Initial commit of Kohana 3.0

This commit is contained in:
Woody Gilk 2008-12-05 01:37:18 +00:00
commit 9f20da909b
35 changed files with 2597 additions and 0 deletions

0
README.markdown Normal file
View file

32
index.php Normal file
View file

@ -0,0 +1,32 @@
<?php
$application = 'application';
$modules = 'modules';
$system = 'system';
define('EXT', '.php');
define('DOCROOT', str_replace('\\', '/', pathinfo(__FILE__, PATHINFO_DIRNAME)).'/');
define('APPPATH', str_replace('\\', '/', realpath($application)).'/');
define('MODPATH', str_replace('\\', '/', realpath($modules)).'/');
define('SYSPATH', str_replace('\\', '/', realpath($system)).'/');
unset($application, $modules, $system);
if (file_exists('install'.EXT))
{
// Installation check
include 'install'.EXT;
}
elseif (file_exists(APPPATH.'bootstrap'.EXT))
{
// Custom boostrap
include APPPATH.'bootstrap'.EXT;
}
else
{
// Default bootstrap
include SYSPATH.'bootstrap'.EXT;
}

58
system/bootstrap.php Normal file
View file

@ -0,0 +1,58 @@
<?php
/**
* Kohana process control file, loaded by the front controller.
*
* $Id: bootstrap.php 3733 2008-11-27 01:12:41Z Shadowhand $
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @license http://kohanaphp.com/license.html
*/
define('KOHANA_VERSION', '3.0');
define('KOHANA_CODENAME', 'renaissance');
// The fastest way to detect a Windows system
define('KOHANA_IS_WIN', DIRECTORY_SEPARATOR === '\\');
if (extension_loaded('mbstring'))
{
// Use mb_* utf8 functions when possible
mb_internal_encoding('UTF-8');
define('SERVER_UTF8', TRUE);
}
else
{
// Use internal utf8 functions
define('SERVER_UTF8', FALSE);
}
// Default output type is UTF-8 text/html
header('Content-Type: text/html; charset=UTF-8');
// Load the main Kohana class
require SYSPATH.'classes/kohana'.EXT;
// Initialize the evironment
Kohana::init();
// Convert global variables to UTF-8
$_GET = utf8::clean($_GET);
$_POST = utf8::clean($_POST);
$_COOKIE = utf8::clean($_COOKIE);
$_SERVER = utf8::clean($_SERVER);
/*
$route = Route::factory('(:controller(/:method(/:id)))')
->defaults(array('controller' => 'welcome', 'method' => 'index'));
echo Kohana::debug($route->matches('uploads/doc/foo.xml'));
*/
$route = Route::factory('(:path/):file(.:format)', array('path' => '.*'));
$view = View::factory('test');
echo $view->render();

202
system/classes/kohana.php Normal file
View file

@ -0,0 +1,202 @@
<?php
/**
* Contains the most low-level helpers methods in Kohana:
*
* - Environment initialization
* - Locating files within the cascading filesystem
* - Auto-loading and transparent extension of classes
* - Variable and path debugging
*
* $Id: kohana.php 3733 2008-11-27 01:12:41Z Shadowhand $
*
* @package Core
* @author Kohana Team
* @copyright (c) 2008 Kohana Team
* @license http://kohanaphp.com/license.html
*/
final class Kohana {
// Has the environment been initialized?
private static $init = FALSE;
// Include paths that are used to find files
private static $include_paths = array(APPPATH, SYSPATH);
// Cache for class methods
private static $cache = array();
/**
* Initializes the environment:
*
* - Enables the auto-loader
* - Enables the exception handler
* - Enables error-to-exception handler
*
* @return void
*/
public static function init()
{
if (self::$init === TRUE)
return;
spl_autoload_register(array(__CLASS__, 'auto_load'));
// The system has been initialized
self::$init = TRUE;
}
/**
* Finds the path of a file by directory, filename, and extension.
* If no extension is give, the default EXT extension will be used.
*
* // Returns an absolute path to views/template.php
* echo Kohana::find_file('views', 'template');
*
* // Returns an absolute path to media/css/style.css
* echo Kohana::find_file('media', 'css/style', 'css');
*
* @param string directory name (views, classes, extensions, etc.)
* @param string filename with subdirectory
* @param string extension to search for
* @return string success
* @return FALSE failure
*/
public static function find_file($dir, $file, $ext = NULL)
{
// Use the defined extension by default
$ext = ($ext === NULL) ? EXT : '.'.$ext;
// Full (relative) path name
$file = $dir.'/'.$file.$ext;
if (isset(self::$cache[__FUNCTION__][$file]))
{
return self::$cache[__FUNCTION__][$file];
}
foreach (self::$include_paths as $path)
{
if (file_exists($path.$file))
{
return self::$cache[__FUNCTION__][$file] = $path.$file;
}
}
return FALSE;
}
/**
* Provides auto-loading support of Kohana classes, as well as transparent
* extension of classes that have a _Core suffix.
*
* Class names are converted to file names by making the class name
* lowercase and converting underscores to slashes:
*
* // Loads classes/my/class/name.php
* Kohana::auto_load('My_Class_Name')
*
* @param string class name
* @param string file extensions to use
* @return boolean
*/
public static function auto_load($class)
{
$file = str_replace('_', '/', strtolower($class));
if ($path = self::find_file('classes', $file))
{
require $path;
}
else
{
return FALSE;
}
if ($path = self::find_file('extensions', $file))
{
require $path;
}
elseif (class_exists($class.'_Core', FALSE))
{
// Class extension to be evaluated
$extension = 'class '.$class.' extends '.$class.'_Core { }';
// Use reflection to find out of the class is abstract
$class = new ReflectionClass($class.'_Core');
if ($class->isAbstract())
{
// Make the extension abstract, too
$extension = 'abstract '.$extension;
}
// Transparent class extensions are possible using eval. Not very
// clean, but it can be avoided by creating empty extensions.
eval($extension);
}
return TRUE;
}
/**
* Returns an HTML string of debugging information about any number of
* variables, each wrapped in a <pre> tag:
*
* // Displays the type and value of each variable
* echo Kohana::debug($foo, $bar, $baz);
*
* @param mixed variable to debug
* @param ...
* @return string
*/
public static function debug()
{
if (func_num_args() === 0)
return;
// Get params
$params = func_get_args();
$output = array();
foreach ($params as $var)
{
$output[] = '<pre>('.gettype($var).') '.htmlspecialchars(print_r($var, TRUE)).'</pre>';
}
return implode("\n", $output);
}
/**
* Removes application, system, modpath, or docroot from a filename,
* replacing them with the plain text equivalents. Useful for debugging
* when you want to display a shorter path.
*
* // Displays SYSPATH/classes/kohana.php
* echo Kohana::debug_path(Kohana::find_file('classes', 'kohana'));
*
* @param string path to debug
* @return string
*/
public static function debug_path($file)
{
if (strpos($file, APPPATH) === 0)
{
$file = 'APPPATH/'.substr($file, strlen(APPPATH));
}
elseif (strpos($file, SYSPATH) === 0)
{
$file = 'SYSPATH/'.substr($file, strlen(SYSPATH));
}
elseif (strpos($file, MODPATH) === 0)
{
$file = 'MODPATH/'.substr($file, strlen(MODPATH));
}
elseif (strpos($file, DOCROOT) === 0)
{
$file = 'DOCROOT/'.substr($file, strlen(DOCROOT));
}
return $file;
}
} // End Kohana

