charset: complete unicode BMP descriptions

diff --git a/base.css b/base.css
index b535be31c05c01ea6545d5c7394f62dccff4c0b1..30b38461aed7090990e0e0b877a96daa5edb4fca 100644 (file)
--- a/base.css
+++ b/base.css
@@ -245,23 +245,21 @@ table.glyphs.dimap {
 /* character properties */
 
 td.X  {background: #FFF} /* unidentified */
-td.Xr {background: #EEE} /* reverse */
-td.Xa {color: #0A0} /* ascii */
-td.Xl {color: #070} /* latin1 */
-  .Xz {color: #D00} /* proposed */
+#digraphs td.Xa {color: #0A0} /* ascii */
+#digraphs td.Xl {color: #070} /* latin1 */
+#digraphs   .Xz {color: #D00} /* proposed */
 
-td.Lm, td.Mc, td.Me, td.Zl, td.Zp, td.Cs {background: #F00} /* unstyled */
+td.Lm, td.Mc, td.Me, td.Zl, td.Zp {background: #F00} /* unstyled */
 
 /* letter scripts */
 td.Armenian,
-td.Greek    {background: #FFE0CF}
+td.Greek    {background: #FFE8CF}
 td.Cyrillic {background: #FFDDA8}
 td.Latin    {background: #FFB}
 td.Aramaic,
 td.Hebrew   {background: #FFD}
 td.Arabic   {background: #EFE}
 td.African  {background: #DED}
-td.XXXXXX   {background: #ACB} /* same as space */
 td.Brahmic  {background: #FBB} /* same as number */
 td.Khmer    {background: #FBA}
 td.Hangul,
@@ -269,9 +267,11 @@ td.Syllabic {background: #DEA}
 td.Katakana {background: #DFA}
 td.Hiragana {background: #DFC}
 td.Bopomofo {background: #BFC}
+td.Han      {background: #CFD}
+td.Alpha    {background: #ADA} /* other scripts */
 
 /* other categories */
-td.Nd, td.Nl, td.No        {background: #FBB} /* number */
+td.Nd, td.Nl, td.No        {background: #FDD} /* number */
 td.Sc                      {background: #FCD} /* currency */
 td.Sm                      {background: #ECE} /* math */
 td.So                      {background: #DCF} /* symbol */
@@ -283,6 +283,10 @@ td.Cc         {color: #666; background: #BBB} /* control */
 td.Zs                      {background: #ACB} /* space */
 td.Zs span                 {background: #EEE}
 td.Co                      {background: #A99} /* private */
+td.Xi, td.Cs               {background: #CCC} /* invalid */
+td.Xd                      {color: #844} /* deprecated */
+td.Xr                      {color: #888} /* reserved (digraph reverse or proposal) */
+.dimap td.Xr               {background: #EEE} /* reversed digraph */
 
 /* implementation-based alternatives */
 td.di-b       {background: #FDD} /* bmp */
@@ -295,16 +299,21 @@ td.di-invalid {background: #BBB} /* impossible */
 /* hover effects */
 td.di-d,
 td.X:hover {cursor: help}
-td.Greek:hover                                     {background: #FA9}
+td.Greek:hover, td.Armenian:hover                  {background: #FA8}
 td.Cyrillic:hover                                  {background: #FB7}
-td.Latin:hover                                     {background: #FF6}
-td.Hebrew:hover                                    {background: #FFA}
+td.Latin:hover                                     {background: #EE4}
+td.Hebrew:hover, td.Aramaic:hover                  {background: #FFA}
 td.Arabic:hover                                    {background: #CFD}
-td.Hangul:hover                                    {background: #CE6}
+td.African:hover                                   {background: #BDB}
+td.Syllabic:hover, td.Hangul:hover                 {background: #CE6}
 td.Katakana:hover                                  {background: #BF7}
 td.Hiragana:hover                                  {background: #AF8}
 td.Bopomofo:hover                                  {background: #8FA}
-td.Nd:hover, td.Nl:hover, td.No:hover              {background: #F88} /* number */
+td.Brahmic:hover                                   {background: #F77}
+td.Khmer:hover                                     {background: #F87}
+td.Han:hover                                       {background: #5EB}
+td.Alpha:hover                                     {background: #5C5}
+td.Nd:hover, td.Nl:hover, td.No:hover              {background: #F99} /* number */
