The key points are highlighted. . .
Method 1: Use the toolkit poi provided by apache. poi uses version 4.1.2
Disadvantages: Inaccurate processing of font styles; inaccurate conversion of wmf formula image parts, this document only supports doc format
Advantages: The conversion speed is relatively fast and local debugging is convenient
Method 2: Use libreoffice, using version 7.5
Address:Download LibreOffice | LibreOffice Simplified Chinese official website – Free and free office suite
Linux installation libreoffice case:linux centos7 tool installation libreOffice libreOffice installation tutorial_centos7 installation libreoffice_the_bog’s blog-CSDN blog
Disadvantages: Relatively slow conversion speed
Advantages: The font style is very precise. This document only supports doc, docx, etc. Convert pdf and other related commands from Baidu
Without further ado, let’s get straight to the code! ! !
Method 1 code implementation:
Relevant jar package address:
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi</artifactId>
<version>4.1.2</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-scratchpad</artifactId>
<version>4.1.2</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
<version>4.1.2</version>
</dependency>
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.9.2</version>
</dependency>
<dependency>
<groupId>org.apache.xmlgraphics</groupId>
<artifactId>batik-codec</artifactId>
<version>1.7</version>
</dependency>
<dependency>
<groupId>net.arnx</groupId>
<artifactId>wmf2svg</artifactId>
<version>0.9.5</version>
</dependency>
package cn.hls.winner.winner_problem_manage.utils;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.PicturesManager;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.usermodel.PictureType;
import org.apache.poi.util.IOUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Attributes;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.util.FileCopyUtils;
import org.springframework.web.multipart.MultipartFile;
import org.w3c.dom.Document;
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.util.ArrayList;
import java.util.List;
import java.util.UUID;
/**
* @author lhz
* @description TODO
* @date 2023/9/18 10:14
*/
public class Word2003Util {
private static final Logger logger = LoggerFactory.getLogger(Word2003Util.class);
/**
*
* @param multipartFile uploaded file
* @param htmlFile html upload path
* @param htmlFileImgUrl html image upload path
* @param wordFileUrl word upload path
* @return
*/
public static String word2003ToHtml(MultipartFile multipartFile, String htmlFile, String htmlFileImgUrl, String wordFileUrl) {
//Need to determine whether the file is doc, docx
if (multipartFile == null) {
return "The word document uploaded is empty!";
}
if (multipartFile.getOriginalFilename().endsWith("docx")) {
return "The word document format is wrong, please upload it in doc format!";
}
logger.info("***** word2003ToHtml start file:{}", multipartFile);
//Return server proxy address
String htmlUrl = "";
//Randomly name html files
String uuid = UUID.randomUUID().toString();
String htmlFileName = uuid + "." + "html";
logger.info("====Initialization====(htmlFileName){parameter} " + htmlFileName);
try {
//Upload the local image address of the server
logger.info("==== htmlFile{parameter} ====" + htmlFile);
//The image address forwarded by nginx
logger.info("==== htmlFileImgUrl{parameter} ====" + htmlFileImgUrl);
//Generate the folder address of the web page
String htmlFileUrl = htmlFile + uuid + "/";
logger.info("==== htmlFileUrl{parameter} ==== " + htmlFileUrl);
//Upload files to the server
boolean flag = upload(multipartFile, wordFileUrl, uuid);
if (!flag) {
return "Word document upload failed!";
}
logger.info("====== Word document uploaded successfully!====");
//Get file name
String name = multipartFile.getOriginalFilename();
String suffix = name.substring(name.lastIndexOf("."));//.Suffix name
