1
0
Fork 0
mirror of https://github.com/wallabag/wallabag.git synced 2025-08-01 17:38:38 +00:00

up to date

This commit is contained in:
tcit 2014-06-07 16:36:57 +02:00
commit 35d4e27588
30 changed files with 4961 additions and 4236 deletions

File diff suppressed because it is too large Load diff

View file

@ -1,338 +1,343 @@
<?php
/**
* Site Config
*
* Each instance of this class should hold extraction patterns and other directives
* for a website. See ContentExtractor class to see how it's used.
*
* @version 0.7
* @date 2012-08-27
* @author Keyvan Minoukadeh
* @copyright 2012 Keyvan Minoukadeh
* @license http://www.gnu.org/licenses/agpl-3.0.html AGPL v3
*/
class SiteConfig
{
// Use first matching element as title (0 or more xpath expressions)
public $title = array();
// Use first matching element as body (0 or more xpath expressions)
public $body = array();
// Use first matching element as author (0 or more xpath expressions)
public $author = array();
// Use first matching element as date (0 or more xpath expressions)
public $date = array();
// Strip elements matching these xpath expressions (0 or more)
public $strip = array();
// Strip elements which contain these strings (0 or more) in the id or class attribute
public $strip_id_or_class = array();
// Strip images which contain these strings (0 or more) in the src attribute
public $strip_image_src = array();
// Additional HTTP headers to send
// NOT YET USED
public $http_header = array();
// Process HTML with tidy before creating DOM (bool or null if undeclared)
public $tidy = null;
protected $default_tidy = true; // used if undeclared
// Autodetect title/body if xpath expressions fail to produce results.
// 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 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.
// * 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.
// 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
public $autodetect_on_failure = null;
protected $default_autodetect_on_failure = true; // used if undeclared
// Clean up content block - attempt to remove elements that appear to be superfluous
// bool or null if undeclared
public $prune = null;
protected $default_prune = true; // used if undeclared
// Test URL - if present, can be used to test the config above
public $test_url = array();
// 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
// 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').
// 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.
public $single_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
public $single_page_link_in_feed = array();
// Which parser to use for turning raw HTML into a DOMDocument (either 'libxml' or 'html5lib')
// string or null if undeclared
public $parser = null;
protected $default_parser = 'libxml'; // used if undeclared
// Strings to search for in HTML before processing begins (used with $replace_string)
public $find_string = array();
// Strings to replace those found in $find_string before HTML processing begins
public $replace_string = array();
// 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_key = null;
public static $debug = false;
protected static $apc = false;
protected static $config_path;
protected static $config_path_fallback;
protected static $config_cache = array();
const HOSTNAME_REGEX = '/^(([a-zA-Z0-9-]*[a-zA-Z0-9])\.)*([A-Za-z0-9-]*[A-Za-z0-9])$/';
protected static function debug($msg) {
if (self::$debug) {
//$mem = round(memory_get_usage()/1024, 2);
//$memPeak = round(memory_get_peak_usage()/1024, 2);
echo '* ',$msg;
//echo ' - mem used: ',$mem," (peak: $memPeak)\n";
echo "\n";
ob_flush();
flush();
}
}
// enable APC caching of certain site config files?
// If enabled the following site config files will be
// cached in APC cache (when requested for first time):
// * anything in site_config/custom/ and its corresponding file in site_config/standard/
// * the site config files associated with HTML fingerprints
// * the global site config file
// returns true if enabled, false otherwise
public static function use_apc($apc=true) {
if (!function_exists('apc_add')) {
if ($apc) self::debug('APC will not be used (function apc_add does not exist)');
return false;
}
self::$apc = $apc;
return $apc;
}
// return bool or null
public function tidy($use_default=true) {
if ($use_default) return (isset($this->tidy)) ? $this->tidy : $this->default_tidy;
return $this->tidy;
}
// return bool or null
public function prune($use_default=true) {
if ($use_default) return (isset($this->prune)) ? $this->prune : $this->default_prune;
return $this->prune;
}
// return string or null
public function parser($use_default=true) {
if ($use_default) return (isset($this->parser)) ? $this->parser : $this->default_parser;
return $this->parser;
}
// return bool or null
public function autodetect_on_failure($use_default=true) {
