):
"""
GIVEN:
- Workflow with webhook action (include_document=True), then move to trash action
WHEN:
- Document matches and workflow runs
THEN:
- Webhook .delay() is called with complete data including file bytes
- Document is moved to trash (soft deleted)
- Webhook task has all necessary data and doesn't rely on document existence
"""
trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
)
webhook_action = WorkflowActionWebhook.objects.create(
use_params=True,
params={
"title": "{{doc_title}}",
"message": "Document being deleted",
},
url="https://paperless-ngx.com/webhook",
include_document=True,
)
webhook_workflow_action = WorkflowAction.objects.create(
type=WorkflowAction.WorkflowActionType.WEBHOOK,
webhook=webhook_action,
)
trash_workflow_action = WorkflowAction.objects.create(
type=WorkflowAction.WorkflowActionType.MOVE_TO_TRASH,
)
w = Workflow.objects.create(
name="Workflow with webhook then move to trash",
order=0,
)
w.triggers.add(trigger)
w.actions.add(webhook_workflow_action, trash_workflow_action)
w.save()
test_file = shutil.copy(
self.SAMPLE_DIR / "simple.pdf",
self.dirs.scratch_dir / "simple.pdf",
)
doc = Document.objects.create(
title="sample test",
correspondent=self.c,
original_filename="simple.pdf",
filename=test_file,
mime_type="application/pdf",
)
self.assertEqual(Document.objects.count(), 1)
self.assertEqual(Document.deleted_objects.count(), 0)
run_workflows(WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED, doc)
mock_webhook_delay.assert_called_once()
call_kwargs = mock_webhook_delay.call_args[1]
self.assertEqual(call_kwargs["url"], "https://paperless-ngx.com/webhook")
self.assertEqual(
call_kwargs["data"],
{"title": "sample test", "message": "Document being deleted"},
)
self.assertIsNotNone(call_kwargs["files"])
self.assertIn("file", call_kwargs["files"])
self.assertEqual(call_kwargs["files"]["file"][0], "simple.pdf")
self.assertEqual(call_kwargs["files"]["file"][2], "application/pdf")
self.assertIsInstance(call_kwargs["files"]["file"][1], bytes)
self.assertEqual(Document.objects.count(), 0)
self.assertEqual(Document.deleted_objects.count(), 1)
@override_settings(
PAPERLESS_EMAIL_HOST="localhost",
EMAIL_ENABLED=True,
PAPERLESS_URL="http://localhost:8000",
)
@mock.patch("django.core.mail.message.EmailMessage.send")
def test_workflow_trash_after_email_failure(self, mock_email_send) -> None:
"""
GIVEN:
- Workflow with email action (that fails), then move to trash action
WHEN:
- Document matches and workflow runs
- Email action raises exception
THEN:
- Email failure is logged
- Move to Trash still executes successfully (soft delete)
"""
mock_email_send.side_effect = Exception("Email server error")
trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
)
email_action = WorkflowActionEmail.objects.create(
subject="Document deleted: {doc_title}",
body="Document {doc_title} will be deleted",
to="user@example.com",
include_document=False,
)
email_workflow_action = WorkflowAction.objects.create(
type=WorkflowAction.WorkflowActionType.EMAIL,
email=email_action,
)
trash_workflow_action = WorkflowAction.objects.create(
type=WorkflowAction.WorkflowActionType.MOVE_TO_TRASH,
)
w = Workflow.objects.create(
name="Workflow with failing email then move to trash",
order=0,
)
w.triggers.add(trigger)
w.actions.add(email_workflow_action, trash_workflow_action)
w.save()
doc = Document.objects.create(
title="sample test",
correspondent=self.c,
original_filename="sample.pdf",
)
self.assertEqual(Document.objects.count(), 1)
self.assertEqual(Document.deleted_objects.count(), 0)
with self.assertLogs("paperless.workflows.actions", level="ERROR") as cm:
run_workflows(WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED, doc)
expected_str = "Error occurred sending notification email"
self.assertIn(expected_str, cm.output[0])
self.assertEqual(Document.objects.count(), 0)
self.assertEqual(Document.deleted_objects.count(), 1)
def test_multiple_workflows_trash_then_assignment(self):
"""
GIVEN:
- Workflow 1 (order=0) with move to trash action
- Workflow 2 (order=1) with assignment action
- Both workflows match the same document
WHEN:
- Workflows run sequentially
THEN:
- First workflow runs and deletes document (soft delete)
- Second workflow does not trigger (document no longer exists)
- Logs confirm move to trash and skipping of remaining workflows
"""
trigger1 = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
)
trash_workflow_action = WorkflowAction.objects.create(
type=WorkflowAction.WorkflowActionType.MOVE_TO_TRASH,
)
w1 = Workflow.objects.create(
name="Workflow 1 - Move to Trash",
order=0,
)
w1.triggers.add(trigger1)
w1.actions.add(trash_workflow_action)
w1.save()
trigger2 = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
)
assignment_action = WorkflowAction.objects.create(
type=WorkflowAction.WorkflowActionType.ASSIGNMENT,
assign_correspondent=self.c2,
)
w2 = Workflow.objects.create(
name="Workflow 2 - Assignment",
order=1,
)
w2.triggers.add(trigger2)
w2.actions.add(assignment_action)
w2.save()
doc = Document.objects.create(
title="sample test",
correspondent=self.c,
original_filename="sample.pdf",
)
self.assertEqual(Document.objects.count(), 1)
self.assertEqual(Document.deleted_objects.count(), 0)
with self.assertLogs("paperless", level="DEBUG") as cm:
run_workflows(WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED, doc)
self.assertEqual(Document.objects.count(), 0)
self.assertEqual(Document.deleted_objects.count(), 1)
# We check logs instead of WorkflowRun.objects.count() because when the document
# is soft-deleted, the WorkflowRun is cascade-deleted (hard delete) since it does
# not inherit from the SoftDeleteModel. The logs confirm that the first workflow
# executed the move to trash and remaining workflows were skipped.
log_output = "\n".join(cm.output)
self.assertIn("Moved document", log_output)
self.assertIn("to trash", log_output)
self.assertIn(
"Document was moved to trash, skipping remaining workflows",
log_output,
)
def test_workflow_delete_action_during_consumption(self):
"""
GIVEN:
- Workflow with consumption trigger and delete action
WHEN:
- Document is being consumed and workflow runs
THEN:
- StopConsumeTaskError is raised to halt consumption
- Original file is deleted
- No document is created
"""
trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
sources=f"{DocumentSource.ConsumeFolder}",
filter_filename="*",
)
action = WorkflowAction.objects.create(
type=WorkflowAction.WorkflowActionType.MOVE_TO_TRASH,
)
w = Workflow.objects.create(
name="Workflow Delete During Consumption",
order=0,
)
w.triggers.add(trigger)
w.actions.add(action)
w.save()
# Create a test file to be consumed
test_file = shutil.copy(
self.SAMPLE_DIR / "simple.pdf",
self.dirs.scratch_dir / "simple.pdf",
)
test_file_path = Path(test_file)
self.assertTrue(test_file_path.exists())
# Create a ConsumableDocument
consumable_doc = ConsumableDocument(
source=DocumentSource.ConsumeFolder,
original_file=test_file_path,
)
self.assertEqual(Document.objects.count(), 0)
# Run workflows with overrides (consumption flow)
with self.assertRaises(StopConsumeTaskError) as context:
run_workflows(
WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
consumable_doc,
overrides=DocumentMetadataOverrides(),
)
self.assertIn("deleted by workflow action", str(context.exception))
# File should be deleted
self.assertFalse(test_file_path.exists())
# No document should be created
self.assertEqual(Document.objects.count(), 0)
def test_workflow_delete_action_during_consumption_with_assignment(self):
"""
GIVEN:
- Workflow with consumption trigger, assignment action, then delete action
WHEN:
- Document is being consumed and workflow runs
THEN:
- StopConsumeTaskError is raised to halt consumption
- Original file is deleted
- No document is created (even though assignment would have worked)
"""
trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
sources=f"{DocumentSource.ConsumeFolder}",
filter_filename="*",
)
assignment_action = WorkflowAction.objects.create(
type=WorkflowAction.WorkflowActionType.ASSIGNMENT,
assign_title="This should not be applied",
assign_correspondent=self.c,
)
trash_workflow_action = WorkflowAction.objects.create(
type=WorkflowAction.WorkflowActionType.MOVE_TO_TRASH,
)
w = Workflow.objects.create(
name="Workflow Assignment then Delete During Consumption",
order=0,
)
w.triggers.add(trigger)
w.actions.add(assignment_action, trash_workflow_action)
w.save()
# Create a test file to be consumed
test_file = shutil.copy(
self.SAMPLE_DIR / "simple.pdf",
self.dirs.scratch_dir / "simple2.pdf",
)
test_file_path = Path(test_file)
self.assertTrue(test_file_path.exists())
# Create a ConsumableDocument
consumable_doc = ConsumableDocument(
source=DocumentSource.ConsumeFolder,
original_file=test_file_path,
)
self.assertEqual(Document.objects.count(), 0)
# Run workflows with overrides (consumption flow)
with self.assertRaises(StopConsumeTaskError):
run_workflows(
WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
consumable_doc,
overrides=DocumentMetadataOverrides(),
)
# File should be deleted
self.assertFalse(test_file_path.exists())
# No document should be created
self.assertEqual(Document.objects.count(), 0)
class TestWebhookSend:
def test_send_webhook_data_or_json(
@@ -4380,17 +3956,13 @@ class TestWebhookSend:
@pytest.fixture
def resolve_to(monkeypatch: pytest.MonkeyPatch) -> Callable[[str], None]:
def resolve_to(monkeypatch):
"""
Force DNS resolution to a specific IP for any hostname.
"""
def _set(ip: str) -> None:
def fake_getaddrinfo(
host: str,
*_args: object,
**_kwargs: object,
) -> list[tuple[Any, ...]]:
def _set(ip: str):
def fake_getaddrinfo(host, *_args, **_kwargs):
return [(socket.AF_INET, None, None, "", (ip, 0))]
monkeypatch.setattr(socket, "getaddrinfo", fake_getaddrinfo)
@@ -4531,7 +4103,7 @@ class TestWebhookSecurity:
def test_strips_user_supplied_host_header(
self,
httpx_mock: HTTPXMock,
resolve_to: Callable[[str], None],
resolve_to,
) -> None:
"""
GIVEN:
@@ -4597,7 +4169,7 @@ class TestDateWorkflowLocalization(
self,
title_template: str,
expected_title: str,
) -> None:
):
"""
GIVEN:
- Document added workflow with title template using localize_date filter
@@ -4662,7 +4234,7 @@ class TestDateWorkflowLocalization(
self,
title_template: str,
expected_title: str,
) -> None:
):
"""
GIVEN:
- Document updated workflow with title template using localize_date filter
@@ -4738,7 +4310,7 @@ class TestDateWorkflowLocalization(
settings: SettingsWrapper,
title_template: str,
expected_title: str,
) -> None:
):
trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
sources=f"{DocumentSource.ApiUpload}",