String filePath = wordFileUrl + uuid + suffix;
logger.info("==== filePath ====" + filePath);
File file = new File(filePath);
// 1) Load word document to generate HWPFDocument object
InputStream inputStream = new FileInputStream(file);
HWPFDocument wordDocument = new HWPFDocument(inputStream);
WordToHtmlConverter wordToHtmlConverter =
new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
//The map's address
String fileImg = htmlFileUrl + "images/";
File htmlFile1 = new File(htmlFileUrl);
if (!htmlFile1.exists()) {
//create
if (htmlFile1.mkdirs()) {
logger.info("Create" + htmlFileUrl + "Success");
} else {
logger.info("Create" + htmlFileUrl + "Success");
}
}
//html proxy address
htmlUrl = htmlFileImgUrl + uuid + "/" + htmlFileName;
//html generation path
htmlFileName = htmlFileUrl + htmlFileName;
logger.info("==== htmlFileName{ html ======== output address} " + htmlFileName);
//Set the location where the image is stored
String finalFileImg = fileImg;
final int[] index = {1};
//Process image address
wordToHtmlConverter.setPicturesManager(new PicturesManager() {
public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches, float heightInches) {
File imgPath = new File(finalFileImg);
if (!imgPath.exists()) {//Create the image directory if it does not exist
imgPath.mkdirs();
}
String extension = pictureType.getExtension();
//Randomly generate image names
suggestedName = finalFileImg + "image" + index[0] + "." + extension;
File file = new File(suggestedName);
OutputStream os = null;
try {
os = new FileOutputStream(file);
os.write(content);
os.close();
//Process wmf formula pictures
// if (extension.equals("wmf") || extension.equals("svg")) {
// if (extension.equals("wmf")) {
// String svgFile = suggestedName.substring(0,
// suggestedName.lastIndexOf(".wmf"))
// + ".svg";
// SvgToPngUtil.wmfToSvg(suggestedName, svgFile);
// }
// String suggestedNameSVG = suggestedName.substring(0, suggestedName.lastIndexOf(".")) + ".svg";
String s = SvgToPngUtil.readToString(suggestedNameSVG);
String suggestedNamePng = suggestedName.substring(0, suggestedName.lastIndexOf(".")) + ".png";
SvgToPngUtil.convertToPng(s, suggestedNamePng);
String s1 = SvgToPngUtil.GetImageStr(suggestedNameSVG);
// //Delete useless pictures
deleteFile(suggestedNameSVG, suggestedName);
// suggestedName = suggestedNameSVG;
// }
} catch (FileNotFoundException e) {
throw new RuntimeException(e);
} catch (IOException e) {
throw new RuntimeException(e);
}
//Here you can specify the path of the picture in the word document.
String imgUlr = suggestedName.replace(htmlFile, htmlFileImgUrl);
index[0] + + ;
return imgUlr;
}
});
wordToHtmlConverter.processDocument(wordDocument);
Document htmlDocument = wordToHtmlConverter.getDocument();
OutputStream outputStream = new FileOutputStream(htmlFileName);
DOMSource domSource = new DOMSource(htmlDocument);
StreamResult streamResult = new StreamResult(outputStream);
TransformerFactory factory = TransformerFactory.newInstance();
Transformer serializer = factory.newTransformer();
serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
serializer.setOutputProperty(OutputKeys.INDENT, "yes");
serializer.setOutputProperty(OutputKeys.METHOD, "html");
serializer.transform(domSource, streamResult);
outputStream.close();
logger.info("====== Web page style conversion begins ====");
String htmlContents = readHtml(htmlFileName);
FileCopyUtils.copy(htmlContents.getBytes("utf-8"), new File(htmlFileName));
logger.info("====== Web page style conversion completed ====");
} catch (Exception e) {
logger.error("word2003ToHtml====Exception");
logger.error(e.getMessage());
throw new RuntimeException(e);
}
//
return htmlUrl;
}
//Get web content
public static String readHtml(String htmlFileName) throws Exception {
StringBuilder htmlContents1 = new StringBuilder();
String htmlContents = "";
