drupal/includes/common.inc

1912 lines
60 KiB
PHP
Raw Normal View History

<?php
/* $Id$ */
/**
* @file
* Common functions that many Drupal modules will need to reference.
*
* The functions that are critical and need to be available even when serving
* a cached page are instead located in bootstrap.inc.
*/
/**
* Set the breadcrumb trail for the current page.
*
* @param $breadcrumb
* Array of links, starting with "home" and proceeding up to but not including
* the current page.
2004-01-06 19:52:14 +00:00
*/
function drupal_set_breadcrumb($breadcrumb = NULL) {
static $stored_breadcrumb;
if (isset($breadcrumb)) {
$stored_breadcrumb = $breadcrumb;
}
return $stored_breadcrumb;
}
/**
* Get the breadcrumb trail for the current page.
*/
function drupal_get_breadcrumb() {
$breadcrumb = drupal_set_breadcrumb();
if (!isset($breadcrumb)) {
$breadcrumb = menu_get_active_breadcrumb();
}
return $breadcrumb;
}
/**
* Add output to the head tag of the HTML page.
* This function can be called as long the headers aren't sent.
*/
function drupal_set_html_head($data = NULL) {
static $stored_head = '';
if (!is_null($data)) {
$stored_head .= $data ."\n";
}
return $stored_head;
}
/**
* Retrieve output to be displayed in the head tag of the HTML page.
*/
function drupal_get_html_head() {
global $base_url;
$output = "<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n";
$output .= "<base href=\"$base_url/\" />\n";
$output .= theme('stylesheet_import', 'misc/drupal.css');
return $output . drupal_set_html_head();
}
/**
* Regenerate the path map from the information in the database.
*/
function drupal_rebuild_path_map() {
drupal_get_path_map('rebuild');
}
2004-01-06 19:52:14 +00:00
/**
* Given a path alias, return the internal path it represents.
*/
function drupal_get_normal_path($path) {
if (($map = drupal_get_path_map()) && isset($map[$path])) {
return $map[$path];
}
elseif (function_exists('conf_url_rewrite')) {
return conf_url_rewrite($path, 'incoming');
}
else {
return $path;
}
}
2004-01-06 19:52:14 +00:00
/**
* Set an HTTP response header for the current page.
*/
function drupal_set_header($header = NULL) {
// We use an array to guarantee there are no leading or trailing delimiters.
// Otherwise, header('') could get called when serving the page later, which
// ends HTTP headers prematurely on some PHP versions.
static $stored_headers = array();
if (strlen($header)) {
header($header);
$stored_headers[] = $header;
}
return implode("\n", $stored_headers);
}
/**
* Get the HTTP response headers for the current page.
*/
function drupal_get_headers() {
return drupal_set_header();
}
/**
* @name HTTP handling
* @{
* Functions to properly handle HTTP responses.
*/
/**
* Prepare a destination query string for use in combination with
* drupal_goto(). Used to direct the user back to the referring page
* after completing a form.
*
* @see drupal_goto()
*/
function drupal_get_destination() {
$destination[] = $_GET['q'];
$params = array('from', 'sort', 'order');
foreach ($params as $param) {
if (isset($_GET[$param])) {
$destination[] = "$param=". $_GET[$param];
}
}
return 'destination='. urlencode(implode('&', $destination));
}
2004-01-06 19:52:14 +00:00
/**
* Send the user to a different Drupal page.
2004-01-06 19:52:14 +00:00
*
* This issues an on-site HTTP redirect. The function makes sure the redirected
* URL is formatted correctly.
2004-01-06 19:52:14 +00:00
*
* Usually the redirected URL is constructed from this function's input
* parameters. However you may override that behavior by setting a
* <em>destination</em> in either the $_REQUEST-array (i.e. by using
* the query string of an URI) or the $_REQUEST['edit']-array (i.e. by
* using a hidden form field). This is used to direct the user back to
* the proper page after completing a form. For example, after editing
* a post on the 'admin/node'-page or after having logged on using the
* 'user login'-block in a sidebar. The function drupal_get_destination()
* can be used to help set the destination URL.
*
* It is advised to use drupal_goto() instead of PHP's header(), because
* drupal_goto() will append the user's session ID to the URI when PHP is
* compiled with "--enable-trans-sid".
*
* This function ends the request; use it rather than a print theme('page')
* statement in your menu callback.
*
* @param $path
* A Drupal path.
* @param $query
* The query string component, if any.
* @param $fragment
* The destination fragment identifier (named anchor).
*
* @see drupal_get_destination()
2004-01-06 19:52:14 +00:00
*/
function drupal_goto($path = '', $query = NULL, $fragment = NULL) {
if ($_REQUEST['destination']) {
extract(parse_url($_REQUEST['destination']));
}
else if ($_REQUEST['edit']['destination']) {
extract(parse_url($_REQUEST['edit']['destination']));
}
// Translate &amp; to simply & in the absolute URL.
$url = str_replace('&amp;', '&', url($path, $query, $fragment, TRUE));
2004-01-06 19:52:14 +00:00
if (ini_get('session.use_trans_sid') && session_id() && !strstr($url, session_id())) {
$sid = session_name() . '=' . session_id();
if (strstr($url, '?') && !strstr($url, $sid)) {
$url = $url .'&'. $sid;
2004-01-06 19:52:14 +00:00
}
else {
$url = $url .'?'. $sid;
2004-01-06 19:52:14 +00:00
}
}
// Before the redirect, allow modules to react to the end of the page request.
module_invoke_all('exit', $url);
header('Location: '. $url);
2004-01-06 19:52:14 +00:00
// The "Location" header sends a REDIRECT status code to the http
// daemon. In some cases this can go wrong, so we make sure none
// of the code below the drupal_goto() call gets executed when we redirect.
2004-01-06 19:52:14 +00:00
exit();
}
/**
* Generates a 404 error if the request can not be handled.
*/
function drupal_not_found() {
header('HTTP/1.0 404 Not Found');
watchdog('page not found', t('%page not found.', array('%page' => '<em>'. db_escape_string($_GET['q']) .'</em>')), WATCHDOG_WARNING);
$path = drupal_get_normal_path(variable_get('site_404', ''));
$status = MENU_NOT_FOUND;
if ($path) {
menu_set_active_item($path);
$status = menu_execute_active_handler();
}
if ($status != MENU_FOUND) {
drupal_set_title(t('Page not found'));
print theme('page', '');
}
}
/**
* Generates a 403 error if the request is not allowed.
*/
function drupal_access_denied() {
header('HTTP/1.0 403 Forbidden');
watchdog('access denied', t('%page denied access.', array('%page' => '<em>'. db_escape_string($_GET['q']) .'</em>')), WATCHDOG_WARNING, l(t('view'), $_GET['q']));
$path = drupal_get_normal_path(variable_get('site_403', ''));
$status = MENU_NOT_FOUND;
if ($path) {
menu_set_active_item($path);
$status = menu_execute_active_handler();
}
if ($status != MENU_FOUND) {
drupal_set_title(t('Access denied'));
print theme('page', message_access());
}
}
/**
* Perform an HTTP request.
*
* This is a flexible and powerful HTTP client implementation. Correctly handles
* GET, POST, PUT or any other HTTP requests. Handles redirects.
*
* @param $url
* A string containing a fully qualified URI.
* @param $headers
* An array containing an HTTP header => value pair.
* @param $method
* A string defining the HTTP request to use.
* @param $data
* A string containing data to include in the request.
* @param $retry
* An integer representing how many times to retry the request in case of a
* redirect.
* @return
* An object containing the HTTP request headers, response code, headers,
* data, and redirect status.
*/
function drupal_http_request($url, $headers = array(), $method = 'GET', $data = NULL, $retry = 3) {
$result = new StdClass();
// Parse the URL, and make sure we can handle the schema.
$uri = parse_url($url);
switch ($uri['scheme']) {
case 'http':
$fp = @fsockopen($uri['host'], ($uri['port'] ? $uri['port'] : 80), $errno, $errstr, 15);
break;
case 'https':
// Note: Only works for PHP 4.3 compiled with OpenSSL.
$fp = @fsockopen('ssl://'. $uri['host'], ($uri['port'] ? $uri['port'] : 443), $errno, $errstr, 20);
break;
default:
$result->error = 'invalid schema '. $uri['scheme'];
return $result;
}
// Make sure the socket opened properly.
if (!$fp) {
$result->error = trim($errno .' '. $errstr);
return $result;
}
// Construct the path to act on.
$path = $uri['path'] ? $uri['path'] : '/';
if ($uri['query']) {
$path .= '?'. $uri['query'];
}
// Create HTTP request.
$defaults = array(
'Host' => 'Host: '. $uri['host'],
'User-Agent' => 'User-Agent: Drupal (+http://www.drupal.org/)',
'Content-Length' => 'Content-Length: '. strlen($data)
);
foreach ($headers as $header => $value) {
$defaults[$header] = $header .': '. $value;
}
$request = $method .' '. $path ." HTTP/1.0\r\n";
$request .= implode("\r\n", $defaults);
$request .= "\r\n\r\n";
if ($data) {
$request .= $data ."\r\n";
}
$result->request = $request;
fwrite($fp, $request);
// Fetch response.
$response = '';
while (!feof($fp) && $data = fread($fp, 1024)) {
$response .= $data;
}
fclose($fp);
// Parse response.
list($headers, $result->data) = explode("\r\n\r\n", $response, 2);
$headers = preg_split("/\r\n|\n|\r/", $headers);
list($protocol, $code, $text) = explode(' ', trim(array_shift($headers)), 3);
$result->headers = array();
// Parse headers.
while ($line = trim(array_shift($headers))) {
list($header, $value) = explode(':', $line, 2);
$result->headers[$header] = trim($value);
}
$responses = array(
100 => 'Continue', 101 => 'Switching Protocols',
200 => 'OK', 201 => 'Created', 202 => 'Accepted', 203 => 'Non-Authoritative Information', 204 => 'No Content', 205 => 'Reset Content', 206 => 'Partial Content',
300 => 'Multiple Choices', 301 => 'Moved Permanently', 302 => 'Found', 303 => 'See Other', 304 => 'Not Modified', 305 => 'Use Proxy', 307 => 'Temporary Redirect',
400 => 'Bad Request', 401 => 'Unauthorized', 402 => 'Payment Required', 403 => 'Forbidden', 404 => 'Not Found', 405 => 'Method Not Allowed', 406 => 'Not Acceptable', 407 => 'Proxy Authentication Required', 408 => 'Request Time-out', 409 => 'Conflict', 410 => 'Gone', 411 => 'Length Required', 412 => 'Precondition Failed', 413 => 'Request Entity Too Large', 414 => 'Request-URI Too Large', 415 => 'Unsupported Media Type', 416 => 'Requested range not satisfiable', 417 => 'Expectation Failed',
500 => 'Internal Server Error', 501 => 'Not Implemented', 502 => 'Bad Gateway', 503 => 'Service Unavailable', 504 => 'Gateway Time-out', 505 => 'HTTP Version not supported'
);
// RFC 2616 states that all unknown HTTP codes must be treated the same as
// the base code in their class.
if (!isset($responses[$code])) {
$code = floor($code / 100) * 100;
}
switch ($code) {
case 200: // OK
case 304: // Not modified
break;
case 301: // Moved permanently
case 302: // Moved temporarily
case 307: // Moved temporarily
$location = $result->headers['Location'];
if ($retry) {
$result = drupal_http_request($result->headers['Location'], $headers, $method, $data, --$retry);
$result->redirect_code = $result->code;
}
$result->redirect_url = $location;
break;
default:
$result->error = $text;
}
$result->code = $code;
return $result;
}
/**
* @} End of "HTTP handling".
*/
/**
* Log errors as defined by administrator
* Error levels:
* 1 = Log errors to database.
* 2 = Log errors to database and to screen.
*/
function error_handler($errno, $message, $filename, $line, $variables) {
if ($errno & (E_ALL ^ E_NOTICE)) {
$types = array(1 => 'error', 2 => 'warning', 4 => 'parse error', 8 => 'notice', 16 => 'core error', 32 => 'core warning', 64 => 'compile error', 128 => 'compile warning', 256 => 'user error', 512 => 'user warning', 1024 => 'user notice', 2048 => 'strict warning');
$entry = $types[$errno] .': '. $message .' in '. $filename .' on line '. $line .'.';
if (variable_get('error_level', 1) == 1) {
print '<pre>'. $entry .'</pre>';
}
watchdog('php', t('%message in %file on line %line.', array('%error' => $types[$errno], '%message' => $message, '%file' => $filename, '%line' => $line)), WATCHDOG_ERROR);
}
}
function _fix_gpc_magic(&$item, $key) {
if (is_array($item)) {
2003-12-19 10:52:37 +00:00
array_walk($item, '_fix_gpc_magic');
}
else {
2003-12-19 13:44:08 +00:00
$item = stripslashes($item);
}
}
/**
* Correct double-escaping problems caused by "magic quotes" in some PHP
* installations.
*/
function fix_gpc_magic() {
static $fixed = false;
if (!$fixed && ini_get('magic_quotes_gpc')) {
array_walk($_GET, '_fix_gpc_magic');
array_walk($_POST, '_fix_gpc_magic');
array_walk($_COOKIE, '_fix_gpc_magic');
array_walk($_REQUEST, '_fix_gpc_magic');
$fixed = true;
}
}
2004-01-06 19:52:14 +00:00
/**
* @name Conversion
* @{
* Converts data structures to different types.
2004-01-06 19:52:14 +00:00
*/
/**
* Convert an associative array to an anonymous object.
