Update views.py

[ci ckip]

.codecov.yml

@@ -14,6 +14,9 @@ flag_management:
 # codecov will only comment if coverage changes
 comment:
   require_changes: true
+  # https://docs.codecov.com/docs/javascript-bundle-analysis
+  require_bundle_changes: true
+  bundle_change_threshold: "50Kb"
 coverage:
   status:
     project:
@@ -22,7 +25,12 @@ coverage:
         threshold: 1%
     patch:
       default:
-        # For the changed lines only, target 75% covered, but
-        # allow as low as 50%
-        target: 75%
+        # For the changed lines only, target 100% covered, but
+        # allow as low as 75%
+        target: 100%
         threshold: 25%
+# https://docs.codecov.com/docs/javascript-bundle-analysis
+bundle_analysis:
+  # Fail if the bundle size increases by more than 1MB
+  warning_threshold: "1MB"
+  status: true

.codespellrc

@@ -1,3 +1,3 @@
 [codespell]
 write-changes = True
-ignore-words-list = criterias,afterall,valeu,ureue,equest,ure
+ignore-words-list = criterias,afterall,valeu,ureue,equest,ure,assertIn

.devcontainer/Dockerfile

@@ -0,0 +1,180 @@
+# syntax=docker/dockerfile:1
+
+FROM --platform=$BUILDPLATFORM docker.io/node:20-bookworm-slim as main-app
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+# Buildx provided, must be defined to use though
+ARG TARGETARCH
+
+# Can be workflow provided, defaults set for manual building
+ARG JBIG2ENC_VERSION=0.29
+ARG QPDF_VERSION=11.9.0
+ARG GS_VERSION=10.03.1
+
+# Set Python environment variables
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    # Ignore warning from Whitenoise
+    PYTHONWARNINGS="ignore:::django.http.response:517" \
+    PNGX_CONTAINERIZED=1
+
+#
+# Begin installation and configuration
+# Order the steps below from least often changed to most
+#
+
+# Packages need for running
+ARG RUNTIME_PACKAGES="\
+  # General utils
+  curl \
+  # Docker specific
+  gosu \
+  # Timezones support
+  tzdata \
+  # fonts for text file thumbnail generation
+  fonts-liberation \
+  gettext \
+  ghostscript \
+  gnupg \
+  icc-profiles-free \
+  imagemagick \
+  # PostgreSQL
+  postgresql-client \
+  # MySQL / MariaDB
+  mariadb-client \
+  # OCRmyPDF dependencies
+  tesseract-ocr \
+  tesseract-ocr-eng \
+  tesseract-ocr-deu \
+  tesseract-ocr-fra \
+  tesseract-ocr-ita \
+  tesseract-ocr-spa \
+  unpaper \
+  pngquant \
+  jbig2dec \
+  # lxml
+  libxml2 \
+  libxslt1.1 \
+  # itself
+  qpdf \
+  # Mime type detection
+  file \
+  libmagic1 \
+  media-types \
+  zlib1g \
+  # Barcode splitter
+  libzbar0 \
+  poppler-utils \
+  htop \
+  sudo"
+
+# Install basic runtime packages.
+# These change very infrequently
+RUN set -eux \
+  echo "Installing system packages" \
+    && apt-get update \
+    && apt-get install --yes --quiet --no-install-recommends ${RUNTIME_PACKAGES}
+
+ARG PYTHON_PACKAGES="\
+  python3 \
+  python3-pip \
+  python3-wheel \
+  pipenv \
+  ca-certificates"
+
+RUN set -eux \
+  echo "Installing python packages" \
+    && apt-get update \
+    && apt-get install --yes --quiet ${PYTHON_PACKAGES}
+
+RUN set -eux \
+  && echo "Installing pre-built updates" \
+    && echo "Installing qpdf ${QPDF_VERSION}" \
+      && curl --fail --silent --show-error --location \
+        --output libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+        https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+      && curl --fail --silent --show-error --location \
+        --output qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+        https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+      && dpkg --install ./libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+      && dpkg --install ./qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+    && echo "Installing Ghostscript ${GS_VERSION}" \
+      && curl --fail --silent --show-error --location \
+          --output libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+      && curl --fail --silent --show-error --location \
+          --output ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+      && curl --fail --silent --show-error --location \
+          --output libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
+          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
+        && dpkg --install ./libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
+        && dpkg --install ./libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+        && dpkg --install ./ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+    && echo "Installing jbig2enc" \
+      && curl --fail --silent --show-error --location \
+        --output jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
+        https://github.com/paperless-ngx/builder/releases/download/jbig2enc-${JBIG2ENC_VERSION}/jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
+      && dpkg --install ./jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb
+
+# setup docker-specific things
+# These change sometimes, but rarely
+WORKDIR /usr/src/paperless/src/docker/
+
+COPY [ \
+  "docker/imagemagick-policy.xml", \
+  "./" \
+]
+
+RUN set -eux \
+  && echo "Configuring ImageMagick" \
+    && mv imagemagick-policy.xml /etc/ImageMagick-6/policy.xml
+
+# Packages needed only for building a few quick Python
+# dependencies
+ARG BUILD_PACKAGES="\
+  build-essential \
+  git \
+  # https://www.psycopg.org/docs/install.html#prerequisites
+  libpq-dev \
+  # https://github.com/PyMySQL/mysqlclient#linux
+  default-libmysqlclient-dev \
+  pkg-config \
+  pre-commit"
+
+# hadolint ignore=DL3042
+RUN --mount=type=cache,target=/root/.cache/pip/,id=pip-cache \
+  set -eux \
+  && echo "Installing build system packages" \
+    && apt-get update \
+    && apt-get install --yes --quiet ${BUILD_PACKAGES}
+
+RUN set -eux \
+  && npm update npm -g
+
+# add users, setup scripts
+# Mount the compiled frontend to expected location
+RUN set -eux \
+  && echo "Setting up user/group" \
+    && groupmod --new-name paperless node \
+    && usermod --login paperless --home /usr/src/paperless node \
+    && usermod -s /bin/bash paperless \
+    && echo "paperless ALL=(ALL) NOPASSWD:ALL" >> /etc/sudoers \
+  && echo "Creating volume directories" \
+    && mkdir --parents --verbose /usr/src/paperless/paperless-ngx/data \
+    && mkdir --parents --verbose /usr/src/paperless/paperless-ngx/media \
+    && mkdir --parents --verbose /usr/src/paperless/paperless-ngx/consume \
+    && mkdir --parents --verbose /usr/src/paperless/paperless-ngx/export \
+    && mkdir --parents --verbose /usr/src/paperless/paperless-ngx/.venv \
+  && echo "Adjusting all permissions" \
+    && chown --from root:root --changes --recursive paperless:paperless /usr/src/paperless
+#  && echo "Collecting static files" \
+#    && gosu paperless python3 manage.py collectstatic --clear --no-input --link \
+#    && gosu paperless python3 manage.py compilemessages
+
+VOLUME ["/usr/src/paperless/paperless-ngx/data", \
+        "/usr/src/paperless/paperless-ngx/media", \
+        "/usr/src/paperless/paperless-ngx/consume", \
+        "/usr/src/paperless/paperless-ngx/export", \
+        "/usr/src/paperless/paperless-ngx/.venv"]

.devcontainer/devcontainer.json

@@ -0,0 +1,28 @@
+{
+    "name": "Paperless Development",
+    "dockerComposeFile": "docker-compose.devcontainer.sqlite-tika.yml",
+    "service": "paperless-development",
+    "workspaceFolder": "/usr/src/paperless/paperless-ngx",
+    "postCreateCommand": "pipenv install --dev && pipenv run pre-commit install",
+    "customizations": {
+        "vscode": {
+          "extensions": [
+            "mhutchie.git-graph",
+            "ms-python.python",
+            "ms-vscode.js-debug-nightly",
+            "eamodio.gitlens",
+            "yzhang.markdown-all-in-one"
+          ],
+          "settings": {
+            "python.defaultInterpreterPath": "/usr/src/paperless/paperless-ngx/.venv/bin/python",
+            "python.pythonPath": "/usr/src/paperless/paperless-ngx/.venv/bin/python",
+            "python.terminal.activateEnvInCurrentTerminal": true,
+            "editor.formatOnPaste": false,
+            "editor.formatOnSave": true,
+            "editor.formatOnType": true,
+            "files.trimTrailingWhitespace": true
+          }
+        }
+      },
+      "remoteUser": "paperless"
+    }

.devcontainer/docker-compose.devcontainer.sqlite-tika.yml

@@ -0,0 +1,83 @@
+# Docker Compose file for developing Paperless NGX in VSCode DevContainers.
+# This file contains everything Paperless NGX needs to run.
+# Paperless supports amd64, arm, and arm64 hardware.
+# All compose files of Paperless configure it in the following way:
+#
+# - Paperless is (re)started on system boot if it was running before shutdown.
+# - Docker volumes for storing data are managed by Docker.
+# - Folders for importing and exporting files are created in the same directory
+#   as this file and mounted to the correct folders inside the container.
+# - Paperless listens on port 8000.
+#
+# SQLite is used as the database. The SQLite file is stored in the data volume.
+#
+# In addition, this Docker Compose file adds the following optional
+# configurations:
+#
+# - Apache Tika and Gotenberg servers are started with Paperless NGX and Paperless
+#   is configured to use these services. These provide support for consuming
+#   Office documents (Word, Excel, PowerPoint, and their LibreOffice counterparts).
+#
+# This file is intended only to be used through VSCOde devcontainers. See README.md
+# in the folder .devcontainer.
+
+
+services:
+  broker:
+    image: docker.io/library/redis:7
+    restart: unless-stopped
+    volumes:
+      - ./redisdata:/data
+
+  # No ports need to be exposed; the VSCode DevContainer plugin manages them.
+  paperless-development:
+    image: paperless-ngx
+    build:
+      context: ../    # Dockerfile cannot access files from parent directories if context is not set.
+      dockerfile: ./.devcontainer/Dockerfile
+    restart: unless-stopped
+    depends_on:
+      - broker
+      - gotenberg
+      - tika
+    volumes:
+      - ..:/usr/src/paperless/paperless-ngx:delegated
+      - ../.devcontainer/vscode:/usr/src/paperless/paperless-ngx/.vscode:delegated # VSCode config files
+      - pipenv:/usr/src/paperless/paperless-ngx/.venv
+      - /usr/src/paperless/paperless-ngx/src/documents/static/frontend # Static frontend files exist only in container
+      - /usr/src/paperless/paperless-ngx/src/.pytest_cache
+      - /usr/src/paperless/paperless-ngx/.ruff_cache
+      - /usr/src/paperless/paperless-ngx/htmlcov
+      - /usr/src/paperless/paperless-ngx/.coverage
+      - ./data:/usr/src/paperless/paperless-ngx/data
+      - ./media:/usr/src/paperless/paperless-ngx/media
+      - ./consume:/usr/src/paperless/paperless-ngx/consume
+      - ~/.gitconfig:/usr/src/paperless/.gitconfig:ro
+    environment:
+      PAPERLESS_REDIS: redis://broker:6379
+      PAPERLESS_TIKA_ENABLED: 1
+      PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
+      PAPERLESS_TIKA_ENDPOINT: http://tika:9998
+      PAPERLESS_STATICDIR: ./src/documents/static
+      PAPERLESS_DEBUG: true
+
+    # Overrides default command so things don't shut down after the process ends.
+    command: /bin/sh -c "chown -R paperless:paperless /usr/src/paperless/paperless-ngx/src/documents/static/frontend && chown -R paperless:paperless /usr/src/paperless/paperless-ngx/.ruff_cache && while sleep 1000; do :; done"
+
+  gotenberg:
+    image: docker.io/gotenberg/gotenberg:7.10
+    restart: unless-stopped
+
+    # 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/.*"
+
+  tika:
+    image: docker.io/apache/tika:latest
+    restart: unless-stopped
+
+volumes:
+  pipenv:

.devcontainer/vscode/launch.json

@@ -0,0 +1,58 @@
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Chrome: Debug Angular Frontend",
+						"description": "Debug the Angular Dev Frontend in Chrome",
+            "type": "chrome",
+            "request": "launch",
+            "url": "http://localhost:4200",
+            "webRoot": "${workspaceFolder}/src-ui",
+            "preLaunchTask": "Start: Frontend Angular"
+        },
+        {
+            "name": "Debug: Backend Server (manage.py runserver)",
+						"description": "Debug the Django Backend Server",
+            "type": "python",
+            "request": "launch",
+            "program": "${workspaceFolder}/src/manage.py",
+            "args": [
+                "runserver"
+            ],
+            "django": true,
+            "console": "integratedTerminal",
+            "env": {
+                "PYTHONPATH": "${workspaceFolder}/src"
+            },
+            "python": "${workspaceFolder}/.venv/bin/python"
+        },
+        {
+            "name": "Debug: Consumer Service (manage.py document_consumer)",
+						"description": "Debug the Consumer Service which processes files from a directory",
+            "type": "python",
+            "request": "launch",
+            "program": "${workspaceFolder}/src/manage.py",
+            "args": [
+                "document_consumer"
+            ],
+            "django": true,
+            "console": "integratedTerminal",
+            "env": {
+                "PYTHONPATH": "${workspaceFolder}/src"
+            },
+            "python": "${workspaceFolder}/.venv/bin/python"
+        }
+    ],
+    "compounds": [
+        {
+            "name": "Debug: FullStack",
+						"description": "Debug run the Angular dev frontend, Django backend, and consumer service",
+            "configurations": [
+                "Chrome: Debug Angular Frontend",
+                "Debug: Backend Server (manage.py runserver)",
+                "Debug: Consumer Service (manage.py document_consumer)"
+            ],
+            "preLaunchTask": "Start: Celery Worker"
+        }
+    ]
+}

