|
@@ 582-587 (lines=6) @@
|
| 579 |
|
$utf8 .= $chrs{$c}; |
| 580 |
|
break; |
| 581 |
|
|
| 582 |
|
case ($ord_chrs_c & 0xE0) == 0xC0: |
| 583 |
|
// characters U-00000080 - U-000007FF, mask 110XXXXX |
| 584 |
|
//see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8 |
| 585 |
|
$utf8 .= substr($chrs, $c, 2); |
| 586 |
|
++$c; |
| 587 |
|
break; |
| 588 |
|
|
| 589 |
|
case ($ord_chrs_c & 0xF0) == 0xE0: |
| 590 |
|
// characters U-00000800 - U-0000FFFF, mask 1110XXXX |
|
@@ 589-594 (lines=6) @@
|
| 586 |
|
++$c; |
| 587 |
|
break; |
| 588 |
|
|
| 589 |
|
case ($ord_chrs_c & 0xF0) == 0xE0: |
| 590 |
|
// characters U-00000800 - U-0000FFFF, mask 1110XXXX |
| 591 |
|
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8 |
| 592 |
|
$utf8 .= substr($chrs, $c, 3); |
| 593 |
|
$c += 2; |
| 594 |
|
break; |
| 595 |
|
|
| 596 |
|
case ($ord_chrs_c & 0xF8) == 0xF0: |
| 597 |
|
// characters U-00010000 - U-001FFFFF, mask 11110XXX |
|
@@ 596-601 (lines=6) @@
|
| 593 |
|
$c += 2; |
| 594 |
|
break; |
| 595 |
|
|
| 596 |
|
case ($ord_chrs_c & 0xF8) == 0xF0: |
| 597 |
|
// characters U-00010000 - U-001FFFFF, mask 11110XXX |
| 598 |
|
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8 |
| 599 |
|
$utf8 .= substr($chrs, $c, 4); |
| 600 |
|
$c += 3; |
| 601 |
|
break; |
| 602 |
|
|
| 603 |
|
case ($ord_chrs_c & 0xFC) == 0xF8: |
| 604 |
|
// characters U-00200000 - U-03FFFFFF, mask 111110XX |
|
@@ 603-608 (lines=6) @@
|
| 600 |
|
$c += 3; |
| 601 |
|
break; |
| 602 |
|
|
| 603 |
|
case ($ord_chrs_c & 0xFC) == 0xF8: |
| 604 |
|
// characters U-00200000 - U-03FFFFFF, mask 111110XX |
| 605 |
|
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8 |
| 606 |
|
$utf8 .= substr($chrs, $c, 5); |
| 607 |
|
$c += 4; |
| 608 |
|
break; |
| 609 |
|
|
| 610 |
|
case ($ord_chrs_c & 0xFE) == 0xFC: |
| 611 |
|
// characters U-04000000 - U-7FFFFFFF, mask 1111110X |
|
@@ 610-615 (lines=6) @@
|
| 607 |
|
$c += 4; |
| 608 |
|
break; |
| 609 |
|
|
| 610 |
|
case ($ord_chrs_c & 0xFE) == 0xFC: |
| 611 |
|
// characters U-04000000 - U-7FFFFFFF, mask 1111110X |
| 612 |
|
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8 |
| 613 |
|
$utf8 .= substr($chrs, $c, 6); |
| 614 |
|
$c += 5; |
| 615 |
|
break; |
| 616 |
|
|
| 617 |
|
} |
| 618 |
|
} |