fix: preserve xlsx merged cells in read file worker (#7083)

packages/global/common/string/textSplitter.ts

@@ -74,12 +74,7 @@ const markdownTableSplit = (props: SplitProps): SplitResponse => {
   }
 
   const header = splitText2Lines[0];
-  const headerSize = header.split('|').length - 2;
-
-  const mdSplitString = `| ${new Array(headerSize > 0 ? headerSize : 1)
-    .fill(0)
-    .map(() => '---')
-    .join(' | ')} |`;
+  const mdSplitString = splitText2Lines[1];
 
   const chunks: string[] = [];
   const defaultChunk = `${header}

packages/service/package.json

@@ -64,7 +64,6 @@
     "next": "catalog:",
     "nextjs-cors": "2.2.1",
     "node-cron": "^3.0.3",
-    "node-xlsx": "^0.24.0",
     "p-limit": "^7.2.0",
     "papaparse": "5.4.1",
     "pg": "^8.10.0",
@@ -76,6 +75,7 @@
     "turndown": "^7.1.2",
     "undici": "^7.18.2",
     "winston": "^3.17.0",
+    "xlsx": "0.18.5",
     "zod": "catalog:"
   },
   "devDependencies": {

packages/service/test/common/file/read/utils.test.ts

@@ -201,6 +201,12 @@ describe('readFileContentByBuffer', () => {
   it('should return formatText when getFormatText is true', async () => {
     const buffer = Buffer.from('content');
 
+    mockReadRawContentFromBuffer.mockResolvedValueOnce({
+      rawText: 'raw-text-with-|',
+      formatText: '| escaped\\|cell |',
+      imageList: []
+    });
+
     const result = await readFileContentByBuffer({
       teamId,
       tmbId,
@@ -210,7 +216,7 @@ describe('readFileContentByBuffer', () => {
       getFormatText: true
     });
 
-    expect(result.rawText).toBeDefined();
+    expect(result.rawText).toBe('| escaped\\|cell |');
   });
 
   it('should return rawText when getFormatText is false', async () => {

packages/service/test/core/dataset/textSplitter.test.ts

@@ -378,3 +378,30 @@ dsgsgfsgs22sddddddd`,
 
   expect(formatChunks(data)).toEqual(formatResult(mock.result));
 });
+
+it('should preserve escaped pipe in markdown table cells when splitting', async () => {
+  const text = `| 项目系数 | 垫付首年考核费 \\| cc | 4.90% |
+| --- | --- | --- |
+| 项目系数 | 投资回报率 \\| abcd | 6.86% |
+| 项目系数 | 当年运营管理成本,cc | 1,500,000.00 |`;
+
+  const data = await rawText2Chunks({
+    rawText: text,
+    chunkTriggerType: ChunkTriggerConfigTypeEnum.forceChunk,
+    chunkTriggerMinSize: 10,
+    maxSize: 10000,
+    chunkSize: 80,
+    backupParse: false
+  });
+
+  expect(data.length).toBeGreaterThan(1);
+
+  for (const chunk of data) {
+    const lines = chunk.q.split('\n');
+    expect(lines[0]).toBe('| 项目系数 | 垫付首年考核费 \\| cc | 4.90% |');
+    expect(lines[1]).toBe('| --- | --- | --- |');
+    expect(lines[1]).not.toBe('| --- | --- | --- | --- |');
+  }
+
+  expect(data.map((chunk) => chunk.q).join('\n')).toContain('投资回报率 \\| abcd');
+});

packages/service/test/worker/readFile/extension/csv.test.ts

+import { describe, expect, it } from 'vitest';
+import { readCsvRawText } from '@fastgpt/service/worker/readFile/extension/csv';
+
+describe('readCsvRawText', () => {
+  it('should keep raw text and remove empty rows and columns from format text', async () => {
+    const rawText = [
+      ',"name|alias",,note,',
+      ',"Alice|A",,"line1\nline2",',
+      ',,,,',
+      ',Bob,,normal,'
+    ].join('\n');
+
+    const result = await readCsvRawText({
+      extension: 'csv',
+      buffer: Buffer.from(rawText, 'utf-8'),
+      encoding: 'utf-8'
+    });
+
+    expect(result.rawText).toBe(rawText);
+    expect(result.formatText).toBe(`| name\\|alias | note |
+| --- | --- |
+| Alice\\|A | line1\\nline2 |
+| Bob | normal |`);
+  });
+});

