1 files changed, 110 insertions, 97 deletions
diff --git a/phpBB/includes/utf/utf_tools.php b/phpBB/includes/utf/utf_tools.php
index 6f3ac93305..e60a40a195 100644
--- a/phpBB/includes/utf/utf_tools.php
+++ b/phpBB/includes/utf/utf_tools.php
@@ -1,10 +1,13 @@
 <?php
 /**
 *
-* @package utf
-* @version $Id$
-* @copyright (c) 2006 phpBB Group
-* @license http://opensource.org/licenses/gpl-license.php GNU Public License
+* This file is part of the phpBB Forum Software package.
+*
+* @copyright (c) phpBB Limited <https://www.phpbb.com>
+* @license GNU General Public License, version 2 (GPL-2.0)
+*
+* For full copyright and license information, please see
+* the docs/CREDITS.txt file.
 *
 */
 
@@ -24,7 +27,6 @@ setlocale(LC_CTYPE, 'C');
 * Whenever possible, these functions will try to use PHP's built-in functions or
 * extensions, otherwise they will default to custom routines.
 *
-* @package utf
 */
 
 if (!extension_loaded('xml'))
@@ -109,70 +111,26 @@ if (extension_loaded('mbstring'))
 	/**
 	* UTF-8 aware alternative to strrpos
 	* Find position of last occurrence of a char in a string
-	*
-	* Notes:
-	* - offset for mb_strrpos was added in 5.2.0, we emulate if it is lower
 	*/
-	if (version_compare(PHP_VERSION, '5.2.0', '>='))
+	/**
+	* UTF-8 aware alternative to strrpos
+	* @ignore
+	*/
+	function utf8_strrpos($str,	$needle, $offset = null)
 	{
-		/**
-		* UTF-8 aware alternative to strrpos
-		* @ignore
-		*/
-		function utf8_strrpos($str,	$needle, $offset = null)
+		// Emulate behaviour of strrpos rather than raising warning
+		if (empty($str))
 		{
-			// Emulate behaviour of strrpos rather than raising warning
-			if (empty($str))
-			{
-				return false;
-			}
+			return false;
+		}
 
-			if (is_null($offset))
-			{
-				return mb_strrpos($str, $needle);
-			}
-			else
-			{
-				return mb_strrpos($str, $needle, $offset);
-			}
+		if (is_null($offset))
+		{
+			return mb_strrpos($str, $needle);
 		}
-	}
-	else
-	{
-		/**
-		* UTF-8 aware alternative to strrpos
-		* @ignore
-		*/
-		function utf8_strrpos($str,	$needle, $offset = null)
+		else
 		{
-			// offset for mb_strrpos was added in 5.2.0
-			if (is_null($offset))
-			{
-				// Emulate behaviour of strrpos rather than raising warning
-				if (empty($str))
-				{
-					return false;
-				}
-
-				return mb_strrpos($str, $needle);
-			}
-			else
-			{
-				if (!is_int($offset))
-				{
-					trigger_error('utf8_strrpos expects parameter 3 to be long', E_USER_ERROR);
-					return false;
-				}
-
-				$str = mb_substr($str, $offset);
-
-				if (false !== ($pos = mb_strrpos($str, $needle)))
-				{
-					return $pos + $offset;
-				}
-
-				return false;
-			}
+			return mb_strrpos($str, $needle, $offset);
 		}
 	}
 
@@ -576,7 +534,7 @@ else
 					return '';
 				}
 
-				$lx = (int)((-$length) / 65535);
+				$lx = (int) ((-$length) / 65535);
 				$ly = (-$length) % 65535;
 
 				// negative length requires ... capture everything
@@ -1756,49 +1714,106 @@ function utf8_case_fold_nfc($text, $option = 'full')
 	return $text;
 }
 
