import org.pdfbox.exceptions.CryptographyException; //导入依赖的package包/类
private void doActionExtractText() throws PageException, IOException, CryptographyException, InvalidPasswordException {
		required("pdf", "extractText", "name", name,true);
		
		PDFDocument doc = toPDFDocument(source,password,null);
		doc.setPages(pages);
		
		pageContext.setVariable(name, PDFUtil.extractText(doc,doc.getPages()));
		/*
		 <cfpdf 
 required 
    action="extracttext" <!---extract all the words in the PDF.---> 
    ***source= "absolute or relative path of the PDF file|PDF document variable| 
            cfdocument variable" 
    pages = "*" <!----page numbers from where the text needs to be extracted from the 
                PDF document---> 

optional 
    addquads = "add the position or quadrants for the text in the PDF" 
    honourspaces = "true|false" 
    overwrite = "true" <!---Overwrite the specified object in the PDF document---> 
    ***password = "" <!--- PDF document password---> 
    type = "string|xml" <!---format in which the text needs to be extracted---> 
    one of the following: 
    destination = "PDF output file pathname" 
    name = "PDF document variable" 
    usestructure = "true|false" 
		 * */
	}
 

import org.pdfbox.exceptions.CryptographyException; //导入依赖的package包/类
public PDDocument toPDDocument() throws CryptographyException, InvalidPasswordException, IOException {
	PDDocument doc;
	if(barr!=null) 
		doc= PDDocument.load(new ByteArrayInputStream(barr,0,barr.length));
	else if(resource instanceof FileResource)
		doc= PDDocument.load((File)resource);
	else 
		doc= PDDocument.load(new ByteArrayInputStream(IOUtil.toBytes(resource),0,barr.length));
	
	if(password!=null)doc.decrypt(password);
	
	
	return doc;
	
}
 

import org.pdfbox.exceptions.CryptographyException; //导入依赖的package包/类
public static Object extractText(PDFDocument doc, Set<Integer> pageNumbers) throws IOException, CryptographyException, InvalidPasswordException {
	PDDocument pdDoc = doc.toPDDocument();
	//PDPageNode pages = pdDoc.getDocumentCatalog().getPages();
	//pages.
	//pdDoc.getDocumentCatalog().
	
	/*Iterator<Integer> it = pageNumbers.iterator();
	int p;
	while(it.hasNext()){
		p=it.next().intValue();
	
		pdDoc.getDocumentCatalog().getPages()
	}
	*/
	
	//print.o(pages);
	
	
	
	//pdDoc.
	
	
	//PDFTextStripperByArea  stripper = new PDFTextStripperByArea();
	//PDFHighlighter  stripper = new PDFHighlighter();
	PDFText2HTML  stripper = new PDFText2HTML();
	//PDFTextStripper stripper = new PDFTextStripper();
    StringWriter writer = new StringWriter();
    stripper.writeText(pdDoc, writer);
    
	
	return writer.toString();
}