【4858.com】php获取汉字首字母的函数,php获取汉语拼音首字母类和函数分享

By admin in 4858.com on 2019年7月21日

一、公司同事整理的类,挺实用的.相信拿出来分享下她不会介意的O(∩_∩)O.可是假如首字母是数字或日文会稍稍题目.

英特网的方法有广大,都以大同小异的法则,遵照须求,做了弹指间本子的class类文件,首要意义是:作用确定,易于修改维护和庞大;
希伯来语的字串:不改变回来(满含数字);粤语字符串:重返拼音首字符; 中国和英国混合串:
重回拼音首字符和菲律宾语。该算法选拔了二分法查找,修复了前头字母Z读取成Y的谬误。好东西要收藏,故在此留下印记,以供后人考证!

代码很简短,这里就很少BB了,大家看注释吧,注释都看不懂的伴儿,求放过PHP!!!

 代码如下

复制代码 代码如下:

复制代码 代码如下:

复制代码 代码如下:

<?php
/**
* 汉字拼音首字母工具类
*  注: 印度语印尼语的字串:不变回来(包蕴数字)    eg .abc123 => abc123
*      粤语字符串:再次回到拼音首字符        eg. 辽宁 => HN
*      中国和英国混合串: 再次回到拼音首字符和韩文   eg. 笔者i笔者j => WIWJ
*  eg.
*  $py = new str2PY();

*  $result = $py->getInitials(‘周杰伦’);
*
*  //获取首字母
*  $result = $py->getFirstString(‘abc’);  //A
*  $resutl = $py->getFirstString(“一聚教程”); //y
*
*/

/**
 * Helper_Spell 汉字拼音首字母工具类
 *
 * @category Helper
 * @package  Helper_Spell
 * @author   Lancer <lancer.he@gmail.com>
 * @version  1.0
 * @see      Translation_Big2gb
 */

<?php
 /**
* Modified by @ 2013-05-07
* 修复二分法查找方法
* 汉字拼音首字母工具类
*  注: 波兰语的字串:不改变回来(满含数字)    eg .abc123 => abc123
*      华语字符串:重返拼音首字符        eg. 测量检验字符串 => CSZFC
*      中国和英国混合串: 重返拼音首字符和英语   eg. 笔者i笔者j => WIWJ
*  eg.
*  $py = new str2PY();
*  $result =
$py->getInitials(‘哟吧才的饿飞就好i就看了吧你哦平去人是他uv小编想一在’);
*/
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, 钦点必要的编码 default: utf-8
     * 支持utf-8, gb2312
     *
     * @param unknown_type $charset
     */
    public function __construct( $charset = ‘utf-8’ )
    {
        $this->_charset    = $charset;
    }
    /**
     * 汉语字符串 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 (汉字或然三个字符为单位)
     *
     * @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;
    }
    /**
     * 判别字符是或不是是ascii字符
     *
     * @param string $char
     * @return bool
     */
    private function _isAscii( $char )
    {
        return ( ord( substr($char,0,1) ) < 160 );
    }
    /**
     * 判别字符串前3个字符是不是是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;
    }
    /**
     * 获取普通话字串的拼音首字符
     *
     * @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*/
        }
    }

<?php
/**
* 汉字拼音首字母工具类
*  注: 乌克兰(Ukraine)语的字串:不改变回来(包罗数字)    eg .abc123 => abc123
*      汉语字符串:重临拼音首字符        eg. 测量试验字符串 => CSZFC
*      中国和英国混合串: 再次回到拼音首字符和希伯来语   eg. 笔者i笔者j => WIWJ
*  eg.
*  $py = new str2PY();

