lucene-索引RTF文档

1、对RTF进行文本提取操作时可以使用部分JAVA标准类处理（javax.swing.text和javax.swing.text.rtf）

2、

public class JavaBuiltInRTFHanlder implementsDocumentHandler{

public DocumentgetDocument(InputSream is)throws DocumentHandlerException{

StringbodyText=null;

DefaultStyleDocument styledDoc=new DefaultSytldDocument();

try{

new RTFEditorKit().read(is,styledDoc,0);

//通过JAVA内置的RTFEditorKit类从RTF文档中提取文本的内容

botyText=sytledDoc.getText(0,styledDoc.getLength());

}

catch (IOException e){

throw new DocumentHandlerException("cannot extract text from a RTFdocument",e);

}

catch (BadLocationException e){

throw new DocumentHandlerException("cannot extract text from a RTFdocument",e);

}

if (bodyText!=null){

Document doc=new Document();

doc.add(Field.UnStored("body",bodyText));

return doc;

}

return null;

}

public static voidmain(String[] args) throws Exception{

JavaBuiltInRTFHandler handler=new JavaBuiltInRTFHandler();

Document doc=handler.getDocument(new FileInputStream(newFile(args[0]));

System.out.println(doc);

}

}