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

package com.dsideal.base.Test;

import cn.hutool.core.io.FileUtil;
import com.jfinal.kit.StrKit;
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.Arrays;
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
        boolean out = false;
        for (Element child : children) {
            if (child.getName().equals("p")) {
//                if (child.element("pPr") == null) continue;
//                if (child.element("pPr").element("rPr") == null) continue;
//                if (child.element("pPr").element("rPr").element("rFonts") == null) continue;
//
//                String font = child.element("pPr").element("rPr").element("rFonts").attribute("ascii").getValue();
//                //子元素需要继续处理
//                if (font.equals("方正仿宋简体")) continue;
//                if (font.equals("华文楷体")) continue;
//
//                if (child.element("pPr").element("rPr").element("sz") != null) {
//                    int fontSize = Integer.parseInt(child.element("pPr").element("rPr").element("sz").attribute("val").getValue());
//                    if (fontSize != 32) continue;
//                }

                List<Element> pChildren = child.elements();
                String content = "";
                for (Element pChild : pChildren) {
                    if (!pChild.getName().equals("pPr")) {
                        if (pChild.getName().equals("r")) {
                            for (Element t : pChild.elements("t")) {
                                //此元素的字体与字号,同受它同级上面<rPr>的<rFonts>属性ascii控制
                                String font = pChild.element("rPr").element("rFonts").attribute("ascii").getValue();
                                if (font.equals("华文楷体")) continue;
                                int fontSize = Integer.parseInt(pChild.element("rPr").element("sz").attribute("val").getValue());
                                if (fontSize != 32) continue;
                                if (font.equals("方正仿宋简体")) {
                                    //加粗，有/b标签的保留，其它的不保留continue掉
                                    if (pChild.element("rPr").element("b") == null) continue;
                                }

                                content = content + t.getText();
                            }
                        }
                    }
                }

                if (!StrKit.isBlank(content)) {
                    //如果content是 "图"+数字形式的，不输出
                    if (!content.contains("(图") && !content.contains("（图")) {
                        //输出全部内容
//                        if(content.startsWith("（")) System.out.print("\t");
//                        //如果content是以 数字+.开头的，那么多输出两个tab
//                        if (content.matches("^[0-9]+\\..*")) System.out.print("\t\t");
//                        System.out.println(content);
                        //只输出四和五
                        String[] printDx = {"一", "二", "三", "六", "七", "八", "九", "十"};
                        //转为 List<String>
                        List<String> printDxList = Arrays.asList(printDx);

                        if (content.startsWith("四") || content.startsWith("五")) {
                            out = true;
                        }
                        for (String s : printDxList) {
                            if (content.startsWith(s)) out = false;
                        }

                        if (out) {
                            if(content.startsWith("（")) System.out.print("\t");
                            System.out.println(content);
                        }
                    }
                }
            }
        }
    }
}