日期:2014-05-20  浏览次数:20838 次

汉字怎么截取,一半摄取,满2就取
如:
String s = "adsf爱上嘎sdf";

getword(int t){
//t=4就返回adsf
//t=5就返回adsf
//t=6就返回adsf爱
}

------解决方案--------------------
Java code

import java.io.UnsupportedEncodingException;

public class StringSpliter {
    static void getword(String str, int length) {
        try {
            byte[] bt = str.getBytes("gbk");
            if (bt[length] < 0) {
                System.out.println(new String(bt, 0, --length, "gbk"));
            } else {
                System.out.println(new String(bt, 0, length, "gbk"));
            }
        } catch (UnsupportedEncodingException e) {
            e.printStackTrace();
        }
    }

    public static void main(String[] args) {
        String str = "adsf爱上嘎sdf";
        StringSpliter.leftStr(str, 6);
    }
}

------解决方案--------------------
Java code


public class TestCut {
    static String s = "adsf爱上嘎sdf";

    public static void main(String[] args) {
    for (int len = 0; len < 12; len++) {
        System.out.println("长度为"+ len + " : "+ getword(s,len));//分别对长度为0,1,...11进行测试
    }
    }
    
    static String getword(String s , int t){
    StringBuffer sb = new StringBuffer();
    for(int i=0; i<s.length()&&i<t; i++){
        char c = s.charAt(i);
        if(isChinese(c)){
        i++;//多加一次
        if(i<t)sb.append(c);
        }
        else sb.append(c);
    }
    return sb.toString();
    }
    
    // /判断字符是否属于中文
    // GENERAL_PUNCTUATION 判断中文的“号
    // CJK_SYMBOLS_AND_PUNCTUATION 判断中文的。号
    // HALFWIDTH_AND_FULLWIDTH_FORMS 判断中文的,号
    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;
    }
    
}
/*output:
长度为0 : 
长度为1 : a
长度为2 : ad
长度为3 : ads
长度为4 : adsf
长度为5 : adsf
长度为6 : adsf爱
长度为7 : adsf爱
长度为8 : adsf爱嘎
长度为9 : adsf爱嘎d
长度为10 : adsf爱嘎df
长度为11 : adsf爱嘎df
*/