Mercurial > hg > ywww
diff goodreads/UTFUtil.php @ 6:077b0a0a3e6d
remaining originals according to dependency walk
author | Robert Boland <robert@markup.co.uk> |
---|---|
date | Thu, 16 Feb 2017 22:29:02 +0000 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/goodreads/UTFUtil.php Thu Feb 16 22:29:02 2017 +0000 @@ -0,0 +1,24 @@ +<?PHP +function convert_utf8($str){ + if(!seems_utf8($str)) + return mb_convert_encoding($str, 'UTF-8'); + return $str; +} + +function seems_utf8($Str) { + for ($i=0; $i<strlen($Str); $i++) { + if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb + elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb + elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb + elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb + elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb + elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b + else return false; # Does not match any model + for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ? + if ((++$i == strlen($Str)) || ((ord($Str[$i]) & 0xC0) != 0x80)) + return false; + } + } + return true; +} +?> \ No newline at end of file