mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-03-12 20:21:23 +00:00
Compare commits
16 Commits
feature-ty
...
feature-cl
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
c7d4fb1f8b | ||
|
|
f15394fa5c | ||
|
|
773eb25f7d | ||
|
|
e2947ccff2 | ||
|
|
61841a767b | ||
|
|
15db023caa | ||
|
|
45b363659e | ||
|
|
7494161c95 | ||
|
|
5331312699 | ||
|
|
b5a002b8ed | ||
|
|
dd8573242d | ||
|
|
86fa74c115 | ||
|
|
b7b9e83f37 | ||
|
|
217b5df591 | ||
|
|
3efc9a5733 | ||
|
|
e19f341974 |
24
.github/dependabot.yml
vendored
24
.github/dependabot.yml
vendored
@@ -12,6 +12,8 @@ updates:
|
||||
open-pull-requests-limit: 10
|
||||
schedule:
|
||||
interval: "monthly"
|
||||
cooldown:
|
||||
default-days: 7
|
||||
labels:
|
||||
- "frontend"
|
||||
- "dependencies"
|
||||
@@ -36,7 +38,9 @@ updates:
|
||||
directory: "/"
|
||||
# Check for updates once a week
|
||||
schedule:
|
||||
interval: "weekly"
|
||||
interval: "monthly"
|
||||
cooldown:
|
||||
default-days: 7
|
||||
labels:
|
||||
- "backend"
|
||||
- "dependencies"
|
||||
@@ -97,6 +101,8 @@ updates:
|
||||
schedule:
|
||||
# Check for updates to GitHub Actions every month
|
||||
interval: "monthly"
|
||||
cooldown:
|
||||
default-days: 7
|
||||
labels:
|
||||
- "ci-cd"
|
||||
- "dependencies"
|
||||
@@ -112,7 +118,9 @@ updates:
|
||||
- "/"
|
||||
- "/.devcontainer/"
|
||||
schedule:
|
||||
interval: "weekly"
|
||||
interval: "monthly"
|
||||
cooldown:
|
||||
default-days: 7
|
||||
open-pull-requests-limit: 5
|
||||
labels:
|
||||
- "dependencies"
|
||||
@@ -123,7 +131,9 @@ updates:
|
||||
- package-ecosystem: "docker-compose"
|
||||
directory: "/docker/compose/"
|
||||
schedule:
|
||||
interval: "weekly"
|
||||
interval: "monthly"
|
||||
cooldown:
|
||||
default-days: 7
|
||||
open-pull-requests-limit: 5
|
||||
labels:
|
||||
- "dependencies"
|
||||
@@ -147,3 +157,11 @@ updates:
|
||||
postgres:
|
||||
patterns:
|
||||
- "docker.io/library/postgres*"
|
||||
- package-ecosystem: "pre-commit" # See documentation for possible values
|
||||
directory: "/" # Location of package manifests
|
||||
schedule:
|
||||
interval: "monthly"
|
||||
groups:
|
||||
pre-commit-dependencies:
|
||||
patterns:
|
||||
- "*"
|
||||
|
||||
12
.github/workflows/ci-docker.yml
vendored
12
.github/workflows/ci-docker.yml
vendored
@@ -104,9 +104,9 @@ jobs:
|
||||
echo "repository=${repo_name}"
|
||||
echo "name=${repo_name}" >> $GITHUB_OUTPUT
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3.12.0
|
||||
uses: docker/setup-buildx-action@v4.0.0
|
||||
- name: Login to GitHub Container Registry
|
||||
uses: docker/login-action@v3.7.0
|
||||
uses: docker/login-action@v4.0.0
|
||||
with:
|
||||
registry: ${{ env.REGISTRY }}
|
||||
username: ${{ github.actor }}
|
||||
@@ -179,22 +179,22 @@ jobs:
|
||||
echo "Downloaded digests:"
|
||||
ls -la /tmp/digests/
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3.12.0
|
||||
uses: docker/setup-buildx-action@v4.0.0
|
||||
- name: Login to GitHub Container Registry
|
||||
uses: docker/login-action@v3.7.0
|
||||
uses: docker/login-action@v4.0.0
|
||||
with:
|
||||
registry: ${{ env.REGISTRY }}
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
- name: Login to Docker Hub
|
||||
if: needs.build-arch.outputs.push-external == 'true'
|
||||
uses: docker/login-action@v3.7.0
|
||||
uses: docker/login-action@v4.0.0
|
||||
with:
|
||||
username: ${{ secrets.DOCKERHUB_USERNAME }}
|
||||
password: ${{ secrets.DOCKERHUB_TOKEN }}
|
||||
- name: Login to Quay.io
|
||||
if: needs.build-arch.outputs.push-external == 'true'
|
||||
uses: docker/login-action@v3.7.0
|
||||
uses: docker/login-action@v4.0.0
|
||||
with:
|
||||
registry: quay.io
|
||||
username: ${{ secrets.QUAY_USERNAME }}
|
||||
|
||||
10
.github/workflows/ci-frontend.yml
vendored
10
.github/workflows/ci-frontend.yml
vendored
@@ -67,7 +67,7 @@ jobs:
|
||||
with:
|
||||
version: 10
|
||||
- name: Use Node.js 24
|
||||
uses: actions/setup-node@v6.2.0
|
||||
uses: actions/setup-node@v6.3.0
|
||||
with:
|
||||
node-version: 24.x
|
||||
cache: 'pnpm'
|
||||
@@ -95,7 +95,7 @@ jobs:
|
||||
with:
|
||||
version: 10
|
||||
- name: Use Node.js 24
|
||||
uses: actions/setup-node@v6.2.0
|
||||
uses: actions/setup-node@v6.3.0
|
||||
with:
|
||||
node-version: 24.x
|
||||
cache: 'pnpm'
|
||||
@@ -130,7 +130,7 @@ jobs:
|
||||
with:
|
||||
version: 10
|
||||
- name: Use Node.js 24
|
||||
uses: actions/setup-node@v6.2.0
|
||||
uses: actions/setup-node@v6.3.0
|
||||
with:
|
||||
node-version: 24.x
|
||||
cache: 'pnpm'
|
||||
@@ -181,7 +181,7 @@ jobs:
|
||||
with:
|
||||
version: 10
|
||||
- name: Use Node.js 24
|
||||
uses: actions/setup-node@v6.2.0
|
||||
uses: actions/setup-node@v6.3.0
|
||||
with:
|
||||
node-version: 24.x
|
||||
cache: 'pnpm'
|
||||
@@ -214,7 +214,7 @@ jobs:
|
||||
with:
|
||||
version: 10
|
||||
- name: Use Node.js 24
|
||||
uses: actions/setup-node@v6.2.0
|
||||
uses: actions/setup-node@v6.3.0
|
||||
with:
|
||||
node-version: 24.x
|
||||
cache: 'pnpm'
|
||||
|
||||
2
.github/workflows/ci-release.yml
vendored
2
.github/workflows/ci-release.yml
vendored
@@ -35,7 +35,7 @@ jobs:
|
||||
with:
|
||||
version: 10
|
||||
- name: Use Node.js 24
|
||||
uses: actions/setup-node@v6.2.0
|
||||
uses: actions/setup-node@v6.3.0
|
||||
with:
|
||||
node-version: 24.x
|
||||
cache: 'pnpm'
|
||||
|
||||
2
.github/workflows/translate-strings.yml
vendored
2
.github/workflows/translate-strings.yml
vendored
@@ -40,7 +40,7 @@ jobs:
|
||||
with:
|
||||
version: 10
|
||||
- name: Use Node.js 24
|
||||
uses: actions/setup-node@v6.2.0
|
||||
uses: actions/setup-node@v6.3.0
|
||||
with:
|
||||
node-version: 24.x
|
||||
cache: 'pnpm'
|
||||
|
||||
@@ -29,7 +29,7 @@ repos:
|
||||
- id: check-case-conflict
|
||||
- id: detect-private-key
|
||||
- repo: https://github.com/codespell-project/codespell
|
||||
rev: v2.4.1
|
||||
rev: v2.4.2
|
||||
hooks:
|
||||
- id: codespell
|
||||
additional_dependencies: [tomli]
|
||||
@@ -46,8 +46,8 @@ repos:
|
||||
- ts
|
||||
- markdown
|
||||
additional_dependencies:
|
||||
- prettier@3.3.3
|
||||
- 'prettier-plugin-organize-imports@4.1.0'
|
||||
- prettier@3.8.1
|
||||
- 'prettier-plugin-organize-imports@4.3.0'
|
||||
# Python hooks
|
||||
- repo: https://github.com/astral-sh/ruff-pre-commit
|
||||
rev: v0.15.5
|
||||
@@ -65,7 +65,7 @@ repos:
|
||||
- id: hadolint
|
||||
# Shell script hooks
|
||||
- repo: https://github.com/lovesegfault/beautysh
|
||||
rev: v6.4.2
|
||||
rev: v6.4.3
|
||||
hooks:
|
||||
- id: beautysh
|
||||
types: [file]
|
||||
|
||||
@@ -5,14 +5,6 @@ const config = {
|
||||
singleQuote: true,
|
||||
// https://prettier.io/docs/en/options.html#trailing-commas
|
||||
trailingComma: 'es5',
|
||||
overrides: [
|
||||
{
|
||||
files: ['docs/*.md'],
|
||||
options: {
|
||||
tabWidth: 4,
|
||||
},
|
||||
},
|
||||
],
|
||||
plugins: [require('prettier-plugin-organize-imports')],
|
||||
}
|
||||
|
||||
|
||||
@@ -56,6 +56,7 @@ services:
|
||||
environment:
|
||||
PAPERLESS_REDIS: redis://broker:6379
|
||||
PAPERLESS_DBHOST: db
|
||||
PAPERLESS_DBENGINE: postgres
|
||||
env_file:
|
||||
- stack.env
|
||||
volumes:
|
||||
|
||||
@@ -62,6 +62,7 @@ services:
|
||||
environment:
|
||||
PAPERLESS_REDIS: redis://broker:6379
|
||||
PAPERLESS_DBHOST: db
|
||||
PAPERLESS_DBENGINE: postgresql
|
||||
PAPERLESS_TIKA_ENABLED: 1
|
||||
PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
|
||||
PAPERLESS_TIKA_ENDPOINT: http://tika:9998
|
||||
|
||||
@@ -56,6 +56,7 @@ services:
|
||||
environment:
|
||||
PAPERLESS_REDIS: redis://broker:6379
|
||||
PAPERLESS_DBHOST: db
|
||||
PAPERLESS_DBENGINE: postgresql
|
||||
volumes:
|
||||
data:
|
||||
media:
|
||||
|
||||
@@ -51,6 +51,7 @@ services:
|
||||
env_file: docker-compose.env
|
||||
environment:
|
||||
PAPERLESS_REDIS: redis://broker:6379
|
||||
PAPERLESS_DBENGINE: sqlite
|
||||
PAPERLESS_TIKA_ENABLED: 1
|
||||
PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
|
||||
PAPERLESS_TIKA_ENDPOINT: http://tika:9998
|
||||
|
||||
@@ -42,6 +42,7 @@ services:
|
||||
env_file: docker-compose.env
|
||||
environment:
|
||||
PAPERLESS_REDIS: redis://broker:6379
|
||||
PAPERLESS_DBENGINE: sqlite
|
||||
volumes:
|
||||
data:
|
||||
media:
|
||||
|
||||
@@ -10,8 +10,10 @@ cd "${PAPERLESS_SRC_DIR}"
|
||||
|
||||
# The whole migrate, with flock, needs to run as the right user
|
||||
if [[ -n "${USER_IS_NON_ROOT}" ]]; then
|
||||
python3 manage.py check --tag compatibility paperless || exit 1
|
||||
exec s6-setlock -n "${data_dir}/migration_lock" python3 manage.py migrate --skip-checks --no-input
|
||||
else
|
||||
s6-setuidgid paperless python3 manage.py check --tag compatibility paperless || exit 1
|
||||
exec s6-setuidgid paperless \
|
||||
s6-setlock -n "${data_dir}/migration_lock" \
|
||||
python3 manage.py migrate --skip-checks --no-input
|
||||
|
||||
@@ -10,16 +10,16 @@ consuming documents at that time.
|
||||
|
||||
Options available to any installation of paperless:
|
||||
|
||||
- Use the [document exporter](#exporter). The document exporter exports all your documents,
|
||||
thumbnails, metadata, and database contents to a specific folder. You may import your
|
||||
documents and settings into a fresh instance of paperless again or store your
|
||||
documents in another DMS with this export.
|
||||
- Use the [document exporter](#exporter). The document exporter exports all your documents,
|
||||
thumbnails, metadata, and database contents to a specific folder. You may import your
|
||||
documents and settings into a fresh instance of paperless again or store your
|
||||
documents in another DMS with this export.
|
||||
|
||||
The document exporter is also able to update an already existing
|
||||
export. Therefore, incremental backups with `rsync` are entirely
|
||||
possible.
|
||||
The document exporter is also able to update an already existing
|
||||
export. Therefore, incremental backups with `rsync` are entirely
|
||||
possible.
|
||||
|
||||
The exporter does not include API tokens and they will need to be re-generated after importing.
|
||||
The exporter does not include API tokens and they will need to be re-generated after importing.
|
||||
|
||||
!!! caution
|
||||
|
||||
@@ -29,28 +29,27 @@ Options available to any installation of paperless:
|
||||
|
||||
Options available to docker installations:
|
||||
|
||||
- Backup the docker volumes. These usually reside within
|
||||
`/var/lib/docker/volumes` on the host and you need to be root in
|
||||
order to access them.
|
||||
- Backup the docker volumes. These usually reside within
|
||||
`/var/lib/docker/volumes` on the host and you need to be root in
|
||||
order to access them.
|
||||
|
||||
Paperless uses 4 volumes:
|
||||
|
||||
- `paperless_media`: This is where your documents are stored.
|
||||
- `paperless_data`: This is where auxiliary data is stored. This
|
||||
folder also contains the SQLite database, if you use it.
|
||||
- `paperless_pgdata`: Exists only if you use PostgreSQL and
|
||||
contains the database.
|
||||
- `paperless_dbdata`: Exists only if you use MariaDB and contains
|
||||
the database.
|
||||
Paperless uses 4 volumes:
|
||||
- `paperless_media`: This is where your documents are stored.
|
||||
- `paperless_data`: This is where auxiliary data is stored. This
|
||||
folder also contains the SQLite database, if you use it.
|
||||
- `paperless_pgdata`: Exists only if you use PostgreSQL and
|
||||
contains the database.
|
||||
- `paperless_dbdata`: Exists only if you use MariaDB and contains
|
||||
the database.
|
||||
|
||||
Options available to bare-metal and non-docker installations:
|
||||
|
||||
- Backup the entire paperless folder. This ensures that if your
|
||||
paperless instance crashes at some point or your disk fails, you can
|
||||
simply copy the folder back into place and it works.
|
||||
- Backup the entire paperless folder. This ensures that if your
|
||||
paperless instance crashes at some point or your disk fails, you can
|
||||
simply copy the folder back into place and it works.
|
||||
|
||||
When using PostgreSQL or MariaDB, you'll also have to backup the
|
||||
database.
|
||||
When using PostgreSQL or MariaDB, you'll also have to backup the
|
||||
database.
|
||||
|
||||
### Restoring {#migrating-restoring}
|
||||
|
||||
@@ -509,19 +508,19 @@ collection for issues.
|
||||
|
||||
The issues detected by the sanity checker are as follows:
|
||||
|
||||
- Missing original files.
|
||||
- Missing archive files.
|
||||
- Inaccessible original files due to improper permissions.
|
||||
- Inaccessible archive files due to improper permissions.
|
||||
- Corrupted original documents by comparing their checksum against
|
||||
what is stored in the database.
|
||||
- Corrupted archive documents by comparing their checksum against what
|
||||
is stored in the database.
|
||||
- Missing thumbnails.
|
||||
- Inaccessible thumbnails due to improper permissions.
|
||||
- Documents without any content (warning).
|
||||
- Orphaned files in the media directory (warning). These are files
|
||||
that are not referenced by any document in paperless.
|
||||
- Missing original files.
|
||||
- Missing archive files.
|
||||
- Inaccessible original files due to improper permissions.
|
||||
- Inaccessible archive files due to improper permissions.
|
||||
- Corrupted original documents by comparing their checksum against
|
||||
what is stored in the database.
|
||||
- Corrupted archive documents by comparing their checksum against what
|
||||
is stored in the database.
|
||||
- Missing thumbnails.
|
||||
- Inaccessible thumbnails due to improper permissions.
|
||||
- Documents without any content (warning).
|
||||
- Orphaned files in the media directory (warning). These are files
|
||||
that are not referenced by any document in paperless.
|
||||
|
||||
```
|
||||
document_sanity_checker
|
||||
|
||||
@@ -25,20 +25,20 @@ documents.
|
||||
|
||||
The following algorithms are available:
|
||||
|
||||
- **None:** No matching will be performed.
|
||||
- **Any:** Looks for any occurrence of any word provided in match in
|
||||
the PDF. If you define the match as `Bank1 Bank2`, it will match
|
||||
documents containing either of these terms.
|
||||
- **All:** Requires that every word provided appears in the PDF,
|
||||
albeit not in the order provided.
|
||||
- **Exact:** Matches only if the match appears exactly as provided
|
||||
(i.e. preserve ordering) in the PDF.
|
||||
- **Regular expression:** Parses the match as a regular expression and
|
||||
tries to find a match within the document.
|
||||
- **Fuzzy match:** Uses a partial matching based on locating the tag text
|
||||
inside the document, using a [partial ratio](https://rapidfuzz.github.io/RapidFuzz/Usage/fuzz.html#partial-ratio)
|
||||
- **Auto:** Tries to automatically match new documents. This does not
|
||||
require you to set a match. See the [notes below](#automatic-matching).
|
||||
- **None:** No matching will be performed.
|
||||
- **Any:** Looks for any occurrence of any word provided in match in
|
||||
the PDF. If you define the match as `Bank1 Bank2`, it will match
|
||||
documents containing either of these terms.
|
||||
- **All:** Requires that every word provided appears in the PDF,
|
||||
albeit not in the order provided.
|
||||
- **Exact:** Matches only if the match appears exactly as provided
|
||||
(i.e. preserve ordering) in the PDF.
|
||||
- **Regular expression:** Parses the match as a regular expression and
|
||||
tries to find a match within the document.
|
||||
- **Fuzzy match:** Uses a partial matching based on locating the tag text
|
||||
inside the document, using a [partial ratio](https://rapidfuzz.github.io/RapidFuzz/Usage/fuzz.html#partial-ratio)
|
||||
- **Auto:** Tries to automatically match new documents. This does not
|
||||
require you to set a match. See the [notes below](#automatic-matching).
|
||||
|
||||
When using the _any_ or _all_ matching algorithms, you can search for
|
||||
terms that consist of multiple words by enclosing them in double quotes.
|
||||
@@ -69,33 +69,33 @@ Paperless tries to hide much of the involved complexity with this
|
||||
approach. However, there are a couple caveats you need to keep in mind
|
||||
when using this feature:
|
||||
|
||||
- Changes to your documents are not immediately reflected by the
|
||||
matching algorithm. The neural network needs to be _trained_ on your
|
||||
documents after changes. Paperless periodically (default: once each
|
||||
hour) checks for changes and does this automatically for you.
|
||||
- The Auto matching algorithm only takes documents into account which
|
||||
are NOT placed in your inbox (i.e. have any inbox tags assigned to
|
||||
them). This ensures that the neural network only learns from
|
||||
documents which you have correctly tagged before.
|
||||
- The matching algorithm can only work if there is a correlation
|
||||
between the tag, correspondent, document type, or storage path and
|
||||
the document itself. Your bank statements usually contain your bank
|
||||
account number and the name of the bank, so this works reasonably
|
||||
well, However, tags such as "TODO" cannot be automatically
|
||||
assigned.
|
||||
- The matching algorithm needs a reasonable number of documents to
|
||||
identify when to assign tags, correspondents, storage paths, and
|
||||
types. If one out of a thousand documents has the correspondent
|
||||
"Very obscure web shop I bought something five years ago", it will
|
||||
probably not assign this correspondent automatically if you buy
|
||||
something from them again. The more documents, the better.
|
||||
- Paperless also needs a reasonable amount of negative examples to
|
||||
decide when not to assign a certain tag, correspondent, document
|
||||
type, or storage path. This will usually be the case as you start
|
||||
filling up paperless with documents. Example: If all your documents
|
||||
are either from "Webshop" or "Bank", paperless will assign one
|
||||
of these correspondents to ANY new document, if both are set to
|
||||
automatic matching.
|
||||
- Changes to your documents are not immediately reflected by the
|
||||
matching algorithm. The neural network needs to be _trained_ on your
|
||||
documents after changes. Paperless periodically (default: once each
|
||||
hour) checks for changes and does this automatically for you.
|
||||
- The Auto matching algorithm only takes documents into account which
|
||||
are NOT placed in your inbox (i.e. have any inbox tags assigned to
|
||||
them). This ensures that the neural network only learns from
|
||||
documents which you have correctly tagged before.
|
||||
- The matching algorithm can only work if there is a correlation
|
||||
between the tag, correspondent, document type, or storage path and
|
||||
the document itself. Your bank statements usually contain your bank
|
||||
account number and the name of the bank, so this works reasonably
|
||||
well, However, tags such as "TODO" cannot be automatically
|
||||
assigned.
|
||||
- The matching algorithm needs a reasonable number of documents to
|
||||
identify when to assign tags, correspondents, storage paths, and
|
||||
types. If one out of a thousand documents has the correspondent
|
||||
"Very obscure web shop I bought something five years ago", it will
|
||||
probably not assign this correspondent automatically if you buy
|
||||
something from them again. The more documents, the better.
|
||||
- Paperless also needs a reasonable amount of negative examples to
|
||||
decide when not to assign a certain tag, correspondent, document
|
||||
type, or storage path. This will usually be the case as you start
|
||||
filling up paperless with documents. Example: If all your documents
|
||||
are either from "Webshop" or "Bank", paperless will assign one
|
||||
of these correspondents to ANY new document, if both are set to
|
||||
automatic matching.
|
||||
|
||||
## Hooking into the consumption process {#consume-hooks}
|
||||
|
||||
@@ -243,12 +243,12 @@ webserver:
|
||||
|
||||
Troubleshooting:
|
||||
|
||||
- Monitor the Docker Compose log
|
||||
`cd ~/paperless-ngx; docker compose logs -f`
|
||||
- Check your script's permission e.g. in case of permission error
|
||||
`sudo chmod 755 post-consumption-example.sh`
|
||||
- Pipe your scripts's output to a log file e.g.
|
||||
`echo "${DOCUMENT_ID}" | tee --append /usr/src/paperless/scripts/post-consumption-example.log`
|
||||
- Monitor the Docker Compose log
|
||||
`cd ~/paperless-ngx; docker compose logs -f`
|
||||
- Check your script's permission e.g. in case of permission error
|
||||
`sudo chmod 755 post-consumption-example.sh`
|
||||
- Pipe your scripts's output to a log file e.g.