packages/service/test/worker/readFile/extension/utils.test.ts

+import { describe, expect, it } from 'vitest';
+import {
+  filterEmptyTableData,
+  formatMarkdownTableCell,
+  formatMarkdownTableRow
+} from '@fastgpt/service/worker/readFile/extension/utils';
+
+describe('filterEmptyTableData', () => {
+  it('should remove empty rows and columns', () => {
+    const result = filterEmptyTableData([
+      ['', 'name', '', 'age', ''],
+      ['', 'Alice', '', 30, ''],
+      ['', '', '', '', ''],
+      ['', 'Bob', '', 25, '']
+    ]);
+
+    expect(result).toEqual([
+      ['name', 'age'],
+      ['Alice', 30],
+      ['Bob', 25]
+    ]);
+  });
+
+  it('should return empty data when all rows are empty', () => {
+    const result = filterEmptyTableData([
+      ['', undefined],
+      [null, '  ']
+    ]);
+
+    expect(result).toEqual([]);
+  });
+});
+
+describe('formatMarkdownTableCell', () => {
+  it('should escape markdown table separators and line breaks', () => {
+    expect(formatMarkdownTableCell('name|alias')).toBe('name\\|alias');
+    expect(formatMarkdownTableCell('line1\r\nline2\nline3\rline4')).toBe(
+      'line1\\nline2\\nline3\\nline4'
+    );
+    expect(formatMarkdownTableCell(null)).toBe('');
+  });
+});
+
+describe('formatMarkdownTableRow', () => {
+  it('should format escaped markdown table row', () => {
+    expect(formatMarkdownTableRow(['name|alias', 'line1\nline2'])).toBe(
+      '| name\\|alias | line1\\nline2 |'
+    );
+  });
+});

packages/service/test/worker/readFile/extension/xlsx.test.ts

+import { describe, expect, it } from 'vitest';
+import XLSX from 'xlsx';
+import { readXlsxRawText } from '@fastgpt/service/worker/readFile/extension/xlsx';
+
+describe('readXlsxRawText', () => {
+  it('should skip empty rows when formatting xlsx content', async () => {
+    const worksheet = XLSX.utils.aoa_to_sheet([
+      ['', 'name|alias', '', 'age', 'city', ''],
+      ['', 'Alice|A', '', 30, 'Bei\njing', ''],
+      [],
+      ['', '', '', '', '', ''],
+      [undefined, undefined, undefined],
+      ['', 'Bob', '', 25, 'Shanghai', '']
+    ]);
+    const workbook = XLSX.utils.book_new();
+    XLSX.utils.book_append_sheet(workbook, worksheet, 'Sheet1');
+    const buffer = XLSX.write(workbook, { type: 'buffer', bookType: 'xlsx' });
+
+    const result = await readXlsxRawText({
+      extension: 'xlsx',
+      buffer,
+      encoding: 'utf-8'
+    });
+
+    expect(result.rawText).toBe(
+      ',name|alias,,age,city,\n,Alice|A,,30,Bei\njing,\n,,,,,\n,,,,,\n,,,,,\n,Bob,,25,Shanghai,'
+    );
+    expect(result.formatText).toContain('| name\\|alias | age | city |');
+    expect(result.formatText).toContain('| Alice\\|A | 30 | Bei\\njing |');
+    expect(result.formatText).toContain('| Bob | 25 | Shanghai |');
+    expect(result.formatText).not.toContain('|  |  |  |');
+  });
+
+  it('should fill merged cells before formatting xlsx content', async () => {
+    const worksheet = XLSX.utils.aoa_to_sheet([
+      ['部门', '姓名', '区域', '', ''],
+      ['销售', '张三', '华东', '', ''],
+      ['', '李四', '', '', ''],
+      ['技术', '王五', '华南', '', ''],
+      ['', '', '', '', '']
+    ]);
+
+    worksheet['!merges'] = [
+      { s: { r: 1, c: 0 }, e: { r: 2, c: 0 } },
+      { s: { r: 0, c: 2 }, e: { r: 0, c: 4 } },
+      { s: { r: 1, c: 2 }, e: { r: 2, c: 4 } }
+    ];
+
+    const workbook = XLSX.utils.book_new();
+    XLSX.utils.book_append_sheet(workbook, worksheet, 'Sheet1');
+    const buffer = XLSX.write(workbook, { type: 'buffer', bookType: 'xlsx' });
+
+    const result = await readXlsxRawText({
+      extension: 'xlsx',
+      buffer,
+      encoding: 'utf-8'
+    });
+
+    expect(result.formatText).toContain('| 部门 | 姓名 | 区域 | 区域 | 区域 |');
+    expect(result.formatText).toContain('| 销售 | 张三 | 华东 | 华东 | 华东 |');
+    expect(result.formatText).toContain('| 销售 | 李四 | 华东 | 华东 | 华东 |');
+    expect(result.formatText).toContain('| 技术 | 王五 | 华南 |  |  |');
+  });
+
+  it('should fill merged cells when sheet data starts from a non-A1 range', async () => {
+    const worksheet = XLSX.utils.aoa_to_sheet([
+      [],
+      ['', '部门', '姓名'],
+      ['', '销售', '张三'],
+      ['', '', '李四']
+    ]);
+
+    worksheet['!ref'] = 'B2:C4';
+    worksheet['!merges'] = [{ s: { r: 2, c: 1 }, e: { r: 3, c: 1 } }];
+
+    const workbook = XLSX.utils.book_new();
+    XLSX.utils.book_append_sheet(workbook, worksheet, 'Sheet1');
+    const buffer = XLSX.write(workbook, { type: 'buffer', bookType: 'xlsx' });
+
+    const result = await readXlsxRawText({
+      extension: 'xlsx',
+      buffer,
+      encoding: 'utf-8'
+    });
+
+    expect(result.formatText).toContain('| 部门 | 姓名 |');
+    expect(result.formatText).toContain('| 销售 | 张三 |');
+    expect(result.formatText).toContain('| 销售 | 李四 |');
+  });
+});