241
system/classes/route.php Normal file
View file

@ -0,0 +1,241 @@
<?php
/**
* Routes are used to determine the controller and method for a requested URI.
* Every route generates a regular expression which is used to match a URI
* and a route. Routes may also contain keys which can be used to set the
* controller, method, and method arguments.
*
* Each :key will be translated to a regular expression using a default regular
* expression pattern. You can override the default pattern by providing a
* pattern for the key:
*
* // This route will only match when :id is a digit
* Route::factory('user/edit/:id', array('id' => '\d+'));
*
* // This route will match when :path is anything
* Route::factory(':path', array('path' => '.*'));
*
* It is also possible to create optional segments by using parenthesis in
* the URI definition:
*
* // This is the standard default route, and no keys are required
* Route::defautl('(:controller(/:method(/:id)))');
*
* // This route only requires the :file key
* Route::factory('(:path/):file(:format)', array('path' => '.*', 'format' => '\.\w+'));
*
* Routes also provide a way to generate URIs (called "reverse routing"), which
* makes them an extremely powerful and flexible way to generate internal links.
*
* $Id: route.php 3730 2008-11-27 00:37:57Z Shadowhand $
*
* @package Core
* @author Kohana Team
* @copyright (c) 2008 Kohana Team
* @license http://kohanaphp.com/license.html
*/
class Route_Core {
const REGEX_KEY = ':[a-zA-Z0-9_]++';
const REGEX_SEGMENT = '[^/.,;?]++';
const REGEX_ESCAPE = '[.\\+*?[^\\]${}=!<>|]';
/**
* Returns a new Route object.
*
* @chainable
* @param string route URI
* @param array regular expressions for keys
* @return Route
*/
public static function factory($uri, array $regex = array())
{
return new Route($uri, $regex);
}
// Route URI string
protected $uri = '';
// Regular expressions for route keys
protected $regex = array();
// Default values for route keys
protected $defaults = array('method' => 'index');
// Compiled regex cache
protected $compiled;
// Matched URI keys
protected $keys = array();
/**
* Creates a new route. Sets the URI and regular expressions for keys.
*
* @param string route URI pattern
* @param array key patterns
*/
public function __construct($uri, array $regex = array())
{
$this->uri = $uri;
if ( ! empty($regex))
{
$this->regex = $regex;
}
}
/**
* Provides default values for keys when they are not present. The default
* method will always be "index" unless it is overloaded with this method.
*
* $route->defaults(array('controller' => 'welcome', 'method' => 'index'));
*
* @chainable
* @param array key values
* @return Route
*/
public function defaults(array $defaults)
{
if (empty($defaults['method']))
{
$defaults['method'] = 'index';
}
$this->defaults = $defaults;
return $this;
}
/**
* Tests if the route matches a given URI. A successful match will return
* all of the routed parameters as an array. A failed match will return
* boolean FALSE.
*
* // This route will only match if the :controller, :method, and :id exist
* $params = Route::factory(':controller/:method/:id', array('id' => '\d+'))
* ->match('users/edit/10');
* // The parameters are now:
* // controller = users
* // method = edit
* // id = 10
*
* This method should almost always be used within an if/else block:
*
* if ($params = $route->match($uri))
* {
* // Parse the parameters
* }
*
* @param string URI to match
* @return array on success
* @return FALSE on failure
*/
public function matches($uri)
{
// Get the compiled regex
$regex = $this->compile();
if (preg_match('#'.$regex.'#', $uri, $matches))
{
$params = array();
foreach ($matches as $key => $value)
{
if (is_int($key))
{
// Skip all unnamed keys
continue;
}
// Set the value for all matched keys
$params[$key] = $value;
}
foreach ($this->defaults as $key => $value)
{
if ( ! isset($params[$key]))
{
// Set default values for any key that was not matched
$params[$key] = $value;
}
}
return $params;
}
else
{
return FALSE;
}
}
/**
* Returns the compiled regular expression for the route. The generated
* pattern will be cached after it is compiled.
*
* @return string
*/
protected function compile()
{
if (isset($this->cache[$this->uri]))
{
// The regex has already been compiled
return $this->cache[$this->uri];
}
// The URI should be considered literal except for keys and optional parts
// Escape everything preg_quote would escape except for : ( )
$this->uri = preg_replace('#'.Route::REGEX_ESCAPE.'#', '\\\\$0', $this->uri);
if (strpos($this->uri, '(') === FALSE)
{
// No optional parts of the URI
$regex = $this->uri;
}
else
{
// Make optional parts of the URI non-capturing and optional
$regex = str_replace(array('(', ')'), array('(?:', ')?'), $this->uri);
}
if (preg_match_all('#'.Route::REGEX_KEY.'#', $regex, $keys))
{
// Compile every :key into its regex equivalent
$replace = $this->compile_keys($keys[0]);
// Replace each :key with with <key>PATTERN
$regex = strtr($regex, $replace);
}
// Add anchors and cache the compiled regex
return $this->compiled = '^'.$regex.'$';
}
protected function compile_keys(array $keys)
{
$groups = array();
foreach ($keys as $key)
{
// Get the key name
$name = substr($key, 1);
// Name the matched segment
$regex = '(?P<'.$name.'>';
if (isset($this->regex[$name]))
{
// Use the pre-defined pattern
$regex .= $this->regex[$name];
}
else
{
// Use the default pattern
$regex .= Route::REGEX_SEGMENT;
}
// Add the regex group with its key
$groups[$key] = $regex.')';
}
return $groups;
}
} // End Kohana_Route

12
system/classes/router.php Normal file
View file

@ -0,0 +1,12 @@
<?php
class Router_Core {
protected $routes = array();
public static function add($name, Route $route)
{
$this->routes[$name] = $route;
}
} // End Kohana_Router

