X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/138b47f5f5ac5364dbfc15075e21b0990ab919d9..6d8c2623e104ad13895ddbe7b23d52ba0d3f0853:/charset.plp?ds=inline
diff --git a/charset.plp b/charset.plp
index 777e0ee..557c66f 100644
--- a/charset.plp
+++ b/charset.plp
@@ -1,30 +1,28 @@
-<:
-use utf8;
-use strict;
-use warnings;
-use open IO => ':utf8';
-
-our $VERSION = '1.0';
-
-$header{content_type} = 'text/html; charset=utf-8';
-
-:>
-
+<(common.inc.plp)><:
+
+Html({
+ title => 'charset cheat sheet',
+ version => '1.0',
+ 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'],
+ data => [qw'charset-unicode.inc.pl charset-utf8.inc.pl'],
+});
-
-charset cheat sheet
-
-
-
-
-
+:>
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;
+my @nibble = (0..9, 'A'..'F');
+my $nibsize = 1;
use Encode qw(decode resolve_alias);
# generate character table(s)
@@ -32,7 +30,7 @@ use Encode qw(decode resolve_alias);
# substr strings is twice as fast as splitting to an array)
my %ALIAS = (
# default => [qw(unicode utf-8 iso-8859-1 cp437 -cp1252- --iso-8859-15- -koi8-f)],
- default => [qw(unicode utf-8 iso-8859-1 -cp1252- --iso-8859-15- cp437 -cp850)],
+ default => [qw(unicode- utf-8 iso-8859-1 -cp1252- --iso-8859-15- cp437 -cp850)],
0 => [qw(cp437 cp863)],
1 => [qw(iso-8859-1 cp1252 MacRoman cp850)],
2 => [qw(iso-8859-2 cp1250 cp852 MacCentralEurRoman MacCroatian MacRumanian)],
@@ -53,14 +51,31 @@ my @request = map {
if ($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 1024;
+ $row{set} = 'Unicode planes';
+ $row{cell} = do 'charset-ucplanes.inc.pl';
+ @nibble = (map { $_.0, $_.8 } 0 .. 7);
+ $nibsize = 8;
+ }
+ elsif ($row{set} = resolve_alias($input)) {
if ($row{set} eq 'Internal') {
- $row{table} = ' 'x640;
+ $row{table} = ' ' x ($endpoint < 255 ? 640 : 8192);
$row{set} = 'Unicode BMP';
+ $row{cell} = do 'charset-unicode.inc.pl';
}
elsif ($row{set} eq 'utf-8-strict') {
$row{table} = undef;
$row{set} = 'UTF-8';
+ $row{cell} = do 'charset-utf8.inc.pl';
}
else {
$row{table} = decode($row{set}, pack 'C*', $row{offset} .. $endpoint);
@@ -86,363 +101,49 @@ for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) {
);
}
-sub quote {
- local $_ = shift;
- s/"/"/g;
- s/</g;
- s/>/>/g;
- return $_;
-}
-
-sub printcell_unicode {
- my ($value) = @_;
- if ($value > 0x27F) {
- print "\n".'?';
- }
- elsif ($value == 0) {
- print ' | control';
- }
- elsif ($value == 2) {
- print ' | latin';
- }
- elsif ($value == 8) {
- print ' | control';
- }
- elsif ($value == 10) {
- print ' | latin supplement';
- }
- elsif ($value == 0x10) {
- print ' | latin ext-A';
- }
- elsif ($value == 0x18) {
- print ' | latin ext-B';
- }
- elsif ($value == 0x20) {
- print ' | latin ext-B';
- }
- elsif ($value == 0x25) {
- print ' | IPA';
- }
- elsif ($value == 0x2B) {
- print ' | spacing modifier';
- }
- elsif ($value == 0x30) {
- print ' | diacritics';
- }
- elsif ($value == 0x38) {
- print ' | greek';
- }
- elsif ($value == 0x40) {
- print ' | cyrillic';
- }
- elsif ($value == 0x50) {
- print ' | cyrillic+';
- }
- elsif ($value == 0x53) {
- print ' | armenian';
- }
- elsif ($value == 0x58) {
- print ' | hebrew';
- }
- elsif ($value == 0x60) {
- print ' | arabic';
- }
- elsif ($value == 0x70) {
- print ' | syriac';
- }
- elsif ($value == 0x75) {
- print ' | arabic+';
- }
- elsif ($value == 0x78) {
- print ' | thaana';
- }
- elsif ($value == 0x7C) {
- print ' | nko';
- }
- elsif ($value == 0x80) {
- print ' | samaritan';
- }
