1、介绍
2、安装和配置
Jacob是一个开源软件,它的官方站点是: http://danadler.com/jacob/ 大家可以到上面下载源代码研究,也可以直接下载编译后的二进制文件。
下载包jacob_x.x.zip,解压后有几个文件:jacob.jar、jacob-x.x-M2-x86.dll
把jacob-x.x-M2-x86.dll拷贝到%JAVA_HOME% 下的 bin 目录下,其中,%JAVA_HOME%就是JDK的安装目录。接着直接在java IDE中引用jacob.jar就可以使用了。
下面这个图,本文章中就未列出代码了,在我的资源共享中,有全的源代码,在我之前的博客中也有调用gs转换的命令。
3、转换word为pdf、html、txt 的示例
package com.shanhy.demo.windowsoffice;
import java.io.File;
import com.jacob.activeX.ActiveXComponent;
import com.jacob.com.ComThread;
import com.jacob.com.Dispatch;
import com.jacob.com.Variant;
/**
*
* 将jacob.dll放入JDK的bin目录下 把jacob.jar放入项目的buildPath中(web项目放到WEB-INF\lib目录下)
*
* @author 单红宇
*
*/
public class ConvertToPdf {
/*转PDF格式值*/
private static final int wdFormatPDF = 17;
private static final int xlFormatPDF = 0;
private static final int ppFormatPDF = 32;
private static final int msoTrue = -1;
private static final int msofalse = 0;
/*转HTML格式值*/
private static final int wdFormatHTML = 8;
private static final int ppFormatHTML = 12;
private static final int xlFormatHTML = 44;
/*转TXT格式值*/
private static final int wdFormatTXT = 2;
public boolean convert2PDF(String inputFile, String pdfFile) {
String suffix = getFileSufix(inputFile);
File file = new File(inputFile);
if (!file.exists()) {
System.out.println("文件不存在!");
return false;
}
if (suffix.equals("pdf")) {
System.out.println("PDF not need to convert!");
return false;
}
if (suffix.equals("doc") || suffix.equals("docx") || suffix.equals("txt")) {
return word2PDF(inputFile, pdfFile);
} else if (suffix.equals("ppt") || suffix.equals("pptx")) {
return ppt2PDF(inputFile, pdfFile);
} else if (suffix.equals("xls") || suffix.equals("xlsx")) {
return excel2PDF(inputFile, pdfFile);
} else {
System.out.println("文件格式不支持转换!");
return false;
}
}
/**
* 获取文件后缀
*
* @param fileName
* @return
* @author SHANHY
*/
private String getFileSufix(String fileName) {
int splitIndex = fileName.lastIndexOf(".");
return fileName.substring(splitIndex + 1);
}
/**
* Word文档转换
*
* @param inputFile
* @param pdfFile
* @author SHANHY
*/
private boolean word2PDF(String inputFile, String pdfFile) {
ComThread.InitSTA();
long start = System.currentTimeMillis();
ActiveXComponent app = null;
Dispatch doc = null;
try {
app = new ActiveXComponent("Word.Application");// 创建一个word对象
app.setProperty("Visible", new Variant(false)); // 不可见打开word
app.setProperty("AutomationSecurity", new Variant(3)); // 禁用宏
Dispatch docs = app.getProperty("Documents").toDispatch();// 获取文挡属性
System.out.println("打开文档 >>> " + inputFile);
// Object[]第三个参数是表示“是否只读方式打开”
// 调用Documents对象中Open方法打开文档,并返回打开的文档对象Document
doc = Dispatch.call(docs, "Open", inputFile, false, true).toDispatch();
// 调用Document对象的SaveAs方法,将文档保存为pdf格式
System.out.println("转换文档 [" + inputFile + "] >>> [" + pdfFile + "]");
Dispatch.call(doc, "SaveAs", pdfFile, wdFormatPDF);//word保存为pdf格式宏,值为17
// Dispatch.call(doc, "ExportAsFixedFormat", pdfFile, wdFormatPDF); // word保存为pdf格式宏,值为17
long end = System.currentTimeMillis();
System.out.println("用时:" + (end - start) + "ms.");
return true;
} catch (Exception e) {
e.printStackTrace();
System.out.println("========Error:文档转换失败:" + e.getMessage());
} finally {
Dispatch.call(doc, "Close", false);
System.out.println("关闭文档");
if (app != null)
app.invoke("Quit", new Variant[] {});
}
// 如果没有这句话,winword.exe进程将不会关闭
ComThread.Release();
ComThread.quitMainSTA();
return false;
}
/**
* PPT文档转换
*
* @param inputFile
* @param pdfFile
* @author SHANHY
*/
private boolean ppt2PDF(String inputFile, String pdfFile) {
