Files
ubuntu-post-install/services/archivebox.sh
Claude bec9228c55 Back up existing files before every service overwrites them
Confirmed live: install_frigate()'s fresh-install path overwrote a
working, hand-crafted docker-compose.yml (Frigate + mosquitto +
frigate-notify) with zero backup, because that file's shape didn't match
what frigate.sh's own "existing install" detection knew how to recognize.
Every service's own detection is a judgment call about what counts as
"already installed" and can miss a real setup built outside this repo's
conventions.

lib/common.sh gains backup_if_exists(FILE) — copies FILE to
FILE.bak.<timestamp> if it exists, no-ops otherwise (including DRY_RUN).
Applied before every service's own `cat > docker-compose.yml`/`cat > .env`
write across all 60 services that do one (115 call sites), plus a matching
standalone-mode stub added to every service's own bootstrap block, same
convention already used for port_in_use/find_free_port. This doesn't
replace a service's own update/fresh-reinstall detection — it's the safety
net underneath it, so a wrong detection costs a .bak file to restore from
instead of the original silently disappearing.

Also fixes the actual gap that surfaced this: services/frigate.sh's
Authelia offer only checked for Authelia installed locally on Frigate's
own box, which is never true for a dedicated NVR box with no local Caddy
either (the common shape — Caddy lives elsewhere, snippet-generation mode
already handles that). Now offers Authelia protection unconditionally and,
when Authelia isn't local, asks whether it lives on the same machine as
Caddy (still "import authelia", since that's local to wherever Caddy ends
up) or on a genuinely separate third machine (the explicit
header-pinned forward_auth form, per CLAUDE.md's "forward_auth to a remote
Authelia" note, needed because a bare authelia:9091 shortcut only works
one hop).
2026-08-26 17:26:17 +00:00

332 lines
12 KiB
Bash

#!/bin/bash
# services/archivebox.sh — Self-hosted web archiving (ArchiveBox).
# Part of the modular post-install system (sourced by setup.sh).
#
# Can also be run standalone on any machine:
# sudo bash archivebox.sh
# (Docker must already be installed when run standalone)
# ── Standalone bootstrap ──────────────────────────────────────────────────────
if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
[[ "$(id -u)" == "0" ]] || { echo "Run with sudo: sudo bash $0"; exit 1; }
_SELF_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
_COMMON="$_SELF_DIR/../lib/common.sh"
if [[ -f "$_COMMON" ]]; then
source "$_COMMON"
else
log_info() { echo -e "\033[0;34m[INFO]\033[0m $*"; }
log_success() { echo -e "\033[0;32m[OK]\033[0m $*"; }
log_warning() { echo -e "\033[1;33m[WARN]\033[0m $*"; }
log_error() { echo -e "\033[0;31m[ERROR]\033[0m $*" >&2; }
require_docker() {
command -v docker &>/dev/null || {
log_error "Docker not found. Install it first:"
log_error " curl -fsSL https://get.docker.com | sudo sh"
return 1
}
docker compose version &>/dev/null || {
log_error "Docker Compose plugin missing:"
log_error " sudo apt-get install -y docker-compose-plugin"
return 1
}
}
ensure_docker_dir_ownership() {
chown -R "$ACTUAL_USER:$ACTUAL_USER" "$@" 2>/dev/null || true
}
port_in_use() {
local _port="$1" _proto="${2:-tcp}"
local _flag="-tlnH"
[ "$_proto" = "udp" ] && _flag="-ulnH"
ss "$_flag" "sport = :${_port}" 2>/dev/null | grep -q .
}
find_free_port() {
local _varname="$1" _port="$2" _proto="${3:-tcp}"
while port_in_use "$_port" "$_proto"; do
_port=$((_port + 1))
done
eval "$_varname='$_port'"
}
prompt_text() {
local _q="$1" _def="$2" _var="$3" _r
[[ "${UNATTENDED:-false}" == "true" ]] && { eval "$_var='$_def'"; return; }
read -r -p " $_q " _r
eval "$_var='${_r:-$_def}'"
}
prompt_yn() {
local _q="$1" _def="$2" _var="$3" _r
[[ "${UNATTENDED:-false}" == "true" ]] && { eval "$_var='$_def'"; return; }
read -r -p " $_q " _r
eval "$_var='${_r:-$_def}'"
}
configure_caddy_for_service() {
local _name="$1" _upstream="$2" _subdomain="$3" _extra="${4:-}"
local _caddy_dir="$DOCKER_DIR/caddy"
local _caddyfile="$_caddy_dir/Caddyfile"
local _display_port="${_upstream##*:}"
local _mode="none"
[[ -d "$_caddy_dir" ]] && _mode="local"
[[ -n "${CADDY_REMOTE_HOST:-}" ]] && [[ "$_mode" != "local" ]] && _mode="remote"
[[ "$_mode" == "none" ]] && {
log_info "Access $_name directly on port $_display_port."
