用PHP提取中英文词语以及数字的首字母的方法介绍

Share on:

最近项目有个需求,在一个中英文(包括阿拉伯数字0-9)的海量词库中,提取每一个词语的首字母:

gannicus——>G

自由自在——>Z

2B——>E

傻X——>S

 

 

function get_first_char($string){
	$s=iconv('UTF-8','gb2312', $string);
	if (ord($string)>128) { //汉字开头
		$asc=ord($s{0})*256+ord($s{1})-65536;
		if($asc>=-20319 and $asc<=-20284)return "A"; if($asc>=-20283 and $asc<=-19776)return "B"; if($asc>=-19775 and $asc<=-19219)return "C"; if($asc>=-19218 and $asc<=-18711)return "D"; if($asc>=-18710 and $asc<=-18527)return "E"; if($asc>=-18526 and $asc<=-18240)return "F"; if($asc>=-18239 and $asc<=-17923)return "G"; if($asc>=-17922 and $asc<=-17418)return "I"; if($asc>=-17417 and $asc<=-16475)return "J"; if($asc>=-16474 and $asc<=-16213)return "K"; if($asc>=-16212 and $asc<=-15641)return "L"; if($asc>=-15640 and $asc<=-15166)return "M"; if($asc>=-15165 and $asc<=-14923)return "N"; if($asc>=-14922 and $asc<=-14915)return "O"; if($asc>=-14914 and $asc<=-14631)return "P"; if($asc>=-14630 and $asc<=-14150)return "Q"; if($asc>=-14149 and $asc<=-14091)return "R"; if($asc>=-14090 and $asc<=-13319)return "S"; if($asc>=-13318 and $asc<=-12839)return "T"; if($asc>=-12838 and $asc<=-12557)return "W"; if($asc>=-12556 and $asc<=-11848)return "X"; if($asc>=-11847 and $asc<=-11056)return "Y"; if($asc>=-11055 and $asc<=-10247)return "Z"; }else if(ord($s)>=48 and ord($s)<=57){ //数字开头 switch(iconv_substr($s,0,1,'utf-8')) { case 1:return "Y"; case 2:return "E"; case 3:return "S"; case 4:return "S"; case 5:return "W"; case 6:return "L"; case 7:return "Q"; case 8:return "B"; case 9:return "J"; case 0:return "L"; } }else if(ord($s)>=65 and ord($s)<=90){ //大写英文开头 return substr($s,0,1); }else if(ord($s)>=97 and ord($s)<=122){ //小写英文开头
		return strtoupper(substr($s,0,1));
	} else {
		return iconv_substr($s0,0,1,'utf-8');//中英混合的词语,不适合上面的各种情况,因此直接提取首个字符即可
	}

}
闽ICP备12003472号-7