View File

@@ -1,6 +1,5 @@
import logging
import re
import uuid
from pathlib import Path
from django.conf import settings
@@ -16,7 +15,6 @@ from documents.models import Document
from documents.models import DocumentType
from documents.models import WorkflowAction
from documents.models import WorkflowTrigger
from documents.plugins.base import StopConsumeTaskError
from documents.signals import document_consumption_finished
from documents.templating.workflows import parse_w_workflow_placeholders
from documents.workflows.webhooks import send_webhook
@@ -340,33 +338,3 @@ def execute_password_removal_action(
document.pk,
extra={"group": logging_group},
)
def execute_move_to_trash_action(
action: WorkflowAction,
document: Document | ConsumableDocument,
logging_group: uuid.UUID | None,
) -> None:
"""
Execute a move to trash action for a workflow on an existing document or a
document in consumption. In case of an existing document it soft-deletes
the document. In case of consumption it aborts consumption and deletes the
file.
"""
if isinstance(document, Document):
document.delete()
logger.debug(
f"Moved document {document} to trash",
extra={"group": logging_group},
)
else:
if document.original_file.exists():
document.original_file.unlink()
logger.info(
f"Workflow move to trash action triggered during consumption, "
f"deleting file {document.original_file}",
extra={"group": logging_group},
)
raise StopConsumeTaskError(
"Document deleted by workflow action during consumption",
)