ComThread.InitSTA();
long start = System.currentTimeMillis();
ActiveXComponent app = null;
Dispatch ppt = null;
try {
app = new ActiveXComponent("PowerPoint.Application");// 创建一个PPT对象
// app.setProperty("Visible", new Variant(false)); // 不可见打开(PPT转换不运行隐藏,所以这里要注释掉)
// app.setProperty("AutomationSecurity", new Variant(3)); // 禁用宏
Dispatch ppts = app.getProperty("Presentations").toDispatch();// 获取文挡属性
System.out.println("打开文档 >>> " + inputFile);
// 调用Documents对象中Open方法打开文档,并返回打开的文档对象Document
ppt = Dispatch.call(ppts, "Open", inputFile,
true,// ReadOnly
true,// Untitled指定文件是否有标题
false// WithWindow指定文件是否可见
).toDispatch();
System.out.println("转换文档 [" + inputFile + "] >>> [" + pdfFile + "]");
Dispatch.call(ppt, "SaveAs", pdfFile, ppFormatPDF);
long end = System.currentTimeMillis();
System.out.println("用时:" + (end - start) + "ms.");
return true;
} catch (Exception e) {
e.printStackTrace();
System.out.println("========Error:文档转换失败:" + e.getMessage());
} finally {
Dispatch.call(ppt, "Close");
System.out.println("关闭文档");
if (app != null)
app.invoke("Quit", new Variant[] {});
}
ComThread.Release();
ComThread.quitMainSTA();
return false;
}
/**
* Excel文档转换
*
* @param inputFile
* @param pdfFile
* @author SHANHY
*/
private boolean excel2PDF(String inputFile, String pdfFile) {
ComThread.InitSTA();
long start = System.currentTimeMillis();
ActiveXComponent app = null;
Dispatch excel = null;
try {
app = new ActiveXComponent("Excel.Application");// 创建一个PPT对象
app.setProperty("Visible", new Variant(false)); // 不可见打开
// app.setProperty("AutomationSecurity", new Variant(3)); // 禁用宏
Dispatch excels = app.getProperty("Workbooks").toDispatch();// 获取文挡属性
System.out.println("打开文档 >>> " + inputFile);
// 调用Documents对象中Open方法打开文档,并返回打开的文档对象Document
excel = Dispatch.call(excels, "Open", inputFile, false, true).toDispatch();
// 调用Document对象方法,将文档保存为pdf格式
System.out.println("转换文档 [" + inputFile + "] >>> [" + pdfFile + "]");
// Excel 不能调用SaveAs方法
Dispatch.call(excel, "ExportAsFixedFormat", xlFormatPDF, pdfFile);
long end = System.currentTimeMillis();
System.out.println("用时:" + (end - start) + "ms.");
return true;
} catch (Exception e) {
e.printStackTrace();
System.out.println("========Error:文档转换失败:" + e.getMessage());
} finally {
Dispatch.call(excel, "Close", false);
System.out.println("关闭文档");
if (app != null)
app.invoke("Quit", new Variant[] {});
}
ComThread.Release();
ComThread.quitMainSTA();
return false;
}
/**
* 测试
*
* @param args
* @author SHANHY
*/
public static void main(String[] args) {
ConvertToPdf d = new ConvertToPdf();
d.convert2PDF("g:\\test.docx", "g:\\test.pdf");
d.convert2PDF("g:\\testppt.pptx", "g:\\testppt.pdf");
d.convert2PDF("g:\\testexcel.xlsx", "g:\\testexcel.pdf");
}
}
读、写Word的简单示例
import com.jacob.activeX.ActiveXComponent;
import com.jacob.com.Variant;
import com.jacob.com.Dispatch;
public class Word {
String strDir = "c:jacob_1.9";
String strInputDoc = strDir + "file_in.doc";
String strOutputDoc = strDir + "file_out.doc";
String strOldText = "[label:import:1]";
String strNewText =
"I am some horribly long sentence, so long that [insert anything]";
boolean isVisible = true;
boolean isSaveOnExit = true;
public Word() {
ActiveXComponent oWord = new ActiveXComponent("Word.Application");
oWord.setProperty("Visible", new Variant(isVisible));
Dispatch oDocuments = oWord.getProperty("Documents").toDispatch();
Dispatch oDocument = Dispatch.call(oDocuments, "Open", strInputDoc).