-/**
-* A wrapper function for the normalizer which takes care of including the class if required and modifies the passed strings
-* to be in NFC (Normalization Form Composition).
-*
-* @param	mixed	$strings	a string or an array of strings to normalize
-* @return	mixed				the normalized content, preserving array keys if array given.
-*/
-function utf8_normalize_nfc($strings)
+if (extension_loaded('intl'))
 {
-	if (empty($strings))
+	/**
+	* wrapper around PHP's native normalizer from intl
+	* previously a PECL extension, included in the core since PHP 5.3.0
+	* http://php.net/manual/en/normalizer.normalize.php
+	*
+	* @param	mixed	$strings	a string or an array of strings to normalize
+	* @return	mixed				the normalized content, preserving array keys if array given.
+	*/
+	function utf8_normalize_nfc($strings)
 	{
-		return $strings;
-	}
+		if (empty($strings))
+		{
+			return $strings;
+		}
 
-	if (!class_exists('utf_normalizer'))
-	{
-		global $phpbb_root_path, $phpEx;
-		include($phpbb_root_path . 'includes/utf/utf_normalizer.' . $phpEx);
-	}
+		if (!is_array($strings))
+		{
+			if (Normalizer::isNormalized($strings))
+			{
+				return $strings;
+			}
+			return (string) Normalizer::normalize($strings);
+		}
+		else
+		{
+			foreach ($strings as $key => $string)
+			{
+				if (is_array($string))
+				{
+					foreach ($string as $_key => $_string)
+					{
+						if (Normalizer::isNormalized($strings[$key][$_key]))
+						{
+							continue;
+						}
+						$strings[$key][$_key] = (string) Normalizer::normalize($strings[$key][$_key]);
+					}
+				}
+				else
+				{
+					if (Normalizer::isNormalized($strings[$key]))
+					{
+						continue;
+					}
+					$strings[$key] = (string) Normalizer::normalize($strings[$key]);
+				}
+			}
+		}
 
-	if (!is_array($strings))
-	{
-		utf_normalizer::nfc($strings);
+		return $strings;
 	}
-	else if (is_array($strings))
+}
+else
+{
+	/**
+	* A wrapper function for the normalizer which takes care of including the class if
+	* required and modifies the passed strings to be in NFC (Normalization Form Composition).
+	*
+	* @param	mixed	$strings	a string or an array of strings to normalize
+	* @return	mixed				the normalized content, preserving array keys if array given.
+	*/
+	function utf8_normalize_nfc($strings)
 	{
-		foreach ($strings as $key => $string)
+		if (empty($strings))
+		{
+			return $strings;
+		}
+
+		if (!class_exists('utf_normalizer'))
+		{
+			global $phpbb_root_path, $phpEx;
+			include($phpbb_root_path . 'includes/utf/utf_normalizer.' . $phpEx);
+		}
+
+		if (!is_array($strings))
+		{
+			utf_normalizer::nfc($strings);
+		}
+		else if (is_array($strings))
 		{
-			if (is_array($string))
+			foreach ($strings as $key => $string)
 			{
-				foreach ($string as $_key => $_string)
+				if (is_array($string))
 				{
-					utf_normalizer::nfc($strings[$key][$_key]);
+					foreach ($string as $_key => $_string)
+					{
+						utf_normalizer::nfc($strings[$key][$_key]);
+					}
+				}
+				else
+				{
+					utf_normalizer::nfc($strings[$key]);
 				}
-			}
-			else
-			{
-				utf_normalizer::nfc($strings[$key]);
 			}
 		}
-	}
 
-	return $strings;
+		return $strings;
+	}
 }
 
 /**
@@ -1921,7 +1936,7 @@ function utf8_wordwrap($string, $width = 75, $break = "\n", $cut = false)
 * UTF8-safe basename() function
 *
 * basename() has some limitations and is dependent on the locale setting
-* according to the PHP manual. Therefore we provide our own locale independant
+* according to the PHP manual. Therefore we provide our own locale independent
 * basename function.
 *
 * @param string $filename The filename basename() should be applied to
@@ -1991,5 +2006,3 @@ function utf8_str_replace($search, $replace, $subject)
 
 	return $subject;
 }
-
-?>
-\ No newline at end of file