update 文档拆分公式

laws-modules/src/main/java/com/jero/modules/split/enums/SplitFilePragraTypeEnum.java

@@ -7,7 +7,10 @@ package com.jero.modules.split.enums;
  */
 public enum SplitFilePragraTypeEnum {
 
-	TEXT("TEXT","文字"),IMG("IMG","图片"),TABLE("TABLE","表格");
+	TEXT("TEXT","文字"),
+	IMG("IMG","图片"),
+	TABLE("TABLE","表格"),
+	MATH("MATH","公式");
 
 	private String value;
 	private String lable;

laws-modules/src/main/java/com/jero/modules/split/service/impl/FileSpiltService.java

@@ -13,12 +13,12 @@ import com.jero.modules.split.enums.SplitFileTypeTypeEnum;
 import com.jero.modules.split.mapper.SarFileSplitMenuEOMapper;
 import com.jero.modules.split.service.IFileSplitItemsEOService;
 import com.jero.modules.split.service.ISarFileSplitItemsValEOService;
-import com.jero.modules.split.util.AsposeUtil;
+import com.jero.modules.split.util.*;
-import com.jero.modules.split.util.FileSplitUtils;
-import com.jero.modules.split.util.ReadWordTable;
 import com.jero.modules.split.vo.TitleNumberVO;
+import lombok.extern.slf4j.Slf4j;
 import org.apache.commons.collections4.CollectionUtils;
 import org.apache.commons.lang3.StringUtils;
+import org.apache.poi.openxml4j.opc.PackagePart;
 import org.apache.poi.openxml4j.util.ZipSecureFile;
 import org.apache.poi.xwpf.usermodel.*;
 import org.apache.shiro.SecurityUtils;
@@ -28,6 +28,9 @@ import org.openxmlformats.schemas.drawingml.x2006.main.CTGraphicalObject;
 import org.openxmlformats.schemas.drawingml.x2006.picture.CTPicture;
 import org.openxmlformats.schemas.drawingml.x2006.wordprocessingDrawing.CTAnchor;
 import org.openxmlformats.schemas.drawingml.x2006.wordprocessingDrawing.CTInline;
+import org.openxmlformats.schemas.officeDocument.x2006.math.CTOMath;
+import org.openxmlformats.schemas.officeDocument.x2006.math.CTOMathArg;
+import org.openxmlformats.schemas.officeDocument.x2006.math.CTOMathPara;
 import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTDrawing;
 import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTLevelText;
 import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTR;
@@ -36,6 +39,9 @@ import org.springframework.beans.factory.annotation.Value;
 import org.springframework.stereotype.Service;
 import org.springframework.transaction.annotation.Propagation;
 import org.springframework.transaction.annotation.Transactional;
+import org.w3c.dom.NamedNodeMap;
+import org.w3c.dom.Node;
+import org.w3c.dom.NodeList;
 
