Files
pdf-ocr-hotfolder/install.sh
T
techadmin cbdc9d6664 Fix Issues #4, #5, #6: LXC-Kompatibilität, WorkingDirectory, GS-Backports
- #4: LXC/Container Drop-in (lxc-compat.conf) deaktiviert systemd-Hardening;
  Installer erkennt Container automatisch und bietet Drop-in an
- #5: WorkingDirectory=/opt/pdf-ocr-hotfolder in Template-Unit ergänzt
- #6: Installer bietet auf Debian 12 bei betroffenen GS-Versionen
  automatisch bookworm-backports Upgrade an (statt nur Warnung)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-11 01:41:54 +02:00

298 lines
11 KiB
Bash
Executable File
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env bash
#
# PDF OCR Hotfolder — Installer / Instanz-Manager für Debian 12/13
#
# Basis-Installation erfolgt einmalig (Code, venv, systemd-Template-Unit).
# Danach werden Hotfolder-Instanzen verwaltet:
# - Beim Erstlauf: mindestens eine Instanz wird angelegt
# - Beim Folgelauf: bestehende Instanzen werden erkannt; neue können ergänzt werden
#
# Unterstützt lokale System-User und AD-User mit lokaler UID (SSSD/Winbind).
#
set -euo pipefail
RED='\033[0;31m'; GREEN='\033[0;32m'; YELLOW='\033[1;33m'; BLUE='\033[0;34m'; NC='\033[0m'
log_info() { echo -e "${GREEN}[INFO]${NC} $*"; }
log_warn() { echo -e "${YELLOW}[WARN]${NC} $*"; }
log_error() { echo -e "${RED}[ERROR]${NC} $*"; }
log_step() { echo -e "\n${BLUE}==>${NC} $*"; }
if [ "${EUID}" -ne 0 ]; then
log_error "Bitte als root ausführen: sudo ./install.sh"
exit 1
fi
INSTALL_DIR="/opt/pdf-ocr-hotfolder"
CONFIG_DIR="/etc/pdf-ocr-hotfolder"
DATA_ROOT="/var/lib/pdf-ocr-hotfolder"
LOG_DIR="/var/log/pdf-ocr-hotfolder"
SERVICE_TEMPLATE="pdf-ocr-hotfolder@.service"
DEFAULT_USER="pdfocr"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO_DIR="$SCRIPT_DIR"
if [ ! -f "$REPO_DIR/pdf_ocr_hotfolder/__init__.py" ]; then
log_error "Repo-Layout nicht erkannt. install.sh aus dem Repo ausführen."
exit 1
fi
# ============================================================
# Basis-Installation (idempotent)
# ============================================================
install_base() {
log_step "System-Pakete installieren"
apt-get update -qq
apt-get install -y --no-install-recommends \
python3 python3-venv python3-pip \
tesseract-ocr tesseract-ocr-deu tesseract-ocr-eng \
ghostscript qpdf unpaper pngquant \
icc-profiles-free ca-certificates curl
log_info "System-Pakete ok ✓"
# Ghostscript-Versions-Check (Issue #3 + Issue #6)
if command -v gs >/dev/null 2>&1; then
GS_VER="$(gs --version 2>/dev/null || echo 0.0)"
log_info "Ghostscript: $GS_VER"
case "$GS_VER" in
10.0.0|10.00.0|10.01.*|10.02.0)
echo
log_warn "═══════════════════════════════════════════════════════════════"
log_warn "Ghostscript $GS_VER ist vom PDF/A-Bug betroffen (10.0.010.02.0)."
log_warn "Mit pdfa_level + skip_text=true kann ocrmypdf KEINE PDFs verarbeiten."
log_warn "═══════════════════════════════════════════════════════════════"
echo
# Prüfe ob Debian bookworm (12) — Backports anbieten
if grep -q 'bookworm' /etc/os-release 2>/dev/null; then
read -r -p "Ghostscript via bookworm-backports upgraden? [J/n]: " UPGRADE_GS
UPGRADE_GS="${UPGRADE_GS:-J}"
if [[ "$UPGRADE_GS" =~ ^[JjYy]$ ]]; then
log_info "Aktiviere bookworm-backports..."
if ! grep -q 'bookworm-backports' /etc/apt/sources.list /etc/apt/sources.list.d/*.list 2>/dev/null; then
echo 'deb http://deb.debian.org/debian bookworm-backports main' \
> /etc/apt/sources.list.d/bookworm-backports.list
apt-get update -qq
fi
apt-get install -y -t bookworm-backports ghostscript
GS_VER_NEW="$(gs --version 2>/dev/null || echo '?')"
