charset: extend inheritance to generic metadata hashes

diff --git a/charset-encoding.inc.pl b/charset-encoding.inc.pl
index 9ae8523700301cadce7a8354b2f7ec2a15869d02..d7d1461fc37471b4511a7daea38920a610775c54 100644 (file)
--- a/charset-encoding.inc.pl
+++ b/charset-encoding.inc.pl
@@ -2,82 +2,82 @@ use 5.014;
 use warnings;
 
 +{
-       'ascii'       => ['' => '00-7F'],
-       'cp437'       => ['cp850' => 0, 'ascii' => '00-1F+80'], # ascii range overridden later
-       'gsm0338'     => ['ascii' => '00-7F'],
-       'dingbats'    => ['' => '20-7F+A0'],
-       'MacDingbats' => ['dingbats' => '80-9F'],
-       'AdobeZdingbat'=> ['MacDingbats' => '80-9F'], # should be identical but maps to private use
-       'symbol'      => ['' => '20-7F+A0'],
-       'AdobeSymbol' => ['symbol' => '20-7F+A0', '' => '20-7F+A0'], # minor differences, irrelevant except for different '€'
-       'wingdings'   => ['' => '20'],
-       'wingdings2'  => ['' => '20'],
-       'wingdings3'  => ['' => '20'],
-       'webdings'    => ['' => '20'],
+       'ascii'        => {inherit => ['' => '00-7F']},
+       'cp437'        => {inherit => ['cp850' => 0, 'ascii' => '00-1F+80']}, # ascii range overridden later
+       'gsm0338'      => {inherit => ['ascii' => '00-7F']},
+       'dingbats'     => {inherit => ['' => '20-7F+A0']},
+       'MacDingbats'  => {inherit => ['dingbats' => '80-9F']},
+       'AdobeZdingbat'=> {inherit => ['MacDingbats' => '80-9F']}, # should be identical but maps to private use
+       'symbol'       => {inherit => ['' => '20-7F+A0']},
+       'AdobeSymbol'  => {inherit => ['symbol' => '20-7F+A0', '' => '20-7F+A0']}, # minor differences, irrelevant except for different '€'
+       'wingdings'    => {inherit => ['' => '20']},
+       'wingdings2'   => {inherit => ['' => '20']},
+       'wingdings3'   => {inherit => ['' => '20']},
+       'webdings'     => {inherit => ['' => '20']},
 
-       'iso-8859-2'  => ['iso-8859-1' => 'A0'],
-       'iso-8859-3'  => ['iso-8859-1' => 'A0'], #TODO: also apply to iso-8859-9
-       'iso-8859-4'  => ['iso-8859-2' => 'A0'],
-       'iso-8859-5'  => ['iso-8859-1' => 'A0'],
-       'iso-8859-6'  => ['cp1256' => '80', 'iso-8859-1' => 'A0'],
-       'iso-8859-7'  => ['iso-8859-1' => 'A0'],
-       'iso-8859-8'  => ['iso-8859-1' => 'A0'],
-       'iso-8859-9'  => ['iso-8859-1' => 'D0-DF+F0'],
-       'iso-8859-10' => ['iso-8859-4' => 'A0'],
-       'iso-8859-11' => ['iso-8859-1' => 'A0'],
-       'iso-8859-13' => ['iso-8859-4' => 'A0'],
-       'iso-8859-14' => ['iso-8859-1' => 'A0'],
-       'iso-8859-15' => ['iso-8859-1' => 'A0-BF'],
-       'iso-8859-16' => ['iso-8859-2' => 'A0'],
-       'hp-roman8'   => ['iso-8859-1' => 'A0'],
+       'iso-8859-2'   => {inherit => ['iso-8859-1' => 'A0']},
+       'iso-8859-3'   => {inherit => ['iso-8859-1' => 'A0']}, #TODO: also apply to iso-8859-9
+       'iso-8859-4'   => {inherit => ['iso-8859-2' => 'A0']},
+       'iso-8859-5'   => {inherit => ['iso-8859-1' => 'A0']},
+       'iso-8859-6'   => {inherit => ['cp1256' => '80', 'iso-8859-1' => 'A0']},
+       'iso-8859-7'   => {inherit => ['iso-8859-1' => 'A0']},
+       'iso-8859-8'   => {inherit => ['iso-8859-1' => 'A0']},
+       'iso-8859-9'   => {inherit => ['iso-8859-1' => 'D0-DF+F0']},
+       'iso-8859-10'  => {inherit => ['iso-8859-4' => 'A0']},
+       'iso-8859-11'  => {inherit => ['iso-8859-1' => 'A0']},
+       'iso-8859-13'  => {inherit => ['iso-8859-4' => 'A0']},
+       'iso-8859-14'  => {inherit => ['iso-8859-1' => 'A0']},
+       'iso-8859-15'  => {inherit => ['iso-8859-1' => 'A0-BF']},
+       'iso-8859-16'  => {inherit => ['iso-8859-2' => 'A0']},
+       'hp-roman8'    => {inherit => ['iso-8859-1' => 'A0']},
 
