ANTAI-WLTMS-API/src/main/java/com/steerinfo/dil/util/POIWordToHtml.java

package com.steerinfo.dil.util;

import fr.opensagres.poi.xwpf.converter.xhtml.Base64EmbedImgManager;
import fr.opensagres.poi.xwpf.converter.xhtml.XHTMLConverter;
import fr.opensagres.poi.xwpf.converter.xhtml.XHTMLOptions;
import org.apache.poi.hwpf.HWPFDocumentCore;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.converter.WordToHtmlUtils;
import org.apache.poi.hwpf.usermodel.Picture;
import org.apache.poi.xwpf.usermodel.*;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTDecimalNumber;
import org.w3c.dom.Document;
import org.w3c.dom.Element;

import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import java.io.*;
import java.math.BigInteger;
import java.util.Base64;
import java.util.Date;
import java.util.List;

/**
 * POIExcelToHtml 文件转换：
 *
 * @author generator
 * @version 1.0-SNAPSHORT 2021-08-09 18:06
 * 类描述
 * 修订历史：
 * 日期：2021-08-09
 * 作者：shadow
 * 参考：https://blog.csdn.net/u013585096/article/details/85104888
 * 描述：Execl转HTML
 * @Copyright 湖南视拓信息技术股份有限公司. All rights reserved.
 * @see null
 */
public class POIWordToHtml {
    private static final String ENCODING = "GB2312";// UTF-8


    public String docToHtml(InputStream input) throws Exception {
        String htmlData = "预览失败";
        try {
        HWPFDocumentCore wordDocument = WordToHtmlUtils.loadDoc(input);
        WordToHtmlConverter wordToHtmlConverter = new ImageConverter(
                DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument()
        );
        //wordToHtmlConverter.setPicturesManager(new PicturesManager() {
        //    @Override
        //    public String savePicture(byte[] content,
        //                              PictureType pictureType, String suggestedName,
        //                              float widthInches, float heightInches) {
        //            //给生成的页面写图片的路径
        //            return "word/media/" + suggestedName;
        //    }
        //});
        wordToHtmlConverter.processDocument(wordDocument);
        Document htmlDocument = wordToHtmlConverter.getDocument();
        ByteArrayOutputStream outStream = new ByteArrayOutputStream();
        DOMSource domSource = new DOMSource(htmlDocument);
        StreamResult streamResult = new StreamResult(outStream);
        TransformerFactory tf = TransformerFactory.newInstance();
        Transformer serializer = tf.newTransformer();
        serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
        serializer.setOutputProperty(OutputKeys.INDENT, "yes");
        serializer.setOutputProperty(OutputKeys.METHOD, "html");
        serializer.transform(domSource, streamResult);
        htmlData =  outStream.toString();
        outStream.close();
        } catch (Exception e){
            e.printStackTrace();
        }
        return htmlData;
    }

    public String docxToHtml(InputStream inputStream) throws IOException {
        String htmlData = "预览失败";
        try{
        XWPFDocument docxDocument = new XWPFDocument(inputStream);
        XHTMLOptions options = XHTMLOptions.create().indent(4);
            //获取文档中的图片
        //List<XWPFPictureData> allPictures = docxDocument.getAllPictures();
        //for (XWPFPictureData xwpfPictureData : allPictures) {
        //    String name = xwpfPictureData.getFileName();
        //    byte[] data = xwpfPictureData.getData();
        //    InputStream input = new ByteArrayInputStream(data);
        //    TODO 图片处理
        //
        //}
        //final String imageUrl = "";
        //不把图片生成出来
        options.setExtractor(null);
        options.setIgnoreStylesIfUnused(false);
        options.setFragment(true);
        //options.URIResolver(new IURIResolver() {
        //    @Override
        //    public String resolve(String uri) {
        //        return imageUrl + uri;
        //    }
        //});
        // 图片转base64 新版本支持
        options.setImageManager(new Base64EmbedImgManager());
         //转换htm1
        ByteArrayOutputStream htmlStream = new ByteArrayOutputStream();
        XHTMLConverter.getInstance().convert(docxDocument, htmlStream, options);
        htmlData = htmlStream.toString();
        htmlStream.close();
        } catch(Exception e) {
            e.printStackTrace();
        }
        return htmlData;
    }


    /**
     * 图片处理
     *
     *
     */
    public class ImageConverter extends WordToHtmlConverter {

        public ImageConverter(Document document) {
            super(document);
        }

        @Override
        protected void processImageWithoutPicturesManager(Element currentBlock, boolean inlined, Picture picture) {
            Element imgNode = currentBlock.getOwnerDocument().createElement("img");
            StringBuffer sb = new StringBuffer();
            sb.append(Base64.getMimeEncoder().encodeToString(picture.getRawContent()));
            sb.insert(0, "data:" + picture.getMimeType() + ";base64,");
            imgNode.setAttribute("src", sb.toString());
            currentBlock.appendChild(imgNode);
        }
    }


    /**
     * 读取word中的文本内容（段落、表格、图片分开处理）转HTML docx后缀名的Word
     * @param
     * @throws IOException
     */
    public  String readWordImgToHtml(InputStream inputStream) throws IOException{
        String htmlData = "预览失败";
        XWPFDocument document = new XWPFDocument(inputStream);
        String htmlText="";
        try {
            // 获取word中的所有段落与表格
            List<IBodyElement> elements = document.getBodyElements();
            for (IBodyElement element : elements) {
                // 段落
                if (element instanceof XWPFParagraph) {
                    htmlText+=getParagraphHtmlText((XWPFParagraph) element);
                }
                // 表格
                else if (element instanceof XWPFTable) {
                    htmlText+=getTabelHtmlText((XWPFTable) element);
                }
            }


