mirror/php-e107
1
0
Fork 0
mirror of https://github.com/e107inc/e107.git synced 2025-08-03 21:27:25 +02:00
Code Issues Releases Wiki Activity

Code cleanup. Removal of deprecated utf8 classes.

Browse Source
This commit is contained in:
Cameron
2020-12-08 07:29:17 -08:00
parent 25c1592e8a
commit 005bff7e59
7 changed files with 118 additions and 832 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
class2.php
View File

@@ -84,14 +84,14 @@ if(function_exists('ini_get'))
if($register_globals == true)
{
if(isset($_REQUEST['_E107'])) { unset($_E107); }
while (list($global) = each($GLOBALS))
foreach($GLOBALS as $global=>$var)
{
if (!preg_match('/^(_POST|_GET|_COOKIE|_SERVER|_FILES|_SESSION|GLOBALS|HTTP.*|_REQUEST|_E107|retrieve_prefs|eplug_admin|eTimingStart.*|oblev_.*)$/', $global))
{
unset($$global);
}
}
unset($global);
unset($global, $var);
}
// MOVED TO $e107->prepare_request()
@@ -285,7 +285,7 @@ if(isset($mySQLport))
}
$e107 = e107::getInstance()->initCore($e107_paths, e_ROOT, $sql_info, varset($E107_CONFIG, array()));
e107::getSingleton('eIPHandler'); // This auto-handles bans etc
unset($dirPaths,$sql_info,$e107_paths);
unset($dirPaths,$e107_paths);
/**
* NEW - system security levels
@@ -401,8 +401,8 @@ $sql = e107::getDb(); //TODO - find & replace $sql, $e107->sql
$sql->db_SetErrorReporting(false);
$dbg->logTime('SQL Connect');
$merror=$sql->db_Connect($mySQLserver, $mySQLuser, $mySQLpassword, $mySQLdefaultdb);
$merror=$sql->db_Connect($sql_info['mySQLserver'], $sql_info['mySQLuser'], $sql_info['mySQLpassword'], $mySQLdefaultdb);
unset($sql_info);
// create after the initial connection.
//DEPRECATED, BC, call the method only when needed
$sql2 = e107::getDb('sql2'); //TODO find & replace all $sql2 calls
@@ -675,7 +675,7 @@ if(isset($pref['lan_global_list']))
{
if(e107::plugLan($path, 'global', true) === false)
{
e107::plugLan($path, 'global', false);
e107::plugLan($path, 'global');
}
}
@@ -703,7 +703,7 @@ $dbg->logTime('Misc resources. Online user tracking, cache');
$e107cache = e107::getCache(); //TODO - find & replace $e107cache, $e107->ecache
//DEPRECATED, BC, call the method only when needed, $e107->override caught by __get()
$override = e107::getSingleton('override', true);
$override = e107::getSingleton('override');
//DEPRECATED, BC, call the method only when needed, $e107->user_class caught by __get()
$e_userclass = e107::getUserClass(); //TODO - find & replace $e_userclass, $e107->user_class
@@ -753,7 +753,7 @@ define('SITECONTACTINFO', $tp->toHTML($pref['sitecontactinfo'], true, 'emotes_of
define('SITEEMAIL', vartrue($pref['replyto_email'],$pref['siteadminemail']));
define('USER_REGISTRATION', vartrue($pref['user_reg'],false)); // User Registration System Active or Not.
define('e_DEVELOPER', $developerMode);
define('e_VERSION', varset($pref['version'],''));
define('e_VERSION', varset($pref['version']));
unset($developerMode);
@@ -1334,7 +1334,7 @@ $dbg->logTime('Login/logout/ban/tz');
if (isset($_POST['userlogin']) || isset($_POST['userlogin_x']))
{
e107::getUser()->login($_POST['username'], $_POST['userpass'], $_POST['autologin'], varset($_POST['hashchallenge'],''), false);
e107::getUser()->login($_POST['username'], $_POST['userpass'], $_POST['autologin'], varset($_POST['hashchallenge']), false);
// e107_require_once(e_HANDLER.'login.php');
// $usr = new userlogin($_POST['username'], $_POST['userpass'], $_POST['autologin'], varset($_POST['hashchallenge'],''));
}
@@ -1347,7 +1347,7 @@ if (($_SERVER['QUERY_STRING'] == 'logout')/* || (($pref['user_tracking'] == 'ses
{
if (USER)
{
if (check_class(varset($pref['user_audit_class'],''))) // Need to note in user audit trail
if (check_class(varset($pref['user_audit_class']))) // Need to note in user audit trail
{
e107::getLog()->user_audit(USER_AUDIT_LOGOUT, null, USERID, USERNAME);
}
@@ -1531,7 +1531,7 @@ if(!defined("THEME_LAYOUT"))
$user_pref = e107::getUser()->getPref();
$pref = e107::getPref();
$cusPagePref = (!empty($user_pref['sitetheme_custompages'])) ? $user_pref['sitetheme_custompages'] : varset($pref['sitetheme_custompages'],array());
$cusPageDef = (empty($user_pref['sitetheme_deflayout'])) ? varset($pref['sitetheme_deflayout'],'') : $user_pref['sitetheme_deflayout'];
$cusPageDef = (empty($user_pref['sitetheme_deflayout'])) ? varset($pref['sitetheme_deflayout']) : $user_pref['sitetheme_deflayout'];
$deflayout = e107::getTheme()->getThemeLayout($cusPagePref, $cusPageDef, e_REQUEST_URL, varset($_SERVER['SCRIPT_FILENAME']));
define("THEME_LAYOUT",$deflayout);
@@ -1882,7 +1882,7 @@ function get_user_data($uid, $extra = '')
unset($extra);
$var = array();
$user = e107::getSystemUser($uid, true);
$user = e107::getSystemUser($uid);
if($user)
{
$var = $user->getUserData();
@@ -2077,7 +2077,7 @@ function init_session()
e107::getDebug()->log("Timezone: ".USERTIMEZONE); // remove later on.
define('USERIP', e107::getIPHandler()->getIP(FALSE));
define('USERIP', e107::getIPHandler()->getIP());
define('POST_REFERER', md5($user->getToken()));
// Check for intruders - outside the model for now
@@ -2733,7 +2733,7 @@ class e_http_header
function __construct()
{
if (strstr(varset($_SERVER['HTTP_ACCEPT_ENCODING'], ''), 'gzip'))
if (strstr(varset($_SERVER['HTTP_ACCEPT_ENCODING']), 'gzip'))
{
$this->compression_browser_support = true;
}

