M36: deepen operational and mobile UX

backend/app/services/data_quality.py

@@ -133,47 +133,61 @@ def _scan_duplicate_customers(db: Session, scan: ScanResult) -> None:
         db.scalars(select(Customer).where(Customer.merged_into_customer_id.is_(None))).all()
     )
     customers.sort(key=lambda c: c.public_ref)
+    # The threshold cannot be reached without an exact email (60 points) or phone
+    # (50 points). Block on those normalized identifiers first, so similarity scoring
+    # scales with plausible candidates instead of comparing every customer pair.
+    candidate_pairs: set[tuple[int, int]] = set()
+    for attribute in ("email", "phone"):
+        blocks: dict[str, list[int]] = {}
+        for index, customer in enumerate(customers):
+            key = _normalize(getattr(customer, attribute))
+            if key:
+                blocks.setdefault(key, []).append(index)
+        for indices in blocks.values():
+            for offset, left in enumerate(indices):
+                candidate_pairs.update((left, right) for right in indices[offset + 1 :])
 
-    for i, a in enumerate(customers):
-        for b in customers[i + 1 :]:
-            score = 0
-            signals: list[dict] = []
-            summary_parts: list[str] = []
-            if _normalize(a.email) and _normalize(a.email) == _normalize(b.email):
-                score += 60
-                signals.append({"code": "duplicate.exact_email"})
-                summary_parts.append("exact email")
-            if _normalize(a.phone) and _normalize(a.phone) == _normalize(b.phone):
-                score += 50
-                signals.append({"code": "duplicate.exact_phone"})
-                summary_parts.append("exact phone")
-            if _normalize(a.postal_code) and _normalize(a.postal_code) == _normalize(b.postal_code):
-                score += 10
-                signals.append({"code": "duplicate.same_postal_code"})
-                summary_parts.append("exact postal code")
-            name_a = f"{_normalize(a.first_name)} {_normalize(a.last_name)}"
-            name_b = f"{_normalize(b.first_name)} {_normalize(b.last_name)}"
-            ratio = SequenceMatcher(None, name_a, name_b).ratio()
-            if ratio >= 0.5:
-                score += round(ratio * 30)
-                signals.append(
-                    {"code": "duplicate.similar_name", "params": {"score": round(ratio, 2)}}
-                )
-                summary_parts.append("similar name")
+    for left, right in sorted(candidate_pairs):
+        a = customers[left]
+        b = customers[right]
+        score = 0
+        signals: list[dict] = []
+        summary_parts: list[str] = []
+        if _normalize(a.email) and _normalize(a.email) == _normalize(b.email):
+            score += 60
+            signals.append({"code": "duplicate.exact_email"})
+            summary_parts.append("exact email")
+        if _normalize(a.phone) and _normalize(a.phone) == _normalize(b.phone):
+            score += 50
+            signals.append({"code": "duplicate.exact_phone"})
+            summary_parts.append("exact phone")
+        if _normalize(a.postal_code) and _normalize(a.postal_code) == _normalize(b.postal_code):
+            score += 10
+            signals.append({"code": "duplicate.same_postal_code"})
+            summary_parts.append("exact postal code")
+        name_a = f"{_normalize(a.first_name)} {_normalize(a.last_name)}"
+        name_b = f"{_normalize(b.first_name)} {_normalize(b.last_name)}"
+        ratio = SequenceMatcher(None, name_a, name_b).ratio()
+        if ratio >= 0.5:
+            score += round(ratio * 30)
+            signals.append(
+                {"code": "duplicate.similar_name", "params": {"score": round(ratio, 2)}}
+            )
+            summary_parts.append("similar name")
 
-            if score >= DUPLICATE_THRESHOLD:
-                _open_issue(
-                    db,
-                    scan,
-                    rule_type="possible_duplicate_customer",
-                    entity_type="customer",
-                    entity_id=a.id,
-                    severity="high",
-                    summary="; ".join(summary_parts) + f" (score {score})",
-                    entity_ref=a.public_ref,
-                    related_refs=[b.public_ref],
-                    signals=signals,
-                )
+        if score >= DUPLICATE_THRESHOLD:
+            _open_issue(
+                db,
+                scan,
+                rule_type="possible_duplicate_customer",
+                entity_type="customer",
+                entity_id=a.id,
+                severity="high",
+                summary="; ".join(summary_parts) + f" (score {score})",
+                entity_ref=a.public_ref,
+                related_refs=[b.public_ref],
+                signals=signals,
+            )
 
 
 def _scan_missing_required_fields(db: Session, scan: ScanResult) -> None: