X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/98699865db67c9772d2a56571e8ddcaee5a5e7bd..f5b22bf2d6aef261464440bd548285b52908be3d:/charset.plp
diff --git a/charset.plp b/charset.plp
index 2dc6964..8b42e62 100644
--- a/charset.plp
+++ b/charset.plp
@@ -1,749 +1,282 @@
-<:
-use utf8;
-use strict;
-use warnings;
-use open IO => ':utf8';
-
-our $VERSION = '1.0';
+<(common.inc.plp)><:
-$header{content_type} = 'text/html; charset=utf-8';
+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'],
+});
-:>
-
+my @tablist = split /[^\w-]+/, $Request || 'default';
-
-charset cheat sheet
-
-
-
-
-
+:>
Character encoding
<:
-my $diinfo = do 'digraphs.inc.pl';
-my %di = map { $diinfo->{$_}->[0] => $_ } grep { ref $diinfo->{$_} }
- keys %$diinfo;
+use POSIX qw( ceil );
+use Shiar_Sheet::FormatChar;
+my $glyphs = Shiar_Sheet::FormatChar->new;
+my @request;
-use Encode qw(decode resolve_alias);
-# generate character table(s)
-# (~16x faster than decoding in loop;
-# 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)],
- 0 => [qw(cp437 cp863)],
- 1 => [qw(iso-8859-1 cp1252 MacRoman cp850)],
- 2 => [qw(iso-8859-2 cp1250 cp852 MacCentralEurRoman MacCroatian MacRumanian)],
- 5 => [qw(koi8-f iso-8859-5 cp1251 MacCyrillic cp855 cp866)],
- 7 => [qw(iso-8859-7 cp1253 MacGreek cp737 cp869)],
- 8 => [qw(iso-8859-8 cp1255 MacHebrew cp862)],
-);
-my @request = map {
- if (my $input = $_) {
- my %row = (offset => 0);
- my $endpoint = 255;
- if ($input =~ s/^--//) {
- $row{offset} = $endpoint > 160 ? 160 : 48;
- }
- elsif ($input =~ s/^-//) {
- $row{offset} = $endpoint > 128 ? 128 : 32;
+sub tabinput {
+ # generate character table(s)
+ my $input = shift or return;
+
+ state $ALIAS = {
+ default => [qw( unicode+0-192 utf-8 iso-8859-1 cp1252+128-159 iso-8859-15+160-191 cp437 cp850+128 )],
+ us => [qw( cp437 cp863+128 AdobeStandardEncoding gsm0338+0-127 )],
+ ebcdic => [qw( cp37 cp500 cp875 cp1026 cp1047 posix-bc )],
+ westeur => [qw( iso-8859-1 iso-8859-15+160-191 cp1252+128-159 iso-8859-14+160 cp850+128 MacRoman+128 nextstep+128 hp-roman8+160 )],
+ centeur => [qw( iso-8859-2 iso-8859-16+160 cp1250+128 cp852+128 MacCentralEurRoman+128 MacCroatian+128 MacRomanian+128 )], # MacRumanian only for DB
+ turkish => [qw( iso-8859-3 iso-8859-9+128 cp857+128 cp1254+128 MacTurkish+128 )],
+ baltic => [qw( iso-8859-4 iso-8859-13+160 cp775+128 cp1257+128 )],
+ nordic => [qw( iso-8859-10 cp865+128 cp861+160-191 MacIcelandic+128 MacSami+160 )],
+ cyrillic => [qw( koi8-f koi8-r+128-192 koi8-u+160-192 iso-8859-5+128 cp1251+128 MacCyrillic+128 cp855+128 cp866+128 )], # MacUkrainian is broken
+ arabic => [qw( iso-8859-6 cp1006+160 cp864+128 cp1256+128 MacArabic )], # MacFarsi same as MacArabic?
