1 files changed, 405 insertions, 0 deletions
diff --git a/inc/3rdparty/config.php b/inc/3rdparty/config.php
new file mode 100644
index 00000000..61fc0d0e
--- /dev/null
+++ b/inc/3rdparty/config.php
@@ -0,0 +1,405 @@
+<?php
+/* Full-Text RSS config */
+// ......IMPORTANT......................................
+// .....................................................
+// Please do not change this file (config.php) directly.
+// Save a copy as custom_config.php and make your
+// changes to that instead. It will automatically
+// override anything in config.php. Because config.php
+// always gets loaded anyway, you can simply specify
+// options you'd like to override in custom_config.php.
+// .....................................................
+// Create config object
+if (!isset($options)) $options = new stdClass();
+// Enable service
+// ----------------------
+// Set this to false if you want to disable the service.
+// If set to false, no feed is produced and users will 
+// be told that the service is disabled.
+$options->enabled = true;
+// Debug mode
+// ----------------------
+// Enable or disable debugging. When enabled debugging works by passing
+// &debug to the makefulltextfeed.php querystring.
+// Valid values:
+// true or 'user' (default) - let user decide
+// 'admin' - debug works only for logged in admin users
+// false - disabled
+$options->debug = true;
+// Default entries (without access key)
+// ----------------------
+// The number of feed items to process when no API key is supplied
+// and no &max=x value is supplied in the querystring.
+$options->default_entries = 5;
+// Max entries (without access key)
+// ----------------------
+// The maximum number of feed items to process when no access key is supplied.
+// This limits the user-supplied &max=x value. For example, if the user
+// asks for 20 items to be processed (&max=20), if max_entries is set to 
+// 10, only 10 will be processed.
+$options->max_entries = 10;
+// Rewrite relative URLs
+// ----------------------
+// With this enabled relative URLs found in the extracted content
+// block are automatically rewritten as absolute URLs.
+$options->rewrite_relative_urls = true;
+// Exclude items if extraction fails
+// ---------------------------------
+// Excludes items from the resulting feed
+// if we cannot extract any content from the
+// item URL.
+// Possible values...
+// Enable: true
+// Disable: false (default)
+// User decides: 'user' (this option will appear on the form)
+$options->exclude_items_on_fail = 'user';
+// Enable multi-page support
+// -------------------------
+// If enabled, we will try to follow next page links on multi-page articles.
+// Currently this only happens for sites where next_page_link has been defined 
+// in a site config file.
+$options->multipage = true;
+// Enable caching
+// ----------------------
+// Enable this if you'd like to cache results
+// for 10 minutes. Cache files are written to disk (in cache/ subfolders
+// - which must be writable).
+// Initially it's best to keep this disabled to make sure everything works
+// as expected. If you have APC enabled, please also see smart_cache in the
+// advanced section.
+$options->caching = false;
+// Cache directory
+// ----------------------
+// Only used if caching is true
+$options->cache_dir = dirname(__FILE__).'/cache';
+// Message to prepend (without access key)
+// ----------------------
+// HTML to insert at the beginning of each feed item when no access key is supplied.
+// Substitution tags:
+// {url} - Feed item URL
+// {effective-url} - Feed item URL after we've followed all redirects
+$options->message_to_prepend = '';
+// Message to append (without access key)
+// ----------------------
+// HTML to insert at the end of each feed item when no access key is supplied.
+// Substitution tags:
+// {url} - Feed item URL
+// {effective-url} - Feed item URL after we've followed all redirects
+$options->message_to_append = '';
+// Error message when content extraction fails (without access key)
+// ----------------------
+$options->error_message = '[unable to retrieve full-text content]';
+// Keep enclosure in feed items
+// If enabled, we will try to preserve enclosures if present.
+// ----------------------
+$options->keep_enclosures = true;
+// Detect language
+// ---------------
+// Should we try and find/guess the language of the article being processed?
+// Values will be placed inside the <dc:language> element inside each <item> element
+// Possible values:
+// * Ignore language: 0
+// * Use article/feed metadata (e.g. HTML lang attribute): 1 (default)
+// * As above, but guess if not present: 2
+// * Always guess: 3
+// * User decides: 'user' (value of 0-3 can be passed in querystring: e.g. &l=2)
+$options->detect_language = 1;
+// Registration key
+// ---------------
+// The registration key is optional. It is not required to use Full-Text RSS, 
+// and does not affect the normal operation of Full-Text RSS. It is currently 
+// only used on admin pages which help you update site patterns with the 
+// latest version offered by FiveFilters.org. For these admin-related 
+// tasks to complete, we will require a valid registration key.