View File

@@ -2,7 +2,7 @@ msgid ""
msgstr ""
"Project-Id-Version: paperless-ngx\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2026-02-24 00:43+0000\n"
"POT-Creation-Date: 2026-02-16 17:32+0000\n"
"PO-Revision-Date: 2022-02-17 04:17\n"
"Last-Translator: \n"
"Language-Team: English\n"
@@ -89,7 +89,7 @@ msgstr ""
msgid "Automatic"
msgstr ""
#: documents/models.py:66 documents/models.py:444 documents/models.py:1663
#: documents/models.py:66 documents/models.py:444 documents/models.py:1659
#: paperless_mail/models.py:23 paperless_mail/models.py:143
msgid "name"
msgstr ""
@@ -252,7 +252,7 @@ msgid "The position of this document in your physical document archive."
msgstr ""
#: documents/models.py:313 documents/models.py:688 documents/models.py:742
#: documents/models.py:1706
#: documents/models.py:1702
msgid "document"
msgstr ""
@@ -1093,197 +1093,193 @@ msgid "Password removal"
msgstr ""
#: documents/models.py:1414
msgid "Move to trash"
msgstr ""
#: documents/models.py:1418
msgid "Workflow Action Type"
msgstr ""
#: documents/models.py:1423 documents/models.py:1665
#: documents/models.py:1419 documents/models.py:1661
#: paperless_mail/models.py:145
msgid "order"
msgstr ""
#: documents/models.py:1426
#: documents/models.py:1422
msgid "assign title"
msgstr ""
#: documents/models.py:1430
#: documents/models.py:1426
msgid "Assign a document title, must be a Jinja2 template, see documentation."
msgstr ""
#: documents/models.py:1438 paperless_mail/models.py:274
#: documents/models.py:1434 paperless_mail/models.py:274
msgid "assign this tag"
msgstr ""
#: documents/models.py:1447 paperless_mail/models.py:282
#: documents/models.py:1443 paperless_mail/models.py:282
msgid "assign this document type"
msgstr ""
#: documents/models.py:1456 paperless_mail/models.py:296
#: documents/models.py:1452 paperless_mail/models.py:296
msgid "assign this correspondent"
msgstr ""
#: documents/models.py:1465
#: documents/models.py:1461
msgid "assign this storage path"
msgstr ""
#: documents/models.py:1474
#: documents/models.py:1470
msgid "assign this owner"
msgstr ""
#: documents/models.py:1481
#: documents/models.py:1477
msgid "grant view permissions to these users"
msgstr ""
#: documents/models.py:1488
#: documents/models.py:1484
msgid "grant view permissions to these groups"
msgstr ""
#: documents/models.py:1495
#: documents/models.py:1491
msgid "grant change permissions to these users"
msgstr ""
#: documents/models.py:1502
#: documents/models.py:1498
msgid "grant change permissions to these groups"
msgstr ""
#: documents/models.py:1509
#: documents/models.py:1505
msgid "assign these custom fields"
msgstr ""
#: documents/models.py:1513
#: documents/models.py:1509
msgid "custom field values"
msgstr ""
#: documents/models.py:1517
#: documents/models.py:1513
msgid "Optional values to assign to the custom fields."
msgstr ""
#: documents/models.py:1526
#: documents/models.py:1522
msgid "remove these tag(s)"
msgstr ""
#: documents/models.py:1531
#: documents/models.py:1527
msgid "remove all tags"
msgstr ""
#: documents/models.py:1538
#: documents/models.py:1534
msgid "remove these document type(s)"
msgstr ""
#: documents/models.py:1543
#: documents/models.py:1539
msgid "remove all document types"
msgstr ""
#: documents/models.py:1550
#: documents/models.py:1546
msgid "remove these correspondent(s)"
msgstr ""
#: documents/models.py:1555
#: documents/models.py:1551
msgid "remove all correspondents"
msgstr ""
#: documents/models.py:1562
#: documents/models.py:1558
msgid "remove these storage path(s)"
msgstr ""
#: documents/models.py:1567
#: documents/models.py:1563
msgid "remove all storage paths"
msgstr ""
#: documents/models.py:1574
#: documents/models.py:1570
msgid "remove these owner(s)"
msgstr ""
#: documents/models.py:1579
#: documents/models.py:1575
msgid "remove all owners"
msgstr ""
#: documents/models.py:1586
#: documents/models.py:1582
msgid "remove view permissions for these users"
msgstr ""
#: documents/models.py:1593
#: documents/models.py:1589
msgid "remove view permissions for these groups"
msgstr ""
#: documents/models.py:1600
#: documents/models.py:1596
msgid "remove change permissions for these users"
msgstr ""
#: documents/models.py:1607
#: documents/models.py:1603
msgid "remove change permissions for these groups"
msgstr ""
#: documents/models.py:1612
#: documents/models.py:1608
msgid "remove all permissions"
msgstr ""
#: documents/models.py:1619
#: documents/models.py:1615
msgid "remove these custom fields"
msgstr ""
#: documents/models.py:1624
#: documents/models.py:1620
msgid "remove all custom fields"
msgstr ""
#: documents/models.py:1633
#: documents/models.py:1629
msgid "email"
msgstr ""
#: documents/models.py:1642
#: documents/models.py:1638
msgid "webhook"
msgstr ""
#: documents/models.py:1646
#: documents/models.py:1642
msgid "passwords"
msgstr ""
#: documents/models.py:1650
#: documents/models.py:1646
msgid ""
"Passwords to try when removing PDF protection. Separate with commas or new "
"lines."
msgstr ""
#: documents/models.py:1655
#: documents/models.py:1651
msgid "workflow action"
msgstr ""
#: documents/models.py:1656
#: documents/models.py:1652
msgid "workflow actions"
msgstr ""
#: documents/models.py:1671
#: documents/models.py:1667
msgid "triggers"
msgstr ""
#: documents/models.py:1678
#: documents/models.py:1674
msgid "actions"
msgstr ""
#: documents/models.py:1681 paperless_mail/models.py:154
#: documents/models.py:1677 paperless_mail/models.py:154
msgid "enabled"
msgstr ""
#: documents/models.py:1692
#: documents/models.py:1688
msgid "workflow"
msgstr ""
#: documents/models.py:1696
#: documents/models.py:1692
msgid "workflow trigger type"
msgstr ""
#: documents/models.py:1710
#: documents/models.py:1706
msgid "date run"
msgstr ""
#: documents/models.py:1716
#: documents/models.py:1712
msgid "workflow run"
msgstr ""
#: documents/models.py:1717
#: documents/models.py:1713
msgid "workflow runs"
msgstr ""

View File

@@ -202,3 +202,43 @@ def audit_log_check(app_configs, **kwargs):
)
return result
@register()
def check_deprecated_db_settings(
app_configs: object,
**kwargs: object,
) -> list[Warning]:
"""Check for deprecated database environment variables.
Detects legacy advanced options that should be migrated to
PAPERLESS_DB_OPTIONS. Returns one Warning per deprecated variable found.
"""
deprecated_vars: dict[str, str] = {
"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",
}
warnings: list[Warning] = []
for var_name, db_option_key in deprecated_vars.items():
if not os.getenv(var_name):
continue
warnings.append(
Warning(
f"Deprecated environment variable: {var_name}",
hint=(
f"{var_name} is no longer supported and will be removed in v3.2. "
f"Set the equivalent option via PAPERLESS_DB_OPTIONS instead. "
f'Example: PAPERLESS_DB_OPTIONS=\'{{"{db_option_key}": "<value>"}}\'. '
"See https://docs.paperless-ngx.com/migration/ for the full reference."
),
id="paperless.W001",
),
)
return warnings

