docextractor.java

来自「一个用于搜索本地文件内容的小型搜索引擎」· Java 代码 · 共 43 行

package invertedList;

import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;

import org.apache.poi.hwpf.extractor.WordExtractor;


/**
 * @author Administrator
 *	A class to extract content from a doc file.
 */
public class DocExtractor extends Extractor {

	/* (non-Javadoc)
	 * @see invertedList.Extractor#getInformation(java.io.File)
	 */
	/** 
	 * @see invertedList.Extractor#getInformation(java.io.File)
	 * get the content of a doc file
	 */
	@Override
	public String getInformation(File file) {
		BufferedInputStream is;
		try {
			is = new BufferedInputStream(new FileInputStream(file));
			WordExtractor extractor = new WordExtractor(is);
			is.close();
			return extractor.getText();
			
		} catch (FileNotFoundException e1) {
			// TODO Auto-generated catch block
			e1.printStackTrace();
		} catch (IOException e2){
			e2.printStackTrace();
		}
		
		return null;
	}
}