+// If you would like one, you can purchase the latest version of Full-Text RSS
+// at http://fivefilters.org/content-only/
+// Your registration key will automatically be sent in the confirmation email.
+// Once you have it, simply copy and paste it here.
+$options->registration_key = '';
+/////////////////////////////////////////////////
+/// RESTRICT ACCESS /////////////////////////////
+/////////////////////////////////////////////////
+// Admin credentials
+// ----------------------
+// Certain pages/actions, e.g. updating site patterns with our online tool, will require admin credentials.
+// To use these pages, enter a password here and you'll be prompted for it when you try to access those pages.
+// If no password or username is set, pages requiring admin privelages will be inaccessible. 
+// The default username is 'admin'.
+// If overriding with an environment variable, separate username and password with a colon, e.g.:
+// ftr_admin_credentials: admin:my-secret-password
+// Example: $options->admin_credentials = array('username'=>'admin', 'password'=>'my-secret-password');
+$options->admin_credentials = array('username'=>'admin', 'password'=>'admin');
+// URLs to allow
+// ----------------------
+// List of URLs (or parts of a URL) which the service will accept.
+// If the list is empty, all URLs (except those specified in the blocked list below)
+// will be permitted.
+// Empty: array();
+// Non-empty example: array('example.com', 'anothersite.org');
+$options->allowed_urls = array();
+// URLs to block
+// ----------------------
+// List of URLs (or parts of a URL) which the service will not accept.
+// Note: this list is ignored if allowed_urls is not empty
+$options->blocked_urls = array();
+// Key holder(s) only?
+// ----------------------
+// Set this to true if you want to restrict access only to
+// those with a key (see below to specify key(s)).
+// If set to true, no feed is produced unless a valid
+// key is provided.
+$options->key_required = false;
+// Favour item titles in feed
+// ----------------------
+// By default, when processing feeds, we assume item titles in the feed
+// have not been truncated. So after processing web pages, the extracted titles
+// are not used in the generated feed. If you prefer to have extracted titles in 
+// the feed you can either set this to false, in which case we will always favour 
+// extracted titles. Alternatively, if set to 'user' (default) we'll use the 
+// extracted title if you pass '&use_extracted_title' in the querystring.
+// Possible values:
+// * Favour feed titles: true 
+// * Favour extracted titles: false
+// * Favour feed titles with user override: 'user' (default)
+// Note: this has no effect when the input URL is to a web page - in these cases
+// we always use the extracted title in the generated feed.
+$options->favour_feed_titles = 'user';
+// Access keys (password protected access)
+// ------------------------------------
+// NOTE: You do not need an API key from fivefilters.org to run your own 
+// copy of the code. This is here if you'd like to restrict access to
+// _your_ copy.
+// Keys let you group users - those with a key and those without - and
+// restrict access to the service to those without a key.
+// If you want everyone to access the service in the same way, you can
+// leave the array below empty and ignore the access key options further down.
+// The options further down let you control how the service should behave 
+// in each mode.
+// Note: Explicitly including the index number (1 and 2 in the examples below) 
+// is highly recommended (when generating feeds, we encode the key and 
+// refer to it by index number and hash).
+$options->api_keys = array();
+// Example:
+// $options->api_keys[1] = 'secret-key-1';
+// $options->api_keys[2] = 'secret-key-2';
+// Default entries (with access key)
+// ----------------------
+// The number of feed items to process when a valid access key is supplied.
+$options->default_entries_with_key = 5;
+// Max entries (with access key)
+// ----------------------
+// The maximum number of feed items to process when a valid access key is supplied.
+$options->max_entries_with_key = 10;
+/////////////////////////////////////////////////
+/// ADVANCED OPTIONS ////////////////////////////
+/////////////////////////////////////////////////
+// Enable XSS filter?
+// ----------------------
+// We have not enabled this by default because we assume the majority of
+// our users do not display the HTML retrieved by Full-Text RSS
+// in a web page without further processing. If you subscribe to our generated
+// feeds in your news reader application, it should, if it's good software, already
+// filter the resulting HTML for XSS attacks, making it redundant for
+// Full-Text RSS do the same. Similarly with frameworks/CMS which display
+// feed content - the content should be treated like any other user-submitted content.
