feat: add cdr validation and normalization domain

tests/unit/test_normalization.py

@@ -0,0 +1,77 @@
+from core.domain.normalization import generate_cdr_id, normalize_cdr, normalize_rat
+from core.domain.validation import parse_raw_cdr
+
+
+def test_normalize_valid_cdr() -> None:
+    payload = {
+        "raw_id": "raw-us-east-9988221",
+        "src_ip": "10.240.12.1",
+        "device_id": "310410998877665",
+        "caller_num": "0019875551234",
+        "svc": "4G_DATA",
+        "up_bytes": 1048576,
+        "down_bytes": 4194304,
+        "rat": 6,
+        "lac": "4021",
+        "ci": "8812",
+        "epoch_start": 1726070000,
+        "epoch_end": 1726070300,
+    }
+
+    raw = parse_raw_cdr(payload)
+
+    normalized = normalize_cdr(raw)
+
+    assert normalized.raw_id == "raw-us-east-9988221"
+    assert normalized.imsi == "310410998877665"
+    assert normalized.msisdn == "+19875551234"
+
+    assert normalized.service_type == "4G_DATA"
+    assert normalized.radio_access_type == "LTE_4G"
+
+    assert normalized.cell_id == "4021_8812"
+
+    assert normalized.bytes_uploaded == 1048576
+    assert normalized.bytes_downloaded == 4194304
+    assert normalized.total_bytes == 5242880
+
+    assert normalized.duration_seconds == 300
+
+    assert str(normalized.source_ip) == "10.240.12.1"
+
+def test_cdr_id_is_deterministic() -> None:
+    first = generate_cdr_id("raw-123")
+    second = generate_cdr_id("raw-123")
+
+    assert first == second
+
+def test_different_raw_ids_generate_different_cdr_ids() -> None:
+    first = generate_cdr_id("raw-123")
+    second = generate_cdr_id("raw-456")
+
+    assert first != second
+
+def test_rat_mapping() -> None:
+    assert normalize_rat(1) == "3G"
+    assert normalize_rat(6) == "LTE_4G"
+    assert normalize_rat(9) == "5G_NR"
+
+def test_missing_source_ip_defaults_to_zero_address() -> None:
+    payload = {
+        "raw_id": "raw-001",
+        "device_id": "310410998877665",
+        "caller_num": "0019875551234",
+        "svc": "4G_DATA",
+        "up_bytes": 100,
+        "down_bytes": 200,
+        "rat": 6,
+        "lac": "4021",
+        "ci": "8812",
+        "epoch_start": 1726070000,
+        "epoch_end": 1726070300,
+    }
+
+    raw = parse_raw_cdr(payload)
+    normalized = normalize_cdr(raw)
+
+    assert str(normalized.source_ip) == "0.0.0.0"