|
@@ 642-647 (lines=6) @@
|
| 639 |
|
$utf8 .= $chrs{$c}; |
| 640 |
|
break; |
| 641 |
|
|
| 642 |
|
case ($ord_chrs_c & 0xE0) == 0xC0: |
| 643 |
|
// characters U-00000080 - U-000007FF, mask 110XXXXX |
| 644 |
|
//see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8 |
| 645 |
|
$utf8 .= substr($chrs, $c, 2); |
| 646 |
|
++$c; |
| 647 |
|
break; |
| 648 |
|
|
| 649 |
|
case ($ord_chrs_c & 0xF0) == 0xE0: |
| 650 |
|
// characters U-00000800 - U-0000FFFF, mask 1110XXXX |
|
@@ 649-654 (lines=6) @@
|
| 646 |
|
++$c; |
| 647 |
|
break; |
| 648 |
|
|
| 649 |
|
case ($ord_chrs_c & 0xF0) == 0xE0: |
| 650 |
|
// characters U-00000800 - U-0000FFFF, mask 1110XXXX |
| 651 |
|
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8 |
| 652 |
|
$utf8 .= substr($chrs, $c, 3); |
| 653 |
|
$c += 2; |
| 654 |
|
break; |
| 655 |
|
|
| 656 |
|
case ($ord_chrs_c & 0xF8) == 0xF0: |
| 657 |
|
// characters U-00010000 - U-001FFFFF, mask 11110XXX |
|
@@ 656-661 (lines=6) @@
|
| 653 |
|
$c += 2; |
| 654 |
|
break; |
| 655 |
|
|
| 656 |
|
case ($ord_chrs_c & 0xF8) == 0xF0: |
| 657 |
|
// characters U-00010000 - U-001FFFFF, mask 11110XXX |
| 658 |
|
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8 |
| 659 |
|
$utf8 .= substr($chrs, $c, 4); |
| 660 |
|
$c += 3; |
| 661 |
|
break; |
| 662 |
|
|
| 663 |
|
case ($ord_chrs_c & 0xFC) == 0xF8: |
| 664 |
|
// characters U-00200000 - U-03FFFFFF, mask 111110XX |
|
@@ 663-668 (lines=6) @@
|
| 660 |
|
$c += 3; |
| 661 |
|
break; |
| 662 |
|
|
| 663 |
|
case ($ord_chrs_c & 0xFC) == 0xF8: |
| 664 |
|
// characters U-00200000 - U-03FFFFFF, mask 111110XX |
| 665 |
|
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8 |
| 666 |
|
$utf8 .= substr($chrs, $c, 5); |
| 667 |
|
$c += 4; |
| 668 |
|
break; |
| 669 |
|
|
| 670 |
|
case ($ord_chrs_c & 0xFE) == 0xFC: |
| 671 |
|
// characters U-04000000 - U-7FFFFFFF, mask 1111110X |
|
@@ 670-675 (lines=6) @@
|
| 667 |
|
$c += 4; |
| 668 |
|
break; |
| 669 |
|
|
| 670 |
|
case ($ord_chrs_c & 0xFE) == 0xFC: |
| 671 |
|
// characters U-04000000 - U-7FFFFFFF, mask 1111110X |
| 672 |
|
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8 |
| 673 |
|
$utf8 .= substr($chrs, $c, 6); |
| 674 |
|
$c += 5; |
| 675 |
|
break; |
| 676 |
|
|
| 677 |
|
} |
| 678 |
|
|