读取pdf以及xls文件并对比

package com.example.demo.BMPLoader;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.List;


import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.util.PDFTextStripper;
import org.apache.poi.hssf.extractor.ExcelExtractor;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;

/**
 * 
 * 读取pdf以及xls文件并对比
 */
public class test {
	
	public static void main(String[] args) {
		String fileName = "D:/1.pdf"; 
		File file = new File(fileName);
		FileInputStream in = null;
		try {
			String string;
	        FileInputStream inputStream = new FileInputStream("D:/实验文件.xls");
	        HSSFWorkbook workbook = new HSSFWorkbook(inputStream);
	        ExcelExtractor excelExtractor = new ExcelExtractor(workbook);
	        string = excelExtractor.getText();
	        System.out.println(string);
			in = new FileInputStream(fileName);
			// 新建一个PDF解析器对象
			PDFParser parser = new PDFParser(in);
			// 对PDF文件进行解析
			parser.parse();
			// 获取解析后得到的PDF文档对象
			PDDocument pdfdocument = parser.getPDDocument();
			// 新建一个PDF文本剥离器
			PDFTextStripper stripper = new PDFTextStripper();
			// 从PDF文档对象中剥离文本
			String result = stripper.getText(pdfdocument);
			//System.out.println("PDF文件的文本内容如下：");
			System.out.println(result);
			List<WordBean> list = ResultUtils.getError(string, result);
			for(WordBean wordBean : list){
				if (wordBean.getTarIndexs() == null) {
					System.err.println(wordBean.getWord()+"--------------原文位置"+wordBean.getOraIndex());
				}
			}
		} catch (Exception e) {
			//String str = file.getAbsolutePath();
			//System.out.println(str);
			e.printStackTrace();
		} finally {
			if (in != null) {
				try {
					in.close();
				} catch (IOException e1) {
				}
			}
		}

	}
}