|
@@ 237-246 (lines=10) @@
|
| 234 |
|
$cc2 = ($c1 & "\x3f") | "\x80"; |
| 235 |
|
$buf .= $cc1 . $cc2; |
| 236 |
|
} |
| 237 |
|
} elseif ($c1 >= "\xe0" & $c1 <= "\xef") { //looks like 3 bytes UTF8 |
| 238 |
|
if ($c2 >= "\x80" && $c2 <= "\xbf" && $c3 >= "\x80" && $c3 <= "\xbf") { //yeah, almost sure it's UTF8 already |
| 239 |
|
$buf .= $c1 . $c2 . $c3; |
| 240 |
|
$i = $i + 2; |
| 241 |
|
} else { //not valid UTF8. Convert it. |
| 242 |
|
$cc1 = (chr(ord($c1) / 64) | "\xc0"); |
| 243 |
|
$cc2 = ($c1 & "\x3f") | "\x80"; |
| 244 |
|
$buf .= $cc1 . $cc2; |
| 245 |
|
} |
| 246 |
|
} elseif ($c1 >= "\xf0" & $c1 <= "\xf7") { //looks like 4 bytes UTF8 |
| 247 |
|
if ($c2 >= "\x80" && $c2 <= "\xbf" && $c3 >= "\x80" && $c3 <= "\xbf" && $c4 >= "\x80" && $c4 <= "\xbf") { //yeah, almost sure it's UTF8 already |
| 248 |
|
$buf .= $c1 . $c2 . $c3; |
| 249 |
|
$i = $i + 2; |
|
@@ 247-254 (lines=8) @@
|
| 244 |
|
$buf .= $cc1 . $cc2; |
| 245 |
|
} |
| 246 |
|
} elseif ($c1 >= "\xf0" & $c1 <= "\xf7") { //looks like 4 bytes UTF8 |
| 247 |
|
if ($c2 >= "\x80" && $c2 <= "\xbf" && $c3 >= "\x80" && $c3 <= "\xbf" && $c4 >= "\x80" && $c4 <= "\xbf") { //yeah, almost sure it's UTF8 already |
| 248 |
|
$buf .= $c1 . $c2 . $c3; |
| 249 |
|
$i = $i + 2; |
| 250 |
|
} else { //not valid UTF8. Convert it. |
| 251 |
|
$cc1 = (chr(ord($c1) / 64) | "\xc0"); |
| 252 |
|
$cc2 = ($c1 & "\x3f") | "\x80"; |
| 253 |
|
$buf .= $cc1 . $cc2; |
| 254 |
|
} |
| 255 |
|
} else { //doesn't look like UTF8, but should be converted |
| 256 |
|
$cc1 = (chr(ord($c1) / 64) | "\xc0"); |
| 257 |
|
$cc2 = (($c1 & "\x3f") | "\x80"); |
kakserpom /
phpdaemon
