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>
2026-04-08 00:22:31 +02:00
commit 76c3a991df
16 changed files with 1261 additions and 0 deletions
@@ -0,0 +1,129 @@
+"""Konfigurations-Loader (TOML)."""
+from __future__ import annotations
+
+import tomllib
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Any
+
+
+@dataclass
+class Paths:
+    incoming: Path
+    outgoing: Path
+    working: Path
+    error: Path
+
+
+@dataclass
+class OcrConfig:
+    languages: str = "deu+eng"
+    jobs: int = 4
+    skip_text: bool = True
+    oversample: int = 300
+    pdfa_level: str = "2"
+    deskew: bool = True
+    clean: bool = False
+    max_workers: int = 2
+    timeout: int = 1800
+
+
+@dataclass
+class VeraPdfConfig:
+    enabled: bool = False
+    binary: str = "/opt/verapdf/verapdf"
+    flavour: str = "1b"
+
+
+@dataclass
+class FolderUpload:
+    enabled: bool = True
+    target: str = ""
+
+
+@dataclass
+class NextcloudUpload:
+    enabled: bool = False
+    url: str = ""
+    username: str = ""
+    password: str = ""
+    remote_path: str = ""
+    verify_ssl: bool = True
+
+
+@dataclass
+class SftpUpload:
+    enabled: bool = False
+    host: str = ""
+    port: int = 22
+    username: str = ""
+    key_file: str = ""
+    password: str = ""
+    remote_path: str = ""
+
+
+@dataclass
+class EmailNotify:
+    enabled: bool = False
+    smtp_host: str = ""
+    smtp_port: int = 587
+    smtp_user: str = ""
+    smtp_password: str = ""
+    use_starttls: bool = True
+    from_addr: str = ""
+    to_addrs: list[str] = field(default_factory=list)
+    on: str = "errors"  # always | errors | never
+
+
+@dataclass
+class Config:
+    paths: Paths
+    ocr: OcrConfig
+    verapdf: VeraPdfConfig
+    folder: FolderUpload
+    nextcloud: NextcloudUpload
+    sftp: SftpUpload
+    email: EmailNotify
+    log_level: str = "INFO"
+
+
+def _section(data: dict[str, Any], *keys: str) -> dict[str, Any]:
+    cur: Any = data
+    for k in keys:
+        cur = cur.get(k, {}) if isinstance(cur, dict) else {}
+    return cur if isinstance(cur, dict) else {}
+
+
+def load_config(path: str | Path) -> Config:
+    path = Path(path)
+    with path.open("rb") as f:
+        data = tomllib.load(f)
+
+    p = _section(data, "paths")
+    paths = Paths(
+        incoming=Path(p["incoming"]),
+        outgoing=Path(p["outgoing"]),
+        working=Path(p["working"]),
+        error=Path(p["error"]),
+    )
+
+    ocr = OcrConfig(**{k: v for k, v in _section(data, "ocr").items()
+                       if k in OcrConfig.__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()
+                             if k in FolderUpload.__annotations__})
+    nextcloud = NextcloudUpload(**{k: v for k, v in _section(data, "upload", "nextcloud").items()
+                                   if k in NextcloudUpload.__annotations__})
+    sftp = SftpUpload(**{k: v for k, v in _section(data, "upload", "sftp").items()
+                         if k in SftpUpload.__annotations__})
+    email = EmailNotify(**{k: v for k, v in _section(data, "notify", "email").items()
+                           if k in EmailNotify.__annotations__})
+
+    log_level = _section(data, "logging").get("level", "INFO")
+
+    return Config(
+        paths=paths, ocr=ocr, verapdf=verapdf,
+        folder=folder, nextcloud=nextcloud, sftp=sftp, email=email,
+        log_level=log_level,
+    )