자바 프로 세 스 디자인-문서 유사 성 검사 시스템-문서 출력 문자열 류

/*
 *             。doc、txt、pdf    
 *      
 */
import java.io.*;
import org.pdfbox.pdmodel.PDDocument;
import org.textmining.text.extraction.WordExtractor;
import org.pdfbox.pdfparser.PDFParser;
import org.pdfbox.util.PDFTextStripper;


public class wordortxt {

	public static String readDoc(String docFilePath) throws Exception {   //doc    
		//        doc  
		File f1 = new File(docFilePath);
		FileInputStream in = new FileInputStream(f1);
		WordExtractor extractor = null;
		String text = null;
		//   WordExtractor 
		extractor = new WordExtractor();
		//  doc      
		text = extractor.extractText(in);
		return text;
	}

	public static String readtxt(String txtFilePath) throws Exception {		//txt    
		File f = new File(txtFilePath);
		FileInputStream inputstream = new FileInputStream(f);
		StringBuffer buffer = new StringBuffer();
		String line; 												//            
		InputStreamReader in=new InputStreamReader(inputstream);
		BufferedReader bufferreader = new BufferedReader(in);
		line = bufferreader.readLine(); 								//      
		while (line != null) { 											//    line        
			buffer.append(line); 										//           buffer  
			buffer.append("
"); 										//      
			line = bufferreader.readLine(); 							//      
		}
		//     buffer        
		inputstream.close();
		String filetext = buffer.toString();
		//inputstream.getEncoding()
		//filetext        
		return filetext;
		//System.out.print(filetext);
		//System.out.print(in.getEncoding());*/	

	}

	public static String readPDF (String PDFFilePath) {						//PDF    
		String resultPDF = null;
		FileInputStream is = null;
		PDDocument document = null;
		try{
			is = new FileInputStream(PDFFilePath);
			PDFParser p = new PDFParser(is);	// PDF      
			p.parse();		//        PDF    				
			document = p.getPDDocument();	//    PDF     
			PDFTextStripper stripper = new PDFTextStripper();	// PDF         
			resultPDF = stripper.getText(document);
		} catch (FileNotFoundException e){
			e.printStackTrace();
		} catch (IOException e ){
			e.printStackTrace();
		} finally {
			if (is != null){
				try {
					is.close();
				}catch (IOException e){
					e.printStackTrace();
				}
			}
			if (document != null){
				try {
					document.close();
				}catch (IOException e){
					e.printStackTrace();
				}
			}
		}
		return resultPDF;
	}

}