reference common overview table
'],
stylesheet => [qw'light'],
- data => [qw'charset-unicode.inc.pl charset-utf8.inc.pl'],
+ data => [qw'charset-unicode.inc.pl charset-ucplanes.inc.pl charset-utf8.inc.pl'],
});
my @tablist = split m{/+}, $Request || 'default';
print join " •\n", (
map {
join " ·\n", pairmap {
- optionlink($b || ucfirst $a, "/charset/$a?compare", $a eq $Request);
+ optionlink($b || ucfirst $a, '/charset'.($a && "/$a?compare"), $a eq $Request);
} @{$_}
}
[
iso => 'ISO',
+ win => 'Windows',
dos => 'DOS',
mac => 'Apple',
ebcdic => 'EBCDIC',
+ $tablist[0] eq 'default' ? () : ('' => 'common'),
],
[
westeur => 'West',
cyrillic => 0,
hebrew => 0,
],
- [ uc => 'Unicode' ],
);
:>.
</p>
my $input = shift or return;
state $ALIAS = {
- default => [qw( unicode+0-639 utf-8 iso-8859-1 iso-8859-15 cp1252 cp437 cp850 )],
- uc => [qw( U+cols=32 unicode+0-4095 unicode+4096-6319 unicode+6320-8191 )],
+ default => [qw( u+0-639 utf-8+realsize iso-8859-1 iso-8859-15 cp1252 cp437 cp850 )],
+ unicode => [qw( uu+cols=32+realsize u+0-4095 u+4096-6319 u+6320-8191 )],
us => [qw( cp437 cp863 gsm0338 AdobeStandardEncoding )],
ebcdic => [qw( cp37 cp500 cp1047 posix-bc cp1026 cp875 )],
iso => [map {"iso-8859-$_"} 1 .. 11, 13 .. 16],
hebrew => [qw( iso-8859-8 cp1255 MacHebrew cp862 U59-5F )],
thai => [qw( iso-8859-11 cp874 MacThai )],
vietnamese => [qw( viscii cp1258 MacVietnamese )],
- symbol => [qw( symbol dingbats MacDingbats AdobeZdingbat AdobeSymbol )],
+ symbols => [qw( symbol dingbats MacDingbats )],
# iso-code shorthand
1 => 'westeur',
return;
}
- state $visible = {}; # all present tables
+ state $visible = {'' => 1}; # all present tables
my %row = (offset => 0, cols => 16);
my $params = $input =~ s/[+](.*)\z// ? $1 : undef;
state $INHERIT = {
'cp437' => ['cp850' => 0, 'ascii' => '0-31+128'], # ascii range overridden later
'gsm0338' => ['ascii' => '0-127'],
+ 'dingbats' => ['' => '32-127+160'],
+ 'MacDingbats' => ['dingbats' => '128-159'],
+ 'AdobeZdingbat'=> ['MacDingbats' => '128-159'], # should be identical but maps to private use
+ 'symbol' => ['' => '32-127+160'],
+ 'AdobeSymbol' => ['symbol' => '32-127+160', '' => '32-127+160'], # minor differences, irrelevant except for different '€'
'iso-8859-2' => ['iso-8859-1' => '160'],
'iso-8859-3' => ['iso-8859-1' => '160'], #TODO: also apply to iso-8859-9
}
for my $param (split /[+]+/, $params // '') {
- if ($param =~ m{ \A cols = (\d+) \z }x) {
+ if ($param eq 'realsize') {
+ $row{realsize}++;
+ }
+ elsif ($param =~ m{ \A cols = (\d+) \z }x) {
$row{cols} = $1;
}
elsif ($param =~ m{ \A (?<offset> \d+) (?: [-] (?<endpoint> \d+) )? \z }x) {
}
}
- if ($input =~ /^U([0-9a-fA-F]+)(?:-([0-9a-fA-F]+))?/) {
+ if ($input =~ m{ \A u ([0-9a-f]+) (?:-([0-9a-f]+))? \z }ix) {
my $start = hex($1) << ($2 ? 4 : 8);
my $end = $2 ? (hex($2) << 4) + $row{cols} - 1 : $start + 255;
$row{table} = join '', map { chr } $start .. $end;
$row{set} = sprintf 'Unicode block U+%02Xxx', $start >> 8;
$row{offset} = $start % 256;
}
- elsif ($input eq 'U') {
+ elsif (lc $input eq 'uu') {
$row{set} = 'Unicode planes';
$row{cell} = do 'charset-ucplanes.inc.pl'
or Alert('Table data could not be read', $@ || $!);
