import org.apache.poi.hssf.usermodel.*;
import org.apache.poi.hssf.util.HSSFColor;
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.ss.usermodel.*;
import org.apache.poi.ss.util.CellRangeAddress;
import org.apache.poi.xssf.usermodel.XSSFCellStyle;
import org.apache.poi.xssf.usermodel.XSSFColor;
import org.apache.poi.xssf.usermodel.XSSFFont;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;
import org.apache.poi.xwpf.converter.core.BasicURIResolver;
import org.apache.poi.xwpf.converter.core.FileImageExtractor;
import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.docx4j.Docx4J;
import org.docx4j.fonts.IdentityPlusMapper;
import org.docx4j.fonts.Mapper;
import org.docx4j.fonts.PhysicalFonts;
import org.docx4j.openpackaging.packages.WordprocessingMLPackage;
import org.docx4j.org.apache.poi.util.IOUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.w3c.dom.Document;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import java.io.*;
import java.text.DecimalFormat;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.HashMap;
import java.util.Map;
/**
* ------------------
* User: tianwf
* Date: 2021/6/1
* Time: 9:29
* ------------------
* Description: office文档转换html
*/
public class OfficeToHtml {
private static final Logger logger = LoggerFactory.getLogger(OfficeToHtml.class);
private static String[] bordesr = { "border-top:", "border-right:", "border-bottom:", "border-left:" };
/**
* 将word2003转换为html文件
* @param wordPath word文件路径
* @param wordName word文件名称无后缀
* @param suffix word文件后缀
* @throws IOException
* @throws TransformerException
* @throws ParserConfigurationException
*/
public static String word2003ToHtml(String wordPath,String wordName,String suffix) throws IOException, TransformerException, ParserConfigurationException {
String htmlPath = wordPath + File.separator + wordName + "_show" + File.separator;
String htmlName = wordName + ".html";
final String imagePath = htmlPath + "image" + File.separator;
// 判断html文件是否存在
File htmlFile = new File(htmlPath + htmlName);
if(htmlFile.exists()) {
return htmlFile.getAbsolutePath();
}
// 原word文档
final String file = wordPath + File.separator + wordName + suffix;
InputStream input = new FileInputStream(new File(file));
HWPFDocument wordDocument = new HWPFDocument(input);
WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
// 设置图片存放的位置
wordToHtmlConverter.setPicturesManager(new PicturesManager() {
@Override
public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches, float heightInches) {
File imgPath = new File(imagePath);
if(!imgPath.exists()){//图片目录不存在则创建
imgPath.mkdirs();
}
File file = new File(imagePath + suggestedName);
try {
OutputStream os = new FileOutputStream(file);
os.write(content);
os.close();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
return "image/" + suggestedName;
}
});
// 解析word文档
wordToHtmlConverter.processDocument(wordDocument);
Document htmlDocument = wordToHtmlConverter.getDocument();