Initial commit: PDF OCR Hotfolder v0.1.0

Komplettes Rewrite des alten Bash-Tools `pdf-tool` in Python.
- ocrmypdf als Library, watchdog für Hotfolder, ThreadPool für Parallelität
- Upload-Targets: folder, Nextcloud (WebDAV), SFTP
- E-Mail-Notify, optional veraPDF
- Interaktiver Installer mit Service-User-Support (lokal + AD via SSSD)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

install.sh

@@ -0,0 +1,157 @@
+#!/usr/bin/env bash
+#
+# PDF OCR Hotfolder — Installer für Debian 12/13
+#
+# Fragt interaktiv nach dem Service-User. Unterstützt:
+#   - Lokal anlegen (neuer System-User)
+#   - Bereits existierender lokaler User
+#   - AD-User mit lokaler UID (z.B. via 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} $*"; }
+log_step()  { echo -e "${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_DIR="/var/lib/pdf-ocr-hotfolder"
+LOG_DIR="/var/log/pdf-ocr-hotfolder"
+SERVICE_NAME="pdf-ocr-hotfolder"
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_DIR="$SCRIPT_DIR"
+
+if [ ! -f "$REPO_DIR/pdf_ocr_hotfolder/__init__.py" ]; then
+    log_error "Repo-Layout nicht erkannt. install.sh aus dem Repo ausführen."
+    exit 1
+fi
+
+echo
+echo "=========================================="
+echo "  PDF OCR Hotfolder — Installation"
+echo "=========================================="
+echo
+
+# ============ 1. System-Dependencies ============
+log_step "Installiere System-Pakete"
+
+apt-get update -qq
+apt-get install -y --no-install-recommends \
+    python3 python3-venv python3-pip \
+    tesseract-ocr tesseract-ocr-deu tesseract-ocr-eng \
+    ghostscript qpdf unpaper pngquant \
+    icc-profiles-free \
+    ca-certificates curl
+
+log_info "System-Pakete installiert ✓"
+
+# ============ 2. Service-User ============
+log_step "Service-User konfigurieren"
+
+read -r -p "Service-User-Name [pdfocr]: " SERVICE_USER
+SERVICE_USER="${SERVICE_USER:-pdfocr}"
+
+if id "$SERVICE_USER" &>/dev/null; then
+    log_info "User '$SERVICE_USER' existiert bereits (lokal oder via AD)."
+    SERVICE_GROUP="$(id -gn "$SERVICE_USER")"
+    log_info "Verwende bestehende primäre Gruppe: $SERVICE_GROUP"
+else
+    log_warn "User '$SERVICE_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 "$DATA_DIR" --shell /usr/sbin/nologin "$SERVICE_USER"
+        SERVICE_GROUP="$SERVICE_USER"
+        log_info "Lokaler System-User '$SERVICE_USER' angelegt ✓"
+    else
+        log_error "User '$SERVICE_USER' muss vor der Installation existieren (z.B. via AD/SSSD)."
+        log_error "Lege ihn an oder wähle einen existierenden Namen."
+        exit 1
+    fi
+fi
+
+# ============ 3. Verzeichnisse ============
+log_step "Verzeichnisse erstellen"
+
+mkdir -p "$INSTALL_DIR" "$CONFIG_DIR" "$LOG_DIR"
+mkdir -p "$DATA_DIR"/{incoming,outgoing,working,error}
+
+cp -r "$REPO_DIR/pdf_ocr_hotfolder" "$INSTALL_DIR/"
+cp "$REPO_DIR/requirements.txt" "$INSTALL_DIR/"
+cp "$REPO_DIR/VERSION" "$INSTALL_DIR/"
+echo "$REPO_DIR" > "$INSTALL_DIR/.repo_path"
+
+if [ ! -f "$CONFIG_DIR/config.toml" ]; then
+    cp "$REPO_DIR/config.example.toml" "$CONFIG_DIR/config.toml"
+    log_info "Beispiel-Konfig nach $CONFIG_DIR/config.toml kopiert"
+else
+    log_info "Bestehende Konfig $CONFIG_DIR/config.toml bleibt unverändert"
+fi
+
+log_info "Verzeichnisse erstellt ✓"
+
+# ============ 4. Python venv ============
+log_step "Python venv anlegen"
+
+if [ ! -d "$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 bereit ✓"
+
+# ============ 5. Berechtigungen ============
+log_step "Berechtigungen setzen"
+
+chown -R "$SERVICE_USER:$SERVICE_GROUP" "$INSTALL_DIR" "$DATA_DIR" "$LOG_DIR"
+chown root:"$SERVICE_GROUP" "$CONFIG_DIR"
+chmod 750 "$CONFIG_DIR"
+if [ -f "$CONFIG_DIR/config.toml" ]; then
+    chown root:"$SERVICE_GROUP" "$CONFIG_DIR/config.toml"
+    chmod 640 "$CONFIG_DIR/config.toml"
+fi
+
+log_info "Berechtigungen gesetzt ✓"
+
+# ============ 6. systemd-Unit ============
+log_step "systemd-Unit installieren"
+
+sed -e "s|__SERVICE_USER__|$SERVICE_USER|g" \
+    -e "s|__SERVICE_GROUP__|$SERVICE_GROUP|g" \
+    "$REPO_DIR/systemd/pdf-ocr-hotfolder.service" \
+    > "/etc/systemd/system/${SERVICE_NAME}.service"
+
+systemctl daemon-reload
+systemctl enable "${SERVICE_NAME}.service"
+
+log_info "systemd-Unit installiert & enabled ✓"
+
+# ============ 7. Start ============
+log_step "Service starten"
+systemctl restart "${SERVICE_NAME}.service"
+sleep 2
+systemctl --no-pager --lines=10 status "${SERVICE_NAME}.service" || true
+
+echo
+echo "=========================================="
+echo "  Installation abgeschlossen"
+echo "=========================================="
+echo
+echo "  Konfiguration:  $CONFIG_DIR/config.toml"
+echo "  Eingang:        $DATA_DIR/incoming"
+echo "  Ausgang:        $DATA_DIR/outgoing"
+echo "  Service-User:   $SERVICE_USER ($SERVICE_GROUP)"
+echo
+echo "  Logs:           journalctl -u $SERVICE_NAME -f"
+echo "  Update:         sudo ./update.sh"
+echo