Merge pull request #1 from inthepoche/dev

Dev
author: tcitworld <thomas.citharet@gmail.com> 2014-01-04 12:30:31 -0800
committer: tcitworld <thomas.citharet@gmail.com> 2014-01-04 12:30:31 -0800
commit: 7f667839764621b5aa01c9db8ce5dde2a29ef18f (patch)
tree: 93d8241ee81c87e18494325ae02f0589a8e328a2 /inc/3rdparty/libraries/content-extractor/SiteConfig.php
parent: a84f77d6ba15a64ff00453f5d5190c021ce460ed (diff)
parent: 2abcccb37180c17318f5226f5d4bc28f30b621ea (diff)
download: wallabag-7f667839764621b5aa01c9db8ce5dde2a29ef18f.tar.gz
wallabag-7f667839764621b5aa01c9db8ce5dde2a29ef18f.tar.zst
wallabag-7f667839764621b5aa01c9db8ce5dde2a29ef18f.zip
1 files changed, 338 insertions, 0 deletions
diff --git a/inc/3rdparty/libraries/content-extractor/SiteConfig.php b/inc/3rdparty/libraries/content-extractor/SiteConfig.php
new file mode 100644
index 00000000..c5e300d7
--- /dev/null
+++ b/inc/3rdparty/libraries/content-extractor/SiteConfig.php
@@ -0,0 +1,338 @@
+<?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;
+        }
+}
+?>
+\ No newline at end of file
author	tcitworld <thomas.citharet@gmail.com>	2014-01-04 12:30:31 -0800
committer	tcitworld <thomas.citharet@gmail.com>	2014-01-04 12:30:31 -0800
commit	7f667839764621b5aa01c9db8ce5dde2a29ef18f (patch)
tree	93d8241ee81c87e18494325ae02f0589a8e328a2 /inc/3rdparty/libraries/content-extractor/SiteConfig.php
parent	a84f77d6ba15a64ff00453f5d5190c021ce460ed (diff)
parent	2abcccb37180c17318f5226f5d4bc28f30b621ea (diff)
download	wallabag-7f667839764621b5aa01c9db8ce5dde2a29ef18f.tar.gz wallabag-7f667839764621b5aa01c9db8ce5dde2a29ef18f.tar.zst wallabag-7f667839764621b5aa01c9db8ce5dde2a29ef18f.zip

diff --git a/inc/3rdparty/libraries/content-extractor/SiteConfig.php b/inc/3rdparty/libraries/content-extractor/SiteConfig.php new file mode 100644 index 00000000..c5e300d7 --- /dev/null +++ b/inc/3rdparty/libraries/content-extractor/SiteConfig.php
@@ -0,0 +1,338 @@
	1	<?php
	2	/**
	3	* Site Config
	4	*
	5	* Each instance of this class should hold extraction patterns and other directives
	6	* for a website. See ContentExtractor class to see how it's used.
	7	*
	8	* @version 0.7
	9	* @date 2012-08-27
	10	* @author Keyvan Minoukadeh
	11	* @copyright 2012 Keyvan Minoukadeh
	12	* @license http://www.gnu.org/licenses/agpl-3.0.html AGPL v3
	13	*/
	14
	15	class SiteConfig
	16	{
	17	// Use first matching element as title (0 or more xpath expressions)
	18	public $title = array();
	19
	20	// Use first matching element as body (0 or more xpath expressions)
	21	public $body = array();
	22
	23	// Use first matching element as author (0 or more xpath expressions)
	24	public $author = array();
	25
	26	// Use first matching element as date (0 or more xpath expressions)
	27	public $date = array();
	28
	29	// Strip elements matching these xpath expressions (0 or more)
	30	public $strip = array();
	31
	32	// Strip elements which contain these strings (0 or more) in the id or class attribute
	33	public $strip_id_or_class = array();
	34
	35	// Strip images which contain these strings (0 or more) in the src attribute
	36	public $strip_image_src = array();
	37
	38	// Additional HTTP headers to send
	39	// NOT YET USED
	40	public $http_header = array();
	41
	42	// Process HTML with tidy before creating DOM (bool or null if undeclared)
	43	public $tidy = null;
	44
	45	protected $default_tidy = true; // used if undeclared
	46
	47	// Autodetect title/body if xpath expressions fail to produce results.
	48	// Note that this applies to title and body separately, ie.
	49	// * if we get a body match but no title match, this option will determine whether we autodetect title
	50	// * if neither match, this determines whether we autodetect title and body.
	51	// Also note that this only applies when there is at least one xpath expression in title or body, ie.