            XHTMLOptions options = XHTMLOptions.create().indent(4);
            options.setExtractor(null);
            options.setIgnoreStylesIfUnused(false);
            options.setFragment(true);
            options.setImageManager(new Base64EmbedImgManager());
            ByteArrayOutputStream htmlStream = new ByteArrayOutputStream();

            XHTMLConverter.getInstance().convert(document, htmlStream, options);
            htmlData = htmlStream.toString();
            htmlStream.close();
            //获取word中的所有图片
            List<XWPFPictureData> picLists= document.getAllPictures();
            for(XWPFPictureData pic:picLists) {
                System.out.println("图片名称:\t" + pic.getFileName());
                System.out.println("图片类型：\t" + pic.getPictureType());
                byte[] data = pic.getData();
                System.out.println(data);
                //字节流图片上传，并返回服务器地址
                String imgUrl = getImageUrl(data, pic.getFileName());
                System.out.println("图片服务器地址：" + imgUrl);
                //组装img
                htmlText += "<p><img alt='' src='" + imgUrl + "'></p>";
            }
            }
        catch (Exception e) {
            e.printStackTrace();
        }
        return  htmlData;
    }
    /**
     * 获取段落内容并组装段落HTML
     * @param paragraph
     */
    private static String getParagraphHtmlText(XWPFParagraph paragraph) {
        // 获取段落中所有内容
        List<XWPFRun> runs = paragraph.getRuns();
        if (runs.size() == 0) {
            return "";
        }
        StringBuffer runText = new StringBuffer();
        for (XWPFRun run : runs) {
            runText.append(run.text());
        }
        return "<p style='margin:unset;text-align:"+paragraph.getAlignment().name()+"'>"+runText.toString()+"</p>";
    }
    /**
     * 获取表格内容并组装表格HTML
     * @param table
     */
    private static String getTabelHtmlText(XWPFTable table) {
        String result="";
        //获取表格数据行
        List<XWPFTableRow> rows = table.getRows();

        if(rows.size()>0){
            result+="<table border='1' cellspacing=0 style='border-collapse: collapse;'>";
            //遍历
            for (int i=0;i<rows.size();i++) {
                XWPFTableRow row = rows.get(i);
                result+="<tr style='font-weight: bold;'>";
                //获取每行的数据列
                List<XWPFTableCell> cells = row.getTableCells();
                for (XWPFTableCell cell : cells) {
                    //获取单元格跨列个数
                    BigInteger gridSpanNum = getCellGridSpanNum(cell);

                    result+="<td colspan="+gridSpanNum+" valign=center style='text-align: center;vertical-align: middle;'>";
                    String cellText="";
                    // 简单获取内容（简单方式是不能获取字体对齐方式的）
                    // System.out.println(cell.getText());
                    // 一个单元格可以理解为一个word文档，单元格里也可以加段落与表格
                    List<XWPFParagraph> paragraphs = cell.getParagraphs();
                    for (XWPFParagraph paragraph : paragraphs) {
                        cellText+="<p style='margin: unset;text-align:"+paragraph.getAlignment().name()+"'>"+getParagraphText(paragraph)+"</p>";
                    }
                    result+=cellText;
                    result+="</td>";
                }

                result+="</tr>";
            }
            result+="</table>";
        }
        return result;
    }
    /**
     * 获取段落内容（ docx后缀名的Word）
     * @param paragraph
     */
    private static String getParagraphText(XWPFParagraph paragraph) {
        // 获取段落中所有内容
        List<XWPFRun> runs = paragraph.getRuns();
        if (runs.size() == 0) {
            //System.out.println("按了回车（新段落）");
            return "";
        }
        StringBuffer runText = new StringBuffer();
        for (XWPFRun run : runs) {
            runText.append(run.text());
        }
//		if (runText.length() > 0) {
//			runText.append("，对齐方式：").append(paragraph.getAlignment().name());
//			System.out.println(runText);
//		}
        return runText.toString();
    }

    /**
     * 字节流图片上传
     * @param data:图片字节流
     * @param fileName:图片名称
     */
    public static String getImageUrl(byte[] data,String fileName) throws Exception{
        String imgUrl="";
        Long res =new Date().getTime();
        //设置文件存储路径，可以存放在你想要指定的路径里面
        String rootPath="D:/mimi/"+File.separator+"upload/images/";
        // 新文件名
        String newFileName =res + fileName.substring(fileName.lastIndexOf("."));
        //新文件
        File newFile=new File(rootPath+File.separator+newFileName);
        //判断文件目录是否存在
        if(!newFile.getParentFile().exists()){
            //如果目标文件所在的目录不存在，则创建父目录
            newFile.getParentFile().mkdirs();
        }

        //-------把图片文件写入磁盘 start ----------------
        FileOutputStream fos = new FileOutputStream(newFile);
        fos.write(data);
        fos.close();
        //-------把图片文件写入磁盘 end ----------------
        //服务器图片地址
        String baseURL = "http://192.168.0.76:8080/mimi/upload/images/";
        imgUrl=baseURL+newFileName;

        return imgUrl;
    }
    /**
     * 获取单元格跨列个数
     * @return
     */
    public static BigInteger getCellGridSpanNum(XWPFTableCell cell){
        BigInteger gridSpanNum =null;
        //获取单元格跨列
        CTDecimalNumber gridSpanXml = cell.getCTTc().getTcPr().getGridSpan();
        if(gridSpanXml!=null){
            gridSpanNum = gridSpanXml.getVal();
            System.out.println("gridSpanNum:"+gridSpanNum);
        }
        return gridSpanNum;
    }



}