feat: Excel-Mehrblattimport als einzelne Dokumentationen ergänzen

netbox_documentation/importers.py

@@ -14,6 +14,21 @@ class ImportResult:
     warnings: list[str] = field(default_factory=list)
 
 
+@dataclass
+class ImportedImage:
+    name: str
+    content: bytes
+    content_type: str
+    cell: str = ""
+
+
+@dataclass
+class ExcelSheetResult:
+    title: str
+    markdown: str
+    images: list[ImportedImage] = field(default_factory=list)
+
+
 def import_document(upload) -> ImportResult:
     suffix = Path(upload.name).suffix.lower()
     content = upload.read()
@@ -58,6 +73,60 @@ def _xlsx(content):
     return ImportResult("\n\n".join(sections))
 
 
+def import_excel_sheets(upload) -> list[ExcelSheetResult]:
+    """Convert each non-empty worksheet into an individual document payload."""
+    from openpyxl import load_workbook
+    from openpyxl.utils import get_column_letter
+    from tabulate import tabulate
+
+    suffix = Path(upload.name).suffix.lower()
+    if suffix not in {".xlsx", ".xlsm"}:
+        raise ImportFailure("Der Mehrblattimport unterstützt XLSX- und XLSM-Dateien.")
+    content = upload.read()
+    upload.seek(0)
+    workbook = load_workbook(BytesIO(content), read_only=False, data_only=True)
+    results = []
+    for sheet in workbook.worksheets:
+        rows = [["" if cell is None else str(cell) for cell in row] for row in sheet.iter_rows(values_only=True)]
+        while rows and not any(value for value in rows[-1]):
+            rows.pop()
+        images = []
+        for number, image in enumerate(getattr(sheet, "_images", ()), 1):
+            image_format = (getattr(image, "format", None) or "png").lower()
+            if image_format == "jpg":
+                image_format = "jpeg"
+            if image_format not in {"png", "jpeg", "gif", "webp"}:
+                continue
+            anchor = getattr(image, "anchor", None)
+            marker = getattr(anchor, "_from", None)
+            cell = f"{get_column_letter(marker.col + 1)}{marker.row + 1}" if marker else ""
+            try:
+                image_content = image._data()
+            except (AttributeError, OSError, ValueError):
+                continue
+            images.append(ImportedImage(
+                name=f"{slugify_filename(sheet.title)}-{number}.{image_format if image_format != 'jpeg' else 'jpg'}",
+                content=image_content, content_type=f"image/{image_format}", cell=cell,
+            ))
+        if not rows and not images:
+            continue
+        if rows:
+            width = max(len(row) for row in rows)
+            rows = [row + [""] * (width - len(row)) for row in rows]
+            markdown = tabulate(rows[1:], headers=rows[0], tablefmt="github")
+        else:
+            markdown = ""
+        results.append(ExcelSheetResult(title=sheet.title, markdown=markdown, images=images))
+    if not results:
+        raise ImportFailure("Die Arbeitsmappe enthält keine Daten oder unterstützten Bilder.")
+    return results
+
+
+def slugify_filename(value):
+    value = re.sub(r"[^A-Za-z0-9._-]+", "-", value).strip("-.")
+    return value[:80] or "arbeitsblatt"
+
+
 def _pdf(content):
     from pypdf import PdfReader
     reader = PdfReader(BytesIO(content))
@@ -70,4 +139,3 @@ def _pdf(content):
     if not pages:
         raise ImportFailure("Das PDF enthält keinen extrahierbaren Text. Für Scans ist OCR erforderlich.")
     return ImportResult("\n\n".join(pages), ["PDF-Layout und Bilder können nicht vollständig übernommen werden."])
-