feat: konfigurierbarer Dateiname + Archiv-Modus für Original (v0.3.0)

Neue [output]-Section:
- name_mode: prefix | suffix | none (suffix wird vor Extension eingefügt)
- name_tag: verbatim einfügbarer String
- original_on_success: delete | archive
- archive_dir mit Kollisions-Schutz (Timestamp-Suffix)

20 neue Tests (50 insgesamt, alle grün).

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

CHANGELOG.md

@@ -1,5 +1,20 @@
 # Changelog
 
+## [0.3.0] - 2026-04-09
+
+### Added
+- Neue Config-Sektion `[output]` mit:
+  - `name_mode` — Platzierung des Tags im Dateinamen: `"prefix"`, `"suffix"` (vor Extension), `"none"`
+  - `name_tag` — verbatim einzufügender String, z.B. `"OCR_"` oder `"_OCR"`
+  - `original_on_success` — `"delete"` (alter Default) oder `"archive"`
+  - `archive_dir` — Zielverzeichnis für `"archive"`, mit Kollisions-Schutz (Timestamp-Suffix)
+- Runtime-Validierung der Output-Config in `check_output_config()`
+- 20 neue Tests für `build_output_name()`, `check_output_config()` und `process_pdf()`
+  mit allen Kombinationen aus Modus + Original-Behandlung
+
+### Changed
+- `process_pdf()` nimmt jetzt `output_cfg: OutputConfig` als Pflicht-Argument
+
 ## [0.2.2] - 2026-04-09
 
 ### Fixed

README.md

@@ -89,6 +89,22 @@ max_workers = 2          # parallele PDFs
 timeout = 1800
 ```
 
+### `[output]`
+```toml
+# Dateiname im outgoing/:
+#   "prefix" → OCR_scan.pdf
+#   "suffix" → scan_OCR.pdf (vor der Extension)
+#   "none"   → scan.pdf (unverändert)
+name_mode = "prefix"
+name_tag  = "OCR_"
+
+# Nach erfolgreichem OCR mit dem Original:
+#   "delete"  → löschen
+#   "archive" → in archive_dir verschieben
+original_on_success = "delete"
+archive_dir = ""     # absoluter Pfad, Pflicht bei "archive"
+```
+
 ### `[upload.nextcloud]`
 ```toml
 enabled = true

VERSION

@@ -1 +1 @@
-0.2.2
+0.3.0

config.example.toml

@@ -34,6 +34,22 @@ max_workers = 2
 # Timeout pro PDF in Sekunden
 timeout = 1800
 
+[output]
+# Wie soll die Ziel-Datei im outgoing/-Ordner benannt werden?
+#   "prefix" : name_tag wird vor den Dateinamen gestellt  (OCR_scan.pdf)
+#   "suffix" : name_tag wird vor die Extension gestellt   (scan_OCR.pdf)
+#   "none"   : Dateiname bleibt wie das Original
+name_mode = "prefix"
+# Verbatim einzufügender String. Leerer String = kein Tag (wie mode="none").
+# Beispiele: "OCR_", "[OCR]_", "_OCR", "_searchable"
+name_tag = "OCR_"
+# Was passiert mit dem Original, wenn OCR erfolgreich war?
+#   "delete"  : Original wird gelöscht (alter Standard)
+#   "archive" : Original wird in archive_dir verschoben
+original_on_success = "delete"
+# Absoluter Pfad; nur relevant wenn original_on_success = "archive"
+archive_dir = ""
+
 [verapdf]
 # PDF/A-Validierung (optional)
 enabled = false

pdf_ocr_hotfolder/config.py

@@ -28,6 +28,18 @@ class OcrConfig:
     timeout: int = 1800
 
 
+@dataclass
+class OutputConfig:
+    # "prefix" | "suffix" | "none"
+    name_mode: str = "prefix"
+    # Tag-String, verbatim eingefügt (Leerstring = kein Tag)
+    name_tag: str = "OCR_"
+    # "delete" | "archive"
+    original_on_success: str = "delete"
+    # Absoluter Pfad; Pflicht wenn original_on_success == "archive"
+    archive_dir: str = ""
+
+
 @dataclass
 class VeraPdfConfig:
     enabled: bool = False
@@ -79,6 +91,7 @@ class EmailNotify:
 class Config:
     paths: Paths
     ocr: OcrConfig
+    output: OutputConfig
     verapdf: VeraPdfConfig
     folder: FolderUpload
     nextcloud: NextcloudUpload
@@ -109,6 +122,8 @@ def load_config(path: str | Path) -> Config:
 
