charset: describe unicode BMP blocks

diff --git a/base.css b/base.css
index d36f4df7b4c75202ade4fefadb688f7940576fba..b535be31c05c01ea6545d5c7394f62dccff4c0b1 100644 (file)
--- a/base.css
+++ b/base.css
@@ -63,13 +63,14 @@ hr ~ .footer {
        margin: 0;
 }
 
-/* "keyboard" (list of keys) */
-
 ul {
        margin: 0;
        padding: 0;
        list-style: none;
 }
+
+/* "keyboard" (list of keys) */
+
 ul#rows {margin-top: -5ex} /* top (esc) row fits besides header */
 li.row1 {margin-left: 7em} /* row offsets relative to ~6em key width */
 li.row2 {margin-left: 8em}
@@ -252,12 +253,19 @@ td.Xl {color: #070} /* latin1 */
 td.Lm, td.Mc, td.Me, td.Zl, td.Zp, td.Cs {background: #F00} /* unstyled */
 
 /* letter scripts */
+td.Armenian,
 td.Greek    {background: #FFE0CF}
 td.Cyrillic {background: #FFDDA8}
 td.Latin    {background: #FFB}
+td.Aramaic,
 td.Hebrew   {background: #FFD}
 td.Arabic   {background: #EFE}
-td.Hangul   {background: #DEA}
+td.African  {background: #DED}
+td.XXXXXX   {background: #ACB} /* same as space */
+td.Brahmic  {background: #FBB} /* same as number */
+td.Khmer    {background: #FBA}
+td.Hangul,
+td.Syllabic {background: #DEA}
 td.Katakana {background: #DFA}
 td.Hiragana {background: #DFC}
 td.Bopomofo {background: #BFC}

diff --git a/charset.plp b/charset.plp
index e9c4fcc7c0d323f2b34895096ad73aacae08339a..25b69b99b47c618048b1b460d008360d7d4ddb75 100644 (file)
--- a/charset.plp
+++ b/charset.plp
@@ -43,7 +43,7 @@ my @request = grep { defined } map {
        $_ ? (resolve_alias($_) or print("Encoding $_ unknown") && ()) : ();
 } map { defined $ALIAS{$_} ? @{ $ALIAS{$_} } : $_ }
        $ENV{PATH_INFO} =~ /\w/ ? split(m{[/+\s]}, $ENV{PATH_INFO}) : 'default';
-my @tables = map { $_ eq 'utf-8-strict' ? undef : decode($_, pack 'C*', 0..255) } @request;
+my @tables = map { $_ eq 'utf-8-strict' ? undef : $_ eq 'Internal' ? ' 'x512 : decode($_, pack 'C*', 0..255) } @request;
 my $NOCHAR = chr 0xFFFD;
 
 for my $cp437 (grep {$request[$_] eq 'cp437'} 0 .. $#request) {
@@ -62,6 +62,232 @@ sub quote {
        return $_;
 }
 