 td.Sc:hover                                        {background: #F8C} /* currency */
 td.Sm:hover                                        {background: #F8F} /* math */
 td.So:hover                                        {background: #A8F} /* symbol */
@@ -315,6 +324,7 @@ td.Mn:hover                                        {background: #CDE} /* modifie
 td.Zs:hover                                        {background: #CED} /* space */
 td.Cc:hover                                        {background: #DDD} /* control */
 td.Co:hover                                        {background: #A77} /* private */
+td.Xr:hover                                        {background: #FFF} /* reserved */
 td.Xa:hover {outline: 1px solid #0F0} /* ascii */
 td.Xl:hover {outline: 1px solid #0C0} /* latin1 */
 td.Xz:hover {outline: 1px solid #F00} /* proposed */

diff --git a/charset.plp b/charset.plp
index 777e0ee9d896c5732e5223163d7c18b671506c22..2dc69649d2b02c56d7468cb602d8f4b385f0e361 100644 (file)
--- a/charset.plp
+++ b/charset.plp
@@ -32,7 +32,7 @@ use Encode qw(decode resolve_alias);
 #  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)],
+       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)],
@@ -55,7 +55,7 @@ my @request = map {
                }
                if ($row{set} = resolve_alias($input)) {
                        if ($row{set} eq 'Internal') {
-                               $row{table} = ' 'x640;
+                               $row{table} = ' ' x ($endpoint < 255 ? 640 : 4096);
                                $row{set} = 'Unicode BMP';
                        }
                        elsif ($row{set} eq 'utf-8-strict') {
@@ -96,32 +96,38 @@ sub quote {
 
 sub printcell_unicode {
        my ($value) = @_;
-       if ($value > 0x27F) {
+       if ($value > 0xFFF) {
                print "\n".'<td class="X">?';
        }
        elsif ($value == 0) {
-               print '<td colspan="2" class="X Cc">control';
+               print '<td colspan="2" class="X Cc" style="border-right:none">control';
        }
        elsif ($value == 2) {
-               print '<td colspan="6" class="X Ll Latin">latin';
+               print '<td colspan="2" class="X L Po" style="border-left:none; border-right:none">comn';
+       }
+       elsif ($value == 4) {
+               print '<td colspan="4" class="X L Latin" style="border-left:none">basic latin';
        }
        elsif ($value == 8) {
-               print '<td colspan="2" class="X Cc">control';
+               print '<td colspan="2" class="X Cc" style="border-right:none">control';
        }
        elsif ($value == 10) {
-               print '<td colspan="6" class="X Ll Latin">latin supplement';
+               print '<td colspan="2" class="X L So" style="border-left:none; border-right:none">comn';
+       }
+       elsif ($value == 12) {
+               print '<td colspan="4" class="X L Latin" style="border-left:none">latin1';
        }
        elsif ($value == 0x10) {
-               print '<td colspan="8" class="X Ll Latin">latin ext-A';
+               print '<td colspan="8" class="X L Latin">latin extended-A';
        }
        elsif ($value == 0x18) {
-               print '<td colspan="8" class="X Ll Latin">latin ext-B';
+               print '<td colspan="8" class="X L Latin">latin extended-B';
        }
        elsif ($value == 0x20) {
-               print '<td colspan="5" class="X Ll Latin">latin ext-B';
+               print '<td colspan="5" class="X L Latin">latin ext-B';
        }
        elsif ($value == 0x25) {
-               print '<td colspan="6" class="X Ll Latin">IPA';
+               print '<td colspan="6" class="X L Latin">IPA';
        }
        elsif ($value == 0x2B) {
                print '<td colspan="5" class="X Sk">spacing modifier';
@@ -130,199 +136,199 @@ sub printcell_unicode {
                print '<td colspan="8" class="X Mn">diacritics';
        }
