Java跨平台将word转为pdf（结合Jodconverter 和OpenOffice.org）

Java跨平台将word转为pdf

（结合Jodconverter开源框架 和OpenOffice.org办公软件）

Jodconverter的版本：jodconverter 2.2.1 

网上的流传的方法：

1. 安装OpenOffice 3     下载路径：http://zh.openoffice.org/new/zh_cn/downloads.html

 

2. 启动OpenOffice服务

 cd C:\Program Files\OpenOffice.org 3\program

         soffice -headless -accept="socket,host=127.0.0.1,port=8100;urp;" -nofirststartwizard

3. 利用Jodconverter编写转换类

 

Java代码

public void convert(String input, String output){   

   File inputFile = new File(input);    

        File outputFile = new File(output);
        OpenOfficeConnection connection = new SocketOpenOfficeConnection(8100);
        try {
            connection.connect();
            DocumentConverter converter = new OpenOfficeDocumentConverter(connection);
            converter.convert(inputFile, outputFile);
        } catch(Exception e) {
            e.printStackTrace();
        } finally {
            try{ if(connection != null){connection.disconnect(); connection = null;}}catch(Exception e){}
        }
    }

public void convert(String input, String output){ 
        File inputFile = new File(input); 
        File outputFile = new File(output); 
        OpenOfficeConnection connection = new SocketOpenOfficeConnection(8100); 
        try { 
            connection.connect(); 
            DocumentConverter converter = new OpenOfficeDocumentConverter(connection); 
            converter.convert(inputFile, outputFile); 
        } catch(Exception e) { 
            e.printStackTrace(); 
        } finally { 
            try{ if(connection != null){connection.disconnect(); connection = null;}}catch(Exception e){} 
        } 
    } 

 

 

以上方法需要启动OpenOffice的服务，麻烦且占内存。

后来，有人又整理了一个方法：直接在转换类中调用启动服务。

 

 

public static int office2PDF(String sourceFile, String destFile) {

        String OpenOffice_HOME = "D:/Program Files/OpenOffice.org 3";// 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,但是这样是尽对没题目的
        // 假如从文件中读取的URL地址最后一个字符不是 '\'，则添加'\'
        if (OpenOffice_HOME.charAt(OpenOffice_HOME.length() - 1) != '/') {
            OpenOffice_HOME += "/";
        }
        Process pro = null;
        try {
            // 启动OpenOffice的服务
            String command = OpenOffice_HOME
                    + "program/soffice.exe -headless -accept=\"socket,host=127.0.0.1,port=8100;urp;\"";
            pro = Runtime.getRuntime().exec(command);
            // connect to an OpenOffice.org instance running on port 8100
            OpenOfficeConnection connection = new SocketOpenOfficeConnection("127.0.0.1", 8100);
            connection.connect();

            // convert
            DocumentConverter converter = new OpenOfficeDocumentConverter(connection);
            converter.convert(inputFile, outputFile);

            // close the connection
            connection.disconnect();
            // 封闭OpenOffice服务的进程
            pro.destroy();

            return 0;
        } catch (FileNotFoundException e) {
            e.printStackTrace();
            return -1;
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            pro.destroy();
        }

        return 1;
    }

public static int office2PDF(String sourceFile, String destFile) {

		String OpenOffice_HOME = "D:/Program Files/OpenOffice.org 3";// 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,但是这样是尽对没题目的
		// 假如从文件中读取的URL地址最后一个字符不是 '\'，则添加'\'
		if (OpenOffice_HOME.charAt(OpenOffice_HOME.length() - 1) != '/') {
			OpenOffice_HOME += "/";
		}
		Process pro = null;
		try {
			// 启动OpenOffice的服务
			String command = OpenOffice_HOME
					+ "program/soffice.exe -headless -accept=\"socket,host=127.0.0.1,port=8100;urp;\"";
			pro = Runtime.getRuntime().exec(command);
			// connect to an OpenOffice.org instance running on port 8100
			OpenOfficeConnection connection = new SocketOpenOfficeConnection("127.0.0.1", 8100);
			connection.connect();

			// convert
			DocumentConverter converter = new OpenOfficeDocumentConverter(connection);
			converter.convert(inputFile, outputFile);