*  $result = $py->getInitials(‘周杰伦’);
*
*  //获取首字母
*  $result = $py->getFirstString(‘abc’);  //A
*  $resutl = $py->getFirstString(“周杰伦”); //Z
*
*/
class str2py
{
    private $_pinyins = array(
=> ‘A’,
=> ‘B’,
=> ‘C’,
=> ‘D’,
=> ‘E’,
=> ‘F’,
=> ‘G’,
=> ‘H’,
=> ‘J’,
=> ‘K’,
=> ‘L’,
=> ‘M’,
=> ‘N’,
=> ‘O’,
=> ‘P’,
=> ‘Q’,
=> ‘R’,
=> ‘S’,
=> ‘T’,
=> ‘W’,
=> ‘X’,
=> ‘Y’,
=> ‘Z’,
    );
    private $_charset = null;
    /**
     * 构造函数, 钦点需求的编码 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 (汉字只怕叁个字符为单位)
     *
     * @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;
【4858.com】php获取汉字首字母的函数,php获取汉语拼音首字母类和函数分享。                $str = substr($str, strlen($word));
            }
        }
        return $words;
    }
    /**
     * 决断字符是还是不是是ascii字符
     *
     * @param string $char
     * @return bool
     */
    private function _isAscii($char)
    {
        return ( ord(substr($char, 0, 1)) < 160 );
    }
    /**
     * 剖断字符串前3个字符是不是是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));
    }
    /**
     *  20150624 wangtianbao 获取首字母
     *  @param string $str
     *  @return string
     */
    public function getFirstString($str)
    {
        //先把中文转换来字母
        $new_string = $this->getInitials($str);
        if (empty($new_string))
        {
            return ”;
        }
        else
        {
            return strtoupper(substr($new_string, 0, 1));
        }
    }
    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 */
        }
    }
    /**
     * 查找须求的方块字内码(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;
            }
        }
    }
}

class str2py
{

class Helper_Spell {
/**
 * $_pinyins
 * @var array
 * @access private
 */
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’,
    215249 => ‘Z’,
);

    /**
     * 查找须要的汉字内码(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;
            }
        }
    }
}
?>

取汉字首字母算是日前差不离没个品种中都急需选取的功力了,这里给我们推荐的是作用比较高的代码,也是在自身项目中应用的,小朋侪们如开掘难题,还请留言,大家共同提升

    private $_pinyins = array(
=> ‘A’,
=> ‘B’,
=> ‘C’,
=> ‘D’,
=> ‘E’,
=> ‘F’,
=> ‘G’,
=> ‘H’,
=> ‘J’,
=> ‘K’,
=> ‘L’,
=> ‘M’,
=> ‘N’,
=> ‘O’,
=> ‘P’,
=> ‘Q’,
=> ‘R’,
=> ‘S’,
=> ‘T’,
=> ‘W’,
=> ‘X’,
=> ‘Y’,
=> ‘Z’,
    );
    private $_charset = null;

/**
 * $_charset
 * @var string
 * @access private
 */
private $_charset = null;

您只怕感兴趣的文章:

  • php
    得到汉字拼音首字母的函数
  • 应用PHP获取汉字的拼音(全部与首字母)
  • php获取汉字拼音首字母的措施
  • PHP自定义函数获取汉字首字母的不二等秘书籍
  • PHP基于ICU扩大intl神速达成汉字转拼音及按拼音首字母分组排序的办法
  • PHP达成将汉字转换为拼音及获得词语首字母的诀窍
  • 采用PHP获取汉字首字母何况分组排序详解

您恐怕感兴趣的文章:

  • php封装的验证码工具类完整实例
  • PHP常用工具类大全附全体代码下载
  • php达成网页缓存的工具类分享
  • PHP抓取、深入分析国内录像网址的录制音讯工具类
  • php达成分页工具类分享
  • 用C实现PHP扩展 Image_Tool
    图片常用管理工科具类的选取
  • 叁个出色的PHP分页实例代码分享
  • php 分页原理详解
  • 大好美丽的php分页类代码
  • 常用PHP封装分页工具类

    /**
     * 构造函数, 钦定须要的编码 default: utf-8
     * 支持utf-8, gb2312
     *
     * @param unknown_type $charset
     */
    public function __construct($charset = ‘utf-8’)
    {
        $this->_charset = $charset;
    }

/**
 * __construct 构造函数, 钦赐须要的编码 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;
    }