 import java.io.FileInputStream;
 import java.io.IOException;
@@ -52,6 +58,7 @@ import java.util.regex.Pattern;
  * <b>日期：</b> 2022-04-07 <br>
  * <b>版权所有：<b>版权归北京卡达克数据技术中心所有。<br>
  */
+@Slf4j
 @Service
 @Transactional(value = "transactionManager", readOnly = false, propagation = Propagation.REQUIRED, rollbackFor = Throwable.class)
 public class FileSpiltService {
@@ -121,22 +128,22 @@ public class FileSpiltService {
 //            nowStart.add(String.valueOf(sarFileSplitInfoEO.getStartNumber()));
 //        }
 //        获取文件地址
-        String fileId = sarFileSplitInfoEO.getFileId();
+//        String fileId = sarFileSplitInfoEO.getFileId();
-        LambdaQueryWrapper<OSSFile> queryWrapper = new LambdaQueryWrapper();
+//        LambdaQueryWrapper<OSSFile> queryWrapper = new LambdaQueryWrapper();
-        queryWrapper.eq(OSSFile::getId, fileId);
+//        queryWrapper.eq(OSSFile::getId, fileId);
-        queryWrapper.orderByDesc(OSSFile::getCreateTime);
+//        queryWrapper.orderByDesc(OSSFile::getCreateTime);
-        List<OSSFile> ossFileList = iossFileService.list(queryWrapper);
+//        List<OSSFile> ossFileList = iossFileService.list(queryWrapper);
-        if (CollectionUtils.isEmpty(ossFileList)) {
+//        if (CollectionUtils.isEmpty(ossFileList)) {
-            throw new JeroBootException("当前文件未找到，请重新选择！");
+//            throw new JeroBootException("当前文件未找到，请重新选择！");
-        }
+//        }
-        OSSFile ossFile = ossFileList.get(0);
+//        OSSFile ossFile = ossFileList.get(0);
-        String readFilePath = ossFile.getUrl();
+//        String readFilePath = ossFile.getUrl();
-        if (StringUtils.isEmpty(readFilePath) || !MinioUtil.doesObjectExist(readFilePath)) {
+//        if (StringUtils.isEmpty(readFilePath) || !MinioUtil.doesObjectExist(readFilePath)) {
-            throw new JeroBootException("当前文件未找到，请重新选择！");
+//            throw new JeroBootException("当前文件未找到，请重新选择！");
-        }
+//        }
-        try (InputStream is = MinioUtil.download(readFilePath);InputStream is1 = MinioUtil.download(readFilePath)) {
+//        try (InputStream is = MinioUtil.download(readFilePath);InputStream is1 = MinioUtil.download(readFilePath)) {
-        //String readFilePath = "E:\\Data\\Downloads\\wordtest\\GB7258标准修订test - 表格测试 - 副本.docx";
+        String readFilePath = "E:\\Data\\Downloads\\wordtest\\GB7258标准修订test - 表格测试 - 副本.docx";
-        //try (InputStream is = new FileInputStream(readFilePath); InputStream is1 = new FileInputStream(readFilePath)) {//需要将文件路更改为word文档所在路径。
+        try (InputStream is = new FileInputStream(readFilePath); InputStream is1 = new FileInputStream(readFilePath)) {//需要将文件路更改为word文档所在路径。
             ZipSecureFile.setMinInflateRatio(-1.0d);
             XWPFDocument doc = new XWPFDocument(is);
 
@@ -165,6 +172,30 @@ public class FileSpiltService {
                 if (element instanceof XWPFParagraph) {
                     XWPFParagraph p = (XWPFParagraph) element;
                     StringBuilder stringBuilder = new StringBuilder();
+
+                    ParagraphChildOrderManager runOrMaths = new ParagraphChildOrderManager(p);
+                    List<Object> childList = runOrMaths.getChildList();
+
+                    for (Object child : childList) {
+                        //if (child instanceof XWPFRun) {
+                        //    //处理段落中的文本以及图片
+                        //    handleParagraphRun(content, (XWPFRun) child, imageParser);
+                        //} else
+                            if (child instanceof CTOMath) {
+                            // 处理word中存在的公式成mathML格式
+                            handleParagraphOMath(stringBuilder, (CTOMath) child);
+                            if (messageList.size() > 0) {
+                                addItermsConditionsMath(messageList.get(messageList.size() - 1), itemValList, stringBuilder.toString());
+                            }
+                        } else if (child instanceof CTOMathPara) {
+                            //处理word中存在的公式
+                            handleParagraphOMath(stringBuilder, (CTOMathPara) child);
+                            if (messageList.size() > 0) {
+                                addItermsConditionsMath(messageList.get(messageList.size() - 1), itemValList, stringBuilder.toString());
+                            }
+                        }
+                    }
+
                     for (XWPFRun xwrun : p.getRuns()) {
                         VerticalAlign subscript = xwrun.getSubscript();
                         String smalltext = xwrun.getText(0);
@@ -426,7 +457,31 @@ public class FileSpiltService {
         return "";
     }
 
