[github/wallabag/wallabag.git] / inc / 3rdparty / config.php

<?php\r
/* Full-Text RSS config */\r
\r
// ......IMPORTANT......................................\r
// .....................................................\r
// Please do not change this file (config.php) directly.\r
// Save a copy as custom_config.php and make your\r
// changes to that instead. It will automatically\r
// override anything in config.php. Because config.php\r
// always gets loaded anyway, you can simply specify\r
// options you'd like to override in custom_config.php.\r
// .....................................................\r
\r
global $options;\r
\r
// Create config object\r
if (!isset($options)) $options = new stdClass();\r
\r
// Enable service\r
// ----------------------\r
// Set this to false if you want to disable the service.\r
// If set to false, no feed is produced and users will\r
// be told that the service is disabled.\r
$options->enabled = true;\r
\r
// Debug mode\r
// ----------------------\r
// Enable or disable debugging. When enabled debugging works by passing\r
// &debug to the makefulltextfeed.php querystring.\r
// Valid values:\r
// true or 'user' (default) - let user decide\r
// 'admin' - debug works only for logged in admin users\r
// false - disabled\r
$options->debug = true;\r
\r
// Default entries (without access key)\r
// ----------------------\r
// The number of feed items to process when no API key is supplied\r
// and no &max=x value is supplied in the querystring.\r
$options->default_entries = 5;\r
\r
// Max entries (without access key)\r
// ----------------------\r
// The maximum number of feed items to process when no access key is supplied.\r
// This limits the user-supplied &max=x value. For example, if the user\r
// asks for 20 items to be processed (&max=20), if max_entries is set to\r
// 10, only 10 will be processed.\r
$options->max_entries = 10;\r
\r
// Full content\r
// ----------------------\r
// By default Full-Text RSS includes the extracted content in the output.\r
// You can exclude this from the output by passing '&content=0' in the querystring.\r
//\r
// Possible values...\r
// Always include: true\r
// Never include: false\r
// Include unless user overrides (&content=0): 'user' (default)\r
//\r
// Note: currently this does not disable full content extraction. It simply omits it\r
// from the output.\r
$options->content = 'user';\r
\r
// Excerpts\r
// ----------------------\r
// By default Full-Text RSS does not include excerpts in the output.\r
// You can enable this by passing '&summary=1' in the querystring.\r
// This will include a plain text excerpt from the extracted content.\r
//\r
// Possible values...\r
// Always include: true (recommended for new users)\r
// Never include: false\r
// Don't include unless user overrides (&summary=1): 'user' (default)\r
//\r
// Important: if both content and excerpts are requested, the excerpt will be\r
// placed in the description element and the full content inside content:encoded.\r
// If excerpts are not requested, the full content will go inside the description element.\r
//\r
// Why are we not returning both excerpts and content by default?\r
// Mainly for backward compatibility.\r
// Excerpts should appear in the feed item's description element. Previous versions\r
// of Full-Text RSS did not return excerpts, so the description element was always\r
// used for the full content (as recommended by the RSS advisory). When returning both,\r
// we need somewhere else to place the content (content:encoded).\r
// Having both enabled should not create any problems for news readers, but it may create\r
// problems for developers upgrading from one of our earlier versions who may now find\r
// their applications are returning excerpts instead of the full content they were\r
// expecting. To avoid such surprises for users who are upgrading Full-Text RSS,\r
// excerpts must be explicitly requested in the querystring by default.\r
//\r
// Why not use a different element name for excerpts?\r
// According to the RSS advisory:\r
// "Publishers who employ summaries should store the summary in description and\r
// the full content in content:encoded, ordering description first within the item.\r