        elsif ($value == 0x38) {
-               print '<td colspan="8" class="X Ll Greek">greek';
+               print '<td colspan="8" class="X L Greek">greek';
        }
        elsif ($value == 0x40) {
-               print '<td colspan="16" class="X Ll Cyrillic">cyrillic';
+               print '<td colspan="16" class="X L Cyrillic">cyrillic';
        }
        elsif ($value == 0x50) {
-               print '<td colspan="3" class="X Ll Cyrillic">cyrillic+';
+               print '<td colspan="3" class="X L Cyrillic">cyrillic+';
        }
        elsif ($value == 0x53) {
-               print '<td colspan="5" class="X Ll Armenian">armenian';
+               print '<td colspan="5" class="X L Armenian">armenian';
        }
        elsif ($value == 0x58) {
-               print '<td colspan="8" class="X Ll Hebrew">hebrew';
+               print '<td colspan="8" class="X L Hebrew">hebrew';
        }
        elsif ($value == 0x60) {
-               print '<td colspan="16" class="X Ll Arabic">arabic';
+               print '<td colspan="16" class="X L Arabic">arabic';
        }
        elsif ($value == 0x70) {
-               print '<td colspan="5" class="X Ll Aramaic">syriac';
+               print '<td colspan="5" class="X L Aramaic">syriac';
        }
        elsif ($value == 0x75) {
-               print '<td colspan="3" class="X Ll Arabic">arabic+';
+               print '<td colspan="3" class="X L Arabic">arabic+';
        }
        elsif ($value == 0x78) {
-               print '<td colspan="4" class="X Ll African">thaana';
+               print '<td colspan="4" class="X L African">thaana';
        }
        elsif ($value == 0x7C) {
-               print '<td colspan="4" class="X Ll African">nko';
+               print '<td colspan="4" class="X L African">n\'ko';
        }
        elsif ($value == 0x80) {
-               print '<td colspan="4" class="X di-rare">samaritan';
+               print '<td colspan="4" class="X Xr L Hebrew">samaritan';
        }
        elsif ($value == 0x84) {
-               print '<td colspan="2" class="X di-rare Ll Aramaic">manda';
+               print '<td colspan="2" class="X Xr L Aramaic">manda';
        }
        elsif ($value == 0x86) {
-               print '<td colspan="12" class="di-invalid">reserved';
+               print '<td colspan="12" class="">reserved';
        }
        elsif ($value == 0x90) {
-               print '<td colspan="8" class="X Ll Brahmic">devanagari';
+               print '<td colspan="8" class="X L Brahmic">devanagari';
        }
        elsif ($value == 0x98) {
-               print '<td colspan="8" class="X Ll Brahmic">bengali';
+               print '<td colspan="8" class="X L Brahmic">bengali';
        }
        elsif ($value == 0xA0) {
-               print '<td colspan="8" class="X Ll Brahmic">gurmukhi';
+               print '<td colspan="8" class="X L Brahmic">gurmukhi';
        }
        elsif ($value == 0xA8) {
-               print '<td colspan="8" class="X Ll Brahmic">gujarati';
+               print '<td colspan="8" class="X L Brahmic">gujarati';
        }
        elsif ($value == 0xB0) {
-               print '<td colspan="8" class="X Ll Brahmic">oriya';
+               print '<td colspan="8" class="X L Brahmic">oriya';
        }
        elsif ($value == 0xB8) {
-               print '<td colspan="8" class="X Ll Brahmic">tamil';
+               print '<td colspan="8" class="X L Brahmic">tamil';
        }
        elsif ($value == 0xC0) {
-               print '<td colspan="8" class="X Ll Brahmic">telugu';
+               print '<td colspan="8" class="X L Brahmic">telugu';
        }
        elsif ($value == 0xC8) {
-               print '<td colspan="8" class="X Ll Brahmic">kannada';
+               print '<td colspan="8" class="X L Brahmic">kannada';
        }
        elsif ($value == 0xD0) {
-               print '<td colspan="8" class="X Ll Brahmic">malayalam';
