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

server/src/jobs/ocrJob.js

@@ -1,6 +1,11 @@
 const cron = require("node-cron");
 
-const { buildMissingRequiredOcrError, runOcrForInvoice } = require("../services/ocr");
+const {
+  buildMissingRequiredOcrError,
+  runOcrForInvoice,
+  sanitizeOcrResultForPersistence,
+  shouldDeduplicateByInvoiceNumberOnly,
+} = require("../services/ocr");
 const { publishInvoiceUpdated } = require("../services/events");
 const { resolveInvoiceDedupBlocker } = require("../services/invoiceGovernance");
 const { readFileBuffer } = require("../services/storage");
@@ -117,18 +122,29 @@ async function getOrCreateOcrResult(prisma, config, claimedInvoice, imageBase64)
   });
 
   if (cached) {
+    const normalized = sanitizeOcrResultForPersistence(ocrProvider, cached.result_json);
+    if (ocrProvider === "tencent") {
+      await prisma.ocrResult.update({
+        where: { id: cached.id },
+        data: { result_json: normalized },
+      });
+    }
+
     return {
       ocrResultId: cached.id,
-      normalized: cached.result_json,
+      normalized,
     };
   }
 
-  const normalized = await runOcrForInvoice({
-    config,
-    ocrType: claimedInvoice.ocr_type,
-    imageBase64,
-    sourceMimeType: claimedInvoice.mime_type,
-  });
+  const normalized = sanitizeOcrResultForPersistence(
+    ocrProvider,
+    await runOcrForInvoice({
+      config,
+      ocrType: claimedInvoice.ocr_type,
+      imageBase64,
+      sourceMimeType: claimedInvoice.mime_type,
+    }),
+  );
 
   try {
     const created = await prisma.ocrResult.create({
@@ -164,9 +180,17 @@ async function getOrCreateOcrResult(prisma, config, claimedInvoice, imageBase64)
       throw error;
     }
 
+    const racedNormalized = sanitizeOcrResultForPersistence(ocrProvider, raced.result_json);
+    if (ocrProvider === "tencent") {
+      await prisma.ocrResult.update({
+        where: { id: raced.id },
+        data: { result_json: racedNormalized },
+      });
+    }
+
     return {
       ocrResultId: raced.id,
-      normalized: raced.result_json,
+      normalized: racedNormalized,
     };
   }
 }
@@ -246,10 +270,10 @@ async function markInvoiceAsQualityFailed(prisma, config, invoiceId, normalized,
   });
 }
 
-async function markInvoiceAsFailed(prisma, claimedInvoice, errorMessage, config) {
+async function markInvoiceAsFailed(prisma, claimedInvoice, errorMessage, config, { terminal = false } = {}) {
   const now = new Date();
   const nextAttempts = Number(claimedInvoice.ocr_attempts || 0) + 1;
-  const isTerminal = nextAttempts >= config.ocrMaxAttempts;
+  const isTerminal = terminal || nextAttempts >= config.ocrMaxAttempts;
   const nextStatus = isTerminal ? "ocr_failed" : "pending_ocr";
 
   await prisma.invoicePool.update({
@@ -313,6 +337,7 @@ async function processClaimedInvoice(prisma, config, claimedInvoice, workerId, l
         fileSha256: claimedInvoice.file_sha256,
         invoiceCode: normalized.invoiceCode,
         invoiceNumber: normalized.invoiceNumber,
+        deduplicateByInvoiceNumberOnly: shouldDeduplicateByInvoiceNumberOnly(normalized),
         ownerEmployeeId: claimedInvoice.owner_employee_id,
       },
     );
@@ -336,7 +361,9 @@ async function processClaimedInvoice(prisma, config, claimedInvoice, workerId, l
     return { outcome: "available", status: "available" };
   } catch (error) {
     const message = trimErrorMessage(error);
-    const status = await markInvoiceAsFailed(prisma, claimedInvoice, message, config);
+    const status = await markInvoiceAsFailed(prisma, claimedInvoice, message, config, {
+      terminal: error?.terminal === true,
+    });
     logger.error(
       {
         err: error,