//Read image web content
BufferedReader buf = new BufferedReader(
new InputStreamReader(new FileInputStream(htmlFileName), "utf-8"));
String c = "";
while ((c = buf.readLine()) != null) {
htmlContents1.append(c + "\
");
}
buf.close();
htmlContents = htmlContents1.toString();
htmlContents = htmlContents.replace("hyphenate:auto;font-family:Times New Roman;", "hyphenate:auto;font-family:宋体;").replace("vertical-align:text-bottom;", "vertical -align: middle;").replace("'","'").replace(" & amp;rsquo;","'");
org.jsoup.nodes.Document document = Jsoup.parse(htmlContents);
formatHtml(document);
htmlContents = document.toString();
return htmlContents;
}
//Web page font style
public static void formatHtml(org.jsoup.nodes.Document document) {
Elements elements = document.getAllElements();
String title = document.title();
logger.info("==== formatHtml ====title" + title);
for (Element element : elements) {
if ("main".equals(element.className())) {
continue;
}
if (title.contains("Physics") || title.contains("Mathematics") || title.contains("Chemistry")) {
if (element.hasClass("s1")) {
element.attr("style", "font-family:Times New Roman;" + element.attr("style"));
}
}
String[] attrs = element.attr("style").split(";");
List<String> attrList = new ArrayList();
for (String attr : attrs) {
if (attr.contains("font-family")) {
attrList.add(attr);
}
}
//Remove the class attributes b1 b2 in the <body> tag
Elements bodies = element.getElementsByTag("body");
for(Element body : bodies){
System.out.println("=======className:" + body.className() + "==========");
if("b1 b2".equals(body.className())){
body.attr("class","");
}
}
}
}
public static void deleteFile(String... imgUrl) {
for (String s : imgUrl) {
File file = new File(s);
try {
if (file.isFile()) {
// Delete Files
if (file.delete()) {
logger.info("The file was deleted successfully ==== The name is: " + file.getName());
} else {
}
} else {
}
} catch (Exception e) {
logger.error("====== Failed to delete picture ======" + e.getMessage());
throw new RuntimeException();
}
}
}
/**
* @param file file
* @param htmlFile file upload address
* @param fileName file name
* @return
*/
public static boolean upload(MultipartFile file, String htmlFile, String fileName) {
InputStream is = null;
OutputStream os = null;
try {
File file1 = new File(htmlFile);
if (!file1.exists()) {
file1.mkdirs();
}
String name = file.getOriginalFilename();
String suffix = name.substring(name.lastIndexOf("."));//.Suffix name
is = file.getInputStream();
os = new FileOutputStream(htmlFile + fileName + suffix);
//Data copy
IOUtils.copy(is, os);
logger.info("==== File writing successful!====");
} catch (IOException e) {
logger.error("====== File upload failed ====" + e.getMessage());
return false;
} finally {
if (null != is) {
try {
is.close();
} catch (IOException e) {
throw new RuntimeException(e);
}
}
if (null != os) {
try {
os.close();
} catch (IOException e) {
throw new RuntimeException(e);
}
}
}
return true;
}
}
Method 2Code implementation:
package com.hls.poi.service;
import com.hls.poi.controller.WordToHtmlController;
import org.apache.poi.util.IOUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.web.multipart.MultipartFile;
import java.io.*;
import java.util.UUID;
public class LibreOfficeCommandWordService {
private static final Logger logger = LoggerFactory.getLogger(WordToHtmlController.class);
/**
* /opt/libreoffice7.5/program/soffice --headless --invisible --convert-to pdf /opt/a/1.docx --outdir /opt/a/
* /opt/a/1.docx after –convert-to pdf is the original file path
* –outdir /opt/a/ (the directory where the converted files are stored)
* <p>
* soffice --headless --invisible --convert-to html:HTML ffc75d91-3594-451d-a55f-a941325bc380.doc --outdir mmm
*/
//You need to find the actual directory where LibreOffice is installed based on the actual situation.
//Mac is installed to /usr/local/bin by default.
