java调用openoffice将office系列文档转换为PDF的示例方法

前导：

发过程中经常会使用java将office系列文档转换为pdf， 一般都使用微软提供的openoffice+jodconverter 实现转换文档。

openoffice既有windows版本也有linux版。不用担心生产环境是linux系统。

1、openoffice依赖jar，以maven为例：

<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> 
 
    <!--jodconverter2.2.1必须依赖slf4j-jdk14必须这个版本，不然源码中日志会报错，很low的一个问题--> 
    <dependency> 
      <groupid>org.slf4j</groupid> 
      <artifactid>slf4j-jdk14</artifactid> 
      <version>1.4.3</version> 
    </dependency> 

2、直接上转换代码，需要监听openoffice应用程序8100端口即可。

public void convert(file sourcefile, file targetfile) { 
 
  try { 
    // 1: 打开连接 
    openofficeconnection connection = new socketopenofficeconnection(8100); 
    connection.connect(); 
 
    documentconverter converter = new openofficedocumentconverter(connection); 
    // 2:获取format 
    documentformatregistry factory = new basicdocumentformatregistry(); 
    documentformat inputdocumentformat = factory 
        .getformatbyfileextension(getextensionname(sourcefile.getabsolutepath())); 
    documentformat outputdocumentformat = factory 
        .getformatbyfileextension(getextensionname(targetfile.getabsolutepath())); 
    // 3:执行转换 
    converter.convert(sourcefile, inputdocumentformat, targetfile, outputdocumentformat); 
  } catch (connectexception e) { 
    log.info("文档转换pdf失败"); 
  } 
} 

3、需注意：jodconverter 在转换2007版本以后的xxx.docx文档会报错，原因大家都明03后缀名xxx.doc  07以后版本xxx.docx

查看jodconverter源码发现documentformat不支持xxx.docx格式basicdocumentformatregistry中public documentformat getformatbyfileextension(string extension)默认支持是使用doc格式

basicdocumentformatregistry类源码

// 
// jodconverter - java opendocument converter 
// copyright (c) 2004-2007 - mirko nasato <[e-mail]> 
// 
// this library is free software; you can redistribute it and/or 
// modify it under the terms of the gnu lesser general public 
// license as published by the free software foundation; either 
// version 2.1 of the license, or (at your option) any later version. 
// 
// this library is distributed in the hope that it will be useful, 
// but without any warranty; without even the implied warranty of 
// merchantability or fitness for a particular purpose. see the gnu 
// lesser general public license for more details. 
// http://www.gnu.org/copyleft/lesser.html 
// 
package com.artofsolving.jodconverter; 
 
import java.util.arraylist; 
import java.util.iterator; 
import java.util.list; 
 
public class basicdocumentformatregistry implements documentformatregistry { 
 
  private list/*<documentformat>*/ documentformats = new arraylist(); 
 
  public void adddocumentformat(documentformat documentformat) { 
    documentformats.add(documentformat); 
  } 
 
  protected list/*<documentformat>*/ getdocumentformats() { 
    return documentformats; 
  } 
 
  /** 
   * @param extension the file extension 
   * @return the documentformat for this extension, or null if the extension is not mapped 
   */ 
  public documentformat getformatbyfileextension(string extension) { 
    if (extension == null) { 
      return null; 
    } 
    string lowerextension = extension.tolowercase(); 
    for (iterator it = documentformats.iterator(); it.hasnext();) { 
      documentformat format = (documentformat) it.next();    
      if (format.getfileextension().equals(lowerextension)) { 
        return format; 
      } 
    } 
    return null; 
  } 
 
  public documentformat getformatbymimetype(string mimetype) { 
    for (iterator it = documentformats.iterator(); it.hasnext();) { 
      documentformat format = (documentformat) it.next();    
      if (format.getmimetype().equals(mimetype)) { 
        return format; 
      } 
    } 
    return null; 
  } 
} 

basicdocumentformatregistry的默认实现类defaultdocumentformatregistry  中支持的文件格式如下

// 
// jodconverter - java opendocument converter 
// copyright (c) 2004-2007 - mirko nasato <[e-mail]> 
// 
// this library is free software; you can redistribute it and/or 
// modify it under the terms of the gnu lesser general public 
// license as published by the free software foundation; either 
// version 2.1 of the license, or (at your option) any later version. 
// 
// this library is distributed in the hope that it will be useful, 
// but without any warranty; without even the implied warranty of 
// merchantability or fitness for a particular purpose. see the gnu 
// lesser general public license for more details. 
// http://www.gnu.org/copyleft/lesser.html 
// 
package com.artofsolving.jodconverter; 
 
