summaryrefslogtreecommitdiff
path: root/indexing/xindy/contrib/xindy-persian/source/variant3-utf8.pl.in
diff options
context:
space:
mode:
Diffstat (limited to 'indexing/xindy/contrib/xindy-persian/source/variant3-utf8.pl.in')
-rw-r--r--indexing/xindy/contrib/xindy-persian/source/variant3-utf8.pl.in181
1 files changed, 181 insertions, 0 deletions
diff --git a/indexing/xindy/contrib/xindy-persian/source/variant3-utf8.pl.in b/indexing/xindy/contrib/xindy-persian/source/variant3-utf8.pl.in
new file mode 100644
index 0000000000..3f3d32c94c
--- /dev/null
+++ b/indexing/xindy/contrib/xindy-persian/source/variant3-utf8.pl.in
@@ -0,0 +1,181 @@
+#!/usr/bin/perl
+
+$language = "Persian";
+$variant = "Three";
+$prefix = "pe";
+$script = "arabic";
+
+$alphabet = [
+['الف',['آ']],
+['الف',['أ']],
+['الف',['ا']],
+['ب',['ب']],
+['پ',['پ']],
+['ت',['ت']],
+['ث',['ث']],
+['ج',['ج']],
+['چ',['چ']],
+['ح',['ح']],
+['خ',['خ']],
+['د',['د']],
+['ذ',['ذ']],
+['ر',['ر']],
+['ز',['ز']],
+['ژ',['ژ']],
+['س',['س']],
+['ش',['ش']],
+['ص',['ص']],
+['ض',['ض']],
+['ط',['ط']],
+['ظ',['ظ']],
+['ع',['ع']],
+['غ',['غ']],
+['ف',['ف']],
+['ق',['ق']],
+['ک',['ک']],
+['گ',['گ']],
+['ل',['ل']],
+['م',['م']],
+['ن',['ن']],
+['و',['ؤ','و']],
+['ه',['ه']],
+['ی',['ئ','ی']],
+['A', ['a','A'],['à','À']],
+ [], # a with breve (romanian)
+ [], # a with circumflex (romanian)
+ [], # a with ogonek (polish)
+['B', ['b','B']],
+ [], # b with hook (hausa)
+['C', ['c','C'],['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'],['ð','Ð']],
+ [], # 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'],['é','É'],['è','È'],['ë','Ë'],['ê','Ê']],
+ [], # e with caron (lower/upper sorbian)
+ [], # e with circumflex (kurdish)
+ [], # e with diaeresis (albanian)
+ [], # e with ogonek (polish)
+['F', ['f','F']],
+['G', ['g','G']],
+ [], # gj (albanian)
+ [], # gy (hungarian)
+ [], # g with circumflex (esperanto)
+ [], # g with breve (turkish)
+ [], # g with cedilla/comma (latvian)
+ [], # postpalatal fricative (gypsy/northrussian)
+['H', ['h','H']],
+ [], # h with circumflex (esperanto)
+ [], # ch (many)
+ [], # dotless i (turkish)
+['I', ['i','I'],['ï','Ï']],
+ [], # i with inverted breve below (gypsy/northrussian)
+ [], # i with circumflex (kurdish, romanian)
+ [], # i with diaeresis (gypsy/northrussian)
+['J', ['j','J']],
+ [], # 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']],
+ [], # 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'],['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'],['ö','Ö'],['ô','Ô']],
+ [], # 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']],
+ [], # rr (albanian)
+ [], # r with caron (czech, slovak/large, upper sorbian)
+ [], # r with acute (lower sorbian)
+ [], # r with cedilla/comma (latvian)
+['S', ['s','S']],
+ [], # 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']],
+ [], # th (albanian)
+ [], # ty (hungarian)
+ [], # t with caron (slovak/large)
+ [], # t with comma below (romanian)
+ [], # c with acute (upper sorbian)
+['U', ['u','U']],
+ [], # 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']],
+ [], # y preceded by apostrophe (hausa)
+[@u{'Ȝ', ['ȝ','Ȝ']}],
+['Z', ['z','Z']],
+ [], # zh (albanian)
+ [], # zs (hungarian)
+ [], # z with caron (many)
+ [], # z with acute (lower sorbian, polish)
+ [], # z with dot above (polish)
+['Þ', ['þ','Þ']],
+[@u{'ƿ', ['ƿ','Ƿ']}],
+ [], # 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 = [
+[['æ','Æ'], 'after', [['a','e'], ['A','e']]],
+[['œ','Œ'], 'after', [['o','e'], ['O','e']]]
+];
+
+@special = ('?', '!', '.', 'letters', '-', '\'', '{', '}','ّ','َ','ِ','ُ','ً','ٍ','ٌ','ْ','ٔ','ء','‌','«','»','ـ', '،', '؛');
+
+do 'make-rules.pl';