+               print '<td colspan="8" class="X L Brahmic">malayalam';
        }
        elsif ($value == 0xD8) {
-               print '<td colspan="8" class="X Ll Brahmic">sinhala';
+               print '<td colspan="8" class="X L Brahmic">sinhala';
        }
        elsif ($value == 0xE0) {
-               print '<td colspan="8" class="X Ll Brahmic Khmer">thai';
+               print '<td colspan="8" class="X L Brahmic Khmer">thai';
        }
        elsif ($value == 0xE8) {
-               print '<td colspan="8" class="X Ll Brahmic Khmer">lao';
+               print '<td colspan="8" class="X L Brahmic Khmer">lao';
        }
        elsif ($value == 0xF0) {
-               print '<td colspan="16" class="X Ll Brahmic">tibetan';
+               print '<td colspan="16" class="X L Brahmic">tibetan';
        }
        elsif ($value == 0x100) {
-               print '<td colspan="10" class="X Ll Brahmic">myanmar';
+               print '<td colspan="10" class="X L Brahmic">myanmar';
        }
        elsif ($value == 0x10A) {
-               print '<td colspan="6" class="X Ll Aramaic">georgian';
+               print '<td colspan="6" class="X L Aramaic">georgian';
        }
        elsif ($value == 0x110) {
-               print '<td colspan="16" class="X Ll Hangul">hangeul jamo';
+               print '<td colspan="16" class="X L Hangul">hangeul jamo';
        }
        elsif ($value == 0x120) {
-               print '<td colspan="16" class="X Ll African">ethiopic';
+               print '<td colspan="16" class="X L African">ethiopic';
        }
        elsif ($value == 0x130) {
-               print '<td colspan="8" class="X Ll African">ethiopic';
+               print '<td colspan="8" class="X L African">ethiopic';
        }
        elsif ($value == 0x138) {
-               print '<td colspan="2" class="X Ll African">eth+';
+               print '<td colspan="2" class="X L African">eth+';
        }
        elsif ($value == 0x13A) {
-               print '<td colspan="6" class="X Ll Syllabic">cherokee';
+               print '<td colspan="6" class="X L Syllabic">cherokee';
        }
        elsif ($value == 0x140) {
-               print '<td colspan="16" rowspan="2" class="X Ll Syllabic">unified canadian aboriginal syllabics';
+               print '<td colspan="16" rowspan="2" class="X L Syllabic">unified canadian aboriginal syllabics';
        }
        elsif ($value == 0x160) {
-               print '<td colspan="8" class="X Ll Syllabic">unified canadian syllabics';
+               print '<td colspan="8" class="X L Syllabic">unified canadian syllabics';
        }
        elsif ($value == 0x168) {
-               print '<td colspan="2" class="X Ll X">ogham';
+               print '<td colspan="2" class="X L Alpha">ogham';
        }
        elsif ($value == 0x16A) {
-               print '<td colspan="6" class="X Ll X">runic';
+               print '<td colspan="6" class="X L Alpha">runic';
        }
        elsif ($value == 0x170) {
-               print '<td colspan="2" class="X Ll Brahmic">tagalog';
+               print '<td colspan="2" class="X L Brahmic">tagalog';
        }
        elsif ($value == 0x172) {
-               print '<td colspan="2" class="X Ll Brahmic">hanun';
+               print '<td colspan="2" class="X L Brahmic">hanun';
        }
        elsif ($value == 0x174) {
-               print '<td colspan="2" class="X Ll Brahmic">buhid';
+               print '<td colspan="2" class="X L Brahmic">buhid';
        }
        elsif ($value == 0x176) {
-               print '<td colspan="2" class="X Ll Brahmic" title="tagbanwa">tagb';
+               print '<td colspan="2" class="X L Brahmic" title="tagbanwa">tagb';
        }
        elsif ($value == 0x178) {
-               print '<td colspan="8" class="X Ll Brahmic Khmer">khmer';
+               print '<td colspan="8" class="X L Brahmic Khmer">khmer';
        }
        elsif ($value == 0x180) {