     ocr = OcrConfig(**{k: v for k, v in _section(data, "ocr").items()
                        if k in OcrConfig.__annotations__})
+    output = OutputConfig(**{k: v for k, v in _section(data, "output").items()
+                             if k in OutputConfig.__annotations__})
     verapdf = VeraPdfConfig(**{k: v for k, v in _section(data, "verapdf").items()
                                if k in VeraPdfConfig.__annotations__})
     folder = FolderUpload(**{k: v for k, v in _section(data, "upload", "folder").items()
@@ -123,7 +138,7 @@ def load_config(path: str | Path) -> Config:
     log_level = _section(data, "logging").get("level", "INFO")
 
     return Config(
-        paths=paths, ocr=ocr, verapdf=verapdf,
+        paths=paths, ocr=ocr, output=output, verapdf=verapdf,
         folder=folder, nextcloud=nextcloud, sftp=sftp, email=email,
         log_level=log_level,
     )

pdf_ocr_hotfolder/processor.py

@@ -7,11 +7,37 @@ import subprocess
 from dataclasses import dataclass
 from pathlib import Path
 
-from .config import OcrConfig, VeraPdfConfig
+from .config import OcrConfig, OutputConfig, VeraPdfConfig
 
 log = logging.getLogger(__name__)
 
 
+def build_output_name(src_name: str, mode: str, tag: str) -> str:
+    """Erzeugt den Ziel-Dateinamen für ein OCR-PDF.
+
+    Args:
+        src_name: Original-Dateiname (z.B. "scan.pdf")
+        mode: "prefix" | "suffix" | "none"
+        tag: Einzufügender String (verbatim, leer = kein Tag)
+
+    Beispiele:
+        prefix "OCR_":  "scan.pdf"  -> "OCR_scan.pdf"
+        suffix "_OCR":  "scan.pdf"  -> "scan_OCR.pdf"
+        suffix "_OCR":  "scan.tar.gz.pdf" -> "scan.tar.gz_OCR.pdf"
+        none:           "scan.pdf"  -> "scan.pdf"
+    """
+    if mode == "none" or not tag:
+        return src_name
+    if mode == "prefix":
+        return f"{tag}{src_name}"
+    if mode == "suffix":
+        # Nur die letzte Extension abspalten, sonst "foo.bar.pdf" kaputt gemacht
+        p = Path(src_name)
+        stem, ext = p.stem, p.suffix
+        return f"{stem}{tag}{ext}"
+    raise ValueError(f"Unbekannter name_mode: {mode!r}")
+
+
 @dataclass
 class ProcessResult:
     source: Path
@@ -71,11 +97,13 @@ def process_pdf(
     error_dir: Path,
     ocr_cfg: OcrConfig,
     vera_cfg: VeraPdfConfig,
+    output_cfg: OutputConfig,
 ) -> ProcessResult:
     """Verarbeitet eine einzelne PDF: move→OCR→validate→outgoing/error."""
+    out_name = build_output_name(src.name, output_cfg.name_mode, output_cfg.name_tag)
     work_src = working_dir / src.name
-    work_out = working_dir / f"OCR_{src.name}"
-    final_out = outgoing_dir / f"OCR_{src.name}"
+    work_out = working_dir / f"__ocr_{out_name}"  # Temp-Name, damit er != src.name ist
+    final_out = outgoing_dir / out_name
 
     try:
         shutil.move(str(src), str(work_src))
@@ -100,10 +128,38 @@ def process_pdf(
 
     outgoing_dir.mkdir(parents=True, exist_ok=True)
     shutil.move(str(work_out), str(final_out))
-    work_src.unlink(missing_ok=True)
+    _dispose_original(work_src, src.name, output_cfg)
     return ProcessResult(src, final_out, True, verapdf_passed=vera_ok)
 
