Merge branch 'small-tupu' of http://124.70.32.114:3100/jianzhenyu/Changsha_tupu into hanyuqing

ruoyi-api/pom.xml

@@ -31,6 +31,33 @@
     <dependencies>
         <!-- 通用工具-->
         <dependency>
+            <groupId>net.sf.saxon</groupId>
+            <artifactId>Saxon-HE</artifactId>
+            <version>12.5</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.poi</groupId>
+            <artifactId>poi</artifactId>
+            <version>5.2.5</version>
+        </dependency>
+
+        <!-- Apache POI OOXML (XSSF, XWPF) -->
+        <dependency>
+            <groupId>org.apache.poi</groupId>
+            <artifactId>poi-ooxml</artifactId>
+            <version>5.2.5</version>
+        </dependency>
+
+        <!-- 必须：OOXML Schema 支持（包含 CTOMath 等类） -->
+        <dependency>
+            <groupId>org.apache.poi</groupId>
+            <artifactId>poi-ooxml-full</artifactId>
+            <version>5.2.5</version>
+        </dependency>
+
+
+
+        <dependency>
             <groupId>com.ruoyi</groupId>
             <artifactId>ruoyi-common</artifactId>
         </dependency>

ruoyi-api/src/main/java/com/ruoyi/api/controller/MathMLController.java

@@ -0,0 +1,175 @@
+package com.ruoyi.api.controller;
+
+import org.apache.xmlbeans.XmlCursor;
+import org.apache.poi.openxml4j.opc.OPCPackage;
+import org.apache.poi.xwpf.usermodel.*;
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.parser.Parser;
+import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTP;
+import org.springframework.web.bind.annotation.GetMapping;
+import org.springframework.web.bind.annotation.RequestMapping;
+import org.springframework.web.bind.annotation.RestController;
+import org.apache.poi.ooxml.POIXMLDocumentPart;
+import org.apache.poi.xwpf.usermodel.XWPFPictureData;
+
+import java.util.Base64;
+import java.util.List;
+import java.util.logging.Logger;
+
+@RestController
+@RequestMapping("/api")
+public class MathMLController {
+
+    private static final Logger log = Logger.getLogger(MathMLController.class.getName());
+
+    @GetMapping("/getWordToHtml")
+    public String t1() {
+        String filePath = "C:\\D\\test.docx"; // ✅ 你的文件路径
+        StringBuilder html = new StringBuilder();
+
+        // 添加 MathJax 支持 MathML 渲染
+
+        try (OPCPackage opc = OPCPackage.open(filePath);
+             XWPFDocument doc = new XWPFDocument(opc)) {
+
+            List<XWPFParagraph> paragraphs = doc.getParagraphs();
+            List<XWPFTable> tables = doc.getTables();
+
+            // 处理段落
+            for (XWPFParagraph para : paragraphs) {
+                handleParagraph(para, html);
+            }
+
+            // 处理表格（含公式）
+            for (XWPFTable table : tables) {
+                html.append("<table border='1' style='border-collapse: collapse; margin: 10px 0;'>");
+                for (XWPFTableRow row : table.getRows()) {
+                    html.append("<tr>");
+                    for (XWPFTableCell cell : row.getTableCells()) {
+                        html.append("<td style='padding: 8px;'>");
+                        for (XWPFParagraph cellPara : cell.getParagraphs()) {
+                            handleParagraph(cellPara, html);
+                        }
+                        html.append("</td>");
+                    }
+                    html.append("</tr>");
+                }
+                html.append("</table>");
+            }
+
+        } catch (Exception e) {
+            html.append("<p style='color:red;'>").append(e.getMessage()).append("</p>");
+        }
+        System.out.println(html.toString());
+        return html.toString();
+    }
+    private void handleParagraph(XWPFParagraph para, StringBuilder html) {
+        System.out.println("处理段落: " + para.getText());
+
+        CTP ctp = para.getCTP();
+        XmlCursor cursor = ctp.newCursor();
+        cursor.selectPath("./*");
+
+        StringBuilder paraHtml = new StringBuilder("<p>");
+
+        while (cursor.toNextSelection()) {