View File

@@ -17,6 +17,8 @@ from dateparser.languages.loader import LocaleDataLoader
from django.utils.translation import gettext_lazy as _
from dotenv import load_dotenv
from paperless.settings.custom import parse_db_settings
logger = logging.getLogger("paperless.settings")
# Tap paperless.conf if it's available
@@ -722,83 +724,8 @@ EMAIL_CERTIFICATE_FILE = __get_optional_path("PAPERLESS_EMAIL_CERTIFICATE_LOCATI
###############################################################################
# Database #
###############################################################################
def _parse_db_settings() -> dict:
databases = {
"default": {
"ENGINE": "django.db.backends.sqlite3",
"NAME": DATA_DIR / "db.sqlite3",
"OPTIONS": {},
},
}
if os.getenv("PAPERLESS_DBHOST"):
# Have sqlite available as a second option for management commands
# This is important when migrating to/from sqlite
databases["sqlite"] = databases["default"].copy()
databases["default"] = {
"HOST": os.getenv("PAPERLESS_DBHOST"),
"NAME": os.getenv("PAPERLESS_DBNAME", "paperless"),
"USER": os.getenv("PAPERLESS_DBUSER", "paperless"),
"PASSWORD": os.getenv("PAPERLESS_DBPASS", "paperless"),
"OPTIONS": {},
}
if os.getenv("PAPERLESS_DBPORT"):
databases["default"]["PORT"] = os.getenv("PAPERLESS_DBPORT")
# Leave room for future extensibility
if os.getenv("PAPERLESS_DBENGINE") == "mariadb":
engine = "django.db.backends.mysql"
# Contrary to Postgres, Django does not natively support connection pooling for MariaDB.
# However, since MariaDB uses threads instead of forks, establishing connections is significantly faster
# compared to PostgreSQL, so the lack of pooling is not an issue
options = {
"read_default_file": "/etc/mysql/my.cnf",
"charset": "utf8mb4",
"ssl_mode": os.getenv("PAPERLESS_DBSSLMODE", "PREFERRED"),
"ssl": {
"ca": os.getenv("PAPERLESS_DBSSLROOTCERT", None),
"cert": os.getenv("PAPERLESS_DBSSLCERT", None),
"key": os.getenv("PAPERLESS_DBSSLKEY", None),
},
}
else: # Default to PostgresDB
engine = "django.db.backends.postgresql"
options = {
"sslmode": os.getenv("PAPERLESS_DBSSLMODE", "prefer"),
"sslrootcert": os.getenv("PAPERLESS_DBSSLROOTCERT", None),
"sslcert": os.getenv("PAPERLESS_DBSSLCERT", None),
"sslkey": os.getenv("PAPERLESS_DBSSLKEY", None),
}
if int(os.getenv("PAPERLESS_DB_POOLSIZE", 0)) > 0:
options.update(
{
"pool": {
"min_size": 1,
"max_size": int(os.getenv("PAPERLESS_DB_POOLSIZE")),
},
},
)
databases["default"]["ENGINE"] = engine
databases["default"]["OPTIONS"].update(options)
if os.getenv("PAPERLESS_DB_TIMEOUT") is not None:
if databases["default"]["ENGINE"] == "django.db.backends.sqlite3":
databases["default"]["OPTIONS"].update(
{"timeout": int(os.getenv("PAPERLESS_DB_TIMEOUT"))},
)
else:
databases["default"]["OPTIONS"].update(
{"connect_timeout": int(os.getenv("PAPERLESS_DB_TIMEOUT"))},
)
databases["sqlite"]["OPTIONS"].update(
{"timeout": int(os.getenv("PAPERLESS_DB_TIMEOUT"))},
)
return databases
DATABASES = _parse_db_settings()
DATABASES = parse_db_settings(DATA_DIR)
if os.getenv("PAPERLESS_DBENGINE") == "mariadb":
# Silence Django error on old MariaDB versions.

View File

@@ -0,0 +1,128 @@
import os
from pathlib import Path
from typing import Any
from paperless.settings.parsers import get_choice_from_env
from paperless.settings.parsers import get_int_from_env
from paperless.settings.parsers import parse_dict_from_str
def parse_db_settings(data_dir: Path) -> dict[str, dict[str, Any]]:
"""Parse database settings from environment variables.
Core connection variables (no deprecation):
- PAPERLESS_DBENGINE (sqlite/postgresql/mariadb)
- PAPERLESS_DBHOST, PAPERLESS_DBPORT
- PAPERLESS_DBNAME, PAPERLESS_DBUSER, PAPERLESS_DBPASS
Advanced options can be set via:
- Legacy individual env vars (deprecated in v3.0, removed in v3.2)
- PAPERLESS_DB_OPTIONS (recommended v3+ approach)
Args:
data_dir: The data directory path for SQLite database location.
Returns:
A databases dict suitable for Django DATABASES setting.
"""
engine = get_choice_from_env(
"PAPERLESS_DBENGINE",
{"sqlite", "postgresql", "mariadb"},
default="sqlite",
)
db_config: dict[str, Any]
base_options: dict[str, Any]
match engine:
case "sqlite":
db_config = {
"ENGINE": "django.db.backends.sqlite3",
"NAME": str((data_dir / "db.sqlite3").resolve()),
}
base_options = {}
case "postgresql":
db_config = {
"ENGINE": "django.db.backends.postgresql",
"HOST": os.getenv("PAPERLESS_DBHOST"),
"NAME": os.getenv("PAPERLESS_DBNAME", "paperless"),
"USER": os.getenv("PAPERLESS_DBUSER", "paperless"),
"PASSWORD": os.getenv("PAPERLESS_DBPASS", "paperless"),
}
base_options = {
"sslmode": os.getenv("PAPERLESS_DBSSLMODE", "prefer"),
"sslrootcert": os.getenv("PAPERLESS_DBSSLROOTCERT"),
"sslcert": os.getenv("PAPERLESS_DBSSLCERT"),
"sslkey": os.getenv("PAPERLESS_DBSSLKEY"),
}
if (pool_size := get_int_from_env("PAPERLESS_DB_POOLSIZE")) is not None:
base_options["pool"] = {
"min_size": 1,
"max_size": pool_size,
}
case "mariadb":
db_config = {
"ENGINE": "django.db.backends.mysql",
"HOST": os.getenv("PAPERLESS_DBHOST"),
"NAME": os.getenv("PAPERLESS_DBNAME", "paperless"),
"USER": os.getenv("PAPERLESS_DBUSER", "paperless"),
"PASSWORD": os.getenv("PAPERLESS_DBPASS", "paperless"),
}
base_options = {
"read_default_file": "/etc/mysql/my.cnf",
"charset": "utf8mb4",
"collation": "utf8mb4_unicode_ci",
"ssl_mode": os.getenv("PAPERLESS_DBSSLMODE", "PREFERRED"),
"ssl": {
"ca": os.getenv("PAPERLESS_DBSSLROOTCERT"),
"cert": os.getenv("PAPERLESS_DBSSLCERT"),
"key": os.getenv("PAPERLESS_DBSSLKEY"),
},
}
case _: # pragma: no cover
raise NotImplementedError(engine)
# Handle port setting for external databases
if (
engine in ("postgresql", "mariadb")
and (port := get_int_from_env("PAPERLESS_DBPORT")) is not None
):
db_config["PORT"] = port
# Handle timeout setting (common across all engines, different key names)
if (timeout := get_int_from_env("PAPERLESS_DB_TIMEOUT")) is not None:
timeout_key = "timeout" if engine == "sqlite" else "connect_timeout"
base_options[timeout_key] = timeout
# Apply PAPERLESS_DB_OPTIONS overrides
db_config["OPTIONS"] = parse_dict_from_str(
os.getenv("PAPERLESS_DB_OPTIONS"),
defaults=base_options,
separator=";",
type_map={
# SQLite options
"timeout": int,
# Postgres/MariaDB options
"connect_timeout": int,
"pool.min_size": int,
"pool.max_size": int,
},
)
databases = {"default": db_config}
# Add SQLite fallback for PostgreSQL/MariaDB
# TODO: Is this really useful/used?
if engine in ("postgresql", "mariadb"):
databases["sqlite"] = {
"ENGINE": "django.db.backends.sqlite3",
"NAME": str((data_dir / "db.sqlite3").resolve()),
"OPTIONS": {},
}
return databases