6
e107_admin/phpinfo.php
View File

@@ -55,7 +55,7 @@ foreach($extensionCheck as $var)
{
$erTitle = deftrue('PHP_LAN_7', "PHP Configuration Issue(s) Found:");
$def = deftrue('PHP_LAN_8', "[x] is missing from the PHP configuration and need to be installed.");
$message = $tp->lanVars($def,$var['label'],true);
$message = e107::getParser()->lanVars($def,$var['label'],true);
$mes->setIcon('fa-hand-stop-o', E_MESSAGE_ERROR)->setTitle($erTitle,E_MESSAGE_ERROR)->addError($message." <a class='alert-link' href='".$var['url']."' target='_blank' title=\"".$var['url']."\">".ADMIN_INFO_ICON."</a> ");
@@ -78,7 +78,7 @@ $security_risks = array(
if(ini_get($risk))
{
$srch = '<tr><td class="forumheader2 text-left">'.$risk.'</td><td class="forumheader3">';
$repl = '<tr><td class="forumheader2 text-left">'.$risk.'</td><td title="'.$tp->toAttribute($diz).'" class="forumheader3 alert alert-danger">';
$repl = '<tr><td class="forumheader2 text-left">'.$risk.'</td><td title="'.e107::getParser()->toAttribute($diz).'" class="forumheader3 alert alert-danger">';
$phpinfo = str_replace($srch,$repl,$phpinfo);
$mes->addWarning("<b>".$risk."</b>: ".$diz);
}
@@ -105,6 +105,6 @@ if(deftrue('e_DEBUG'))
$mes->addDebug("Session ID: ".session_id());
}
$ns->tablerender("PHPInfo", $mes->render(). $phpinfo);
e107::getRender()->tablerender("PHPInfo", $mes->render(). $phpinfo);
require_once("footer.php");

