package com.example.util;
import java.io.UnsupportedEncodingException;
/**
* @author yulongfei
* @version 1.0
* @Date 2022-11-07 9:58
* @since 1.0
*/
public class ChineseCharacterHelper {
static final int GB_SP_DIFF = 160;
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};
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'};
public static void main(String[] args) {
String spells = getSpells("丰台台");
System.out.println(spells);
}
/**
* 提取汉字字符串的首字母
*
* @param characters 汉字字符串
* @return
*/
public static String getSpells(String characters) {
StringBuffer buffer = new StringBuffer();
for (int i = 0; i < characters.length(); i++) {
char ch = characters.charAt(i);
if ((ch >> 7) == 0) {
// 判断是否为汉字,如果左移7为为0就不是汉字,否则是汉字
buffer.append(ch);
} else {
char spell = getFirstLetter(ch);
buffer.append(spell);
}
}
return buffer.toString();
}
/**
* 获取一个汉字的首字母
*
* @param ch 汉字
* @return
*/
public static Character getFirstLetter(char ch) {
byte[] uniCode = null;
try {
uniCode = String.valueOf(ch).getBytes("GBK");
} catch (UnsupportedEncodingException e) {
e.printStackTrace();
return null;
}
if (uniCode[0] < 128 && uniCode[0] > 0) { // 非汉字
return null;
} else {
return convert(uniCode);
}
}
/**
* 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;
}
}