//CentOS is installed in /usr/bin by default
private final static String sofficeDir = "/opt/libreoffice7.6/program/";
/**
* @param multipartFile uploaded file
* @param htmlFile html upload path
* @param htmlFileImgUrl html image upload path
* @param wordFileUrl word upload path
* @param sofficeDir libreOffice installation address
* @throwsException
*/
public String word2html(MultipartFile multipartFile, String htmlFile, String htmlFileImgUrl, String wordFileUrl, String sofficeDir) throws Exception {
try {
logger.info("exec command:[{}]\
output: [{}]", "Enter word2pdf{} method");
//Need to determine whether the file is doc, docx
if (multipartFile == null) {
return "The word document uploaded is empty!";
}
//Return server proxy address
String htmlUrl = "";
//Randomly name html files
String uuid = UUID.randomUUID().toString();
String htmlFileName = uuid + "." + "html";
logger.info("====Initialization====(htmlFileName){parameter} " + htmlFileName);
//Upload the local image address of the server
logger.info("==== htmlFile{parameter} ====" + htmlFile);
//The image address forwarded by nginx
logger.info("==== htmlFileImgUrl{parameter} ====" + htmlFileImgUrl);
//Generate the folder address of the web page
String htmlFileUrl = htmlFile + uuid + "/";
logger.info("==== htmlFileUrl{parameter} ==== " + htmlFileUrl);
//Upload files to the server
boolean flag = upload(multipartFile, wordFileUrl, uuid);
if (!flag) {
return "Word document upload failed!";
}
logger.info("====== Word document uploaded successfully!====");
//Get file name
String name = multipartFile.getOriginalFilename();
String suffix = name.substring(name.lastIndexOf("."));//.Suffix name
//Word document path after uploading /home/winnersoft/date/tomcat/html-root/office/word/8ea8aec0-7fb5-4fbc-b73c-6f0e47b2857e.doc
String inPath = wordFileUrl + uuid + suffix;
logger.info("==== inPath ====" + inPath);
if (!new File(inPath).exists()) {
return "The word document does not exist!";
}
//The map's address
File htmlFile1 = new File(htmlFileUrl);
if (!htmlFile1.exists()) {
//create
if (htmlFile1.mkdirs()) {
logger.info("Create" + htmlFileUrl + "Success");
} else {
logger.info("Create" + htmlFileUrl + "Success");
}
}
//html proxy address //http://172.18.222.25:82/office/html/8ea8aec0-7fb5-4fbc-b73c-6f0e47b2857e/8ea8aec0-7fb5-4fbc-b73c-6f0e47b2857e.html
htmlUrl = htmlFileImgUrl + uuid + "/" + htmlFileName;
//html generation path /home/winnersoft/date/tomcat/html-root/office/html/af7ac82f-71bc-498c-8866-8bf7ef325345/
htmlFileName = htmlFileUrl;
logger.info("==== outPath{ html ======== output address} " + htmlFileName);
//Set the location where the image is stored
// String command = String.format("%s/soffice --convert-to pdf:writer_pdf_Export %s --outdir %s", sofficeDir, inPath, outPath);
String command = String.format("%s/soffice --headless --invisible --convert-to html:HTML %s --outdir %s", sofficeDir, inPath, htmlFileName);
logger.info("command==================================" + command);
String output = this.executeCommand(command);
logger.info("exec command:[{}]\
output: [{}]", command, output);
return htmlUrl;
} catch (IOException e) {
logger.error("io exception" + e.getMessage());
throw new RuntimeException(e);
} catch (InterruptedException e) {
throw new RuntimeException(e);
}
}
protected String executeCommand(String command) throws IOException, InterruptedException {
logger.info("executeCommand{} execute conversion");
StringBuffer output = new StringBuffer();
Process p;
p = Runtime.getRuntime().exec(command);
p.waitFor();
try (
InputStreamReader inputStreamReader = new InputStreamReader(p.getInputStream(), "UTF-8");
BufferedReader reader = new BufferedReader(inputStreamReader)
) {
String line = "";
while ((line = reader.readLine()) != null) {
output.append(line + "\
");
}
}
// Destroy the child process
p.destroy();
return output.toString();
}
/**
* @param file file
* @param htmlFile file upload address
* @param fileName file name
* @return
*/
public static boolean upload(MultipartFile file, String htmlFile, String fileName) {
InputStream is = null;
OutputStream os = null;
try {
File file1 = new File(htmlFile);
if (!file1.exists()) {
file1.mkdirs();
}
String name = file.getOriginalFilename();
String suffix = name.substring(name.lastIndexOf("."));//.Suffix name
is = file.getInputStream();
os = new FileOutputStream(htmlFile + fileName + suffix);
//Data copy
IOUtils.copy(is, os);
logger.info("==== File writing successful!====");
} catch (IOException e) {
logger.error("====== File upload failed ====" + e.getMessage());
return false;
} finally {
if (null != is) {
try {
is.close();
} catch (IOException e) {
throw new RuntimeException(e);
}
}
if (null != os) {
try {
os.close();
} catch (IOException e) {
throw new RuntimeException(e);
}
}
}
return true;
}
}