extract_ids.py impl. Bauen der json Files so dass die Bezeichnungen immer mit dabei stehen ausser in den Blättern.

lib/extract_ids.py

@@ -0,0 +1,137 @@
+"""Extract 9-digit Sivas IDs from JSON tree files generated by jsonFromXlsx.py.
+
+Collects Sivas numbers that sit one hierarchy level above the leaves
+and writes them as 'nummer: bezeichnung' into a text file.
+
+Usage:
+    python extract_ids.py --filename KA135776
+    python extract_ids.py --filename KA135776 --tab soll
+    python extract_ids.py --all
+"""
+
+import argparse
+import json
+import os
+import re
+import sys
+from pathlib import Path
+
+
+RE_SIVAS = re.compile(r"^(\d{9})")
+
+
+def is_leaf_value(v) -> bool:
+    """True if v is a leaf entry (string, anzahl-dict, or laenge-dict)."""
+    if isinstance(v, str):
+        return True
+    if isinstance(v, dict) and ("anzahl" in v or "laenge" in v):
+        return True
+    return False
+
+
+def extract_ids_from_tree(tree: dict) -> dict[str, str]:
+    """Collect 9-digit Sivas numbers one level above leaves.
+
+    Returns dict of nummer -> bezeichnung.
+    """
+    ids: dict[str, str] = {}
+
+    def walk(node: dict):
+        for key, value in node.items():
+            if not isinstance(value, dict) or "anzahl" in value or "laenge" in value:
+                continue  # leaf, skip
+            # Check if all children are leaves
+            all_leaves = all(is_leaf_value(v) for v in value.values())
+            m = RE_SIVAS.match(key)
+            if all_leaves and value and m:
+                nummer = m.group(1)
+                # Bezeichnung from key: part after "nummer-", underscores back to spaces
+                if len(key) > 9:
+                    bez = key[10:].replace("_", " ")
+                else:
+                    bez = nummer
+                ids[nummer] = bez
+            else:
+                walk(value)
+
+    walk(tree)
+    return ids
+
+
+def process_json(json_path: Path, tab: str, results_dir: Path) -> int:
+    """Extract IDs from one JSON file. Returns number of IDs found."""
+    with open(json_path, encoding="utf-8") as f:
+        tree = json.load(f)
+
+    ids = extract_ids_from_tree(tree)
+
+    # Derive project name: strip _ist/_soll suffix
+    project_name = json_path.stem
+    for suffix in ("_ist", "_soll"):
+        if project_name.endswith(suffix):
+            project_name = project_name[: -len(suffix)]
+            break
+
+    ids_path = results_dir / f"{project_name}_ids_{tab}.txt"
+    with open(ids_path, "w", encoding="utf-8") as f:
+        for nummer, bez in sorted(ids.items()):
+            f.write(f"{nummer}: {bez}\n")
+
+    print(f"  {json_path.name} -> {ids_path.name} ({len(ids)} IDs)")
+    return len(ids)
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Extrahiert 9-stellige Sivas-Nummern aus JSON-Baeumen im results/-Ordner."
+    )
+    parser.add_argument(
+        "--filename",
+        default=None,
+        help="Suchmuster fuer JSON-Dateien im results/-Ordner (z.B. 'KA135776')",
+    )
+    parser.add_argument(
+        "--tab",
+        choices=["soll", "ist"],
+        default="ist",
+        help="Welches Tab gelesen wird: 'ist' oder 'soll' (default: ist)",
+    )
+    parser.add_argument(
+        "--all",
+        action="store_true",
+        dest="process_all",
+        help="Alle *_<tab>.json Dateien im results/-Ordner verarbeiten",
+    )
+    args = parser.parse_args()
+
+    if not args.process_all and not args.filename:
+        parser.error("Entweder --filename oder --all muss angegeben werden.")
+
+    project_root = Path(os.environ.get("PROJECT", Path(__file__).resolve().parent.parent))
+    results_dir = project_root / "results"
+
+    if not results_dir.exists():
+        print(f"FEHLER: results/-Ordner nicht gefunden: {results_dir}")
+        sys.exit(1)
+
+    pattern = f"*_{args.tab}.json"
+    json_files = sorted(results_dir.glob(pattern))
+    if args.filename:
+        json_files = [f for f in json_files if args.filename.lower() in f.name.lower()]
+
+    if not json_files:
+        print(f"FEHLER: Keine JSON-Dateien mit Muster '{pattern}' in {results_dir} gefunden.")
+        if args.filename:
+            print(f"  (Filter: '{args.filename}')")
+        sys.exit(1)
+
+    print(f"Verarbeite {len(json_files)} JSON-Dateien aus {results_dir}\n")
+    total_ids = 0
+    for json_path in json_files:
+        total_ids += process_json(json_path, args.tab, results_dir)
+
+    print(f"\nFertig: {total_ids} IDs aus {len(json_files)} Dateien extrahiert.")
+
+
+if __name__ == "__main__":
+    main()