当前位置:首页 > PHP教程 > PHP常见问题

php获取汉字首字母的函数

网上的方法有不少,都是一样的原理,按照需求,做了一下版本的class类文件,主要功能是:功能明确,易于修改维护和扩展; 英文的字串:不变返回(包括数字);中文字符串:返回拼音首字符; 中英混合串: 返回拼音首字符和英文。该算法采用了二分法查找,修复了之前字母z读取成y的错误。好东西要收藏,故在此留下印记,以供后人考证!

复制代码 代码如下:

<?php
 /**
* modified by http://iulog.com @ 2013-05-07
* 修复二分法查找方法
* 汉字拼音首字母工具类
*  注: 英文的字串:不变返回(包括数字)    eg .abc123 => abc123
*      中文字符串:返回拼音首字符        eg. 测试字符串 => cszfc
*      中英混合串: 返回拼音首字符和英文   eg. 我i我j => wiwj
*  eg.
*  $py = new str2py();
*  $result = $py->getinitials('啊吧才的饿飞就好i就看了吗你哦平去人是他uv我想一在');
*/
class str2py
{
    private $_pinyins = array(
        176161 => 'a',
        176197 => 'b',
        178193 => 'c',
        180238 => 'd',
        182234 => 'e',
        183162 => 'f',
        184193 => 'g',
        185254 => 'h',
        187247 => 'j',
        191166 => 'k',
        192172 => 'l',
        194232 => 'm',
        196195 => 'n',
        197182 => 'o',
        197190 => 'p',
        198218 => 'q',
        200187 => 'r',
        200246 => 's',
        203250 => 't',
        205218 => 'w',
        206244 => 'x',
        209185 => 'y',
        212209 => 'z',
    );
    private $_charset = null;
    /**
     * 构造函数, 指定需要的编码 default: utf-8
     * 支持utf-8, gb2312
     *
     * @param unknown_type $charset
     */
    public function __construct( $charset = 'utf-8' )
    {
        $this->_charset    = $charset;
    }
    /**
     * 中文字符串 substr
     *
     * @param string $str
     * @param int    $start
     * @param int    $len
     * @return string
     */
    private function _msubstr ($str, $start, $len)
    {
        $start  = $start * 2;
        $len    = $len * 2;
        $strlen = strlen($str);
        $result = '';
        for ( $i = 0; $i < $strlen; $i++ ) {
            if ( $i >= $start && $i < ($start + $len) ) {
                if ( ord(substr($str, $i, 1)) > 129 ) $result .= substr($str, $i, 2);
                else $result .= substr($str, $i, 1);
            }
            if ( ord(substr($str, $i, 1)) > 129 ) $i++;
        }
        return $result;
    }
    /**
     * 字符串切分为数组 (汉字或者一个字符为单位)
     *
     * @param string $str
     * @return array
     */
    private function _cutword( $str )
    {
        $words = array();
         while ( $str != "" )
         {
            if ( $this->_isascii($str) ) {/*非中文*/
                $words[] = $str[0];
                $str = substr( $str, strlen($str[0]) );
            }else{
                $word = $this->_msubstr( $str, 0, 1 );
                $words[] = $word;
                $str = substr( $str, strlen($word) );
            }
         }
         return $words;
    }
    /**
     * 判断字符是否是ascii字符
     *
     * @param string $char
     * @return bool
     */
    private function _isascii( $char )
    {
        return ( ord( substr($char,0,1) ) < 160 );
    }
    /**
     * 判断字符串前3个字符是否是ascii字符
     *
     * @param string $str
     * @return bool
     */
    private function _isasciis( $str )
    {
        $len = strlen($str) >= 3 ? 3: 2;
        $chars = array();
        for( $i = 1; $i < $len -1; $i++ ){
            $chars[] = $this->_isascii( $str[$i] ) ? 'yes':'no';
        }
        $result = array_count_values( $chars );
        if ( empty($result['no']) ){
            return true;
        }
        return false;
    }
    /**
     * 获取中文字串的拼音首字符
     *
     * @param string $str
     * @return string
     */
    public function getinitials( $str )
    {
        if ( empty($str) ) return '';
        if ( $this->_isascii($str[0]) && $this->_isasciis( $str )){
            return $str;
        }
        $result = array();
        if ( $this->_charset == 'utf-8' ){
            $str = iconv( 'utf-8', 'gb2312', $str );
        }
        $words = $this->_cutword( $str );
        foreach ( $words as $word )
        {
            if ( $this->_isascii($word) ) {/*非中文*/
                $result[] = $word;
                continue;
            }
            $code = ord( substr($word,0,1) ) * 1000 + ord( substr($word,1,1) );
            /*获取拼音首字母a--z*/
            if ( ($i = $this->_search($code)) != -1 ){
                $result[] = $this->_pinyins[$i];
            }
        }
        return strtoupper(implode('',$result));
    }
    private function _getchar( $ascii )
    {
        if ( $ascii >= 48 && $ascii <= 57){
            return chr($ascii);  /*数字*/
        }elseif ( $ascii>=65 && $ascii<=90 ){
            return chr($ascii);   /* a--z*/
        }elseif ($ascii>=97 && $ascii<=122){
            return chr($ascii-32); /* a--z*/
        }else{
            return '-'; /*其他*/
        }
    }

    /**
     * 查找需要的汉字内码(gb2312) 对应的拼音字符( 二分法 )
     *
     * @param int $code
     * @return int
     */
    private function _search( $code )
    {
        $data = array_keys($this->_pinyins);
        $lower = 0;
        $upper = sizeof($data)-1;
  $middle = (int) round(($lower + $upper) / 2);
        if ( $code < $data[0] ) return -1;
        for (;;) {
            if ( $lower > $upper ){
                return $data[$lower-1];
            }
            $tmp = (int) round(($lower + $upper) / 2);
            if ( !isset($data[$tmp]) ){
    return $data[$middle];
            }else{
    $middle = $tmp;
   }
            if ( $data[$middle] < $code ){
                $lower = (int)$middle + 1;
            }else if ( $data[$middle] == $code ) {
                return $data[$middle];
            }else{
                $upper = (int)$middle - 1;
            }
        }
    }
}
?>



【说明】本文章由站长整理发布,文章内容不代表本站观点,如文中有侵权行为,请与本站客服联系(QQ:)!