字符截取

 1     /**
 2  * 字符截取 支持UTF8/GBK
 3  * @param $string
 4  * @param $length
 5  * @param $dot
 6  */
 7 public static function str_cut($string, $length, $dot = '...') {
 8     $strlen = strlen($string);
 9     if($strlen <= $length) return $string;
10     $string = str_replace(array(' ','&nbsp;', '&amp;', '&quot;', '&#039;', '&ldquo;', '&rdquo;', '&mdash;', '&lt;', '&gt;', '&middot;', '&hellip;'), array('∵',' ', '&', '"', "'", '“', '”', '—', '<', '>', '·', '…'), $string);
11     $strcut = '';
12 
13         $length = intval($length-strlen($dot)-$length/3);
14         $n = $tn = $noc = 0;
15         while($n < strlen($string)) {
16                 $t = ord($string[$n]);
17                 if($t == 9 || $t == 10 || (32 <= $t && $t <= 126)) {
18                         $tn = 1; $n++; $noc++;
19                 } elseif(194 <= $t && $t <= 223) {
20                         $tn = 2; $n += 2; $noc += 2;
21                 } elseif(224 <= $t && $t <= 239) {
22                         $tn = 3; $n += 3; $noc += 2;
23                 } elseif(240 <= $t && $t <= 247) {
24                         $tn = 4; $n += 4; $noc += 2;
25                 } elseif(248 <= $t && $t <= 251) {
26                         $tn = 5; $n += 5; $noc += 2;
27                 } elseif($t == 252 || $t == 253) {
28                         $tn = 6; $n += 6; $noc += 2;
29                 } else {
30                         $n++;
31                 }
32                 if($noc >= $length) {
33                         break;
34                 }
35         }
36         if($noc > $length) {
37                 $n -= $tn;
38         }
39         $strcut = substr($string, 0, $n);
40         $strcut = str_replace(array('∵', '&', '"', "'", '“', '”', '—', '<', '>', '·', '…'), array(' ', '&amp;', '&quot;', '&#039;', '&ldquo;', '&rdquo;', '&mdash;', '&lt;', '&gt;', '&middot;', '&hellip;'), $strcut);
41     return $strcut.$dot;
42 }
43 \\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\方法二
44 
45  /*
46         Utf-8、gb2312都支持的汉字截取函数
47         cut_str(字符串, 截取长度, 开始长度, 编码);
48         编码默认为 utf-8
49         开始长度默认为 0
50     */
51     public static function cut_str($string, $sublen, $start = 0, $code = 'UTF-8')
52     {
53             if($code == 'UTF-8')
54             {
55                     $pa ="/[x01-x7f]|[xc2-xdf][x80-xbf]|xe0[xa0-xbf][x80-xbf]|[xe1-xef][x80-xbf][x80-xbf]|xf0[x90-xbf][x80-xbf][x80-xbf]|[xf1-xf7][x80-xbf][x80-xbf][x80-xbf]/";
56                     preg_match_all($pa, $string, $t_string); 
57 
58                     if(count($t_string[0]) - $start > $sublen) 
59                     {
60                             return join('', array_slice($t_string[0], $start, $sublen))."...";
61                     }
62                     return join('', array_slice($t_string[0], $start, $sublen));
63             }
64             else
65             {
66                     $start = $start*2;
67                     $sublen = $sublen*2;
68                     $strlen = strlen($string);
69                     $tmpstr = ''; 
70                     for($i=0; $i<$strlen; $i++)
71                     {
72                             if($i>=$start && $i<($start+$sublen))
73                             {
74                                     if(ord(substr($string, $i, 1))>129)
75                                     {
76                                             $tmpstr.= substr($string, $i, 2);
77                                     }
78                                     else
79                                     {
80                                             $tmpstr.= substr($string, $i, 1);
81                                     }
82                             }
83                             if(ord(substr($string, $i, 1))>129) 
84                             {
85                                     $i++;
86                             }
87                     }
88                     if(strlen($tmpstr)<$strlen ) $tmpstr.= "...";
89                     return $tmpstr;
90             }
91     }
92     
93     
94     
95     
96     
97     
98