if ($use_default) return (isset($this->autodetect_on_failure)) ? $this->autodetect_on_failure : $this->default_autodetect_on_failure;
return $this->autodetect_on_failure;
}
public static function set_config_path($path, $fallback=null) {
self::$config_path = $path;
self::$config_path_fallback = $fallback;
}
public static function add_to_cache($key, SiteConfig $config, $use_apc=true) {
$key = strtolower($key);
if (substr($key, 0, 4) == 'www.') $key = substr($key, 4);
if ($config->cache_key) $key = $config->cache_key;
self::$config_cache[$key] = $config;
if (self::$apc && $use_apc) {
self::debug("Adding site config to APC cache with key sc.$key");
apc_add("sc.$key", $config);
}
self::debug("Cached site config with key $key");
}
public static function is_cached($key) {
$key = strtolower($key);
if (substr($key, 0, 4) == 'www.') $key = substr($key, 4);
if (array_key_exists($key, self::$config_cache)) {
return true;
} elseif (self::$apc && (bool)apc_fetch("sc.$key")) {
return true;
}
return false;
}
public function append(SiteConfig $newconfig) {
// 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) {
// append array elements for this config variable from $newconfig to this config
//$this->$var = $this->$var + $newconfig->$var;
$this->$var = array_unique(array_merge($this->$var, $newconfig->$var));
}
// check for single statement commands
// we do not overwrite existing non null values
foreach (array('tidy', 'prune', 'parser', 'autodetect_on_failure') as $var) {
if ($this->$var === null) $this->$var = $newconfig->$var;
}
}
// returns SiteConfig instance if an appropriate one is found, false otherwise
// if $exact_host_match is true, we will not look for wildcard config matches
// by default if host is 'test.example.org' we will look for and load '.example.org.txt' if it exists
public static function build($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;
// check for site configuration
$try = array($host);
// should we look for wildcard matches
if (!$exact_host_match) {
$split = explode('.', $host);
if (count($split) > 1) {
array_shift($split);
$try[] = '.'.implode('.', $split);
}
}
// look for site config file in primary folder
self::debug(". looking for site config for $host in primary folder");
foreach ($try as $h) {
if (array_key_exists($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"))) {
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)");
$file_primary = self::$config_path."/$h.txt";
$matched_name = $h;
break;
}
}
// if we found site config, process it
if (isset($file_primary)) {
$config_lines = file($file_primary, FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
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;
$config->cache_key = $matched_name;
// if autodetec on failure is off (on by default) we do not need to look
// in secondary folder
if (!$config->autodetect_on_failure()) {
self::debug('... autodetect on failure is disabled (no other site config files will be loaded)');
return $config;
}
}
// look for site config file in secondary folder
if (isset(self::$config_path_fallback)) {
self::debug(". looking for site config for $host in secondary folder");
foreach ($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";
$matched_name = $h;
break;
}
}
if (!isset($file_secondary)) {
self::debug("... no site config match in secondary folder");
}
}
// return false if no config file found
if (!isset($file_primary) && !isset($file_secondary)) {
self::debug("... no site config match for $host");
return false;
}
// return primary config if secondary not found
if (!isset($file_secondary) && isset($config)) {
return $config;
}
// process secondary config file
$config_lines = file($file_secondary, FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
if (!$config_lines || !is_array($config_lines)) {
// failed to process secondary
if (isset($config)) {
// return primary config
return $config;
} else {
return false;
}
}
// merge with primary and return
if (isset($config)) {
self::debug('. merging config files');
$config->append(self::build_from_array($config_lines));
return $config;
} else {
// return just secondary
$config = self::build_from_array($config_lines);
// if APC caching is available and enabled, mark this for cache
//$config->cache_in_apc = true;
$config->cache_key = $matched_name;
return $config;
}
}
public static function build_from_array(array $lines) {
$config = new SiteConfig();
foreach ($lines as $line) {
$line = trim($line);
// skip comments, empty lines
if ($line == '' || $line[0] == '#') continue;
// get command
$command = explode(':', $line, 2);
// if there's no colon ':', skip this line
if (count($command) != 2) continue;
$val = trim($command[1]);
$command = trim($command[0]);
if ($command == '' || $val == '') continue;
// check for commands where we accept multiple statements
if (in_array($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'))) {
array_push($config->$command, $val);
