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

这个提交包含在:
2026-07-28 22:02:11 +08:00
父节点 b4bd484260
当前提交 ac17092fa0
共修改 19 个文件,包含 1277 行新增和 127 行删除
@@ -1,6 +1,7 @@
const {
INVOICE_UNAVAILABLE_REASONS,
classifyInvoiceConflict,
buildInvoiceDedupFilters,
formatInvoiceOcrFailureMessage,
resolveInvoiceAvailability,
resolveUploadDedupDecision,
@@ -32,6 +33,17 @@ function buildTx(conflicts) {
}
describe("invoiceGovernance dedup", () => {
it("uses invoice number alone only when the caller marks a known no-code subtype", () => {
expect(
buildInvoiceDedupFilters({
invoiceNumber: "251234",
deduplicateByInvoiceNumberOnly: true,
}),
).toEqual([{ invoice_code: null, invoice_number: "251234" }]);
expect(buildInvoiceDedupFilters({ invoiceNumber: "251234" })).toEqual([]);
});
it("ignores manually archived invoices when re-uploading the same file", async () => {
const archivedManual = buildInvoice({
status: "archived",
@@ -122,5 +134,13 @@ describe("invoiceGovernance dedup", () => {
expect(formatInvoiceOcrFailureMessage("mock_ocr_failed")).toBe(
"票据识别失败,请重试或人工补齐关键信息。",
);
expect(formatInvoiceOcrFailureMessage("multiple_invoices_not_supported")).toBe(
"一个 PDF 第一页只能包含一张发票,请拆分后重新上传。",
);
expect(
formatInvoiceOcrFailureMessage(
"[pdf_native][ResourceUnavailable.ResourcePackageRunOut] resource package run out",
),
).toBe("票据识别额度或计费状态暂不可用,请联系管理员。");
});
});
+144 -3
查看文件
@@ -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();
});
});
@@ -43,6 +43,7 @@ async function buildApp({
invoiceConflicts = [],
statusRows = [],
permissionCodes = ["invoice.upload"],
maxUploadSizeBytes = 5 * 1024 * 1024,
} = {}) {
const tempDir = await fs.mkdtemp(path.join(os.tmpdir(), "hyb-oa-r71-invoice-upload-"));
const invoicePoolCreate = vi.fn(async ({ data }) => ({
@@ -74,7 +75,7 @@ async function buildApp({
app.decorate("config", {
appTimezone: "Asia/Shanghai",
storageDir: tempDir,
maxUploadSizeBytes: 5 * 1024 * 1024,
maxUploadSizeBytes,
invoiceArchiveUnusedDays: 30,
ocrProvider,
jobDriver,
@@ -121,7 +122,7 @@ async function buildApp({
await app.register(multipart, {
attachFieldsToBody: false,
limits: { files: 1, fileSize: 5 * 1024 * 1024 },
limits: { files: 1, fileSize: maxUploadSizeBytes },
});
await app.register(invoicePoolRoutes, { prefix: "/api" });
@@ -271,6 +272,48 @@ describe("invoicePool upload route", () => {
}
});
it("rejects a PDF above the 7 MiB Tencent OCR input boundary before storage", async () => {
const { app, prisma, tempDir } = await buildApp({
maxUploadSizeBytes: 8 * 1024 * 1024,
});
try {
const requestPayload = buildMultipartRequest({
filename: "invoice.pdf",
contentType: "application/pdf",
content: Buffer.alloc(7 * 1024 * 1024 + 1, 0x20),
fields: [["ocr_type", "vat"]],
});
const response = await app.inject({
method: "POST",
url: "/api/invoice-pool/upload",
headers: {
authorization: "Bearer test",
...requestPayload.headers,
},
payload: requestPayload.payload,
});
expect(response.statusCode).toBe(400);
expect(response.json().error).toEqual(
expect.objectContaining({
code: "VALID_001",
message: "PDF 发票不能超过 7 MiB",
details: {
file: "ocr_pdf_too_large",
maxBytes: 7 * 1024 * 1024,
},
}),
);
expect(prisma.invoicePool.create).not.toHaveBeenCalled();
expect(prisma.auditLog.create).not.toHaveBeenCalled();
} finally {
await app.close();
await fs.rm(tempDir, { recursive: true, force: true });
}
});
it("reuses same-owner existing invoice instead of creating a duplicate file record", async () => {
const existingInvoiceId = "22222222-2222-4222-8222-222222222222";
const { app, prisma, tempDir } = await buildApp({
+208 -35
查看文件
@@ -1,51 +1,224 @@
const {
normalizeVatInvoiceResult,
buildGeneralInvoiceRequest,
isTerminalTencentErrorCode,
normalizeGeneralInvoiceResult,
} = require("../../../src/services/ocr/tencent");
const {
buildMissingRequiredOcrError,
getMissingRequiredOcrFields,
