Add grouped_run_statistics/src/grouped_run_statistics/cli.py

grouped_run_statistics/src/grouped_run_statistics/cli.py

@@ -0,0 +1,60 @@
+import argparse
+import json
+from pathlib import Path
+from collections import defaultdict
+from grouped_run_statistics.core import group_runs
+
+
+def main():
+    """CLI entrypoint for grouping run statistics based on pinned status."""
+    parser = argparse.ArgumentParser(description="Group run data by pinned/unpinned status and generate aggregated statistics.")
+    parser.add_argument(
+        "--input",
+        type=str,
+        required=True,
+        help="Pfad zur Eingabedatei mit Run-Daten im JSON-Format."
+    )
+    parser.add_argument(
+        "--output",
+        type=str,
+        required=True,
+        help="Pfad zur Ausgabedatei mit den gruppierten Statistikdaten im JSON-Format."
+    )
+
+    args = parser.parse_args()
+
+    input_path = Path(args.input)
+    output_path = Path(args.output)
+
+    if not input_path.exists():
+        raise FileNotFoundError(f"Input file not found: {input_path}")
+
+    with input_path.open("r", encoding="utf-8") as f:
+        try:
+            run_data = json.load(f)
+        except json.JSONDecodeError as e:
+            raise ValueError(f"Invalid JSON input: {e}") from e
+
+    if not isinstance(run_data, list):
+        raise ValueError("Input JSON must be a list of run records.")
+
+    # Validate minimal fields for data integrity
+    for idx, record in enumerate(run_data):
+        if not isinstance(record, dict):
+            raise ValueError(f"Run record at index {idx} is not a dictionary.")
+        required_keys = {"id", "pinned", "status"}
+        if not required_keys.issubset(record.keys()):
+            missing = required_keys - set(record.keys())
+            raise ValueError(f"Run record {idx} missing required fields: {missing}")
+
+    grouped_stats = group_runs(run_data)
+
+    # Ensure output directory exists
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+
+    with output_path.open("w", encoding="utf-8") as f:
+        json.dump(grouped_stats, f, indent=2)
+
+
+if __name__ == "__main__":
+    main()