前言
因为网上的信息比较多，每个项目又不太一样，故整理一下以作记录。
一、下载openoffice
下载地址：/download/
下载后，安装即可。
二、引入依赖
使用的JodConverter版本为2.2.1。因为jodconverter2.2.1必须依赖slf4j-jdk14必须这个版本，但是因为该版本过低，所以使用slf4j-api，slf4j-log4j12作为替代代替。
<!--openOffice所需依赖--><dependency><groupId>com.artofsolving</groupId><artifactId>jodconverter</artifactId><version>2.2.1</version></dependency><dependency><groupId>org.openoffice</groupId><artifactId>jurt</artifactId><version>3.0.1</version></dependency><dependency><groupId>org.openoffice</groupId><artifactId>ridl</artifactId><version>3.0.1</version></dependency><dependency><groupId>org.openoffice</groupId><artifactId>juh</artifactId><version>3.0.1</version></dependency><dependency><groupId>org.openoffice</groupId><artifactId>unoil</artifactId><version>3.0.1</version></dependency><dependency><groupId>org.slf4j</groupId><artifactId>slf4j-api</artifactId><version>1.5.6</version></dependency><dependency><groupId>org.slf4j</groupId><artifactId>slf4j-log4j12</artifactId><version>1.5.6</version></dependency>
代码实现
private static String OPENOFFICE_START = "E:\\it\\OpenOffice4\\program\\soffice.exe -headless -accept=\"socket,host=127.0.0.1,port=8100;urp;\"";//openoffice安装路径以及启动命令private static String OPENOFFICE_IP = "127.0.0.1";//ipprivate static int OPENOFFICE_PORT = 8100;//端口private static String FILE_PATH = "D:\\fileConversion\\sourceFile";//源文件夹private static String DESTFILE_PATH = "D:\\fileConversion\\destFile\\";//目标文件夹private static String DESTFILE_SUFFIX = ".pdf";//文件后缀//使用openoffice 将word格式的文件转换为pdf格式@Testpublic void OfficeTest(){//获取源文件的文件夹下所有文件Map fileMap = null;Process progress = null;//openOffice进程OpenOfficeConnection connection = null;//openOffice连接// 调用openoffice服务线程try {if (progress == null){progress = Runtime.getRuntime().exec(OPENOFFICE_START);}connection = new SocketOpenOfficeConnection(OPENOFFICE_IP, OPENOFFICE_PORT);//创建连接对象connection.connect();//用于测试openOffice连接时间DateFormat df = new SimpleDateFormat("yyyy-MM-dd HH:mm");System.out.println("连接时间:" + df.format(new Date()));DocumentConverter converter = new StreamOpenOfficeDocumentConverter(connection);//创建转换器/*** 获取文件夹下所有文件的集合**/ fileMap = readfile(FILE_PATH);Set<Map.Entry<String,String>> setFile = fileMap.entrySet();for (Map.Entry<String, String> file : setFile) {String fileName = file.getKey();//文件名String filePath = file.getValue();//绝对路径String destFileName = fileName.substring(0, fileName.lastIndexOf("."));//获取不带后缀的文件名//转换文件converter.convert(filePath, DESTFILE_PATH + destFileName + DESTFILE_SUFFIX);}System.out.println("转换完成");} catch (IOException e) {e.printStackTrace();}finally {if (connection != null) {// 关闭连接System.out.println("关闭连接");connection.disconnect();}if (progress != null) {// 关闭进程System.out.println("关闭进程");progress.destroy();}}}
获取文件夹下所有文件
/*** 读取某个文件夹下的所有文件(支持多级文件夹)*/public Map readfile(String filepath) throws FileNotFoundException, IOException {//声明一个HashMap，用于存放源文件，格式：<文件名，绝对路径>，以文件名为KEY，可以得到整个文件所在的路径和文件名Map<String, String> fileMap = new HashMap<>();try {File file = new File(filepath);if (!file.isDirectory()) {//文件fileMap.put(file.getName(),file.getAbsolutePath());} else if (file.isDirectory()) {//文件夹String[] filelist = file.list();for (int i = 0; i < filelist.length; i++) {File readfile = new File(filepath + "\\" + filelist[i]);if (!readfile.isDirectory()) {fileMap.put(readfile.getName(),readfile.getAbsolutePath());} else if (readfile.isDirectory()) {readfile(filepath + "\\" + filelist[i]);}}}} catch (FileNotFoundException e) {System.out.println("readfile() Exception:" + e.getMessage());}return fileMap;}
注意JodConverter2.2.1不兼容docx、xlsx、pptx格式。
解决方法：重写BasicDocumentFormatRegistry类。新建com.artofsolving.jodconverter包
/*** openOffice工具类,用于解决不兼容docx\xlsx和pptx,导致转换pdf异常问题*/public class BasicDocumentFormatRegistry implements DocumentFormatRegistry {private List documentFormats = new ArrayList();public BasicDocumentFormatRegistry() {}public void addDocumentFormat(DocumentFormat documentFormat) {this.documentFormats.add(documentFormat);}protected List getDocumentFormats() {return this.documentFormats;}public DocumentFormat getFormatByFileExtension(String extension) {if (extension == null) {return null;} else {if (extension.indexOf("doc") >= 0) {extension = "doc";}if (extension.indexOf("ppt") >= 0) {extension = "ppt";}if (extension.indexOf("xls") >= 0) {extension = "xls";}String lowerExtension = extension.toLowerCase();Iterator it = this.documentFormats.iterator();DocumentFormat format;do {if (!it.hasNext()) {return null;}format = (DocumentFormat)it.next();} while(!format.getFileExtension().equals(lowerExtension));return format;}}public DocumentFormat getFormatByMimeType(String mimeType) {Iterator it = this.documentFormats.iterator();DocumentFormat format;do {if (!it.hasNext()) {return null;}format = (DocumentFormat)it.next();} while(!format.getMimeType().equals(mimeType));return format;}}
总结：结合网上信息，进行资源整合，作为笔记。