-               print '<td colspan="11" class="X Ll Aramaic">mongolian';
+               print '<td colspan="11" class="X L Aramaic">mongolian';
        }
        elsif ($value == 0x18B) {
-               print '<td colspan="5" class="X Ll Syllabic di-rare">canadian+';
+               print '<td colspan="5" class="X Xr L Syllabic">canadian+';
        }
        elsif ($value == 0x190) {
-               print '<td colspan="5" class="X Ll Brahmic">limbu';
+               print '<td colspan="5" class="X L Brahmic">limbu';
        }
        elsif ($value == 0x195) {
-               print '<td colspan="4" class="X Ll Brahmic">tai le';
+               print '<td colspan="4" class="X L Brahmic">tai le';
        }
        elsif ($value == 0x198) {
-               print '<td colspan="6" class="X Ll Brahmic">new tai lue';
+               print '<td colspan="6" class="X L Brahmic">new tai lue';
        }
        elsif ($value == 0x19E) {
-               print '<td colspan="2" class="X Ll Brahmic Khmer" title="khmer symbols">km';
+               print '<td colspan="2" class="X L Brahmic Khmer" title="khmer symbols">km';
        }
        elsif ($value == 0x1A0) {
-               print '<td colspan="2" class="X Ll Brahmic">lontara';
+               print '<td colspan="2" class="X L Brahmic">lontara';
        }
        elsif ($value == 0x1A2) {
-               print '<td colspan="9" class="X Ll Brahmic di-rare">tai tham';
+               print '<td colspan="9" class="X Xr L Brahmic">tai tham';
        }
        elsif ($value == 0x1AB) {
-               print '<td colspan="5" class="di-invalid">reserved';
+               print '<td colspan="5" class="">reserved';
        }
        elsif ($value == 0x1B0) {
-               print '<td colspan="8" class="X Ll ">balinese';
+               print '<td colspan="8" class="X L Brahmic">balinese';
        }
        elsif ($value == 0x1B8) {
-               print '<td colspan="4" class="X Ll ">sundanese';
+               print '<td colspan="4" class="X L Brahmic">sundanese';
        }
        elsif ($value == 0x1BC) {
-               print '<td colspan="4" class="X Ll di-rare">batak';
+               print '<td colspan="4" class="X Xr L Brahmic">batak';
        }
        elsif ($value == 0x1C0) {
-               print '<td colspan="5" class="X Ll ">lepcha';
+               print '<td colspan="5" class="X L Brahmic">lepcha';
        }
        elsif ($value == 0x1C5) {
-               print '<td colspan="3" class="X Ll ">ol chiki';
+               print '<td colspan="3" class="X L Alpha">ol chiki';
        }
        elsif ($value == 0x1C8) {
-               print '<td colspan="5" class="di-invalid">reserved';
+               print '<td colspan="5" class="">reserved';
        }
        elsif ($value == 0x1CD) {
-               print '<td colspan="3" class="X Ll di-rare">vedic';
+               print '<td colspan="3" class="X Xr Brahmic">vedic';
        }
        elsif ($value == 0x1D0) {
-               print '<td colspan="8" class="X Ll Latin">phonetic';
+               print '<td colspan="8" class="X L Latin">phonetic';
        }
        elsif ($value == 0x1D8) {
-               print '<td colspan="4" class="X Ll Latin">phonetic+';
+               print '<td colspan="4" class="X L Latin">phonetic+';
        }
        elsif ($value == 0x1DC) {
                print '<td colspan="4" class="X Mn">combining';
        }
        elsif ($value == 0x1E0) {
-               print '<td colspan="16" class="X Ll Latin">latin extended additional';
+               print '<td colspan="16" class="X L Latin">latin extended additional';
        }
        elsif ($value == 0x1F0) {
-               print '<td colspan="16" class="X Ll Greek">greek+';
+               print '<td colspan="16" class="X L Greek">greek+';
        }
        elsif ($value == 0x200) {
-               print '<td colspan="7" class="X Pd">general punctuation';
+               print '<td colspan="7" class="X Po">general punctuation';