// On items with no summary, the full content should be stored in description."\r
// See: http://www.rssboard.org/rss-profile#namespace-elements-content-encoded\r
//\r
// For more consistent element naming, we recommend new users set this option to true.\r
// The full content can still be excluded via the querystring, but the element names\r
// will not change: when $options->summary = true, the description element will always\r
// be reserved for the excerpt and content:encoded always for full content.\r
$options->summary = 'user';\r
\r
// Rewrite relative URLs\r
// ----------------------\r
// With this enabled relative URLs found in the extracted content\r
// block are automatically rewritten as absolute URLs.\r
$options->rewrite_relative_urls = true;\r
\r
// Exclude items if extraction fails\r
// ---------------------------------\r
// Excludes items from the resulting feed\r
// if we cannot extract any content from the\r
// item URL.\r
// Possible values...\r
// Enable: true\r
// Disable: false (default)\r
// User decides: 'user' (this option will appear on the form)\r
$options->exclude_items_on_fail = 'user';\r
\r
// Enable multi-page support\r
// -------------------------\r
// If enabled, we will try to follow next page links on multi-page articles.\r
// Currently this only happens for sites where next_page_link has been defined\r
// in a site config file.\r
$options->multipage = true;\r
\r
// Enable caching\r
// ----------------------\r
// Enable this if you'd like to cache results\r
// for 10 minutes. Cache files are written to disk (in cache/ subfolders\r
// - which must be writable).\r
// Initially it's best to keep this disabled to make sure everything works\r
// as expected. If you have APC enabled, please also see smart_cache in the\r
// advanced section.\r
$options->caching = false;\r
\r
// Cache directory\r
// ----------------------\r
// Only used if caching is true\r
$options->cache_dir = dirname(__FILE__).'/cache';\r
\r
// Message to prepend (without access key)\r
// ----------------------\r
// HTML to insert at the beginning of each feed item when no access key is supplied.\r
// Substitution tags:\r
// {url} - Feed item URL\r
// {effective-url} - Feed item URL after we've followed all redirects\r
$options->message_to_prepend = '';\r
\r
// Message to append (without access key)\r
// ----------------------\r
// HTML to insert at the end of each feed item when no access key is supplied.\r
// Substitution tags:\r
// {url} - Feed item URL\r
// {effective-url} - Feed item URL after we've followed all redirects\r
$options->message_to_append = '';\r
\r
// Error message when content extraction fails (without access key)\r
// ----------------------\r
$options->error_message = '[unable to retrieve full-text content]';\r
\r
// Keep enclosure in feed items\r
// If enabled, we will try to preserve enclosures if present.\r
// ----------------------\r
$options->keep_enclosures = true;\r
\r
// Detect language\r
// ---------------\r
// Should we try and find/guess the language of the article being processed?\r
// Values will be placed inside the <dc:language> element inside each <item> element\r
// Possible values:\r
// * Ignore language: 0\r
// * Use article/feed metadata (e.g. HTML lang attribute): 1 (default)\r
// * As above, but guess if not present: 2\r
// * Always guess: 3\r
// * User decides: 'user' (value of 0-3 can be passed in querystring: e.g. &l=2)\r
$options->detect_language = 1;\r
\r
// Registration key\r
// ---------------\r
// The registration key is optional. It is not required to use Full-Text RSS,\r
// and does not affect the normal operation of Full-Text RSS. It is currently\r
// only used on admin pages which help you update site patterns with the\r
// latest version offered by FiveFilters.org. For these admin-related\r
// tasks to complete, we will require a valid registration key.\r
// If you would like one, you can purchase the latest version of Full-Text RSS\r
// at http://fivefilters.org/content-only/\r
// Your registration key will automatically be sent in the confirmation email.\r
// Once you have it, simply copy and paste it here.\r
