Use Unicode notation (U+XXXX) instead of HTML notation (&#xXXXX;) in comments

[lhc/web/wiklou.git] / languages / classes / LanguageKu.php

diff --git a/languages/classes/LanguageKu.php b/languages/classes/LanguageKu.php
index ef77775..580f64a 100644 (file)
--- a/languages/classes/LanguageKu.php
+++ b/languages/classes/LanguageKu.php
@@ -57,16 +57,16 @@ class KuConverter extends LanguageConverter {
                '؟' => '?',
 
                # digits
-               '٠' => '0', # ٠
-               '١' => '1', # ١
-               '٢' => '2', # ٢
-               '٣' => '3', # ٣
-               '٤' => '4', # ٤
-               '٥' => '5', # ٥
-               '٦' => '6', # ٦
-               '٧' => '7', # ٧
-               '٨' => '8', # ٨
-               '٩' => '9', # ٩
+               '٠' => '0', # U+0660
+               '١' => '1', # U+0661
+               '٢' => '2', # U+0662
+               '٣' => '3', # U+0663
+               '٤' => '4', # U+0664
+               '٥' => '5', # U+0665
+               '٦' => '6', # U+0666
+               '٧' => '7', # U+0667
+               '٨' => '8', # U+0668
+               '٩' => '9', # U+0669
        ];
 
        public $mLatinToArabic = [
@@ -130,16 +130,16 @@ class KuConverter extends LanguageConverter {
 
 /*             # deactivated for now, breaks links i.e. in header of Special:Recentchanges :-(
                # digits
-               '0' => '٠', # ٠
-               '1' => '١', # ١
-               '2' => '٢', # ٢
-               '3' => '٣', # ٣
-               '4' => '٤', # ٤
-               '5' => '٥', # ٥
-               '6' => '٦', # ٦
-               '7' => '٧', # ٧
-               '8' => '٨', # ٨
-               '9' => '٩', # ٩
+               '0' => '٠', # U+0660
+               '1' => '١', # U+0661
+               '2' => '٢', # U+0662
+               '3' => '٣', # U+0663
+               '4' => '٤', # U+0664
+               '5' => '٥', # U+0665
+               '6' => '٦', # U+0666
+               '7' => '٧', # U+0667
+               '8' => '٨', # U+0668
+               '9' => '٩', # U+0669
 */
                ];
 
@@ -192,7 +192,8 @@ class KuConverter extends LanguageConverter {
                /* From Kazakh interface, maybe we need it later
                $breaks = '[^\w\x80-\xff]';
                // regexp for roman numbers
-               $roman = 'M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})';
+               // Lookahead assertion ensures $roman doesn't match the empty string
+               $roman = '(?=[MDCLXVI])M{0,4}(C[DM]|D?C{0,3})(X[LC]|L?X{0,3})(I[VX]|V?I{0,3})';
                $roman = '';
 
                $reg = '/^'.$roman.'$|^'.$roman.$breaks.'|'.$breaks.$roman.'$|'.$breaks.$roman.$breaks.'/';