return 0
}
echo ""
local _do_caddy=""
if [[ "$_mode" == "remote" ]]; then
log_info "Remote Caddy configured (${CADDY_REMOTE_HOST})."
log_info "A snippet file will be saved to ~/docker/caddy-snippets/."
fi
read -r -p " Configure Caddy reverse proxy for $_name? [y/N]: " _do_caddy
[[ "${_do_caddy,,}" == "y" ]] || {
log_info "Skipping — access at: http://localhost:$_display_port"
return 0
}
local _default_domain=""
if [[ -n "${SITE_DOMAIN:-}" ]] && [[ "$SITE_DOMAIN" != "example.com" ]]; then
_default_domain="${_subdomain}.${SITE_DOMAIN}"
log_info "Default: $_default_domain"
fi
local _domain=""
read -r -p " Domain [${_default_domain:-required}]: " _domain
_domain="${_domain:-$_default_domain}"
[[ -n "$_domain" ]] || { log_warning "No domain entered — skipping Caddy."; return 0; }
local _block_upstream="$_upstream"
if [[ "$_mode" == "remote" ]]; then
_block_upstream="${CADDY_REMOTE_HOST}:${_display_port}"
fi
local _site_block
_site_block="$(cat << CBLOCK
# $_name
${_domain} {
reverse_proxy ${_block_upstream}
header {
Strict-Transport-Security "max-age=31536000; includeSubDomains; preload"
X-Content-Type-Options "nosniff"
X-Frame-Options "SAMEORIGIN"
Referrer-Policy "strict-origin-when-cross-origin"
}
log {
output file /var/log/caddy/${_domain}.log
format json
}
${_extra}
}
CBLOCK
)"
if [[ "$_mode" == "local" ]]; then
if [[ -f "$_caddyfile" ]]; then
local _bk="$_caddy_dir/Caddyfile.backup.$(date +%Y%m%d-%H%M%S)"
cp "$_caddyfile" "$_bk"
log_info "Backed up Caddyfile to $(basename "$_bk")"
else
touch "$_caddyfile"
fi
if grep -q "^${_domain}" "$_caddyfile" 2>/dev/null; then
log_warning "$_domain already in Caddyfile"
local _ow=""
read -r -p " Overwrite? [y/N]: " _ow
[[ "${_ow,,}" == "y" ]] || { log_info "Keeping existing entry."; return 0; }
sed -i "/^${_domain}/,/^}/d" "$_caddyfile"
fi
printf '%s\n' "$_site_block" >> "$_caddyfile"
log_success "Added $_domain to Caddyfile"
docker exec caddy caddy fmt --overwrite /etc/caddy/Caddyfile 2>/dev/null || true
if docker exec caddy caddy reload --config /etc/caddy/Caddyfile 2>/dev/null; then
log_success "$_name accessible at: https://$_domain"
else
log_warning "Reload failed — check: docker logs caddy"
log_info "Manual reload: docker exec caddy caddy reload --config /etc/caddy/Caddyfile"
fi
else
local _snippet_dir="$DOCKER_DIR/caddy-snippets"
local _snippet_file="$_snippet_dir/${_subdomain}.caddy"
mkdir -p "$_snippet_dir"
printf '%s\n' "$_site_block" > "$_snippet_file"
chown "$ACTUAL_USER:$ACTUAL_USER" "$_snippet_file" 2>/dev/null || true
log_success "Snippet saved: $_snippet_file"
log_info "Copy to Caddy machine:"
log_info " scp $_snippet_file caddy-host:~/caddy-snippets/"
log_info " rsync -av $_snippet_dir/ caddy-host:~/caddy-snippets/ (all at once)"
fi
}
write_readme() {
local _dir="$1"; shift
mkdir -p "$_dir"
cat > "$_dir/README.md"
}
backup_if_exists() {
local _file="$1"
[ -f "$_file" ] || return 0
cp -p "$_file" "${_file}.bak.$(date +%Y%m%d-%H%M%S)" 2>/dev/null
}
fi
ACTUAL_USER="${ACTUAL_USER:-${SUDO_USER:-$USER}}"
ACTUAL_HOME="$(getent passwd "$ACTUAL_USER" 2>/dev/null | cut -d: -f6 || echo "${HOME:-/root}")"
DOCKER_DIR="${DOCKER_DIR:-$ACTUAL_HOME/docker}"
DRY_RUN="${DRY_RUN:-false}"
UNATTENDED="${UNATTENDED:-false}"
SITE_TZ="${SITE_TZ:-$(cat /etc/timezone 2>/dev/null || echo UTC)}"
SITE_DOMAIN="${SITE_DOMAIN:-example.com}"
SITE_CADDY_NET="${SITE_CADDY_NET:-caddy_net}"
CADDY_REMOTE_HOST="${CADDY_REMOTE_HOST:-}"
register_service() { :; }
_RUN_STANDALONE=1
fi
# ─────────────────────────────────────────────────────────────────────────────
register_service archivebox utilities "Self-hosted web archiving — save pages like Wayback Machine (ArchiveBox)" 8000
install_archivebox() {
require_docker || return 1
local AB_DIR="$DOCKER_DIR/archivebox"
local WEB_PORT="8000"
if [ "$DRY_RUN" = true ]; then
echo "[DRY-RUN] archivebox would:"
echo " - Create $AB_DIR with docker-compose.yml"
echo " - Initialize ArchiveBox data directory"
echo " - Expose port 8000 (web UI), auto-scanned for a free host port"
