X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/38dcfca045c69d0e303e8e5a4ca4915202e19970..47ca3b887159be3f6e047d093ed1bafac4adc706:/charset.plp
diff --git a/charset.plp b/charset.plp
index c83508b..25b69b9 100644
--- a/charset.plp
+++ b/charset.plp
@@ -26,12 +26,24 @@ my $diinfo = do 'digraphs.inc.pl';
my %di = map { $diinfo->{$_}->[0] => $_ } grep { ref $diinfo->{$_} }
keys %$diinfo;
-use Encode qw(decode);
+use Encode qw(decode resolve_alias);
# generate character table(s)
# (~16x faster than decoding in loop;
# substr strings is twice as fast as splitting to an array)
-my @request = ('iso-8859-1', 'cp437');
-my @tables = map { decode($_, pack 'C*', 0..255) } @request;
+my %ALIAS = (
+ default => [qw(utf-8 iso-8859-1 cp437)],
+ 0 => [qw(cp437 cp863)],
+ 1 => [qw(iso-8859-1 cp1252 MacRoman cp850)],
+ 2 => [qw(iso-8859-2 cp1250 cp852 MacCentralEurRoman MacCroatian MacRumanian)],
+ 5 => [qw(koi8-f iso-8859-5 cp1251 MacCyrillic cp855 cp866)],
+ 7 => [qw(iso-8859-7 cp1253 MacGreek cp737 cp869)],
+ 8 => [qw(iso-8859-8 cp1255 MacHebrew cp862)],
+);
+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 : $_ eq 'Internal' ? ' 'x512 : decode($_, pack 'C*', 0..255) } @request;
my $NOCHAR = chr 0xFFFD;
for my $cp437 (grep {$request[$_] eq 'cp437'} 0 .. $#request) {
@@ -50,12 +62,297 @@ sub quote {
return $_;
}
+sub printcell_unicode {
+ my ($value) = @_;
+ if ($value > 0x1FF) {
+ print "\n".'
?';
+ }
+ elsif ($value == 0) {
+ print ' | control';
+ }
+ elsif ($value == 2) {
+ print ' | latin';
+ }
+ elsif ($value == 8) {
+ print ' | control';
+ }
+ elsif ($value == 10) {
+ print ' | latin supplement';
+ }
+ elsif ($value == 0x10) {
+ print ' | latin ext-A';
+ }
+ elsif ($value == 0x18) {
+ print ' | latin ext-B';
+ }
+ elsif ($value == 0x20) {
+ print ' | latin ext-B';
+ }
+ elsif ($value == 0x25) {
+ print ' | IPA';
+ }
+ elsif ($value == 0x2B) {
+ print ' | spacing modifier';
+ }
+ elsif ($value == 0x30) {
+ print ' | diacritics';
+ }
+ elsif ($value == 0x38) {
+ print ' | greek';
+ }
+ elsif ($value == 0x40) {
+ print ' | cyrillic';
+ }
+ elsif ($value == 0x50) {
+ print ' | cyrillic+';
+ }
+ elsif ($value == 0x53) {
+ print ' | armenian';
+ }
+ elsif ($value == 0x58) {
+ print ' | hebrew';
+ }
+ elsif ($value == 0x60) {
+ print ' | arabic';
+ }
+ elsif ($value == 0x70) {
+ print ' | syriac';
+ }
+ elsif ($value == 0x75) {
+ print ' | arabic+';
+ }
+ elsif ($value == 0x78) {
+ print ' | thaana';
+ }
+ elsif ($value == 0x7C) {
+ print ' | nko';
+ }
+ elsif ($value == 0x80) {
+ print ' | samaritan';
+ }
+ elsif ($value == 0x84) {
+ print ' | manda';
+ }
+ elsif ($value == 0x86) {
+ print ' | reserved';
+ }
+ elsif ($value == 0x90) {
+ print ' | devanagari';
+ }
+ elsif ($value == 0x98) {
+ print ' | bengali';
+ }
+ elsif ($value == 0xA0) {
+ print ' | gurmukhi';
+ }
+ elsif ($value == 0xA8) {
+ print ' | gujarati';
+ }
+ elsif ($value == 0xB0) {
+ print ' | oriya';
+ }
+ elsif ($value == 0xB8) {
+ print ' | tamil';
+ }
+ elsif ($value == 0xC0) {
+ print ' | telugu';
+ }
+ elsif ($value == 0xC8) {
+ print ' | kannada';
+ }
+ elsif ($value == 0xD0) {
+ print ' | malayalam';
+ }
+ elsif ($value == 0xD8) {
+ print ' | sinhala';
+ }
+ elsif ($value == 0xE0) {
+ print ' | thai';
+ }
+ elsif ($value == 0xE8) {
+ print ' | lao';
+ }
+ elsif ($value == 0xF0) {
+ print ' | tibetan';
+ }
+ elsif ($value == 0x100) {
+ print ' | myanmar';
+ }
+ elsif ($value == 0x10A) {
+ print ' | georgian';
+ }