*/
function array2object($array) {
if (is_array($array)) {
$object = new StdClass();
foreach ($array as $key => $value) {
- import.module: + Improved input filtering; this should make the news items look more consistent in terms of mark-up. + Quoted all array indices: converted all instances of $foo[bar] to $foo["bar"]. Made various other changes to make the import module compliant with the coding style. - theme.inc: + Fixed small XHTML glitch - comment system: + Made it possible for users to edit their comments (when certain criteria are matched). + Renamed the SQL table field "lid" to "nid" and updated the code to reflect this change: this is a rather /annoying/ change that has been asked for a few times. It will impact the contributed BBS/forum modules and requires a tiny SQL update: sql> ALTER TABLE comments CHANGE lid nid int(10) NOT NULL; + Moved most (all?) of the comment related logic from node.php to comment.module where it belongs. This also marks a first step towards removing/reducing "node.php". + Added a delete button to the comment admin form and made it so that Drupal prompts for confirmation prior to deleting a comment from the database. This behavior is similar to that of deleting nodes. + Disabled comment moderation for now. + Some of the above changes will make it easier to integrate the upcomcing mail-to-web and web-to-mail gateways. They are part of a bigger plan. ;) - node system: + Made it so that updating nodes (like for instance updating blog entries) won't trigger the submission rate throttle. + Fixed a small glitch where a node's title wasn't always passed to the $theme->header() function. + Made "node_array()" and "node_object()" more generic and named them "object2array()" and "array2object()". + Moved most (all?) of the comment related logic from node.php to comment.module where it belongs. This also marks a first step towards removing/reducing "node.php". - misc: + Applied three patches by Foxen. One to improve performance of the book module, and two other patches to fix small glitches in common.inc. Thanks Foxen!
2001-12-30 16:16:38 +00:00
$object->$key = $value;
}
}
else {
$object = $array;
- import.module: + Improved input filtering; this should make the news items look more consistent in terms of mark-up. + Quoted all array indices: converted all instances of $foo[bar] to $foo["bar"]. Made various other changes to make the import module compliant with the coding style. - theme.inc: + Fixed small XHTML glitch - comment system: + Made it possible for users to edit their comments (when certain criteria are matched). + Renamed the SQL table field "lid" to "nid" and updated the code to reflect this change: this is a rather /annoying/ change that has been asked for a few times. It will impact the contributed BBS/forum modules and requires a tiny SQL update: sql> ALTER TABLE comments CHANGE lid nid int(10) NOT NULL; + Moved most (all?) of the comment related logic from node.php to comment.module where it belongs. This also marks a first step towards removing/reducing "node.php". + Added a delete button to the comment admin form and made it so that Drupal prompts for confirmation prior to deleting a comment from the database. This behavior is similar to that of deleting nodes. + Disabled comment moderation for now. + Some of the above changes will make it easier to integrate the upcomcing mail-to-web and web-to-mail gateways. They are part of a bigger plan. ;) - node system: + Made it so that updating nodes (like for instance updating blog entries) won't trigger the submission rate throttle. + Fixed a small glitch where a node's title wasn't always passed to the $theme->header() function. + Made "node_array()" and "node_object()" more generic and named them "object2array()" and "array2object()". + Moved most (all?) of the comment related logic from node.php to comment.module where it belongs. This also marks a first step towards removing/reducing "node.php". - misc: + Applied three patches by Foxen. One to improve performance of the book module, and two other patches to fix small glitches in common.inc. Thanks Foxen!
2001-12-30 16:16:38 +00:00
}
return $object;
}
/**
* Convert an object to an associative array.
*/
function object2array($object) {
if (is_object($object)) {
foreach ($object as $key => $value) {
- import.module: + Improved input filtering; this should make the news items look more consistent in terms of mark-up. + Quoted all array indices: converted all instances of $foo[bar] to $foo["bar"]. Made various other changes to make the import module compliant with the coding style. - theme.inc: + Fixed small XHTML glitch - comment system: + Made it possible for users to edit their comments (when certain criteria are matched). + Renamed the SQL table field "lid" to "nid" and updated the code to reflect this change: this is a rather /annoying/ change that has been asked for a few times. It will impact the contributed BBS/forum modules and requires a tiny SQL update: sql> ALTER TABLE comments CHANGE lid nid int(10) NOT NULL; + Moved most (all?) of the comment related logic from node.php to comment.module where it belongs. This also marks a first step towards removing/reducing "node.php". + Added a delete button to the comment admin form and made it so that Drupal prompts for confirmation prior to deleting a comment from the database. This behavior is similar to that of deleting nodes. + Disabled comment moderation for now. + Some of the above changes will make it easier to integrate the upcomcing mail-to-web and web-to-mail gateways. They are part of a bigger plan. ;) - node system: + Made it so that updating nodes (like for instance updating blog entries) won't trigger the submission rate throttle. + Fixed a small glitch where a node's title wasn't always passed to the $theme->header() function. + Made "node_array()" and "node_object()" more generic and named them "object2array()" and "array2object()". + Moved most (all?) of the comment related logic from node.php to comment.module where it belongs. This also marks a first step towards removing/reducing "node.php". - misc: + Applied three patches by Foxen. One to improve performance of the book module, and two other patches to fix small glitches in common.inc. Thanks Foxen!
2001-12-30 16:16:38 +00:00
$array[$key] = $value;
}
}
else {
$array = $object;
- import.module: + Improved input filtering; this should make the news items look more consistent in terms of mark-up. + Quoted all array indices: converted all instances of $foo[bar] to $foo["bar"]. Made various other changes to make the import module compliant with the coding style. - theme.inc: + Fixed small XHTML glitch - comment system: + Made it possible for users to edit their comments (when certain criteria are matched). + Renamed the SQL table field "lid" to "nid" and updated the code to reflect this change: this is a rather /annoying/ change that has been asked for a few times. It will impact the contributed BBS/forum modules and requires a tiny SQL update: sql> ALTER TABLE comments CHANGE lid nid int(10) NOT NULL; + Moved most (all?) of the comment related logic from node.php to comment.module where it belongs. This also marks a first step towards removing/reducing "node.php". + Added a delete button to the comment admin form and made it so that Drupal prompts for confirmation prior to deleting a comment from the database. This behavior is similar to that of deleting nodes. + Disabled comment moderation for now. + Some of the above changes will make it easier to integrate the upcomcing mail-to-web and web-to-mail gateways. They are part of a bigger plan. ;) - node system: + Made it so that updating nodes (like for instance updating blog entries) won't trigger the submission rate throttle. + Fixed a small glitch where a node's title wasn't always passed to the $theme->header() function. + Made "node_array()" and "node_object()" more generic and named them "object2array()" and "array2object()". + Moved most (all?) of the comment related logic from node.php to comment.module where it belongs. This also marks a first step towards removing/reducing "node.php". - misc: + Applied three patches by Foxen. One to improve performance of the book module, and two other patches to fix small glitches in common.inc. Thanks Foxen!
2001-12-30 16:16:38 +00:00
}
return $array;
}
/**
* @} End of "Conversion".
*/
- import.module: + Improved input filtering; this should make the news items look more consistent in terms of mark-up. + Quoted all array indices: converted all instances of $foo[bar] to $foo["bar"]. Made various other changes to make the import module compliant with the coding style. - theme.inc: + Fixed small XHTML glitch - comment system: + Made it possible for users to edit their comments (when certain criteria are matched). + Renamed the SQL table field "lid" to "nid" and updated the code to reflect this change: this is a rather /annoying/ change that has been asked for a few times. It will impact the contributed BBS/forum modules and requires a tiny SQL update: sql> ALTER TABLE comments CHANGE lid nid int(10) NOT NULL; + Moved most (all?) of the comment related logic from node.php to comment.module where it belongs. This also marks a first step towards removing/reducing "node.php". + Added a delete button to the comment admin form and made it so that Drupal prompts for confirmation prior to deleting a comment from the database. This behavior is similar to that of deleting nodes. + Disabled comment moderation for now. + Some of the above changes will make it easier to integrate the upcomcing mail-to-web and web-to-mail gateways. They are part of a bigger plan. ;) - node system: + Made it so that updating nodes (like for instance updating blog entries) won't trigger the submission rate throttle. + Fixed a small glitch where a node's title wasn't always passed to the $theme->header() function. + Made "node_array()" and "node_object()" more generic and named them "object2array()" and "array2object()". + Moved most (all?) of the comment related logic from node.php to comment.module where it belongs. This also marks a first step towards removing/reducing "node.php". - misc: + Applied three patches by Foxen. One to improve performance of the book module, and two other patches to fix small glitches in common.inc. Thanks Foxen!
2001-12-30 16:16:38 +00:00
2004-01-06 19:52:14 +00:00
/**
* @name Messages
* @{
* Frequently used messages.
2004-01-06 19:52:14 +00:00
*/
/**
* Return a string with an "access denied" message.
*
* Always consider whether to use drupal_access_denied() instead to return a
* proper (and customizable) 403 error.
*/
function message_access() {
return t('You are not authorized to access this page.');
}
/**
* Return a string with a "not applicable" message.
*/
function message_na() {
return t('n/a');
}
/**
* @} End of "Messages".
*/
/**
* Initialize the localization system.
*/
function locale_initialize() {
global $user;
if (function_exists('i18n_get_lang')) {
return i18n_get_lang();
}
if (function_exists('locale')) {
$languages = locale_supported_languages();
$languages = $languages['name'];
}
else {
// Ensure the locale/language is correctly returned, even without locale.module.
// Useful for e.g. XML/HTML 'lang' attributes.
$languages = array('en' => 'English');
}
2003-03-04 15:10:37 +00:00
if ($user->uid && $languages[$user->language]) {
return $user->language;
}
else {
return key($languages);
}
}
2004-01-06 19:52:14 +00:00
/**
* Translate strings to the current locale.
2004-01-06 19:52:14 +00:00
*
* When using t(), try to put entire sentences and strings in one t() call.
* This makes it easier for translators. HTML markup within translation strings
* is acceptable, if necessary. The suggested syntax for a link embedded
* within a translation string is:
* @code
* $msg = t('You must log in below or <a href="%url">create a new
* account</a> before viewing the next page.', array('%url'
* => url('user/register')));
* @endcode
* We suggest the same syntax for links to other sites. This makes it easy to
* change link URLs if needed (which happens often) without requiring updates
* to translations.
2004-01-06 19:52:14 +00:00
*
* @param $string
* A string containing the English string to translate.
* @param $args
* An associative array of replacements to make after translation. Incidences
* of any key in this array are replaced with the corresponding value.
* @return
* The translated string.
2004-01-06 19:52:14 +00:00
*/
function t($string, $args = 0) {
global $locale;
if (function_exists('locale') && $locale != 'en') {
$string = locale($string);
}
if (!$args) {
return $string;
}
else {
return strtr($string, $args);
}
}
/**
* Encode special characters in a string for display as HTML.
*
* Note that we'd like to use htmlspecialchars($input, $quotes, 'utf-8')
* as outlined in the PHP manual, but we can't because there's a bug in
* PHP < 4.3 that makes it mess up multibyte charsets if we specify the
* charset. This will be changed later once we make PHP 4.3 a requirement.
*/
function drupal_specialchars($input, $quotes = ENT_NOQUOTES) {
return htmlspecialchars($input, $quotes);
}
2004-01-06 19:52:14 +00:00
/**
* @defgroup validation Input validation
* @{
* Functions to validate user input.
2004-01-06 19:52:14 +00:00
*/
/**
* Verify the syntax of the given e-mail address.
*
* Empty e-mail addresses are allowed. See RFC 2822 for details.
*
* @param $mail
* A string containing an email address.
* @return
* TRUE if the address is in a valid format.
*/
function valid_email_address($mail) {
$user = '[a-zA-Z0-9_\-\.\+\^!#\$%&*+\/\=\?\`\|\{\}~\']+';
$domain = '(?:(?:[a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9\-]*[a-zA-Z0-9])\.?)+';
$ipv4 = '[0-9]{1,3}(\.[0-9]{1,3}){3}';
$ipv6 = '[0-9a-fA-F]{1,4}(\:[0-9a-fA-F]{1,4}){7}';
return preg_match("/^$user@($domain|(\[($ipv4|$ipv6)\]))$/", $mail);
}
/**
* Verify the syntax of the given URL.
*
* @param $url
* The URL to verify.
* @param $absolute
* Whether the URL is absolute (beginning with a scheme such as "http:").
* @return
* TRUE if the URL is in a valid format.
*/
function valid_url($url, $absolute = FALSE) {
$allowed_characters = '[a-z0-9\/:_\-_\.\?\$,~=#&%\+]';
if ($absolute) {
return preg_match("/^(http|https|ftp):\/\/". $allowed_characters ."+$/i", $url);
}
else {
return preg_match("/^". $allowed_characters ."+$/i", $url);
}
}
/**
* Validate data input by a user.
*
* Ensures that user data cannot be used to perform attacks on the site.
*
* @param $data
* The input to check.
* @return
* TRUE if the input data is acceptable.
*/
2004-01-06 19:52:14 +00:00
function valid_input_data($data) {
if (is_array($data) || is_object($data)) {
// Form data can contain a number of nested arrays.
2004-01-06 19:52:14 +00:00
foreach ($data as $key => $value) {
2004-01-17 23:19:02 +00:00
if (!valid_input_data($key) || !valid_input_data($value)) {
return FALSE;
2004-01-06 19:52:14 +00:00
}
}
}
2004-12-28 11:04:24 +00:00
else if (isset($data)) {
// Detect dangerous input data.
2004-01-06 19:52:14 +00:00
// Decode all normal character entities.