- elsif ($value == 0x84) {
- print ' | manda';
- }
- elsif ($value == 0x86) {
- print ' | reserved';
- }
- elsif ($value == 0x90) {
- print ' | devanagari';
- }
- elsif ($value == 0x98) {
- print ' | bengali';
- }
- elsif ($value == 0xA0) {
- print ' | gurmukhi';
- }
- elsif ($value == 0xA8) {
- print ' | gujarati';
- }
- elsif ($value == 0xB0) {
- print ' | oriya';
- }
- elsif ($value == 0xB8) {
- print ' | tamil';
- }
- elsif ($value == 0xC0) {
- print ' | telugu';
- }
- elsif ($value == 0xC8) {
- print ' | kannada';
- }
- elsif ($value == 0xD0) {
- print ' | malayalam';
- }
- elsif ($value == 0xD8) {
- print ' | sinhala';
- }
- elsif ($value == 0xE0) {
- print ' | thai';
- }
- elsif ($value == 0xE8) {
- print ' | lao';
- }
- elsif ($value == 0xF0) {
- print ' | tibetan';
- }
- elsif ($value == 0x100) {
- print ' | myanmar';
- }
- elsif ($value == 0x10A) {
- print ' | georgian';
- }
- elsif ($value == 0x110) {
- print ' | hangeul jamo';
- }
- elsif ($value == 0x120) {
- print ' | ethiopic';
- }
- elsif ($value == 0x130) {
- print ' | ethiopic';
- }
- elsif ($value == 0x138) {
- print ' | eth+';
- }
- elsif ($value == 0x13A) {
- print ' | cherokee';
- }
- elsif ($value == 0x140) {
- print ' | unified canadian aboriginal syllabics';
- }
- elsif ($value == 0x160) {
- print ' | unified canadian syllabics';
- }
- elsif ($value == 0x168) {
- print ' | ogham';
- }
- elsif ($value == 0x16A) {
- print ' | runic';
- }
- elsif ($value == 0x170) {
- print ' | tagalog';
- }
- elsif ($value == 0x172) {
- print ' | hanun';
- }
- elsif ($value == 0x174) {
- print ' | buhid';
- }
- elsif ($value == 0x176) {
- print ' | tagb';
- }
- elsif ($value == 0x178) {
- print ' | khmer';
- }
- elsif ($value == 0x180) {
- print ' | mongolian';
- }
- elsif ($value == 0x18B) {
- print ' | canadian+';
- }
- elsif ($value == 0x190) {
- print ' | limbu';
- }
- elsif ($value == 0x195) {
- print ' | tai le';
- }
- elsif ($value == 0x198) {
- print ' | new tai lue';
- }
- elsif ($value == 0x19E) {
- print ' | km';
- }
- elsif ($value == 0x1A0) {
- print ' | lontara';
- }
- elsif ($value == 0x1A2) {
- print ' | tai tham';
- }
- elsif ($value == 0x1AB) {
- print ' | reserved';
- }
- elsif ($value == 0x1B0) {
- print ' | balinese';
- }
- elsif ($value == 0x1B8) {
- print ' | sundanese';
- }
- elsif ($value == 0x1BC) {
- print ' | batak';
- }
- elsif ($value == 0x1C0) {
- print ' | lepcha';
- }
- elsif ($value == 0x1C5) {
- print ' | ol chiki';
- }
- elsif ($value == 0x1C8) {
- print ' | reserved';
- }
- elsif ($value == 0x1CD) {
- print ' | vedic';
- }
- elsif ($value == 0x1D0) {
- print ' | phonetic';
- }
- elsif ($value == 0x1D8) {
- print ' | phonetic+';
- }
- elsif ($value == 0x1DC) {
- print ' | combining';
- }
- elsif ($value == 0x1E0) {
- print ' | latin extended additional';
- }
- elsif ($value == 0x1F0) {
- print ' | greek+';
- }
- elsif ($value == 0x200) {
- print ' | general punctuation';
- }
- elsif ($value == 0x207) {
- print ' | su[bp]script';
- }
- elsif ($value == 0x20A) {
- print ' | currency';
- }
- elsif ($value == 0x20D) {
- print ' | overlay';
- }
- elsif ($value == 0x210) {
- print ' | letterlike';
- }
- elsif ($value == 0x215) {
- print ' | number';
- }
- elsif ($value == 0x219) {
- print ' | arrows';
- }
- elsif ($value == 0x220) {
- print ' | mathematical symbols';
- }
- elsif ($value == 0x230) {
- print ' | miscellaneous technical';
- }
- elsif ($value == 0x240) {
- print ' | control';
- }
