Add unknowns_classifier/src/unknowns_classifier/cli.py

unknowns_classifier/src/unknowns_classifier/cli.py

@@ -0,0 +1,61 @@
+import argparse
+import json
+import os
+from pathlib import Path
+from typing import List, Dict
+
+from unknowns_classifier.core import classify_unknowns
+
+def main() -> None:
+    """CLI entrypoint for classifying unknown cases from drift reports."""
+    parser = argparse.ArgumentParser(
+        description="Klassifiziert Unknown-Cases aus Drift-Reports in vordefinierte Kategorien."
+    )
+    parser.add_argument(
+        "--input",
+        required=True,
+        help="Pfad zum Ordner mit drift_report.json-Dateien."
+    )
+    parser.add_argument(
+        "--output",
+        required=False,
+        default="output/classified_unknowns.json",
+        help="Pfad zur Ausgabedatei für Klassifikationsergebnisse."
+    )
+
+    args = parser.parse_args()
+
+    input_path = Path(args.input)
+    output_path = Path(args.output)
+
+    if not input_path.exists() or not input_path.is_dir():
+        raise FileNotFoundError(f"Eingabeordner nicht gefunden: {input_path}")
+
+    unknown_cases: List[Dict] = []
+
+    for report_file in input_path.glob("*.json"):
+        with report_file.open('r', encoding='utf-8') as f:
+            try:
+                data = json.load(f)
+            except json.JSONDecodeError as e:
+                raise ValueError(f"Fehler beim Lesen von {report_file}: {e}") from e
+            if isinstance(data, dict) and 'unknowns' in data:
+                cases = data['unknowns']
+                if isinstance(cases, list):
+                    unknown_cases.extend(cases)
+
+    if not unknown_cases:
+        print("Keine Unknown-Cases gefunden.")
+        return
+
+    classified = classify_unknowns(unknown_cases)
+
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+
+    with output_path.open('w', encoding='utf-8') as f:
+        json.dump([c.__dict__ for c in classified], f, indent=2, ensure_ascii=False)
+
+    print(f"Klassifikation abgeschlossen. Ergebnisse gespeichert in: {output_path}")
+
+if __name__ == "__main__":
+    main()