要获取汉字首字母的方法有很多,这个我们一般要把汉字分出来然后转换成拼音,然后再利用substr取第一个字母了,下面我网上找到两个实例,各有千秋大家一起来看看吧.
例1,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,代码如下:
- <?php
-
-
-
-
-
-
-
-
-
-
- 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;
-
-
-
-
-
-
- public function __construct( $charset = 'utf-8' )
- {
- $this->_charset = $charset;
- }
-
-
-
-
-
-
-
-
- private function _msubstr ($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;
- }
-
-
-
-
-
-
- private function _cutWord( $str )
- {
- $words = array();
- while ( $str != "" )
- {
- if ( $this->_isAscii($str) ) {
- $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;
- }
-
-
-
-
-
-
- private function _isAscii( $char )
- {
- return ( ord( substr($char,0,1) ) < 160 );
- }
-
-
-
-
-
-
- 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( $chars );
- if ( emptyempty($result['no']) ){
- return true;
- }
- return false;
- }
-
-
-
-
-
-
- public function getInitials( $str )
- {
- if ( emptyempty($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) ) {
- $result[] = $word;
- continue;
- }
- $code = ord( substr($word,0,1) ) * 1000 + ord( substr($word,1,1) );
-
- if ( ($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);
- }elseif ( $ascii>=65 && $ascii<=90 ){
- return chr($ascii);
- }elseif ($ascii>=97 && $ascii<=122){
- return chr($ascii-32);
- }else{
- return '-';
- }
- }
-
-
-
-
-
-
-
- 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;
- }
- }
- }
- }
- ?>
例2,取汉字的asc区间然后返回汉字首字母了,代码如下:
- <meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
- <?php
- function getfirstchar($s0){
- $fchar = ord($s0{0});
- if($fchar >= ord("A") and $fchar <= ord("z") )return strtoupper($s0{0});
- $s1 = iconv("UTF-8","gb2312", $s0);
- $s2 = iconv("gb2312","UTF-8", $s1);
- if($s2 == $s0){$s = $s1;}else{$s = $s0;}
- $asc = ord($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 $asc <= -10247) return "Z";
- return null;
- }
-
-
- function pinyin1($zh){
- $ret = "";
- $s1 = iconv("UTF-8","gb2312", $zh);
- $s2 = iconv("gb2312","UTF-8", $s1);
- if($s2 == $zh){$zh = $s1;}
- for($i = 0; $i < strlen($zh); $i++){
- $s1 = substr($zh,$i,1);
- $p = ord($s1);
- if($p > 160){
- $s2 = substr($zh,$i++,2);
- $ret .= getfirstchar($s2);
- }else{
- $ret .= $s1;
- }
- }
- return $ret;
- }
- echo "这是中文字符串<br/>";
- echo pinyin1('这是中文字符串');
- ?>
|