125
e107_handlers/e_parse_class.php
View File

@@ -33,26 +33,26 @@ class e_parse extends e_parser
//var $e_sc;
// BBCode processor
var $e_bb;
protected $e_bb;
// Profanity filter
var $e_pf;
protected $e_pf;
// Emote filter
var $e_emote;
protected $e_emote;
// 'Hooked' parsers (array)
var $e_hook;
protected $e_hook;
var $search = array('&amp;#039;', '&#039;', '&#39;', '&quot;', 'onerror', '&gt;', '&amp;quot;', ' & ');
protected $search = array('&amp;#039;', '&#039;', '&#39;', '&quot;', 'onerror', '&gt;', '&amp;quot;', ' & ');
var $replace = array("'", "'", "'", '"', 'one<i></i>rror', '>', '"', ' &amp; ');
protected $replace = array("'", "'", "'", '"', 'one<i></i>rror', '>', '"', ' &amp; ');
// Set to TRUE or FALSE once it has been calculated
var $e_highlighting;
protected $e_highlighting;
// Highlight query
var $e_query;
protected $e_query;
public $thumbWidth = 100;
@@ -72,7 +72,7 @@ class e_parse extends e_parser
// Set up the defaults
var $e_optDefault = array(
protected $e_optDefault = array(
// default context: reflects legacy settings (many items enabled)
'context' => 'OLDDEFAULT',
//
@@ -116,7 +116,7 @@ class e_parse extends e_parser
);
// Super modifiers override default option values
var $e_SuperMods = array(
protected $e_SuperMods = array(
//text is part of a title (e.g. news title)
'TITLE' =>
array(
@@ -184,7 +184,7 @@ class e_parse extends e_parser
);
// Individual modifiers change the current context
var $e_Modifiers = array(
protected $e_Modifiers = array(
'emotes_off' => array('emotes' => FALSE),
'emotes_on' => array('emotes' => TRUE),
'no_hook' => array('hook' => FALSE),
@@ -267,7 +267,7 @@ class e_parse extends e_parser
/**
* Initialise the type of UTF-8 processing methods depending on PHP version and mb string extension.
*
* Note: mb string is required during installation of e107.
* NOTE: can't be called until CHARSET is known
but we all know that it is UTF-8 now
*
@@ -278,19 +278,13 @@ class e_parse extends e_parser
// Start by working out what, if anything, we do about utf-8 handling.
// 'Do nothing' is the simple option
$this->utfAction = 0;
// CHARSET is utf-8
// if(strtolower(CHARSET) == 'utf-8')
// {
if(PHP_MAJOR_VERSION < 6)
{
// Need to do something here
if(extension_loaded('mbstring') && defined('MB_OVERLOAD_STRING'))
if(PHP_MAJOR_VERSION < 6 && extension_loaded('mbstring'))
{
// Check for function overloading
$temp = ini_get('mbstring.func_overload');
// Just check the string functions - will be non-zero if overloaded
if(($temp & MB_OVERLOAD_STRING) == 0)
if(defined('MB_OVERLOAD_STRING') && ($temp & MB_OVERLOAD_STRING) == 0)
{
// Can use the mb_string routines
$this->utfAction = 1;
@@ -298,16 +292,6 @@ class e_parse extends e_parser
// Set the default encoding, so we don't have to specify every time
mb_internal_encoding('UTF-8');
}
else
{
// Must use emulation - will probably be slow!
$this->utfAction = 2;
require_once(E_UTF8_PACK.'utils/unicode.php');
// Always load the core routines - bound to need some of them!
require_once(E_UTF8_PACK.'native/core.php');
}
}
// }
}
@@ -344,13 +328,14 @@ class e_parse extends e_parser
{
switch($this->utfAction)
{
case 0:
return strtolower($str);
case 1:
return mb_strtolower($str);
case 0:
default:
return strtolower($str);
}
// Default case shouldn't happen often
return utf8_strtolower($str);
}
@@ -365,13 +350,13 @@ class e_parse extends e_parser
{
switch($this->utfAction)
{
case 0:
return strtoupper($str);
case 1:
return mb_strtoupper($str);
default:
return strtoupper($str);
}
// Default case shouldn't happen often
return utf8_strtoupper($str);
}
@@ -391,12 +376,13 @@ class e_parse extends e_parser
{
switch($this->utfAction)
{
case 0:
return strpos($haystack, $needle, $offset);
case 1:
return mb_strpos($haystack, $needle, $offset);
default:
return strpos($haystack, $needle, $offset);
}
return utf8_strpos($haystack, $needle, $offset);
}
@@ -416,12 +402,13 @@ class e_parse extends e_parser
{
switch($this->utfAction)
{
case 0:
return strrpos($haystack, $needle, $offset);
case 1:
return mb_strrpos($haystack, $needle, $offset);
default:
return strrpos($haystack, $needle, $offset);
}
return utf8_strrpos($haystack, $needle, $offset);
}
@@ -431,7 +418,7 @@ class e_parse extends e_parser
*
* @param string $haystack The UTF-8 encoded string to search in.
* @param mixed $needle If needle is not a string, it is converted to an integer and applied as the ordinal value of a character.
* @param integer $length [optional] (PHP 5.3+) If TRUE, returns the part of the haystack before the first occurrence of the needle (excluding needle).
* @param integer $before_needle [optional] (PHP 5.3+) If TRUE, returns the part of the haystack before the first occurrence of the needle (excluding needle).
* @return string Returns the matched substring. If needle is not found, returns FALSE.
*/
public function ustristr($haystack, $needle, $before_needle = false)
@@ -466,8 +453,7 @@ class e_parse extends e_parser
{
switch($this->utfAction)
{
case 0:
return substr($str, $start, $length);
case 1:
if(is_null($length))
{
