unicode: prepend unicode 6.0 support level

Distinguish more recent characters as .l2 in all modes.
In html mode, further distinguish latin1 (i.e. HTML version 3.2) subset
from HTML4 entities.

diff --git a/Shiar_Sheet/FormatChar.pm b/Shiar_Sheet/FormatChar.pm
index 35f60765c7c394022482159c694629272b13fb2c..8b00318a43850ee2a5ad5567de66f317a71589f2 100644 (file)
--- a/Shiar_Sheet/FormatChar.pm
+++ b/Shiar_Sheet/FormatChar.pm
@@ -109,31 +109,34 @@ sub cell {
 
                if ($self->{style} eq 'di') {
                        if ($class =~ /\bu-di\b/) {
 
                if ($self->{style} eq 'di') {
                        if ($class =~ /\bu-di\b/) {

-                               push @class, ('l3', 'u-di'); # standard digraph
+                               push @class, ('l4', 'u-di'); # standard digraph

                        }
                        elsif ($class =~ /\bu-prop\b/) {
                        }
                        elsif ($class =~ /\bu-prop\b/) {

-                               push @class, ('l2', 'u-prop'); # unofficial
+                               push @class, ('l3', 'u-prop'); # unofficial

                        }
                }
                elsif ($self->{style} eq 'html') {
                        if (defined $entity) {
                        }
                }
                elsif ($self->{style} eq 'html') {
                        if (defined $entity) {

-                               push @class, ('l3', 'u-html');
+                               push @class, ($codepoint <= 0xFF ? 'l4' : 'l3', 'u-html');

                        }
                }
                else {
                        if ($codepoint <= 0xFF) {
                        }
                }
                else {
                        if ($codepoint <= 0xFF) {

-                               push @class, 'l3', 'u-lat1';  # latin1
+                               push @class, 'l4', 'u-lat1';  # latin1

                        }
                        elsif ($codepoint <= 0xD7FF) {
                        }
                        elsif ($codepoint <= 0xD7FF) {

-                               push @class, 'l2', 'u-bmp';  # bmp
+                               push @class, 'l3', 'u-bmp';  # bmp

                        }
                }
 
                if ($input =~ /[ -~]/) {
                        }
                }
 
                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 {
                }
                else {

-                       push @class, 'l1'; # basic unicode
+                       push @class, 'l1'; # any unicode

                }
        }}
 
                }
        }}
 

diff --git a/unicode.plp b/unicode.plp
index 095b206f9d07abd6eb2f3cbcba0e8e2d680b0fed..b14deffa41f47152cec6d749b4606cec62332a2c 100644 (file)
--- a/unicode.plp
+++ b/unicode.plp
@@ -163,9 +163,10 @@ $glyphs->print(map {
 
 <div class="legend">
        <table class="glyphs"><tr>
 
 <div class="legend">
        <table class="glyphs"><tr>

-       <td class="X l4">ascii
-       <td class="X l3"><:= $glyphs->{style} eq 'di' ? 'digraph' : 'latin1' :>
-       <td class="X l2"><:= $glyphs->{style} eq 'di' ? 'proposed' : 'BMP' :>
+       <td class="X l5">ascii
+       <td class="X l4"><:= $glyphs->{style} eq 'di' ? 'digraph' : 'latin1' :>
+       <td class="X l3"><:= $glyphs->{style} eq 'di' ? 'proposed' : 'HTML4' :>
+       <td class="X l2">unicode ≤6.0

        <td class="X l1">other unicode
        <td class="X ex">discouraged
        </table>
        <td class="X l1">other unicode
        <td class="X ex">discouraged
        </table>