.devcontainer/vscode/settings.json

@@ -0,0 +1,11 @@
+{
+    "python.testing.pytestArgs": [
+        "src"
+    ],
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true,
+    "files.watcherExclude": {
+        "**/.venv/**": true,
+        "**/pytest_cache/**": true
+    }
+}

.devcontainer/vscode/tasks.json

@@ -0,0 +1,223 @@
+{
+	"version": "2.0.0",
+	"tasks": [
+		{
+			"label": "Start: Celery Worker",
+			"description": "Start the Celery Worker which processes background and consume tasks",
+			"type": "shell",
+			"command": "pipenv run celery --app paperless worker -l DEBUG",
+			"isBackground": true,
+			"options": {
+				"cwd": "${workspaceFolder}/src"
+			},
+			"problemMatcher": [
+				{
+					"owner": "custom",
+					"pattern": [
+						{
+							"regexp": ".",
+							"file": 1,
+							"location": 2,
+							"message": 3
+						}
+					],
+					"background": {
+						"activeOnStart": true,
+						"beginsPattern": "celery.*",
+						"endsPattern": "ready"
+					}
+				}
+			]
+		},
+		{
+			"label": "Start: Frontend Angular",
+			"description": "Start the Frontend Angular Dev Server",
+			"type": "shell",
+			"command": "npm start",
+			"isBackground": true,
+			"options": {
+				"cwd": "${workspaceFolder}/src-ui"
+			},
+			"problemMatcher": [
+				{
+					"owner": "custom",
+					"pattern": [
+						{
+							"regexp": ".",
+							"file": 1,
+							"location": 2,
+							"message": 3
+						}
+					],
+					"background": {
+						"activeOnStart": true,
+						"beginsPattern": ".*",
+						"endsPattern": "Compiled successfully"
+					}
+				}
+			]
+		},
+		{
+			"label": "Start: Consumer Service (manage.py document_consumer)",
+			"description": "Start the Consumer Service which processes files from a directory",
+			"type": "shell",
+			"command": "pipenv run python manage.py document_consumer",
+			"group": "build",
+			"presentation": {
+				"echo": true,
+				"reveal": "always",
+				"focus": false,
+				"panel": "shared",
+				"showReuseMessage": false,
+				"clear": true,
+				"revealProblems": "onProblem"
+			},
+			"options": {
+				"cwd": "${workspaceFolder}/src"
+			}
+		},
+		{
+			"label": "Start: Backend Server (manage.py runserver)",
+			"description": "Start the Backend Server which serves the Django API and the compiled Angular frontend",
+			"type": "shell",
+			"command": "pipenv run python manage.py runserver",
+			"group": "build",
+			"presentation": {
+				"echo": true,
+				"reveal": "always",
+				"focus": false,
+				"panel": "shared",
+				"showReuseMessage": false,
+				"clear": true,
+				"revealProblems": "onProblem"
+			},
+			"options": {
+				"cwd": "${workspaceFolder}/src"
+			}
+		},
+		{
+			"label": "Maintenance: manage.py migrate",
+			"description": "Apply database migrations",
+			"type": "shell",
+			"command": "pipenv run python manage.py migrate",
+			"group": "none",
+			"presentation": {
+				"echo": true,
+				"reveal": "always",
+				"focus": true,
+				"panel": "shared",
+				"showReuseMessage": false,
+				"clear": true,
+				"revealProblems": "onProblem"
+			},
+			"options": {
+				"cwd": "${workspaceFolder}/src"
+			}
+		},
+		{
+			"label": "Maintenance: Build Documentation",
+			"description": "Build the documentation with MkDocs",
+			"type": "shell",
+			"command": "pipenv run mkdocs build --config-file mkdocs.yml && pipenv run mkdocs serve",
+			"group": "none",
+			"presentation": {
+				"echo": true,
+				"reveal": "always",
+				"focus": true,
+				"panel": "shared",
+				"showReuseMessage": false,
+				"clear": true,
+				"revealProblems": "onProblem"
+			},
+			"options": {
+				"cwd": "${workspaceFolder}"
+			}
+		},
+		{
+			"label": "Maintenance: manage.py createsuperuser",
+			"description": "Create a superuser",
+			"type": "shell",
+			"command": "pipenv run python manage.py createsuperuser",
+			"group": "none",
+			"presentation": {
+				"echo": true,
+				"reveal": "always",
+				"focus": true,
+				"panel": "shared",
+				"showReuseMessage": false,
+				"clear": true,
+				"revealProblems": "onProblem"
+			},
+			"options": {
+				"cwd": "${workspaceFolder}/src"
+			}
+		},
+		{
+			"label": "Maintenance: recreate .venv",
+			"description": "Recreate the python virtual environment and install python dependencies",
+			"type": "shell",
+			"command": "rm -R -v .venv/* || pipenv install --dev",
+			"group": "none",
+			"presentation": {
+				"echo": true,
+				"reveal": "always",
+				"focus": true,
+				"panel": "shared",
+				"showReuseMessage": false,
+				"clear": true,
+				"revealProblems": "onProblem"
+			},
+			"options": {
+				"cwd": "${workspaceFolder}"
+			}
+		},
+		{
+			"label": "Maintenance: Install Frontend Dependencies",
+			"description": "Install frontend (npm) dependencies",
+			"type": "npm",
+			"script": "install",
+			"path": "src-ui",
+			"group": "clean",
+			"problemMatcher": [],
+			"detail": "install dependencies from package"
+		},
+		{
+			"description": "Clean install frontend dependencies and build the frontend for production",
+			"label": "Maintenance: Compile frontend for production",
+			"type": "shell",
+			"command": "npm ci && ./node_modules/.bin/ng build --configuration production",
+			"group": "none",
+			"presentation": {
+				"echo": true,
+				"reveal": "always",
+				"focus": true,
+				"panel": "shared",
+				"showReuseMessage": false,
+				"clear": true,
+				"revealProblems": "onProblem"
+			},
+			"options": {
+				"cwd": "${workspaceFolder}/src-ui"
+			}
+		},
+		{
+			"label": "Project Setup: Run all Init Tasks",
+			"description": "Runs all init tasks to setup the project including migrate the database, create a superuser and compile the frontend for production",
+			"dependsOrder": "sequence",
+			"dependsOn": [
+				"Maintenance: manage.py migrate",
+				"Maintenance: manage.py createsuperuser",
+				"Maintenance: Compile frontend for production"
+			]
+		},
+		{
+			"label": "Project Start: Run all Services",
+			"description": "Runs all services required to start the project including the Celery Worker, the Consumer Service and the Backend Server",
+			"dependsOn": [
+				"Start: Celery Worker",
+				"Start: Consumer Service (manage.py document_consumer)",
+				"Start: Backend Server (manage.py runserver)"
+			]
+		}
+	]
+}

.dockerignore

@@ -26,3 +26,5 @@
 ./dist
 ./scripts
 ./resources
+# Other stuff
+**/*.drawio.png

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -9,7 +9,7 @@ body:
         ### ⚠️ Please remember: issues are for *bugs*
         That is, something you believe affects every single user of Paperless-ngx, not just you. If you're not sure, start with one of the other options below.
 
-        Also, note that **Paperless-ngx does not perform OCR itself**, that is handled by other tools. Problems with OCR of specific files should likely be raised 'upstream', see https://github.com/ocrmypdf/OCRmyPDF/issues or https://github.com/tesseract-ocr/tesseract/issues
+        Also, note that **Paperless-ngx does not perform OCR or archive file creation itself**, those are handled by other tools. Problems with OCR or archive versions of specific files should likely be raised 'upstream', see https://github.com/ocrmypdf/OCRmyPDF/issues or https://github.com/tesseract-ocr/tesseract/issues
   - type: markdown
     attributes:
       value: |
@@ -86,22 +86,23 @@ body:
       description: Note there are significant differences from the official image and linuxserver.io, please check if your issue is specific to the third-party image.
     validations:
       required: true
+  - type: textarea
+    id: system-status
+    attributes:
+      label: System status
+      description: If available, copy & paste the system status output from Settings > System Status > Copy
+      render: json
   - type: input
     id: browser
     attributes:
       label: Browser
       description: Which browser you are using, if relevant.
       placeholder: e.g. Chrome, Safari
-  - type: input
+  - type: textarea
     id: config-changes
     attributes:
       label: Configuration changes
       description: Any configuration changes you made in `docker-compose.yml`, `docker-compose.env` or `paperless.conf`.
-  - type: input
-    id: other
-    attributes:
-      label: Other
-      description: Any other relevant details.
   - type: checkboxes
     id: required-checks
     attributes:
@@ -109,6 +110,8 @@ body:
       options:
         - label: I believe this issue is a bug that affects all users of Paperless-ngx, not something specific to my installation.
           required: true
+        - label: This issue is not about the OCR or archive creation of a specific file(s). Otherwise, please see above regarding OCR tools.
+          required: true
         - label: I have already searched for relevant existing issues and discussions before opening this report.
           required: true
         - label: I have updated the title field above with a concise description.

.github/ISSUE_TEMPLATE/config.yml

@@ -2,10 +2,10 @@ blank_issues_enabled: false
 contact_links:
   - name: 🤔 Questions and Help
     url: https://github.com/paperless-ngx/paperless-ngx/discussions
-    about: This issue tracker is not for support questions. Please refer to our Discussions.
+    about: General questions or support for using Paperless-ngx.
   - name: 💬 Chat
     url: https://matrix.to/#/#paperlessngx:matrix.org
     about: Want to discuss Paperless-ngx with others? Check out our chat.
   - name: 🚀 Feature Request
     url: https://github.com/paperless-ngx/paperless-ngx/discussions/new?category=feature-requests
-    about: Remember to search for existing feature requests and "up-vote" any you like
+    about: Remember to search for existing feature requests and "up-vote" those that you like.

.github/dependabot.yml

@@ -53,7 +53,6 @@ updates:
       development:
         patterns:
           - "*pytest*"
-          - "black"
           - "ruff"
           - "mkdocs-material"
       django:

.github/workflows/ci.yml

@@ -16,9 +16,9 @@ on:
 env:
   # This is the version of pipenv all the steps will use
   # If changing this, change Dockerfile
-  DEFAULT_PIP_ENV_VERSION: "2023.12.1"
+  DEFAULT_PIP_ENV_VERSION: "2024.4.1"
   # This is the default version of Python to use in most steps which aren't specific
-  DEFAULT_PYTHON_VERSION: "3.10"
+  DEFAULT_PYTHON_VERSION: "3.11"
 
 jobs:
   pre-commit:
@@ -30,7 +30,7 @@ jobs:
       github.repository
 
     name: Linting Checks
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     steps:
       -
         name: Checkout repository
@@ -46,7 +46,7 @@ jobs:
 
   documentation:
     name: "Build & Deploy Documentation"
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     needs:
       - pre-commit
     steps:
@@ -95,12 +95,12 @@ jobs:
 
   tests-backend:
     name: "Backend Tests (Python ${{ matrix.python-version }})"
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     needs:
       - pre-commit
     strategy:
       matrix:
-        python-version: ['3.9', '3.10', '3.11']
+        python-version: ['3.10', '3.11', '3.12']
       fail-fast: false
     steps:
       -
@@ -131,7 +131,7 @@ jobs:
       -
         name: Configure ImageMagick
         run: |
-          sudo cp docker/imagemagick-policy.xml /etc/ImageMagick-6/policy.xml
+          sudo cp docker/rootfs/etc/ImageMagick-6/paperless-policy.xml /etc/ImageMagick-6/policy.xml
       -
         name: Install Python dependencies
         run: |
@@ -170,7 +170,7 @@ jobs:
 
   install-frontend-depedendencies:
     name: "Install Frontend Dependencies"
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     needs:
       - pre-commit
     steps:
@@ -201,7 +201,7 @@ jobs:
 
   tests-frontend:
     name: "Frontend Tests (Node ${{ matrix.node-version }} - ${{ matrix.shard-index }}/${{ matrix.shard-count }})"
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     needs:
       - install-frontend-depedendencies
     strategy:
@@ -260,8 +260,8 @@ jobs:
           retention-days: 7
 