public class defaultdocumentformatregistry extends basicdocumentformatregistry { 
 
  public defaultdocumentformatregistry() { 
    final documentformat pdf = new documentformat("portable document format", "application/pdf", "pdf"); 
    pdf.setexportfilter(documentfamily.drawing, "draw_pdf_export"); 
    pdf.setexportfilter(documentfamily.presentation, "impress_pdf_export"); 
    pdf.setexportfilter(documentfamily.spreadsheet, "calc_pdf_export"); 
    pdf.setexportfilter(documentfamily.text, "writer_pdf_export"); 
    adddocumentformat(pdf); 
     
    final documentformat swf = new documentformat("macromedia flash", "application/x-shockwave-flash", "swf"); 
    swf.setexportfilter(documentfamily.drawing, "draw_flash_export"); 
    swf.setexportfilter(documentfamily.presentation, "impress_flash_export"); 
    adddocumentformat(swf); 
     
    final documentformat xhtml = new documentformat("xhtml", "application/xhtml+xml", "xhtml"); 
    xhtml.setexportfilter(documentfamily.presentation, "xhtml impress file"); 
    xhtml.setexportfilter(documentfamily.spreadsheet, "xhtml calc file"); 
    xhtml.setexportfilter(documentfamily.text, "xhtml writer file"); 
    adddocumentformat(xhtml); 
 
    // html is treated as text when supplied as input, but as an output it is also 
    // available for exporting spreadsheet and presentation formats 
    final documentformat html = new documentformat("html", documentfamily.text, "text/html", "html"); 
    html.setexportfilter(documentfamily.presentation, "impress_html_export"); 
    html.setexportfilter(documentfamily.spreadsheet, "html (starcalc)"); 
    html.setexportfilter(documentfamily.text, "html (starwriter)"); 
    adddocumentformat(html); 
     
    final documentformat odt = new documentformat("opendocument text", documentfamily.text, "application/vnd.oasis.opendocument.text", "odt"); 
    odt.setexportfilter(documentfamily.text, "writer8"); 
    adddocumentformat(odt); 
 
    final documentformat sxw = new documentformat("openoffice.org 1.0 text document", documentfamily.text, "application/vnd.sun.xml.writer", "sxw"); 
    sxw.setexportfilter(documentfamily.text, "staroffice xml (writer)"); 
    adddocumentformat(sxw); 
 
    final documentformat doc = new documentformat("microsoft word", documentfamily.text, "application/msword", "doc"); 
    doc.setexportfilter(documentfamily.text, "ms word 97"); 
    adddocumentformat(doc); 
 
    final documentformat rtf = new documentformat("rich text format", documentfamily.text, "text/rtf", "rtf"); 
    rtf.setexportfilter(documentfamily.text, "rich text format"); 
    adddocumentformat(rtf); 
 
    final documentformat wpd = new documentformat("wordperfect", documentfamily.text, "application/wordperfect", "wpd"); 
    adddocumentformat(wpd); 
 
    final documentformat txt = new documentformat("plain text", documentfamily.text, "text/plain", "txt"); 
    // set filtername to "text" to prevent ooo from tryign to display the "ascii filter options" dialog 
    // alternatively filtername could be "text (encoded)" and filteroptions used to set encoding if needed 
    txt.setimportoption("filtername", "text"); 
    txt.setexportfilter(documentfamily.text, "text"); 
    adddocumentformat(txt); 
 
    final documentformat wikitext = new documentformat("mediawiki wikitext", "text/x-wiki", "wiki"); 
    wikitext.setexportfilter(documentfamily.text, "mediawiki"); 
    adddocumentformat(wikitext); 
     
    final documentformat ods = new documentformat("opendocument spreadsheet", documentfamily.spreadsheet, "application/vnd.oasis.opendocument.spreadsheet", "ods"); 
    ods.setexportfilter(documentfamily.spreadsheet, "calc8"); 
    adddocumentformat(ods); 
 
    final documentformat sxc = new documentformat("openoffice.org 1.0 spreadsheet", documentfamily.spreadsheet, "application/vnd.sun.xml.calc", "sxc"); 
    sxc.setexportfilter(documentfamily.spreadsheet, "staroffice xml (calc)"); 
    adddocumentformat(sxc); 
 
    final documentformat xls = new documentformat("microsoft excel", documentfamily.spreadsheet, "application/vnd.ms-excel", "xls"); 
    xls.setexportfilter(documentfamily.spreadsheet, "ms excel 97"); 
    adddocumentformat(xls); 
 
