Modules

Kohana_UTF8

A port of phputf8 to a unified set of files. Provides multi-byte aware replacement string functions.

For UTF-8 support to work correctly, the following requirements must be met:

PCRE needs to be compiled with UTF-8 support (--enable-utf8)
Support for Unicode properties is highly recommended (--enable-unicode-properties)
UTF-8 conversion will be much more reliable if the iconv extension is loaded
The mbstring extension is highly recommended, but must not be overloading string functions

This file is licensed differently from the rest of Kohana. As a port of phputf8, this file is released under the LGPL.

package: Kohana
category: Base
author: Kohana Team
copyright: © 2007-2012 Kohana Team; © 2005 Harry Fuecks
license: http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt

Class declared in SYSPATH/classes/kohana/utf8.php on line 26.

Constants

None

Properties

public static array $called

List of called methods that have had their required file included.

array(1) (
    "transliterate_to_ascii" => bool TRUE
)

public static boolean $server_utf8

Does the server support UTF-8 natively?

bool TRUE

Methods

public static clean( mixed $var [, string $charset = NULL ] ) (defined in Kohana_UTF8)

Recursively cleans arrays, objects, and strings. Removes ASCII control codes and converts to the requested charset while silently discarding incompatible characters.

UTF8::clean($_GET); // Clean GET data

This method requires Iconv

Parameters

mixed $var required - Variable to clean
string $charset = NULL - Character set, defaults to Kohana::$charset

Return Values

mixed

Source Code

public static function clean($var, $charset = NULL)
{
	if ( ! $charset)
	{
		// Use the application character set
		$charset = Kohana::$charset;
	}

	if (is_array($var) OR is_object($var))
	{
		foreach ($var as $key => $val)
		{
			// Recursion!
			$var[self::clean($key)] = self::clean($val);
		}
	}
	elseif (is_string($var) AND $var !== '')
	{
		// Remove control characters
		$var = self::strip_ascii_ctrl($var);

		if ( ! self::is_ascii($var))
		{
			// Disable notices
			$error_reporting = error_reporting(~E_NOTICE);

			// iconv is expensive, so it is only used when needed
			$var = iconv($charset, $charset.'//IGNORE', $var);

			// Turn notices back on
			error_reporting($error_reporting);
		}
	}

	return $var;
}

public static from_unicode( array $arr ) (defined in Kohana_UTF8)

Takes an array of ints representing the Unicode characters and returns a UTF-8 string. Astral planes are supported i.e. the ints in the input can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates are not allowed.

$str = UTF8::to_unicode($array);

The Original Code is Mozilla Communicator client code. The Initial Developer of the Original Code is Netscape Communications Corporation. Portions created by the Initial Developer are Copyright (C) 1998 the Initial Developer. Ported to PHP by Henri Sivonen hsivonen@iki.fi, see http://hsivonen.iki.fi/php-utf8/ Slight modifications to fit with phputf8 library by Harry Fuecks hfuecks@gmail.com.

Parameters

array $arr required - $str unicode code points representing a string

Return Values

string - Utf8 string of characters
boolean - FALSE if a code point cannot be found

Source Code

public static function from_unicode($arr)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _from_unicode($arr);
}

public static is_ascii( mixed $str ) (defined in Kohana_UTF8)

Tests whether a string contains only 7-bit ASCII bytes. This is used to determine when to use native functions or UTF-8 functions.

$ascii = UTF8::is_ascii($str);

Parameters

mixed $str required - String or array of strings to check

Return Values

boolean

Source Code

public static function is_ascii($str)
{
	if (is_array($str))
	{
		$str = implode($str);
	}

	return ! preg_match('/[^\x00-\x7F]/S', $str);
}

public static ltrim( string $str [, string $charlist = NULL ] ) (defined in Kohana_UTF8)

Strips whitespace (or other UTF-8 characters) from the beginning of a string. This is a UTF8-aware version of ltrim.

$str = UTF8::ltrim($str);

Parameters

string $str required - Input string
string $charlist = NULL - String of characters to remove

Return Values

string

Source Code

public static function ltrim($str, $charlist = NULL)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _ltrim($str, $charlist);
}

public static ord( string $chr ) (defined in Kohana_UTF8)

Returns the unicode ordinal for a character. This is a UTF8-aware version of ord.

$digit = UTF8::ord($character);

Parameters

string $chr required - UTF-8 encoded character

Return Values

integer

Source Code

public static function ord($chr)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _ord($chr);
}

public static rtrim( string $str [, string $charlist = NULL ] ) (defined in Kohana_UTF8)

Strips whitespace (or other UTF-8 characters) from the end of a string. This is a UTF8-aware version of rtrim.