$row{endpoint} = 1023 * $row{cell}->{colsize};
}
+ elsif (lc $input eq 'u') {
+ $row{cell} = do 'charset-unicode.inc.pl'
+ or Alert('Table data could not be read', $@ || $!);
+
+ $row{endpoint} ||= 8191;
+ $row{endpoint} *= $row{cell}->{colsize};
+ $row{startpoint} = $row{cell}->{colsize} * $row{offset};
+ $row{offset} = 0;
+ $row{set} = 'Unicode ' . (
+ $row{startpoint} < 0x10000 && $row{endpoint} < 0x10000 ? 'BMP' :
+ $row{startpoint} >= 0x10000 && $row{endpoint} < 0x20000 ? 'SMP' :
+ 'allocations'
+ );
+ }
+ elsif ($input =~ m/^utf-*8$/i) {
+ $row{set} = 'UTF-8';
+ $row{cell} = do 'charset-utf8.inc.pl'
+ or Alert('Table data could not be read', $@ || $!);
+ $row{endpoint} = 255;
+ }
elsif ($row{set} = Encode::resolve_alias($input)) {
- if ($row{set} eq 'Internal') {
- $row{cell} = do 'charset-unicode.inc.pl'
- or Alert('Table data could not be read', $@ || $!);
-
- $row{endpoint} ||= 8191;
- $row{endpoint} *= $row{cell}->{colsize};
- $row{startpoint} = $row{cell}->{colsize} * $row{offset};
- $row{offset} = 0;
- $row{set} = 'Unicode ' . (
- $row{startpoint} < 0x10000 && $row{endpoint} < 0x10000 ? 'BMP' :
- $row{startpoint} >= 0x10000 && $row{endpoint} < 0x20000 ? 'SMP' :
- 'allocations'
- );
- }
- elsif ($row{set} eq 'utf-8-strict') {
- $row{set} = 'UTF-8';
- $row{cell} = do 'charset-utf8.inc.pl'
- or Alert('Table data could not be read', $@ || $!);
- $row{endpoint} = 255;
+ $row{endpoint} ||= 255;
+ if ($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} .. $row{endpoint}
+ ];
}
else {
- $row{endpoint} ||= 255;
- if ($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} .. $row{endpoint}
- ];
+ # ~16x faster than decoding in loop;
+ # substr strings is twice as fast as splitting to an array
+ $row{table} = Encode::decode($row{set}, pack 'C*', $row{offset} .. $row{endpoint});
+ }
+ $row{endpoint} -= $row{offset};
+
+ if ($row{set} eq 'cp437') {
+ if ($row{offset} <= 0xED and $row{endpoint} >= 0xED - $row{offset}) {
+ # replace phi glyph
+ substr($row{table}, 0xED - $row{offset}, 1) = 'ϕ';
}
- else {
- # ~16x faster than decoding in loop;
- # substr strings is twice as fast as splitting to an array
- $row{table} = Encode::decode($row{set}, pack 'C*', $row{offset} .. $row{endpoint});
+ if ($row{offset} < 0x20) {
+ # replace control characters by visible variants
+ my $sub = substr ' ☺☻♥♦♣♠•◘○◙♂♀♪♫☼►◄↕‼¶§▬↨↑↓→←∟↔▲▼', $row{offset};
+ substr($row{table}, 0, length $sub) = $sub;
}
- $row{endpoint} -= $row{offset};
-
- if ($row{set} eq 'cp437' and !$row{offset}) {
- substr($row{table}, 237, 1) = pack 'U*', 0x3D5; # phi sign
- substr($row{table}, 0, 32) = pack 'U*', map {hex} qw(
- 2007 263A 263B 2665 2666 2663 2660 2022
- 25D8 25CB 25D9 2642 2640 266A 266B 263C
- 25BA 25C4 2195 203C 00B6 00A7 25AC 21A8
- 2191 2193 2192 2190 221F 2194 25B2 25BC
- );
+ }
+ elsif ($row{set} eq 'symbol') {
+ if ($row{offset} <= 0x60 and $row{endpoint} >= 0x60 - $row{offset}) {
+ # replace radical extender by closest unicode equivalent
+ substr($row{table}, 0x60 - $row{offset}, 1) = '│';
+ }
+ if ($row{offset} <= 0xBD and $row{endpoint} >= 0xFF - $row{offset}) {
+ substr($row{table}, 0xBD - $row{offset}, 2) = '⏐⎯'; # arrow extenders