+    /**
+     * 处理公式
+     *
+     * @param content
+     * @param child
+     */
+    private static void handleParagraphOMath(StringBuilder content, CTOMath child) {
+        log.info(">> 开始解析段落中的CTOMath公式");
+        //将word中的omml格式转换成mathML
+        String mathMLFromNode = OmmlUtils.getMathMLFromNode(child.xmlText());
+        content.append(mathMLFromNode);
+    }
 
+    /**
+     * 处理公式(将word中的omML格式的公式转换成mathML格式的工单)
+     *
+     * @param content
+     * @param child
+     */
+    private static void handleParagraphOMath(StringBuilder content, CTOMathPara child) {
+        log.info(">> 开始解析段落中的CTOMathPara公式");
+        //将word中的omml格式转换成mathML
+        String mathMLFromNode = OmmlUtils.getMathMLFromNode(child.xmlText());
+        content.append(mathMLFromNode);
+    }
 
     /**
      * 通过传递过来的编号，得出下次可能出现的编号
@@ -863,6 +918,113 @@ public class FileSpiltService {
         return imageBundleList;
     }
 
+    private List<String> readMathInParagraph(XWPFParagraph paragraph) {
+        //图片索引List
+        List<String> imageBundleList = new ArrayList<String>();
+
+        //段落中所有XWPFRun
+        List<XWPFRun> runList = paragraph.getRuns();
+        StringBuffer text = new StringBuffer();
+        for (XWPFRun run : runList) {
+            Node runNode = run.getCTR().getDomNode();
+            text.append(getText(runNode));
+
+            String math = getMath(run, runNode);
+            text.append(math);
+        }
+        System.out.println("段落内容：".concat(text.toString()));
+        return imageBundleList;
+    }
+
+    /**
+     * 获取字符串
+     *
+     * @param runNode
+     * @return
+     */
+    private String getText(Node runNode) {
+        Node textNode = getChildNode(runNode, "w:t");
+        if (textNode == null) {
+            return "";
+        }
+        return textNode.getFirstChild().getNodeValue();
+    }
+
+    private String getMath(XWPFRun run, Node runNode) {
+        Node objectNode = getChildNode(runNode, "m:oMathPara");
+        if (objectNode == null) {
+            return "";
+        }
+        Node shapeNode = getChildNode(objectNode, "v:shape");
+        if (shapeNode == null) {
+            return "";
+        }
+        Node imageNode = getChildNode(shapeNode, "v:imagedata");
+        if (imageNode == null) {
+            return "";
+        }
+        Node binNode = getChildNode(objectNode, "o:OLEObject");
+        if (binNode == null) {
+            return "";
+        }
+
+        XWPFDocument word = run.getDocument();
+
+        NamedNodeMap shapeAttrs = shapeNode.getAttributes();
+        // 图片在Word中显示的宽高
+        String style = shapeAttrs.getNamedItem("style").getNodeValue();
+        System.out.println("图片宽高：".concat(style));
+
+        System.out.println("--------------");
+
+        NamedNodeMap imageAttrs = imageNode.getAttributes();
+        // 图片在Word中的ID
+        String imageRid = imageAttrs.getNamedItem("r:id").getNodeValue();
+        // 获取图片信息
+        PackagePart imgPart = word.getPartById(imageRid);
+        System.out.println("图片名称".concat(imgPart.getPartName().getName()));
+        try {
+            System.out.println(imgPart.getInputStream());
+        } catch (IOException e) {
+            e.printStackTrace();
+        }
+
+        System.out.println("--------------");
+
+        NamedNodeMap binAttrs = binNode.getAttributes();
+        // 公式二进制文件在Word中的ID
+        String binRid = binAttrs.getNamedItem("r:id").getNodeValue();
+        // 获取二进制文件
+        PackagePart binPart = word.getPartById(binRid);
+        System.out.println("二进制文件名称：".concat(binPart.getPartName().getName()));
+        try {
+            System.out.println(binPart.getInputStream());
+        } catch (IOException e) {
+            e.printStackTrace();
+        }
+        System.out.println("--------------");
+
+        return "{公式#}";
+    }
+
+    private Node getChildNode(Node node, String nodeName) {
+        if (!node.hasChildNodes()) {
+            return null;
+        }
+        NodeList childNodes = node.getChildNodes();
+        for (int i = 0; i < childNodes.getLength(); i++) {
+            Node childNode = childNodes.item(i);
+            if (nodeName.equals(childNode.getNodeName())) {
+                return childNode;
+            }
+            childNode = getChildNode(childNode, nodeName);
+            if (childNode != null) {
+                return childNode;
+            }
+        }
+        return null;
+    }
+
     // 像每个条款中依次插入每一段的内容
     public static void addItermsConditionsText(SarFileSplitItemsEO message, List<SarFileSplitItemsValEO> itemsValList, String p) {
         message.getItemsCondi().add(p);
@@ -870,6 +1032,13 @@ public class FileSpiltService {
         itemsValList.add(getSplitItemsValObject(message.getId(), SplitFilePragraTypeEnum.TEXT.getValue(), p, message.getItemsCondi().size(), null));
     }
 
