MySQL 中文转拼音函数

需求是将字符串中的汉字转为拼音。创建一个汉字转拼音的函数,在其中判断每个字符是否为中文,如果是则查询拼音表取得对应的拼音,否则原样返回。网上的大部分 MySQL 转拼音函数都是通过创建一个拼音对照表,然后在自定义函数中查询该表实现的。以下对这种实现做了修改,具有以下特点:

  • 不需要拼音表。
  • 与数据库字符集无关。
  • 根据参数可分别返回全拼小写、全拼大写、全拼首字母大写。
  • 不考虑多音字拼音上下文语义的正确性。
  • 通过嵌套使用 MySQL 的 elt、interval 函数确定一个汉字对应的唯一拼音。

创建自定义函数

drop function if exists to_pinyin;
delimiter //
create function to_pinyin(name varchar(255) charset gbk, flag int) returns varchar(255) charset gbk
begin
    declare mycode int;
    declare tmp_lcode varchar(2) charset gbk;
    declare lcode int;
    declare tmp_rcode varchar(2) charset gbk;
    declare rcode int;
    declare l_pin_yin_ varchar(6);
 
    declare mypy varchar(255) charset gbk default '';
    declare lp int;
 
    set mycode = 0;
    set lp = 1;
 
    set name = hex(name);
 
    while lp < length(name) do
 
        set tmp_lcode = substring(name, lp, 2);
        set lcode = cast(ascii(unhex(tmp_lcode)) as unsigned); 
        set tmp_rcode = substring(name, lp + 2, 2);
        set rcode = cast(ascii(unhex(tmp_rcode)) as unsigned); 
        if lcode > 128 then
            set mycode =abs(65536 - lcode * 256 - rcode);
 
