1
0
mirror of https://github.com/moparisthebest/wallabag synced 2024-11-23 17:42:15 -05:00

Merge pull request #707 from mariroz/dev

update to 3.2 version of full-text-rss, issue #694
This commit is contained in:
Nicolas Lœuillet 2014-05-29 12:50:28 +02:00
commit 87f01ea2e9
24 changed files with 4870 additions and 4208 deletions

View File

@ -19,7 +19,7 @@ if (!isset($options)) $options = new stdClass();
// Enable service // Enable service
// ---------------------- // ----------------------
// Set this to false if you want to disable the 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. // be told that the service is disabled.
$options->enabled = true; $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. // 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 // 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. // 10, only 10 will be processed.
$options->max_entries = 10; $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 // Rewrite relative URLs
// ---------------------- // ----------------------
// With this enabled relative URLs found in the extracted content // With this enabled relative URLs found in the extracted content
@ -67,7 +121,7 @@ $options->exclude_items_on_fail = 'user';
// Enable multi-page support // Enable multi-page support
// ------------------------- // -------------------------
// If enabled, we will try to follow next page links on multi-page articles. // 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. // in a site config file.
$options->multipage = true; $options->multipage = true;
@ -125,10 +179,10 @@ $options->detect_language = 1;
// Registration key // Registration key
// --------------- // ---------------
// The registration key is optional. It is not required to use Full-Text RSS, // 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 // 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 // only used on admin pages which help you update site patterns with the
// latest version offered by FiveFilters.org. For these admin-related // latest version offered by FiveFilters.org. For these admin-related
// tasks to complete, we will require a valid registration key. // 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 // If you would like one, you can purchase the latest version of Full-Text RSS
// at http://fivefilters.org/content-only/ // 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. // 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. // 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'. // The default username is 'admin'.
// If overriding with an environment variable, separate username and password with a colon, e.g.: // If overriding with an environment variable, separate username and password with a colon, e.g.:
// ftr_admin_credentials: admin:my-secret-password // ftr_admin_credentials: admin:my-secret-password
// Example: $options->admin_credentials = array('username'=>'admin', 'password'=>'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 // URLs to allow
// ---------------------- // ----------------------
@ -178,12 +232,12 @@ $options->key_required = false;
// ---------------------- // ----------------------
// By default, when processing feeds, we assume item titles in the 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 // 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 // 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 // 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 titles. Alternatively, if set to 'user' (default) we'll use the
// extracted title if you pass '&use_extracted_title' in the querystring. // extracted title if you pass '&use_extracted_title' in the querystring.
// Possible values: // Possible values:
// * Favour feed titles: true // * Favour feed titles: true
// * Favour extracted titles: false // * Favour extracted titles: false
// * Favour feed titles with user override: 'user' (default) // * 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 // 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) // 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 // copy of the code. This is here if you'd like to restrict access to
// _your_ copy. // _your_ copy.
// Keys let you group users - those with a key and those without - and // Keys let you group users - those with a key and those without - and
// restrict access to the service to those without a key. // restrict access to the service to those without a key.
// If you want everyone to access the service in the same way, you can // 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. // 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. // in each mode.
// Note: Explicitly including the index number (1 and 2 in the examples below) // Note: Explicitly including the index number (1 and 2 in the examples below)
// is highly recommended (when generating feeds, we encode the key and // is highly recommended (when generating feeds, we encode the key and
// refer to it by index number and hash). // refer to it by index number and hash).
$options->api_keys = array(); $options->api_keys = array();
// Example: // Example:
@ -232,13 +286,13 @@ $options->max_entries_with_key = 10;
// filter the resulting HTML for XSS attacks, making it redundant for // filter the resulting HTML for XSS attacks, making it redundant for
// Full-Text RSS do the same. Similarly with frameworks/CMS which display // 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. // 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 // 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 // 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 // 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 // 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 // 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 // If enabled, we'll pass retrieved HTML content through htmLawed with
// safe flag on and style attributes denied, see // safe flag on and style attributes denied, see
// http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed/htmLawed_README.htm#s3.6 // http://www.bioinformatics.org/phplabware/internal_utilities/htmLawed/htmLawed_README.htm#s3.6
@ -253,8 +307,8 @@ $options->xss_filter = 'user';
// Allowed parsers // Allowed parsers
// ---------------------- // ----------------------
// Full-Text RSS attempts to use PHP's libxml extension to process HTML. // 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. // While fast, on some sites it may not always produce good results.
// For these sites, you can specify an alternative HTML parser: // For these sites, you can specify an alternative HTML parser:
// parser: html5lib // parser: html5lib
// The html5lib parser is bundled with Full-Text RSS. // The html5lib parser is bundled with Full-Text RSS.
// see http://code.google.com/p/html5lib/ // see http://code.google.com/p/html5lib/
@ -273,7 +327,7 @@ $options->cors = false;
// Use APC user cache? // 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.' // for the first time) in APC's user cache. Keys prefixed with 'sc.'
// This improves performance by reducing disk access. // This improves performance by reducing disk access.
// Note: this has no effect if APC is unavailable on your server. // Note: this has no effect if APC is unavailable on your server.
@ -346,7 +400,7 @@ $options->rewrite_url = array(
// Valid actions: // Valid actions:
// * 'exclude' - exclude this item from the result // * 'exclude' - exclude this item from the result
// * 'link' - create HTML link to the item // * 'link' - create HTML link to the item
$options->content_type_exc = array( $options->content_type_exc = array(
'application/pdf' => array('action'=>'link', 'name'=>'PDF'), 'application/pdf' => array('action'=>'link', 'name'=>'PDF'),
'image' => array('action'=>'link', 'name'=>'Image'), 'image' => array('action'=>'link', 'name'=>'Image'),
'audio' => array('action'=>'link', 'name'=>'Audio'), 'audio' => array('action'=>'link', 'name'=>'Audio'),
@ -375,13 +429,13 @@ $options->cache_cleanup = 100;
/// DO NOT CHANGE ANYTHING BELOW THIS /////////// /// 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 (basename(__FILE__) == 'config.php') {
if (file_exists(dirname(__FILE__).'/custom_config.php')) { if (file_exists(dirname(__FILE__).'/custom_config.php')) {
require_once dirname(__FILE__).'/custom_config.php'; require_once dirname(__FILE__).'/custom_config.php';
} }
// check for environment variables - often used on cloud platforms // check for environment variables - often used on cloud platforms
// environment variables should be prefixed with 'ftr_', e.g. // environment variables should be prefixed with 'ftr_', e.g.
// ftr_max_entries: 1 // ftr_max_entries: 1