/**
 * getInitialsFirst 重临第四个汉字的拼音
 *
 * @access public
 * @static
 * @param  string $str
 * @return string
 * @example Helper_Spell::getInitialsFirst(‘我的爱’); => w
 */
public static function getInitialsFirst( $str, $charset = ‘utf-8’ ) {
    $chars = array(
        ‘A’,’B’,’C’,’D’,’E’,’F’,
        ‘G’,’H’,’I’,’J’,’K’,’L’,
        ‘M’,’N’,’O’,’P’,’Q’,’R’,
        ‘S’,’T’,’U’,’V’,’W’,’X’,
        ‘Y’,’Z’);

    /**
     * 字符串切分为数组 (汉字恐怕一个字符为单位)
     *
     * @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;
    }

    $string = self::getInitials( $str );
    $length = strlen($string);

    /**
     * 剖断字符是还是不是是ascii字符
     *
     * @param string $char
     * @return bool
     */
    private function _isAscii($char)
    {
        return ( ord(substr($char, 0, 1)) < 160 );
    }

    for($i=0; $i < $length; $i++) {
        if ( in_array( $string{$i}, $chars ) ) {
            return $string{$i};
        }
    }
    return ‘*’;
}

    /**
     * 判定字符串前3个字符是不是是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;
    }

/**
 * getInitials 重回拼音组合
 *
 * @access public
 * @static
 * @param  string $str
 * @return string
 * @example Helper_Spell::getInitials(‘我的爱’); => wda
 */
public static function getInitials( $str, $charset = ‘utf-8’ ) {
    $instance = new Helper_Spell( $charset );
    return $instance->_getInitials( $str );
}

    /**
     * 获取汉语字串的拼音首字符
     *
     * @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));
    }

/**
 * _getInitials 得到中文字串的拼音首字符
 *              注:俄语的字串:不改变回来(满含数字)    eg .abc123 =>
abc123
 *                  普通话字符串:重回拼音首字符        eg. 王小明 =>
WXM
 *                  中国和英国混合串: 重返拼音首字符和法文  eg. 笔者i我j =>
WIWJ
 *
 * @access private
 * @param  string $str
 * @return string
 */
private function _getInitials( $str, $translation=TRUE ){
    if ( empty($str) ) return ”;
    if ( $this->_isAscii($str[0]) && $this->_isAsciis( $str
))
        return $str;

    /**
     *  二〇一五0624 wangtianbao 获取首字母
     *  @param string $str
     *  @return string
     */
    public function getFirstString($str)
    {
        //先把普通话转换来字母
        $new_string = $this->getInitials($str);

    if ( $translation )
        $str = Translation_Big2gb::big2gb( $str );

        if (empty($new_string))
        {
            return ”;
        }
        else
        {
            return strtoupper(substr($new_string, 0, 1));
        }
    }

    $result = array();
    if ( $this->_charset == ‘utf-8’ ){
        //IGNORE很关键,加上那一个即不过ICONV()函数忽略错误,继续实行
        $str = iconv( ‘utf-8’, ‘gbk//IGNORE’, $str );
    }
    $words = $this->_cutWord( $str );

    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 */
        }
    }

    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

    /**
     * 查找须求的汉字内码(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;
            }
        }
    }

        if ( ($i = $this->_search($code)) != -1 ){
            $result[] = $this->_pinyins[$i];
        }
    }
    return strtoupper(implode(”, $result));
}

}

/**
 * _msubstr 得到中文字符串
 *
 * @access private
 * @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;
}

一旦大家感兴趣,有深切学习的主张,能够把它改成生成全拼音。

/**
 * _cutWord  字符串切分为数组 (汉字恐怕多个字符为单位)
 *
 * @access private
 * @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;
}

/**
 * _isAscii 判定字符是或不是是ascii字符
 *
 * @access private
 * @param  string $char
 * @return bool
 */
private function _isAscii( $char ) {
    return ( ord( substr($char,0,1) ) < 160 );
}

 

/**
 * _isAsciis 剖断字符串前3个字符是不是是ascii字符
 *
 * @access private
 * @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;
}

/**
 * _getChar 通过ASC码重临字母大概数字
 *
 * @access private
 * @param  string $ascii
 * @return string
 */
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
    }
}