			// close the connection
			connection.disconnect();
			// 封闭OpenOffice服务的进程
			pro.destroy();

			return 0;
		} catch (FileNotFoundException e) {
			e.printStackTrace();
			return -1;
		} catch (IOException e) {
			e.printStackTrace();
		} finally {
			pro.destroy();
		}

		return 1;
	}

 

 

本人却在google code无意中发现jodconverter 的新版本jodconverter-core 3.0-beta-4。

但是不知道为什么用不了maven，只能下载包 。地址：https://code.google.com/p/jodconverter/downloads/list

并结合其他开发者的整理如下：

 

       /**
 * 将Office文档转换为PDF. 运行该函数需要用到OpenOffice, OpenOffice
 *
 * @param sourceFile
 *            源文件,绝对路径. 可以是Office2003-2007全部格式的文档, Office2010的没测试. 包括.doc, .docx, .xls, .xlsx, .ppt, .pptx等.
 *
 * @param destFile
 *            目标文件.绝对路径.
 */
public static void word2pdf(String inputFilePath) {
    DefaultOfficeManagerConfiguration config = new DefaultOfficeManagerConfiguration();

    String officeHome = getOfficeHome();
    config.setOfficeHome(officeHome);

    OfficeManager officeManager = config.buildOfficeManager();
    officeManager.start();

    OfficeDocumentConverter converter = new OfficeDocumentConverter(officeManager);
    String outputFilePath = getOutputFilePath(inputFilePath);
    File inputFile = new File(inputFilePath);
    if (inputFile.exists()) {// 找不到源文件, 则返回
        File outputFile = new File(outputFilePath);
        if (!outputFile.getParentFile().exists()) { // 假如目标路径不存在, 则新建该路径
            outputFile.getParentFile().mkdirs();
        }
        converter.convert(inputFile, outputFile);
    }

    officeManager.stop();
}

public static String getOutputFilePath(String inputFilePath) {
    String outputFilePath = inputFilePath.replaceAll(".doc", ".pdf");
    return outputFilePath;
}

public static String getOfficeHome() {
    String osName = System.getProperty("os.name");
    if (Pattern.matches("Linux.*", osName)) {
        return "/opt/openoffice.org3";
    } else if (Pattern.matches("Windows.*", osName)) {
        return "D:/Program Files/OpenOffice.org 3";
    } else if (Pattern.matches("Mac.*", osName)) {
        return "/Application/OpenOffice.org.app/Contents";
    }
    return null;
}

        /**
	 * 将Office文档转换为PDF. 运行该函数需要用到OpenOffice, OpenOffice
	 * 
	 * @param sourceFile
	 *            源文件,绝对路径. 可以是Office2003-2007全部格式的文档, Office2010的没测试. 包括.doc, .docx, .xls, .xlsx, .ppt, .pptx等.
	 * 
	 * @param destFile
	 *            目标文件.绝对路径.
	 */
	public static void word2pdf(String inputFilePath) {
		DefaultOfficeManagerConfiguration config = new DefaultOfficeManagerConfiguration();

		String officeHome = getOfficeHome();
		config.setOfficeHome(officeHome);

		OfficeManager officeManager = config.buildOfficeManager();
		officeManager.start();

		OfficeDocumentConverter converter = new OfficeDocumentConverter(officeManager);
		String outputFilePath = getOutputFilePath(inputFilePath);
		File inputFile = new File(inputFilePath);
		if (inputFile.exists()) {// 找不到源文件, 则返回
			File outputFile = new File(outputFilePath);
			if (!outputFile.getParentFile().exists()) { // 假如目标路径不存在, 则新建该路径
				outputFile.getParentFile().mkdirs();
			}
			converter.convert(inputFile, outputFile);
		}

		officeManager.stop();
	}

	public static String getOutputFilePath(String inputFilePath) {
		String outputFilePath = inputFilePath.replaceAll(".doc", ".pdf");
		return outputFilePath;
	}

	public static String getOfficeHome() {
		String osName = System.getProperty("os.name");
		if (Pattern.matches("Linux.*", osName)) {
			return "/opt/openoffice.org3";
		} else if (Pattern.matches("Windows.*", osName)) {
			return "D:/Program Files/OpenOffice.org 3";
		} else if (Pattern.matches("Mac.*", osName)) {
			return "/Application/OpenOffice.org.app/Contents";
		}
		return null;
	}