X-Git-Url: http://git.shiar.net/sheet.git/blobdiff_plain/bb412b576d883e11a4ec09d01c34a933d894af6c..c795df707c547786ce244da6915d9409f2a65179:/charset.plp
diff --git a/charset.plp b/charset.plp
index f546f2d..e5fdd45 100644
--- a/charset.plp
+++ b/charset.plp
@@ -1,30 +1,25 @@
-<:
-use utf8;
-use strict;
-use warnings;
-use open IO => ':utf8';
-
-our $VERSION = '1.0';
-
-$header{content_type} = 'text/html; charset=utf-8';
-
-:>
-
-
-
-charset cheat sheet
-
-
-
+<(common.inc.plp)><:
+
+Html({
+ title => 'charset cheat sheet',
+ version => 'v1.0',
+ description => [
+ "Reference sheet with all glyphs in common character encoding tables,",
+ "and an overview of Unicode ranges and UTF-8 bytes.",
+ ],
+ keywords => [qw'
+ charset codepage unicode ascii utf8 latin glyph character encoding
+ reference common overview table
+ '],
+ stylesheet => [qw'light'],
+});
-
+:>
Character encoding
<:
-my $diinfo = do 'digraphs.inc.pl';
-my %di = map { $diinfo->{$_}->[0] => $_ } grep { ref $diinfo->{$_} }
- keys %$diinfo;
+use Shiar_Sheet::FormatChar;
+my $glyphs = Shiar_Sheet::FormatChar->new;
use Encode qw(decode resolve_alias);
# generate character table(s)
@@ -53,7 +48,20 @@ my @request = map {
if ($input =~ s/-$//) {
$endpoint = $row{offset} ? $row{offset} < 160 ? 159 : 191 : 127;
}
- if ($row{set} = resolve_alias($input)) {
+
+ if ($input =~ /^U([0-9a-f]+)(?:-([0-9a-f]+))?/) {
+ my $start = hex($1) << ($2 ? 4 : 8);
+ my $end = $2 ? hex($2) << 4 : $start + 240;
+ $row{table} = join '', map { chr } $start .. $end+15;
+ utf8::upgrade($row{table}); # prevent latin1 output
+ $row{set} = sprintf 'Unicode block U+%02Xxx', $start >> 8;
+ }
+ elsif ($input eq 'U') {
+ $row{table} = ' ' x 512;
+ $row{set} = 'Unicode planes';
+ $row{cell} = do 'charset-ucplanes.inc.pl';
+ }
+ elsif ($row{set} = resolve_alias($input)) {
if ($row{set} eq 'Internal') {
$row{table} = ' ' x ($endpoint < 255 ? 640 : 4096);
$row{set} = 'Unicode BMP';
@@ -88,21 +96,11 @@ for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) {
);
}
-sub quote {
- local $_ = shift;
- s/"/"/g;
- s/</g;
- s/>/>/g;
- return $_;
-}
-
-print "\n";
-
my @nibble = (0..9, 'A'..'F');
for my $row (@request) {
- print '';
+ printf '', !$row->{cell} && ' charmap';
printf '%s', $row->{set};
- print '';
+ print '' x 17;
for my $section (qw{thead}) {
print "<$section>â±";
print ' | ', $_ for @nibble;
@@ -123,41 +121,54 @@ for my $row (@request) {
next;
}
- my $info = [ord $glyph];
- if (defined (my $mnem = $di{ord $glyph})) {
- $info = $diinfo->{$mnem};
- }
- my ($codepoint, $name, $prop, $script, $string) = @$info;
-
- $glyph = quote($string || $glyph);
- my $desc = sprintf 'U+%04X%s', $codepoint, $name && " ($name)";
- my @class = ('X', grep {$_} $prop, $script);
-
- $glyph = "$glyph" if $prop eq 'Zs';
-
- printf "\n".' | %s',
- join(' ', @class), quote($desc), $glyph;
+ print "\n".$glyphs->glyph_cell($glyph);
}
print "\n";
}
- print " |
---|
\n";
+ print "
\n";
}
-print "
\n";
-
:>
-
+
+
+ control
+ | whitespace
+ | diacritic
+ | punctuation
+ | symbol
+ | numeric
+ | greek
+ | aramaic
+ | syllabic
+ african
+ | japanese
+ | cjk
+ | chinese
+ |
+ | alphabetic
+ |
+
+
+ unicode 5.0
+ | proposed
+ | deprecated
+ | unassigned
+ | invalid
+ |
+
-