/**
 * _search 查找要求的方块字内码(gb2312) 对应的拼音字符(二分法)
 *
 * @access private
 * @param int $code
 * @return int
 */
private function _search( $code ) {   
    $data = array_keys($this->_pinyins);

    $lower = 0;
    $upper = sizeof($data)-1;

    // 排除非一流汉字
    if ($code < $data[0] || $code > $data[23]) return -1;

    for (;;) {        
        if ( $lower > $upper ){            
            return $data[$lower-1];
        }
        $middle = (int) round(($lower + $upper) / 2);
        if ( !isset($data[$middle]) ) {         
            return -1;
        }

        if ( $data[$middle] < $code ){
            $lower = (int)$middle + 1;
        } else if ( $data[$middle] == $code ) {          
            return $data[$middle];
        } else {
            $upper = (int)$middle – 1;
        }
    }// end for
}

}

二、用来获取中文的首字母

本条是将汉语转换为拼音的类:charset

复制代码 代码如下:

<?php
/**
 * 汉字转会为拼音,拼音转化为汉字
 *
 */

class charset
{
    private $_code=array(
    array(“a”,’-20319′),
    array(“ai”,’-20317′),
    array(“an”,’-20304′),
    array(“ang”,’-20295′),
    array(“ao”,’-20292′),
    array(“ba”,’-20283′),
    array(“bai”,’-20265′),
    array(“ban”,’-20257′),
    array(“bang”,’-20242′),
    array(“bao”,’-20230′),
    array(“bei”,’-20051′),
    array(“ben”,’-20036′),
    array(“beng”,’-20032′),
    array(“bi”,’-20026′),
    array(“bian”,’-20002′),
    array(“biao”,’-19990′),
    array(“bie”,’-19986′),
    array(“bin”,’-19982′),
    array(“bing”,’-19976′),
    array(“bo”,’-19805′),
    array(“bu”,’-19784′),
    array(“ca”,’-19775′),
    array(“cai”,’-19774′),
    array(“can”,’-19763′),
    array(“cang”,’-19756′),
    array(“cao”,’-19751′),
    array(“ce”,’-19746′),
    array(“ceng”,’-19741′),
    array(“cha”,’-19739′),
    array(“chai”,’-19728′),
    array(“chan”,’-19725′),
    array(“chang”,’-19715′),
    array(“chao”,’-19540′),
    array(“che”,’-19531′),
    array(“chen”,’-19525′),
    array(“cheng”,’-19515′),
    array(“chi”,’-19500′),
    array(“chong”,’-19484′),
    array(“chou”,’-19479′),
    array(“chu”,’-19467′),
    array(“chuai”,’-19289′),
    array(“chuan”,’-19288′),
    array(“chuang”,’-19281′),
    array(“chui”,’-19275′),
    array(“chun”,’-19270′),
    array(“chuo”,’-19263′),
    array(“ci”,’-19261′),
    array(“cong”,’-19249′),
    array(“cou”,’-19243′),
    array(“cu”,’-19242′),
    array(“cuan”,’-19238′),
    array(“cui”,’-19235′),
    array(“cun”,’-19227′),
    array(“cuo”,’-19224′),
    array(“da”,’-19218′),
    array(“dai”,’-19212′),
    array(“dan”,’-19038′),
    array(“dang”,’-19023′),
    array(“dao”,’-19018′),
    array(“de”,’-19006′),
    array(“deng”,’-19003′),
    array(“di”,’-18996′),
    array(“dian”,’-18977′),
    array(“diao”,’-18961′),
    array(“die”,’-18952′),
    array(“ding”,’-18783′),
    array(“diu”,’-18774′),
    array(“dong”,’-18773′),
    array(“dou”,’-18763′),
    array(“du”,’-18756′),
    array(“duan”,’-18741′),
    array(“dui”,’-18735′),
    array(“dun”,’-18731′),
    array(“duo”,’-18722′),
    array(“e”,’-18710′),
    array(“en”,’-18697′),