- elsif ($value == 0x244) {
- print ' | OCR';
- }
- elsif ($value == 0x246) {
- print ' | enclosed alphanumerics';
- }
- elsif ($value == 0x250) {
- print ' | box drawing';
- }
- elsif ($value == 0x258) {
- print ' | blocks';
- }
- elsif ($value == 0x25A) {
- print ' | geometric shapes';
- }
- elsif ($value == 0x260) {
- print ' | miscellaneous symbols';
- }
- elsif ($value == 0x270) {
- print ' | dingbats';
- }
- elsif ($value == 0x27C) {
- print ' | maths-A';
- }
- elsif ($value == 0x27F) {
- print ' | arr';
+sub range_cell {
+ my ($table, $offset) = @_;
+ my $def = $table->{$offset} or return;
+ my ($len, $class, $name, $title) = @{$def};
+
+ my $attr = '';
+ $len /= $nibsize;
+ $name //= $len <= 2 ? 'res' : 'reserved';
+
+ if (my $part = $offset/$nibsize % 16) {
+ # continued row
+ my $cols = 16 - $part; # remaining
+ $cols = $len if $len < $cols; #TODO: optimise
+ if ($len -= $cols) {
+ # continued on new row
+ $table->{$offset + $nibsize*$cols} = [$len*$nibsize, "$class joinu", $name, $title];
+ $name = '';
+ $class .= ' joind';
+ }
+ $len = $cols;
+ }
+ elsif (my $rows = $len >> 4) {
+ # multiple full rows
+ if ($len -= $rows << 4) {
+ # partial row remains
+ $table->{$offset + $nibsize*$rows * 16} = [$len*$nibsize, "$class joinu", '', $title];
+ $class .= ' joind';
+ }
+ $attr .= sprintf ' rowspan=%d', $rows;
+ $len = 16;
}
-}
-sub printcell_utf8 {
- my ($value) = @_;
- if ($value <= 0x7F) {
- print ' | Single byte ASCII'
- if $value == 0;
- }
- elsif ($value <= 0xBF) {
- print ' | Multi-byte continuation'
- if $value == 0x80;
- }
- elsif ($value <= 0xC1) {
- print ' | (Overl.)'
- if $value == 0xC0;
- }
- elsif ($value <= 0xDF) {
- print ' | 2-byte sequence start'
- if $value == 0xC2;
- print ' | '
- if $value == 0xD0;
- }
- elsif ($value <= 0xEF) {
- print ' | 3-byte sequence start'
- if $value == 0xE0;
- }
- elsif ($value <= 0xF4) {
- print ' | 4-byte sequence'
- if $value == 0xF0;
- }
- elsif ($value <= 0xF7) {
- print ' | (Overflow)'
- if $value == 0xF5;
- }
- elsif ($value <= 0xFB) {
- print ' | 5-byte'
- if $value == 0xF8;
- }
- elsif ($value <= 0xFD) {
- print ' | 6-byte'
- if $value == 0xFC;
- }
- elsif ($value <= 0xFF) {
- print ' | Invalid'
- if $value == 0xFE;
- }
- else {
- print "\n".' | ?';
- }
+ $attr .= sprintf ' colspan=%d', $len unless $len == 1;
+ $attr .= $1 if $class and $class =~ s/( \w+="[^"]*")//;
+ $attr .= sprintf ' class="%s"', $class if $class;
+ $attr .= sprintf ' title="%s"', EscapeHTML($title) if $title;
+ return " | $name";
}
-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;
@@ -450,57 +151,72 @@ for my $row (@request) {
}
print ' | ';
for my $msb (0 .. (length($row->{table}) || 256) - 1 >> 4) {
- printf '%X', $msb + ($row->{offset} >> 4);
+ printf ' |
---|
%X', ($msb + ($row->{offset} >> 4)) * $nibsize;
for my $lsb (0 .. $#nibble) {
- if ($row->{set} eq 'UTF-8') {
- printcell_utf8(($msb<<4) + $lsb);
- next;
- }
- elsif ($row->{set} eq 'Unicode BMP') {
- printcell_unicode(($msb<<4) + $lsb);
+ my $val = ( ($msb<<4) + $lsb ) * $nibsize;
+ if ($row->{cell}) {
+ if (ref $row->{cell} eq 'CODE') {
+ print $row->{cell}->($val);
+ next;
+ }
+ print range_cell($row->{cell}, $val);
next;
}
- my $glyph = substr $row->{table}, ($msb<<4) + $lsb, 1;
+ my $glyph = substr $row->{table}, $val, 1;
if ($glyph eq $NOCHAR) {
print ' | ';
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 7.0
+ | proposed
+ | deprecated
+ | unassigned
+ | invalid
+ |
+
-
|