function filterUtf8($str) { /*utf8 编码表: * Unicode符号范围 | UTF-8编码方式 * u0000 0000 - u0000 007F | 0xxxxxxx * u0000 0080 - u0000 07FF | 110xxxxx 10xxxxxx * u0000 0800 - u0000 FFFF | 1110xxxx 10xxxxxx 10xxxxxx * */ $re = ''; $str = str_split(bin2hex($str), 2); $mo = 1<<7; $mo2 = $mo | (1 << 6); $mo3 = $mo2 | (1 << 5); //三个字节 $mo4 = $mo3 | (1 << 4); //四个字节 $mo5 = $mo4 | (1 << 3); //五个字节 $mo6 = $mo5 | (1 << 2); //六个字节 for ($i = 0; $i < count($str); $i++) { if ((hexdec($str[$i]) & ($mo)) == 0) { $re .= chr(hexdec($str[$i])); continue; } //4字节 及其以上舍去 if ((hexdec($str[$i]) & ($mo6) ) == $mo6) { $i = $i +5; continue; } if ((hexdec($str[$i]) & ($mo5) ) == $mo5) { $i = $i +4; continue; } if ((hexdec($str[$i]) & ($mo4) ) == $mo4) { $i = $i +3; continue; } if ((hexdec($str[$i]) & ($mo3) ) == $mo3 ) { $i = $i +2; if (((hexdec($str[$i]) & ($mo) ) == $mo) && ((hexdec($str[$i - 1]) & ($mo) ) == $mo) ) { $r = chr(hexdec($str[$i - 2])). chr(hexdec($str[$i - 1])). chr(hexdec($str[$i])); $re .= $r; } continue; } if ((hexdec($str[$i]) & ($mo2) ) == $mo2 ) { $i = $i +1; if ((hexdec($str[$i]) & ($mo) ) == $mo) { $re .= chr(hexdec($str[$i - 1])) . chr(hexdec($str[$i])); } continue; } } return $re; }
The above introduces the filtering of characters exceeding three bytes in utf8 characters, or non-utf8 characters, including the content. I hope it will be helpful to friends who are interested in PHP tutorials.