+// 
+// If you are writing an application yourself which is processing feeds generated by
+// Full-Text RSS, you can either filter the HTML yourself to remove potential XSS attacks
+// or enable this option. This might be useful if you are processing our generated
+// feeds with JavaScript on the client side - although there's client side xss
+// filtering available too, e.g. https://code.google.com/p/google-caja/wiki/JsHtmlSanitizer
+// 
+// If enabled, we'll pass retrieved HTML content through htmLawed with
+// safe flag on and style attributes denied, see
+// http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed/htmLawed_README.htm#s3.6
+// Note: if enabled this will also remove certain elements you may want to preserve, such as iframes.
+//
+// Valid values:
+// true - enabled, all content will be filtered
+// 'user' (default) - user must pass &xss in makefulltextfeed.php querystring to enable
+// false - disabled
+$options->xss_filter = 'user';
+// Allowed parsers
+// ----------------------
+// Full-Text RSS attempts to use PHP's libxml extension to process HTML.
+// While fast, on some sites it may not always produce good results. 
+// For these sites, you can specify an alternative HTML parser: 
+// parser: html5lib
+// The html5lib parser is bundled with Full-Text RSS.
+// see http://code.google.com/p/html5lib/
+//
+// To disable HTML parsing with html5lib, you can remove it from this list.
+// By default we allow both: libxml and html5lib.
+$options->allowed_parsers = array('libxml', 'html5lib');
+//$options->allowed_parsers = array('libxml'); //disable html5lib - forcing libxml in all cases
+// Enable Cross-Origin Resource Sharing (CORS)
+// ----------------------
+// If enabled we'll send the following HTTP header
+// Access-Control-Allow-Origin: *
+// see http://en.wikipedia.org/wiki/Cross-origin_resource_sharing
+$options->cors = false;
+// Use APC user cache?
+// ----------------------
+// If enabled we will store site config files (when requested 
+// for the first time) in APC's user cache. Keys prefixed with 'sc.'
+// This improves performance by reducing disk access.
+// Note: this has no effect if APC is unavailable on your server.
+$options->apc = true;
+// Smart cache (experimental)
+// ----------------------
+// With this option enabled we will not cache to disk immediately.
+// We will store the cache key in APC and if it's requested again
+// we will cache results to disk. Keys prefixed with 'cache.'
+// This improves performance by reducing disk access.
+// Note: this has no effect if APC is disabled or unavailable on your server,
+// or if you have caching disabled.
+$options->smart_cache = true;
+// Fingerprints
+// ----------------------
+// key is fingerprint (fragment to find in HTML)
+// value is host name to use for site config lookup if fingerprint matches
+$options->fingerprints = array(
+        // Posterous
+        '<meta name="generator" content="Posterous"' => array('hostname'=>'fingerprint.posterous.com', 'head'=>true),
+        // Blogger
+        '<meta content=\'blogger\' name=\'generator\'' => array('hostname'=>'fingerprint.blogspot.com', 'head'=>true),
+        '<meta name="generator" content="Blogger"' => array('hostname'=>'fingerprint.blogspot.com', 'head'=>true),
+        // WordPress (hosted)
+        // '<meta name="generator" content="WordPress.com"' => array('hostname'=>'fingerprint.wordpress.com', 'head'=>true),
+        // WordPress (self-hosted and hosted)
+        '<meta name="generator" content="WordPress' => array('hostname'=>'fingerprint.wordpress.com', 'head'=>true)
+);
+// User Agent strings - mapping domain names
+// ----------------------
+// e.g. $options->user_agents = array('example.org' => 'PHP/5.2');
+$options->user_agents = array( 'lifehacker.com' => 'PHP/5.2',
+                                                           'gawker.com' => 'PHP/5.2',
+                                                           'deadspin.com' => 'PHP/5.2',
+                                                           'kotaku.com' => 'PHP/5.2',
+                                                           'jezebel.com' => 'PHP/5.2',
+                                                           'io9.com' => 'PHP/5.2',
+                                                           'jalopnik.com' => 'PHP/5.2',
+                                                           'gizmodo.com' => 'PHP/5.2',
+                                                           '.wikipedia.org' => 'Mozilla/5.2',
+                                                           '.fok.nl' => 'Googlebot/2.1',
+                                                           'getpocket.com' => 'PHP/5.2'
+                                                          );
+// URL Rewriting
+// ----------------------
+// Currently allows simple string replace of URLs.