|
||||
`echo "${DOCUMENT_ID}" | tee --append /usr/src/paperless/scripts/post-consumption-example.log`
|
||||
|
||||
## File name handling {#file-name-handling}
|
||||
|
||||
@@ -307,35 +307,35 @@ will create a directory structure as follows:
|
||||
|
||||
Paperless provides the following variables for use within filenames:
|
||||
|
||||
- `{{ asn }}`: The archive serial number of the document, or "none".
|
||||
- `{{ correspondent }}`: The name of the correspondent, or "none".
|
||||
- `{{ document_type }}`: The name of the document type, or "none".
|
||||
- `{{ tag_list }}`: A comma separated list of all tags assigned to the
|
||||
document.
|
||||
- `{{ title }}`: The title of the document.
|
||||
- `{{ created }}`: The full date (ISO 8601 format, e.g. `2024-03-14`) the document was created.
|
||||
- `{{ created_year }}`: Year created only, formatted as the year with
|
||||
century.
|
||||
- `{{ created_year_short }}`: Year created only, formatted as the year
|
||||
without century, zero padded.
|
||||
- `{{ created_month }}`: Month created only (number 01-12).
|
||||
- `{{ created_month_name }}`: Month created name, as per locale
|
||||
- `{{ created_month_name_short }}`: Month created abbreviated name, as per
|
||||
locale
|
||||
- `{{ created_day }}`: Day created only (number 01-31).
|
||||
- `{{ added }}`: The full date (ISO format) the document was added to
|
||||
paperless.
|
||||
- `{{ added_year }}`: Year added only.
|
||||
- `{{ added_year_short }}`: Year added only, formatted as the year without
|
||||
century, zero padded.
|
||||
- `{{ added_month }}`: Month added only (number 01-12).
|
||||
- `{{ added_month_name }}`: Month added name, as per locale
|
||||
- `{{ added_month_name_short }}`: Month added abbreviated name, as per
|
||||
locale
|
||||
- `{{ added_day }}`: Day added only (number 01-31).
|
||||
- `{{ owner_username }}`: Username of document owner, if any, or "none"
|
||||
- `{{ original_name }}`: Document original filename, minus the extension, if any, or "none"
|
||||
- `{{ doc_pk }}`: The paperless identifier (primary key) for the document.
|
||||
- `{{ asn }}`: The archive serial number of the document, or "none".
|
||||
- `{{ correspondent }}`: The name of the correspondent, or "none".
|
||||
- `{{ document_type }}`: The name of the document type, or "none".
|
||||
- `{{ tag_list }}`: A comma separated list of all tags assigned to the
|
||||
document.
|
||||
- `{{ title }}`: The title of the document.
|
||||
- `{{ created }}`: The full date (ISO 8601 format, e.g. `2024-03-14`) the document was created.
|
||||
- `{{ created_year }}`: Year created only, formatted as the year with
|
||||
century.
|
||||
- `{{ created_year_short }}`: Year created only, formatted as the year
|
||||
without century, zero padded.
|
||||
- `{{ created_month }}`: Month created only (number 01-12).
|
||||
- `{{ created_month_name }}`: Month created name, as per locale
|
||||
- `{{ created_month_name_short }}`: Month created abbreviated name, as per
|
||||
locale
|
||||
- `{{ created_day }}`: Day created only (number 01-31).
|
||||
- `{{ added }}`: The full date (ISO format) the document was added to
|
||||
paperless.
|
||||
- `{{ added_year }}`: Year added only.
|
||||
- `{{ added_year_short }}`: Year added only, formatted as the year without
|
||||
century, zero padded.
|
||||
- `{{ added_month }}`: Month added only (number 01-12).
|
||||
- `{{ added_month_name }}`: Month added name, as per locale
|
||||
- `{{ added_month_name_short }}`: Month added abbreviated name, as per
|
||||
locale
|
||||
- `{{ added_day }}`: Day added only (number 01-31).
|
||||
- `{{ owner_username }}`: Username of document owner, if any, or "none"
|
||||
- `{{ original_name }}`: Document original filename, minus the extension, if any, or "none"
|
||||
- `{{ doc_pk }}`: The paperless identifier (primary key) for the document.
|
||||
|
||||
!!! warning
|
||||
|
||||
@@ -388,10 +388,10 @@ before empty placeholders are removed as well, empty directories are omitted.
|
||||
When a single storage layout is not sufficient for your use case, storage paths allow for more complex
|
||||
structure to set precisely where each document is stored in the file system.
|
||||
|
||||
- Each storage path is a [`PAPERLESS_FILENAME_FORMAT`](configuration.md#PAPERLESS_FILENAME_FORMAT) and
|
||||
follows the rules described above
|
||||
- Each document is assigned a storage path using the matching algorithms described above, but can be
|
||||
overwritten at any time
|
||||
- Each storage path is a [`PAPERLESS_FILENAME_FORMAT`](configuration.md#PAPERLESS_FILENAME_FORMAT) and
|
||||
follows the rules described above
|
||||
- Each document is assigned a storage path using the matching algorithms described above, but can be
|
||||
overwritten at any time
|
||||
|
||||
For example, you could define the following two storage paths:
|
||||
|
||||
@@ -457,13 +457,13 @@ The `get_cf_value` filter retrieves a value from custom field data with optional
|
||||
|
||||
###### Parameters
|
||||
|
||||
- `custom_fields`: This _must_ be the provided custom field data
|
||||
- `name` (str): Name of the custom field to retrieve
|
||||
- `default` (str, optional): Default value to return if field is not found or has no value
|
||||
- `custom_fields`: This _must_ be the provided custom field data
|
||||
- `name` (str): Name of the custom field to retrieve
|
||||
- `default` (str, optional): Default value to return if field is not found or has no value
|
||||
|
||||
###### Returns
|
||||
|
||||
- `str | None`: The field value, default value, or `None` if neither exists
|
||||
- `str | None`: The field value, default value, or `None` if neither exists
|
||||
|
||||
###### Examples
|
||||
|
||||
@@ -487,12 +487,12 @@ The `datetime` filter formats a datetime string or datetime object using Python'
|
||||
|
||||
###### Parameters
|
||||
|
||||
- `value` (str | datetime): Date/time value to format (strings will be parsed automatically)
|
||||
- `format` (str): Python strftime format string
|
||||
- `value` (str | datetime): Date/time value to format (strings will be parsed automatically)
|
||||
- `format` (str): Python strftime format string
|
||||
|
||||
###### Returns
|
||||
|
||||
- `str`: Formatted datetime string
|
||||
- `str`: Formatted datetime string
|
||||
|
||||
###### Examples
|
||||
|
||||
@@ -525,13 +525,13 @@ An ISO string can also be provided to control the output format.
|
||||
|
||||
###### Parameters
|
||||
|
||||
- `value` (date | datetime | str): Date, datetime object or ISO string to format (datetime should be timezone-aware)
|
||||
- `format` (str): Format type - either a Babel preset ('short', 'medium', 'long', 'full') or custom pattern
|
||||
- `locale` (str): Locale code for localization (e.g., 'en_US', 'fr_FR', 'de_DE')
|
||||
- `value` (date | datetime | str): Date, datetime object or ISO string to format (datetime should be timezone-aware)
|
||||
- `format` (str): Format type - either a Babel preset ('short', 'medium', 'long', 'full') or custom pattern
|
||||
- `locale` (str): Locale code for localization (e.g., 'en_US', 'fr_FR', 'de_DE')
|
||||
|
||||
###### Returns
|
||||
|
||||
- `str`: Localized, formatted date string
|
||||
- `str`: Localized, formatted date string
|
||||
|
||||
###### Examples
|
||||
|
||||
@@ -565,15 +565,15 @@ See the [supported format codes](https://unicode.org/reports/tr35/tr35-dates.htm
|
||||
|
||||
### Format Presets
|
||||
|
||||
- **short**: Abbreviated format (e.g., "1/15/24")
|
||||
- **medium**: Medium-length format (e.g., "Jan 15, 2024")
|
||||
- **long**: Long format with full month name (e.g., "January 15, 2024")
|
||||
- **full**: Full format including day of week (e.g., "Monday, January 15, 2024")
|
||||
- **short**: Abbreviated format (e.g., "1/15/24")
|
||||
- **medium**: Medium-length format (e.g., "Jan 15, 2024")
|
||||
- **long**: Long format with full month name (e.g., "January 15, 2024")
|
||||
- **full**: Full format including day of week (e.g., "Monday, January 15, 2024")
|
||||
|
||||
#### Additional Variables
|
||||
|
||||
- `{{ tag_name_list }}`: A list of tag names applied to the document, ordered by the tag name. Note this is a list, not a single string
|
||||
- `{{ custom_fields }}`: A mapping of custom field names to their type and value. A user can access the mapping by field name or check if a field is applied by checking its existence in the variable.
|
||||
- `{{ tag_name_list }}`: A list of tag names applied to the document, ordered by the tag name. Note this is a list, not a single string
|
||||
- `{{ custom_fields }}`: A mapping of custom field names to their type and value. A user can access the mapping by field name or check if a field is applied by checking its existence in the variable.
|
||||
|
||||
!!! tip
|
||||
|
||||
@@ -675,15 +675,15 @@ installation, you can use volumes to accomplish this:
|
||||
|
||||
```yaml
|
||||
services:
|
||||
# ...
|
||||
webserver:
|
||||
environment:
|
||||
- PAPERLESS_ENABLE_FLOWER
|
||||
ports:
|
||||
- 5555:5555 # (2)!
|
||||
# ...
|
||||
webserver:
|
||||
environment:
|
||||
- PAPERLESS_ENABLE_FLOWER
|
||||
ports:
|
||||
- 5555:5555 # (2)!
|
||||
# ...
|
||||
volumes:
|
||||
- /path/to/my/flowerconfig.py:/usr/src/paperless/src/paperless/flowerconfig.py:ro # (1)!
|
||||
volumes:
|
||||
- /path/to/my/flowerconfig.py:/usr/src/paperless/src/paperless/flowerconfig.py:ro # (1)!
|
||||
```
|
||||
|
||||
1. Note the `:ro` tag means the file will be mounted as read only.
|
||||
@@ -714,11 +714,11 @@ For example, using Docker Compose:
|
||||
|
||||
```yaml
|
||||
services:
|
||||
# ...
|
||||
webserver:
|
||||
# ...
|
||||
webserver:
|
||||
# ...
|
||||
volumes:
|
||||
- /path/to/my/scripts:/custom-cont-init.d:ro # (1)!
|
||||
volumes:
|
||||
- /path/to/my/scripts:/custom-cont-init.d:ro # (1)!
|
||||
```
|
||||
|
||||
1. Note the `:ro` tag means the folder will be mounted as read only. This is for extra security against changes
|
||||
@@ -771,16 +771,16 @@ Paperless is able to utilize barcodes for automatically performing some tasks.
|
||||
|
||||
At this time, the library utilized for detection of barcodes supports the following types:
|
||||
|
||||
- AN-13/UPC-A
|
||||
- UPC-E
|
||||
- EAN-8
|
||||
- Code 128
|
||||
- Code 93
|
||||
- Code 39
|
||||
- Codabar
|
||||
- Interleaved 2 of 5
|
||||
- QR Code
|
||||
- SQ Code
|
||||
- AN-13/UPC-A
|
||||
- UPC-E
|
||||
- EAN-8
|
||||
- Code 128
|
||||
- Code 93
|
||||
- Code 39
|
||||
- Codabar
|
||||
- Interleaved 2 of 5
|
||||
- QR Code
|
||||
- SQ Code
|
||||
|
||||
For usage in Paperless, the type of barcode does not matter, only the contents of it.
|
||||
|
||||
@@ -793,8 +793,8 @@ below.
|
||||
If document splitting is enabled, Paperless splits _after_ a separator barcode by default.
|
||||
This means:
|
||||
|
||||
- any page containing the configured separator barcode starts a new document, starting with the **next** page
|
||||
- pages containing the separator barcode are discarded
|
||||
- any page containing the configured separator barcode starts a new document, starting with the **next** page
|
||||
- pages containing the separator barcode are discarded
|
||||
|
||||
This is intended for dedicated separator sheets such as PATCH-T pages.
|
||||
|
||||
@@ -831,10 +831,10 @@ to `true`.
|
||||
When enabled, documents will be split at pages containing tag barcodes, similar to how
|
||||
ASN barcodes work. Key features:
|
||||
|
||||
- The page with the tag barcode is **retained** in the resulting document
|
||||
- **Each split document extracts its own tags** - only tags on pages within that document are assigned
|
||||
- Multiple tag barcodes can trigger multiple splits in the same document
|
||||
- Works seamlessly with ASN barcodes - each split document gets its own ASN and tags
|
||||
- The page with the tag barcode is **retained** in the resulting document
|
||||
- **Each split document extracts its own tags** - only tags on pages within that document are assigned
|
||||
- Multiple tag barcodes can trigger multiple splits in the same document
|
||||
- Works seamlessly with ASN barcodes - each split document gets its own ASN and tags
|
||||
|
||||
This is useful for batch scanning where you place tag barcode pages between different
|
||||
documents to both separate and categorize them in a single operation.
|
||||
@@ -996,9 +996,9 @@ If using docker, you'll need to add the following volume mounts to your `docker-
|
||||
|
||||
```yaml
|
||||
webserver:
|
||||
volumes:
|
||||
- /home/user/.gnupg/pubring.gpg:/usr/src/paperless/.gnupg/pubring.gpg
|
||||
- <path to gpg-agent socket>:/usr/src/paperless/.gnupg/S.gpg-agent
|
||||
volumes:
|
||||
- /home/user/.gnupg/pubring.gpg:/usr/src/paperless/.gnupg/pubring.gpg
|
||||
- <path to gpg-agent socket>:/usr/src/paperless/.gnupg/S.gpg-agent
|
||||
```
|
||||
|
||||
For a 'bare-metal' installation no further configuration is necessary. If you
|
||||
@@ -1006,9 +1006,9 @@ want to use a separate `GNUPG_HOME`, you can do so by configuring the [PAPERLESS
|
||||
|
||||
### Troubleshooting
|
||||
|
||||
- Make sure, that `gpg-agent` is running on your host machine
|
||||
- Make sure, that encryption and decryption works from inside the container using the `gpg` commands from above.
|
||||
- Check that all files in `/usr/src/paperless/.gnupg` have correct permissions
|
||||
- Make sure, that `gpg-agent` is running on your host machine
|
||||
- Make sure, that encryption and decryption works from inside the container using the `gpg` commands from above.
|
||||
- Check that all files in `/usr/src/paperless/.gnupg` have correct permissions
|
||||
|
||||
```shell
|
||||
paperless@9da1865df327:~/.gnupg$ ls -al
|
||||
|
||||
212
docs/api.md
212
docs/api.md
@@ -66,10 +66,10 @@ Full text searching is available on the `/api/documents/` endpoint. Two
|
||||
specific query parameters cause the API to return full text search
|
||||
results:
|
||||
|
||||
- `/api/documents/?query=your%20search%20query`: Search for a document
|
||||
using a full text query. For details on the syntax, see [Basic Usage - Searching](usage.md#basic-usage_searching).
|
||||
- `/api/documents/?more_like_id=1234`: Search for documents similar to
|
||||
the document with id 1234.
|
||||
- `/api/documents/?query=your%20search%20query`: Search for a document
|
||||
using a full text query. For details on the syntax, see [Basic Usage - Searching](usage.md#basic-usage_searching).
|
||||
- `/api/documents/?more_like_id=1234`: Search for documents similar to
|
||||
the document with id 1234.
|
||||
|
||||
Pagination works exactly the same as it does for normal requests on this
|
||||
endpoint.
|
||||
@@ -106,12 +106,12 @@ attribute with various information about the search results:
|
||||
}
|
||||
```
|
||||
|
||||
- `score` is an indication how well this document matches the query
|
||||
relative to the other search results.
|
||||
- `highlights` is an excerpt from the document content and highlights
|
||||
the search terms with `<span>` tags as shown above.
|
||||
- `rank` is the index of the search results. The first result will
|
||||
have rank 0.
|
||||
- `score` is an indication how well this document matches the query
|
||||
relative to the other search results.
|
||||
- `highlights` is an excerpt from the document content and highlights
|
||||
the search terms with `<span>` tags as shown above.
|
||||
- `rank` is the index of the search results. The first result will
|
||||
have rank 0.
|
||||
|
||||
### Filtering by custom fields
|
||||
|
||||
@@ -122,33 +122,33 @@ use cases:
|
||||
1. Documents with a custom field "due" (date) between Aug 1, 2024 and
|
||||
Sept 1, 2024 (inclusive):
|
||||
|
||||
`?custom_field_query=["due", "range", ["2024-08-01", "2024-09-01"]]`
|
||||
`?custom_field_query=["due", "range", ["2024-08-01", "2024-09-01"]]`
|
||||
|
||||
2. Documents with a custom field "customer" (text) that equals "bob"
|
||||
(case sensitive):
|
||||
|
||||
`?custom_field_query=["customer", "exact", "bob"]`
|
||||
`?custom_field_query=["customer", "exact", "bob"]`
|
||||
|
||||
3. Documents with a custom field "answered" (boolean) set to `true`:
|
||||
|
||||
`?custom_field_query=["answered", "exact", true]`
|
||||
`?custom_field_query=["answered", "exact", true]`
|
||||
|
||||
4. Documents with a custom field "favorite animal" (select) set to either
|
||||
"cat" or "dog":
|
||||
|
||||
`?custom_field_query=["favorite animal", "in", ["cat", "dog"]]`
|
||||
`?custom_field_query=["favorite animal", "in", ["cat", "dog"]]`
|
||||
|
||||
5. Documents with a custom field "address" (text) that is empty:
|
||||
|
||||
`?custom_field_query=["OR", [["address", "isnull", true], ["address", "exact", ""]]]`
|
||||
`?custom_field_query=["OR", [["address", "isnull", true], ["address", "exact", ""]]]`
|
||||
|
||||
6. Documents that don't have a field called "foo":
|
||||
|
||||
`?custom_field_query=["foo", "exists", false]`
|
||||
`?custom_field_query=["foo", "exists", false]`
|
||||
|
||||
7. Documents that have document links "references" to both document 3 and 7:
|
||||
|
||||
`?custom_field_query=["references", "contains", [3, 7]]`
|
||||
`?custom_field_query=["references", "contains", [3, 7]]`
|
||||
|
||||
All field types support basic operations including `exact`, `in`, `isnull`,
|
||||
and `exists`. String, URL, and monetary fields support case-insensitive
|
||||
@@ -164,8 +164,8 @@ Get auto completions for a partial search term.
|
||||
|
||||
Query parameters:
|
||||
|
||||
- `term`: The incomplete term.
|
||||
- `limit`: Amount of results. Defaults to 10.
|
||||
- `term`: The incomplete term.
|
||||
- `limit`: Amount of results. Defaults to 10.
|
||||
|
||||
Results returned by the endpoint are ordered by importance of the term
|
||||
in the document index. The first result is the term that has the highest
|
||||
@@ -189,19 +189,19 @@ from there.
|
||||
|
||||
The endpoint supports the following optional form fields:
|
||||
|
||||
- `title`: Specify a title that the consumer should use for the
|
||||
document.
|
||||
- `created`: Specify a DateTime where the document was created (e.g.
|
||||
"2016-04-19" or "2016-04-19 06:15:00+02:00").
|
||||
- `correspondent`: Specify the ID of a correspondent that the consumer
|
||||
should use for the document.
|
||||
- `document_type`: Similar to correspondent.
|
||||
- `storage_path`: Similar to correspondent.
|
||||
- `tags`: Similar to correspondent. Specify this multiple times to
|
||||
have multiple tags added to the document.
|
||||
- `archive_serial_number`: An optional archive serial number to set.
|
||||
- `custom_fields`: Either an array of custom field ids to assign (with an empty
|
||||
value) to the document or an object mapping field id -> value.
|
||||
- `title`: Specify a title that the consumer should use for the
|
||||
document.
|
||||
- `created`: Specify a DateTime where the document was created (e.g.
|
||||
"2016-04-19" or "2016-04-19 06:15:00+02:00").
|
||||
- `correspondent`: Specify the ID of a correspondent that the consumer
|
||||
should use for the document.
|
||||
- `document_type`: Similar to correspondent.
|
||||
- `storage_path`: Similar to correspondent.
|
||||
- `tags`: Similar to correspondent. Specify this multiple times to
|
||||
have multiple tags added to the document.
|
||||
- `archive_serial_number`: An optional archive serial number to set.
|
||||
- `custom_fields`: Either an array of custom field ids to assign (with an empty
|
||||
value) to the document or an object mapping field id -> value.
|
||||
|
||||
The endpoint will immediately return HTTP 200 if the document consumption
|
||||
process was started successfully, with the UUID of the consumption task
|
||||
@@ -215,16 +215,16 @@ consumption including the ID of a created document if consumption succeeded.
|
||||
|
||||
Document versions are file-level versions linked to one root document.
|
||||
|
||||
- Root document metadata (title, tags, correspondent, document type, storage path, custom fields, permissions) remains shared.
|
||||
- Version-specific file data (file, mime type, checksums, archive info, extracted text content) belongs to the selected/latest version.
|
||||
- Root document metadata (title, tags, correspondent, document type, storage path, custom fields, permissions) remains shared.
|
||||
- Version-specific file data (file, mime type, checksums, archive info, extracted text content) belongs to the selected/latest version.
|
||||
|
||||
Version-aware endpoints:
|
||||
|
||||
- `GET /api/documents/{id}/`: returns root document data; `content` resolves to latest version content by default. Use `?version={version_id}` to resolve content for a specific version.
|
||||
- `PATCH /api/documents/{id}/`: content updates target the selected version (`?version={version_id}`) or latest version by default; non-content metadata updates target the root document.
|
||||
- `GET /api/documents/{id}/download/`, `GET /api/documents/{id}/preview/`, `GET /api/documents/{id}/thumb/`, `GET /api/documents/{id}/metadata/`: accept `?version={version_id}`.
|
||||
- `POST /api/documents/{id}/update_version/`: uploads a new version using multipart form field `document` and optional `version_label`.
|
||||
- `DELETE /api/documents/{root_id}/versions/{version_id}/`: deletes a non-root version.
|
||||
- `GET /api/documents/{id}/`: returns root document data; `content` resolves to latest version content by default. Use `?version={version_id}` to resolve content for a specific version.
|
||||
- `PATCH /api/documents/{id}/`: content updates target the selected version (`?version={version_id}`) or latest version by default; non-content metadata updates target the root document.
|
||||
- `GET /api/documents/{id}/download/`, `GET /api/documents/{id}/preview/`, `GET /api/documents/{id}/thumb/`, `GET /api/documents/{id}/metadata/`: accept `?version={version_id}`.
|
||||
- `POST /api/documents/{id}/update_version/`: uploads a new version using multipart form field `document` and optional `version_label`.
|
||||
- `DELETE /api/documents/{root_id}/versions/{version_id}/`: deletes a non-root version.
