pierre/wallabag
1
0
Fork 0
forked from wallabag/wallabag
Code Issues Pull Requests Packages Projects Releases 1 Wiki Activity

update to 3.2 version of full-text-rss, issue #694

Browse Source
This commit is contained in:
Maryana Rozhankivska
2014-05-22 17:16:38 +03:00
parent ab157bbb75
commit 3ec62cf95a
15 changed files with 4417 additions and 4174 deletions
Download Patch File Download Diff File Expand all files Collapse all files

104
inc/3rdparty/config.php vendored
View File

@ -19,7 +19,7 @@ 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
// If set to false, no feed is produced and users will
// be told that the service is disabled.
$options->enabled = true;
@ -43,10 +43,64 @@ $options->default_entries = 5;
// ----------------------
// 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
// 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;
// Full content
// ----------------------
// By default Full-Text RSS includes the extracted content in the output.
// You can exclude this from the output by passing '&content=0' in the querystring.
//
// Possible values...
// Always include: true
// Never include: false
// Include unless user overrides (&content=0): 'user' (default)
//
// Note: currently this does not disable full content extraction. It simply omits it
// from the output.
$options->content = 'user';
// Excerpts
// ----------------------
// By default Full-Text RSS does not include excerpts in the output.
// You can enable this by passing '&summary=1' in the querystring.
// This will include a plain text excerpt from the extracted content.
//
// Possible values...
// Always include: true (recommended for new users)
// Never include: false
// Don't include unless user overrides (&summary=1): 'user' (default)
//
// Important: if both content and excerpts are requested, the excerpt will be
// placed in the description element and the full content inside content:encoded.
// If excerpts are not requested, the full content will go inside the description element.
//
// Why are we not returning both excerpts and content by default?
// Mainly for backward compatibility.
// Excerpts should appear in the feed item's description element. Previous versions
// of Full-Text RSS did not return excerpts, so the description element was always
// used for the full content (as recommended by the RSS advisory). When returning both,
// we need somewhere else to place the content (content:encoded).
// Having both enabled should not create any problems for news readers, but it may create
// problems for developers upgrading from one of our earlier versions who may now find
// their applications are returning excerpts instead of the full content they were
// expecting. To avoid such surprises for users who are upgrading Full-Text RSS,
// excerpts must be explicitly requested in the querystring by default.
//
// Why not use a different element name for excerpts?
// According to the RSS advisory:
// "Publishers who employ summaries should store the summary in description and
// the full content in content:encoded, ordering description first within the item.
// On items with no summary, the full content should be stored in description."
// See: http://www.rssboard.org/rss-profile#namespace-elements-content-encoded
//
// For more consistent element naming, we recommend new users set this option to true.
// The full content can still be excluded via the querystring, but the element names
// will not change: when $options->summary = true, the description element will always
// be reserved for the excerpt and content:encoded always for full content.
$options->summary = 'user';
// Rewrite relative URLs
// ----------------------
// With this enabled relative URLs found in the extracted content
@ -67,7 +121,7 @@ $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
// Currently this only happens for sites where next_page_link has been defined
// in a site config file.
$options->multipage = true;
@ -125,10 +179,10 @@ $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
// 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/
@ -144,12 +198,12 @@ $options->registration_key = '';
// ----------------------
// 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.
// 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');
$options->admin_credentials = array('username'=>'admin', 'password'=>'');
// URLs to allow
// ----------------------
@ -178,12 +232,12 @@ $options->key_required = false;
// ----------------------
// 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
// 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 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
@ -192,17 +246,17 @@ $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
// 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
// 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
// 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:
@ -232,13 +286,13 @@ $options->max_entries_with_key = 10;
// 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
@ -253,8 +307,8 @@ $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:
// 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/
@ -273,7 +327,7 @@ $options->cors = false;
// Use APC user cache?
// ----------------------
// If enabled we will store site config files (when requested
// 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.
@ -346,7 +400,7 @@ $options->rewrite_url = array(
// Valid actions:
// * 'exclude' - exclude this item from the result
// * 'link' - create HTML link to the item
$options->content_type_exc = array(
$options->content_type_exc = array(
'application/pdf' => array('action'=>'link', 'name'=>'PDF'),
'image' => array('action'=>'link', 'name'=>'Image'),
'audio' => array('action'=>'link', 'name'=>'Audio'),
@ -375,13 +429,13 @@ $options->cache_cleanup = 100;
/// DO NOT CHANGE ANYTHING BELOW THIS ///////////
/////////////////////////////////////////////////
if (!defined('_FF_FTR_VERSION')) define('_FF_FTR_VERSION', '3.1');
if (!defined('_FF_FTR_VERSION')) define('_FF_FTR_VERSION', '3.2');
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