+// Useful for rewriting certain URLs to point to a single page
+// or HTML view. Although using the single_page_link site config
+// instruction is the preferred way to do this, sometimes, as
+// with Google Docs URLs, it's not possible.
+// Note: this might move to the site config file at some point.
+$options->rewrite_url = array(
+        // Rewrite public Google Docs URLs to point to HTML view:
+        // if a URL contains docs.google.com, replace /Doc? with /View?
+        'docs.google.com' => array('/Doc?' => '/View?'),
+        'tnr.com' => array('tnr.com/article/' => 'tnr.com/print/article/'),
+        '.m.wikipedia.org' => array('.m.wikipedia.org' => '.wikipedia.org'),
+        'm.vanityfair.com' => array('m.vanityfair.com' => 'www.vanityfair.com')
+);
+// Content-Type exceptions
+// -----------------------
+// Here you can define different actions based
+// on the Content-Type header returned by server.
+// MIME type as key, action as value.
+// Valid actions:
+// * 'exclude' - exclude this item from the result
+// * 'link' - create HTML link to the item
+$options->content_type_exc = array( 
+                                                           'application/pdf' => array('action'=>'link', 'name'=>'PDF'),
+                                                           'image' => array('action'=>'link', 'name'=>'Image'),
+                                                           'audio' => array('action'=>'link', 'name'=>'Audio'),
+                                                           'video' => array('action'=>'link', 'name'=>'Video')
+                                                          );
+// Cache directory level
+// ----------------------
+// Spread cache files over different directories (only used if caching is enabled).
+// Used to prevent large number of files in one directory.
+// This corresponds to Zend_Cache's hashed_directory_level
+// see http://framework.zend.com/manual/en/zend.cache.backends.html
+// It's best not to change this if you're unsure.
+$options->cache_directory_level = 0;
+// Cache cleanup
+// -------------
+// 0 = script will not clean cache (rename cachecleanup.php and use it for scheduled (e.g. cron) cache cleanup)
+// 1 = clean cache everytime the script runs (not recommended)
+// 100 = clean cache roughly once every 100 script runs
+// x = clean cache roughly once every x script runs
+// ...you get the idea :)
+$options->cache_cleanup = 100;
+/////////////////////////////////////////////////
+/// DO NOT CHANGE ANYTHING BELOW THIS ///////////
+/////////////////////////////////////////////////
+if (!defined('_FF_FTR_VERSION')) define('_FF_FTR_VERSION', '3.1');
+if (basename(__FILE__) == 'config.php') {
+        if (file_exists(dirname(__FILE__).'/custom_config.php')) {
+                require_once dirname(__FILE__).'/custom_config.php';
+        }
+        
+        // check for environment variables - often used on cloud platforms
+        // environment variables should be prefixed with 'ftr_', e.g.
+        // ftr_max_entries: 1
+        // will set the max_entries value to 1.
+        foreach ($options as $_key=>&$_val) {
+                $_key = "ftr_$_key";
+                if (($_env = getenv($_key)) !== false) {
+                        if (is_array($_val)) {
+                                if ($_key === 'ftr_admin_credentials') {
+                                        $_val = array_combine(array('username', 'password'), array_map('trim', explode(':', $_env, 2)));
+                                        if ($_val === false) $_val = array('username'=>'admin', 'password'=>'');
+                                }
+                        } elseif ($_env === 'true' || $_env === 'false') {
+                                $_val = ($_env === 'true');
+                        } elseif (is_numeric($_env)) {
+                                $_val = (int)$_env;
+                        } else { // string
+                                $_val = $_env;
+                        }
+                }
+        }
+        unset($_key, $_val, $_env);
+}
+\ No newline at end of file

diff --git a/inc/3rdparty/config.php b/inc/3rdparty/config.php new file mode 100644 index 00000000..61fc0d0e --- /dev/null +++ b/inc/3rdparty/config.php
@@ -0,0 +1,405 @@
	1	<?php
	2	/* Full-Text RSS config */
	3
	4	// ......IMPORTANT......................................
	5	// .....................................................
	6	// Please do not change this file (config.php) directly.
	7	// Save a copy as custom_config.php and make your
	8	// changes to that instead. It will automatically
	9	// override anything in config.php. Because config.php
	10	// always gets loaded anyway, you can simply specify
	11	// options you'd like to override in custom_config.php.
	12	// .....................................................
	13
	14	// Create config object
	15	if (!isset($options)) $options = new stdClass();
	16
	17	// Enable service
	18	// ----------------------
	19	// Set this to false if you want to disable the service.