+    // 像每个条款中依次插入每一段的内容
+    public static void addItermsConditionsMath(SarFileSplitItemsEO message, List<SarFileSplitItemsValEO> itemsValList, String p) {
+        message.getItemsCondi().add(p);
+        message.setItemContent(message.getItemContent() + "<p>" + p + "</p>");
+        itemsValList.add(getSplitItemsValObject(message.getId(), SplitFilePragraTypeEnum.MATH.getValue(), p, message.getItemsCondi().size(), null));
+    }
+
     public static void addItermsConditionsOfTable(SarFileSplitItemsEO message, List<SarFileSplitItemsValEO> itemsValList, XWPFTable table) throws IOException {
         StringBuilder tabaleStringNew = new StringBuilder("");
         //将表格转为html字符串

laws-modules/src/main/java/com/jero/modules/split/util/OmmlUtils.java

@@ -0,0 +1,42 @@
+package com.jero.modules.split.util;
+
+import javax.xml.transform.Source;
+import javax.xml.transform.Transformer;
+import javax.xml.transform.TransformerException;
+import javax.xml.transform.TransformerFactory;
+import javax.xml.transform.stream.StreamResult;
+import javax.xml.transform.stream.StreamSource;
+import java.io.File;
+import java.io.IOException;
+import java.io.StringReader;
+import java.io.StringWriter;
+
+/**
+ * @author liJiaRao
+ * @date 2023-11-09 9:51
+ */
+public class OmmlUtils {
+    /**
+     * 将word文档中公式格式为omML转换为mathMl
+     * @param omML
+     * @return
+     */
+    public static String getMathMLFromNode(String omML) {
+        //通过word中的xsl转成器解析omml公式格式
+        //StreamSource xslSource = new StreamSource(new File("src/main/resources/OMML2MML.XSL"));
+        StringWriter writer = new StringWriter();
+        try {
+            Transformer t = TransformerFactory.newInstance().newTransformer();
+            Source sources = new StreamSource(new StringReader(omML));
+            StreamResult result = new StreamResult(writer);
+            t.transform(sources, result);
+        } catch (TransformerException e) {
+            e.printStackTrace();
+        }
+        String mathML = writer.getBuffer().toString();
+        mathML = mathML.replaceAll("xmlns:m=\"http://schemas.openxmlformats.org/officeDocument/2006/math\"", "");
+        mathML = mathML.replaceAll("xmlns:mml", "xmlns");
+        mathML = mathML.replaceAll("mml:", "");
+        return mathML;
+    }
+}

laws-modules/src/main/java/com/jero/modules/split/util/ParagraphChildOrderManager.java