// check for single statement commands that evaluate to true or false
} elseif (in_array($command, array('tidy', 'prune', 'autodetect_on_failure'))) {
$config->$command = ($val == 'yes');
// check for single statement commands stored as strings
} elseif (in_array($command, array('parser'))) {
$config->$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'))) {
$command = $match[1];
array_push($config->find_string, $match[2]);
array_push($config->$command, $val);
}
}
}
return $config;
}
}
?>
<?php
/**
* Site Config
*
* Each instance of this class should hold extraction patterns and other directives
* for a website. See ContentExtractor class to see how it's used.
*
* @version 0.8
* @date 2013-04-16
* @author Keyvan Minoukadeh
* @copyright 2013 Keyvan Minoukadeh
* @license http://www.gnu.org/licenses/agpl-3.0.html AGPL v3
*/
class SiteConfig
{
// Use first matching element as title (0 or more xpath expressions)
public $title = array();
// Use first matching element as body (0 or more xpath expressions)
public $body = array();
// Use first matching element as author (0 or more xpath expressions)
public $author = array();
// Use first matching element as date (0 or more xpath expressions)
public $date = array();
// Strip elements matching these xpath expressions (0 or more)
public $strip = array();
// Strip elements which contain these strings (0 or more) in the id or class attribute
public $strip_id_or_class = array();
// Strip images which contain these strings (0 or more) in the src attribute
public $strip_image_src = array();
// Additional HTTP headers to send
// NOT YET USED
public $http_header = array();
// Process HTML with tidy before creating DOM (bool or null if undeclared)
public $tidy = null;
protected $default_tidy = true; // used if undeclared
// Autodetect title/body if xpath expressions fail to produce results.
// 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 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.
// * 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.
// 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
public $autodetect_on_failure = null;
protected $default_autodetect_on_failure = true; // used if undeclared
// Clean up content block - attempt to remove elements that appear to be superfluous
// bool or null if undeclared
public $prune = null;
protected $default_prune = true; // used if undeclared
// Test URL - if present, can be used to test the config above
public $test_url = array();
// 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
// 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').
// 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.
public $single_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
public $single_page_link_in_feed = array();
// Which parser to use for turning raw HTML into a DOMDocument (either 'libxml' or 'html5lib')
// string or null if undeclared
public $parser = null;
protected $default_parser = 'libxml'; // used if undeclared
// Strings to search for in HTML before processing begins (used with $replace_string)
public $find_string = array();
// Strings to replace those found in $find_string before HTML processing begins
public $replace_string = array();
// 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_key = null;
public static $debug = false;
protected static $apc = false;
protected static $config_path;
protected static $config_path_fallback;
protected static $config_cache = array();
const HOSTNAME_REGEX = '/^(([a-zA-Z0-9-]*[a-zA-Z0-9])\.)*([A-Za-z0-9-]*[A-Za-z0-9])$/';
protected static function debug($msg) {
if (self::$debug) {
//$mem = round(memory_get_usage()/1024, 2);
//$memPeak = round(memory_get_peak_usage()/1024, 2);
echo '* ',$msg;
//echo ' - mem used: ',$mem," (peak: $memPeak)\n";
echo "\n";
ob_flush();
flush();
}
}
// enable APC caching of certain site config files?
// If enabled the following site config files will be
// cached in APC cache (when requested for first time):
// * anything in site_config/custom/ and its corresponding file in site_config/standard/
// * the site config files associated with HTML fingerprints
// * the global site config file
// returns true if enabled, false otherwise
public static function use_apc($apc=true) {
if (!function_exists('apc_add')) {
if ($apc) self::debug('APC will not be used (function apc_add does not exist)');
return false;
}
self::$apc = $apc;
return $apc;
}
// return bool or null
public function tidy($use_default=true) {
if ($use_default) return (isset($this->tidy)) ? $this->tidy : $this->default_tidy;
return $this->tidy;
}
// return bool or null
public function prune($use_default=true) {
if ($use_default) return (isset($this->prune)) ? $this->prune : $this->default_prune;
return $this->prune;
}
// return string or null
public function parser($use_default=true) {
if ($use_default) return (isset($this->parser)) ? $this->parser : $this->default_parser;
