package com.dz.netVerify.wordToHtml;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.List;
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 org.apache.commons.io.FileUtils;
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.Picture;
import org.apache.poi.hwpf.usermodel.PictureType;
import org.apache.poi.xwpf.converter.core.FileImageExtractor;
import org.apache.poi.xwpf.converter.core.FileURIResolver;
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.w3c.dom.Document;
public class WordToHtmlController {
/**
* word2003版转换
*
* @throws IOException
*/
public void parseDocx2Html() throws Throwable {
final String path = "F:\\";
final String file = "测试文旦编辑.doc";
InputStream input = new FileInputStream(path + file);
String suffix = file.substring(file.indexOf(".") + 1);// //截取文件格式名
// 实例化WordToHtmlConverter,为图片等资源文件做准备
WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
wordToHtmlConverter.setPicturesManager(new PicturesManager() {
@Override
public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches,
float heightInches) {
return suggestedName;
}
});
if ("doc".equals(suffix.toLowerCase())) {
// docx
HWPFDocument wordDocument = new HWPFDocument(input);
wordToHtmlConverter.processDocument(wordDocument);
// 处理图片,会在同目录下生成 image/media/ 路径并保存图片
List pics = wordDocument.getPicturesTable().getAllPictures();
if (pics != null) {
for (int i = 0; i < pics.size(); i++) {
Picture pic = (Picture) pics.get(i);
try {
pic.writeImageContent(new FileOutputStream(path + pic.suggestFullFileName()));
} catch (FileNotFoundException e) {
e.printStackTrace();
}
}
}
}
// 转换
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");// 编码格式
serializer.setOutputProperty(OutputKeys.INDENT, "yes");// 是否用空白分割
serializer.setOutputProperty(OutputKeys.METHOD, "html");// 输出类型
serializer.transform(domSource, streamResult);
outStream.close();
String content = new String(outStream.toByteArray());
FileUtils.writeStringToFile(new File(path, "interface.html"), content, "utf-8");
}
/**
* word2007版转换
*
* @throws IOException
*/
public static void parseToHtml() throws IOException {
File f = new File("F:/test.docx");
if (!f.exists()) {
System.out.println("Sorry File does not Exists!");
} else {
if (f.getName().endsWith(".docx") || f.getName().endsWith(".DOCX")) {
// 1) 加载XWPFDocument及文件
InputStream in = new FileInputStream(f);
XWPFDocument document = new XWPFDocument(in);
// 2) 实例化XHTML内容(这里将会把图片等文件放到生成的"word/media"目录)
File imageFolderFile = new File("f:/test");
XHTMLOptions options = XHTMLOptions.create().URIResolver(new FileURIResolver(imageFolderFile));
options.setExtractor(new FileImageExtractor(imageFolderFile));
// options.setIgnoreStylesIfUnused(false);
// options.setFragment(true);
// 3) 将XWPFDocument转成XHTML并生成文件
OutputStream out = new FileOutputStream(new File("F:/result.html"));
XHTMLConverter.getInstance().convert(document, out, options);
} else {
System.out.println("Enter only MS Office 2007+ files");
}
}
}
public static void main(String[] args) throws Throwable {
new WordToHtmlController().parseDocx2Html();
}
}