PHP calculates Chinese string lengths, and functions to intercept Chinese strings

Header (' Content-type:text/html;charset=utf-8 '); /** * Statistics Chinese string length function * @param $str string to calculate the length * @param $type calculated length type, 0 (default) means one character in Chinese, 1 for a Chinese figure of two characters * @http://bbs.it-home.org * */ function Abslength ($STR) { if (empty ($STR)) { return 0; } if (function_exists (' Mb_strlen ')) { Return Mb_strlen ($str, ' utf-8 '); } else { Preg_match_all ("/./u", $str, $ar); return count ($ar [0]); } } $STR = ' Scripting Academy welcome everyone, Ye!. '; $len = Abslength ($STR); Var_dump ($len); Return 12 $len = Abslength ($str, ' 1 '); Echo ' '. $len; return 22 /* Utf-8 code to intercept Chinese strings, parameters can refer to the SUBSTR function @param $str the string to intercept @param $start start position to intercept, negative number is reverse intercept @param $end the length to be intercepted */ function Utf8_substr ($str, $start =0) { if (empty ($STR)) { return false; } if (function_exists (' mb_substr ')) { if (Func_num_args () >= 3) { $end = Func_get_arg (2); Return Mb_substr ($str, $start, $end, ' utf-8 '); } else { Mb_internal_encoding ("UTF-8"); Return Mb_substr ($str, $start); } } else { $null = ""; Preg_match_all ("/./u", $str, $ar); if (Func_num_args () >= 3) { $end = Func_get_arg (2); Return join ($null, array_slice ($ar [0], $start, $end)); } else { Return join ($null, array_slice ($ar [0], $start)); } } } $str 2 = ' wo to intercept Zhongwen '; Echo ' '; Echo utf8_substr ($str 2,0,-4); Return wo to intercept Zhon ?> Copy Code 2, support Gb2312,gbk,utf-8,big5 Chinese interception method /* * Chinese interception, support Gb2312,gbk,utf-8,big5 * bbs.it-home.org * @param string $str the string to intercept * @param int $start intercept start position * @param int $length intercept length * @param string $charset UTF-8|GB2312|GBK|BIG5 encoding * @param $suffix whether to add suffix */ Public Function Csubstr ($STR, $start =0, $length, $charset = "Utf-8", $suffix =true) { if (function_exists ("Mb_substr")) { if (Mb_strlen ($str, $charset) <= $length) return $str; $slice = Mb_substr ($str, $start, $length, $charset); } Else { $re [' utf-8 '] = "/[\x01-\x7f]| [\XC2-\XDF] [\x80-\xbf]| [\xe0-\xef] [\X80-\XBF] {2}| [\xf0-\xff] [\X80-\XBF] {3}/"; $re [' gb2312 '] = "/[\x01-\x7f]| [\xb0-\xf7] [\xa0-\xfe]/]; $re [' gbk '] = "/[\x01-\x7f]| [\x81-\xfe] [\x40-\xfe]/]; $re [' big5 '] = "/[\x01-\x7f]| [\x81-\xfe] ([\x40-\x7e]|\xa1-\xfe]) /"; Preg_match_all ($re [$charset], $STR, $match); if (count ($match [0]) <= $length) return $str; $slice = Join ("", Array_slice ($match [0], $start, $length)); } if ($suffix) return $slice. " ..."; return $slice; } ?> Copy Code

