first ruggedy draft

packages/matching/mousehold_matching/fingerprints.py

@@ -0,0 +1,64 @@
+from __future__ import annotations
+
+import hashlib
+import json
+import re
+from datetime import date, datetime
+from decimal import Decimal
+from typing import Any
+
+
+def _stable_default(value: Any) -> str:
+    if isinstance(value, datetime | date):
+        return value.isoformat()
+    if isinstance(value, Decimal):
+        return str(value)
+    return str(value)
+
+
+def _stable_json(value: Any) -> str:
+    return json.dumps(
+        value, default=_stable_default, ensure_ascii=False, sort_keys=True, separators=(",", ":")
+    )
+
+
+def compute_raw_observation_hash(
+    *,
+    source_type: str,
+    source_reference: str | None = None,
+    raw_text: str | None = None,
+    raw_payload: dict[str, Any] | None = None,
+) -> str:
+    payload = {
+        "source_reference": source_reference,
+        "source_type": source_type,
+        "raw_payload": raw_payload or {},
+        "raw_text": raw_text or "",
+    }
+    return hashlib.sha256(_stable_json(payload).encode("utf-8")).hexdigest()
+
+
+def normalize_counterparty(value: str | None) -> str:
+    if not value:
+        return ""
+    compact = re.sub(r"[^a-z0-9]+", " ", value.lower())
+    return re.sub(r"\s+", " ", compact).strip()
+
+
+def compute_normalized_transaction_fingerprint(
+    *,
+    amount: Decimal | str | int | float,
+    currency: str,
+    event_date: date | str,
+    merchant: str | None = None,
+    counterparty: str | None = None,
+    external_id: str | None = None,
+) -> str:
+    normalized = {
+        "amount": str(Decimal(str(amount)).quantize(Decimal("0.01"))),
+        "currency": currency.upper(),
+        "event_date": event_date.isoformat() if isinstance(event_date, date) else event_date,
+        "party": normalize_counterparty(merchant or counterparty),
+        "external_id": external_id or "",
+    }
+    return hashlib.sha256(_stable_json(normalized).encode("utf-8")).hexdigest()