File diff suppressed because it is too large Load Diff

View File

@ -1,338 +1,343 @@
<?php <?php
/** /**
* Site Config * Site Config
* *
* Each instance of this class should hold extraction patterns and other directives * Each instance of this class should hold extraction patterns and other directives
* for a website. See ContentExtractor class to see how it's used. * for a website. See ContentExtractor class to see how it's used.
* *
* @version 0.7 * @version 0.8
* @date 2012-08-27 * @date 2013-04-16
* @author Keyvan Minoukadeh * @author Keyvan Minoukadeh
* @copyright 2012 Keyvan Minoukadeh * @copyright 2013 Keyvan Minoukadeh
* @license http://www.gnu.org/licenses/agpl-3.0.html AGPL v3 * @license http://www.gnu.org/licenses/agpl-3.0.html AGPL v3
*/ */
class SiteConfig class SiteConfig
{ {
// Use first matching element as title (0 or more xpath expressions) // Use first matching element as title (0 or more xpath expressions)
public $title = array(); public $title = array();
// Use first matching element as body (0 or more xpath expressions) // Use first matching element as body (0 or more xpath expressions)
public $body = array(); public $body = array();
// Use first matching element as author (0 or more xpath expressions) // Use first matching element as author (0 or more xpath expressions)
public $author = array(); public $author = array();
// Use first matching element as date (0 or more xpath expressions) // Use first matching element as date (0 or more xpath expressions)
public $date = array(); public $date = array();
// Strip elements matching these xpath expressions (0 or more) // Strip elements matching these xpath expressions (0 or more)
public $strip = array(); public $strip = array();
// Strip elements which contain these strings (0 or more) in the id or class attribute // Strip elements which contain these strings (0 or more) in the id or class attribute
public $strip_id_or_class = array(); public $strip_id_or_class = array();
// Strip images which contain these strings (0 or more) in the src attribute // Strip images which contain these strings (0 or more) in the src attribute
public $strip_image_src = array(); public $strip_image_src = array();
// Additional HTTP headers to send // Additional HTTP headers to send
// NOT YET USED // NOT YET USED
public $http_header = array(); public $http_header = array();
// Process HTML with tidy before creating DOM (bool or null if undeclared) // Process HTML with tidy before creating DOM (bool or null if undeclared)
public $tidy = null; public $tidy = null;
protected $default_tidy = true; // used if undeclared protected $default_tidy = true; // used if undeclared
// Autodetect title/body if xpath expressions fail to produce results. // Autodetect title/body if xpath expressions fail to produce results.
// Note that this applies to title and body separately, ie. // Note that this applies to title and body separately, ie.
// * if we get a body match but no title match, this option will determine whether we autodetect title // * if we get a body match but no title match, this option will determine whether we autodetect title
// * if neither match, this determines whether we autodetect title and body. // * if neither match, this determines whether we autodetect title and body.
// Also note that this only applies when there is at least one xpath expression in title or body, ie. // Also note that this only applies when there is at least one xpath expression in title or body, ie.
// * if title and body are both empty (no xpath expressions), this option has no effect (both title and body will be auto-detected) // * if title and body are both empty (no xpath expressions), this option has no effect (both title and body will be auto-detected)
// * if there's an xpath expression for title and none for body, body will be auto-detected and this option will determine whether we auto-detect title if the xpath expression for it fails to produce results. // * if there's an xpath expression for title and none for body, body will be auto-detected and this option will determine whether we auto-detect title if the xpath expression for it fails to produce results.
// Usage scenario: you want to extract something specific from a set of URLs, e.g. a table, and if the table is not found, you want to ignore the entry completely. Auto-detection is unlikely to succeed here, so you construct your patterns and set this option to false. Another scenario may be a site where auto-detection has proven to fail (or worse, picked up the wrong content). // Usage scenario: you want to extract something specific from a set of URLs, e.g. a table, and if the table is not found, you want to ignore the entry completely. Auto-detection is unlikely to succeed here, so you construct your patterns and set this option to false. Another scenario may be a site where auto-detection has proven to fail (or worse, picked up the wrong content).
// bool or null if undeclared // bool or null if undeclared
public $autodetect_on_failure = null; public $autodetect_on_failure = null;
protected $default_autodetect_on_failure = true; // used if undeclared protected $default_autodetect_on_failure = true; // used if undeclared
// Clean up content block - attempt to remove elements that appear to be superfluous // Clean up content block - attempt to remove elements that appear to be superfluous
// bool or null if undeclared // bool or null if undeclared
public $prune = null; public $prune = null;
protected $default_prune = true; // used if undeclared protected $default_prune = true; // used if undeclared
// Test URL - if present, can be used to test the config above // Test URL - if present, can be used to test the config above
public $test_url = array(); public $test_url = array();
// Single-page link - should identify a link element or URL pointing to the page holding the entire article // Single-page link - should identify a link element or URL pointing to the page holding the entire article
// This is useful for sites which split their articles across multiple pages. Links to such pages tend to // This is useful for sites which split their articles across multiple pages. Links to such pages tend to
// display the first page with links to the other pages at the bottom. Often there is also a link to a page // display the first page with links to the other pages at the bottom. Often there is also a link to a page
// which displays the entire article on one page (e.g. 'print view'). // which displays the entire article on one page (e.g. 'print view').
// This should be an XPath expression identifying the link to that page. If present and we find a match, // This should be an XPath expression identifying the link to that page. If present and we find a match,
// we will retrieve that page and the rest of the options in this config will be applied to the new page. // we will retrieve that page and the rest of the options in this config will be applied to the new page.
public $single_page_link = array(); public $single_page_link = array();
public $next_page_link = array(); public $next_page_link = array();
// Single-page link in feed? - same as above, but patterns applied to item description HTML taken from feed // Single-page link in feed? - same as above, but patterns applied to item description HTML taken from feed
public $single_page_link_in_feed = array(); public $single_page_link_in_feed = array();
// Which parser to use for turning raw HTML into a DOMDocument (either 'libxml' or 'html5lib') // Which parser to use for turning raw HTML into a DOMDocument (either 'libxml' or 'html5lib')
// string or null if undeclared // string or null if undeclared
public $parser = null; public $parser = null;
protected $default_parser = 'libxml'; // used if undeclared protected $default_parser = 'libxml'; // used if undeclared
// Strings to search for in HTML before processing begins (used with $replace_string) // Strings to search for in HTML before processing begins (used with $replace_string)
public $find_string = array(); public $find_string = array();
// Strings to replace those found in $find_string before HTML processing begins // Strings to replace those found in $find_string before HTML processing begins
public $replace_string = array(); public $replace_string = array();
// the options below cannot be set in the config files which this class represents // the options below cannot be set in the config files which this class represents
//public $cache_in_apc = false; // used to decide if we should cache in apc or not //public $cache_in_apc = false; // used to decide if we should cache in apc or not
public $cache_key = null; public $cache_key = null;
public static $debug = false; public static $debug = false;
protected static $apc = false; protected static $apc = false;
protected static $config_path; protected static $config_path;
protected static $config_path_fallback; protected static $config_path_fallback;
protected static $config_cache = array(); protected static $config_cache = array();
const HOSTNAME_REGEX = '/^(([a-zA-Z0-9-]*[a-zA-Z0-9])\.)*([A-Za-z0-9-]*[A-Za-z0-9])$/'; const HOSTNAME_REGEX = '/^(([a-zA-Z0-9-]*[a-zA-Z0-9])\.)*([A-Za-z0-9-]*[A-Za-z0-9])$/';
protected static function debug($msg) { protected static function debug($msg) {
if (self::$debug) { if (self::$debug) {
//$mem = round(memory_get_usage()/1024, 2); //$mem = round(memory_get_usage()/1024, 2);
//$memPeak = round(memory_get_peak_usage()/1024, 2); //$memPeak = round(memory_get_peak_usage()/1024, 2);
echo '* ',$msg; echo '* ',$msg;
//echo ' - mem used: ',$mem," (peak: $memPeak)\n"; //echo ' - mem used: ',$mem," (peak: $memPeak)\n";
echo "\n"; echo "\n";
ob_flush(); ob_flush();
flush(); flush();
} }
} }
// enable APC caching of certain site config files? // enable APC caching of certain site config files?
// If enabled the following site config files will be // If enabled the following site config files will be
// cached in APC cache (when requested for first time): // cached in APC cache (when requested for first time):
// * anything in site_config/custom/ and its corresponding file in site_config/standard/ // * anything in site_config/custom/ and its corresponding file in site_config/standard/
// * the site config files associated with HTML fingerprints // * the site config files associated with HTML fingerprints
// * the global site config file // * the global site config file
// returns true if enabled, false otherwise // returns true if enabled, false otherwise
public static function use_apc($apc=true) { public static function use_apc($apc=true) {
if (!function_exists('apc_add')) { if (!function_exists('apc_add')) {
if ($apc) self::debug('APC will not be used (function apc_add does not exist)'); if ($apc) self::debug('APC will not be used (function apc_add does not exist)');
return false; return false;
} }
self::$apc = $apc; self::$apc = $apc;
return $apc; return $apc;
} }
// return bool or null // return bool or null
public function tidy($use_default=true) { public function tidy($use_default=true) {
if ($use_default) return (isset($this->tidy)) ? $this->tidy : $this->default_tidy; if ($use_default) return (isset($this->tidy)) ? $this->tidy : $this->default_tidy;
return $this->tidy; return $this->tidy;
} }
// return bool or null // return bool or null
public function prune($use_default=true) { public function prune($use_default=true) {
if ($use_default) return (isset($this->prune)) ? $this->prune : $this->default_prune; if ($use_default) return (isset($this->prune)) ? $this->prune : $this->default_prune;
return $this->prune; return $this->prune;
} }
// return string or null // return string or null
public function parser($use_default=true) { public function parser($use_default=true) {
if ($use_default) return (isset($this->parser)) ? $this->parser : $this->default_parser; if ($use_default) return (isset($this->parser)) ? $this->parser : $this->default_parser;
return $this->parser; return $this->parser;
} }
// return bool or null // return bool or null
public function autodetect_on_failure($use_default=true) { public function autodetect_on_failure($use_default=true) {
if ($use_default) return (isset($this->autodetect_on_failure)) ? $this->autodetect_on_failure : $this->default_autodetect_on_failure; if ($use_default) return (isset($this->autodetect_on_failure)) ? $this->autodetect_on_failure : $this->default_autodetect_on_failure;
return $this->autodetect_on_failure; return $this->autodetect_on_failure;
} }
public static function set_config_path($path, $fallback=null) { public static function set_config_path($path, $fallback=null) {
self::$config_path = $path; self::$config_path = $path;
self::$config_path_fallback = $fallback; self::$config_path_fallback = $fallback;
} }
public static function add_to_cache($key, SiteConfig $config, $use_apc=true) { public static function add_to_cache($key, SiteConfig $config, $use_apc=true) {
$key = strtolower($key); $key = strtolower($key);
if (substr($key, 0, 4) == 'www.') $key = substr($key, 4); if (substr($key, 0, 4) == 'www.') $key = substr($key, 4);
if ($config->cache_key) $key = $config->cache_key; if ($config->cache_key) $key = $config->cache_key;
self::$config_cache[$key] = $config; self::$config_cache[$key] = $config;
if (self::$apc && $use_apc) { if (self::$apc && $use_apc) {
self::debug("Adding site config to APC cache with key sc.$key"); self::debug("Adding site config to APC cache with key sc.$key");
apc_add("sc.$key", $config); apc_add("sc.$key", $config);
} }
self::debug("Cached site config with key $key"); self::debug("Cached site config with key $key");
} }
public static function is_cached($key) { public static function is_cached($key) {
$key = strtolower($key); $key = strtolower($key);
if (substr($key, 0, 4) == 'www.') $key = substr($key, 4); if (substr($key, 0, 4) == 'www.') $key = substr($key, 4);
if (array_key_exists($key, self::$config_cache)) { if (array_key_exists($key, self::$config_cache)) {
return true; return true;
} elseif (self::$apc && (bool)apc_fetch("sc.$key")) { } elseif (self::$apc && (bool)apc_fetch("sc.$key")) {
return true; return true;
} }
return false; return false;
} }
public function append(SiteConfig $newconfig) { public function append(SiteConfig $newconfig) {
// check for commands where we accept multiple statements (no test_url) // check for commands where we accept multiple statements (no test_url)
foreach (array('title', 'body', 'author', 'date', 'strip', 'strip_id_or_class', 'strip_image_src', 'single_page_link', 'single_page_link_in_feed', 'next_page_link', 'http_header', 'find_string', 'replace_string') as $var) { foreach (array('title', 'body', 'author', 'date', 'strip', 'strip_id_or_class', 'strip_image_src', 'single_page_link', 'single_page_link_in_feed', 'next_page_link', 'http_header') as $var) {
// append array elements for this config variable from $newconfig to this config // append array elements for this config variable from $newconfig to this config
//$this->$var = $this->$var + $newconfig->$var; //$this->$var = $this->$var + $newconfig->$var;
$this->$var = array_unique(array_merge($this->$var, $newconfig->$var)); $this->$var = array_unique(array_merge($this->$var, $newconfig->$var));
} }
// check for single statement commands // check for single statement commands
// we do not overwrite existing non null values // we do not overwrite existing non null values
foreach (array('tidy', 'prune', 'parser', 'autodetect_on_failure') as $var) { foreach (array('tidy', 'prune', 'parser', 'autodetect_on_failure') as $var) {
if ($this->$var === null) $this->$var = $newconfig->$var; if ($this->$var === null) $this->$var = $newconfig->$var;
} }
} // treat find_string and replace_string separately (don't apply array_unique) (thanks fabrizio!)
foreach (array('find_string', 'replace_string') as $var) {
// returns SiteConfig instance if an appropriate one is found, false otherwise // append array elements for this config variable from $newconfig to this config
// if $exact_host_match is true, we will not look for wildcard config matches //$this->$var = $this->$var + $newconfig->$var;
// by default if host is 'test.example.org' we will look for and load '.example.org.txt' if it exists $this->$var = array_merge($this->$var, $newconfig->$var);
public static function build($host, $exact_host_match=false) { }
$host = strtolower($host); }
if (substr($host, 0, 4) == 'www.') $host = substr($host, 4);
if (!$host || (strlen($host) > 200) || !preg_match(self::HOSTNAME_REGEX, ltrim($host, '.'))) return false; // returns SiteConfig instance if an appropriate one is found, false otherwise
// check for site configuration // if $exact_host_match is true, we will not look for wildcard config matches
$try = array($host); // by default if host is 'test.example.org' we will look for and load '.example.org.txt' if it exists
// should we look for wildcard matches public static function build($host, $exact_host_match=false) {
if (!$exact_host_match) { $host = strtolower($host);
$split = explode('.', $host); if (substr($host, 0, 4) == 'www.') $host = substr($host, 4);
if (count($split) > 1) { if (!$host || (strlen($host) > 200) || !preg_match(self::HOSTNAME_REGEX, ltrim($host, '.'))) return false;
array_shift($split); // check for site configuration
$try[] = '.'.implode('.', $split); $try = array($host);
} // should we look for wildcard matches
} if (!$exact_host_match) {
$split = explode('.', $host);
// look for site config file in primary folder if (count($split) > 1) {
self::debug(". looking for site config for $host in primary folder"); array_shift($split);
foreach ($try as $h) { $try[] = '.'.implode('.', $split);
if (array_key_exists($h, self::$config_cache)) { }
self::debug("... site config for $h already loaded in this request"); }
return self::$config_cache[$h];
} elseif (self::$apc && ($sconfig = apc_fetch("sc.$h"))) { // look for site config file in primary folder
self::debug("... site config for $h in APC cache"); self::debug(". looking for site config for $host in primary folder");
return $sconfig; foreach ($try as $h) {
} elseif (file_exists(self::$config_path."/$h.txt")) { if (array_key_exists($h, self::$config_cache)) {
self::debug("... found site config ($h.txt)"); self::debug("... site config for $h already loaded in this request");
$file_primary = self::$config_path."/$h.txt"; return self::$config_cache[$h];
$matched_name = $h; } elseif (self::$apc && ($sconfig = apc_fetch("sc.$h"))) {
break; self::debug("... site config for $h in APC cache");
} return $sconfig;
} } elseif (file_exists(self::$config_path."/$h.txt")) {
self::debug("... found site config ($h.txt)");
// if we found site config, process it $file_primary = self::$config_path."/$h.txt";
if (isset($file_primary)) { $matched_name = $h;
$config_lines = file($file_primary, FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES); break;
if (!$config_lines || !is_array($config_lines)) return false; }
$config = self::build_from_array($config_lines); }
// if APC caching is available and enabled, mark this for cache
//$config->cache_in_apc = true; // if we found site config, process it
$config->cache_key = $matched_name; if (isset($file_primary)) {
$config_lines = file($file_primary, FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
// if autodetec on failure is off (on by default) we do not need to look if (!$config_lines || !is_array($config_lines)) return false;
// in secondary folder $config = self::build_from_array($config_lines);
if (!$config->autodetect_on_failure()) { // if APC caching is available and enabled, mark this for cache
self::debug('... autodetect on failure is disabled (no other site config files will be loaded)'); //$config->cache_in_apc = true;
return $config; $config->cache_key = $matched_name;
}
} // if autodetec on failure is off (on by default) we do not need to look
// in secondary folder
// look for site config file in secondary folder if (!$config->autodetect_on_failure()) {
if (isset(self::$config_path_fallback)) { self::debug('... autodetect on failure is disabled (no other site config files will be loaded)');
self::debug(". looking for site config for $host in secondary folder"); return $config;
foreach ($try as $h) { }
if (file_exists(self::$config_path_fallback."/$h.txt")) { }
self::debug("... found site config in secondary folder ($h.txt)");
$file_secondary = self::$config_path_fallback."/$h.txt"; // look for site config file in secondary folder
$matched_name = $h; if (isset(self::$config_path_fallback)) {
break; self::debug(". looking for site config for $host in secondary folder");
} foreach ($try as $h) {
} if (file_exists(self::$config_path_fallback."/$h.txt")) {
if (!isset($file_secondary)) { self::debug("... found site config in secondary folder ($h.txt)");
self::debug("... no site config match in secondary folder"); $file_secondary = self::$config_path_fallback."/$h.txt";
} $matched_name = $h;
} break;
}
// return false if no config file found }
if (!isset($file_primary) && !isset($file_secondary)) { if (!isset($file_secondary)) {
self::debug("... no site config match for $host"); self::debug("... no site config match in secondary folder");
return false; }
} }
// return primary config if secondary not found // return false if no config file found
if (!isset($file_secondary) && isset($config)) { if (!isset($file_primary) && !isset($file_secondary)) {
return $config; self::debug("... no site config match for $host");
} return false;
}
// process secondary config file
$config_lines = file($file_secondary, FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES); // return primary config if secondary not found
if (!$config_lines || !is_array($config_lines)) { if (!isset($file_secondary) && isset($config)) {
// failed to process secondary return $config;
if (isset($config)) { }
// return primary config
return $config; // process secondary config file
} else { $config_lines = file($file_secondary, FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
return false; if (!$config_lines || !is_array($config_lines)) {
} // failed to process secondary
} if (isset($config)) {
// return primary config
// merge with primary and return return $config;
if (isset($config)) { } else {
self::debug('. merging config files'); return false;
$config->append(self::build_from_array($config_lines)); }
return $config; }
} else {
// return just secondary // merge with primary and return
$config = self::build_from_array($config_lines); if (isset($config)) {
// if APC caching is available and enabled, mark this for cache self::debug('. merging config files');
//$config->cache_in_apc = true; $config->append(self::build_from_array($config_lines));
$config->cache_key = $matched_name; return $config;
return $config; } else {
} // return just secondary
} $config = self::build_from_array($config_lines);
// if APC caching is available and enabled, mark this for cache
public static function build_from_array(array $lines) { //$config->cache_in_apc = true;
$config = new SiteConfig(); $config->cache_key = $matched_name;
foreach ($lines as $line) { return $config;
$line = trim($line); }
}
// skip comments, empty lines
if ($line == '' || $line[0] == '#') continue; public static function build_from_array(array $lines) {
$config = new SiteConfig();
// get command foreach ($lines as $line) {
$command = explode(':', $line, 2); $line = trim($line);
// if there's no colon ':', skip this line
if (count($command) != 2) continue; // skip comments, empty lines
$val = trim($command[1]); if ($line == '' || $line[0] == '#') continue;
$command = trim($command[0]);
if ($command == '' || $val == '') continue; // get command
$command = explode(':', $line, 2);
// check for commands where we accept multiple statements // if there's no colon ':', skip this line
if (in_array($command, array('title', 'body', 'author', 'date', 'strip', 'strip_id_or_class', 'strip_image_src', 'single_page_link', 'single_page_link_in_feed', 'next_page_link', 'http_header', 'test_url', 'find_string', 'replace_string'))) { if (count($command) != 2) continue;
array_push($config->$command, $val); $val = trim($command[1]);
// check for single statement commands that evaluate to true or false $command = trim($command[0]);
} elseif (in_array($command, array('tidy', 'prune', 'autodetect_on_failure'))) { if ($command == '' || $val == '') continue;
$config->$command = ($val == 'yes');
// check for single statement commands stored as strings // check for commands where we accept multiple statements
} elseif (in_array($command, array('parser'))) { if (in_array($command, array('title', 'body', 'author', 'date', 'strip', 'strip_id_or_class', 'strip_image_src', 'single_page_link', 'single_page_link_in_feed', 'next_page_link', 'http_header', 'test_url', 'find_string', 'replace_string'))) {
$config->$command = $val; array_push($config->$command, $val);
// check for replace_string(find): replace // check for single statement commands that evaluate to true or false
} elseif ((substr($command, -1) == ')') && preg_match('!^([a-z0-9_]+)\((.*?)\)$!i', $command, $match)) { } elseif (in_array($command, array('tidy', 'prune', 'autodetect_on_failure'))) {
if (in_array($match[1], array('replace_string'))) { $config->$command = ($val == 'yes');
$command = $match[1]; // check for single statement commands stored as strings
array_push($config->find_string, $match[2]); } elseif (in_array($command, array('parser'))) {
array_push($config->$command, $val); $config->$command = $val;
} // check for replace_string(find): replace
} } elseif ((substr($command, -1) == ')') && preg_match('!^([a-z0-9_]+)\((.*?)\)$!i', $command, $match)) {
} if (in_array($match[1], array('replace_string'))) {
return $config; $command = $match[1];
} array_push($config->find_string, $match[2]);
} array_push($config->$command, $val);
?> }
}
}
return $config;
}
}