	20	// If set to false, no feed is produced and users will
	21	// be told that the service is disabled.
	22	$options->enabled = true;
	23
	24	// Debug mode
	25	// ----------------------
	26	// Enable or disable debugging. When enabled debugging works by passing
	27	// &debug to the makefulltextfeed.php querystring.
	28	// Valid values:
	29	// true or 'user' (default) - let user decide
	30	// 'admin' - debug works only for logged in admin users
	31	// false - disabled
	32	$options->debug = true;
	33
	34	// Default entries (without access key)
	35	// ----------------------
	36	// The number of feed items to process when no API key is supplied
	37	// and no &max=x value is supplied in the querystring.
	38	$options->default_entries = 5;
	39
	40	// Max entries (without access key)
	41	// ----------------------
	42	// The maximum number of feed items to process when no access key is supplied.
	43	// This limits the user-supplied &max=x value. For example, if the user
	44	// asks for 20 items to be processed (&max=20), if max_entries is set to
	45	// 10, only 10 will be processed.
	46	$options->max_entries = 10;
	47
	48	// Rewrite relative URLs
	49	// ----------------------
	50	// With this enabled relative URLs found in the extracted content
	51	// block are automatically rewritten as absolute URLs.
	52	$options->rewrite_relative_urls = true;
	53
	54	// Exclude items if extraction fails
	55	// ---------------------------------
	56	// Excludes items from the resulting feed
	57	// if we cannot extract any content from the
	58	// item URL.
	59	// Possible values...
	60	// Enable: true
	61	// Disable: false (default)
	62	// User decides: 'user' (this option will appear on the form)
	63	$options->exclude_items_on_fail = 'user';
	64
	65	// Enable multi-page support
	66	// -------------------------
	67	// If enabled, we will try to follow next page links on multi-page articles.
	68	// Currently this only happens for sites where next_page_link has been defined
	69	// in a site config file.
	70	$options->multipage = true;
	71
	72	// Enable caching
	73	// ----------------------
	74	// Enable this if you'd like to cache results
	75	// for 10 minutes. Cache files are written to disk (in cache/ subfolders
	76	// - which must be writable).
	77	// Initially it's best to keep this disabled to make sure everything works
	78	// as expected. If you have APC enabled, please also see smart_cache in the
	79	// advanced section.
	80	$options->caching = false;
	81
	82	// Cache directory
	83	// ----------------------
	84	// Only used if caching is true
	85	$options->cache_dir = dirname(__FILE__).'/cache';
	86
	87	// Message to prepend (without access key)
	88	// ----------------------
	89	// HTML to insert at the beginning of each feed item when no access key is supplied.
	90	// Substitution tags:
	91	// {url} - Feed item URL
	92	// {effective-url} - Feed item URL after we've followed all redirects
	93	$options->message_to_prepend = '';
	94
	95	// Message to append (without access key)
	96	// ----------------------
	97	// HTML to insert at the end of each feed item when no access key is supplied.
	98	// Substitution tags:
	99	// {url} - Feed item URL
	100	// {effective-url} - Feed item URL after we've followed all redirects
	101	$options->message_to_append = '';
	102
	103	// Error message when content extraction fails (without access key)
	104	// ----------------------
	105	$options->error_message = '[unable to retrieve full-text content]';
	106
	107	// Keep enclosure in feed items
	108	// If enabled, we will try to preserve enclosures if present.
	109	// ----------------------
	110	$options->keep_enclosures = true;
	111
	112	// Detect language
	113	// ---------------
	114	// Should we try and find/guess the language of the article being processed?
	115	// Values will be placed inside the <dc:language> element inside each <item> element
	116	// Possible values:
	117	// * Ignore language: 0
	118	// * Use article/feed metadata (e.g. HTML lang attribute): 1 (default)
	119	// * As above, but guess if not present: 2
	120	// * Always guess: 3
	121	// * User decides: 'user' (value of 0-3 can be passed in querystring: e.g. &l=2)
	122	$options->detect_language = 1;
	123
	124	// Registration key
	125	// ---------------
	126	// The registration key is optional. It is not required to use Full-Text RSS,
	127	// and does not affect the normal operation of Full-Text RSS. It is currently
	128	// only used on admin pages which help you update site patterns with the
	129	// latest version offered by FiveFilters.org. For these admin-related
	130	// tasks to complete, we will require a valid registration key.