View File

@@ -0,0 +1,192 @@
import copy
import os
from collections.abc import Callable
from collections.abc import Mapping
from pathlib import Path
from typing import Any
from typing import TypeVar
from typing import overload
T = TypeVar("T")
def str_to_bool(value: str) -> bool:
"""
Converts a string representation of truth to a boolean value.
Recognizes 'true', '1', 't', 'y', 'yes' as True, and
'false', '0', 'f', 'n', 'no' as False. Case-insensitive.
Args:
value: The string to convert.
Returns:
The boolean representation of the string.
Raises:
ValueError: If the string is not a recognized boolean value.
"""
val_lower = value.strip().lower()
if val_lower in ("true", "1", "t", "y", "yes"):
return True
elif val_lower in ("false", "0", "f", "n", "no"):
return False
raise ValueError(f"Cannot convert '{value}' to a boolean.")
@overload
def get_int_from_env(key: str) -> int | None: ...
@overload
def get_int_from_env(key: str, default: None) -> int | None: ...
@overload
def get_int_from_env(key: str, default: int) -> int: ...
def get_int_from_env(key: str, default: int | None = None) -> int | None:
"""
Return an integer value based on the environment variable.
If default is provided, returns that value when key is missing.
If default is None, returns None when key is missing.
"""
if key not in os.environ:
return default
return int(os.environ[key])
def parse_dict_from_str(
env_str: str | None,
defaults: dict[str, Any] | None = None,
type_map: Mapping[str, Callable[[str], Any]] | None = None,
separator: str = ",",
) -> dict[str, Any]:
"""
Parses a key-value string into a dictionary, applying defaults and casting types.
Supports nested keys via dot-notation, e.g.:
"database.host=localhost,database.port=5432"
Args:
env_str: The string from the environment variable (e.g., "port=9090,debug=true").
defaults: A dictionary of default values (can contain nested dicts).
type_map: A dictionary mapping keys (dot-notation allowed) to a type or a parsing
function (e.g., {'port': int, 'debug': bool, 'database.port': int}).
The special `bool` type triggers custom boolean parsing.
separator: The character used to separate key-value pairs. Defaults to ','.
Returns:
A dictionary with the parsed and correctly-typed settings.
Raises:
ValueError: If a value cannot be cast to its specified type.
"""
def _set_nested(d: dict, keys: list[str], value: Any) -> None:
"""Set a nested value, creating intermediate dicts as needed."""
cur = d
for k in keys[:-1]:
if k not in cur or not isinstance(cur[k], dict):
cur[k] = {}
cur = cur[k]
cur[keys[-1]] = value
def _get_nested(d: dict, keys: list[str]) -> Any:
"""Get nested value or raise KeyError if not present."""
cur = d
for k in keys:
if not isinstance(cur, dict) or k not in cur:
raise KeyError
cur = cur[k]
return cur
def _has_nested(d: dict, keys: list[str]) -> bool:
try:
_get_nested(d, keys)
return True
except KeyError:
return False
settings: dict[str, Any] = copy.deepcopy(defaults) if defaults else {}
_type_map = type_map if type_map else {}
if not env_str:
return settings
# Parse the environment string using the specified separator
pairs = [p.strip() for p in env_str.split(separator) if p.strip()]
for pair in pairs:
if "=" not in pair:
# ignore malformed pairs
continue
key, val = pair.split("=", 1)
key = key.strip()
val = val.strip()
if not key:
continue
parts = key.split(".")
_set_nested(settings, parts, val)
# Apply type casting to the updated settings (supports nested keys in type_map)
for key, caster in _type_map.items():
key_parts = key.split(".")
if _has_nested(settings, key_parts):
raw_val = _get_nested(settings, key_parts)
# Only cast if it's a string (i.e. from env parsing). If defaults already provided
# a different type we leave it as-is.
if isinstance(raw_val, str):
try:
if caster is bool:
parsed = str_to_bool(raw_val)
elif caster is Path:
parsed = Path(raw_val).resolve()
else:
parsed = caster(raw_val)
except (ValueError, TypeError) as e:
caster_name = getattr(caster, "__name__", repr(caster))
raise ValueError(
f"Error casting key '{key}' with value '{raw_val}' "
f"to type '{caster_name}'",
) from e
_set_nested(settings, key_parts, parsed)
return settings
def get_choice_from_env(
env_key: str,
choices: set[str],
default: str | None = None,
) -> str:
"""
Gets and validates an environment variable against a set of allowed choices.
Args:
env_key: The environment variable key to validate
choices: Set of valid choices for the environment variable
default: Optional default value if environment variable is not set
Returns:
The validated environment variable value
Raises:
ValueError: If the environment variable value is not in choices
or if no default is provided and env var is missing
"""
value = os.environ.get(env_key, default)
if value is None:
raise ValueError(
f"Environment variable '{env_key}' is required but not set.",
)
if value not in choices:
raise ValueError(
f"Environment variable '{env_key}' has invalid value '{value}'. "
f"Valid choices are: {', '.join(sorted(choices))}",
)
return value