704
system/classes/utf8.php Normal file
View file

@ -0,0 +1,704 @@
<?php
/**
* A port of [phputf8][ref-p8] 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][ref-uc] is highly recommended (--enable-unicode-properties)
* - UTF-8 conversion will be much more reliable if the [iconv extension][ref-ie] is loaded
* - The [mbstring extension][ref-mb] 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][ref-p8], this file is released under the LGPL.*
*
* [ref-p8]: http://phputf8.sourceforge.net/
* [ref-uc]: http://php.net/manual/reference.pcre.pattern.modifiers.php
* [ref-ie]: http://php.net/iconv
* [ref-mb]: http://php.net/mbstring
*
* $Id: utf8.php 3735 2008-11-28 17:56:34Z Geert $
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
final class utf8 {
// Called methods
static $called = array();
/**
* Recursively cleans arrays, objects, and strings. Removes ASCII control
* codes and converts to UTF-8 while silently discarding incompatible
* UTF-8 characters.
*
* @param mixed variable to clean
* @return mixed
*/
public static function clean($var)
{
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
$ER = error_reporting(~E_NOTICE);
// iconv is expensive, so it is only used when needed
$var = iconv('UTF-8', 'UTF-8//IGNORE', $var);
// Turn notices back on
error_reporting($ER);
}
}
return $var;
}
/**
* Tests whether a string contains only 7-bit ASCII bytes. This is used to
* determine when to use native functions or UTF-8 functions.
*
* @param string string to check
* @return bool
*/
public static function is_ascii($str)
{
return ! preg_match('/[^\x00-\x7F]/S', $str);
}
/**
* Strips out device control codes in the ASCII range.
*
* @param string string to clean
* @return string
*/
public static function strip_ascii_ctrl($str)
{
return preg_replace('/[\x00-\x08\x0B\x0C\x0E-\x1F\x7F]+/S', '', $str);
}
/**
* Strips out all non-7bit ASCII bytes.
*
* @param string string to clean
* @return string
*/
public static function strip_non_ascii($str)
{
return preg_replace('/[^\x00-\x7F]+/S', '', $str);
}
/**
* Replaces special/accented UTF-8 characters by ASCII-7 'equivalents'.
*
* @author Andreas Gohr <andi@splitbrain.org>
*
* @param string string to transliterate
* @param integer -1 lowercase only, +1 uppercase only, 0 both cases
* @return string
*/
public static function transliterate_to_ascii($str, $case = 0)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _transliterate_to_ascii($str, $case);
}
/**
* Returns the length of the given string.
*
* @see http://php.net/strlen
*
* @param string string being measured for length
* @return integer
*/
public static function strlen($str)
{
if (SERVER_UTF8)
return mb_strlen($str);
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _strlen($str);
}
/**
* Finds position of first occurrence of a UTF-8 string.
*
* @see http://php.net/strlen
* @author Harry Fuecks <hfuecks@gmail.com>
*
* @param string haystack
* @param string needle
* @param integer offset from which character in haystack to start searching
* @return integer position of needle
* @return boolean FALSE if the needle is not found
*/
public static function strpos($str, $search, $offset = 0)
{
if (SERVER_UTF8)
return mb_strpos($str, $search, $offset);
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _strpos($str, $search, $offset);
}
/**
* Finds position of last occurrence of a char in a UTF-8 string.
*
* @see http://php.net/strrpos
* @author Harry Fuecks <hfuecks@gmail.com>
*
* @param string haystack
* @param string needle
* @param integer offset from which character in haystack to start searching
* @return integer position of needle
* @return boolean FALSE if the needle is not found
*/
public static function strrpos($str, $search, $offset = 0)
{
if (SERVER_UTF8)
return mb_strrpos($str, $search, $offset);
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _strrpos($str, $search, $offset);
}
/**
* Returns part of a UTF-8 string.
*
* @see http://php.net/substr
* @author Chris Smith <chris@jalakai.co.uk>
*
* @param string input string
* @param integer offset
* @param integer length limit
* @return string
*/
public static function substr($str, $offset, $length = NULL)
{
if (SERVER_UTF8)
return ($length === NULL) ? mb_substr($str, $offset) : mb_substr($str, $offset, $length);
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _substr($str, $offset, $length);
}
/**
* Replaces text within a portion of a UTF-8 string.
*
* @see http://php.net/substr_replace
* @author Harry Fuecks <hfuecks@gmail.com>
*
* @param string input string
* @param string replacement string
* @param integer offset
* @return string
*/
public static function substr_replace($str, $replacement, $offset, $length = NULL)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _substr_replace($str, $replacement, $offset, $length);
}
/**
* Makes a UTF-8 string lowercase.
*
* @see http://php.net/strtolower
* @author Andreas Gohr <andi@splitbrain.org>
*
* @param string mixed case string
* @return string
*/
public static function strtolower($str)
{
if (SERVER_UTF8)
return mb_strtolower($str);
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _strtolower($str);
}
/**
* Makes a UTF-8 string uppercase.
*
* @see http://php.net/strtoupper
* @author Andreas Gohr <andi@splitbrain.org>
*
* @param string mixed case string
* @return string
*/
public static function strtoupper($str)
{
if (SERVER_UTF8)
return mb_strtoupper($str);
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _strtoupper($str);
}
/**
* Makes a UTF-8 string's first character uppercase.
*
* @see http://php.net/ucfirst
* @author Harry Fuecks <hfuecks@gmail.com>
*
* @param string mixed case string
* @return string
*/
public static function ucfirst($str)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _ucfirst($str);
}
/**
* Makes the first character of every word in a UTF-8 string uppercase.
*
* @see http://php.net/ucwords
* @author Harry Fuecks <hfuecks@gmail.com>
*
* @param string mixed case string
* @return string
*/
public static function ucwords($str)
{
if (SERVER_UTF8)
return mb_convert_case($str, MB_CASE_TITLE);
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _ucwords($str);
}
/**
* Case-insensitive UTF-8 string comparison.
*
* @see http://php.net/strcasecmp
* @author Harry Fuecks <hfuecks@gmail.com>
*
* @param string string to compare
* @param string string to compare
* @return integer less than 0 if str1 is less than str2
* @return integer greater than 0 if str1 is greater than str2
* @return integer 0 if they are equal
*/
public static function strcasecmp($str1, $str2)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _strcasecmp($str1, $str2);
}
/**
* Returns a string or an array with all occurrences of search in subject
* (ignoring case) and replaced with the given replace value.
*
* **Note:** This function is very slow compared to the native version.
*
* @see http://php.net/str_ireplace
* @author Harry Fuecks <hfuecks@gmail.com
*
* @param string|array text to replace
* @param string|array replacement text
* @param string|array subject text
* @param integer number of matched and replaced needles will be returned via this parameter which is passed by reference
* @return string if the input was a string
* @return array if the input was an array
*/
public static function str_ireplace($search, $replace, $str, & $count = NULL)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _str_ireplace($search, $replace, $str, $count);
}
/**
* Case-insenstive UTF-8 version of strstr. Returns all of input string
* from the first occurrence of needle to the end.
*
* @see http://php.net/stristr
* @author Harry Fuecks <hfuecks@gmail.com>
*
* @param string input string
* @param string needle
* @return string matched substring if found
* @return boolean FALSE if the substring was not found
*/
public static function stristr($str, $search)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _stristr($str, $search);
}
/**
* Finds the length of the initial segment matching mask.
*
* @see http://php.net/strspn
* @author Harry Fuecks <hfuecks@gmail.com>
*
* @param string input string
* @param string mask for search
* @param integer start position of the string to examine
* @param integer length of the string to examine
* @return integer length of the initial segment that contains characters in the mask
*/
public static function strspn($str, $mask, $offset = NULL, $length = NULL)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _strspn($str, $mask, $offset, $length);
}
/**
* Finds the length of the initial segment not matching mask.
*
* @see http://php.net/strcspn
* @author Harry Fuecks <hfuecks@gmail.com>
*
* @param string input string
* @param string mask for search
* @param integer start position of the string to examine
* @param integer length of the string to examine
* @return integer length of the initial segment that contains characters not in the mask
*/
public static function strcspn($str, $mask, $offset = NULL, $length = NULL)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _strcspn($str, $mask, $offset, $length);
}
/**
* Pads a UTF-8 string to a certain length with another string.
*
* @see http://php.net/str_pad
* @author Harry Fuecks <hfuecks@gmail.com>
*
* @param string input string
* @param integer desired string length after padding
* @param string string to use as padding
* @param string padding type: STR_PAD_RIGHT, STR_PAD_LEFT, or STR_PAD_BOTH
* @return string
*/
public static function str_pad($str, $final_str_length, $pad_str = ' ', $pad_type = STR_PAD_RIGHT)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _str_pad($str, $final_str_length, $pad_str, $pad_type);
}
/**
* Converts a UTF-8 string to an array.
*
* @see http://php.net/str_split
* @author Harry Fuecks <hfuecks@gmail.com>
*
* @param string input string
* @param integer maximum length of each chunk
* @return array
*/
public static function str_split($str, $split_length = 1)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _str_split($str, $split_length);
}
/**
* Reverses a UTF-8 string.
*
* @see http://php.net/strrev
* @author Harry Fuecks <hfuecks@gmail.com>
*
* @param string string to be reversed
* @return string
*/
public static function strrev($str)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _strrev($str);
}
/**
* Strips whitespace (or other UTF-8 characters) from the beginning and
* end of a string.
*
* @see http://php.net/trim
* @author Andreas Gohr <andi@splitbrain.org>
*
* @param string input string
* @param string string of characters to remove
* @return string
*/
public static function trim($str, $charlist = NULL)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _trim($str, $charlist);
}
/**
* Strips whitespace (or other UTF-8 characters) from the beginning of a string.
*
* @see http://php.net/ltrim
* @author Andreas Gohr <andi@splitbrain.org>
*
* @param string input string
* @param string string of characters to remove
* @return string
*/
public static function ltrim($str, $charlist = NULL)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _ltrim($str, $charlist);
}
/**
* Strips whitespace (or other UTF-8 characters) from the end of a string.
*
* @see http://php.net/rtrim
* @author Andreas Gohr <andi@splitbrain.org>
*
* @param string input string
* @param string string of characters to remove
* @return string
*/
public static function rtrim($str, $charlist = NULL)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _rtrim($str, $charlist);
}
/**
* Returns the unicode ordinal for a character.
*
* @see http://php.net/ord
* @author Harry Fuecks <hfuecks@gmail.com>
*
* @param string UTF-8 encoded character
* @return integer
*/
public static function ord($chr)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _ord($chr);
}
/**
* Takes an UTF-8 string and returns an array of ints representing the Unicode characters.
* Astral planes are supported i.e. the ints in the output can be > 0xFFFF.
* Occurrances of the BOM are ignored. Surrogates are not allowed.
*
* The Original Code is Mozilla Communicator client code.
* The Initial Developer of the Original Code is Netscape Communications Corporation.
* Portions created by the Initial Developer are Copyright (C) 1998 the Initial Developer.
* Ported to PHP by Henri Sivonen <hsivonen@iki.fi>, see http://hsivonen.iki.fi/php-utf8/
* Slight modifications to fit with phputf8 library by Harry Fuecks <hfuecks@gmail.com>
*
* @param string UTF-8 encoded string
* @return array unicode code points
* @return boolean FALSE if the string is invalid
*/
public static function to_unicode($str)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _to_unicode($str);
}
/**
* Takes an array of ints representing the Unicode characters and returns a UTF-8 string.
* Astral planes are supported i.e. the ints in the input can be > 0xFFFF.
* Occurrances of the BOM are ignored. Surrogates are not allowed.
*
* The Original Code is Mozilla Communicator client code.
* The Initial Developer of the Original Code is Netscape Communications Corporation.
* Portions created by the Initial Developer are Copyright (C) 1998 the Initial Developer.
* Ported to PHP by Henri Sivonen <hsivonen@iki.fi>, see http://hsivonen.iki.fi/php-utf8/
* Slight modifications to fit with phputf8 library by Harry Fuecks <hfuecks@gmail.com>.
*
* @param array unicode code points representing a string
* @return string utf8 string of characters
* @return boolean FALSE if a code point cannot be found
*/
public static function from_unicode($arr)
{
if ( ! isset(self::$called[__FUNCTION__]))
{
require SYSPATH.'utf8/'.__FUNCTION__.EXT;
// Function has been called
self::$called[__FUNCTION__] = TRUE;
}
return _from_unicode($arr);
}
} // End utf8