packages/service/test/worker/readFile/integration.test.ts

 import { describe, it, expect, beforeAll, afterEach, afterAll, vi } from 'vitest';
 import path from 'path';
 import { existsSync, readFileSync } from 'fs';
+import XLSX from 'xlsx';
 import { JSZip } from '@fastgpt/service/core/ai/skill/package';
 
 const { mockUploadImage2S3Bucket } = vi.hoisted(() => ({
@@ -231,6 +232,26 @@ describeIfEnabled('readFile worker (real spawn integration)', () => {
     expect(result.rawText).toContain('Shanghai');
   });
 
+  it('解析 xlsx 时应转义 Markdown 表格分隔符', async () => {
+    const worksheet = XLSX.utils.aoa_to_sheet([
+      ['name|alias', 'fullwidth｜pipe'],
+      ['Alice|A', '保留｜字符']
+    ]);
+    const workbook = XLSX.utils.book_new();
+    XLSX.utils.book_append_sheet(workbook, worksheet, 'Sheet1');
+    const buffer = XLSX.write(workbook, { type: 'buffer', bookType: 'xlsx' });
+
+    const result = await readRawContentFromBuffer({
+      extension: 'xlsx',
+      encoding: 'utf-8',
+      buffer
+    });
+
+    expect(result.rawText).toContain('name|alias,fullwidth｜pipe');
+    expect(result.formatText).toContain('| name\\|alias | fullwidth｜pipe |');
+    expect(result.formatText).toContain('| Alice\\|A | 保留｜字符 |');
+  });
+
   it('解析带图片 docx 时通过主线程 uploadFile handler 上传图片', async () => {
     mockUploadImage2S3Bucket.mockResolvedValueOnce('dataset/test/docx-parsed/image.png');
 

packages/service/worker/readFile/extension/csv.ts

 import Papa from 'papaparse';
 import { type ReadRawTextByBuffer, type ReadFileResponse } from '../type';
 import { readFileRawText } from './rawText';
+import { filterEmptyTableData, formatMarkdownTableRow } from './utils';
 
 // 加载源文件内容
 export const readCsvRawText = async (params: ReadRawTextByBuffer): Promise<ReadFileResponse> => {
@@ -8,15 +9,19 @@ export const readCsvRawText = async (params: ReadRawTextByBuffer): Promise<ReadF
 
   const csvArr = Papa.parse(rawText).data as string[][];
 
-  const header = csvArr[0];
+  const filteredData = filterEmptyTableData(csvArr);
+  const header = filteredData[0];
+  if (!header) {
+    return {
+      rawText,
+      formatText: ''
+    };
+  }
 
