R77-A1: 修复腾讯OCR的PDF识别链路

server/src/services/ocr/tencent.js

@@ -1,4 +1,5 @@
 const tencentcloud = require("tencentcloud-sdk-nodejs");
+const PDF_MIME_TYPE = "application/pdf";
 
 function normalizeDate(value) {
   if (!value || typeof value !== "string") {
@@ -33,7 +34,7 @@ function toNumberString(value) {
     return null;
   }
 
-  const stripped = value.replace(/[,￥\s]/g, "").trim();
+  const stripped = value.replace(/[,￥¥\s]/g, "").trim();
   if (!stripped) {
     return null;
   }
@@ -84,6 +85,35 @@ function normalizeString(value) {
   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");
@@ -105,32 +135,69 @@ function createTencentOcrClient(config) {
 }
 
 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 derivedAmount = amount ?? subtractNumberStrings(totalAmountFromSource, taxAmount);
-  const derivedTotalAmount = totalAmountFromSource ?? addNumberStrings(derivedAmount, taxAmount);
+  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),
-    invoiceNumber: normalizeIdentifier(result?.InvoiceNum),
-    invoiceDate: normalizeDate(result?.InvoiceDate),
+    invoiceCode: normalizeIdentifier(result?.InvoiceCode) ?? invoiceCodeFromInfo,
+    invoiceNumber: normalizeIdentifier(result?.InvoiceNum) ?? invoiceNumberFromInfo,
+    invoiceDate: normalizeDate(result?.InvoiceDate) ?? invoiceDateFromInfo,
     amount: derivedAmount,
-    taxAmount,
+    taxAmount: resolvedTaxAmount,
     totalAmount: derivedTotalAmount,
-    sellerName: normalizeString(result?.SellerName),
-    buyerName: normalizeString(result?.BuyerName),
+    sellerName: normalizeString(result?.SellerName) ?? sellerNameFromInfo,
+    buyerName: normalizeString(result?.BuyerName) ?? buyerNameFromInfo,
     raw: result ?? {},
   };
 }
 
-async function runTencentVatOcr(config, imageBase64) {
+async function runTencentVatOcr(config, { imageBase64, sourceMimeType }) {
   const client = createTencentOcrClient(config);
-  const result = await client.VatInvoiceOCR({
-    ImageBase64: imageBase64,
-  });
+  const transportMode = resolveTransportMode(sourceMimeType);
 
-  return normalizeVatInvoiceResult(result);
+  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 = {