POI 提取Word文本出错

POI提取word出错

代码如下

package com.util.extract;

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.util.PDFTextStripper;
import org.apache.poi.POIXMLDocument;
import org.apache.poi.POIXMLTextExtractor;
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.RichTextRun;
import org.apache.poi.hslf.usermodel.SlideShow;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.openxml4j.exceptions.OpenXML4JException;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.xmlbeans.XmlException;

public class FileExtractor {
		public static String getSuffix(String fileName){
	    String suffix=fileName.substring(fileName.lastIndexOf(".")+1);
	    return suffix;
	}
	public static String wordExtractor(String fileName){	
		try{
		InputStream in = new FileInputStream(fileName);
		String text = "";
		if(getSuffix(fileName).equals("doc")){
			WordExtractor wordExtractor = new WordExtractor(in);
			text = wordExtractor.getText();
		}else if(getSuffix(fileName).equals("docx")){
			OPCPackage opcPackage =  POIXMLDocument.openPackage(fileName);    
			POIXMLTextExtractor ex = new XWPFWordExtractor(opcPackage);       		
			text = ex.getText();
		}else if(getSuffix(fileName).equals("pdf")){
		    PDFParser p = new PDFParser(in); 
			p.parse();         
            PDFTextStripper ts = new PDFTextStripper();         	         
			text = ts.getText(p.getPDDocument());
		}else{
			text = "";
		}
		in.close();
		return text;
		}catch(IOException e){
			e.printStackTrace();
			return null;
		} catch (XmlException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
			return null;
		} catch (OpenXML4JException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
			return null;	
		}
	}
	
}

 

测试代码为

public class TestExtractor {
	
	public static void main(String[] args) throws IOException{
		String filename = "test.doc";
		String content = FileExtractor.wordExtractor(filename);
		System.out.println(content);
	}
}

 

提取的文件大小为1.6M,并且不是纯文本，word中还有批注、目录等。

 

异常为

Exception in thread "main" java.lang.ArrayIndexOutOfBoundsException: 204138
	at org.apache.poi.util.LittleEndian.getShort(LittleEndian.java:46)
	at org.apache.poi.hwpf.model.ListLevel.<init>(ListLevel.java:120)
	at org.apache.poi.hwpf.model.ListFormatOverrideLevel.<init>(ListFormatOverrideLevel.java:48)
	at org.apache.poi.hwpf.model.ListTables.<init>(ListTables.java:91)
	at org.apache.poi.hwpf.HWPFDocument.<init>(HWPFDocument.java:236)
	at org.apache.poi.hwpf.HWPFDocument.<init>(HWPFDocument.java:131)
	at org.apache.poi.hwpf.extractor.WordExtractor.<init>(WordExtractor.java:61)
	at org.apache.poi.hwpf.extractor.WordExtractor.<init>(WordExtractor.java:53)
	at com.util.extract.FileExtractor.wordExtractor(FileExtractor.java:41)
	at com.util.extract.TestExtractor.main(TestExtractor.java:17)

 

不明白是什么原因，大致感觉可能是不是word文件不太大？