X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/0ded18d239731231ec81b0a559b0f5ef616acda5..1436e579bd7ccf52d5e53d2db969eb74093df149:/charset.plp?ds=inline
diff --git a/charset.plp b/charset.plp
index 2d4293d..51c391c 100644
--- a/charset.plp
+++ b/charset.plp
@@ -15,7 +15,7 @@ Html({
data => [qw'charset-unicode.inc.pl charset-utf8.inc.pl'],
});
-my @tablist = split /[^\w-]+/, $Request || 'default';
+my @tablist = split m{/+}, $Request || 'default';
:>
Character encoding
@@ -39,19 +39,23 @@ 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 )],
baltic => [qw( iso-8859-4 iso-8859-13 cp1257 cp775 )],
nordic => [qw( iso-8859-10 cp865 cp861 MacIcelandic MacSami )],
cyrillic => [qw( koi8-r koi8-u koi8-f iso-8859-5 cp1251 MacCyrillic cp866 cp855 )], # MacUkrainian is broken
- arabic => [qw( iso-8859-6 cp1006 cp864 cp1256 MacArabic )], # MacFarsi same as MacArabic?
+ arabic => [qw( iso-8859-6 cp1256 MacArabic cp864 cp1006 MacFarsi )],
greek => [qw( iso-8859-7 cp1253 MacGreek cp737 cp869 )],
hebrew => [qw( iso-8859-8 cp1255 MacHebrew cp862 )],
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',
@@ -83,13 +87,13 @@ sub tabinput {
'gsm0338' => ['ascii' => '0-127'],
'iso-8859-2' => ['iso-8859-1' => '160'],
- 'iso-8859-3' => ['iso-8859-1' => '160'],
+ 'iso-8859-3' => ['iso-8859-1' => '160'], #TODO: also apply to iso-8859-9
'iso-8859-4' => ['iso-8859-2' => '160'],
'iso-8859-5' => ['iso-8859-1' => '160'],
- 'iso-8859-6' => ['iso-8859-1' => '160'],
+ 'iso-8859-6' => ['cp1256' => '128', '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'],
@@ -100,14 +104,14 @@ sub tabinput {
'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
- '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'],
- 'cp1258' => ['cp1252' => '128'],
+ 'cp1258' => ['cp1252' => '128-159+192'],
'cp850' => ['cp437' => '144'],
'cp860' => ['cp437' => '128-175'],
@@ -115,25 +119,31 @@ sub tabinput {
'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
- 'cp866' => ['cp437' => '128'],
+ 'cp866' => ['cp437' => '128-175+224'],
'cp855' => ['cp437' => '128'],
- 'cp1006' => ['cp437' => '128'],
- 'cp737' => ['cp437' => '128'],
+ 'cp1006' => ['iso-8859-6' => '160', 'cp437' => '128'],
+ 'cp737' => ['cp437' => '128-175+224'],
'cp869' => ['cp437' => '128'],
- 'cp862' => ['cp437' => '128'],
- 'cp864' => ['cp437' => '128'],
+ 'cp862' => ['cp437' => '128-159'],
+ 'cp864' => ['MacArabic' => '128', 'iso-8859-6' => '128', 'cp437' => '128'], #TODO: compare form variants
'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' => ['iso-8859-8' => '128', 'MacRoman' => '128-143+160'], # partial ascii
+ 'MacArabic' => ['iso-8859-6' => '128', 'cp864' => '128', 'MacRoman' => '128'], #TODO: multiple parents
+ 'MacFarsi' => ['MacArabic' => '176-191', 'MacRoman' => '128'],
};
my @parents = @{ $INHERIT->{$input} || [] };
@@ -158,14 +168,21 @@ sub tabinput {
if (defined $params) {
$params =~ m{
\A (? \d+)
+ (?: (?: [-] (? \d+) )? (?: [+] (? \d+) ) )?
(?: [-] (? \d+) )? \z
}x or Alert([
"Unknown range parameters for $input",
- "$params
is not in format start(-end)",
+ "$params
is not in format start(-stop)(+restart(-end))",
]);
$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]+))?/) {
@@ -197,7 +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
@@ -307,6 +324,11 @@ for my $row (@request) {
}
print '';
while ($offset < $row->{endpoint}) {
+ if ($row->{skip}->{$offset}) {
+ $offset += $cols * $colsize;
+ next;
+ }
+
print '';
{
if (my $rowmod = $offset % $rowdiv) {
|
---|