int area = (short) bytes[0]; int pos = (short) bytes[1]; int code = (area << 8 & 0xff00) + (pos & 0xff);
for (int i = 0; i < 26; i++) { int max = 55290; if (i != 25) { max = AREA_CODE[i + 1]; } if (AREA_CODE[i] <= code && code < max) { return new String(new byte[]{(byte) (65 + i)}); } }
http://www.blogjava.net/Vencent/articles/31465.htmlpackage Test;/**
* Title:获得汉字的拼音首字母
* Description: GB 2312-80 把收录的汉字分成两级。第一级汉字是常用汉字,计 3755 个,
* 置于 16~55 区,按汉语拼音字母/笔形顺序排列;第二级汉字是次常用汉字,
* 计 3008 个,置于 56~87 区,按部首/笔画顺序排列,所以本程序只能查到
* 对一级汉字的声母。同时对符合声母(zh,ch,sh)只能取首字母(z,c,s)
* Copyright: Copyright (c) 2004
* Company:
* @author not attributable
* @version 1.0
*/
public class TestFirstLetter { // 国标码和区位码转换常量
private static final int GB_SP_DIFF = 160;//存放国标一级汉字不同读音的起始区位码
private static final int[] secPosvalueList = {
1601, 1637, 1833, 2078, 2274, 2302, 2433, 2594, 2787,
3106, 3212, 3472, 3635, 3722, 3730, 3858, 4027, 4086,
4390, 4558, 4684, 4925, 5249, 5600};//存放国标一级汉字不同读音的起始区位码对应读音
private static final char[] firstLetter = {
'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'j',
'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's',
't', 'w', 'x', 'y', 'z'};//获取一个字符串的拼音码
public static String getFirstLetter(String oriStr) {
String str = oriStr.toLowerCase();
StringBuffer buffer = new StringBuffer();
char ch;
char[] temp;
for (int i = 0; i < str.length(); i++) { //依次处理str中每个字符
ch = str.charAt(i);
temp = new char[] {
ch};
byte[] uniCode = new String(temp).getBytes();
if (uniCode[0] < 128 && uniCode[0] > 0) { // 非汉字
buffer.append(temp);
}
else {
buffer.append(convert(uniCode));
}
}
return buffer.toString();
} /** 获取一个汉字的拼音首字母。
* GB码两个字节分别减去160,转换成10进制码组合就可以得到区位码
* 例如汉字"你"的GB码是0xC4/0xE3,分别减去0xA0(160)就是0x24/0x43
* 0x24转成10进制就是36,0x43是67,那么它的区位码就是3667,在对照表中读音为‘n'
*/ private static char convert(byte[] bytes) { char result = '-';
int secPosvalue = 0;
int i;
for (i = 0; i < bytes.length; i++) {
bytes[i] -= GB_SP_DIFF;
}
secPosvalue = bytes[0] * 100 + bytes[1];
for (i = 0; i < 23; i++) {
if (secPosvalue >= secPosvalueList[i] &&
secPosvalue < secPosvalueList[i + 1]) {
result = firstLetter[i];
break;
}
}
return result;
}
public static void main(String[] args) {
System.out.println(getFirstLetter("中华人民共和国"));
}
}
import java.io.UnsupportedEncodingException;
/**
* Created by IntelliJ IDEA.
* User: Hex
* Date: 2009-1-15
* Time: 12:47:24
*/
public class GB2Alpha {
private static final int[] AREA_CODE = new int[]{
45217, 45253, 45761, 46318, 46826, 47010, 47297, 47614, 48119, 48119, 49062,
49324, 49896, 50371, 50614, 50622, 50906, 51387, 51446, 52218, 52698, 52698,
52698, 52980, 53689, 54481
};
public static String getFirstAlpha(String text) {
if (text == null || "".equals(text)) {
return "";
}
StringBuffer sb = new StringBuffer();
for (int i = 0; i < text.length(); i++) {
sb.append(getAlpha(text.substring(i, i + 1)));
}
return sb.toString();
}
private static String getAlpha(String character) {
byte[] bytes;
try {
bytes = character.getBytes("GBK");
} catch (UnsupportedEncodingException e) {
e.printStackTrace();
return character;
}
if (bytes.length < 2) {
return character;
}
int area = (short) bytes[0];
int pos = (short) bytes[1];
int code = (area << 8 & 0xff00) + (pos & 0xff);
for (int i = 0; i < 26; i++) {
int max = 55290;
if (i != 25) {
max = AREA_CODE[i + 1];
}
if (AREA_CODE[i] <= code && code < max) {
return new String(new byte[]{(byte) (65 + i)});
}
}
return character;
}
public static void main(String[] args) {
System.out.println(getFirstAlpha("你好"));
}
}