$data = decode_entities($data, array('<', '&', '"'));
// Check strings:
$match = preg_match('/\Wjavascript\s*:/i', $data);
$match += preg_match('/\Wexpression\s*\(/i', $data);
$match += preg_match('/\Walert\s*\(/i', $data);
2004-01-06 19:52:14 +00:00
// Check attributes:
2004-01-06 19:52:14 +00:00
$match += preg_match("/\W(dynsrc|datasrc|data|lowsrc|on[a-z]+)\s*=[^>]+?>/i", $data);
// Check tags:
2004-01-06 19:52:14 +00:00
$match += preg_match("/<\s*(applet|script|object|style|embed|form|blink|meta|html|frame|iframe|layer|ilayer|head|frameset|xml)/i", $data);
if ($match) {
watchdog('security', t('Terminated request because of suspicious input data: %data.', array('%data' => '<em>'. drupal_specialchars($data) .'</em>')));
return FALSE;
2004-01-06 19:52:14 +00:00
}
}
return TRUE;
2004-01-06 19:52:14 +00:00
}
/**
* @} End of "defgroup validation".
*/
2004-01-06 19:52:14 +00:00
/**
* Register an event for the current visitor (hostname/IP) to the flood control mechanism.
*
* @param $name
* The name of the event.
*/
function flood_register_event($name) {
db_query("INSERT INTO {flood} (event, hostname, timestamp) VALUES ('%s', '%s', %d)", $name, $_SERVER['REMOTE_ADDR'], time());
}
/**
* Check if the current visitor (hostname/IP) is allowed to proceed with the specified event.
* The user is allowed to proceed if he did not trigger the specified event more than
* $threshold times per hour.
*
* @param $name
* The name of the event.
* @param $number
* The maximum number of the specified event per hour (per visitor).
* @return
* True if the user did not exceed the hourly threshold. False otherwise.
*/
function flood_is_allowed($name, $threshold) {
$number = db_num_rows(db_query("SELECT event FROM {flood} WHERE event = '%s' AND hostname = '%s' AND timestamp > %d", $name, $_SERVER['REMOTE_ADDR'], time() - 3600));
return ($number < $threshold ? TRUE : FALSE);
}
function check_form($text) {
return drupal_specialchars($text, ENT_QUOTES);
}
function check_file($filename) {
return is_uploaded_file($filename);
}
/**
* @defgroup format Formatting
* @{
* Functions to format numbers, strings, dates, etc.
*/
/**
* Formats an RSS channel.
*
* Arbitrary elements may be added using the $args associative array.
*/
function format_rss_channel($title, $link, $description, $items, $language = 'en', $args = array()) {
// arbitrary elements may be added using the $args associative array
$output = "<channel>\n";
$output .= ' <title>'. drupal_specialchars(strip_tags($title)) ."</title>\n";
$output .= ' <link>'. drupal_specialchars(strip_tags($link)) ."</link>\n";
$output .= ' <description>'. drupal_specialchars(strip_tags($description)) ."</description>\n";
$output .= ' <language>'. drupal_specialchars(strip_tags($language)) ."</language>\n";
foreach ($args as $key => $value) {
$output .= ' <'. $key .'>'. drupal_specialchars(strip_tags($value)) ."</$key>\n";
}
$output .= $items;
$output .= "</channel>\n";
return $output;
}
/**
* Format a single RSS item.
*
* Arbitrary elements may be added using the $args associative array.
*/
function format_rss_item($title, $link, $description, $args = array()) {
$output = "<item>\n";
$output .= ' <title>'. drupal_specialchars(strip_tags($title)) ."</title>\n";
$output .= ' <link>'. drupal_specialchars(strip_tags($link)) ."</link>\n";
The Input formats - filter patch has landed. I still need to make update instructions for modules and update the hook docs. Here's an overview of the changes: 1) Multiple Input formats: they are complete filter configurations (what filters to use, in what order and with which settings). Input formats are admin-definable, and usage of them is role-dependant. For example, you can set it up so that regular users can only use limited HTML, while admins can free HTML without any tag limitations. The input format can be chosen per content item (nodes, comments, blocks, ...) when you add/edit them. If only a single format is available, there is no choice, and nothing changes with before. The default install (and the upgrade) contains a basic set of formats which should satisfy the average user's needs. 2) Filters have toggles Because now you might want to enable a filter only on some input formats, an explicit toggle is provided by the filter system. Modules do not need to worry about it and filters that still have their own on/off switch should get rid of it. 3) Multiple filters per module This was necessary to accomodate the next change, and it's also a logical extension of the filter system. 4) Embedded PHP is now a filter Thanks to the multiple input formats, I was able to move the 'embedded PHP' feature from block.module, page.module and book.module into a simple filter which executes PHP code. This filter is part of filter.module, and by default there is an input format 'PHP', restricted to the administrator only, which contains this filter. This change means that block.module now passes custom block contents through the filter system. As well as from reducing code duplication and avoiding two type selectors for page/book nodes, you can now combine PHP code with other filters. 5) User-supplied PHP code now requires <?php ?> tags. This is required for teasers to work with PHP code. Because PHP evaluation is now just another step in the filter process, we can't do this. Also, because teasers are generated before filtering, this would result in errors when the teaser generation would cut off a piece of PHP code. Also, regular PHP syntax explicitly includes the <?php ?> tags for PHP files, so it makes sense to use the same convention for embedded PHP in Drupal. 6) Filter caching was added. Benchmarking shows that even for a simple setup (basic html filtering + legacy URL rewriting), filtercache can offer speedups. Unlike the old filtercache, this uses the normal cache table. 7) Filtertips were moved from help into a hook_filter_tips(). This was required to accomodate the fact that there are multiple filters per module, and that filter settings are format dependant. Shoehorning filter tips into _help was ugly and silly. The display of the filter tips is done through the input format selector, so filter_tips_short() no longer exists. 8) A more intelligent linebreak convertor was added, which doesn't stop working if you use block-level tags and which adds <p> tags.
2004-08-10 18:34:29 +00:00
$output .= ' <description>'. drupal_specialchars($description) ."</description>\n";
foreach ($args as $key => $value) {
if (is_array($value)) {
if ($value['key']) {
$output .= ' <'. $value['key'];
if (is_array($value['attributes'])) {
$output .= drupal_attributes($value['attributes']);
}
if ($value['value']) {
$output .= '>'. $value['value'] .'</'. $value['key'] .">\n";
}
else {
$output .= " />\n";
}
}
}
else {
$output .= ' <'. $key .'>'. drupal_specialchars(strip_tags($value)) ."</$key>\n";
}
}
$output .= "</item>\n";
return $output;
}
/**
* Format a string containing a count of items.
*
* This function ensures that the string is pluralized correctly. Since t() is
* called by this function, make sure not to pass already-localized strings to it.
*
* @param $count
* The item count to display.
* @param $singular
* The string for the singular case. Please make sure it is clear this is
* singular, to ease translation (e.g. use "1 new comment" instead of "1 new").
* @param $plural
* The string for the plural case. Please make sure it is clear this is plural,
* to ease translation. Use %count in place of the item count, as in "%count
* new comments".
* @return
* A translated string.
*/
function format_plural($count, $singular, $plural) {
if ($count == 1) return t($singular, array("%count" => $count));
// get the plural index through the gettext formula
$index = (function_exists('locale')) ? locale_get_plural($count) : -1;
if ($index < 0) { // backward compatibility
return t($plural, array("%count" => $count));
}
else {
switch ($index) {
case "0":
return t($singular, array("%count" => $count));
case "1":
return t($plural, array("%count" => $count));
default:
return t(strtr($plural, array("%count" => '%count['. $index .']')), array('%count['. $index .']' => $count));
}
}
}
/**
* Generate a string representation for the given byte count.
*
* @param $size
* The size in bytes.
* @return
* A translated string representation of the size.
*/
function format_size($size) {
$suffix = t('bytes');
if ($size > 1024) {
$size = round($size / 1024, 2);
$suffix = t('KB');
}
if ($size > 1024) {
$size = round($size / 1024, 2);
$suffix = t('MB');
}
return t('%size %suffix', array('%size' => $size, '%suffix' => $suffix));
}
/**
* Format a time interval with the requested granularity.
*
* @param $timestamp
* The length of the interval in seconds.
* @param $granularity
* How many different units to display in the string.
* @return
* A translated string representation of the interval.
*/
function format_interval($timestamp, $granularity = 2) {
$units = array('1 year|%count years' => 31536000, '1 week|%count weeks' => 604800, '1 day|%count days' => 86400, '1 hour|%count hours' => 3600, '1 min|%count min' => 60, '1 sec|%count sec' => 1);
$output = '';
foreach ($units as $key => $value) {
$key = explode('|', $key);
if ($timestamp >= $value) {
$output .= ($output ? ' ' : '') . format_plural(floor($timestamp / $value), $key[0], $key[1]);
$timestamp %= $value;
$granularity--;
}
if ($granularity == 0) {
break;
}
}
return $output ? $output : t('0 sec');
}
/**
* Format a date with the given configured format or a custom format string.
*
* Drupal allows administrators to select formatting strings for 'small',
* 'medium' and 'large' date formats. This function can handle these formats,
* as well as any custom format.
*
* @param $timestamp
* The exact date to format, as a UNIX timestamp.
* @param $type
* The format to use. Can be "small", "medium" or "large" for the preconfigured
* date formats. If "custom" is specified, then $format is required as well.
* @param $format
* A PHP date format string as required by date(). A backslash should be used
* before a character to avoid interpreting the character as part of a date
* format.
* @param $timezone
* Time zone offset in seconds; if omitted, the user's time zone is used.
* @return
* A translated date string in the requested format.
*/
function format_date($timestamp, $type = 'medium', $format = '', $timezone = NULL) {
if ($timezone === NULL) {
global $user;
if (variable_get('configurable_timezones', 1) && $user->uid && strlen($user->timezone)) {
$timezone = $user->timezone;
}
else {
$timezone = variable_get('date_default_timezone', 0);
}
}
$timestamp += $timezone;
switch ($type) {
case 'small':
$format = variable_get('date_format_short', 'm/d/Y - H:i');
break;
case 'large':
$format = variable_get('date_format_long', 'l, F j, Y - H:i');
break;
case 'custom':
// No change to format
break;
case 'medium':
default:
$format = variable_get('date_format_medium', 'D, m/d/Y - H:i');
}
$max = strlen($format);
$date = '';
for ($i = 0; $i < $max; $i++) {
$c = $format{$i};
if (strpos('AaDFlM', $c) !== false) {
$date .= t(gmdate($c, $timestamp));
}
else if (strpos('BdgGhHiIjLmnsStTUwWYyz', $c) !== false) {
$date .= gmdate($c, $timestamp);
}
else if ($c == 'r') {
$date .= format_date($timestamp - $timezone, 'custom', 'D, d M Y H:i:s O', $timezone);
}
else if ($c == 'O') {
$date .= sprintf('%s%02d%02d', ($timezone < 0 ? '-' : '+'), abs($timezone / 3600), abs($timezone % 3600) / 60);
}
else if ($c == 'Z') {
$date .= $timezone;
}
else if ($c == '\\') {
$date .= $format[++$i];
}
else {
$date .= $c;
}
}
return $date;
}
/**
* Format a username.
*
* @param $object
* The user object to format, usually returned from user_load().
* @return
* A string containing an HTML link to the user's page if the passed object
* suggests that this is a site user. Otherwise, only the username is returned.
*/
function format_name($object) {
if ($object->uid && $object->name) {
// Shorten the name when it is too long or it will break many tables.
if (strlen($object->name) > 20) {
$name = truncate_utf8($object->name, 15) .'...';
}
else {
$name = $object->name;
}
$output = l($name, 'user/'. $object->uid, array('title' => t('View user profile.')));
}
else if ($object->name) {
// Sometimes modules display content composed by people who are
// not registered members of the site (e.g. mailing list or news
// aggregator modules). This clause enables modules to display
// the true author of the content.
if ($object->homepage) {
$output = '<a href="'. $object->homepage .'">'. $object->name .'</a>';
}
else {
$output = $object->name;
}
$output .= ' ('. t('not verified') .')';
}
else {
$output = variable_get('anonymous', 'Anonymous');
}
return $output;
}
/**
* @} End of "defgroup format".
*/
2004-01-06 19:52:14 +00:00
/**
* @defgroup form Form generation
2004-01-06 19:52:14 +00:00
* @{
* Functions to enable output of HTML forms and form elements.
*
* Drupal uses these functions to achieve consistency in its form presentation,
* while at the same time simplifying code and reducing the amount of HTML that
* must be explicitly generated by modules.
2004-01-06 19:52:14 +00:00
*/
/**
* Generate a form from a set of form elements.
*
* @param $form
* An HTML string containing one or more form elements.
* @param $method
* The query method to use ("post" or "get").
* @param $action
* The URL to send the form contents to, if not the current page.
* @param $attributes
* An associative array of attributes to add to the form tag.
* @result
* An HTML string with the contents of $form wrapped in a form tag.
*/
function form($form, $method = 'post', $action = NULL, $attributes = NULL) {
if (!$action) {
- Bugfix: made request_uri() rewrite ( and ) with their entity equivalents to avoid XSS attacks! Patch by Al, Moshe, Marco, Kjartan and me. - Bugfix: the admin module does now import drupal.css prior to admin.css. Patch by me. - Bugfix: the admin module was still emitting a <base href=""> tag. I removed this as it is been taken care of by theme_head(); Patch by me. - Bugfix: made the tracker module's pager only consider published pages. Patch by Moshe. - Bugfix: cured some typos in the comment module's help function. Patch by Marco. - Bugfix: fixed a typo in the pager_display() that caused optional attributes to be discarded. - Bugfix: made the Xtemplate emit empty boxes like any other theme does. Patch by Al. - Bugfix: fixed broken link on the statistics module's log page. Reported by Kjartan. - CSS improvements: made the HTML output emitted by the tracker module look nicer. Patch by Moshe and Al. - CSS improvements: added CSS classes for form elements. Patch by Al. - CSS improvements: added a vertical gap between the last form item and the submit button. Patch by Al. Note that Opera 6 is not picking up this CSS but apparently others browsers such as Konqueror do. - Xtemplate improvements: changed the color of the selected day in the archive module's calendar. Patch by Al. - Usability improvements: made the "birthday" field of the profile module look nicer. Patch by Al. ------ - TODO: it might be a good idea to emit the following meta tag in the theme_head() function: <meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" /> Currently, some themes (and modules!) emit this while others don't. This would also make it possible to change the charset site-wide. - TODO: now we added support for td.dark and td.light to drupal.css, maybe it can be removed from admin.css as well as xtemplate.css?