return 0
fi
# Scan for a free host port — this default (8000) isn't unique to
# ArchiveBox in this repo, so a plain install shouldn't silently claim a
# port another already-running service holds. See CLAUDE.md's "Port
# collision avoidance" section.
find_free_port WEB_PORT "$WEB_PORT"
mkdir -p "$AB_DIR"
ensure_docker_dir_ownership "$AB_DIR"
cd "$AB_DIR" || return 1
# Mirrors configure_caddy_for_service's own mode resolution (lib/common.sh):
# explicit CADDY_MODE from the site config wins, then a local ~/docker/caddy,
# then the legacy CADDY_REMOTE_HOST var. Only "local" joins caddy_net — a
# remote Caddy box can't resolve container names on this host's bridge
# network anyway; it reaches this service via the host's published port.
local _CADDY_MODE="${CADDY_MODE:-none}"
[ "$_CADDY_MODE" = "none" ] && [ -d "$DOCKER_DIR/caddy" ] && _CADDY_MODE="local"
[ "$_CADDY_MODE" = "none" ] && [ -n "${CADDY_REMOTE_HOST:-}" ] && _CADDY_MODE="remote"
local _CADDY_NET_BLOCK=""
local _CADDY_NET_SECTION=""
if [ "$_CADDY_MODE" = "local" ]; then
_CADDY_NET_BLOCK=" networks:
- caddy_net
"
_CADDY_NET_SECTION="
networks:
caddy_net:
external: true
name: ${SITE_CADDY_NET:-caddy_net}
"
fi
backup_if_exists docker-compose.yml
cat > docker-compose.yml << ABCOMPOSE
name: archivebox
services:
archivebox:
image: archivebox/archivebox:latest
container_name: archivebox
restart: unless-stopped
user: "1000:1000"
environment:
- ALLOWED_HOSTS=*
- MEDIA_MAX_SIZE=750m
- PUBLIC_INDEX=True
- PUBLIC_SNAPSHOTS=True
- PUBLIC_ADD_VIEW=False
volumes:
- ./data:/data
ports:
- "${WEB_PORT}:8000"
${_CADDY_NET_BLOCK}${_CADDY_NET_SECTION}
ABCOMPOSE
backup_if_exists .env
cat > .env << ABENV
CADDY_NET=$SITE_CADDY_NET
ABENV
mkdir -p data
chown -R "$ACTUAL_USER:$ACTUAL_USER" "$AB_DIR"
log_info "Initializing ArchiveBox data directory..."
docker compose run --rm archivebox init --setup \
&& log_success "ArchiveBox initialized" \
|| log_warning "Init failed — will retry on first start"
configure_caddy_for_service "ArchiveBox" "archivebox:8000" "archive"
write_readme "$AB_DIR" << MD
# ArchiveBox
Self-hosted web archiving — saves full snapshots of web pages (HTML, screenshots,
PDFs, WARC) like a personal Wayback Machine.
- Web UI: http://localhost:${WEB_PORT}
## Manage
\`\`\`bash
cd ~/docker/archivebox
docker compose up -d # start
docker compose down # stop
docker compose logs -f # logs
docker compose pull && docker compose up -d # update
\`\`\`
## Add URLs to archive
\`\`\`bash
# Via web UI — visit http://localhost:${WEB_PORT} and use the Add page
# Via CLI:
echo "https://example.com" | docker compose run --rm archivebox add
docker compose run --rm archivebox add --depth=1 https://example.com
\`\`\`
## Create admin user
\`\`\`bash
docker compose run --rm archivebox manage createsuperuser
\`\`\`
MD
local START_AB=""
prompt_yn "Start ArchiveBox now? (y/n):" "y" START_AB
if [ "$START_AB" = "y" ] || [ "$START_AB" = "Y" ]; then
docker compose up -d \
&& log_success "ArchiveBox started — http://localhost:${WEB_PORT}" \
|| log_warning "Start failed — check: docker compose logs"
fi
echo ""
echo " Web UI: http://localhost:${WEB_PORT}"
echo " Add URLs via the web UI or: echo 'URL' | docker compose run --rm archivebox add"
echo ""
}
[[ "${_RUN_STANDALONE:-0}" == 1 ]] && install_archivebox