首先要下载openoffic工具
地址:http://www.openoffice.org/zh-cn/download/
安装好openoffice后在OpenOffice 4\program文件夹下打开cmd开启服务,
命令:soffice -headless -accept="socket,host=127.0.0.1,port=8100;urp;" -nofirststartwizard
maven需要引入的jar包
备注:jodconverter.2.2.2找不到该版的maven地址,低版本的不支持docx格式的文档转。所以把jar包放到webapp/openOffic文件下,引用了一下。
com.artofsolving
jodconverter
2.2.2
system
${project.basedir}/src/main/webapp/openOffic/jodconverter-2.2.2.jar
commons-cli
commons-cli
1.2
org.openoffice
juh
3.1.0
org.openoffice
jurt
3.1.0
org.openoffice
ridl
3.0.1
org.openoffice
unoil
3.0.1
com.thoughtworks.xstream
xstream
1.3.1
controller
/**
* 在线预览
* @param fileid
*/
@RequestMapping(value = "view")
public String view(String fileid){
fileid = "4";
try {
SysFileVO fileVO = FileService.get(Integer.parseInt(fileid));
//源文件地址 如:D://360Downloads/【详细设计】XXX平台.doc
String filepath = fileVO.getNewName();
//源文件改成pdf后的地址 如:D://360Downloads/【详细设计】XXX平台.pdf
String pdfUrl = filepath.substring(0,filepath.lastIndexOf("."))+".pdf";
OpenOfficUtil.doc2pdf(filepath,pdfUrl);
return pdfUrl;
}catch (Exception e){
logger.info("查看异常",e);
}
return null;
}
OpenOfficUtil工具类
该工具类也支持文档转HTML
package com.suneee.utils;
import com.artofsolving.jodconverter.DocumentConverter;
import com.artofsolving.jodconverter.openoffice.connection.OpenOfficeConnection;
import com.artofsolving.jodconverter.openoffice.connection.SocketOpenOfficeConnection;
import com.artofsolving.jodconverter.openoffice.converter.OpenOfficeDocumentConverter;
import java.io.*;
import java.net.ConnectException;
import java.nio.charset.Charset;
import java.util.Date;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class OpenOfficUtil {
//这里是OpenOffice的安装目录, 在我的项目中,为了便于拓展接口,没有直接写成这个样子,但是这样是绝对没问题的
private static String OpenOffice_HOME="C:\\Program Files (x86)\\OpenOffice 4";
private static String host="127.0.0.1";
private static Integer port=8100;
private static String commands="program\\soffice -headless -accept=\"socket,host="+host+",port="+port+";urp;\"";
private static String filepath="/usr/local/ydyl/tomcat8/webapps/uploadimg";
private static String imgUrl="/uploadimg/";
private static OpenOfficeConnection connection= new SocketOpenOfficeConnection(port);
/**
* 将word文档转换成html文档
* @param docFile 需要转换的word文档
* @param filepath 转换之后html的存放路径
* @return 转换之后的html文件
*/
public static File convert(File docFile, String filepath, OpenOfficeConnection con) {
// 创建保存html的文件
File htmlFile = new File(filepath + "/" + new Date().getTime() + ".html");
System.out.println("--------zh1--------------"+new Date().getSeconds());
// 创建转换器
DocumentConverter converter = new OpenOfficeDocumentConverter(con);
// 转换文档问html
converter.convert(docFile, htmlFile);
System.out.println("--------zhlast1s--------------"+new Date().getSeconds());
// 关闭openoffice连接
con.disconnect();
return htmlFile;
}
/**
*
* 将word转换成html文件,并且获取html文件代码。
* @return 转换成功的html代码
* @throws IOException
*/
public static String toHtmlString(String url) throws IOException {
boolean connected = connection.isConnected();
if(!connected){
connection= new SocketOpenOfficeConnection(port);
}
File docFile = new File(url);
// 转换word文档
File htmlFile = convert(docFile, filepath,connection);
// 获取html文件流
StringBuffer htmlSb = new StringBuffer();
try {
BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(htmlFile),Charset.forName("utf-8")));
while (br.ready()) {
htmlSb.append(br.readLine());
}
br.close();
// 删除临时文件
htmlFile.delete();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
// HTML文件字符串
String htmlStr = htmlSb.toString();
// 返回经过清洁的html文本
return clearFormat(htmlStr, filepath);
}
/**
*
* 清除一些不需要的html标记
*
*
*
* @param htmlStr
*
* 带有复杂html标记的html语句
*
* @return 去除了不需要html标记的语句
*/
protected static String clearFormat(String htmlStr, String docImgPath) {
// 获取body内容的正则
String bodyReg = "";
Pattern bodyPattern = Pattern.compile(bodyReg);
Matcher bodyMatcher = bodyPattern.matcher(htmlStr);
if (bodyMatcher.find()) {
// 获取BODY内容,并转化BODY标签为DIV
htmlStr = bodyMatcher.group().replaceFirst("", "
]*>.*?)(<\\/P>)", // "
]*)(>.*?)(<\\/P>)", "
");
// 删除不需要的标签
htmlStr = htmlStr.replaceAll("<[/]?(font|FONT|span|SPAN|xml|XML|del|DEL|ins|INS|meta|META|[ovwxpOVWXP]:\\w+)[^>]*?>","");
// 删除不需要的属性
htmlStr = htmlStr.replaceAll("<([^>]*)(?:lang|LANG|class|CLASS|style|STYLE|size|SIZE|face|FACE|[ovwxpOVWXP]:\\w+)=(?:'[^']*'|\"\"[^\"\"]*\"\"|[^>]+)([^>]*)>","<$1$2>");
return htmlStr;
}
public static void doc2pdf(String docUrl,String pdfUrl) throws Exception {
boolean connected = connection.isConnected();
if(!connected){
connection= new SocketOpenOfficeConnection(port);
}
File docFile = new File(docUrl);
File pdfFile = new File(pdfUrl);
if (docFile.exists()) {
if (!pdfFile.exists()) {
try {
connection.connect();
DocumentConverter converter = new OpenOfficeDocumentConverter(connection);
converter.convert(docFile, pdfFile);
// close the connection
connection.disconnect();
System.out.println("****pdf转换成功,PDF输出:" + pdfFile.getPath()+ "****");
} catch (ConnectException e) {
e.printStackTrace();
System.out.println("****swf转换器异常,openoffice服务未启动!****");
throw e;
} catch (com.artofsolving.jodconverter.openoffice.connection.OpenOfficeException e) {
e.printStackTrace();
System.out.println("****swf转换器异常,读取转换文件失败****");
throw e;
} catch (Exception e) {
e.printStackTrace();
throw e;
}
} else {
System.out.println("****已经转换为pdf,不需要再进行转化****");
}
} else {
System.out.println("****swf转换器异常,需要转换的文档不存在,无法转换****");
}
}
}