2003-06-03 18:04:47 +00:00
$action = request_uri();
}
return '<form action="'. $action .'" method="'. $method .'"'. drupal_attributes($attributes) .">\n". $form ."\n</form>\n";
}
/**
* File an error against the form element with the specified name.
*/
function form_set_error($name, $message) {
$GLOBALS['form'][$name] = $message;
drupal_set_message($message, 'error');
}
/**
* Return an associative array of all errors.
*/
function form_get_errors() {
if (array_key_exists('form', $GLOBALS)) {
return $GLOBALS['form'];
}
}
/**
* Return the error message filed against the form with the specified name.
*/
function _form_get_error($name) {
if (array_key_exists('form', $GLOBALS)) {
return $GLOBALS['form'][$name];
}
}
function _form_get_class($name, $required, $error) {
return $name. ($required ? ' required' : '') . ($error ? ' error' : '');
}
/**
* Format a general form item.
*
* @param $title
* The label for the form item.
* @param $value
* The contents of the form item.
* @param $description
* Explanatory text to display after the form item.
* @param $id
* A unique identifier for the form item.
* @param $required
* Whether the user must fill in this form element before submitting the form.
* @param $error
* An error message to display alongside the form element.
* @return
* A themed HTML string representing the form item.
*/
function form_item($title, $value, $description = NULL, $id = NULL, $required = FALSE, $error = FALSE) {
return theme('form_element', $title, $value, $description, $id, $required, $error);
}
/**
* Format a group of form items.
*
* @param $legend
* The label for the form item group.
* @param $group
* The form items within the group, as an HTML string.
* @param $description
* Explanatory text to display after the form item group.
* @return
* A themed HTML string representing the form item group.
*/
function form_group($legend, $group, $description = NULL) {
return '<fieldset>' . ($legend ? '<legend>'. $legend .'</legend>' : '') . $group . ($description ? '<div class="description">'. $description .'</div>' : '') . "</fieldset>\n";
}
/**
* Format a radio button.
*
* @param $title
* The label for the radio button.
* @param $name
* The internal name used to refer to the button.
* @param $value
* The value that the form element takes on when selected.
* @param $checked
* Whether the button will be initially selected when the page is rendered.
* @param $description
* Explanatory text to display after the form item.
* @param $attributes
* An associative array of HTML attributes to add to the button.
* @param $required
* Whether the user must select this radio button before submitting the form.
* @return
* A themed HTML string representing the radio button.
*/
function form_radio($title, $name, $value = 1, $checked = FALSE, $description = NULL, $attributes = NULL, $required = FALSE) {
$element = '<input type="radio" class="'. _form_get_class('form-radio', $required, _form_get_error($name)) .'" name="edit['. $name .']" value="'. $value .'"'. ($checked ? ' checked="checked"' : '') . drupal_attributes($attributes) .' />';
if (!is_null($title)) {
$element = '<label class="option">'. $element .' '. $title .'</label>';
}
return theme('form_element', NULL, $element, $description, $name, $required, _form_get_error($name));
}
/**
* Format a set of radio buttons.
*
* @param $title
* The label for the radio buttons as a group.
* @param $name
* The internal name used to refer to the buttons.
* @param $value
* The currently selected radio button's key.
* @param $options
* An associative array of buttons to display. The keys in this array are
* button values, while the values are the labels to display for each button.
* @param $description
* Explanatory text to display after the form item.
* @param $required
* Whether the user must select a radio button before submitting the form.
* @param $attributes
* An associative array of HTML attributes to add to each button.
* @return
* A themed HTML string representing the radio button set.
*/
function form_radios($title, $name, $value, $options, $description = NULL, $required = FALSE, $attributes = NULL) {
if (count($options) > 0) {
$choices = '';
foreach ($options as $key => $choice) {
$choices .= '<label class="option"><input type="radio" class="form-radio" name="edit['. $name .']" value="'. $key .'"'. ($key == $value ? ' checked="checked"' : ''). drupal_attributes($attributes) .' /> '. $choice .'</label><br />';
}
return theme('form_element', $title, $choices, $description, NULL, $required, _form_get_error($name));
}
}
/**
* Format a checkbox.
*
* @param $title
* The label for the checkbox.
* @param $name
* The internal name used to refer to the button.
* @param $value
* The value that the form element takes on when selected.
* @param $checked
* Whether the button will be initially selected when the page is rendered.
* @param $description
* Explanatory text to display after the form item.
* @param $attributes
* An associative array of HTML attributes to add to the button.
* @param $required
* Whether the user must check this box before submitting the form.
* @return
* A themed HTML string representing the checkbox.
*/
function form_checkbox($title, $name, $value = 1, $checked = FALSE, $description = NULL, $attributes = NULL, $required = FALSE) {
$element = '<input type="checkbox" class="'. _form_get_class('form-checkbox', $required, _form_get_error($name)) .'" name="edit['. $name .']" id="edit-'. $name .'" value="'. $value .'"'. ($checked ? ' checked="checked"' : '') . drupal_attributes($attributes) .' />';
if (!is_null($title)) {
$element = '<label class="option">'. $element .' '. $title .'</label>';
}
// Note: because unchecked boxes are not included in the POST data, we include
// a form_hidden() which will be overwritten for a checked box.
return form_hidden($name, 0) . theme('form_element', NULL, $element, $description, $name, $required, _form_get_error($name));
}
/**
* Format a set of checkboxes.
*
* @param $title
* The label for the checkboxes as a group.
* @param $name
* The internal name used to refer to the buttons.
* @param $values
* A linear array of keys of the initially checked boxes.
* @param $options
* An associative array of buttons to display. The keys in this array are
* button values, while the values are the labels to display for each button.
* @param $description
* Explanatory text to display after the form item.
* @param $attributes
* An associative array of HTML attributes to add to each button.
* @param $required
* Whether the user must check a box before submitting the form.
* @return
* A themed HTML string representing the radio button set.
*/
function form_checkboxes($title, $name, $values, $options, $description = NULL, $attributes = NULL, $required = FALSE) {
if (count($options) > 0) {
if (!isset($values) || $values == 0) {
$values = array();
}
$choices = '';
foreach ($options as $key => $choice) {
$choices .= '<label class="option"><input type="checkbox" class="form-checkbox" name="edit['. $name .'][]" value="'. $key .'"'. (in_array($key, $values) ? ' checked="checked"' : ''). drupal_attributes($attributes) .' /> '. $choice .'</label><br />';
}
// Note: because unchecked boxes are not included in the POST data, we
// include a form_hidden() which will be overwritten as soon as there is at
// least one checked box.
return form_hidden($name, 0) . theme('form_element', $title, $choices, $description, NULL, $required, _form_get_error($name));
}
}
/**
* Format a single-line text field.
*
* @param $title
* The label for the text field.
* @param $name
* The internal name used to refer to the field.
* @param $value
* The initial value for the field at page load time.
* @param $size
* A measure of the visible size of the field (passed directly to HTML).
* @param $maxlength
* The maximum number of characters that may be entered in the field.
* @param $description
* Explanatory text to display after the form item.
* @param $attributes
* An associative array of HTML attributes to add to the form item.
* @param $required
* Whether the user must enter some text in the field.
* @return
* A themed HTML string representing the field.
*/
function form_textfield($title, $name, $value, $size, $maxlength, $description = NULL, $attributes = NULL, $required = FALSE) {
$size = $size ? ' size="'. $size .'"' : '';
return theme('form_element', $title, '<input type="text" maxlength="'. $maxlength .'" class="'. _form_get_class('form-text', $required, _form_get_error($name)) .'" name="edit['. $name .']" id="edit-'. $name .'"'. $size .' value="'. check_form($value) .'"'. drupal_attributes($attributes) .' />', $description, 'edit-'. $name, $required, _form_get_error($name));
}
/**
* Format a single-line text field that does not display its contents visibly.
*
* @param $title
* The label for the text field.
* @param $name
* The internal name used to refer to the field.
* @param $value
* The initial value for the field at page load time.
* @param $size
* A measure of the visible size of the field (passed directly to HTML).
* @param $maxlength
* The maximum number of characters that may be entered in the field.
* @param $description
* Explanatory text to display after the form item.
* @param $attributes
* An associative array of HTML attributes to add to the form item.
* @param $required
* Whether the user must enter some text in the field.
* @return
* A themed HTML string representing the field.
*/
function form_password($title, $name, $value, $size, $maxlength, $description = NULL, $attributes = NULL, $required = FALSE) {
$size = $size ? ' size="'. $size .'"' : '';
return theme('form_element', $title, '<input type="password" class="'. _form_get_class('form-password', $required, _form_get_error($name)) .'" maxlength="'. $maxlength .'" name="edit['. $name .']" id="edit-'. $name .'"'. $size .' value="'. check_form($value) .'"'. drupal_attributes($attributes) .' />', $description, 'edit-'. $name, $required, _form_get_error($name));
}
/**
* Format a multiple-line text field.
*
* @param $title
* The label for the text field.
* @param $name
* The internal name used to refer to the field.
* @param $value
* The initial value for the field at page load time.
* @param $cols
* The width of the field, in columns of text.
* @param $rows
* The height of the field, in rows of text.
* @param $description
* Explanatory text to display after the form item.
* @param $attributes
* An associative array of HTML attributes to add to the form item.
* @param $required
* Whether the user must enter some text in the field.
* @return
* A themed HTML string representing the field.
*/
function form_textarea($title, $name, $value, $cols, $rows, $description = NULL, $attributes = NULL, $required = FALSE) {
$cols = $cols ? ' cols="'. $cols .'"' : '';
$output = '';
// e.g. optionally plug in a WYSIWYG editor
foreach (module_list() as $module_name) {
if (module_hook($module_name, 'textarea')) {
$output .= module_invoke($module_name, 'textarea', 'pre', $name);
}
}
$output .= theme('form_element', $title, '<textarea wrap="virtual"'. $cols .' rows="'. $rows .'" name="edit['. $name .']" id="edit-'. $name .'" class="'. _form_get_class('textarea', $required, _form_get_error($name)) .'"'. drupal_attributes($attributes) .'>'. check_form($value) .'</textarea>', $description, 'edit-'. $name, $required, _form_get_error($name));
// e.g. optionally plug in a WYSIWYG editor
foreach (module_list() as $module_name) {
if (module_hook($module_name, 'textarea')) {
$output .= module_invoke($module_name, 'textarea', 'post', $name);
}
}
return $output;
}
/**
* Format a dropdown menu or scrolling selection box.
*
* @param $title
* The label for the form element.
* @param $name
* The internal name used to refer to the form element.
* @param $value
* The key of the currently selected item, or a linear array of keys of all the
* currently selected items if multiple selections are allowed.
* @param $options
* An associative array of buttons to display. The keys in this array are
* button values, while the values are the labels to display for each button.
* @param $description
* Explanatory text to display after the form item.
* @param $extra
* Additional HTML to inject into the select element tag.
* @param $multiple
* Whether the user may select more than one item.
* @param $required
* Whether the user must select a value before submitting the form.
* @return
* A themed HTML string representing the form element.
*
* It is possible to group options together; to do this, change the format of
* $options to an associative array in which the keys are group labels, and the
* values are associative arrays in the normal $options format.
*/
function form_select($title, $name, $value, $options, $description = NULL, $extra = 0, $multiple = FALSE, $required = FALSE) {
$select = '';
foreach ($options as $key => $choice) {
if (is_array($choice)) {
$select .= '<optgroup label="'. $key .'">';
foreach ($choice as $key => $choice) {
$select .= '<option value="'. $key .'"'. (is_array($value) ? (in_array($key, $value) ? ' selected="selected"' : '') : ($value == $key ? ' selected="selected"' : '')) .'>'. check_form($choice) .'</option>';
}
$select .= '</optgroup>';
}
else {
$select .= '<option value="'. $key .'"'. (is_array($value) ? (in_array($key, $value) ? ' selected="selected"' : '') : ($value == $key ? ' selected="selected"' : '')) .'>'. check_form($choice) .'</option>';
}
}
return theme('form_element', $title, '<select name="edit['. $name .']'. ($multiple ? '[]' : '') .'"'. ($multiple ? ' multiple="multiple" ' : '') . ($extra ? ' '. $extra : '') .' id="edit-'. $name .'">'. $select .'</select>', $description, 'edit-'. $name, $required, _form_get_error($name));
}
/**
* Format a file upload field.
*
* @param $title
* The label for the file upload field.
* @param $name
* The internal name used to refer to the field.
* @param $size
* A measure of the visible size of the field (passed directly to HTML).
* @param $description
* Explanatory text to display after the form item.
* @param $required
* Whether the user must upload a file to the field.
* @return
* A themed HTML string representing the field.
*
* For assistance with handling the uploaded file correctly, see the API
* provided by file.inc.
*/
function form_file($title, $name, $size, $description = NULL, $required = FALSE) {
return theme('form_element', $title, '<input type="file" class="'. _form_get_class('form-file', $required, _form_get_error($name)) .'" name="edit['. $name .']" id="edit-'. $name .'" size="'. $size ."\" />\n", $description, 'edit-'. $name, $required, _form_get_error($error));
}
/**
* Store data in a hidden form field.