@@ -0,0 +1,87 @@
+package com.jero.modules.split.util;
+
+import org.apache.poi.xwpf.usermodel.XWPFParagraph;
+import org.apache.poi.xwpf.usermodel.XWPFRun;
+import org.apache.xmlbeans.XmlCursor;
+import org.openxmlformats.schemas.officeDocument.x2006.math.CTOMath;
+import org.openxmlformats.schemas.officeDocument.x2006.math.CTOMathPara;
+
+import java.util.ArrayList;
+import java.util.LinkedList;
+import java.util.List;
+import java.util.Queue;
+
+/**
+ * 可以把公式和XWPFRun按顺序遍历，用到了以CTP开头的底层方式
+ * <p>
+ * XWPFParagraph中主有两个方法可以分别提出XWPFRun和CTOMath，但是不知道位置
+ * ParagraphChildOrderManager这个类是专门解决这个问题的
+ * @author liJiaRao
+ * @date 2023-11-09 9:24
+ */
+public class ParagraphChildOrderManager {
+    public static int TYPE_RUN = 1;
+    public static int TYPE_OMATH = 2;
+
+    List<Integer> typeList = new ArrayList<Integer>();
+    XWPFParagraph p;
+
+    public ParagraphChildOrderManager(XWPFParagraph paragraph) {
+        this.p = paragraph;
+        //using a cursor to go through the paragraph from top to down
+        XmlCursor xmlcursor = paragraph.getCTP().newCursor();
+        while (xmlcursor.hasNextToken()) {
+            XmlCursor.TokenType tokenType = xmlcursor.toNextToken();
+            if (tokenType.isStart()) {
+                if (xmlcursor.getName().getPrefix().equalsIgnoreCase("w") && xmlcursor.getName().getLocalPart().equalsIgnoreCase("r")) {
+                    typeList.add(TYPE_RUN);
+                } else if (xmlcursor.getName().getLocalPart().equalsIgnoreCase("oMath")) {
+                    typeList.add(TYPE_OMATH);
+                }
+            } else if (tokenType.isEnd()) {
+                xmlcursor.push();
+                xmlcursor.toParent();
+                if (xmlcursor.getName().getLocalPart().equalsIgnoreCase("p")) {
+                    break;
+                }
+                xmlcursor.pop();
+            }
+        }
+    }
+
+    public List<Object> getChildList() {
+        List<Object> runsOrMathList = new ArrayList<Object>();
+        List<XWPFRun> runs = p.getRuns();
+        List<CTOMath> oMathList = p.getCTP().getOMathList();
+
+//        Queue<Object> mathQueue = null;
+        if (oMathList != null && oMathList.size() > 0) {
+            Queue<XWPFRun> runsQueue = new LinkedList<XWPFRun>(runs);
+            Queue<CTOMath> mathQueue = new LinkedList<CTOMath>(oMathList);
+
+            for (int i = 0; i < typeList.size(); i++) {
+                Integer type = typeList.get(i);
+                if (type.equals(TYPE_RUN) && runs.size() > 0) {
+
+                    runsOrMathList.add(runsQueue.poll());
+                } else if (type.equals(TYPE_OMATH) && mathQueue.size() > 0) {
+                    runsOrMathList.add(mathQueue.poll());
+                }
+            }
+            return runsOrMathList;
+        } else {
+            List<CTOMathPara> oMathParaList = p.getCTP().getOMathParaList();
+            Queue<XWPFRun> runsQueue = new LinkedList<XWPFRun>(runs);
+            Queue<CTOMathPara> mathQueue = new LinkedList<CTOMathPara>(oMathParaList);
+            for (int i = 0; i < typeList.size(); i++) {
+                Integer type = typeList.get(i);
+                if (type.equals(TYPE_RUN) && runs.size() > 0) {
+                    runsOrMathList.add(runsQueue.poll());
+                } else if (type.equals(TYPE_OMATH) && mathQueue.size() > 0) {
+                    runsOrMathList.add(mathQueue.poll());
+                }
+            }
+            return runsOrMathList;
+        }
+    }
+}