X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/0c9d5cd332b3a9124f75926de5094c90b353e238..b690e02814ec7b65b10789fac83cd7c8b2b72b30:/charset-encoding.inc.pl

diff --git a/charset-encoding.inc.pl b/charset-encoding.inc.pl
index 71ba2ba..6e46477 100644
--- a/charset-encoding.inc.pl
+++ b/charset-encoding.inc.pl
@@ -28,7 +28,7 @@ use utf8;
 	                   +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 )],
 
@@ -131,9 +131,33 @@ use utf8;
 	'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
+	'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']},
@@ -164,8 +188,9 @@ use utf8;
 	}},
 	u              => {setup => sub {
 		my $row = shift;
-		$row->{cell} = do 'charset-unicode.inc.pl'
+		state $celldata = do 'charset-unicode.inc.pl'
 			or Alert('Table data could not be read', $@ || $!);
+		$row->{cell} = $celldata;
 
 		$row->{endpoint} ||= 0x1FFF;
 		$row->{set} = 'Unicode ' . (
@@ -188,7 +213,6 @@ use utf8;
 		$row->{set} = 'UTF-8';
 		$row->{cell} = do 'charset-utf8.inc.pl'
 			or Alert('Table data could not be read', $@ || $!);
-		$row->{endpoint} = 0xFF;
 		return $row;
 	}},
 	'utf-8'        => 'utf8',