    final documentformat csv = new documentformat("csv", documentfamily.spreadsheet, "text/csv", "csv"); 
    csv.setimportoption("filtername", "text - txt - csv (starcalc)"); 
    csv.setimportoption("filteroptions", "44,34,0"); // field separator: ','; text delimiter: '"'  
    csv.setexportfilter(documentfamily.spreadsheet, "text - txt - csv (starcalc)"); 
    csv.setexportoption(documentfamily.spreadsheet, "filteroptions", "44,34,0"); 
    adddocumentformat(csv); 
 
    final documentformat tsv = new documentformat("tab-separated values", documentfamily.spreadsheet, "text/tab-separated-values", "tsv"); 
    tsv.setimportoption("filtername", "text - txt - csv (starcalc)"); 
    tsv.setimportoption("filteroptions", "9,34,0"); // field separator: '\t'; text delimiter: '"' 
    tsv.setexportfilter(documentfamily.spreadsheet, "text - txt - csv (starcalc)"); 
    tsv.setexportoption(documentfamily.spreadsheet, "filteroptions", "9,34,0"); 
    adddocumentformat(tsv); 
 
    final documentformat odp = new documentformat("opendocument presentation", documentfamily.presentation, "application/vnd.oasis.opendocument.presentation", "odp"); 
    odp.setexportfilter(documentfamily.presentation, "impress8"); 
    adddocumentformat(odp); 
 
    final documentformat sxi = new documentformat("openoffice.org 1.0 presentation", documentfamily.presentation, "application/vnd.sun.xml.impress", "sxi"); 
    sxi.setexportfilter(documentfamily.presentation, "staroffice xml (impress)"); 
    adddocumentformat(sxi); 
 
    final documentformat ppt = new documentformat("microsoft powerpoint", documentfamily.presentation, "application/vnd.ms-powerpoint", "ppt"); 
    ppt.setexportfilter(documentfamily.presentation, "ms powerpoint 97"); 
    adddocumentformat(ppt); 
     
    final documentformat odg = new documentformat("opendocument drawing", documentfamily.drawing, "application/vnd.oasis.opendocument.graphics", "odg"); 
    odg.setexportfilter(documentfamily.drawing, "draw8"); 
    adddocumentformat(odg); 
     
    final documentformat svg = new documentformat("scalable vector graphics", "image/svg+xml", "svg"); 
    svg.setexportfilter(documentfamily.drawing, "draw_svg_export"); 
    adddocumentformat(svg); 
  } 
} 

 解决方法：重写basicdocumentformatregistry类中public documentformat getformatbyfileextension(string extension)方法，只要是后缀名包含doc则使用doc的documentformat文档格式

// 
// jodconverter - java opendocument converter 
// copyright (c) 2004-2007 - mirko nasato <[e-mail]> 
// 
// this library is free software; you can redistribute it and/or 
// modify it under the terms of the gnu lesser general public 
// license as published by the free software foundation; either 
// version 2.1 of the license, or (at your option) any later version. 
// 
// this library is distributed in the hope that it will be useful, 
// but without any warranty; without even the implied warranty of 
// merchantability or fitness for a particular purpose. see the gnu 
// lesser general public license for more details. 
// http://www.gnu.org/copyleft/lesser.html 
// 
package com.artofsolving.jodconverter; 
 
import java.util.arraylist; 
import java.util.iterator; 
import java.util.list; 
 
/** 
 * 重写 basicdocumentformatregistry 文档格式 
 * @author huguangjun 
 */ 
public class basicdocumentformatregistry implements documentformatregistry { 
 
  private list/* <documentformat> */ documentformats = new arraylist(); 
 
  public void adddocumentformat(documentformat documentformat) { 
    documentformats.add(documentformat); 
  } 
 
  protected list/* <documentformat> */ getdocumentformats() { 
    return documentformats; 
  } 
 
  /** 
   * @param extension 
   *      the file extension 
   * @return the documentformat for this extension, or null if the extension 
   *     is not mapped 
   */ 
  public documentformat getformatbyfileextension(string extension) { 
    if (extension == null) { 
      return null; 
    } 
    //将文件名后缀统一转化 
    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(); 
    for (iterator it = documentformats.iterator(); it.hasnext();) { 
      documentformat format = (documentformat) it.next(); 
      if (format.getfileextension().equals(lowerextension)) { 
        return format; 
      } 
    } 
    return null; 
  } 
 
  public documentformat getformatbymimetype(string mimetype) { 
    for (iterator it = documentformats.iterator(); it.hasnext();) { 
      documentformat format = (documentformat) it.next(); 
      if (format.getmimetype().equals(mimetype)) { 
        return format; 
      } 
    } 
    return null; 
  } 
} 

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。