    array(“er”,’-18696′),
    array(“fa”,’-18526′),
    array(“fan”,’-18518′),
    array(“fang”,’-18501′),
    array(“fei”,’-18490′),
    array(“fen”,’-18478′),
    array(“feng”,’-18463′),
    array(“fo”,’-18448′),
    array(“fou”,’-18447′),
    array(“fu”,’-18446′),
    array(“ga”,’-18239′),
    array(“gai”,’-18237′),
    array(“gan”,’-18231′),
    array(“gang”,’-18220′),
    array(“gao”,’-18211′),
    array(“ge”,’-18201′),
    array(“gei”,’-18184′),
4858.com,    array(“gen”,’-18183′),
    array(“geng”,’-18181′),
    array(“gong”,’-18012′),
    array(“gou”,’-17997′),
    array(“gu”,’-17988′),
    array(“gua”,’-17970′),
    array(“guai”,’-17964′),
    array(“guan”,’-17961′),
    array(“guang”,’-17950′),
    array(“gui”,’-17947′),
    array(“gun”,’-17931′),
    array(“guo”,’-17928′),
    array(“ha”,’-17922′),
    array(“hai”,’-17759′),
    array(“han”,’-17752′),
    array(“hang”,’-17733′),
    array(“hao”,’-17730′),
    array(“he”,’-17721′),
    array(“hei”,’-17703′),
    array(“hen”,’-17701′),
    array(“heng”,’-17697′),
    array(“hong”,’-17692′),
    array(“hou”,’-17683′),
    array(“hu”,’-17676′),
    array(“hua”,’-17496′),
    array(“huai”,’-17487′),
    array(“huan”,’-17482′),
    array(“huang”,’-17468′),
    array(“hui”,’-17454′),
    array(“hun”,’-17433′),
    array(“huo”,’-17427′),
    array(“ji”,’-17417′),
    array(“jia”,’-17202′),
    array(“jian”,’-17185′),
    array(“jiang”,’-16983′),
    array(“jiao”,’-16970′),
    array(“jie”,’-16942′),
    array(“jin”,’-16915′),
    array(“jing”,’-16733′),
    array(“jiong”,’-16708′),
    array(“jiu”,’-16706′),
    array(“ju”,’-16689′),
    array(“juan”,’-16664′),
    array(“jue”,’-16657′),
    array(“jun”,’-16647′),
    array(“ka”,’-16474′),
    array(“kai”,’-16470′),
    array(“kan”,’-16465′),
    array(“kang”,’-16459′),
    array(“kao”,’-16452′),
    array(“ke”,’-16448′),
    array(“ken”,’-16433′),
    array(“keng”,’-16429′),
    array(“kong”,’-16427′),
    array(“kou”,’-16423′),
    array(“ku”,’-16419′),
    array(“kua”,’-16412′),
    array(“kuai”,’-16407′),
    array(“kuan”,’-16403′),
    array(“kuang”,’-16401′),
    array(“kui”,’-16393′),
    array(“kun”,’-16220′),
    array(“kuo”,’-16216′),
    array(“la”,’-16212′),
    array(“lai”,’-16205′),
    array(“lan”,’-16202′),
    array(“lang”,’-16187′),
    array(“lao”,’-16180′),
    array(“le”,’-16171′),
    array(“lei”,’-16169′),
    array(“leng”,’-16158′),
    array(“li”,’-16155′),
    array(“lia”,’-15959′),
    array(“lian”,’-15958′),
    array(“liang”,’-15944′),
    array(“liao”,’-15933′),
    array(“lie”,’-15920′),
    array(“lin”,’-15915′),
    array(“ling”,’-15903′),
    array(“liu”,’-15889′),
    array(“long”,’-15878′),
    array(“lou”,’-15707′),
    array(“lu”,’-15701′),
    array(“lv”,’-15681′),
    array(“luan”,’-15667′),
    array(“lue”,’-15661′),
    array(“lun”,’-15659′),
    array(“luo”,’-15652′),
    array(“ma”,’-15640′),
    array(“mai”,’-15631′),
    array(“man”,’-15625′),
    array(“mang”,’-15454′),
    array(“mao”,’-15448′),
    array(“me”,’-15436′),
