update at 2026-02-14 10:58:54

miniapp/utils/sankey.js

@@ -1,11 +1,33 @@
 /**
  * 统一清洗文本，避免空格导致节点重复。
  */
+function tryRecoverUtf8Mojibake(value) {
+  const original = String(value);
+  if (!original) {
+    return original;
+  }
+  if (/[\u4e00-\u9fff]/.test(original)) {
+    return original;
+  }
+  if (!/[ÃÂÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ]/.test(original)) {
+    return original;
+  }
+  try {
+    const recovered = decodeURIComponent(escape(original));
+    if (/[\u4e00-\u9fff]/.test(recovered)) {
+      return recovered;
+    }
+  } catch (error) {
+    // 忽略恢复失败，回退原文
+  }
+  return original;
+}
+
 function normalizeText(value) {
   if (value === null || value === undefined) {
     return '';
   }
-  return String(value).trim();
+  return tryRecoverUtf8Mojibake(value).trim();
 }
 
 /**

src/core/parser.ts

@@ -5,11 +5,33 @@ import type { RawTable } from './types';
 /**
  * 将任意单元格值转换为字符串，统一处理 null/undefined 场景。
  */
+function tryRecoverUtf8Mojibake(value: unknown): string {
+  const original = String(value);
+  if (!original) {
+    return original;
+  }
+  if (/[\u4e00-\u9fff]/.test(original)) {
+    return original;
+  }
+  if (!/[ÃÂÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ]/.test(original)) {
+    return original;
+  }
+  try {
+    const recovered = decodeURIComponent(escape(original));
+    if (/[\u4e00-\u9fff]/.test(recovered)) {
+      return recovered;
+    }
+  } catch {
+    // 忽略恢复失败，回退原文
+  }
+  return original;
+}
+
 function normalizeCell(value: unknown): string {
   if (value === null || value === undefined) {
     return '';
   }
-  return String(value).trim();
+  return tryRecoverUtf8Mojibake(value).trim();
 }
 
 /**

tests/core.spec.ts

@@ -78,6 +78,19 @@ describe('core parser & sankey', () => {
     expect(table.rows).toEqual([['A', 'B', '0']]);
   });
 
+  it('xlsx 中常见中文乱码应尝试自动恢复', () => {
+    const sheet = XLSX.utils.aoa_to_sheet([['人數'], ['张三']]);
+    const workbook = XLSX.utils.book_new();
+    XLSX.utils.book_append_sheet(workbook, sheet, 'S1');
+    const buffer = XLSX.write(workbook, { bookType: 'xlsx', type: 'buffer' });
+    const table = parseXlsxBuffer(
+      buffer.buffer.slice(buffer.byteOffset, buffer.byteOffset + buffer.byteLength)
+    );
+
+    expect(table.headers).toEqual(['人數']);
+    expect(table.rows).toEqual([['张三']]);
+  });
+
   it('源数据非法时，告警包含单元格内容和位置', () => {
     const table = {
       headers: ['source', 'value', 'target'],

tests/miniapp.spec.ts

@@ -74,4 +74,17 @@ describe('miniapp utils sankey', () => {
 
     expect(table.rows).toEqual([['A', 'B', '0']]);
   });
+
+  it('xlsx 中常见中文乱码应尝试自动恢复', () => {
+    const sheet = XLSX.utils.aoa_to_sheet([['人數'], ['张三']]);
+    const workbook = XLSX.utils.book_new();
+    XLSX.utils.book_append_sheet(workbook, sheet, 'S1');
+    const buffer = XLSX.write(workbook, { bookType: 'xlsx', type: 'buffer' });
+    const arrayBuffer = buffer.buffer.slice(buffer.byteOffset, buffer.byteOffset + buffer.byteLength);
+
+    const table = parseXlsxBuffer(arrayBuffer);
+
+    expect(table.headers).toEqual(['人數']);
+    expect(table.rows).toEqual([['张三']]);
+  });
 });