package com.qiuyueyuan.common.utils;
import java.io.UnsupportedEncodingException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import net.sourceforge.pinyin4j.PinyinHelper;
import net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat;
import net.sourceforge.pinyin4j.format.HanyuPinyinToneType;
/**
* @ClassName: ChinesToEnglishUtil
* @Description: 汉字转拼音工具
* @author yanxinjie
* @date 2020年12月13日 下午2:44:57
*
*/
public class ChinesToEnglishUtil {
  public static String convertHanzi2Pinyin(String hanzi, boolean flag) {
        /***
         * ^[\u2E80-\u9FFF]+$ 匹配所有东亚区的语言
         * ^[\u4E00-\u9FFF]+$ 匹配简体和繁体
         * ^[\u4E00-\u9FA5]+$ 匹配简体
         */
        String regExp = "^[\u4E00-\u9FFF]+$";
        StringBuffer sb = new StringBuffer();
        if (hanzi == null || "".equals(hanzi.trim())) {
            return "";
        }
        String pinyin = "";
        for (int i = 0; i < hanzi.length(); i++) {
            char unit = hanzi.charAt(i);
            if (match(String.valueOf(unit), regExp))//是汉字，则转拼音
            {
                pinyin = convertSingleHanzi2Pinyin(unit);
                if (flag) {
                    sb.append(pinyin);
                } else {
                    sb.append(pinyin.charAt(0));
                }
            } else {
                sb.append(unit);
            }
        }
        return sb.toString();
    }
    /***
     * 将单个汉字转成拼音
     *
     * @param hanzi
     * @return
     */
    private static String convertSingleHanzi2Pinyin(char hanzi) {
        HanyuPinyinOutputFormat outputFormat = new HanyuPinyinOutputFormat();
        outputFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
        String[] res;
        StringBuffer sb = new StringBuffer();
        try {
            res = PinyinHelper.toHanyuPinyinStringArray(hanzi, outputFormat);
            sb.append(res[0]);//对于多音字，只用第一个拼音
        } catch (Exception e) {
            return "";
        }
        return sb.toString();
    }
    /***
     * @param str   源字符串
     * @param regex 正则表达式
     * @return 是否匹配
     */
    public static boolean match(String str, String regex) {
        Pattern pattern = Pattern.compile(regex);
        Matcher matcher = pattern.matcher(str);
        return matcher.find();
    }
     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" };  
        /** 
         * 取得给定汉字串的首字母串,即声母串 
         * @param str 给定汉字串 
         * @return 声母串 
         */  
        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;  
        }  
        /** 
         * 取得给定汉字的首字母,即声母 
         * @param chinese 给定的汉字 
         * @return 给定汉字的声母 
         */  
        public static String getFirstLetter(String chinese) {
            if (chinese == null || chinese.trim().length() == 0) {  
                return "";  
            }  
            chinese = conversionStr(chinese, "GB2312", "ISO8859-1");  
            if (chinese.length() > 1) // 判断是不是汉字  
            {  
                int li_SectorCode = (int) chinese.charAt(0); // 汉字区码  
                int li_PositionCode = (int) chinese.charAt(1); // 汉字位码  
                li_SectorCode = li_SectorCode - 160;  
                li_PositionCode = li_PositionCode - 160;  
                int li_SecPosCode = li_SectorCode * 100 + li_PositionCode; // 汉字区位码  
                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 // 非汉字字符,如图形符号或ASCII码  
                {  
                    chinese =conversionStr(chinese, "ISO8859-1", "GB2312");  
                    chinese = chinese.substring(0, 1);  
                }  
            }  
            return chinese;  
        }  
        /** 
         * 字符串编码转换 
         * @param str 要转换编码的字符串 
         * @param charsetName 原来的编码 
         * @param toCharsetName 转换后的编码 
         * @return 经过编码转换后的字符串 
         */  
        private static String conversionStr(String str, String charsetName,String toCharsetName) {
            try {  
                str = new String(str.getBytes(charsetName), toCharsetName);  
            } catch (UnsupportedEncodingException ex) {  
                System.out.println("字符串编码转换异常：" + ex.getMessage());  
            }  
            return str;  
        }
    public static void main(String[] args) {
    System.out.println(getAllFirstLetter("耐克"));
  }
}