From 176ae32b3f32b45a6ff8c81921aa9fbed2e28ace Mon Sep 17 00:00:00 2001
From: Andreas Gohr <andi@splitbrain.org>
Date: Sat, 11 Oct 2008 11:10:34 +0200
Subject: Do romanization of certain characters different from what deaccent
 does FS#1117

Some characters are deaccented/romanized different in different languages, we
now do one way in deaccent and the other way in romanize. Giving the user a
choice what she prefers. (Currently affects a handful scandinavian letters).

darcs-hash:20081011091034-7ad00-08535e03639b0b0c634e2438609ac10545f14f48.gz
---
 _test/cases/inc/utf8_romanize.test.php | 10 ++++++++++
 inc/utf8.php                           |  3 +++
 2 files changed, 13 insertions(+)

diff --git a/_test/cases/inc/utf8_romanize.test.php b/_test/cases/inc/utf8_romanize.test.php
index 28595b594..9aade570b 100644
--- a/_test/cases/inc/utf8_romanize.test.php
+++ b/_test/cases/inc/utf8_romanize.test.php
@@ -22,5 +22,15 @@ class utf8_romanize_test extends UnitTestCase {
             $line++;
         }
     }
+
+    /**
+     * Test romanization of character that would usually be deaccented in a different
+     * way FS#1117
+     *
+     * @author Andreas Gohr <andi@splitbrain.org>
+     */
+    function test_deaccented(){
+        $this->assertEqual("a A a A a o O",utf8_romanize("å Å ä Ä ä ö Ö"));
+    }
 }
 //Setup VIM: ex: et ts=4 enc=utf-8 :
diff --git a/inc/utf8.php b/inc/utf8.php
index 99e2fcaa1..966c40c6c 100644
--- a/inc/utf8.php
+++ b/inc/utf8.php
@@ -1184,6 +1184,9 @@ $UTF8_SPECIAL_CHARS2 =
  */
 global $UTF8_ROMANIZATION;
 $UTF8_ROMANIZATION = array(
+  // scandinavian - differs from what we do in deaccent
+  'å'=>'a','Å'=>'A','ä'=>'a','Ä'=>'A','ö'=>'o','Ö'=>'O', 
+
   //russian cyrillic
   'а'=>'a','А'=>'A','б'=>'b','Б'=>'B','в'=>'v','В'=>'V','г'=>'g','Г'=>'G',
   'д'=>'d','Д'=>'D','е'=>'e','Е'=>'E','ё'=>'jo','Ё'=>'Jo','ж'=>'zh','Ж'=>'Zh',
-- 
cgit v1.2.3