sanitizeOcrResultForPersistence,
shouldDeduplicateByInvoiceNumberOnly,
} = require("../../../src/services/ocr");
describe("tencent VAT OCR normalization", () => {
it("normalizes identifiers, date and amounts from Tencent result", () => {
const normalized = normalizeVatInvoiceResult({
InvoiceCode: " 0440 0320 4111 ",
InvoiceNum: " 1234 5678 ",
InvoiceDate: "2026年4月28日",
AmountWithoutTax: "1,488.50",
TaxAmount: "194.50",
AmountInFiguers: "¥1683.00",
SellerName: " 北京悦海堂餐饮管理有限公司 ",
BuyerName: " 华印公司 ",
function buildInvoiceItem(subType, fieldName, payload) {
return {
Code: "OK",
SubType: subType,
SingleInvoiceInfos: {
[fieldName]: payload,
},
};
}
describe("Tencent general invoice OCR", () => {
it("builds a single-page PDF request without cut images or sensitive extras", () => {
expect(buildGeneralInvoiceRequest("cGRm")).toEqual({
ImageBase64: "cGRm",
EnableOther: false,
EnablePdf: true,
PdfPageNumber: 1,
EnableMultiplePage: false,
EnableCutImage: false,
EnableItemPolygon: false,
EnableQRCode: false,
EnableSeal: false,
});
});
it("marks credential, billing and invalid-input provider errors as terminal", () => {
expect(isTerminalTencentErrorCode("AuthFailure.SecretIdNotFound")).toBe(true);
expect(isTerminalTencentErrorCode("FailedOperation.Arrears")).toBe(true);
expect(isTerminalTencentErrorCode("FailedOperation.NoChargePermission")).toBe(true);
expect(isTerminalTencentErrorCode("InvalidParameterValue.InvalidImageContent")).toBe(true);
expect(isTerminalTencentErrorCode("LimitExceeded.TooLargeFileError")).toBe(true);
expect(isTerminalTencentErrorCode("ResourceUnavailable.InArrears")).toBe(true);
expect(isTerminalTencentErrorCode("ResourceUnavailable.ResourcePackageRunOut")).toBe(true);
expect(isTerminalTencentErrorCode("ResourcesSoldOut.ChargeStatusException")).toBe(true);
expect(isTerminalTencentErrorCode("ocr_credentials_missing")).toBe(true);
expect(isTerminalTencentErrorCode("unsupported_source_mime_type")).toBe(true);
expect(isTerminalTencentErrorCode("RequestLimitExceeded")).toBe(false);
expect(isTerminalTencentErrorCode("InternalError")).toBe(false);
});
it("normalizes a VAT electronic common invoice without preserving the provider payload", () => {
const normalized = normalizeGeneralInvoiceResult({
MixedInvoiceItems: [
buildInvoiceItem("VatElectronicCommonInvoice", "VatElectronicCommonInvoice", {
Code: " 0440 0320 4111 ",
Number: " 1234 5678 ",
Date: "2026年4月28日",
PretaxAmount: "1,488.50",
Tax: "194.50",
Total: "¥1683.00",
Seller: " 合成酒店 ",
Buyer: " 合成公司 ",
SellerBankAccount: "SENSITIVE-BANK-ACCOUNT",
}),
],
RequestId: "SENSITIVE-REQUEST-ID",
});
expect(normalized).toEqual({
documentSubtype: "VatElectronicCommonInvoice",
documentCategory: "vat_invoice",
documentCount: 1,
invoiceCode: "044003204111",
invoiceNumber: "12345678",
invoiceDate: "2026-04-28",
amount: "1488.50",
taxAmount: "194.50",
totalAmount: "1683.00",
sellerName: "合成酒店",
buyerName: "合成公司",
});
expect(JSON.stringify(normalized)).not.toContain("SENSITIVE-");
});
it("accepts a full electronic VAT invoice without fabricating an invoice code", () => {
const normalized = normalizeGeneralInvoiceResult({
MixedInvoiceItems: [
buildInvoiceItem("VatElectronicInvoiceFull", "VatElectronicInvoiceFull", {
Number: " 25 12345678901234567890 ",
Date: "2026/04/28",
PretaxAmount: "450.00",
Tax: "27.00",
Total: "477.00",
Seller: "合成住宿服务商",
Buyer: "合成公司",
}),
],
});
expect(normalized).toEqual(
expect.objectContaining({
invoiceCode: "044003204111",
invoiceNumber: "12345678",
invoiceDate: "2026-04-28",
amount: "1488.50",
taxAmount: "194.50",
totalAmount: "1683.00",
sellerName: "北京悦海堂餐饮管理有限公司",
buyerName: "华印公司",
documentCategory: "full_vat_invoice",
invoiceCode: null,
invoiceNumber: "2512345678901234567890",
totalAmount: "477.00",
}),
);
expect(getMissingRequiredOcrFields("vat", normalized)).toEqual([]);