*
* @param $name
* The internal name used to refer to the field.
* @param $value
* The stored data.
* @return
* A themed HTML string representing the hidden field.
*
* This function can be useful in retaining information between page requests,
* but be sure to validate the data on the receiving page as it is possible for
* an attacker to change the value before it is submitted.
*/
function form_hidden($name, $value) {
return '<input type="hidden" name="edit['. $name .']" value="'. check_form($value) ."\" />\n";
}
/**
* Format an action button.
*
* @param $value
* Both the label for the button, and the value passed to the target page
* when this button is clicked.
* @param $name
* The internal name used to refer to the button.
* @param $type
* What type to pass to the HTML input tag.
* @param $attributes
* An associative array of HTML attributes to add to the form item.
* @return
* A themed HTML string representing the button.
*/
function form_button($value, $name = 'op', $type = 'submit', $attributes = NULL) {
return '<input type="'. $type .'" class="form-'. $type .'" name="'. $name .'" value="'. check_form($value) .'" '. drupal_attributes($attributes) ." />\n";
}
/**
* Format a form submit button.
*
* @param $value
* Both the label for the button, and the value passed to the target page
* when this button is clicked.
* @param $name
* The internal name used to refer to the button.
* @param $attributes
* An associative array of HTML attributes to add to the form item.
* @return
* A themed HTML string representing the button.
*/
function form_submit($value, $name = 'op', $attributes = NULL) {
return form_button($value, $name, 'submit', $attributes);
}
/**
* Format a weight selection menu.
*
* @param $title
* The label for the form element.
* @param $name
* The internal name used to refer to the form element.
* @param $value
* The selected weight value at page load time.
* @param $delta
* The largest in absolute value the weight can be. For example, if set to 10,
* weights could range from -10 to 10 inclusive.
* @param $description
* Explanatory text to display after the form item.
* @param $extra
* Additional HTML to inject into the select element tag.
* @return
* A themed HTML string representing the form element.
*/
function form_weight($title = NULL, $name = 'weight', $value = 0, $delta = 10, $description = NULL, $extra = 0) {
2003-04-03 22:18:27 +00:00
for ($n = (-1 * $delta); $n <= $delta; $n++) {
$weights[$n] = $n;
}
return form_select($title, $name, $value, $weights, $description, $extra);
}
/**
* @} End of "defgroup form".
*/
/**
* Generate an internal Drupal URL.
*
* @param $path
* The Drupal path being linked to, such as "admin/node".
* @param $query
* A query string to append to the link.
* @param $fragment
* A fragment identifier (named anchor) to append to the link.
* @param $absolute
* Whether to force the output to be an absolute link (beginning with http:).
* Useful for links that will be displayed outside the site, such as in an RSS feed.
* @return
* an HTML string containing a link to the given path.
*
* When creating links in modules, consider whether l() could be a better
* alternative than url().
*/
function url($path = NULL, $query = NULL, $fragment = NULL, $absolute = FALSE) {
global $base_url;
2004-01-17 23:19:02 +00:00
static $script;
if (empty($script)) {
// On some web servers, such as IIS, we can't omit "index.php". So, we
// generate "index.php?q=foo" instead of "?q=foo" on anything that is not
// Apache.
$script = (strpos($_SERVER['SERVER_SOFTWARE'], 'Apache') === false) ? 'index.php' : '';
}
$path = drupal_get_path_alias($path);
if (isset($fragment)) {
$fragment = '#'. $fragment;
}
$base = ($absolute ? $base_url . '/' : '');
if (variable_get('clean_url', '0') == '0') {
if (isset($path)) {
2003-02-14 19:52:45 +00:00
if (isset($query)) {
return $base . $script .'?q='. $path .'&amp;'. $query . $fragment;
2003-02-14 19:52:45 +00:00
}
else {
return $base . $script .'?q='. $path . $fragment;
2003-02-14 19:52:45 +00:00
}
}
else {
2003-02-14 19:52:45 +00:00
if (isset($query)) {
return $base . $script .'?'. $query . $fragment;
2003-02-14 19:52:45 +00:00
}
else {
return $base . $fragment;
2003-02-14 19:52:45 +00:00
}
}
}
else {
if (isset($path)) {
2003-02-14 19:52:45 +00:00
if (isset($query)) {
return $base . $path .'?'. $query . $fragment;
2003-02-14 19:52:45 +00:00
}
else {
return $base . $path . $fragment;
2003-02-14 19:52:45 +00:00
}
}
else {
2003-02-14 19:52:45 +00:00
if (isset($query)) {
return $base . $script .'?'. $query . $fragment;
2003-02-14 19:52:45 +00:00
}
else {
return $base . $fragment;
2003-02-14 19:52:45 +00:00
}
}
}
}
/**
* Format an attribute string to insert in a tag.
*
* @param $attributes
* An associative array of HTML attributes.
* @return
* An HTML string ready for insertion in a tag.
*/
function drupal_attributes($attributes = array()) {
if ($attributes) {
$t = array();
foreach ($attributes as $key => $value) {
$t[] = $key .'="'. $value .'"';
}
return ' '. implode($t, ' ');
}
}
2003-01-06 19:51:01 +00:00
/**
* Format an internal Drupal link.
*
* This function correctly handles aliased paths, and allows themes to highlight
* links to the current page correctly, so all internal links output by modules
* should be generated by this function if possible.
*
* @param $text
* The text to be enclosed with the anchor tag.
* @param $path
* The Drupal path being linked to, such as "admin/node".
* @param $attributes
* An associative array of HTML attributes to apply to the anchor tag.
* @param $query
* A query string to append to the link.
* @param $fragment
* A fragment identifier (named anchor) to append to the link.
* @param $absolute
* Whether to force the output to be an absolute link (beginning with http:).
* Useful for links that will be displayed outside the site, such as in an RSS feed.
* @return
* an HTML string containing a link to the given path.
*/
function l($text, $path, $attributes = array(), $query = NULL, $fragment = NULL, $absolute = FALSE) {
if (drupal_get_normal_path($path) == $_GET['q']) {
if (isset($attributes['class'])) {
$attributes['class'] .= ' active';
}
else {
$attributes['class'] = 'active';
}
}
return '<a href="'. url($path, $query, $fragment, $absolute) .'"'. drupal_attributes($attributes) .'>'. $text .'</a>';
}
/**
* Perform end-of-request tasks.
*
* This function sets the page cache if appropriate, and allows modules to
* react to the closing of the page by calling hook_exit().
*/
function drupal_page_footer() {
if (variable_get('cache', 0)) {
page_set_cache();
}
module_invoke_all('exit');
}
/**
* Form an associative array from a linear array.
*
* This function walks through the provided array and constructs an associative
* array out of it. The keys of the resulting array will be the values of the
* input array. The values will be the same as the keys unless a function is
* specified, in which case the output of the function is used for the values
* instead.
*
* @param $array
* A linear array.
* @param $function
* The name of a function to apply to all values before output.
* @result
* An associative array.
*/
function drupal_map_assoc($array, $function = NULL) {
if (!isset($function)) {
$result = array();
foreach ($array as $value) {
$result[$value] = $value;
}
return $result;
}
elseif (function_exists($function)) {
$result = array();
foreach($array as $value) {
$result[$value] = $function($value);
}
return $result;
}
}
/**
* Prepare a new XML parser.
*
* This is a wrapper around xml_parser_create() which extracts the encoding from
* the XML data first and sets the output encoding to UTF-8. This function should
* be used instead of xml_parser_create(), because PHP's XML parser doesn't check
* the input encoding itself.
*
* This is also where unsupported encodings should be converted.
* Callers should take this into account: $data might have been changed after
* the call.
*
* @param &$data
* The XML data which will be parsed later.
* @return
* An XML parser object.
*/
function drupal_xml_parser_create(&$data) {
$encoding = 'utf-8';
if (ereg('^<\?xml[^>]+encoding="([^"]+)"', $data, $match)) {
$encoding = $match[1];
}
// Unsupported encodings are converted here into UTF-8.
$php_supported = array('utf-8', 'iso-8859-1', 'us-ascii');
if (!in_array(strtolower($encoding), $php_supported)) {
$out = drupal_convert_to_utf8($data, $encoding);
if ($out !== false) {
$data = $out;
$encoding = 'utf-8';
}
else {
watchdog('php', t("Could not convert XML encoding '%s' to UTF-8.", $encoding), WATCHDOG_WARNING);
return 0;
}
}
$xml_parser = xml_parser_create($encoding);
xml_parser_set_option($xml_parser, XML_OPTION_TARGET_ENCODING, 'utf-8');
return $xml_parser;
}
/**
* Convert data to UTF-8
*
2005-03-03 20:08:02 +00:00
* Requires the iconv, GNU recode or mbstring PHP extension.
*
* @param $data
* The data to be converted.
* @param $encoding
* The encoding that the data is in
* @return
* Converted data or FALSE.
*/
function drupal_convert_to_utf8($data, $encoding) {
if (function_exists('iconv')) {
$out = @iconv($encoding, 'utf-8', $data);
}
else if (function_exists('mb_convert_encoding')) {
$out = @mb_convert_encoding($data, 'utf-8', $encoding);
}
else if (function_exists('recode_string')) {
$out = @recode_string($encoding . '..utf-8', $data);
}
else {
watchdog('php', t("Unsupported encoding '%s'. Please install iconv, GNU recode or mbstring for PHP.", $encoding), WATCHDOG_ERROR);
return FALSE;
}
return $out;
}
/**
* Truncate a UTF-8-encoded string safely.
*
* If the end position is in the middle of a UTF-8 sequence, it scans backwards
* until the beginning of the byte sequence.
*
* Use this function whenever you want to chop off a string at an unsure
* location. On the other hand, if you're sure that you're splitting on a
* character boundary (e.g. after using strpos() or similar), you can safely use
* substr() instead.
*
* @param $string
* The string to truncate.
* @param $len
* An upper limit on the returned string length.
* @param $wordsafe
* Flag to truncate at nearest word boundary. Defaults to FALSE.
* @return
* The truncated string.
*/
function truncate_utf8($string, $len, $wordsafe = FALSE) {
$slen = strlen($string);
if ($slen <= $len) {
return $string;
}
if ($wordsafe) {
while (($string[--$len] != ' ') && ($len > 0)) {};
}
if ((ord($string[$len]) < 0x80) || (ord($string[$len]) >= 0xC0)) {
return substr($string, 0, $len);
}
while (ord($string[--$len]) < 0xC0) {};
return substr($string, 0, $len);
}
/**
* Encodes MIME/HTTP header values that contain non US-ASCII characters.
*
- Patch #12232 by Steven/UnConed: search module improvements. 1) Clean up the text analyser: make it handle UTF-8 and all sorts of characters. The word splitter now does intelligent splitting into words and supports all Unicode characters. It has smart handling of acronyms, URLs, dates, ... 2) It now indexes the filtered output, which means it can take advantage of HTML tags. Meaningful tags (headers, strong, em, ...) are analysed and used to boost certain words scores. This has the side-effect of allowing the indexing of PHP nodes. 3) Link analyser for node links. The HTML analyser also checks for links. If they point to a node on the current site (handles path aliases) then the link's words are counted as part of the target node. This helps bring out commonly linked FAQs and answers to the top of the results. 4) Index comments along with the node. This means that the search can make a difference between a single node/comment about 'X' and a whole thread about 'X'. It also makes the search results much shorter and more relevant (before this patch, comments were even shown first). 5) We now keep track of total counts as well as a per item count for a word. This allows us to divide the word score by the total before adding up the scores for different words, and automatically makes noisewords have less influence than rare words. This dramatically improves the relevancy of multiword searches. This also makes the disadvantage of now using OR searching instead of AND searching less problematic. 6) Includes support for text preprocessors through a hook. This is required to index Chinese and Japanese, because these languages do not use spaces between words. An external utility can be used to split these into words through a simple wrapper module. Other uses could be spell checking (although it would have no UI). 7) Indexing is now regulated: only a certain amount of items will be indexed per cron run. This prevents PHP from running out of memory or timing out. This also makes the reindexing required for this patch automatic. I also added an index coverage estimate to the search admin screen. 8) Code cleanup! Moved all the search stuff from common.inc into search.module, rewired some hooks and simplified the functions used. The search form and results now also use valid XHTML and form_ functions. The search admin was moved from search/configure to admin/search for consistency. 9) Improved search output: we also show much more info per item: date, author, node type, amount of comments and a cool dynamic excerpt à la Google. The search form is now much more simpler and the help is only displayed as tips when no search results are found. 10) By moving all search logic to SQL, I was able to add a pager to the search results. This improves usability and performance dramatically.
2004-10-31 03:03:27 +00:00
* For example, mime_header_encode('tést.txt') returns "=?UTF-8?B?dMOpc3QudHh0?=".
*
* See http://www.rfc-editor.org/rfc/rfc2047.txt for more information.
*
* Notes:
* - Only encode strings that contain non-ASCII characters.
* - The chunks come in groupings of 4 bytes when using base64 encoding.
* - trim() is used to ensure that no extra spacing is added by chunk_split() or
* preg_replace().
* - Using \n as the chunk separator may cause problems on some systems and may
* have to be changed to \r\n or \r.