100
inc/3rdparty/libraries/feedwriter/FeedItem.php vendored Normal file → Executable file
View File

@ -1,7 +1,7 @@
<?php <?php
/** /**
* Univarsel Feed Writer * Univarsel Feed Writer
* *
* FeedItem class - Used as feed element in FeedWriter class * FeedItem class - Used as feed element in FeedWriter class
* *
* @package UnivarselFeedWriter * @package UnivarselFeedWriter
@ -12,20 +12,20 @@
{ {
private $elements = array(); //Collection of feed elements private $elements = array(); //Collection of feed elements
private $version; private $version;
/** /**
* Constructor * Constructor
* *
* @param contant (RSS1/RSS2/ATOM) RSS2 is default. * @param contant (RSS1/RSS2/ATOM) RSS2 is default.
*/ */
function __construct($version = RSS2) function __construct($version = RSS2)
{ {
$this->version = $version; $this->version = $version;
} }
/** /**
* Set element (overwrites existing elements with $elementName) * Set element (overwrites existing elements with $elementName)
* *
* @access public * @access public
* @param srting The tag name of an element * @param srting The tag name of an element
* @param srting The content of tag * @param srting The content of tag
@ -38,11 +38,11 @@
unset($this->elements[$elementName]); unset($this->elements[$elementName]);
} }
$this->addElement($elementName, $content, $attributes); $this->addElement($elementName, $content, $attributes);
} }
/** /**
* Add an element to elements array * Add an element to elements array
* *
* @access public * @access public
* @param srting The tag name of an element * @param srting The tag name of an element
* @param srting The content of tag * @param srting The content of tag
@ -61,11 +61,11 @@
$this->elements[$elementName][$i]['content'] = $content; $this->elements[$elementName][$i]['content'] = $content;
$this->elements[$elementName][$i]['attributes'] = $attributes; $this->elements[$elementName][$i]['attributes'] = $attributes;
} }
/** /**
* Set multiple feed elements from an array. * Set multiple feed elements from an array.
* Elements which have attributes cannot be added by this method * Elements which have attributes cannot be added by this method
* *
* @access public * @access public
* @param array array of elements in 'tagName' => 'tagContent' format. * @param array array of elements in 'tagName' => 'tagContent' format.
* @return void * @return void
@ -73,15 +73,15 @@
public function addElementArray($elementArray) public function addElementArray($elementArray)
{ {
if(! is_array($elementArray)) return; if(! is_array($elementArray)) return;
foreach ($elementArray as $elementName => $content) foreach ($elementArray as $elementName => $content)
{ {
$this->addElement($elementName, $content); $this->addElement($elementName, $content);
} }
} }
/** /**
* Return the collection of elements in this feed item * Return the collection of elements in this feed item
* *
* @access public * @access public
* @return array * @return array
*/ */
@ -89,68 +89,74 @@
{ {
return $this->elements; return $this->elements;
} }
// Wrapper functions ------------------------------------------------------ // Wrapper functions ------------------------------------------------------
/** /**
* Set the 'dscription' element of feed item * Set the 'dscription' element of feed item
* *
* @access public * @access public
* @param string The content of 'description' element * @param string The content of 'description' element
* @return void * @return void
*/ */
public function setDescription($description) public function setDescription($description)
{ {
$this->setElement('description', $description); $tag = ($this->version == ATOM)? 'summary' : 'description';
$this->setElement($tag, $description);
} }
/** /**
* @desc Set the 'title' element of feed item * @desc Set the 'title' element of feed item
* @access public * @access public
* @param string The content of 'title' element * @param string The content of 'title' element
* @return void * @return void
*/ */
public function setTitle($title) public function setTitle($title)
{ {
$this->setElement('title', $title); $this->setElement('title', $title);
} }
/** /**
* Set the 'date' element of feed item * Set the 'date' element of feed item
* *
* @access public * @access public
* @param string The content of 'date' element * @param string The content of 'date' element
* @return void * @return void
*/ */
public function setDate($date) public function setDate($date)
{ {
if(! is_numeric($date)) if(! is_numeric($date))
{ {
$date = strtotime($date); $date = strtotime($date);
} }
if($this->version == RSS2) if($this->version == ATOM)
{ {
$tag = 'pubDate'; $tag = 'updated';
$value = date(DATE_RSS, $date); $value = date(DATE_ATOM, $date);
} }
else elseif($this->version == RSS2)
{ {
$tag = 'dc:date'; $tag = 'pubDate';
$value = date("Y-m-d", $date); $value = date(DATE_RSS, $date);
} }
else
$this->setElement($tag, $value); {
$tag = 'dc:date';
$value = date("Y-m-d", $date);
}
$this->setElement($tag, $value);
} }
/** /**
* Set the 'link' element of feed item * Set the 'link' element of feed item
* *
* @access public * @access public
* @param string The content of 'link' element * @param string The content of 'link' element
* @return void * @return void
*/ */
public function setLink($link) public function setLink($link)
{ {
if($this->version == RSS2 || $this->version == RSS1) if($this->version == RSS2 || $this->version == RSS1)
{ {
@ -161,27 +167,27 @@
{ {
$this->setElement('link','',array('href'=>$link)); $this->setElement('link','',array('href'=>$link));
$this->setElement('id', FeedWriter::uuid($link,'urn:uuid:')); $this->setElement('id', FeedWriter::uuid($link,'urn:uuid:'));
} }
} }
/** /**
* Set the 'source' element of feed item * Set the 'source' element of feed item
* *
* @access public * @access public
* @param string The content of 'source' element * @param string The content of 'source' element
* @return void * @return void
*/ */
public function setSource($link) public function setSource($link)
{ {
$attributes = array('url'=>$link); $attributes = array('url'=>$link);
$this->setElement('source', "wallabag",$attributes); $this->setElement('source', "wallabag",$attributes);
} }
/** /**
* Set the 'encloser' element of feed item * Set the 'encloser' element of feed item
* For RSS 2.0 only * For RSS 2.0 only
* *
* @access public * @access public
* @param string The url attribute of encloser tag * @param string The url attribute of encloser tag
* @param string The length attribute of encloser tag * @param string The length attribute of encloser tag
@ -193,6 +199,6 @@
$attributes = array('url'=>$url, 'length'=>$length, 'type'=>$type); $attributes = array('url'=>$url, 'length'=>$length, 'type'=>$type);
$this->setElement('enclosure','',$attributes); $this->setElement('enclosure','',$attributes);
} }
} // end of class FeedItem } // end of class FeedItem
?> ?>

View File

@ -97,15 +97,12 @@ define('JSONP', 3, true);
header('X-content-type-options: nosniff'); header('X-content-type-options: nosniff');
} elseif ($this->version == JSON) { } elseif ($this->version == JSON) {
header('Content-type: application/json; charset=UTF-8'); header('Content-type: application/json; charset=UTF-8');
$this->json = new stdClass();
} elseif ($this->version == JSONP) { } elseif ($this->version == JSONP) {
header('Content-type: application/javascript; charset=UTF-8'); header('Content-type: application/javascript; charset=UTF-8');
$this->json = new stdClass();
} }
} }
if ($this->version == JSON || $this->version == JSONP) {
$this->json = new stdClass();
}
$this->printHead(); $this->printHead();
$this->printChannels(); $this->printChannels();
@ -116,6 +113,11 @@ define('JSONP', 3, true);
} }
} }
public function &getItems()
{
return $this->items;
}
/** /**
* Create a new FeedItem. * Create a new FeedItem.
* *
@ -199,7 +201,8 @@ define('JSONP', 3, true);
*/ */
public function setDescription($description) public function setDescription($description)
{ {
$this->setChannelElement('description', $description); $tag = ($this->version == ATOM)? 'subtitle' : 'description';
$this->setChannelElement($tag, $desciption);
} }
/** /**
@ -244,7 +247,7 @@ define('JSONP', 3, true);
{ {
$out = '<?xml version="1.0" encoding="utf-8"?>'."\n"; $out = '<?xml version="1.0" encoding="utf-8"?>'."\n";
if ($this->xsl) $out .= '<?xml-stylesheet type="text/xsl" href="'.htmlspecialchars($this->xsl).'"?>' . PHP_EOL; if ($this->xsl) $out .= '<?xml-stylesheet type="text/xsl" href="'.htmlspecialchars($this->xsl).'"?>' . PHP_EOL;
$out .= '<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:media="http://search.yahoo.com/mrss/">' . PHP_EOL; $out .= '<rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:media="http://search.yahoo.com/mrss/">' . PHP_EOL;
echo $out; echo $out;
} }
elseif ($this->version == JSON || $this->version == JSONP) elseif ($this->version == JSON || $this->version == JSONP)

View File

@ -134,6 +134,7 @@ class HTML5_TreeBuilder {
// Namespaces for foreign content // Namespaces for foreign content
const NS_HTML = null; // to prevent DOM from requiring NS on everything const NS_HTML = null; // to prevent DOM from requiring NS on everything
const NS_XHTML = 'http://www.w3.org/1999/xhtml';
const NS_MATHML = 'http://www.w3.org/1998/Math/MathML'; const NS_MATHML = 'http://www.w3.org/1998/Math/MathML';
const NS_SVG = 'http://www.w3.org/2000/svg'; const NS_SVG = 'http://www.w3.org/2000/svg';
const NS_XLINK = 'http://www.w3.org/1999/xlink'; const NS_XLINK = 'http://www.w3.org/1999/xlink';
@ -3157,11 +3158,19 @@ class HTML5_TreeBuilder {
} }
private function insertElement($token, $append = true) { private function insertElement($token, $append = true) {
$el = $this->dom->createElementNS(self::NS_HTML, $token['name']); //$el = $this->dom->createElementNS(self::NS_HTML, $token['name']);
$namespaceURI = strpos($token['name'], ':') ? self::NS_XHTML : self::NS_HTML;
$el = $this->dom->createElementNS($namespaceURI, $token['name']);
if (!empty($token['attr'])) { if (!empty($token['attr'])) {
foreach($token['attr'] as $attr) { foreach($token['attr'] as $attr) {
if(!$el->hasAttribute($attr['name'])) {
// mike@macgirvin.com 2011-11-17, check attribute name for
// validity (ignoring extenders and combiners) as illegal chars in names
// causes everything to abort
$valid = preg_match('/^[a-zA-Z\_\:]([\-a-zA-Z0-9\_\:\.]+$)/',$attr['name']);
if($attr['name'] && (!$el->hasAttribute($attr['name'])) && ($valid)) {
$el->setAttribute($attr['name'], $attr['value']); $el->setAttribute($attr['name'], $attr['value']);
} }
} }

