get Chinese Length by checking byte array in UTF-8 - Android Internationalization

Android examples for Internationalization:Chinese

  1. HOME
  2. Android
  3. Internationalization
  4. Chinese

Description

get Chinese Length by checking byte array in UTF-8

Demo Code

import android.text.TextUtils;
import android.util.Base64;
import java.io.UnsupportedEncodingException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.regex.PatternSyntaxException;

public class Main{
    public static int getChineseLength(String src, String endcoding) {
        int len = 0;
        try {//from  w w w .  j av  a2  s.co  m
            int j = 0;
            byte[] byteValue = src.getBytes(endcoding);
            while (true) {
                short tmpst = (short) (byteValue[j] & 0xF0);
                if (tmpst >= 0xB0) {
                    if (tmpst < 0xC0) {
                        j += 2;
                        len += 2;
                    } else if ((tmpst == 0xC0) || (tmpst == 0xD0)) {
                        j += 2;
                        len += 2;
                    } else if (tmpst == 0xE0) {
                        j += 3;
                        len += 2;
                    } else if (tmpst == 0xF0) {
                        short tmpst0 = (short) (((short) byteValue[j]) & 0x0F);
                        if (tmpst0 == 0) {
                            j += 4;
                            len += 2;
                        } else if ((tmpst0 > 0) && (tmpst0 < 12)) {
                            j += 5;
                            len += 2;
                        } else if (tmpst0 > 11) {
                            j += 6;
                            len += 2;
                        }
                    }
                } else {
                    j += 1;
                    len += 1;
                }
                if (j > byteValue.length - 1) {
                    break;
                }
            }
        } catch (UnsupportedEncodingException e) {
            return 0;
        }
        return len;
    }
    public static int getChineseLength(String src) {
        return getChineseLength(src, "UTF-8");
    }

}

Related Tutorials