	131	// If you would like one, you can purchase the latest version of Full-Text RSS
	132	// at http://fivefilters.org/content-only/
	133	// Your registration key will automatically be sent in the confirmation email.
	134	// Once you have it, simply copy and paste it here.
	135	$options->registration_key = '';
	136
	137	/////////////////////////////////////////////////
	138	/// RESTRICT ACCESS /////////////////////////////
	139	/////////////////////////////////////////////////
	140
	141	// Admin credentials
	142	// ----------------------
	143	// Certain pages/actions, e.g. updating site patterns with our online tool, will require admin credentials.
	144	// To use these pages, enter a password here and you'll be prompted for it when you try to access those pages.
	145	// If no password or username is set, pages requiring admin privelages will be inaccessible.
	146	// The default username is 'admin'.
	147	// If overriding with an environment variable, separate username and password with a colon, e.g.:
	148	// ftr_admin_credentials: admin:my-secret-password
	149	// Example: $options->admin_credentials = array('username'=>'admin', 'password'=>'my-secret-password');
	150	$options->admin_credentials = array('username'=>'admin', 'password'=>'admin');
	151
	152	// URLs to allow
	153	// ----------------------
	154	// List of URLs (or parts of a URL) which the service will accept.
	155	// If the list is empty, all URLs (except those specified in the blocked list below)
	156	// will be permitted.
	157	// Empty: array();
	158	// Non-empty example: array('example.com', 'anothersite.org');
	159	$options->allowed_urls = array();
	160
	161	// URLs to block
	162	// ----------------------
	163	// List of URLs (or parts of a URL) which the service will not accept.
	164	// Note: this list is ignored if allowed_urls is not empty
	165	$options->blocked_urls = array();
	166
	167	// Key holder(s) only?
	168	// ----------------------
	169	// Set this to true if you want to restrict access only to
	170	// those with a key (see below to specify key(s)).
	171	// If set to true, no feed is produced unless a valid
	172	// key is provided.
	173	$options->key_required = false;
	174
	175	// Favour item titles in feed
	176	// ----------------------
	177	// By default, when processing feeds, we assume item titles in the feed
	178	// have not been truncated. So after processing web pages, the extracted titles
	179	// are not used in the generated feed. If you prefer to have extracted titles in
	180	// the feed you can either set this to false, in which case we will always favour
	181	// extracted titles. Alternatively, if set to 'user' (default) we'll use the
	182	// extracted title if you pass '&use_extracted_title' in the querystring.
	183	// Possible values:
	184	// * Favour feed titles: true
	185	// * Favour extracted titles: false
	186	// * Favour feed titles with user override: 'user' (default)
	187	// Note: this has no effect when the input URL is to a web page - in these cases
	188	// we always use the extracted title in the generated feed.
	189	$options->favour_feed_titles = 'user';
	190
	191	// Access keys (password protected access)
	192	// ------------------------------------
	193	// NOTE: You do not need an API key from fivefilters.org to run your own
	194	// copy of the code. This is here if you'd like to restrict access to
	195	// _your_ copy.
	196	// Keys let you group users - those with a key and those without - and
	197	// restrict access to the service to those without a key.
	198	// If you want everyone to access the service in the same way, you can
	199	// leave the array below empty and ignore the access key options further down.
	200	// The options further down let you control how the service should behave
	201	// in each mode.
	202	// Note: Explicitly including the index number (1 and 2 in the examples below)
	203	// is highly recommended (when generating feeds, we encode the key and
	204	// refer to it by index number and hash).
	205	$options->api_keys = array();
	206	// Example:
	207	// $options->api_keys[1] = 'secret-key-1';
	208	// $options->api_keys[2] = 'secret-key-2';
	209
	210	// Default entries (with access key)
	211	// ----------------------
	212	// The number of feed items to process when a valid access key is supplied.
	213	$options->default_entries_with_key = 5;
	214
	215	// Max entries (with access key)
	216	// ----------------------
	217	// The maximum number of feed items to process when a valid access key is supplied.
	218	$options->max_entries_with_key = 10;
	219
	220	/////////////////////////////////////////////////
	221	/// ADVANCED OPTIONS ////////////////////////////
	222	/////////////////////////////////////////////////
	223
	224	// Enable XSS filter?
	225	// ----------------------
	226	// We have not enabled this by default because we assume the majority of
	227	// our users do not display the HTML retrieved by Full-Text RSS
	228	// in a web page without further processing. If you subscribe to our generated
	229	// feeds in your news reader application, it should, if it's good software, already
	230	// filter the resulting HTML for XSS attacks, making it redundant for
	231	// Full-Text RSS do the same. Similarly with frameworks/CMS which display
	232	// feed content - the content should be treated like any other user-submitted content.