View File

@ -1,404 +1,403 @@
<?php <?php
/** /**
* Cookie Jar * Cookie Jar
* *
* PHP class for handling cookies, as defined by the Netscape spec: * PHP class for handling cookies, as defined by the Netscape spec:
* <http://curl.haxx.se/rfc/cookie_spec.html> * <http://curl.haxx.se/rfc/cookie_spec.html>
* *
* This class should be used to handle cookies (storing cookies from HTTP response messages, and * This class should be used to handle cookies (storing cookies from HTTP response messages, and
* sending out cookies in HTTP request messages). This has been adapted for FiveFilters.org * sending out cookies in HTTP request messages). This has been adapted for FiveFilters.org
* from the original version used in HTTP Navigator. See http://www.keyvan.net/code/http-navigator/ * from the original version used in HTTP Navigator. See http://www.keyvan.net/code/http-navigator/
* *
* This class is mainly based on Cookies.pm <http://search.cpan.org/author/GAAS/libwww-perl-5.65/ * This class is mainly based on Cookies.pm <http://search.cpan.org/author/GAAS/libwww-perl-5.65/
* lib/HTTP/Cookies.pm> from the libwww-perl collection <http://www.linpro.no/lwp/>. * lib/HTTP/Cookies.pm> from the libwww-perl collection <http://www.linpro.no/lwp/>.
* Unlike Cookies.pm, this class only supports the Netscape cookie spec, not RFC 2965. * Unlike Cookies.pm, this class only supports the Netscape cookie spec, not RFC 2965.
* *
* @version 0.5 * @version 0.5
* @date 2011-03-15 * @date 2011-03-15
* @see http://php.net/HttpRequestPool * @see http://php.net/HttpRequestPool
* @author Keyvan Minoukadeh * @author Keyvan Minoukadeh
* @copyright 2011 Keyvan Minoukadeh * @copyright 2011 Keyvan Minoukadeh
* @license http://www.gnu.org/licenses/agpl-3.0.html AGPL v3 * @license http://www.gnu.org/licenses/agpl-3.0.html AGPL v3
*/ */
class CookieJar class CookieJar
{ {
/** /**
* Cookies - array containing all cookies. * Cookies - array containing all cookies.
* *
* <pre> * <pre>
* Cookies are stored like this: * Cookies are stored like this:
* [domain][path][name] = array * [domain][path][name] = array
* where array is: * where array is:
* 0 => value, 1 => secure, 2 => expires * 0 => value, 1 => secure, 2 => expires
* </pre> * </pre>
* @var array * @var array
* @access private * @access private
*/ */
public $cookies = array(); public $cookies = array();
public $debug = false; public $debug = false;
/** /**
* Constructor * Constructor
*/ */
function __construct() { function __construct() {
} }
protected function debug($msg, $file=null, $line=null) { protected function debug($msg, $file=null, $line=null) {
if ($this->debug) { if ($this->debug) {
$mem = round(memory_get_usage()/1024, 2); $mem = round(memory_get_usage()/1024, 2);
$memPeak = round(memory_get_peak_usage()/1024, 2); $memPeak = round(memory_get_peak_usage()/1024, 2);
echo '* ',$msg; echo '* ',$msg;
if (isset($file, $line)) echo " ($file line $line)"; if (isset($file, $line)) echo " ($file line $line)";
echo ' - mem used: ',$mem," (peak: $memPeak)\n"; echo ' - mem used: ',$mem," (peak: $memPeak)\n";
ob_flush(); ob_flush();
flush(); flush();
} }
} }
/** /**
* Get matching cookies * Get matching cookies
* *
* Only use this method if you cannot use add_cookie_header(), for example, if you want to use * Only use this method if you cannot use add_cookie_header(), for example, if you want to use
* this cookie jar class without using the request class. * this cookie jar class without using the request class.
* *
* @param array $param associative array containing 'domain', 'path', 'secure' keys * @param array $param associative array containing 'domain', 'path', 'secure' keys
* @return string * @return string
* @see add_cookie_header() * @see add_cookie_header()
*/ */
public function getMatchingCookies($url) public function getMatchingCookies($url)
{ {
if (($parts = @parse_url($url)) && isset($parts['scheme'], $parts['host'], $parts['path'])) { if (($parts = @parse_url($url)) && isset($parts['scheme'], $parts['host'], $parts['path'])) {
$param['domain'] = $parts['host']; $param['domain'] = $parts['host'];
$param['path'] = $parts['path']; $param['path'] = $parts['path'];
$param['secure'] = (strtolower($parts['scheme']) == 'https'); $param['secure'] = (strtolower($parts['scheme']) == 'https');
unset($parts); unset($parts);
} else { } else {
return false; return false;
} }
// RFC 2965 notes: // RFC 2965 notes:
// If multiple cookies satisfy the criteria above, they are ordered in // If multiple cookies satisfy the criteria above, they are ordered in
// the Cookie header such that those with more specific Path attributes // the Cookie header such that those with more specific Path attributes
// precede those with less specific. Ordering with respect to other // precede those with less specific. Ordering with respect to other
// attributes (e.g., Domain) is unspecified. // attributes (e.g., Domain) is unspecified.
$domain = $param['domain']; $domain = $param['domain'];
if (strpos($domain, '.') === false) $domain .= '.local'; if (strpos($domain, '.') === false) $domain .= '.local';
$request_path = $param['path']; $request_path = $param['path'];
if ($request_path == '') $request_path = '/'; if ($request_path == '') $request_path = '/';
$request_secure = $param['secure']; $request_secure = $param['secure'];
$now = time(); $now = time();
$matched_cookies = array(); $matched_cookies = array();
// domain - find matching domains // domain - find matching domains
$this->debug('Finding matching domains for '.$domain, __FILE__, __LINE__); $this->debug('Finding matching domains for '.$domain, __FILE__, __LINE__);
while (strpos($domain, '.') !== false) { while (strpos($domain, '.') !== false) {
if (isset($this->cookies[$domain])) { if (isset($this->cookies[$domain])) {
$this->debug(' domain match found: '.$domain); $this->debug(' domain match found: '.$domain);
$cookies =& $this->cookies[$domain]; $cookies =& $this->cookies[$domain];
} else { } else {
$domain = $this->_reduce_domain($domain); $domain = $this->_reduce_domain($domain);
continue; continue;
} }
// paths - find matching paths starting from most specific // paths - find matching paths starting from most specific
$this->debug(' - Finding matching paths for '.$request_path); $this->debug(' - Finding matching paths for '.$request_path);
$paths = array_keys($cookies); $paths = array_keys($cookies);
usort($paths, array($this, '_cmp_length')); usort($paths, array($this, '_cmp_length'));
foreach ($paths as $path) { foreach ($paths as $path) {
// continue to next cookie if request path does not path-match cookie path // continue to next cookie if request path does not path-match cookie path
if (!$this->_path_match($request_path, $path)) continue; if (!$this->_path_match($request_path, $path)) continue;
// loop through cookie names // loop through cookie names
$this->debug(' path match found: '.$path); $this->debug(' path match found: '.$path);
foreach ($cookies[$path] as $name => $values) { foreach ($cookies[$path] as $name => $values) {
// if this cookie is secure but request isn't, continue to next cookie // if this cookie is secure but request isn't, continue to next cookie
if ($values[1] && !$request_secure) continue; if ($values[1] && !$request_secure) continue;
// if cookie is not a session cookie and has expired, continue to next cookie // if cookie is not a session cookie and has expired, continue to next cookie
if (is_int($values[2]) && ($values[2] < $now)) continue; if (is_int($values[2]) && ($values[2] < $now)) continue;
// cookie matches request // cookie matches request
$this->debug(' cookie match: '.$name.'='.$values[0]); $this->debug(' cookie match: '.$name.'='.$values[0]);
$matched_cookies[] = $name.'='.$values[0]; $matched_cookies[] = $name.'='.$values[0];
} }
} }
$domain = $this->_reduce_domain($domain); $domain = $this->_reduce_domain($domain);
} }
// return cookies // return cookies
return implode('; ', $matched_cookies); return implode('; ', $matched_cookies);
} }
/** /**
* Parse Set-Cookie values. * Parse Set-Cookie values.
* *
* Only use this method if you cannot use extract_cookies(), for example, if you want to use * Only use this method if you cannot use extract_cookies(), for example, if you want to use
* this cookie jar class without using the response class. * this cookie jar class without using the response class.
* *
* @param array $set_cookies array holding 1 or more "Set-Cookie" header values * @param array $set_cookies array holding 1 or more "Set-Cookie" header values
* @param array $param associative array containing 'host', 'path' keys * @param array $param associative array containing 'host', 'path' keys
* @return void * @return void
* @see extract_cookies() * @see extract_cookies()
*/ */
public function storeCookies($url, $set_cookies) public function storeCookies($url, $set_cookies)
{ {
if (count($set_cookies) == 0) return; if (count($set_cookies) == 0) return;
$param = @parse_url($url); $param = @parse_url($url);
if (!is_array($param) || !isset($param['host'])) return; if (!is_array($param) || !isset($param['host'])) return;
$request_host = $param['host']; $request_host = $param['host'];
if (strpos($request_host, '.') === false) $request_host .= '.local'; if (strpos($request_host, '.') === false) $request_host .= '.local';
$request_path = @$param['path']; $request_path = @$param['path'];
if ($request_path == '') $request_path = '/'; if ($request_path == '') $request_path = '/';
// //
// loop through set-cookie headers // loop through set-cookie headers
// //
foreach ($set_cookies as $set_cookie) { foreach ($set_cookies as $set_cookie) {
$this->debug('Parsing: '.$set_cookie); $this->debug('Parsing: '.$set_cookie);
// temporary cookie store (before adding to jar) // temporary cookie store (before adding to jar)
$tmp_cookie = array(); $tmp_cookie = array();
$param = explode(';', $set_cookie); $param = explode(';', $set_cookie);
// loop through params // loop through params
for ($x=0; $x<count($param); $x++) { for ($x=0; $x<count($param); $x++) {
$key_val = explode('=', $param[$x], 2); $key_val = explode('=', $param[$x], 2);
if (count($key_val) != 2) { if (count($key_val) != 2) {
// if the first param isn't a name=value pair, continue to the next set-cookie // if the first param isn't a name=value pair, continue to the next set-cookie
// header // header
if ($x == 0) continue 2; if ($x == 0) continue 2;
// check for secure flag // check for secure flag
if (strtolower(trim($key_val[0])) == 'secure') $tmp_cookie['secure'] = true; if (strtolower(trim($key_val[0])) == 'secure') $tmp_cookie['secure'] = true;
// continue to next param // continue to next param
continue; continue;
} }
list($key, $val) = array_map('trim', $key_val); list($key, $val) = array_map('trim', $key_val);
// first name=value pair is the cookie name and value // first name=value pair is the cookie name and value
// the name and value are stored under 'name' and 'value' to avoid conflicts // the name and value are stored under 'name' and 'value' to avoid conflicts
// with later parameters. // with later parameters.
if ($x == 0) { if ($x == 0) {
$tmp_cookie = array('name'=>$key, 'value'=>$val); $tmp_cookie = array('name'=>$key, 'value'=>$val);
continue; continue;
} }
$key = strtolower($key); $key = strtolower($key);
if (in_array($key, array('expires', 'path', 'domain', 'secure'))) { if (in_array($key, array('expires', 'path', 'domain', 'secure'))) {
$tmp_cookie[$key] = $val; $tmp_cookie[$key] = $val;
} }
} }
// //
// set cookie // set cookie
// //
// check domain // check domain
if (isset($tmp_cookie['domain']) && ($tmp_cookie['domain'] != $request_host) && if (isset($tmp_cookie['domain']) && ($tmp_cookie['domain'] != $request_host) &&
($tmp_cookie['domain'] != ".$request_host")) { ($tmp_cookie['domain'] != ".$request_host")) {
$domain = $tmp_cookie['domain']; $domain = $tmp_cookie['domain'];
if ((strpos($domain, '.') === false) && ($domain != 'local')) { if ((strpos($domain, '.') === false) && ($domain != 'local')) {
$this->debug(' - domain "'.$domain.'" has no dot and is not a local domain'); $this->debug(' - domain "'.$domain.'" has no dot and is not a local domain');
continue; continue;
} }
if (preg_match('/\.[0-9]+$/', $domain)) { if (preg_match('/\.[0-9]+$/', $domain)) {
$this->debug(' - domain "'.$domain.'" appears to be an ip address'); $this->debug(' - domain "'.$domain.'" appears to be an ip address');
continue; continue;
} }
if (substr($domain, 0, 1) != '.') $domain = ".$domain"; if (substr($domain, 0, 1) != '.') $domain = ".$domain";
if (!$this->_domain_match($request_host, $domain)) { if (!$this->_domain_match($request_host, $domain)) {
$this->debug(' - request host "'.$request_host.'" does not domain-match "'.$domain.'"'); $this->debug(' - request host "'.$request_host.'" does not domain-match "'.$domain.'"');
continue; continue;
} }
} else { } else {
// if domain is not specified in the set-cookie header, domain will default to // if domain is not specified in the set-cookie header, domain will default to
// the request host // the request host
$domain = $request_host; $domain = $request_host;
} }
// check path // check path
if (isset($tmp_cookie['path']) && ($tmp_cookie['path'] != '')) { if (isset($tmp_cookie['path']) && ($tmp_cookie['path'] != '')) {
$path = urldecode($tmp_cookie['path']); $path = urldecode($tmp_cookie['path']);
if (!$this->_path_match($request_path, $path)) { if (!$this->_path_match($request_path, $path)) {
$this->debug(' - request path "'.$request_path.'" does not path-match "'.$path.'"'); $this->debug(' - request path "'.$request_path.'" does not path-match "'.$path.'"');
continue; continue;
} }
} else { } else {
$path = $request_path; $path = $request_path;
$path = substr($path, 0, strrpos($path, '/')); $path = substr($path, 0, strrpos($path, '/'));
if ($path == '') $path = '/'; if ($path == '') $path = '/';
} }
// check if secure // check if secure
$secure = (isset($tmp_cookie['secure'])) ? true : false; $secure = (isset($tmp_cookie['secure'])) ? true : false;
// check expiry // check expiry
if (isset($tmp_cookie['expires'])) { if (isset($tmp_cookie['expires'])) {
if (($expires = strtotime($tmp_cookie['expires'])) < 0) { if (($expires = strtotime($tmp_cookie['expires'])) < 0) {
$expires = null; $expires = null;
} }
} else { } else {
$expires = null; $expires = null;
} }
// set cookie // set cookie
$this->set_cookie($domain, $path, $tmp_cookie['name'], $tmp_cookie['value'], $secure, $expires); $this->set_cookie($domain, $path, $tmp_cookie['name'], $tmp_cookie['value'], $secure, $expires);
} }
} }
// return array of set-cookie values extracted from HTTP response headers (string $h) // return array of set-cookie values extracted from HTTP response headers (string $h)
public function extractCookies($h) { public function extractCookies($h) {
$x = 0; $x = 0;
$lines = 0; $lines = 0;
$headers = array(); $headers = array();
$last_match = false; $last_match = false;
$h = explode("\n", $h); $h = explode("\n", $h);
foreach ($h as $line) { foreach ($h as $line) {
$line = rtrim($line); $line = rtrim($line);
$lines++; $lines++;
$trimmed_line = trim($line); $trimmed_line = trim($line);
if (isset($line_last)) { if (isset($line_last)) {
// check if we have \r\n\r\n (indicating the end of headers) // check if we have \r\n\r\n (indicating the end of headers)
// some servers will not use CRLF (\r\n), so we make CR (\r) optional. // some servers will not use CRLF (\r\n), so we make CR (\r) optional.
// if (preg_match('/\015?\012\015?\012/', $line_last.$line)) { // if (preg_match('/\015?\012\015?\012/', $line_last.$line)) {
// break; // break;
// } // }
// As an alternative, we can check if the current trimmed line is empty // As an alternative, we can check if the current trimmed line is empty
if ($trimmed_line == '') { if ($trimmed_line == '') {
break; break;
} }
// check for continuation line... // check for continuation line...
// RFC 2616 Section 2.2 "Basic Rules": // RFC 2616 Section 2.2 "Basic Rules":
// HTTP/1.1 header field values can be folded onto multiple lines if the // HTTP/1.1 header field values can be folded onto multiple lines if the
// continuation line begins with a space or horizontal tab. All linear // continuation line begins with a space or horizontal tab. All linear
// white space, including folding, has the same semantics as SP. A // white space, including folding, has the same semantics as SP. A
// recipient MAY replace any linear white space with a single SP before // recipient MAY replace any linear white space with a single SP before
// interpreting the field value or forwarding the message downstream. // interpreting the field value or forwarding the message downstream.
if ($last_match && preg_match('/^\s+(.*)/', $line, $match)) { if ($last_match && preg_match('/^\s+(.*)/', $line, $match)) {
// append to previous header value // append to previous header value
$headers[$x-1] .= ' '.rtrim($match[1]); $headers[$x-1] .= ' '.rtrim($match[1]);
continue; continue;
} }
} }
$line_last = $line; $line_last = $line;
// split header name and value // split header name and value
if (preg_match('/^Set-Cookie\s*:\s*(.*)/i', $line, $match)) { if (preg_match('/^Set-Cookie\s*:\s*(.*)/i', $line, $match)) {
$headers[$x++] = rtrim($match[1]); $headers[$x++] = rtrim($match[1]);
$last_match = true; $last_match = true;
} else { } else {
$last_match = false; $last_match = false;
} }
} }
return $headers; return $headers;
} }
/** /**
* Set Cookie * Set Cookie
* @param string $domain * @param string $domain
* @param string $path * @param string $path
* @param string $name cookie name * @param string $name cookie name
* @param string $value cookie value * @param string $value cookie value
* @param bool $secure * @param bool $secure
* @param int $expires expiry time (null if session cookie, <= 0 will delete cookie) * @param int $expires expiry time (null if session cookie, <= 0 will delete cookie)
* @return void * @return void
*/ */
function set_cookie($domain, $path, $name, $value, $secure=false, $expires=null) function set_cookie($domain, $path, $name, $value, $secure=false, $expires=null)
{ {
if ($domain == '') return; if ($domain == '') return;
if ($path == '') return; if ($path == '') return;
if ($name == '') return; if ($name == '') return;
// check if cookie needs to go // check if cookie needs to go
if (isset($expires) && ($expires <= 0)) { if (isset($expires) && ($expires <= 0)) {
if (isset($this->cookies[$domain][$path][$name])) unset($this->cookies[$domain][$path][$name]); if (isset($this->cookies[$domain][$path][$name])) unset($this->cookies[$domain][$path][$name]);
return; return;
} }
if ($value == '') return; if ($value == '') return;
$this->cookies[$domain][$path][$name] = array($value, $secure, $expires); $this->cookies[$domain][$path][$name] = array($value, $secure, $expires);
return; return;
} }
/** /**
* Clear cookies - [domain [,path [,name]]] - call method with no arguments to clear all cookies. * Clear cookies - [domain [,path [,name]]] - call method with no arguments to clear all cookies.
* @param string $domain * @param string $domain
* @param string $path * @param string $path
* @param string $name * @param string $name
* @return void * @return void
*/ */
function clear($domain=null, $path=null, $name=null) function clear($domain=null, $path=null, $name=null)
{ {
if (!isset($domain)) { if (!isset($domain)) {
$this->cookies = array(); $this->cookies = array();
} elseif (!isset($path)) { } elseif (!isset($path)) {
if (isset($this->cookies[$domain])) unset($this->cookies[$domain]); if (isset($this->cookies[$domain])) unset($this->cookies[$domain]);
} elseif (!isset($name)) { } elseif (!isset($name)) {
if (isset($this->cookies[$domain][$path])) unset($this->cookies[$domain][$path]); if (isset($this->cookies[$domain][$path])) unset($this->cookies[$domain][$path]);
} elseif (isset($name)) { } elseif (isset($name)) {
if (isset($this->cookies[$domain][$path][$name])) unset($this->cookies[$domain][$path][$name]); if (isset($this->cookies[$domain][$path][$name])) unset($this->cookies[$domain][$path][$name]);
} }
} }
/** /**
* Compare string length - used for sorting * Compare string length - used for sorting
* @access private * @access private
* @return int * @return int
*/ */
function _cmp_length($a, $b) function _cmp_length($a, $b)
{ {
$la = strlen($a); $lb = strlen($b); $la = strlen($a); $lb = strlen($b);
if ($la == $lb) return 0; if ($la == $lb) return 0;
return ($la > $lb) ? -1 : 1; return ($la > $lb) ? -1 : 1;
} }
/** /**
* Reduce domain * Reduce domain
* @param string $domain * @param string $domain
* @return string * @return string
* @access private * @access private
*/ */
function _reduce_domain($domain) function _reduce_domain($domain)
{ {
if ($domain == '') return ''; if ($domain == '') return '';
if (substr($domain, 0, 1) == '.') return substr($domain, 1); if (substr($domain, 0, 1) == '.') return substr($domain, 1);
return substr($domain, strpos($domain, '.')); return substr($domain, strpos($domain, '.'));
} }
/** /**
* Path match - check if path1 path-matches path2 * Path match - check if path1 path-matches path2
* *
* From RFC 2965: * From RFC 2965:
* <i>For two strings that represent paths, P1 and P2, P1 path-matches P2 * <i>For two strings that represent paths, P1 and P2, P1 path-matches P2
* if P2 is a prefix of P1 (including the case where P1 and P2 string- * if P2 is a prefix of P1 (including the case where P1 and P2 string-
* compare equal). Thus, the string /tec/waldo path-matches /tec.</i> * compare equal). Thus, the string /tec/waldo path-matches /tec.</i>
* @param string $path1 * @param string $path1
* @param string $path2 * @param string $path2
* @return bool * @return bool
* @access private * @access private
*/ */
function _path_match($path1, $path2) function _path_match($path1, $path2)
{ {
return (substr($path1, 0, strlen($path2)) == $path2); return (substr($path1, 0, strlen($path2)) == $path2);
} }
/** /**
* Domain match - check if domain1 domain-matches domain2 * Domain match - check if domain1 domain-matches domain2
* *
* A few extracts from RFC 2965: * A few extracts from RFC 2965:
* - A Set-Cookie2 from request-host y.x.foo.com for Domain=.foo.com * - A Set-Cookie2 from request-host y.x.foo.com for Domain=.foo.com
* would be rejected, because H is y.x and contains a dot. * would be rejected, because H is y.x and contains a dot.
* *
* - A Set-Cookie2 from request-host x.foo.com for Domain=.foo.com * - A Set-Cookie2 from request-host x.foo.com for Domain=.foo.com
* would be accepted. * would be accepted.
* *
* - A Set-Cookie2 with Domain=.com or Domain=.com., will always be * - A Set-Cookie2 with Domain=.com or Domain=.com., will always be
* rejected, because there is no embedded dot. * rejected, because there is no embedded dot.
* *
* - A Set-Cookie2 from request-host example for Domain=.local will * - A Set-Cookie2 from request-host example for Domain=.local will
* be accepted, because the effective host name for the request- * be accepted, because the effective host name for the request-
* host is example.local, and example.local domain-matches .local. * host is example.local, and example.local domain-matches .local.
* *
* I'm ignoring the first point for now (must check to see how other browsers handle * I'm ignoring the first point for now (must check to see how other browsers handle
* this rule for Set-Cookie headers) * this rule for Set-Cookie headers)
* *
* @param string $domain1 * @param string $domain1
* @param string $domain2 * @param string $domain2
* @return bool * @return bool
* @access private * @access private
*/ */
function _domain_match($domain1, $domain2) function _domain_match($domain1, $domain2)
{ {
$domain1 = strtolower($domain1); $domain1 = strtolower($domain1);
$domain2 = strtolower($domain2); $domain2 = strtolower($domain2);
while (strpos($domain1, '.') !== false) { while (strpos($domain1, '.') !== false) {
if ($domain1 == $domain2) return true; if ($domain1 == $domain2) return true;
$domain1 = $this->_reduce_domain($domain1); $domain1 = $this->_reduce_domain($domain1);
continue; continue;
} }
return false; return false;
} }
} }
?>