*/
function mime_header_encode($string, $charset = 'UTF-8') {
if (!preg_match('/^[\x20-\x7E]*$/', $string)) {
$chunk_size = 75 - 7 - strlen($charset);
$chunk_size -= $chunk_size % 4;
$string = trim(chunk_split(base64_encode($string), $chunk_size, "\n"));
$string = trim(preg_replace('/^(.*)$/m', " =?$charset?B?\\1?=", $string));
}
return $string;
}
- Patch #12232 by Steven/UnConed: search module improvements. 1) Clean up the text analyser: make it handle UTF-8 and all sorts of characters. The word splitter now does intelligent splitting into words and supports all Unicode characters. It has smart handling of acronyms, URLs, dates, ... 2) It now indexes the filtered output, which means it can take advantage of HTML tags. Meaningful tags (headers, strong, em, ...) are analysed and used to boost certain words scores. This has the side-effect of allowing the indexing of PHP nodes. 3) Link analyser for node links. The HTML analyser also checks for links. If they point to a node on the current site (handles path aliases) then the link's words are counted as part of the target node. This helps bring out commonly linked FAQs and answers to the top of the results. 4) Index comments along with the node. This means that the search can make a difference between a single node/comment about 'X' and a whole thread about 'X'. It also makes the search results much shorter and more relevant (before this patch, comments were even shown first). 5) We now keep track of total counts as well as a per item count for a word. This allows us to divide the word score by the total before adding up the scores for different words, and automatically makes noisewords have less influence than rare words. This dramatically improves the relevancy of multiword searches. This also makes the disadvantage of now using OR searching instead of AND searching less problematic. 6) Includes support for text preprocessors through a hook. This is required to index Chinese and Japanese, because these languages do not use spaces between words. An external utility can be used to split these into words through a simple wrapper module. Other uses could be spell checking (although it would have no UI). 7) Indexing is now regulated: only a certain amount of items will be indexed per cron run. This prevents PHP from running out of memory or timing out. This also makes the reindexing required for this patch automatic. I also added an index coverage estimate to the search admin screen. 8) Code cleanup! Moved all the search stuff from common.inc into search.module, rewired some hooks and simplified the functions used. The search form and results now also use valid XHTML and form_ functions. The search admin was moved from search/configure to admin/search for consistency. 9) Improved search output: we also show much more info per item: date, author, node type, amount of comments and a cool dynamic excerpt à la Google. The search form is now much more simpler and the help is only displayed as tips when no search results are found. 10) By moving all search logic to SQL, I was able to add a pager to the search results. This improves usability and performance dramatically.
2004-10-31 03:03:27 +00:00
/**
* Decode all HTML entities (including numerical ones) to regular UTF-8 bytes.
*
* @param $text
* The text to decode entities in.
* @param $exclude
* An array of characters which should not be decoded. For example,
* array('<', '&', '"'). This affects both named and numerical entities.
- Patch #12232 by Steven/UnConed: search module improvements. 1) Clean up the text analyser: make it handle UTF-8 and all sorts of characters. The word splitter now does intelligent splitting into words and supports all Unicode characters. It has smart handling of acronyms, URLs, dates, ... 2) It now indexes the filtered output, which means it can take advantage of HTML tags. Meaningful tags (headers, strong, em, ...) are analysed and used to boost certain words scores. This has the side-effect of allowing the indexing of PHP nodes. 3) Link analyser for node links. The HTML analyser also checks for links. If they point to a node on the current site (handles path aliases) then the link's words are counted as part of the target node. This helps bring out commonly linked FAQs and answers to the top of the results. 4) Index comments along with the node. This means that the search can make a difference between a single node/comment about 'X' and a whole thread about 'X'. It also makes the search results much shorter and more relevant (before this patch, comments were even shown first). 5) We now keep track of total counts as well as a per item count for a word. This allows us to divide the word score by the total before adding up the scores for different words, and automatically makes noisewords have less influence than rare words. This dramatically improves the relevancy of multiword searches. This also makes the disadvantage of now using OR searching instead of AND searching less problematic. 6) Includes support for text preprocessors through a hook. This is required to index Chinese and Japanese, because these languages do not use spaces between words. An external utility can be used to split these into words through a simple wrapper module. Other uses could be spell checking (although it would have no UI). 7) Indexing is now regulated: only a certain amount of items will be indexed per cron run. This prevents PHP from running out of memory or timing out. This also makes the reindexing required for this patch automatic. I also added an index coverage estimate to the search admin screen. 8) Code cleanup! Moved all the search stuff from common.inc into search.module, rewired some hooks and simplified the functions used. The search form and results now also use valid XHTML and form_ functions. The search admin was moved from search/configure to admin/search for consistency. 9) Improved search output: we also show much more info per item: date, author, node type, amount of comments and a cool dynamic excerpt à la Google. The search form is now much more simpler and the help is only displayed as tips when no search results are found. 10) By moving all search logic to SQL, I was able to add a pager to the search results. This improves usability and performance dramatically.
2004-10-31 03:03:27 +00:00
*/
function decode_entities($text, $exclude = array()) {
- Patch #12232 by Steven/UnConed: search module improvements. 1) Clean up the text analyser: make it handle UTF-8 and all sorts of characters. The word splitter now does intelligent splitting into words and supports all Unicode characters. It has smart handling of acronyms, URLs, dates, ... 2) It now indexes the filtered output, which means it can take advantage of HTML tags. Meaningful tags (headers, strong, em, ...) are analysed and used to boost certain words scores. This has the side-effect of allowing the indexing of PHP nodes. 3) Link analyser for node links. The HTML analyser also checks for links. If they point to a node on the current site (handles path aliases) then the link's words are counted as part of the target node. This helps bring out commonly linked FAQs and answers to the top of the results. 4) Index comments along with the node. This means that the search can make a difference between a single node/comment about 'X' and a whole thread about 'X'. It also makes the search results much shorter and more relevant (before this patch, comments were even shown first). 5) We now keep track of total counts as well as a per item count for a word. This allows us to divide the word score by the total before adding up the scores for different words, and automatically makes noisewords have less influence than rare words. This dramatically improves the relevancy of multiword searches. This also makes the disadvantage of now using OR searching instead of AND searching less problematic. 6) Includes support for text preprocessors through a hook. This is required to index Chinese and Japanese, because these languages do not use spaces between words. An external utility can be used to split these into words through a simple wrapper module. Other uses could be spell checking (although it would have no UI). 7) Indexing is now regulated: only a certain amount of items will be indexed per cron run. This prevents PHP from running out of memory or timing out. This also makes the reindexing required for this patch automatic. I also added an index coverage estimate to the search admin screen. 8) Code cleanup! Moved all the search stuff from common.inc into search.module, rewired some hooks and simplified the functions used. The search form and results now also use valid XHTML and form_ functions. The search admin was moved from search/configure to admin/search for consistency. 9) Improved search output: we also show much more info per item: date, author, node type, amount of comments and a cool dynamic excerpt à la Google. The search form is now much more simpler and the help is only displayed as tips when no search results are found. 10) By moving all search logic to SQL, I was able to add a pager to the search results. This improves usability and performance dramatically.
2004-10-31 03:03:27 +00:00
static $table;
// We store named entities in a table for quick processing.
if (!isset($table)) {
// Get all named HTML entities.
2005-02-09 17:33:53 +00:00
$table = array_flip(get_html_translation_table(HTML_ENTITIES));
// PHP gives us ISO-8859-1 data, we need UTF-8.
- Patch #12232 by Steven/UnConed: search module improvements. 1) Clean up the text analyser: make it handle UTF-8 and all sorts of characters. The word splitter now does intelligent splitting into words and supports all Unicode characters. It has smart handling of acronyms, URLs, dates, ... 2) It now indexes the filtered output, which means it can take advantage of HTML tags. Meaningful tags (headers, strong, em, ...) are analysed and used to boost certain words scores. This has the side-effect of allowing the indexing of PHP nodes. 3) Link analyser for node links. The HTML analyser also checks for links. If they point to a node on the current site (handles path aliases) then the link's words are counted as part of the target node. This helps bring out commonly linked FAQs and answers to the top of the results. 4) Index comments along with the node. This means that the search can make a difference between a single node/comment about 'X' and a whole thread about 'X'. It also makes the search results much shorter and more relevant (before this patch, comments were even shown first). 5) We now keep track of total counts as well as a per item count for a word. This allows us to divide the word score by the total before adding up the scores for different words, and automatically makes noisewords have less influence than rare words. This dramatically improves the relevancy of multiword searches. This also makes the disadvantage of now using OR searching instead of AND searching less problematic. 6) Includes support for text preprocessors through a hook. This is required to index Chinese and Japanese, because these languages do not use spaces between words. An external utility can be used to split these into words through a simple wrapper module. Other uses could be spell checking (although it would have no UI). 7) Indexing is now regulated: only a certain amount of items will be indexed per cron run. This prevents PHP from running out of memory or timing out. This also makes the reindexing required for this patch automatic. I also added an index coverage estimate to the search admin screen. 8) Code cleanup! Moved all the search stuff from common.inc into search.module, rewired some hooks and simplified the functions used. The search form and results now also use valid XHTML and form_ functions. The search admin was moved from search/configure to admin/search for consistency. 9) Improved search output: we also show much more info per item: date, author, node type, amount of comments and a cool dynamic excerpt à la Google. The search form is now much more simpler and the help is only displayed as tips when no search results are found. 10) By moving all search logic to SQL, I was able to add a pager to the search results. This improves usability and performance dramatically.
2004-10-31 03:03:27 +00:00
$table = array_map('utf8_encode', $table);
}
$text = strtr($text, array_diff($table, $exclude));
- Patch #12232 by Steven/UnConed: search module improvements. 1) Clean up the text analyser: make it handle UTF-8 and all sorts of characters. The word splitter now does intelligent splitting into words and supports all Unicode characters. It has smart handling of acronyms, URLs, dates, ... 2) It now indexes the filtered output, which means it can take advantage of HTML tags. Meaningful tags (headers, strong, em, ...) are analysed and used to boost certain words scores. This has the side-effect of allowing the indexing of PHP nodes. 3) Link analyser for node links. The HTML analyser also checks for links. If they point to a node on the current site (handles path aliases) then the link's words are counted as part of the target node. This helps bring out commonly linked FAQs and answers to the top of the results. 4) Index comments along with the node. This means that the search can make a difference between a single node/comment about 'X' and a whole thread about 'X'. It also makes the search results much shorter and more relevant (before this patch, comments were even shown first). 5) We now keep track of total counts as well as a per item count for a word. This allows us to divide the word score by the total before adding up the scores for different words, and automatically makes noisewords have less influence than rare words. This dramatically improves the relevancy of multiword searches. This also makes the disadvantage of now using OR searching instead of AND searching less problematic. 6) Includes support for text preprocessors through a hook. This is required to index Chinese and Japanese, because these languages do not use spaces between words. An external utility can be used to split these into words through a simple wrapper module. Other uses could be spell checking (although it would have no UI). 7) Indexing is now regulated: only a certain amount of items will be indexed per cron run. This prevents PHP from running out of memory or timing out. This also makes the reindexing required for this patch automatic. I also added an index coverage estimate to the search admin screen. 8) Code cleanup! Moved all the search stuff from common.inc into search.module, rewired some hooks and simplified the functions used. The search form and results now also use valid XHTML and form_ functions. The search admin was moved from search/configure to admin/search for consistency. 9) Improved search output: we also show much more info per item: date, author, node type, amount of comments and a cool dynamic excerpt à la Google. The search form is now much more simpler and the help is only displayed as tips when no search results are found. 10) By moving all search logic to SQL, I was able to add a pager to the search results. This improves usability and performance dramatically.
2004-10-31 03:03:27 +00:00
// Any remaining entities are numerical. Use a regexp to replace them.
return preg_replace('/&#(x?)([A-Za-z0-9]+);/e', '_decode_entities("$1", "$2", "$0", $exclude)', $text);
- Patch #12232 by Steven/UnConed: search module improvements. 1) Clean up the text analyser: make it handle UTF-8 and all sorts of characters. The word splitter now does intelligent splitting into words and supports all Unicode characters. It has smart handling of acronyms, URLs, dates, ... 2) It now indexes the filtered output, which means it can take advantage of HTML tags. Meaningful tags (headers, strong, em, ...) are analysed and used to boost certain words scores. This has the side-effect of allowing the indexing of PHP nodes. 3) Link analyser for node links. The HTML analyser also checks for links. If they point to a node on the current site (handles path aliases) then the link's words are counted as part of the target node. This helps bring out commonly linked FAQs and answers to the top of the results. 4) Index comments along with the node. This means that the search can make a difference between a single node/comment about 'X' and a whole thread about 'X'. It also makes the search results much shorter and more relevant (before this patch, comments were even shown first). 5) We now keep track of total counts as well as a per item count for a word. This allows us to divide the word score by the total before adding up the scores for different words, and automatically makes noisewords have less influence than rare words. This dramatically improves the relevancy of multiword searches. This also makes the disadvantage of now using OR searching instead of AND searching less problematic. 6) Includes support for text preprocessors through a hook. This is required to index Chinese and Japanese, because these languages do not use spaces between words. An external utility can be used to split these into words through a simple wrapper module. Other uses could be spell checking (although it would have no UI). 7) Indexing is now regulated: only a certain amount of items will be indexed per cron run. This prevents PHP from running out of memory or timing out. This also makes the reindexing required for this patch automatic. I also added an index coverage estimate to the search admin screen. 8) Code cleanup! Moved all the search stuff from common.inc into search.module, rewired some hooks and simplified the functions used. The search form and results now also use valid XHTML and form_ functions. The search admin was moved from search/configure to admin/search for consistency. 9) Improved search output: we also show much more info per item: date, author, node type, amount of comments and a cool dynamic excerpt à la Google. The search form is now much more simpler and the help is only displayed as tips when no search results are found. 10) By moving all search logic to SQL, I was able to add a pager to the search results. This improves usability and performance dramatically.
