use 5.014;
use warnings;
+use utf8;
+{
- default => [qw( u+0-27F utf-8+realsize iso-8859-1 iso-8859-15 cp1252 cp437 cp850 )],
+ default => [qw( u+0-27F utf8+realsize iso-8859-1 iso-8859-15 cp1252 cp437 cp850 )],
unicode => [qw( uu+cols=32+realsize u+0-FFF u+1000-18AF u+18B0-1FFF )],
us => [qw( cp437 cp863 gsm0338 AdobeStandardEncoding )],
ebcdic => [qw( cp37 cp500 cp1047 posix-bc cp1026 cp875 )],
+600 +8A0-8BF+8E0 +750-77F )],
greek => [qw( iso-8859-7 cp1253 MacGreek cp737 cp869 +370 +1F00 )],
hebrew => [qw( iso-8859-8 cp1255 MacHebrew cp862 +590 )],
- thai => [qw( iso-8859-11 cp874 MacThai )],
+ thai => [qw( iso-8859-11 cp874 MacThai )], # U+0E00 identical to iso-8859-11
vietnamese => [qw( viscii cp1258 MacVietnamese )],
symbols => [qw( symbol dingbats MacDingbats wingdings wingdings2 wingdings3 webdings )],
11 => 'thai',
'ascii' => {inherit => ['' => '00-7F']},
- 'cp437' => {inherit => ['cp850' => 0, 'ascii' => '00-1F+80']}, # ascii range overridden later
+ 'cp437' => {
+ inherit => ['cp850' => 0, 'ascii' => '00-1F+80'], # ascii range overridden later
+ replace => {
+ 0 => ' ☺☻♥♦♣♠•◘○◙♂♀♪♫☼►◄↕‼¶§▬↨↑↓→←∟↔▲▼', # visible variants of control characters
+ 0xED => 'ϕ', # non-greek usage and appearance
+ },
+ },
'gsm0338' => {inherit => ['ascii' => '00-7F']},
'dingbats' => {inherit => ['' => '20-7F+A0']},
- 'MacDingbats' => {inherit => ['dingbats' => '80-9F']},
- 'AdobeZdingbat'=> {inherit => ['MacDingbats' => '80-9F']}, # should be identical but maps to private use
- 'symbol' => {inherit => ['' => '20-7F+A0']},
- 'AdobeSymbol' => {inherit => ['symbol' => '20-7F+A0', '' => '20-7F+A0']}, # minor differences, irrelevant except for different '€'
- 'wingdings' => {inherit => ['' => '20']},
- 'wingdings2' => {inherit => ['' => '20']},
- 'wingdings3' => {inherit => ['' => '20']},
- 'webdings' => {inherit => ['' => '20']},
+ 'macdingbats' => {inherit => ['dingbats' => '80-9F']},
+ 'adobezdingbat'=> {inherit => ['MacDingbats' => '80-9F']}, # should be identical but maps to private use
+ 'symbol' => {
+ inherit => ['' => '20-7F+A0'],
+ replace => {
+ 0x60 => '│', # replace radical extender by closest unicode equivalent
+ 0xBD => '⏐⎯', # arrow extenders
+ 0xD2 => '®©™', # serif variants
+ 0xE0 => '◊', # replace lookalike, should match AdobeSymbol
+ 0xE2 => '®©™', # sans-serif variants
+ 0xE6 => '⎛⎜⎝⎡⎢⎣⎧⎨⎩⎪',
+ 0xF0 => '€',
+ 0xF4 => '⎮⌡⎞⎟⎠⎤⎥⎦⎫⎬⎭',
+ },
+ },
+ 'adobesymbol' => {inherit => ['symbol' => '20-7F+A0', '' => '20-7F+A0']}, # minor differences, irrelevant except for different '€'
+ 'wingdings' => {inherit => ['' => '20'], setup => sub {require Encode::Wingdings}},
+ 'wingdings2' => {inherit => ['' => '20'], setup => sub {require Encode::Wingdings2}},
+ 'wingdings3' => {inherit => ['' => '20'], setup => sub {require Encode::Wingdings3}},
+ 'webdings' => {inherit => ['' => '20'], setup => sub {require Encode::Webdings}},
'iso-8859-2' => {inherit => ['iso-8859-1' => 'A0']},
'iso-8859-3' => {inherit => ['iso-8859-1' => 'A0']}, #TODO: also apply to iso-8859-9
'koi8-u' => {inherit => ['koi8-r' => '90-BF']},
'koi8-f' => {inherit => ['koi8-u' => '90-BF']},
- 'MacRomanian' => {inherit => ['MacRoman' => 'A0-BF+D0-DF']},
- 'MacRumanian' => {inherit => ['MacRomanian' => 'A0-BF+D0-DF', 'MacRoman' => 'A0-BF+D0-DF']},
- 'MacCroatian' => {inherit => ['MacRoman' => 'A0']},
- 'MacCentralEurRoman' => {inherit => ['MacRoman' => '80']},
- 'MacIcelandic' => {inherit => ['MacRoman' => 'A0-AF+D0-EF']},
- 'MacTurkish' => {inherit => ['MacRoman' => 'D0-DF']}, # F5 is unassigned
- 'MacSami' => {inherit => ['MacIcelandic' => '90-BF+D0-DF+F0', 'MacRoman' => '90']},
- 'MacGreek' => {inherit => ['MacRoman' => '80']},
- 'MacCyrillic' => {inherit => ['MacRoman' => '80']},