View File

@@ -2,13 +2,17 @@ import os
from pathlib import Path
from unittest import mock
import pytest
from django.core.checks import Warning
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
from paperless.checks import debug_mode_check
from paperless.checks import paths_check
from paperless.checks import settings_values_check
@@ -237,3 +241,157 @@ class TestAuditLogChecks(TestCase):
("auditlog table was found but audit log is disabled."),
msg.msg,
)
DEPRECATED_VARS: dict[str, str] = {
"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",
}
class TestDeprecatedDbSettings:
"""Test suite for the check_deprecated_db_settings system check."""
def test_no_deprecated_vars_returns_empty(
self,
mocker: MockerFixture,
) -> None:
"""No warnings when none of the deprecated vars are present."""
# clear=True ensures vars from the outer test environment do not leak in
mocker.patch.dict(os.environ, {}, clear=True)
result = check_deprecated_db_settings(None)
assert result == []
@pytest.mark.parametrize(
("env_var", "db_option_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(
self,
mocker: MockerFixture,
env_var: str,
db_option_key: str,
) -> None:
"""Each deprecated var in isolation produces exactly one warning."""
mocker.patch.dict(os.environ, {env_var: "some_value"}, clear=True)
result = check_deprecated_db_settings(None)
assert len(result) == 1
warning = result[0]
assert isinstance(warning, Warning)
assert warning.id == "paperless.W001"
assert env_var in warning.hint
assert db_option_key in warning.hint
def test_multiple_deprecated_vars_produce_one_warning_each(
self,
mocker: MockerFixture,
) -> None:
"""Each deprecated var present in the environment gets its own warning."""
set_vars = {
"PAPERLESS_DB_TIMEOUT": "30",
"PAPERLESS_DB_POOLSIZE": "10",
"PAPERLESS_DBSSLMODE": "require",
}
mocker.patch.dict(os.environ, set_vars, clear=True)
result = check_deprecated_db_settings(None)
assert len(result) == len(set_vars)
assert all(isinstance(w, Warning) for w in result)
assert all(w.id == "paperless.W001" for w in result)
all_hints = " ".join(w.hint for w in result)
for var_name in set_vars:
assert var_name in all_hints
def test_all_deprecated_vars_produces_one_warning_each(
self,
mocker: MockerFixture,
) -> None:
"""All deprecated vars set simultaneously produces one warning per var."""
all_vars = {var: "some_value" for var in DEPRECATED_VARS}
mocker.patch.dict(os.environ, all_vars, clear=True)
result = check_deprecated_db_settings(None)
assert len(result) == len(DEPRECATED_VARS)
assert all(isinstance(w, Warning) for w in result)
assert all(w.id == "paperless.W001" for w in result)
def test_unset_vars_not_mentioned_in_warnings(
self,
mocker: MockerFixture,
) -> None:
"""Vars absent from the environment do not appear in any warning."""
mocker.patch.dict(
os.environ,
{"PAPERLESS_DB_TIMEOUT": "30"},
clear=True,
)
result = check_deprecated_db_settings(None)
assert len(result) == 1
assert "PAPERLESS_DB_TIMEOUT" in result[0].hint
unset_vars = [v for v in DEPRECATED_VARS if v != "PAPERLESS_DB_TIMEOUT"]
for var_name in unset_vars:
assert var_name not in result[0].hint
def test_empty_string_var_not_treated_as_set(
self,
mocker: MockerFixture,
) -> None:
"""A var set to an empty string is not flagged as a deprecated setting."""
mocker.patch.dict(
os.environ,
{"PAPERLESS_DB_TIMEOUT": ""},
clear=True,
)
result = check_deprecated_db_settings(None)
assert result == []
def test_warning_mentions_migration_target(
self,
mocker: MockerFixture,
) -> None:
"""Each warning hints at PAPERLESS_DB_OPTIONS as the migration target."""
mocker.patch.dict(
os.environ,
{"PAPERLESS_DBSSLMODE": "require"},
clear=True,
)
result = check_deprecated_db_settings(None)
assert len(result) == 1
assert "PAPERLESS_DB_OPTIONS" in result[0].hint
def test_warning_message_identifies_var(
self,
mocker: MockerFixture,
) -> None:
"""The warning message (not just the hint) identifies the offending var."""
mocker.patch.dict(
os.environ,
{"PAPERLESS_DBSSLCERT": "/path/to/cert.pem"},
clear=True,
)
result = check_deprecated_db_settings(None)
assert len(result) == 1
assert "PAPERLESS_DBSSLCERT" in result[0].msg