+sub printcell_unicode {
+       my ($value) = @_;
+       if ($value > 0x1FF) {
+               print "\n".'<td class="X">?';
+       }
+       elsif ($value == 0) {
+               print '<td colspan="2" class="X Cc">control';
+       }
+       elsif ($value == 2) {
+               print '<td colspan="6" class="X Ll Latin">latin';
+       }
+       elsif ($value == 8) {
+               print '<td colspan="2" class="X Cc">control';
+       }
+       elsif ($value == 10) {
+               print '<td colspan="6" class="X Ll Latin">latin supplement';
+       }
+       elsif ($value == 0x10) {
+               print '<td colspan="8" class="X Ll Latin">latin ext-A';
+       }
+       elsif ($value == 0x18) {
+               print '<td colspan="8" class="X Ll Latin">latin ext-B';
+       }
+       elsif ($value == 0x20) {
+               print '<td colspan="5" class="X Ll Latin">latin ext-B';
+       }
+       elsif ($value == 0x25) {
+               print '<td colspan="6" class="X Ll Latin">IPA';
+       }
+       elsif ($value == 0x2B) {
+               print '<td colspan="5" class="X Sk">spacing modifier';
+       }
+       elsif ($value == 0x30) {
+               print '<td colspan="8" class="X Mn">diacritics';
+       }
+       elsif ($value == 0x38) {
+               print '<td colspan="8" class="X Ll Greek">greek';
+       }
+       elsif ($value == 0x40) {
+               print '<td colspan="16" class="X Ll Cyrillic">cyrillic';
+       }
+       elsif ($value == 0x50) {
+               print '<td colspan="3" class="X Ll Cyrillic">cyrillic+';
+       }
+       elsif ($value == 0x53) {
+               print '<td colspan="5" class="X Ll Armenian">armenian';
+       }
+       elsif ($value == 0x58) {
+               print '<td colspan="8" class="X Ll Hebrew">hebrew';
+       }
+       elsif ($value == 0x60) {
+               print '<td colspan="16" class="X Ll Arabic">arabic';
+       }
+       elsif ($value == 0x70) {
+               print '<td colspan="5" class="X Ll Aramaic">syriac';
+       }
+       elsif ($value == 0x75) {
+               print '<td colspan="3" class="X Ll Arabic">arabic+';
+       }
+       elsif ($value == 0x78) {
+               print '<td colspan="4" class="X Ll African">thaana';
+       }
+       elsif ($value == 0x7C) {
+               print '<td colspan="4" class="X Ll African">nko';
+       }
+       elsif ($value == 0x80) {
+               print '<td colspan="4" class="X di-rare">samaritan';
+       }
+       elsif ($value == 0x84) {
+               print '<td colspan="2" class="X di-rare Ll Aramaic">manda';
+       }
+       elsif ($value == 0x86) {
+               print '<td colspan="12" class="di-invalid">reserved';
+       }
+       elsif ($value == 0x90) {
+               print '<td colspan="8" class="X Ll Brahmic">devanagari';
+       }
+       elsif ($value == 0x98) {
+               print '<td colspan="8" class="X Ll Brahmic">bengali';
+       }
+       elsif ($value == 0xA0) {
+               print '<td colspan="8" class="X Ll Brahmic">gurmukhi';
+       }
+       elsif ($value == 0xA8) {
+               print '<td colspan="8" class="X Ll Brahmic">gujarati';
+       }
+       elsif ($value == 0xB0) {
+               print '<td colspan="8" class="X Ll Brahmic">oriya';
+       }
+       elsif ($value == 0xB8) {
+               print '<td colspan="8" class="X Ll Brahmic">tamil';
+       }
+       elsif ($value == 0xC0) {
+               print '<td colspan="8" class="X Ll Brahmic">telugu';
+       }
+       elsif ($value == 0xC8) {
+               print '<td colspan="8" class="X Ll Brahmic">kannada';
+       }
+       elsif ($value == 0xD0) {
+               print '<td colspan="8" class="X Ll Brahmic">malayalam';
+       }
+       elsif ($value == 0xD8) {
+               print '<td colspan="8" class="X Ll Brahmic">sinhala';
+       }
+       elsif ($value == 0xE0) {
+               print '<td colspan="8" class="X Ll Brahmic Khmer">thai';
+       }
+       elsif ($value == 0xE8) {
+               print '<td colspan="8" class="X Ll Brahmic Khmer">lao';
+       }
+       elsif ($value == 0xF0) {
+               print '<td colspan="16" class="X Ll Brahmic">tibetan';
+       }
+       elsif ($value == 0x100) {
+               print '<td colspan="10" class="X Ll Brahmic">myanmar';
+       }
+       elsif ($value == 0x10A) {
+               print '<td colspan="6" class="X Ll Aramaic">georgian';
+       }
+       elsif ($value == 0x110) {
+               print '<td colspan="16" class="X Ll Hangul">hangeul jamo';
+       }
+       elsif ($value == 0x120) {
+               print '<td colspan="16" class="X Ll African">ethiopic';
