Mysql按汉语拼音首字母查询数据

Mysql按汉语拼音首字母查询数据,第1张

网络上类似的代码大多只能在gb2312编码下使用,下面这个类同时能在utf-8编码下将汉字转换为拼音,具体的代码和用法如下:

<?php

function Pinyin($_String, $_Code='gb2312')

{

$_DataKey = "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"

$_DataValue = "-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"

$_TDataKey = explode('|', $_DataKey)

$_TDataValue = explode('|', $_DataValue)

$_Data = (PHP_VERSION>='5.0') ? array_combine($_TDataKey, $_TDataValue) : _Array_Combine($_TDataKey, $_TDataValue)

arsort($_Data)

reset($_Data)

if($_Code != 'gb2312') $_String = _U2_Utf8_Gb($_String)

$_Res = ''

for($i=0$i<strlen($_String)$i++)

{

$_P = ord(substr($_String, $i, 1))

if($_P>160) { $_Q = ord(substr($_String, ++$i, 1))$_P = $_P*256 + $_Q - 65536}

$_Res .= _Pinyin($_P, $_Data)

}

return preg_replace("/[^a-z0-9]*/", '', $_Res)

}

function _Pinyin($_Num, $_Data)

{

if ($_Num>0 &&$_Num<160 ) return chr($_Num)

elseif($_Num<-20319 || $_Num>-10247) return ''

else {

foreach($_Data as $k=>$v){ if($v<=$_Num) break}

return $k

}

}

function _U2_Utf8_Gb($_C)

{

$_String = ''

if($_C <0x80) $_String .= $_C

elseif($_C <0x800)

{

$_String .= chr(0xC0 | $_C>>6)

$_String .= chr(0x80 | $_C &0x3F)

}elseif($_C <0x10000){

$_String .= chr(0xE0 | $_C>>12)

$_String .= chr(0x80 | $_C>>6 &0x3F)

$_String .= chr(0x80 | $_C &0x3F)

} elseif($_C <0x200000) {

$_String .= chr(0xF0 | $_C>>18)

$_String .= chr(0x80 | $_C>>12 &0x3F)

$_String .= chr(0x80 | $_C>>6 &0x3F)

$_String .= chr(0x80 | $_C &0x3F)

}

return iconv('UTF-8', 'GB2312', $_String)

}

function _Array_Combine($_Arr1, $_Arr2)

{

for($i=0$i<count($_Arr1)$i++) $_Res[$_Arr1[$i]] = $_Arr2[$i]

return $_Res

}

//用法:

//第二个参数留空则为gb1232编码

echo Pinyin('中国站长天空')

//第二个参数随意设置则为utf-8编码

echo Pinyin('中国站长天空',1)

?>

新建一个存储过程进行判断

DELIMITER //CREATE DEFINER=`baixiong`@`%` FUNCTION `getFirstCode`(in_string VARCHAR(100)) RETURNS varchar(100) CHARSET utf8DETERMINISTICCOMMENT '获取中文首字母函数'BEGIN#定义临时字符串变量,用于接收函数中传递进来的字符串值,这里是in_stringDECLARE tmp_str VARCHAR(100) CHARSET gbk DEFAULT '' #定义临时字符串变量,用于存放函数中传递进来的字符串值的第一个字符DECLARE tmp_char VARCHAR(2) CHARSET gbk DEFAULT ''#tmp_str的长度DECLARE tmp_loc SMALLINT DEFAULT 0#初始化,将in_string赋给tmp_strSET tmp_str = in_string#获取tmp_str最左端的首个字符,注意这里是获取首个字符,该字符可能是汉字,也可能不是。SET tmp_char = LEFT(tmp_str,1)#获取字符的编码范围的位置,为了确认汉字拼音首字母是那一个SET tmp_loc=INTERVAL(CONV(HEX(tmp_char),16,10),0xB0A1,0xB0C5,0xB2C1,0xB4EE,0xB6EA,0xB7A2,0xB8C1,0xB9FE,0xBBF7,0xBFA6,0xC0AC,0xC2E8,0xC4C3,0xC5B6,0xC5BE,0xC6DA,0xC8BB,0xC8F6,0xCBFA,0xCDDA ,0xCEF4,0xD1B9,0xD4D1)#判断左端首个字符是多字节还是单字节字符,要是多字节则认为是汉字且作以下拼音获取,要是单字节则不处理。如果是多字节字符但是不在对应的编码范围之内,即对应的不是大写字母则也不做处理,这样数字或者特殊字符就保持原样了IF (LENGTH(tmp_char)>1 AND tmp_loc>0 AND tmp_loc<24) THENSELECT ELT(tmp_loc,'A','B','C','D','E','F','G','H','J','K','L','M','N','O','P','Q','R','S','T','W','X','Y','Z') INTO tmp_char#获得汉字拼音首字符END IFRETURN tmp_char#返回汉字拼音首字符END//DELIMITER


欢迎分享,转载请注明来源:内存溢出

原文地址: http://outofmemory.cn/zaji/6111209.html

(0)
打赏 微信扫一扫 微信扫一扫 支付宝扫一扫 支付宝扫一扫
上一篇 2023-03-15
下一篇 2023-03-15

发表评论

登录后才能评论

评论列表(0条)

保存