$options->registration_key = '';\r
\r
/////////////////////////////////////////////////\r
/// RESTRICT ACCESS /////////////////////////////\r
/////////////////////////////////////////////////\r
\r
// Admin credentials\r
// ----------------------\r
// Certain pages/actions, e.g. updating site patterns with our online tool, will require admin credentials.\r
// To use these pages, enter a password here and you'll be prompted for it when you try to access those pages.\r
// If no password or username is set, pages requiring admin privelages will be inaccessible.\r
// The default username is 'admin'.\r
// If overriding with an environment variable, separate username and password with a colon, e.g.:\r
// ftr_admin_credentials: admin:my-secret-password\r
// Example: $options->admin_credentials = array('username'=>'admin', 'password'=>'my-secret-password');\r
$options->admin_credentials = array('username'=>'admin', 'password'=>'');\r
\r
// URLs to allow\r
// ----------------------\r
// List of URLs (or parts of a URL) which the service will accept.\r
// If the list is empty, all URLs (except those specified in the blocked list below)\r
// will be permitted.\r
// Empty: array();\r
// Non-empty example: array('example.com', 'anothersite.org');\r
$options->allowed_urls = array();\r
\r
// URLs to block\r
// ----------------------\r
// List of URLs (or parts of a URL) which the service will not accept.\r
// Note: this list is ignored if allowed_urls is not empty\r
$options->blocked_urls = array();\r
\r
// Key holder(s) only?\r
// ----------------------\r
// Set this to true if you want to restrict access only to\r
// those with a key (see below to specify key(s)).\r
// If set to true, no feed is produced unless a valid\r
// key is provided.\r
$options->key_required = false;\r
\r
// Favour item titles in feed\r
// ----------------------\r
// By default, when processing feeds, we assume item titles in the feed\r
// have not been truncated. So after processing web pages, the extracted titles\r
// are not used in the generated feed. If you prefer to have extracted titles in\r
// the feed you can either set this to false, in which case we will always favour\r
// extracted titles. Alternatively, if set to 'user' (default) we'll use the\r
// extracted title if you pass '&use_extracted_title' in the querystring.\r
// Possible values:\r
// * Favour feed titles: true\r
// * Favour extracted titles: false\r
// * Favour feed titles with user override: 'user' (default)\r
// Note: this has no effect when the input URL is to a web page - in these cases\r
// we always use the extracted title in the generated feed.\r
$options->favour_feed_titles = 'user';\r
\r
// Access keys (password protected access)\r
// ------------------------------------\r
// NOTE: You do not need an API key from fivefilters.org to run your own\r
// copy of the code. This is here if you'd like to restrict access to\r
// _your_ copy.\r
// Keys let you group users - those with a key and those without - and\r
// restrict access to the service to those without a key.\r
// If you want everyone to access the service in the same way, you can\r
// leave the array below empty and ignore the access key options further down.\r
// The options further down let you control how the service should behave\r
// in each mode.\r
// Note: Explicitly including the index number (1 and 2 in the examples below)\r
// is highly recommended (when generating feeds, we encode the key and\r
// refer to it by index number and hash).\r
$options->api_keys = array();\r
// Example:\r
// $options->api_keys[1] = 'secret-key-1';\r
// $options->api_keys[2] = 'secret-key-2';\r
\r
// Default entries (with access key)\r
// ----------------------\r
// The number of feed items to process when a valid access key is supplied.\r
$options->default_entries_with_key = 5;\r
\r
// Max entries (with access key)\r
// ----------------------\r
// The maximum number of feed items to process when a valid access key is supplied.\r
$options->max_entries_with_key = 10;\r
\r
/////////////////////////////////////////////////\r
/// ADVANCED OPTIONS ////////////////////////////\r
/////////////////////////////////////////////////\r
\r