$str = UTF8::rtrim($str);

Parameters

string $str required - Input string
string $charlist = NULL - String of characters to remove

Return Values

string

Source Code

public static function rtrim($str, $charlist = NULL)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _rtrim($str, $charlist);
}

public static str_ireplace( string|array $search , string|array $replace , string|array $str [, integer & $count = NULL ] ) (defined in Kohana_UTF8)

Returns a string or an array with all occurrences of search in subject (ignoring case) and replaced with the given replace value. This is a UTF8-aware version of str_ireplace.

This function is very slow compared to the native version. Avoid using it when possible.

Parameters

string|array $search required - Text to replace
string|array $replace required - Replacement text
string|array $str required - Subject text
byref integer $count = NULL - Number of matched and replaced needles will be returned via this parameter which is passed by reference

Return Values

string - If the input was a string
array - If the input was an array

Source Code

public static function str_ireplace($search, $replace, $str, & $count = NULL)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _str_ireplace($search, $replace, $str, $count);
}

public static str_pad( string $str , integer $final_str_length [, string $pad_str = string(1) " " , string $pad_type = integer 1 ] ) (defined in Kohana_UTF8)

Pads a UTF-8 string to a certain length with another string. This is a UTF8-aware version of str_pad.

$str = UTF8::str_pad($str, $length);

Parameters

string $str required - Input string
integer $final_str_length required - Desired string length after padding
string $pad_str = string(1) " " - String to use as padding
string $pad_type = integer 1 - Padding type: STR_PAD_RIGHT, STR_PAD_LEFT, or STR_PAD_BOTH

Return Values

string

Source Code

public static function str_pad($str, $final_str_length, $pad_str = ' ', $pad_type = STR_PAD_RIGHT)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _str_pad($str, $final_str_length, $pad_str, $pad_type);
}

public static str_split( string $str [, integer $split_length = integer 1 ] ) (defined in Kohana_UTF8)

Converts a UTF-8 string to an array. This is a UTF8-aware version of str_split.

$array = UTF8::str_split($str);

Parameters

string $str required - Input string
integer $split_length = integer 1 - Maximum length of each chunk

Return Values

array

Source Code

public static function str_split($str, $split_length = 1)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _str_split($str, $split_length);
}

public static strcasecmp( string $str1 , string $str2 ) (defined in Kohana_UTF8)

Case-insensitive UTF-8 string comparison. This is a UTF8-aware version of strcasecmp.

$compare = UTF8::strcasecmp($str1, $str2);

Parameters

string $str1 required - String to compare
string $str2 required - String to compare

Return Values

integer - Less than 0 if str1 is less than str2
integer - Greater than 0 if str1 is greater than str2
integer - 0 if they are equal

Source Code

public static function strcasecmp($str1, $str2)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _strcasecmp($str1, $str2);
}

public static strcspn( string $str , string $mask [, integer $offset = NULL , integer $length = NULL ] ) (defined in Kohana_UTF8)

Finds the length of the initial segment not matching mask. This is a UTF8-aware version of strcspn.

$found = UTF8::strcspn($str, $mask);

Parameters

string $str required - Input string
string $mask required - Mask for search
integer $offset = NULL - Start position of the string to examine
integer $length = NULL - Length of the string to examine

Return Values

integer - Length of the initial segment that contains characters not in the mask

Source Code

public static function strcspn($str, $mask, $offset = NULL, $length = NULL)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _strcspn($str, $mask, $offset, $length);
}

public static strip_ascii_ctrl( string $str ) (defined in Kohana_UTF8)

Strips out device control codes in the ASCII range.

$str = UTF8::strip_ascii_ctrl($str);

Parameters

string $str required - String to clean

Return Values

string

Source Code

public static function strip_ascii_ctrl($str)
{
	return preg_replace('/[\x00-\x08\x0B\x0C\x0E-\x1F\x7F]+/S', '', $str);
}

public static strip_non_ascii( string $str ) (defined in Kohana_UTF8)

Strips out all non-7bit ASCII bytes.

$str = UTF8::strip_non_ascii($str);

Parameters

string $str required - String to clean

Return Values

string

Source Code

public static function strip_non_ascii($str)
{
	return preg_replace('/[^\x00-\x7F]+/S', '', $str);
}

public static stristr( string $str , string $search ) (defined in Kohana_UTF8)

Case-insenstive UTF-8 version of strstr. Returns all of input string from the first occurrence of needle to the end. This is a UTF8-aware version of stristr.

$found = UTF8::stristr($str, $search);

Parameters

string $str required - Input string
string $search required - Needle

Return Values

string - Matched substring if found
FALSE - If the substring was not found

Source Code

public static function stristr($str, $search)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _stristr($str, $search);
}

public static strlen( string $str ) (defined in Kohana_UTF8)

Returns the length of the given string. This is a UTF8-aware version of strlen.

