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

const tencentcloud = require("tencentcloud-sdk-nodejs");
const PDF_MIME_TYPE = "application/pdf";

function normalizeDate(value) {
  if (!value || typeof value !== "string") {
    return null;
  }

  const compact = value.trim();
  if (!compact) {
    return null;
  }

  const replaced = compact.replace(/年|\//g, "-").replace(/月/g, "-").replace(/日/g, "");
  const matched = replaced.match(/^(\d{4})-(\d{1,2})-(\d{1,2})$/);
  if (!matched) {
    return null;
  }

  const [, year, month, day] = matched;
  return `${year}-${month.padStart(2, "0")}-${day.padStart(2, "0")}`;
}

function toNumberString(value) {
  if (value == null) {
    return null;
  }

  if (typeof value === "number" && Number.isFinite(value)) {
    return value.toFixed(2);
  }

  if (typeof value !== "string") {
    return null;
  }

  const stripped = value.replace(/[,￥¥\s]/g, "").trim();
  if (!stripped) {
    return null;
  }

  const num = Number(stripped);
  if (!Number.isFinite(num)) {
    return null;
  }

  return num.toFixed(2);
}

function addNumberStrings(...values) {
  const normalized = values.map((value) => toNumberString(value));
  if (normalized.some((value) => value == null)) {
    return null;
  }

  const total = normalized.reduce((sum, value) => sum + Number(value), 0);
  return total.toFixed(2);
}

function subtractNumberStrings(minuend, subtrahend) {
  const normalizedMinuend = toNumberString(minuend);
  const normalizedSubtrahend = toNumberString(subtrahend);
  if (normalizedMinuend == null || normalizedSubtrahend == null) {
    return null;
  }

  return (Number(normalizedMinuend) - Number(normalizedSubtrahend)).toFixed(2);
}

function normalizeIdentifier(value) {
  if (typeof value !== "string") {
    return null;
  }

  const normalized = value.replace(/\s+/g, "").trim();
  return normalized || null;
}

function normalizeString(value) {
  if (typeof value !== "string") {
    return null;
  }

  const normalized = value.replace(/\s+/g, " ").trim();
  return normalized || null;
}

function normalizeInvoiceInfoMap(result) {
  if (!Array.isArray(result?.VatInvoiceInfos)) {
    return null;
  }

  return result.VatInvoiceInfos.reduce((acc, item) => {
    if (typeof item?.Name !== "string") {
      return acc;
    }

    acc[item.Name.trim()] = item?.Value;
    return acc;
  }, {});
}

function resolveTransportMode(sourceMimeType) {
  return sourceMimeType === PDF_MIME_TYPE ? "pdf_native" : "image_native";
}

function wrapTencentError(error, transportMode) {
  const code = typeof error?.code === "string" ? error.code : "ocr_failed";
  const message = error?.message ?? "ocr_failed";
  const wrapped = new Error(message);
  wrapped.code = code;
  wrapped.transportMode = transportMode;
  wrapped.cause = error;
  return wrapped;
}

function createTencentOcrClient(config) {
  if (!config.tencentSecretId || !config.tencentSecretKey) {
    throw new Error("Tencent OCR credentials are missing");
  }

  const OcrClient = tencentcloud.ocr.v20181119.Client;
  return new OcrClient({
    credential: {
      secretId: config.tencentSecretId,
      secretKey: config.tencentSecretKey,
    },
    region: config.tencentOcrRegion,
    profile: {
      httpProfile: {
        timeout: config.ocrTimeoutMs,
      },
    },
  });
}

function normalizeVatInvoiceResult(result) {
  const infoMap = normalizeInvoiceInfoMap(result);
  const invoiceCodeFromInfo =
    normalizeIdentifier(infoMap?.["发票代码"]) ?? normalizeIdentifier(infoMap?.["发票号码"]);
  const invoiceNumberFromInfo =
    normalizeIdentifier(infoMap?.["发票号码"]) ?? normalizeIdentifier(infoMap?.["发票代码"]);
  const invoiceDateFromInfo = normalizeDate(infoMap?.["开票日期"]);
  const amountFromInfo = toNumberString(infoMap?.["合计金额"] ?? infoMap?.["小计金额"]);
  const taxAmountFromInfo = toNumberString(infoMap?.["合计税额"] ?? infoMap?.["小计税额"]);
  const totalAmountFromInfo = toNumberString(infoMap?.["价税合计(小写)"]);
  const sellerNameFromInfo = normalizeString(infoMap?.["销售方名称"]);
  const buyerNameFromInfo = normalizeString(infoMap?.["购买方名称"]);
  const amount = toNumberString(result?.AmountWithoutTax);
  const taxAmount = toNumberString(result?.TaxAmount);
  const totalAmountFromSource = toNumberString(result?.TotalAmount ?? result?.AmountInFiguers);
  const resolvedAmount = amount ?? amountFromInfo;
  const resolvedTaxAmount = taxAmount ?? taxAmountFromInfo;
  const resolvedTotalAmountFromSource = totalAmountFromSource ?? totalAmountFromInfo;
  const derivedAmount =
    resolvedAmount ?? subtractNumberStrings(resolvedTotalAmountFromSource, resolvedTaxAmount);
  const derivedTotalAmount =
    resolvedTotalAmountFromSource ?? addNumberStrings(derivedAmount, resolvedTaxAmount);

  return {
    invoiceCode: normalizeIdentifier(result?.InvoiceCode) ?? invoiceCodeFromInfo,
    invoiceNumber: normalizeIdentifier(result?.InvoiceNum) ?? invoiceNumberFromInfo,
    invoiceDate: normalizeDate(result?.InvoiceDate) ?? invoiceDateFromInfo,
    amount: derivedAmount,
    taxAmount: resolvedTaxAmount,
    totalAmount: derivedTotalAmount,
    sellerName: normalizeString(result?.SellerName) ?? sellerNameFromInfo,
    buyerName: normalizeString(result?.BuyerName) ?? buyerNameFromInfo,
    raw: result ?? {},
  };
}

async function runTencentVatOcr(config, { imageBase64, sourceMimeType }) {
  const client = createTencentOcrClient(config);
  const transportMode = resolveTransportMode(sourceMimeType);

  try {
    const request = {
      ImageBase64: imageBase64,
    };

    if (transportMode === "pdf_native") {
      request.IsPdf = true;
      request.PdfPageNumber = 1;
    }

    const result = await client.VatInvoiceOCR(request);
    const normalized = normalizeVatInvoiceResult(result);

    return {
      ...normalized,
      transportMode,
      raw: {
        ...(normalized.raw ?? {}),
        transportMode,
      },
    };
  } catch (error) {
    throw wrapTencentError(error, transportMode);
  }
}

module.exports = {
  normalizeVatInvoiceResult,
  runTencentVatOcr,
};