charset: move encoding-specific setup code to include
authorMischa POSLAWSKY <perl@shiar.org>
Sat, 22 Apr 2017 10:15:20 +0000 (12:15 +0200)
committerMischa POSLAWSKY <perl@shiar.org>
Thu, 25 May 2017 20:10:24 +0000 (22:10 +0200)
charset-encoding.inc.pl
charset.plp

index fc6b4b1..0f1d2d6 100644 (file)
@@ -52,10 +52,10 @@ use warnings;
        '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']},
+       'wingdings'    => {inherit => ['' => '20'], setup => sub {require Encode::Wingdings}},
+       'wingdings2'   => {inherit => ['' => '20'], setup => sub {require Encode::Wingdings2}},
+       'wingdings3'   => {inherit => ['' => '20'], setup => sub {require Encode::Wingdings3}},
+       'webdings'     => {inherit => ['' => '20'], setup => sub {require Encode::Webdings}},
 
        'iso-8859-2'   => {inherit => ['iso-8859-1' => 'A0']},
        'iso-8859-3'   => {inherit => ['iso-8859-1' => 'A0']}, #TODO: also apply to iso-8859-9
@@ -122,4 +122,55 @@ use warnings;
        'cp1047'       => {inherit => ['cp37' => '10-2F+50-5F+A0-BF']},
        'cp1026'       => {inherit => ['cp37' => '40']},
        'cp875'        => {inherit => ['cp37' => '30']},
+
+       ''             => {setup => sub {
+               my $row = shift;
+               $row->{offset} = delete $row->{startpoint};
+               $row->{set} = 'Unicode characters';
+               my $block = $row->{offset} >> 8;
+               $row->{endpoint} ||= ($block + 1 << 8) - 1;
+               $block == ($row->{endpoint} >> 8) or undef $block;
+
+               $row->{table} = join '', map { chr } $row->{offset} .. $row->{endpoint};
+               utf8::upgrade($row->{table});  # prevent latin1 output
+
+               $row->{endpoint} -= $row->{offset};
+
+               if (defined $block) {
+                       $row->{set} = sprintf 'Unicode block U+%02Xxx', $block;
+                       $row->{offset} %= 0x100;
+               }
+
+               return $row;
+       }},
+       u              => {setup => sub {
+               my $row = shift;
+               $row->{cell} = do 'charset-unicode.inc.pl'
+                       or Alert('Table data could not be read', $@ || $!);
+
+               $row->{endpoint} ||= 0x1FFF;
+               $row->{set} = 'Unicode ' . (
+                       $row->{startpoint} <  0x1000 && $row->{endpoint} < 0x1000 ? 'BMP' :
+                       $row->{startpoint} >= 0x1000 && $row->{endpoint} < 0x2000 ? 'SMP' :
+                       'allocations'
+               );
+               return $row;
+       }},
+       uu             => {setup => sub {
+               my $row = shift;
+               $row->{cell} = do 'charset-ucplanes.inc.pl'
+                       or Alert('Table data could not be read', $@ || $!);
+               $row->{endpoint} ||= 0x3FF;
+               $row->{set} = 'Unicode planes';
+               return $row;
+       }},
+       'utf-8'        => 'utf8',
+       utf8           => {setup => sub {
+               my $row = shift;
+               $row->{set} = 'UTF-8';
+               $row->{cell} = do 'charset-utf8.inc.pl'
+                       or Alert('Table data could not be read', $@ || $!);
+               $row->{endpoint} = 0xFF;
+               return $row;
+       }},
 };
index 4f60765..ed495fe 100644 (file)
@@ -143,50 +143,12 @@ sub tabinput {
                }
        }
 
-       if ($input =~ m{ \A (?:wing|web)dings \d* \z }ix) {
-               eval "require Encode::\u$input";
+       if ($charset->{setup}) {
+               eval { $charset->{setup}->(\%row) }
+                       or Alert("Incomplete setup of $input", $@);
        }
 
-       if ($input eq '') {
-               $row{offset} = delete $row{startpoint};
-               $row{set} = 'Unicode characters';
-               my $block = $row{offset} >> 8;
-               $row{endpoint} ||= ($block + 1 << 8) - 1;
-               $block == ($row{endpoint} >> 8) or undef $block;
-
-               $row{table} = join '', map { chr } $row{offset} .. $row{endpoint};
-               utf8::upgrade($row{table});  # prevent latin1 output
-
-               $row{endpoint} -= $row{offset};
-
-               if (defined $block) {
-                       $row{set} = sprintf 'Unicode block U+%02Xxx', $block;
-                       $row{offset} %= 0x100;
-               }
-       }
-       elsif (lc $input eq 'uu') {
-               $row{cell} = do 'charset-ucplanes.inc.pl'
-                       or Alert('Table data could not be read', $@ || $!);
-               $row{endpoint} ||= 0x3FF;
-               $row{set} = 'Unicode planes';
-       }
-       elsif (lc $input eq 'u') {
-               $row{cell} = do 'charset-unicode.inc.pl'
-                       or Alert('Table data could not be read', $@ || $!);
-
-               $row{endpoint} ||= 0x1FFF;
-               $row{set} = 'Unicode ' . (
-                       $row{startpoint} <  0x1000 && $row{endpoint} < 0x1000 ? 'BMP' :
-                       $row{startpoint} >= 0x1000 && $row{endpoint} < 0x2000 ? 'SMP' :
-                       'allocations'
-               );
-       }
-       elsif ($input =~ m/^utf-*8$/i) {
-               $row{set} = 'UTF-8';
-               $row{cell} = do 'charset-utf8.inc.pl'
-                       or Alert('Table data could not be read', $@ || $!);
-               $row{endpoint} = 0xFF;
-       }
+       if ($row{set}) {}
        elsif ($row{set} = Encode::resolve_alias($input)) {
                $row{offset} = delete $row{startpoint};
                $row{endpoint} ||= 0xFF;