        }
        elsif ($value == 0x207) {
-               print '<td colspan="3" class="X Latin">su[bp]script';
+               print '<td colspan="3" class="X Latin">suþscript'; # suth now means "sub and/or sup"
        }
        elsif ($value == 0x20A) {
                print '<td colspan="3" class="X Sc">currency';
@@ -375,23 +381,260 @@ sub printcell_unicode {
        elsif ($value == 0x27F) {
                print '<td colspan="1" class="X So" title="supplemental arrows-A">arr';
        }
+       elsif ($value == 0x280) {
+               print '<td colspan="16" class="X L Alpha">braille';
+       }
+       elsif ($value == 0x290) {
+               print '<td colspan="8" class="X So">supplemental arrows-B';
+       }
+       elsif ($value == 0x298) {
+               print '<td colspan="8" class="X Sm">mathematical symbols-B';
+       }
+       elsif ($value == 0x2A0) {
+               print '<td colspan="16" class="X Sm">supplemental mathematical operators';
+       }
+       elsif ($value == 0x2B0) {
+               print '<td colspan="16" class="X So">miscellaneous symbols and arrows';
+       }
+       elsif ($value == 0x2C0) {
+               print '<td colspan="6" class="X L Cyrillic">glagolitic';
+       }
+       elsif ($value == 0x2C6) {
+               print '<td colspan="2" class="X L Latin">latin-C';
+       }
+       elsif ($value == 0x2C8) {
+               print '<td colspan="8" class="X L Greek">coptic';
+       }
+       elsif ($value == 0x2D0) {
+               print '<td colspan="3" class="X L Aramaic">georgian+';
+       }
+       elsif ($value == 0x2D3) {
+               print '<td colspan="5" class="X L Alpha">tifinagh'; #TODO: proto-canaanite
+       }
+       elsif ($value == 0x2D8) {
+               print '<td colspan="6" class="X L African">ethiopic+';
+       }
+       elsif ($value == 0x2DE) {
+               print '<td colspan="2" class="X L Cyrillic">cyrl-A';
+       }
+       elsif ($value == 0x2E0) {
+               print '<td colspan="8" class="X Po">punctuation+';
+       }
+       elsif ($value == 0x2E8) {
+               print '<td colspan="8" class="X L Han">cjk radicals';
+       }
+       elsif ($value == 0x2F0) {
+               print '<td colspan="14" class="X L Han">kangxi radicals';
+       }
+       elsif ($value == 0x2FE) {
+               print '<td colspan="1" class="">';
+       }
+       elsif ($value == 0x2FF) {
+               print '<td colspan="1" class="X So Han">idc';
+       }
+       elsif ($value == 0x300) {
+               print '<td colspan="4" class="X Po Han">cjk misc';
+       }
+       elsif ($value == 0x304) {
+               print '<td colspan="6" class="X L Hiragana">hiragana';
+       }
+       elsif ($value == 0x30A) {
+               print '<td colspan="6" class="X L Katakana">katakana';
+       }
+       elsif ($value == 0x310) {
+               print '<td colspan="3" class="X L Bopomofo">bopomofo';
+       }
+       elsif ($value == 0x313) {
+               print '<td colspan="6" class="X L Katakana">hangeul compat';
+       }
+       elsif ($value == 0x319) {
+               print '<td colspan="1" class="X L Han" title="kanbun">kbn';
+       }
+       elsif ($value == 0x31A) {
+               print '<td colspan="2" class="X L Bopomofo" title="bopomofo extended">bpmf';
+       }
+       elsif ($value == 0x31C) {
+               print '<td colspan="3" class="X L Han" title="CJK strokes">strokes';
+       }
+       elsif ($value == 0x31F) {
+               print '<td colspan="1" class="X L Katakana" title="katakana phonetic extensions">k+';
+       }
+       elsif ($value == 0x320) {
+               print '<td colspan="16" class="X L Han">enclosed cjk characters';
+       }
+       elsif ($value == 0x330) {
+               print '<td colspan="16" class="X Xd L Han">cjk compatibility';
+       }
+       elsif ($value == 0x340) {