276
system/classes/view.php Normal file
View file

@ -0,0 +1,276 @@
<?php
/**
* Acts as an object wrapper for HTML pages with embedded PHP, called "views".
* Variables can be assigned with the view object and referenced locally within
* the view.
*
* $Id: view.php 3740 2008-12-01 20:24:43Z Geert $
*
* @package Core
* @author Kohana Team
* @copyright (c) 2008 Kohana Team
* @license http://kohanaphp.com/license.html
*/
class View_Core {
// Array of global variables
protected static $global_data = array();
/**
* Returns a new View object.
*
* @chainable
* @param string view filename
* @param array array of values
* @return View
*/
public static function factory($file = NULL, array $data = array())
{
return new View($file, $data);
}
/**
* Captures the output that is generated when a view is included.
* The view data will be extracted to make local variables. This method
* is static to prevent object scope resolution.
*
* @param string filename
* @param array variables
* @return string
*/
protected static function capture($kohana_view_filename, array $kohana_view_data)
{
// Import the view variables to local namespace
extract($kohana_view_data, EXTR_SKIP);
// Capture the view output
ob_start();
// Load the view within the current scope
include $kohana_view_filename;
// Get the captured output and close the buffer
return ob_get_clean();
}
// View filename
protected $file;
// Array of local variables
protected $data = array();
/**
* Sets the initial view filename and local data.
*
* @param string view filename
* @param array array of values
* @return void
*/
public function __construct($file = NULL, array $data = array())
{
if ( ! empty($file))
{
$this->set_filename($file);
}
if ( ! empty($data))
{
$this->data = array_merge($this->data, $data);
}
}
/**
* Magic method, searches for the given variable and returns its value.
* Local variables will be returned before global variables.
*
* @param string variable name
* @return mixed
*/
public function __get($key)
{
if (isset($this->data[$key]))
{
return $this->data[$key];
}
elseif (isset(View::$global_data[$key]))
{
return View::$global_data[$key];
}
else
{
return NULL;
}
}
/**
* Magic method, calls set() with the same parameters.
*
* @param string variable name
* @param mixed value
* @return void
*/
public function __set($key, $value)
{
$this->set($key, $value);
}
/**
* Magic method, returns the output of render(). If any exceptions are
* thrown, the exception output will be returned instead.
*
* @return string
*/
public function __toString()
{
try
{
return $this->render();
}
catch (Kohana_Exception $e)
{
return (string) $e;
}
}
/**
* Sets the view filename. If the view file cannot be found, an exception
* will be thrown.
*
* @chainable
* @throws Kohana_Exception
* @param string filename
* @return View
*/
public function set_filename($file)
{
if ($file = Kohana::find_file('views', $file))
{
$this->file = $file;
}
else
{
throw new Kohana_Exception('kohana.file_not_found', 'views', $file);
}
return $this;
}
/**
* Assigns a variable by name. Assigned values will be available as a
* variable within the view file:
*
* // This value can be accessed as $foo within the view
* $view->set('foo', 'my value');
*
* @chainable
* @param string variable name or an array of variables
* @param mixed value
* @return View
*/
public function set($key, $value = NULL)
{
if (is_array($key))
{
foreach ($key as $key2 => $value)
{
$this->data[$key2] = $value;
}
}
else
{
$this->data[$key] = $value;
}
return $this;
}
/**
* Exactly the same as set, but assigns the value globally.
*
* @chainable
* @param string variable name or an array of variables
* @param mixed value
* @return View
*/
public function set_global($key, $value = NULL)
{
if (is_array($key))
{
foreach ($key as $key2 => $value)
{
View::$global_data[$key2] = $value;
}
}
else
{
View::$global_data[$key] = $value;
}
return $this;
}
/**
* Assigns a value by reference. The benefit of binding is that values can
* be altered without re-setting them. It is also possible to bind variables
* before they have values. Assigned values will be available as a
* variable within the view file:
*
* // This reference can be accessed as $ref within the view
* $view->bind('ref', $bar);
*
* @chainable
* @param string variable name
* @param mixed referenced variable
* @return View
*/
public function bind($key, & $value)
{
$this->data[$key] =& $value;
return $this;
}
/**
* Exactly the same as bind, but assigns the value globally.
*
* @chainable
* @param string variable name
* @param mixed referenced variable
* @return View
*/
public function bind_global($key, & $value)
{
View::$global_data[$key] =& $value;
return $this;
}
/**
* Renders the view object to a string. Global and local data are merged
* and extracted to create local variables within the view file.
* Optionally, the view filename can be set before rendering.
*
* @throws Kohana_Exception
* @param string filename
* @return string
*/
public function render($file = NULL)
{
if ( ! empty($file))
{
$this->set_filename($file);
}
if (empty($this->file))
{
throw new Kohana_Exception('kohana.view.set_filename');
}
// Combine global and local data. Global variables with the same name
// will be overwritten by local variables.
$data = array_merge(View::$global_data, $this->data);
return View::capture($this->file, $data);
}
} // End View

View file

@ -0,0 +1,3 @@
<?php
class Route extends Route_Core {}

View file

@ -0,0 +1,3 @@
<?php
class Router extends Router_Core {}

View file

@ -0,0 +1,3 @@
<?php
class View extends View_Core {}

View file

@ -0,0 +1,68 @@
<?php
/**
* utf8::from_unicode
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _from_unicode($arr)
{
ob_start();
$keys = array_keys($arr);
foreach ($keys as $k)
{
// ASCII range (including control chars)
if (($arr[$k] >= 0) AND ($arr[$k] <= 0x007f))
{
echo chr($arr[$k]);
}
// 2 byte sequence
elseif ($arr[$k] <= 0x07ff)
{
echo chr(0xc0 | ($arr[$k] >> 6));
echo chr(0x80 | ($arr[$k] & 0x003f));
}
// Byte order mark (skip)
elseif ($arr[$k] == 0xFEFF)
{
// nop -- zap the BOM
}
// Test for illegal surrogates
elseif ($arr[$k] >= 0xD800 AND $arr[$k] <= 0xDFFF)
{
// Found a surrogate
trigger_error('utf8::from_unicode: Illegal surrogate at index: '.$k.', value: '.$arr[$k], E_USER_WARNING);
return FALSE;
}
// 3 byte sequence
elseif ($arr[$k] <= 0xffff)
{
echo chr(0xe0 | ($arr[$k] >> 12));
echo chr(0x80 | (($arr[$k] >> 6) & 0x003f));
echo chr(0x80 | ($arr[$k] & 0x003f));
}
// 4 byte sequence
elseif ($arr[$k] <= 0x10ffff)
{
echo chr(0xf0 | ($arr[$k] >> 18));
echo chr(0x80 | (($arr[$k] >> 12) & 0x3f));
echo chr(0x80 | (($arr[$k] >> 6) & 0x3f));
echo chr(0x80 | ($arr[$k] & 0x3f));
}
// Out of range
else
{
trigger_error('utf8::from_unicode: Codepoint out of Unicode range at index: '.$k.', value: '.$arr[$k], E_USER_WARNING);
return FALSE;
}
}
$result = ob_get_contents();
ob_end_clean();
return $result;
}

22
system/utf8/ltrim.php Normal file
View file

@ -0,0 +1,22 @@
<?php
/**
* utf8::ltrim
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _ltrim($str, $charlist = NULL)
{
if ($charlist === NULL)
return ltrim($str);
if (utf8::is_ascii($charlist))
return ltrim($str, $charlist);
$charlist = preg_replace('#[-\[\]:\\\\^/]#', '\\\\$0', $charlist);
return preg_replace('/^['.$charlist.']+/u', '', $str);
}

76
system/utf8/ord.php Normal file
View file

@ -0,0 +1,76 @@
<?php
/**
* utf8::ord
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _ord($chr)
{
$ord0 = ord($chr);
if ($ord0 >= 0 AND $ord0 <= 127)
return $ord0;
if ( ! isset($chr[1]))
{
trigger_error('Short sequence - at least 2 bytes expected, only 1 seen', E_USER_WARNING);
return FALSE;
}
$ord1 = ord($chr[1]);
if ($ord0 >= 192 AND $ord0 <= 223)
return ($ord0 - 192) * 64 + ($ord1 - 128);
if ( ! isset($chr[2]))
{
trigger_error('Short sequence - at least 3 bytes expected, only 2 seen', E_USER_WARNING);
return FALSE;
}
$ord2 = ord($chr[2]);
if ($ord0 >= 224 AND $ord0 <= 239)
return ($ord0 - 224) * 4096 + ($ord1 - 128) * 64 + ($ord2 - 128);
if ( ! isset($chr[3]))
{
trigger_error('Short sequence - at least 4 bytes expected, only 3 seen', E_USER_WARNING);
return FALSE;
}
$ord3 = ord($chr[3]);
if ($ord0 >= 240 AND $ord0 <= 247)
return ($ord0 - 240) * 262144 + ($ord1 - 128) * 4096 + ($ord2-128) * 64 + ($ord3 - 128);
if ( ! isset($chr[4]))
{
trigger_error('Short sequence - at least 5 bytes expected, only 4 seen', E_USER_WARNING);
return FALSE;
}
$ord4 = ord($chr[4]);
if ($ord0 >= 248 AND $ord0 <= 251)
return ($ord0 - 248) * 16777216 + ($ord1-128) * 262144 + ($ord2 - 128) * 4096 + ($ord3 - 128) * 64 + ($ord4 - 128);
if ( ! isset($chr[5]))
{
trigger_error('Short sequence - at least 6 bytes expected, only 5 seen', E_USER_WARNING);
return FALSE;
}
if ($ord0 >= 252 AND $ord0 <= 253)
return ($ord0 - 252) * 1073741824 + ($ord1 - 128) * 16777216 + ($ord2 - 128) * 262144 + ($ord3 - 128) * 4096 + ($ord4 - 128) * 64 + (ord($chr[5]) - 128);
if ($ord0 >= 254 AND $ord0 <= 255)
{
trigger_error('Invalid UTF-8 with surrogate ordinal '.$ord0, E_USER_WARNING);
return FALSE;
}
}

22
system/utf8/rtrim.php Normal file
View file

@ -0,0 +1,22 @@
<?php
/**
* utf8::rtrim
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _rtrim($str, $charlist = NULL)
{
if ($charlist === NULL)
return rtrim($str);
if (utf8::is_ascii($charlist))
return rtrim($str, $charlist);
$charlist = preg_replace('#[-\[\]:\\\\^/]#', '\\\\$0', $charlist);
return preg_replace('/['.$charlist.']++$/uD', '', $str);
}

View file

@ -0,0 +1,70 @@
<?php
/**
* utf8::str_ireplace
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _str_ireplace($search, $replace, $str, & $count = NULL)
{
if (utf8::is_ascii($search) AND utf8::is_ascii($replace) AND utf8::is_ascii($str))
return str_ireplace($search, $replace, $str, $count);
if (is_array($str))
{
foreach ($str as $key => $val)
{
$str[$key] = utf8::str_ireplace($search, $replace, $val, $count);
}
return $str;
}
if (is_array($search))
{
$keys = array_keys($search);
foreach ($keys as $k)
{
if (is_array($replace))
{
if (array_key_exists($k, $replace))
{
$str = utf8::str_ireplace($search[$k], $replace[$k], $str, $count);
}
else
{
$str = utf8::str_ireplace($search[$k], '', $str, $count);
}
}
else
{
$str = utf8::str_ireplace($search[$k], $replace, $str, $count);
}
}
return $str;
}
$search = utf8::strtolower($search);
$str_lower = utf8::strtolower($str);
$total_matched_strlen = 0;
$i = 0;
while (preg_match('/(.*?)'.preg_quote($search, '/').'/s', $str_lower, $matches))
{
$matched_strlen = strlen($matches[0]);
$str_lower = substr($str_lower, $matched_strlen);
$offset = $total_matched_strlen + strlen($matches[1]) + ($i * (strlen($replace) - 1));
$str = substr_replace($str, $replace, $offset, strlen($search));
$total_matched_strlen += $matched_strlen;
$i++;
}
$count += $i;
return $str;
}