2004-10-31 03:03:27 +00:00
}
/**
* Helper function for decode_entities
*/
function _decode_entities($hex, $codepoint, $original, $exclude) {
- Patch #12232 by Steven/UnConed: search module improvements. 1) Clean up the text analyser: make it handle UTF-8 and all sorts of characters. The word splitter now does intelligent splitting into words and supports all Unicode characters. It has smart handling of acronyms, URLs, dates, ... 2) It now indexes the filtered output, which means it can take advantage of HTML tags. Meaningful tags (headers, strong, em, ...) are analysed and used to boost certain words scores. This has the side-effect of allowing the indexing of PHP nodes. 3) Link analyser for node links. The HTML analyser also checks for links. If they point to a node on the current site (handles path aliases) then the link's words are counted as part of the target node. This helps bring out commonly linked FAQs and answers to the top of the results. 4) Index comments along with the node. This means that the search can make a difference between a single node/comment about 'X' and a whole thread about 'X'. It also makes the search results much shorter and more relevant (before this patch, comments were even shown first). 5) We now keep track of total counts as well as a per item count for a word. This allows us to divide the word score by the total before adding up the scores for different words, and automatically makes noisewords have less influence than rare words. This dramatically improves the relevancy of multiword searches. This also makes the disadvantage of now using OR searching instead of AND searching less problematic. 6) Includes support for text preprocessors through a hook. This is required to index Chinese and Japanese, because these languages do not use spaces between words. An external utility can be used to split these into words through a simple wrapper module. Other uses could be spell checking (although it would have no UI). 7) Indexing is now regulated: only a certain amount of items will be indexed per cron run. This prevents PHP from running out of memory or timing out. This also makes the reindexing required for this patch automatic. I also added an index coverage estimate to the search admin screen. 8) Code cleanup! Moved all the search stuff from common.inc into search.module, rewired some hooks and simplified the functions used. The search form and results now also use valid XHTML and form_ functions. The search admin was moved from search/configure to admin/search for consistency. 9) Improved search output: we also show much more info per item: date, author, node type, amount of comments and a cool dynamic excerpt à la Google. The search form is now much more simpler and the help is only displayed as tips when no search results are found. 10) By moving all search logic to SQL, I was able to add a pager to the search results. This improves usability and performance dramatically.
2004-10-31 03:03:27 +00:00
if ($hex != '') {
$codepoint = base_convert($codepoint, 16, 10);
}
if ($codepoint < 0x80) {
$str = chr($codepoint);
- Patch #12232 by Steven/UnConed: search module improvements. 1) Clean up the text analyser: make it handle UTF-8 and all sorts of characters. The word splitter now does intelligent splitting into words and supports all Unicode characters. It has smart handling of acronyms, URLs, dates, ... 2) It now indexes the filtered output, which means it can take advantage of HTML tags. Meaningful tags (headers, strong, em, ...) are analysed and used to boost certain words scores. This has the side-effect of allowing the indexing of PHP nodes. 3) Link analyser for node links. The HTML analyser also checks for links. If they point to a node on the current site (handles path aliases) then the link's words are counted as part of the target node. This helps bring out commonly linked FAQs and answers to the top of the results. 4) Index comments along with the node. This means that the search can make a difference between a single node/comment about 'X' and a whole thread about 'X'. It also makes the search results much shorter and more relevant (before this patch, comments were even shown first). 5) We now keep track of total counts as well as a per item count for a word. This allows us to divide the word score by the total before adding up the scores for different words, and automatically makes noisewords have less influence than rare words. This dramatically improves the relevancy of multiword searches. This also makes the disadvantage of now using OR searching instead of AND searching less problematic. 6) Includes support for text preprocessors through a hook. This is required to index Chinese and Japanese, because these languages do not use spaces between words. An external utility can be used to split these into words through a simple wrapper module. Other uses could be spell checking (although it would have no UI). 7) Indexing is now regulated: only a certain amount of items will be indexed per cron run. This prevents PHP from running out of memory or timing out. This also makes the reindexing required for this patch automatic. I also added an index coverage estimate to the search admin screen. 8) Code cleanup! Moved all the search stuff from common.inc into search.module, rewired some hooks and simplified the functions used. The search form and results now also use valid XHTML and form_ functions. The search admin was moved from search/configure to admin/search for consistency. 9) Improved search output: we also show much more info per item: date, author, node type, amount of comments and a cool dynamic excerpt à la Google. The search form is now much more simpler and the help is only displayed as tips when no search results are found. 10) By moving all search logic to SQL, I was able to add a pager to the search results. This improves usability and performance dramatically.
2004-10-31 03:03:27 +00:00
}
else if ($codepoint < 0x800) {
$str = chr(0xC0 | ($codepoint >> 6))
- Patch #12232 by Steven/UnConed: search module improvements. 1) Clean up the text analyser: make it handle UTF-8 and all sorts of characters. The word splitter now does intelligent splitting into words and supports all Unicode characters. It has smart handling of acronyms, URLs, dates, ... 2) It now indexes the filtered output, which means it can take advantage of HTML tags. Meaningful tags (headers, strong, em, ...) are analysed and used to boost certain words scores. This has the side-effect of allowing the indexing of PHP nodes. 3) Link analyser for node links. The HTML analyser also checks for links. If they point to a node on the current site (handles path aliases) then the link's words are counted as part of the target node. This helps bring out commonly linked FAQs and answers to the top of the results. 4) Index comments along with the node. This means that the search can make a difference between a single node/comment about 'X' and a whole thread about 'X'. It also makes the search results much shorter and more relevant (before this patch, comments were even shown first). 5) We now keep track of total counts as well as a per item count for a word. This allows us to divide the word score by the total before adding up the scores for different words, and automatically makes noisewords have less influence than rare words. This dramatically improves the relevancy of multiword searches. This also makes the disadvantage of now using OR searching instead of AND searching less problematic. 6) Includes support for text preprocessors through a hook. This is required to index Chinese and Japanese, because these languages do not use spaces between words. An external utility can be used to split these into words through a simple wrapper module. Other uses could be spell checking (although it would have no UI). 7) Indexing is now regulated: only a certain amount of items will be indexed per cron run. This prevents PHP from running out of memory or timing out. This also makes the reindexing required for this patch automatic. I also added an index coverage estimate to the search admin screen. 8) Code cleanup! Moved all the search stuff from common.inc into search.module, rewired some hooks and simplified the functions used. The search form and results now also use valid XHTML and form_ functions. The search admin was moved from search/configure to admin/search for consistency. 9) Improved search output: we also show much more info per item: date, author, node type, amount of comments and a cool dynamic excerpt à la Google. The search form is now much more simpler and the help is only displayed as tips when no search results are found. 10) By moving all search logic to SQL, I was able to add a pager to the search results. This improves usability and performance dramatically.
2004-10-31 03:03:27 +00:00
. chr(0x80 | ($codepoint & 0x3F));
}
else if ($codepoint < 0x10000) {
$str = chr(0xE0 | ( $codepoint >> 12))
- Patch #12232 by Steven/UnConed: search module improvements. 1) Clean up the text analyser: make it handle UTF-8 and all sorts of characters. The word splitter now does intelligent splitting into words and supports all Unicode characters. It has smart handling of acronyms, URLs, dates, ... 2) It now indexes the filtered output, which means it can take advantage of HTML tags. Meaningful tags (headers, strong, em, ...) are analysed and used to boost certain words scores. This has the side-effect of allowing the indexing of PHP nodes. 3) Link analyser for node links. The HTML analyser also checks for links. If they point to a node on the current site (handles path aliases) then the link's words are counted as part of the target node. This helps bring out commonly linked FAQs and answers to the top of the results. 4) Index comments along with the node. This means that the search can make a difference between a single node/comment about 'X' and a whole thread about 'X'. It also makes the search results much shorter and more relevant (before this patch, comments were even shown first). 5) We now keep track of total counts as well as a per item count for a word. This allows us to divide the word score by the total before adding up the scores for different words, and automatically makes noisewords have less influence than rare words. This dramatically improves the relevancy of multiword searches. This also makes the disadvantage of now using OR searching instead of AND searching less problematic. 6) Includes support for text preprocessors through a hook. This is required to index Chinese and Japanese, because these languages do not use spaces between words. An external utility can be used to split these into words through a simple wrapper module. Other uses could be spell checking (although it would have no UI). 7) Indexing is now regulated: only a certain amount of items will be indexed per cron run. This prevents PHP from running out of memory or timing out. This also makes the reindexing required for this patch automatic. I also added an index coverage estimate to the search admin screen. 8) Code cleanup! Moved all the search stuff from common.inc into search.module, rewired some hooks and simplified the functions used. The search form and results now also use valid XHTML and form_ functions. The search admin was moved from search/configure to admin/search for consistency. 9) Improved search output: we also show much more info per item: date, author, node type, amount of comments and a cool dynamic excerpt à la Google. The search form is now much more simpler and the help is only displayed as tips when no search results are found. 10) By moving all search logic to SQL, I was able to add a pager to the search results. This improves usability and performance dramatically.
2004-10-31 03:03:27 +00:00
. chr(0x80 | (($codepoint >> 6) & 0x3F))
. chr(0x80 | ( $codepoint & 0x3F));
}
else if ($codepoint < 0x200000) {
$str = chr(0xF0 | ( $codepoint >> 18))
- Patch #12232 by Steven/UnConed: search module improvements. 1) Clean up the text analyser: make it handle UTF-8 and all sorts of characters. The word splitter now does intelligent splitting into words and supports all Unicode characters. It has smart handling of acronyms, URLs, dates, ... 2) It now indexes the filtered output, which means it can take advantage of HTML tags. Meaningful tags (headers, strong, em, ...) are analysed and used to boost certain words scores. This has the side-effect of allowing the indexing of PHP nodes. 3) Link analyser for node links. The HTML analyser also checks for links. If they point to a node on the current site (handles path aliases) then the link's words are counted as part of the target node. This helps bring out commonly linked FAQs and answers to the top of the results. 4) Index comments along with the node. This means that the search can make a difference between a single node/comment about 'X' and a whole thread about 'X'. It also makes the search results much shorter and more relevant (before this patch, comments were even shown first). 5) We now keep track of total counts as well as a per item count for a word. This allows us to divide the word score by the total before adding up the scores for different words, and automatically makes noisewords have less influence than rare words. This dramatically improves the relevancy of multiword searches. This also makes the disadvantage of now using OR searching instead of AND searching less problematic. 6) Includes support for text preprocessors through a hook. This is required to index Chinese and Japanese, because these languages do not use spaces between words. An external utility can be used to split these into words through a simple wrapper module. Other uses could be spell checking (although it would have no UI). 7) Indexing is now regulated: only a certain amount of items will be indexed per cron run. This prevents PHP from running out of memory or timing out. This also makes the reindexing required for this patch automatic. I also added an index coverage estimate to the search admin screen. 8) Code cleanup! Moved all the search stuff from common.inc into search.module, rewired some hooks and simplified the functions used. The search form and results now also use valid XHTML and form_ functions. The search admin was moved from search/configure to admin/search for consistency. 9) Improved search output: we also show much more info per item: date, author, node type, amount of comments and a cool dynamic excerpt à la Google. The search form is now much more simpler and the help is only displayed as tips when no search results are found. 10) By moving all search logic to SQL, I was able to add a pager to the search results. This improves usability and performance dramatically.
2004-10-31 03:03:27 +00:00
. chr(0x80 | (($codepoint >> 12) & 0x3F))
. chr(0x80 | (($codepoint >> 6) & 0x3F))
. chr(0x80 | ( $codepoint & 0x3F));
}
if (in_array($str, $exclude)) {
return $original;
}
else {
return $str;
}
- Patch #12232 by Steven/UnConed: search module improvements. 1) Clean up the text analyser: make it handle UTF-8 and all sorts of characters. The word splitter now does intelligent splitting into words and supports all Unicode characters. It has smart handling of acronyms, URLs, dates, ... 2) It now indexes the filtered output, which means it can take advantage of HTML tags. Meaningful tags (headers, strong, em, ...) are analysed and used to boost certain words scores. This has the side-effect of allowing the indexing of PHP nodes. 3) Link analyser for node links. The HTML analyser also checks for links. If they point to a node on the current site (handles path aliases) then the link's words are counted as part of the target node. This helps bring out commonly linked FAQs and answers to the top of the results. 4) Index comments along with the node. This means that the search can make a difference between a single node/comment about 'X' and a whole thread about 'X'. It also makes the search results much shorter and more relevant (before this patch, comments were even shown first). 5) We now keep track of total counts as well as a per item count for a word. This allows us to divide the word score by the total before adding up the scores for different words, and automatically makes noisewords have less influence than rare words. This dramatically improves the relevancy of multiword searches. This also makes the disadvantage of now using OR searching instead of AND searching less problematic. 6) Includes support for text preprocessors through a hook. This is required to index Chinese and Japanese, because these languages do not use spaces between words. An external utility can be used to split these into words through a simple wrapper module. Other uses could be spell checking (although it would have no UI). 7) Indexing is now regulated: only a certain amount of items will be indexed per cron run. This prevents PHP from running out of memory or timing out. This also makes the reindexing required for this patch automatic. I also added an index coverage estimate to the search admin screen. 8) Code cleanup! Moved all the search stuff from common.inc into search.module, rewired some hooks and simplified the functions used. The search form and results now also use valid XHTML and form_ functions. The search admin was moved from search/configure to admin/search for consistency. 9) Improved search output: we also show much more info per item: date, author, node type, amount of comments and a cool dynamic excerpt à la Google. The search form is now much more simpler and the help is only displayed as tips when no search results are found. 10) By moving all search logic to SQL, I was able to add a pager to the search results. This improves usability and performance dramatically.
2004-10-31 03:03:27 +00:00
}
/**
* Count the amount of characters in a UTF-8 string. This is less than or
* equal to the byte count.
