Erste lauffähige Version

2026-05-21 10:36:16 +02:00
commit 6a103adac4
98 changed files with 4107 additions and 0 deletions
@@ -0,0 +1,74 @@
+"""
+DOCX-Rendering und PDF-Konvertierung.
+"""
+from __future__ import annotations
+
+import logging
+import re
+import subprocess
+import tempfile
+from pathlib import Path
+
+from docx import Document
+from docxtpl import DocxTemplate
+
+logger = logging.getLogger(__name__)
+
+PLACEHOLDER_RE = re.compile(r"\{\{\s*([A-Za-z_][A-Za-z0-9_]*)")
+
+
+def extract_placeholders(docx_path: Path) -> list[str]:
+    """Liest die Jinja-Platzhalter aus einem DOCX und gibt sie sortiert zurück."""
+    doc = Document(str(docx_path))
+    found: set[str] = set()
+    for para in doc.paragraphs:
+        for m in PLACEHOLDER_RE.finditer(para.text):
+            found.add(m.group(1))
+    for table in doc.tables:
+        for row in table.rows:
+            for cell in row.cells:
+                for para in cell.paragraphs:
+                    for m in PLACEHOLDER_RE.finditer(para.text):
+                        found.add(m.group(1))
+    return sorted(found)
+
+
+def render_docx(template_path: Path, context: dict, out_path: Path) -> Path:
+    """Füllt das DOCX-Template mit Kontext und schreibt das Ergebnis."""
+    tpl = DocxTemplate(str(template_path))
+    tpl.render(context)
+    tpl.save(str(out_path))
+    return out_path
+
+
+def docx_to_pdf(docx_path: Path, out_dir: Path) -> Path:
+    """Konvertiert DOCX nach PDF mit LibreOffice headless.
+
+    LibreOffice braucht ein eigenes Profilverzeichnis, sonst kollidieren
+    parallele Worker.
+    """
+    out_dir.mkdir(parents=True, exist_ok=True)
+    with tempfile.TemporaryDirectory(prefix="lo-profile-") as profile_dir:
+        cmd = [
+            "soffice",
+            "--headless",
+            "--nologo",
+            "--norestore",
+            "--nolockcheck",
+            f"-env:UserInstallation=file://{profile_dir}",
+            "--convert-to", "pdf",
+            "--outdir", str(out_dir),
+            str(docx_path),
+        ]
+        logger.info("LibreOffice convert: %s", " ".join(cmd))
+        result = subprocess.run(  # noqa: S603
+            cmd, capture_output=True, text=True, timeout=120, check=False
+        )
+        if result.returncode != 0:
+            raise RuntimeError(
+                f"LibreOffice-Konvertierung fehlgeschlagen: {result.stderr}"
+            )
+    pdf_path = out_dir / (docx_path.stem + ".pdf")
+    if not pdf_path.exists():
+        raise FileNotFoundError(f"PDF nicht gefunden: {pdf_path}")
+    return pdf_path
@@ -0,0 +1,14 @@
+from pathlib import Path
+
+from pypdf import PdfWriter
+
+
+def merge_pdfs(pdfs: list[Path], out_path: Path) -> Path:
+    writer = PdfWriter()
+    for pdf in pdfs:
+        writer.append(str(pdf))
+    out_path.parent.mkdir(parents=True, exist_ok=True)
+    with out_path.open("wb") as f:
+        writer.write(f)
+    writer.close()
+    return out_path