charset: generic varchar option to identify array maps

Clears the last hardcoded name exceptions.

diff --git a/charset-encoding.inc.pl b/charset-encoding.inc.pl
index b40d75a2661871ff776613da8a82115e742a4d15..ec53ef54ac66b8dc0c825b76f8090ded15a7fbba 100644 (file)
--- a/charset-encoding.inc.pl
+++ b/charset-encoding.inc.pl
@@ -133,6 +133,7 @@ use utf8;
        '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
@@ -144,6 +145,7 @@ use utf8;
        '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}",

diff --git a/charset.plp b/charset.plp
index 6300622f3ea16088b40c6aee93c63a96f93ec1b2..6ec4a242986f85ef4475ae7b9441729995fe0f03 100644 (file)
--- a/charset.plp
+++ b/charset.plp
@@ -152,7 +152,7 @@ sub tabinput {
        if ($row{set}) {}
        elsif ($row{set} = Encode::resolve_alias($input)) {
                $row{offset} = delete $row{startpoint};
-               if ($row{set} eq 'MacHebrew' or $row{set} eq 'MacThai') {
+               if ($charset->{varchar}) {
                        # array of possibly multiple characters per code point
                        $row{table} = [
                                map { Encode::decode($row{set}, pack 'C*', $_) } $row{offset} .. $row{endpoint}