+ substr($row{table}, 0xD2 - $row{offset}, 3) = '®©™'; # serif variants
+ substr($row{table}, 0xE0 - $row{offset}, 1) = '◊'; # replace lookalike, should match AdobeSymbol
+ substr($row{table}, 0xE2 - $row{offset}, 3) = '®©™'; # sans-serif variants
+ substr($row{table}, 0xE6 - $row{offset}, 10) = '⎛⎜⎝⎡⎢⎣⎧⎨⎩⎪';
+ substr($row{table}, 0xF0 - $row{offset}, 1) = '€';
+ substr($row{table}, 0xF4 - $row{offset}, 11) = '⎮⌡⎞⎟⎠⎤⎥⎦⎫⎬⎭';
}
-
- $visible->{ascii} = # assume common base
- $visible->{ $row{set} } = 1;
}
+
+ $visible->{ascii} = # assume common base
+ $visible->{ $row{set} } = 1;
}
else {
Alert("Encoding <q>$input</q> unknown");
if ($len -= $rest) {
# continued on new row
my @next = ($len * $colsize, "$class joinu");
+ my $separate = $cols - $len > $rest; # columns not on next row
if ($len > $rest) {
# minority remains
push @next, $name, $title;
$title ||= $name;
- $name = '';
+ $name = $separate && '…';
}
else {
# minority on next row
- push @next, '"', $title || $name;
+ push @next, $separate && '"', $title || $name;
}
$table->{$offset + $colsize*$rest} //= \@next;
$class .= ' joind';
$class .= ' joind';
}
- # coalesce multiple rows
- while ($rows > 3) {
- $info->{skip}->{$offset += $rowsize}++;
- $rows--;
- }
- if ($rows > 2) {
- $info->{skip}->{$offset += $rowsize} = 0;
+ unless ($info->{realsize}) {
+ # coalesce multiple rows
+ while ($rows > 3) {
+ $info->{skip}->{$offset += $rowsize}++;
+ $rows--;
+ }
+ if ($rows > 2) {
+ $info->{skip}->{$offset += $rowsize} = 0;
+ }
}
$attr .= sprintf ' rowspan=%d', $rows;
$attr .= $1 if $class and $class =~ s/( \w+="[^"]*")//;
$attr .= sprintf ' class="%s"', $class if $class;
$attr .= sprintf ' title="%s"', EscapeHTML($title) if $title;
- return "<td$attr>$name";
+ return "<td$attr>$name\n";
}
for my $row (@request) {
printf '<div class="section"><table class="glyphs%s">', !$row->{cell} && ' charmap';
my $title = $row->{set};
$title .= " <aside>(over $_)</aside>"
- for grep { $_ ne 'iso-8859-1' } $row->{parent} // ();
+ for $row->{parent} || ();
printf '<caption>%s</caption>', $title;
print '<col>' x ($cols + 1);
for my $section (qw{thead}) {
printf '%X', ($offset + $row->{offset}) / $rowdiv;
}
}
+ say '';
+
for (1 .. $cols) {
if ($row->{cell}) {
print range_cell($row, $offset);
next;
}
+ my $cp = $offset + $row->{offset};
my $glyph = ref $row->{table} eq 'ARRAY' ? $row->{table}->[$offset] :
substr $row->{table}, $offset, 1;
- if ($glyph eq $NOCHAR) {
- print '<td>';
- next;
- }
+ my ($cell, $name, $class) = $glyph eq $NOCHAR ? () :
+ $glyphs->glyph_html($glyph);
if (exists $get{compare}) {
state $visible = {};
- my $cp = $offset + $row->{offset};
- printf '<td class="%s" title="%3$s">%2$s',
+ $class = (
$cp == ord $glyph ? 'l4' :
$row->{parent} && $glyph eq
Encode::decode($row->{parent}, pack 'C', $cp) ? 'l3' :
+ !$class ? undef :
$visible->{$glyph} ? 'l2' :
- 'l1',
- $glyphs->glyph_html($glyph);
+ 'l1'
+ );
$visible->{$glyph}++;
- next;
}
- print "\n".$glyphs->glyph_cell($glyph);
+ say sprintf $class ? '<td title="%s" class="X %s">%s' : '<td title="%s">',
+ $name, $class, $cell;
}
continue {
$offset += $colsize;
}
- print "\n";
}
say '</table></div>';
}
git.shiar.nl / sheet.git / blobdiff