fix: add pptx encoding try catch (#1393)

labring · May 8, 2024 · 7b75a99 · 7b75a99
1 parent 2e468fc
commit 7b75a99
Show file tree

Hide file tree

Showing 3 changed files with 21 additions and 11 deletions.
diff --git a/packages/service/common/buffer/rawText/schema.ts b/packages/service/common/buffer/rawText/schema.ts
@@ -28,6 +28,6 @@ try {
   console.log(error);
 }
 
-export const MongoRwaTextBuffer: Model<RawTextBufferSchemaType> =
+export const MongoRawTextBuffer: Model<RawTextBufferSchemaType> =
   models[collectionName] || model(collectionName, RawTextBufferSchema);
-MongoRwaTextBuffer.syncIndexes();
+MongoRawTextBuffer.syncIndexes();
diff --git a/packages/service/common/file/gridfs/controller.ts b/packages/service/common/file/gridfs/controller.ts
@@ -6,7 +6,7 @@ import { DatasetFileSchema } from '@fastgpt/global/core/dataset/type';
 import { MongoFileSchema } from './schema';
 import { detectFileEncoding } from '@fastgpt/global/common/file/tools';
 import { CommonErrEnum } from '@fastgpt/global/common/error/code/common';
-import { MongoRwaTextBuffer } from '../../buffer/rawText/schema';
+import { MongoRawTextBuffer } from '../../buffer/rawText/schema';
 import { readFileRawContent } from '../read/utils';
 import { PassThrough } from 'stream';
 
@@ -162,7 +162,7 @@ export const readFileContentFromMongo = async ({
   filename: string;
 }> => {
   // read buffer
-  const fileBuffer = await MongoRwaTextBuffer.findOne({ sourceId: fileId }).lean();
+  const fileBuffer = await MongoRawTextBuffer.findOne({ sourceId: fileId }).lean();
   if (fileBuffer) {
     return {
       rawText: fileBuffer.rawText,
@@ -208,7 +208,7 @@ export const readFileContentFromMongo = async ({
   });
 
   if (rawText.trim()) {
-    MongoRwaTextBuffer.create({
+    MongoRawTextBuffer.create({
       sourceId: fileId,
       rawText,
       metadata: {

diff --git a/packages/service/worker/file/parseOffice.ts b/packages/service/worker/file/parseOffice.ts
@@ -44,9 +44,13 @@ const parsePowerPoint = async ({
   }
 
   // Returning an array of all the xml contents read using fs.readFileSync
-  const xmlContentArray = files.map((file) =>
-    fs.readFileSync(`${decompressPath}/${file.path}`, encoding)
-  );
+  const xmlContentArray = files.map((file) => {
+    try {
+      return fs.readFileSync(`${decompressPath}/${file.path}`, encoding);
+    } catch (err) {
+      return fs.readFileSync(`${decompressPath}/${file.path}`, 'utf-8');
+    }
+  });
 
   let responseArr: string[] = [];
 
@@ -95,9 +99,15 @@ export const parseOffice = async ({
   //   const decompressPath = `${DEFAULTDECOMPRESSSUBLOCATION}/test`;
 
   // write new file
-  fs.writeFileSync(filepath, buffer, {
-    encoding
-  });
+  try {
+    fs.writeFileSync(filepath, buffer, {
+      encoding
+    });
+  } catch (err) {
+    fs.writeFileSync(filepath, buffer, {
+      encoding: 'utf-8'
+    });
+  }
 
   const text = await (async () => {
     try {