summaryrefslogtreecommitdiff
path: root/Build/source/utils/xindy-old/make-rules/alphabets/general/utf8.pl.in
diff options
context:
space:
mode:
Diffstat (limited to 'Build/source/utils/xindy-old/make-rules/alphabets/general/utf8.pl.in')
-rw-r--r--Build/source/utils/xindy-old/make-rules/alphabets/general/utf8.pl.in150
1 files changed, 150 insertions, 0 deletions
diff --git a/Build/source/utils/xindy-old/make-rules/alphabets/general/utf8.pl.in b/Build/source/utils/xindy-old/make-rules/alphabets/general/utf8.pl.in
new file mode 100644
index 00000000000..99b2f103de6
--- /dev/null
+++ b/Build/source/utils/xindy-old/make-rules/alphabets/general/utf8.pl.in
@@ -0,0 +1,150 @@
+#!/usr/bin/env perl
+
+$language = "A general sorting order for Western European languages";
+$prefix = "xy";
+$script = "latin";
+
+$alphabet = [
+['A', ['a','A'],['á','Á'],['à','À'],@u{['ă','Ă'],}['â','Â'],['ã','Ã'],['å','Å'],
+ ['ä','Ä']@u{,['ą','Ą']}],
+ [], # a with breve (romanian)
+ [], # a with circumflex (romanian)
+ [], # a with ogonek (polish)
+['B', ['b','B']],
+ [], # b with hook (hausa)
+['C', ['c','C']@u{,['č','Č'],['ć','Ć'],['ĉ','Ĉ']},['ç','Ç']],
+ [], # ch (spanish/traditional)
+ [], # cs (hungarian)
+ [], # c with caron (many)
+ [], # c with acute (croatian, lower sorbian, polish)
+ [], # c with circumflex (esperanto)
+ [], # c with cedilla (albanian, kurdish, turkish)
+['D', ['d','D']@u{,['ď','Ď'],['đ','Đ']}],
+ [], # dh (albanian)
+ [], # dz (hungarian)
+ [], # dzs (hungarian)
+ [], # d+z with caron (croatian)
+ [], # d+z with acute (upper sorbian)
+ [], # d with caron (slovak/large)
+ [], # d with stroke (croatian)
+ [], # d with hook (hausa)
+ [], # eth (icelandic)
+['E', ['e','E']@u{,['ě','Ě']},['é','É'],['è','È'],['ê','Ê'],['ë','Ë']@u{,['ę','Ę']}],
+ [], # e with caron (lower/upper sorbian)
+ [], # e with circumflex (kurdish)
+ [], # e with diaeresis (albanian)
+ [], # e with ogonek (polish)
+['F', ['f','F']],
+['G', ['g','G']@u{,['ĝ','Ĝ'],['ğ','Ğ']}],
+ [], # gj (albanian)
+ [], # gy (hungarian)
+ [], # g with circumflex (esperanto)
+ [], # g with breve (turkish)
+ [], # g with cedilla/comma (latvian)
+ [], # postpalatal fricative (gypsy/northrussian)
+['H', ['h','H']@u{,['ĥ','Ĥ']}],
+ [], # h with circumflex (esperanto)
+ [], # ch (many)
+ [], # dotless i (turkish)
+['I', ['i','I']@u{,['ı'],['','İ']},['í','Í'],['ì','Ì'],['î','Î'],['ï','Ï']],
+ [], # i with inverted breve below (gypsy/northrussian)
+ [], # i with circumflex (kurdish, romanian)
+ [], # i with diaeresis (gypsy/northrussian)
+['J', ['j','J']@u{,['ĵ','Ĵ']}],
+ [], # j with circumflex (esperanto)
+['K', ['k','K']],
+ [], # kh (gypsy/northrussian)
+ [], # k with cedilla/comma (latvian)
+ [], # k with hook (hausa)
+ [], # x (gypsy/northrussian)
+ [], # l with stroke (lower/upper sorbian)
+['L', ['l','L']@u{,['ľ','Ľ'],['ł','Ł']}],
+ [], # lj (croatian)
+ [], # ll (albanian, spanish/traditional)