@@ -477,8 +463,11 @@ class e_parse extends e_parser
{
return mb_substr($str, $start, $length);
}
default:
return substr($str, $start, $length);
}
return utf8_substr($str, $start, $length);
}
/**
@@ -541,7 +530,7 @@ class e_parse extends e_parser
$data = str_replace(array('%7B','%7D'),array('{','}'),$data); // fix for {e_XXX} paths.
}
else // caused double-encoding of '&'
// else // caused double-encoding of '&'
{
// $data = str_replace('&amp;','&',$data);
// $data = str_replace('<','&lt;',$data);
@@ -658,7 +647,7 @@ class e_parse extends e_parser
$checkTags = explode(',', $tagList);
}
$tagArray = array_flip($checkTags);
foreach ($tagArray as &$v) { $v = 0; }; // Data fields become zero; keys are tag names.
foreach ($tagArray as &$v) { $v = 0; } // Data fields become zero; keys are tag names.
$data = strtolower(preg_replace('#\[code\].*?\[\/code\]#i', '', $data)); // Ignore code blocks. All lower case simplifies the rest
$matches = array();
if (!preg_match_all('#<(\/|)([^<>]*?[^\/])>#', $data, $matches, PREG_SET_ORDER))
@@ -770,7 +759,7 @@ class e_parse extends e_parser
// XXX REmove ME.
private function modTag($match)
{
$ans = '';
if (isset($match[1]))
{
$chop = intval(strlen($match[1]) / 2);
@@ -890,7 +879,9 @@ class e_parse extends e_parser
/**
* Check if we are using the simple-Parse array format, or a legacy .sc format which contains 'return '
*
* @param array $extraCodes
* @return bool
*/
private function isSimpleParse($extraCodes)
{
@@ -975,7 +966,7 @@ class e_parse extends e_parser
$nobreak = explode(" ", strtolower($nobreak));
// Variable setup
$intag = FALSE;
$innbk = array();
$drain = "";
@@ -1423,7 +1414,7 @@ class e_parse extends e_parser
$this->e_highlighting = TRUE;
if(!isset($this->e_query))
{
$query = preg_match('#(q|p)=(.*?)(&|$)#', $shr, $matches);
preg_match('#(q|p)=(.*?)(&|$)#', $shr, $matches);
$this->e_query = str_replace(array('+', '*', '"', ' '), array('', '.*?', '', '\b|\b'), trim(urldecode($matches[2])));
}
}
@@ -2191,8 +2182,8 @@ class e_parse extends e_parser
'ά' => 'a', 'έ' => 'e', 'ί' => 'i', 'ό' => 'o', 'ύ' => 'y', 'ή' => 'h', 'ώ' => 'w', 'ς' => 's',
'ϊ' => 'i', 'ΰ' => 'y', 'ϋ' => 'y', 'ΐ' => 'i',
// Turkish
'Ş' => 'S', 'İ' => 'I', 'Ç' => 'C', 'Ü' => 'U', 'Ö' => 'O', 'Ğ' => 'G',
'ş' => 's', 'ı' => 'i', 'ç' => 'c', 'ü' => 'u', 'ö' => 'o', 'ğ' => 'g',
'Ş' => 'S', 'İ' => 'I', /*'Ç' => 'C', 'Ü' => 'U', 'Ö' => 'O',*/ 'Ğ' => 'G',
'ş' => 's', 'ı' => 'i', /*'ç' => 'c', 'ü' => 'u', 'ö' => 'o',*/ 'ğ' => 'g',
// Russian
'А' => 'A', 'Б' => 'B', 'В' => 'V', 'Г' => 'G', 'Д' => 'D', 'Е' => 'E', 'Ё' => 'Yo', 'Ж' => 'Zh',
'З' => 'Z', 'И' => 'I', 'Й' => 'J', 'К' => 'K', 'Л' => 'L', 'М' => 'M', 'Н' => 'N', 'О' => 'O',
@@ -2213,15 +2204,15 @@ class e_parse extends e_parser
'č' => 'c', 'ď' => 'd', 'ě' => 'e', 'ň' => 'n', 'ř' => 'r', 'š' => 's', 'ť' => 't', 'ů' => 'u',
'ž' => 'z',
// Polish
'Ą' => 'A', 'Ć' => 'C', 'Ę' => 'e', 'Ł' => 'L', 'Ń' => 'N', 'Ó' => 'o', 'Ś' => 'S', 'Ź' => 'Z',
'Ą' => 'A', 'Ć' => 'C', 'Ę' => 'e', 'Ł' => 'L', 'Ń' => 'N', /*'Ó' => 'o',*/ 'Ś' => 'S', 'Ź' => 'Z',
'Ż' => 'Z',
'ą' => 'a', 'ć' => 'c', 'ę' => 'e', 'ł' => 'l', 'ń' => 'n', 'ó' => 'o', 'ś' => 's', 'ź' => 'z',
'ą' => 'a', 'ć' => 'c', 'ę' => 'e', 'ł' => 'l', 'ń' => 'n',/* 'ó' => 'o',*/ 'ś' => 's', 'ź' => 'z',
'ż' => 'z',
// Latvian
'Ā' => 'A', 'Č' => 'C', 'Ē' => 'E', 'Ģ' => 'G', 'Ī' => 'i', 'Ķ' => 'k', 'Ļ' => 'L', 'Ņ' => 'N',
'Š' => 'S', 'Ū' => 'u', 'Ž' => 'Z',
'ā' => 'a', 'č' => 'c', 'ē' => 'e', 'ģ' => 'g', 'ī' => 'i', 'ķ' => 'k', 'ļ' => 'l', 'ņ' => 'n',
'š' => 's', 'ū' => 'u', 'ž' => 'z',
'Ā' => 'A',/* 'Č' => 'C',*/ 'Ē' => 'E', 'Ģ' => 'G', 'Ī' => 'i', 'Ķ' => 'k', 'Ļ' => 'L', 'Ņ' => 'N',
/*'Š' => 'S',*/ 'Ū' => 'u',
'ā' => 'a', 'ē' => 'e', 'ģ' => 'g', 'ī' => 'i', 'ķ' => 'k', 'ļ' => 'l', 'ņ' => 'n',
'ū' => 'u',
'ľ' => 'l', 'ŕ'=>'r',
);
@@ -4889,7 +4880,7 @@ class e_parser
{
$ext = pathinfo($file,PATHINFO_EXTENSION);
return ($ext === 'youtube' || $ext === 'youtubepl') ? true : false;
return $ext === 'youtube' || $ext === 'youtubepl';
}
@@ -4908,7 +4899,7 @@ class e_parser
$ext = pathinfo($file,PATHINFO_EXTENSION);
return ($ext === 'jpg' || $ext === 'png' || $ext === 'gif' || $ext === 'jpeg') ? true : false;
return $ext === 'jpg' || $ext === 'png' || $ext === 'gif' || $ext === 'jpeg';
}
@@ -5220,7 +5211,7 @@ TMPL;
print_a( $filter3);
// Filter by String.
$filter1 = $tp->filter($text,'str');
$filter1 = $tp->filter($text);
echo "<h3>User-input &gg; filter(\$text, 'str')</h3>";
print_a($filter1);
@@ -5355,7 +5346,7 @@ return;
echo "<h2>New Parser</h2>";
echo "<h3>Processed</h3>";
$cleaned = $this->cleanHtml($html, true); // false = don't check html pref.
$cleaned = $this->cleanHtml($html); // false = don't check html pref.
print_a($cleaned);
$dbg->logTime('new Parser');
// $dbg->logTime('------ End Parser Test -------');
@@ -5998,7 +5989,7 @@ class e_emotefilter
class e_profanityFilter
{
var $profanityList;
protected $profanityList;
function __construct()
{
@@ -6101,6 +6092,8 @@ class textparse {
e107::getDebug()->logDeprecated();
}
unset($mode); // keep PHPStorm happy
return e107::getParser()->toDB($text);
}