   tests-coverage-upload:
-    name: "Upload Coverage"
-    runs-on: ubuntu-22.04
+    name: "Upload to Codecov"
+    runs-on: ubuntu-24.04
     needs:
       - tests-backend
       - tests-frontend
@@ -283,7 +283,7 @@ jobs:
           merge-multiple: true
       -
         name: Upload frontend coverage to Codecov
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v5
         with:
           # not required for public repos, but intermittently fails otherwise
           token: ${{ secrets.CODECOV_TOKEN }}
@@ -299,17 +299,41 @@ jobs:
           path: src/
       -
         name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v5
         with:
           # not required for public repos, but intermittently fails otherwise
           token: ${{ secrets.CODECOV_TOKEN }}
           # future expansion
           flags: backend
           directory: src/
+      -
+        name: Use Node.js 20
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20.x
+          cache: 'npm'
+          cache-dependency-path: 'src-ui/package-lock.json'
+      -
+        name: Cache frontend dependencies
+        id: cache-frontend-deps
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.npm
+            ~/.cache
+          key: ${{ runner.os }}-frontenddeps-${{ hashFiles('src-ui/package-lock.json') }}
+      -
+        name: Re-link Angular cli
+        run: cd src-ui && npm link @angular/cli
+      -
+        name: Build frontend and upload analysis
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+        run: cd src-ui && ng build --configuration=production
 
   build-docker-image:
     name: Build Docker image for ${{ github.ref_name }}
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     if: github.event_name == 'push' && (startsWith(github.ref, 'refs/heads/feature-') || startsWith(github.ref, 'refs/heads/fix-') || github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/beta' || contains(github.ref, 'beta.rc') || startsWith(github.ref, 'refs/tags/v'))
     concurrency:
       group: ${{ github.workflow }}-build-docker-image-${{ github.ref_name }}
@@ -382,7 +406,7 @@ jobs:
       -
         name: Login to Docker Hub
         uses: docker/login-action@v3
-        # Don't attempt to login is not pushing to Docker Hub
+        # Don't attempt to login if not pushing to Docker Hub
         if: steps.push-other-places.outputs.enable == 'true'
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
@@ -390,7 +414,7 @@ jobs:
       -
         name: Login to Quay.io
         uses: docker/login-action@v3
-        # Don't attempt to login is not pushing to Quay.io
+        # Don't attempt to login if not pushing to Quay.io
         if: steps.push-other-places.outputs.enable == 'true'
         with:
           registry: quay.io
@@ -398,7 +422,7 @@ jobs:
           password: ${{ secrets.QUAY_ROBOT_TOKEN }}
       -
         name: Build and push
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@v6
         with:
           context: .
           file: ./Dockerfile
@@ -406,6 +430,8 @@ jobs:
           push: ${{ github.event_name != 'pull_request' }}
           tags: ${{ steps.docker-meta.outputs.tags }}
           labels: ${{ steps.docker-meta.outputs.labels }}
+          build-args: |
+            PNGX_TAG_VERSION=${{ steps.docker-meta.outputs.version }}
           # Get cache layers from this branch, then dev
           # This allows new branches to get at least some cache benefits, generally from dev
           cache-from: |
@@ -435,7 +461,7 @@ jobs:
     needs:
       - build-docker-image
       - documentation
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     steps:
       -
         name: Checkout
@@ -456,12 +482,6 @@ jobs:
         name: Install Python dependencies
         run: |
           pipenv --python ${{ steps.setup-python.outputs.python-version }} sync --dev
-      -
-        name: Patch whitenoise
-        run: |
-          curl --fail --silent --show-error --location --output 484.patch https://github.com/evansd/whitenoise/pull/484.patch
-          patch -d $(pipenv --venv)/lib/python3.10/site-packages --verbose -p2 < 484.patch
-          rm 484.patch
       -
         name: Install system dependencies
         run: |
@@ -549,7 +569,7 @@ jobs:
 
   publish-release:
     name: "Publish Release"
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     outputs:
       prerelease: ${{ steps.get_version.outputs.prerelease }}
       changelog: ${{ steps.create-release.outputs.body }}
@@ -599,7 +619,7 @@ jobs:
 
   append-changelog:
     name: "Append Changelog"
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     needs:
       - publish-release
     if: needs.publish-release.outputs.prerelease == 'false'
@@ -629,7 +649,9 @@ jobs:
           git checkout ${{ needs.publish-release.outputs.version }}-changelog
           echo -e "# Changelog\n\n${{ needs.publish-release.outputs.changelog }}\n" > changelog-new.md
           echo "Manually linking usernames"
-          sed -i -r 's|@(.+?) \(\[#|[@\1](https://github.com/\1) ([#|ig' changelog-new.md
+          sed -i -r 's|@([a-zA-Z0-9_]+) \(\[#|[@\1](https://github.com/\1) ([#|g' changelog-new.md
+          echo "Removing unneeded comment tags"
+          sed -i -r 's|@<!---->|@|g' changelog-new.md
           CURRENT_CHANGELOG=`tail --lines +2 changelog.md`
           echo -e "$CURRENT_CHANGELOG" >> changelog-new.md
           mv changelog-new.md changelog.md

.github/workflows/cleanup-tags.yml

@@ -21,7 +21,7 @@ jobs:
   cleanup-images:
     name: Cleanup Image Tags for ${{ matrix.primary-name }}
     if: github.repository_owner == 'paperless-ngx'
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     strategy:
       fail-fast: false
       matrix:
@@ -33,7 +33,7 @@ jobs:
       -
         name: Clean temporary images
         if: "${{ env.TOKEN != '' }}"
-        uses: stumpylog/image-cleaner-action/ephemeral@v0.5.0
+        uses: stumpylog/image-cleaner-action/ephemeral@v0.9.0
         with:
           token: "${{ env.TOKEN }}"
           owner: "${{ github.repository_owner }}"
@@ -47,7 +47,7 @@ jobs:
   cleanup-untagged-images:
     name: Cleanup Untagged Images Tags for ${{ matrix.primary-name }}
     if: github.repository_owner == 'paperless-ngx'
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     needs:
       - cleanup-images
     strategy:
@@ -61,7 +61,7 @@ jobs:
       -
         name: Clean untagged images
         if: "${{ env.TOKEN != '' }}"
-        uses: stumpylog/image-cleaner-action/untagged@v0.5.0
+        uses: stumpylog/image-cleaner-action/untagged@v0.9.0
         with:
           token: "${{ env.TOKEN }}"
           owner: "${{ github.repository_owner }}"

.github/workflows/codeql-analysis.yml

@@ -23,7 +23,7 @@ on:
 jobs:
   analyze:
     name: Analyze
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     permissions:
       actions: read
       contents: read

.github/workflows/crowdin.yml

@@ -15,13 +15,14 @@ on:
 jobs:
   synchronize-with-crowdin:
     name: Crowdin Sync
-    runs-on: ubuntu-latest
+    if: github.repository_owner == 'paperless-ngx'
+    runs-on: ubuntu-24.04
 
     steps:
     - name: Checkout
       uses: actions/checkout@v4
     - name: crowdin action
-      uses: crowdin/github-action@v1
+      uses: crowdin/github-action@v2
       with:
         upload_translations: false
         download_translations: true

.github/workflows/project-actions.yml

@@ -15,7 +15,7 @@ permissions:
 jobs:
   pr_opened_or_reopened:
     name: pr_opened_or_reopened
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     permissions:
       # write permission is required for autolabeler
       pull-requests: write

.github/workflows/repo-maintenance.yml

@@ -16,13 +16,14 @@ concurrency:
 jobs:
   stale:
     name: 'Stale'
-    runs-on: ubuntu-latest
+    if: github.repository_owner == 'paperless-ngx'
+    runs-on: ubuntu-24.04
     steps:
       - uses: actions/stale@v9
         with:
           days-before-stale: 7
           days-before-close: 14
-          any-of-labels: 'cant-reproduce,not a bug'
+          any-of-labels: 'stale,cant-reproduce,not a bug'
           stale-issue-label: stale
           stale-pr-label: stale
           stale-issue-message: >
@@ -31,7 +32,8 @@ jobs:
             for your contributions. See our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.
   lock-threads:
     name: 'Lock Old Threads'
-    runs-on: ubuntu-latest
+    if: github.repository_owner == 'paperless-ngx'
+    runs-on: ubuntu-24.04
     steps:
       - uses: dessant/lock-threads@v5
         with:
@@ -56,7 +58,8 @@ jobs:
             See our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.
   close-answered-discussions:
     name: 'Close Answered Discussions'
-    runs-on: ubuntu-latest
+    if: github.repository_owner == 'paperless-ngx'
+    runs-on: ubuntu-24.04
     steps:
       - uses: actions/github-script@v7
         with:
@@ -112,7 +115,8 @@ jobs:
             }
   close-outdated-discussions:
     name: 'Close Outdated Discussions'
-    runs-on: ubuntu-latest
+    if: github.repository_owner == 'paperless-ngx'
+    runs-on: ubuntu-24.04
     steps:
       - uses: actions/github-script@v7
         with:
@@ -203,7 +207,8 @@ jobs:
             }
   close-unsupported-feature-requests:
     name: 'Close Unsupported Feature Requests'
-    runs-on: ubuntu-latest
+    if: github.repository_owner == 'paperless-ngx'
+    runs-on: ubuntu-24.04
     steps:
       - uses: actions/github-script@v7
         with:
@@ -212,15 +217,20 @@ jobs:
               return new Promise(resolve => setTimeout(resolve, ms));
             }
 
+            const CUTOFF_MAX_COUNT = 80;
             const CUTOFF_1_DAYS = 180;
             const CUTOFF_1_COUNT = 5;
             const CUTOFF_2_DAYS = 365;
-            const CUTOFF_2_COUNT = 10;
+            const CUTOFF_2_COUNT = 20;
+            const CUTOFF_3_DAYS = 730;
+            const CUTOFF_3_COUNT = 40;
 
             const cutoff1Date = new Date();
             cutoff1Date.setDate(cutoff1Date.getDate() - CUTOFF_1_DAYS);
             const cutoff2Date = new Date();
             cutoff2Date.setDate(cutoff2Date.getDate() - CUTOFF_2_DAYS);
+            const cutoff3Date = new Date();
+            cutoff3Date.setDate(cutoff3Date.getDate() - CUTOFF_3_DAYS);
 
             const query = `query(
                 $owner:String!,
@@ -250,9 +260,12 @@ jobs:
             const result = await github.graphql(query, variables);
 
             for (const discussion of result.repository.discussions.nodes) {
-              const discussionDate = new Date(discussion.updatedAt);
-              if ((discussionDate < cutoff1Date && discussion.upvoteCount < CUTOFF_1_COUNT) ||
-                  (discussionDate < cutoff2Date && discussion.upvoteCount < CUTOFF_2_COUNT)) {
+              const discussionUpdatedDate = new Date(discussion.updatedAt);
+              const discussionCreatedDate = new Date(discussion.createdAt);
+              if ((discussionUpdatedDate < cutoff1Date && discussion.upvoteCount < CUTOFF_MAX_COUNT) ||
+                  (discussionCreatedDate < cutoff1Date && discussion.upvoteCount < CUTOFF_1_COUNT) ||
+                  (discussionCreatedDate < cutoff2Date && discussion.upvoteCount < CUTOFF_2_COUNT) ||
+                  (discussionCreatedDate < cutoff3Date && discussion.upvoteCount < CUTOFF_3_COUNT)) {
                 console.log(`Closing discussion #${discussion.number} (${discussion.id}), last updated at ${discussion.updatedAt} with votes ${discussion.upvoteCount}`);
                 const addCommentMutation = `mutation($discussion:ID!, $body:String!) {
                   addDiscussionComment(input:{discussionId:$discussion, body:$body}) {

.gitignore

@@ -22,6 +22,7 @@ var/
 *.egg-info/
 .installed.cfg
 *.egg
+/src/paperless_mail/templates/node_modules
 
 # PyInstaller
 #  Usually these files are written by a python script from a template
@@ -65,6 +66,8 @@ target/
 .vscode
 /src-ui/.vscode
 /docs/.vscode
+.vscode-server
+*CommandMarker
 
 # Other stuff that doesn't belong
 .virtualenv
@@ -97,3 +100,9 @@ scripts/nuke
 
 # celery schedule file
 celerybeat-schedule*
+
+# ignore .devcontainer sub folders
+/.devcontainer/consume/
+/.devcontainer/data/
+/.devcontainer/media/
+/.devcontainer/redisdata/