+       }
+       elsif ($value == 0x130) {
+               print '<td colspan="8" class="X Ll African">ethiopic';
+       }
+       elsif ($value == 0x138) {
+               print '<td colspan="2" class="X Ll African">eth+';
+       }
+       elsif ($value == 0x13A) {
+               print '<td colspan="6" class="X Ll X">cherokee';
+       }
+       elsif ($value == 0x140) {
+               print '<td colspan="16" rowspan="2" class="X Ll Syllabic">unified canadian aboriginal syllabics';
+       }
+       elsif ($value == 0x160) {
+               print '<td colspan="8" class="X Ll Syllabic">unified canadian syllabics';
+       }
+       elsif ($value == 0x168) {
+               print '<td colspan="2" class="X Ll X">ogham';
+       }
+       elsif ($value == 0x16A) {
+               print '<td colspan="6" class="X Ll X">runic';
+       }
+       elsif ($value == 0x170) {
+               print '<td colspan="2" class="X Ll Brahmic">tagalog';
+       }
+       elsif ($value == 0x172) {
+               print '<td colspan="2" class="X Ll Brahmic">hanun';
+       }
+       elsif ($value == 0x174) {
+               print '<td colspan="2" class="X Ll Brahmic">buhid';
+       }
+       elsif ($value == 0x176) {
+               print '<td colspan="2" class="X Ll Brahmic" title="tagbanwa">tagb';
+       }
+       elsif ($value == 0x178) {
+               print '<td colspan="8" class="X Ll Brahmic Khmer">khmer';
+       }
+       elsif ($value == 0x180) {
+               print '<td colspan="11" class="X Ll Aramaic">mongolian';
+       }
+       elsif ($value == 0x18B) {
+               print '<td colspan="5" class="X Ll Syllabic di-rare">canadian+';
+       }
+       elsif ($value == 0x190) {
+               print '<td colspan="5" class="X Ll Brahmic">limbu';
+       }
+       elsif ($value == 0x195) {
+               print '<td colspan="4" class="X Ll Brahmic">tai le';
+       }
+       elsif ($value == 0x198) {
+               print '<td colspan="6" class="X Ll Brahmic">new tai lue';
+       }
+       elsif ($value == 0x19E) {
+               print '<td colspan="2" class="X Ll Brahmic Khmer" title="khmer symbols">km';
+       }
+       elsif ($value == 0x1A0) {
+               print '<td colspan="2" class="X Ll Brahmic">lontara';
+       }
+       elsif ($value == 0x1A2) {
+               print '<td colspan="9" class="X Ll Brahmic di-rare">tai tham';
+       }
+       elsif ($value == 0x1AB) {
+               print '<td colspan="5" class="di-invalid">reserved';
+       }
+       elsif ($value == 0x1B0) {
+               print '<td colspan="8" class="X Ll ">balinese';
+       }
+       elsif ($value == 0x1B8) {
+               print '<td colspan="4" class="X Ll ">sundanese';
+       }
+       elsif ($value == 0x1BC) {
+               print '<td colspan="4" class="X Ll di-rare">batak';
+       }
+       elsif ($value == 0x1C0) {
+               print '<td colspan="5" class="X Ll ">lepcha';
+       }
+       elsif ($value == 0x1C5) {
+               print '<td colspan="3" class="X Ll ">ol chiki';
+       }
+       elsif ($value == 0x1C8) {
+               print '<td colspan="5" class="di-invalid">reserved';
+       }
+       elsif ($value == 0x1CD) {
+               print '<td colspan="3" class="X Ll di-rare">vedic';
+       }
+       elsif ($value == 0x1D0) {
+               print '<td colspan="8" class="X Ll Latin">phonetic';
+       }
+       elsif ($value == 0x1D8) {
+               print '<td colspan="4" class="X Ll 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';
+       }
+       elsif ($value == 0x1F0) {
+               print '<td colspan="16" class="X Ll Greek">greek+';
+       }
+}
+
 sub printcell_utf8 {
        my ($value) = @_;
        if ($value <= 0x7F) {
@@ -134,13 +360,17 @@ for my $tablenum (0 .. $#tables) {
                print "\n";
        }
        print '<tbody>';
-       for my $msb (0 .. $#nibble) {
-               print '<tr><th>', $nibble[$msb];
+       for my $msb (0 .. (length($tables[$tablenum]) || 256) - 1 >> 4) {
+               printf '<tr><th>%X', $msb;
                for my $lsb (0 .. $#nibble) {
                        if ($request[$tablenum] eq 'utf-8-strict') {
                                printcell_utf8(($msb<<4) + $lsb);
                                next;
                        }
+                       elsif ($request[$tablenum] eq 'Internal') {
+                               printcell_unicode(($msb<<4) + $lsb);
+                               next;
+                       }
 
                        my $glyph = substr $tables[$tablenum], ($msb<<4) + $lsb, 1;
                        if ($glyph eq $NOCHAR) {