wordreader.java

一个搜索引擎,希望对大家有用

package ch7.poi;

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

import org.textmining.text.extraction.WordExtractor;

public class WordReader {

	public static String readDoc(String doc) throws Exception {
		// 创建输入流读取DOC文件
		FileInputStream in = new FileInputStream(new File(doc));
		WordExtractor extractor = null;
		String text = null;
		// 创建WordExtractor
		extractor = new WordExtractor();
		// 对DOC文件进行提取
		text = extractor.extractText(in);
		return text;
	}

	public static void main(String[] args) {
		// TODO Auto-generated method stub
		try {
			String text = WordReader.readDoc("c:/test.doc");
			System.out.println(text);
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

}