File diff suppressed because it is too large Load Diff

View File

@ -1,79 +1,78 @@
<?php <?php
/** /**
* Humble HTTP Agent extension for SimplePie_File * Humble HTTP Agent extension for SimplePie_File
* *
* This class is designed to extend and override SimplePie_File * This class is designed to extend and override SimplePie_File
* in order to prevent duplicate HTTP requests being sent out. * in order to prevent duplicate HTTP requests being sent out.
* The idea is to initialise an instance of Humble HTTP Agent * The idea is to initialise an instance of Humble HTTP Agent
* and attach it, to a static class variable, of this class. * and attach it, to a static class variable, of this class.
* SimplePie will then automatically initialise this class * SimplePie will then automatically initialise this class
* *
* @date 2011-02-28 * @date 2011-02-28
*/ */
class SimplePie_HumbleHttpAgent extends SimplePie_File class SimplePie_HumbleHttpAgent extends SimplePie_File
{ {
protected static $agent; protected static $agent;
var $url; var $url;
var $useragent; var $useragent;
var $success = true; var $success = true;
var $headers = array(); var $headers = array();
var $body; var $body;
var $status_code; var $status_code;
var $redirects = 0; var $redirects = 0;
var $error; var $error;
var $method = SIMPLEPIE_FILE_SOURCE_NONE; var $method = SIMPLEPIE_FILE_SOURCE_NONE;
public static function set_agent(HumbleHttpAgent $agent) { public static function set_agent(HumbleHttpAgent $agent) {
self::$agent = $agent; self::$agent = $agent;
} }
public function __construct($url, $timeout = 10, $redirects = 5, $headers = null, $useragent = null, $force_fsockopen = false) { public function __construct($url, $timeout = 10, $redirects = 5, $headers = null, $useragent = null, $force_fsockopen = false) {
if (class_exists('idna_convert')) if (class_exists('idna_convert'))
{ {
$idn = new idna_convert(); $idn = new idna_convert();
$parsed = SimplePie_Misc::parse_url($url); $parsed = SimplePie_Misc::parse_url($url);
$url = SimplePie_Misc::compress_parse_url($parsed['scheme'], $idn->encode($parsed['authority']), $parsed['path'], $parsed['query'], $parsed['fragment']); $url = SimplePie_Misc::compress_parse_url($parsed['scheme'], $idn->encode($parsed['authority']), $parsed['path'], $parsed['query'], $parsed['fragment']);
} }
$this->url = $url; $this->url = $url;
$this->useragent = $useragent; $this->useragent = $useragent;
if (preg_match('/^http(s)?:\/\//i', $url)) if (preg_match('/^http(s)?:\/\//i', $url))
{ {
if (!is_array($headers)) if (!is_array($headers))
{ {
$headers = array(); $headers = array();
} }
$this->method = SIMPLEPIE_FILE_SOURCE_REMOTE | SIMPLEPIE_FILE_SOURCE_CURL; $this->method = SIMPLEPIE_FILE_SOURCE_REMOTE | SIMPLEPIE_FILE_SOURCE_CURL;
$headers2 = array(); $headers2 = array();
foreach ($headers as $key => $value) { foreach ($headers as $key => $value) {
$headers2[] = "$key: $value"; $headers2[] = "$key: $value";
} }
//TODO: allow for HTTP headers //TODO: allow for HTTP headers
// curl_setopt($fp, CURLOPT_HTTPHEADER, $headers2); // curl_setopt($fp, CURLOPT_HTTPHEADER, $headers2);
$response = self::$agent->get($url); $response = self::$agent->get($url);
if ($response === false || !isset($response['status_code'])) { if ($response === false || !isset($response['status_code'])) {
$this->error = 'failed to fetch URL'; $this->error = 'failed to fetch URL';
$this->success = false; $this->success = false;
} else { } else {
// The extra lines at the end are there to satisfy SimplePie's HTTP parser. // The extra lines at the end are there to satisfy SimplePie's HTTP parser.
// The class expects a full HTTP message, whereas we're giving it only // The class expects a full HTTP message, whereas we're giving it only
// headers - the new lines indicate the start of the body. // headers - the new lines indicate the start of the body.
$parser = new SimplePie_HTTP_Parser($response['headers']."\r\n\r\n"); $parser = new SimplePie_HTTP_Parser($response['headers']."\r\n\r\n");
if ($parser->parse()) { if ($parser->parse()) {
$this->headers = $parser->headers; $this->headers = $parser->headers;
//$this->body = $parser->body; //$this->body = $parser->body;
$this->body = $response['body']; $this->body = $response['body'];
$this->status_code = $parser->status_code; $this->status_code = $parser->status_code;
} }
} }
} }
else else
{ {
$this->error = 'invalid URL'; $this->error = 'invalid URL';
$this->success = false; $this->success = false;
} }
} }
} }
?>

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,57 @@
<?php
class Text_LanguageDetect_Exception extends Exception
{
/**
* Database file could not be found
*/
const DB_NOT_FOUND = 10;
/**
* Database file found, but not readable
*/
const DB_NOT_READABLE = 11;
/**
* Database file is empty
*/
const DB_EMPTY = 12;
/**
* Database contents is not a PHP array
*/
const DB_NOT_ARRAY = 13;
/**
* Magic quotes are activated
*/
const MAGIC_QUOTES = 14;
/**
* Parameter of invalid type passed to method
*/
const PARAM_TYPE = 20;
/**
* Character in parameter is invalid
*/
const INVALID_CHAR = 21;
/**
* Language is not in the database
*/
const UNKNOWN_LANGUAGE = 30;
/**
* Error during block detection
*/
const BLOCK_DETECTION = 40;
/**
* Error while clustering languages
*/
const NO_HIGHEST_KEY = 50;
}

