相关性代码调整

src/common/js/commonJS.js

@@ -6,7 +6,7 @@ import mammoth from "mammoth";
 import { MathfieldElement } from 'mathlive';
 import 'mathlive/dist/mathlive-static.css';
 import 'mathlive/dist/mathlive-fonts.css';
-import { importWordDocumentWithMath as parseWordDocumentWithMath, parseHtmlToLatex as convertHtmlToLatex } from '@/utils/wordMathImport';
+import { importWordDocumentWithMath as parseWordDocumentWithMath, parseHtmlToLatex as convertHtmlToLatex, postProcessImportedWordHtml, parseImportedHtmlToContentRows, mergeAdjacentBlueTags, normalizeSpacesAroundBlueTags } from '@/utils/wordMathImport';
 import api from '../../api/index.js';
 import Common from '@/components/common/common'
 import Tiff from 'tiff.js';
@@ -1518,6 +1518,9 @@ str = str.replace(regex, function (match, content, offset, fullString) {
                 if (type == 'table' && tag == 'img' && (attrName === "src" || attrName === "width" || attrName === "height")) {
                     return attrMatch;
                 }
+                if (tag === 'img' && (attrName === 'src' || attrName === 'width' || attrName === 'height' || attrName === 'alt')) {
+                    return attrMatch;
+                }
                 return '';
             });
 
@@ -1527,7 +1530,7 @@ str = str.replace(regex, function (match, content, offset, fullString) {
         if (type == 'table') {
             inputHtml = inputHtml.replace(/<(?!\/?(strong|em|sub|sup|b|i|blue|wmath|img|myfigure|mytable|myh3))[^>]+>/g, ''); // 删除不需要的标签
         } else {
-            inputHtml = inputHtml.replace(/<(?!\/?(strong|em|sub|sup|b|i|blue|wmath|myfigure|mytable|myh3))[^>]+>/g, ''); // 删除不需要的标签
+            inputHtml = inputHtml.replace(/<(?!\/?(strong|em|sub|sup|b|i|blue|wmath|myfigure|mytable|myh3|img))[^>]+>/g, ''); // 删除不需要的标签
         }
 
 
@@ -1543,8 +1546,8 @@ str = str.replace(regex, function (match, content, offset, fullString) {
 
     },
 
-    importWordDocumentWithMath(file) {
-        return parseWordDocumentWithMath(file);
+    importWordDocumentWithMath(file, options) {
+        return parseWordDocumentWithMath(file, options);
     },
 
     parseHtmlToLatex(html) {
@@ -1552,42 +1555,35 @@ str = str.replace(regex, function (match, content, offset, fullString) {
     },
 
     cleanAndParseWordContent(content) {
-        // 1️⃣ 解析成 <p> 段落数组
-        let tempDiv = document.createElement('div');
-        tempDiv.innerHTML = content; // 解析 HTML 内容
-        let paragraphs = tempDiv.querySelectorAll("p"); // 选取所有 <p> 作为数据项
+        const rows = parseImportedHtmlToContentRows(content);
+        const parsedData = [];
 
-        // 2️⃣ 将 <p> 内容转换为数组，并处理内容
-        let parsedData = Array.from(paragraphs).map(p => {
-            let text = p.innerHTML.trim(); // 获取内容，去除两端空格
-            text = replaceNegativeSign(text);
+        rows.forEach((raw) => {
+            const rawStr = String(raw || '');
+            if (rawStr && (/wordTableHtml/i.test(rawStr) || /<table[\s>]/i.test(rawStr))) {
+                parsedData.push(/wordTableHtml/i.test(rawStr) ? rawStr : `<div class="thumbnailTableBox wordTableHtml table_Box">${rawStr}</div>`);
+                return;
+            }
+            if (rawStr === '') {
+                parsedData.push('');
+                return;
+            }
 
-            text = this.transformHtmlString(text)
-            // 3️⃣ **正确移除 <o:p>（Word 复制的无效标签）**
-            text = text.replace(/<\/?o:p[^>]*>/g, "");
-
-            // 4️⃣ **移除所有 style="..."**
-            text = text.replace(/\s*style="[^"]*"/gi, "");
-
-            // 5️⃣ **修正标签替换**
-            text = text.replace(/<strong>/gi, "<b>").replace(/<\/strong>/gi, "</b>");
-            text = text.replace(/<em>/gi, "<i>").replace(/<\/em>/gi, "</i>");
-
-            // 6️⃣ **移除空的 span、b、i 标签**
-            text = text.replace(/<span>\s*<\/span>/gi, "");
-            text = text.replace(/<b>\s*<\/b>/gi, "");
-            text = text.replace(/<i>\s*<\/i>/gi, "");
-
-            // 7️⃣ **确保不移除半个标签（修复匹配规则）**
-            text = text.replace(/<[^\/>]+>\s*<\/[^>]+>/gi, match => {
-                return match.trim() === "" ? "" : match;
-            });
-
-            // 8️⃣ **返回最终内容**
-            return text.trim() === "" ? "" : text;
+            let text = replaceNegativeSign(rawStr.trim());
+            text = this.transformHtmlString(text);
+            text = text.replace(/<\/?o:p[^>]*>/g, '');
+            text = text.replace(/\s*style="[^"]*"/gi, '');
+            text = text.replace(/<strong>/gi, '<b>').replace(/<\/strong>/gi, '</b>');
+            text = text.replace(/<em>/gi, '<i>').replace(/<\/em>/gi, '</i>');
+            text = text.replace(/<span>\s*<\/span>/gi, '');
+            text = text.replace(/<b>\s*<\/b>/gi, '');
+            text = text.replace(/<i>\s*<\/i>/gi, '');
+            text = text.replace(/<[^\/>]+>\s*<\/[^>]+>/gi, (match) => (match.trim() === '' ? '' : match));
+            text = mergeAdjacentBlueTags(text);
+            text = normalizeSpacesAroundBlueTags(text);
+            parsedData.push(text.trim() === '' ? '' : text);
         });
 
-
         return parsedData;
     },
 
@@ -2865,12 +2861,12 @@ str = str.replace(regex, function (match, content, offset, fullString) {
                               background: 'rgba(0, 0, 0, 0.45)'
                           })
                         : null;
-                    parseWordDocumentWithMath(file)
+                    parseWordDocumentWithMath(file, { textOnly: true })
                         .then((html) => {
                             if (!html) {
                                 throw new Error('empty content');
                             }
-                            ed.insertContent(html);
+                            ed.setContent(html);
                             const body = ed.getBody();
                             body.querySelectorAll('wmath').forEach((el) => {
                               let latex = (el.getAttribute('data-latex') || '').trim();