package com.htfg.dto;
import java.io.BufferedWriter;
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.OutputStream;
import java.io.OutputStreamWriter;
import java.util.List;
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 org.apache.poi.POIXMLDocument;
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.openxml4j.opc.OPCPackage;
import org.apache.poi.xwpf.converter.core.BasicURIResolver;
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.ParagraphAlignment;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.w3c.dom.Document;
public class DocumentTransformUtil {
/**
* doc2html核心方法
* @param docFile doc文件
* @param htmlFile html文件
*/
public static void doc2Html(final File docFile,
File htmlFile) {
String imgsdirStr = docFile.getParentFile().getParent()+"\\temps\\imgs\\"+docFile.getName().replace(".doc", "");
final File imgDir = new File(imgsdirStr);
if(!imgDir.exists() && !imgDir.isDirectory()){
imgDir.mkdir();
}
try {
HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(docFile
));
WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
DocumentBuilderFactory.newInstance().newDocumentBuilder()
.newDocument());
wordToHtmlConverter.setPicturesManager(new PicturesManager() {
public String savePicture(byte[] content,
PictureType pictureType, String suggestedName,
float widthInches, float heightInches) {
return "../temps/imgs/" +docFile.getName().replace(".doc", "")+"/"+ suggestedName;
}
});
wordToHtmlConverter.processDocument(wordDocument);
List pics = wordDocument.getPicturesTable().getAllPictures();
if (pics != null) {
for (int i = 0; i < pics.size(); i++) {
Picture pic = (Picture) pics.get(i);
try {
String imgtmppath = docFile.getParentFile().getParent()+"/temps/imgs/"+docFile.getName().replace(".doc", "")+"/";
pic.writeImageContent(new FileOutputStream(imgtmppath
+ pic.suggestFullFileName()));
} catch (FileNotFoundException e) {
e.printStackTrace();
}
}
}
Document htmlDocument = wordToHtmlConverter.getDocument();
ByteArrayOutputStream out = new ByteArrayOutputStream();
DOMSource domSource = new DOMSource(htmlDocument);
StreamResult streamResult = new StreamResult(out);
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);
out.close();
writeFile(new String(out.toByteArray()), htmlFile);
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* docx格式word转换为html
*
* @param fileName
* docx文件路径
* @param outPutFile
* html输出文件路径
* @throws TransformerException
* @throws IOException
* @throws ParserConfigurationException
*/
public static void docx2Html(final File docFile,File htmlFile) throws TransformerException, IOException, ParserConfigurationException {
String imgsdirStr = docFile.getParentFile().getParent()+"/temps/imgs/";
final File imgDir = new File(imgsdirStr);
long startTime = System.currentTimeMillis();
OPCPackage pack = POIXMLDocument.openPackage(docFile.getPath());
XWPFDocument document = new XWPFDocument(pack);
XHTMLOptions options = XHTMLOptions.create().indent(4);
// 导出图片
options.URIResolver(new BasicURIResolver("http://localhost:8080/SearchBySolr/res/temps/imgs"));
File imageFolder = new File(imgsdirStr);
options.setExtractor(new FileImageExtractor(imageFolder));
// URI resolver
//options.URIResolver(new FileURIResolver(imageFolder));
List paragraphs = document.getParagraphs();
//段落的格式,下面及个设置,将使新添加的文字向左对其,无缩进.
for(XWPFParagraph p:paragraphs){
p.setIndentationLeft(2);
p.setIndentationHanging(0);
p.setAlignment(ParagraphAlignment.LEFT);
p.setWordWrap(true);
}
OutputStream out = new FileOutputStream(htmlFile);
XHTMLConverter.getInstance().convert(document, out, options);
//System.out.println("Generate " + fileOutName + " with " + (System.currentTimeMillis() - startTime) + " ms.");
}
/**
* 把文件夹内doc转为htmls
* @param docsDir docs保存目录
* @param htmlsDir htmls保存路径
*/
public static void docs2Htmls(File docsDir, File htmlsDir) {
File[] files = docsDir.listFiles();
for (File file : files) {
doc2Html(file, new File(htmlsDir+"\\"+file.getName().replace(".doc", ".html")));
}
}
public static void docxs2Htmls(File docsDir, File htmlsDir) {
File[] files = docsDir.listFiles();
for (File file : files) {
doc2Html(file, new File(htmlsDir+"\\"+file.getName().replace(".docx", ".html")));
}
}
/**
* 把文档内用写入html文件
*
* @param content
* 文档内容
* @param htmlFile
* html文件
*/
private static void writeFile(String content, File htmlFile) {
FileOutputStream fos = null;
BufferedWriter bw = null;
try {
fos = new FileOutputStream(htmlFile);
bw = new BufferedWriter(new OutputStreamWriter(fos, "utf-8"));
bw.write(content);
} catch (FileNotFoundException fnfe) {
fnfe.printStackTrace();
} catch (IOException ioe) {
ioe.printStackTrace();
} finally {
try {
if (bw != null)
bw.close();
if (fos != null)
fos.close();
} catch (IOException ie) {
ie.printStackTrace();
}
}
}
}