	233	//
	234	// If you are writing an application yourself which is processing feeds generated by
	235	// Full-Text RSS, you can either filter the HTML yourself to remove potential XSS attacks
	236	// or enable this option. This might be useful if you are processing our generated
	237	// feeds with JavaScript on the client side - although there's client side xss
	238	// filtering available too, e.g. https://code.google.com/p/google-caja/wiki/JsHtmlSanitizer
	239	//
	240	// If enabled, we'll pass retrieved HTML content through htmLawed with
	241	// safe flag on and style attributes denied, see
	242	// http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed/htmLawed_README.htm#s3.6
	243	// Note: if enabled this will also remove certain elements you may want to preserve, such as iframes.
	244	//
	245	// Valid values:
	246	// true - enabled, all content will be filtered
	247	// 'user' (default) - user must pass &xss in makefulltextfeed.php querystring to enable
	248	// false - disabled
	249	$options->xss_filter = 'user';
	250
	251	// Allowed parsers
	252	// ----------------------
	253	// Full-Text RSS attempts to use PHP's libxml extension to process HTML.
	254	// While fast, on some sites it may not always produce good results.
	255	// For these sites, you can specify an alternative HTML parser:
	256	// parser: html5lib
	257	// The html5lib parser is bundled with Full-Text RSS.
	258	// see http://code.google.com/p/html5lib/
	259	//
	260	// To disable HTML parsing with html5lib, you can remove it from this list.
	261	// By default we allow both: libxml and html5lib.
	262	$options->allowed_parsers = array('libxml', 'html5lib');
	263	//$options->allowed_parsers = array('libxml'); //disable html5lib - forcing libxml in all cases
	264
	265	// Enable Cross-Origin Resource Sharing (CORS)
	266	// ----------------------
	267	// If enabled we'll send the following HTTP header
	268	// Access-Control-Allow-Origin: *
	269	// see http://en.wikipedia.org/wiki/Cross-origin_resource_sharing
	270	$options->cors = false;
	271
	272	// Use APC user cache?
	273	// ----------------------
	274	// If enabled we will store site config files (when requested
	275	// for the first time) in APC's user cache. Keys prefixed with 'sc.'
	276	// This improves performance by reducing disk access.
	277	// Note: this has no effect if APC is unavailable on your server.
	278	$options->apc = true;
	279
	280	// Smart cache (experimental)
	281	// ----------------------
	282	// With this option enabled we will not cache to disk immediately.
	283	// We will store the cache key in APC and if it's requested again
	284	// we will cache results to disk. Keys prefixed with 'cache.'
	285	// This improves performance by reducing disk access.
	286	// Note: this has no effect if APC is disabled or unavailable on your server,
	287	// or if you have caching disabled.
	288	$options->smart_cache = true;
	289
	290	// Fingerprints
	291	// ----------------------
	292	// key is fingerprint (fragment to find in HTML)
	293	// value is host name to use for site config lookup if fingerprint matches
	294	$options->fingerprints = array(
	295	// Posterous
	296	'<meta name="generator" content="Posterous"' => array('hostname'=>'fingerprint.posterous.com', 'head'=>true),
	297	// Blogger
	298	'<meta content=\'blogger\' name=\'generator\'' => array('hostname'=>'fingerprint.blogspot.com', 'head'=>true),
	299	'<meta name="generator" content="Blogger"' => array('hostname'=>'fingerprint.blogspot.com', 'head'=>true),
	300	// WordPress (hosted)
	301	// '<meta name="generator" content="WordPress.com"' => array('hostname'=>'fingerprint.wordpress.com', 'head'=>true),
	302	// WordPress (self-hosted and hosted)
	303	'<meta name="generator" content="WordPress' => array('hostname'=>'fingerprint.wordpress.com', 'head'=>true)
	304	);
	305
	306	// User Agent strings - mapping domain names
	307	// ----------------------
	308	// e.g. $options->user_agents = array('example.org' => 'PHP/5.2');
	309	$options->user_agents = array( 'lifehacker.com' => 'PHP/5.2',
	310	'gawker.com' => 'PHP/5.2',
	311	'deadspin.com' => 'PHP/5.2',
	312	'kotaku.com' => 'PHP/5.2',
	313	'jezebel.com' => 'PHP/5.2',
	314	'io9.com' => 'PHP/5.2',
	315	'jalopnik.com' => 'PHP/5.2',
	316	'gizmodo.com' => 'PHP/5.2',
	317	'.wikipedia.org' => 'Mozilla/5.2',
	318	'.fok.nl' => 'Googlebot/2.1',
	319	'getpocket.com' => 'PHP/5.2'
	320	);
	321
	322	// URL Rewriting
	323	// ----------------------
	324	// Currently allows simple string replace of URLs.
