中英文截取指定长度的字符,保证不会出乱码,截取最终长度为length,或length-1

package com.luodfu.test;
import java.io.UnsupportedEncodingException;
/**
* 中英文截取指定长度的字符
* 一个中文算两个字符，保证不会出乱码
* 截取最终长度为length,或length-1
* @author luodongfu
* @place hangzhou
*/
public class TestChinese {

public static void main(String[] args) {
String aa="A22中z文G测试_英文A看_看";
System.out.println(subChineseStr(aa,7) );
System.out.println(subChineseStr(aa,8) );
System.out.println(subChineseStr(aa,9) );
}

/**
* 判断字符是否为中文
* @param c
* @return
*/
public static boolean isChinese(char c) {
Character.UnicodeBlock ub = Character.UnicodeBlock.of(c);
if (ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS
|| ub == Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS
|| ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A
|| ub == Character.UnicodeBlock.GENERAL_PUNCTUATION
|| ub == Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION
|| ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {
return true;
}
return false;
}

/**
* 截取中英文字符中指定长度，保证不会出现乱码。
* 截取最终长度为length,或length-1.这样就不会出现乱码了，呵呵
* @param str 被截取的字符串
* @param length 截取几个长度
* @return
*/
public static String subChineseStr(String str,int length)
{
if(str==null||str.trim().equals(""))
{
return "";
}
try {
if(str.getBytes("GBK").length<=length)
{
return str;
}
} catch (UnsupportedEncodingException e) {
e.printStackTrace();
return "";
}
StringBuffer sb=new StringBuffer();
int count=0;
char[] ch = str.toCharArray();
for (int i = 0; i < ch.length; i++) {
char c = ch[i];
if (isChinese(c))
{
if(count<=length-2)
{
sb.append(c);
}
count=count+2;
}
else
{
if(count<length)
{
sb.append(c);
}
count++;
}
}
return sb.toString();
}
}

测试结果如下：

A22中z
A22中z文
A22中z文G