+               print '<td colspan="16" rowspan="25" class="X L Han">cjk unified ideographs extension A';
+       }
+       elsif ($value == 0x4D0) {
+               print '<td colspan="12" class="X L Han" style="border-top:none">cjk unified ideographs extension A';
+       }
+       elsif ($value == 0x4DC) {
+               print '<td colspan="4" class="X So">hexagrams';
+       }
+       elsif ($value == 0x4E0) {
+               print '<td colspan="16" rowspan="82" class="X L Han">cjk unified ideographs';
+       }
+       elsif ($value == 0xA00) {
+               print '<td colspan="16" rowspan="4" class="X L Syllabic">yi';
+       }
+       elsif ($value == 0xA40) {
+               print '<td colspan="9" class="X L Syllabic" style="border-top:none">yi';
+       }
+       elsif ($value == 0xA49) {
+               print '<td colspan="4" class="X L Syllabic">yi radicals';
+       }
+       elsif ($value == 0xA4D) {
+               print '<td colspan="3" class="X Xr L Latin">lisu';
+       }
+       elsif ($value == 0xA50) {
+               print '<td colspan="16" class="X L Syllabic">vai';
+       }
+       elsif ($value == 0xA60) {
+               print '<td colspan="4" class="X L Syllabic" style="border-top:none">vai';
+       }
+       elsif ($value == 0xA64) {
+               print '<td colspan="6" class="X L Cyrillic">cyrillic extended-B';
+       }
+       elsif ($value == 0xA6A) {
+               print '<td colspan="6" class="X Xr L Syllabic">bamum';
+       }
+       elsif ($value == 0xA70) {
+               print '<td colspan="2" class="X L Mn">tones';
+       }
+       elsif ($value == 0xA72) {
+               print '<td colspan="14" class="X L Latin">latin extended-D';
+       }
+       elsif ($value == 0xA80) {
+               print '<td colspan="3" class="X L Brahmic">sylheti';
+       }
+       elsif ($value == 0xA83) {
+               print '<td colspan="1" class="X Xr No">in';
+       }
+       elsif ($value == 0xA84) {
+               print '<td colspan="4" class="X L Brahmic">phags-pa';
+       }
+       elsif ($value == 0xA88) {
+               print '<td colspan="6" class="X L Brahmic">saurashtra';
+       }
+       elsif ($value == 0xA8E) {
+               print '<td colspan="2" class="X Xr L Brahmic">deva+';
+       }
+       elsif ($value == 0xA90) {
+               print '<td colspan="3" class="X L Brahmic">kayah li';
+       }
+       elsif ($value == 0xA93) {
+               print '<td colspan="3" class="X L Brahmic">rejang';
+       }
+       elsif ($value == 0xA96) {
+               print '<td colspan="2" class="X Xr L Hangul">jamo-A';
+       }
+       elsif ($value == 0xA98) {
+               print '<td colspan="6" class="X Xr L Brahmic">javanese';
+       }
+       elsif ($value == 0xA9E) {
+               print '<td colspan="2" class="">res';
+       }
+       elsif ($value == 0xAA0) {
+               print '<td colspan="6" class="X L Brahmic">cham';
+       }
+       elsif ($value == 0xAA6) {
+               print '<td colspan="2" class="X Xr L Brahmic" title="myanmar extended-A">mym-A';
+       }
+       elsif ($value == 0xAA8) {
+               print '<td colspan="6" class="X Xr L Brahmic Khmer">tai viet';
+       }
+       elsif ($value == 0xAAE) {
+               print '<td colspan="2" class="X Xr L Brahmic" title="meetei mayek extended">mtei+';
+       }
+       elsif ($value == 0xAB0) {
+               print '<td colspan="12" class="">reserved';
+       }
+       elsif ($value == 0xABC) {
+               print '<td colspan="4" class="X Xr L Brahmic" title="meetei mayek">manipuri';
+       }
+       elsif ($value == 0xAC0) {
+               print '<td colspan="16" rowspan="43" class="X L Hangul">hangeul syllables';
+       }
+       elsif ($value == 0xD70) {
+               print '<td colspan="11" class="X L Hangul" style="border-top:none">hangeul syllables';
+       }
+       elsif ($value == 0xD7B) {