+ greek => [qw( iso-8859-7 cp1253+128 MacGreek+128 cp737+128 cp869+128 )],
+ hebrew => [qw( iso-8859-8 cp1255+128 MacHebrew+128 cp862+128 )],
+ thai => [qw( iso-8859-11 cp874+128-159 MacThai+128 )],
+ vietnamese => [qw( viscii cp1258 MacVietnamese )],
+ symbol => [qw( symbol dingbats MacDingbats AdobeZdingbat AdobeSymbol )],
+ # iso-code shorthand
+ 1 => 'westeur',
+ 2 => 'centeur',
+ 3 => 'turkish',
+ 4 => 'baltic',
+ 5 => 'cyrillic',
+ 6 => 'arabic',
+ 7 => 'greek',
+ 8 => 'hebrew',
+ 9 => 'turkish',
+ 10 => 'nordic',
+ 11 => 'thai',
+ };
+ if (my $follow = $ALIAS->{$input}) {
+ tabinput($_) for ref $follow ? @{$follow} : $follow;
+ return;
+ }
+
+ my %row = (offset => 0, cols => 16);
+ my $endpoint = 255;
+ my $params = $input =~ s/[+](.*)\z// ? $1 : undef;
+
+ if (defined $params and $params =~ m/^ (\d+) (-\d+)? /x) {
+ $row{offset} = $1;
+ $endpoint = -$2 if $2;
+ }
+ if ($row{offset}) {
+ $row{setnote} = 'over cp437' if $input eq 'cp850';
+ $row{setnote} = 'over iso-8859-1' if $input =~ /^iso-8859-|^cp125/;
+ }
+
+ if ($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'
+ or Alert('Table data could not be read', $@ || $!);
+ $row{cols} *= 2;
+ }
+ elsif ($row{set} = Encode::resolve_alias($input)) {
+ if ($row{set} eq 'Internal') {
+ $row{table} = ' ' x ($endpoint < 255 ? 640 : 8192);
+ $row{set} = 'Unicode BMP';
+ $row{cell} = do 'charset-unicode.inc.pl'
+ or Alert('Table data could not be read', $@ || $!);
}
- if ($input =~ s/-$//) {
- $endpoint = $row{offset} ? $row{offset} < 160 ? 159 : 191 : 127;
- }
- if ($row{set} = resolve_alias($input)) {
- if ($row{set} eq 'Internal') {
- $row{table} = ' ' x ($endpoint < 255 ? 640 : 4096);
- $row{set} = 'Unicode BMP';
- }
- elsif ($row{set} eq 'utf-8-strict') {
- $row{table} = undef;
- $row{set} = 'UTF-8';
- }
- else {
- $row{table} = decode($row{set}, pack 'C*', $row{offset} .. $endpoint);
- }
+ elsif ($row{set} eq 'utf-8-strict') {
+ $row{table} = undef;
+ $row{set} = 'UTF-8';
+ $row{cell} = do 'charset-utf8.inc.pl'
+ or Alert('Table data could not be read', $@ || $!);
}
else {
- print "Encoding $input unknown
\n";
+ $row{table} = Encode::decode($row{set}, pack 'C*', $row{offset} .. $endpoint);
+ # (~16x faster than decoding in loop;
+ # substr strings is twice as fast as splitting to an array)
+
+ if ($row{set} eq 'cp437') {
+ 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
+ );
+ }
}
- \%row;
}
else {
- ();
+ Alert("Encoding $input
unknown");
+ return;
}
-} map { defined $ALIAS{$_} ? @{ $ALIAS{$_} } : $_ }
- $ENV{PATH_INFO} =~ /\w/ ? split(m{[/+\s]}, $ENV{PATH_INFO}) : 'default';
+ push @request, \%row;
+}
+tabinput($_) for @tablist;
+
my $NOCHAR = chr 0xFFFD;
-for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) {
- substr($request[$cp437]->{table}, 237, 1) = pack 'U*', 0x3D5; # phi sign
- substr($request[$cp437]->{table}, 0, 32) = pack 'U*', map {hex} qw(
- 2007 263A 263B 2665 2666 2663 2660 2022 25D8 25CB 25D9 2642 2640 266A 266B 263C
