package Shiar_Sheet::FormatChar;
+use 5.010;
use strict;
use warnings;
+use utf8;
use Data::Dump 'pp';
use PLP::Functions 'EscapeHTML';
EscapeHTML($_[0]), # cell
join(' | ', map { $_->[1] } @chars), # title
$chars[0][2], # class
- join(' ', grep { defined } map { $_->[3] } @chars), # digraph
+ join(' ', map { $_->[3] // '…' } @chars), # digraph
);
}
push @class, 'u-invalid';
$cell = '';
}
- else {
+ else {{
push @class, 'X';
if ($input =~ s/^-//) {
$input =~ s/^\\//; # escaped char
($cell, $title, my $class, $mnem, $entity) = $self->glyphs_html($input);
+ my $codepoint = ord $input;
+
+ if ($self->{style} eq 'univer') {
+ if ($input =~ /\p{age=unassigned}/) {
+ # check include for assignments after unicode 6.0 (perl v5.14)
+ state $agemap = do 'unicode-age.inc.pl';
+ my $version = $agemap->{$codepoint};
+ push @class, $version ? 'l2' : 'l1';
+ }
+ elsif ($input =~ /^\p{in=1.1}*$/) {
+ push @class, 'l5'; # first release 1993
+ }
+ elsif ($input =~ /^\p{in=3.0}*$/) {
+ push @class, 'l4'; # 20th century
+ }
+ elsif ($input =~ /^\p{in=4.1}*$/) {
+ push @class, 'l4'; # over 10 years ago
+ }
+ elsif ($input =~ /^\p{in=6.0}*$/) {
+ push @class, 'l3'; # before 2012
+ }
+ else {
+ push @class, 'l2'; # more recent
+ }
+ next;
+ }
if ($self->{style} eq 'di') {
- if ($class =~ /\bu-di\b/) {
- push @class, ('l3', 'u-di'); # standard digraph
+ if ($mnem =~ /…/) {
+ # incomplete representation, usually partial
+ }
+ elsif ($class =~ /\bu-di\b/) {
+ push @class, ('l4', 'u-di'); # standard digraph
}
elsif ($class =~ /\bu-prop\b/) {
- push @class, ('l2', 'u-prop'); # unofficial
+ push @class, ('l3', 'u-prop'); # unofficial
}
}
elsif ($self->{style} eq 'html') {
if (defined $entity) {
- push @class, ('l3', 'u-html');
+ push @class, ($codepoint <= 0xFF ? 'l4' : 'l3', 'u-html');
}
}
else {
- my $codepoint = ord(substr $input, 0, 1);
if ($codepoint <= 0xFF) {
- push @class, 'l3', 'u-lat1'; # latin1
+ push @class, 'l4', 'u-lat1'; # latin1
}
elsif ($codepoint <= 0xD7FF) {
- push @class, 'l2', 'u-bmp'; # bmp
+ push @class, 'l3', 'u-bmp'; # bmp
}
}
if ($input =~ /[ -~]/) {
- push @class, 'l4', 'u-ascii'; # ascii
+ push @class, 'l5', 'u-ascii'; # ascii
+ }
+ elsif ($input =~ /^\p{in=6.0}+$/) {
+ push @class, 'l2'; # in unicode 6.0
}
else {
- push @class, 'l1'; # basic unicode
+ push @class, 'l1'; # any unicode
}
- }
+ }}
my $anno = '';
if ($cell ne '') {
}
}
- return sprintf('<td%s%s%s>%s%s',
- defined $title ? qq{ title="$title"} : '',
- @class ? sprintf(' class="%s"', join ' ', @class) : '',
- $html || '',
+ return sprintf('<%s>%s%s',
+ join(' ', 'td',
+ defined $title ? qq{ title="$title"} : (),
+ @class ? sprintf('class="%s"', join ' ', @class) : (),
+ $html || (),
+ ),
$cell eq '' ? ' ' : $cell,
$anno,
);
if ($cell =~ s/^>//) {
# header cell text follows
$cell =~ s/_/ /g; # underscores may be used instead of whitespace (for qw//ability)
- $rows[-1] .= '<th>'.($cell || ' ');
+ my $class = $cell =~ s/^-// && ' class="ex"';
+ $rows[-1] .= "<th$class>".($cell || ' ');
}
next;
}
$colspan++;
next;
}
+ elsif ($cell eq '>-') {
+ $rows[-1] .= '<th>';
+ next;
+ }
$rows[-1] .= $self->cell($cell,
- $colspan > 1 && qq{ colspan="$colspan"},
+ $colspan > 1 && qq{colspan="$colspan"},
);
$colspan = 1;