文本文件中查询中文字符串

文本文件中查询中文字符串

package hda.search_chinese;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * Daan Han
 * 
 */
public class App {
	public static void main(String[] args) throws IOException {
		
		String dir = "/your/dir/here";
		
		listFile(dir);

		System.out.println("===========");
		System.out.println("totalLine:  " + totalLine);
		System.out.println("totalWords: " + totalWords);
	}

	
	static int totalLine = 0;
	static int totalWords = 0;
	
	public static void dodo(String s) {
		for (String string : getChinese(s)) {
			System.out.println(string);
		}
	}

	public static List<String> getChinese(String s) {
		String temp = null;
		List<String> ret = new ArrayList<String>(2);
		Pattern p = Pattern.compile("(\\([ |\\( \\)]*)*[\u0391-\uFFE5]+([ |\\( \\)]+[\u0391-\uFFE5]+)*\\)*");
		Matcher m = p.matcher(s);
		while (m.find()) {
			temp = m.group(0);
			ret.add(temp);
			totalLine++;
			totalWords+=temp.length();
		}
		return ret;
	}

	public static void listFile(String dir) throws IOException {
		

		String encoding = "GBK";

		File d = new File(dir);
		for (File file : d.listFiles()) {
			
			System.out.printf("\n%s\n",file.getAbsoluteFile());
			
			if (file.exists() && file.isDirectory()){
				if (!file.getName().equals("WEB-INF")) // 过滤WEB-INF
					listFile(file.getAbsolutePath());
			}
			else if (file.exists() && file.isFile() && file.getName().endsWith(".jsp")) { // 只处理jsp
				
				InputStreamReader read = new InputStreamReader(
						new FileInputStream(file), encoding);
				BufferedReader bufferedReader = new BufferedReader(read);
				String lineTxt = null;
				while ((lineTxt = bufferedReader.readLine()) != null) {
					// System.out.println(lineTxt);
					dodo(lineTxt);
				}
				read.close();
			} else {
				System.out.println("找不到指定的文件");
			}

		}

	}
}