View File

@@ -1,19 +1,21 @@
import datetime
import os
from pathlib import Path
from unittest import TestCase
from unittest import mock
import pytest
from celery.schedules import crontab
from pytest_mock import MockerFixture
from paperless.settings import _parse_base_paths
from paperless.settings import _parse_beat_schedule
from paperless.settings import _parse_dateparser_languages
from paperless.settings import _parse_db_settings
from paperless.settings import _parse_ignore_dates
from paperless.settings import _parse_paperless_url
from paperless.settings import _parse_redis_url
from paperless.settings import default_threads_per_worker
from paperless.settings.custom import parse_db_settings
class TestIgnoreDateParsing(TestCase):
@@ -378,62 +380,302 @@ class TestCeleryScheduleParsing(TestCase):
)
class TestDBSettings(TestCase):
def test_db_timeout_with_sqlite(self) -> None:
"""
GIVEN:
- PAPERLESS_DB_TIMEOUT is set
WHEN:
- Settings are parsed
THEN:
- PAPERLESS_DB_TIMEOUT set for sqlite
"""
with mock.patch.dict(
os.environ,
{
"PAPERLESS_DB_TIMEOUT": "10",
},
):
databases = _parse_db_settings()
class TestParseDbSettings:
"""Test suite for parse_db_settings function."""
self.assertDictEqual(
@pytest.mark.parametrize(
("env_vars", "expected_database_settings"),
[
pytest.param(
{},
{
"timeout": 10.0,
"default": {
"ENGINE": "django.db.backends.sqlite3",
"NAME": None, # Will be replaced with tmp_path
"OPTIONS": {},
},
},
databases["default"]["OPTIONS"],
)
def test_db_timeout_with_not_sqlite(self) -> None:
"""
GIVEN:
- PAPERLESS_DB_TIMEOUT is set but db is not sqlite
WHEN:
- Settings are parsed
THEN:
- PAPERLESS_DB_TIMEOUT set correctly in non-sqlite db & for fallback sqlite db
"""
with mock.patch.dict(
os.environ,
{
"PAPERLESS_DBHOST": "127.0.0.1",
"PAPERLESS_DB_TIMEOUT": "10",
},
):
databases = _parse_db_settings()
self.assertDictEqual(
databases["default"]["OPTIONS"],
databases["default"]["OPTIONS"]
| {
"connect_timeout": 10.0,
},
)
self.assertDictEqual(
id="default-sqlite",
),
pytest.param(
{
"timeout": 10.0,
"PAPERLESS_DBENGINE": "sqlite",
"PAPERLESS_DB_OPTIONS": "timeout=30",
},
databases["sqlite"]["OPTIONS"],
{
"default": {
"ENGINE": "django.db.backends.sqlite3",
"NAME": None, # Will be replaced with tmp_path
"OPTIONS": {
"timeout": 30,
},
},
},
id="sqlite-with-timeout-override",
),
pytest.param(
{
"PAPERLESS_DBENGINE": "postgresql",
"PAPERLESS_DBHOST": "localhost",
},
{
"default": {
"ENGINE": "django.db.backends.postgresql",
"HOST": "localhost",
"NAME": "paperless",
"USER": "paperless",
"PASSWORD": "paperless",
"OPTIONS": {
"sslmode": "prefer",
"sslrootcert": None,
"sslcert": None,
"sslkey": None,
},
},
"sqlite": {
"ENGINE": "django.db.backends.sqlite3",
"NAME": None, # Will be replaced with tmp_path
"OPTIONS": {},
},
},
id="postgresql-defaults",
),
pytest.param(
{
"PAPERLESS_DBENGINE": "postgresql",
"PAPERLESS_DBHOST": "paperless-db-host",
"PAPERLESS_DBPORT": "1111",
"PAPERLESS_DBNAME": "customdb",
"PAPERLESS_DBUSER": "customuser",
"PAPERLESS_DBPASS": "custompass",
"PAPERLESS_DB_OPTIONS": "pool.max_size=50;pool.min_size=2;sslmode=require",
},
{
"default": {
"ENGINE": "django.db.backends.postgresql",
"HOST": "paperless-db-host",
"PORT": 1111,
"NAME": "customdb",
"USER": "customuser",
"PASSWORD": "custompass",
"OPTIONS": {
"sslmode": "require",
"sslrootcert": None,
"sslcert": None,
"sslkey": None,
"pool": {
"min_size": 2,
"max_size": 50,
},
},
},
"sqlite": {
"ENGINE": "django.db.backends.sqlite3",
"NAME": None, # Will be replaced with tmp_path
"OPTIONS": {},
},
},
id="postgresql-overrides",
),
pytest.param(
{
"PAPERLESS_DBENGINE": "postgresql",
"PAPERLESS_DBHOST": "pghost",
"PAPERLESS_DB_POOLSIZE": "10",
},
{
"default": {
"ENGINE": "django.db.backends.postgresql",
"HOST": "pghost",
"NAME": "paperless",
"USER": "paperless",
"PASSWORD": "paperless",
"OPTIONS": {
"sslmode": "prefer",
"sslrootcert": None,
"sslcert": None,
"sslkey": None,
"pool": {
"min_size": 1,
"max_size": 10,
},
},
},
"sqlite": {
"ENGINE": "django.db.backends.sqlite3",
"NAME": None, # Will be replaced with tmp_path
"OPTIONS": {},
},
},
id="postgresql-legacy-poolsize",
),
pytest.param(
{
"PAPERLESS_DBENGINE": "postgresql",
"PAPERLESS_DBHOST": "pghost",
"PAPERLESS_DBSSLMODE": "require",
"PAPERLESS_DBSSLROOTCERT": "/certs/ca.crt",
"PAPERLESS_DB_TIMEOUT": "30",
},
{
"default": {
"ENGINE": "django.db.backends.postgresql",
"HOST": "pghost",
"NAME": "paperless",
"USER": "paperless",
"PASSWORD": "paperless",
"OPTIONS": {
"sslmode": "require",
"sslrootcert": "/certs/ca.crt",
"sslcert": None,
"sslkey": None,
"connect_timeout": 30,
},
},
"sqlite": {
"ENGINE": "django.db.backends.sqlite3",
"NAME": None, # Will be replaced with tmp_path
"OPTIONS": {},
},
},
id="postgresql-legacy-ssl-and-timeout",
),
pytest.param(
{
"PAPERLESS_DBENGINE": "mariadb",
"PAPERLESS_DBHOST": "localhost",
},
{
"default": {
"ENGINE": "django.db.backends.mysql",
"HOST": "localhost",
"NAME": "paperless",
"USER": "paperless",
"PASSWORD": "paperless",
"OPTIONS": {
"read_default_file": "/etc/mysql/my.cnf",
"charset": "utf8mb4",
"collation": "utf8mb4_unicode_ci",
"ssl_mode": "PREFERRED",
"ssl": {
"ca": None,
"cert": None,
"key": None,
},
},
},
"sqlite": {
"ENGINE": "django.db.backends.sqlite3",
"NAME": None, # Will be replaced with tmp_path
"OPTIONS": {},
},
},
id="mariadb-defaults",
),
pytest.param(
{
"PAPERLESS_DBENGINE": "mariadb",
"PAPERLESS_DBHOST": "paperless-mariadb-host",
"PAPERLESS_DBPORT": "5555",
"PAPERLESS_DBUSER": "my-cool-user",
"PAPERLESS_DBPASS": "my-secure-password",
"PAPERLESS_DB_OPTIONS": "ssl.ca=/path/to/ca.pem;ssl_mode=REQUIRED",
},
{
"default": {
"ENGINE": "django.db.backends.mysql",
"HOST": "paperless-mariadb-host",
"PORT": 5555,
"NAME": "paperless",
"USER": "my-cool-user",
"PASSWORD": "my-secure-password",
"OPTIONS": {
"read_default_file": "/etc/mysql/my.cnf",
"charset": "utf8mb4",
"collation": "utf8mb4_unicode_ci",
"ssl_mode": "REQUIRED",
"ssl": {
"ca": "/path/to/ca.pem",
"cert": None,
"key": None,
},
},
},
"sqlite": {
"ENGINE": "django.db.backends.sqlite3",
"NAME": None, # Will be replaced with tmp_path
"OPTIONS": {},
},
},
id="mariadb-overrides",
),
pytest.param(
{
"PAPERLESS_DBENGINE": "mariadb",
"PAPERLESS_DBHOST": "mariahost",
"PAPERLESS_DBSSLMODE": "REQUIRED",
"PAPERLESS_DBSSLROOTCERT": "/certs/ca.pem",
"PAPERLESS_DBSSLCERT": "/certs/client.pem",
"PAPERLESS_DBSSLKEY": "/certs/client.key",
"PAPERLESS_DB_TIMEOUT": "25",
},
{
"default": {
"ENGINE": "django.db.backends.mysql",
"HOST": "mariahost",
"NAME": "paperless",
"USER": "paperless",
"PASSWORD": "paperless",
"OPTIONS": {
"read_default_file": "/etc/mysql/my.cnf",
"charset": "utf8mb4",
"collation": "utf8mb4_unicode_ci",
"ssl_mode": "REQUIRED",
"ssl": {
"ca": "/certs/ca.pem",
"cert": "/certs/client.pem",
"key": "/certs/client.key",
},
"connect_timeout": 25,
},
},
"sqlite": {
"ENGINE": "django.db.backends.sqlite3",
"NAME": None, # Will be replaced with tmp_path
"OPTIONS": {},
},
},
id="mariadb-legacy-ssl-and-timeout",
),
],
)
def test_parse_db_settings(
self,
tmp_path: Path,
mocker: MockerFixture,
env_vars: dict[str, str],
expected_database_settings: dict[str, dict],
) -> None:
"""Test various database configurations with defaults and overrides."""
# Clear environment and set test vars
mocker.patch.dict(os.environ, env_vars, clear=True)
# Update expected paths with actual tmp_path
if (
"default" in expected_database_settings
and expected_database_settings["default"]["NAME"] is None
):
expected_database_settings["default"]["NAME"] = str(
tmp_path / "db.sqlite3",
)
if "sqlite" in expected_database_settings:
expected_database_settings["sqlite"]["NAME"] = str(
tmp_path / "db.sqlite3",
)
settings = parse_db_settings(tmp_path)
assert settings == expected_database_settings
class TestPaperlessURLSettings(TestCase):