- 25BA 25C4 2195 203C 00B6 00A7 25AC 21A8 2191 2193 2192 2190 221F 2194 25B2 25BC
- );
-}
+sub range_cell {
+ my ($info, $offset) = @_;
+ my $table = $info->{cell} or return;
+ my $def = $table->{$offset} or return;
+ my ($len, $class, $name, $title) = @{$def};
-sub quote {
- local $_ = shift;
- s/"/"/g;
- s/</g;
- s/>/>/g;
- return $_;
-}
+ my $cols = $info->{cols};
+ my $colsize = $table->{colsize} || 1;
+ my $attr = '';
+ $len /= $colsize;
+ $name //= $len <= 2 ? 'res' : 'reserved';
-sub printcell_unicode {
- my ($value) = @_;
- if ($value > 0xFFF) {
- print "\n".'?';
- }
- elsif ($value == 0) {
- print ' | control';
- }
- elsif ($value == 2) {
- print ' | comn';
- }
- elsif ($value == 4) {
- print ' | basic latin';
- }
- elsif ($value == 8) {
- print ' | control';
- }
- elsif ($value == 10) {
- print ' | comn';
- }
- elsif ($value == 12) {
- print ' | latin1';
- }
- elsif ($value == 0x10) {
- print ' | latin extended-A';
- }
- elsif ($value == 0x18) {
- print ' | latin extended-B';
- }
- elsif ($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 ($value == 0x7C) {
- print ' | n\'ko';
- }
- elsif ($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 ' | suþscript'; # suth now means "sub and/or sup"
- }
- 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 ($value == 0x27F) {
- print ' | arr';
- }
- elsif ($value == 0x280) {
- print ' | braille';
- }
- elsif ($value == 0x290) {
- print ' | supplemental arrows-B';
- }
- elsif ($value == 0x298) {
- print ' | mathematical symbols-B';
- }
- elsif ($value == 0x2A0) {
- print ' | supplemental mathematical operators';
- }
- elsif ($value == 0x2B0) {
- print ' | miscellaneous symbols and arrows';
- }
- elsif ($value == 0x2C0) {
- print ' | glagolitic';
- }
- elsif ($value == 0x2C6) {
- print ' | latin-C';
- }
- elsif ($value == 0x2C8) {
- print ' | coptic';
- }
- elsif ($value == 0x2D0) {
- print ' | georgian+';
- }
- elsif ($value == 0x2D3) {
- print ' | tifinagh'; #TODO: proto-canaanite
- }
- elsif ($value == 0x2D8) {
- print ' | ethiopic+';
- }
- elsif ($value == 0x2DE) {
- print ' | cyrl-A';
- }
- elsif ($value == 0x2E0) {
- print ' | punctuation+';
- }
- elsif ($value == 0x2E8) {
- print ' | cjk radicals';
- }
- elsif ($value == 0x2F0) {
- print ' | kangxi radicals';
- }
- elsif ($value == 0x2FE) {
- print ' | ';
- }
- elsif ($value == 0x2FF) {
- print ' | idc';
- }
- elsif ($value == 0x300) {
- print ' | cjk misc';
- }
- elsif ($value == 0x304) {
- print ' | hiragana';
- }
- elsif ($value == 0x30A) {
- print ' | katakana';
- }
- elsif ($value == 0x310) {
- print ' | bopomofo';
- }
- elsif ($value == 0x313) {
- print ' | hangeul compat';
- }
- elsif ($value == 0x319) {
- print ' | kbn';
- }
- elsif ($value == 0x31A) {
- print ' | bpmf';
- }
- elsif ($value == 0x31C) {
- print ' | strokes';
- }
- elsif ($value == 0x31F) {
- print ' | k+';
- }
- elsif ($value == 0x320) {
- print ' | enclosed cjk characters';
- }