$length = UTF8::strlen($str);

Parameters

string $str required - String being measured for length

Return Values

integer

Source Code

public static function strlen($str)
{
	if (UTF8::$server_utf8)
		return mb_strlen($str, Kohana::$charset);

	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _strlen($str);
}

public static strpos( string $str , string $search [, integer $offset = integer 0 ] ) (defined in Kohana_UTF8)

Finds position of first occurrence of a UTF-8 string. This is a UTF8-aware version of strpos.

$position = UTF8::strpos($str, $search);

Parameters

string $str required - Haystack
string $search required - Needle
integer $offset = integer 0 - Offset from which character in haystack to start searching

Return Values

integer - Position of needle
boolean - FALSE if the needle is not found

Source Code

public static function strpos($str, $search, $offset = 0)
{
	if (UTF8::$server_utf8)
		return mb_strpos($str, $search, $offset, Kohana::$charset);

	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _strpos($str, $search, $offset);
}

public static strrev( string $str ) (defined in Kohana_UTF8)

Reverses a UTF-8 string. This is a UTF8-aware version of strrev.

$str = UTF8::strrev($str);

Parameters

string $str required - String to be reversed

Return Values

string

Source Code

public static function strrev($str)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _strrev($str);
}

public static strrpos( string $str , string $search [, integer $offset = integer 0 ] ) (defined in Kohana_UTF8)

Finds position of last occurrence of a char in a UTF-8 string. This is a UTF8-aware version of strrpos.

$position = UTF8::strrpos($str, $search);

Parameters

string $str required - Haystack
string $search required - Needle
integer $offset = integer 0 - Offset from which character in haystack to start searching

Return Values

integer - Position of needle
boolean - FALSE if the needle is not found

Source Code

public static function strrpos($str, $search, $offset = 0)
{
	if (UTF8::$server_utf8)
		return mb_strrpos($str, $search, $offset, Kohana::$charset);

	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _strrpos($str, $search, $offset);
}

public static strspn( string $str , string $mask [, integer $offset = NULL , integer $length = NULL ] ) (defined in Kohana_UTF8)

Finds the length of the initial segment matching mask. This is a UTF8-aware version of strspn.

$found = UTF8::strspn($str, $mask);

Parameters

string $str required - Input string
string $mask required - Mask for search
integer $offset = NULL - Start position of the string to examine
integer $length = NULL - Length of the string to examine

Return Values

integer - Length of the initial segment that contains characters in the mask

Source Code

public static function strspn($str, $mask, $offset = NULL, $length = NULL)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _strspn($str, $mask, $offset, $length);
}

public static strtolower( string $str ) (defined in Kohana_UTF8)

Makes a UTF-8 string lowercase. This is a UTF8-aware version of strtolower.

$str = UTF8::strtolower($str);

Parameters

string $str required - Mixed case string

Return Values

string

Source Code

public static function strtolower($str)
{
	if (UTF8::$server_utf8)
		return mb_strtolower($str, Kohana::$charset);

	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _strtolower($str);
}

public static strtoupper( string $str ) (defined in Kohana_UTF8)

Makes a UTF-8 string uppercase. This is a UTF8-aware version of strtoupper.

Parameters

string $str required - Mixed case string

Return Values

string

Source Code

public static function strtoupper($str)
{
	if (UTF8::$server_utf8)
		return mb_strtoupper($str, Kohana::$charset);

	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _strtoupper($str);
}

public static substr( string $str , integer $offset [, integer $length = NULL ] ) (defined in Kohana_UTF8)

Returns part of a UTF-8 string. This is a UTF8-aware version of substr.

$sub = UTF8::substr($str, $offset);

Parameters

string $str required - Input string
integer $offset required - Offset
integer $length = NULL - Length limit

Return Values

string

Source Code

public static function substr($str, $offset, $length = NULL)
{
	if (UTF8::$server_utf8)
		return ($length === NULL)
			? mb_substr($str, $offset, mb_strlen($str), Kohana::$charset)
			: mb_substr($str, $offset, $length, Kohana::$charset);

	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _substr($str, $offset, $length);
}

public static substr_replace( string $str , string $replacement , integer $offset [, $length = NULL ] ) (defined in Kohana_UTF8)

Replaces text within a portion of a UTF-8 string. This is a UTF8-aware version of substr_replace.

$str = UTF8::substr_replace($str, $replacement, $offset);

Parameters

string $str required - Input string
string $replacement required - Replacement string
integer $offset required - Offset
unknown $length = NULL

Return Values

string

Source Code

public static function substr_replace($str, $replacement, $offset, $length = NULL)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _substr_replace($str, $replacement, $offset, $length);
}

public static to_unicode( string $str ) (defined in Kohana_UTF8)

Takes an UTF-8 string and returns an array of ints representing the Unicode characters. Astral planes are supported i.e. the ints in the output can be > 0xFFFF. Occurrences of the BOM are ignored. Surrogates are not allowed.