.pre-commit-config.yaml

@@ -5,7 +5,7 @@
 repos:
   # General hooks
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v5.0.0
     hooks:
       - id: check-docstring-first
       - id: check-json
@@ -29,15 +29,16 @@ repos:
       - id: check-case-conflict
       - id: detect-private-key
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.6
+    rev: v2.4.0
     hooks:
       - id: codespell
         exclude: "(^src-ui/src/locale/)|(^src-ui/e2e/)|(^src/paperless_mail/tests/samples/)"
         exclude_types:
           - pofile
           - json
-  - repo: https://github.com/pre-commit/mirrors-prettier
-    rev: 'v3.1.0'
+  # See https://github.com/prettier/prettier/issues/15742 for the fork reason
+  - repo: https://github.com/rbubley/mirrors-prettier
+    rev: 'v3.3.3'
     hooks:
       - id: prettier
         types_or:
@@ -45,15 +46,15 @@ repos:
           - ts
           - markdown
         exclude: "(^Pipfile\\.lock$)"
+        additional_dependencies:
+          - prettier@3.3.3
+          - 'prettier-plugin-organize-imports@4.1.0'
   # Python hooks
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.3.0'
+    rev: v0.9.6
     hooks:
       - id: ruff
-  - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 24.2.0
-    hooks:
-      - id: black
+      - id: ruff-format
   # Dockerfile hooks
   - repo: https://github.com/AleksaC/hadolint-py
     rev: v2.12.0.3
@@ -64,9 +65,11 @@ repos:
     rev: v6.2.1
     hooks:
       - id: beautysh
+        additional_dependencies:
+          - setuptools
         args:
           - "--tab"
   - repo: https://github.com/shellcheck-py/shellcheck-py
-    rev: "v0.9.0.6"
+    rev: "v0.10.0.1"
     hooks:
       - id: shellcheck

.prettierrc

@@ -1,16 +0,0 @@
-{
-    # https://prettier.io/docs/en/options.html#semicolons
-    "semi": false,
-    # https://prettier.io/docs/en/options.html#quotes
-    "singleQuote": true,
-    # https://prettier.io/docs/en/options.html#trailing-commas
-    "trailingComma": "es5",
-    "overrides": [
-        {
-            "files": ["index.md", "administration.md"],
-            "options": {
-                "tabWidth": 4
-            }
-        }
-    ]
-}

.prettierrc.js

@@ -0,0 +1,19 @@
+const config = {
+	// https://prettier.io/docs/en/options.html#semicolons
+	semi: false,
+	// https://prettier.io/docs/en/options.html#quotes
+	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')],
+}
+
+module.exports = config

.python-version

@@ -1 +1 @@
-3.9.18
+3.10.15

.ruff.toml

@@ -2,7 +2,7 @@ fix = true
 line-length = 88
 respect-gitignore = true
 src = ["src"]
-target-version = "py39"
+target-version = "py310"
 output-format = "grouped"
 show-fixes = true
 
@@ -31,17 +31,57 @@ extend-select = [
   "PLE",   # https://docs.astral.sh/ruff/rules/#pylint-pl
   "RUF",   # https://docs.astral.sh/ruff/rules/#ruff-specific-rules-ruf
   "FLY",   # https://docs.astral.sh/ruff/rules/#flynt-fly
+  "PTH",   # https://docs.astral.sh/ruff/rules/#flake8-use-pathlib-pth
+  "FBT",   # https://docs.astral.sh/ruff/rules/#flake8-boolean-trap-fbt
 ]
-# TODO PTH https://docs.astral.sh/ruff/rules/#flake8-use-pathlib-pth
 ignore = ["DJ001", "SIM105", "RUF012"]
 
 [lint.per-file-ignores]
 ".github/scripts/*.py" = ["E501", "INP001", "SIM117"]
 "docker/wait-for-redis.py" = ["INP001", "T201"]
+"src/documents/file_handling.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/management/commands/document_consumer.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/management/commands/document_exporter.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/migrations/0012_auto_20160305_0040.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/migrations/0014_document_checksum.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/migrations/1003_mime_types.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/migrations/1012_fix_archive_files.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/models.py" = ["SIM115", "PTH"]  # TODO PTH Enable & remove
+"src/documents/parsers.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/signals/handlers.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tasks.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tests/test_api_app_config.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tests/test_classifier.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tests/test_consumer.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tests/test_file_handling.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tests/test_management.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tests/test_management_consumer.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tests/test_management_exporter.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tests/test_management_thumbnails.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tests/test_migration_archive_files.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tests/test_migration_document_pages_count.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tests/test_migration_mime_type.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tests/test_sanity_check.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tests/test_tasks.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/tests/test_views.py" = ["PTH"]  # TODO Enable & remove
+"src/documents/views.py" = ["PTH"]  # TODO Enable & remove
+"src/paperless/checks.py" = ["PTH"]  # TODO Enable & remove
+"src/paperless/settings.py" = ["PTH"]  # TODO Enable & remove
+"src/paperless/tests/test_checks.py" = ["PTH"]  # TODO Enable & remove
+"src/paperless/urls.py" = ["PTH"]  # TODO Enable & remove
+"src/paperless/views.py" = ["PTH"]  # TODO Enable & remove
+"src/paperless_mail/mail.py" = ["PTH"]  # TODO Enable & remove
+"src/paperless_mail/preprocessor.py" = ["PTH"]  # TODO Enable & remove
+"src/paperless_tesseract/parsers.py" = ["PTH"]  # TODO Enable & remove
+"src/paperless_tesseract/tests/test_parser.py" = ["RUF001", "PTH"]  # TODO PTH Enable & remove
+"src/paperless_tika/tests/test_live_tika.py" = ["PTH"]  # TODO Enable & remove
+"src/paperless_tika/tests/test_tika_parser.py" = ["PTH"]  # TODO Enable & remove
+# Testing
 "*/tests/*.py" = ["E501", "SIM117"]
+# Migrations
 "*/migrations/*.py" = ["E501", "SIM", "T201"]
-"src/paperless_tesseract/tests/test_parser.py" = ["RUF001"]
-"src/documents/models.py" = ["SIM115"]
+# Docker specific
+"docker/rootfs/usr/local/bin/wait-for-redis.py" = ["INP001", "T201"]
 
 [lint.isort]
 force-single-line = true

CODE_OF_CONDUCT.md

@@ -5,7 +5,7 @@
 We as members, contributors, and leaders pledge to make participation in our
 community a harassment-free experience for everyone, regardless of age, body
 size, visible or invisible disability, ethnicity, sex characteristics, gender
-identity and expression, level of experience, education, socio-economic status,
+identity and expression, level of experience, education, socioeconomic status,
 nationality, personal appearance, race, religion, or sexual identity
 and orientation.
 

CONTRIBUTING.md

@@ -11,7 +11,7 @@ If you want to implement something big:
 
 ## Python
 
-Paperless supports python 3.9 - 3.11. We format Python code with [Black](https://github.com/psf/black).
+Paperless supports python 3.10 - 3.12 at this time. We format Python code with [ruff](https://docs.astral.sh/ruff/formatter/).
 
 ## Branches
 
@@ -147,7 +147,7 @@ community members. That said, in an effort to keep the repository organized and
 - Issues, pull requests and discussions that are closed will be locked after 30 days of inactivity.
 - Discussions with a marked answer will be automatically closed.
 - Discussions in the 'General' or 'Support' categories will be closed after 180 days of inactivity.
-- Feature requests that do not meet the following thresholds will be closed: 5 "up-votes" after 180 days of inactivity or 10 "up-votes" after 365 days.
+- Feature requests that do not meet the following thresholds will be closed: 180 days of inactivity, < 5 "up-votes" after 180 days, < 20 "up-votes" after 1 year or < 80 "up-votes" at 2 years.
 
 In all cases, threads can be re-opened by project maintainers and, of course, users can always create a new discussion for related concerns.
 Finally, remember that all information remains searchable and 'closed' feature requests can still serve as inspiration for new features.

Dockerfile

@@ -13,6 +13,16 @@ WORKDIR /src/src-ui
 RUN set -eux \
   && npm update npm -g \
   && npm ci
+
+ARG PNGX_TAG_VERSION=
+# Add the tag to the environment file if its a tagged dev build
+RUN set -eux && \
+case "${PNGX_TAG_VERSION}" in \
+  dev|beta|fix*|feature*) \
+    sed -i -E "s/version: '([0-9\.]+)'/version: '\1 #${PNGX_TAG_VERSION}'/g" /src/src-ui/src/environments/environment.prod.ts \
+    ;; \
+esac
+
 RUN set -eux \
   && ./node_modules/.bin/ng build --configuration production
 
@@ -21,7 +31,7 @@ RUN set -eux \
 # Comments:
 #  - pipenv dependencies are not left in the final image
 #  - pipenv can't touch the final image somehow
-FROM --platform=$BUILDPLATFORM docker.io/python:3.11-alpine as pipenv-base
+FROM --platform=$BUILDPLATFORM docker.io/python:3.12-alpine AS pipenv-base
 
 WORKDIR /usr/src/pipenv
 
@@ -29,15 +39,70 @@ COPY Pipfile* ./
 
 RUN set -eux \
   && echo "Installing pipenv" \
-    && python3 -m pip install --no-cache-dir --upgrade pipenv==2023.12.1 \
+    && python3 -m pip install --no-cache-dir --upgrade pipenv==2024.4.1 \
   && echo "Generating requirement.txt" \
     && pipenv requirements > requirements.txt
 
+# Stage: s6-overlay-base
+# Purpose: Installs s6-overlay and rootfs
+# Comments:
+#  - Don't leave anything extra in here either
+FROM docker.io/python:3.12-slim-bookworm AS s6-overlay-base
+
+WORKDIR /usr/src/s6
+
+# https://github.com/just-containers/s6-overlay#customizing-s6-overlay-behaviour
+ENV \
+    S6_BEHAVIOUR_IF_STAGE2_FAILS=2 \
+    S6_CMD_WAIT_FOR_SERVICES_MAXTIME=0 \
+    S6_VERBOSITY=1 \
+    PATH=/command:$PATH
+
+# Buildx provided, must be defined to use though
+ARG TARGETARCH
+ARG TARGETVARIANT
+# Lock this version
+ARG S6_OVERLAY_VERSION=3.2.0.2
+
+ARG S6_BUILD_TIME_PKGS="curl \
+                        xz-utils"
+
+RUN set -eux \
+    && echo "Installing build time packages" \
+      && apt-get update \
+      && apt-get install --yes --quiet --no-install-recommends ${S6_BUILD_TIME_PKGS} \
+    && echo "Determining arch" \
+      && S6_ARCH="" \
+      && if [ "${TARGETARCH}${TARGETVARIANT}" = "amd64" ]; then S6_ARCH="x86_64"; \
+      elif [ "${TARGETARCH}${TARGETVARIANT}" = "arm64" ]; then S6_ARCH="aarch64"; fi\
+      && if [ -z "${S6_ARCH}" ]; then { echo "Error: Not able to determine arch"; exit 1; }; fi \
+    && echo "Installing s6-overlay for ${S6_ARCH}" \
+      && curl --fail --silent --no-progress-meter --show-error --location --remote-name-all --parallel --parallel-max 4 \
+        "https://github.com/just-containers/s6-overlay/releases/download/v${S6_OVERLAY_VERSION}/s6-overlay-noarch.tar.xz" \
+        "https://github.com/just-containers/s6-overlay/releases/download/v${S6_OVERLAY_VERSION}/s6-overlay-noarch.tar.xz.sha256" \
+        "https://github.com/just-containers/s6-overlay/releases/download/v${S6_OVERLAY_VERSION}/s6-overlay-${S6_ARCH}.tar.xz" \
+        "https://github.com/just-containers/s6-overlay/releases/download/v${S6_OVERLAY_VERSION}/s6-overlay-${S6_ARCH}.tar.xz.sha256" \
+      && echo "Validating s6-archive checksums" \
+        && sha256sum --check ./*.sha256 \
+      && echo "Unpacking archives" \
+        && tar --directory / -Jxpf s6-overlay-noarch.tar.xz \
+        && tar --directory / -Jxpf s6-overlay-${S6_ARCH}.tar.xz \
+      && echo "Removing downloaded archives" \
+        && rm ./*.tar.xz \
+        && rm ./*.sha256 \
+    && echo "Cleaning up image" \
+      && apt-get --yes purge ${S6_BUILD_TIME_PKGS} \
+      && apt-get --yes autoremove --purge \
+      && rm -rf /var/lib/apt/lists/*
+
+# Copy our service defs and filesystem
+COPY ./docker/rootfs /
+
 # Stage: main-app
 # Purpose: The final image
 # Comments:
 #  - Don't leave anything extra in here
-FROM docker.io/python:3.11-slim-bookworm as main-app
+FROM s6-overlay-base AS main-app
 
 LABEL org.opencontainers.image.authors="paperless-ngx team <hello@paperless-ngx.com>"
 LABEL org.opencontainers.image.documentation="https://docs.paperless-ngx.com/"
@@ -51,9 +116,9 @@ ARG DEBIAN_FRONTEND=noninteractive
 ARG TARGETARCH
 
