254 |
Gdesignation => "\x42", ## F of designation or 0 |
Gdesignation => "\x42", ## F of designation or 0 |
255 |
Ginvoke => 1, |
Ginvoke => 1, |
256 |
}, |
}, |
257 |
|
undef_char => ["\x3F", {type => 'G94', charset => 'B'}], |
258 |
use_revision => 1, ## Output IRR |
use_revision => 1, ## Output IRR |
259 |
}; |
}; |
260 |
\%C; |
\%C; |
572 |
if (defined $t) { |
if (defined $t) { |
573 |
$r .= $t; |
$r .= $t; |
574 |
} else { |
} else { |
575 |
$r .= _i2g ("\x3F", $C, type => 'G94', charset => 'B'); |
$r .= _i2g ($C->{option}->{undef_char}->[0], $C, |
576 |
|
%{ $C->{option}->{undef_char}->[1] }); |
577 |
} |
} |
578 |
} |
} |
579 |
$r . _back2ascii ($C); |
$r . _back2ascii ($C); |
627 |
sub _i2g ($%%) { |
sub _i2g ($%%) { |
628 |
my ($s, $C, %O) = @_; |
my ($s, $C, %O) = @_; |
629 |
my $r = ''; |
my $r = ''; |
630 |
my $set = $CHARSET{$O{type}}->{$O{charset}}; |
my $set = $CHARSET{$O{type}}->{$O{charset}. |
631 |
|
($O{revision}&&$C->{option}->{use_revision}?$O{revision}:'')}; |
632 |
my $set0 = $CHARSET{$O{type}}->{$O{charset_id}}; |
my $set0 = $CHARSET{$O{type}}->{$O{charset_id}}; |
633 |
## -- designate character set |
## -- designate character set |
634 |
my $G = 0; |
my $G = 0; |
682 |
} elsif ($C->{C0}->{'C_SS'.$G}) { |
} elsif ($C->{C0}->{'C_SS'.$G}) { |
683 |
$r .= _i2c ($C->{C0}->{'C_SS'.$G}, $C, type => 'C0') || return undef; |
$r .= _i2c ($C->{C0}->{'C_SS'.$G}, $C, type => 'C0') || return undef; |
684 |
} else { ## Both C0 and C1 set do not have SS2/3. |
} else { ## Both C0 and C1 set do not have SS2/3. |
685 |
|
$left = 0 if $G == 1 && !$C->{C0}->{C_LS1}; |
686 |
$r .= __invoke ($C, $G => $left) if $C->{$left?'GL':'GR'} ne 'G'.$G; |
$r .= __invoke ($C, $G => $left) if $C->{$left?'GL':'GR'} ne 'G'.$G; |
687 |
} |
} |
688 |
} else { |
} else { |
759 |
|
|
760 |
Encode, perlunicode |
Encode, perlunicode |
761 |
|
|
762 |
|
=head1 TODO |
763 |
|
|
764 |
|
=over 4 |
765 |
|
|
766 |
|
=item NCR (coding system other than ISO/IEC 2022) support |
767 |
|
|
768 |
|
=over 2 |
769 |
|
|
770 |
|
=item ESC 02/05 02/15 03/x of X Compound Text |
771 |
|
|
772 |
|
=back |
773 |
|
|
774 |
|
=item Output of control character sets, single control functions |
775 |
|
|
776 |
|
=item Designation sequence of control character sets (input) |
777 |
|
|
778 |
|
=item Special graphic character sets such as G3 of EUC-TW |
779 |
|
|
780 |
|
=item SUPER SHIFT (SS) invoke function of old control character set |
781 |
|
|
782 |
|
=item Safe transparent of control string (ISO/IEC 6429) |
783 |
|
|
784 |
|
=item Output of unoutputable characters as alternative notation such as SGML-like entity |
785 |
|
|
786 |
|
=item C0 set invoked to CR area like ISIRI code |
787 |
|
|
788 |
|
Really need? |
789 |
|
|
790 |
|
=item special treatment of 0x20, 0x7E, 0xA0, 0xFF |
791 |
|
|
792 |
|
For example, GB mongolian sets use MSP (MONGOLIAN SPACE) |
793 |
|
with these code positions. |
794 |
|
|
795 |
|
And, no less coding systems does not use (or does ban using) DEL. |
796 |
|
|
797 |
|
=item A lot of character sets don't have pseudo-UCS mapping. |
798 |
|
|
799 |
|
Most of 9m^n (n >= 3) sets, 9m^n sets with I byte, 9m^n |
800 |
|
DRCSes do not have pseudo-UCS mapping area. It is |
801 |
|
questionable to allocate lots of code positions to these |
802 |
|
rarely-(or no-)used character sets. |
803 |
|
|
804 |
|
=item Even character sets that have pseudo-UCS mapping, some of them can't be outputed in ISO/IEC 2022. |
805 |
|
|
806 |
|
Because output of rarely-used character sets is |
807 |
|
not implemented yet. |
808 |
|
|
809 |
|
=back |
810 |
|
|
811 |
=head1 LICENSE |
=head1 LICENSE |
812 |
|
|
813 |
Copyright 2002 wakaba <w@suika.fam.cx> |
Copyright 2002 wakaba <w@suika.fam.cx> |