hyb-oa/server/src/services/ocr/index.js

const { runTencentGeneralInvoiceOcr } = require("./tencent");
const { runMockOcr } = require("./mock");

const OCR_PDF_MAX_BYTES = 7 * 1024 * 1024;

const REQUIRED_OCR_FIELDS_BY_TYPE = {
  vat: ["invoiceCode", "invoiceNumber", "invoiceDate", "totalAmount", "sellerName"],
};

const REQUIRED_OCR_FIELDS_BY_DOCUMENT_CATEGORY = {
  vat_invoice: ["invoiceCode", "invoiceNumber", "invoiceDate", "totalAmount", "sellerName"],
  full_vat_invoice: ["invoiceNumber", "invoiceDate", "totalAmount", "sellerName"],
  electronic_train_ticket: ["invoiceNumber", "invoiceDate", "totalAmount", "buyerName"],
};

const NUMBER_ONLY_DEDUP_DOCUMENT_CATEGORIES = new Set([
  "full_vat_invoice",
  "electronic_train_ticket",
]);

const SAFE_DOCUMENT_CATEGORIES = new Set([
  "vat_invoice",
  "full_vat_invoice",
  "electronic_train_ticket",
]);

const SAFE_QUALITY_ERRORS = new Set([
  "invoice_not_detected",
  "multiple_invoices_not_supported",
  "invoice_recognition_failed",
  "unsupported_invoice_subtype",
]);

const SAFE_NORMALIZED_FIELDS = [
  "invoiceCode",
  "invoiceNumber",
  "invoiceDate",
  "amount",
  "taxAmount",
  "totalAmount",
  "sellerName",
  "buyerName",
];

function isOcrEnabledForType(config, ocrType) {
  if (config.ocrProvider === "mock") {
    return ocrType === "vat";
  }

  return config.ocrProvider === "tencent" && ocrType === "vat";
}

function getMissingRequiredOcrFields(ocrType, normalized) {
  const requiredFields =
    REQUIRED_OCR_FIELDS_BY_DOCUMENT_CATEGORY[normalized?.documentCategory] ??
    REQUIRED_OCR_FIELDS_BY_TYPE[ocrType] ??
    [];
  if (!requiredFields.length) {
    return [];
  }

  return requiredFields.filter((field) => {
    const value = normalized?.[field];
    return value == null || value === "";
  });
}

function buildMissingRequiredOcrError(ocrType, normalized) {
  if (typeof normalized?.qualityError === "string" && normalized.qualityError) {
    return normalized.qualityError;
  }

  const missingFields = getMissingRequiredOcrFields(ocrType, normalized);
  if (!missingFields.length) {
    return null;
  }

  return `missing_required_fields:${missingFields.join(",")}`;
}

async function runOcrForInvoice({ config, ocrType, imageBase64, sourceMimeType }) {
  if (config.ocrProvider === "mock") {
    return runMockOcr({ ocrType, imageBase64 });
  }

  if (config.ocrProvider !== "tencent") {
    throw new Error(`Unsupported OCR provider: ${config.ocrProvider}`);
  }

  if (ocrType !== "vat") {
    throw new Error(`Unsupported OCR type: ${ocrType}`);
  }

  return runTencentGeneralInvoiceOcr(config, { imageBase64, sourceMimeType });
}

function shouldDeduplicateByInvoiceNumberOnly(normalized) {
  return Boolean(
    normalized?.invoiceNumber &&
      !normalized?.invoiceCode &&
      NUMBER_ONLY_DEDUP_DOCUMENT_CATEGORIES.has(normalized?.documentCategory),
  );
}

function normalizeSafeString(value, maxLength) {
  if (typeof value !== "string") {
    return null;
  }

  const normalized = value.trim();
  return normalized ? normalized.slice(0, maxLength) : null;
}

function sanitizeOcrResultForPersistence(ocrProvider, normalized) {
  if (ocrProvider !== "tencent") {
    return normalized;
  }

  const safe = {
    documentSubtype: normalizeSafeString(normalized?.documentSubtype, 64),
    documentCategory: SAFE_DOCUMENT_CATEGORIES.has(normalized?.documentCategory)
      ? normalized.documentCategory
      : null,
    documentCount:
      Number.isInteger(normalized?.documentCount) && normalized.documentCount >= 0
        ? Math.min(normalized.documentCount, 100)
        : 1,
  };

  for (const field of SAFE_NORMALIZED_FIELDS) {
    safe[field] = normalizeSafeString(normalized?.[field], field.endsWith("Name") ? 256 : 64);
  }

  if (SAFE_QUALITY_ERRORS.has(normalized?.qualityError)) {
    safe.qualityError = normalized.qualityError;
  }

  if (normalized?.transportMode === "pdf_native") {
    safe.transportMode = "pdf_native";
  }

  return safe;
}

module.exports = {
  OCR_PDF_MAX_BYTES,
  buildMissingRequiredOcrError,
  getMissingRequiredOcrFields,
  isOcrEnabledForType,
  runOcrForInvoice,
  sanitizeOcrResultForPersistence,
  shouldDeduplicateByInvoiceNumberOnly,
};