*/
function string_length(&$text) {
return strlen(preg_replace("/[\x80-\xBF]/", '', $text));
}
The Input formats - filter patch has landed. I still need to make update instructions for modules and update the hook docs. Here's an overview of the changes: 1) Multiple Input formats: they are complete filter configurations (what filters to use, in what order and with which settings). Input formats are admin-definable, and usage of them is role-dependant. For example, you can set it up so that regular users can only use limited HTML, while admins can free HTML without any tag limitations. The input format can be chosen per content item (nodes, comments, blocks, ...) when you add/edit them. If only a single format is available, there is no choice, and nothing changes with before. The default install (and the upgrade) contains a basic set of formats which should satisfy the average user's needs. 2) Filters have toggles Because now you might want to enable a filter only on some input formats, an explicit toggle is provided by the filter system. Modules do not need to worry about it and filters that still have their own on/off switch should get rid of it. 3) Multiple filters per module This was necessary to accomodate the next change, and it's also a logical extension of the filter system. 4) Embedded PHP is now a filter Thanks to the multiple input formats, I was able to move the 'embedded PHP' feature from block.module, page.module and book.module into a simple filter which executes PHP code. This filter is part of filter.module, and by default there is an input format 'PHP', restricted to the administrator only, which contains this filter. This change means that block.module now passes custom block contents through the filter system. As well as from reducing code duplication and avoiding two type selectors for page/book nodes, you can now combine PHP code with other filters. 5) User-supplied PHP code now requires <?php ?> tags. This is required for teasers to work with PHP code. Because PHP evaluation is now just another step in the filter process, we can't do this. Also, because teasers are generated before filtering, this would result in errors when the teaser generation would cut off a piece of PHP code. Also, regular PHP syntax explicitly includes the <?php ?> tags for PHP files, so it makes sense to use the same convention for embedded PHP in Drupal. 6) Filter caching was added. Benchmarking shows that even for a simple setup (basic html filtering + legacy URL rewriting), filtercache can offer speedups. Unlike the old filtercache, this uses the normal cache table. 7) Filtertips were moved from help into a hook_filter_tips(). This was required to accomodate the fact that there are multiple filters per module, and that filter settings are format dependant. Shoehorning filter tips into _help was ugly and silly. The display of the filter tips is done through the input format selector, so filter_tips_short() no longer exists. 8) A more intelligent linebreak convertor was added, which doesn't stop working if you use block-level tags and which adds <p> tags.
2004-08-10 18:34:29 +00:00
/**
* Evaluate a string of PHP code.
The Input formats - filter patch has landed. I still need to make update instructions for modules and update the hook docs. Here's an overview of the changes: 1) Multiple Input formats: they are complete filter configurations (what filters to use, in what order and with which settings). Input formats are admin-definable, and usage of them is role-dependant. For example, you can set it up so that regular users can only use limited HTML, while admins can free HTML without any tag limitations. The input format can be chosen per content item (nodes, comments, blocks, ...) when you add/edit them. If only a single format is available, there is no choice, and nothing changes with before. The default install (and the upgrade) contains a basic set of formats which should satisfy the average user's needs. 2) Filters have toggles Because now you might want to enable a filter only on some input formats, an explicit toggle is provided by the filter system. Modules do not need to worry about it and filters that still have their own on/off switch should get rid of it. 3) Multiple filters per module This was necessary to accomodate the next change, and it's also a logical extension of the filter system. 4) Embedded PHP is now a filter Thanks to the multiple input formats, I was able to move the 'embedded PHP' feature from block.module, page.module and book.module into a simple filter which executes PHP code. This filter is part of filter.module, and by default there is an input format 'PHP', restricted to the administrator only, which contains this filter. This change means that block.module now passes custom block contents through the filter system. As well as from reducing code duplication and avoiding two type selectors for page/book nodes, you can now combine PHP code with other filters. 5) User-supplied PHP code now requires <?php ?> tags. This is required for teasers to work with PHP code. Because PHP evaluation is now just another step in the filter process, we can't do this. Also, because teasers are generated before filtering, this would result in errors when the teaser generation would cut off a piece of PHP code. Also, regular PHP syntax explicitly includes the <?php ?> tags for PHP files, so it makes sense to use the same convention for embedded PHP in Drupal. 6) Filter caching was added. Benchmarking shows that even for a simple setup (basic html filtering + legacy URL rewriting), filtercache can offer speedups. Unlike the old filtercache, this uses the normal cache table. 7) Filtertips were moved from help into a hook_filter_tips(). This was required to accomodate the fact that there are multiple filters per module, and that filter settings are format dependant. Shoehorning filter tips into _help was ugly and silly. The display of the filter tips is done through the input format selector, so filter_tips_short() no longer exists. 8) A more intelligent linebreak convertor was added, which doesn't stop working if you use block-level tags and which adds <p> tags.
2004-08-10 18:34:29 +00:00
*
* This is a wrapper around PHP's eval(). It uses output buffering to capture both
* returned and printed text. Unlike eval(), we require code to be surrounded by
* <?php ?> tags; in other words, we evaluate the code as if it were a stand-alone
* PHP file.
*
* Using this wrapper also ensures that the PHP code which is evaluated can not
* overwrite any variables in the calling code, unlike a regular eval() call.
*
* @param $code
* The code to evaluate.
* @return
* A string containing the printed output of the code, followed by the returned
* output of the code.
The Input formats - filter patch has landed. I still need to make update instructions for modules and update the hook docs. Here's an overview of the changes: 1) Multiple Input formats: they are complete filter configurations (what filters to use, in what order and with which settings). Input formats are admin-definable, and usage of them is role-dependant. For example, you can set it up so that regular users can only use limited HTML, while admins can free HTML without any tag limitations. The input format can be chosen per content item (nodes, comments, blocks, ...) when you add/edit them. If only a single format is available, there is no choice, and nothing changes with before. The default install (and the upgrade) contains a basic set of formats which should satisfy the average user's needs. 2) Filters have toggles Because now you might want to enable a filter only on some input formats, an explicit toggle is provided by the filter system. Modules do not need to worry about it and filters that still have their own on/off switch should get rid of it. 3) Multiple filters per module This was necessary to accomodate the next change, and it's also a logical extension of the filter system. 4) Embedded PHP is now a filter Thanks to the multiple input formats, I was able to move the 'embedded PHP' feature from block.module, page.module and book.module into a simple filter which executes PHP code. This filter is part of filter.module, and by default there is an input format 'PHP', restricted to the administrator only, which contains this filter. This change means that block.module now passes custom block contents through the filter system. As well as from reducing code duplication and avoiding two type selectors for page/book nodes, you can now combine PHP code with other filters. 5) User-supplied PHP code now requires <?php ?> tags. This is required for teasers to work with PHP code. Because PHP evaluation is now just another step in the filter process, we can't do this. Also, because teasers are generated before filtering, this would result in errors when the teaser generation would cut off a piece of PHP code. Also, regular PHP syntax explicitly includes the <?php ?> tags for PHP files, so it makes sense to use the same convention for embedded PHP in Drupal. 6) Filter caching was added. Benchmarking shows that even for a simple setup (basic html filtering + legacy URL rewriting), filtercache can offer speedups. Unlike the old filtercache, this uses the normal cache table. 7) Filtertips were moved from help into a hook_filter_tips(). This was required to accomodate the fact that there are multiple filters per module, and that filter settings are format dependant. Shoehorning filter tips into _help was ugly and silly. The display of the filter tips is done through the input format selector, so filter_tips_short() no longer exists. 8) A more intelligent linebreak convertor was added, which doesn't stop working if you use block-level tags and which adds <p> tags.
2004-08-10 18:34:29 +00:00
*/
function drupal_eval($code) {
ob_start();
print eval('?>'. $code);
$output = ob_get_contents();
ob_end_clean();
return $output;
The Input formats - filter patch has landed. I still need to make update instructions for modules and update the hook docs. Here's an overview of the changes: 1) Multiple Input formats: they are complete filter configurations (what filters to use, in what order and with which settings). Input formats are admin-definable, and usage of them is role-dependant. For example, you can set it up so that regular users can only use limited HTML, while admins can free HTML without any tag limitations. The input format can be chosen per content item (nodes, comments, blocks, ...) when you add/edit them. If only a single format is available, there is no choice, and nothing changes with before. The default install (and the upgrade) contains a basic set of formats which should satisfy the average user's needs. 2) Filters have toggles Because now you might want to enable a filter only on some input formats, an explicit toggle is provided by the filter system. Modules do not need to worry about it and filters that still have their own on/off switch should get rid of it. 3) Multiple filters per module This was necessary to accomodate the next change, and it's also a logical extension of the filter system. 4) Embedded PHP is now a filter Thanks to the multiple input formats, I was able to move the 'embedded PHP' feature from block.module, page.module and book.module into a simple filter which executes PHP code. This filter is part of filter.module, and by default there is an input format 'PHP', restricted to the administrator only, which contains this filter. This change means that block.module now passes custom block contents through the filter system. As well as from reducing code duplication and avoiding two type selectors for page/book nodes, you can now combine PHP code with other filters. 5) User-supplied PHP code now requires <?php ?> tags. This is required for teasers to work with PHP code. Because PHP evaluation is now just another step in the filter process, we can't do this. Also, because teasers are generated before filtering, this would result in errors when the teaser generation would cut off a piece of PHP code. Also, regular PHP syntax explicitly includes the <?php ?> tags for PHP files, so it makes sense to use the same convention for embedded PHP in Drupal. 6) Filter caching was added. Benchmarking shows that even for a simple setup (basic html filtering + legacy URL rewriting), filtercache can offer speedups. Unlike the old filtercache, this uses the normal cache table. 7) Filtertips were moved from help into a hook_filter_tips(). This was required to accomodate the fact that there are multiple filters per module, and that filter settings are format dependant. Shoehorning filter tips into _help was ugly and silly. The display of the filter tips is done through the input format selector, so filter_tips_short() no longer exists. 8) A more intelligent linebreak convertor was added, which doesn't stop working if you use block-level tags and which adds <p> tags.
2004-08-10 18:34:29 +00:00
}
/**
* Returns the path to a system item (module, theme, etc.).
*
* @param $type
* The type of the item (i.e. theme, theme_engine, module).
* @param $name
* The name of the item for which the path is requested.
*
* @return
* The path to the requested item.
*/
function drupal_get_path($type, $name) {
return dirname(drupal_get_filename($type, $name));
}
/**
* Provide a substitute clone() function for PHP4.
*/
if (version_compare(phpversion(), '5.0') < 0) {
eval('
function clone($object) {
return $object;
}
');
}
// Set the Drupal custom error handler.
set_error_handler('error_handler');
include_once 'includes/theme.inc';
include_once 'includes/pager.inc';
include_once 'includes/menu.inc';
include_once 'includes/tablesort.inc';
include_once 'includes/file.inc';
2004-08-17 18:40:59 +00:00
include_once 'includes/xmlrpc.inc';
include_once 'includes/image.inc';
// Emit the correct charset HTTP header.
drupal_set_header('Content-Type: text/html; charset=utf-8');
- Bugfix: renamed the SQL field 'types' to 'nodes' because 'types' is a reserved keyword in MySQL 4. This fixes critical bug #1618. Patch by Marco. ==> This fix requires to run update.php! - Bugfix: made sessions work without warnings when register_globals is turned off. The solution is to use $_SESSION instead of session_register(). This fixes critical bug #1797. Patch by Marco. - Bugfix: sometimes error messages where being discarded when previewing a node. Patch by Craig Courtney. - Bugfix: fixed charset problems. This fixes critical bug #1549. Patch '0023.charset.patch' by Al. - Code improvements: removed some dead code from the comment module. Patch by Marco. - Documentation improvements: polished the node module help texts and form descriptions. Patch '0019.node.module.help.patch' by Al. - CSS improvements all over the map! Patch '0021.more.css.patch' by Al. - GUI improvements: improved the position of Druplicon in the admin menu. Patch '0020.admin.logo.patch' by Al. - GUI improvements: new logos for theme Marvin and theme UnConeD. Logos by Kristjan Jansen. - GUI improvements: small changes to the output emitted by the profile module. Suggestions by Steven Wittens. - GUI improvements: small fixes to Xtemplate. Patch '0022.xtemplate.css.patch' by Al. TODO: - Some modules such as the buddy list module and the annotation module in the contributions repository are also using session_register(). They should be updated. We should setup a task on Drupal. - There is code emitting '<div align="right">' which doesn't validate. - Does our XML feeds validate with the charset changes? - The forum module's SQL doesn't work properly on PostgreSQL.
2003-06-04 18:24:39 +00:00
// Initialize $_GET['q'] prior to loading modules and invoking hook_init().
if (!empty($_GET['q'])) {
$_GET['q'] = drupal_get_normal_path(trim($_GET['q'], '/'));
}
else {
$_GET['q'] = drupal_get_normal_path(variable_get('site_frontpage', 'node'));
}
// Initialize all enabled modules.
module_init();
2004-12-28 11:04:24 +00:00
if (!user_access('bypass input data check')) {
// We can't use $_REQUEST because it consists of the contents of $_POST,
2004-12-28 11:04:24 +00:00
// $_GET and $_COOKIE: if any of the input arrays share a key, only one
// value will be verified.
if (!valid_input_data($_GET)
|| !valid_input_data($_POST)
2004-12-28 11:04:24 +00:00
|| !valid_input_data($_COOKIE)
|| !valid_input_data($_FILES)) {
die('Terminated request because of suspicious input data.');
}
}
// Initialize the localization system.
$locale = locale_initialize();
// Initialize the enabled theme.
$theme = init_theme();
2003-03-04 15:10:37 +00:00
?>