package com.anxin.ssk.common;
import java.io.UnsupportedEncodingException;
import java.util.HashMap;
import java.util.Map;
import java.util.Map.Entry;
/**
* 取得給定漢字串的首字母串,即聲母串 Title: ChineseCharToEn
*
* @author: (le.qiao)
* @e-mail: [email protected]
* @myblog: <a href="http://qiaolevip.iteye.com" target="_blank" rel="external nofollow" >http://qiaolevip.iteye.com</a>
* @date: 2014-1-15 注:隻支援GB2312字元集中的漢字
*
*/
public class LetterUtil {
private final static int[] li_SecPosValue = { 1601, 1637, 1833, 2078, 2274, 2302, 2433, 2594, 2787, 3106, 3212, 3472, 3635, 3722, 3730, 3858, 4027, 4086,
4390, 4558, 4684, 4925, 5249, 5590 };
private final static String[] lc_FirstLetter = { "a", "b", "c", "d", "e", "f", "g", "h", "j", "k", "l", "m", "n", "o", "p", "q", "r", "s", "t", "w", "x",
"y", "z" };
/**
* 取得給定漢字串的首字母串,即聲母串
*
* @param str 給定漢字串
* @return 聲母串
*/
public static String getAllFirstLetter(String str) {
if (str == null || str.trim().length() == 0) {
return "";
}
String _str = "";
for (int i = 0; i < str.length(); i++) {
_str = _str + getFirstLetter(str.substring(i, i + 1));
}
return _str;
}
/**
* 取得給定漢字的首字母,即聲母
*
* @param chinese 給定的漢字
* @return 給定漢字的聲母
*/
public static String getFirstLetter(String chinese) {
if (chinese == null || chinese.trim().length() == 0) {
return "";
}
chinese = conversionStr(chinese, "GB2312", "ISO8859-1");
if (chinese.length() > 1) // 判斷是不是漢字
{
int li_SectorCode = (int) chinese.charAt(0); // 漢字區碼
int li_PositionCode = (int) chinese.charAt(1); // 漢字位碼
li_SectorCode = li_SectorCode - 160;
li_PositionCode = li_PositionCode - 160;
int li_SecPosCode = li_SectorCode * 100 + li_PositionCode; // 漢字區位碼
if (li_SecPosCode > 1600 && li_SecPosCode < 5590) {
for (int i = 0; i < 23; i++) {
if (li_SecPosCode >= li_SecPosValue[i] && li_SecPosCode < li_SecPosValue[i + 1]) {
chinese = lc_FirstLetter[i];
break;
}
}
} else // 非漢字字元,如圖形符号或ASCII碼
{
chinese = conversionStr(chinese, "ISO8859-1", "GB2312");
chinese = chinese.substring(0, 1);
Map<String, String> exceptWords = new HashMap<String, String>();
// 歡迎大家補充說明~歡迎大家補充說明~歡迎大家補充說明
exceptWords.put("a", "庵");
exceptWords.put("g", "崮");
exceptWords.put("l", "崂");
exceptWords.put("j", "泾");
exceptWords.put("r", "榕");
exceptWords.put("x", "鑫");
exceptWords.put("y", "懿");
exceptWords.put("z", "梓");
for (Entry<String, String> letterSet : exceptWords.entrySet()) {
if (letterSet.getValue().indexOf(chinese) != -1) {
chinese = letterSet.getKey();
break;
}
}
}
}
return chinese;
}
/**
* 字元串編碼轉換
*
* @param str 要轉換編碼的字元串
* @param charsetName 原來的編碼
* @param toCharsetName 轉換後的編碼
* @return 經過編碼轉換後的字元串
*/
private static String conversionStr(String str, String charsetName, String toCharsetName) {
try {
str = new String(str.getBytes(charsetName), toCharsetName);
} catch (UnsupportedEncodingException ex) {
System.out.println("字元串編碼轉換異常:" + ex.getMessage());
}
return str;
}
public static void main(String[] args) {
System.out.println("擷取拼音首字母:" + LetterUtil.getAllFirstLetter("泾崂"));
String address = "(金浜小區)栖山路1689弄";
address = address.substring(address.indexOf(")") + 1);
System.out.println("擷取拼音首字母:" + LetterUtil.getFirstLetter(address));
}
}