   // format to md table
-  const formatText = `| ${header.join(' | ')} |
+  const formatText = `${formatMarkdownTableRow(header)}
 | ${header.map(() => '---').join(' | ')} |
-${csvArr
-  .slice(1)
-  .map((row) => `| ${row.map((item) => item.replace(/\n/g, '\\n')).join(' | ')} |`)
-  .join('\n')}`;
+${filteredData.slice(1).map(formatMarkdownTableRow).join('\n')}`;
 
   return {
     rawText,

packages/service/worker/readFile/extension/utils.ts

+/**
+ * 清理表格二维数组中的全空行和全空列，保留原始行列顺序。
+ * 这里只判断单元格文本是否有有效内容，不做类型转换或业务格式化。
+ */
+export const filterEmptyTableData = (data: unknown[][]) => {
+  const filteredRows = data.filter((row) => row.some((cell) => String(cell ?? '').trim() !== ''));
+
+  const maxColumnLength = Math.max(0, ...filteredRows.map((row) => row.length));
+  const columnIndexes = Array.from({ length: maxColumnLength }, (_, index) => index).filter(
+    (index) => filteredRows.some((row) => String(row[index] ?? '').trim() !== '')
+  );
+
+  return filteredRows.map((row) => columnIndexes.map((index) => row[index] ?? ''));
+};
+
+/**
+ * 转义 Markdown table 单元格中的结构字符，避免单元格内容破坏表格列结构。
+ */
+export const formatMarkdownTableCell = (cell: unknown) => {
+  return String(cell ?? '')
+    .replace(/\r\n|\r|\n/g, '\\n')
+    .replace(/\|/g, '\\|');
+};
+
+export const formatMarkdownTableRow = (row: unknown[]) => {
+  return `| ${row.map(formatMarkdownTableCell).join(' | ')} |`;
+};

packages/service/worker/readFile/extension/xlsx.ts

 import { CUSTOM_SPLIT_SIGN } from '@fastgpt/global/common/string/textSplitter';
 import { type ReadRawTextByBuffer, type ReadFileResponse } from '../type';
-import xlsx from 'node-xlsx';
-import Papa from 'papaparse';
+import XLSX from 'xlsx';
+import { filterEmptyTableData, formatMarkdownTableRow } from './utils';
 
 export const readXlsxRawText = async ({
   buffer
 }: ReadRawTextByBuffer): Promise<ReadFileResponse> => {
-  const result = xlsx.parse(buffer, {
-    skipHidden: false,
-    defval: ''
+  const workbook = XLSX.read(buffer, {
+    type: 'buffer',
+    cellDates: true
   });
 
+  const result = workbook.SheetNames.map((name) => {
+    const worksheet = workbook.Sheets[name];
+    const data = XLSX.utils.sheet_to_json<unknown[]>(worksheet, {
+      header: 1,
+      defval: '',
+      blankrows: true,
+      raw: false
+    });
+
+    const merges = worksheet['!merges'] ?? [];
+    const sheetRange = worksheet['!ref'] ? XLSX.utils.decode_range(worksheet['!ref']) : undefined;
+    const startRow = sheetRange?.s.r ?? 0;
+    const startColumn = sheetRange?.s.c ?? 0;
+
+    if (merges.length > 0) {
+      // 合并单元格只有左上角存值；!merges 使用 Excel 绝对坐标，
+      // 但 sheet_to_json 生成的二维数组从 !ref 起点开始，所以填充前要扣掉起始偏移。
+      // 必须先补齐合并区域，再做空行空列过滤，否则会丢失用户在 Excel 中表达的结构语义。
+      for (const merge of merges) {
+        const startDataRow = merge.s.r - startRow;
+        const startDataColumn = merge.s.c - startColumn;
+        const endDataRow = merge.e.r - startRow;
+        const endDataColumn = merge.e.c - startColumn;
+
+        const value = data[startDataRow]?.[startDataColumn] ?? '';
+        if (String(value).trim() === '') continue;
+
+        for (let rowIndex = startDataRow; rowIndex <= endDataRow; rowIndex++) {
+          if (rowIndex < 0) continue;
+          data[rowIndex] ??= [];
+
+          for (let columnIndex = startDataColumn; columnIndex <= endDataColumn; columnIndex++) {
+            if (columnIndex < 0) continue;
+            data[rowIndex][columnIndex] = value;
+          }
+        }
+      }
+    }
+
+    return {
+      name,
+      data
+    };
+  });
+
+  const filteredResult = result.map(({ name, data }) => ({
+    name,
+    data: filterEmptyTableData(data)
+  }));
+
   const format2Csv = result.map(({ name, data }) => {
     return {
       title: `#${name}`,
@@ -20,17 +70,14 @@ export const readXlsxRawText = async ({
 
   const rawText = format2Csv.map((item) => item.csvText).join('\n');
 
