java实现检测是否字符串中包含中文

时间:2022-02-08 19:01:01

代码非常实用,这里就不错废话,直接奉上

主要功能是实现判断字符串是否包含汉字 并且替换成ASCLL

?
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
private static String regEx = "[\\u4e00-\\u9fa5]";
 
  /**
   * 判断字符串是否包含汉字 并且替换成ASCLL
   *
   * @param str_para
   * @return str_result
   */
  private static String isChinese_Replace( String str_para )
  {
    Pattern p      = Pattern.compile( regEx );
    String str_result   = str_para;
    String str_0      = "";
    String str_1      = "";
    String str_data[]   = null;
    String str_return_reslut  = "";
    if ( str_result != null && str_result.trim().length() > 0 )
    {
      try {
        str_data = str_result.split( "" );
        for ( int i = 0; i < str_data.length; i++ )
        {
          Matcher m = p.matcher( str_data[i] );
          /* L.d(str_data[i]); */
          int count = 0;
          if ( m.find() )
          {
            count++;
            str_result   = m.group( 0 );
            byte[] b    = str_result.getBytes( "GBK" );
            str_0      = Integer.toHexString( b[0] );
            str_1      = Integer.toHexString( b[1] );
            str_return_reslut  = str_return_reslut + "/" + conver10( str_0 ) + conver10( str_1 ) + "/";
          } else {
            str_return_reslut = str_return_reslut + str_data[i];
          }
        }
      } catch ( NumberFormatException e ) {
        e.printStackTrace();
      } catch ( UnsupportedEncodingException e ) {
        e.printStackTrace();
      }
    } else {
      return(str_return_reslut);
    }
    return(str_return_reslut);
  }
  /* 字符串转换十进制 */
  public static int conver10( String str_0 )
  {
    return(Integer.parseInt( str_0.substring( str_0.length() - 2, str_0.length() ), 16 ) );
  }

我们来看个稍微简单些的代码,一些需求不高的地方可以用到

?
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class demo {
static String regEx = "[\u4e00-\u9fa5]";
static Pattern pat = Pattern.compile(regEx);
public static void main(String[] args) {
String input = "Hell world!";
System.out.println(isContainsChinese(input));
input = "hello world";
System.out.println(isContainsChinese(input));
}
  
public static boolean isContainsChinese(String str)
{
Matcher matcher = pat.matcher(str);
boolean flg = false;
if (matcher.find())  {
flg = true;
}
return flg;
}

最后我们附上各种字符的unicode编码的范围:
     * 汉字:[0x4e00,0x9fa5](或十进制[19968,40869])
     * 数字:[0x30,0x39](或十进制[48, 57])
     *小写字母:[0x61,0x7a](或十进制[97, 122])
     * 大写字母:[0x41,0x5a](或十进制[65, 90])