 # Can be workflow provided, defaults set for manual building
-ARG JBIG2ENC_VERSION=0.29
-ARG QPDF_VERSION=11.6.4
-ARG GS_VERSION=10.02.1
+ARG JBIG2ENC_VERSION=0.30
+ARG QPDF_VERSION=11.9.0
+ARG GS_VERSION=10.03.1
 
 # Set Python environment variables
 ENV PYTHONDONTWRITEBYTECODE=1 \
@@ -83,7 +148,6 @@ ARG RUNTIME_PACKAGES="\
   icc-profiles-free \
   imagemagick \
   # PostgreSQL
-  libpq5 \
   postgresql-client \
   # MySQL / MariaDB
   mariadb-client \
@@ -118,91 +182,39 @@ RUN set -eux \
     && apt-get update \
     && apt-get install --yes --quiet --no-install-recommends ${RUNTIME_PACKAGES} \
     && echo "Installing pre-built updates" \
+      && curl --fail --silent --no-progress-meter --show-error --location --remote-name-all --parallel --parallel-max 4 \
+        https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+        https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+        https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+        https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+        https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
+        https://github.com/paperless-ngx/builder/releases/download/jbig2enc-${JBIG2ENC_VERSION}/jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
       && echo "Installing qpdf ${QPDF_VERSION}" \
-        && curl --fail --silent --show-error --location \
-          --output libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-          https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-        && curl --fail --silent --show-error --location \
-          --output qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-          https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
         && dpkg --install ./libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
         && dpkg --install ./qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
       && echo "Installing Ghostscript ${GS_VERSION}" \
-        && curl --fail --silent --show-error --location \
-          --output libgs10_${GS_VERSION}.dfsg-2_${TARGETARCH}.deb \
-          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
-        && curl --fail --silent --show-error --location \
-          --output ghostscript_${GS_VERSION}.dfsg-2_${TARGETARCH}.deb \
-          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
-        && curl --fail --silent --show-error --location \
-          --output libgs10-common_${GS_VERSION}.dfsg-2_all.deb \
-          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
-        && dpkg --install ./libgs10-common_${GS_VERSION}.dfsg-2_all.deb \
-        && dpkg --install ./libgs10_${GS_VERSION}.dfsg-2_${TARGETARCH}.deb \
-        && dpkg --install ./ghostscript_${GS_VERSION}.dfsg-2_${TARGETARCH}.deb \
+        && dpkg --install ./libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
+        && dpkg --install ./libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
+        && dpkg --install ./ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
       && echo "Installing jbig2enc" \
-        && curl --fail --silent --show-error --location \
-          --output jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
-          https://github.com/paperless-ngx/builder/releases/download/jbig2enc-${JBIG2ENC_VERSION}/jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
         && dpkg --install ./jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
+      && echo "Configuring imagemagick" \
+        && cp /etc/ImageMagick-6/paperless-policy.xml /etc/ImageMagick-6/policy.xml \
       && echo "Cleaning up image layer" \
         && rm --force --verbose *.deb \
-    && rm --recursive --force --verbose /var/lib/apt/lists/* \
-  && echo "Installing supervisor" \
-    && python3 -m pip install --default-timeout=1000 --upgrade --no-cache-dir supervisor==4.2.5
+    && rm --recursive --force --verbose /var/lib/apt/lists/*
 
 # Copy gunicorn config
 # Changes very infrequently
 WORKDIR /usr/src/paperless/
 
-COPY gunicorn.conf.py .
-
-# setup docker-specific things
-# These change sometimes, but rarely
-WORKDIR /usr/src/paperless/src/docker/
-
-COPY [ \
-  "docker/imagemagick-policy.xml", \
-  "docker/supervisord.conf", \
-  "docker/docker-entrypoint.sh", \
-  "docker/docker-prepare.sh", \
-  "docker/paperless_cmd.sh", \
-  "docker/wait-for-redis.py", \
-  "docker/env-from-file.sh", \
-  "docker/management_script.sh", \
-  "docker/flower-conditional.sh", \
-  "docker/install_management_commands.sh", \
-  "/usr/src/paperless/src/docker/" \
-]
-
-RUN set -eux \
-  && echo "Configuring ImageMagick" \
-    && mv imagemagick-policy.xml /etc/ImageMagick-6/policy.xml \
-  && echo "Configuring supervisord" \
-    && mkdir /var/log/supervisord /var/run/supervisord \
-    && mv supervisord.conf /etc/supervisord.conf \
-  && echo "Setting up Docker scripts" \
-    && mv docker-entrypoint.sh /sbin/docker-entrypoint.sh \
-    && chmod 755 /sbin/docker-entrypoint.sh \
-    && mv docker-prepare.sh /sbin/docker-prepare.sh \
-    && chmod 755 /sbin/docker-prepare.sh \
-    && mv wait-for-redis.py /sbin/wait-for-redis.py \
-    && chmod 755 /sbin/wait-for-redis.py \
-    && mv env-from-file.sh /sbin/env-from-file.sh \
-    && chmod 755 /sbin/env-from-file.sh \
-    && mv paperless_cmd.sh /usr/local/bin/paperless_cmd.sh \
-    && chmod 755 /usr/local/bin/paperless_cmd.sh \
-    && mv flower-conditional.sh /usr/local/bin/flower-conditional.sh \
-    && chmod 755 /usr/local/bin/flower-conditional.sh \
-  && echo "Installing management commands" \
-    && chmod +x install_management_commands.sh \
-    && ./install_management_commands.sh
+COPY --chown=1000:1000 gunicorn.conf.py /usr/src/paperless/gunicorn.conf.py
 
 WORKDIR /usr/src/paperless/src/
 
 # Python dependencies
 # Change pretty frequently
-COPY --from=pipenv-base /usr/src/pipenv/requirements.txt ./
+COPY --chown=1000:1000 --from=pipenv-base /usr/src/pipenv/requirements.txt ./
 
 # Packages needed only for building a few quick Python
 # dependencies
@@ -215,27 +227,32 @@ ARG BUILD_PACKAGES="\
   default-libmysqlclient-dev \
   pkg-config"
 
+ARG ZXING_VERSION=2.3.0
+ARG PSYCOPG_VERSION=3.2.4
+
 # hadolint ignore=DL3042
 RUN --mount=type=cache,target=/root/.cache/pip/,id=pip-cache \
   set -eux \
   && echo "Installing build system packages" \
     && apt-get update \
     && apt-get install --yes --quiet --no-install-recommends ${BUILD_PACKAGES} \
-    && python3 -m pip install --no-cache-dir --upgrade wheel \
+    && python3 -m pip install --upgrade wheel \
   && echo "Installing Python requirements" \
-    && python3 -m pip install --default-timeout=1000 --requirement requirements.txt \
-  && echo "Patching whitenoise for compression speedup" \
-    && curl --fail --silent --show-error --location --output 484.patch https://github.com/evansd/whitenoise/pull/484.patch \
-    && patch -d /usr/local/lib/python3.11/site-packages --verbose -p2 < 484.patch \
-    && rm 484.patch \
+    && curl --fail --silent --no-progress-meter --show-error --location --remote-name-all --parallel --parallel-max 4 \
+      https://github.com/paperless-ngx/builder/releases/download/psycopg-${PSYCOPG_VERSION}/psycopg_c-${PSYCOPG_VERSION}-cp312-cp312-linux_x86_64.whl \
+      https://github.com/paperless-ngx/builder/releases/download/psycopg-${PSYCOPG_VERSION}/psycopg_c-${PSYCOPG_VERSION}-cp312-cp312-linux_aarch64.whl \
+      https://github.com/paperless-ngx/builder/releases/download/zxing-${ZXING_VERSION}/zxing_cpp-${ZXING_VERSION}-cp312-cp312-linux_aarch64.whl \
+      https://github.com/paperless-ngx/builder/releases/download/zxing-${ZXING_VERSION}/zxing_cpp-${ZXING_VERSION}-cp312-cp312-linux_x86_64.whl \
+    && python3 -m pip install --default-timeout=1000 --find-links . --requirement requirements.txt \
   && echo "Installing NLTK data" \
     && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" snowball_data \
     && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" stopwords \
-    && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" punkt \
+    && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" punkt_tab \
   && echo "Cleaning up image" \
     && apt-get --yes purge ${BUILD_PACKAGES} \
     && apt-get --yes autoremove --purge \
     && apt-get clean --yes \
+    && rm --recursive --force --verbose *.whl \
     && rm --recursive --force --verbose /var/lib/apt/lists/* \
     && rm --recursive --force --verbose /tmp/* \
     && rm --recursive --force --verbose /var/tmp/* \
@@ -259,21 +276,21 @@ RUN set -eux \
     && mkdir --parents --verbose /usr/src/paperless/media \
     && mkdir --parents --verbose /usr/src/paperless/consume \
     && mkdir --parents --verbose /usr/src/paperless/export \
+  && echo "Creating gnupg directory" \
+    && mkdir -m700 --verbose /usr/src/paperless/.gnupg \
   && echo "Adjusting all permissions" \
     && chown --from root:root --changes --recursive paperless:paperless /usr/src/paperless \
   && echo "Collecting static files" \
-    && gosu paperless python3 manage.py collectstatic --clear --no-input --link \
-    && gosu paperless python3 manage.py compilemessages
+    && s6-setuidgid paperless python3 manage.py collectstatic --clear --no-input --link \
+    && s6-setuidgid paperless python3 manage.py compilemessages
 
 VOLUME ["/usr/src/paperless/data", \
         "/usr/src/paperless/media", \
         "/usr/src/paperless/consume", \
         "/usr/src/paperless/export"]
 
-ENTRYPOINT ["/sbin/docker-entrypoint.sh"]
+ENTRYPOINT ["/init"]
 
 EXPOSE 8000
 
-CMD ["/usr/local/bin/paperless_cmd.sh"]
-
 HEALTHCHECK --interval=30s --timeout=10s --retries=5 CMD [ "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000" ]

Pipfile

@@ -7,37 +7,42 @@ name = "pypi"
 dateparser = "~=1.2"
 # WARNING: django does not use semver.
 #          Only patch versions are guaranteed to not introduce breaking changes.
-django = "~=4.2.11"
-django-allauth = "*"
+django = "~=5.1.5"
+django-allauth = {extras = ["mfa", "socialaccount"], version = "*"}
 django-auditlog = "*"
 django-celery-results = "*"
 django-compression-middleware = "*"
 django-cors-headers = "*"
 django-extensions = "*"
-django-filter = "~=23.5"
+django-filter = "~=25.1"
 django-guardian = "*"
 django-multiselectfield = "*"
-djangorestframework = "~=3.14"
+django-soft-delete = "*"
+djangorestframework = "~=3.15.2"
 djangorestframework-guardian = "*"
+drf-spectacular = "*"
+drf-spectacular-sidecar = "*"
 drf-writable-nested = "*"
 bleach = "*"
 celery = {extras = ["redis"], version = "*"}
-channels = "~=4.0"
+channels = "~=4.2"
 channels-redis = "*"
 concurrent-log-handler = "*"
 filelock = "*"
 flower = "*"
 gotenberg-client = "*"
 gunicorn = "*"
+httpx-oauth = "*"
 imap-tools = "*"
 inotifyrecursive = "~=0.3"
+jinja2 = "~=3.1"
 langdetect = "*"
 mysqlclient = "*"
 nltk = "*"
-ocrmypdf = "~=15.4"
+ocrmypdf = "~=16.9"
 pathvalidate = "*"
 pdf2image = "*"
-psycopg2 = "*"
+psycopg = {version = "*", extras = ["c"]}
 python-dateutil = "*"
 python-dotenv = "*"
 python-gnupg = "*"
@@ -46,23 +51,24 @@ python-magic = "*"
 pyzbar = "*"
 rapidfuzz = "*"
 redis = {extras = ["hiredis"], version = "*"}
-scikit-learn = "~=1.4"
+scikit-learn = "~=1.6"
 setproctitle = "*"
 tika-client = "*"
 tqdm = "*"
+# See https://github.com/paperless-ngx/paperless-ngx/issues/5494
 uvicorn = {extras = ["standard"], version = "==0.25.0"}
-watchdog = "~=4.0"
-whitenoise = "~=6.6"
-whoosh="~=2.7"
-zxing-cpp = {version = "*", platform_machine = "== 'x86_64'"}
+watchdog = "~=6.0"
+whitenoise = "~=6.9"
+whoosh = "~=2.7"
+zxing-cpp = "*"
+
 
 [dev-packages]
 # Linting
-black = "*"
 pre-commit = "*"
 ruff = "*"
-# Testing
 factory-boy = "*"
+# Testing
 pytest = "*"
 pytest-cov = "*"
 pytest-django = "*"
@@ -70,6 +76,7 @@ pytest-httpx = "*"
 pytest-env = "*"
 pytest-sugar = "*"
 pytest-xdist = "*"
+pytest-mock = "*"
 pytest-rerunfailures = "*"
 imagehash = "*"
 daphne = "*"
@@ -92,5 +99,4 @@ types-tqdm = "*"
 types-Markdown = "*"
 types-Pygments = "*"
 types-colorama = "*"
-types-psycopg2 = "*"
 types-setuptools = "*"

