-<:
-use utf8;
-use strict;
-use warnings;
-use open IO => ':utf8';
-
-use Unicode::UCD qw(charinfo);
+<(common.inc.plp)><:
+use 5.010; # state
+
+Html({
+ title => 'digraph cheat sheet',
+ version => 'v1.1',
+ description => [
+ "Complete table of digraph characters from RFC-1345.",
+ ],
+ keywords => [qw'
+ digraph mnemonic compose composition pair
+ character char glyph table unicode vim
+ '],
+ stylesheet => [qw'light'],
+ data => [qw( digraphs.inc.pl )],
+});
-our $VERSION = '1.0';
-
-$header{content_type} = 'text/html; charset=utf-8';
+:>
+<h1>RFC-1345 Digraphs</h1>
-:><!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
- "http://www.w3.org/TR/html4/loose.dtd">
-<html>
+<p>Character mnemonics
+following composition key ⎄:
+i^k in <a href="/vi">Vim</a>,
+^u^\ in <a href="/readline">Emacs</a>,
+^a^v in <a href="/screen">Screen</a>.
+Also see <a href="/unicode">common Unicode</a>.</p>
-<head>
-<title>digraph cheat sheet</title>
-<meta http-equiv="content-type" content="utf-8">
-<style>
-h1 {
- text-align: center;
- margin: 0 auto 0.2em;
-}
-table {
- border-collapse: collapse;
- table-layout: fixed; /* prevent resizing, notably in msie6 */
-}
-#legend {
- margin-top: 1em;
-}
-#legend table {
- width: 100%;
- table-layout: auto;
-#}
-#legend td {
- padding: 0 0.2em;
-}
-thead th, td {
- width: 1.2em; /* msie only looks at the first row */
- min-width: 1em; /* prevents gecko from restricting to page width */
-}
-th, td {
- text-align: center;
-}
-td {
- border: 1px solid #888;
- background: #DDD;
-}
-td.X {
- background: #FFF;
-}
+<p class="aside">Unofficial <span class="u-prop ex">proposals</span>
+are available as <a href="/digraphs.vim">ex commands</a>.</p>
-td.Lm, td.Mc, td.Me, td.Zl, td.Zp, td.Cs {background:red} /* unknown */
-
-/* letters */
-td.Greek {background: #FFE0CF}
-td.Cyrillic {background: #FFDDA8}
-td.Latin {background: #FFB}
-td.Hebrew {background: #FFD}
-td.Arabic {background: #EFE}
-td.Hiragana {background: #DFC}
-td.Katakana {background: #DFA}
-td.Bopomofo {background: #BFC}
-
-td.Nd, td.Nl,
-td.No {background: #FBB} /* number */
-td.Sc {background: #FCD} /* currency */
-td.Sm {background: #ECE} /* math */
-td.So {background: #DDCCFF} /* symbol */
-td.Cf, td.Pd,
-td.Po {background: #CDF} /* punctuation */
-td.Ps, td.Pe, td.Pi,
-td.Pf {background: #BEF} /* quote */
-td.Lm,
-td.Sk {background: #CEE} /* spacing modifier */
-td.Mn {background: #ACC} /* modifier */
-td.Cc {background: #BBB; color: #666} /* control */
-td.Zs {background: #ACB} /* space */
-td.Zs span {background: #EEE}
-
-td.Xa {color: #040} /* ascii */
-td.Xl {color: #080} /* latin1 */
-td.Co {color: #800} /* private */
-td.Xz {color: #F00} /* proposed */
-
-tr:hover td {
- background: #FF8;
+<:
+my $di = do 'digraphs.inc.pl'
+ or die "Error loading digraphs data: ", $@ // $!;
+
+if (exists $get{v}) {
+ # show characters for inverted mnemonics (vim alternatives)
+ $di->{ substr($_, 1, 1) . substr($_, 0, 1) } ||=
+ [ $di->{$_}->[0], '', 'l0 ex', '', $di->{$_}->[4] ]
+ for grep { ref $di->{$_} } keys %{$di};
}
-</style>
-</head>
-<body>
-<h1>RFC-1345 Digraphs</h1>
+my @chars = (
+ [qw{! " % ' ( ) * + , - . /}],
+ ['0'..'9'], [qw{: ; < = > ?}],
+ ['A'..'M'], ['N'..'Z'],
+ ['a'..'m'], ['n'..'z'],
+);
+my @chars2 = (['_'], @chars); # trailing character (extended set)
+my @columns = !exists $get{split} ? \@chars2 :
+ ([@chars2[0, 1, 3, 4, 6]], [@chars2[2, 5, 7]]);
+
+if (exists $get{xorg}) {
+ my $xorg = do 'data/digraphs-xorg.inc.pl'
+ or die "Error loading Xorg data: ", $@ // $!;
+ $_ = [ord $_] for values %{$xorg};
+ $xorg->{$_}->[2] = # class = compatibility
+ $di->{$_} ? $di->{$_}->[0] != $xorg->{$_}->[0] ? 'l1' : # conflict
+ $di->{$_}->[2] =~ /\bu-di\b/ ? 'l5' : 'l3' : 'l2' # rfc|any|none
+ for keys %{$xorg};
+
+ for my $cp (map {$_->[0]} values %{$xorg}) {
+ next if (state $seen = {})->{$cp}++; # List::MoreUtils::uniq
+
+ # find multiple equivalent mnemonics
+ my @equiv = grep {$cp eq $_->[0]}
+ map {$xorg->{$_}} sort keys %{$xorg}; # values ordered by mnem.