toDispatch();
Dispatch oSelection = oWord.getProperty("Selection").toDispatch();
Dispatch oFind = oWord.call(oSelection, "Find").toDispatch();
Dispatch.put(oFind, "Text", strOldText);
Dispatch.call(oFind, "Execute");
Dispatch.put(oSelection, "Text", strNewText);
Dispatch.call(oSelection, "MoveDown");
Dispatch.put(oSelection, "Text",
"nSo we got the next line including BR.n");
Dispatch oFont = Dispatch.get(oSelection, "Font").toDispatch();
Dispatch.put(oFont, "Bold", "1");
Dispatch.put(oFont, "Italic", "1");
Dispatch.put(oFont, "Underline", "0");
Dispatch oAlign = Dispatch.get(oSelection, "ParagraphFormat").
toDispatch();
Dispatch.put(oAlign, "Alignment", "3");
Dispatch oWordBasic = (Dispatch) Dispatch.call(oWord, "WordBasic").
getDispatch();
Dispatch.call(oWordBasic, "FileSaveAs", strOutputDoc);
Dispatch.call(oDocument, "Close", new Variant(isSaveOnExit));
oWord.invoke("Quit", new Variant[0]);
}
public static void main(String[] args) {
Word word = new Word();
}
}
4、jacob.jar的结构
jacob包括两个部分:
com.jacob.activeX: ActiveXComponent类
com.jacob.com: 其它类和元素
5、Jacob类
Jacob的结构很简单,包含以下几个类:
ActiveXComponent Class:封装了Dispatch对象,用于创建一个封装了COM组件对象的Java Object
Dispatch Class:用于指向封装后的MS数据结构。常用的方法有call,subcall,get,invoke…后面会介绍使用方法。
Variant Class:用于映射COM的Variant数据类型。提供Java和COM的数据交换。
ComException Class:异常类
6、Jacob方法
用于访问COM/DLL对象的方法,读取、修改COM/DLL对象的属性。
call method:属于Dispatch类。用于访问COM/DLL对象的方法。方法进行了重载,方便不同场合调用。返回一个Variant类型的值。
callSub method:使用方法和call一样,不过它不返回值。
get method:读取COM对象的属性值,返回一个Variant类型值。
put method:设置COM对象的属性值。
invoke method:call的另一种用法,更复杂一些。
invokesub method:subcall的另一种用法
getProperty method:属于ActiveXComponent类,读取属性值,返回一个Variant类型值。
setProperty method:属于ActiveXComponent类,设置属性值。
要注意一点:在使用Jacob时,很重要的一点是,用户必须安装有Office的应用程序。否则也就无法建立Java-COM桥,进而无法解析了。
7、最后列一下ActiveX 控件名称
MS控件名 | a1的值 |
InternetExplorer | InternetExplorer.Application |
Excel | Excel.Application |
Word | Word.Application |
Powerpoint | Powerpoint.Application |
vb/java Script | ScriptControl |
windows media Player | WMPlayer.OCX |
Outlook | Outlook.Application |
Visio | Visio.Application |
DAO | DAO.PrivateDBEngine.35 |
MultiFace | MultiFace.Face |
部分内容参考: http://www.cnblogs.com/vulcans/archive/2009/09/08/1562588.html