- elsif ($value == 0x330) {
- print ' | cjk compatibility';
- }
- elsif ($value == 0x340) {
- print ' | cjk unified ideographs extension A';
- }
- elsif ($value == 0x4D0) {
- print ' | cjk unified ideographs extension A';
- }
- elsif ($value == 0x4DC) {
- print ' | hexagrams';
- }
- elsif ($value == 0x4E0) {
- print ' | cjk unified ideographs';
- }
- elsif ($value == 0xA00) {
- print ' | yi';
- }
- elsif ($value == 0xA40) {
- print ' | yi';
- }
- elsif ($value == 0xA49) {
- print ' | yi radicals';
- }
- elsif ($value == 0xA4D) {
- print ' | lisu';
- }
- elsif ($value == 0xA50) {
- print ' | vai';
- }
- elsif ($value == 0xA60) {
- print ' | vai';
- }
- elsif ($value == 0xA64) {
- print ' | cyrillic extended-B';
- }
- elsif ($value == 0xA6A) {
- print ' | bamum';
- }
- elsif ($value == 0xA70) {
- print ' | tones';
- }
- elsif ($value == 0xA72) {
- print ' | latin extended-D';
- }
- elsif ($value == 0xA80) {
- print ' | sylheti';
- }
- elsif ($value == 0xA83) {
- print ' | in';
- }
- elsif ($value == 0xA84) {
- print ' | phags-pa';
- }
- elsif ($value == 0xA88) {
- print ' | saurashtra';
- }
- elsif ($value == 0xA8E) {
- print ' | deva+';
- }
- elsif ($value == 0xA90) {
- print ' | kayah li';
- }
- elsif ($value == 0xA93) {
- print ' | rejang';
- }
- elsif ($value == 0xA96) {
- print ' | jamo-A';
- }
- elsif ($value == 0xA98) {
- print ' | javanese';
- }
- elsif ($value == 0xA9E) {
- print ' | res';
- }
- elsif ($value == 0xAA0) {
- print ' | cham';
- }
- elsif ($value == 0xAA6) {
- print ' | mym-A';
- }
- elsif ($value == 0xAA8) {
- print ' | tai viet';
- }
- elsif ($value == 0xAAE) {
- print ' | mtei+';
- }
- elsif ($value == 0xAB0) {
- print ' | reserved';
- }
- elsif ($value == 0xABC) {
- print ' | manipuri';
- }
- elsif ($value == 0xAC0) {
- print ' | hangeul syllables';
- }
- elsif ($value == 0xD70) {
- print ' | hangeul syllables';
- }
- elsif ($value == 0xD7B) {
- print ' | haungeul jamo-B';
- }
- elsif ($value == 0xD80) {
- print ' | high surrogates';
- }
- elsif ($value == 0xDC0) {
- print ' | low surrogates';
- }
- elsif ($value == 0xE00) {
- print ' | private use';
- }
- elsif ($value == 0xF90) {
- print ' | cjk compatibility ideographs';
- }
- elsif ($value == 0xFB0) {
- print ' | presentation';
- }
- elsif ($value == 0xFB5) {
- print ' | ';
- }
- elsif ($value == 0xFC0) {
- print ' | arabic presentation forms A';
- }
- elsif ($value == 0xFD0) {
- print ' | ';
- }
- elsif ($value == 0xFDD) {
- print ' | ?';
- }
- elsif ($value == 0xFDF) {
- print ' | ';
- }
- elsif ($value == 0xFE0) {
- print ' | var';
- }
- elsif ($value == 0xFE1) {
- print ' | ver';
- }
- elsif ($value == 0xFE2) {
- print ' | ½';
- }
- elsif ($value == 0xFE3) {
- print ' | comp';
- }
- elsif ($value == 0xFE5) {
- print ' | small';
- }
- elsif ($value == 0xFE7) {
- print ' | arabic presentation B';
- }
- elsif ($value == 0xFF0) {
- print ' | halfwidth & fullwidth forms';
- }
- elsif ($value == 0xFFF) {
- print ' | sp';