-  const formatText = result
+  const formatText = filteredResult
     .map(({ data }) => {
       const header = data[0];
       if (!header) return;
 
-      const formatText = `| ${header.join(' | ')} |
+      const formatText = `${formatMarkdownTableRow(header)}
 | ${header.map(() => '---').join(' | ')} |
-${data
-  .slice(1)
-  .map((row) => `| ${row.map((cell) => String(cell).replace(/\n/g, '\\n')).join(' | ')} |`)
-  .join('\n')}`;
+${data.slice(1).map(formatMarkdownTableRow).join('\n')}`;
 
       return formatText;
     })

pnpm-lock.yaml

@@ -602,9 +602,6 @@ importers:
       node-cron:
         specifier: ^3.0.3
         version: 3.0.3
-      node-xlsx:
-        specifier: ^0.24.0
-        version: 0.24.0
       p-limit:
         specifier: ^7.2.0
         version: 7.2.0
@@ -638,6 +635,9 @@ importers:
       winston:
         specifier: ^3.17.0
         version: 3.17.0
+      xlsx:
+        specifier: 0.18.5
+        version: 0.18.5
       zod:
         specifier: 'catalog:'
         version: 4.1.12
@@ -7152,6 +7152,10 @@ packages:
     resolution: {integrity: sha512-4B/qKCfeE/ODUaAUpSwfzazo5x29WD4r3vXiWsB7I2mSDAihwEqKO+g8GELZUQSSAo5e1XTYh3ZVfLyxBc12nA==}
     engines: {node: '>= 10.0.0'}
 
+  adler-32@1.3.1:
+    resolution: {integrity: sha512-ynZ4w/nUUv5rrsR8UUGoe1VC9hZj6V5hU9Qw1HlMDJGEJw5S7TfTErWTjMys6M7vr0YWcPqs3qAr4ss0nDfP+A==}
+    engines: {node: '>=0.8'}
+
   adm-zip@0.5.17:
     resolution: {integrity: sha512-+Ut8d9LLqwEvHHJl1+PIHqoyDxFgVN847JTVM3Izi3xHDWPE4UtzzXysMZQs64DMcrJfBeS/uoEP4AD3HQHnQQ==}
     engines: {node: '>=12.0'}
@@ -7749,6 +7753,10 @@ packages:
   ccount@2.0.1:
     resolution: {integrity: sha512-eyrF0jiFpY+3drT6383f1qhkbGsLSifNAjA61IUjZjmLCWjItY6LB9ft9YhoDgwfmclB2zhu51Lc7+95b8NRAg==}
 
+  cfb@1.2.2:
+    resolution: {integrity: sha512-KfdUZsSOw19/ObEWasvBP/Ac4reZvAGauZhs6S/gqNhXhI7cKwvlH7ulj+dOEYnca4bm4SGo8C1bTAQvnTjgQA==}
+    engines: {node: '>=0.8'}
+
   chai@6.2.2:
     resolution: {integrity: sha512-NUPRluOfOiTKBKvWPtSD4PhFvWCqOi0BGStNWs57X9js7XGTprSmFoz5F0tWhR4WPjNeR9jXqdC7/UpSJTnlRg==}
     engines: {node: '>=18'}
@@ -7907,6 +7915,10 @@ packages:
   codemirror@6.0.2:
     resolution: {integrity: sha512-VhydHotNW5w1UGK0Qj96BwSk/Zqbp9WbnyK2W/eVMv4QyF41INRGpjUhFJY7/uDNuudSc33a/PKr4iDqRduvHw==}
 