log_info "Ghostscript aktualisiert: $GS_VER$GS_VER_NEW"
else
log_warn "Workaround: In der Config [ocr].pdfa_level = \"\" setzen (Default ab v0.2.2)"
fi
else
log_warn "Kein Debian bookworm erkannt — manuelles Upgrade nötig."
log_warn "Workaround: In der Config [ocr].pdfa_level = \"\" setzen (Default ab v0.2.2)"
fi
echo
;;
esac
fi
# LXC/Container-Erkennung (Issue #4)
if systemd-detect-virt --container -q 2>/dev/null; then
VIRT_TYPE="$(systemd-detect-virt --container 2>/dev/null || echo 'container')"
log_warn "Container-Umgebung erkannt ($VIRT_TYPE)."
log_warn "systemd-Hardening kann in Containern fehlschlagen (Error 226/NAMESPACE)."
read -r -p "LXC-Kompatibilitäts-Drop-in installieren? [J/n]: " LXC_FIX
LXC_FIX="${LXC_FIX:-J}"
if [[ "$LXC_FIX" =~ ^[JjYy]$ ]]; then
local LXC_DROPIN_DIR="/etc/systemd/system/pdf-ocr-hotfolder@.service.d"
mkdir -p "$LXC_DROPIN_DIR"
cp "$REPO_DIR/systemd/lxc-compat.conf" "$LXC_DROPIN_DIR/lxc-compat.conf"
systemctl daemon-reload
log_info "LXC-Kompatibilitäts-Drop-in installiert ✓"
fi
fi
log_step "Default-User '$DEFAULT_USER' prüfen"
if id "$DEFAULT_USER" &>/dev/null; then
log_info "'$DEFAULT_USER' existiert bereits"
else
adduser --system --group --home "$DATA_ROOT" --shell /usr/sbin/nologin "$DEFAULT_USER"
log_info "System-User '$DEFAULT_USER' angelegt ✓"
fi
log_step "Verzeichnisse anlegen"
mkdir -p "$INSTALL_DIR" "$CONFIG_DIR" "$DATA_ROOT" "$LOG_DIR"
chown root:"$DEFAULT_USER" "$CONFIG_DIR"
chmod 750 "$CONFIG_DIR"
log_step "Code kopieren"
rm -rf "$INSTALL_DIR/pdf_ocr_hotfolder"
cp -r "$REPO_DIR/pdf_ocr_hotfolder" "$INSTALL_DIR/"
cp "$REPO_DIR/requirements.txt" "$INSTALL_DIR/"
cp "$REPO_DIR/VERSION" "$INSTALL_DIR/"
cp "$REPO_DIR/config.example.toml" "$INSTALL_DIR/"
echo "$REPO_DIR" > "$INSTALL_DIR/.repo_path"
log_step "Python venv"
if [ ! -d "$INSTALL_DIR/venv" ]; then
python3 -m venv "$INSTALL_DIR/venv"
fi
"$INSTALL_DIR/venv/bin/pip" install --upgrade pip -q
"$INSTALL_DIR/venv/bin/pip" install -r "$INSTALL_DIR/requirements.txt" -q
log_info "venv ok ✓"
log_step "systemd Template-Unit installieren"
cp "$REPO_DIR/systemd/$SERVICE_TEMPLATE" "/etc/systemd/system/$SERVICE_TEMPLATE"
systemctl daemon-reload
log_info "Template-Unit installiert ✓"
chown -R "$DEFAULT_USER":"$DEFAULT_USER" "$INSTALL_DIR" "$LOG_DIR"
}
# ============================================================
# Instanz-Verwaltung
# ============================================================
list_instances() {
find "$CONFIG_DIR" -maxdepth 1 -name '*.toml' -type f 2>/dev/null \
| sed 's|.*/||; s|\.toml$||' \
| sort
}
show_existing_instances() {
local instances
mapfile -t instances < <(list_instances)
if [ "${#instances[@]}" -eq 0 ]; then
log_info "Keine bestehenden Instanzen gefunden."
return
fi
echo
log_info "Bestehende Instanzen:"
for name in "${instances[@]}"; do
local active
active=$(systemctl is-active "pdf-ocr-hotfolder@${name}.service" 2>/dev/null || echo inactive)
printf " • %-30s [%s]\n" "$name" "$active"
done
echo
}
create_instance() {
echo
read -r -p "Instanz-Name (nur a-z, 0-9, -): " INST
if [[ ! "$INST" =~ ^[a-z0-9][a-z0-9-]*$ ]]; then
log_error "Ungültiger Name. Abbruch."
return 1
fi
if [ -f "$CONFIG_DIR/$INST.toml" ]; then
log_error "Instanz '$INST' existiert bereits. Abbruch."
