Initial SOC memory POC implementation

pipeline/jobs/ingest_case.py

@@ -0,0 +1,41 @@
+"""Batch-ingest mock case files and emit normalized case JSON documents."""
+from __future__ import annotations
+
+import json
+from dataclasses import asdict
+from pathlib import Path
+
+from pipeline.transforms.normalize_case import load_and_normalize_case
+
+
+def ingest_cases(input_dir: str | Path, output_dir: str | Path) -> list[Path]:
+    input_dir = Path(input_dir)
+    output_dir = Path(output_dir)
+    output_dir.mkdir(parents=True, exist_ok=True)
+
+    written: list[Path] = []
+    for src in sorted(input_dir.rglob("*.json")):
+        normalized = load_and_normalize_case(src)
+        dest = output_dir / f"{normalized.id}.json"
+        with dest.open("w", encoding="utf-8") as f:
+            json.dump(asdict(normalized), f, ensure_ascii=False, indent=2)
+        written.append(dest)
+    return written
+
+
+def main() -> None:
+    import argparse
+
+    parser = argparse.ArgumentParser(description="Normalize a directory of mock case JSON files.")
+    parser.add_argument("--input-dir", default="evaluation/datasets/mock_cases", help="Directory containing raw mock case files")
+    parser.add_argument("--output-dir", default="evaluation/datasets/normalized_cases", help="Directory to write normalized case files")
+    args = parser.parse_args()
+
+    written = ingest_cases(args.input_dir, args.output_dir)
+    print(f"normalized_cases={len(written)}")
+    for path in written:
+        print(path)
+
+
+if __name__ == "__main__":
+    main()