+            String nodeXml = cursor.xmlText();
+
+            if (nodeXml.contains("<m:oMath") || nodeXml.contains("<m:oMathPara")) {
+                System.out.println("✅ 发现公式！");
+                String mathml = MathMLConverter.convertOmmlToMathML(nodeXml);
+                paraHtml.append(mathml);
+            } else if (nodeXml.startsWith("<w:r ")) {
+                // 处理文本 run（可能包含文字、图片）
+                processRunXml(nodeXml, para, paraHtml);
+            }
+        }
+        cursor.dispose();
+
+        if (paraHtml.length() > 3) {
+            paraHtml.append("</p>");
+            html.append(paraHtml);
+        }
+    }
+
+    private void processRunXml(String xml, XWPFParagraph para, StringBuilder html) {
+        try {
+            // 使用 Jsoup 解析 XML
+            Document doc = Jsoup.parse(xml, "", Parser.xmlParser());
+            Element wR = doc.child(0);
+
+            // 查找 blip 标签中的 r:embed
+            Element blip = wR.selectFirst("a|blip");
+            String relId = null;
+            if (blip != null) {
+                relId = blip.attr("r:embed");
+            }
+
+            // 如果没找到，尝试从其他标签找 r:embed
+            if ((relId == null || relId.isEmpty())) {
+                for (Element e : wR.select("[r|embed]")) {
+                    relId = e.attr("r:embed");
+                    if (relId != null && !relId.isEmpty()) break;
+                }
+            }
+
+            // 情况1：找到了 relId → 提取图片
+            if (relId != null && !relId.isEmpty()) {
+                POIXMLDocumentPart imagePart = para.getDocument().getRelationById(relId);
+                if (imagePart instanceof XWPFPictureData) {
+                    XWPFPictureData pictureData = (XWPFPictureData) imagePart;
+                    byte[] imageData = pictureData.getData();
+
+                    String ext;
+                    int pictureType = pictureData.getPictureType();
+                    if (pictureType == XWPFDocument.PICTURE_TYPE_JPEG) {
+                        ext = "jpeg";
+                    } else if (pictureType == XWPFDocument.PICTURE_TYPE_PNG) {
+                        ext = "png";
+                    } else if (pictureType == XWPFDocument.PICTURE_TYPE_GIF) {
+                        ext = "gif";
+                    } else if (pictureType == XWPFDocument.PICTURE_TYPE_BMP) {
+                        ext = "bmp";
+                    } else {
+                        ext = "png"; // 默认值
+                    }
+
+                    String base64 = Base64.getEncoder().encodeToString(imageData);
+                    String imgUrl = "data:image/" + ext + ";base64," + base64;
+                    html.append("<img src=\"").append(imgUrl)
+                            .append("\" style=\"max-width:100%;height:auto;vertical-align:middle;\" />");
+                    return;
+                }
+            }
+
+            // 情况2：没有图片，提取文本
+            String text = extractTextFromRunXml(xml);
+            if (text != null && !text.trim().isEmpty()) {
+                html.append(text);
+            }
+
+        } catch (Exception e) {
+            e.printStackTrace();
+            html.append("<span style='color:red;'>[图片解析错误]</span>");
+        }
+    }
+
+    // 辅助方法：从 <w:r> XML 中提取文本
+    private String extractTextFromRunXml(String xml) {
+        try {
+            javax.xml.parsers.DocumentBuilder db = javax.xml.parsers.DocumentBuilderFactory.newInstance().newDocumentBuilder();
+            org.w3c.dom.Document doc = db.parse(new java.io.ByteArrayInputStream(xml.getBytes()));
+            org.w3c.dom.NodeList texts = doc.getElementsByTagName("w:t");
+            StringBuilder sb = new StringBuilder();
+            for (int i = 0; i < texts.getLength(); i++) {
+                sb.append(texts.item(i).getTextContent());
+            }
+            return sb.toString();
+        } catch (Exception e) {
+            e.printStackTrace();
+            return "";
+        }
+    }
+}

