X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/78ab2cc012e8290671af6f601d78ba3530dab3aa..133e96335267b12bb7e97d9bbe551a3a043bd32a:/Shiar_Sheet/FormatChar.pm?ds=inline
diff --git a/Shiar_Sheet/FormatChar.pm b/Shiar_Sheet/FormatChar.pm
index 72d2e3d..f471497 100644
--- a/Shiar_Sheet/FormatChar.pm
+++ b/Shiar_Sheet/FormatChar.pm
@@ -8,7 +8,7 @@ use utf8;
use Data::Dump 'pp';
use PLP::Functions 'EscapeHTML';
-our $VERSION = '1.08';
+our $VERSION = '1.10';
our $uc = do 'data/unicode-char.inc.pl';
@@ -17,14 +17,25 @@ sub new {
bless { anno => ['di', 0], style => 'di' }, $class;
}
-sub glyph_info {
+sub glyph_mkinfo {
my ($self, $codepoint) = @_;
- return $uc->{chr $codepoint} || eval {
+ # attempt to get unicode character information
+ my $info = eval {
require Unicode::UCD;
- if (my $fullinfo = Unicode::UCD::charinfo($codepoint)) {
- return [@$fullinfo{qw/category name - string/}];
- }
- } || [];
+ Unicode::UCD::charinfo($codepoint)
+ || { category => 'Xn', name => '' };
+ } or return;
+ my $string;
+ if ($info->{combining}) {
+ # overlay combining diacritics
+ $string = chr(9676) . chr($codepoint);
+ }
+ return [@$info{qw( category name )}, undef, $string];
+}
+
+sub glyph_info {
+ my ($self, $codepoint) = @_;
+ return $uc->{chr $codepoint} || $self->glyph_mkinfo($codepoint) || [];
}
sub glyph_html {
@@ -61,6 +72,31 @@ sub glyph_cell {
return sprintf('
%s', $self->glyph_html($char));
}
+sub glyph_level_univer {
+ my ($self, $input) = @_;
+ if ($input =~ /\p{age=unassigned}/) {
+ # check include for assignments after unicode 6.0 (perl v5.14)
+ state $agemap = do 'data/unicode-age.inc.pl';
+ my $version = $agemap->{ord $input};
+ return $version ? 'l2' : 'l1';
+ }
+ elsif ($input =~ /^\p{in=1.1}*$/) {
+ return 'l5'; # first release 1993
+ }
+ elsif ($input =~ /^\p{in=3.0}*$/) {
+ return 'l4'; # 20th century
+ }
+ elsif ($input =~ /^\p{in=4.1}*$/) {
+ return 'l4'; # over 10 years ago
+ }
+ elsif ($input =~ /^\p{in=6.0}*$/) {
+ return 'l3'; # before 2012
+ }
+ else {
+ return 'l2'; # more recent
+ }
+}
+
sub cell {
my ($self, $input, $html) = @_;
my (@class, $title, $cell, $mnem, $entity);
@@ -81,33 +117,13 @@ sub cell {
$input =~ s/^\\//; # escaped char
($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 'data/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
- }
+ push @class, $self->glyph_level_univer($input);
next;
}
+ my $codepoint = ord $input;
if ($self->{style} eq 'di') {
if ($mnem and $mnem =~ /â¦/) {
# incomplete representation, usually partial
|