From 44183a35436975b037fd362bc45bc1e6290444de Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Luk=C3=A1=C5=A1=20Kucharczyk?= <lukas@kucharczyk.xyz>
Date: Tue, 14 Mar 2023 14:26:13 +0100
Subject: [PATCH] Add paperless-ngx

---
 .env               |  4 ++-
 docker-compose.yml | 65 ++++++++++++++++++++++++++++++++++++++++++++++
 paperless-ngx.env  | 42 ++++++++++++++++++++++++++++++
 3 files changed, 110 insertions(+), 1 deletion(-)
 create mode 100755 paperless-ngx.env

diff --git a/.env b/.env
index 2b7e155..05c77ff 100644
--- a/.env
+++ b/.env
@@ -57,4 +57,6 @@ STASH_INTERNAL_PORT=9999
 NAVIDROME_EXTERNAL_PORT=4533
 NAVIDROME_INTERNAL_PORT=4533
 MALOJA_EXTERNAL_PORT=42010
-MALOJA_INTERNAL_PORT=42010
\ No newline at end of file
+MALOJA_INTERNAL_PORT=42010
+PAPERLESS_EXTERNAL_PORT=8004
+PAPERLESS_INTERNAL_PORT=8000
\ No newline at end of file
diff --git a/docker-compose.yml b/docker-compose.yml
index 54f65e4..84ab0b4 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -502,6 +502,71 @@ services:
       - "${DOCKER_STORAGE_PATH}/maloja:/data"
     restart: unless-stopped
 
+  redis:
+    image: docker.io/library/redis:7
+    restart: unless-stopped
+    volumes:
+      - "${DOCKER_STORAGE_PATH}/redis:/data"
+
+  paperless-ngx:
+    container_name: paperless-ngx
+    image: ghcr.io/paperless-ngx/paperless-ngx:latest
+    restart: unless-stopped
+    depends_on:
+      - redis
+      - gotenberg
+      - tika
+    ports:
+      - "${PAPERLESS_EXTERNAL_PORT}:${PAPERLESS_INTERNAL_PORT}"
+    networks:
+      - public
+    profiles:
+      - base
+    healthcheck:
+      test:
+        [
+          "CMD",
+          "curl",
+          "-fs",
+          "-S",
+          "--max-time",
+          "2",
+          "http://localhost:8000"
+        ]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+    volumes:
+      - "${DOCKER_STORAGE_PATH}/paperless-ngx/data:/usr/src/paperless/data"
+      - "${DOCKER_STORAGE_PATH}/paperless-ngx/media:/usr/src/paperless/media"
+      - "${DOCKER_STORAGE_PATH}/paperless-ngx/export:/usr/src/paperless/export"
+      - "${DOCKER_STORAGE_PATH}/paperless-ngx/consume:/usr/src/paperless/consume"
+    env_file: paperless-ngx.env
+    environment:
+      PAPERLESS_REDIS: redis://redis:6379
+      PAPERLESS_TIKA_ENABLED: 1
+      PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
+      PAPERLESS_TIKA_ENDPOINT: http://tika:9998
+
+  gotenberg:
+    image: docker.io/gotenberg/gotenberg:7.6
+    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.
+    profiles:
+      - base
+    command:
+      - "gotenberg"
+      - "--chromium-disable-javascript=true"
+      - "--chromium-allow-list=file:///tmp/.*"
+
+  tika:
+    image: ghcr.io/paperless-ngx/tika:latest
+    profiles:
+      - base
+    restart: unless-stopped
+
 networks:
   loki:
   caddy:
diff --git a/paperless-ngx.env b/paperless-ngx.env
new file mode 100755
index 0000000..6e5281d
--- /dev/null
+++ b/paperless-ngx.env
@@ -0,0 +1,42 @@
+# 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=ces chi-sim
+
+###############################################################################
+# 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.
+
+# 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)
+#PAPERLESS_URL=https://paperless.example.com
+
+# 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=Europe/Prague
+
+# The default language to use for OCR. Set this to the language most of your
+# documents are written in.
+PAPERLESS_OCR_LANGUAGE=eng+ces+chi_sim
+
+# 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