-       'cp1252'      => ['iso-8859-1' => '80-9F'],
-       'cp1250'      => ['iso-8859-2' => '80-BF', 'cp1252' => '80'],
-       'cp1254'      => ['iso-8859-9' => '80-9F', 'cp1252' => '80-9F+D0'],
-       'cp874'       => ['iso-8859-11' => '80-9F', 'cp1252' => '80'], # windows-874 actually cp1162
-       'cp1257'      => ['iso-8859-13' => '80-9F+FF', 'cp1252' => '80'],
-       'cp1251'      => ['cp1252' => '80'],
-       'cp1253'      => ['cp1252' => '80'],
-       'cp1255'      => ['iso-8859-8' => '80-DF', 'cp1252' => '80'],
-       'cp1256'      => ['cp1252' => '80'],
-       'cp1258'      => ['cp1252' => '80-9F+C0'],
+       'cp1252'       => {inherit => ['iso-8859-1' => '80-9F']},
+       'cp1250'       => {inherit => ['iso-8859-2' => '80-BF', 'cp1252' => '80']},
+       'cp1254'       => {inherit => ['iso-8859-9' => '80-9F', 'cp1252' => '80-9F+D0']},
+       'cp874'        => {inherit => ['iso-8859-11' => '80-9F', 'cp1252' => '80']}, # windows-874 actually cp1162
+       'cp1257'       => {inherit => ['iso-8859-13' => '80-9F+FF', 'cp1252' => '80']},
+       'cp1251'       => {inherit => ['cp1252' => '80']},
+       'cp1253'       => {inherit => ['cp1252' => '80']},
+       'cp1255'       => {inherit => ['iso-8859-8' => '80-DF', 'cp1252' => '80']},
+       'cp1256'       => {inherit => ['cp1252' => '80']},
+       'cp1258'       => {inherit => ['cp1252' => '80-9F+C0']},
 
-       'cp850'       => ['cp437' => '90'],
-       'cp860'       => ['cp437' => '80-AF'],
-       'cp861'       => ['cp865' => '80-AF'],
-       'cp863'       => ['cp437' => '80-AF'],
-       'cp865'       => ['cp437' => '90-AF'],
-       'cp852'       => ['cp850' => '80', 'cp437' => '80'],
-       'cp857'       => ['cp850' => '80-AF+D0-EF', 'cp437' => '80'],
-       'cp775'       => ['cp850' => '80'],  # partial cp437
-       'cp866'       => ['cp437' => '80-AF+E0'],
-       'cp855'       => ['cp437' => '80'],
-       'cp1006'      => ['iso-8859-6' => 'A0', 'cp437' => '80'],
-       'cp737'       => ['cp437' => '80-AF+E0'],
-       'cp869'       => ['cp437' => '80'],
-       'cp862'       => ['cp437' => '80-9F'],
-       'cp864'       => ['MacArabic' => '80', 'iso-8859-6' => '80', 'cp437' => '80'], #TODO: compare form variants
+       'cp850'        => {inherit => ['cp437' => '90']},
+       'cp860'        => {inherit => ['cp437' => '80-AF']},
+       'cp861'        => {inherit => ['cp865' => '80-AF']},
+       'cp863'        => {inherit => ['cp437' => '80-AF']},
+       'cp865'        => {inherit => ['cp437' => '90-AF']},
+       'cp852'        => {inherit => ['cp850' => '80', 'cp437' => '80']},
+       'cp857'        => {inherit => ['cp850' => '80-AF+D0-EF', 'cp437' => '80']},
+       'cp775'        => {inherit => ['cp850' => '80']},  # partial cp437
+       'cp866'        => {inherit => ['cp437' => '80-AF+E0']},
+       'cp855'        => {inherit => ['cp437' => '80']},
+       'cp1006'       => {inherit => ['iso-8859-6' => 'A0', 'cp437' => '80']},
+       'cp737'        => {inherit => ['cp437' => '80-AF+E0']},
+       'cp869'        => {inherit => ['cp437' => '80']},
+       'cp862'        => {inherit => ['cp437' => '80-9F']},
+       'cp864'        => {inherit => ['MacArabic' => '80', 'iso-8859-6' => '80', 'cp437' => '80']}, #TODO: compare form variants
 
-       'koi8-u'      => ['koi8-r' => '90-BF'],
-       'koi8-f'      => ['koi8-u' => '90-BF'],
+       'koi8-u'       => {inherit => ['koi8-r' => '90-BF']},
+       'koi8-f'       => {inherit => ['koi8-u' => '90-BF']},
 