View File

@ -0,0 +1,339 @@
<?php
/**
* Part of Text_LanguageDetect
*
* PHP version 5
*
* @category Text
* @package Text_LanguageDetect
* @author Christian Weiske <cweiske@php.net>
* @copyright 2011 Christian Weiske <cweiske@php.net>
* @license http://www.debian.org/misc/bsd.license BSD
* @version SVN: $Id$
* @link http://pear.php.net/package/Text_LanguageDetect/
*/
/**
* Provides a mapping between the languages from lang.dat and the
* ISO 639-1 and ISO-639-2 codes.
*
* Note that this class contains only languages that exist in lang.dat.
*
* @category Text
* @package Text_LanguageDetect
* @author Christian Weiske <cweiske@php.net>
* @copyright 2011 Christian Weiske <cweiske@php.net>
* @license http://www.debian.org/misc/bsd.license BSD
* @link http://www.loc.gov/standards/iso639-2/php/code_list.php
*/
class Text_LanguageDetect_ISO639
{
/**
* Maps all language names from the language database to the
* ISO 639-1 2-letter language code.
*
* NULL indicates that there is no 2-letter code.
*
* @var array
*/
public static $nameToCode2 = array(
'albanian' => 'sq',
'arabic' => 'ar',
'azeri' => 'az',
'bengali' => 'bn',
'bulgarian' => 'bg',
'cebuano' => null,
'croatian' => 'hr',
'czech' => 'cs',
'danish' => 'da',
'dutch' => 'nl',
'english' => 'en',
'estonian' => 'et',
'farsi' => 'fa',
'finnish' => 'fi',
'french' => 'fr',
'german' => 'de',
'hausa' => 'ha',
'hawaiian' => null,
'hindi' => 'hi',
'hungarian' => 'hu',
'icelandic' => 'is',
'indonesian' => 'id',
'italian' => 'it',
'kazakh' => 'kk',
'kyrgyz' => 'ky',
'latin' => 'la',
'latvian' => 'lv',
'lithuanian' => 'lt',
'macedonian' => 'mk',
'mongolian' => 'mn',
'nepali' => 'ne',
'norwegian' => 'no',
'pashto' => 'ps',
'pidgin' => null,
'polish' => 'pl',
'portuguese' => 'pt',
'romanian' => 'ro',
'russian' => 'ru',
'serbian' => 'sr',
'slovak' => 'sk',
'slovene' => 'sl',
'somali' => 'so',
'spanish' => 'es',
'swahili' => 'sw',
'swedish' => 'sv',
'tagalog' => 'tl',
'turkish' => 'tr',
'ukrainian' => 'uk',
'urdu' => 'ur',
'uzbek' => 'uz',
'vietnamese' => 'vi',
'welsh' => 'cy',
);
/**
* Maps all language names from the language database to the
* ISO 639-2 3-letter language code.
*
* @var array
*/
public static $nameToCode3 = array(
'albanian' => 'sqi',
'arabic' => 'ara',
'azeri' => 'aze',
'bengali' => 'ben',
'bulgarian' => 'bul',
'cebuano' => 'ceb',
'croatian' => 'hrv',
'czech' => 'ces',
'danish' => 'dan',
'dutch' => 'nld',
'english' => 'eng',
'estonian' => 'est',
'farsi' => 'fas',
'finnish' => 'fin',
'french' => 'fra',
'german' => 'deu',
'hausa' => 'hau',
'hawaiian' => 'haw',
'hindi' => 'hin',
'hungarian' => 'hun',
'icelandic' => 'isl',
'indonesian' => 'ind',
'italian' => 'ita',
'kazakh' => 'kaz',
'kyrgyz' => 'kir',
'latin' => 'lat',
'latvian' => 'lav',
'lithuanian' => 'lit',
'macedonian' => 'mkd',
'mongolian' => 'mon',
'nepali' => 'nep',
'norwegian' => 'nor',
'pashto' => 'pus',
'pidgin' => 'crp',
'polish' => 'pol',
'portuguese' => 'por',
'romanian' => 'ron',
'russian' => 'rus',
'serbian' => 'srp',
'slovak' => 'slk',
'slovene' => 'slv',
'somali' => 'som',
'spanish' => 'spa',
'swahili' => 'swa',
'swedish' => 'swe',
'tagalog' => 'tgl',
'turkish' => 'tur',
'ukrainian' => 'ukr',
'urdu' => 'urd',
'uzbek' => 'uzb',
'vietnamese' => 'vie',
'welsh' => 'cym',
);
/**
* Maps ISO 639-1 2-letter language codes to the language names
* in the language database
*
* Not all languages have a 2 letter code, so some are missing
*
* @var array
*/
public static $code2ToName = array(
'ar' => 'arabic',
'az' => 'azeri',
'bg' => 'bulgarian',
'bn' => 'bengali',
'cs' => 'czech',
'cy' => 'welsh',
'da' => 'danish',
'de' => 'german',
'en' => 'english',
'es' => 'spanish',
'et' => 'estonian',
'fa' => 'farsi',
'fi' => 'finnish',
'fr' => 'french',
'ha' => 'hausa',
'hi' => 'hindi',
'hr' => 'croatian',
'hu' => 'hungarian',
'id' => 'indonesian',
'is' => 'icelandic',
'it' => 'italian',
'kk' => 'kazakh',
'ky' => 'kyrgyz',
'la' => 'latin',
'lt' => 'lithuanian',
'lv' => 'latvian',
'mk' => 'macedonian',
'mn' => 'mongolian',
'ne' => 'nepali',
'nl' => 'dutch',
'no' => 'norwegian',
'pl' => 'polish',
'ps' => 'pashto',
'pt' => 'portuguese',
'ro' => 'romanian',
'ru' => 'russian',
'sk' => 'slovak',
'sl' => 'slovene',
'so' => 'somali',
'sq' => 'albanian',
'sr' => 'serbian',
'sv' => 'swedish',
'sw' => 'swahili',
'tl' => 'tagalog',
'tr' => 'turkish',
'uk' => 'ukrainian',
'ur' => 'urdu',
'uz' => 'uzbek',
'vi' => 'vietnamese',
);
/**
* Maps ISO 639-2 3-letter language codes to the language names
* in the language database.
*
* @var array
*/
public static $code3ToName = array(
'ara' => 'arabic',
'aze' => 'azeri',
'ben' => 'bengali',
'bul' => 'bulgarian',
'ceb' => 'cebuano',
'ces' => 'czech',
'crp' => 'pidgin',
'cym' => 'welsh',
'dan' => 'danish',
'deu' => 'german',
'eng' => 'english',
'est' => 'estonian',
'fas' => 'farsi',
'fin' => 'finnish',
'fra' => 'french',
'hau' => 'hausa',
'haw' => 'hawaiian',
'hin' => 'hindi',
'hrv' => 'croatian',
'hun' => 'hungarian',
'ind' => 'indonesian',
'isl' => 'icelandic',
'ita' => 'italian',
'kaz' => 'kazakh',
'kir' => 'kyrgyz',
'lat' => 'latin',
'lav' => 'latvian',
'lit' => 'lithuanian',
'mkd' => 'macedonian',
'mon' => 'mongolian',
'nep' => 'nepali',
'nld' => 'dutch',
'nor' => 'norwegian',
'pol' => 'polish',
'por' => 'portuguese',
'pus' => 'pashto',
'rom' => 'romanian',
'rus' => 'russian',
'slk' => 'slovak',
'slv' => 'slovene',
'som' => 'somali',
'spa' => 'spanish',
'sqi' => 'albanian',
'srp' => 'serbian',
'swa' => 'swahili',
'swe' => 'swedish',
'tgl' => 'tagalog',
'tur' => 'turkish',
'ukr' => 'ukrainian',
'urd' => 'urdu',
'uzb' => 'uzbek',
'vie' => 'vietnamese',
);
/**
* Returns the 2-letter ISO 639-1 code for the given language name.
*
* @param string $lang English language name like "swedish"
*
* @return string Two-letter language code (e.g. "sv") or NULL if not found
*/
public static function nameToCode2($lang)
{
$lang = strtolower($lang);
if (!isset(self::$nameToCode2[$lang])) {
return null;
}
return self::$nameToCode2[$lang];
}
/**
* Returns the 3-letter ISO 639-2 code for the given language name.
*
* @param string $lang English language name like "swedish"
*
* @return string Three-letter language code (e.g. "swe") or NULL if not found
*/
public static function nameToCode3($lang)
{
$lang = strtolower($lang);
if (!isset(self::$nameToCode3[$lang])) {
return null;
}
return self::$nameToCode3[$lang];
}
/**
* Returns the language name for the given 2-letter ISO 639-1 code.
*
* @param string $code Two-letter language code (e.g. "sv")
*
* @return string English language name like "swedish"
*/
public static function code2ToName($code)
{
$lang = strtolower($code);
if (!isset(self::$code2ToName[$code])) {
return null;
}
return self::$code2ToName[$code];
}
/**
* Returns the language name for the given 3-letter ISO 639-2 code.
*
* @param string $code Three-letter language code (e.g. "swe")
*
* @return string English language name like "swedish"
*/
public static function code3ToName($code)
{
$lang = strtolower($code);
if (!isset(self::$code3ToName[$code])) {
return null;
}
return self::$code3ToName[$code];
}
}

View File

@ -8,7 +8,7 @@
* @author Nicholas Pisarro * @author Nicholas Pisarro
* @copyright 2006 * @copyright 2006
* @license BSD * @license BSD
* @version CVS: $Id: Parser.php,v 1.5 2006/03/11 05:45:05 taak Exp $ * @version CVS: $Id: Parser.php 322327 2012-01-15 17:55:59Z cweiske $
* @link http://pear.php.net/package/Text_LanguageDetect/ * @link http://pear.php.net/package/Text_LanguageDetect/
* @link http://langdetect.blogspot.com/ * @link http://langdetect.blogspot.com/
*/ */
@ -28,7 +28,7 @@
* @author Nicholas Pisarro * @author Nicholas Pisarro
* @copyright 2006 * @copyright 2006
* @license BSD * @license BSD
* @version release: 0.2.3 * @version release: 0.3.0
*/ */
class Text_LanguageDetect_Parser extends Text_LanguageDetect class Text_LanguageDetect_Parser extends Text_LanguageDetect
{ {
@ -102,21 +102,17 @@ class Text_LanguageDetect_Parser extends Text_LanguageDetect
* @access private * @access private
* @param string $string string to be parsed * @param string $string string to be parsed
*/ */
function Text_LanguageDetect_Parser($string, $db=null, $unicode_db=null) { function Text_LanguageDetect_Parser($string) {
if (isset($db)) $this->_db_filename = $db;
if (isset($unicode_db)) $this->_unicode_db_filename = $unicode_db;
$this->_string = $string; $this->_string = $string;
} }
/** /**
* Returns true if a string is suitable for parsing * Returns true if a string is suitable for parsing
* *
* @static
* @access public
* @param string $str input string to test * @param string $str input string to test
* @return bool true if acceptable, false if not * @return bool true if acceptable, false if not
*/ */
function validateString($str) { public static function validateString($str) {
if (!empty($str) && strlen($str) > 3 && preg_match('/\S/', $str)) { if (!empty($str) && strlen($str) > 3 && preg_match('/\S/', $str)) {
return true; return true;
} else { } else {
@ -222,8 +218,7 @@ class Text_LanguageDetect_Parser extends Text_LanguageDetect
// unicode startup // unicode startup
if ($this->_compile_unicode) { if ($this->_compile_unicode) {
$blocks =& $this->_read_unicode_block_db(); $blocks = $this->_read_unicode_block_db();
$block_count = count($blocks); $block_count = count($blocks);
$skipped_count = 0; $skipped_count = 0;
@ -349,6 +344,4 @@ class Text_LanguageDetect_Parser extends Text_LanguageDetect
} }
} }
/* vim: set expandtab tabstop=4 shiftwidth=4 softtabstop=4: */ /* vim: set expandtab tabstop=4 shiftwidth=4 softtabstop=4: */
?>