return $this->parser;
}
// return bool or null
public function autodetect_on_failure($use_default=true) {
if ($use_default) return (isset($this->autodetect_on_failure)) ? $this->autodetect_on_failure : $this->default_autodetect_on_failure;
return $this->autodetect_on_failure;
}
public static function set_config_path($path, $fallback=null) {
self::$config_path = $path;
self::$config_path_fallback = $fallback;
}
public static function add_to_cache($key, SiteConfig $config, $use_apc=true) {
$key = strtolower($key);
if (substr($key, 0, 4) == 'www.') $key = substr($key, 4);
if ($config->cache_key) $key = $config->cache_key;
self::$config_cache[$key] = $config;
if (self::$apc && $use_apc) {
self::debug("Adding site config to APC cache with key sc.$key");
apc_add("sc.$key", $config);
}
self::debug("Cached site config with key $key");
}
public static function is_cached($key) {
$key = strtolower($key);
if (substr($key, 0, 4) == 'www.') $key = substr($key, 4);
if (array_key_exists($key, self::$config_cache)) {
return true;
} elseif (self::$apc && (bool)apc_fetch("sc.$key")) {
return true;
}
return false;
}
public function append(SiteConfig $newconfig) {
// 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') as $var) {
// append array elements for this config variable from $newconfig to this config
//$this->$var = $this->$var + $newconfig->$var;
$this->$var = array_unique(array_merge($this->$var, $newconfig->$var));
}
// check for single statement commands
// we do not overwrite existing non null values
foreach (array('tidy', 'prune', 'parser', 'autodetect_on_failure') as $var) {
if ($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) {
// append array elements for this config variable from $newconfig to this config
//$this->$var = $this->$var + $newconfig->$var;
$this->$var = array_merge($this->$var, $newconfig->$var);
}
}
// returns SiteConfig instance if an appropriate one is found, false otherwise
// if $exact_host_match is true, we will not look for wildcard config matches
// by default if host is 'test.example.org' we will look for and load '.example.org.txt' if it exists
public static function build($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;
// check for site configuration
$try = array($host);
// should we look for wildcard matches
if (!$exact_host_match) {
$split = explode('.', $host);
if (count($split) > 1) {
array_shift($split);
$try[] = '.'.implode('.', $split);
}
}
// look for site config file in primary folder
self::debug(". looking for site config for $host in primary folder");
foreach ($try as $h) {
if (array_key_exists($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"))) {
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)");
$file_primary = self::$config_path."/$h.txt";
$matched_name = $h;
break;
}
}
// if we found site config, process it
if (isset($file_primary)) {
$config_lines = file($file_primary, FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
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;
$config->cache_key = $matched_name;
// if autodetec on failure is off (on by default) we do not need to look
// in secondary folder
if (!$config->autodetect_on_failure()) {
self::debug('... autodetect on failure is disabled (no other site config files will be loaded)');
return $config;
}
}
// look for site config file in secondary folder
if (isset(self::$config_path_fallback)) {
self::debug(". looking for site config for $host in secondary folder");
foreach ($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";
$matched_name = $h;
break;
}
}
if (!isset($file_secondary)) {
self::debug("... no site config match in secondary folder");
}
}
// return false if no config file found
if (!isset($file_primary) && !isset($file_secondary)) {
self::debug("... no site config match for $host");
return false;
}
// return primary config if secondary not found
if (!isset($file_secondary) && isset($config)) {
return $config;
}
// process secondary config file
$config_lines = file($file_secondary, FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
if (!$config_lines || !is_array($config_lines)) {
// failed to process secondary
if (isset($config)) {
// return primary config
return $config;
} else {
return false;
}
}
// merge with primary and return
if (isset($config)) {
self::debug('. merging config files');
$config->append(self::build_from_array($config_lines));
return $config;
} else {
// return just secondary
$config = self::build_from_array($config_lines);
// if APC caching is available and enabled, mark this for cache
//$config->cache_in_apc = true;
$config->cache_key = $matched_name;
return $config;
}
}
public static function build_from_array(array $lines) {
$config = new SiteConfig();
foreach ($lines as $line) {
$line = trim($line);
// skip comments, empty lines
if ($line == '' || $line[0] == '#') continue;
// get command
$command = explode(':', $line, 2);
