Streamline config and switch to pg15

.env

@@ -1,2 +1,6 @@
-IMAGE_VERSION_PAPERLESS="2.14.7"
+IMAGE_VERSION_PAPERLESS="2.18.4"
-IMAGE_VERSION_GOTENBERG="8.9.2"
+#IMAGE_VERSION_PAPERLESS="2.17.1"
+IMAGE_VERSION_GOTENBERG="8.24"
+PG_PASSWORD="!Wvnzo3#S57KF0bDF"
+PG_USER="ppldbuser"
+#IMAGE_VERSION_GOTENBERG="8.9.2"

compose-db-only.yml

@@ -0,0 +1,47 @@
+services:
+  db:
+    container_name: db-pg
+    image: docker.io/library/postgres:13
+    restart: unless-stopped
+    volumes:
+      - /volume1/docker/paperless-ngx/pgdata:/var/lib/postgresql/data
+    environment:
+      POSTGRES_DB: paperless
+      POSTGRES_USER: paperless
+      POSTGRES_PASSWORD: paperless
+
+  db-15:
+    container_name: paperless-postgres-db
+    image: postgres:15-alpine
+    restart: unless-stopped
+    volumes:
+      - paperless-postgres-db:/var/lib/postgresql/data
+    environment:
+      POSTGRES_DB: paperless
+      POSTGRES_USER: ppldbuser
+      POSTGRES_PASSWORD: "!Wvnzo3#S57KF0bDF"
+
+  db-backup:
+    image: postgres:latest
+    env_file: ./paperless-backup.env
+    volumes:
+      - ./database-dump:/dump
+      - /etc/localtime:/etc/localtime:ro
+    entrypoint: |
+      bash -c 'bash -s <<EOF
+      trap "break;exit" SIGHUP SIGINT SIGTERM
+      sleep 2m
+      while /bin/true; do
+        pg_dump -Fc > /dump/dump_\`date +%d-%m-%Y"_"%H_%M_%S\`.psql
+        (ls -t /dump/dump*.psql|head -n $$BACKUP_NUM_KEEP;ls /dump/dump*.psql)|sort|uniq -u|xargs rm -- {}
+        sleep $$BACKUP_FREQUENCY
+      done
+      EOF'
+
+volumes:
+  data:
+  media:
+  pgdata:
+  paperless-postgres-db:
+    name: paperless-postgres-db
+  redisdata:

compose-solo.yml

@@ -0,0 +1,41 @@
+version: "3.4"
+services:
+  db:
+    container_name: db-pg
+    image: docker.io/library/postgres:13
+    restart: unless-stopped
+    volumes:
+      - /volume1/docker/paperless-ngx/pgdata:/var/lib/postgresql/data
+    environment:
+      POSTGRES_DB: paperless
+      POSTGRES_USER: paperless
+      POSTGRES_PASSWORD: paperless
+
+  db-15:
+    container_name: paperless-postgres-db
+    image: postgres:15-alpine
+    restart: unless-stopped
+    volumes:
+      - paperless-postgres-db:/var/lib/postgresql/data
+    environment:
+      POSTGRES_DB: paperless
+      POSTGRES_USER: ppldbuser
+      POSTGRES_PASSWORD: "!Wvnzo3#S57KF0bDF"
+
+  adminer:
+    image: adminer
+    restart: always
+    ports:
+      - 8484:8080
+
+  pgadmin:
+    image: chorss/docker-pgadmin4
+    ports:
+      - 5050:5050
+
+
+volumes:
+  data:
+  media:
+  pgdata:
+  redisdata:

docker-compose.env

@@ -0,0 +1,56 @@
+# 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.
+
+# 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://ppl.homeee.schnorbus.net
+
+# 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
+
+# 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
+
+
+PAPERLESS_SECRET_KEY=supergeheim
+PAPERLESS_ADMIN_USER=admin
+PAPERLESS_ADMIN_PASSWORD=123456
+PAPERLESS_BASE_URL="http://localhost:8000"
+PAPERLESS_POST_CONSUME_AUTH_TOKEN="0cf8eb062d0ecfc0aa70611125427692cb577d68" 
+PAPERLESS_POST_CONSUME_EXTRACTOR_NOTIFY_TAG="Title changed"
+PAPERLESS_POST_CONSUME_EXPAND_BY_DATE=True
+
+PAPERLESS_DBPASS="!Wvnzo3#S57KF0bDF"
+
+PAPERLESS_OCR_USER_ARGS="{'continue_on_soft_render_error':true}"
+
+IMAGE_VERSION_PAPERLESS="2.14.7"