File diff suppressed because it is too large Load Diff

View File

@ -3,8 +3,8 @@
// Author: Keyvan Minoukadeh // Author: Keyvan Minoukadeh
// Copyright (c) 2013 Keyvan Minoukadeh // Copyright (c) 2013 Keyvan Minoukadeh
// License: AGPLv3 // License: AGPLv3
// Version: 3.1 // Version: 3.2
// Date: 2013-03-05 // Date: 2013-05-13
// More info: http://fivefilters.org/content-only/ // More info: http://fivefilters.org/content-only/
// Help: http://help.fivefilters.org // Help: http://help.fivefilters.org
@ -25,12 +25,8 @@ along with this program. If not, see <http://www.gnu.org/licenses/>.
// Usage // Usage
// ----- // -----
// Request this file passing it your feed in the querystring: makefulltextfeed.php?url=mysite.org // Request this file passing it a web page or feed URL in the querystring: makefulltextfeed.php?url=example.org/article
// The following options can be passed in the querystring: // For more request parameters, see http://help.fivefilters.org/customer/portal/articles/226660-usage
// * URL: url=[feed or website url] (required, should be URL-encoded - in php: urlencode($url))
// * URL points to HTML (not feed): html=true (optional, by default it's automatically detected)
// * API key: key=[api key] (optional, refer to config.php)
// * Max entries to process: max=[max number of items] (optional)
error_reporting(E_ALL ^ E_NOTICE); error_reporting(E_ALL ^ E_NOTICE);
ini_set("display_errors", 1); ini_set("display_errors", 1);
@ -76,8 +72,8 @@ header('X-Robots-Tag: noindex, nofollow');
//////////////////////////////// ////////////////////////////////
// Check if service is enabled // Check if service is enabled
//////////////////////////////// ////////////////////////////////
if (!$options->enabled) { if (!$options->enabled) {
die('The full-text RSS service is currently disabled'); die('The full-text RSS service is currently disabled');
} }
//////////////////////////////// ////////////////////////////////
@ -121,8 +117,8 @@ $options->smart_cache = $options->smart_cache && function_exists('apc_inc');
//////////////////////////////// ////////////////////////////////
// Check for feed URL // Check for feed URL
//////////////////////////////// ////////////////////////////////
if (!isset($_GET['url'])) { if (!isset($_GET['url'])) {
die('No URL supplied'); die('No URL supplied');
} }
$url = trim($_GET['url']); $url = trim($_GET['url']);
if (strtolower(substr($url, 0, 7)) == 'feed://') { if (strtolower(substr($url, 0, 7)) == 'feed://') {
@ -161,10 +157,12 @@ if (isset($_GET['key']) && ($key_index = array_search($_GET['key'], $options->ap
if (isset($_GET['links'])) $redirect .= '&links='.urlencode($_GET['links']); if (isset($_GET['links'])) $redirect .= '&links='.urlencode($_GET['links']);
if (isset($_GET['exc'])) $redirect .= '&exc='.urlencode($_GET['exc']); if (isset($_GET['exc'])) $redirect .= '&exc='.urlencode($_GET['exc']);
if (isset($_GET['format'])) $redirect .= '&format='.urlencode($_GET['format']); if (isset($_GET['format'])) $redirect .= '&format='.urlencode($_GET['format']);
if (isset($_GET['callback'])) $redirect .= '&callback='.urlencode($_GET['callback']); if (isset($_GET['callback'])) $redirect .= '&callback='.urlencode($_GET['callback']);
if (isset($_GET['l'])) $redirect .= '&l='.urlencode($_GET['l']); if (isset($_GET['l'])) $redirect .= '&l='.urlencode($_GET['l']);
if (isset($_GET['xss'])) $redirect .= '&xss'; if (isset($_GET['xss'])) $redirect .= '&xss';
if (isset($_GET['use_extracted_title'])) $redirect .= '&use_extracted_title'; if (isset($_GET['use_extracted_title'])) $redirect .= '&use_extracted_title';
if (isset($_GET['content'])) $redirect .= '&content='.urlencode($_GET['content']);
if (isset($_GET['summary'])) $redirect .= '&summary='.urlencode($_GET['summary']);
if (isset($_GET['debug'])) $redirect .= '&debug'; if (isset($_GET['debug'])) $redirect .= '&debug';
if ($debug_mode) { if ($debug_mode) {
debug('Redirecting to hide access key, follow URL below to continue'); debug('Redirecting to hide access key, follow URL below to continue');
@ -177,7 +175,7 @@ if (isset($_GET['key']) && ($key_index = array_search($_GET['key'], $options->ap
/////////////////////////////////////////////// ///////////////////////////////////////////////
// Set timezone. // Set timezone.
// Prevents warnings, but needs more testing - // Prevents warnings, but needs more testing -
// perhaps if timezone is set in php.ini we // perhaps if timezone is set in php.ini we
// don't need to set it at all... // don't need to set it at all...
/////////////////////////////////////////////// ///////////////////////////////////////////////
@ -199,7 +197,7 @@ if (isset($_GET['key']) && isset($_GET['hash']) && isset($options->api_keys[(int
} }
$key_index = ($valid_key) ? (int)$_GET['key'] : 0; $key_index = ($valid_key) ? (int)$_GET['key'] : 0;
if (!$valid_key && $options->key_required) { if (!$valid_key && $options->key_required) {
die('A valid key must be supplied'); die('A valid key must be supplied');
} }
if (!$valid_key && isset($_GET['key']) && $_GET['key'] != '') { if (!$valid_key && isset($_GET['key']) && $_GET['key'] != '') {
die('The entered key is invalid'); die('The entered key is invalid');
@ -250,6 +248,28 @@ if ($options->favour_feed_titles == 'user') {
$favour_feed_titles = $options->favour_feed_titles; $favour_feed_titles = $options->favour_feed_titles;
} }
///////////////////////////////////////////////
// Include full content in output?
///////////////////////////////////////////////
if ($options->content === 'user') {
if (isset($_GET['content']) && $_GET['content'] === '0') {
$options->content = false;
} else {
$options->content = true;
}
}
///////////////////////////////////////////////
// Include summaries in output?
///////////////////////////////////////////////
if ($options->summary === 'user') {
if (isset($_GET['summary']) && $_GET['summary'] === '1') {
$options->summary = true;
} else {
$options->summary = false;
}
}
/////////////////////////////////////////////// ///////////////////////////////////////////////
// Exclude items if extraction fails // Exclude items if extraction fails
/////////////////////////////////////////////// ///////////////////////////////////////////////
@ -272,15 +292,6 @@ if ($options->detect_language === 'user') {
$detect_language = $options->detect_language; $detect_language = $options->detect_language;
} }
if ($detect_language >= 2) {
$language_codes = array('albanian' => 'sq','arabic' => 'ar','azeri' => 'az','bengali' => 'bn','bulgarian' => 'bg',
'cebuano' => 'ceb', // ISO 639-2
'croatian' => 'hr','czech' => 'cs','danish' => 'da','dutch' => 'nl','english' => 'en','estonian' => 'et','farsi' => 'fa','finnish' => 'fi','french' => 'fr','german' => 'de','hausa' => 'ha',
'hawaiian' => 'haw', // ISO 639-2
'hindi' => 'hi','hungarian' => 'hu','icelandic' => 'is','indonesian' => 'id','italian' => 'it','kazakh' => 'kk','kyrgyz' => 'ky','latin' => 'la','latvian' => 'lv','lithuanian' => 'lt','macedonian' => 'mk','mongolian' => 'mn','nepali' => 'ne','norwegian' => 'no','pashto' => 'ps',
'pidgin' => 'cpe', // ISO 639-2
'polish' => 'pl','portuguese' => 'pt','romanian' => 'ro','russian' => 'ru','serbian' => 'sr','slovak' => 'sk','slovene' => 'sl','somali' => 'so','spanish' => 'es','swahili' => 'sw','swedish' => 'sv','tagalog' => 'tl','turkish' => 'tr','ukrainian' => 'uk','urdu' => 'ur','uzbek' => 'uz','vietnamese' => 'vi','welsh' => 'cy');
}
$use_cld = extension_loaded('cld') && (version_compare(PHP_VERSION, '5.3.0') >= 0); $use_cld = extension_loaded('cld') && (version_compare(PHP_VERSION, '5.3.0') >= 0);
///////////////////////////////////// /////////////////////////////////////
@ -330,7 +341,7 @@ if ($options->cors) header('Access-Control-Allow-Origin: *');
////////////////////////////////// //////////////////////////////////
if ($options->caching) { if ($options->caching) {
debug('Caching is enabled...'); debug('Caching is enabled...');
$cache_id = md5($max.$url.$valid_key.$links.$favour_feed_titles.$xss_filter.$exclude_on_fail.$format.$detect_language.(int)isset($_GET['pubsub'])); $cache_id = md5($max.$url.(int)$valid_key.$links.(int)$favour_feed_titles.(int)$options->content.(int)$options->summary.(int)$xss_filter.(int)$exclude_on_fail.$format.$detect_language.(int)isset($_GET['pubsub']));
$check_cache = true; $check_cache = true;
if ($options->apc && $options->smart_cache) { if ($options->apc && $options->smart_cache) {
apc_add("cache.$cache_id", 0, 10*60); apc_add("cache.$cache_id", 0, 10*60);
@ -468,7 +479,7 @@ if ($img_url = $feed->get_image_url()) {
//////////////////////////////////////////// ////////////////////////////////////////////
// Loop through feed items // Loop through feed items
//////////////////////////////////////////// ////////////////////////////////////////////
$items = $feed->get_items(0, $max); $items = $feed->get_items(0, $max);
// Request all feed items in parallel (if supported) // Request all feed items in parallel (if supported)
$urls_sanitized = array(); $urls_sanitized = array();
$urls = array(); $urls = array();
@ -550,24 +561,43 @@ foreach ($items as $key => $item) {
$is_single_page = false; $is_single_page = false;
if ($single_page_response = getSinglePage($item, $html, $effective_url)) { if ($single_page_response = getSinglePage($item, $html, $effective_url)) {
$is_single_page = true; $is_single_page = true;
$html = $single_page_response['body'];
// remove strange things
$html = str_replace('</[>', '', $html);
$html = convert_to_utf8($html, $single_page_response['headers']);
$effective_url = $single_page_response['effective_url']; $effective_url = $single_page_response['effective_url'];
debug("Retrieved single-page view from $effective_url"); // check if action defined for returned Content-Type
$mime_info = get_mime_action_info($single_page_response['headers']);
if (isset($mime_info['action'])) {
if ($mime_info['action'] == 'exclude') {
continue; // skip this feed item entry
} elseif ($mime_info['action'] == 'link') {
if ($mime_info['type'] == 'image') {
$html = "<a href=\"$effective_url\"><img src=\"$effective_url\" alt=\"{$mime_info['name']}\" /></a>";
} else {
$html = "<a href=\"$effective_url\">Download {$mime_info['name']}</a>";
}
$extracted_title = $mime_info['name'];
$do_content_extraction = false;
}
}
if ($do_content_extraction) {
$html = $single_page_response['body'];
// remove strange things
$html = str_replace('</[>', '', $html);
$html = convert_to_utf8($html, $single_page_response['headers']);
debug("Retrieved single-page view from $effective_url");
}
unset($single_page_response); unset($single_page_response);
} }
}
if ($do_content_extraction) {
debug('--------'); debug('--------');
debug('Attempting to extract content'); debug('Attempting to extract content');
$extract_result = $extractor->process($html, $effective_url); $extract_result = $extractor->process($html, $effective_url);
$readability = $extractor->readability; $readability = $extractor->readability;
$content_block = ($extract_result) ? $extractor->getContent() : null; $content_block = ($extract_result) ? $extractor->getContent() : null;
$extracted_title = ($extract_result) ? $extractor->getTitle() : ''; $extracted_title = ($extract_result) ? $extractor->getTitle() : '';
// Deal with multi-page articles // Deal with multi-page articles
//die('Next: '.$extractor->getNextPageUrl()); //die('Next: '.$extractor->getNextPageUrl());
$is_multi_page = (!$is_single_page && $extract_result && $extractor->getNextPageUrl()); $is_multi_page = (!$is_single_page && $extract_result && $extractor->getNextPageUrl());
if ($options->multipage && $is_multi_page) { if ($options->multipage && $is_multi_page && $options->content) {
debug('--------'); debug('--------');
debug('Attempting to process multi-page article'); debug('Attempting to process multi-page article');
$multi_page_urls = array(); $multi_page_urls = array();
@ -580,7 +610,7 @@ foreach ($items as $key => $item) {
// check it's not what we have already! // check it's not what we have already!
if (!in_array($next_page_url, $multi_page_urls)) { if (!in_array($next_page_url, $multi_page_urls)) {
// it's not, so let's attempt to fetch it // it's not, so let's attempt to fetch it
$multi_page_urls[] = $next_page_url; $multi_page_urls[] = $next_page_url;
$_prev_ref = $http->referer; $_prev_ref = $http->referer;
if (($response = $http->get($next_page_url, true)) && $response['status_code'] < 300) { if (($response = $http->get($next_page_url, true)) && $response['status_code'] < 300) {
// make sure mime type is not something with a different action associated // make sure mime type is not something with a different action associated
@ -605,13 +635,15 @@ foreach ($items as $key => $item) {
// did we successfully deal with this multi-page article? // did we successfully deal with this multi-page article?
if (empty($multi_page_content)) { if (empty($multi_page_content)) {
debug('Failed to extract all parts of multi-page article, so not going to include them'); debug('Failed to extract all parts of multi-page article, so not going to include them');
$multi_page_content[] = $readability->dom->createElement('p')->innerHTML = '<em>This article appears to continue on subsequent pages which we could not extract</em>'; $_page = $readability->dom->createElement('p');
$_page->innerHTML = '<em>This article appears to continue on subsequent pages which we could not extract</em>';
$multi_page_content[] = $_page;
} }
foreach ($multi_page_content as $_page) { foreach ($multi_page_content as $_page) {
$_page = $content_block->ownerDocument->importNode($_page, true); $_page = $content_block->ownerDocument->importNode($_page, true);
$content_block->appendChild($_page); $content_block->appendChild($_page);
} }
unset($multi_page_urls, $multi_page_content, $page_mime_info, $next_page_url); unset($multi_page_urls, $multi_page_content, $page_mime_info, $next_page_url, $_page);
} }
} }
// use extracted title for both feed and item title if we're using single-item dummy feed // use extracted title for both feed and item title if we're using single-item dummy feed
@ -658,7 +690,7 @@ foreach ($items as $key => $item) {
} else { } else {
$html = $content_block->ownerDocument->saveXML($content_block); // essentially outerHTML $html = $content_block->ownerDocument->saveXML($content_block); // essentially outerHTML
} }
unset($content_block); //unset($content_block);
// post-processing cleanup // post-processing cleanup
$html = preg_replace('!<p>[\s\h\v]*</p>!u', '', $html); $html = preg_replace('!<p>[\s\h\v]*</p>!u', '', $html);
if ($links == 'remove') { if ($links == 'remove') {
@ -671,130 +703,155 @@ foreach ($items as $key => $item) {
} }
} }
if ($valid_key && isset($_GET['pubsub'])) { // used only on fivefilters.org at the moment if ($valid_key && isset($_GET['pubsub'])) { // used only on fivefilters.org at the moment
$newitem->addElement('guid', 'http://fivefilters.org/content-only/redirect.php?url='.urlencode($item->get_permalink()), array('isPermaLink'=>'false')); $newitem->addElement('guid', 'http://fivefilters.org/content-only/redirect.php?url='.urlencode($item->get_permalink()), array('isPermaLink'=>'false'));
} else {
$newitem->addElement('guid', $item->get_permalink(), array('isPermaLink'=>'true'));
}
// filter xss?
if ($xss_filter) {
debug('Filtering HTML to remove XSS');
$html = htmLawed::hl($html, array('safe'=>1, 'deny_attribute'=>'style', 'comment'=>1, 'cdata'=>1));
}
// add content
if ($options->summary === true) {
// get summary
$summary = '';
if (!$do_content_extraction) {
$summary = $html;
} else { } else {
$newitem->addElement('guid', $item->get_permalink(), array('isPermaLink'=>'true')); // Try to get first few paragraphs
} if (isset($content_block) && ($content_block instanceof DOMElement)) {
// filter xss? $_paras = $content_block->getElementsByTagName('p');
if ($xss_filter) { foreach ($_paras as $_para) {
debug('Filtering HTML to remove XSS'); $summary .= preg_replace("/[\n\r\t ]+/", ' ', $_para->textContent).' ';
$html = htmLawed::hl($html, array('safe'=>1, 'deny_attribute'=>'style', 'comment'=>1, 'cdata'=>1)); if (strlen($summary) > 200) break;
}
$newitem->setDescription($html);
// set date
if ((int)$item->get_date('U') > 0) {
$newitem->setDate((int)$item->get_date('U'));
} elseif ($extractor->getDate()) {
$newitem->setDate($extractor->getDate());
}
// add authors
if ($authors = $item->get_authors()) {
foreach ($authors as $author) {
// for some feeds, SimplePie stores author's name as email, e.g. http://feeds.feedburner.com/nymag/intel
if ($author->get_name() !== null) {
$newitem->addElement('dc:creator', $author->get_name());
} elseif ($author->get_email() !== null) {
$newitem->addElement('dc:creator', $author->get_email());
} }
} } else {
} elseif ($authors = $extractor->getAuthors()) { $summary = $html;
//TODO: make sure the list size is reasonable
foreach ($authors as $author) {
// TODO: xpath often selects authors from other articles linked from the page.
// for now choose first item
$newitem->addElement('dc:creator', $author);
break;
} }
} }
unset($_paras, $_para);
// add language $summary = get_excerpt($summary);
if ($detect_language) { $newitem->setDescription($summary);
$language = $extractor->getLanguage(); if ($options->content) $newitem->setElement('content:encoded', $html);
if (!$language) $language = $feed->get_language(); } else {
if (($detect_language == 3 || (!$language && $detect_language == 2)) && $text_sample) { if ($options->content) $newitem->setDescription($html);
try { }
if ($use_cld) {
// Use PHP-CLD extension // set date
$php_cld = 'CLD\detect'; // in quotes to prevent PHP 5.2 parse error if ((int)$item->get_date('U') > 0) {
$res = $php_cld($text_sample); $newitem->setDate((int)$item->get_date('U'));
if (is_array($res) && count($res) > 0) { } elseif ($extractor->getDate()) {
$language = $res[0]['code']; $newitem->setDate($extractor->getDate());
} }
} else {
//die('what'); // add authors
// Use PEAR's Text_LanguageDetect if ($authors = $item->get_authors()) {
if (!isset($l)) { foreach ($authors as $author) {
$l = new Text_LanguageDetect('libraries/language-detect/lang.dat', 'libraries/language-detect/unicode_blocks.dat'); // for some feeds, SimplePie stores author's name as email, e.g. http://feeds.feedburner.com/nymag/intel
} if ($author->get_name() !== null) {
$l_result = $l->detect($text_sample, 1); $newitem->addElement('dc:creator', $author->get_name());
if (count($l_result) > 0) { } elseif ($author->get_email() !== null) {
$language = $language_codes[key($l_result)]; $newitem->addElement('dc:creator', $author->get_email());
} }
}
} elseif ($authors = $extractor->getAuthors()) {
//TODO: make sure the list size is reasonable
foreach ($authors as $author) {
// TODO: xpath often selects authors from other articles linked from the page.
// for now choose first item
$newitem->addElement('dc:creator', $author);
break;
}
}
// add language
if ($detect_language) {
$language = $extractor->getLanguage();
if (!$language) $language = $feed->get_language();
if (($detect_language == 3 || (!$language && $detect_language == 2)) && $text_sample) {
try {
if ($use_cld) {
// Use PHP-CLD extension
$php_cld = 'CLD\detect'; // in quotes to prevent PHP 5.2 parse error
$res = $php_cld($text_sample);
if (is_array($res) && count($res) > 0) {
$language = $res[0]['code'];
} }
} catch (Exception $e) { } else {
//die('error: '.$e); //die('what');
// do nothing // Use PEAR's Text_LanguageDetect
} if (!isset($l)) {
} $l = new Text_LanguageDetect();
if ($language && (strlen($language) < 7)) { $l->setNameMode(2); // return ISO 639-1 codes (e.g. "en")
$newitem->addElement('dc:language', $language); }
} $l_result = $l->detect($text_sample, 1);
} if (count($l_result) > 0) {
$language = key($l_result);
// add MIME type (if it appeared in our exclusions lists)
if (isset($mime_info['mime'])) $newitem->addElement('dc:format', $mime_info['mime']);
// add effective URL (URL after redirects)
if (isset($effective_url)) {
//TODO: ensure $effective_url is valid witout - sometimes it causes problems, e.g.
//http://www.siasat.pk/forum/showthread.php?108883-Pakistan-Chowk-by-Rana-Mubashir-<2D>-25th-March-2012-Special-Program-from-Liari-(Karachi)
//temporary measure: use utf8_encode()
$newitem->addElement('dc:identifier', remove_url_cruft(utf8_encode($effective_url)));
} else {
$newitem->addElement('dc:identifier', remove_url_cruft($item->get_permalink()));
}
// add categories
if ($categories = $item->get_categories()) {
foreach ($categories as $category) {
if ($category->get_label() !== null) {
$newitem->addElement('category', $category->get_label());
}
}
}
// check for enclosures
if ($options->keep_enclosures) {
if ($enclosures = $item->get_enclosures()) {
foreach ($enclosures as $enclosure) {
// thumbnails
foreach ((array)$enclosure->get_thumbnails() as $thumbnail) {
$newitem->addElement('media:thumbnail', '', array('url'=>$thumbnail));
} }
if (!$enclosure->get_link()) continue;
$enc = array();
// Media RSS spec ($enc): http://search.yahoo.com/mrss
// SimplePie methods ($enclosure): http://simplepie.org/wiki/reference/start#methods4
$enc['url'] = $enclosure->get_link();
if ($enclosure->get_length()) $enc['fileSize'] = $enclosure->get_length();
if ($enclosure->get_type()) $enc['type'] = $enclosure->get_type();
if ($enclosure->get_medium()) $enc['medium'] = $enclosure->get_medium();
if ($enclosure->get_expression()) $enc['expression'] = $enclosure->get_expression();
if ($enclosure->get_bitrate()) $enc['bitrate'] = $enclosure->get_bitrate();
if ($enclosure->get_framerate()) $enc['framerate'] = $enclosure->get_framerate();
if ($enclosure->get_sampling_rate()) $enc['samplingrate'] = $enclosure->get_sampling_rate();
if ($enclosure->get_channels()) $enc['channels'] = $enclosure->get_channels();
if ($enclosure->get_duration()) $enc['duration'] = $enclosure->get_duration();
if ($enclosure->get_height()) $enc['height'] = $enclosure->get_height();
if ($enclosure->get_width()) $enc['width'] = $enclosure->get_width();
if ($enclosure->get_language()) $enc['lang'] = $enclosure->get_language();
$newitem->addElement('media:content', '', $enc);
} }
} catch (Exception $e) {
//die('error: '.$e);
// do nothing
} }
} }
/* } */ if ($language && (strlen($language) < 7)) {
$newitem->addElement('dc:language', $language);
}
}
// add MIME type (if it appeared in our exclusions lists)
if (isset($mime_info['mime'])) $newitem->addElement('dc:format', $mime_info['mime']);
// add effective URL (URL after redirects)
if (isset($effective_url)) {
//TODO: ensure $effective_url is valid witout - sometimes it causes problems, e.g.
//http://www.siasat.pk/forum/showthread.php?108883-Pakistan-Chowk-by-Rana-Mubashir-<2D>-25th-March-2012-Special-Program-from-Liari-(Karachi)
//temporary measure: use utf8_encode()
$newitem->addElement('dc:identifier', remove_url_cruft(utf8_encode($effective_url)));
} else {
$newitem->addElement('dc:identifier', remove_url_cruft($item->get_permalink()));
}
// add categories
if ($categories = $item->get_categories()) {
foreach ($categories as $category) {
if ($category->get_label() !== null) {
$newitem->addElement('category', $category->get_label());
}
}
}
// check for enclosures
if ($options->keep_enclosures) {
if ($enclosures = $item->get_enclosures()) {
foreach ($enclosures as $enclosure) {
// thumbnails
foreach ((array)$enclosure->get_thumbnails() as $thumbnail) {
$newitem->addElement('media:thumbnail', '', array('url'=>$thumbnail));
}
if (!$enclosure->get_link()) continue;
$enc = array();
// Media RSS spec ($enc): http://search.yahoo.com/mrss
// SimplePie methods ($enclosure): http://simplepie.org/wiki/reference/start#methods4
$enc['url'] = $enclosure->get_link();
if ($enclosure->get_length()) $enc['fileSize'] = $enclosure->get_length();
if ($enclosure->get_type()) $enc['type'] = $enclosure->get_type();
if ($enclosure->get_medium()) $enc['medium'] = $enclosure->get_medium();
if ($enclosure->get_expression()) $enc['expression'] = $enclosure->get_expression();
if ($enclosure->get_bitrate()) $enc['bitrate'] = $enclosure->get_bitrate();
if ($enclosure->get_framerate()) $enc['framerate'] = $enclosure->get_framerate();
if ($enclosure->get_sampling_rate()) $enc['samplingrate'] = $enclosure->get_sampling_rate();
if ($enclosure->get_channels()) $enc['channels'] = $enclosure->get_channels();
if ($enclosure->get_duration()) $enc['duration'] = $enclosure->get_duration();
if ($enclosure->get_height()) $enc['height'] = $enclosure->get_height();
if ($enclosure->get_width()) $enc['width'] = $enclosure->get_width();
if ($enclosure->get_language()) $enc['lang'] = $enclosure->get_language();
$newitem->addElement('media:content', '', $enc);
}
}
}
$output->addItem($newitem); $output->addItem($newitem);
unset($html); unset($html);
$item_count++; $item_count++;