+               print '<td colspan="5" class="X L Hangul">haungeul jamo-B';
+       }
+       elsif ($value == 0xD80) {
+               print '<td colspan="16" rowspan="4" class="X Cs">high surrogates';
+       }
+       elsif ($value == 0xDC0) {
+               print '<td colspan="16" rowspan="4" class="X Cs">low surrogates';
+       }
+       elsif ($value == 0xE00) {
+               print '<td colspan="16" rowspan="25" class="X Co">private use';
+       }
+       elsif ($value == 0xF90) {
+               print '<td colspan="16" rowspan="2" class="X L Han">cjk compatibility ideographs';
+       }
+       elsif ($value == 0xFB0) {
+               print '<td colspan="5" class="X Xd L">presentation';
+       }
+       elsif ($value == 0xFB5) {
+               print '<td colspan="11" class="X Xd L Arabic" style="border-bottom:none">';
+       }
+       elsif ($value == 0xFC0) {
+               print '<td colspan="16" class="X Xd L Arabic" style="border-top:none; border-bottom:none">arabic presentation forms A';
+       }
+       elsif ($value == 0xFD0) {
+               print '<td colspan="13" class="X Xd L Arabic" style="border-top:none">';
+       }
+       elsif ($value == 0xFDD) {
+               print '<td colspan="2" class="Xi">?';
+       }
+       elsif ($value == 0xFDF) {
+               print '<td colspan="1" class="X Xd L Arabic" style="border-top:none">';
+       }
+       elsif ($value == 0xFE0) {
+               print '<td colspan="1" class="X Cc">var';
+       }
+       elsif ($value == 0xFE1) {
+               print '<td colspan="1" class="X L Pd">ver';
+       }
+       elsif ($value == 0xFE2) {
+               print '<td colspan="1" class="X L Mn">½';
+       }
+       elsif ($value == 0xFE3) {
+               print '<td colspan="2" class="X Xd Pd Han">comp';
+       }
+       elsif ($value == 0xFE5) {
+               print '<td colspan="2" class="X Xd L Latin">small';
+       }
+       elsif ($value == 0xFE7) {
+               print '<td colspan="9" class="X Xd L Arabic">arabic presentation B';
+       }
+       elsif ($value == 0xFF0) {
+               print '<td colspan="15" class="X L Latin">halfwidth &amp; fullwidth forms';
+       }
+       elsif ($value == 0xFFF) {
+               print '<td colspan="1" class="X Cc">sp';
+       }
 }
 
 sub printcell_utf8 {
        my ($value) = @_;
        if ($value <= 0x7F) {
                print '<td rowspan="8" colspan="16" class="X di-a"',
-                         ' title="U+0000 – U+007F">Single byte ASCII'
+                         ' title="U+0000 – U+007F">single byte ASCII'
                        if $value == 0;
        }
        elsif ($value <= 0xBF) {
                print '<td rowspan="4" colspan="16" class="X di-d"',
-                         '>Multi-byte continuation'
+                         '>multi-byte continuation'
                        if $value == 0x80;
        }
        elsif ($value <= 0xC1) {
                print '<td colspan="2" class="X di-b" style="border-right:none; border-bottom:none"',
-                         ' title="U+0000 – U+007F">(Overl.)'
+                         ' title="U+0000 – U+007F">(overl.)'
                        if $value == 0xC0;
        }
        elsif ($value <= 0xDF) {
@@ -414,7 +657,7 @@ sub printcell_utf8 {
        }
        elsif ($value <= 0xF7) {
                print '<td colspan="3" class="X di-b" style="border-left:none"',
-                         ' title="U+11·0000 – U+1FF·FFFF">(Overflow)'
+                         ' title="U+11·0000 – U+1FF·FFFF">(overflow)'
                        if $value == 0xF5;
        }
        elsif ($value <= 0xFB) {
@@ -428,7 +671,7 @@ sub printcell_utf8 {
                        if $value == 0xFC;
        }
        elsif ($value <= 0xFF) {
-               print '<td colspan="2" class="di-invalid">Invalid'
+               print '<td colspan="2" class="di-invalid">invalid'
                        if $value == 0xFE;
        }
        else {