50
system/utf8/str_pad.php Normal file
View file

@ -0,0 +1,50 @@
<?php
/**
* utf8::str_pad
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _str_pad($str, $final_str_length, $pad_str = ' ', $pad_type = STR_PAD_RIGHT)
{
if (utf8::is_ascii($str) AND utf8::is_ascii($pad_str))
return str_pad($str, $final_str_length, $pad_str, $pad_type);
$str_length = utf8::strlen($str);
if ($final_str_length <= 0 OR $final_str_length <= $str_length)
return $str;
$pad_str_length = utf8::strlen($pad_str);
$pad_length = $final_str_length - $str_length;
if ($pad_type == STR_PAD_RIGHT)
{
$repeat = ceil($pad_length / $pad_str_length);
return utf8::substr($str.str_repeat($pad_str, $repeat), 0, $final_str_length);
}
if ($pad_type == STR_PAD_LEFT)
{
$repeat = ceil($pad_length / $pad_str_length);
return utf8::substr(str_repeat($pad_str, $repeat), 0, floor($pad_length)).$str;
}
if ($pad_type == STR_PAD_BOTH)
{
$pad_length /= 2;
$pad_length_left = floor($pad_length);
$pad_length_right = ceil($pad_length);
$repeat_left = ceil($pad_length_left / $pad_str_length);
$repeat_right = ceil($pad_length_right / $pad_str_length);
$pad_left = utf8::substr(str_repeat($pad_str, $repeat_left), 0, $pad_length_left);
$pad_right = utf8::substr(str_repeat($pad_str, $repeat_right), 0, $pad_length_left);
return $pad_left.$str.$pad_right;
}
trigger_error('utf8::str_pad: Unknown padding type (' . $pad_type . ')', E_USER_ERROR);
}

27
system/utf8/str_split.php Normal file
View file

@ -0,0 +1,27 @@
<?php
/**
* utf8::str_split
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _str_split($str, $split_length = 1)
{
$split_length = (int) $split_length;
if (utf8::is_ascii($str))
return str_split($str, $split_length);
if ($split_length < 1)
return FALSE;
if (utf8::strlen($str) <= $split_length)
return array($str);
preg_match_all('/.{'.$split_length.'}|[^\x00]{1,'.$split_length.'}$/us', $str, $matches);
return $matches[0];
}

View file

@ -0,0 +1,19 @@
<?php
/**
* utf8::strcasecmp
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _strcasecmp($str1, $str2)
{
if (utf8::is_ascii($str1) AND utf8::is_ascii($str2))
return strcasecmp($str1, $str2);
$str1 = utf8::strtolower($str1);
$str2 = utf8::strtolower($str2);
return strcmp($str1, $str2);
}

30
system/utf8/strcspn.php Normal file
View file

@ -0,0 +1,30 @@
<?php
/**
* utf8::strcspn
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _strcspn($str, $mask, $offset = NULL, $length = NULL)
{
if ($str == '' OR $mask == '')
return 0;
if (utf8::is_ascii($str) AND utf8::is_ascii($mask))
return ($offset === NULL) ? strcspn($str, $mask) : (($length === NULL) ? strcspn($str, $mask, $offset) : strcspn($str, $mask, $offset, $length));
if ($offset !== NULL OR $length !== NULL)
{
$str = utf8::substr($str, $offset, $length);
}
// Escape these characters: - [ ] . : \ ^ /
// The . and : are escaped to prevent possible warnings about POSIX regex elements
$mask = preg_replace('#[-[\].:\\\\^/]#', '\\\\$0', $mask);
preg_match('/^[^'.$mask.']+/u', $str, $matches);
return isset($matches[0]) ? utf8::strlen($matches[0]) : 0;
}

28
system/utf8/stristr.php Normal file
View file

@ -0,0 +1,28 @@
<?php
/**
* utf8::stristr
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _stristr($str, $search)
{
if (utf8::is_ascii($str) AND utf8::is_ascii($search))
return stristr($str, $search);
if ($search == '')
return $str;
$str_lower = utf8::strtolower($str);
$search_lower = utf8::strtolower($search);
preg_match('/^(.*?)'.preg_quote($search, '/').'/s', $str_lower, $matches);
if (isset($matches[1]))
return substr($str, strlen($matches[1]));
return FALSE;
}

17
system/utf8/strlen.php Normal file
View file

@ -0,0 +1,17 @@
<?php
/**
* utf8::strlen
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _strlen($str)
{
if (utf8::is_ascii($str))
return strlen($str);
return strlen(utf8_decode($str));
}

27
system/utf8/strpos.php Normal file
View file

@ -0,0 +1,27 @@
<?php
/**
* utf8::strpos
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _strpos($str, $search, $offset = 0)
{
$offset = (int) $offset;
if (utf8::is_ascii($str) AND utf8::is_ascii($search))
return strpos($str, $search, $offset);
if ($offset == 0)
{
$array = explode($search, $str, 2);
return isset($array[1]) ? utf8::strlen($array[0]) : FALSE;
}
$str = utf8::substr($str, $offset);
$pos = utf8::strpos($str, $search);
return ($pos === FALSE) ? FALSE : $pos + $offset;
}

18
system/utf8/strrev.php Normal file
View file

@ -0,0 +1,18 @@
<?php
/**
* utf8::strrev
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _strrev($str)
{
if (utf8::is_ascii($str))
return strrev($str);
preg_match_all('/./us', $str, $matches);
return implode('', array_reverse($matches[0]));
}

27
system/utf8/strrpos.php Normal file
View file

@ -0,0 +1,27 @@
<?php
/**
* utf8::strrpos
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _strrpos($str, $search, $offset = 0)
{
$offset = (int) $offset;
if (utf8::is_ascii($str) AND utf8::is_ascii($search))
return strrpos($str, $search, $offset);
if ($offset == 0)
{
$array = explode($search, $str, -1);
return isset($array[0]) ? utf8::strlen(implode($search, $array)) : FALSE;
}
$str = utf8::substr($str, $offset);
$pos = utf8::strrpos($str, $search);
return ($pos === FALSE) ? FALSE : $pos + $offset;
}

30
system/utf8/strspn.php Normal file
View file

@ -0,0 +1,30 @@
<?php
/**
* utf8::strspn
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _strspn($str, $mask, $offset = NULL, $length = NULL)
{
if ($str == '' OR $mask == '')
return 0;
if (utf8::is_ascii($str) AND utf8::is_ascii($mask))
return ($offset === NULL) ? strspn($str, $mask) : (($length === NULL) ? strspn($str, $mask, $offset) : strspn($str, $mask, $offset, $length));
if ($offset !== NULL OR $length !== NULL)
{
$str = utf8::substr($str, $offset, $length);
}
// Escape these characters: - [ ] . : \ ^ /
// The . and : are escaped to prevent possible warnings about POSIX regex elements
$mask = preg_replace('#[-[\].:\\\\^/]#', '\\\\$0', $mask);
preg_match('/^[^'.$mask.']+/u', $str, $matches);
return isset($matches[0]) ? utf8::strlen($matches[0]) : 0;
}