// Enable XSS filter?\r
// ----------------------\r
// We have not enabled this by default because we assume the majority of\r
// our users do not display the HTML retrieved by Full-Text RSS\r
// in a web page without further processing. If you subscribe to our generated\r
// feeds in your news reader application, it should, if it's good software, already\r
// filter the resulting HTML for XSS attacks, making it redundant for\r
// Full-Text RSS do the same. Similarly with frameworks/CMS which display\r
// feed content - the content should be treated like any other user-submitted content.\r
//\r
// If you are writing an application yourself which is processing feeds generated by\r
// Full-Text RSS, you can either filter the HTML yourself to remove potential XSS attacks\r
// or enable this option. This might be useful if you are processing our generated\r
// feeds with JavaScript on the client side - although there's client side xss\r
// filtering available too, e.g. https://code.google.com/p/google-caja/wiki/JsHtmlSanitizer\r
//\r
// If enabled, we'll pass retrieved HTML content through htmLawed with\r
// safe flag on and style attributes denied, see\r
// http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed/htmLawed_README.htm#s3.6\r
// Note: if enabled this will also remove certain elements you may want to preserve, such as iframes.\r
//\r
// Valid values:\r
// true - enabled, all content will be filtered\r
// 'user' (default) - user must pass &xss in makefulltextfeed.php querystring to enable\r
// false - disabled\r
$options->xss_filter = 'user';\r
\r
// Allowed parsers\r
// ----------------------\r
// Full-Text RSS attempts to use PHP's libxml extension to process HTML.\r
// While fast, on some sites it may not always produce good results.\r
// For these sites, you can specify an alternative HTML parser:\r
// parser: html5lib\r
// The html5lib parser is bundled with Full-Text RSS.\r
// see http://code.google.com/p/html5lib/\r
//\r
// To disable HTML parsing with html5lib, you can remove it from this list.\r
// By default we allow both: libxml and html5lib.\r
$options->allowed_parsers = array('libxml', 'html5lib');\r
//$options->allowed_parsers = array('libxml'); //disable html5lib - forcing libxml in all cases\r
\r
// Enable Cross-Origin Resource Sharing (CORS)\r
// ----------------------\r
// If enabled we'll send the following HTTP header\r
// Access-Control-Allow-Origin: *\r
// see http://en.wikipedia.org/wiki/Cross-origin_resource_sharing\r
$options->cors = false;\r
\r
// Use APC user cache?\r
// ----------------------\r
// If enabled we will store site config files (when requested\r
// for the first time) in APC's user cache. Keys prefixed with 'sc.'\r
// This improves performance by reducing disk access.\r
// Note: this has no effect if APC is unavailable on your server.\r
$options->apc = true;\r
\r
// Smart cache (experimental)\r
// ----------------------\r
// With this option enabled we will not cache to disk immediately.\r
// We will store the cache key in APC and if it's requested again\r
// we will cache results to disk. Keys prefixed with 'cache.'\r
// This improves performance by reducing disk access.\r
// Note: this has no effect if APC is disabled or unavailable on your server,\r
// or if you have caching disabled.\r
$options->smart_cache = true;\r
\r
// Fingerprints\r
// ----------------------\r
// key is fingerprint (fragment to find in HTML)\r
// value is host name to use for site config lookup if fingerprint matches\r
$options->fingerprints = array(\r
	// Posterous\r
	'<meta name="generator" content="Posterous"' => array('hostname'=>'fingerprint.posterous.com', 'head'=>true),\r
	// Blogger\r
	'<meta content=\'blogger\' name=\'generator\'' => array('hostname'=>'fingerprint.blogspot.com', 'head'=>true),\r
	'<meta name="generator" content="Blogger"' => array('hostname'=>'fingerprint.blogspot.com', 'head'=>true),\r
	// WordPress (hosted)\r
	// '<meta name="generator" content="WordPress.com"' => array('hostname'=>'fingerprint.wordpress.com', 'head'=>true),\r
	// WordPress (self-hosted and hosted)\r
	'<meta name="generator" content="WordPress' => array('hostname'=>'fingerprint.wordpress.com', 'head'=>true)\r