 
+def _dispose_original(work_src: Path, original_name: str, cfg: OutputConfig) -> None:
+    """Entsorgt das Original nach erfolgreichem OCR — löschen oder archivieren."""
+    if not work_src.exists():
+        return
+    mode = cfg.original_on_success
+    if mode == "delete":
+        work_src.unlink(missing_ok=True)
+        return
+    if mode == "archive":
+        if not cfg.archive_dir:
+            log.error("original_on_success=archive aber archive_dir ist leer — lösche stattdessen")
+            work_src.unlink(missing_ok=True)
+            return
+        archive = Path(cfg.archive_dir)
+        archive.mkdir(parents=True, exist_ok=True)
+        dest = archive / original_name
+        # Bei Namens-Kollision mit Timestamp umbenennen
+        if dest.exists():
+            from datetime import datetime
+            ts = datetime.now().strftime("%Y%m%d-%H%M%S")
+            dest = archive / f"{dest.stem}_{ts}{dest.suffix}"
+        shutil.move(str(work_src), str(dest))
+        log.info("Original archiviert: %s", dest)
+        return
+    log.warning("Unbekannter original_on_success=%r — lösche stattdessen", mode)
+    work_src.unlink(missing_ok=True)
+
+
 def _move_to_error(p: Path, error_dir: Path) -> None:
     error_dir.mkdir(parents=True, exist_ok=True)
     try:

pdf_ocr_hotfolder/service.py

@@ -72,6 +72,20 @@ def detect_ghostscript_version() -> str | None:
     return result.stdout.strip() or None
 
 
+def check_output_config(mode: str, archive_dir: str) -> None:
+    """Validiert die [output]-Section. Wirft PreflightError bei Problemen."""
+    valid_modes = {"delete", "archive"}
+    if mode not in valid_modes:
+        raise PreflightError(
+            f"[output].original_on_success={mode!r} ungültig. "
+            f"Erlaubt: {sorted(valid_modes)}"
+        )
+    if mode == "archive" and not archive_dir:
+        raise PreflightError(
+            "[output].original_on_success='archive' erfordert [output].archive_dir"
+        )
+
+
 def check_preflight(pdfa_level: str = "") -> None:
     """Prüft externe Abhängigkeiten.
 
@@ -173,6 +187,8 @@ class HotfolderService:
 
     def run(self) -> None:
         check_preflight(self.cfg.ocr.pdfa_level)
+        check_output_config(self.cfg.output.original_on_success,
+                            self.cfg.output.archive_dir)
         self.ensure_dirs()
         self._scan_existing()
 
@@ -197,6 +213,8 @@ class HotfolderService:
             Anzahl fehlgeschlagener PDFs (0 = alles ok).
         """
         check_preflight(self.cfg.ocr.pdfa_level)
+        check_output_config(self.cfg.output.original_on_success,
+                            self.cfg.output.archive_dir)
         self.ensure_dirs()
         self._scan_existing()
         self._executor.shutdown(wait=True)
@@ -254,6 +272,7 @@ class HotfolderService:
             error_dir=self.cfg.paths.error,
             ocr_cfg=self.cfg.ocr,
             vera_cfg=self.cfg.verapdf,
+            output_cfg=self.cfg.output,
         )
 
         with self._lock:

tests/conftest.py

@@ -11,6 +11,7 @@ from pdf_ocr_hotfolder.config import (
     FolderUpload,
     NextcloudUpload,
     OcrConfig,
+    OutputConfig,
     Paths,
     SftpUpload,
     VeraPdfConfig,
@@ -32,6 +33,7 @@ def tmp_config(tmp_path: Path) -> Config:
     return Config(
         paths=paths,
         ocr=OcrConfig(max_workers=1),
+        output=OutputConfig(),
         verapdf=VeraPdfConfig(enabled=False),
         folder=FolderUpload(enabled=False),
         nextcloud=NextcloudUpload(enabled=False),

tests/test_once_exit_code.py

@@ -8,7 +8,7 @@ from pdf_ocr_hotfolder.processor import ProcessResult
 from pdf_ocr_hotfolder.service import HotfolderService
 
 
-def _fake_success(src: Path, working_dir, outgoing_dir, error_dir, ocr_cfg, vera_cfg):
+def _fake_success(src: Path, working_dir, outgoing_dir, error_dir, **kwargs):
     out = outgoing_dir / f"OCR_{src.name}"
     out.parent.mkdir(parents=True, exist_ok=True)
     out.write_bytes(b"%PDF-1.4 ocr\n")
@@ -16,7 +16,7 @@ def _fake_success(src: Path, working_dir, outgoing_dir, error_dir, ocr_cfg, vera
     return ProcessResult(src, out, True)
 