            -- 取对应的拼音
            set l_pin_yin_ = elt(interval(0-mycode,
                      -20319,-20317,-20304,-20295,-20292,-20283,-20265,-20257,-20242,-20230,-20051,-20036,
                      -20032,-20026,-20002,-19990,-19986,-19982,-19976,-19805,-19784,-19775,-19774,-19763,
                      -19756,-19751,-19746,-19741,-19739,-19728,-19725,-19715,-19540,-19531,-19525,-19515,
                      -19500,-19484,-19479,-19467,-19289,-19288,-19281,-19275,-19270,-19263,-19261,-19249,
                      -19243,-19242,-19238,-19235,-19227,-19224,-19218,-19212,-19038,-19023,-19018,-19006,
                      -19003,-18996,-18977,-18961,-18952,-18783,-18774,-18773,-18763,-18756,-18741,-18735,
                      -18731,-18722,-18710,-18697,-18696,-18526,-18518,-18501,-18490,-18478,-18463,-18448,
                      -18447,-18446,-18239,-18237,-18231,-18220,-18211,-18201,-18184,-18183,-18181,-18012,
                      -17997,-17988,-17970,-17964,-17961,-17950,-17947,-17931,-17928,-17922,-17759,-17752,
                      -17733,-17730,-17721,-17703,-17701,-17697,-17692,-17683,-17676,-17496,-17487,-17482,
                      -17468,-17454,-17433,-17427,-17417,-17202,-17185,-16983,-16970,-16942,-16915,-16733,
                      -16708,-16706,-16689,-16664,-16657,-16647,-16474,-16470,-16465,-16459,-16452,-16448,
                      -16433,-16429,-16427,-16423,-16419,-16412,-16407,-16403,-16401,-16393,-16220,-16216,
                      -16212,-16205,-16202,-16187,-16180,-16171,-16169,-16158,-16155,-15959,-15958,-15944,
                      -15933,-15920,-15915,-15903,-15889,-15878,-15707,-15701,-15681,-15667,-15661,-15659,
                      -15652,-15640,-15631,-15625,-15454,-15448,-15436,-15435,-15419,-15416,-15408,-15394,
                      -15385,-15377,-15375,-15369,-15363,-15362,-15183,-15180,-15165,-15158,-15153,-15150,
                      -15149,-15144,-15143,-15141,-15140,-15139,-15128,-15121,-15119,-15117,-15110,-15109,
                      -14941,-14937,-14933,-14930,-14929,-14928,-14926,-14922,-14921,-14914,-14908,-14902,
                      -14894,-14889,-14882,-14873,-14871,-14857,-14678,-14674,-14670,-14668,-14663,-14654,
                      -14645,-14630,-14594,-14429,-14407,-14399,-14384,-14379,-14368,-14355,-14353,-14345,
                      -14170,-14159,-14151,-14149,-14145,-14140,-14137,-14135,-14125,-14123,-14122,-14112,
                      -14109,-14099,-14097,-14094,-14092,-14090,-14087,-14083,-13917,-13914,-13910,-13907,
                      -13906,-13905,-13896,-13894,-13878,-13870,-13859,-13847,-13831,-13658,-13611,-13601,
                      -13406,-13404,-13400,-13398,-13395,-13391,-13387,-13383,-13367,-13359,-13356,-13343,
                      -13340,-13329,-13326,-13318,-13147,-13138,-13120,-13107,-13096,-13095,-13091,-13076,
                      -13068,-13063,-13060,-12888,-12875,-12871,-12860,-12858,-12852,-12849,-12838,-12831,
                      -12829,-12812,-12802,-12607,-12597,-12594,-12585,-12556,-12359,-12346,-12320,-12300,
                      -12120,-12099,-12089,-12074,-12067,-12058,-12039,-11867,-11861,-11847,-11831,-11798,
                      -11781,-11604,-11589,-11536,-11358,-11340,-11339,-11324,-11303,-11097,-11077,-11067,
                      -11055,-11052,-11045,-11041,-11038,-11024,-11020,-11019,-11018,-11014,-10838,-10832,
                      -10815,-10800,-10790,-10780,-10764,-10587,-10544,-10533,-10519,-10331,-10329,-10328,
                      -10322,-10315,-10309,-10307,-10296,-10281,-10274,-10270,-10262,-10260,-10256,-10254),
                      'a','ai','an','ang','ao','ba','bai','ban','bang','bao','bei','ben',
                      'beng','bi','bian','biao','bie','bin','bing','bo','bu','ca','cai','can',
                      'cang','cao','ce','ceng','cha','chai','chan','chang','chao','che','chen','cheng',
                      'chi','chong','chou','chu','chuai','chuan','chuang','chui','chun','chuo','ci','cong',
                      'cou','cu','cuan','cui','cun','cuo','da','dai','dan','dang','dao','de',
                      'deng','di','dian','diao','die','ding','diu','dong','dou','du','duan','dui',
                      'dun','duo','e','en','er','fa','fan','fang','fei','fen','feng','fo',
                      'fou','fu','ga','gai','gan','gang','gao','ge','gei','gen','geng','gong',
                      'gou','gu','gua','guai','guan','guang','gui','gun','guo','ha','hai','han',
                      'hang','hao','he','hei','hen','heng','hong','hou','hu','hua','huai','huan',
                      'huang','hui','hun','huo','ji','jia','jian','jiang','jiao','jie','jin','jing',
                      'jiong','jiu','ju','juan','jue','jun','ka','kai','kan','kang','kao','ke',
                      'ken','keng','kong','kou','ku','kua','kuai','kuan','kuang','kui','kun','kuo',
                      'la','lai','lan','lang','lao','le','lei','leng','li','lia','lian','liang',
                      'liao','lie','lin','ling','liu','long','lou','lu','lv','luan','lue','lun',
                      'luo','ma','mai','man','mang','mao','me','mei','men','meng','mi','mian',
                      'miao','mie','min','ming','miu','mo','mou','mu','na','nai','nan','nang',
                      'nao','ne','nei','nen','neng','ni','nian','niang','niao','nie','nin','ning',
                      'niu','nong','nu','nv','nuan','nue','nuo','o','ou','pa','pai','pan',
                      'pang','pao','pei','pen','peng','pi','pian','piao','pie','pin','ping','po',
                      'pu','qi','qia','qian','qiang','qiao','qie','qin','qing','qiong','qiu','qu',
                      'quan','que','qun','ran','rang','rao','re','ren','reng','ri','rong','rou',
                      'ru','ruan','rui','run','ruo','sa','sai','san','sang','sao','se','sen',
                      'seng','sha','shai','shan','shang','shao','she','shen','sheng','shi','shou','shu',
                      'shua','shuai','shuan','shuang','shui','shun','shuo','si','song','sou','su','suan',
                      'sui','sun','suo','ta','tai','tan','tang','tao','te','teng','ti','tian',
                      'tiao','tie','ting','tong','tou','tu','tuan','tui','tun','tuo','wa','wai',
                      'wan','wang','wei','wen','weng','wo','wu','xi','xia','xian','xiang','xiao',
                      'xie','xin','xing','xiong','xiu','xu','xuan','xue','xun','ya','yan','yang',
                      'yao','ye','yi','yin','ying','yo','yong','you','yu','yuan','yue','yun',
                      'za','zai','zan','zang','zao','ze','zei','zen','zeng','zha','zhai','zhan',
                      'zhang','zhao','zhe','zhen','zheng','zhi','zhong','zhou','zhu','zhua','zhuai','zhuan',
                      'zhuang','zhui','zhun','zhuo','zi','zong','zou','zu','zuan','zui','zun','zuo');
 