// if there's no colon ':', skip this line
if (count($command) != 2) continue;
$val = trim($command[1]);
$command = trim($command[0]);
if ($command == '' || $val == '') continue;
// check for commands where we accept multiple statements
if (in_array($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'))) {
array_push($config->$command, $val);
// check for single statement commands that evaluate to true or false
} elseif (in_array($command, array('tidy', 'prune', 'autodetect_on_failure'))) {
$config->$command = ($val == 'yes');
// check for single statement commands stored as strings
} elseif (in_array($command, array('parser'))) {
$config->$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'))) {
$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
/**
* Univarsel Feed Writer
*
*
* FeedItem class - Used as feed element in FeedWriter class
*
* @package UnivarselFeedWriter
@ -12,20 +12,20 @@
{
private $elements = array(); //Collection of feed elements
private $version;
/**
* Constructor
*
* @param contant (RSS1/RSS2/ATOM) RSS2 is default.
*/
* Constructor
*
* @param contant (RSS1/RSS2/ATOM) RSS2 is default.
*/
function __construct($version = RSS2)
{
{
$this->version = $version;
}
/**
* Set element (overwrites existing elements with $elementName)
*
*
* @access public
* @param srting The tag name of an element
* @param srting The content of tag
@ -38,11 +38,11 @@
unset($this->elements[$elementName]);
}
$this->addElement($elementName, $content, $attributes);
}
}
/**
* Add an element to elements array
*
*
* @access public
* @param srting The tag name of an element
* @param srting The content of tag
@ -61,11 +61,11 @@
$this->elements[$elementName][$i]['content'] = $content;
$this->elements[$elementName][$i]['attributes'] = $attributes;
}
/**
* Set multiple feed elements from an array.
* Set multiple feed elements from an array.
* Elements which have attributes cannot be added by this method
*
*
* @access public
* @param array array of elements in 'tagName' => 'tagContent' format.
* @return void
@ -73,15 +73,15 @@
public function addElementArray($elementArray)
{
if(! is_array($elementArray)) return;
foreach ($elementArray as $elementName => $content)
foreach ($elementArray as $elementName => $content)
{
$this->addElement($elementName, $content);
}
}
/**
* Return the collection of elements in this feed item
*
*
* @access public
* @return array
*/
@ -89,68 +89,74 @@
{
return $this->elements;
}
// Wrapper functions ------------------------------------------------------
/**
* Set the 'dscription' element of feed item
*
*
* @access public
* @param string The content of 'description' element
* @return void
*/
public function setDescription($description)
public function setDescription($description)
{
$this->setElement('description', $description);
$tag = ($this->version == ATOM)? 'summary' : 'description';
$this->setElement($tag, $description);
}
/**
* @desc Set the 'title' element of feed item
* @access public
* @param string The content of 'title' element
* @return void
*/
public function setTitle($title)
public function setTitle($title)
{
$this->setElement('title', $title);
$this->setElement('title', $title);
}
/**
* Set the 'date' element of feed item
*
*
* @access public
* @param string The content of 'date' element
* @return void
*/
public function setDate($date)
public function setDate($date)
{
if(! is_numeric($date))
{
$date = strtotime($date);
}
if($this->version == RSS2)
if($this->version == ATOM)
{
$tag = 'pubDate';
$value = date(DATE_RSS, $date);
$tag = 'updated';
$value = date(DATE_ATOM, $date);
}
else
elseif($this->version == RSS2)
{
$tag = 'dc:date';
$value = date("Y-m-d", $date);
$tag = 'pubDate';
$value = date(DATE_RSS, $date);
}
$this->setElement($tag, $value);
else
{
$tag = 'dc:date';
$value = date("Y-m-d", $date);
}
$this->setElement($tag, $value);
}
/**
* Set the 'link' element of feed item
*
*
* @access public
* @param string The content of 'link' element
* @return void
*/
public function setLink($link)
public function setLink($link)
{
if($this->version == RSS2 || $this->version == RSS1)
{
@ -161,27 +167,27 @@
{
$this->setElement('link','',array('href'=>$link));
$this->setElement('id', FeedWriter::uuid($link,'urn:uuid:'));
}
}
}
/**
* Set the 'source' element of feed item
*
*
* @access public
* @param string The content of 'source' element
* @return void
*/
public function setSource($link)
public function setSource($link)
{
$attributes = array('url'=>$link);
$this->setElement('source', "wallabag",$attributes);
}
/**
* Set the 'encloser' element of feed item
* For RSS 2.0 only
*
*
* @access public
* @param string The url attribute of encloser tag
* @param string The length attribute of encloser tag
@ -193,6 +199,6 @@
$attributes = array('url'=>$url, 'length'=>$length, 'type'=>$type);
$this->setElement('enclosure','',$attributes);
}
} // end of class FeedItem
?>