docker-compose.yml

@@ -0,0 +1,120 @@
+services:
+  broker:
+    container_name: paperless-broker
+    image: docker.io/library/redis:7
+    restart: unless-stopped
+    volumes:
+      - /volume1/docker/paperless-ngx/redisdata:/data
+
+#  db:
+#    container_name: db-pg
+#    image: docker.io/library/postgres:13
+#    restart: unless-stopped
+#    volumes:
+#      - /volume1/docker/paperless-ngx/pgdata:/var/lib/postgresql/data
+#    environment:
+#      POSTGRES_DB: paperless
+#      POSTGRES_USER: paperless
+#      POSTGRES_PASSWORD: paperless
+
+  db-15:
+    container_name: paperless-postgres-db
+    image: postgres:15-alpine
+    restart: unless-stopped
+    volumes:
+      - paperless-postgres-db:/var/lib/postgresql/data
+    environment:
+      POSTGRES_DB: paperless
+      POSTGRES_USER: ${PG_USER}
+      POSTGRES_PASSWORD: ${PG_PASSWORD}
+
+  db-backup:
+    container_name: paperless-db-backup
+    image: postgres:15-alpine
+    env_file: ./paperless-backup.env
+    volumes:
+      - ./database-dump:/dump
+      - /etc/localtime:/etc/localtime:ro
+    entrypoint: |
+      bash -c 'bash -s <<EOF
+      trap "break;exit" SIGHUP SIGINT SIGTERM
+      sleep 2m
+      while /bin/true; do
+        pg_dump -Fc > /dump/dump_\`date +%d-%m-%Y"_"%H_%M_%S\`.psql
+        (ls -t /dump/dump*.psql|head -n $$BACKUP_NUM_KEEP;ls /dump/dump*.psql)|sort|uniq -u|xargs rm -- {}
+        sleep $$BACKUP_FREQUENCY
+      done
+      EOF'
+
+  adminer:
+    image: adminer
+    restart: always
+    ports:
+      - 8484:8080
+
+  webserver:
+    container_name: paperless-webserver
+#    image: ghcr.io/paperless-ngx/paperless-ngx:2.8.6
+    image: ghcr.io/paperless-ngx/paperless-ngx:${IMAGE_VERSION_PAPERLESS}
+    restart: unless-stopped
+    depends_on:
+      - db-15
+      - broker
+      - gotenberg
+      - tika
+    ports:
+    # <Host Port>:<Container Port>
+      - 8010:8000
+    healthcheck:
+      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+    volumes:
+      - /home/basti/Projects/paperless/data:/usr/src/paperless/data
+      - /home/basti/Projects/paperless/media:/usr/src/paperless/media
+      - /home/basti/Projects/paperless/export:/usr/src/paperless/export
+      - /var/opt/paperless/consume:/usr/src/paperless/consume
+      - /home/basti/Projects/paperless/scripts:/usr/src/paperless/scripts
+    environment:
+      PAPERLESS_REDIS: redis://broker:6379
+      PAPERLESS_DBHOST: db-15
+      PAPERLESS_DBUSER: ${PG_USER}
+      
+  
+      PAPERLESS_OCR_LANGUAGE: deu+eng
+      PAPERLESS_CONSUMER_DELETE_DUPLICATES: "true"
+      PAPERLESS_POST_CONSUME_SCRIPT: /usr/src/paperless/scripts/post_consume.py
+      PAPERLESS_PRE_CONSUME_SCRIPT: /usr/src/paperless/scripts/pre-consume.sh
+      USERMAP_UID: 0
+      USERMAP_GID: 0
+      PAPERLESS_TIKA_ENABLED: 1
+      PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
+      PAPERLESS_TIKA_ENDPOINT: http://tika:9998
+    env_file:
+      - ./docker-compose.env
+
+  gotenberg:
+    container_name: paperless-gotenberg
+    image: docker.io/gotenberg/gotenberg:${IMAGE_VERSION_GOTENBERG}
+    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:
+    container_name: paperless-tika
+    image: docker.io/apache/tika:latest
+    restart: unless-stopped
+
+volumes:
+  data:
+  media:
+  pgdata:
+  paperless-postgres-db:
+    name: paperless-postgres-db
+  redisdata:

paperless-backup.env

@@ -0,0 +1,11 @@
+# For database backups
+POSTGRES_DB=paperless
+POSTGRES_USER=ppldbuser
+POSTGRES_PASSWORD="!Wvnzo3#S57KF0bDF"
+
+PGDATABASE=paperless
+PGUSER=ppldbuser
+PGPASSWORD="!Wvnzo3#S57KF0bDF"
+PGHOST=db-15
+BACKUP_NUM_KEEP=7
+BACKUP_FREQUENCY=1d

pg_backup.md

@@ -0,0 +1,44 @@
+# Postgres Backup
+
+## Backup
+
+```
+docker exec -i -e PGPASSWORD=<postgresql_password> postgres /usr/bin/pg_dumpall \
+ -U <postgresql_user> <postgresql_database> | gzip -9 > postgres-backup.sql.gz
+```
+
+## Restore
+First, copy dump to container:
+
+```
+docker cp ./paperless_dump.sql db-pg-15:/backups
+```
+
+
+
+## Advanced
+
+```
+  pgbackups:
+    container_name: Backup
+    image: prodrigestivill/postgres-backup-local
+    restart: always
+    volumes:
+      - ./backup:/backups
+    links:
+      - db:db
+    depends_on:
+      - db
+    environment:
+      - POSTGRES_HOST=db
+      - POSTGRES_DB=${DB_NAME}
+      - POSTGRES_USER=${DB_USER}
+      - POSTGRES_PASSWORD=${DB_PASSWORD}
+      - POSTGRES_EXTRA_OPTS=-Z9 --schema=public --blobs
+      - SCHEDULE=@every 0h30m00s
+      - BACKUP_KEEP_DAYS=7
+      - BACKUP_KEEP_WEEKS=4
+      - BACKUP_KEEP_MONTHS=6
+      - HEALTHCHECK_PORT=81
+```
+