View File

@@ -23,7 +23,6 @@ def get_embedding_model() -> BaseEmbedding:
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:
return HuggingFaceEmbedding(

View File

@@ -65,14 +65,12 @@ def test_get_embedding_model_openai(mock_ai_config):
mock_ai_config.return_value.llm_embedding_backend = LLMEmbeddingBackend.OPENAI
mock_ai_config.return_value.llm_embedding_model = "text-embedding-3-small"
mock_ai_config.return_value.llm_api_key = "test_api_key"
mock_ai_config.return_value.llm_endpoint = "http://test-url"
with patch("paperless_ai.embedding.OpenAIEmbedding") as MockOpenAIEmbedding:
model = get_embedding_model()
MockOpenAIEmbedding.assert_called_once_with(
model="text-embedding-3-small",
api_key="test_api_key",
api_base="http://test-url",
)
assert model == MockOpenAIEmbedding.return_value

View File

@@ -536,7 +536,6 @@ class MailAccountHandler(LoggingMixin):
self.log.debug(f"Processing mail account {account}")
total_processed_files = 0
consumed_messages: set[tuple[str, str | None]] = set()
try:
with get_mailbox(
account.imap_server,
@@ -575,7 +574,6 @@ class MailAccountHandler(LoggingMixin):
M,
rule,
supports_gmail_labels=supports_gmail_labels,
consumed_messages=consumed_messages,
)
if total_processed_files > 0 and rule.stop_processing:
self.log.debug(
@@ -607,8 +605,7 @@ class MailAccountHandler(LoggingMixin):
rule: MailRule,
*,
supports_gmail_labels: bool,
consumed_messages: set[tuple[str, str | None]],
) -> int:
):
folders = [rule.folder]
# In case of MOVE, make sure also the destination exists
if rule.action == MailRule.MailAction.MOVE:
@@ -655,26 +652,11 @@ class MailAccountHandler(LoggingMixin):
mails_processed = 0
total_processed_files = 0
rule_seen_messages: set[tuple[str, str | None]] = set()
for message in messages:
if TYPE_CHECKING:
assert isinstance(message, MailMessage)
message_key = (rule.folder, message.uid)
if message_key in rule_seen_messages:
self.log.debug(
f"Skipping duplicate fetched mail '{message.uid}' subject '{message.subject}' from '{message.from_}'.",
)
continue
rule_seen_messages.add(message_key)
if message_key in consumed_messages:
self.log.debug(
f"Skipping mail '{message.uid}' subject '{message.subject}' from '{message.from_}', already queued by a previous rule in this run.",
)
continue
if ProcessedMail.objects.filter(
rule=rule,
uid=message.uid,
@@ -687,8 +669,6 @@ class MailAccountHandler(LoggingMixin):
try:
processed_files = self._handle_message(message, rule)
if processed_files > 0:
consumed_messages.add(message_key)
total_processed_files += processed_files
mails_processed += 1

View File

@@ -863,66 +863,6 @@ class TestMail(
self.assertEqual(len(self.mailMocker.bogus_mailbox.messages), 0)
def test_handle_mail_account_overlapping_rules_only_first_consumes(self) -> None:
account = MailAccount.objects.create(
name="test",
imap_server="",
username="admin",
password="secret",
)
first_rule = MailRule.objects.create(
name="testrule-first",
account=account,
action=MailRule.MailAction.DELETE,
filter_subject="Claim",
order=1,
)
_ = MailRule.objects.create(
name="testrule-second",
account=account,
action=MailRule.MailAction.DELETE,
filter_subject="Claim",
order=2,
)
self.mail_account_handler.handle_mail_account(account)
self.mailMocker.apply_mail_actions()
self.assertEqual(self.mailMocker._queue_consumption_tasks_mock.call_count, 1)
queued_rule = self.mailMocker._queue_consumption_tasks_mock.call_args.kwargs[
"rule"
]
self.assertEqual(queued_rule.id, first_rule.id)
def test_handle_mail_account_skip_duplicate_uids_from_fetch(self) -> None:
account = MailAccount.objects.create(
name="test",
imap_server="",
username="admin",
password="secret",
)
_ = MailRule.objects.create(
name="testrule",
account=account,
action=MailRule.MailAction.DELETE,
filter_subject="Duplicated mail",
)
duplicated_message = self.mailMocker.messageBuilder.create_message(
subject="Duplicated mail",
)
self.mailMocker.bogus_mailbox.messages = [
duplicated_message,
duplicated_message,
]
self.mailMocker.bogus_mailbox.updateClient()
self.mail_account_handler.handle_mail_account(account)
self.mailMocker.apply_mail_actions()
self.assertEqual(self.mailMocker._queue_consumption_tasks_mock.call_count, 1)
@pytest.mark.flaky(reruns=4)
def test_handle_mail_account_flag(self) -> None:
account = MailAccount.objects.create(

View File

@@ -16,6 +16,7 @@ repo_name = "paperless-ngx/paperless-ngx"
nav = [
"index.md",
"setup.md",
"migration.md",
"usage.md",
"configuration.md",
"administration.md",