- 'MacHebrew' => {inherit => ['iso-8859-8' => '80', 'MacRoman' => '80-8F+A0']}, # partial ascii
- 'MacArabic' => {inherit => ['iso-8859-6' => '80', 'cp864' => '80', 'MacRoman' => '80']}, #TODO: multiple parents
- 'MacFarsi' => {inherit => ['MacArabic' => 'B0-BF', 'MacRoman' => '80']},
+ 'macromanian' => {inherit => ['MacRoman' => 'A0-BF+D0-DF']},
+ 'macrumanian' => {inherit => ['MacRomanian' => 'A0-BF+D0-DF', 'MacRoman' => 'A0-BF+D0-DF']},
+ 'maccroatian' => {inherit => ['MacRoman' => 'A0']},
+ 'maccentraleurroman' => {inherit => ['MacRoman' => '80']},
+ 'macicelandic' => {inherit => ['MacRoman' => 'A0-AF+D0-EF']},
+ 'macturkish' => {inherit => ['MacRoman' => 'D0-DF']}, # F5 is unassigned
+ 'macsami' => {inherit => ['MacIcelandic' => '90-BF+D0-DF+F0', 'MacRoman' => '90']},
+ 'macgreek' => {inherit => ['MacRoman' => '80']},
+ 'maccyrillic' => {inherit => ['MacRoman' => '80']},
+ 'machebrew' => {
+ inherit => ['iso-8859-8' => '80', 'MacRoman' => '80-8F+A0'], # ignore partial ascii
+ varchar => 1,
+ replace => {
+ # strip private use characters for unneeded roundtrip
+ 0xDE => chr(0x5C7), # qamats qatan
+ 0xC0 => 'לֹ', # lamed holam
+ #TODO: private use for canoral codes (obsolete nikud positioning)
+ },
+ },
+ 'macarabic' => {inherit => ['iso-8859-6' => '80', 'cp864' => '80', 'MacRoman' => '80']}, #TODO: multiple parents
+ 'macfarsi' => {inherit => ['MacArabic' => 'B0-BF', 'MacRoman' => '80']},
+ 'macthai' => {
+ inherit => ['iso-8859-11' => '80-9F+D0'],
+ varchar => 1,
+ replace => {
+ # strip appended private use characters for unneeded roundtrip
+ 0x83 => "\x{E48}", 0x88 => "\x{E48}", 0x98 => "\x{E48}",
+ 0x84 => "\x{E49}", 0x89 => "\x{E49}", 0x99 => "\x{E49}",
+ 0x85 => "\x{E4A}", 0x8A => "\x{E4A}", 0x9A => "\x{E4A}",
+ 0x86 => "\x{E4B}", 0x8B => "\x{E4B}", 0x9B => "\x{E4B}",
+ 0x87 => "\x{E4C}", 0x8C => "\x{E4C}", 0x9C => "\x{E4C}",
+ 0x8F => "\x{E4D}",
+ 0x92 => "\x{E31}", 0x93 => "\x{E47}", 0x94 => "\x{E34}",
+ 0x95 => "\x{E35}", 0x96 => "\x{E36}", 0x97 => "\x{E37}",
+ },
+ },
'cp37' => {inherit => ['posix-bc' => '00']},
'posix-bc' => {inherit => ['cp1047' => '40']},
'cp1047' => {inherit => ['cp37' => '10-2F+50-5F+A0-BF']},
'cp1026' => {inherit => ['cp37' => '40']},
'cp875' => {inherit => ['cp37' => '30']},
+
+ '' => {setup => sub {
+ my $row = shift;
+ $row->{offset} = delete $row->{startpoint};
+ $row->{set} = 'Unicode characters';
+ my $block = $row->{offset} >> 8;
+ $row->{endpoint} ||= ($block + 1 << 8) - 1;
+ $block == ($row->{endpoint} >> 8) or undef $block;
+
+ $row->{table} = join '', map { chr } $row->{offset} .. $row->{endpoint};
+ utf8::upgrade($row->{table}); # prevent latin1 output
+
+ $row->{endpoint} -= $row->{offset};
+
+ if (defined $block) {
+ $row->{set} = sprintf 'Unicode block U+%02Xxx', $block;
+ $row->{offset} %= 0x100;
+ }
+
+ return $row;
+ }},
+ u => {setup => sub {
+ my $row = shift;
+ state $celldata = do 'charset-unicode.inc.pl'
+ or Alert('Table data could not be read', $@ || $!);
+ $row->{cell} = $celldata;
+
+ $row->{endpoint} ||= 0x1FFF;
+ $row->{set} = 'Unicode ' . (
+ $row->{startpoint} < 0x1000 && $row->{endpoint} < 0x1000 ? 'BMP' :
+ $row->{startpoint} >= 0x1000 && $row->{endpoint} < 0x2000 ? 'SMP' :
+ 'allocations'
+ );
+ return $row;
+ }},
+ uu => {setup => sub {
+ my $row = shift;
+ $row->{cell} = do 'charset-ucplanes.inc.pl'
+ or Alert('Table data could not be read', $@ || $!);
+ $row->{endpoint} ||= 0x3FF;
+ $row->{set} = 'Unicode planes';
+ return $row;
+ }},
+ utf8 => {setup => sub {
+ my $row = shift;
+ $row->{set} = 'UTF-8';
+ $row->{cell} = do 'charset-utf8.inc.pl'
+ or Alert('Table data could not be read', $@ || $!);
+ return $row;
+ }},
+ 'utf-8' => 'utf8',
};