feat(polizas): OCR capture for insurance policy PDFs

Mirrors the utility statement intake on the insurance side: a policy_ocr batch/document pair of tables, a GMX parser, a matcher keyed on Policy.policyNumber, and a "Captura" screen under /polizas that proposes policy -> customer for staff to confirm. Lifts the OCR seam out of StatementsModule into its own OcrModule so PolicyOcrModule can inject OCR_PROVIDER without taking on the rest of the statement pipeline; StatementsModule now imports it and binds nothing itself. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-01 14:07:29 -07:00
parent 5bce0e4c94
commit 5e9cb12fba
22 changed files with 3203 additions and 136 deletions
@@ -0,0 +1,101 @@
+import { Injectable } from "@nestjs/common";
+import { PrismaService } from "../prisma/prisma.service";
+import type { ParsedPolicy } from "./parsers/policy-parser";
+
+export interface MatchResult {
+  policyId: string | null;
+  customerId: string | null;
+  /** Why it landed here — shown in the review queue verbatim. */
+  note: string;
+  /** True only for an unambiguous hit on `Policy.policyNumber`. */
+  confident: boolean;
+  /**
+   * Every policy that carries the parsed number, with its customer. >1 means
+   * the policy number is shared across customers and a human must pick.
+   */
+  candidates: { policyId: string; customerId: string; customerName: string; policyNumber: string }[];
+}
+
+/**
+ * Resolves a parsed policy page to an existing Policy (and its customer) the
+ * office already holds.
+ *
+ * **Match on `Policy.policyNumber` alone, never on the printed insured name.**
+ * The certificate's "Insured" line is the account's registrant, which drifts
+ * from the current owner — the same problem the statement matcher cites for
+ * utility bills ("ARNAIZ ROSAS ELSA AURORA" on a CESPT receipt for a
+ * customer this office holds as "CATT, RANDY"). Names are surfaced for the
+ * reviewer to sanity-check and never feed matching.
+ *
+ * A policy number that matches zero rows means the policy is new: the
+ * review screen then offers a customer picker and the confirm step creates
+ * the row. Multiple hits are surfaced rather than auto-picked — duplicate
+ * policy numbers across customers do occur (same group policy bound by two
+ * related parties), and picking one arbitrarily would silently book the
+ * wrong coverage.
+ */
+@Injectable()
+export class PolicyMatcherService {
+  constructor(private readonly prisma: PrismaService) {}
+
+  async match(parsed: ParsedPolicy): Promise<MatchResult> {
+    if (!parsed.policyNumber) {
+      return this.unmatched("no se pudo leer el número de póliza");
+    }
+
+    const rows = await this.prisma.policy.findMany({
+      where: { policyNumber: parsed.policyNumber },
+      select: {
+        id: true,
+        policyNumber: true,
+        customerId: true,
+        customer: { select: { name: true } },
+      },
+    });
+
+    const candidates = rows.map((r) => ({
+      policyId: r.id,
+      customerId: r.customerId,
+      customerName: r.customer.name,
+      policyNumber: r.policyNumber,
+    }));
+
+    if (rows.length === 0) {
+      return {
+        policyId: null,
+        customerId: null,
+        note: `no se encontró ninguna póliza con el número ${parsed.policyNumber}`,
+        confident: false,
+        candidates: [],
+      };
+    }
+
+    if (rows.length > 1) {
+      return {
+        policyId: null,
+        customerId: null,
+        note: `${rows.length} pólizas comparten el número ${parsed.policyNumber}`,
+        confident: false,
+        candidates,
+      };
+    }
+
+    return {
+      policyId: candidates[0].policyId,
+      customerId: candidates[0].customerId,
+      note: `coincidencia exacta por número de póliza ${parsed.policyNumber}`,
+      confident: true,
+      candidates,
+    };
+  }
+
+  private unmatched(note: string): MatchResult {
+    return {
+      policyId: null,
+      customerId: null,
+      note,
+      confident: false,
+      candidates: [],
+    };
+  }
+}