Add scheduled backup feature with document exporter

.gitignore

@@ -0,0 +1,2 @@
+.devcontainer/
+.vscode/

paperless-ngx/DOCS.md

@@ -70,6 +70,10 @@ consumer_subdirs_as_tags: false
 ssl: false
 certfile: fullchain.pem
 keyfile: privkey.pem
+backup_enabled: false
+backup_path: /data/exports
+backup_cron: "0 3 * * *"
+backup_keep_count: 3
 ```
 
 ### Option: `url`
@@ -152,6 +156,22 @@ The private key file to use for SSL.
 
 Let you set `client_max_body_size` of _nginx_ manually
 
+### Option: `backup_enabled`
+
+Enables or disables automatic backups of your Paperless data. Set to `true` to enable scheduled backups. `false` ist default.
+
+### Option: `backup_path`
+
+Specifies the directory where backup files will be stored. The default path is `/data/exports`.
+
+### Option: `backup_cron`
+
+Defines the cron schedule for automatic backups. The default value `"0 2 * * *"` runs backups daily at 3:00 AM. Use standard cron syntax to customize the backup schedule.
+
+### Option: `backup_keep_count`
+
+Sets the number of most recent backups to retain. Older backups beyond this count will be automatically deleted. The default is `3` backups.
+
 ### More personalisation
 
 You can add more configurations options in `/addon_config/paperless_ngx/paperless.conf`

paperless-ngx/Dockerfile

@@ -94,7 +94,9 @@
   libgs10-common=${GHOSTSCRIPT_VERSION} \
   ghostscript=${GHOSTSCRIPT_VERSION} \
   libjbig2enc-dev=0.30-1 \
-  qpdf=12.2.0-1"
+  qpdf=12.2.0-1 \
+  zip \
+  unzip"
 
 # Buildx provided, must be defined to use though
 ARG TARGETARCH
@@ -109,7 +111,7 @@
 # Install basic runtime packages.
 # These change very infrequently
 # hadolint ignore=DL3003,DL3042,DL3008,SC2086
 RUN --mount=type=cache,target=/root/.cache/uv/,id=uv-cache \
   set -eux \
   echo "Installing system packages" \
   && apt-get update \
@@ -145,7 +147,7 @@
 
 # Install requirements
 # hadolint ignore=DL3042,DL3008,DL3013,SC2086
 RUN --mount=type=cache,target=/root/.cache/uv/,id=uv-cache \
   set -eux \
   && echo "Installing build system packages" \
   && apt-get update \
@@ -168,6 +170,19 @@
   && rm -rf /var/tmp/* \
   && rm -rf /var/cache/apt/archives/
 
+
+# Install supercronic
+# Latest releases available at https://github.com/aptible/supercronic/releases
+ENV SUPERCRONIC_URL=https://github.com/aptible/supercronic/releases/download/v0.2.41/supercronic-linux-amd64 \
+    SUPERCRONIC_SHA1SUM=f70ad28d0d739a96dc9e2087ae370c257e79b8d7 \
+    SUPERCRONIC=supercronic-linux-amd64
+
+RUN curl -fsSLO "$SUPERCRONIC_URL" \
+ && echo "${SUPERCRONIC_SHA1SUM}  ${SUPERCRONIC}" | sha1sum -c - \
+ && chmod +x "$SUPERCRONIC" \
+ && mv "$SUPERCRONIC" "/usr/local/bin/${SUPERCRONIC}" \
+ && ln -s "/usr/local/bin/${SUPERCRONIC}" /usr/local/bin/supercronic
+
 WORKDIR /usr/src/paperless/docker/
 
 RUN set -eux \
@@ -202,6 +217,10 @@
 # Copy root filesystem
 COPY rootfs/ /
 
+RUN chmod +x /usr/local/bin/paperless_backup.sh \
+  && chmod +x /etc/cont-init.d/90-cron-backup.sh \
+  && chmod +x /etc/services.d/supercronic/run
+
 # Build arguments
 ARG BUILD_ARCH
 ARG BUILD_DATE

paperless-ngx/config.yaml

@@ -37,6 +37,10 @@ options:
   keyfile: privkey.pem
   ingress_auth: false
   tika_gotenberg: false
+  backup_enabled: false
+  backup_path: "/data/exports"
+  backup_cron: "0 3 * * *"
+  backup_keep_count: 3
 schema:
   url: str?
   csrf_allowed:
@@ -59,3 +63,7 @@ schema:
   ingress_auth: bool
   tika_gotenberg: bool
   locales: str?
+  backup_enabled: bool
+  backup_path: str
+  backup_cron: str
+  backup_keep_count: int

paperless-ngx/rootfs/etc/cont-init.d/90-cron-backup.sh

@@ -0,0 +1,30 @@
+#!/command/with-contenv bashio
+# shellcheck shell=bash
+set -e
+
+echo "[INFO] Configuring backup cron job..."
+
+if bashio::config.has_value 'backup_enabled'; then
+    BACKUP_ENABLED="$(bashio::config 'backup_enabled')"
+else
+    BACKUP_ENABLED="false"
+fi
+
+if bashio::config.has_value 'backup_cron'; then
+    CRON_SCHEDULE="$(bashio::config 'backup_cron')"
+else
+    CRON_SCHEDULE="0 2 * * *"
+fi
+
+if [ "$BACKUP_ENABLED" == "false" ]; then
+    echo "[INFO] Backup cron job is disabled in configuration. Skipping setup."
+    exit 0
+fi
+
+mkdir -p /etc/cron.d
+
+echo "${CRON_SCHEDULE} /usr/local/bin/paperless_backup.sh >> /proc/1/fd/1 2>&1" > /etc/cron.d/paperless-backup
+
+chmod 0644 /etc/cron.d/paperless-backup
+
+echo "[INFO] Backup cron job configured with schedule: $CRON_SCHEDULE"

paperless-ngx/rootfs/etc/services.d/supercronic/run

@@ -0,0 +1,3 @@
+#!/command/with-contenv bashio
+# shellcheck shell=bash
+exec /usr/local/bin/supercronic /etc/cron.d/paperless-backup

paperless-ngx/rootfs/usr/local/bin/paperless_backup.sh

@@ -0,0 +1,45 @@
+#!/command/with-contenv bashio
+# shellcheck shell=bash
+set -e
+
+cd /usr/src/paperless/src || { echo "[ERROR] Cannot change into /usr/src/paperless/src"; exit 1; }
+
+if bashio::config.has_value 'backup_path'; then
+    BACKUP_PATH="$(bashio::config 'backup_path')"
+else
+    echo "[ERROR] No backup path configured. Please set 'backup_path' in the add-on configuration."
+    exit 1
+fi
+
+if bashio::config.has_value 'backup_keep_count'; then
+    BACKUP_KEEP_COUNT="$(bashio::config 'backup_keep_count')"
+else
+    echo "[WARN] 'backup_keep_count' not set, defaulting to 3"
+    BACKUP_KEEP_COUNT=3
+fi
+
+NOW=$(date '+%Y-%m-%d-%H:%M:%S')
+echo "[INFO] Backup started: $NOW"
+
+mkdir -p "$BACKUP_PATH"
+
+python3 manage.py document_exporter \
+  "$BACKUP_PATH" \
+  -z \
+  -zn "paperless-export-$NOW" \
+  --no-progress-bar \
+  || { echo "[ERROR] Creating export failed"; exit 1; }
+
+echo "[INFO] Backup completed: $BACKUP_PATH/paperless-export-$NOW.zip"
+
+# -----------------------------
+# Delete old backups
+# -----------------------------
+mapfile -t BACKUPS < <(ls -1t "$BACKUP_PATH"/paperless-export-*.zip 2>/dev/null)
+
+if [ "${#BACKUPS[@]}" -gt "$BACKUP_KEEP_COUNT" ]; then
+    for ((i=BACKUP_KEEP_COUNT; i<${#BACKUPS[@]}; i++)); do
+        echo "[INFO] Deleting old backup: ${BACKUPS[i]}"
+        rm -f "${BACKUPS[i]}"
+    done
+fi

paperless-ngx/translations/en.yaml

@@ -64,5 +64,17 @@ configuration:
   locales:
     name: Locales
     description: Your language (fr_FR, en_US, de_DE, etc)
+  backup_enabled:
+    name: Enable Backup
+    description: Enable or disable automatic backups
+  backup_path:
+    name: Backup Path
+    description: Path to store backups
+  backup_cron:
+    name: Backup Cron Schedule
+    description: Cron schedule for automatic backups
+  backup_keep_count:
+    name: Backup Keep Count
+    description: Number of backups to keep
 network:
   80/tcp: Web interface (Not required for Ingress)