+ elsif ($value == 0x110) {
+ print ' | hangeul jamo';
+ }
+ elsif ($value == 0x120) {
+ print ' | ethiopic';
+ }
+ elsif ($value == 0x130) {
+ print ' | ethiopic';
+ }
+ elsif ($value == 0x138) {
+ print ' | eth+';
+ }
+ elsif ($value == 0x13A) {
+ print ' | cherokee';
+ }
+ elsif ($value == 0x140) {
+ print ' | unified canadian aboriginal syllabics';
+ }
+ elsif ($value == 0x160) {
+ print ' | unified canadian syllabics';
+ }
+ elsif ($value == 0x168) {
+ print ' | ogham';
+ }
+ elsif ($value == 0x16A) {
+ print ' | runic';
+ }
+ elsif ($value == 0x170) {
+ print ' | tagalog';
+ }
+ elsif ($value == 0x172) {
+ print ' | hanun';
+ }
+ elsif ($value == 0x174) {
+ print ' | buhid';
+ }
+ elsif ($value == 0x176) {
+ print ' | tagb';
+ }
+ elsif ($value == 0x178) {
+ print ' | khmer';
+ }
+ elsif ($value == 0x180) {
+ print ' | mongolian';
+ }
+ elsif ($value == 0x18B) {
+ print ' | canadian+';
+ }
+ elsif ($value == 0x190) {
+ print ' | limbu';
+ }
+ elsif ($value == 0x195) {
+ print ' | tai le';
+ }
+ elsif ($value == 0x198) {
+ print ' | new tai lue';
+ }
+ elsif ($value == 0x19E) {
+ print ' | km';
+ }
+ elsif ($value == 0x1A0) {
+ print ' | lontara';
+ }
+ elsif ($value == 0x1A2) {
+ print ' | tai tham';
+ }
+ elsif ($value == 0x1AB) {
+ print ' | reserved';
+ }
+ elsif ($value == 0x1B0) {
+ print ' | balinese';
+ }
+ elsif ($value == 0x1B8) {
+ print ' | sundanese';
+ }
+ elsif ($value == 0x1BC) {
+ print ' | batak';
+ }
+ elsif ($value == 0x1C0) {
+ print ' | lepcha';
+ }
+ elsif ($value == 0x1C5) {
+ print ' | ol chiki';
+ }
+ elsif ($value == 0x1C8) {
+ print ' | reserved';
+ }
+ elsif ($value == 0x1CD) {
+ print ' | vedic';
+ }
+ elsif ($value == 0x1D0) {
+ print ' | phonetic';
+ }
+ elsif ($value == 0x1D8) {
+ print ' | phonetic+';
+ }
+ elsif ($value == 0x1DC) {
+ print ' | combining';
+ }
+ elsif ($value == 0x1E0) {
+ print ' | latin extended additional';
+ }
+ elsif ($value == 0x1F0) {
+ print ' | greek+';
+ }
+}
+
+sub printcell_utf8 {
+ my ($value) = @_;
+ if ($value <= 0x7F) {
+ print ' | Single byte ASCII'
+ if $value == 0;
+ }
+ elsif ($value <= 0xBF) {
+ print ' | Multi-byte continuation'
+ if $value == 0x80;
+ }
+ elsif ($value <= 0xC1) {
+ print ' | (Overl.)'
+ if $value == 0xC0;
+ }
+ elsif ($value <= 0xDF) {
+ print ' | 2-byte sequence start'
+ if $value == 0xC2;
+ print ' | '
+ if $value == 0xD0;
+ }
+ elsif ($value <= 0xEF) {
+ print ' | 3-byte sequence start'
+ if $value == 0xE0;
+ }
+ elsif ($value <= 0xF4) {
+ print ' | 4-byte sequence'
+ if $value == 0xF0;
+ }
+ elsif ($value <= 0xF7) {
+ print ' | (Overflow)'
+ if $value == 0xF5;
+ }
+ elsif ($value <= 0xFB) {
+ print ' | 5-byte'
+ if $value == 0xF8;
+ }
+ elsif ($value <= 0xFD) {
+ print ' | 6-byte'
+ if $value == 0xFC;
+ }
+ elsif ($value <= 0xFF) {
+ print ' | Invalid'
+ if $value == 0xFE;
+ }
+ else {
+ print "\n".' | ?';
+ }
+}
+
print "\n";
my @nibble = (0..9, 'A'..'F');
for my $tablenum (0 .. $#tables) {
print '';
- printf '%s', $request[$tablenum];
+ printf '%s', $request[$tablenum] eq 'utf-8-strict' ? 'UTF-8' : $request[$tablenum];
print '';
for my $section (qw{thead}) {
print "<$section>â±";
@@ -63,9 +360,18 @@ for my $tablenum (0 .. $#tables) {
print "\n";
}
print ' | ';
- for my $msb (0 .. $#nibble) {
- print '', $nibble[$msb];
+ for my $msb (0 .. (length($tables[$tablenum]) || 256) - 1 >> 4) {
+ printf ' |
---|
%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) {
print ' | ';
|
---|
|