View file

@ -2,6 +2,7 @@
define('RSS2', 1, true);
define('JSON', 2, true);
define('JSONP', 3, true);
define('ATOM', 4, true);
/**
* Univarsel Feed Writer class
@ -101,11 +102,11 @@ define('JSONP', 3, true);
header('Content-type: application/javascript; charset=UTF-8');
}
}
if ($this->version == JSON || $this->version == JSONP) {
$this->json = new stdClass();
}
$this->printHead();
$this->printChannels();
@ -116,6 +117,11 @@ define('JSONP', 3, true);
}
}
public function &getItems()
{
return $this->items;
}
/**
* Create a new FeedItem.
*
@ -199,7 +205,8 @@ define('JSONP', 3, true);
*/
public function setDescription($description)
{
$this->setChannelElement('description', $description);
$tag = ($this->version == ATOM)? 'subtitle' : 'description';
$this->setChannelElement($tag, $description);
}
/**
@ -244,7 +251,7 @@ define('JSONP', 3, true);
{
$out = '<?xml version="1.0" encoding="utf-8"?>'."\n";
if ($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 $out;
}
elseif ($this->version == JSON || $this->version == JSONP)

View file

@ -134,6 +134,7 @@ class HTML5_TreeBuilder {
// Namespaces for foreign content
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_SVG = 'http://www.w3.org/2000/svg';
const NS_XLINK = 'http://www.w3.org/1999/xlink';
@ -3157,11 +3158,19 @@ class HTML5_TreeBuilder {
}
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'])) {
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']);
}
}