View File

@ -66,6 +66,38 @@ class DummySingleItem {
// HELPER FUNCTIONS // HELPER FUNCTIONS
/////////////////////////////// ///////////////////////////////
// Adapted from WordPress
// http://core.trac.wordpress.org/browser/tags/3.5.1/wp-includes/formatting.php#L2173
function get_excerpt($text, $num_words=55, $more=null) {
if (null === $more) $more = '&hellip;';
$text = strip_tags($text);
//TODO: Check if word count is based on single characters (East Asian characters)
/*
if (1==2) {
$text = trim(preg_replace("/[\n\r\t ]+/", ' ', $text), ' ');
preg_match_all('/./u', $text, $words_array);
$words_array = array_slice($words_array[0], 0, $num_words + 1);
$sep = '';
} else {
$words_array = preg_split("/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY);
$sep = ' ';
}
*/
$words_array = preg_split("/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY);
$sep = ' ';
if (count($words_array) > $num_words) {
array_pop($words_array);
$text = implode($sep, $words_array);
$text = $text.$more;
} else {
$text = implode($sep, $words_array);
}
// trim whitespace at beginning or end of string
// See: http://stackoverflow.com/questions/4166896/trim-unicode-whitespace-in-php-5-2
$text = preg_replace('/^[\pZ\pC]+|[\pZ\pC]+$/u', '', $text);
return $text;
}
function url_allowed($url) { function url_allowed($url) {
global $options; global $options;
if (!empty($options->allowed_urls)) { if (!empty($options->allowed_urls)) {
@ -165,14 +197,6 @@ function convert_to_utf8($html, $header=null)
if (strtolower($encoding) != 'utf-8') { if (strtolower($encoding) != 'utf-8') {
debug('Converting to UTF-8'); debug('Converting to UTF-8');
$html = SimplePie_Misc::change_encoding($html, $encoding, 'utf-8'); $html = SimplePie_Misc::change_encoding($html, $encoding, 'utf-8');
/*
if (function_exists('iconv')) {
// iconv appears to handle certain character encodings better than mb_convert_encoding
$html = iconv($encoding, 'utf-8', $html);
} else {
$html = mb_convert_encoding($html, 'utf-8', $encoding);
}
*/
} }
} }
} }
@ -196,7 +220,7 @@ function makeAbsolute($base, $elem) {
} }
function makeAbsoluteAttr($base, $e, $attr) { function makeAbsoluteAttr($base, $e, $attr) {
if ($e->hasAttribute($attr)) { if ($e->hasAttribute($attr)) {
// Trim leading and trailing white space. I don't really like this but // Trim leading and trailing white space. I don't really like this but
// unfortunately it does appear on some sites. e.g. <img src=" /path/to/image.jpg" /> // unfortunately it does appear on some sites. e.g. <img src=" /path/to/image.jpg" />
$url = trim(str_replace('%20', ' ', $e->getAttribute($attr))); $url = trim(str_replace('%20', ' ', $e->getAttribute($attr)));
$url = str_replace(' ', '%20', $url); $url = str_replace(' ', '%20', $url);

View File

@ -0,0 +1,12 @@
title: //title
body: //iframe
replace_string(<![CDATA[): _
replace_string(]]>): _
single_page_link: //link[@type='application/xml+oembed']
prune: no
tidy: no
http://www.dailymotion.com/video/x1vk5oh_before-they-were-on-game-of-thrones_people

View File

@ -0,0 +1,3 @@
<?php
// this is here to prevent directory listing over the web
?>

11
inc/3rdparty/site_config/custom/ted.com.txt vendored Executable file
View File

@ -0,0 +1,11 @@
title: //title
body: //div[@class='talk-article__body talk-transcript__body'] | //div[@class='media__image media__image--thumb talk-link__image']
strip_id_or_class: talk-transcript__para__time
single_page_link: //a[@id='hero-transcript-link']
#prune: no
tidy: no
test_url: http://www.ted.com/talks/andrew_solomon_how_the_worst_moments_in_our_lives_make_us_who_we_are

View File

@ -1,3 +1,2 @@
<?php <?php
// this is here to prevent directory listing over the web // this is here to prevent directory listing over the web
?>

View File

@ -1 +1 @@
4 2013-05-12T22:53:07Z

View File

@ -1142,11 +1142,12 @@ class Poche
* return new purifier object with actual config * return new purifier object with actual config
*/ */
protected function getPurifier() { protected function getPurifier() {
$config = HTMLPurifier_Config::createDefault(); $config = HTMLPurifier_Config::createDefault();
$config->set('Cache.SerializerPath', CACHE); $config->set('Cache.SerializerPath', CACHE);
$config->set('HTML.SafeIframe', true); $config->set('HTML.SafeIframe', true);
$config->set('URI.SafeIframeRegexp', '%^(https?:)?//(www\.youtube(?:-nocookie)?\.com/embed/|player\.vimeo\.com/video/)%'); //allow YouTube and Vimeo$purifier = new HTMLPurifier($config); //allow YouTube, Vimeo and dailymotion videos
$config->set('URI.SafeIframeRegexp', '%^(https?:)?//(www\.youtube(?:-nocookie)?\.com/embed/|player\.vimeo\.com/video/|www\.dailymotion\.com/embed/video/)%');
return new HTMLPurifier($config); return new HTMLPurifier($config);
} }

14
themes/default/_search-form.twig Normal file → Executable file
View File

@ -7,17 +7,3 @@
</p> </p>
</form> </form>
</div> </div>
<script type="text/javascript">
$(document).ready(function() {
$("#search-form").hide();
$("#search").click(function(){
$("#search-form").toggle();
$("#search").toggleClass("current");
$("#search-arrow").toggleClass("arrow-down");
});
});
</script>

View File

@ -384,8 +384,8 @@ a#bagit-form-close {
background-color: #000; background-color: #000;
color: #fff; color: #fff;
padding: 0 4px 1px 3px; padding: 0 4px 1px 3px;
font-weight: bold; font-weight: bold;
font-size: 0.7em; font-size: 0.7em;
border-radius: 4px; border-radius: 4px;
} }
.add-to-wallabag-link-after:hover, .add-to-wallabag-link-after:active { .add-to-wallabag-link-after:hover, .add-to-wallabag-link-after:active {
@ -394,6 +394,23 @@ a#bagit-form-close {
.add-to-wallabag-link-after:visited { .add-to-wallabag-link-after:visited {
color: #999; color: #999;
} }
a.add-to-wallabag-link-after {
visibility: hidden;
position: absolute;
opacity: 0;
transition-duration: 2s;
transition-timing-function: ease-out;
}
#article article a:hover + a.add-to-wallabag-link-after, a.add-to-wallabag-link-after:hover {
opacity: 1;
visibility: visible;
transition-duration: .3s;
transition-timing-function: ease-in;
}
a.add-to-wallabag-link-after:after {
content: "w";
}
#add-link-result { #add-link-result {
display: inline; display: inline;