charset: skip option to omit rows
authorMischa POSLAWSKY <perl@shiar.org>
Sat, 8 Apr 2017 12:37:05 +0000 (14:37 +0200)
committerMischa POSLAWSKY <perl@shiar.org>
Mon, 24 Apr 2017 23:51:41 +0000 (01:51 +0200)
Input only allows two start-stop ranges for now.

charset.plp

index 2d4293d80adb98dd0c76198cf75d4f44f2576552..e1efd83c0880e8885f06569486751206fb63e784 100644 (file)
@@ -15,7 +15,7 @@ Html({
        data => [qw'charset-unicode.inc.pl charset-utf8.inc.pl'],
 });
 
        data => [qw'charset-unicode.inc.pl charset-utf8.inc.pl'],
 });
 
-my @tablist = split /[^\w-]+/, $Request || 'default';
+my @tablist = split m{/+}, $Request || 'default';
 
 :>
 <h1>Character encoding</h1>
 
 :>
 <h1>Character encoding</h1>
@@ -89,7 +89,7 @@ sub tabinput {
                        'iso-8859-6'  => ['iso-8859-1' => '160'],
                        'iso-8859-7'  => ['iso-8859-1' => '160'],
                        'iso-8859-8'  => ['iso-8859-1' => '160'],
                        'iso-8859-6'  => ['iso-8859-1' => '160'],
                        'iso-8859-7'  => ['iso-8859-1' => '160'],
                        'iso-8859-8'  => ['iso-8859-1' => '160'],
-                       'iso-8859-9'  => ['iso-8859-1' => '208'],
+                       'iso-8859-9'  => ['iso-8859-1' => '208-223+240'],
                        'iso-8859-10' => ['iso-8859-4' => '160'],
                        'iso-8859-11' => ['iso-8859-1' => '160'],
                        'iso-8859-13' => ['iso-8859-4' => '160'],
                        'iso-8859-10' => ['iso-8859-4' => '160'],
                        'iso-8859-11' => ['iso-8859-1' => '160'],
                        'iso-8859-13' => ['iso-8859-4' => '160'],
@@ -100,14 +100,14 @@ sub tabinput {
 
                        'cp1252'      => ['iso-8859-1' => '128-159'],
                        'cp1250'      => ['iso-8859-2' => '128-191', 'cp1252' => '128'],
 
                        'cp1252'      => ['iso-8859-1' => '128-159'],
                        'cp1250'      => ['iso-8859-2' => '128-191', 'cp1252' => '128'],
-                       'cp1254'      => ['iso-8859-9' => '128-159', 'cp1252' => '128'],
+                       'cp1254'      => ['iso-8859-9' => '128-159', 'cp1252' => '128-159+208'],
                        'cp874'       => ['iso-8859-11' => '128-159', 'cp1252' => '128'], # windows-874 actually cp1162
                        'cp874'       => ['iso-8859-11' => '128-159', 'cp1252' => '128'], # windows-874 actually cp1162
-                       'cp1257'      => ['iso-8859-13' => '128', 'cp1252' => '128'],
+                       'cp1257'      => ['iso-8859-13' => '128-159+255', 'cp1252' => '128'],
                        'cp1251'      => ['cp1252' => '128'],
                        'cp1253'      => ['cp1252' => '128'],
                        'cp1255'      => ['iso-8859-8' => '128-223', 'cp1252' => '128'],
                        'cp1256'      => ['cp1252' => '128'],
                        'cp1251'      => ['cp1252' => '128'],
                        'cp1253'      => ['cp1252' => '128'],
                        'cp1255'      => ['iso-8859-8' => '128-223', 'cp1252' => '128'],
                        'cp1256'      => ['cp1252' => '128'],
-                       'cp1258'      => ['cp1252' => '128'],
+                       'cp1258'      => ['cp1252' => '128-159+192'],
 
                        'cp850'       => ['cp437' => '144'],
                        'cp860'       => ['cp437' => '128-175'],
 