    array(“mei”,’-15435′),
    array(“men”,’-15419′),
    array(“meng”,’-15416′),
    array(“mi”,’-15408′),
    array(“mian”,’-15394′),
    array(“miao”,’-15385′),
    array(“mie”,’-15377′),
    array(“min”,’-15375′),
    array(“ming”,’-15369′),
    array(“miu”,’-15363′),
    array(“mo”,’-15362′),
    array(“mou”,’-15183′),
    array(“mu”,’-15180′),
    array(“na”,’-15165′),
    array(“nai”,’-15158′),
    array(“nan”,’-15153′),
    array(“nang”,’-15150′),
    array(“nao”,’-15149′),
    array(“ne”,’-15144′),
    array(“nei”,’-15143′),
    array(“nen”,’-15141′),
    array(“neng”,’-15140′),
    array(“ni”,’-15139′),
    array(“nian”,’-15128′),
    array(“niang”,’-15121′),
    array(“niao”,’-15119′),
    array(“nie”,’-15117′),
    array(“nin”,’-15110′),
    array(“ning”,’-15109′),
    array(“niu”,’-14941′),
    array(“nong”,’-14937′),
    array(“nu”,’-14933′),
    array(“nv”,’-14930′),
    array(“nuan”,’-14929′),
    array(“nue”,’-14928′),
    array(“nuo”,’-14926′),
    array(“o”,’-14922′),
    array(“ou”,’-14921′),
    array(“pa”,’-14914′),
    array(“pai”,’-14908′),
    array(“pan”,’-14902′),
    array(“pang”,’-14894′),
    array(“pao”,’-14889′),
    array(“pei”,’-14882′),
    array(“pen”,’-14873′),
    array(“peng”,’-14871′),
    array(“pi”,’-14857′),
    array(“pian”,’-14678′),
    array(“piao”,’-14674′),
    array(“pie”,’-14670′),
    array(“pin”,’-14668′),
    array(“ping”,’-14663′),
    array(“po”,’-14654′),
    array(“pu”,’-14645′),
    array(“qi”,’-14630′),
    array(“qia”,’-14594′),
    array(“qian”,’-14429′),
    array(“qiang”,’-14407′),
    array(“qiao”,’-14399′),
    array(“qie”,’-14384′),
    array(“qin”,’-14379′),
    array(“qing”,’-14368′),
    array(“qiong”,’-14355′),
    array(“qiu”,’-14353′),
    array(“qu”,’-14345′),
    array(“quan”,’-14170′),
    array(“que”,’-14159′),
    array(“qun”,’-14151′),
    array(“ran”,’-14149′),
    array(“rang”,’-14145′),
    array(“rao”,’-14140′),
    array(“re”,’-14137′),
    array(“ren”,’-14135′),
    array(“reng”,’-14125′),
    array(“ri”,’-14123′),
    array(“rong”,’-14122′),
    array(“rou”,’-14112′),
    array(“ru”,’-14109′),
    array(“ruan”,’-14099′),
    array(“rui”,’-14097′),
    array(“run”,’-14094′),
    array(“ruo”,’-14092′),
    array(“sa”,’-14090′),
    array(“sai”,’-14087′),
    array(“san”,’-14083′),
    array(“sang”,’-13917′),
    array(“sao”,’-13914′),
    array(“se”,’-13910′),
    array(“sen”,’-13907′),
    array(“seng”,’-13906′),
    array(“sha”,’-13905′),
    array(“shai”,’-13896′),
    array(“shan”,’-13894′),
    array(“shang”,’-13878′),
    array(“shao”,’-13870′),
    array(“she”,’-13859′),
    array(“shen”,’-13847′),
    array(“sheng”,’-13831′),
    array(“shi”,’-13658′),
    array(“shou”,’-13611′),
    array(“shu”,’-13601′),
    array(“shua”,’-13406′),
    array(“shuai”,’-13404′),
    array(“shuan”,’-13400′),
    array(“shuang”,’-13398′),
    array(“shui”,’-13395′),
    array(“shun”,’-13391′),
    array(“shuo”,’-13387′),
    array(“si”,’-13383′),
    array(“song”,’-13367′),
    array(“sou”,’-13359′),