            if l_pin_yin_ is null then     -- 非汉字取原字符
               set mypy = concat(mypy,convert(unhex(substring(name, lp, 4)) using gbk));
            else                           -- 汉字取拼音
               set l_pin_yin_ = case flag 
                   when 1 then lower(l_pin_yin_)
                   when 2 then upper(l_pin_yin_)
                   when 3 then concat(upper(substr(l_pin_yin_,1,1)),lower(substr(l_pin_yin_,2)))  
                   else lower(l_pin_yin_)  
               end;
               set mypy = concat(mypy,l_pin_yin_);
            end if;
            set lp = lp + 4;
        else                               -- ASCII字符
            set mypy = concat(mypy,char(cast(ascii(unhex(substring(name, lp, 2))) as unsigned)));
            set lp = lp + 2;
        end if;
    end while;
    return mypy;
end;
//
delimiter ;

测试

mysql> set @s:='123 中文 ......中a ^华b人 c $民 d共[和]国 Good!';
Query OK, 0 rows affected (0.00 sec)
 
mysql> select to_pinyin(@s,3);
+----------------------------------------------------------------+
| to_pinyin(@s,3)                                                |
+----------------------------------------------------------------+
| 123 ZhongWen ......Zhonga ^HuabRen c $Min dGong[He]Guo Good!      |
+----------------------------------------------------------------+
1 row in set (0.00 sec)
相关推荐
C吴新科1 小时前
MySQL入门操作详解
mysql
Ai 编码助手3 小时前
MySQL中distinct与group by之间的性能进行比较
数据库·mysql
白云如幻4 小时前
MySQL排序查询
数据库·mysql
苹果醋34 小时前
Java8->Java19的初步探索
java·运维·spring boot·mysql·nginx
stars_User5 小时前
MySQL数据库面试题(下)
数据库·mysql
Yaml45 小时前
智能化健身房管理:Spring Boot与Vue的创新解决方案
前端·spring boot·后端·mysql·vue·健身房管理
yanwushu5 小时前
Xserver v1.4.2发布,支持自动重载 nginx 配置
mysql·nginx·php·个人开发·composer
蓝眸少年CY6 小时前
MySQL 【流程控制】函数
mysql
掘金-我是哪吒7 小时前
微服务mysql,redis,elasticsearch, kibana,cassandra,mongodb, kafka
redis·mysql·mongodb·elasticsearch·微服务
zmgst8 小时前
canal1.1.7使用canal-adapter进行mysql同步数据
java·数据库·mysql