README.md

@@ -30,14 +30,14 @@ Thanks to the generous folks at [DigitalOcean](https://m.do.co/c/8d70b916d462),
   - [Translation](#translation)
   - [Feature Requests](#feature-requests)
   - [Bugs](#bugs)
-- [Affiliated Projects](#affiliated-projects)
+- [Related Projects](#related-projects)
 - [Important Note](#important-note)
 
 <p align="right">This project is supported by:<br/>
   <a href="https://m.do.co/c/8d70b916d462" style="padding-top: 4px; display: block;">
     <picture>
       <source media="(prefers-color-scheme: dark)" srcset="https://opensource.nyc3.cdn.digitaloceanspaces.com/attribution/assets/SVG/DO_Logo_horizontal_white.svg" width="140px">
-      <source media="(prefers-color-scheme: light)" srcset="https://opensource.nyc3.cdn.digitaloceanspaces.com/attribution/assets/SVG/DO_Logo_horizontal_black_.svg" width="140px">
+      <source media="(prefers-color-scheme: light)" srcset="https://opensource.nyc3.cdn.digitaloceanspaces.com/attribution/assets/SVG/DO_Logo_horizontal_blue.svg" width="140px">
       <img src="https://opensource.nyc3.cdn.digitaloceanspaces.com/attribution/assets/SVG/DO_Logo_horizontal_black_.svg" width="140px">
     </picture>
   </a>
@@ -55,7 +55,7 @@ A full list of [features](https://docs.paperless-ngx.com/#features) and [screens
 
 # Getting started
 
-The easiest way to deploy paperless is `docker compose`. The files in the [`/docker/compose` directory](https://github.com/paperless-ngx/paperless-ngx/tree/main/docker/compose) are configured to pull the image from GitHub Packages.
+The easiest way to deploy paperless is `docker compose`. The files in the [`/docker/compose` directory](https://github.com/paperless-ngx/paperless-ngx/tree/main/docker/compose) are configured to pull the image from the GitHub container registry.
 
 If you'd like to jump right in, you can configure a `docker compose` environment with our install script:
 
