From 1abfaba47f3c1c4352eb728afcd4b6871b7bb4a0 Mon Sep 17 00:00:00 2001
From: Andreas Gohr <andi@splitbrain.org>
Date: Tue, 21 Feb 2006 22:26:05 +0100
Subject: fixes for utf-8 to/from unicode conversion

The functions utf8_to unicode and unicode_to_utf8 didn't work correctly
with some 3 and 4 byte strings. This exchanges those functions against
two more sophisticated ones. It also adds unit testing for them.

darcs-hash:20060221212605-7ad00-7bfefe8c9615d5a7f3b33c279ce79d4200d4778c.gz
---
 _test/cases/inc/utf8_unicode.test.php | 60 +++++++++++++++++++++++++++++++++++
 _test/cases/inc/utf8_utf16be.test.php |  2 +-
 2 files changed, 61 insertions(+), 1 deletion(-)
 create mode 100644 _test/cases/inc/utf8_unicode.test.php

(limited to '_test')

diff --git a/_test/cases/inc/utf8_unicode.test.php b/_test/cases/inc/utf8_unicode.test.php
new file mode 100644
index 000000000..453aad216
--- /dev/null
+++ b/_test/cases/inc/utf8_unicode.test.php
@@ -0,0 +1,60 @@
+<?php
+
+require_once DOKU_INC.'inc/utf8.php';
+
+// use no mbstring help here
+if(!defined('UTF8_NOMBSTRING')) define('UTF8_NOMBSTRING',1);
+
+class utf8_unicode_test extends UnitTestCase {
+
+    function test_from_1byte(){
+        $in  = 'a';
+        $out = array(97);
+        $this->assertEqual(utf8_to_unicode($in),$out);
+    }
+
+    function test_from_2byte(){
+        $in  = "\xc3\xbc";
+        $out = array(252);
+        $this->assertEqual(utf8_to_unicode($in),$out);
+    }
+
+    function test_from_3byte(){
+        $in  = "\xe2\x99\x8a";
+        $out = array(9802);
+        $this->assertEqual(utf8_to_unicode($in),$out);
+    }
+
+    function test_from_4byte(){
+        $in  = "\xf4\x80\x80\x81";
+        $out = array(1048577);
+        $this->assertEqual(utf8_to_unicode($in),$out);
+    }
+
+    function test_to_1byte(){
+        $out  = 'a';
+        $in = array(97);
+        $this->assertEqual(unicode_to_utf8($in),$out);
+    }
+
+    function test_to_2byte(){
+        $out  = "\xc3\xbc";
+        $in = array(252);
+        $this->assertEqual(unicode_to_utf8($in),$out);
+    }
+
+    function test_to_3byte(){
+        $out  = "\xe2\x99\x8a";
+        $in = array(9802);
+        $this->assertEqual(unicode_to_utf8($in),$out);
+    }
+
+    function test_to_4byte(){
+        $out  = "\xf4\x80\x80\x81";
+        $in = array(1048577);
+        $this->assertEqual(unicode_to_utf8($in),$out);
+    }
+
+}
+
+//Setup VIM: ex: et ts=4 enc=utf-8 :
diff --git a/_test/cases/inc/utf8_utf16be.test.php b/_test/cases/inc/utf8_utf16be.test.php
index 2d79ca35a..3a346da51 100644
--- a/_test/cases/inc/utf8_utf16be.test.php
+++ b/_test/cases/inc/utf8_utf16be.test.php
@@ -3,7 +3,7 @@
 require_once DOKU_INC.'inc/utf8.php';
 
 // use no mbstring help here
-define('UTF8_NOMBSTRING',1);
+if(!defined('UTF8_NOMBSTRING')) define('UTF8_NOMBSTRING',1);
 
 class utf8_utf16be_test extends UnitTestCase {
     // some chars from various code regions
-- 
cgit v1.2.3