 
-def _fake_failure(src: Path, working_dir, outgoing_dir, error_dir, ocr_cfg, vera_cfg):
+def _fake_failure(src: Path, working_dir, outgoing_dir, error_dir, **kwargs):
     error_dir.mkdir(parents=True, exist_ok=True)
     dest = error_dir / src.name
     src.rename(dest)

tests/test_output_naming.py

@@ -0,0 +1,190 @@
+"""Tests für Feature: konfigurierbare Dateinamen und Original-Behandlung."""
+from __future__ import annotations
+
+from pathlib import Path
+from unittest.mock import patch
+
+import pytest
+
+from pdf_ocr_hotfolder.config import OcrConfig, OutputConfig, VeraPdfConfig
+from pdf_ocr_hotfolder.processor import build_output_name, process_pdf
+from pdf_ocr_hotfolder.service import PreflightError, check_output_config
+
+
+# ---------------- build_output_name ----------------
+
+@pytest.mark.parametrize("src,mode,tag,expected", [
+    # prefix
+    ("scan.pdf",          "prefix", "OCR_",  "OCR_scan.pdf"),
+    ("scan.pdf",          "prefix", "[OCR] ", "[OCR] scan.pdf"),
+    # suffix (Tag vor Extension)
+    ("scan.pdf",          "suffix", "_OCR",  "scan_OCR.pdf"),
+    ("scan.pdf",          "suffix", "-ocr",  "scan-ocr.pdf"),
+    # none
+    ("scan.pdf",          "none",   "OCR_",  "scan.pdf"),
+    # leerer Tag = none
+    ("scan.pdf",          "prefix", "",      "scan.pdf"),
+    ("scan.pdf",          "suffix", "",      "scan.pdf"),
+    # Mehrfach-Punkte im Namen: nur letzte Extension zählt
+    ("rechnung.2026.pdf", "suffix", "_OCR",  "rechnung.2026_OCR.pdf"),
+    ("rechnung.2026.pdf", "prefix", "OCR_",  "OCR_rechnung.2026.pdf"),
+    # Name ohne Extension
+    ("NO_EXT",            "suffix", "_OCR",  "NO_EXT_OCR"),
+])
+def test_build_output_name(src, mode, tag, expected) -> None:
+    assert build_output_name(src, mode, tag) == expected
+
+
+def test_build_output_name_invalid_mode() -> None:
+    with pytest.raises(ValueError, match="name_mode"):
+        build_output_name("x.pdf", "bogus", "OCR_")
+
+
+# ---------------- check_output_config ----------------
+
+def test_check_output_config_delete_ok() -> None:
+    check_output_config("delete", "")  # ok
+
+
+def test_check_output_config_archive_requires_dir() -> None:
+    with pytest.raises(PreflightError, match="archive_dir"):
+        check_output_config("archive", "")
+
+
+def test_check_output_config_archive_with_dir_ok() -> None:
+    check_output_config("archive", "/var/archive")  # ok
+
+
+def test_check_output_config_invalid_mode() -> None:
+    with pytest.raises(PreflightError, match="ungültig"):
+        check_output_config("trash", "")
+
+
+# ---------------- process_pdf mit Original-Behandlung ----------------
+
+def _fake_ocr(src: Path, dst: Path, cfg: OcrConfig) -> None:
+    """Simuliert ocrmypdf: kopiert Inhalt, erzeugt Zieldatei."""
+    dst.write_bytes(b"%PDF-1.4 OCRed\n" + src.read_bytes())
+
+
+def _prepare(tmp_path: Path) -> dict:
+    dirs = {
+        "working": tmp_path / "working",
+        "outgoing": tmp_path / "outgoing",
+        "error": tmp_path / "error",
+        "archive": tmp_path / "archive",
+        "incoming": tmp_path / "incoming",
+    }
+    for d in dirs.values():
+        d.mkdir(parents=True, exist_ok=True)
+    src = dirs["incoming"] / "scan.pdf"
+    src.write_bytes(b"%PDF-1.4 original\n")
+    return {"src": src, **dirs}
+
+
+def test_process_pdf_prefix_delete(tmp_path: Path) -> None:
+    env = _prepare(tmp_path)
+    out_cfg = OutputConfig(name_mode="prefix", name_tag="OCR_",
+                           original_on_success="delete")
+    with patch("pdf_ocr_hotfolder.processor.run_ocr", side_effect=_fake_ocr):
+        result = process_pdf(
+            src=env["src"],
+            working_dir=env["working"],
+            outgoing_dir=env["outgoing"],
+            error_dir=env["error"],
+            ocr_cfg=OcrConfig(),