View file

@ -0,0 +1,81 @@
<?php
/**
* utf8::strtolower
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _strtolower($str)
{
if (utf8::is_ascii($str))
return strtolower($str);
static $UTF8_UPPER_TO_LOWER = NULL;
if ($UTF8_UPPER_TO_LOWER === NULL)
{
$UTF8_UPPER_TO_LOWER = array(
0x0041=>0x0061, 0x03A6=>0x03C6, 0x0162=>0x0163, 0x00C5=>0x00E5, 0x0042=>0x0062,
0x0139=>0x013A, 0x00C1=>0x00E1, 0x0141=>0x0142, 0x038E=>0x03CD, 0x0100=>0x0101,
0x0490=>0x0491, 0x0394=>0x03B4, 0x015A=>0x015B, 0x0044=>0x0064, 0x0393=>0x03B3,
0x00D4=>0x00F4, 0x042A=>0x044A, 0x0419=>0x0439, 0x0112=>0x0113, 0x041C=>0x043C,
0x015E=>0x015F, 0x0143=>0x0144, 0x00CE=>0x00EE, 0x040E=>0x045E, 0x042F=>0x044F,
0x039A=>0x03BA, 0x0154=>0x0155, 0x0049=>0x0069, 0x0053=>0x0073, 0x1E1E=>0x1E1F,
0x0134=>0x0135, 0x0427=>0x0447, 0x03A0=>0x03C0, 0x0418=>0x0438, 0x00D3=>0x00F3,
0x0420=>0x0440, 0x0404=>0x0454, 0x0415=>0x0435, 0x0429=>0x0449, 0x014A=>0x014B,
0x0411=>0x0431, 0x0409=>0x0459, 0x1E02=>0x1E03, 0x00D6=>0x00F6, 0x00D9=>0x00F9,
0x004E=>0x006E, 0x0401=>0x0451, 0x03A4=>0x03C4, 0x0423=>0x0443, 0x015C=>0x015D,
0x0403=>0x0453, 0x03A8=>0x03C8, 0x0158=>0x0159, 0x0047=>0x0067, 0x00C4=>0x00E4,
0x0386=>0x03AC, 0x0389=>0x03AE, 0x0166=>0x0167, 0x039E=>0x03BE, 0x0164=>0x0165,
0x0116=>0x0117, 0x0108=>0x0109, 0x0056=>0x0076, 0x00DE=>0x00FE, 0x0156=>0x0157,
0x00DA=>0x00FA, 0x1E60=>0x1E61, 0x1E82=>0x1E83, 0x00C2=>0x00E2, 0x0118=>0x0119,
0x0145=>0x0146, 0x0050=>0x0070, 0x0150=>0x0151, 0x042E=>0x044E, 0x0128=>0x0129,
0x03A7=>0x03C7, 0x013D=>0x013E, 0x0422=>0x0442, 0x005A=>0x007A, 0x0428=>0x0448,
0x03A1=>0x03C1, 0x1E80=>0x1E81, 0x016C=>0x016D, 0x00D5=>0x00F5, 0x0055=>0x0075,
0x0176=>0x0177, 0x00DC=>0x00FC, 0x1E56=>0x1E57, 0x03A3=>0x03C3, 0x041A=>0x043A,
0x004D=>0x006D, 0x016A=>0x016B, 0x0170=>0x0171, 0x0424=>0x0444, 0x00CC=>0x00EC,
0x0168=>0x0169, 0x039F=>0x03BF, 0x004B=>0x006B, 0x00D2=>0x00F2, 0x00C0=>0x00E0,
0x0414=>0x0434, 0x03A9=>0x03C9, 0x1E6A=>0x1E6B, 0x00C3=>0x00E3, 0x042D=>0x044D,
0x0416=>0x0436, 0x01A0=>0x01A1, 0x010C=>0x010D, 0x011C=>0x011D, 0x00D0=>0x00F0,
0x013B=>0x013C, 0x040F=>0x045F, 0x040A=>0x045A, 0x00C8=>0x00E8, 0x03A5=>0x03C5,
0x0046=>0x0066, 0x00DD=>0x00FD, 0x0043=>0x0063, 0x021A=>0x021B, 0x00CA=>0x00EA,
0x0399=>0x03B9, 0x0179=>0x017A, 0x00CF=>0x00EF, 0x01AF=>0x01B0, 0x0045=>0x0065,
0x039B=>0x03BB, 0x0398=>0x03B8, 0x039C=>0x03BC, 0x040C=>0x045C, 0x041F=>0x043F,
0x042C=>0x044C, 0x00DE=>0x00FE, 0x00D0=>0x00F0, 0x1EF2=>0x1EF3, 0x0048=>0x0068,
0x00CB=>0x00EB, 0x0110=>0x0111, 0x0413=>0x0433, 0x012E=>0x012F, 0x00C6=>0x00E6,
0x0058=>0x0078, 0x0160=>0x0161, 0x016E=>0x016F, 0x0391=>0x03B1, 0x0407=>0x0457,
0x0172=>0x0173, 0x0178=>0x00FF, 0x004F=>0x006F, 0x041B=>0x043B, 0x0395=>0x03B5,
0x0425=>0x0445, 0x0120=>0x0121, 0x017D=>0x017E, 0x017B=>0x017C, 0x0396=>0x03B6,
0x0392=>0x03B2, 0x0388=>0x03AD, 0x1E84=>0x1E85, 0x0174=>0x0175, 0x0051=>0x0071,
0x0417=>0x0437, 0x1E0A=>0x1E0B, 0x0147=>0x0148, 0x0104=>0x0105, 0x0408=>0x0458,
0x014C=>0x014D, 0x00CD=>0x00ED, 0x0059=>0x0079, 0x010A=>0x010B, 0x038F=>0x03CE,
0x0052=>0x0072, 0x0410=>0x0430, 0x0405=>0x0455, 0x0402=>0x0452, 0x0126=>0x0127,
0x0136=>0x0137, 0x012A=>0x012B, 0x038A=>0x03AF, 0x042B=>0x044B, 0x004C=>0x006C,
0x0397=>0x03B7, 0x0124=>0x0125, 0x0218=>0x0219, 0x00DB=>0x00FB, 0x011E=>0x011F,
0x041E=>0x043E, 0x1E40=>0x1E41, 0x039D=>0x03BD, 0x0106=>0x0107, 0x03AB=>0x03CB,
0x0426=>0x0446, 0x00DE=>0x00FE, 0x00C7=>0x00E7, 0x03AA=>0x03CA, 0x0421=>0x0441,
0x0412=>0x0432, 0x010E=>0x010F, 0x00D8=>0x00F8, 0x0057=>0x0077, 0x011A=>0x011B,
0x0054=>0x0074, 0x004A=>0x006A, 0x040B=>0x045B, 0x0406=>0x0456, 0x0102=>0x0103,
0x039B=>0x03BB, 0x00D1=>0x00F1, 0x041D=>0x043D, 0x038C=>0x03CC, 0x00C9=>0x00E9,
0x00D0=>0x00F0, 0x0407=>0x0457, 0x0122=>0x0123,
);
}
$uni = utf8::to_unicode($str);
if ($uni === FALSE)
return FALSE;
for ($i = 0, $c = count($uni); $i < $c; $i++)
{
if (isset($UTF8_UPPER_TO_LOWER[$uni[$i]]))
{
$uni[$i] = $UTF8_UPPER_TO_LOWER[$uni[$i]];
}
}
return utf8::from_unicode($uni);
}

