把不同文件转化成字符串

功能：把word,excel,text,ptf等文件转化成字符串

package lucene.service;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;

import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.util.PDFTextStripper;
import org.apache.poi.hslf.HSLFSlideShow;
import org.apache.poi.hslf.model.Slide;
import org.apache.poi.hslf.model.TextRun;
import org.apache.poi.hslf.usermodel.SlideShow;
import org.apache.poi.hssf.usermodel.HSSFCell;
import org.apache.poi.hssf.usermodel.HSSFRow;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.hwpf.extractor.WordExtractor;

public class File2StringUtils {

	public static String wordTranslation(File file) throws IOException {
		InputStream in = new FileInputStream(file);
		WordExtractor wordExtractor = new WordExtractor(in);
		return wordExtractor.getText();
	}
	
	public static String powerPointTranslation(File file) throws IOException {
		InputStream in = new FileInputStream(file);
		StringBuffer sb = new StringBuffer("");
		SlideShow ss = new SlideShow(new HSLFSlideShow(in));
		Slide[] slides = ss.getSlides();
		for (int i = 0; i < slides.length; i++) {
			TextRun[] t = slides[i].getTextRuns();
			for (int j = 0; j < t.length; j++) {
				sb.append(t[j].getText());
			}
			sb.append(slides[i].getTitle());
		}
		return sb.toString();
	}
	
	public static String excelTranlation(File file)  {
		StringBuffer sb = new StringBuffer("");
		try {
			InputStream in = new FileInputStream(file);
			HSSFWorkbook workbook = new HSSFWorkbook(in);
			int numberOfSheet = workbook.getNumberOfSheets();
			for(int i = 0 ; i < numberOfSheet ; i ++) {
				HSSFSheet sheet = workbook.getSheetAt(i);
				int rows = sheet.getLastRowNum();
				for(int j = 0 ; j < rows; j ++) {
					HSSFRow row = sheet.getRow(j);
					int cells = row.getLastCellNum();
					for(int k = 0 ; k < cells ; k ++) {
						HSSFCell cell = row.getCell(k);
						String str = cell.getStringCellValue();
						sb.append(str + " ");
					}
				}
			}
		}  catch (Exception e) {
			return sb.toString();
		}
			
		return sb.toString();
	}
	
	public static String pdfTranslation(File file) throws IOException {
		InputStream in = new FileInputStream(file);
		PDFParser parser = new PDFParser(in);
		parser.parse();
		PDDocument doc = parser.getPDDocument();
		PDFTextStripper stripper = new PDFTextStripper();	
		return stripper.getText(doc);
	} 
	
	
	public static void main(String[] args) throws IOException {
		
//		File file= new File("D:\\test\\doc.doc");
//		System.out.println(wordTranslation(file));
		
		
//		File file= new File("D:\\test\\ppt.ppt");
//		System.out.println(powerPointTranslation(file));
		
//		File file= new File("D:\\test\\xls.xls");
//		System.out.println(excelTranlation(file));
		
		File file= new File("D:\\test\\pdf.pdf");
		System.out.println(pdfTranslation(file));
	}
}