                        'cp850'       => ['cp437' => '144'],
                        'cp860'       => ['cp437' => '128-175'],
@@ -115,14 +115,14 @@ sub tabinput {
                        'cp863'       => ['cp437' => '128-175'],
                        'cp865'       => ['cp437' => '144-175'],
                        'cp852'       => ['cp850' => '128', 'cp437' => '128'],
                        'cp863'       => ['cp437' => '128-175'],
                        'cp865'       => ['cp437' => '144-175'],
                        'cp852'       => ['cp850' => '128', 'cp437' => '128'],
-                       'cp857'       => ['cp850' => '128-239', 'cp437' => '128'],
+                       'cp857'       => ['cp850' => '128-175+208-239', 'cp437' => '128'],
                        'cp775'       => ['cp850' => '128'],  # partial cp437
                        'cp775'       => ['cp850' => '128'],  # partial cp437
-                       'cp866'       => ['cp437' => '128'],
+                       'cp866'       => ['cp437' => '128-175+224'],
                        'cp855'       => ['cp437' => '128'],
                        'cp1006'      => ['cp437' => '128'],
                        'cp855'       => ['cp437' => '128'],
                        'cp1006'      => ['cp437' => '128'],
-                       'cp737'       => ['cp437' => '128'],
+                       'cp737'       => ['cp437' => '128-175+224'],
                        'cp869'       => ['cp437' => '128'],
                        'cp869'       => ['cp437' => '128'],
-                       'cp862'       => ['cp437' => '128'],
+                       'cp862'       => ['cp437' => '128-159'],
                        'cp864'       => ['cp437' => '128'],
 
                        'koi8-u'      => ['koi8-r' => 128],
                        'cp864'       => ['cp437' => '128'],
 
                        'koi8-u'      => ['koi8-r' => 128],
@@ -158,14 +158,21 @@ sub tabinput {
        if (defined $params) {
                $params =~ m{
                        \A (?<offset> \d+)
        if (defined $params) {
                $params =~ m{
                        \A (?<offset> \d+)
+                       (?: (?: [-] (?<stop> \d+) )? (?: [+] (?<restart> \d+) ) )?
                        (?: [-] (?<endpoint> \d+) )? \z
                }x or Alert([
                        "Unknown range parameters for $input",
                        (?: [-] (?<endpoint> \d+) )? \z
                }x or Alert([
                        "Unknown range parameters for $input",
-                       "<q>$params</q> is not in format start(-end)",
+                       "<q>$params</q> is not in format start(-stop)(+restart(-end))",
                ]);
 
                $row{offset} = $+{offset};
                $endpoint = $+{endpoint} if $+{endpoint};
                ]);
 
                $row{offset} = $+{offset};
                $endpoint = $+{endpoint} if $+{endpoint};
+               if (my $restart = $+{restart}) {
+                       my $skip = int(($+{stop} || $row{offset}) / $row{cols});
+                       for ($skip + 1 .. ($restart / $row{cols}) - 1) {
+                               $row{skip}->{ $_ * $row{cols} - $row{offset} }++;
+                       }
+               }
        }
 
        if ($input =~ /^U([0-9a-f]+)(?:-([0-9a-f]+))?/) {
        }
 
        if ($input =~ /^U([0-9a-f]+)(?:-([0-9a-f]+))?/) {
@@ -307,6 +314,11 @@ for my $row (@request) {
        }
        print '<tbody>';
        while ($offset < $row->{endpoint}) {
        }
        print '<tbody>';
        while ($offset < $row->{endpoint}) {
+               if ($row->{skip}->{$offset}) {
+                       $offset += $cols * $colsize;
+                       next;
+               }
+
                print '<tr><th>';
                {
                        if (my $rowmod = $offset % $rowdiv) {
                print '<tr><th>';
                {
                        if (my $rowmod = $offset % $rowdiv) {