'commit'

src/main/java/com/dsideal/base/Test/MyXWPFSDT.java

@@ -0,0 +1,29 @@
+package com.dsideal.base.Test;
+
+import org.apache.poi.xwpf.usermodel.*;
+import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTSdtBlock;
+import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTSdtRun;
+
+public class MyXWPFSDT extends XWPFAbstractSDT implements IBodyElement, IRunBody, ISDTContents, IRunElement {
+
+    private final ISDTContent content;
+    private CTSdtBlock block;
+
+    public MyXWPFSDT(CTSdtRun sdtRun, IBody part) {
+        super(sdtRun.getSdtPr(), part);
+        this.content = new XWPFSDTContent(sdtRun.getSdtContent(), part, this);
+    }
+
+    public MyXWPFSDT(CTSdtBlock block, IBody part) {
+        super(block.getSdtPr(), part);
+        this.content = new XWPFSDTContent(block.getSdtContent(), part, this);
+        this.block = block;
+    }
+    public ISDTContent getContent() {
+        return this.content;
+    }
+    public CTSdtBlock getBlock(){
+        return this.block;
+    }
+
+}

src/main/java/com/dsideal/base/Test/ReadWordDirectory.java

@@ -0,0 +1,33 @@
+package com.dsideal.base.Test;
+
+import org.apache.poi.xwpf.usermodel.XWPFDocument;
+import org.apache.poi.xwpf.usermodel.XWPFParagraph;
+import java.io.FileInputStream;
+import java.io.InputStream;
+import java.util.List;
+
+public class ReadWordDirectory {
+    public static void main(String[] args) {
+        try {
+            String filePath = "c:/双柏县人口变化及其对教育的影响.docx";
+            InputStream is = new FileInputStream(filePath);
+            XWPFDocument document = new XWPFDocument(is);
+            
+            // 获取文档中的所有段落
+            List<XWPFParagraph> paragraphs = document.getParagraphs();
+            for (XWPFParagraph paragraph : paragraphs) {
+                // 检查段落样式是否为标题样式，根据需要调整样式级别
+                if (paragraph.getStyle() != null && paragraph.getStyle().startsWith("Heading")) {
+                    // 输出标题文本
+                    System.out.println(paragraph.getText());
+                }
+            }
+            
+            // 关闭文档和输入流
+            document.close();
+            is.close();
+        } catch (Exception e) {
+            e.printStackTrace();
+        }
+    }
+}

src/main/java/com/dsideal/base/Test/ReadWordTOC.java

@@ -0,0 +1,86 @@
+package com.dsideal.base.Test;
+
+import cn.hutool.core.io.FileUtil;
+import org.apache.commons.io.FileUtils;
+import org.dom4j.Document;
+import org.dom4j.DocumentException;
+import org.dom4j.Element;
+import org.dom4j.io.SAXReader;
+
+import java.io.*;
+import java.util.List;
+import java.util.zip.ZipEntry;
+import java.util.zip.ZipInputStream;
+
+import static com.dsideal.base.Tools.FillData.DataEaseKit.DsKit.DocxUnzipDirectory;
+
+public class ReadWordTOC {
+    public static void main(String[] args) throws IOException, DocumentException {
+        String wordPath = "c:/双柏县人口变化及其对教育的影响.docx";
+        //解压缩
+        if (new File(DocxUnzipDirectory).exists()) {
+            FileUtils.deleteDirectory(new File(DocxUnzipDirectory));
+        }
+        File file = new File(wordPath);//取得word文件
+        FileInputStream inputStream = new FileInputStream(file);
+        ZipInputStream zipInputStream = new ZipInputStream(inputStream);
+        ZipEntry entry;
+        byte[] ch = new byte[256];
+        while ((entry = zipInputStream.getNextEntry()) != null) {
+            File zFile = new File(DocxUnzipDirectory + entry.getName());
+            if (entry.isDirectory()) {
+                if (!zFile.exists()) {
+                    zFile.mkdirs();
+                }
+                zipInputStream.closeEntry();
+            } else {
+                File fpath = new File(zFile.getParent());
+                if (!fpath.exists()) {
+                    fpath.mkdirs();
+                }
+                FileOutputStream outputStream = new FileOutputStream(zFile);
+                int i;
+                while ((i = zipInputStream.read(ch)) != -1) {
+                    outputStream.write(ch, 0, i);
+                }
+                zipInputStream.closeEntry();
+                outputStream.close();
+            }
+        }
+        inputStream.close();
+
+        //读入XML
+        String xmlPath = DocxUnzipDirectory + "word\\document.xml";
+        ///w:document/w:body/w:p/w:r/w:t
+        //System.out.println(FileUtil.readUtf8String(xmlPath).contains("加强"));
+
+        SAXReader reader = new SAXReader();        // 创建 SAXReader 对象，读取 XML 文件
+        Document document = reader.read(new File(xmlPath));
+        Element root = document.getRootElement();// 获取根元素
+        List<Element> children = root.element("body").elements("p");//工作区
+
+        for (Element child : children) {
+            if (child.getName().equals("p")) {
+                List<Element> pChildren = child.elements();
+                boolean isBookmark = false;
+                String content = "";
+                for (Element pChild : pChildren) {
+                    if (pChild.getName().equals("bookmarkStart")) {
+                        isBookmark = true;
+                    }
+                    if (isBookmark && !pChild.getName().equals("bookmarkStart") && !pChild.getName().equals("bookmarkEnd")) {
+                        if (pChild.getName().equals("r")) {
+                            for (Element t : pChild.elements("t")) {
+                                content = content + t.getText();
+                            }
+                        }
+                    }
+                    if (pChild.getName().equals("bookmarkEnd")) {
+                        isBookmark = false;
+                        System.out.println(content);
+                    }
+                }
+            }
+        }
+    }
+}