mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-09-21 17:08:33 +00:00
Trenton H
530059c5c0
* Preprocesses classifier content with Tantivy instead of NLTK Tokenizing and stemming now happen in one Rust call instead of NLTK's Python tokenizer and per word stemming, which also removes the Redis backed stem cache from every preprocessing call. The output matches the NLTK pipeline closely; tokens containing digits are now stemmed, and the English stop words follow Snowball's list. Stemming and stop word removal apply whenever the OCR language is one of the supported classifier languages, so PAPERLESS_ENABLE_NLTK and PAPERLESS_NLTK_DIR are removed. * Copies packages instead of hardlinking them in backend CI, some NLTK thing * Adds a normalization to NFC to better fit what Tantivy expects
172 lines
4.2 KiB
YAML
172 lines
4.2 KiB
YAML
# Please see the documentation for all configuration options:
|
|
# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
|
|
version: 2
|
|
# Required for uv support for now
|
|
enable-beta-ecosystems: true
|
|
updates:
|
|
# Enable version updates for pnpm
|
|
- package-ecosystem: "npm"
|
|
target-branch: "dev"
|
|
# Look for `pnpm-lock.yaml` file in the `/src-ui` directory
|
|
directory: "/src-ui"
|
|
open-pull-requests-limit: 10
|
|
schedule:
|
|
interval: "monthly"
|
|
cooldown:
|
|
default-days: 7
|
|
labels:
|
|
- "frontend"
|
|
- "dependencies"
|
|
groups:
|
|
frontend-angular-dependencies:
|
|
patterns:
|
|
- "@angular*"
|
|
- "@ng-*"
|
|
- "ngx-*"
|
|
- "ng2-pdf-viewer"
|
|
frontend-jest-dependencies:
|
|
patterns:
|
|
- "@types/jest"
|
|
- "jest*"
|
|
frontend-eslint-dependencies:
|
|
patterns:
|
|
- "@typescript-eslint*"
|
|
- "eslint"
|
|
# Enable version updates for Python
|
|
- package-ecosystem: "uv"
|
|
target-branch: "dev"
|
|
directory: "/"
|
|
# Check for updates once a week
|
|
schedule:
|
|
interval: "monthly"
|
|
cooldown:
|
|
default-days: 7
|
|
labels:
|
|
- "backend"
|
|
- "dependencies"
|
|
groups:
|
|
# Development & CI/CD Tooling
|
|
development:
|
|
patterns:
|
|
- "*pytest*"
|
|
- "ruff"
|
|
- "zensical"
|
|
- "prek*"
|
|
# Django & DRF Ecosystem
|
|
django-ecosystem:
|
|
patterns:
|
|
- "*django*"
|
|
- "drf-*"
|
|
- "djangorestframework"
|
|
- "whitenoise"
|
|
- "bleach"
|
|
- "jinja2"
|
|
# Async, Task Queuing & Caching
|
|
async-tasks:
|
|
patterns:
|
|
- "celery*"
|
|
- "channels*"
|
|
- "flower"
|
|
- "redis"
|
|
# Document, PDF, and OCR Processing
|
|
document-processing:
|
|
patterns:
|
|
- "ocrmypdf"
|
|
- "pdf2image"
|
|
- "zxing-cpp"
|
|
- "tika-client"
|
|
- "gotenberg-client"
|
|
- "python-magic"
|
|
- "python-gnupg"
|
|
# Data, NLP, and Search
|
|
data-nlp-search:
|
|
patterns:
|
|
- "scikit-learn"
|
|
- "langdetect"
|
|
- "rapidfuzz"
|
|
- "whoosh-reloaded"
|
|
# Utilities (Patch Updates)
|
|
utilities-patch:
|
|
update-types:
|
|
- "patch"
|
|
# Utilities (Minor Updates)
|
|
utilities-minor:
|
|
update-types:
|
|
- "minor"
|
|
# Enable updates for GitHub Actions
|
|
- package-ecosystem: "github-actions"
|
|
target-branch: "dev"
|
|
directory: "/"
|
|
schedule:
|
|
# Check for updates to GitHub Actions every month
|
|
interval: "monthly"
|
|
cooldown:
|
|
default-days: 7
|
|
labels:
|
|
- "ci-cd"
|
|
- "dependencies"
|
|
groups:
|
|
actions:
|
|
update-types:
|
|
- "major"
|
|
- "minor"
|
|
- "patch"
|
|
# Update Dockerfile in root directory
|
|
- package-ecosystem: "docker"
|
|
directories:
|
|
- "/"
|
|
- "/.devcontainer/"
|
|
schedule:
|
|
interval: "monthly"
|
|
cooldown:
|
|
default-days: 7
|
|
open-pull-requests-limit: 5
|
|
labels:
|
|
- "dependencies"
|
|
commit-message:
|
|
prefix: "docker"
|
|
include: "scope"
|
|
# Update Docker Compose files in docker/compose directory
|
|
- package-ecosystem: "docker-compose"
|
|
directory: "/docker/compose/"
|
|
schedule:
|
|
interval: "monthly"
|
|
cooldown:
|
|
default-days: 7
|
|
open-pull-requests-limit: 5
|
|
labels:
|
|
- "dependencies"
|
|
commit-message:
|
|
prefix: "docker-compose"
|
|
include: "scope"
|
|
groups:
|
|
# Individual groups for each image
|
|
gotenberg:
|
|
patterns:
|
|
- "docker.io/gotenberg/gotenberg*"
|
|
tika:
|
|
patterns:
|
|
- "docker.io/apache/tika*"
|
|
redis:
|
|
patterns:
|
|
- "docker.io/library/redis*"
|
|
mariadb:
|
|
patterns:
|
|
- "docker.io/library/mariadb*"
|
|
postgres:
|
|
patterns:
|
|
- "docker.io/library/postgres*"
|
|
greenmail:
|
|
patterns:
|
|
- "docker.io/greenmail*"
|
|
- package-ecosystem: "pre-commit" # See documentation for possible values
|
|
directory: "/" # Location of package manifests
|
|
schedule:
|
|
interval: "monthly"
|
|
cooldown:
|
|
default-days: 7
|
|
groups:
|
|
pre-commit-dependencies:
|
|
patterns:
|
|
- "*"
|