+ if (my $part = $offset/$colsize % $cols) {
+ # continued row
+ my $rest = $cols - $part; # remaining
+ $rest = $len if $len < $rest; #TODO: optimise
+ if ($len -= $rest) {
+ # continued on new row
+ my @next = ($len * $colsize, "$class joinu");
+ if ($len > $rest) {
+ # minority remains
+ push @next, $name, $title;
+ $title ||= $name;
+ $name = '';
+ }
+ else {
+ # minority on next row
+ push @next, '"', $title || $name;
+ }
+ $table->{$offset + $colsize*$rest} //= \@next;
+ $class .= ' joind';
+ }
+ $len = $rest;
+ }
+ elsif (my $rows = int($len / $cols)) {
+ # multiple full rows
+ if ($len -= $rows * $cols) {
+ # partial row remains
+ $table->{$offset + $colsize*$rows * $cols} //= [$len*$colsize, "$class joinu", '', $title];
+ $class .= ' joind';
+ }
+ $attr .= sprintf ' rowspan=%d', $rows;
+ $len = $cols;
}
-}
-sub printcell_utf8 {
- my ($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 '%s', $row->{set};
- print '';
+ my $cols = $row->{cols};
+ my $colsize = $row->{cell} && $row->{cell}->{colsize} || 1;
+ my $coldigits = ceil(log($colsize * $cols) / log(16)); # uniform length of hexadecimal header
+ my $rowdiv = 16 ** $coldigits; # row divide for column digits
+ $rowdiv = 1 if $rowdiv != $cols * $colsize; # divide only if all columns are matched
+ my $offset = 0;
+ my $endpoint = $offset + (length($row->{table}) || 256) * $colsize;
+
+ printf '', !$row->{cell} && ' charmap';
+ my $title = $row->{set};
+ $title .= " " for $row->{setnote} // ();
+ printf '%s', $title;
+ print '' x ($cols + 1);
for my $section (qw{thead}) {
- print "<$section>â±";
- print ' | ', $_ for @nibble;
+ print "<$section> |
---|
", $rowdiv == 1 ? '+' : 'â±';
+ printf ' | %0*X', $coldigits, $_ * $colsize for 0 .. $cols - 1;
print "\n";
}
print ' | ';
- for my $msb (0 .. (length($row->{table}) || 256) - 1 >> 4) {
- printf '%X', $msb + ($row->{offset} >> 4);
- for my $lsb (0 .. $#nibble) {
- if ($row->{set} eq 'UTF-8') {
- printcell_utf8(($msb<<4) + $lsb);
- next;
+ while ($offset < $endpoint - 1) {
+ print ' |
---|
';
+ {
+ if (my $rowmod = $offset % $rowdiv) {
+ # offset in column units
+ printf '+%X', $rowmod;
+ }
+ else {
+ # divided row offset
+ printf '%X', ($offset + $row->{offset}) / $rowdiv;
}
- elsif ($row->{set} eq 'Unicode BMP') {
- printcell_unicode(($msb<<4) + $lsb);
+ }
+ for (1 .. $cols) {
+ if ($row->{cell}) {
+ print range_cell($row, $offset);
next;
}
- my $glyph = substr $row->{table}, ($msb<<4) + $lsb, 1;
+ my $glyph = substr $row->{table}, $offset, 1;
if ($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);
+ }
+ continue {
+ $offset += $colsize;
}
print "\n";
}
- print " |
---|
\n";
+ say ' ';
}
-print " \n";
-
:>
-
+
+
+ control
+ | whitespace
+ | diacritic
+ | punctuation
+ | symbol
+ | numeric
+ | greek
+ | aramaic
+ | syllabic
+ african
+ | japanese
+ | cjk
+ | chinese
+ |
+ | alphabetic
+ |
+
+
+ unicode 7.0
+ | proposed
+ | deprecated
+ | unassigned
+ | invalid
+ |
+
-
|