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：

 
      com.artofsolving 
      jodconverter 
      2.2.1 
     
     
      org.openoffice 
      jurt 
      3.0.1 
     
     
      org.openoffice 
      ridl 
      3.0.1 
     
     
      org.openoffice 
      juh 
      3.0.1 
     
     
      org.openoffice 
      unoil 
      3.0.1 
     
 
     
     
      org.slf4j 
      slf4j-jdk14 
      1.4.3

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  
// 
// 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 documentFormats = new ArrayList(); 
 
  public void adddocumentFormat(documentFormat documentFormat) { 
    documentFormats.add(documentFormat); 
  } 
 
  protected List getdocumentFormats() { 
    return documentFormats; 
  } 
 
   
  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  
// 
// 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  
// 
// 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 documentFormats = new ArrayList(); 
 
  public void adddocumentFormat(documentFormat documentFormat) { 
    documentFormats.add(documentFormat); 
  } 
 
  protected List getdocumentFormats() { 
    return documentFormats; 
  } 
 
   
  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考高分网。

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

Java相关栏目本月热门文章