@@ -63,7 +63,7 @@ If you'd like to jump right in, you can configure a `docker compose` environment
 bash -c "$(curl -L https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/install-paperless-ngx.sh)"
 ```
 
-Alternatively, you can install the dependencies and setup apache and a database server yourself. The [documentation](https://docs.paperless-ngx.com/setup/#installation) has a step by step guide on how to do it.
+More details and step-by-step guides for alternative installation methods can be found in [the documentation](https://docs.paperless-ngx.com/setup/#installation).
 
 Migrating from Paperless-ng is easy, just drop in the new docker image! See the [documentation on migrating](https://docs.paperless-ngx.com/setup/#migrating-to-paperless-ngx) for more details.
 
@@ -93,9 +93,9 @@ Feature requests can be submitted via [GitHub Discussions](https://github.com/pa
 
 For bugs please [open an issue](https://github.com/paperless-ngx/paperless-ngx/issues) or [start a discussion](https://github.com/paperless-ngx/paperless-ngx/discussions) if you have questions.
 
-# Affiliated Projects
+# Related Projects
 
-Please see [the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Affiliated-Projects) for a user-maintained list of affiliated projects and software that is compatible with Paperless-ngx.
+Please see [the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Related-Projects) for a user-maintained list of related projects and software that is compatible with Paperless-ngx.
 
 # Important Note
 

docker/compose/docker-compose.ci-test.yml

@@ -3,10 +3,9 @@
 # Can be used locally or by the CI to start the necessary containers with the
 # correct networking for the tests
 
-version: "3.7"
 services:
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:7.10
+    image: docker.io/gotenberg/gotenberg:8.7
     hostname: gotenberg
     container_name: gotenberg
     network_mode: host
@@ -20,7 +19,7 @@ services:
       - "--log-level=warn"
       - "--log-format=text"
   tika:
-    image: ghcr.io/paperless-ngx/tika:latest
+    image: docker.io/apache/tika:latest
     hostname: tika
     container_name: tika
     network_mode: host

docker/compose/docker-compose.env

@@ -1,26 +1,17 @@
+###############################################################################
+# Paperless-ngx settings                                                      #
+###############################################################################
+
+# See http://docs.paperless-ngx.com/configuration/ for all available options.
+
 # The UID and GID of the user used to run paperless in the container. Set this
 # to your UID and GID on the host so that you have write access to the
 # consumption directory.
 #USERMAP_UID=1000
 #USERMAP_GID=1000
 
-# Additional languages to install for text recognition, separated by a
-# whitespace. Note that this is
-# different from PAPERLESS_OCR_LANGUAGE (default=eng), which defines the
-# language used for OCR.
-# The container installs English, German, Italian, Spanish and French by
-# default.
-# See https://packages.debian.org/search?keywords=tesseract-ocr-&searchon=names&suite=buster
-# for available languages.
-#PAPERLESS_OCR_LANGUAGES=tur ces
-
-###############################################################################
-# Paperless-specific settings                                                 #
-###############################################################################
-
-# All settings defined in the paperless.conf.example can be used here. The
-# Docker setup does not use the configuration file.
-# A few commonly adjusted settings are provided below.
+# See the documentation linked above for all options. A few commonly adjusted settings
+# are provided below.
 
 # This is required if you will be exposing Paperless-ngx on a public domain
 # (if doing so please consider security measures such as reverse proxy)
@@ -30,13 +21,17 @@
 # be a very long sequence of random characters. You don't need to remember it.
 #PAPERLESS_SECRET_KEY=change-me
 
-# Use this variable to set a timezone for the Paperless Docker containers. If not specified, defaults to UTC.
+# Use this variable to set a timezone for the Paperless Docker containers. Defaults to UTC.
 #PAPERLESS_TIME_ZONE=America/Los_Angeles
 
 # The default language to use for OCR. Set this to the language most of your
 # documents are written in.
 #PAPERLESS_OCR_LANGUAGE=eng
 
-# Set if accessing paperless via a domain subpath e.g. https://domain.com/PATHPREFIX and using a reverse-proxy like traefik or nginx
-#PAPERLESS_FORCE_SCRIPT_NAME=/PATHPREFIX
-#PAPERLESS_STATIC_URL=/PATHPREFIX/static/ # trailing slash required
+# Additional languages to install for text recognition, separated by a whitespace.
+# Note that this is different from PAPERLESS_OCR_LANGUAGE (default=eng), which defines
+# the language used for OCR.
+# The container installs English, German, Italian, Spanish and French by default.
+# See https://packages.debian.org/search?keywords=tesseract-ocr-&searchon=names&suite=buster
+# for available languages.
+#PAPERLESS_OCR_LANGUAGES=tur ces

docker/compose/docker-compose.mariadb-tika.yml

@@ -30,7 +30,6 @@
 # For more extensive installation and update instructions, refer to the
 # documentation.
 
-version: "3.4"
 services:
   broker:
     image: docker.io/library/redis:7
@@ -39,7 +38,7 @@ services:
       - redisdata:/data
 
   db:
-    image: docker.io/library/mariadb:10
+    image: docker.io/library/mariadb:11
     restart: unless-stopped
     volumes:
       - dbdata:/var/lib/mysql
@@ -78,7 +77,7 @@ services:
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
 
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:7.10
+    image: docker.io/gotenberg/gotenberg:8.7
     restart: unless-stopped
     # The gotenberg chromium route is used to convert .eml files. We do not
     # want to allow external content like tracking pixels or even javascript.
@@ -88,7 +87,7 @@ services:
       - "--chromium-allow-list=file:///tmp/.*"
 
   tika:
-    image: ghcr.io/paperless-ngx/tika:latest
+    image: docker.io/apache/tika:latest
     restart: unless-stopped
 
 volumes:

docker/compose/docker-compose.mariadb.yml

@@ -26,7 +26,6 @@
 # For more extensive installation and update instructions, refer to the
 # documentation.
 
-version: "3.4"
 services:
   broker:
     image: docker.io/library/redis:7
@@ -35,7 +34,7 @@ services:
       - redisdata:/data
 
   db:
-    image: docker.io/library/mariadb:10
+    image: docker.io/library/mariadb:11
     restart: unless-stopped
     volumes:
       - dbdata:/var/lib/mysql

docker/compose/docker-compose.portainer.yml

@@ -19,6 +19,8 @@
 #
 # - Open portainer Stacks list and click 'Add stack'
 # - Paste the contents of this file and assign a name, e.g. 'paperless'
+# - Upload 'docker-compose.env' by clicking on 'Load variables from .env file'
+# - Modify the environment variables as needed
 # - Click 'Deploy the stack' and wait for it to be deployed
 # - Open the list of containers, select paperless_webserver_1
 # - Click 'Console' and then 'Connect' to open the command line inside the container
@@ -28,7 +30,6 @@
 # For more extensive installation and update instructions, refer to the
 # documentation.
 
-version: "3.4"
 services:
   broker:
     image: docker.io/library/redis:7
@@ -37,7 +38,7 @@ services:
       - redisdata:/data
 
   db:
-    image: docker.io/library/postgres:15
+    image: docker.io/library/postgres:16
     restart: unless-stopped
     volumes:
       - pgdata:/var/lib/postgresql/data
@@ -62,28 +63,8 @@ services:
     environment:
       PAPERLESS_REDIS: redis://broker:6379
       PAPERLESS_DBHOST: db
-# The UID and GID of the user used to run paperless in the container. Set this
-# to your UID and GID on the host so that you have write access to the
-# consumption directory.
-      USERMAP_UID: 1000
-      USERMAP_GID: 100
-# Additional languages to install for text recognition, separated by a
-# whitespace. Note that this is
-# different from PAPERLESS_OCR_LANGUAGE (default=eng), which defines the
-# language used for OCR.
-# The container installs English, German, Italian, Spanish and French by
-# default.
-# See https://packages.debian.org/search?keywords=tesseract-ocr-&searchon=names&suite=buster
-# for available languages.
-      #PAPERLESS_OCR_LANGUAGES: tur ces
-# Adjust this key if you plan to make paperless available publicly. It should
-# be a very long sequence of random characters. You don't need to remember it.
-      #PAPERLESS_SECRET_KEY: change-me
-# Use this variable to set a timezone for the Paperless Docker containers. If not specified, defaults to UTC.
-      #PAPERLESS_TIME_ZONE: America/Los_Angeles
-# The default language to use for OCR. Set this to the language most of your
-# documents are written in.
-      #PAPERLESS_OCR_LANGUAGE: eng
+    env_file:
+      - stack.env
 
 volumes:
   data:

docker/compose/docker-compose.postgres-tika.yml

@@ -30,7 +30,6 @@
 # For more extensive installation and update instructions, refer to the
 # documentation.
 
-version: "3.4"
 services:
   broker:
     image: docker.io/library/redis:7
@@ -39,7 +38,7 @@ services:
       - redisdata:/data
 
   db:
-    image: docker.io/library/postgres:15
+    image: docker.io/library/postgres:16
     restart: unless-stopped
     volumes:
       - pgdata:/var/lib/postgresql/data
@@ -72,7 +71,7 @@ services:
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
 
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:7.10
+    image: docker.io/gotenberg/gotenberg:8.7
     restart: unless-stopped
 
     # The gotenberg chromium route is used to convert .eml files. We do not
@@ -83,7 +82,7 @@ services:
       - "--chromium-allow-list=file:///tmp/.*"
 
   tika:
-    image: ghcr.io/paperless-ngx/tika:latest
+    image: docker.io/apache/tika:latest
     restart: unless-stopped
 
 volumes:

docker/compose/docker-compose.postgres.yml

@@ -26,7 +26,6 @@
 # For more extensive installation and update instructions, refer to the
 # documentation.
 
-version: "3.4"
 services:
   broker:
     image: docker.io/library/redis:7
@@ -35,7 +34,7 @@ services:
       - redisdata:/data
 
   db:
-    image: docker.io/library/postgres:15
+    image: docker.io/library/postgres:16
     restart: unless-stopped
     volumes:
       - pgdata:/var/lib/postgresql/data

docker/compose/docker-compose.sqlite-tika.yml

@@ -30,7 +30,6 @@
 # For more extensive installation and update instructions, refer to the
 # documentation.
 
-version: "3.4"
 services:
   broker:
     image: docker.io/library/redis:7
@@ -60,7 +59,7 @@ services:
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
 
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:7.10
+    image: docker.io/gotenberg/gotenberg:8.7
     restart: unless-stopped
 
     # The gotenberg chromium route is used to convert .eml files. We do not
@@ -71,7 +70,7 @@ services:
       - "--chromium-allow-list=file:///tmp/.*"
 
   tika:
-    image: ghcr.io/paperless-ngx/tika:latest
+    image: docker.io/apache/tika:latest
     restart: unless-stopped
 
 volumes:

docker/compose/docker-compose.sqlite.yml

@@ -23,7 +23,6 @@
 # For more extensive installation and update instructions, refer to the
 # documentation.
 
-version: "3.4"
 services:
   broker:
     image: docker.io/library/redis:7

docker/docker-entrypoint.sh

@@ -10,8 +10,8 @@ map_uidgid() {
 	local -r usermap_new_gid=${USERMAP_GID:-${usermap_original_gid:-$usermap_new_uid}}
 	if [[ ${usermap_new_uid} != "${usermap_original_uid}" || ${usermap_new_gid} != "${usermap_original_gid}" ]]; then
 		echo "Mapping UID and GID for paperless:paperless to $usermap_new_uid:$usermap_new_gid"
-		usermod -o -u "${usermap_new_uid}" paperless
-		groupmod -o -g "${usermap_new_gid}" paperless
+		usermod --non-unique --uid "${usermap_new_uid}" paperless
+		groupmod --non-unique --gid "${usermap_new_gid}" paperless
 	fi
 }
 
@@ -42,7 +42,7 @@ custom_container_init() {
 		fi
 
 		# Make sure custom init directory has files in it
-		if [ -n "$(/bin/ls -A "${custom_script_dir}" 2>/dev/null)" ]; then
+		if [ -n "$(/bin/ls --almost-all "${custom_script_dir}" 2>/dev/null)" ]; then
 			echo "[custom-init] files found in ${custom_script_dir} executing"
 			# Loop over files in the directory
 			for SCRIPT in "${custom_script_dir}"/*; do
@@ -86,13 +86,13 @@ initialize() {
 		"${CONSUME_DIR}"; do
 		if [[ ! -d "${dir}" ]]; then
 			echo "Creating directory ${dir}"
-			mkdir --parents "${dir}"
+			mkdir --parents --verbose "${dir}"
 		fi
 	done
 
 	local -r tmp_dir="${PAPERLESS_SCRATCH_DIR:=/tmp/paperless}"
 	echo "Creating directory scratch directory ${tmp_dir}"
-	mkdir --parents "${tmp_dir}"
+	mkdir --parents --verbose "${tmp_dir}"
 
 	set +e
 	echo "Adjusting permissions of paperless files. This may take a while."
@@ -102,7 +102,7 @@ initialize() {
 		"${DATA_DIR}" \
 		"${MEDIA_ROOT_DIR}" \
 		"${CONSUME_DIR}"; do
-		find "${dir}" -not \( -user paperless -and -group paperless \) -exec chown paperless:paperless {} +
+		find "${dir}" -not \( -user paperless -and -group paperless \) -exec chown --changes paperless:paperless {} +
 	done
 	set -e
 
@@ -122,33 +122,44 @@ install_languages() {
 	if [ ${#langs[@]} -eq 0 ]; then
 		return
 	fi
-	apt-get update
 
+	# Build list of packages to install
+	to_install=()
 	for lang in "${langs[@]}"; do
 		pkg="tesseract-ocr-$lang"
 
-		if dpkg -s "$pkg" &>/dev/null; then
+		if dpkg --status "$pkg" &>/dev/null; then
 			echo "Package $pkg already installed!"
 			continue
-		fi
-
-		if ! apt-cache show "$pkg" &>/dev/null; then
-			echo "Package $pkg not found! :("
-			continue
-		fi
-
-		echo "Installing package $pkg..."
-		if ! apt-get -y install "$pkg" &>/dev/null; then
-			echo "Could not install $pkg"
-			exit 1
+		else
+			to_install+=("$pkg")
 		fi
 	done
+
+	# Use apt only when we install packages
+	if [ ${#to_install[@]} -gt 0 ]; then
+		apt-get update
+
+		for pkg in "${to_install[@]}"; do
+
+			if ! apt-cache show "$pkg" &>/dev/null; then
+				echo "Skipped $pkg: Package not found! :("
+				continue
+			fi
+
+			echo "Installing package $pkg..."
+			if ! apt-get --assume-yes install "$pkg" &>/dev/null; then
+				echo "Could not install $pkg"
+				exit 1
+			fi
+		done
+	fi
 }
 
 echo "Paperless-ngx docker container starting..."
 
 gosu_cmd=(gosu paperless)
-if [ "$(id -u)" == "$(id -u paperless)" ]; then
+if [ "$(id --user)" == "$(id --user paperless)" ]; then
 	gosu_cmd=()
 fi
 

docker/docker-prepare.sh

@@ -1,118 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-
-wait_for_postgres() {
-	local attempt_num=1
-	local -r max_attempts=5
-
-	echo "Waiting for PostgreSQL to start..."
-
-	local -r host="${PAPERLESS_DBHOST:-localhost}"
-	local -r port="${PAPERLESS_DBPORT:-5432}"
-
-	# Disable warning, host and port can't have spaces
-	# shellcheck disable=SC2086
-	while [ ! "$(pg_isready -h ${host} -p ${port})" ]; do
-
-		if [ $attempt_num -eq $max_attempts ]; then
-			echo "Unable to connect to database."
-			exit 1
-		else
-			echo "Attempt $attempt_num failed! Trying again in 5 seconds..."
-		fi
-
-		attempt_num=$(("$attempt_num" + 1))
-		sleep 5
-	done
-}
-
-wait_for_mariadb() {
-	echo "Waiting for MariaDB to start..."
-
-	local -r host="${PAPERLESS_DBHOST:=localhost}"
-	local -r port="${PAPERLESS_DBPORT:=3306}"
-
-	local attempt_num=1
-	local -r max_attempts=5
-
-	# Disable warning, host and port can't have spaces
-	# shellcheck disable=SC2086
-	while ! true > /dev/tcp/$host/$port; do
-
-		if [ $attempt_num -eq $max_attempts ]; then
-			echo "Unable to connect to database."
-			exit 1
-		else
-			echo "Attempt $attempt_num failed! Trying again in 5 seconds..."
-
-		fi
-
