R73-A2 收敛 VAT OCR 归一化与质量门槛

这个提交包含在:
2026-04-28 21:13:21 +08:00
父节点 82fbd39114
当前提交 b7c018922c
共修改 9 个文件,包含 600 行新增和 14 行删除
+127
查看文件
@@ -0,0 +1,127 @@
const fs = require("node:fs/promises");
const os = require("node:os");
const path = require("node:path");
const { runOcrOnce } = require("../../../src/jobs/ocrJob");
function buildClaimedInvoice(overrides = {}) {
return {
id: "11111111-1111-4111-8111-111111111111",
file_sha256: "sha256-1",
ocr_type: "vat",
storage_path: "20260428/invoice.txt",
ocr_attempts: 0,
...overrides,
};
}
function buildPrisma(claimedInvoices) {
return {
$queryRaw: vi.fn(async () => claimedInvoices),
ocrResult: {
findUnique: vi.fn(async () => null),
create: vi.fn(async () => ({ id: "ocr-result-1" })),
},
invoicePool: {
findFirst: vi.fn(async () => null),
update: vi.fn(async () => ({ id: "invoice-1" })),
},
};
}
describe("ocrJob quality gate", () => {
let tempDir = "";
beforeEach(async () => {
vi.clearAllMocks();
tempDir = await fs.mkdtemp(path.join(os.tmpdir(), "hyb-oa-r73-ocr-job-"));
await fs.mkdir(path.join(tempDir, "20260428"), { recursive: true });
});
afterEach(async () => {
await fs.rm(tempDir, { recursive: true, force: true });
});
it("marks invoice available when OCR returns all required VAT fields", async () => {
await fs.writeFile(
path.join(tempDir, "20260428/invoice.txt"),
"MOCK_SUCCESS_R73",
"utf8",
);
const prisma = buildPrisma([buildClaimedInvoice()]);
const logger = {
warn: vi.fn(),
error: vi.fn(),
};
const result = await runOcrOnce(
prisma,
{
storageDir: tempDir,
ocrBatchSize: 1,
ocrLockTtlSeconds: 300,
ocrMaxAttempts: 3,
ocrProvider: "mock",
},
logger,
"ocr-test-worker",
);
expect(result).toEqual({ claimed: 1, available: 1, duplicate: 0, failed: 0 });
expect(prisma.invoicePool.update).toHaveBeenCalledWith(
expect.objectContaining({
where: { id: "11111111-1111-4111-8111-111111111111" },
data: expect.objectContaining({
status: "available",
ocr_last_error: null,
}),
}),
);
});
it("marks invoice ocr_failed when required VAT fields are missing", async () => {
await fs.writeFile(
path.join(tempDir, "20260428/invoice.txt"),
"MOCK_OCR_MISSING:invoiceCode,sellerName",
"utf8",
);
const prisma = buildPrisma([buildClaimedInvoice()]);
const logger = {
warn: vi.fn(),
error: vi.fn(),
};
const result = await runOcrOnce(
prisma,
{
storageDir: tempDir,
ocrBatchSize: 1,
ocrLockTtlSeconds: 300,
ocrMaxAttempts: 3,
ocrProvider: "mock",
},
logger,
"ocr-test-worker",
);
expect(result).toEqual({ claimed: 1, available: 0, duplicate: 0, failed: 1 });
expect(prisma.invoicePool.update).toHaveBeenCalledWith(
expect.objectContaining({
where: { id: "11111111-1111-4111-8111-111111111111" },
data: expect.objectContaining({
status: "ocr_failed",
ocr_last_error: "missing_required_fields:invoiceCode,sellerName",
}),
}),
);
expect(logger.warn).toHaveBeenCalledWith(
expect.objectContaining({
invoiceId: "11111111-1111-4111-8111-111111111111",
qualityError: "missing_required_fields:invoiceCode,sellerName",
}),
"OCR invoice marked as failed for missing required fields",
);
});
});