-       'MacRomanian' => ['MacRoman' => 'A0-BF+D0-DF'],
-       'MacRumanian' => ['MacRomanian' => 'A0-BF+D0-DF', 'MacRoman' => 'A0-BF+D0-DF'],
-       'MacCroatian' => ['MacRoman' => 'A0'],
-       'MacCentralEurRoman' => ['MacRoman' => '80'],
-       'MacIcelandic'=> ['MacRoman' => 'A0-AF+D0-EF'],
-       'MacTurkish'  => ['MacRoman' => 'D0-DF'], # F5 is unassigned
-       'MacSami'     => ['MacIcelandic' => '90-BF+D0-DF+F0', 'MacRoman' => '90'],
-       'MacGreek'    => ['MacRoman' => '80'],
-       'MacCyrillic' => ['MacRoman' => '80'],
-       'MacHebrew'   => ['iso-8859-8' => '80', 'MacRoman' => '80-8F+A0'], # partial ascii
-       'MacArabic'   => ['iso-8859-6' => '80', 'cp864' => '80', 'MacRoman' => '80'], #TODO: multiple parents
-       'MacFarsi'    => ['MacArabic' => 'B0-BF', 'MacRoman' => '80'],
+       'MacRomanian'  => {inherit => ['MacRoman' => 'A0-BF+D0-DF']},
+       'MacRumanian'  => {inherit => ['MacRomanian' => 'A0-BF+D0-DF', 'MacRoman' => 'A0-BF+D0-DF']},
+       'MacCroatian'  => {inherit => ['MacRoman' => 'A0']},
+       'MacCentralEurRoman' => {inherit => ['MacRoman' => '80']},
+       'MacIcelandic' => {inherit => ['MacRoman' => 'A0-AF+D0-EF']},
+       'MacTurkish'   => {inherit => ['MacRoman' => 'D0-DF']}, # F5 is unassigned
+       'MacSami'      => {inherit => ['MacIcelandic' => '90-BF+D0-DF+F0', 'MacRoman' => '90']},
+       'MacGreek'     => {inherit => ['MacRoman' => '80']},
+       'MacCyrillic'  => {inherit => ['MacRoman' => '80']},
+       'MacHebrew'    => {inherit => ['iso-8859-8' => '80', 'MacRoman' => '80-8F+A0']}, # partial ascii
+       'MacArabic'    => {inherit => ['iso-8859-6' => '80', 'cp864' => '80', 'MacRoman' => '80']}, #TODO: multiple parents
+       'MacFarsi'     => {inherit => ['MacArabic' => 'B0-BF', 'MacRoman' => '80']},
 
-       'cp37'        => ['posix-bc' => '00'],
-       'posix-bc'    => ['cp1047' => '40'],
-       'cp500'       => ['cp37' => '40-5F+B0-BF'],
-       'cp1047'      => ['cp37' => '10-2F+50-5F+A0-BF'],
-       'cp1026'      => ['cp37' => '40'],
-       'cp875'       => ['cp37' => '30'],
+       'cp37'         => {inherit => ['posix-bc' => '00']},
+       'posix-bc'     => {inherit => ['cp1047' => '40']},
+       'cp500'        => {inherit => ['cp37' => '40-5F+B0-BF']},
+       'cp1047'       => {inherit => ['cp37' => '10-2F+50-5F+A0-BF']},
+       'cp1026'       => {inherit => ['cp37' => '40']},
+       'cp875'        => {inherit => ['cp37' => '30']},
 };

diff --git a/charset.plp b/charset.plp
index 7ff3f420a2dd25d4dc652ad67231193da1313a2b..1b672e93ebfc091575b912728d32d7660d5fe1ca 100644 (file)
--- a/charset.plp
+++ b/charset.plp
@@ -76,7 +76,7 @@ use Shiar_Sheet::FormatChar;
 my $glyphs = Shiar_Sheet::FormatChar->new;
 my @request;
 
-my $INHERIT = do 'charset-encoding.inc.pl'
+my $charsets = do 'charset-encoding.inc.pl'
        or Alert('Encoding metadata could not be read', $@ || $!);
 
 sub tabinput {
@@ -136,7 +136,8 @@ sub tabinput {
        my $params = $input =~ s/[+](.*)\z// ? $1 : undef;
 
        if (not defined $params) {
-               my @parents = @{ $INHERIT->{$input} || [] };
+               my $charset = $charsets->{$input} || {};
+               my @parents = @{ $charset->{inherit} || [] };
 
                if (my ($parent, $part) = pairfirst { defined $visible->{$a} } @parents) {
                        $row{parent} = $parent;