	325	// Useful for rewriting certain URLs to point to a single page
	326	// or HTML view. Although using the single_page_link site config
	327	// instruction is the preferred way to do this, sometimes, as
	328	// with Google Docs URLs, it's not possible.
	329	// Note: this might move to the site config file at some point.
	330	$options->rewrite_url = array(
	331	// Rewrite public Google Docs URLs to point to HTML view:
	332	// if a URL contains docs.google.com, replace /Doc? with /View?
	333	'docs.google.com' => array('/Doc?' => '/View?'),
	334	'tnr.com' => array('tnr.com/article/' => 'tnr.com/print/article/'),
	335	'.m.wikipedia.org' => array('.m.wikipedia.org' => '.wikipedia.org'),
	336	'm.vanityfair.com' => array('m.vanityfair.com' => 'www.vanityfair.com')
	337	);
	338
	339	// Content-Type exceptions
	340	// -----------------------
	341	// Here you can define different actions based
	342	// on the Content-Type header returned by server.
	343	// MIME type as key, action as value.
	344	// Valid actions:
	345	// * 'exclude' - exclude this item from the result
	346	// * 'link' - create HTML link to the item
	347	$options->content_type_exc = array(
	348	'application/pdf' => array('action'=>'link', 'name'=>'PDF'),
	349	'image' => array('action'=>'link', 'name'=>'Image'),
	350	'audio' => array('action'=>'link', 'name'=>'Audio'),
	351	'video' => array('action'=>'link', 'name'=>'Video')
	352	);
	353
	354	// Cache directory level
	355	// ----------------------
	356	// Spread cache files over different directories (only used if caching is enabled).
	357	// Used to prevent large number of files in one directory.
	358	// This corresponds to Zend_Cache's hashed_directory_level
	359	// see http://framework.zend.com/manual/en/zend.cache.backends.html
	360	// It's best not to change this if you're unsure.
	361	$options->cache_directory_level = 0;
	362
	363	// Cache cleanup
	364	// -------------
	365	// 0 = script will not clean cache (rename cachecleanup.php and use it for scheduled (e.g. cron) cache cleanup)
	366	// 1 = clean cache everytime the script runs (not recommended)
	367	// 100 = clean cache roughly once every 100 script runs
	368	// x = clean cache roughly once every x script runs
	369	// ...you get the idea :)
	370	$options->cache_cleanup = 100;
	371
	372	/////////////////////////////////////////////////
	373	/// DO NOT CHANGE ANYTHING BELOW THIS ///////////
	374	/////////////////////////////////////////////////
	375
	376	if (!defined('_FF_FTR_VERSION')) define('_FF_FTR_VERSION', '3.1');
	377
	378	if (basename(__FILE__) == 'config.php') {
	379	if (file_exists(dirname(__FILE__).'/custom_config.php')) {
	380	require_once dirname(__FILE__).'/custom_config.php';
	381	}
	382
	383	// check for environment variables - often used on cloud platforms
	384	// environment variables should be prefixed with 'ftr_', e.g.
	385	// ftr_max_entries: 1
	386	// will set the max_entries value to 1.
	387	foreach ($options as $_key=>&$_val) {
	388	$_key = "ftr_$_key";
	389	if (($_env = getenv($_key)) !== false) {
	390	if (is_array($_val)) {
	391	if ($_key === 'ftr_admin_credentials') {
	392	$_val = array_combine(array('username', 'password'), array_map('trim', explode(':', $_env, 2)));
	393	if ($_val === false) $_val = array('username'=>'admin', 'password'=>'');
	394	}
	395	} elseif ($_env === 'true' \|\| $_env === 'false') {
	396	$_val = ($_env === 'true');
	397	} elseif (is_numeric($_env)) {
	398	$_val = (int)$_env;
	399	} else { // string
	400	$_val = $_env;
	401	}
	402	}
	403	}
	404	unset($_key, $_val, $_env);
	405	} \ No newline at end of file