);\r
\r
// User Agent strings - mapping domain names\r
// ----------------------\r
// e.g. $options->user_agents = array('example.org' => 'PHP/5.2');\r
$options->user_agents = array( 'lifehacker.com' => 'PHP/5.2',\r
							   'gawker.com' => 'PHP/5.2',\r
							   'deadspin.com' => 'PHP/5.2',\r
							   'kotaku.com' => 'PHP/5.2',\r
							   'jezebel.com' => 'PHP/5.2',\r
							   'io9.com' => 'PHP/5.2',\r
							   'jalopnik.com' => 'PHP/5.2',\r
							   'gizmodo.com' => 'PHP/5.2',\r
							   '.wikipedia.org' => 'Mozilla/5.2',\r
							   '.fok.nl' => 'Googlebot/2.1',\r
							   'getpocket.com' => 'PHP/5.2'\r
							  );\r
\r
// URL Rewriting\r
// ----------------------\r
// Currently allows simple string replace of URLs.\r
// Useful for rewriting certain URLs to point to a single page\r
// or HTML view. Although using the single_page_link site config\r
// instruction is the preferred way to do this, sometimes, as\r
// with Google Docs URLs, it's not possible.\r
// Note: this might move to the site config file at some point.\r
$options->rewrite_url = array(\r
	// Rewrite public Google Docs URLs to point to HTML view:\r
	// if a URL contains docs.google.com, replace /Doc? with /View?\r
	'docs.google.com' => array('/Doc?' => '/View?'),\r
	'tnr.com' => array('tnr.com/article/' => 'tnr.com/print/article/'),\r
	'.m.wikipedia.org' => array('.m.wikipedia.org' => '.wikipedia.org'),\r
	'm.vanityfair.com' => array('m.vanityfair.com' => 'www.vanityfair.com')\r
);\r
\r
// Content-Type exceptions\r
// -----------------------\r
// Here you can define different actions based\r
// on the Content-Type header returned by server.\r
// MIME type as key, action as value.\r
// Valid actions:\r
// * 'exclude' - exclude this item from the result\r
// * 'link' - create HTML link to the item\r
$options->content_type_exc = array(\r
							   'application/pdf' => array('action'=>'link', 'name'=>'PDF'),\r
							   'image' => array('action'=>'link', 'name'=>'Image'),\r
							   'audio' => array('action'=>'link', 'name'=>'Audio'),\r
							   'video' => array('action'=>'link', 'name'=>'Video')\r
							  );\r
\r
// Cache directory level\r
// ----------------------\r
// Spread cache files over different directories (only used if caching is enabled).\r
// Used to prevent large number of files in one directory.\r
// This corresponds to Zend_Cache's hashed_directory_level\r
// see http://framework.zend.com/manual/en/zend.cache.backends.html\r
// It's best not to change this if you're unsure.\r
$options->cache_directory_level = 0;\r
\r
// Cache cleanup\r
// -------------\r
// 0 = script will not clean cache (rename cachecleanup.php and use it for scheduled (e.g. cron) cache cleanup)\r
// 1 = clean cache everytime the script runs (not recommended)\r
// 100 = clean cache roughly once every 100 script runs\r
// x = clean cache roughly once every x script runs\r
// ...you get the idea :)\r
$options->cache_cleanup = 100;\r
\r
/////////////////////////////////////////////////\r
/// DO NOT CHANGE ANYTHING BELOW THIS ///////////\r
/////////////////////////////////////////////////\r
\r
if (!defined('_FF_FTR_VERSION')) define('_FF_FTR_VERSION', '3.2');\r
\r
if (basename(__FILE__) == 'config.php') {\r
	if (file_exists(dirname(__FILE__).'/custom_config.php')) {\r
		require_once dirname(__FILE__).'/custom_config.php';\r
	}\r
\r
	// check for environment variables - often used on cloud platforms\r
	// environment variables should be prefixed with 'ftr_', e.g.\r
	// ftr_max_entries: 1\r
	// will set the max_entries value to 1.\r
	foreach ($options as $_key=>&$_val) {\r
		$_key = "ftr_$_key";\r
		if (($_env = getenv($_key)) !== false) {\r
			if (is_array($_val)) {\r
				if ($_key === 'ftr_admin_credentials') {\r
					$_val = array_combine(array('username', 'password'), array_map('trim', explode(':', $_env, 2)));\r
					if ($_val === false) $_val = array('username'=>'admin', 'password'=>'');\r
				}\r
			} elseif ($_env === 'true' || $_env === 'false') {\r
				$_val = ($_env === 'true');\r
			} elseif (is_numeric($_env)) {\r
				$_val = (int)$_env;\r
			} else { // string\r
				$_val = $_env;\r
			}\r
		}\r
	}\r
	unset($_key, $_val, $_env);\r
}