|
||||
|
||||
## Permissions
|
||||
|
||||
@@ -282,34 +282,34 @@ a json payload of the format:
|
||||
|
||||
The following methods are supported:
|
||||
|
||||
- `set_correspondent`
|
||||
- Requires `parameters`: `{ "correspondent": CORRESPONDENT_ID }`
|
||||
- `set_document_type`
|
||||
- Requires `parameters`: `{ "document_type": DOCUMENT_TYPE_ID }`
|
||||
- `set_storage_path`
|
||||
- Requires `parameters`: `{ "storage_path": STORAGE_PATH_ID }`
|
||||
- `add_tag`
|
||||
- Requires `parameters`: `{ "tag": TAG_ID }`
|
||||
- `remove_tag`
|
||||
- Requires `parameters`: `{ "tag": TAG_ID }`
|
||||
- `modify_tags`
|
||||
- Requires `parameters`: `{ "add_tags": [LIST_OF_TAG_IDS] }` and `{ "remove_tags": [LIST_OF_TAG_IDS] }`
|
||||
- `delete`
|
||||
- No `parameters` required
|
||||
- `reprocess`
|
||||
- No `parameters` required
|
||||
- `set_permissions`
|
||||
- Requires `parameters`:
|
||||
- `"set_permissions": PERMISSIONS_OBJ` (see format [above](#permissions)) and / or
|
||||
- `"owner": OWNER_ID or null`
|
||||
- `"merge": true or false` (defaults to false)
|
||||
- The `merge` flag determines if the supplied permissions will overwrite all existing permissions (including
|
||||
removing them) or be merged with existing permissions.
|
||||
- `modify_custom_fields`
|
||||
- Requires `parameters`:
|
||||
- `"add_custom_fields": { CUSTOM_FIELD_ID: VALUE }`: JSON object consisting of custom field id:value pairs to add to the document, can also be a list of custom field IDs
|
||||
to add with empty values.
|
||||
- `"remove_custom_fields": [CUSTOM_FIELD_ID]`: custom field ids to remove from the document.
|
||||
- `set_correspondent`
|
||||
- Requires `parameters`: `{ "correspondent": CORRESPONDENT_ID }`
|
||||
- `set_document_type`
|
||||
- Requires `parameters`: `{ "document_type": DOCUMENT_TYPE_ID }`
|
||||
- `set_storage_path`
|
||||
- Requires `parameters`: `{ "storage_path": STORAGE_PATH_ID }`
|
||||
- `add_tag`
|
||||
- Requires `parameters`: `{ "tag": TAG_ID }`
|
||||
- `remove_tag`
|
||||
- Requires `parameters`: `{ "tag": TAG_ID }`
|
||||
- `modify_tags`
|
||||
- Requires `parameters`: `{ "add_tags": [LIST_OF_TAG_IDS] }` and `{ "remove_tags": [LIST_OF_TAG_IDS] }`
|
||||
- `delete`
|
||||
- No `parameters` required
|
||||
- `reprocess`
|
||||
- No `parameters` required
|
||||
- `set_permissions`
|
||||
- Requires `parameters`:
|
||||
- `"set_permissions": PERMISSIONS_OBJ` (see format [above](#permissions)) and / or
|
||||
- `"owner": OWNER_ID or null`
|
||||
- `"merge": true or false` (defaults to false)
|
||||
- The `merge` flag determines if the supplied permissions will overwrite all existing permissions (including
|
||||
removing them) or be merged with existing permissions.
|
||||
- `modify_custom_fields`
|
||||
- Requires `parameters`:
|
||||
- `"add_custom_fields": { CUSTOM_FIELD_ID: VALUE }`: JSON object consisting of custom field id:value pairs to add to the document, can also be a list of custom field IDs
|
||||
to add with empty values.
|
||||
- `"remove_custom_fields": [CUSTOM_FIELD_ID]`: custom field ids to remove from the document.
|
||||
|
||||
#### Document-editing operations
|
||||
|
||||
@@ -335,16 +335,16 @@ operations, using the endpoint: `/api/bulk_edit_objects/`, which requires a json
|
||||
|
||||
The REST API is versioned.
|
||||
|
||||
- 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`.
|
||||
- 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`.
|
||||
|
||||
API versions are specified by submitting an additional HTTP `Accept`
|
||||
header with every request:
|
||||
@@ -384,56 +384,56 @@ Initial API version.
|
||||
|
||||
#### Version 2
|
||||
|
||||
- Added field `Tag.color`. This read/write string field contains a hex
|
||||
color such as `#a6cee3`.
|
||||
- Added read-only field `Tag.text_color`. This field contains the text
|
||||
color to use for a specific tag, which is either black or white
|
||||
depending on the brightness of `Tag.color`.
|
||||
- Removed field `Tag.colour`.
|
||||
- Added field `Tag.color`. This read/write string field contains a hex
|
||||
color such as `#a6cee3`.
|
||||
- Added read-only field `Tag.text_color`. This field contains the text
|
||||
color to use for a specific tag, which is either black or white
|
||||
depending on the brightness of `Tag.color`.
|
||||
- Removed field `Tag.colour`.
|
||||
|
||||
#### Version 3
|
||||
|
||||
- Permissions endpoints have been added.
|
||||
- The format of the `/api/ui_settings/` has changed.
|
||||
- Permissions endpoints have been added.
|
||||
- The format of the `/api/ui_settings/` has changed.
|
||||
|
||||
#### Version 4
|
||||
|
||||
- Consumption templates were refactored to workflows and API endpoints
|
||||
changed as such.
|
||||
- Consumption templates were refactored to workflows and API endpoints
|
||||
changed as such.
|
||||
|
||||
#### Version 5
|
||||
|
||||
- Added bulk deletion methods for documents and objects.
|
||||
- Added bulk deletion methods for documents and objects.
|
||||
|
||||
#### Version 6
|
||||
|
||||
- Moved acknowledge tasks endpoint to be under `/api/tasks/acknowledge/`.
|
||||
- Moved acknowledge tasks endpoint to be under `/api/tasks/acknowledge/`.
|
||||
|
||||
#### Version 7
|
||||
|
||||
- The format of select type custom fields has changed to return the options
|
||||
as an array of objects with `id` and `label` fields as opposed to a simple
|
||||
list of strings. When creating or updating a custom field value of a
|
||||
document for a select type custom field, the value should be the `id` of
|
||||
the option whereas previously was the index of the option.
|
||||
- The format of select type custom fields has changed to return the options
|
||||
as an array of objects with `id` and `label` fields as opposed to a simple
|
||||
list of strings. When creating or updating a custom field value of a
|
||||
document for a select type custom field, the value should be the `id` of
|
||||
the option whereas previously was the index of the option.
|
||||
|
||||
#### Version 8
|
||||
|
||||
- The user field of document notes now returns a simplified user object
|
||||
rather than just the user ID.
|
||||
- The user field of document notes now returns a simplified user object
|
||||
rather than just the user ID.
|
||||
|
||||
#### Version 9
|
||||
|
||||
- The document `created` field is now a date, not a datetime. The
|
||||
`created_date` field is considered deprecated and will be removed in a
|
||||
future version.
|
||||
- The document `created` field is now a date, not a datetime. The
|
||||
`created_date` field is considered deprecated and will be removed in a
|
||||
future version.
|
||||
|
||||
#### Version 10
|
||||
|
||||
- The `show_on_dashboard` and `show_in_sidebar` fields of saved views have been
|
||||
removed. Relevant settings are now stored in the UISettings model. Compatibility is maintained
|
||||
for versions < 10 until support for API v9 is dropped.
|
||||
- Document-editing operations such as `merge`, `rotate`, and `edit_pdf` have been
|
||||
moved from the bulk edit endpoint to their own individual endpoints. Using these methods via
|
||||
the bulk edit endpoint is still supported for compatibility with versions < 10 until support
|
||||
for API v9 is dropped.
|
||||
- The `show_on_dashboard` and `show_in_sidebar` fields of saved views have been
|
||||
removed. Relevant settings are now stored in the UISettings model. Compatibility is maintained
|
||||
for versions < 10 until support for API v9 is dropped.
|
||||
- Document-editing operations such as `merge`, `rotate`, and `edit_pdf` have been
|
||||
moved from the bulk edit endpoint to their own individual endpoints. Using these methods via
|
||||
the bulk edit endpoint is still supported for compatibility with versions < 10 until support
|
||||
for API v9 is dropped.
|
||||
|
||||
9976
docs/changelog.md
9976
docs/changelog.md
File diff suppressed because it is too large
Load Diff
@@ -8,17 +8,17 @@ common [OCR](#ocr) related settings and some frontend settings. If set, these wi
|
||||
preference over the settings via environment variables. If not set, the environment setting
|
||||
or applicable default will be utilized instead.
|
||||
|
||||
- If you run paperless on docker, `paperless.conf` is not used.
|
||||
Rather, configure paperless by copying necessary options to
|
||||
`docker-compose.env`.
|
||||
- If you run paperless on docker, `paperless.conf` is not used.
|
||||
Rather, configure paperless by copying necessary options to
|
||||
`docker-compose.env`.
|
||||
|
||||
- If you are running paperless on anything else, paperless will search
|
||||
for the configuration file in these locations and use the first one
|
||||
it finds:
|
||||
- The environment variable `PAPERLESS_CONFIGURATION_PATH`
|
||||
- `/path/to/paperless/paperless.conf`
|
||||
- `/etc/paperless.conf`
|
||||
- `/usr/local/etc/paperless.conf`
|
||||
- If you are running paperless on anything else, paperless will search
|
||||
for the configuration file in these locations and use the first one
|
||||
it finds:
|
||||
- The environment variable `PAPERLESS_CONFIGURATION_PATH`
|
||||
- `/path/to/paperless/paperless.conf`
|
||||
- `/etc/paperless.conf`
|
||||
- `/usr/local/etc/paperless.conf`
|
||||
|
||||
## Required services
|
||||
|
||||
|
||||
@@ -6,23 +6,23 @@ on Paperless-ngx.
|
||||
Check out the source from GitHub. The repository is organized in the
|
||||
following way:
|
||||
|
||||
- `main` always represents the latest release and will only see
|
||||
changes when a new release is made.
|
||||
- `dev` contains the code that will be in the next release.
|
||||
- `feature-X` contains bigger changes that will be in some release, but
|
||||
not necessarily the next one.
|
||||
- `main` always represents the latest release and will only see
|
||||
changes when a new release is made.
|
||||
- `dev` contains the code that will be in the next release.
|
||||
- `feature-X` contains bigger changes that will be in some release, but
|
||||
not necessarily the next one.
|
||||
|
||||
When making functional changes to Paperless-ngx, _always_ make your changes
|
||||
on the `dev` branch.
|
||||
|
||||
Apart from that, the folder structure is as follows:
|
||||
|
||||
- `docs/` - Documentation.
|
||||
- `src-ui/` - Code of the front end.
|
||||
- `src/` - Code of the back end.
|
||||
- `scripts/` - Various scripts that help with different parts of
|
||||
development.
|
||||
- `docker/` - Files required to build the docker image.
|
||||
- `docs/` - Documentation.
|
||||
- `src-ui/` - Code of the front end.
|
||||
- `src/` - Code of the back end.
|
||||
- `scripts/` - Various scripts that help with different parts of
|
||||
development.
|
||||
- `docker/` - Files required to build the docker image.
|
||||
|
||||
## Contributing to Paperless-ngx
|
||||
|
||||
@@ -94,18 +94,17 @@ first-time setup.
|
||||
```
|
||||
|
||||
7. You can now either ...
|
||||
- install Redis or
|
||||
|
||||
- install Redis or
|
||||
- use the included `scripts/start_services.sh` to use Docker to fire
|
||||
up a Redis instance (and some other services such as Tika,
|
||||
Gotenberg and a database server) or
|
||||
|
||||
- use the included `scripts/start_services.sh` to use Docker to fire
|
||||
up a Redis instance (and some other services such as Tika,
|
||||
Gotenberg and a database server) or
|
||||
- spin up a bare Redis container
|
||||
|
||||
- spin up a bare Redis container
|
||||
|
||||
```bash
|
||||
docker run -d -p 6379:6379 --restart unless-stopped redis:latest
|
||||
```
|
||||
```bash
|
||||
docker run -d -p 6379:6379 --restart unless-stopped redis:latest
|
||||
```
|
||||
|
||||
8. Continue with either back-end or front-end development – or both :-).
|
||||
|
||||
@@ -118,9 +117,9 @@ work well for development, but you can use whatever you want.
|
||||
Configure the IDE to use the `src/`-folder as the base source folder.
|
||||
Configure the following launch configurations in your IDE:
|
||||
|
||||
- `uv run manage.py runserver`
|
||||
- `uv run manage.py document_consumer`
|
||||
- `uv run celery --app paperless worker -l DEBUG` (or any other log level)
|
||||
- `uv run manage.py runserver`
|
||||
- `uv run manage.py document_consumer`
|
||||
- `uv run celery --app paperless worker -l DEBUG` (or any other log level)
|
||||
|
||||
To start them all:
|
||||
|
||||
@@ -146,11 +145,11 @@ pnpm ng build --configuration production
|
||||
|
||||
### Testing
|
||||
|
||||
- Run `pytest` in the `src/` directory to execute all tests. This also
|
||||
generates a HTML coverage report. When running tests, `paperless.conf`
|
||||
is loaded as well. However, the tests rely on the default
|
||||
configuration. This is not ideal. But for now, make sure no settings
|
||||
except for DEBUG are overridden when testing.
|
||||
- Run `pytest` in the `src/` directory to execute all tests. This also
|
||||
generates a HTML coverage report. When running tests, `paperless.conf`
|
||||
is loaded as well. However, the tests rely on the default
|
||||
configuration. This is not ideal. But for now, make sure no settings
|
||||
except for DEBUG are overridden when testing.
|
||||
|
||||
!!! note
|
||||
|
||||
@@ -254,14 +253,14 @@ these parts have to be translated separately.
|
||||
|
||||
### Front end localization
|
||||
|
||||
- The AngularJS front end does localization according to the [Angular
|
||||
documentation](https://angular.io/guide/i18n).
|
||||
- The source language of the project is "en_US".
|
||||
- The source strings end up in the file `src-ui/messages.xlf`.
|
||||
- The translated strings need to be placed in the
|
||||
`src-ui/src/locale/` folder.
|
||||
- In order to extract added or changed strings from the source files,
|
||||
call `ng extract-i18n`.
|
||||
- The AngularJS front end does localization according to the [Angular
|
||||
documentation](https://angular.io/guide/i18n).
|
||||
- The source language of the project is "en_US".
|
||||
- The source strings end up in the file `src-ui/messages.xlf`.
|
||||
- The translated strings need to be placed in the
|
||||
`src-ui/src/locale/` folder.
|
||||
- In order to extract added or changed strings from the source files,
|
||||
call `ng extract-i18n`.
|
||||
|
||||
Adding new languages requires adding the translated files in the
|
||||
`src-ui/src/locale/` folder and adjusting a couple files.
|
||||
@@ -307,18 +306,18 @@ A majority of the strings that appear in the back end appear only when
|
||||
the admin is used. However, some of these are still shown on the front
|
||||
end (such as error messages).
|
||||
|
||||
- The django application does localization according to the [Django
|
||||
documentation](https://docs.djangoproject.com/en/3.1/topics/i18n/translation/).
|
||||
- The source language of the project is "en_US".
|
||||
- Localization files end up in the folder `src/locale/`.
|
||||
- In order to extract strings from the application, call
|
||||
`uv run manage.py makemessages -l en_US`. This is important after
|
||||
making changes to translatable strings.
|
||||
- The message files need to be compiled for them to show up in the
|
||||
application. Call `uv run manage.py compilemessages` to do this.
|
||||
The generated files don't get committed into git, since these are
|
||||
derived artifacts. The build pipeline takes care of executing this
|
||||
command.
|
||||
- The django application does localization according to the [Django
|
||||
documentation](https://docs.djangoproject.com/en/3.1/topics/i18n/translation/).
|
||||
- The source language of the project is "en_US".
|
||||
- Localization files end up in the folder `src/locale/`.
|
||||
- In order to extract strings from the application, call
|
||||
`uv run manage.py makemessages -l en_US`. This is important after
|
||||
making changes to translatable strings.
|
||||
- The message files need to be compiled for them to show up in the
|
||||
application. Call `uv run manage.py compilemessages` to do this.
|
||||
The generated files don't get committed into git, since these are
|
||||
derived artifacts. The build pipeline takes care of executing this
|
||||
command.
|
||||
|
||||
Adding new languages requires adding the translated files in the
|
||||
`src/locale/`-folder and adjusting the file
|
||||
@@ -381,10 +380,10 @@ base code.
|
||||
Paperless-ngx uses parsers to add documents. A parser is
|
||||
responsible for:
|
||||
|
||||
- Retrieving the content from the original
|
||||
- Creating a thumbnail
|
||||
- _optional:_ Retrieving a created date from the original
|
||||
- _optional:_ Creating an archived document from the original
|
||||
- Retrieving the content from the original
|
||||
- Creating a thumbnail
|
||||
- _optional:_ Retrieving a created date from the original
|
||||
- _optional:_ Creating an archived document from the original
|
||||
|
||||
Custom parsers can be added to Paperless-ngx to support more file types. In
|
||||
order to do that, you need to write the parser itself and announce its
|
||||
@@ -442,17 +441,17 @@ def myparser_consumer_declaration(sender, **kwargs):
|
||||
}
|
||||
```
|
||||
|
||||
- `parser` is a reference to a class that extends `DocumentParser`.
|
||||
- `weight` is used whenever two or more parsers are able to parse a
|
||||
file: The parser with the higher weight wins. This can be used to
|
||||
override the parsers provided by Paperless-ngx.
|
||||
- `mime_types` is a dictionary. The keys are the mime types your
|
||||
parser supports and the value is the default file extension that
|
||||
Paperless-ngx should use when storing files and serving them for
|
||||
download. We could guess that from the file extensions, but some
|
||||
mime types have many extensions associated with them and the Python
|
||||
methods responsible for guessing the extension do not always return
|
||||
the same value.
|
||||
- `parser` is a reference to a class that extends `DocumentParser`.
|
||||
- `weight` is used whenever two or more parsers are able to parse a
|
||||
file: The parser with the higher weight wins. This can be used to
|
||||
override the parsers provided by Paperless-ngx.
|
||||
- `mime_types` is a dictionary. The keys are the mime types your
|
||||
parser supports and the value is the default file extension that
|
||||
Paperless-ngx should use when storing files and serving them for
|
||||
download. We could guess that from the file extensions, but some
|
||||
mime types have many extensions associated with them and the Python
|
||||
methods responsible for guessing the extension do not always return
|
||||
the same value.
|
||||
|
||||
## Using Visual Studio Code devcontainer
|
||||
|
||||
@@ -471,9 +470,8 @@ To get started:
|
||||
2. VS Code will prompt you with "Reopen in container". Do so and wait for the environment to start.
|
||||
|
||||
3. In case your host operating system is Windows:
|
||||
|
||||
- The Source Control view in Visual Studio Code might show: "The detected Git repository is potentially unsafe as the folder is owned by someone other than the current user." Use "Manage Unsafe Repositories" to fix this.
|
||||
- Git might have detecteded modifications for all files, because Windows is using CRLF line endings. Run `git checkout .` in the containers terminal to fix this issue.
|
||||
- The Source Control view in Visual Studio Code might show: "The detected Git repository is potentially unsafe as the folder is owned by someone other than the current user." Use "Manage Unsafe Repositories" to fix this.
|
||||
- Git might have detecteded modifications for all files, because Windows is using CRLF line endings. Run `git checkout .` in the containers terminal to fix this issue.
|
||||
|
||||
4. Initialize the project by running the task **Project Setup: Run all Init Tasks**. This
|
||||
will initialize the database tables and create a superuser. Then you can compile the front end
|
||||
@@ -538,12 +536,12 @@ class MyDateParserPlugin(DateParserPluginBase):
|
||||
|
||||
Your parser instance is initialized with a `DateParserConfig` object accessible via `self.config`. This provides:
|
||||
|
||||
- `languages: list[str]` - List of language codes for date parsing
|
||||
- `timezone_str: str` - Timezone string for date localization
|
||||
- `ignore_dates: set[datetime.date]` - Dates that should be filtered out
|
||||
- `reference_time: datetime.datetime` - Current time for filtering future dates
|
||||
- `filename_date_order: str | None` - Date order preference for filenames (e.g., "DMY", "MDY")
|
||||
- `content_date_order: str` - Date order preference for content
|
||||
- `languages: list[str]` - List of language codes for date parsing
|
||||
- `timezone_str: str` - Timezone string for date localization
|
||||
- `ignore_dates: set[datetime.date]` - Dates that should be filtered out
|
||||
- `reference_time: datetime.datetime` - Current time for filtering future dates
|
||||
- `filename_date_order: str | None` - Date order preference for filenames (e.g., "DMY", "MDY")
|
||||
- `content_date_order: str` - Date order preference for content
|
||||
|
||||
The base class provides two helper methods you can use:
|
||||
|
||||
|
||||
34
docs/faq.md
34
docs/faq.md
@@ -44,28 +44,28 @@ system. On Linux, chances are high that this location is
|
||||
You can always drag those files out of that folder to use them
|
||||
elsewhere. Here are a couple notes about that.
|
||||
|
||||
- Paperless-ngx never modifies your original documents. It keeps
|
||||
checksums of all documents and uses a scheduled sanity checker to
|
||||
check that they remain the same.
|
||||
- By default, paperless uses the internal ID of each document as its
|
||||
filename. This might not be very convenient for export. However, you
|
||||
can adjust the way files are stored in paperless by
|
||||
[configuring the filename format](advanced_usage.md#file-name-handling).
|
||||
- [The exporter](administration.md#exporter) is
|
||||
another easy way to get your files out of paperless with reasonable
|
||||
file names.
|
||||
- Paperless-ngx never modifies your original documents. It keeps
|
||||
checksums of all documents and uses a scheduled sanity checker to
|
||||
check that they remain the same.
|
||||
- By default, paperless uses the internal ID of each document as its
|
||||
filename. This might not be very convenient for export. However, you
|
||||
can adjust the way files are stored in paperless by
|
||||
[configuring the filename format](advanced_usage.md#file-name-handling).
|
||||
- [The exporter](administration.md#exporter) is
|
||||
another easy way to get your files out of paperless with reasonable
|
||||
file names.
|
||||
|
||||
## _What file types does paperless-ngx support?_
|
||||
|
||||
**A:** Currently, the following files are supported:
|
||||
|
||||
- PDF documents, PNG images, JPEG images, TIFF images, GIF images and
|
||||
WebP images are processed with OCR and converted into PDF documents.
|
||||
- Plain text documents are supported as well and are added verbatim to
|
||||
paperless.
|
||||
- With the optional Tika integration enabled (see [Tika configuration](https://docs.paperless-ngx.com/configuration#tika)),
|
||||
Paperless also supports various Office documents (.docx, .doc, odt,
|
||||
.ppt, .pptx, .odp, .xls, .xlsx, .ods).
|
||||
- PDF documents, PNG images, JPEG images, TIFF images, GIF images and
|
||||
WebP images are processed with OCR and converted into PDF documents.