ruoyi-api/src/main/java/com/ruoyi/api/controller/MathMLConverter.java

@@ -0,0 +1,100 @@
+package com.ruoyi.api.controller;
+
+import lombok.var;
+import net.sf.saxon.s9api.*;
+
+import javax.xml.transform.*;
+import javax.xml.transform.stream.StreamResult;
+import javax.xml.transform.stream.StreamSource;
+import java.io.InputStream;
+import java.io.StringReader;
+import java.io.StringWriter;
+
+public class MathMLConverter {
+
+    private static final Processor processor = new Processor(false);
+    private static final XsltCompiler xsltCompiler = processor.newXsltCompiler();  // ✅ 正确类型
+
+    // 加载你已有的 OMML2MML.XSL
+    private static final XsltExecutable executable;
+
+    static {
+        try (var xslStream = MathMLConverter.class.getResourceAsStream("/OMML2MML.XSL")) {
+            if (xslStream == null) {
+                throw new RuntimeException("❌ XSLT file '/OMML2MML.XSL' not found in resources!");
+            }
+            executable = xsltCompiler.compile(new StreamSource(xslStream));  // ✅ 使用 xsltCompiler
+        } catch (Exception e) {
+            throw new ExceptionInInitializerError("❌ Failed to load XSLT: " + e.getMessage());
+        }
+    }
+
+    /**
+     * 将 OMML XML 字符串转换为 MathML
+     */
+    public static String convertOmmlToMathML(String omml) {
+        try {
+            // 加载 XSL 文件
+            InputStream xslStream = MathMLConverter.class.getClassLoader()
+                    .getResourceAsStream("OMML2MML.XSL");
+            if (xslStream == null) {
+                throw new RuntimeException("XSL 文件未找到，请检查路径：OMML2MML.XSL");
+            }
+
+            Source xslSource = new StreamSource(xslStream);
+            Transformer transformer = TransformerFactory.newInstance().newTransformer(xslSource);
+
+            // 设置输出属性
+            transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes"); // ❌ 不要 XML 声明
+            transformer.setOutputProperty(OutputKeys.INDENT, "no");
+            transformer.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "0");
+
+            // 输入 OMML
+            Source source = new StreamSource(new StringReader(omml));
+
+            // 输出
+            StringWriter stringWriter = new StringWriter();
+            Result result = new StreamResult(stringWriter);
+            transformer.transform(source, result);
+
+            String mathml = stringWriter.toString().trim();
+
+            // 🔧 清理和修复 MathML
+            mathml = cleanupMathML(mathml);
+
+            return mathml;
+
+        } catch (Exception e) {
+            e.printStackTrace();
+            return "<math xmlns=\"http://www.w3.org/1998/Math/MathML\"><mtext>公式解析错误</mtext></math>";
+        }
+    }
+
+    // 新增：清理 MathML 输出
+    private static String cleanupMathML(String mathml) {
+        if (mathml == null || mathml.isEmpty()) {
+            return "";
+        }
+
+        // 1. 移除 XML 声明（如果还在）
+        mathml = mathml.replaceFirst("(?s)<!\\?xml.*?\\?>\\s*", "");
+
+        // 2. 替换 mml:math -> math，并修复命名空间
+        mathml = mathml.replaceAll("mml:math", "math");
+        mathml = mathml.replaceAll("xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"", "xmlns=\"http://www.w3.org/1998/Math/MathML\"");
+        mathml = mathml.replaceAll("xmlns:m=\"[^\"]*\"", ""); // 移除 m: 命名空间
+
+        // 3. 移除多余的 mml: 前缀
+        mathml = mathml.replaceAll("mml:([a-z])", "$1"); // mml:mi -> mi, mml:mo -> mo 等
+
+        // 4. 确保根元素是 <math xmlns="...">
+        if (mathml.startsWith("<math ") && !mathml.contains("xmlns=\"http://www.w3.org/1998/Math/MathML\"")) {
+            mathml = mathml.replaceFirst("<math ", "<math xmlns=\"http://www.w3.org/1998/Math/MathML\" ");
+        } else if (!mathml.startsWith("<math")) {
+            // 如果根标签不是 math，手动包装
+            mathml = "<math xmlns=\"http://www.w3.org/1998/Math/MathML\">" + mathml + "</math>";
+        }
+
+        return mathml.trim();
+    }
+}