return 1
fi
local default_base="$DATA_ROOT/$INST"
read -r -p "Basis-Pfad für Daten [$default_base]: " BASE
BASE="${BASE:-$default_base}"
read -r -p "Service-User [$DEFAULT_USER]: " SVC_USER
SVC_USER="${SVC_USER:-$DEFAULT_USER}"
local SVC_GROUP
if id "$SVC_USER" &>/dev/null; then
SVC_GROUP="$(id -gn "$SVC_USER")"
log_info "User '$SVC_USER' existiert (Gruppe: $SVC_GROUP)"
else
log_warn "User '$SVC_USER' existiert nicht."
read -r -p "Lokal als System-User anlegen? [J/n]: " CREATE_USER
CREATE_USER="${CREATE_USER:-J}"
if [[ "$CREATE_USER" =~ ^[JjYy]$ ]]; then
adduser --system --group --home "$BASE" --shell /usr/sbin/nologin "$SVC_USER"
SVC_GROUP="$SVC_USER"
log_info "User '$SVC_USER' angelegt ✓"
else
log_error "User muss existieren (z.B. via AD/SSSD). Abbruch."
return 1
fi
fi
log_info "Lege Datenverzeichnisse unter $BASE an..."
mkdir -p "$BASE"/{incoming,outgoing,working,error}
chown -R "$SVC_USER":"$SVC_GROUP" "$BASE"
log_info "Erstelle Config $CONFIG_DIR/$INST.toml..."
sed \
-e "s|/var/lib/pdf-ocr-hotfolder/incoming|$BASE/incoming|" \
-e "s|/var/lib/pdf-ocr-hotfolder/outgoing|$BASE/outgoing|" \
-e "s|/var/lib/pdf-ocr-hotfolder/working|$BASE/working|" \
-e "s|/var/lib/pdf-ocr-hotfolder/error|$BASE/error|" \
"$INSTALL_DIR/config.example.toml" > "$CONFIG_DIR/$INST.toml"
chown root:"$SVC_GROUP" "$CONFIG_DIR/$INST.toml"
chmod 640 "$CONFIG_DIR/$INST.toml"
# Drop-in für abweichenden Service-User
if [ "$SVC_USER" != "$DEFAULT_USER" ]; then
local DROPIN_DIR="/etc/systemd/system/pdf-ocr-hotfolder@${INST}.service.d"
mkdir -p "$DROPIN_DIR"
cat > "$DROPIN_DIR/user.conf" <<EOF
[Service]
User=$SVC_USER
Group=$SVC_GROUP
EOF
log_info "Drop-in für User '$SVC_USER' erstellt"
fi
systemctl daemon-reload
systemctl enable --now "pdf-ocr-hotfolder@${INST}.service"
sleep 1
if systemctl is-active --quiet "pdf-ocr-hotfolder@${INST}.service"; then
log_info "✅ Instanz '$INST' läuft"
else
log_warn "Instanz '$INST' läuft nicht. Logs: journalctl -u pdf-ocr-hotfolder@${INST}"
fi
echo
echo " Config: $CONFIG_DIR/$INST.toml"
echo " Eingang: $BASE/incoming"
echo " Ausgang: $BASE/outgoing"
echo " User: $SVC_USER ($SVC_GROUP)"
echo
}
# ============================================================
# Main
# ============================================================
echo
echo "=========================================="
echo " PDF OCR Hotfolder — Installer"
echo "=========================================="
if [ ! -d "$INSTALL_DIR/venv" ] || [ ! -f "/etc/systemd/system/$SERVICE_TEMPLATE" ]; then
log_step "Basis-Installation"
install_base
else
log_info "Basis-Installation bereits vorhanden ($INSTALL_DIR)"
log_info "Überspringe Basis-Setup (nutze update.sh für Code-Updates)"
fi
show_existing_instances
# Erste Instanz ist Pflicht, wenn noch keine vorhanden
mapfile -t existing < <(list_instances)
if [ "${#existing[@]}" -eq 0 ]; then
log_info "Lege erste Hotfolder-Instanz an."
create_instance || true
fi
while true; do
read -r -p "Weitere Instanz anlegen? [j/N]: " MORE
MORE="${MORE:-N}"
if [[ "$MORE" =~ ^[JjYy]$ ]]; then
create_instance || true
else
break
fi
done
echo
echo "=========================================="
echo " Fertig"
echo "=========================================="
show_existing_instances
echo " Logs: journalctl -u pdf-ocr-hotfolder@<instanz> -f"
echo " Neustart: systemctl restart pdf-ocr-hotfolder@<instanz>"
echo " Update: sudo ./update.sh"
echo