|
||||
- Plain text documents are supported as well and are added verbatim to
|
||||
paperless.
|
||||
- With the optional Tika integration enabled (see [Tika configuration](https://docs.paperless-ngx.com/configuration#tika)),
|
||||
Paperless also supports various Office documents (.docx, .doc, odt,
|
||||
.ppt, .pptx, .odp, .xls, .xlsx, .ods).
|
||||
|
||||
Paperless-ngx determines the type of a file by inspecting its content
|
||||
rather than its file extensions. However, files processed via the
|
||||
|
||||
@@ -28,36 +28,36 @@ physical documents into a searchable online archive so you can keep, well, _less
|
||||
|
||||
## Features
|
||||
|
||||
- **Organize and index** your scanned documents with tags, correspondents, types, and more.
|
||||
- _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way, unless you explicitly choose to do so.
|
||||
- Performs **OCR** on your documents, adding searchable and selectable text, even to documents scanned with only images.
|
||||
- Utilizes the open-source Tesseract engine to recognize more than 100 languages.
|
||||
- _New!_ Supports remote OCR with Azure AI (opt-in).
|
||||
- Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals.
|
||||
- Uses machine-learning to automatically add tags, correspondents and document types to your documents.
|
||||
- **New**: Paperless-ngx can now leverage AI (Large Language Models or LLMs) for document suggestions. This is an optional feature that can be enabled (and is disabled by default).
|
||||
- Supports PDF documents, images, plain text files, Office documents (Word, Excel, PowerPoint, and LibreOffice equivalents)[^1] and more.
|
||||
- Paperless stores your documents plain on disk. Filenames and folders are managed by paperless and their format can be configured freely with different configurations assigned to different documents.
|
||||
- **Beautiful, modern web application** that features:
|
||||
- Customizable dashboard with statistics.
|
||||
- Filtering by tags, correspondents, types, and more.
|
||||
- Bulk editing of tags, correspondents, types and more.
|
||||
- Drag-and-drop uploading of documents throughout the app.
|
||||
- Customizable views can be saved and displayed on the dashboard and / or sidebar.
|
||||
- Support for custom fields of various data types.
|
||||
- Shareable public links with optional expiration.
|
||||
- **Full text search** helps you find what you need:
|
||||
- Auto completion suggests relevant words from your documents.
|
||||
- Results are sorted by relevance to your search query.
|
||||
- Highlighting shows you which parts of the document matched the query.
|
||||
- Searching for similar documents ("More like this")
|
||||
- **Email processing**[^1]: import documents from your email accounts:
|
||||
- Configure multiple accounts and rules for each account.
|
||||
- After processing, paperless can perform actions on the messages such as marking as read, deleting and more.
|
||||
- A built-in robust **multi-user permissions** system that supports 'global' permissions as well as per document or object.
|
||||
- A powerful workflow system that gives you even more control.
|
||||
- **Optimized** for multi core systems: Paperless-ngx consumes multiple documents in parallel.
|
||||
- The integrated sanity checker makes sure that your document archive is in good health.
|
||||
- **Organize and index** your scanned documents with tags, correspondents, types, and more.
|
||||
- _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way, unless you explicitly choose to do so.
|
||||
- Performs **OCR** on your documents, adding searchable and selectable text, even to documents scanned with only images.
|
||||
- Utilizes the open-source Tesseract engine to recognize more than 100 languages.
|
||||
- _New!_ Supports remote OCR with Azure AI (opt-in).
|
||||
- Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals.
|
||||
- Uses machine-learning to automatically add tags, correspondents and document types to your documents.
|
||||
- **New**: Paperless-ngx can now leverage AI (Large Language Models or LLMs) for document suggestions. This is an optional feature that can be enabled (and is disabled by default).
|
||||
- Supports PDF documents, images, plain text files, Office documents (Word, Excel, PowerPoint, and LibreOffice equivalents)[^1] and more.
|
||||
- Paperless stores your documents plain on disk. Filenames and folders are managed by paperless and their format can be configured freely with different configurations assigned to different documents.
|
||||
- **Beautiful, modern web application** that features:
|
||||
- Customizable dashboard with statistics.
|
||||
- Filtering by tags, correspondents, types, and more.
|
||||
- Bulk editing of tags, correspondents, types and more.
|
||||
- Drag-and-drop uploading of documents throughout the app.
|
||||
- Customizable views can be saved and displayed on the dashboard and / or sidebar.
|
||||
- Support for custom fields of various data types.
|
||||
- Shareable public links with optional expiration.
|
||||
- **Full text search** helps you find what you need:
|
||||
- Auto completion suggests relevant words from your documents.
|
||||
- Results are sorted by relevance to your search query.
|
||||
- Highlighting shows you which parts of the document matched the query.
|
||||
- Searching for similar documents ("More like this")
|
||||
- **Email processing**[^1]: import documents from your email accounts:
|
||||
- Configure multiple accounts and rules for each account.
|
||||
- After processing, paperless can perform actions on the messages such as marking as read, deleting and more.
|
||||
- A built-in robust **multi-user permissions** system that supports 'global' permissions as well as per document or object.
|
||||
- A powerful workflow system that gives you even more control.
|
||||
- **Optimized** for multi core systems: Paperless-ngx consumes multiple documents in parallel.
|
||||
- The integrated sanity checker makes sure that your document archive is in good health.
|
||||
|
||||
[^1]: Office document and email consumption support is optional and provided by Apache Tika (see [configuration](https://docs.paperless-ngx.com/configuration/#tika))
|
||||
|
||||
|
||||
@@ -42,12 +42,12 @@ The `CONSUMER_BARCODE_SCANNER` setting has been removed. zxing-cpp is now the on
|
||||
|
||||
### Action Required
|
||||
|
||||
- If you were already using `CONSUMER_BARCODE_SCANNER=ZXING`, simply remove the setting.
|
||||
- If you had `CONSUMER_BARCODE_SCANNER=PYZBAR` or were using the default, no functional changes are needed beyond
|
||||
removing the setting. zxing-cpp supports all the same barcode formats and you should see improved detection
|
||||
reliability.
|
||||
- The `libzbar0` / `libzbar-dev` system packages are no longer required and can be removed from any custom Docker
|
||||
images or host installations.
|
||||
- If you were already using `CONSUMER_BARCODE_SCANNER=ZXING`, simply remove the setting.
|
||||
- If you had `CONSUMER_BARCODE_SCANNER=PYZBAR` or were using the default, no functional changes are needed beyond
|
||||
removing the setting. zxing-cpp supports all the same barcode formats and you should see improved detection
|
||||
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
|
||||
|
||||
|
||||
235
docs/setup.md
235
docs/setup.md
@@ -44,8 +44,8 @@ account. In short, it automates the [Docker Compose setup](#docker) described be
|
||||
|
||||
#### Prerequisites
|
||||
|
||||
- Docker and Docker Compose must be [installed](https://docs.docker.com/engine/install/){:target="\_blank"}.
|
||||
- macOS users will need [GNU sed](https://formulae.brew.sh/formula/gnu-sed) with support for running as `sed` as well as [wget](https://formulae.brew.sh/formula/wget).
|
||||
- Docker and Docker Compose must be [installed](https://docs.docker.com/engine/install/){:target="\_blank"}.
|
||||
- macOS users will need [GNU sed](https://formulae.brew.sh/formula/gnu-sed) with support for running as `sed` as well as [wget](https://formulae.brew.sh/formula/wget).
|
||||
|
||||
#### Run the installation script
|
||||
|
||||
@@ -63,7 +63,7 @@ credentials you provided during the installation script.
|
||||
|
||||
#### Prerequisites
|
||||
|
||||
- Docker and Docker Compose must be [installed](https://docs.docker.com/engine/install/){:target="\_blank"}.
|
||||
- Docker and Docker Compose must be [installed](https://docs.docker.com/engine/install/){:target="\_blank"}.
|
||||
|
||||
#### Installation
|
||||
|
||||
@@ -101,7 +101,7 @@ credentials you provided during the installation script.
|
||||
|
||||
```yaml
|
||||
ports:
|
||||
- 8010:8000
|
||||
- 8010:8000
|
||||
```
|
||||
|
||||
3. Modify `docker-compose.env` with any configuration options you need.
|
||||
@@ -145,11 +145,11 @@ a [superuser](usage.md#superusers) account.
|
||||
If you want to run Paperless as a rootless container, make this
|
||||
change in `docker-compose.yml`:
|
||||
|
||||
- Set the `user` running the container to map to the `paperless`
|
||||
user in the container. This value (`user_id` below) should be
|
||||
the same ID that `USERMAP_UID` and `USERMAP_GID` are set to in
|
||||
`docker-compose.env`. See `USERMAP_UID` and `USERMAP_GID`
|
||||
[here](configuration.md#docker).
|
||||
- Set the `user` running the container to map to the `paperless`
|
||||
user in the container. This value (`user_id` below) should be
|
||||
the same ID that `USERMAP_UID` and `USERMAP_GID` are set to in
|
||||
`docker-compose.env`. See `USERMAP_UID` and `USERMAP_GID`
|
||||
[here](configuration.md#docker).
|
||||
|
||||
Your entry for Paperless should contain something like:
|
||||
|
||||
@@ -171,26 +171,25 @@ to enable polling and disable inotify. See [here](configuration.md#polling).
|
||||
|
||||
#### Prerequisites
|
||||
|
||||
- Paperless runs on Linux only, Windows is not supported.
|
||||
- Python 3.11, 3.12, 3.13, or 3.14 is required. As a policy, Paperless-ngx aims to support at least the three most recent Python versions and drops support for versions as they reach end-of-life. Newer versions may work, but some dependencies may not be fully compatible.
|
||||
- Paperless runs on Linux only, Windows is not supported.
|
||||
- Python 3.11, 3.12, 3.13, or 3.14 is required. As a policy, Paperless-ngx aims to support at least the three most recent Python versions and drops support for versions as they reach end-of-life. Newer versions may work, but some dependencies may not be fully compatible.
|
||||
|
||||
#### Installation
|
||||
|
||||
1. Install dependencies. Paperless requires the following packages:
|
||||
|
||||
- `python3`
|
||||
- `python3-pip`
|
||||
- `python3-dev`
|
||||
- `default-libmysqlclient-dev` for MariaDB
|
||||
- `pkg-config` for mysqlclient (python dependency)
|
||||
- `fonts-liberation` for generating thumbnails for plain text
|
||||
files
|
||||
- `imagemagick` >= 6 for PDF conversion
|
||||
- `gnupg` for handling encrypted documents
|
||||
- `libpq-dev` for PostgreSQL
|
||||
- `libmagic-dev` for mime type detection
|
||||
- `mariadb-client` for MariaDB compile time
|
||||
- `poppler-utils` for barcode detection
|
||||
- `python3`
|
||||
- `python3-pip`
|
||||
- `python3-dev`
|
||||
- `default-libmysqlclient-dev` for MariaDB
|
||||
- `pkg-config` for mysqlclient (python dependency)
|
||||
- `fonts-liberation` for generating thumbnails for plain text
|
||||
files
|
||||
- `imagemagick` >= 6 for PDF conversion
|
||||
- `gnupg` for handling encrypted documents
|
||||
- `libpq-dev` for PostgreSQL
|
||||
- `libmagic-dev` for mime type detection
|
||||
- `mariadb-client` for MariaDB compile time
|
||||
- `poppler-utils` for barcode detection
|
||||
|
||||
Use this list for your preferred package management:
|
||||
|
||||
@@ -200,18 +199,17 @@ to enable polling and disable inotify. See [here](configuration.md#polling).
|
||||
|
||||
These dependencies are required for OCRmyPDF, which is used for text
|
||||
recognition.
|
||||
|
||||
- `unpaper`
|
||||
- `ghostscript`
|
||||
- `icc-profiles-free`
|
||||
- `qpdf`
|
||||
- `liblept5`
|
||||
- `libxml2`
|
||||
- `pngquant` (suggested for certain PDF image optimizations)
|
||||
- `zlib1g`
|
||||
- `tesseract-ocr` >= 4.0.0 for OCR
|
||||
- `tesseract-ocr` language packs (`tesseract-ocr-eng`,
|
||||
`tesseract-ocr-deu`, etc)
|
||||
- `unpaper`
|
||||
- `ghostscript`
|
||||
- `icc-profiles-free`
|
||||
- `qpdf`
|
||||
- `liblept5`
|
||||
- `libxml2`
|
||||
- `pngquant` (suggested for certain PDF image optimizations)
|
||||
- `zlib1g`
|
||||
- `tesseract-ocr` >= 4.0.0 for OCR
|
||||
- `tesseract-ocr` language packs (`tesseract-ocr-eng`,
|
||||
`tesseract-ocr-deu`, etc)
|
||||
|
||||
Use this list for your preferred package management:
|
||||
|
||||
@@ -220,16 +218,14 @@ to enable polling and disable inotify. See [here](configuration.md#polling).
|
||||
```
|
||||
|
||||
On Raspberry Pi, these libraries are required as well:
|
||||
|
||||
- `libatlas-base-dev`
|
||||
- `libxslt1-dev`
|
||||
- `mime-support`
|
||||
- `libatlas-base-dev`
|
||||
- `libxslt1-dev`
|
||||
- `mime-support`
|
||||
|
||||
You will also need these for installing some of the python dependencies:
|
||||
|
||||
- `build-essential`
|
||||
- `python3-setuptools`
|
||||
- `python3-wheel`
|
||||
- `build-essential`
|
||||
- `python3-setuptools`
|
||||
- `python3-wheel`
|
||||
|
||||
Use this list for your preferred package management:
|
||||
|
||||
@@ -279,44 +275,41 @@ to enable polling and disable inotify. See [here](configuration.md#polling).
|
||||
6. Configure Paperless-ngx. See [configuration](configuration.md) for details.
|
||||
Edit the included `paperless.conf` and adjust the settings to your
|
||||
needs. Required settings for getting Paperless-ngx running are:
|
||||
|
||||
- [`PAPERLESS_REDIS`](configuration.md#PAPERLESS_REDIS) should point to your Redis server, such as
|
||||
`redis://localhost:6379`.
|
||||
- [`PAPERLESS_DBENGINE`](configuration.md#PAPERLESS_DBENGINE) is optional, and should be one of `postgres`,
|
||||
`mariadb`, or `sqlite`
|
||||
- [`PAPERLESS_DBHOST`](configuration.md#PAPERLESS_DBHOST) should be the hostname on which your
|
||||
PostgreSQL server is running. Do not configure this to use
|
||||
SQLite instead. Also configure port, database name, user and
|
||||
password as necessary.
|
||||
- [`PAPERLESS_CONSUMPTION_DIR`](configuration.md#PAPERLESS_CONSUMPTION_DIR) should point to the folder
|
||||
that Paperless-ngx should watch for incoming documents.
|
||||
Likewise, [`PAPERLESS_DATA_DIR`](configuration.md#PAPERLESS_DATA_DIR) and
|
||||
[`PAPERLESS_MEDIA_ROOT`](configuration.md#PAPERLESS_MEDIA_ROOT) define where Paperless-ngx stores its data.
|
||||
If needed, these can point to the same directory.
|
||||
- [`PAPERLESS_SECRET_KEY`](configuration.md#PAPERLESS_SECRET_KEY) should be a random sequence of
|
||||
characters. It's used for authentication. Failure to do so
|
||||
allows third parties to forge authentication credentials.
|
||||
- Set [`PAPERLESS_URL`](configuration.md#PAPERLESS_URL) if you are behind a reverse proxy. This should
|
||||
point to your domain. Please see
|
||||
[configuration](configuration.md) for more
|
||||
information.
|
||||
- [`PAPERLESS_REDIS`](configuration.md#PAPERLESS_REDIS) should point to your Redis server, such as
|
||||
`redis://localhost:6379`.
|
||||
- [`PAPERLESS_DBENGINE`](configuration.md#PAPERLESS_DBENGINE) is optional, and should be one of `postgres`,
|
||||
`mariadb`, or `sqlite`
|
||||
- [`PAPERLESS_DBHOST`](configuration.md#PAPERLESS_DBHOST) should be the hostname on which your
|
||||
PostgreSQL server is running. Do not configure this to use
|
||||
SQLite instead. Also configure port, database name, user and
|
||||
password as necessary.
|
||||
- [`PAPERLESS_CONSUMPTION_DIR`](configuration.md#PAPERLESS_CONSUMPTION_DIR) should point to the folder
|
||||
that Paperless-ngx should watch for incoming documents.
|
||||
Likewise, [`PAPERLESS_DATA_DIR`](configuration.md#PAPERLESS_DATA_DIR) and
|
||||
[`PAPERLESS_MEDIA_ROOT`](configuration.md#PAPERLESS_MEDIA_ROOT) define where Paperless-ngx stores its data.
|
||||
If needed, these can point to the same directory.
|
||||
- [`PAPERLESS_SECRET_KEY`](configuration.md#PAPERLESS_SECRET_KEY) should be a random sequence of
|
||||
characters. It's used for authentication. Failure to do so
|
||||
allows third parties to forge authentication credentials.
|
||||
- Set [`PAPERLESS_URL`](configuration.md#PAPERLESS_URL) if you are behind a reverse proxy. This should
|
||||
point to your domain. Please see
|
||||
[configuration](configuration.md) for more
|
||||
information.
|
||||
|
||||
You can make many more adjustments, especially for OCR.
|
||||
The following options are recommended for most users:
|
||||
|
||||
- Set [`PAPERLESS_OCR_LANGUAGE`](configuration.md#PAPERLESS_OCR_LANGUAGE) to the language most of your
|
||||
documents are written in.
|
||||
- Set [`PAPERLESS_TIME_ZONE`](configuration.md#PAPERLESS_TIME_ZONE) to your local time zone.
|
||||
- Set [`PAPERLESS_OCR_LANGUAGE`](configuration.md#PAPERLESS_OCR_LANGUAGE) to the language most of your
|
||||
documents are written in.
|
||||
- Set [`PAPERLESS_TIME_ZONE`](configuration.md#PAPERLESS_TIME_ZONE) to your local time zone.
|
||||
|
||||
!!! warning
|
||||
|
||||
Ensure your Redis instance [is secured](https://redis.io/docs/latest/operate/oss_and_stack/management/security/).
|
||||
|
||||
7. Create the following directories if they do not already exist:
|
||||
|
||||
- `/opt/paperless/media`
|
||||
- `/opt/paperless/data`
|
||||
- `/opt/paperless/consume`
|
||||
- `/opt/paperless/media`
|
||||
- `/opt/paperless/data`
|
||||
- `/opt/paperless/consume`
|
||||
|
||||
Adjust these paths if you configured different folders.
|
||||
Then verify that the `paperless` user has write permissions:
|
||||
@@ -391,11 +384,10 @@ to enable polling and disable inotify. See [here](configuration.md#polling).
|
||||
starting point.
|
||||
|
||||
Paperless needs:
|
||||
|
||||
- The `webserver` script to run the webserver.
|
||||
- The `consumer` script to watch the input folder.
|
||||
- The `taskqueue` script for background workers (document consumption, etc.).
|
||||
- The `scheduler` script for periodic tasks such as email checking.
|
||||
- The `webserver` script to run the webserver.
|
||||
- The `consumer` script to watch the input folder.
|
||||
- The `taskqueue` script for background workers (document consumption, etc.).
|
||||
- The `scheduler` script for periodic tasks such as email checking.
|
||||
|
||||
!!! note
|
||||
|
||||
@@ -501,19 +493,19 @@ your setup depending on how you installed Paperless.
|
||||
This section describes how to update an existing Paperless Docker
|
||||
installation. Keep these points in mind:
|
||||
|
||||
- Read the [changelog](changelog.md) and
|
||||
take note of breaking changes.
|
||||
- Decide whether to stay on SQLite or migrate to PostgreSQL.
|
||||
Both work fine with Paperless-ngx.
|
||||
However, if you already have a database server running
|
||||
for other services, you might as well use it for Paperless as well.
|
||||
- The task scheduler of Paperless, which is used to execute periodic
|
||||
tasks such as email checking and maintenance, requires a
|
||||
[Redis](https://redis.io/) message broker instance. The
|
||||
Docker Compose route takes care of that.
|
||||
- The layout of the folder structure for your documents and data
|
||||
remains the same, so you can plug your old Docker volumes into
|
||||
paperless-ngx and expect it to find everything where it should be.
|
||||
- Read the [changelog](changelog.md) and
|
||||
take note of breaking changes.
|
||||
- Decide whether to stay on SQLite or migrate to PostgreSQL.
|
||||
Both work fine with Paperless-ngx.
|
||||
However, if you already have a database server running
|
||||
for other services, you might as well use it for Paperless as well.
|
||||
- The task scheduler of Paperless, which is used to execute periodic
|
||||
tasks such as email checking and maintenance, requires a
|
||||
[Redis](https://redis.io/) message broker instance. The
|
||||
Docker Compose route takes care of that.
|
||||
- The layout of the folder structure for your documents and data
|
||||
remains the same, so you can plug your old Docker volumes into
|
||||
paperless-ngx and expect it to find everything where it should be.
|
||||
|
||||
Migration to Paperless-ngx is then performed in a few simple steps:
|
||||
|
||||
@@ -598,7 +590,6 @@ commands as well.
|
||||
1. Stop and remove the Paperless container.
|
||||
2. If using an external database, stop that container.
|
||||
3. Update Redis configuration.
|
||||
|
||||
1. If `REDIS_URL` is already set, change it to [`PAPERLESS_REDIS`](configuration.md#PAPERLESS_REDIS)
|
||||
and continue to step 4.
|
||||
|
||||
@@ -610,22 +601,18 @@ commands as well.
|
||||
the new Redis container.
|
||||
|
||||
4. Update user mapping.
|
||||
|
||||
1. If set, change the environment variable `PUID` to `USERMAP_UID`.
|
||||
|
||||
1. If set, change the environment variable `PGID` to `USERMAP_GID`.
|
||||
|
||||
5. Update configuration paths.
|
||||
|
||||
1. Set the environment variable [`PAPERLESS_DATA_DIR`](configuration.md#PAPERLESS_DATA_DIR) to `/config`.
|
||||
|
||||
6. Update media paths.
|
||||
|
||||
1. Set the environment variable [`PAPERLESS_MEDIA_ROOT`](configuration.md#PAPERLESS_MEDIA_ROOT) to
|
||||
`/data/media`.
|
||||
|
||||
7. Update timezone.
|
||||
|
||||
1. Set the environment variable [`PAPERLESS_TIME_ZONE`](configuration.md#PAPERLESS_TIME_ZONE) to the same
|
||||
value as `TZ`.
|
||||
|
||||
@@ -639,33 +626,33 @@ commands as well.
|
||||
Paperless runs on Raspberry Pi. Some tasks can be slow on lower-powered
|
||||
hardware, but a few settings can improve performance:
|
||||
|
||||
- Stick with SQLite to save some resources. See [troubleshooting](troubleshooting.md#log-reports-creating-paperlesstask-failed)
|
||||
if you encounter issues with SQLite locking.
|
||||
- If you do not need the filesystem-based consumer, consider disabling it
|
||||
entirely by setting [`PAPERLESS_CONSUMER_DISABLE`](configuration.md#PAPERLESS_CONSUMER_DISABLE) to `true`.
