实现腾讯通用票据OCR安全适配（07-28-travel-reimbursement-guide）

server/tests/unit/jobs/ocrJob.test.js

@@ -19,15 +19,16 @@ function buildClaimedInvoice(overrides = {}) {
   };
 }
 
-function buildPrisma(claimedInvoices) {
+function buildPrisma(claimedInvoices, { cachedOcrResult = null, invoiceConflicts = [] } = {}) {
   return {
     $queryRaw: vi.fn(async () => claimedInvoices),
     ocrResult: {
-      findUnique: vi.fn(async () => null),
+      findUnique: vi.fn(async () => cachedOcrResult),
       create: vi.fn(async () => ({ id: "ocr-result-1" })),
+      update: vi.fn(async ({ data }) => ({ id: cachedOcrResult?.id, ...data })),
     },
     invoicePool: {
-      findMany: vi.fn(async () => []),
+      findMany: vi.fn(async () => invoiceConflicts),
       findFirst: vi.fn(async () => null),
       update: vi.fn(async () => ({ id: "invoice-1" })),
     },
@@ -218,4 +219,144 @@ describe("ocrJob quality gate", () => {
     );
     expect(JSON.stringify(createdPayload)).not.toContain("\\u0000");
   });
+
+  it("accepts a cached no-code electronic train ticket and checks number-only duplicates", async () => {
+    await fs.writeFile(path.join(tempDir, "20260428/invoice.pdf"), "%PDF-1.4 synthetic");
+
+    const cachedOcrResult = {
+      id: "ocr-result-train",
+      result_json: {
+        documentSubtype: "ElectronicTrainTicketFull",
+        documentCategory: "electronic_train_ticket",
+        documentCount: 1,
+        transportMode: "pdf_native",
+        invoiceCode: null,
+        invoiceNumber: "251234567890",
+        invoiceDate: "2026-07-26",
+        amount: "95.00",
+        taxAmount: "5.00",
+        totalAmount: "100.00",
+        sellerName: null,
+        buyerName: "合成公司",
+        raw: {
+          UserName: "SENSITIVE-CACHED-PASSENGER",
+          UserID: "SENSITIVE-CACHED-ID",
+        },
+      },
+    };
+    const prisma = buildPrisma(
+      [
+        buildClaimedInvoice({
+          ocr_provider: "tencent",
+          storage_path: "20260428/invoice.pdf",
+          mime_type: "application/pdf",
+        }),
+      ],
+      { cachedOcrResult },
+    );
+    const logger = { warn: vi.fn(), error: vi.fn() };
+
+    const result = await runOcrOnce(
+      prisma,
+      {
+        storageDir: tempDir,
+        ocrBatchSize: 1,
+        ocrLockTtlSeconds: 300,
+        ocrMaxAttempts: 3,
+        ocrProvider: "tencent",
+      },
+      logger,
+      "ocr-test-worker",
+    );
+
+    expect(result).toEqual({ claimed: 1, available: 1, duplicate: 0, failed: 0 });
+    expect(prisma.invoicePool.update).toHaveBeenCalledWith(
+      expect.objectContaining({
+        data: expect.objectContaining({
+          status: "available",
+          invoice_code: null,
+          invoice_number: "251234567890",
+          seller_name: null,
+          buyer_name: "合成公司",
+        }),
+      }),
+    );
+    expect(prisma.invoicePool.findMany).toHaveBeenCalledWith(
+      expect.objectContaining({
+        where: expect.objectContaining({
+          AND: expect.arrayContaining([
+            expect.objectContaining({
+              OR: expect.arrayContaining([
+                { invoice_code: null, invoice_number: "251234567890" },
+              ]),
+            }),
+          ]),
+        }),
+      }),
+    );
+    expect(prisma.ocrResult.create).not.toHaveBeenCalled();
+    expect(prisma.ocrResult.update).toHaveBeenCalledWith(
+      expect.objectContaining({
+        where: { id: "ocr-result-train" },
+        data: expect.objectContaining({
+          result_json: expect.not.objectContaining({ raw: expect.anything() }),
+        }),
+      }),
+    );
+    expect(JSON.stringify(prisma.ocrResult.update.mock.calls[0][0])).not.toContain(
+      "SENSITIVE-CACHED",
+    );
+  });
+
+  it("marks a cached multiple-invoice result as a quality failure without provider retry", async () => {
+    await fs.writeFile(path.join(tempDir, "20260428/invoice.pdf"), "%PDF-1.4 synthetic");
+
+    const prisma = buildPrisma(
+      [
+        buildClaimedInvoice({
+          ocr_provider: "tencent",
+          storage_path: "20260428/invoice.pdf",
+          mime_type: "application/pdf",
+        }),
+      ],
+      {
+        cachedOcrResult: {
+          id: "ocr-result-multiple",
+          result_json: {
+            documentSubtype: null,
+            documentCategory: null,
+            documentCount: 2,
+            qualityError: "multiple_invoices_not_supported",
+            transportMode: "pdf_native",
+          },
+        },
+      },
+    );
+    const logger = { warn: vi.fn(), error: vi.fn() };
+
+    const result = await runOcrOnce(
+      prisma,
+      {
+        storageDir: tempDir,
+        ocrBatchSize: 1,
+        ocrLockTtlSeconds: 300,
+        ocrMaxAttempts: 3,
+        ocrProvider: "tencent",
+      },
+      logger,
+      "ocr-test-worker",
+    );
+
+    expect(result).toEqual({ claimed: 1, available: 0, duplicate: 0, failed: 1 });
+    expect(prisma.invoicePool.update).toHaveBeenCalledWith(
+      expect.objectContaining({
+        data: expect.objectContaining({
+          status: "ocr_failed",
+          ocr_last_error: "multiple_invoices_not_supported",
+          ocr_attempts: { increment: 1 },
+        }),
+      }),
+    );
+    expect(logger.error).not.toHaveBeenCalled();
+  });
 });