Hilfskripte zum Extrakt aus dem Produktprogramm erstellt. Kernkonzepte in README.md und doc

lib/create_examples.py

@@ -0,0 +1,159 @@
+"""
+create_examples.py - Liest Stuecklisten-Daten aus Excel-Dateien im Examples-Ordner.
+
+Verwendung:
+  python create_examples.py [--example-dir <pfad>]
+"""
+
+from __future__ import annotations
+
+import argparse
+import logging
+import sys
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any
+
+log = logging.getLogger(__name__)
+
+
+@dataclass
+class StkItem:
+    position: str
+    teilenummer: str
+    menge: Any
+
+
+def _cell_str(value: Any) -> str:
+    return str(value).strip() if value is not None else ""
+
+
+def _find_col_index(header_row: tuple[Any, ...], candidates: list[str]) -> int | None:
+    normalized = [_cell_str(v).lower() for v in header_row]
+    for candidate in candidates:
+        candidate_norm = candidate.lower()
+        if candidate_norm in normalized:
+            return normalized.index(candidate_norm)
+    return None
+
+
+def _extract_stk_liste_ist(xlsx_path: Path) -> list[StkItem]:
+    import openpyxl
+
+    wb = openpyxl.load_workbook(str(xlsx_path), read_only=True, data_only=True)
+    if "Stk.-Liste IST" not in wb.sheetnames:
+        wb.close()
+        raise ValueError("Reiter 'Stk.-Liste IST' nicht gefunden")
+
+    ws = wb["Stk.-Liste IST"]
+
+    header_idx: tuple[int | None, int | None, int | None] | None = None
+    items: list[StkItem] = []
+
+    for row in ws.iter_rows(values_only=True):
+        if header_idx is None:
+            pos_idx = _find_col_index(list(row), ["position", "pos", "pos."])
+            part_idx = _find_col_index(
+                list(row),
+                ["teilenummer", "teilnummer", "article", "artikelnummer"],
+            )
+            qty_idx = _find_col_index(list(row), ["menge", "anzahl", "qty", "quantity"])
+            if pos_idx is not None and part_idx is not None and qty_idx is not None:
+                header_idx = (pos_idx, part_idx, qty_idx)
+            continue
+
+        pos_idx, part_idx, qty_idx = header_idx
+        assert pos_idx is not None and part_idx is not None and qty_idx is not None
+
+        position = _cell_str(row[pos_idx]) if pos_idx < len(row) else ""
+        teilenummer = _cell_str(row[part_idx]) if part_idx < len(row) else ""
+        menge = row[qty_idx] if qty_idx < len(row) else None
+
+        # Leere Zeilen ueberspringen
+        if not position and not teilenummer and menge in ("", None):
+            continue
+        if not position or not teilenummer:
+            continue
+
+        items.append(StkItem(position=position, teilenummer=teilenummer, menge=menge))
+
+    wb.close()
+    return items
+
+
+def process_all(example_dir: Path) -> dict[str, list[dict[str, Any]]]:
+    """
+    Durchsucht rekursiv alle Unterverzeichnisse in example_dir.
+
+    Pro Unterverzeichnis wird die erste gefundene .xlsx-Datei gelesen und aus
+    dem Reiter "Stk.-Liste IST" werden Position, Teilenummer, Menge extrahiert.
+    """
+    if not example_dir.exists():
+        log.error("Beispiel-Verzeichnis existiert nicht: %s", example_dir)
+        sys.exit(1)
+
+    subdirs = sorted([p for p in example_dir.rglob("*") if p.is_dir()])
+    if not subdirs:
+        log.error("Keine Unterverzeichnisse in %s gefunden", example_dir)
+        sys.exit(1)
+
+    log.info("Gefunden: %d Unterverzeichnisse in %s", len(subdirs), example_dir)
+
+    result: dict[str, list[dict[str, Any]]] = {}
+    for folder in subdirs:
+        xlsx_files = sorted(folder.glob("*.xlsx"))
+        if not xlsx_files:
+            continue
+
+        xlsx_path = xlsx_files[0]
+        rel_folder = str(folder.relative_to(example_dir))
+        log.info("Verarbeite %s: %s", rel_folder, xlsx_path.name)
+        try:
+            items = _extract_stk_liste_ist(xlsx_path)
+        except ValueError as exc:
+            log.warning("%s/%s uebersprungen: %s", rel_folder, xlsx_path.name, exc)
+            continue
+
+        result[rel_folder] = [
+            {
+                "position": item.position,
+                "teilenummer": item.teilenummer,
+                "menge": item.menge,
+            }
+            for item in items
+        ]
+
+    log.info("Fertig. Gelesene Verzeichnisse mit Daten: %d", len(result))
+    return result
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Liest Position/Teilenummer/Menge aus Example-Exceldateien"
+    )
+    parser.add_argument("--example-dir", type=Path, default=None,
+                        help="example/ Verzeichnis (default: aus PV_EXAMPLES oder ./examples)")
+    parser.add_argument("--verbose", "-v", action="store_true",
+                        help="Ausfuehrliche Ausgabe")
+    args = parser.parse_args()
+
+    logging.basicConfig(
+        level=logging.DEBUG if args.verbose else logging.INFO,
+        format="%(levelname)-7s %(message)s",
+    )
+
+    import os
+    if args.example_dir:
+        example_dir = args.example_dir.resolve()
+    elif os.environ.get("PV_EXAMPLES"):
+        example_dir = Path(os.environ["PV_EXAMPLES"]).resolve()
+    else:
+        example_dir = Path("example").resolve()
+
+    log.info("Beispiel-Verzeichnis: %s", example_dir)
+    data = process_all(example_dir)
+    log.info("Objekt erzeugt mit %d Schluesseln", len(data))
+
+
+if __name__ == "__main__":
+    main()