|
||||
- Consider setting [`PAPERLESS_OCR_PAGES`](configuration.md#PAPERLESS_OCR_PAGES) to 1, so that Paperless
|
||||
OCRs only the first page of your documents. In most cases, this page
|
||||
contains enough information to be able to find it.
|
||||
- [`PAPERLESS_TASK_WORKERS`](configuration.md#PAPERLESS_TASK_WORKERS) and [`PAPERLESS_THREADS_PER_WORKER`](configuration.md#PAPERLESS_THREADS_PER_WORKER) are
|
||||
configured to use all cores. The Raspberry Pi models 3 and up have 4
|
||||
cores, meaning that Paperless will use 2 workers and 2 threads per
|
||||
worker. This may result in sluggish response times during
|
||||
consumption, so you might want to lower these settings (example: 2
|
||||
workers and 1 thread to always have some computing power left for
|
||||
other tasks).
|
||||
- Keep [`PAPERLESS_OCR_MODE`](configuration.md#PAPERLESS_OCR_MODE) at its default value `skip` and consider
|
||||
OCRing your documents before feeding them into Paperless. Some
|
||||
scanners are able to do this!
|
||||
- Set [`PAPERLESS_OCR_SKIP_ARCHIVE_FILE`](configuration.md#PAPERLESS_OCR_SKIP_ARCHIVE_FILE) to `with_text` to skip archive
|
||||
file generation for already OCRed documents, or `always` to skip it
|
||||
for all documents.
|
||||
- If you want to perform OCR on the device, consider using
|
||||
`PAPERLESS_OCR_CLEAN=none`. This will speed up OCR times and use
|
||||
less memory at the expense of slightly worse OCR results.
|
||||
- If using Docker, consider setting [`PAPERLESS_WEBSERVER_WORKERS`](configuration.md#PAPERLESS_WEBSERVER_WORKERS) to 1. This will save some memory.
|
||||
- Consider setting [`PAPERLESS_ENABLE_NLTK`](configuration.md#PAPERLESS_ENABLE_NLTK) to false, to disable the
|
||||
more advanced language processing, which can take more memory and
|
||||
processing time.
|
||||
- Stick with SQLite to save some resources. See [troubleshooting](troubleshooting.md#log-reports-creating-paperlesstask-failed)
|
||||
if you encounter issues with SQLite locking.
|
||||
- If you do not need the filesystem-based consumer, consider disabling it
|
||||
entirely by setting [`PAPERLESS_CONSUMER_DISABLE`](configuration.md#PAPERLESS_CONSUMER_DISABLE) to `true`.
|
||||
- Consider setting [`PAPERLESS_OCR_PAGES`](configuration.md#PAPERLESS_OCR_PAGES) to 1, so that Paperless
|
||||
OCRs only the first page of your documents. In most cases, this page
|
||||
contains enough information to be able to find it.
|
||||
- [`PAPERLESS_TASK_WORKERS`](configuration.md#PAPERLESS_TASK_WORKERS) and [`PAPERLESS_THREADS_PER_WORKER`](configuration.md#PAPERLESS_THREADS_PER_WORKER) are
|
||||
configured to use all cores. The Raspberry Pi models 3 and up have 4
|
||||
cores, meaning that Paperless will use 2 workers and 2 threads per
|
||||
worker. This may result in sluggish response times during
|
||||
consumption, so you might want to lower these settings (example: 2
|
||||
workers and 1 thread to always have some computing power left for
|
||||
other tasks).
|
||||
- Keep [`PAPERLESS_OCR_MODE`](configuration.md#PAPERLESS_OCR_MODE) at its default value `skip` and consider
|
||||
OCRing your documents before feeding them into Paperless. Some
|
||||
scanners are able to do this!
|
||||
- Set [`PAPERLESS_OCR_SKIP_ARCHIVE_FILE`](configuration.md#PAPERLESS_OCR_SKIP_ARCHIVE_FILE) to `with_text` to skip archive
|
||||
file generation for already OCRed documents, or `always` to skip it
|
||||
for all documents.
|
||||
- If you want to perform OCR on the device, consider using
|
||||
`PAPERLESS_OCR_CLEAN=none`. This will speed up OCR times and use
|
||||
less memory at the expense of slightly worse OCR results.
|
||||
- If using Docker, consider setting [`PAPERLESS_WEBSERVER_WORKERS`](configuration.md#PAPERLESS_WEBSERVER_WORKERS) to 1. This will save some memory.
|
||||
- Consider setting [`PAPERLESS_ENABLE_NLTK`](configuration.md#PAPERLESS_ENABLE_NLTK) to false, to disable the
|
||||
more advanced language processing, which can take more memory and
|
||||
processing time.
|
||||
|
||||
For details, refer to [configuration](configuration.md).
|
||||
|
||||
|
||||
@@ -4,27 +4,27 @@
|
||||
|
||||
Check for the following issues:
|
||||
|
||||
- Ensure that the directory you're putting your documents in is the
|
||||
folder paperless is watching. With docker, this setting is performed
|
||||
in the `docker-compose.yml` file. Without Docker, look at the
|
||||
`CONSUMPTION_DIR` setting. Don't adjust this setting if you're
|
||||
using docker.
|
||||
- Ensure that the directory you're putting your documents in is the
|
||||
folder paperless is watching. With docker, this setting is performed
|
||||
in the `docker-compose.yml` file. Without Docker, look at the
|
||||
`CONSUMPTION_DIR` setting. Don't adjust this setting if you're
|
||||
using docker.
|
||||
|
||||
- Ensure that redis is up and running. Paperless does its task
|
||||
processing asynchronously, and for documents to arrive at the task
|
||||
processor, it needs redis to run.
|
||||
- Ensure that redis is up and running. Paperless does its task
|
||||
processing asynchronously, and for documents to arrive at the task
|
||||
processor, it needs redis to run.
|
||||
|
||||
- Ensure that the task processor is running. Docker does this
|
||||
automatically. Manually invoke the task processor by executing
|
||||
- Ensure that the task processor is running. Docker does this
|
||||
automatically. Manually invoke the task processor by executing
|
||||
|
||||
```shell-session
|
||||
celery --app paperless worker
|
||||
```
|
||||
```shell-session
|
||||
celery --app paperless worker
|
||||
```
|
||||
|
||||
- Look at the output of paperless and inspect it for any errors.
|
||||
- Look at the output of paperless and inspect it for any errors.
|
||||
|
||||
- Go to the admin interface, and check if there are failed tasks. If
|
||||
so, the tasks will contain an error message.
|
||||
- Go to the admin interface, and check if there are failed tasks. If
|
||||
so, the tasks will contain an error message.
|
||||
|
||||
## Consumer warns `OCR for XX failed`
|
||||
|
||||
@@ -78,12 +78,12 @@ Ensure that `chown` is possible on these directories.
|
||||
This indicates that the Auto matching algorithm found no documents to
|
||||
learn from. This may have two reasons:
|
||||
|
||||
- You don't use the Auto matching algorithm: The error can be safely
|
||||
ignored in this case.
|
||||
- You are using the Auto matching algorithm: The classifier explicitly
|
||||
excludes documents with Inbox tags. Verify that there are documents
|
||||
in your archive without inbox tags. The algorithm will only learn
|
||||
from documents not in your inbox.
|
||||
- You don't use the Auto matching algorithm: The error can be safely
|
||||
ignored in this case.
|
||||
- You are using the Auto matching algorithm: The classifier explicitly
|
||||
excludes documents with Inbox tags. Verify that there are documents
|
||||
in your archive without inbox tags. The algorithm will only learn
|
||||
from documents not in your inbox.
|
||||
|
||||
## UserWarning in sklearn on every single document
|
||||
|
||||
@@ -127,10 +127,10 @@ change in the `docker-compose.yml` file:
|
||||
# The gotenberg chromium route is used to convert .eml files. We do not
|
||||
# want to allow external content like tracking pixels or even javascript.
|
||||
command:
|
||||
- 'gotenberg'
|
||||
- '--chromium-disable-javascript=true'
|
||||
- '--chromium-allow-list=file:///tmp/.*'
|
||||
- '--api-timeout=60s'
|
||||
- 'gotenberg'
|
||||
- '--chromium-disable-javascript=true'
|
||||
- '--chromium-allow-list=file:///tmp/.*'
|
||||
- '--api-timeout=60s'
|
||||
```
|
||||
|
||||
## Permission denied errors in the consumption directory
|
||||
|
||||
404
docs/usage.md
404
docs/usage.md
@@ -14,42 +14,42 @@ for finding and managing your documents.
|
||||
Paperless essentially consists of two different parts for managing your
|
||||
documents:
|
||||
|
||||
- The _consumer_ watches a specified folder and adds all documents in
|
||||
that folder to paperless.
|
||||
- The _web server_ (web UI) provides a UI that you use to manage and
|
||||
search documents.
|
||||
- The _consumer_ watches a specified folder and adds all documents in
|
||||
that folder to paperless.
|
||||
- The _web server_ (web UI) provides a UI that you use to manage and
|
||||
search documents.
|
||||
|
||||
Each document has data fields that you can assign to them:
|
||||
|
||||
- A _Document_ is a piece of paper that sometimes contains valuable
|
||||
information.
|
||||
- The _correspondent_ of a document is the person, institution or
|
||||
company that a document either originates from, or is sent to.
|
||||
- A _tag_ is a label that you can assign to documents. Think of labels
|
||||
as more powerful folders: Multiple documents can be grouped together
|
||||
with a single tag, however, a single document can also have multiple
|
||||
tags. This is not possible with folders. The reason folders are not
|
||||
implemented in paperless is simply that tags are much more versatile
|
||||
than folders.
|
||||
- A _document type_ is used to demarcate the type of a document such
|
||||
as letter, bank statement, invoice, contract, etc. It is used to
|
||||
identify what a document is about.
|
||||
- The document _storage path_ is the location where the document files
|
||||
are stored. See [Storage Paths](advanced_usage.md#storage-paths) for
|
||||
more information.
|
||||
- The _date added_ of a document is the date the document was scanned
|
||||
into paperless. You cannot and should not change this date.
|
||||
- The _date created_ of a document is the date the document was
|
||||
initially issued. This can be the date you bought a product, the
|
||||
date you signed a contract, or the date a letter was sent to you.
|
||||
- The _archive serial number_ (short: ASN) of a document is the
|
||||
identifier of the document in your physical document binders. See
|
||||
[recommended workflow](#usage-recommended-workflow) below.
|
||||
- The _content_ of a document is the text that was OCR'ed from the
|
||||
document. This text is fed into the search engine and is used for
|
||||
matching tags, correspondents and document types.
|
||||
- Paperless-ngx also supports _custom fields_ which can be used to
|
||||
store additional metadata about a document.
|
||||
- A _Document_ is a piece of paper that sometimes contains valuable
|
||||
information.
|
||||
- The _correspondent_ of a document is the person, institution or
|
||||
company that a document either originates from, or is sent to.
|
||||
- A _tag_ is a label that you can assign to documents. Think of labels
|
||||
as more powerful folders: Multiple documents can be grouped together
|
||||
with a single tag, however, a single document can also have multiple
|
||||
tags. This is not possible with folders. The reason folders are not
|
||||
implemented in paperless is simply that tags are much more versatile
|
||||
than folders.
|
||||
- A _document type_ is used to demarcate the type of a document such
|
||||
as letter, bank statement, invoice, contract, etc. It is used to
|
||||
identify what a document is about.
|
||||
- The document _storage path_ is the location where the document files
|
||||
are stored. See [Storage Paths](advanced_usage.md#storage-paths) for
|
||||
more information.
|
||||
- The _date added_ of a document is the date the document was scanned
|
||||
into paperless. You cannot and should not change this date.
|
||||
- The _date created_ of a document is the date the document was
|
||||
initially issued. This can be the date you bought a product, the
|
||||
date you signed a contract, or the date a letter was sent to you.
|
||||
- The _archive serial number_ (short: ASN) of a document is the
|
||||
identifier of the document in your physical document binders. See
|
||||
[recommended workflow](#usage-recommended-workflow) below.
|
||||
- The _content_ of a document is the text that was OCR'ed from the
|
||||
document. This text is fed into the search engine and is used for
|
||||
matching tags, correspondents and document types.
|
||||
- Paperless-ngx also supports _custom fields_ which can be used to
|
||||
store additional metadata about a document.
|
||||
|
||||
## The Web UI
|
||||
|
||||
@@ -93,12 +93,12 @@ download the document or share it via a share link.
|
||||
|
||||
Think of versions as **file history** for a document.
|
||||
|
||||
- Versions track the underlying file and extracted text content (OCR/text).
|
||||
- Metadata such as tags, correspondent, document type, storage path and custom fields stay on the "root" document.
|
||||
- Version files follow normal filename formatting (including storage paths) and add a `_vN` suffix (for example `_v1`, `_v2`).
|
||||
- By default, search and document content use the latest version.
|
||||
- In document detail, selecting a version switches the preview, file metadata and content (and download etc buttons) to that version.
|
||||
- Deleting a non-root version keeps metadata and falls back to the latest remaining version.
|
||||
- Versions track the underlying file and extracted text content (OCR/text).
|
||||
- Metadata such as tags, correspondent, document type, storage path and custom fields stay on the "root" document.
|
||||
- Version files follow normal filename formatting (including storage paths) and add a `_vN` suffix (for example `_v1`, `_v2`).
|
||||
- By default, search and document content use the latest version.
|
||||
- In document detail, selecting a version switches the preview, file metadata and content (and download etc buttons) to that version.
|
||||
- Deleting a non-root version keeps metadata and falls back to the latest remaining version.
|
||||
|
||||
### Management Lists
|
||||
|
||||
@@ -218,21 +218,20 @@ patterns can include wildcards and multiple patterns separated by a comma.
|
||||
The actions all ensure that the same mail is not consumed twice by
|
||||
different means. These are as follows:
|
||||
|
||||
- **Delete:** Immediately deletes mail that paperless has consumed
|
||||
documents from. Use with caution.
|
||||
- **Mark as read:** Mark consumed mail as read. Paperless will not
|
||||
consume documents from already read mails. If you read a mail before
|
||||
paperless sees it, it will be ignored.
|
||||
- **Flag:** Sets the 'important' flag on mails with consumed
|
||||
documents. Paperless will not consume flagged mails.
|
||||
- **Move to folder:** Moves consumed mails out of the way so that
|
||||
paperless won't consume them again.
|
||||
- **Add custom Tag:** Adds a custom tag to mails with consumed
|
||||
documents (the IMAP standard calls these "keywords"). Paperless
|
||||
will not consume mails already tagged. Not all mail servers support
|
||||
this feature!
|
||||
|
||||
- **Apple Mail support:** Apple Mail clients allow differently colored tags. For this to work use `apple:<color>` (e.g. _apple:green_) as a custom tag. Available colors are _red_, _orange_, _yellow_, _blue_, _green_, _violet_ and _grey_.
|
||||
- **Delete:** Immediately deletes mail that paperless has consumed
|
||||
documents from. Use with caution.
|
||||
- **Mark as read:** Mark consumed mail as read. Paperless will not
|
||||
consume documents from already read mails. If you read a mail before
|
||||
paperless sees it, it will be ignored.
|
||||
- **Flag:** Sets the 'important' flag on mails with consumed
|
||||
documents. Paperless will not consume flagged mails.
|
||||
- **Move to folder:** Moves consumed mails out of the way so that
|
||||
paperless won't consume them again.
|
||||
- **Add custom Tag:** Adds a custom tag to mails with consumed
|
||||
documents (the IMAP standard calls these "keywords"). Paperless
|
||||
will not consume mails already tagged. Not all mail servers support
|
||||
this feature!
|
||||
- **Apple Mail support:** Apple Mail clients allow differently colored tags. For this to work use `apple:<color>` (e.g. _apple:green_) as a custom tag. Available colors are _red_, _orange_, _yellow_, _blue_, _green_, _violet_ and _grey_.
|
||||
|
||||
!!! warning
|
||||
|
||||
@@ -325,12 +324,12 @@ or using [email](#workflow-action-email) or [webhook](#workflow-action-webhook)
|
||||
|
||||
"Share links" are public links to files (or an archive of files) and can be created and managed under the 'Send' button on the document detail screen or from the bulk editor.
|
||||
|
||||
- Share links do not require a user to login and thus link directly to a file or bundled download.
|
||||
- Links are unique and are of the form `{paperless-url}/share/{randomly-generated-slug}`.
|
||||
- Links can optionally have an expiration time set.
|
||||
- After a link expires or is deleted users will be redirected to the regular paperless-ngx login.
|
||||
- From the document detail screen you can create a share link for that single document.
|
||||
- From the bulk editor you can create a **share link bundle** for any selection. Paperless-ngx prepares a ZIP archive in the background and exposes a single share link. You can revisit the "Manage share link bundles" dialog to monitor progress, retry failed bundles, or delete links.
|
||||
- Share links do not require a user to login and thus link directly to a file or bundled download.
|
||||
- Links are unique and are of the form `{paperless-url}/share/{randomly-generated-slug}`.
|
||||
- Links can optionally have an expiration time set.
|
||||
- After a link expires or is deleted users will be redirected to the regular paperless-ngx login.
|
||||
- From the document detail screen you can create a share link for that single document.
|
||||
- From the bulk editor you can create a **share link bundle** for any selection. Paperless-ngx prepares a ZIP archive in the background and exposes a single share link. You can revisit the "Manage share link bundles" dialog to monitor progress, retry failed bundles, or delete links.
|
||||
|
||||
!!! tip
|
||||
|
||||
@@ -514,25 +513,25 @@ flowchart TD
|
||||
|
||||
Workflows allow you to filter by:
|
||||
|
||||
- Source, e.g. documents uploaded via consume folder, API (& the web UI) and mail fetch
|
||||
- File name, including wildcards e.g. \*.pdf will apply to all pdfs.
|
||||
- File path, including wildcards. Note that enabling `PAPERLESS_CONSUMER_RECURSIVE` would allow, for
|
||||
example, automatically assigning documents to different owners based on the upload directory.
|
||||
- Mail rule. Choosing this option will force 'mail fetch' to be the workflow source.
|
||||
- Content matching (`Added`, `Updated` and `Scheduled` triggers only). Filter document content using the matching settings.
|
||||
- Source, e.g. documents uploaded via consume folder, API (& the web UI) and mail fetch
|
||||
- File name, including wildcards e.g. \*.pdf will apply to all pdfs.
|
||||
- File path, including wildcards. Note that enabling `PAPERLESS_CONSUMER_RECURSIVE` would allow, for
|
||||
example, automatically assigning documents to different owners based on the upload directory.
|
||||
- Mail rule. Choosing this option will force 'mail fetch' to be the workflow source.
|
||||
- Content matching (`Added`, `Updated` and `Scheduled` triggers only). Filter document content using the matching settings.
|
||||
|
||||
There are also 'advanced' filters available for `Added`, `Updated` and `Scheduled` triggers:
|
||||
|
||||
- Any Tags: Filter for documents with any of the specified tags.
|
||||
- All Tags: Filter for documents with all of the specified tags.
|
||||
- No Tags: Filter for documents with none of the specified tags.
|
||||
- Document type: Filter documents with this document type.
|
||||
- Not Document types: Filter documents without any of these document types.
|
||||
- Correspondent: Filter documents with this correspondent.
|
||||
- Not Correspondents: Filter documents without any of these correspondents.
|
||||
- Storage path: Filter documents with this storage path.
|
||||
- Not Storage paths: Filter documents without any of these storage paths.
|
||||
- Custom field query: Filter documents with a custom field query (the same as used for the document list filters).
|
||||
- Any Tags: Filter for documents with any of the specified tags.
|
||||
- All Tags: Filter for documents with all of the specified tags.
|
||||
- No Tags: Filter for documents with none of the specified tags.
|
||||
- Document type: Filter documents with this document type.
|
||||
- Not Document types: Filter documents without any of these document types.
|
||||
- Correspondent: Filter documents with this correspondent.
|
||||
- Not Correspondents: Filter documents without any of these correspondents.
|
||||
- Storage path: Filter documents with this storage path.
|
||||
- Not Storage paths: Filter documents without any of these storage paths.
|
||||
- Custom field query: Filter documents with a custom field query (the same as used for the document list filters).
|
||||
|
||||
### Workflow Actions
|
||||
|
||||
@@ -544,37 +543,37 @@ The following workflow action types are available:
|
||||
|
||||
"Assignment" actions can assign:
|
||||
|
||||
- Title, see [workflow placeholders](usage.md#workflow-placeholders) below
|
||||
- Tags, correspondent, document type and storage path
|
||||
- Document owner
|
||||
- View and / or edit permissions to users or groups
|
||||
- Custom fields. Note that no value for the field will be set
|
||||
- Title, see [workflow placeholders](usage.md#workflow-placeholders) below
|
||||
- Tags, correspondent, document type and storage path
|
||||
- Document owner
|
||||
- View and / or edit permissions to users or groups
|
||||
- Custom fields. Note that no value for the field will be set
|
||||
|
||||
##### Removal {#workflow-action-removal}
|
||||
|
||||
"Removal" actions can remove either all of or specific sets of the following:
|
||||
|
||||
- Tags, correspondents, document types or storage paths
|
||||
- Document owner
|
||||
- View and / or edit permissions
|
||||
- Custom fields
|
||||
- Tags, correspondents, document types or storage paths
|
||||
- Document owner
|
||||
- View and / or edit permissions
|
||||
- Custom fields
|
||||
|
||||
##### Email {#workflow-action-email}
|
||||
|
||||
"Email" actions can send documents via email. This action requires a mail server to be [configured](configuration.md#email-sending). You can specify:
|
||||
|
||||
- The recipient email address(es) separated by commas
|
||||
- The subject and body of the email, which can include placeholders, see [placeholders](usage.md#workflow-placeholders) below
|
||||
- Whether to include the document as an attachment
|
||||
- The recipient email address(es) separated by commas
|
||||
- The subject and body of the email, which can include placeholders, see [placeholders](usage.md#workflow-placeholders) below
|
||||
- Whether to include the document as an attachment
|
||||
|
||||
##### Webhook {#workflow-action-webhook}
|
||||
|
||||
"Webhook" actions send a POST request to a specified URL. You can specify:
|
||||
|
||||
- The URL to send the request to
|
||||
- The request body as text or as key-value pairs, which can include placeholders, see [placeholders](usage.md#workflow-placeholders) below.
|
||||
- Encoding for the request body, either JSON or form data
|
||||
- The request headers as key-value pairs
|
||||
- The URL to send the request to
|
||||
- The request body as text or as key-value pairs, which can include placeholders, see [placeholders](usage.md#workflow-placeholders) below.
|
||||
- Encoding for the request body, either JSON or form data
|
||||
- The request headers as key-value pairs
|
||||
|
||||
For security reasons, webhooks can be limited to specific ports and disallowed from connecting to local URLs. See the relevant
|
||||
[configuration settings](configuration.md#workflow-webhooks) to change this behavior. If you are allowing non-admins to create workflows,
|
||||
@@ -605,33 +604,33 @@ The available inputs differ depending on the type of workflow trigger.
|
||||
This is because at the time of consumption (when the text is to be set), no automatic tags etc. have been
|
||||
applied. You can use the following placeholders in the template with any trigger type:
|
||||
|
||||
- `{{correspondent}}`: assigned correspondent name
|
||||
- `{{document_type}}`: assigned document type name
|
||||
- `{{owner_username}}`: assigned owner username
|
||||
- `{{added}}`: added datetime
|
||||
- `{{added_year}}`: added year
|
||||
- `{{added_year_short}}`: added year
|
||||
- `{{added_month}}`: added month
|
||||
- `{{added_month_name}}`: added month name
|
||||
- `{{added_month_name_short}}`: added month short name
|
||||
- `{{added_day}}`: added day
|
||||
- `{{added_time}}`: added time in HH:MM format
|
||||
- `{{original_filename}}`: original file name without extension
|
||||
- `{{filename}}`: current file name without extension (for "added" workflows this may not be final yet, you can use `{{original_filename}}`)
|
||||
- `{{doc_title}}`: current document title (cannot be used in title assignment)
|
||||
- `{{correspondent}}`: assigned correspondent name
|
||||
- `{{document_type}}`: assigned document type name
|
||||
- `{{owner_username}}`: assigned owner username
|
||||
- `{{added}}`: added datetime
|
||||
- `{{added_year}}`: added year
|
||||
- `{{added_year_short}}`: added year
|
||||
- `{{added_month}}`: added month
|
||||
- `{{added_month_name}}`: added month name
|
||||
- `{{added_month_name_short}}`: added month short name
|
||||
- `{{added_day}}`: added day
|
||||
- `{{added_time}}`: added time in HH:MM format
|
||||
- `{{original_filename}}`: original file name without extension
|
||||
- `{{filename}}`: current file name without extension (for "added" workflows this may not be final yet, you can use `{{original_filename}}`)
|
||||
- `{{doc_title}}`: current document title (cannot be used in title assignment)
|
||||
|
||||
The following placeholders are only available for "added" or "updated" triggers
|
||||
|
||||
- `{{created}}`: created datetime
|
||||
- `{{created_year}}`: created year
|
||||
- `{{created_year_short}}`: created year
|
||||
- `{{created_month}}`: created month
|
||||
- `{{created_month_name}}`: created month name
|
||||
- `{{created_month_name_short}}`: created month short name
|
||||
- `{{created_day}}`: created day
|
||||
- `{{created_time}}`: created time in HH:MM format
|
||||
- `{{doc_url}}`: URL to the document in the web UI. Requires the `PAPERLESS_URL` setting to be set.
|
||||
- `{{doc_id}}`: Document ID
|
||||
- `{{created}}`: created datetime
|
||||
- `{{created_year}}`: created year
|
||||
- `{{created_year_short}}`: created year
|
||||
- `{{created_month}}`: created month
|
||||
- `{{created_month_name}}`: created month name
|
||||
- `{{created_month_name_short}}`: created month short name
|
||||
- `{{created_day}}`: created day
|
||||
- `{{created_time}}`: created time in HH:MM format
|
||||
- `{{doc_url}}`: URL to the document in the web UI. Requires the `PAPERLESS_URL` setting to be set.
|
||||
- `{{doc_id}}`: Document ID
|
||||
|
||||
##### Examples
|
||||
|
||||
@@ -676,26 +675,26 @@ Multiple fields may be attached to a document but the same field name cannot be
|
||||
|
||||
The following custom field types are supported:
|
||||
|
||||
- `Text`: any text
|
||||
- `Boolean`: true / false (check / unchecked) field
|
||||
- `Date`: date
|
||||
- `URL`: a valid url
|
||||
- `Integer`: integer number e.g. 12
|
||||
- `Number`: float number e.g. 12.3456
|
||||
- `Monetary`: [ISO 4217 currency code](https://en.wikipedia.org/wiki/ISO_4217#List_of_ISO_4217_currency_codes) and a number with exactly two decimals, e.g. USD12.30
|
||||
- `Document Link`: reference(s) to other document(s) displayed as links, automatically creates a symmetrical link in reverse
|
||||
- `Select`: a pre-defined list of strings from which the user can choose
|
||||
- `Text`: any text
|
||||
- `Boolean`: true / false (check / unchecked) field
|
||||
- `Date`: date
|
||||
- `URL`: a valid url
|
||||
- `Integer`: integer number e.g. 12
|
||||
- `Number`: float number e.g. 12.3456
|
||||
- `Monetary`: [ISO 4217 currency code](https://en.wikipedia.org/wiki/ISO_4217#List_of_ISO_4217_currency_codes) and a number with exactly two decimals, e.g. USD12.30
|
||||
- `Document Link`: reference(s) to other document(s) displayed as links, automatically creates a symmetrical link in reverse
|
||||
- `Select`: a pre-defined list of strings from which the user can choose
|
||||
|
||||
## PDF Actions
|
||||
|
||||
Paperless-ngx supports basic editing operations for PDFs (these operations currently cannot be performed on non-PDF files). When viewing an individual document you can
|
||||
open the 'PDF Editor' to use a simple UI for re-arranging, rotating, deleting pages and splitting documents.
|
||||
|
||||
- Merging documents: available when selecting multiple documents for 'bulk editing'.
|
||||
- Rotating documents: available when selecting multiple documents for 'bulk editing' and via the pdf editor on an individual document's details page.
|
||||
- Splitting documents: via the pdf editor on an individual document's details page.
|
||||
- Deleting pages: via the pdf editor on an individual document's details page.
|
||||
- Re-arranging pages: via the pdf editor on an individual document's details page.
|
||||
- Merging documents: available when selecting multiple documents for 'bulk editing'.
|
||||
- Rotating documents: available when selecting multiple documents for 'bulk editing' and via the pdf editor on an individual document's details page.
|
||||
- Splitting documents: via the pdf editor on an individual document's details page.
|
||||
- Deleting pages: via the pdf editor on an individual document's details page.
|
||||
- Re-arranging pages: via the pdf editor on an individual document's details page.
|
||||
|
||||
!!! important
|
||||
|
||||
@@ -773,18 +772,18 @@ the system.
|
||||
Here are a couple examples of tags and types that you could use in your
|
||||
collection.
|
||||
|
||||
- An `inbox` tag for newly added documents that you haven't manually
|
||||
edited yet.
|
||||
- A tag `car` for everything car related (repairs, registration,
|
||||
insurance, etc)
|
||||
- A tag `todo` for documents that you still need to do something with,
|
||||
such as reply, or perform some task online.
|
||||
- A tag `bank account x` for all bank statement related to that
|
||||
account.
|
||||
- A tag `mail` for anything that you added to paperless via its mail
|
||||
processing capabilities.
|
||||
- A tag `missing_metadata` when you still need to add some metadata to
|
||||
a document, but can't or don't want to do this right now.
|
||||
- An `inbox` tag for newly added documents that you haven't manually
|
||||
edited yet.
|
||||
- A tag `car` for everything car related (repairs, registration,
|
||||
insurance, etc)
|
||||
- A tag `todo` for documents that you still need to do something with,
|
||||
such as reply, or perform some task online.
|
||||
- A tag `bank account x` for all bank statement related to that
|
||||
account.
|
||||
- A tag `mail` for anything that you added to paperless via its mail
|
||||
processing capabilities.
|
||||
- A tag `missing_metadata` when you still need to add some metadata to
|
||||
a document, but can't or don't want to do this right now.
|
||||
|
||||
## Searching {#basic-usage_searching}
|
||||
|
||||
@@ -873,8 +872,8 @@ The following diagram shows how easy it is to manage your documents.
|
||||
|
||||
### Preparations in paperless
|
||||
|
||||
- Create an inbox tag that gets assigned to all new documents.
|
||||
- Create a TODO tag.
|
||||
- Create an inbox tag that gets assigned to all new documents.
|
||||
- Create a TODO tag.
|
||||
|
||||
### Processing of the physical documents
|
||||
|
||||
@@ -948,15 +947,15 @@ Some documents require attention and require you to act on the document.
|
||||
You may take two different approaches to handle these documents based on
|
||||
how regularly you intend to scan documents and use paperless.
|
||||
|
||||
- If you scan and process your documents in paperless regularly,
|
||||
assign a TODO tag to all scanned documents that you need to process.
|
||||
Create a saved view on the dashboard that shows all documents with
|
||||
this tag.
|
||||
- If you do not scan documents regularly and use paperless solely for
|
||||
archiving, create a physical todo box next to your physical inbox
|
||||
and put documents you need to process in the TODO box. When you
|
||||
performed the task associated with the document, move it to the
|
||||
inbox.
|
||||
- If you scan and process your documents in paperless regularly,
|
||||
assign a TODO tag to all scanned documents that you need to process.
|
||||
Create a saved view on the dashboard that shows all documents with
|
||||
this tag.
|
||||
- If you do not scan documents regularly and use paperless solely for
|
||||
archiving, create a physical todo box next to your physical inbox
|
||||
and put documents you need to process in the TODO box. When you
|
||||
performed the task associated with the document, move it to the
|
||||
inbox.
|
||||
|
||||
## Remote OCR
|
||||
|
||||
@@ -977,64 +976,63 @@ or page limitations (e.g. with a free tier).
|
||||
|
||||
Paperless-ngx consists of the following components:
|
||||
|
||||
- **The webserver:** This serves the administration pages, the API,
|
||||
and the new frontend. This is the main tool you'll be using to interact
|
||||
with paperless. You may start the webserver directly with
|
||||
- **The webserver:** This serves the administration pages, the API,
|
||||
and the new frontend. This is the main tool you'll be using to interact
|
||||
with paperless. You may start the webserver directly with
|
||||
|
||||
```shell-session
|
||||
cd /path/to/paperless/src/
|
||||
granian --interface asginl --ws "paperless.asgi:application"
|
||||
```
|
||||
```shell-session
|
||||
cd /path/to/paperless/src/
|
||||
granian --interface asginl --ws "paperless.asgi:application"
|
||||
```
|
||||
|
||||
or by any other means such as Apache `mod_wsgi`.
|
||||
or by any other means such as Apache `mod_wsgi`.
|
||||
|
||||
- **The consumer:** This is what watches your consumption folder for
|
||||
documents. However, the consumer itself does not really consume your
|
||||
documents. Now it notifies a task processor that a new file is ready
|
||||
for consumption. I suppose it should be named differently. This was
|
||||
also used to check your emails, but that's now done elsewhere as
|
||||
well.
|
||||
- **The consumer:** This is what watches your consumption folder for
|
||||
documents. However, the consumer itself does not really consume your
|
||||
documents. Now it notifies a task processor that a new file is ready
|
||||
for consumption. I suppose it should be named differently. This was
|
||||
also used to check your emails, but that's now done elsewhere as
|
||||
well.
|
||||
|
||||
Start the consumer with the management command `document_consumer`:
|
||||
Start the consumer with the management command `document_consumer`:
|
||||
|
||||
```shell-session
|
||||
cd /path/to/paperless/src/
|
||||
python3 manage.py document_consumer
|
||||
```
|
||||
```shell-session
|
||||
cd /path/to/paperless/src/
|
||||
python3 manage.py document_consumer
|
||||
```
|
||||
|
||||
- **The task processor:** Paperless relies on [Celery - Distributed
|
||||
Task Queue](https://docs.celeryq.dev/en/stable/index.html) for doing
|
||||
most of the heavy lifting. This is a task queue that accepts tasks
|
||||
from multiple sources and processes these in parallel. It also comes
|
||||
with a scheduler that executes certain commands periodically.
|
||||
- **The task processor:** Paperless relies on [Celery - Distributed
|
||||
Task Queue](https://docs.celeryq.dev/en/stable/index.html) for doing
|
||||
most of the heavy lifting. This is a task queue that accepts tasks
|
||||
from multiple sources and processes these in parallel. It also comes
|
||||
with a scheduler that executes certain commands periodically.
|
||||
|
||||
This task processor is responsible for:
|
||||
This task processor is responsible for:
|
||||
- Consuming documents. When the consumer finds new documents, it
|
||||
notifies the task processor to start a consumption task.
|
||||
- The task processor also performs the consumption of any
|
||||
documents you upload through the web interface.
|
||||
- Consuming emails. It periodically checks your configured
|
||||
accounts for new emails and notifies the task processor to
|
||||
consume the attachment of an email.
|
||||
- Maintaining the search index and the automatic matching
|
||||
algorithm. These are things that paperless needs to do from time
|
||||
to time in order to operate properly.
|
||||
|
||||
- Consuming documents. When the consumer finds new documents, it
|
||||
notifies the task processor to start a consumption task.
|
||||
- The task processor also performs the consumption of any
|
||||
documents you upload through the web interface.
|
||||
- Consuming emails. It periodically checks your configured
|
||||
accounts for new emails and notifies the task processor to
|
||||
consume the attachment of an email.
|
||||
- Maintaining the search index and the automatic matching
|
||||
algorithm. These are things that paperless needs to do from time
|
||||
to time in order to operate properly.
|
||||
This allows paperless to process multiple documents from your
|
||||
consumption folder in parallel! On a modern multi core system, this
|
||||
makes the consumption process with full OCR blazingly fast.
|
||||
|
||||
This allows paperless to process multiple documents from your
|
||||
consumption folder in parallel! On a modern multi core system, this
|
||||
makes the consumption process with full OCR blazingly fast.
|
||||
The task processor comes with a built-in admin interface that you
|
||||
can use to check whenever any of the tasks fail and inspect the
|
||||
errors (i.e., wrong email credentials, errors during consuming a
|
||||
specific file, etc).
|
||||
|
||||
The task processor comes with a built-in admin interface that you
|
||||
can use to check whenever any of the tasks fail and inspect the
|
||||
errors (i.e., wrong email credentials, errors during consuming a
|
||||
specific file, etc).
|
||||
- A [redis](https://redis.io/) message broker: This is a really
|
||||
lightweight service that is responsible for getting the tasks from
|
||||
the webserver and the consumer to the task scheduler. These run in a
|
||||
different process (maybe even on different machines!), and
|
||||
therefore, this is necessary.
|
||||
|
||||
- A [redis](https://redis.io/) message broker: This is a really
|
||||
lightweight service that is responsible for getting the tasks from
|
||||
the webserver and the consumer to the task scheduler. These run in a
|
||||
different process (maybe even on different machines!), and
|
||||
therefore, this is necessary.
|
||||
|
||||
- Optional: A database server. Paperless supports PostgreSQL, MariaDB
|
||||
and SQLite for storing its data.
|
||||
- Optional: A database server. Paperless supports PostgreSQL, MariaDB
|
||||
and SQLite for storing its data.
|
||||
|
||||
@@ -42,10 +42,10 @@ dependencies = [
|
||||
"djangorestframework~=3.16",
|
||||
"djangorestframework-guardian~=0.4.0",
|
||||
"drf-spectacular~=0.28",
|
||||
"drf-spectacular-sidecar~=2026.1.1",
|
||||
"drf-spectacular-sidecar~=2026.3.1",
|
||||
"drf-writable-nested~=0.7.1",
|
||||
"faiss-cpu>=1.10",
|
||||
"filelock~=3.24.3",
|
||||
"filelock~=3.25.2",
|
||||
"flower~=2.0.1",
|
||||
"gotenberg-client~=0.13.1",
|
||||
"httpx-oauth~=0.16",
|
||||
@@ -72,7 +72,7 @@ dependencies = [
|
||||
"rapidfuzz~=3.14.0",
|
||||
"redis[hiredis]~=5.2.1",
|
||||
"regex>=2025.9.18",
|
||||
"scikit-learn~=1.7.0",
|
||||
"scikit-learn~=1.8.0",
|
||||
"sentence-transformers>=4.1",
|
||||
"setproctitle~=1.3.4",
|
||||
"tika-client~=0.10.0",
|
||||
@@ -111,7 +111,7 @@ docs = [
|
||||
testing = [
|
||||
"daphne",
|
||||
"factory-boy~=3.3.1",
|
||||
"faker~=40.5.1",
|
||||
"faker~=40.8.0",
|
||||
"imagehash",
|
||||
"pytest~=9.0.0",
|
||||
"pytest-cov~=7.0.0",
|
||||
|
||||
@@ -31,8 +31,8 @@ export enum EditDialogMode {
|
||||
|
||||
@Directive()
|
||||
export abstract class EditDialogComponent<
|
||||
T extends ObjectWithPermissions | ObjectWithId,
|
||||
>
|
||||
T extends ObjectWithPermissions | ObjectWithId,
|
||||
>
|
||||
extends LoadingComponentWithPermissions
|
||||
implements OnInit
|
||||
{
|
||||
|
||||
@@ -1644,9 +1644,9 @@ describe('DocumentDetailComponent', () => {
|
||||
expect(
|
||||
fixture.debugElement.query(By.css('.preview-sticky img'))
|
||||
).not.toBeUndefined()
|
||||
;(component.document.mime_type =
|
||||
;((component.document.mime_type =
|
||||
'application/vnd.openxmlformats-officedocument.wordprocessingml.document'),
|
||||
fixture.detectChanges()
|
||||
fixture.detectChanges())
|
||||
expect(component.archiveContentRenderType).toEqual(
|
||||
component.ContentRenderType.Other
|
||||
)
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import { DatePipe } from '@angular/common'
|
||||
import { provideHttpClient, withInterceptorsFromDi } from '@angular/common/http'
|
||||
import {
|
||||
HttpTestingController,
|
||||
@@ -138,6 +139,7 @@ describe('BulkEditorComponent', () => {
|
||||
},
|
||||
},
|
||||
FilterPipe,
|
||||
DatePipe,
|
||||
SettingsService,
|
||||
{
|
||||
provide: UserService,
|
||||
|
||||
@@ -62,7 +62,7 @@ export function hslToRgb(h, s, l) {
|
||||
* @return Array The HSL representation
|
||||
*/
|
||||
export function rgbToHsl(r, g, b) {
|
||||
;(r /= 255), (g /= 255), (b /= 255)
|
||||
;((r /= 255), (g /= 255), (b /= 255))
|
||||
var max = Math.max(r, g, b),
|
||||
min = Math.min(r, g, b)
|
||||
var h,
|
||||
|
||||
@@ -5,7 +5,7 @@
|
||||
export const environment = {
|
||||
production: false,
|
||||
apiBaseUrl: 'http://localhost:8000/api/',
|
||||
apiVersion: '9',
|
||||
apiVersion: '10',
|
||||
appTitle: 'Paperless-ngx',
|
||||
tag: 'dev',
|
||||
version: 'DEVELOPMENT',
|
||||
|
||||
@@ -9,6 +9,7 @@ from pathlib import Path
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Callable
|
||||
from collections.abc import Iterator
|
||||
from datetime import datetime
|
||||
|
||||
@@ -191,7 +192,12 @@ class DocumentClassifier:
|
||||
|
||||
target_file_temp.rename(target_file)
|
||||
|
||||
def train(self) -> bool:
|
||||
def train(
|
||||
self,
|
||||
status_callback: Callable[[str], None] | None = None,
|
||||
) -> bool:
|
||||
notify = status_callback if status_callback is not None else lambda _: None
|
||||
|
||||
# Get non-inbox documents
|
||||
docs_queryset = (
|
||||
Document.objects.exclude(
|
||||
@@ -213,6 +219,7 @@ class DocumentClassifier:
|
||||
|
||||
# Step 1: Extract and preprocess training data from the database.
|
||||
logger.debug("Gathering data from database...")
|
||||
notify(f"Gathering data from {docs_queryset.count()} document(s)...")
|
||||
hasher = sha256()
|
||||
for doc in docs_queryset:
|
||||
y = -1
|
||||
@@ -290,6 +297,7 @@ class DocumentClassifier:
|
||||
|
||||
# Step 2: vectorize data
|
||||
logger.debug("Vectorizing data...")
|
||||
notify("Vectorizing document content...")
|
||||
|
||||
def content_generator() -> Iterator[str]:
|
||||
"""
|
||||
@@ -316,6 +324,7 @@ class DocumentClassifier:
|
||||
# Step 3: train the classifiers
|
||||
if num_tags > 0:
|
||||
logger.debug("Training tags classifier...")
|
||||
notify(f"Training tags classifier ({num_tags} tag(s))...")
|
||||
|
||||
if num_tags == 1:
|
||||
# Special case where only one tag has auto:
|
||||
@@ -339,6 +348,9 @@ class DocumentClassifier:
|
||||
|
||||
if num_correspondents > 0:
|
||||
logger.debug("Training correspondent classifier...")
|
||||
notify(
|
||||
f"Training correspondent classifier ({num_correspondents} correspondent(s))...",
|
||||
)
|
||||
self.correspondent_classifier = MLPClassifier(tol=0.01)
|
||||
self.correspondent_classifier.fit(data_vectorized, labels_correspondent)
|
||||
else:
|
||||
@@ -349,6 +361,9 @@ class DocumentClassifier:
|
||||
|
||||
if num_document_types > 0:
|
||||
logger.debug("Training document type classifier...")
|
||||
notify(
|
||||
f"Training document type classifier ({num_document_types} type(s))...",
|
||||
)
|
||||
self.document_type_classifier = MLPClassifier(tol=0.01)
|
||||
self.document_type_classifier.fit(data_vectorized, labels_document_type)
|
||||
else:
|
||||
@@ -361,6 +376,7 @@ class DocumentClassifier:
|
||||
logger.debug(
|
||||
"Training storage paths classifier...",
|
||||
)
|
||||
notify(f"Training storage path classifier ({num_storage_paths} path(s))...")
|
||||
self.storage_path_classifier = MLPClassifier(tol=0.01)
|
||||
self.storage_path_classifier.fit(
|
||||
data_vectorized,
|
||||
|
||||
@@ -1,13 +1,29 @@
|
||||
from django.core.management.base import BaseCommand
|
||||
from __future__ import annotations
|
||||
|
||||
import time
|
||||
|
||||
from documents.management.commands.base import PaperlessCommand
|
||||
from documents.tasks import train_classifier
|
||||
|
||||
|
||||
class Command(BaseCommand):
|
||||
class Command(PaperlessCommand):
|
||||
help = (
|
||||
"Trains the classifier on your data and saves the resulting models to a "
|
||||
"file. The document consumer will then automatically use this new model."
