URLEncoder的只编码中文字符的类

package log;

import java.io.UnsupportedEncodingException;
import java.net.URLEncoder;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * 正则替换字符串里面的汉字部分。
 * 
 * @author 赵学庆 www.java2000.net
 */
public class URLEncoderHZ {
  public static void main(String[] args) throws Exception {
    String str = "http://192.168.1.1:8080/resources/电话.xls";
    System.out.println(encode(str, "UTF-8"));
  }

  private static String zhPattern = "[\u4e00-\u9fa5]+";

  /**
   * 替换字符串卷
   * 
   * @param str 被替换的字符串
   * @param charset 字符集
   * @return 替换好的
   * @throws UnsupportedEncodingException 不支持的字符集
   */
  public static String encode(String str, String charset) throws UnsupportedEncodingException {
    Pattern p = Pattern.compile(zhPattern);
    Matcher m = p.matcher(str);
    StringBuffer b = new StringBuffer();
    while (m.find()) {
      m.appendReplacement(b, URLEncoder.encode(m.group(0), charset));
    }
    m.appendTail(b);
    return b.toString();
  }
}

 

输出
http://192.168.1.1:8080/resources/%E7%94%B5%E8%AF%9D.xls

你可能感兴趣的:(java,.net)