zoukankan      html  css  js  c++  java
  • emoji表情符处理替换成空格

    /**
       * 用filterOffUtf8Mb4
       * Description: 过滤率四个字节的utf-8字符(emoji表情符),替换成四个空格。
       *         四字节utf-8字符mysql存储报错 
       * @Version1.0
       * @param s
       * @return
       * @throws UnsupportedEncodingException 
       * @throws Exception
       */
      public static String parseUtf8(String s) throws UnsupportedEncodingException {
        byte[] b = s.getBytes("utf-8");
        for(int i=0, len=b.length; i<len; i++){
          if ((b[i] & 0xF8) == 0xF0) {//F8=1111 1000,F0=1111 0000过滤4位UTF8编码(字头11110xxx)
            b[i++] = 32;
            b[i++] = 32;
            b[i++] = 32;
            b[i++] = 32;
          }
          else if ((b[i] & 0xFC) == 0xF8) {//FC=1111 1100,F8=1111 1000过滤5位UTF8编码(字头111110xx)
            b[i++] = 32;
            b[i++] = 32;
            b[i++] = 32;
            b[i++] = 32;
            b[i++] = 32;
          }
          else if ((b[i] & 0xFE) == 0xFC) {//FE=1111 1110,FC=1111 1100,过滤6位UTF8编码(字头1111110x)
            b[i++] = 32;
            b[i++] = 32;
            b[i++] = 32;
            b[i++] = 32;
            b[i++] = 32;
            b[i++] = 32;
          }
        }
        return new String(b, "utf-8");

      }




  • 相关阅读:
    OpenWRT Mac 虚拟机PD 分享 for 软路由
    How to write u disk from img in mac os x
    linux find file > 100 M
    gojs for data flow
    正则表达式
    grep
    搜索引擎Query Rewrite
    Kafka replication
    cassandra写数据CommitLog
    Solr DIH JDBC 源码解析
  • 原文地址:https://www.cnblogs.com/jgig11/p/5773005.html
Copyright © 2011-2022 走看看