Add Paperless-ngx (#1047)

Co-authored-by: nmfretz <nmfretz@gmail.com>

paperless/docker-compose.yml

@@ -0,0 +1,61 @@
+version: "3.7"
+
+services:
+  app_proxy:
+    environment:
+      APP_HOST: paperless_webserver_1
+      APP_PORT: 8000
+
+  broker:
+    image: docker.io/library/redis:7@sha256:d6ecc832969a4827645a083da38345327b3447772fe907e7d4311c79b4e3a06e
+    restart: on-failure
+    volumes:
+      - ${APP_DATA_DIR}/data/redisdata:/data
+
+  db:
+    image: docker.io/library/postgres:16
+    restart: unless-stopped
+    volumes:
+      - ${APP_DATA_DIR}/data/pgdata:/var/lib/postgresql/data
+    environment:
+      POSTGRES_DB: paperless
+      POSTGRES_USER: paperless
+      POSTGRES_PASSWORD: paperless
+
+  webserver:
+    image: ghcr.io/paperless-ngx/paperless-ngx:2.7.2@sha256:703c990a790dfd4d25fb56df3afec27b13cb0926a3818bf265edac9c71311647
+    restart: on-failure
+    depends_on:
+      - db
+      - broker
+      - gotenberg
+      - tika
+    volumes:
+      - ${APP_DATA_DIR}/data/data:/usr/src/paperless/data
+      - ${APP_DATA_DIR}/data/media:/usr/src/paperless/media
+      # TODO: move these inside the paperless app data dir once umbrelOS supports navigating to it via the UI
+      - ${UMBREL_ROOT}/data/storage/paperless/export:/usr/src/paperless/export
+      - ${UMBREL_ROOT}/data/storage/paperless/consume:/usr/src/paperless/consume
+    environment:
+      PAPERLESS_REDIS: redis://paperless_broker_1:6379
+      PAPERLESS_DBHOST: paperless_db_1
+      PAPERLESS_TIKA_ENABLED: 1
+      PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://paperless_gotenberg_1:3000
+      PAPERLESS_TIKA_ENDPOINT: http://paperless_tika_1:9998
+      PAPERLESS_ADMIN_USER: admin
+      PAPERLESS_ADMIN_PASSWORD: $APP_PASSWORD
+
+  gotenberg:
+    image: docker.io/gotenberg/gotenberg:7.10@sha256:d03b8a04c6e6c5e568b38f57352266dee4674849b71818774025f8f48d869a9a
+    restart: on-failure
+
+    # 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: ghcr.io/paperless-ngx/tika:2.9.1-minimal@sha256:20db3df89eaeb1b271dd840888fe909b88b12f4b86ef641ec07a1d45d4c5168f
+    restart: on-failure

paperless/exports.sh

@@ -0,0 +1,32 @@
+# Ensure that Paperless consume and export directories are created with the correct permissions
+UMBREL_DATA_DIR="${UMBREL_ROOT}/data"
+UMBREL_DATA_STORAGE_DIR="${UMBREL_DATA_DIR}/storage"
+UMBREL_DATA_STORAGE_PAPERLESS_DIR="${UMBREL_DATA_STORAGE_DIR}/paperless"
+UMBREL_DATA_STORAGE_PAPERLESS_CONSUME_DIR="${UMBREL_DATA_STORAGE_PAPERLESS_DIR}/consume"
+UMBREL_DATA_STORAGE_PAPERLESS_EXPORT_DIR="${UMBREL_DATA_STORAGE_PAPERLESS_DIR}/export"
+DESIRED_OWNER="1000:1000"
+
+if [[ ! -d "${UMBREL_DATA_STORAGE_PAPERLESS_CONSUME_DIR}" ]]; then
+  mkdir -p "${UMBREL_DATA_STORAGE_PAPERLESS_CONSUME_DIR}"
+fi
+
+if [[ ! -d "${UMBREL_DATA_STORAGE_PAPERLESS_EXPORT_DIR}" ]]; then
+  mkdir -p "${UMBREL_DATA_STORAGE_PAPERLESS_EXPORT_DIR}"
+fi
+
+set_paperless_correct_permissions() {
+	local -r path="${1}"
+
+	if [[ -d "${path}" ]]; then
+		owner=$(stat -c "%u:%g" "${path}")
+
+		if [[ "${owner}" != "${DESIRED_OWNER}" ]]; then
+			chown "${DESIRED_OWNER}" "${path}"
+		fi
+	fi
+}
+
+set_paperless_correct_permissions "${UMBREL_DATA_STORAGE_DIR}"
+set_paperless_correct_permissions "${UMBREL_DATA_STORAGE_PAPERLESS_DIR}"
+set_paperless_correct_permissions "${UMBREL_DATA_STORAGE_PAPERLESS_CONSUME_DIR}"
+set_paperless_correct_permissions "${UMBREL_DATA_STORAGE_PAPERLESS_EXPORT_DIR}"

paperless/umbrel-app.yml

@@ -0,0 +1,40 @@
+manifestVersion: 1
+id: paperless
+category: files
+name: Paperless-ngx
+version: "2.7.2"
+tagline: Transform your physical documents into a searchable online archive
+description: >-
+  Paperless-ngx is a community-supported open-source document management system that transforms your physical documents into a searchable online archive so you can keep, well, less paper.
+
+  - Organize and index your scanned documents with tags, correspondents, types, and more.
+
+  - Your data is stored locally on your server and is never transmitted or shared in any way.
+
+  - Performs OCR on your documents, adding searchable and selectable text, even to documents scanned with only images.
+
+  - Utilizes the open-source Tesseract engine to recognize more than 100 languages.
+
+  - Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals.
+
+  - Uses machine-learning to automatically add tags, correspondents and document types to your documents.
+
+  - Supports PDF documents, images, plain text files, Office documents (Word, Excel, Powerpoint, and LibreOffice equivalents)1 and more.
+
+  - Paperless stores your documents plain on disk. Filenames and folders are managed by paperless and their format can be configured freely with different configurations assigned to different documents.
+releaseNotes: ""
+developer: Paperless-ngx Community
+website: https://docs.paperless-ngx.com/
+dependencies: []
+repo: https://github.com/paperless-ngx/paperless-ngx
+support: https://github.com/paperless-ngx/paperless-ngx/discussions
+port: 2349
+gallery:
+  - 1.jpg
+  - 2.jpg
+  - 3.jpg
+path: ""
+defaultUsername: "admin"
+deterministicPassword: true
+submitter: highghlow
+submission: https://github.com/getumbrel/umbrel-apps/pull/1047