charset: mac preset for all charsets related to MacRoman

[sheet.git] / charset.plp

diff --git a/charset.plp b/charset.plp
index e1efd83c0880e8885f06569486751206fb63e784..1f2be559e3e61f18edc858cb2903c05cda91fd1e 100644 (file)
--- a/charset.plp
+++ b/charset.plp
@@ -39,7 +39,10 @@ sub tabinput {
                                   cp737 cp869 cp866 cp855 cp862 cp864 )],
                aix        => [qw( cp1006 )],
                win        => [qw( cp1252 cp1250 cp1254 cp1257 cp1258 cp1253 cp1251 cp1255 cp1256 cp874 )],
+               mac        => [qw( MacRoman MacRomanian MacRumanian MacCroatian MacCentralEurRoman MacTurkish MacIcelandic MacSami
+                                  MacGreek MacCyrillic MacHebrew MacArabic MacFarsi MacThai )],
 
+               # languages
                westeur    => [qw( iso-8859-1 iso-8859-15 cp1252 iso-8859-14 cp850 hp-roman8 nextstep MacRoman )],
                centeur    => [qw( iso-8859-2 iso-8859-16 cp1250 cp852 MacRomanian MacCroatian MacCentralEurRoman )], # MacRumanian only for DB
                turkish    => [qw( iso-8859-9 iso-8859-3 cp1254 cp857 MacTurkish )],
@@ -52,6 +55,7 @@ sub tabinput {
                thai       => [qw( iso-8859-11 cp874 MacThai )],
                vietnamese => [qw( viscii cp1258 MacVietnamese )],
                symbol     => [qw( symbol dingbats MacDingbats AdobeZdingbat AdobeSymbol )],
+
                # iso-code shorthand
                1 => 'westeur',
                2 => 'centeur',
@@ -128,12 +132,18 @@ sub tabinput {
                        'koi8-u'      => ['koi8-r' => 128],
                        'koi8-f'      => ['koi8-u' => 128],
 
-                       'MacRomanian' => ['MacRoman' => '160'],
+                       'MacRomanian' => ['MacRoman' => '160-191+208-223'],
+                       'MacRumanian' => ['MacRomanian' => '160-191+208-223', 'MacRoman' => '160-191+208-223'],
                        'MacCroatian' => ['MacRoman' => '160'],
                        'MacCentralEurRoman' => ['MacRoman' => '128'],
+                       'MacIcelandic'=> ['MacRoman' => '160-175+208-239'], #TODO: gaps at C/E
                        'MacTurkish'  => ['MacRoman' => '208-223'], # F5 is unassigned
+                       'MacSami'     => ['MacIcelandic' => '144', 'MacRoman' => '144'],
+                       'MacGreek'    => ['MacRoman' => '128'],
                        'MacCyrillic' => ['MacRoman' => '128'],
-                       'MacHebrew'   => ['MacRoman' => '128'],
+                       'MacHebrew'   => ['MacRoman' => '128-143+160'], # partial ascii
+                       'MacArabic'   => ['MacRoman' => '128'],
+                       'MacFarsi'    => ['MacArabic' => '176-191', 'MacRoman' => '128'],
                };
 
                my @parents = @{ $INHERIT->{$input} || [] };
@@ -204,7 +214,7 @@ sub tabinput {
                        $row{endpoint} = 255;
                }
                else {
-                       if ($row{set} eq 'MacHebrew') {
+                       if ($row{set} eq 'MacHebrew' or $row{set} eq 'MacThai') {
                                # array of possibly multiple characters per code point
                                $row{table} = [
                                        map { Encode::decode($row{set}, pack 'C*', $_) } $row{offset} .. $endpoint