expect(shouldDeduplicateByInvoiceNumberOnly(normalized)).toBe(true);
});
it("derives amount from total and tax when Tencent omits AmountWithoutTax", () => {
const result = normalizeVatInvoiceResult({
InvoiceCode: "044003204111",
InvoiceNum: "12345678",
InvoiceDate: "2026/04/28",
TaxAmount: 194.5,
TotalAmount: 1683,
SellerName: "北京悦海堂餐饮管理有限公司",
BuyerName: "华印公司",
it("normalizes an electronic train ticket without retaining passenger identity fields", () => {
const normalized = normalizeGeneralInvoiceResult({
MixedInvoiceItems: [
buildInvoiceItem("ElectronicTrainTicketFull", "ElectronicTrainTicketFull", {
Number: " 25 98765432109876543210 ",
Date: "2026年7月26日",
Total: "553.00元",
Tax: "4.06",
Buyer: "合成公司",
UserName: "SENSITIVE-PASSENGER-NAME",
UserID: "SENSITIVE-PASSENGER-ID",
ElectronicTicketNum: "SENSITIVE-TICKET-NUMBER",
}),
],
});
expect(result).toEqual(
expect.objectContaining({
amount: "1488.50",
taxAmount: "194.50",
totalAmount: "1683.00",
}),
expect(normalized).toEqual({
documentSubtype: "ElectronicTrainTicketFull",
documentCategory: "electronic_train_ticket",
documentCount: 1,
invoiceCode: null,
invoiceNumber: "2598765432109876543210",
invoiceDate: "2026-07-26",
amount: "548.94",
taxAmount: "4.06",
totalAmount: "553.00",
sellerName: null,
buyerName: "合成公司",
});
expect(buildMissingRequiredOcrError("vat", normalized)).toBeNull();
expect(shouldDeduplicateByInvoiceNumberOnly(normalized)).toBe(true);
expect(JSON.stringify(normalized)).not.toContain("SENSITIVE-");
});
it("returns safe terminal quality results for zero, multiple and unsupported invoices", () => {
expect(normalizeGeneralInvoiceResult({ MixedInvoiceItems: [] })).toEqual(
expect.objectContaining({ qualityError: "invoice_not_detected", documentCount: 0 }),
);
const multiple = normalizeGeneralInvoiceResult({
MixedInvoiceItems: [
buildInvoiceItem("ElectronicTrainTicketFull", "ElectronicTrainTicketFull", {
UserID: "SENSITIVE-FIRST-ID",
}),
buildInvoiceItem("ElectronicTrainTicketFull", "ElectronicTrainTicketFull", {
UserID: "SENSITIVE-SECOND-ID",
}),
],
});
expect(multiple).toEqual(
expect.objectContaining({ qualityError: "multiple_invoices_not_supported", documentCount: 2 }),
);
expect(JSON.stringify(multiple)).not.toContain("SENSITIVE-");
const unsupported = normalizeGeneralInvoiceResult({
MixedInvoiceItems: [buildInvoiceItem("TaxiTicket", "TaxiTicket", { Number: "SENSITIVE-NO" })],
});
expect(buildMissingRequiredOcrError("vat", unsupported)).toBe("unsupported_invoice_subtype");
expect(JSON.stringify(unsupported)).not.toContain("SENSITIVE-");
});
it("requires buyer name for electronic train tickets but not invoice code or seller", () => {
const normalized = {
documentCategory: "electronic_train_ticket",
invoiceCode: null,
invoiceNumber: "251234",
invoiceDate: "2026-07-26",
totalAmount: "100.00",
sellerName: null,
buyerName: null,
};
expect(getMissingRequiredOcrFields("vat", normalized)).toEqual(["buyerName"]);
expect(buildMissingRequiredOcrError("vat", normalized)).toBe(
"missing_required_fields:buyerName",
);
});
it("strips raw and unknown fields from historical Tencent cache payloads", () => {
const sanitized = sanitizeOcrResultForPersistence("tencent", {
invoiceCode: "044001",
invoiceNumber: "12345678",
invoiceDate: "2026-07-26",
totalAmount: "100.00",
sellerName: "合成销售方",
buyerName: "合成购买方",
transportMode: "pdf_native",
raw: {
UserName: "SENSITIVE-CACHED-NAME",
UserID: "SENSITIVE-CACHED-ID",
},
RequestId: "SENSITIVE-CACHED-REQUEST",
});
expect(sanitized).toEqual({
documentSubtype: null,
documentCategory: null,
documentCount: 1,
invoiceCode: "044001",
invoiceNumber: "12345678",
invoiceDate: "2026-07-26",
amount: null,
taxAmount: null,
totalAmount: "100.00",
sellerName: "合成销售方",
buyerName: "合成购买方",
transportMode: "pdf_native",
});
expect(JSON.stringify(sanitized)).not.toContain("SENSITIVE-");
});
});