+ [], # ly (hungarian)
+ [], # l with cedilla/comma (latvian)
+ [], # l with stroke (polish)
+ [], # l with caron (slovak/large)
+['M', ['m','M']],
+['N', ['n','N'],@u{['ň','Ň'],['ń','Ń'],}['ñ','Ñ']],
+ [], # nj (albanian, croatian)
+ [], # ny (hungarian)
+ [], # n with caron (slovak/large)
+ [], # n with acute (lower/upper sorbian, polish)
+ [], # n with tilde (spanish/modern, spanish/traditional)
+ [], # n with cedilla/comma (latvian)
+['O', ['o','O'],['ó','Ó'],['ò','Ò'],['ô','Ô'],['õ','Õ'],['ö','Ö']@u{,['ő','Ő']},
+ ['ø','Ø']],
+ [], # o with acute (polish, upper sorbian)
+ [], # o with circumflex (vietnamese)
+ [], # o with horn (vietnamese)
+ [], # o with diaeresis (hungarian, turkish)
+['P', ['p','P']],
+ [], # ph (gypsy/northrussian)
+['Q', ['q','Q']],
+['R', ['r','R']@u{,['ř','Ř'],['ŕ','Ŕ']}],
+ [], # rr (albanian)
+ [], # r with caron (czech, slovak/large, upper sorbian)
+ [], # r with acute (lower sorbian)
+ [], # r with cedilla/comma (latvian)
+['S', ['s','S']@9{,['š','Š']}@u{,['ś','Ś'],['ŝ','Ŝ'],['ș','Ș'],['ş','Ş']}],
+ [], # sh (albanian)
+ [], # sz (hungarian)
+ [], # s with caron (many)
+ [], # s with acute (lower sorbian, polish)
+ [], # s with circumflex (esperanto)
+ [], # s with comma below (romanian)
+ [], # s with cedilla (kurdish, turkish)
+ [], # z (estonian)
+ [], # z with caron (estonian)
+['T', ['t','T']@u{,['ť','Ť'],['ț','Ț']}],
+ [], # th (albanian)
+ [], # ty (hungarian)
+ [], # t with caron (slovak/large)
+ [], # t with comma below (romanian)
+ [], # c with acute (upper sorbian)
+['U', ['u','U'],['ú','Ú'],['ù','Ù']@u{,['ŭ','Ŭ']},['û','Û']@u{,['ů','Ů']},['ü','Ü'],
+ @u{['ű','Ű']}],
+ [], # u with breve (esperanto)
+ [], # u with circumflex (kurdish)
+ [], # u with horn (vietnamese)
+ [], # u with diaeresis (hungarian, turkish)
+['V', ['v','V']],
+['W', ['w','W']],
+ [], # o with tilde (estonian)
+ [], # a with diaeresis (estonian)
+ [], # o with diaeresis (estonian)
+ [], # u with diaeresis (estonian)
+['X', ['x','X']],
+ [], # xh (albanian)
+['Y', ['y','Y'],['ý','Ý'],['ÿ'@9{,'Ÿ'}]],
+ [], # y preceded by apostrophe (hausa)
+ [], # yogh (english)
+['Z', ['z','Z']@9{,['ž','Ž']}@u{,['ź','Ź'],['ż','Ż']}],
+ [], # zh (albanian)
+ [], # zs (hungarian)
+ [], # z with caron (many)
+ [], # z with acute (lower sorbian, polish)
+ [], # z with dot above (polish)
+ [], # thorn (icelandic)
+ [], # wynn (english)
+ [], # ligature ae (danish, icelandic, norwegian)
+ [], # o with stroke (danish, norwegian)
+ [], # a with ring above (danish, norwegian, swedish)
+ [], # a with diaeresis (finnish, swedish)
+ [], # o with diaeresis (finnish, swedish)
+ [], # a with ring above (icelandic)
+];
+
+$sortcase = 'Aa';
+#$sortcase = 'aA';
+
+$ligatures = [
+[['ß'], 'after', [['s','s']]],
+[['æ','Æ'], 'after', [['a','e'], ['A','e']]],
+@9{[['œ','Œ'], 'after', [['o','e'], ['O','e']]]}
+];
+
+@special = ('?', '!', '.', 'letters', '-', '\'');
+
+do 'make-rules.pl';