+
+ # search for the most compatible match
+ my ($compat) = sort {
+ $equiv[$b]->[2] cmp $equiv[$a]->[2] # highest level
+ || $b <=> $a # fallback to last mnemonic
+ } 0 .. $#equiv;
+
+ # reclassify all but one as level 0 (omitted)
+ splice @equiv, $compat // -1, 1, ();
+ $_->[2] = 'l0 ex' for @equiv;
+ }
-<:
-my $di = do 'digraphs.inc.pl';
-
-sub quote {
- local $_ = shift;
- s/"/"/g;
- s/</</g;
- s/>/>/g;
- return $_;
+ $chars2[0] = [qw( # ^ _ ` ~ )];
+ @chars = @chars2;
+ $di = $xorg;
}
-my @chars = ((map {chr} ord '!' .. ord 'Z'), 'a'..'z');
-splice @chars, $_, 1, () for 2, 3-1, 5-2, 31-3; # remove character exceptions # $ & @
-my @chars2 = (@chars, '_'); # trailing character (extended set)
-
-print '<table>';
+for my $colchars (@columns) {
+print '<table class="glyphs dimap"><col>';
+print qq'<colgroup span="$_">' for map {scalar @$_} @{$colchars};
+print "</colgroup><col>\n";
for my $section (qw{thead tfoot}) {
- print "<$section><tr><th> ";
- print "<th>$_" for @chars2;
+ print "<$section><tr><th>↳";
+ print '<th>', EscapeHTML($_) for map {@$_} @{$colchars};
+ print "<th> \n";
}
-print '<tbody>';
-for my $c1 (@chars) {
- print "<tr><th>$c1";
- for my $c2 (@chars2) {
- my $mnem = $c1 . $c2;
- if (not defined $di->{$mnem}) {
- print '<td>';
- next;
+for my $c1group (@chars) {
+ print '<tbody>';
+ for my $c1 (@$c1group) {
+ print '<tr><th>', EscapeHTML($c1);
+ for my $c2 (map {@$_} @$colchars) {
+ my $mnem = $c1 . $c2;
+ if (not defined $di->{$mnem}) {
+ print '<td>';
+ next;
+ }
+ if (ref $di->{$mnem} ne 'ARRAY') {
+ printf '<td class="X Xr" title="%s">', EscapeHTML($mnem);
+ next;
+ }
+ my ($codepoint, $name, $prop, $script, $string) = @{ $di->{$mnem} };
+
+ my $glyph = $string || chr $codepoint;
+ utf8::upgrade($glyph); # prevent latin1 output
+ my $desc = $mnem . ($name && " ($name)");
+ my @class = ('X', grep {$_} $prop, $script);
+
+ $glyph = EscapeHTML($glyph);
+ $glyph = "<span>$glyph</span>" if $script =~ /\bZs\b/;
+
+ printf "\n".'<td class="%s" title="%s">%s',
+ join(' ', @class), EscapeHTML($desc), $glyph;
}
- my $chr = $di->{$mnem};
- my $glyph = chr $chr;
- utf8::upgrade($glyph); # prevent latin1 output
- my $info = charinfo($chr);
-
- my $desc = $mnem;
- $desc .= " ($_)" for $info->{name} || ();
-
- my @class = 'X';
- push @class, $_ for $info->{category} || ();
- push @class, $_ for $info->{script} || ();
-
- $glyph = quote($glyph);
- $glyph = "<span>$glyph</span>" if $info->{category} eq 'Zs';
-
- printf "\n".'<td class="%s" title="%s">%s',
- join(' ', @class), quote($desc), $glyph;
+ print "\n<th>", EscapeHTML($c1), "\n";
}
- print "\n<th>$c1\n";
}
print "</table>\n";
+print '<hr>' if exists $get{split};
+}
+
+if (exists $get{xorg}) {
:>
-<div id="legend">
- <table><tr>
+<div class="legend">
+ <table class="glyphs"><tr>
+ <td class="X l5">matching RFC-1345
+ <td class="X l3">matching proposal
+ <td class="X l2">unique to Xorg
+ <td class="X l1">conflict
+ <td class="X l0 ex">duplicate
+ </table>
+</div>
+<: } else { :>
+<div class="legend">
+ <table class="glyphs"><tr>
<td class="X Cc">control
- <td class="X Zs"><span>spacing</span>
- <td class="X Mn">modifier
- <td class="X Sk">spacing modifier
+ <td class="X Zs"><span>space</span>
+ <td class="X Mn">combining
+ <td class="X Sk">spacing modifier
<td class="X Pf">quote
<td class="X Po">punctuation
<td class="X So">symbol
<td class="X Latin">latin
<td class="X Hebrew">hebrew
<td class="X Arabic">arabic
+ <td class="X Hangul">korean
<td class="X Hiragana">japanese
<td class="X Bopomofo">chinese
</table>
- <table><tr>
+ <table class="glyphs"><tr>
<td class="X">unicode
- <td class="X Xa">ascii
<td class="X Xl">latin1
- <td class="X Co">private
- <td class="X Xz">proposed
+ <td class="X Xa">ascii
+ <td class="X u-prop">vim extension
+ <td class="X u-prop ex">proposal
+ <td class="X ex">not in vim
</table>
</div>
-</html>
+<: }