+  codepage@1.15.0:
+    resolution: {integrity: sha512-3g6NUTPd/YtuuGrhMnOMRjFc+LJw/bnMp3+0r/Wcz3IXUuCosKRJvMphm5+Q+bvTVGcJJuRvVLuYba+WojaFaA==}
+    engines: {node: '>=0.8'}
+
   collapse-white-space@2.1.0:
     resolution: {integrity: sha512-loKTxY1zCOuG4j9f6EPnuyyYkf58RnhhWTvRoZEokgB+WbdXehfjFviyOVYkqzEWz1Q5kRiZdBYS5SwxbQYwzw==}
 
@@ -9341,6 +9353,10 @@ packages:
     resolution: {integrity: sha512-buRG0fpBtRHSTCOASe6hD258tEubFoRLb4ZNA6NxMVHNw2gOcwHo9wyablzMzOA5z9xA9L1KNjk/Nt6MT9aYow==}
     engines: {node: '>= 0.6'}
 
+  frac@1.1.2:
+    resolution: {integrity: sha512-w/XBfkibaTl3YDqASwfDUqkna4Z2p9cFSr1aHDt0WoMTECnRfBOv2WArlZILlqgWlmdIlALXGpM2AOhEk5W3IA==}
+    engines: {node: '>=0.8'}
+
   fraction.js@5.3.4:
     resolution: {integrity: sha512-1X1NTtiJphryn/uLQz3whtY6jK3fTqoE3ohKs0tT+Ujr1W59oopxmoEh7Lu5p6vBaPbgoM0bzveAW4Qi5RyWDQ==}
 
@@ -11659,11 +11675,6 @@ packages:
   node-releases@2.0.37:
     resolution: {integrity: sha512-1h5gKZCF+pO/o3Iqt5Jp7wc9rH3eJJ0+nh/CIoiRwjRxde/hAHyLPXYN4V3CqKAbiZPSeJFSWHmJsbkicta0Eg==}
 
-  node-xlsx@0.24.0:
-    resolution: {integrity: sha512-1olwK48XK9nXZsyH/FCltvGrQYvXXZuxVitxXXv2GIuRm51aBi1+5KwR4rWM4KeO61sFU+00913WLZTD+AcXEg==}
-    engines: {node: '>=10.0.0'}
-    hasBin: true
-
   nodemailer@7.0.13:
     resolution: {integrity: sha512-PNDFSJdP+KFgdsG3ZzMXCgquO7I6McjY2vlqILjtJd0hy8wEvtugS9xKRF2NWlPNGxvLCXlTNIae4serI7dinw==}
     engines: {node: '>=6.0.0'}
@@ -13350,6 +13361,10 @@ packages:
     resolution: {integrity: sha512-JPopy3jfNmPcUz5Ru6skKhHNRJbsvcEW6Z4SirKkucLS8Jya1Bmf4FVX8giOkLm8xQJ7kK68P6GXoVSTkbedUA==}
     engines: {node: '>= 14.19.3'}
 
+  ssf@0.11.2:
+    resolution: {integrity: sha512-+idbmIXoYET47hH+d7dfm2epdOMUDjqcB4648sTZ+t2JwoyBFL/insLfB/racrDmsKB3diwsDA696pZMieAC5g==}
+    engines: {node: '>=0.8'}
+
   sshpk@1.18.0:
     resolution: {integrity: sha512-2p2KJZTSqQ/I3+HX42EpYOa2l3f8Erv8MWKsy2I9uf4wA7yFIkXRffYdsx86y6z4vHtV8u7g+pPlr8/4ouAxsQ==}
     engines: {node: '>=0.10.0'}
@@ -14591,10 +14606,18 @@ packages:
     resolution: {integrity: sha512-DLiFIXYC5fMPxaRg832S6F5mJYvePtmO5G9v9IgUFPhXm9/GkXarH/TUrBAVzhTCzAj9anE/+GjrgXp/54nOgw==}
     engines: {node: '>= 12.0.0'}
 
+  wmf@1.0.2:
+    resolution: {integrity: sha512-/p9K7bEh0Dj6WbXg4JG0xvLQmIadrner1bi45VMJTfnbVHsc7yIajZyoSoK60/dtVBs12Fm6WkUI5/3WAVsNMw==}
+    engines: {node: '>=0.8'}
+
   word-wrap@1.2.5:
     resolution: {integrity: sha512-BN22B5eaMMI9UMtjrGd5g5eCYPpCPDUy0FJXbYsaT5zYxjFOckS53SQDE3pWkVoWpHXVb3BrYcEN4Twa55B5cA==}
     engines: {node: '>=0.10.0'}
 