4
e107_handlers/e_thumbnail_class.php
View File

@@ -169,7 +169,7 @@ class e_thumbnail
$tp = e107::getParser();
// convert raw to SC path
$this->_request['src'] = str_replace($tp->getUrlConstants('raw'), $tp->getUrlConstants('sc'), $this->_request['src']);
$this->_request['src'] = str_replace($tp->getUrlConstants('raw'), $tp->getUrlConstants(), $this->_request['src']);
// convert absolute and full url to SC URL
$this->_src = $tp->createConstants($this->_request['src'], 'mix');
@@ -228,7 +228,7 @@ class e_thumbnail
$fname = e107::getParser()->thumbCacheFile($this->_src_path, $options);
$cache_filename = e_CACHE_IMAGE . $fname;
// $this->sendCachedImage($cache_filename, $thumbnfo);
$this->sendCachedImage($cache_filename, $thumbnfo);
// No Cached file found - proceed with image creation.

438
e107_handlers/utf8/native/core.php
View File

@@ -1,438 +0,0 @@
<?php
/**
* @version $Id$
* @package utf8
* @subpackage strings
*/
/**
* Define UTF8_CORE as required
*/
if ( !defined('UTF8_CORE') ) {
define('UTF8_CORE',TRUE);
}
//--------------------------------------------------------------------
/**
* Unicode aware replacement for strlen(). Returns the number
* of characters in the string (not the number of bytes), replacing
* multibyte characters with a single byte equivalent
* utf8_decode() converts characters that are not in ISO-8859-1
* to '?', which, for the purpose of counting, is alright - It's
* much faster than iconv_strlen
* Note: this function does not count bad UTF-8 bytes in the string
* - these are simply ignored
* @author <chernyshevsky at hotmail dot com>
* @link http://www.php.net/manual/en/function.strlen.php
* @link http://www.php.net/manual/en/function.utf8-decode.php
* @param string UTF-8 string
* @return int number of UTF-8 characters in string
* @package utf8
* @subpackage strings
*/
function utf8_strlen($str){
return strlen(utf8_decode($str));
}
//--------------------------------------------------------------------
/**
* UTF-8 aware alternative to strpos
* Find position of first occurrence of a string
* Note: This will get alot slower if offset is used
* Note: requires utf8_strlen amd utf8_substr to be loaded
* @param string haystack
* @param string needle (you should validate this with utf8_is_valid)
* @param integer offset in characters (from left)
* @return mixed integer position or FALSE on failure
* @see http://www.php.net/strpos
* @see utf8_strlen
* @see utf8_substr
* @package utf8
* @subpackage strings
*/
function utf8_strpos($str, $needle, $offset = NULL) {
if ( is_null($offset) ) {
$ar = explode($needle, $str, 2);
if ( count($ar) > 1 ) {
return utf8_strlen($ar[0]);
}
return FALSE;
} else {
if ( !is_int($offset) ) {
trigger_error('utf8_strpos: Offset must be an integer',E_USER_ERROR);
return FALSE;
}
$str = utf8_substr($str, $offset);
if ( FALSE !== ( $pos = utf8_strpos($str, $needle) ) ) {
return $pos + $offset;
}
return FALSE;
}
}
//--------------------------------------------------------------------
/**
* UTF-8 aware alternative to strrpos
* Find position of last occurrence of a char in a string
* Note: This will get alot slower if offset is used
* Note: requires utf8_substr and utf8_strlen to be loaded
* @param string haystack
* @param string needle (you should validate this with utf8_is_valid)
* @param integer (optional) offset (from left)
* @return mixed integer position or FALSE on failure
* @see http://www.php.net/strrpos
* @see utf8_substr
* @see utf8_strlen
* @package utf8
* @subpackage strings
*/
function utf8_strrpos($str, $needle, $offset = NULL) {
if ( is_null($offset) ) {
$ar = explode($needle, $str);
if ( count($ar) > 1 ) {
// Pop off the end of the string where the last match was made
array_pop($ar);
$str = join($needle,$ar);
return utf8_strlen($str);
}
return FALSE;
} else {
if ( !is_int($offset) ) {
trigger_error('utf8_strrpos expects parameter 3 to be long',E_USER_WARNING);
return FALSE;
}
$str = utf8_substr($str, $offset);
if ( FALSE !== ( $pos = utf8_strrpos($str, $needle) ) ) {
return $pos + $offset;
}
return FALSE;
}
}
//--------------------------------------------------------------------
/**
* UTF-8 aware alternative to substr
* Return part of a string given character offset (and optionally length)
*
* Note arguments: comparied to substr - if offset or length are
* not integers, this version will not complain but rather massages them
* into an integer.
*
* Note on returned values: substr documentation states false can be
* returned in some cases (e.g. offset > string length)
* mb_substr never returns false, it will return an empty string instead.
* This adopts the mb_substr approach
*
* Note on implementation: PCRE only supports repetitions of less than
* 65536, in order to accept up to MAXINT values for offset and length,
* we'll repeat a group of 65535 characters when needed.