+            vera_cfg=VeraPdfConfig(enabled=False),
+            output_cfg=out_cfg,
+        )
+    assert result.success
+    assert (env["outgoing"] / "OCR_scan.pdf").exists()
+    # Original ist weg, weder in incoming noch in working
+    assert not env["src"].exists()
+    assert not (env["working"] / "scan.pdf").exists()
+
+
+def test_process_pdf_suffix_delete(tmp_path: Path) -> None:
+    env = _prepare(tmp_path)
+    out_cfg = OutputConfig(name_mode="suffix", name_tag="_OCR",
+                           original_on_success="delete")
+    with patch("pdf_ocr_hotfolder.processor.run_ocr", side_effect=_fake_ocr):
+        result = process_pdf(
+            src=env["src"],
+            working_dir=env["working"],
+            outgoing_dir=env["outgoing"],
+            error_dir=env["error"],
+            ocr_cfg=OcrConfig(),
+            vera_cfg=VeraPdfConfig(enabled=False),
+            output_cfg=out_cfg,
+        )
+    assert result.success
+    assert (env["outgoing"] / "scan_OCR.pdf").exists()
+
+
+def test_process_pdf_none_mode(tmp_path: Path) -> None:
+    env = _prepare(tmp_path)
+    out_cfg = OutputConfig(name_mode="none", name_tag="OCR_",
+                           original_on_success="delete")
+    with patch("pdf_ocr_hotfolder.processor.run_ocr", side_effect=_fake_ocr):
+        result = process_pdf(
+            src=env["src"],
+            working_dir=env["working"],
+            outgoing_dir=env["outgoing"],
+            error_dir=env["error"],
+            ocr_cfg=OcrConfig(),
+            vera_cfg=VeraPdfConfig(enabled=False),
+            output_cfg=out_cfg,
+        )
+    assert result.success
+    # Ausgang hat GLEICHEN Namen wie Original
+    assert (env["outgoing"] / "scan.pdf").exists()
+
+
+def test_process_pdf_archive_original(tmp_path: Path) -> None:
+    env = _prepare(tmp_path)
+    out_cfg = OutputConfig(name_mode="prefix", name_tag="OCR_",
+                           original_on_success="archive",
+                           archive_dir=str(env["archive"]))
+    with patch("pdf_ocr_hotfolder.processor.run_ocr", side_effect=_fake_ocr):
+        result = process_pdf(
+            src=env["src"],
+            working_dir=env["working"],
+            outgoing_dir=env["outgoing"],
+            error_dir=env["error"],
+            ocr_cfg=OcrConfig(),
+            vera_cfg=VeraPdfConfig(enabled=False),
+            output_cfg=out_cfg,
+        )
+    assert result.success
+    assert (env["outgoing"] / "OCR_scan.pdf").exists()
+    # Original liegt jetzt im Archiv
+    archived = env["archive"] / "scan.pdf"
+    assert archived.exists()
+    assert archived.read_bytes() == b"%PDF-1.4 original\n"
+
+
+def test_process_pdf_archive_name_collision(tmp_path: Path) -> None:
+    """Bei Namens-Kollision im Archiv wird Timestamp angehängt."""
+    env = _prepare(tmp_path)
+    # Vorhandene Kollisions-Datei
+    (env["archive"] / "scan.pdf").write_bytes(b"old")
+
+    out_cfg = OutputConfig(name_mode="prefix", name_tag="OCR_",
+                           original_on_success="archive",
+                           archive_dir=str(env["archive"]))
+    with patch("pdf_ocr_hotfolder.processor.run_ocr", side_effect=_fake_ocr):
+        process_pdf(
+            src=env["src"],
+            working_dir=env["working"],
+            outgoing_dir=env["outgoing"],
+            error_dir=env["error"],
+            ocr_cfg=OcrConfig(),
+            vera_cfg=VeraPdfConfig(enabled=False),
+            output_cfg=out_cfg,
+        )
+    # Alte Datei unverändert
+    assert (env["archive"] / "scan.pdf").read_bytes() == b"old"
+    # Neue Datei mit Timestamp-Suffix
+    archived = list(env["archive"].glob("scan_*.pdf"))
+    assert len(archived) == 1
+    assert archived[0].read_bytes() == b"%PDF-1.4 original\n"