note 71814 added to function.utf8-encode

/* Every function seen so far is incomplete or resource consumpting. Here are two -- integer 2 utf sequence (i3u) and utf sequence to integer (u3i). Below is a code snippet that checks well behavior at the range boundaries. Someday they might be hardcoded into PHP... */ function i3u($i) { // returns UCS-16 or UCS-32 to UTF-8 from an integer $i=(int)$i; // integer? if ($i<0) return false; // positive? if ($i<=0x7f) return chr($i); // range 0 if (($i & 0x7fffffff) <> $i) return '?'; // 31 bit? if ($i<=0x7ff) return chr(0xc0 | ($i >> 6)) . chr(0x80 | ($i & 0x3f)); if ($i<=0xffff) return chr(0xe0 | ($i >> 12)) . chr(0x80 | ($i >> 6) & 0x3f) . chr(0x80 | $i & 0x3f); if ($i<=0x1fffff) return chr(0xf0 | ($i >> 18)) . chr(0x80 | ($i >> 12) & 0x3f) . chr(0x80 | ($i >> 6) & 0x3f) . chr(0x80 | $i & 0x3f); if ($i<=0x3ffffff) return chr(0xf8 | ($i >> 24)) . chr(0x80 | ($i >> 18) & 0x3f) . chr(0x80 | ($i >> 12) & 0x3f) . chr(0x80 | ($i >> 6) & 0x3f) . chr(0x80 | $i & 0x3f); return chr(0xfc | ($i >> 30)) . chr(0x80 | ($i >> 24) & 0x3f) . chr(0x80 | ($i >> 18) & 0x3f) . chr(0x80 | ($i >> 12) & 0x3f) . chr(0x80 | ($i >> 6) & 0x3f) . chr(0x80 | $i & 0x3f); } function u3i($s,$strict=1) { // returns integer on valid UTF-8 seq, NULL on empty, else FALSE // NOT strict: takes only DATA bits, present or not; strict: length and bits checking if ($s=='') return NULL; $l=strlen($s); $o=ord($s{0}); if ($o <= 0x7f && $l==1) return $o; if ($l>6 && $strict) return false; if ($strict) for ($i=1;$i<$l;$i++) if (ord($s{$i}) > 0xbf || ord($s{$i})< 0x80) return false; if ($o < 0xc2) return false; // no-go even if strict=0 if ($o <= 0xdf && ($l=2 && $strict)) return (($o & 0x1f) << 6 | (ord($s{1}) & 0x3f)); if ($o <= 0xef && ($l=3 && $strict)) return (($o & 0x0f) << 12 | (ord($s{1}) & 0x3f) << 6 | (ord($s{2}) & 0x3f)); if ($o <= 0xf7 && ($l=4 && $strict)) return (($o & 0x07) << 18 | (ord($s{1}) & 0x3f) << 12 | (ord($s{2}) & 0x3f) << 6 | (ord($s{3}) & 0x3f)); if ($o <= 0xfb && ($l=5 && $strict)) return (($o & 0x03) << 24 | (ord($s{1}) & 0x3f) << 18 | (ord($s{2}) & 0x3f) << 12 | (ord($s{3}) & 0x3f) << 6 | (ord($s{4}) & 0x3f)); if ($o <= 0xfd && ($l=6 && $strict)) return (($o & 0x01) << 30 | (ord($s{1}) & 0x3f) << 24 | (ord($s{2}) & 0x3f) << 18 | (ord($s{3}) & 0x3f) << 12 | (ord($s{4}) & 0x3f) << 6 | (ord($s{5}) & 0x3f)); return false; } // boundary behavior checking $do=array(0x7f,0x7ff,0xffff,0x1fffff,0x3ffffff,0x7fffffff); foreach ($do as $ii) for ($i=$ii;$i<=$ii+1; $i++) { $o=i3u($i); for ($j=0;$j<strlen($o);$j++) print "O[$j]=" . sprintf('%08b',ord($o{$j})) . ", "; print "c=$i, o=[$o].\n"; print "Back: [$o] => [" . u3i($o) . "]\n"; } ---- Server IP: 217.72.76.77 Probable Submitter: 194.165.109.246 ---- Manual Page -- http://www.php.net/manual/en/function.utf8-encode.php Edit -- https://master.php.net/note/edit/71814 Del: integrated -- https://master.php.net/note/delete/71814/integrated Del: useless -- https://master.php.net/note/delete/71814/useless Del: bad code -- https://master.php.net/note/delete/71814/bad+code Del: spam -- https://master.php.net/note/delete/71814/spam Del: non-english -- https://master.php.net/note/delete/71814/non-english Del: in docs -- https://master.php.net/note/delete/71814/in+docs Del: other reasons-- https://master.php.net/note/delete/71814 Reject -- https://master.php.net/note/reject/71814 Search -- https://master.php.net/manage/user-notes.php