*
* Note on implementation: calculating the number of characters in the
* string is a relatively expensive operation, so we only carry it out when
* necessary. It isn't necessary for +ve offsets and no specified length
*
* @author Chris Smith<chris@jalakai.co.uk>
* @param string
* @param integer number of UTF-8 characters offset (from left)
* @param integer (optional) length in UTF-8 characters from offset
* @return mixed string or FALSE if failure
* @package utf8
* @subpackage strings
*/
function utf8_substr($str, $offset, $length = NULL) {
// generates E_NOTICE
// for PHP4 objects, but not PHP5 objects
$str = (string)$str;
$offset = (int)$offset;
if (!is_null($length)) $length = (int)$length;
// handle trivial cases
if ($length === 0) return '';
if ($offset < 0 && $length < 0 && $length < $offset)
return '';
// normalise negative offsets (we could use a tail
// anchored pattern, but they are horribly slow!)
if ($offset < 0) {
// see notes
$strlen = strlen(utf8_decode($str));
$offset = $strlen + $offset;
if ($offset < 0) $offset = 0;
}
$Op = '';
$Lp = '';
// establish a pattern for offset, a
// non-captured group equal in length to offset
if ($offset > 0) {
$Ox = (int)($offset/65535);
$Oy = $offset%65535;
if ($Ox) {
$Op = '(?:.{65535}){'.$Ox.'}';
}
$Op = '^(?:'.$Op.'.{'.$Oy.'})';
} else {
// offset == 0; just anchor the pattern
$Op = '^';
}
// establish a pattern for length
if (is_null($length)) {
// the rest of the string
$Lp = '(.*)$';
} else {
if (!isset($strlen)) {
// see notes
$strlen = strlen(utf8_decode($str));
}
// another trivial case
if ($offset > $strlen) return '';
if ($length > 0) {
// reduce any length that would
// go passed the end of the string
$length = min($strlen-$offset, $length);
$Lx = (int)( $length / 65535 );
$Ly = $length % 65535;
// negative length requires a captured group
// of length characters
if ($Lx) $Lp = '(?:.{65535}){'.$Lx.'}';
$Lp = '('.$Lp.'.{'.$Ly.'})';
} else if ($length < 0) {
if ( $length < ($offset - $strlen) ) {
return '';
}
$Lx = (int)((-$length)/65535);
$Ly = (-$length)%65535;
// negative length requires ... capture everything
// except a group of -length characters
// anchored at the tail-end of the string
if ($Lx) $Lp = '(?:.{65535}){'.$Lx.'}';
$Lp = '(.*)(?:'.$Lp.'.{'.$Ly.'})$';
}
}
if (!preg_match( '#'.$Op.$Lp.'#us',$str, $match )) {
return '';
}
return $match[1];
}
//---------------------------------------------------------------
/**
* UTF-8 aware alternative to strtolower
* Make a string lowercase
* Note: The concept of a characters "case" only exists is some alphabets
* such as Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does
* not exist in the Chinese alphabet, for example. See Unicode Standard
* Annex #21: Case Mappings
* Note: requires utf8_to_unicode and utf8_from_unicode
* @author Andreas Gohr <andi@splitbrain.org>
* @param string
* @return mixed either string in lowercase or FALSE is UTF-8 invalid
* @see http://www.php.net/strtolower
* @see utf8_to_unicode
* @see utf8_from_unicode
* @see http://www.unicode.org/reports/tr21/tr21-5.html
* @see http://dev.splitbrain.org/view/darcs/dokuwiki/inc/utf8.php
* @package utf8
* @subpackage strings
*/
function utf8_strtolower($string){
static $UTF8_UPPER_TO_LOWER = NULL;
if ( is_null($UTF8_UPPER_TO_LOWER) ) {
$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,
);
}
$uni = utf8_to_unicode($string);
if ( !$uni ) {
return FALSE;
}
$cnt = count($uni);
for ($i=0; $i < $cnt; $i++){
if ( isset($UTF8_UPPER_TO_LOWER[$uni[$i]]) ) {
$uni[$i] = $UTF8_UPPER_TO_LOWER[$uni[$i]];
}
}
return utf8_from_unicode($uni);
}
//---------------------------------------------------------------
/**
* UTF-8 aware alternative to strtoupper
* Make a string uppercase
* Note: The concept of a characters "case" only exists is some alphabets
* such as Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does
* not exist in the Chinese alphabet, for example. See Unicode Standard
* Annex #21: Case Mappings
* Note: requires utf8_to_unicode and utf8_from_unicode
* @author Andreas Gohr <andi@splitbrain.org>
* @param string
* @return mixed either string in lowercase or FALSE is UTF-8 invalid
* @see http://www.php.net/strtoupper
* @see utf8_to_unicode
* @see utf8_from_unicode
* @see http://www.unicode.org/reports/tr21/tr21-5.html
* @see http://dev.splitbrain.org/view/darcs/dokuwiki/inc/utf8.php
* @package utf8
* @subpackage strings
*/
function utf8_strtoupper($string){
static $UTF8_LOWER_TO_UPPER = NULL;
if ( is_null($UTF8_LOWER_TO_UPPER) ) {
$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,
);
}
$uni = utf8_to_unicode($string);
if ( !$uni ) {
return FALSE;
}
$cnt = count($uni);
for ($i=0; $i < $cnt; $i++){
if( isset($UTF8_LOWER_TO_UPPER[$uni[$i]]) ) {
$uni[$i] = $UTF8_LOWER_TO_UPPER[$uni[$i]];
}
}
return utf8_from_unicode($uni);
}