$array = UTF8::to_unicode($str);

Parameters

string $str required - UTF-8 encoded string

Return Values

array - Unicode code points
FALSE - If the string is invalid

Source Code

public static function to_unicode($str)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _to_unicode($str);
}

public static transliterate_to_ascii( string $str [, integer $case = integer 0 ] ) (defined in Kohana_UTF8)

Replaces special/accented UTF-8 characters by ASCII-7 "equivalents".

$ascii = UTF8::transliterate_to_ascii($utf8);

Parameters

string $str required - String to transliterate
integer $case = integer 0 - -1 lowercase only, +1 uppercase only, 0 both cases

Return Values

string

Source Code

public static function transliterate_to_ascii($str, $case = 0)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _transliterate_to_ascii($str, $case);
}

public static trim( string $str [, string $charlist = NULL ] ) (defined in Kohana_UTF8)

Strips whitespace (or other UTF-8 characters) from the beginning and end of a string. This is a UTF8-aware version of trim.

$str = UTF8::trim($str);

Parameters

string $str required - Input string
string $charlist = NULL - String of characters to remove

Return Values

string

Source Code

public static function trim($str, $charlist = NULL)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _trim($str, $charlist);
}

public static ucfirst( string $str ) (defined in Kohana_UTF8)

Makes a UTF-8 string's first character uppercase. This is a UTF8-aware version of ucfirst.

$str = UTF8::ucfirst($str);

Parameters

string $str required - Mixed case string

Return Values

string

Source Code

public static function ucfirst($str)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _ucfirst($str);
}

public static ucwords( string $str ) (defined in Kohana_UTF8)

Makes the first character of every word in a UTF-8 string uppercase. This is a UTF8-aware version of ucwords.

$str = UTF8::ucwords($str);

Parameters

string $str required - Mixed case string

Return Values

string

Source Code

public static function ucwords($str)
{
	if ( ! isset(self::$called[__FUNCTION__]))
	{
		require Kohana::find_file('utf8', __FUNCTION__);

		// Function has been called
		self::$called[__FUNCTION__] = TRUE;
	}

	return _ucwords($str);
}

Modules

Kohana_UTF8

Constants

Properties

Methods

Properties

public static array $called

public static boolean $server_utf8

Methods

public static clean( mixed $var [, string $charset = NULL ] ) (defined in Kohana_UTF8)

Parameters

Tags

Return Values

Source Code

public static from_unicode( array $arr ) (defined in Kohana_UTF8)

Parameters

Return Values

Source Code

public static is_ascii( mixed $str ) (defined in Kohana_UTF8)

Parameters

Return Values

Source Code

public static ltrim( string $str [, string $charlist = NULL ] ) (defined in Kohana_UTF8)

Parameters

Tags

Return Values

Source Code

public static ord( string $chr ) (defined in Kohana_UTF8)

Parameters

Tags

Return Values

Source Code

public static rtrim( string $str [, string $charlist = NULL ] ) (defined in Kohana_UTF8)

Parameters

Tags

Return Values

Source Code

public static str_ireplace( string|array $search , string|array $replace , string|array $str [, integer & $count = NULL ] ) (defined in Kohana_UTF8)

Parameters

Tags

Return Values

Source Code

public static str_pad( string $str , integer $final_str_length [, string $pad_str = string(1) " " , string $pad_type = integer 1 ] ) (defined in Kohana_UTF8)

Parameters

Tags

Return Values

Source Code

public static str_split( string $str [, integer $split_length = integer 1 ] ) (defined in Kohana_UTF8)

Parameters

Tags

Return Values

Source Code

public static strcasecmp( string $str1 , string $str2 ) (defined in Kohana_UTF8)

Parameters

Tags

Return Values

Source Code

public static strcspn( string $str , string $mask [, integer $offset = NULL , integer $length = NULL ] ) (defined in Kohana_UTF8)

Parameters

Tags

Return Values

Source Code

public static strip_ascii_ctrl( string $str ) (defined in Kohana_UTF8)

Parameters

Return Values

Source Code

public static strip_non_ascii( string $str ) (defined in Kohana_UTF8)

Parameters

Return Values

Source Code

public static stristr( string $str , string $search ) (defined in Kohana_UTF8)

Parameters

Tags

Return Values

Source Code

public static strlen( string $str ) (defined in Kohana_UTF8)

Parameters

Tags

Return Values

Source Code

public static `array` $called

public static `boolean` $server_utf8