|
||||
)
|
||||
supports_progress_bar = False
|
||||
supports_multiprocessing = False
|
||||
|
||||
def handle(self, *args, **options):
|
||||
train_classifier(scheduled=False)
|
||||
def handle(self, *args, **options) -> None:
|
||||
start = time.monotonic()
|
||||
|
||||
with self.buffered_logging("paperless.tasks"):
|
||||
train_classifier(
|
||||
scheduled=False,
|
||||
status_callback=lambda msg: self.console.print(f" {msg}"),
|
||||
)
|
||||
|
||||
elapsed = time.monotonic() - start
|
||||
self.console.print(
|
||||
f"[green]✓[/green] Classifier training complete ({elapsed:.1f}s)",
|
||||
)
|
||||
|
||||
@@ -169,7 +169,7 @@ def match_storage_paths(document: Document, classifier: DocumentClassifier, user
|
||||
def matches(matching_model: MatchingModel, document: Document):
|
||||
search_flags = 0
|
||||
|
||||
document_content = document.content
|
||||
document_content = document.get_effective_content() or ""
|
||||
|
||||
# Check that match is not empty
|
||||
if not matching_model.match.strip():
|
||||
|
||||
@@ -5,7 +5,7 @@ from django.db import migrations
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0003_workflowaction_order"),
|
||||
("documents", "0002_squashed"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
@@ -1,18 +0,0 @@
|
||||
# Generated by Django 5.2.9 on 2026-01-20 20:06
|
||||
|
||||
from django.db import migrations
|
||||
from django.db import models
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0002_squashed"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.AddField(
|
||||
model_name="workflowaction",
|
||||
name="order",
|
||||
field=models.PositiveIntegerField(default=0, verbose_name="order"),
|
||||
),
|
||||
]
|
||||
@@ -6,7 +6,7 @@ from django.db import models
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0004_remove_document_storage_type"),
|
||||
("documents", "0003_remove_document_storage_type"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
@@ -6,7 +6,7 @@ from django.db import models
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0005_workflowtrigger_filter_has_any_correspondents_and_more"),
|
||||
("documents", "0004_workflowtrigger_filter_has_any_correspondents_and_more"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
@@ -7,7 +7,7 @@ from django.db import models
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0006_alter_document_checksum_unique"),
|
||||
("documents", "0005_alter_document_checksum_unique"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
@@ -46,7 +46,7 @@ def revoke_share_link_bundle_permissions(apps, schema_editor):
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
migrations.swappable_dependency(settings.AUTH_USER_MODEL),
|
||||
("documents", "0007_document_content_length"),
|
||||
("documents", "0006_document_content_length"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
@@ -6,7 +6,7 @@ from django.db import models
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0008_sharelinkbundle"),
|
||||
("documents", "0007_sharelinkbundle"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
@@ -7,7 +7,7 @@ from django.db import models
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0009_workflowaction_passwords_alter_workflowaction_type"),
|
||||
("documents", "0008_workflowaction_passwords_alter_workflowaction_type"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
@@ -7,7 +7,7 @@ from django.db import models
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0010_alter_document_content_length"),
|
||||
("documents", "0009_alter_document_content_length"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
@@ -6,7 +6,7 @@ from django.db import models
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0011_optimize_integer_field_sizes"),
|
||||
("documents", "0010_optimize_integer_field_sizes"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
@@ -7,7 +7,7 @@ from django.db import models
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0012_alter_workflowaction_type"),
|
||||
("documents", "0011_alter_workflowaction_type"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
@@ -6,7 +6,7 @@ from django.db import models
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0013_document_root_document"),
|
||||
("documents", "0012_document_root_document"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
@@ -124,7 +124,7 @@ def _restore_visibility_fields(apps, schema_editor):
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0014_alter_paperlesstask_task_name"),
|
||||
("documents", "0013_alter_paperlesstask_task_name"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
@@ -7,7 +7,7 @@ from django.db import models
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("documents", "0015_savedview_visibility_to_ui_settings"),
|
||||
("documents", "0014_savedview_visibility_to_ui_settings"),
|
||||
migrations.swappable_dependency(settings.AUTH_USER_MODEL),
|
||||
]
|
||||
|
||||
@@ -361,6 +361,42 @@ class Document(SoftDeleteModel, ModelWithOwner): # type: ignore[django-manager-
|
||||
res += f" {self.title}"
|
||||
return res
|
||||
|
||||
def get_effective_content(self) -> str | None:
|
||||
"""
|
||||
Returns the effective content for the document.
|
||||
|
||||
For root documents, this is the latest version's content when available.
|
||||
For version documents, this is always the document's own content.
|
||||
If the queryset already annotated ``effective_content``, that value is used.
|
||||
"""
|
||||
if hasattr(self, "effective_content"):
|
||||
return getattr(self, "effective_content")
|
||||
|
||||
if self.root_document_id is not None or self.pk is None:
|
||||
return self.content
|
||||
|
||||
prefetched_cache = getattr(self, "_prefetched_objects_cache", None)
|
||||
prefetched_versions = (
|
||||
prefetched_cache.get("versions")
|
||||
if isinstance(prefetched_cache, dict)
|
||||
else None
|
||||
)
|
||||
if prefetched_versions:
|
||||
latest_prefetched = max(prefetched_versions, key=lambda doc: doc.id)
|
||||
return latest_prefetched.content
|
||||
|
||||
latest_version_content = (
|
||||
Document.objects.filter(root_document=self)
|
||||
.order_by("-id")
|
||||
.values_list("content", flat=True)
|
||||
.first()
|
||||
)
|
||||
return (
|
||||
latest_version_content
|
||||
if latest_version_content is not None
|
||||
else self.content
|
||||
)
|
||||
|
||||
@property
|
||||
def suggestion_content(self):
|
||||
"""
|
||||
@@ -373,15 +409,21 @@ class Document(SoftDeleteModel, ModelWithOwner): # type: ignore[django-manager-
|
||||
This improves processing speed for large documents while keeping
|
||||
enough context for accurate suggestions.
|
||||
"""
|
||||
if not self.content or len(self.content) <= 1200000:
|
||||
return self.content
|
||||
effective_content = self.get_effective_content()
|
||||
if not effective_content or len(effective_content) <= 1200000:
|
||||
return effective_content
|
||||
else:
|
||||
# Use 80% from the start and 20% from the end
|
||||
# to preserve both opening and closing context.
|
||||
head_len = 800000
|
||||
tail_len = 200000
|
||||
|
||||
return " ".join((self.content[:head_len], self.content[-tail_len:]))
|
||||
return " ".join(
|
||||
(
|
||||
effective_content[:head_len],
|
||||
effective_content[-tail_len:],
|
||||
),
|
||||
)
|
||||
|
||||
@property
|
||||
def source_path(self) -> Path:
|
||||
|
||||
@@ -100,7 +100,11 @@ def index_reindex(*, iter_wrapper: IterWrapper[Document] = _identity) -> None:
|
||||
|
||||
|
||||
@shared_task
|
||||
def train_classifier(*, scheduled=True) -> None:
|
||||
def train_classifier(
|
||||
*,
|
||||
scheduled=True,
|
||||
status_callback: Callable[[str], None] | None = None,
|
||||
) -> None:
|
||||
task = PaperlessTask.objects.create(
|
||||
type=PaperlessTask.TaskType.SCHEDULED_TASK
|
||||
if scheduled
|
||||
@@ -136,7 +140,7 @@ def train_classifier(*, scheduled=True) -> None:
|
||||
classifier = DocumentClassifier()
|
||||
|
||||
try:
|
||||
if classifier.train():
|
||||
if classifier.train(status_callback=status_callback):
|
||||
logger.info(
|
||||
f"Saving updated classifier model to {settings.MODEL_FILE}...",
|
||||
)
|
||||
|
||||
@@ -156,6 +156,46 @@ class TestDocument(TestCase):
|
||||
)
|
||||
self.assertEqual(doc.get_public_filename(), "2020-12-25 test")
|
||||
|
||||
def test_suggestion_content_uses_latest_version_content_for_root_documents(
|
||||
self,
|
||||
) -> None:
|
||||
root = Document.objects.create(
|
||||
title="root",
|
||||
checksum="root",
|
||||
mime_type="application/pdf",
|
||||
content="outdated root content",
|
||||
)
|
||||
version = Document.objects.create(
|
||||
title="v1",
|
||||
checksum="v1",
|
||||
mime_type="application/pdf",
|
||||
root_document=root,
|
||||
content="latest version content",
|
||||
)
|
||||
|
||||
self.assertEqual(root.suggestion_content, version.content)
|
||||
|
||||
def test_content_length_is_per_document_row_for_versions(self) -> None:
|
||||
root = Document.objects.create(
|
||||
title="root",
|
||||
checksum="root",
|
||||
mime_type="application/pdf",
|
||||
content="abc",
|
||||
)
|
||||
version = Document.objects.create(
|
||||
title="v1",
|
||||
checksum="v1",
|
||||
mime_type="application/pdf",
|
||||
root_document=root,
|
||||
content="abcdefgh",
|
||||
)
|
||||
|
||||
root.refresh_from_db()
|
||||
version.refresh_from_db()
|
||||
|
||||
self.assertEqual(root.content_length, 3)
|
||||
self.assertEqual(version.content_length, 8)
|
||||
|
||||
|
||||
def test_suggestion_content() -> None:
|
||||
"""
|
||||
|
||||
@@ -1,7 +1,10 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import filecmp
|
||||
import shutil
|
||||
from io import StringIO
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING
|
||||
from unittest import mock
|
||||
|
||||
import pytest
|
||||
@@ -11,6 +14,9 @@ from django.core.management import call_command
|
||||
from django.test import TestCase
|
||||
from django.test import override_settings
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from pytest_mock import MockerFixture
|
||||
|
||||
from documents.file_handling import generate_filename
|
||||
from documents.models import Document
|
||||
from documents.tasks import update_document_content_maybe_archive_file
|
||||
@@ -135,14 +141,32 @@ class TestRenamer(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
|
||||
|
||||
|
||||
@pytest.mark.management
|
||||
class TestCreateClassifier(TestCase):
|
||||
@mock.patch(
|
||||
"documents.management.commands.document_create_classifier.train_classifier",
|
||||
)
|
||||
def test_create_classifier(self, m) -> None:
|
||||
call_command("document_create_classifier")
|
||||
class TestCreateClassifier:
|
||||
def test_create_classifier(self, mocker: MockerFixture) -> None:
|
||||
m = mocker.patch(
|
||||
"documents.management.commands.document_create_classifier.train_classifier",
|
||||
)
|
||||
|
||||
m.assert_called_once()
|
||||
call_command("document_create_classifier", "--skip-checks")
|
||||
|
||||
m.assert_called_once_with(scheduled=False, status_callback=mocker.ANY)
|
||||
assert callable(m.call_args.kwargs["status_callback"])
|
||||
|
||||
def test_create_classifier_callback_output(self, mocker: MockerFixture) -> None:
|
||||
"""Callback passed to train_classifier writes each phase message to the console."""
|
||||
m = mocker.patch(
|
||||
"documents.management.commands.document_create_classifier.train_classifier",
|
||||
)
|
||||
|
||||
def invoke_callback(**kwargs):
|
||||
kwargs["status_callback"]("Vectorizing document content...")
|
||||
|
||||
m.side_effect = invoke_callback
|
||||
|
||||
stdout = StringIO()
|
||||
call_command("document_create_classifier", "--skip-checks", stdout=stdout)
|
||||
|
||||
assert "Vectorizing document content..." in stdout.getvalue()
|
||||
|
||||
|
||||
@pytest.mark.management
|
||||
|
||||
@@ -48,6 +48,52 @@ class _TestMatchingBase(TestCase):
|
||||
|
||||
|
||||
class TestMatching(_TestMatchingBase):
|
||||
def test_matches_uses_latest_version_content_for_root_documents(self) -> None:
|
||||
root = Document.objects.create(
|
||||
title="root",
|
||||
checksum="root",
|
||||
mime_type="application/pdf",
|
||||
content="root content without token",
|
||||
)
|
||||
Document.objects.create(
|
||||
title="v1",
|
||||
checksum="v1",
|
||||
mime_type="application/pdf",
|
||||
root_document=root,
|
||||
content="latest version contains keyword",
|
||||
)
|
||||
tag = Tag.objects.create(
|
||||
name="tag",
|
||||
match="keyword",
|
||||
matching_algorithm=Tag.MATCH_ANY,
|
||||
)
|
||||
|
||||
self.assertTrue(matching.matches(tag, root))
|
||||
|
||||
def test_matches_does_not_fall_back_to_root_content_when_version_exists(
|
||||
self,
|
||||
) -> None:
|
||||
root = Document.objects.create(
|
||||
title="root",
|
||||
checksum="root",
|
||||
mime_type="application/pdf",
|
||||
content="root contains keyword",
|
||||
)
|
||||
Document.objects.create(
|
||||
title="v1",
|
||||
checksum="v1",
|
||||
mime_type="application/pdf",
|
||||
root_document=root,
|
||||
content="latest version without token",
|
||||
)
|
||||
tag = Tag.objects.create(
|
||||
name="tag",
|
||||
match="keyword",
|
||||
matching_algorithm=Tag.MATCH_ANY,
|
||||
)
|
||||
|
||||
self.assertFalse(matching.matches(tag, root))
|
||||
|
||||
def test_match_none(self) -> None:
|
||||
self._test_matching(
|
||||
"",
|
||||
|
||||
@@ -6,8 +6,8 @@ SIDEBAR_VIEWS_VISIBLE_IDS_KEY = "sidebar_views_visible_ids"
|
||||
|
||||
|
||||
class TestMigrateSavedViewVisibilityToUiSettings(TestMigrations):
|
||||
migrate_from = "0013_document_root_document"
|
||||
migrate_to = "0015_savedview_visibility_to_ui_settings"
|
||||
migrate_from = "0013_alter_paperlesstask_task_name"
|
||||
migrate_to = "0014_savedview_visibility_to_ui_settings"
|
||||
|
||||
def setUpBeforeMigration(self, apps) -> None:
|
||||
User = apps.get_model("auth", "User")
|
||||
@@ -132,8 +132,8 @@ class TestMigrateSavedViewVisibilityToUiSettings(TestMigrations):
|
||||
|
||||
|
||||
class TestReverseMigrateSavedViewVisibilityFromUiSettings(TestMigrations):
|
||||
migrate_from = "0015_savedview_visibility_to_ui_settings"
|
||||
migrate_to = "0014_alter_paperlesstask_task_name"
|
||||
migrate_from = "0014_savedview_visibility_to_ui_settings"
|
||||
migrate_to = "0013_alter_paperlesstask_task_name"
|
||||
|
||||
def setUpBeforeMigration(self, apps) -> None:
|
||||
User = apps.get_model("auth", "User")
|
||||
|
||||
@@ -2,8 +2,8 @@ from documents.tests.utils import TestMigrations
|
||||
|
||||
|
||||
class TestMigrateShareLinkBundlePermissions(TestMigrations):
|
||||
migrate_from = "0007_document_content_length"
|
||||
migrate_to = "0008_sharelinkbundle"
|
||||
migrate_from = "0006_document_content_length"
|
||||
migrate_to = "0007_sharelinkbundle"
|
||||
|
||||
def setUpBeforeMigration(self, apps) -> None:
|
||||
User = apps.get_model("auth", "User")
|
||||
@@ -24,8 +24,8 @@ class TestMigrateShareLinkBundlePermissions(TestMigrations):
|
||||
|
||||
|
||||
class TestReverseMigrateShareLinkBundlePermissions(TestMigrations):
|
||||
migrate_from = "0008_sharelinkbundle"
|
||||
migrate_to = "0007_document_content_length"
|
||||
migrate_from = "0007_sharelinkbundle"
|
||||
migrate_to = "0006_document_content_length"
|
||||
|
||||
def setUpBeforeMigration(self, apps) -> None:
|
||||
User = apps.get_model("auth", "User")
|
||||
|
||||
@@ -1528,13 +1528,17 @@ class DocumentViewSet(
|
||||
|
||||
return Response(sorted(entries, key=lambda x: x["timestamp"], reverse=True))
|
||||
|
||||
@extend_schema(
|
||||
operation_id="documents_email_document",
|
||||
deprecated=True,
|
||||
)
|
||||
@action(
|
||||
methods=["post"],
|
||||
detail=True,
|
||||
url_path="email",
|
||||
permission_classes=[IsAuthenticated, ViewDocumentsPermissions],
|
||||
)
|
||||
# TODO: deprecated as of 2.19, remove in future release
|
||||
# TODO: deprecated, remove with drop of support for API v9
|
||||
def email_document(self, request, pk=None):
|
||||
request_data = request.data.copy()
|
||||
request_data.setlist("documents", [pk])
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -7,6 +7,7 @@ from pathlib import Path
|
||||
|
||||
from django.conf import settings
|
||||
from django.core.checks import Error
|
||||
from django.core.checks import Tags
|
||||
from django.core.checks import Warning
|
||||
from django.core.checks import register
|
||||
from django.db import connections
|
||||
@@ -204,15 +205,16 @@ def audit_log_check(app_configs, **kwargs):
|
||||
return result
|
||||
|
||||
|
||||
@register()
|
||||
@register(Tags.compatibility)
|
||||
def check_v3_minimum_upgrade_version(
|
||||
app_configs: object,
|
||||
**kwargs: object,
|
||||
) -> list[Error]:
|
||||
"""Enforce that upgrades to v3 must start from v2.20.9.
|
||||
"""
|
||||
Enforce that upgrades to v3 must start from v2.20.10.
|
||||
|
||||
v3 squashes all prior migrations into 0001_squashed and 0002_squashed.
|
||||
If a user skips v2.20.9, the data migration in 1075_workflowaction_order
|
||||
If a user skips v2.20.10, the data migration in 1075_workflowaction_order
|
||||
never runs and the squash may apply schema changes against an incomplete
|
||||
database state.
|
||||
"""
|
||||
@@ -239,7 +241,7 @@ def check_v3_minimum_upgrade_version(
|
||||
if {"0001_squashed", "0002_squashed"} & applied:
|
||||
return []
|
||||
|
||||
# On v2.20.9 exactly — squash will pick up cleanly from here
|
||||
# On v2.20.10 exactly — squash will pick up cleanly from here
|
||||
if "1075_workflowaction_order" in applied:
|
||||
return []
|
||||
|
||||
@@ -250,8 +252,8 @@ def check_v3_minimum_upgrade_version(
|
||||
Error(
|
||||
"Cannot upgrade to Paperless-ngx v3 from this version.",
|
||||
hint=(
|
||||
"Upgrading to v3 can only be performed from v2.20.9."
|
||||
"Please upgrade to v2.20.9, run migrations, then upgrade to v3."
|
||||
"Upgrading to v3 can only be performed from v2.20.10."
|
||||
"Please upgrade to v2.20.10, run migrations, then upgrade to v3."
|
||||
"See https://docs.paperless-ngx.com/setup/#upgrading for details."