    array(“su”,’-13356′),
    array(“suan”,’-13343′),
    array(“sui”,’-13340′),
    array(“sun”,’-13329′),
    array(“suo”,’-13326′),
    array(“ta”,’-13318′),
    array(“tai”,’-13147′),
    array(“tan”,’-13138′),
    array(“tang”,’-13120′),
    array(“tao”,’-13107′),
    array(“te”,’-13096′),
    array(“teng”,’-13095′),
    array(“ti”,’-13091′),
    array(“tian”,’-13076′),
    array(“tiao”,’-13068′),
    array(“tie”,’-13063′),
    array(“ting”,’-13060′),
    array(“tong”,’-12888′),
    array(“tou”,’-12875′),
    array(“tu”,’-12871′),
    array(“tuan”,’-12860′),
    array(“tui”,’-12858′),
    array(“tun”,’-12852′),
    array(“tuo”,’-12849′),
    array(“wa”,’-12838′),
    array(“wai”,’-12831′),
    array(“wan”,’-12829′),
    array(“wang”,’-12812′),
    array(“wei”,’-12802′),
    array(“wen”,’-12607′),
    array(“weng”,’-12597′),
    array(“wo”,’-12594′),
    array(“wu”,’-12585′),
    array(“xi”,’-12556′),
    array(“xia”,’-12359′),
    array(“xian”,’-12346′),
    array(“xiang”,’-12320′),
    array(“xiao”,’-12300′),
    array(“xie”,’-12120′),
    array(“xin”,’-12099′),
    array(“xing”,’-12089′),
    array(“xiong”,’-12074′),
    array(“xiu”,’-12067′),
    array(“xu”,’-12058′),
    array(“xuan”,’-12039′),
    array(“xue”,’-11867′),
    array(“xun”,’-11861′),
    array(“ya”,’-11847′),
    array(“yan”,’-11831′),
    array(“yang”,’-11798′),
    array(“yao”,’-11781′),
    array(“ye”,’-11604′),
    array(“yi”,’-11589′),
    array(“yin”,’-11536′),
    array(“ying”,’-11358′),
    array(“yo”,’-11340′),
    array(“yong”,’-11339′),
    array(“you”,’-11324′),
    array(“yu”,’-11303′),
    array(“yuan”,’-11097′),
    array(“yue”,’-11077′),
    array(“yun”,’-11067′),
    array(“za”,’-11055′),
    array(“zai”,’-11052′),
    array(“zan”,’-11045′),
    array(“zang”,’-11041′),
    array(“zao”,’-11038′),
    array(“ze”,’-11024′),
    array(“zei”,’-11020′),
    array(“zen”,’-11019′),
    array(“zeng”,’-11018′),
    array(“zha”,’-11014′),
    array(“zhai”,’-10838′),
    array(“zhan”,’-10832′),
    array(“zhang”,’-10815′),
    array(“zhao”,’-10800′),
    array(“zhe”,’-10790′),
    array(“zhen”,’-10780′),
    array(“zheng”,’-10764′),
    array(“zhi”,’-10587′),
    array(“zhong”,’-10544′),
    array(“zhou”,’-10533′),
    array(“zhu”,’-10519′),
    array(“zhua”,’-10331′),
    array(“zhuai”,’-10329′),
    array(“zhuan”,’-10328′),
    array(“zhuang”,’-10322′),
    array(“zhui”,’-10315′),
    array(“zhun”,’-10309′),
    array(“zhuo”,’-10307′),
    array(“zi”,’-10296′),
    array(“zong”,’-10281′),
    array(“zou”,’-10274′),
    array(“zu”,’-10270′),
    array(“zuan”,’-10262′),
    array(“zui”,’-10260′),
    array(“zun”,’-10256′),
    array(“zuo”,’-10254′)
    );
    //拼音转化函数
    function PinYin($str){
        $ret=””;
        for($i=0;$i<strlen($str);$i++){
            $p=ord(substr($str,$i,1)); //查看ASCII码
            if($p>160){ //若是是中文,再多截取二个字符
                $q=ord(substr($str,++$i,1));
                $p=$p*256+$q-65536;
            }
            $ret.=$this->convert($p);
        }
        return $ret;
    }