+  word@0.3.0:
+    resolution: {integrity: sha512-OELeY0Q61OXpdUfTp+oweA/vtLVg5VDOXh+3he3PNzLGG/y0oylSOC1xRVj0+l4vQ3tj/bB1HVHv1ocXkQceFA==}
+    engines: {node: '>=0.8'}
+
   wrap-ansi@6.2.0:
     resolution: {integrity: sha512-r6lPcBGxZXlIcymEu7InxDMhdW0KDxpLgoFLcguasxCaJ/SOIZwINatK9KY/tf+ZrlywOKU0UDj3ATXUBfxJXA==}
     engines: {node: '>=8'}
@@ -14649,9 +14672,8 @@ packages:
     resolution: {integrity: sha512-GCPAHLvrIH13+c0SuacwvRYj2SxJXQ4kaVTT5xgL3kPrz56XxkF21IGhjSE1+W0aw7gpBWRGXLCPnPby6lSpmQ==}
     engines: {node: '>=12'}
 
-  xlsx@https://cdn.sheetjs.com/xlsx-0.20.2/xlsx-0.20.2.tgz:
-    resolution: {tarball: https://cdn.sheetjs.com/xlsx-0.20.2/xlsx-0.20.2.tgz}
-    version: 0.20.2
+  xlsx@0.18.5:
+    resolution: {integrity: sha512-dmg3LCjBPHZnQp5/F/+nnTa+miPJxUXB6vtk42YjBBKayDNagxGEeIdWApkYPOf3Z3pm3k62Knjzp7lMeTEtFQ==}
     engines: {node: '>=0.8'}
     hasBin: true
 
@@ -21755,6 +21777,8 @@ snapshots:
 
   address@1.2.2: {}
 
+  adler-32@1.3.1: {}
+
   adm-zip@0.5.17: {}
 
   agent-base@6.0.2:
@@ -22454,6 +22478,11 @@ snapshots:
 
   ccount@2.0.1: {}
 
+  cfb@1.2.2:
+    dependencies:
+      adler-32: 1.3.1
+      crc-32: 1.2.2
+
   chai@6.2.2: {}
 
   chalk@1.1.3:
@@ -22629,6 +22658,8 @@ snapshots:
       '@codemirror/state': 6.5.2
       '@codemirror/view': 6.38.6
 
+  codepage@1.15.0: {}
+
   collapse-white-space@2.1.0: {}
 
   color-convert@1.9.3:
@@ -24525,6 +24556,8 @@ snapshots:
 
   forwarded@0.2.0: {}
 
+  frac@1.1.2: {}
+
   fraction.js@5.3.4: {}
 
   framer-motion@9.1.7(react-dom@18.3.1(react@18.3.1))(react@18.3.1):
@@ -27479,10 +27512,6 @@ snapshots:
 
   node-releases@2.0.37: {}
 
-  node-xlsx@0.24.0:
-    dependencies:
-      xlsx: https://cdn.sheetjs.com/xlsx-0.20.2/xlsx-0.20.2.tgz
-
   nodemailer@7.0.13: {}
 
   non-layered-tidy-tree-layout@2.0.2: {}
@@ -29594,6 +29623,10 @@ snapshots:
 
   sse-decoder@1.0.0: {}
 
+  ssf@0.11.2:
+    dependencies:
+      frac: 1.1.2
+
   sshpk@1.18.0:
     dependencies:
       asn1: 0.2.6
@@ -31085,8 +31118,12 @@ snapshots:
       triple-beam: 1.4.1
       winston-transport: 4.9.0
 
+  wmf@1.0.2: {}
+
   word-wrap@1.2.5: {}
 
+  word@0.3.0: {}
+
   wrap-ansi@6.2.0:
     dependencies:
       ansi-styles: 4.3.0
@@ -31136,7 +31173,15 @@ snapshots:
 
   xdg-basedir@5.1.0: {}
 
-  xlsx@https://cdn.sheetjs.com/xlsx-0.20.2/xlsx-0.20.2.tgz: {}
+  xlsx@0.18.5:
+    dependencies:
+      adler-32: 1.3.1
+      cfb: 1.2.2
+      codepage: 1.15.0
+      crc-32: 1.2.2
+      ssf: 0.11.2
+      wmf: 1.0.2
+      word: 0.3.0
 
   xml-crypto@6.1.2:
     dependencies: