unicode: full repository of common accented latin

All letter/diacritic combinations for major european languages,
included for ?html for a more complete entity coverage.

diff --git a/unicode-table.inc.pl b/unicode-table.inc.pl
index 3cebcebec89e5ffd6a88ece8f8308dba5e455969..7ab3dd3c79292f96791019ebac85e436dde9288c 100644 (file)
--- a/unicode-table.inc.pl
+++ b/unicode-table.inc.pl
@@ -106,6 +106,25 @@ latin => {
                . ă ę œ ů š ð
                . ı ė º ư ș đ
        }],
+       vowels   => [qw{
+               . á é í ó ú ý
+               . â ê î ô û ŷ
+               . à è ì ò ù ỳ
+               . ã ẽ ĩ õ ũ ỹ
+               . ä ë ï ö ü ÿ
+               . æ & ij œ ᵫ -
+               . å - ı ⱺ ů ẙ
+               . ă ĕ ĭ ŏ ŭ -
+               . ǎ ě ǐ ǒ ǔ -
+               . ą ę į ǫ ų -
+       }],
+       westeuro => [qw{
+               . ç ð ñ ß þ
+       }],
+       easteuro => [qw{
+               . č ď ľ ň ř š ť ž
+               . ć đ ł ń ŕ ś ŧ ź ż
+       }],
        uncommon => [qw{
                .>Englisc   æ ð ē ȝ œ þ ƿ
                .>Sámi      á č đ ŋ š ŧ ž

diff --git a/unicode.plp b/unicode.plp
index 7100aaddf9245aad99c312b5c533303260cebfc3..76c31ec6f37e4c9312898a22f4cb84abe583565b 100644 (file)
--- a/unicode.plp
+++ b/unicode.plp
@@ -117,6 +117,12 @@ my @config = qw(
                        ?kataderiv
 );
 
+splice @config, 4, 2, qw(
+               latin/vowels=-5?latin/vowels
+                        westeuro
+                       ?easteuro
+) if exists $get{html};
+
 $_ and m{/*+(.+)} and @config = split /[ ]/, $1 for $ENV{PATH_INFO}, $get{q};
 
 my $tables = do 'unicode-table.inc.pl' or die $@ || $!;