    //转化函数
    function convert($num){
        if($num>0&&$num<160){ //假使不是汉字,直接回到相对字符
            return chr($num);
        }elseif($num<“-20319″||$num>”-10247″){
            return “”;
        }else{ //汉字,查找对应拼音
            for($i=count($this->_code)-1;$i>=0;$i–){
                if($this->_code[$i][1]<=$num)
                break;
            }
            return substr($this->_code[$i][0],0,1);
        }
    }
}

 

 

下边那一个是用来测验代码的:

复制代码 代码如下:

<?php

include_once ‘charset.class.php’;
header(‘Content-type: text/html;charset=utf-8’);

$charset=new charset();
foreach(array(‘武汉’,’中国’,’上海’) as $val){
 echo
iconv(‘gbk’,’utf-8//IGNORE’,strtoupper($charset->PinYin(mb_convert_encoding($val,’gbk’,’utf-8′))));
 echo ‘<br/>’;
}

三、那是网络找到个二个办法,经过测验能够符合规律使用,但对一些生僻字也许新鲜字符会万分.

复制代码 代码如下:

function getFirstCharter($str){
 if(empty($str)){return ”;}
 $fchar=ord($str{0});
 if($fchar>=ord(‘A’)&&$fchar<=ord(‘z’)) return
strtoupper($str{0});
 $s1=iconv(‘UTF-8′,’gb2312’,$str);
 $s2=iconv(‘gb2312′,’UTF-8’,$s1);
 $s=$s2==$str?$s1:$str;
 $asc=ord($s{0})*256+ord($s{1})-65536;
 if($asc>=-20319&&$asc<=-20284) return ‘A’;
 if($asc>=-20283&&$asc<=-19776) return ‘B’;
 if($asc>=-19775&&$asc<=-19219) return ‘C’;
 if($asc>=-19218&&$asc<=-18711) return ‘D’;
 if($asc>=-18710&&$asc<=-18527) return ‘E’;
 if($asc>=-18526&&$asc<=-18240) return ‘F’;
 if($asc>=-18239&&$asc<=-17923) return ‘G’;
 if($asc>=-17922&&$asc<=-17418) return ‘H’;
 if($asc>=-17417&&$asc<=-16475) return ‘J’;
 if($asc>=-16474&&$asc<=-16213) return ‘K’;
 if($asc>=-16212&&$asc<=-15641) return ‘L’;
 if($asc>=-15640&&$asc<=-15166) return ‘M’;
 if($asc>=-15165&&$asc<=-14923) return ‘N’;
 if($asc>=-14922&&$asc<=-14915) return ‘O’;
 if($asc>=-14914&&$asc<=-14631) return ‘P’;
 if($asc>=-14630&&$asc<=-14150) return ‘Q’;
 if($asc>=-14149&&$asc<=-14091) return ‘R’;
 if($asc>=-14090&&$asc<=-13319) return ‘S’;
 if($asc>=-13318&&$asc<=-12839) return ‘T’;
 if($asc>=-12838&&$asc<=-12557) return ‘W’;
 if($asc>=-12556&&$asc<=-11848) return ‘X’;
 if($asc>=-11847&&$asc<=-11056) return ‘Y’;
 if($asc>=-11055&&$asc<=-10247) return ‘Z’;
 return null;

}

您或然感兴趣的稿子:

  • PHP提取汉语首字母
  • php
    得到汉字拼音首字母的函数
  • 用PHP提取中法文词语以及数字的首字母的措施介绍
  • 使用PHP获取汉字的拼音(全体与首字母)
  • php
    粤语字符串首字母的获得函数分享
  • php获取汉字首字母的函数
  • 分享一段PHP制作的中文拼音首字母工具类
  • php实现字符串首字母大写和单词首字母大写的不二秘技
  • php完成字符串首字母转变来大写的法子
  • php获得字符串首字母的点子
  • PHP达成获取中乌Crane语首字母
  • php获取印度语印尼语姓名首字母的措施
  • php获取汉字拼音首字母的不二秘诀

发表评论

电子邮件地址不会被公开。 必填项已用*标注

网站地图xml地图
Copyright @ 2010-2019 美高梅手机版4858 版权所有