Skripts

python/merge_neu.py

@@ -0,0 +1,116 @@
+import json
+import sys
+import os
+
+# Felder, die ersetzt werden sollen, wenn sie in der Quelle vorhanden sind
+REPLACEMENT_FIELDS = [
+    "permanent",
+    "symptoms",
+    "contraction",
+    "name",
+    "description",
+    "durationValue",
+    "durationUnit",
+    "incubationValue",
+    "incubationUnit",
+    "results"
+]
+
+def merge_entry(target, source, warn_ids):
+    sid = source.get("id", "unbekannt")
+
+    # Standardfelder ersetzen
+    for field in REPLACEMENT_FIELDS:
+        if field in source:
+            target[field] = source[field]
+
+    # Effekte bearbeiten
+    source_effects = source.get('effects', [])
+    target_effects = target.get('effects', [])
+
+    # Effekte vergleichen und nur anhängen, wenn sie unterschiedlich sind
+    if isinstance(source_effects, list) and isinstance(target_effects, list):
+        for source_effect in source_effects:
+            if source_effect not in target_effects:
+                target_effects.append(source_effect)
+
+        # Label in Ziel-Effekten aktualisieren
+        new_name = source.get("name", target.get("name"))
+        for effect in target_effects:
+            if isinstance(effect, dict):
+                effect["label"] = new_name
+
+        # Aktualisierte Effekte zurückschreiben
+        target["effects"] = target_effects
+
+    elif isinstance(source_effects, list):
+        # Wenn Ziel keine Liste ist, aber Quelle schon, einfach ersetzen
+        target["effects"] = source_effects
+    else:
+        # Unerwartetes Format protokollieren
+        warn_ids.append(sid)
+
+    return target
+
+def merge_files(target_file, source_files, output_file=None, new_ids_log="new_ids.txt", warn_log="warn_ids.txt"):
+    with open(target_file, "r", encoding="utf-8") as f:
+        target_json = json.load(f)
+
+    target_entries = target_json.get("entries", target_json)
+    target_by_id = {entry["id"]: entry for entry in target_entries}
+    new_ids = []
+    warn_ids = []
+
+    for source_path in source_files:
+        print(f"🔄 Verarbeite {source_path} ...")
+        with open(source_path, "r", encoding="utf-8") as f:
+            source_json = json.load(f)
+
+        source_entries = source_json.get("entries", source_json)
+
+        for source_entry in source_entries:
+            sid = source_entry.get("id")
+            if not sid:
+                print("⚠️  Eintrag ohne ID übersprungen.")
+                continue
+
+            if sid in target_by_id:
+                target_by_id[sid] = merge_entry(target_by_id[sid], source_entry, warn_ids)
+            else:
+                target_by_id[sid] = source_entry
+                new_ids.append(sid)
+
+    # Ursprungsstruktur beibehalten
+    if "entries" in target_json:
+        target_json["entries"] = list(target_by_id.values())
+        final_output = target_json
+    else:
+        final_output = list(target_by_id.values())
+
+    # Datei überschreiben
+    with open(output_file or target_file, "w", encoding="utf-8") as f:
+        json.dump(final_output, f, indent=4, ensure_ascii=False)
+
+    # Neue IDs dokumentieren
+    if new_ids:
+        with open(new_ids_log, "w", encoding="utf-8") as f:
+            f.write("\n".join(new_ids))
+        print(f"🆕 {len(new_ids)} neue IDs – siehe {new_ids_log}")
+
+    # Warnungen dokumentieren
+    if warn_ids:
+        with open(warn_log, "w", encoding="utf-8") as f:
+            f.write("\n".join(warn_ids))
+        print(f"⚠️ {len(warn_ids)} Items mit ungültigen 'effects' – siehe {warn_log}")
+
+    print(f"📁 Merge abgeschlossen → Datei überschrieben: {target_file}")
+
+# Aufruf: python merge_items_with_effects_deduplicated.py ziel.json quelle1.json [quelle2.json ...]
+if __name__ == "__main__":
+    if len(sys.argv) < 3:
+        print("Nutzung: python merge_items_with_effects_deduplicated.py ziel.json quelle1.json [quelle2.json ...]")
+        sys.exit(1)
+
+    target = sys.argv[1]
+    sources = sys.argv[2:]
+    merge_files(target, sources)