View file

@ -0,0 +1,81 @@
<?php
/**
* utf8::strtoupper
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _strtoupper($str)
{
if (utf8::is_ascii($str))
return strtoupper($str);
static $UTF8_LOWER_TO_UPPER = NULL;
if ($UTF8_LOWER_TO_UPPER === NULL)
{
$UTF8_LOWER_TO_UPPER = array(
0x0061=>0x0041, 0x03C6=>0x03A6, 0x0163=>0x0162, 0x00E5=>0x00C5, 0x0062=>0x0042,
0x013A=>0x0139, 0x00E1=>0x00C1, 0x0142=>0x0141, 0x03CD=>0x038E, 0x0101=>0x0100,
0x0491=>0x0490, 0x03B4=>0x0394, 0x015B=>0x015A, 0x0064=>0x0044, 0x03B3=>0x0393,
0x00F4=>0x00D4, 0x044A=>0x042A, 0x0439=>0x0419, 0x0113=>0x0112, 0x043C=>0x041C,
0x015F=>0x015E, 0x0144=>0x0143, 0x00EE=>0x00CE, 0x045E=>0x040E, 0x044F=>0x042F,
0x03BA=>0x039A, 0x0155=>0x0154, 0x0069=>0x0049, 0x0073=>0x0053, 0x1E1F=>0x1E1E,
0x0135=>0x0134, 0x0447=>0x0427, 0x03C0=>0x03A0, 0x0438=>0x0418, 0x00F3=>0x00D3,
0x0440=>0x0420, 0x0454=>0x0404, 0x0435=>0x0415, 0x0449=>0x0429, 0x014B=>0x014A,
0x0431=>0x0411, 0x0459=>0x0409, 0x1E03=>0x1E02, 0x00F6=>0x00D6, 0x00F9=>0x00D9,
0x006E=>0x004E, 0x0451=>0x0401, 0x03C4=>0x03A4, 0x0443=>0x0423, 0x015D=>0x015C,
0x0453=>0x0403, 0x03C8=>0x03A8, 0x0159=>0x0158, 0x0067=>0x0047, 0x00E4=>0x00C4,
0x03AC=>0x0386, 0x03AE=>0x0389, 0x0167=>0x0166, 0x03BE=>0x039E, 0x0165=>0x0164,
0x0117=>0x0116, 0x0109=>0x0108, 0x0076=>0x0056, 0x00FE=>0x00DE, 0x0157=>0x0156,
0x00FA=>0x00DA, 0x1E61=>0x1E60, 0x1E83=>0x1E82, 0x00E2=>0x00C2, 0x0119=>0x0118,
0x0146=>0x0145, 0x0070=>0x0050, 0x0151=>0x0150, 0x044E=>0x042E, 0x0129=>0x0128,
0x03C7=>0x03A7, 0x013E=>0x013D, 0x0442=>0x0422, 0x007A=>0x005A, 0x0448=>0x0428,
0x03C1=>0x03A1, 0x1E81=>0x1E80, 0x016D=>0x016C, 0x00F5=>0x00D5, 0x0075=>0x0055,
0x0177=>0x0176, 0x00FC=>0x00DC, 0x1E57=>0x1E56, 0x03C3=>0x03A3, 0x043A=>0x041A,
0x006D=>0x004D, 0x016B=>0x016A, 0x0171=>0x0170, 0x0444=>0x0424, 0x00EC=>0x00CC,
0x0169=>0x0168, 0x03BF=>0x039F, 0x006B=>0x004B, 0x00F2=>0x00D2, 0x00E0=>0x00C0,
0x0434=>0x0414, 0x03C9=>0x03A9, 0x1E6B=>0x1E6A, 0x00E3=>0x00C3, 0x044D=>0x042D,
0x0436=>0x0416, 0x01A1=>0x01A0, 0x010D=>0x010C, 0x011D=>0x011C, 0x00F0=>0x00D0,
0x013C=>0x013B, 0x045F=>0x040F, 0x045A=>0x040A, 0x00E8=>0x00C8, 0x03C5=>0x03A5,
0x0066=>0x0046, 0x00FD=>0x00DD, 0x0063=>0x0043, 0x021B=>0x021A, 0x00EA=>0x00CA,
0x03B9=>0x0399, 0x017A=>0x0179, 0x00EF=>0x00CF, 0x01B0=>0x01AF, 0x0065=>0x0045,
0x03BB=>0x039B, 0x03B8=>0x0398, 0x03BC=>0x039C, 0x045C=>0x040C, 0x043F=>0x041F,
0x044C=>0x042C, 0x00FE=>0x00DE, 0x00F0=>0x00D0, 0x1EF3=>0x1EF2, 0x0068=>0x0048,
0x00EB=>0x00CB, 0x0111=>0x0110, 0x0433=>0x0413, 0x012F=>0x012E, 0x00E6=>0x00C6,
0x0078=>0x0058, 0x0161=>0x0160, 0x016F=>0x016E, 0x03B1=>0x0391, 0x0457=>0x0407,
0x0173=>0x0172, 0x00FF=>0x0178, 0x006F=>0x004F, 0x043B=>0x041B, 0x03B5=>0x0395,
0x0445=>0x0425, 0x0121=>0x0120, 0x017E=>0x017D, 0x017C=>0x017B, 0x03B6=>0x0396,
0x03B2=>0x0392, 0x03AD=>0x0388, 0x1E85=>0x1E84, 0x0175=>0x0174, 0x0071=>0x0051,
0x0437=>0x0417, 0x1E0B=>0x1E0A, 0x0148=>0x0147, 0x0105=>0x0104, 0x0458=>0x0408,
0x014D=>0x014C, 0x00ED=>0x00CD, 0x0079=>0x0059, 0x010B=>0x010A, 0x03CE=>0x038F,
0x0072=>0x0052, 0x0430=>0x0410, 0x0455=>0x0405, 0x0452=>0x0402, 0x0127=>0x0126,
0x0137=>0x0136, 0x012B=>0x012A, 0x03AF=>0x038A, 0x044B=>0x042B, 0x006C=>0x004C,
0x03B7=>0x0397, 0x0125=>0x0124, 0x0219=>0x0218, 0x00FB=>0x00DB, 0x011F=>0x011E,
0x043E=>0x041E, 0x1E41=>0x1E40, 0x03BD=>0x039D, 0x0107=>0x0106, 0x03CB=>0x03AB,
0x0446=>0x0426, 0x00FE=>0x00DE, 0x00E7=>0x00C7, 0x03CA=>0x03AA, 0x0441=>0x0421,
0x0432=>0x0412, 0x010F=>0x010E, 0x00F8=>0x00D8, 0x0077=>0x0057, 0x011B=>0x011A,
0x0074=>0x0054, 0x006A=>0x004A, 0x045B=>0x040B, 0x0456=>0x0406, 0x0103=>0x0102,
0x03BB=>0x039B, 0x00F1=>0x00D1, 0x043D=>0x041D, 0x03CC=>0x038C, 0x00E9=>0x00C9,
0x00F0=>0x00D0, 0x0457=>0x0407, 0x0123=>0x0122,
);
}
$uni = utf8::to_unicode($str);
if ($uni === FALSE)
return FALSE;
for ($i = 0, $c = count($uni); $i < $c; $i++)
{
if (isset($UTF8_LOWER_TO_UPPER[$uni[$i]]))
{
$uni[$i] = $UTF8_LOWER_TO_UPPER[$uni[$i]];
}
}
return utf8::from_unicode($uni);
}

72
system/utf8/substr.php Normal file
View file

@ -0,0 +1,72 @@
<?php
/**
* utf8::substr
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _substr($str, $offset, $length = NULL)
{
if (utf8::is_ascii($str))
return ($length === NULL) ? substr($str, $offset) : substr($str, $offset, $length);
// Normalize params
$str = (string) $str;
$strlen = utf8::strlen($str);
$offset = (int) ($offset < 0) ? max(0, $strlen + $offset) : $offset; // Normalize to positive offset
$length = ($length === NULL) ? NULL : (int) $length;
// Impossible
if ($length === 0 OR $offset >= $strlen OR ($length < 0 AND $length <= $offset - $strlen))
return '';
// Whole string
if ($offset == 0 AND ($length === NULL OR $length >= $strlen))
return $str;
// Build regex
$regex = '^';
// Create an offset expression
if ($offset > 0)
{
// PCRE repeating quantifiers must be less than 65536, so repeat when necessary
$x = (int) ($offset / 65535);
$y = (int) ($offset % 65535);
$regex .= ($x == 0) ? '' : '(?:.{65535}){'.$x.'}';
$regex .= ($y == 0) ? '' : '.{'.$y.'}';
}
// Create a length expression
if ($length === NULL)
{
$regex .= '(.*)'; // No length set, grab it all
}
// Find length from the left (positive length)
elseif ($length > 0)
{
// Reduce length so that it can't go beyond the end of the string
$length = min($strlen - $offset, $length);
$x = (int) ($length / 65535);
$y = (int) ($length % 65535);
$regex .= '(';
$regex .= ($x == 0) ? '' : '(?:.{65535}){'.$x.'}';
$regex .= '.{'.$y.'})';
}
// Find length from the right (negative length)
else
{
$x = (int) (-$length / 65535);
$y = (int) (-$length % 65535);
$regex .= '(.*)';
$regex .= ($x == 0) ? '' : '(?:.{65535}){'.$x.'}';
$regex .= '.{'.$y.'}';
}
preg_match('/'.$regex.'/us', $str, $matches);
return $matches[1];
}

View file

@ -0,0 +1,22 @@
<?php
/**
* utf8::substr_replace
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _substr_replace($str, $replacement, $offset, $length = NULL)
{
if (utf8::is_ascii($str))
return ($length === NULL) ? substr_replace($str, $replacement, $offset) : substr_replace($str, $replacement, $offset, $length);
$length = ($length === NULL) ? utf8::strlen($str) : (int) $length;
preg_match_all('/./us', $str, $str_array);
preg_match_all('/./us', $replacement, $replacement_array);
array_splice($str_array[0], $offset, $length, $replacement_array[0]);
return implode('', $str_array[0]);
}

141
system/utf8/to_unicode.php Normal file
View file

@ -0,0 +1,141 @@
<?php
/**
* utf8::to_unicode
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _to_unicode($str)
{
$mState = 0; // cached expected number of octets after the current octet until the beginning of the next UTF8 character sequence
$mUcs4 = 0; // cached Unicode character
$mBytes = 1; // cached expected number of octets in the current sequence
$out = array();
$len = strlen($str);
for ($i = 0; $i < $len; $i++)
{
$in = ord($str[$i]);
if ($mState == 0)
{
// When mState is zero we expect either a US-ASCII character or a
// multi-octet sequence.
if (0 == (0x80 & $in))
{
// US-ASCII, pass straight through.
$out[] = $in;
$mBytes = 1;
}
elseif (0xC0 == (0xE0 & $in))
{
// First octet of 2 octet sequence
$mUcs4 = $in;
$mUcs4 = ($mUcs4 & 0x1F) << 6;
$mState = 1;
$mBytes = 2;
}
elseif (0xE0 == (0xF0 & $in))
{
// First octet of 3 octet sequence
$mUcs4 = $in;
$mUcs4 = ($mUcs4 & 0x0F) << 12;
$mState = 2;
$mBytes = 3;
}
elseif (0xF0 == (0xF8 & $in))
{
// First octet of 4 octet sequence
$mUcs4 = $in;
$mUcs4 = ($mUcs4 & 0x07) << 18;
$mState = 3;
$mBytes = 4;
}
elseif (0xF8 == (0xFC & $in))
{
// First octet of 5 octet sequence.
//
// This is illegal because the encoded codepoint must be either
// (a) not the shortest form or
// (b) outside the Unicode range of 0-0x10FFFF.
// Rather than trying to resynchronize, we will carry on until the end
// of the sequence and let the later error handling code catch it.
$mUcs4 = $in;
$mUcs4 = ($mUcs4 & 0x03) << 24;
$mState = 4;
$mBytes = 5;
}
elseif (0xFC == (0xFE & $in))
{
// First octet of 6 octet sequence, see comments for 5 octet sequence.
$mUcs4 = $in;
$mUcs4 = ($mUcs4 & 1) << 30;
$mState = 5;
$mBytes = 6;
}
else
{
// Current octet is neither in the US-ASCII range nor a legal first octet of a multi-octet sequence.
trigger_error('utf8::to_unicode: Illegal sequence identifier in UTF-8 at byte '.$i, E_USER_WARNING);
return FALSE;
}
}
else
{
// When mState is non-zero, we expect a continuation of the multi-octet sequence
if (0x80 == (0xC0 & $in))
{
// Legal continuation
$shift = ($mState - 1) * 6;
$tmp = $in;
$tmp = ($tmp & 0x0000003F) << $shift;
$mUcs4 |= $tmp;
// End of the multi-octet sequence. mUcs4 now contains the final Unicode codepoint to be output
if (0 == --$mState)
{
// Check for illegal sequences and codepoints
// From Unicode 3.1, non-shortest form is illegal
if (((2 == $mBytes) AND ($mUcs4 < 0x0080)) OR
((3 == $mBytes) AND ($mUcs4 < 0x0800)) OR
((4 == $mBytes) AND ($mUcs4 < 0x10000)) OR
(4 < $mBytes) OR
// From Unicode 3.2, surrogate characters are illegal
(($mUcs4 & 0xFFFFF800) == 0xD800) OR
// Codepoints outside the Unicode range are illegal
($mUcs4 > 0x10FFFF))
{
trigger_error('utf8::to_unicode: Illegal sequence or codepoint in UTF-8 at byte '.$i, E_USER_WARNING);
return FALSE;
}
if (0xFEFF != $mUcs4)
{
// BOM is legal but we don't want to output it
$out[] = $mUcs4;
}
// Initialize UTF-8 cache
$mState = 0;
$mUcs4 = 0;
$mBytes = 1;
}
}
else
{
// ((0xC0 & (*in) != 0x80) AND (mState != 0))
// Incomplete multi-octet sequence
trigger_error('utf8::to_unicode: Incomplete multi-octet sequence in UTF-8 at byte '.$i, E_USER_WARNING);
return FALSE;
}
}
}
return $out;
}