-		attempt_num=$(("$attempt_num" + 1))
-		sleep 5
-	done
-}
-
-wait_for_redis() {
-	# We use a Python script to send the Redis ping
-	# instead of installing redis-tools just for 1 thing
-	if ! python3 /sbin/wait-for-redis.py; then
-		exit 1
-	fi
-}
-
-migrations() {
-	(
-		# flock is in place to prevent multiple containers from doing migrations
-		# simultaneously. This also ensures that the db is ready when the command
-		# of the current container starts.
-		flock 200
-		echo "Apply database migrations..."
-		python3 manage.py migrate --skip-checks --no-input
-	) 200>"${DATA_DIR}/migration_lock"
-}
-
-django_checks() {
-	# Explicitly run the Django system checks
-	echo "Running Django checks"
-	python3 manage.py check
-}
-
-search_index() {
-
-	local -r index_version=8
-	local -r index_version_file=${DATA_DIR}/.index_version
-
-	if [[ (! -f "${index_version_file}") || $(<"${index_version_file}") != "$index_version" ]]; then
-		echo "Search index out of date. Updating..."
-		python3 manage.py document_index reindex --no-progress-bar
-		echo ${index_version} | tee "${index_version_file}" >/dev/null
-	fi
-}
-
-superuser() {
-	if [[ -n "${PAPERLESS_ADMIN_USER}" ]]; then
-		python3 manage.py manage_superuser
-	fi
-}
-
-do_work() {
-	if [[ "${PAPERLESS_DBENGINE}" == "mariadb" ]]; then
-		wait_for_mariadb
-	elif [[ -n "${PAPERLESS_DBHOST}" ]]; then
-		wait_for_postgres
-	fi
-
-	wait_for_redis
-
-	migrations
-
-	django_checks
-
-	search_index
-
-	superuser
-
-}
-
-do_work

docker/env-from-file.sh

@@ -1,42 +0,0 @@
-#!/usr/bin/env bash
-
-# Scans the environment variables for those with the suffix _FILE
-# When located, checks the file exists, and exports the contents
-# of the file as the same name, minus the suffix
-# This allows the use of Docker secrets or mounted files
-# to fill in any of the settings configurable via environment
-# variables
-
-set -eu
-
-for line in $(printenv)
-do
-	# Extract the name of the environment variable
-	env_name=${line%%=*}
-	# Check if it starts with "PAPERLESS_" and ends in "_FILE"
-	if [[ ${env_name} == PAPERLESS_*_FILE ]]; then
-		# This should have been named different..
-		if [[ ${env_name} == "PAPERLESS_OCR_SKIP_ARCHIVE_FILE" ]]; then
-			continue
-		fi
-		# Extract the value of the environment
-		env_value=${line#*=}
-
-		# Check the file exists
-		if [[ -f ${env_value} ]]; then
-
-			# Trim off the _FILE suffix
-			non_file_env_name=${env_name%"_FILE"}
-			echo "Setting ${non_file_env_name} from file"
-
-			# Reads the value from th file
-			val="$(< "${!env_name}")"
-
-			# Sets the normal name to the read file contents
-			export "${non_file_env_name}"="${val}"
-
-		else
-			echo "File ${env_value} referenced by ${env_name} doesn't exist"
-		fi
-	fi
-done

docker/flower-conditional.sh

@@ -1,12 +0,0 @@
-#!/usr/bin/env bash
-
-echo "Checking if we should start flower..."
-
-if [[ -n  "${PAPERLESS_ENABLE_FLOWER}" ]]; then
-	# Small delay to allow celery to be up first
-	echo "Starting flower in 5s"
-	sleep 5
-	celery --app paperless flower --conf=/usr/src/paperless/src/paperless/flowerconfig.py
-else
-	echo "Not starting flower"
-fi

docker/install_management_commands.sh

@@ -1,5 +1,7 @@
 #!/usr/bin/env bash
 
+# Run this script to generate the management commands again (for example if a new command is create or the template is updated)
+
 set -eu
 
 for command in decrypt_documents \
@@ -14,9 +16,11 @@ for command in decrypt_documents \
 	document_thumbnails \
 	document_sanity_checker \
 	document_fuzzy_match \
-	manage_superuser;
+	manage_superuser \
+	convert_mariadb_uuid \
+	prune_audit_logs;
 do
 	echo "installing $command..."
-	sed "s/management_command/$command/g" management_script.sh > /usr/local/bin/$command
-	chmod +x /usr/local/bin/$command
+	sed "s/management_command/$command/g" management_script.sh >"$PWD/rootfs/usr/local/bin/$command"
+	chmod +x "$PWD/rootfs/usr/local/bin/$command"
 done

docker/management_script.sh

@@ -1,17 +1,13 @@
-#!/usr/bin/env bash
+#!/command/with-contenv /usr/bin/bash
+# shellcheck shell=bash
 
 set -e
 
-cd /usr/src/paperless/src/
-# This ensures environment is setup
-# shellcheck disable=SC1091
-source /sbin/env-from-file.sh
+cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]] ;
-then
-	gosu paperless python3 manage.py management_command "$@"
-elif [[ $(id -un) == "paperless" ]] ;
-then
+if [[ $(id -u) == 0 ]]; then
+	s6-setuidgid paperless python3 manage.py management_command "$@"
+elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py management_command "$@"
 else
 	echo "Unknown user."

docker/paperless_cmd.sh

@@ -1,16 +0,0 @@
-#!/usr/bin/env bash
-
-SUPERVISORD_WORKING_DIR="${PAPERLESS_SUPERVISORD_WORKING_DIR:-$PWD}"
-rootless_args=()
-if [ "$(id -u)" == "$(id -u paperless)" ]; then
-	rootless_args=(
-		--user
-		paperless
-		--logfile
-		"${SUPERVISORD_WORKING_DIR}/supervisord.log"
-		--pidfile
-		"${SUPERVISORD_WORKING_DIR}/supervisord.pid"
-	)
-fi
-
-exec /usr/local/bin/supervisord -c /etc/supervisord.conf "${rootless_args[@]}"

docker/rootfs/etc/s6-overlay/s6-rc.d/init-complete/run

@@ -0,0 +1,8 @@
+#!/command/with-contenv /usr/bin/bash
+# shellcheck shell=bash
+declare -r log_prefix="[init-complete]"
+declare -r end_time=$(date +%s)
+declare -r start_time=${PAPERLESS_START_TIME_S}
+
+echo "${log_prefix} paperless-ngx docker container init completed in $(($end_time-$start_time)) seconds"
+echo "${log_prefix} Starting services"

docker/rootfs/etc/s6-overlay/s6-rc.d/init-complete/type

@@ -0,0 +1 @@
+oneshot

docker/rootfs/etc/s6-overlay/s6-rc.d/init-complete/up

@@ -0,0 +1 @@
+/etc/s6-overlay/s6-rc.d/init-complete/run

docker/rootfs/etc/s6-overlay/s6-rc.d/init-custom-init/run

@@ -0,0 +1,44 @@
+#!/command/with-contenv /usr/bin/bash
+# shellcheck shell=bash
+
+declare -r log_prefix="[custom-init]"
+
+# Mostly borrowed from the LinuxServer.io base image
+# https://github.com/linuxserver/docker-baseimage-ubuntu/tree/bionic/root/etc/cont-init.d
+declare -r custom_script_dir="/custom-cont-init.d"
+
+# Tamper checking.
+# Don't run files which are owned by anyone except root
+# Don't run files which are writeable by others
+if [ -d "${custom_script_dir}" ]; then
+	if [ -n "$(/usr/bin/find "${custom_script_dir}" -maxdepth 1 ! -user root)" ]; then
+		echo "${log_prefix} **** Potential tampering with custom scripts detected ****"
+		echo "${log_prefix} **** The folder '${custom_script_dir}' must be owned by root ****"
+		exit 0
+	fi
+	if [ -n "$(/usr/bin/find "${custom_script_dir}" -maxdepth 1 -perm -o+w)" ]; then
+		echo "${log_prefix} **** The folder '${custom_script_dir}' or some of contents have write permissions for others, which is a security risk. ****"
+		echo "${log_prefix} **** Please review the permissions and their contents to make sure they are owned by root, and can only be modified by root. ****"
+		exit 0
+	fi
+
+	# Make sure custom init directory has files in it
+	if [ -n "$(/bin/ls --almost-all "${custom_script_dir}" 2>/dev/null)" ]; then
+		echo "${log_prefix} files found in ${custom_script_dir} executing"
+		# Loop over files in the directory
+		for SCRIPT in "${custom_script_dir}"/*; do
+			NAME="$(basename "${SCRIPT}")"
+			if [ -f "${SCRIPT}" ]; then
+				echo "${log_prefix} ${NAME}: executing..."
+				/command/with-contenv /bin/bash "${SCRIPT}"
+				echo "${log_prefix} ${NAME}: exited $?"
+			elif [ ! -f "${SCRIPT}" ]; then
+				echo "${log_prefix} ${NAME}: is not a file"
+			fi
+		done
+	else
+		echo "${log_prefix} no custom files found exiting..."
+	fi
+else
+	echo "${log_prefix} ${custom_script_dir} doesn't exist, nothing to do"
+fi

docker/rootfs/etc/s6-overlay/s6-rc.d/init-custom-init/type

@@ -0,0 +1 @@
+oneshot

docker/rootfs/etc/s6-overlay/s6-rc.d/init-custom-init/up

@@ -0,0 +1 @@
+/etc/s6-overlay/s6-rc.d/init-custom-init/run

docker/rootfs/etc/s6-overlay/s6-rc.d/init-env-file/run

@@ -0,0 +1,30 @@
+#!/command/with-contenv /usr/bin/bash
+# shellcheck shell=bash
+
+declare -r log_prefix="[env-init]"
+
+echo "${log_prefix} Checking for environment from files"
+
+if find /run/s6/container_environment/*"_FILE" -maxdepth 1 > /dev/null 2>&1; then
+	for FILENAME in /run/s6/container_environment/*; do
+		if [[ "${FILENAME##*/}" == PAPERLESS_*_FILE ]]; then
+			# This should have been named different..
+			if [[ ${FILENAME} == "PAPERLESS_OCR_SKIP_ARCHIVE_FILE" || ${FILENAME} == "PAPERLESS_MODEL_FILE" ]]; then
+				continue
+			fi
+			SECRETFILE=$(cat "${FILENAME}")
+			# Check the file exists
+			if [[ -f ${SECRETFILE} ]]; then
+				# Trim off trailing _FILE
+				FILESTRIP=${FILENAME//_FILE/}
+				# Set environment variable
+				cat "${SECRETFILE}" > "${FILESTRIP}"
+				echo "${log_prefix} ${FILESTRIP##*/} set from ${FILENAME##*/}"
+			else
+				echo "${log_prefix} cannot find secret in ${FILENAME##*/}"
+			fi
+		fi
+	done
+else
+		echo "${log_prefix} No *_FILE environment found"
+fi

docker/rootfs/etc/s6-overlay/s6-rc.d/init-env-file/type

@@ -0,0 +1 @@
+oneshot

docker/rootfs/etc/s6-overlay/s6-rc.d/init-env-file/up

@@ -0,0 +1 @@
+/etc/s6-overlay/s6-rc.d/init-env-file/run

docker/rootfs/etc/s6-overlay/s6-rc.d/init-folders/run

@@ -0,0 +1,33 @@
+#!/command/with-contenv /usr/bin/bash
+# shellcheck shell=bash
+
+declare -r log_prefix="[init-folders]"
+
+declare -r export_dir="/usr/src/paperless/export"
+declare -r data_dir="${PAPERLESS_DATA_DIR:-/usr/src/paperless/data}"
+declare -r media_root_dir="${PAPERLESS_MEDIA_ROOT:-/usr/src/paperless/media}"
+declare -r consume_dir="${PAPERLESS_CONSUMPTION_DIR:-/usr/src/paperless/consume}"
+declare -r tmp_dir="${PAPERLESS_SCRATCH_DIR:=/tmp/paperless}"
+
+echo "${log_prefix} Checking for folder existence"
+
+for dir in \
+	"${export_dir}" \
+	"${data_dir}" "${data_dir}/index" \
+	"${media_root_dir}" "${media_root_dir}/documents" "${media_root_dir}/documents/originals" "${media_root_dir}/documents/thumbnails" \
+	"${consume_dir}" \
+	"${tmp_dir}"; do
+	if [[ ! -d "${dir}" ]]; then
+		mkdir --parents --verbose "${dir}"
+	fi
+done
+
+echo "${log_prefix} Adjusting file and folder permissions"
+for dir in \
+	"${export_dir}" \
+	"${data_dir}" \
+	"${media_root_dir}" \
+	"${consume_dir}" \
+	"${tmp_dir}"; do
+	find "${dir}" -not \( -user paperless -and -group paperless \) -exec chown --changes paperless:paperless {} +
+done

docker/rootfs/etc/s6-overlay/s6-rc.d/init-folders/type

@@ -0,0 +1 @@
+oneshot

docker/rootfs/etc/s6-overlay/s6-rc.d/init-folders/up

@@ -0,0 +1 @@
+/etc/s6-overlay/s6-rc.d/init-folders/run

docker/rootfs/etc/s6-overlay/s6-rc.d/init-migrations/run

@@ -0,0 +1,20 @@
+#!/command/with-contenv /usr/bin/bash
+# shellcheck shell=bash
+declare -r log_prefix="[init-migrations]"
+declare -r data_dir="${PAPERLESS_DATA_DIR:-/usr/src/paperless/data}"
+
+(
+	# flock is in place to prevent multiple containers from doing migrations
+	# simultaneously. This also ensures that the db is ready when the command
+	# of the current container starts.
+	flock 200
+	echo "${log_prefix} Apply database migrations..."
+	cd "${PAPERLESS_SRC_DIR}"
+
+	if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+		exec python3 manage.py migrate --skip-checks --no-input
+	else
+		exec s6-setuidgid paperless python3 manage.py migrate --skip-checks --no-input
+	fi
+
+) 200>"${data_dir}/migration_lock"

docker/rootfs/etc/s6-overlay/s6-rc.d/init-migrations/type

@@ -0,0 +1 @@
+oneshot

docker/rootfs/etc/s6-overlay/s6-rc.d/init-migrations/up

@@ -0,0 +1 @@
+/etc/s6-overlay/s6-rc.d/init-migrations/run

docker/rootfs/etc/s6-overlay/s6-rc.d/init-modify-user/run

@@ -0,0 +1,22 @@
+#!/command/with-contenv /usr/bin/bash
+# shellcheck shell=bash
+declare -r log_prefix="[init-user]"
+
+declare -r usermap_original_uid=$(id -u paperless)
+declare -r usermap_original_gid=$(id -g paperless)
+declare -r usermap_new_uid=${USERMAP_UID:-$usermap_original_uid}
+declare -r usermap_new_gid=${USERMAP_GID:-${usermap_original_gid:-$usermap_new_uid}}
+
+if [[ ${usermap_new_uid} != "${usermap_original_uid}" ]]; then
+	echo "${log_prefix} Mapping UID for paperless to $usermap_new_uid"
+	usermod --non-unique --uid "${usermap_new_uid}" paperless
+else
+	echo "${log_prefix} No UID changes for paperless"
+fi
+
+if [[ ${usermap_new_gid} != "${usermap_original_gid}" ]]; then
+	echo "${log_prefix} Mapping GID for paperless to $usermap_new_gid"
+	groupmod --non-unique --gid "${usermap_new_gid}" paperless
+else
+	echo "${log_prefix} No GID changes for paperless"
+fi

docker/rootfs/etc/s6-overlay/s6-rc.d/init-modify-user/type

@@ -0,0 +1 @@
+oneshot

docker/rootfs/etc/s6-overlay/s6-rc.d/init-modify-user/up

@@ -0,0 +1 @@
+/etc/s6-overlay/s6-rc.d/init-modify-user/run

docker/rootfs/etc/s6-overlay/s6-rc.d/init-search-index/run

@@ -0,0 +1,28 @@
+#!/command/with-contenv /usr/bin/bash
+# shellcheck shell=bash
+
+declare -r log_prefix="[init-index]"
+
+declare -r index_version=9
+declare -r data_dir="${PAPERLESS_DATA_DIR:-/usr/src/paperless/data}"
+declare -r index_version_file="${data_dir}/.index_version"
+
+update_index () {
+	echo "${log_prefix} Search index out of date. Updating..."
+	cd "${PAPERLESS_SRC_DIR}"
+	if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+		python3 manage.py document_index reindex --no-progress-bar
+		echo ${index_version} | tee "${index_version_file}" > /dev/null
+	else
+		s6-setuidgid paperless python3 manage.py document_index reindex --no-progress-bar
+		echo ${index_version} | s6-setuidgid paperless tee "${index_version_file}" > /dev/null
+	fi
+}
+
+if [[ (! -f "${index_version_file}") ]]; then
+	echo "${log_prefix} No index version file found"
+	update_index
+elif [[ $(<"${index_version_file}") != "$index_version" ]]; then
+	echo "${log_prefix} index version updated"
+	update_index
+fi

docker/rootfs/etc/s6-overlay/s6-rc.d/init-search-index/type

@@ -0,0 +1 @@
+oneshot

docker/rootfs/etc/s6-overlay/s6-rc.d/init-search-index/up

@@ -0,0 +1 @@
+/etc/s6-overlay/s6-rc.d/init-search-index/run

docker/rootfs/etc/s6-overlay/s6-rc.d/init-start/run

@@ -0,0 +1,19 @@
+#!/command/with-contenv /usr/bin/bash
+# shellcheck shell=bash
+
+declare -r log_prefix="[init-start]"
+
+echo "${log_prefix} paperless-ngx docker container starting..."
+
+# Set some directories into environment for other steps to access via environment
+# Sort of like variables for later
+printf "/usr/src/paperless/src" > /var/run/s6/container_environment/PAPERLESS_SRC_DIR
+echo $(date +%s) > /var/run/s6/container_environment/PAPERLESS_START_TIME_S
+
+# Check if we're starting as a non-root user
+if [ $(id -u) == $(id -u paperless) ]; then
+	printf "true" > /var/run/s6/container_environment/USER_IS_NON_ROOT
+	echo "${log_prefix}  paperless-ngx docker container running under a user"
+else
+	echo "${log_prefix}  paperless-ngx docker container starting init as root"
+fi

docker/rootfs/etc/s6-overlay/s6-rc.d/init-start/type

@@ -0,0 +1 @@
+oneshot

docker/rootfs/etc/s6-overlay/s6-rc.d/init-start/up

@@ -0,0 +1 @@
+/etc/s6-overlay/s6-rc.d/init-start/run

docker/rootfs/etc/s6-overlay/s6-rc.d/init-superuser/run

@@ -0,0 +1,20 @@
+#!/command/with-contenv /usr/bin/bash
+# shellcheck shell=bash
+
+declare -r log_prefix="[init-superuser]"
+
+if [[ -n "${PAPERLESS_ADMIN_USER}" ]]; then
+	echo "${log_prefix} Creating superuser..."
+	cd "${PAPERLESS_SRC_DIR}"
+
+	if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+		python3 manage.py manage_superuser
+	else
+		s6-setuidgid paperless python3 manage.py manage_superuser
+	fi
+
+	echo "${log_prefix} Superuser creation done"
+
+else
+	echo "${log_prefix} Not creating superuser"
+fi

docker/rootfs/etc/s6-overlay/s6-rc.d/init-superuser/type

@@ -0,0 +1 @@
+oneshot

docker/rootfs/etc/s6-overlay/s6-rc.d/init-superuser/up

@@ -0,0 +1 @@
+/etc/s6-overlay/s6-rc.d/init-superuser/run