269
e107_handlers/utf8/utils/unicode.php
View File

@@ -1,269 +0,0 @@
<?php
/**
* @version $Id$
* Tools for conversion between UTF-8 and unicode
* 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. All Rights Reserved.
* Ported to PHP by Henri Sivonen (http://hsivonen.iki.fi)
* Slight modifications to fit with phputf8 library by Harry Fuecks (hfuecks gmail com)
* @see http://lxr.mozilla.org/seamonkey/source/intl/uconv/src/nsUTF8ToUnicode.cpp
* @see http://lxr.mozilla.org/seamonkey/source/intl/uconv/src/nsUnicodeToUTF8.cpp
* @see http://hsivonen.iki.fi/php-utf8/
* @package utf8
* @subpackage unicode
*/
//--------------------------------------------------------------------
/**
* Takes an UTF-8 string and returns an array of ints representing the
* Unicode characters. Astral planes are supported ie. the ints in the
* output can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
* are not allowed.
* Returns false if the input string isn't a valid UTF-8 octet sequence
* and raises a PHP error at level E_USER_WARNING
* Note: this function has been modified slightly in this library to
* trigger errors on encountering bad bytes
* @author <hsivonen@iki.fi>
* @param string UTF-8 encoded string
* @return mixed array of unicode code points or FALSE if UTF-8 invalid
* @see utf8_from_unicode
* @see http://hsivonen.iki.fi/php-utf8/
* @package utf8
* @subpackage unicode
*/
function utf8_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;
$mBytes = 1;
} else if (0xC0 == (0xE0 & ($in))) {
// First octet of 2 octet sequence
$mUcs4 = ($in);
$mUcs4 = ($mUcs4 & 0x1F) << 6;
$mState = 1;
$mBytes = 2;
} else if (0xE0 == (0xF0 & ($in))) {
// First octet of 3 octet sequence
$mUcs4 = ($in);
$mUcs4 = ($mUcs4 & 0x0F) << 12;
$mState = 2;
$mBytes = 3;
} else if (0xF0 == (0xF8 & ($in))) {
// First octet of 4 octet sequence
$mUcs4 = ($in);
$mUcs4 = ($mUcs4 & 0x07) << 18;
$mState = 3;
$mBytes = 4;
} else if (0xF8 == (0xFC & ($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;
$mBytes = 5;
} else if (0xFC == (0xFE & ($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 == $mBytes) && ($mUcs4 < 0x0080)) ||
((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
((4 == $mBytes) && ($mUcs4 < 0x10000)) ||
(4 < $mBytes) ||
// From Unicode 3.2, surrogate characters are illegal
(($mUcs4 & 0xFFFFF800) == 0xD800) ||
// 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 UTF8 cache
$mState = 0;
$mUcs4 = 0;
$mBytes = 1;
}
} else {
/**
*((0xC0 & (*in) != 0x80) && (mState != 0))
* Incomplete multi-octet sequence.
*/
trigger_error(
'utf8_to_unicode: Incomplete multi-octet '.
' sequence in UTF-8 at byte '.$i,
E_USER_WARNING
);
return FALSE;
}
}
}
return $out;
}
//--------------------------------------------------------------------
/**
* Takes an array of ints representing the Unicode characters and returns
* a UTF-8 string. Astral planes are supported ie. the ints in the
* input can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
* are not allowed.
* Returns false if the input array contains ints that represent
* surrogates or are outside the Unicode range
* and raises a PHP error at level E_USER_WARNING
* Note: this function has been modified slightly in this library to use
* output buffering to concatenate the UTF-8 string (faster) as well as
* reference the array by it's keys
* @param array of unicode code points representing a string
* @return mixed UTF-8 string or FALSE if array contains invalid code points
* @author <hsivonen@iki.fi>
* @see utf8_to_unicode
* @see http://hsivonen.iki.fi/php-utf8/
* @package utf8
* @subpackage unicode
*/
function utf8_from_unicode($arr) {
ob_start();
foreach (array_keys($arr) as $k) {
# ASCII range (including control chars)
if ( ($arr[$k] >= 0) && ($arr[$k] <= 0x007f) ) {
echo chr($arr[$k]);
# 2 byte sequence
} else if ($arr[$k] <= 0x07ff) {
echo chr(0xc0 | ($arr[$k] >> 6));
echo chr(0x80 | ($arr[$k] & 0x003f));
# Byte order mark (skip)
} else if($arr[$k] == 0xFEFF) {
// nop -- zap the BOM
# Test for illegal surrogates
} else if ($arr[$k] >= 0xD800 && $arr[$k] <= 0xDFFF) {
// found a surrogate
trigger_error(
'utf8_from_unicode: Illegal surrogate '.
'at index: '.$k.', value: '.$arr[$k],
E_USER_WARNING
);
return FALSE;
# 3 byte sequence
} else if ($arr[$k] <= 0xffff) {
echo chr(0xe0 | ($arr[$k] >> 12));
echo chr(0x80 | (($arr[$k] >> 6) & 0x003f));
echo chr(0x80 | ($arr[$k] & 0x003f));
# 4 byte sequence
} else if ($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[$k] & 0x3f));
} else {
trigger_error(
'utf8_from_unicode: Codepoint out of Unicode range '.
'at index: '.$k.', value: '.$arr[$k],
E_USER_WARNING
);
// out of range
return FALSE;
}
}
$result = ob_get_contents();
ob_end_clean();
return $result;
}

58
install.php
View File

@@ -328,17 +328,17 @@ function cookie($name, $value, $expire=0, $path = e_HTTP, $domain = '', $secure
class e_install
{
var $paths;
var $template;
var $debug_info;
var $debug_db_info;
var $e107;
var $previous_steps;
var $stage;
var $post_data;
var $required = array();
var $dbLink = NULL; // DB link - needed for PHP5.3 bug
var $session = null;
// private $paths;
public $template;
private $debug_info;
// private $debug_db_info;
private $e107;
public $previous_steps;
private $stage;
private $post_data;
private $required = array();
private $session;
protected $pdo = false;
protected $debug = false;
@@ -699,7 +699,7 @@ class e_install
$this->previous_steps['mysql']['user'] = trim($tp->filter($_POST['name']));
$this->previous_steps['mysql']['password'] = trim($tp->filter($_POST['password']));
$this->previous_steps['mysql']['db'] = trim($tp->filter($_POST['db']));
$this->previous_steps['mysql']['createdb'] = (isset($_POST['createdb']) && $_POST['createdb'] == true ? true : false);
$this->previous_steps['mysql']['createdb'] = isset($_POST['createdb']) && $_POST['createdb'] == true;
$this->previous_steps['mysql']['prefix'] = trim($tp->filter($_POST['prefix']));
$this->setDb();
@@ -710,7 +710,7 @@ class e_install
$this->previous_steps['mysql']['overwritedb'] = 1;
}
$success = $this->check_name($this->previous_steps['mysql']['db'], FALSE) && $this->check_name($this->previous_steps['mysql']['prefix'], TRUE);
$success = $this->check_name($this->previous_steps['mysql']['db']) && $this->check_name($this->previous_steps['mysql']['prefix'], TRUE);
if ($success)
{
@@ -903,7 +903,7 @@ class e_install
$this->template->SetTag("stage_title", LANINS_008);
$this->template->SetTag("percent", 50);
$this->template->SetTag("bartype", 'warning');
$not_writable = $this->check_writable_perms('must_write'); // Some directories MUST be writable
$not_writable = $this->check_writable_perms(); // Some directories MUST be writable
$opt_writable = $this->check_writable_perms('can_write'); // Some directories CAN optionally be writable
$version_fail = false;
$perms_errors = "";
@@ -1654,8 +1654,8 @@ if($this->pdo == true)
{
global $e_forms;
$data = array('name'=>$this->previous_steps['prefs']['sitename'], 'theme'=>$this->previous_steps['prefs']['sitetheme'], 'language'=>$this->previous_steps['language'], 'url'=>$_SERVER['HTTP_REFERER']);;
$base = base64_encode(http_build_query($data, null, '&'));
$data = array('name'=>$this->previous_steps['prefs']['sitename'], 'theme'=>$this->previous_steps['prefs']['sitetheme'], 'language'=>$this->previous_steps['language'], 'url'=>$_SERVER['HTTP_REFERER']);
$base = base64_encode(http_build_query($data, null));
$url = "https://e107.org/e-install/".$base;
$e_forms->add_plain_html("<img src='".$url."' style='width:1px; height:1px' />");
@@ -1812,8 +1812,8 @@ if($this->pdo == true)
// Admin log fix - don't allow logs to be called inside pref handler
// FIX
e107::getConfig('core')->setParam('nologs', true); // change to false to enable log
$pref = e107::getConfig('core')->getPref();
e107::getConfig()->setParam('nologs', true); // change to false to enable log
$pref = e107::getConfig()->getPref();
// Set Preferences defined during install - overwriting those that may exist in the XML.
@@ -1837,7 +1837,7 @@ if($this->pdo == true)
### URL related prefs
// set all prefs so that they are available, required for adminReadModules() - it checks which plugins are installed
e107::getConfig('core')->setPref($this->previous_steps['prefs']);
e107::getConfig()->setPref($this->previous_steps['prefs']);
$url_modules = eRouter::adminReadModules();
$url_locations = eRouter::adminBuildLocations($url_modules);
@@ -1863,8 +1863,8 @@ if($this->pdo == true)
}
// Set prefs, save
e107::getConfig('core')->setPref($this->previous_steps['prefs']);
e107::getConfig('core')->save(FALSE,TRUE, FALSE); // save preferences made during install.
e107::getConfig()->setPref($this->previous_steps['prefs']);
e107::getConfig()->save(FALSE,TRUE, FALSE); // save preferences made during install.
installLog::add('Core prefs set to install choices');
// Create the admin user - replacing any that may be been included in the XML.
@@ -2127,7 +2127,7 @@ if($this->pdo == true)
installLog::add("DB Connection made");
$this->dbLink = $link; // Needed for mysql_close() to work round bug in PHP 5.3
// $dbLink = $link; // Needed for mysql_close() to work round bug in PHP 5.3
// $db_selected = mysql_select_db($this->previous_steps['mysql']['db'], $link);
$db_selected = $sql->database($this->previous_steps['mysql']['db'],$this->previous_steps['mysql']['prefix']);
if(!$db_selected)
@@ -2242,8 +2242,8 @@ if($this->pdo == true)
class e_forms
{
var $form;
var $opened;
public $form;
private $opened;
function start_form($id, $action, $method = "post" )
{
@@ -2353,9 +2353,9 @@ function create_tables_unattended()
class SimpleTemplate
{
var $Tags = array();
var $open_tag = "{";
var $close_tag = "}";
private $Tags = array();
private $open_tag = "{";
private $close_tag = "}";
function __construct()
{
@@ -2402,7 +2402,7 @@ class SimpleTemplate
function template_data()
{
$data = '<!DOCTYPE html>
return '<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
@@ -2519,7 +2519,7 @@ function template_data()
</body>
</html>
';
return $data;
}
/**