From daf9c01a2c25515eea87fb4f4c905f49c30d0214 Mon Sep 17 00:00:00 2001
From: Derek Jones <derek.jones@ellislab.com>
Date: Fri, 5 Mar 2010 10:29:30 -0600
Subject: added convert_accented_characters() function to Text Helper

---
 system/application/config/foreign_chars.php | 64 +++++++++++++++++++++++++++++
 system/helpers/text_helper.php              | 48 +++++++++++++++++++---
 2 files changed, 107 insertions(+), 5 deletions(-)
 create mode 100644 system/application/config/foreign_chars.php

diff --git a/system/application/config/foreign_chars.php b/system/application/config/foreign_chars.php
new file mode 100644
index 000000000..8d70a2f62
--- /dev/null
+++ b/system/application/config/foreign_chars.php
@@ -0,0 +1,64 @@
+<?php  if ( ! defined('BASEPATH')) exit('No direct script access allowed');
+/*
+| -------------------------------------------------------------------
+| Foreign Characters
+| -------------------------------------------------------------------
+| This file contains an array of foreign characters for transliteration
+| conversion used by the Text helper
+|
+*/
+$foreign_characters = array('223'	=>	"ss", // ß
+							'224'	=>  "a",  
+							'225'	=>  "a", 
+							'226'	=>	"a", 
+							'229'	=>	"a",
+							'227'	=>	"ae", 
+							'230'	=>	"ae", 
+							'228'	=>	"ae",
+							'231'	=>	"c",
+							'232'	=>	"e",  // è
+							'233'	=>	"e",  // é
+							'234'	=>	"e",  // ê  								
+							'235'	=>	"e",  // ë
+							'236'	=>  "i",
+							'237' 	=>  "i",
+							'238' 	=>	"i",
+							'239' 	=>	"i",
+							'241'	=>	"n",
+							'242'	=>  "o",
+							'243'	=>  "o",
+							'244' 	=>	"o", 
+							'245'	=>	"o",
+							'246'	=>	"oe", // ö
+							'249'	=>  "u",
+							'250' 	=>  "u", 
+							'251' 	=>	"u",
+							'252'	=>	"ue", // ü
+							'255'	=>	"y",
+							'257'	=>	"aa", 
+							'269'	=>	"ch", 
+							'275'	=>	"ee", 
+							'291'	=>	"gj", 
+							'299'	=>	"ii", 
+							'311'	=>	"kj", 
+							'316'	=>	"lj", 
+							'326'	=>	"nj", 
+							'353'	=>	"sh", 
+							'363'	=>	"uu", 
+							'382'	=>	"zh",
+							'256'	=>	"aa", 
+							'268'	=>	"ch", 
+							'274'	=>	"ee", 
+							'290'	=>	"gj", 
+							'298'	=>	"ii", 
+							'310'	=>	"kj", 
+							'315'	=>	"lj", 
+							'325'	=>	"nj", 
+							'352'	=>	"sh", 
+							'362'	=>	"uu", 
+							'381'	=>	"zh",
+							);				
+
+
+/* End of file foreign_chars.php */
+/* Location: ./system/application/config/foreign_chars.php */
\ No newline at end of file
diff --git a/system/helpers/text_helper.php b/system/helpers/text_helper.php
index 1e672937b..477260216 100644
--- a/system/helpers/text_helper.php
+++ b/system/helpers/text_helper.php
@@ -87,7 +87,7 @@ if ( ! function_exists('character_limiter'))
 		{
 			return $str;
 		}
-
+									
 		$out = "";
 		foreach (explode(' ', trim($str)) as $val)
 		{
@@ -136,7 +136,7 @@ if ( ! function_exists('ascii_to_entities'))
 					$out  .= '&#'.array_shift($temp).';';
 					$count = 1;
 				}
-
+			
 				$out .= $str[$i];
 		   }
 		   else
@@ -248,7 +248,7 @@ if ( ! function_exists('word_censor'))
 		// \w, \b and a few others do not match on a unicode character
 		// set for performance reasons. As a result words like über
 		// will not match on a word boundary. Instead, we'll assume that
-		// a bad word will be bookended by any of these characters.
+		// a bad word will be bookeneded by any of these characters.
 		$delim = '[-_\'\"`(){}<>\[\]|!?@#%&,.:;^~*+=\/ 0-9\n\r\t]';
 
 		foreach ($censored as $badword)
@@ -352,6 +352,44 @@ if ( ! function_exists('highlight_phrase'))
 		return $str;
 	}
 }
+
+// ------------------------------------------------------------------------
+
+/**
+ * Convert Accented Foreign Characters to ASCII
+ *
+ * @access	public
+ * @param	string	the text string
+ * @return	string
+ */	
+if ( ! function_exists('convert_accented_characters'))
+{
+	function convert_accented_characters($match)
+	{
+		if ( ! file_exists(APPPATH.'config/foreign_chars'.EXT))
+		{
+			return $match;
+		}
+	
+		include APPPATH.'config/foreign_chars'.EXT;
+	
+		if ( ! isset($foreign_characters))
+		{
+			return $match;
+		}
+								
+		$ord = ord($match['1']);
+		
+		if (isset($foreign_characters[$ord]))
+		{
+			return $foreign_characters[$ord];
+		}
+		else
+		{
+			return $match['1'];
+		}
+	}
+}
 	
 // ------------------------------------------------------------------------
 
@@ -431,7 +469,7 @@ if ( ! function_exists('word_wrap'))
 			// word into smaller chunks so we'll add it back to our current line
 			if ($temp != '')
 			{
-				$output .= $temp . "\n" . $line; 
+				$output .= $temp."\n".$line; 
 			}
 			else
 			{
@@ -456,7 +494,7 @@ if ( ! function_exists('word_wrap'))
 		return $output;	
 	}
 }
-
+ 
 
 /* End of file text_helper.php */
 /* Location: ./system/helpers/text_helper.php */
\ No newline at end of file
-- 
cgit v1.2.3-24-g4f1b