View file

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

File diff suppressed because it is too large Load diff

View file

@ -1,79 +1,78 @@
<?php
/**
* Humble HTTP Agent extension for SimplePie_File
*
* This class is designed to extend and override SimplePie_File
* in order to prevent duplicate HTTP requests being sent out.
* The idea is to initialise an instance of Humble HTTP Agent
* and attach it, to a static class variable, of this class.
* SimplePie will then automatically initialise this class
*
* @date 2011-02-28
*/
class SimplePie_HumbleHttpAgent extends SimplePie_File
{
protected static $agent;
var $url;
var $useragent;
var $success = true;
var $headers = array();
var $body;
var $status_code;
var $redirects = 0;
var $error;
var $method = SIMPLEPIE_FILE_SOURCE_NONE;
public static function set_agent(HumbleHttpAgent $agent) {
self::$agent = $agent;
}
public function __construct($url, $timeout = 10, $redirects = 5, $headers = null, $useragent = null, $force_fsockopen = false) {
if (class_exists('idna_convert'))
{
$idn = new idna_convert();
$parsed = SimplePie_Misc::parse_url($url);
$url = SimplePie_Misc::compress_parse_url($parsed['scheme'], $idn->encode($parsed['authority']), $parsed['path'], $parsed['query'], $parsed['fragment']);
}
$this->url = $url;
$this->useragent = $useragent;
if (preg_match('/^http(s)?:\/\//i', $url))
{
if (!is_array($headers))
{
$headers = array();
}
$this->method = SIMPLEPIE_FILE_SOURCE_REMOTE | SIMPLEPIE_FILE_SOURCE_CURL;
$headers2 = array();
foreach ($headers as $key => $value) {
$headers2[] = "$key: $value";
}
//TODO: allow for HTTP headers
// curl_setopt($fp, CURLOPT_HTTPHEADER, $headers2);
$response = self::$agent->get($url);
if ($response === false || !isset($response['status_code'])) {
$this->error = 'failed to fetch URL';
$this->success = false;
} else {
// 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
// headers - the new lines indicate the start of the body.
$parser = new SimplePie_HTTP_Parser($response['headers']."\r\n\r\n");
if ($parser->parse()) {
$this->headers = $parser->headers;
//$this->body = $parser->body;
$this->body = $response['body'];
$this->status_code = $parser->status_code;
}
}
}
else
{
$this->error = 'invalid URL';
$this->success = false;
}
}
}
?>
<?php
/**
* Humble HTTP Agent extension for SimplePie_File
*
* This class is designed to extend and override SimplePie_File
* in order to prevent duplicate HTTP requests being sent out.
* The idea is to initialise an instance of Humble HTTP Agent
* and attach it, to a static class variable, of this class.
* SimplePie will then automatically initialise this class
*
* @date 2011-02-28
*/
class SimplePie_HumbleHttpAgent extends SimplePie_File
{
protected static $agent;
var $url;
var $useragent;
var $success = true;
var $headers = array();
var $body;
var $status_code;
var $redirects = 0;
var $error;
var $method = SIMPLEPIE_FILE_SOURCE_NONE;
public static function set_agent(HumbleHttpAgent $agent) {
self::$agent = $agent;
}
public function __construct($url, $timeout = 10, $redirects = 5, $headers = null, $useragent = null, $force_fsockopen = false) {
if (class_exists('idna_convert'))
{
$idn = new idna_convert();
$parsed = SimplePie_Misc::parse_url($url);
$url = SimplePie_Misc::compress_parse_url($parsed['scheme'], $idn->encode($parsed['authority']), $parsed['path'], $parsed['query'], $parsed['fragment']);
}
$this->url = $url;
$this->useragent = $useragent;
if (preg_match('/^http(s)?:\/\//i', $url))
{
if (!is_array($headers))
{
$headers = array();
}
$this->method = SIMPLEPIE_FILE_SOURCE_REMOTE | SIMPLEPIE_FILE_SOURCE_CURL;
$headers2 = array();
foreach ($headers as $key => $value) {
$headers2[] = "$key: $value";
}
//TODO: allow for HTTP headers
// curl_setopt($fp, CURLOPT_HTTPHEADER, $headers2);
$response = self::$agent->get($url);
if ($response === false || !isset($response['status_code'])) {
$this->error = 'failed to fetch URL';
$this->success = false;
} else {
// 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
// headers - the new lines indicate the start of the body.
$parser = new SimplePie_HTTP_Parser($response['headers']."\r\n\r\n");
if ($parser->parse()) {
$this->headers = $parser->headers;
//$this->body = $parser->body;
$this->body = $response['body'];
$this->status_code = $parser->status_code;
}
}
}
else
{
$this->error = 'invalid URL';
$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
* @copyright 2006
* @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://langdetect.blogspot.com/
*/
@ -28,7 +28,7 @@
* @author Nicholas Pisarro
* @copyright 2006
* @license BSD
* @version release: 0.2.3
* @version release: 0.3.0
*/
class Text_LanguageDetect_Parser extends Text_LanguageDetect
{
@ -102,21 +102,17 @@ class Text_LanguageDetect_Parser extends Text_LanguageDetect
* @access private
* @param string $string string to be parsed
*/
function Text_LanguageDetect_Parser($string, $db=null, $unicode_db=null) {
if (isset($db)) $this->_db_filename = $db;
if (isset($unicode_db)) $this->_unicode_db_filename = $unicode_db;
function Text_LanguageDetect_Parser($string) {
$this->_string = $string;
}
/**
* Returns true if a string is suitable for parsing
*
* @static
* @access public
* @param string $str input string to test
* @return bool true if acceptable, false if not
*/
function validateString($str) {
public static function validateString($str) {
if (!empty($str) && strlen($str) > 3 && preg_match('/\S/', $str)) {
return true;
} else {
@ -222,8 +218,7 @@ class Text_LanguageDetect_Parser extends Text_LanguageDetect
// unicode startup
if ($this->_compile_unicode) {
$blocks =& $this->_read_unicode_block_db();
$blocks = $this->_read_unicode_block_db();
$block_count = count($blocks);
$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