View file

@ -0,0 +1,77 @@
<?php
/**
* utf8::transliterate_to_ascii
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _transliterate_to_ascii($str, $case = 0)
{
static $UTF8_LOWER_ACCENTS = NULL;
static $UTF8_UPPER_ACCENTS = NULL;
if ($case <= 0)
{
if ($UTF8_LOWER_ACCENTS === NULL)
{
$UTF8_LOWER_ACCENTS = array(
'à' => 'a', 'ô' => 'o', 'ď' => 'd', 'ḟ' => 'f', 'ë' => 'e', 'š' => 's', 'ơ' => 'o',
'ß' => 'ss', 'ă' => 'a', 'ř' => 'r', 'ț' => 't', 'ň' => 'n', 'ā' => 'a', 'ķ' => 'k',
'ŝ' => 's', 'ỳ' => 'y', 'ņ' => 'n', 'ĺ' => 'l', 'ħ' => 'h', 'ṗ' => 'p', 'ó' => 'o',
'ú' => 'u', 'ě' => 'e', 'é' => 'e', 'ç' => 'c', 'ẁ' => 'w', 'ċ' => 'c', 'õ' => 'o',
'ṡ' => 's', 'ø' => 'o', 'ģ' => 'g', 'ŧ' => 't', 'ș' => 's', 'ė' => 'e', 'ĉ' => 'c',
'ś' => 's', 'î' => 'i', 'ű' => 'u', 'ć' => 'c', 'ę' => 'e', 'ŵ' => 'w', 'ṫ' => 't',
'ū' => 'u', 'č' => 'c', 'ö' => 'o', 'è' => 'e', 'ŷ' => 'y', 'ą' => 'a', 'ł' => 'l',
'ų' => 'u', 'ů' => 'u', 'ş' => 's', 'ğ' => 'g', 'ļ' => 'l', 'ƒ' => 'f', 'ž' => 'z',
'ẃ' => 'w', 'ḃ' => 'b', 'å' => 'a', 'ì' => 'i', 'ï' => 'i', 'ḋ' => 'd', 'ť' => 't',
'ŗ' => 'r', 'ä' => 'a', 'í' => 'i', 'ŕ' => 'r', 'ê' => 'e', 'ü' => 'u', 'ò' => 'o',
'ē' => 'e', 'ñ' => 'n', 'ń' => 'n', 'ĥ' => 'h', 'ĝ' => 'g', 'đ' => 'd', 'ĵ' => 'j',
'ÿ' => 'y', 'ũ' => 'u', 'ŭ' => 'u', 'ư' => 'u', 'ţ' => 't', 'ý' => 'y', 'ő' => 'o',
'â' => 'a', 'ľ' => 'l', 'ẅ' => 'w', 'ż' => 'z', 'ī' => 'i', 'ã' => 'a', 'ġ' => 'g',
'ṁ' => 'm', 'ō' => 'o', 'ĩ' => 'i', 'ù' => 'u', 'į' => 'i', 'ź' => 'z', 'á' => 'a',
'û' => 'u', 'þ' => 'th', 'ð' => 'dh', 'æ' => 'ae', 'µ' => 'u', 'ĕ' => 'e',
);
}
$str = str_replace(
array_keys($UTF8_LOWER_ACCENTS),
array_values($UTF8_LOWER_ACCENTS),
$str
);
}
if ($case >= 0)
{
if ($UTF8_UPPER_ACCENTS === NULL)
{
$UTF8_UPPER_ACCENTS = array(
'À' => 'A', 'Ô' => 'O', 'Ď' => 'D', 'Ḟ' => 'F', 'Ë' => 'E', 'Š' => 'S', 'Ơ' => 'O',
'Ă' => 'A', 'Ř' => 'R', 'Ț' => 'T', 'Ň' => 'N', 'Ā' => 'A', 'Ķ' => 'K', 'Ĕ' => 'E',
'Ŝ' => 'S', 'Ỳ' => 'Y', 'Ņ' => 'N', 'Ĺ' => 'L', 'Ħ' => 'H', 'Ṗ' => 'P', 'Ó' => 'O',
'Ú' => 'U', 'Ě' => 'E', 'É' => 'E', 'Ç' => 'C', 'Ẁ' => 'W', 'Ċ' => 'C', 'Õ' => 'O',
'Ṡ' => 'S', 'Ø' => 'O', 'Ģ' => 'G', 'Ŧ' => 'T', 'Ș' => 'S', 'Ė' => 'E', 'Ĉ' => 'C',
'Ś' => 'S', 'Î' => 'I', 'Ű' => 'U', 'Ć' => 'C', 'Ę' => 'E', 'Ŵ' => 'W', 'Ṫ' => 'T',
'Ū' => 'U', 'Č' => 'C', 'Ö' => 'O', 'È' => 'E', 'Ŷ' => 'Y', 'Ą' => 'A', 'Ł' => 'L',
'Ų' => 'U', 'Ů' => 'U', 'Ş' => 'S', 'Ğ' => 'G', 'Ļ' => 'L', 'Ƒ' => 'F', 'Ž' => 'Z',
'Ẃ' => 'W', 'Ḃ' => 'B', 'Å' => 'A', 'Ì' => 'I', 'Ï' => 'I', 'Ḋ' => 'D', 'Ť' => 'T',
'Ŗ' => 'R', 'Ä' => 'A', 'Í' => 'I', 'Ŕ' => 'R', 'Ê' => 'E', 'Ü' => 'U', 'Ò' => 'O',
'Ē' => 'E', 'Ñ' => 'N', 'Ń' => 'N', 'Ĥ' => 'H', 'Ĝ' => 'G', 'Đ' => 'D', 'Ĵ' => 'J',
'Ÿ' => 'Y', 'Ũ' => 'U', 'Ŭ' => 'U', 'Ư' => 'U', 'Ţ' => 'T', 'Ý' => 'Y', 'Ő' => 'O',
'Â' => 'A', 'Ľ' => 'L', 'Ẅ' => 'W', 'Ż' => 'Z', 'Ī' => 'I', 'Ã' => 'A', 'Ġ' => 'G',
'Ṁ' => 'M', 'Ō' => 'O', 'Ĩ' => 'I', 'Ù' => 'U', 'Į' => 'I', 'Ź' => 'Z', 'Á' => 'A',
'Û' => 'U', 'Þ' => 'Th', 'Ð' => 'Dh', 'Æ' => 'Ae',
);
}
$str = str_replace(
array_keys($UTF8_UPPER_ACCENTS),
array_values($UTF8_UPPER_ACCENTS),
$str
);
}
return $str;
}

17
system/utf8/trim.php Normal file
View file

@ -0,0 +1,17 @@
<?php
/**
* utf8::trim
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _trim($str, $charlist = NULL)
{
if ($charlist === NULL)
return trim($str);
return utf8::ltrim(utf8::rtrim($str, $charlist), $charlist);
}

18
system/utf8/ucfirst.php Normal file
View file

@ -0,0 +1,18 @@
<?php
/**
* utf8::ucfirst
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _ucfirst($str)
{
if (utf8::is_ascii($str))
return ucfirst($str);
preg_match('/^(.?)(.*)$/us', $str, $matches);
return utf8::strtoupper($matches[1]).$matches[2];
}

23
system/utf8/ucwords.php Normal file
View file

@ -0,0 +1,23 @@
<?php
/**
* utf8::ucwords
*
* @package Core
* @author Kohana Team
* @copyright (c) 2007-2008 Kohana Team
* @copyright (c) 2005 Harry Fuecks
* @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt
*/
function _ucwords($str)
{
if (utf8::is_ascii($str))
return ucwords($str);
// [\x0c\x09\x0b\x0a\x0d\x20] matches form feeds, horizontal tabs, vertical tabs, linefeeds and carriage returns.
// This corresponds to the definition of a 'word' defined at http://php.net/ucwords
return preg_replace(
'/(?<=^|[\x0c\x09\x0b\x0a\x0d\x20])[^\x0c\x09\x0b\x0a\x0d\x20]/ue',
'utf8::strtoupper(\'$0\')',
$str
);
}