|
||||
),
|
||||
id="paperless.E002",
|
||||
|
||||
@@ -209,7 +209,6 @@ def parse_db_settings(data_dir: Path) -> dict[str, dict[str, Any]]:
|
||||
engine = get_choice_from_env(
|
||||
"PAPERLESS_DBENGINE",
|
||||
{"sqlite", "postgresql", "mariadb"},
|
||||
default="sqlite",
|
||||
)
|
||||
except ValueError:
|
||||
# MariaDB users already had to set PAPERLESS_DBENGINE, so it was picked up above
|
||||
|
||||
@@ -581,11 +581,11 @@ class TestV3MinimumUpgradeVersionCheck:
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- DB is on an old v2 version (pre-v2.20.9)
|
||||
- DB is on an old v2 version (pre-v2.20.10)
|
||||
WHEN:
|
||||
- The v3 upgrade check runs
|
||||
THEN:
|
||||
- The error hint explicitly references v2.20.9 so users know what to do
|
||||
- The error hint explicitly references v2.20.10 so users know what to do
|
||||
"""
|
||||
mocker.patch.dict(
|
||||
"paperless.checks.connections",
|
||||
@@ -593,7 +593,7 @@ class TestV3MinimumUpgradeVersionCheck:
|
||||
)
|
||||
result = check_v3_minimum_upgrade_version(None)
|
||||
assert len(result) == 1
|
||||
assert "v2.20.9" in result[0].hint
|
||||
assert "v2.20.10" in result[0].hint
|
||||
|
||||
def test_db_error_is_swallowed(self, mocker: MockerFixture) -> None:
|
||||
"""
|
||||
|
||||
90
uv.lock
generated
90
uv.lock
generated
@@ -1172,14 +1172,14 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "drf-spectacular-sidecar"
|
||||
version = "2026.1.1"
|
||||
version = "2026.3.1"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "django", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/1e/81/c7b0e3ccbd5a039c4f4fcfecf88391a666ca1406a953886e2f39295b1c90/drf_spectacular_sidecar-2026.1.1.tar.gz", hash = "sha256:6f7c173a8ddbbbdafc7a27e028614b65f07a89ca90f996a432d57460463b56be", size = 2468060, upload-time = "2026-01-01T11:27:12.682Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/aa/42/2f8c1b2846399d47094ec414bc0d6a7cce7ba95fd6545a97285eee89f7f1/drf_spectacular_sidecar-2026.3.1.tar.gz", hash = "sha256:5b7fedad66e3851f2f442480792c08115d79217959d01645b93d3d2258938be1", size = 2461501, upload-time = "2026-03-01T11:31:19.708Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/db/96/38725edda526f3e9e597f531beeec94b0ef433d9494f06a13b7636eecb6e/drf_spectacular_sidecar-2026.1.1-py3-none-any.whl", hash = "sha256:af8df62f1b594ec280351336d837eaf2402ab25a6bc2a1fad7aee9935821070f", size = 2489520, upload-time = "2026-01-01T11:27:11.056Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c1/28/2d5e64d101ebc5180674fcaf7b5a35e398e2f8d9688b2e8d52b0e1394e7d/drf_spectacular_sidecar-2026.3.1-py3-none-any.whl", hash = "sha256:864edb83e022e13e3941c325c3cc0c954c843fa2e1d0bc95e81887664b2d3dad", size = 2481725, upload-time = "2026-03-01T11:31:18.469Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -1230,11 +1230,11 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "faker"
|
||||
version = "40.5.1"
|
||||
version = "40.8.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/03/2a/96fff3edcb10f6505143448a4b91535f77b74865cec45be52690ee280443/faker-40.5.1.tar.gz", hash = "sha256:70222361cd82aa10cb86066d1a4e8f47f2bcdc919615c412045a69c4e6da0cd3", size = 1952684, upload-time = "2026-02-23T21:34:38.362Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/70/03/14428edc541467c460d363f6e94bee9acc271f3e62470630fc9a647d0cf2/faker-40.8.0.tar.gz", hash = "sha256:936a3c9be6c004433f20aa4d99095df5dec82b8c7ad07459756041f8c1728875", size = 1956493, upload-time = "2026-03-04T16:18:48.161Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/4d/a9/1eed4db92d0aec2f9bfdf1faae0ab0418b5e121dda5701f118a7a4f0cd6a/faker-40.5.1-py3-none-any.whl", hash = "sha256:c69640c1e13bad49b4bcebcbf1b52f9f1a872b6ea186c248ada34d798f1661bf", size = 1987053, upload-time = "2026-02-23T21:34:36.418Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/4c/3b/c6348f1e285e75b069085b18110a4e6325b763a5d35d5e204356fc7c20b3/faker-40.8.0-py3-none-any.whl", hash = "sha256:eb21bdba18f7a8375382eb94fb436fce07046893dc94cb20817d28deb0c3d579", size = 1989124, upload-time = "2026-03-04T16:18:46.45Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -1251,11 +1251,11 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "filelock"
|
||||
version = "3.24.3"
|
||||
version = "3.25.2"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/73/92/a8e2479937ff39185d20dd6a851c1a63e55849e447a55e798cc2e1f49c65/filelock-3.24.3.tar.gz", hash = "sha256:011a5644dc937c22699943ebbfc46e969cdde3e171470a6e40b9533e5a72affa", size = 37935, upload-time = "2026-02-19T00:48:20.543Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/94/b8/00651a0f559862f3bb7d6f7477b192afe3f583cc5e26403b44e59a55ab34/filelock-3.25.2.tar.gz", hash = "sha256:b64ece2b38f4ca29dd3e810287aa8c48182bbecd1ae6e9ae126c9b35f1382694", size = 40480, upload-time = "2026-03-11T20:45:38.487Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/9c/0f/5d0c71a1aefeb08efff26272149e07ab922b64f46c63363756224bd6872e/filelock-3.24.3-py3-none-any.whl", hash = "sha256:426e9a4660391f7f8a810d71b0555bce9008b0a1cc342ab1f6947d37639e002d", size = 24331, upload-time = "2026-02-19T00:48:18.465Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a4/a5/842ae8f0c08b61d6484b52f99a03510a3a72d23141942d216ebe81fefbce/filelock-3.25.2-py3-none-any.whl", hash = "sha256:ca8afb0da15f229774c9ad1b455ed96e85a81373065fb10446672f64444ddf70", size = 26759, upload-time = "2026-03-11T20:45:37.437Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -2958,10 +2958,10 @@ requires-dist = [
|
||||
{ name = "djangorestframework", specifier = "~=3.16" },
|
||||
{ name = "djangorestframework-guardian", specifier = "~=0.4.0" },
|
||||
{ name = "drf-spectacular", specifier = "~=0.28" },
|
||||
{ name = "drf-spectacular-sidecar", specifier = "~=2026.1.1" },
|
||||
{ name = "drf-spectacular-sidecar", specifier = "~=2026.3.1" },
|
||||
{ name = "drf-writable-nested", specifier = "~=0.7.1" },
|
||||
{ name = "faiss-cpu", specifier = ">=1.10" },
|
||||
{ name = "filelock", specifier = "~=3.24.3" },
|
||||
{ name = "filelock", specifier = "~=3.25.2" },
|
||||
{ name = "flower", specifier = "~=2.0.1" },
|
||||
{ name = "gotenberg-client", specifier = "~=0.13.1" },
|
||||
{ name = "granian", extras = ["uvloop"], marker = "extra == 'webserver'", specifier = "~=2.7.0" },
|
||||
@@ -2995,7 +2995,7 @@ requires-dist = [
|
||||
{ name = "rapidfuzz", specifier = "~=3.14.0" },
|
||||
{ name = "redis", extras = ["hiredis"], specifier = "~=5.2.1" },
|
||||
{ name = "regex", specifier = ">=2025.9.18" },
|
||||
{ name = "scikit-learn", specifier = "~=1.7.0" },
|
||||
{ name = "scikit-learn", specifier = "~=1.8.0" },
|
||||
{ name = "sentence-transformers", specifier = ">=4.1" },
|
||||
{ name = "setproctitle", specifier = "~=1.3.4" },
|
||||
{ name = "tika-client", specifier = "~=0.10.0" },
|
||||
@@ -3011,7 +3011,7 @@ provides-extras = ["mariadb", "postgres", "webserver"]
|
||||
dev = [
|
||||
{ name = "daphne" },
|
||||
{ name = "factory-boy", specifier = "~=3.3.1" },
|
||||
{ name = "faker", specifier = "~=40.5.1" },
|
||||
{ name = "faker", specifier = "~=40.8.0" },
|
||||
{ name = "imagehash" },
|
||||
{ name = "prek", specifier = "~=0.3.0" },
|
||||
{ name = "pytest", specifier = "~=9.0.0" },
|
||||
@@ -3034,7 +3034,7 @@ lint = [
|
||||
testing = [
|
||||
{ name = "daphne" },
|
||||
{ name = "factory-boy", specifier = "~=3.3.1" },
|
||||
{ name = "faker", specifier = "~=40.5.1" },
|
||||
{ name = "faker", specifier = "~=40.8.0" },
|
||||
{ name = "imagehash" },
|
||||
{ name = "pytest", specifier = "~=9.0.0" },
|
||||
{ name = "pytest-cov", specifier = "~=7.0.0" },
|
||||
@@ -3657,15 +3657,15 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "pyrefly"
|
||||
version = "0.54.0"
|
||||
version = "0.55.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/81/44/c10b16a302fda90d0af1328f880b232761b510eab546616a7be2fdf35a57/pyrefly-0.54.0.tar.gz", hash = "sha256:c6663be64d492f0d2f2a411ada9f28a6792163d34133639378b7f3dd9a8dca94", size = 5098893, upload-time = "2026-02-23T15:44:35.111Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/bf/c4/76e0797215e62d007f81f86c9c4fb5d6202685a3f5e70810f3fd94294f92/pyrefly-0.55.0.tar.gz", hash = "sha256:434c3282532dd4525c4840f2040ed0eb79b0ec8224fe18d957956b15471f2441", size = 5135682, upload-time = "2026-03-03T00:46:38.122Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/5f/99/8fdcdb4e55f0227fdd9f6abce36b619bab1ecb0662b83b66adc8cba3c788/pyrefly-0.54.0-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:58a3f092b6dc25ef79b2dc6c69a40f36784ca157c312bfc0baea463926a9db6d", size = 12223973, upload-time = "2026-02-23T15:44:14.278Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/90/35/c2aaf87a76003ad27b286594d2e5178f811eaa15bfe3d98dba2b47d56dd1/pyrefly-0.54.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:615081414106dd95873bc39c3a4bed68754c6cc24a8177ac51d22f88f88d3eb3", size = 11785585, upload-time = "2026-02-23T15:44:17.468Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c4/4a/ced02691ed67e5a897714979196f08ad279ec7ec7f63c45e00a75a7f3c0e/pyrefly-0.54.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0cbcaf20f5fe585079079a95205c1f3cd4542d17228cdf1df560288880623b70", size = 33381977, upload-time = "2026-02-23T15:44:19.736Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0b/ce/72a117ed437c8f6950862181014b41e36f3c3997580e29b772b71e78d587/pyrefly-0.54.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:66d5da116c0d34acfbd66663addd3ca8aa78a636f6692a66e078126d3620a883", size = 35962821, upload-time = "2026-02-23T15:44:22.357Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/85/de/89013f5ae0a35d2b6b01274a92a35ee91431ea001050edf0a16748d39875/pyrefly-0.54.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6ef3ac27f1a4baaf67aead64287d3163350844794aca6315ad1a9650b16ec26a", size = 38496689, upload-time = "2026-02-23T15:44:25.236Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/39/b0/16e50cf716784513648e23e726a24f71f9544aa4f86103032dcaa5ff71a2/pyrefly-0.55.0-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:49aafcefe5e2dd4256147db93e5b0ada42bff7d9a60db70e03d1f7055338eec9", size = 12210073, upload-time = "2026-03-03T00:46:15.51Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/3a/ad/89500c01bac3083383011600370289fbc67700c5be46e781787392628a3a/pyrefly-0.55.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:2827426e6b28397c13badb93c0ede0fb0f48046a7a89e3d774cda04e8e2067cd", size = 11767474, upload-time = "2026-03-03T00:46:18.003Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/78/68/4c66b260f817f304ead11176ff13985625f7c269e653304b4bdb546551af/pyrefly-0.55.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7346b2d64dc575bd61aa3bca854fbf8b5a19a471cbdb45e0ca1e09861b63488c", size = 33260395, upload-time = "2026-03-03T00:46:20.509Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/47/09/10bd48c9f860064f29f412954126a827d60f6451512224912c265e26bbe6/pyrefly-0.55.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:233b861b4cff008b1aff62f4f941577ed752e4d0060834229eb9b6826e6973c9", size = 35848269, upload-time = "2026-03-03T00:46:23.418Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a9/39/bc65cdd5243eb2dfea25dd1321f9a5a93e8d9c3a308501c4c6c05d011585/pyrefly-0.55.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f5aa85657d76da1d25d081a49f0e33c8fc3ec91c1a0f185a8ed393a5a3d9e178", size = 38449820, upload-time = "2026-03-03T00:46:26.309Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -4283,7 +4283,7 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "scikit-learn"
|
||||
version = "1.7.2"
|
||||
version = "1.8.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "joblib", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
@@ -4291,28 +4291,32 @@ dependencies = [
|
||||
{ name = "scipy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
{ name = "threadpoolctl", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/98/c2/a7855e41c9d285dfe86dc50b250978105dce513d6e459ea66a6aeb0e1e0c/scikit_learn-1.7.2.tar.gz", hash = "sha256:20e9e49ecd130598f1ca38a1d85090e1a600147b9c02fa6f15d69cb53d968fda", size = 7193136, upload-time = "2025-09-09T08:21:29.075Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/0e/d4/40988bf3b8e34feec1d0e6a051446b1f66225f8529b9309becaeef62b6c4/scikit_learn-1.8.0.tar.gz", hash = "sha256:9bccbb3b40e3de10351f8f5068e105d0f4083b1a65fa07b6634fbc401a6287fd", size = 7335585, upload-time = "2025-12-10T07:08:53.618Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/43/83/564e141eef908a5863a54da8ca342a137f45a0bfb71d1d79704c9894c9d1/scikit_learn-1.7.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c7509693451651cd7361d30ce4e86a1347493554f172b1c72a39300fa2aea79e", size = 9331967, upload-time = "2025-09-09T08:20:32.421Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/18/d6/ba863a4171ac9d7314c4d3fc251f015704a2caeee41ced89f321c049ed83/scikit_learn-1.7.2-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:0486c8f827c2e7b64837c731c8feff72c0bd2b998067a8a9cbc10643c31f0fe1", size = 8648645, upload-time = "2025-09-09T08:20:34.436Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ef/0e/97dbca66347b8cf0ea8b529e6bb9367e337ba2e8be0ef5c1a545232abfde/scikit_learn-1.7.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:89877e19a80c7b11a2891a27c21c4894fb18e2c2e077815bcade10d34287b20d", size = 9715424, upload-time = "2025-09-09T08:20:36.776Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f7/32/1f3b22e3207e1d2c883a7e09abb956362e7d1bd2f14458c7de258a26ac15/scikit_learn-1.7.2-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8da8bf89d4d79aaec192d2bda62f9b56ae4e5b4ef93b6a56b5de4977e375c1f1", size = 9509234, upload-time = "2025-09-09T08:20:38.957Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a7/aa/3996e2196075689afb9fce0410ebdb4a09099d7964d061d7213700204409/scikit_learn-1.7.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:8d91a97fa2b706943822398ab943cde71858a50245e31bc71dba62aab1d60a96", size = 9259818, upload-time = "2025-09-09T08:20:43.19Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/43/5d/779320063e88af9c4a7c2cf463ff11c21ac9c8bd730c4a294b0000b666c9/scikit_learn-1.7.2-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:acbc0f5fd2edd3432a22c69bed78e837c70cf896cd7993d71d51ba6708507476", size = 8636997, upload-time = "2025-09-09T08:20:45.468Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/5c/d0/0c577d9325b05594fdd33aa970bf53fb673f051a45496842caee13cfd7fe/scikit_learn-1.7.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e5bf3d930aee75a65478df91ac1225ff89cd28e9ac7bd1196853a9229b6adb0b", size = 9478381, upload-time = "2025-09-09T08:20:47.982Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/82/70/8bf44b933837ba8494ca0fc9a9ab60f1c13b062ad0197f60a56e2fc4c43e/scikit_learn-1.7.2-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b4d6e9deed1a47aca9fe2f267ab8e8fe82ee20b4526b2c0cd9e135cea10feb44", size = 9300296, upload-time = "2025-09-09T08:20:50.366Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ae/93/a3038cb0293037fd335f77f31fe053b89c72f17b1c8908c576c29d953e84/scikit_learn-1.7.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0b7dacaa05e5d76759fb071558a8b5130f4845166d88654a0f9bdf3eb57851b7", size = 9212382, upload-time = "2025-09-09T08:20:54.731Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/40/dd/9a88879b0c1104259136146e4742026b52df8540c39fec21a6383f8292c7/scikit_learn-1.7.2-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:abebbd61ad9e1deed54cca45caea8ad5f79e1b93173dece40bb8e0c658dbe6fe", size = 8592042, upload-time = "2025-09-09T08:20:57.313Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/46/af/c5e286471b7d10871b811b72ae794ac5fe2989c0a2df07f0ec723030f5f5/scikit_learn-1.7.2-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:502c18e39849c0ea1a5d681af1dbcf15f6cce601aebb657aabbfe84133c1907f", size = 9434180, upload-time = "2025-09-09T08:20:59.671Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f1/fd/df59faa53312d585023b2da27e866524ffb8faf87a68516c23896c718320/scikit_learn-1.7.2-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:7a4c328a71785382fe3fe676a9ecf2c86189249beff90bf85e22bdb7efaf9ae0", size = 9283660, upload-time = "2025-09-09T08:21:01.71Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/55/87/ef5eb1f267084532c8e4aef98a28b6ffe7425acbfd64b5e2f2e066bc29b3/scikit_learn-1.7.2-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:9acb6c5e867447b4e1390930e3944a005e2cb115922e693c08a323421a6966e8", size = 9558731, upload-time = "2025-09-09T08:21:06.381Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/93/f8/6c1e3fc14b10118068d7938878a9f3f4e6d7b74a8ddb1e5bed65159ccda8/scikit_learn-1.7.2-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:2a41e2a0ef45063e654152ec9d8bcfc39f7afce35b08902bfe290c2498a67a6a", size = 9038852, upload-time = "2025-09-09T08:21:08.628Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/83/87/066cafc896ee540c34becf95d30375fe5cbe93c3b75a0ee9aa852cd60021/scikit_learn-1.7.2-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:98335fb98509b73385b3ab2bd0639b1f610541d3988ee675c670371d6a87aa7c", size = 9527094, upload-time = "2025-09-09T08:21:11.486Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/9c/2b/4903e1ccafa1f6453b1ab78413938c8800633988c838aa0be386cbb33072/scikit_learn-1.7.2-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:191e5550980d45449126e23ed1d5e9e24b2c68329ee1f691a3987476e115e09c", size = 9367436, upload-time = "2025-09-09T08:21:13.602Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d9/82/dee5acf66837852e8e68df6d8d3a6cb22d3df997b733b032f513d95205b7/scikit_learn-1.7.2-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:fa8f63940e29c82d1e67a45d5297bdebbcb585f5a5a50c4914cc2e852ab77f33", size = 9208906, upload-time = "2025-09-09T08:21:18.557Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/3c/30/9029e54e17b87cb7d50d51a5926429c683d5b4c1732f0507a6c3bed9bf65/scikit_learn-1.7.2-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:f95dc55b7902b91331fa4e5845dd5bde0580c9cd9612b1b2791b7e80c3d32615", size = 8627836, upload-time = "2025-09-09T08:21:20.695Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/60/18/4a52c635c71b536879f4b971c2cedf32c35ee78f48367885ed8025d1f7ee/scikit_learn-1.7.2-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9656e4a53e54578ad10a434dc1f993330568cfee176dff07112b8785fb413106", size = 9426236, upload-time = "2025-09-09T08:21:22.645Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/99/7e/290362f6ab582128c53445458a5befd471ed1ea37953d5bcf80604619250/scikit_learn-1.7.2-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:96dc05a854add0e50d3f47a1ef21a10a595016da5b007c7d9cd9d0bffd1fcc61", size = 9312593, upload-time = "2025-09-09T08:21:24.65Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c9/92/53ea2181da8ac6bf27170191028aee7251f8f841f8d3edbfdcaf2008fde9/scikit_learn-1.8.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:146b4d36f800c013d267b29168813f7a03a43ecd2895d04861f1240b564421da", size = 8595835, upload-time = "2025-12-10T07:07:39.385Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/01/18/d154dc1638803adf987910cdd07097d9c526663a55666a97c124d09fb96a/scikit_learn-1.8.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:f984ca4b14914e6b4094c5d52a32ea16b49832c03bd17a110f004db3c223e8e1", size = 8080381, upload-time = "2025-12-10T07:07:41.93Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/8a/44/226142fcb7b7101e64fdee5f49dbe6288d4c7af8abf593237b70fca080a4/scikit_learn-1.8.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5e30adb87f0cc81c7690a84f7932dd66be5bac57cfe16b91cb9151683a4a2d3b", size = 8799632, upload-time = "2025-12-10T07:07:43.899Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/36/4d/4a67f30778a45d542bbea5db2dbfa1e9e100bf9ba64aefe34215ba9f11f6/scikit_learn-1.8.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ada8121bcb4dac28d930febc791a69f7cb1673c8495e5eee274190b73a4559c1", size = 9103788, upload-time = "2025-12-10T07:07:45.982Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/90/74/e6a7cc4b820e95cc38cf36cd74d5aa2b42e8ffc2d21fe5a9a9c45c1c7630/scikit_learn-1.8.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:5fb63362b5a7ddab88e52b6dbb47dac3fd7dafeee740dc6c8d8a446ddedade8e", size = 8548242, upload-time = "2025-12-10T07:07:51.568Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/49/d8/9be608c6024d021041c7f0b3928d4749a706f4e2c3832bbede4fb4f58c95/scikit_learn-1.8.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:5025ce924beccb28298246e589c691fe1b8c1c96507e6d27d12c5fadd85bfd76", size = 8079075, upload-time = "2025-12-10T07:07:53.697Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/dd/47/f187b4636ff80cc63f21cd40b7b2d177134acaa10f6bb73746130ee8c2e5/scikit_learn-1.8.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4496bb2cf7a43ce1a2d7524a79e40bc5da45cf598dbf9545b7e8316ccba47bb4", size = 8660492, upload-time = "2025-12-10T07:07:55.574Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/97/74/b7a304feb2b49df9fafa9382d4d09061a96ee9a9449a7cbea7988dda0828/scikit_learn-1.8.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a0bcfe4d0d14aec44921545fd2af2338c7471de9cb701f1da4c9d85906ab847a", size = 8931904, upload-time = "2025-12-10T07:07:57.666Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/03/aa/e22e0768512ce9255eba34775be2e85c2048da73da1193e841707f8f039c/scikit_learn-1.8.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0d6ae97234d5d7079dc0040990a6f7aeb97cb7fa7e8945f1999a429b23569e0a", size = 8513770, upload-time = "2025-12-10T07:08:03.251Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/58/37/31b83b2594105f61a381fc74ca19e8780ee923be2d496fcd8d2e1147bd99/scikit_learn-1.8.0-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:edec98c5e7c128328124a029bceb09eda2d526997780fef8d65e9a69eead963e", size = 8044458, upload-time = "2025-12-10T07:08:05.336Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2d/5a/3f1caed8765f33eabb723596666da4ebbf43d11e96550fb18bdec42b467b/scikit_learn-1.8.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:74b66d8689d52ed04c271e1329f0c61635bcaf5b926db9b12d58914cdc01fe57", size = 8610341, upload-time = "2025-12-10T07:08:07.732Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/38/cf/06896db3f71c75902a8e9943b444a56e727418f6b4b4a90c98c934f51ed4/scikit_learn-1.8.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8fdf95767f989b0cfedb85f7ed8ca215d4be728031f56ff5a519ee1e3276dc2e", size = 8900022, upload-time = "2025-12-10T07:08:09.862Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d2/7d/a630359fc9dcc95496588c8d8e3245cc8fd81980251079bc09c70d41d951/scikit_learn-1.8.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:7cc267b6108f0a1499a734167282c00c4ebf61328566b55ef262d48e9849c735", size = 8826045, upload-time = "2025-12-10T07:08:15.215Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/cc/56/a0c86f6930cfcd1c7054a2bc417e26960bb88d32444fe7f71d5c2cfae891/scikit_learn-1.8.0-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:fe1c011a640a9f0791146011dfd3c7d9669785f9fed2b2a5f9e207536cf5c2fd", size = 8420324, upload-time = "2025-12-10T07:08:17.561Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/46/1e/05962ea1cebc1cf3876667ecb14c283ef755bf409993c5946ade3b77e303/scikit_learn-1.8.0-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:72358cce49465d140cc4e7792015bb1f0296a9742d5622c67e31399b75468b9e", size = 8680651, upload-time = "2025-12-10T07:08:19.952Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/fe/56/a85473cd75f200c9759e3a5f0bcab2d116c92a8a02ee08ccd73b870f8bb4/scikit_learn-1.8.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:80832434a6cc114f5219211eec13dcbc16c2bac0e31ef64c6d346cde3cf054cb", size = 8925045, upload-time = "2025-12-10T07:08:22.11Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/24/05/1af2c186174cc92dcab2233f327336058c077d38f6fe2aceb08e6ab4d509/scikit_learn-1.8.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:c22a2da7a198c28dd1a6e1136f19c830beab7fdca5b3e5c8bba8394f8a5c45b3", size = 8528667, upload-time = "2025-12-10T07:08:27.541Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a8/25/01c0af38fe969473fb292bba9dc2b8f9b451f3112ff242c647fee3d0dfe7/scikit_learn-1.8.0-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:6b595b07a03069a2b1740dc08c2299993850ea81cce4fe19b2421e0c970de6b7", size = 8066524, upload-time = "2025-12-10T07:08:29.822Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/be/ce/a0623350aa0b68647333940ee46fe45086c6060ec604874e38e9ab7d8e6c/scikit_learn-1.8.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:29ffc74089f3d5e87dfca4c2c8450f88bdc61b0fc6ed5d267f3988f19a1309f6", size = 8657133, upload-time = "2025-12-10T07:08:31.865Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b8/cb/861b41341d6f1245e6ca80b1c1a8c4dfce43255b03df034429089ca2a2c5/scikit_learn-1.8.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fb65db5d7531bccf3a4f6bec3462223bea71384e2cda41da0f10b7c292b9e7c4", size = 8923223, upload-time = "2025-12-10T07:08:34.166Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2d/d1/ef294ca754826daa043b2a104e59960abfab4cf653891037d19dd5b6f3cf/scikit_learn-1.8.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:4511be56637e46c25721e83d1a9cea9614e7badc7040c4d573d75fbe257d6fd7", size = 8848305, upload-time = "2025-12-10T07:08:41.013Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/5b/e2/b1f8b05138ee813b8e1a4149f2f0d289547e60851fd1bb268886915adbda/scikit_learn-1.8.0-cp314-cp314t-macosx_12_0_arm64.whl", hash = "sha256:a69525355a641bf8ef136a7fa447672fb54fe8d60cab5538d9eb7c6438543fb9", size = 8432257, upload-time = "2025-12-10T07:08:42.873Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/26/11/c32b2138a85dcb0c99f6afd13a70a951bfdff8a6ab42d8160522542fb647/scikit_learn-1.8.0-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c2656924ec73e5939c76ac4c8b026fc203b83d8900362eb2599d8aee80e4880f", size = 8678673, upload-time = "2025-12-10T07:08:45.362Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c7/57/51f2384575bdec454f4fe4e7a919d696c9ebce914590abf3e52d47607ab8/scikit_learn-1.8.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:15fc3b5d19cc2be65404786857f2e13c70c83dd4782676dd6814e3b89dc8f5b9", size = 8922467, upload-time = "2025-12-10T07:08:47.408Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
||||
Reference in New Issue
Block a user