	52	// * if title and body are both empty (no xpath expressions), this option has no effect (both title and body will be auto-detected)
	53	// * 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.
	54	// 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).
	55	// bool or null if undeclared
	56	public $autodetect_on_failure = null;
	57	protected $default_autodetect_on_failure = true; // used if undeclared
	58
	59	// Clean up content block - attempt to remove elements that appear to be superfluous
	60	// bool or null if undeclared
	61	public $prune = null;
	62	protected $default_prune = true; // used if undeclared
	63
	64	// Test URL - if present, can be used to test the config above
	65	public $test_url = array();
	66
	67	// Single-page link - should identify a link element or URL pointing to the page holding the entire article
	68	// This is useful for sites which split their articles across multiple pages. Links to such pages tend to
	69	// display the first page with links to the other pages at the bottom. Often there is also a link to a page
	70	// which displays the entire article on one page (e.g. 'print view').
	71	// This should be an XPath expression identifying the link to that page. If present and we find a match,
	72	// we will retrieve that page and the rest of the options in this config will be applied to the new page.
	73	public $single_page_link = array();
	74
	75	public $next_page_link = array();
	76
	77	// Single-page link in feed? - same as above, but patterns applied to item description HTML taken from feed
	78	public $single_page_link_in_feed = array();
	79
	80	// Which parser to use for turning raw HTML into a DOMDocument (either 'libxml' or 'html5lib')
	81	// string or null if undeclared
	82	public $parser = null;
	83	protected $default_parser = 'libxml'; // used if undeclared
	84
	85	// Strings to search for in HTML before processing begins (used with $replace_string)
	86	public $find_string = array();
	87	// Strings to replace those found in $find_string before HTML processing begins
	88	public $replace_string = array();
	89
	90	// the options below cannot be set in the config files which this class represents
	91
	92	//public $cache_in_apc = false; // used to decide if we should cache in apc or not
	93	public $cache_key = null;
	94	public static $debug = false;
	95	protected static $apc = false;
	96	protected static $config_path;
	97	protected static $config_path_fallback;
	98	protected static $config_cache = array();
	99	const HOSTNAME_REGEX = '/^(([a-zA-Z0-9-][a-zA-Z0-9])\.)([A-Za-z0-9-]*[A-Za-z0-9])$/';
	100
	101	protected static function debug($msg) {
	102	if (self::$debug) {
	103	//$mem = round(memory_get_usage()/1024, 2);
	104	//$memPeak = round(memory_get_peak_usage()/1024, 2);
	105	echo '* ',$msg;
	106	//echo ' - mem used: ',$mem," (peak: $memPeak)\n";
	107	echo "\n";
	108	ob_flush();
	109	flush();
	110	}
	111	}
	112
	113	// enable APC caching of certain site config files?
	114	// If enabled the following site config files will be
	115	// cached in APC cache (when requested for first time):
	116	// * anything in site_config/custom/ and its corresponding file in site_config/standard/
	117	// * the site config files associated with HTML fingerprints
	118	// * the global site config file
	119	// returns true if enabled, false otherwise
	120	public static function use_apc($apc=true) {
	121	if (!function_exists('apc_add')) {
	122	if ($apc) self::debug('APC will not be used (function apc_add does not exist)');
	123	return false;
	124	}
	125	self::$apc = $apc;
	126	return $apc;
	127	}
	128
	129	// return bool or null
	130	public function tidy($use_default=true) {
	131	if ($use_default) return (isset($this->tidy)) ? $this->tidy : $this->default_tidy;
	132	return $this->tidy;
	133	}
	134
	135	// return bool or null
	136	public function prune($use_default=true) {
	137	if ($use_default) return (isset($this->prune)) ? $this->prune : $this->default_prune;
	138	return $this->prune;
	139	}
	140
	141	// return string or null
	142	public function parser($use_default=true) {
	143	if ($use_default) return (isset($this->parser)) ? $this->parser : $this->default_parser;
	144	return $this->parser;
	145	}
	146
	147	// return bool or null
	148	public function autodetect_on_failure($use_default=true) {
	149	if ($use_default) return (isset($this->autodetect_on_failure)) ? $this->autodetect_on_failure : $this->default_autodetect_on_failure;
	150	return $this->autodetect_on_failure;
	151	}
	152
	153	public static function set_config_path($path, $fallback=null) {
	154	self::$config_path = $path;
	155	self::$config_path_fallback = $fallback;
	156	}
	157
	158	public static function add_to_cache($key, SiteConfig $config, $use_apc=true) {
	159	$key = strtolower($key);
	160	if (substr($key, 0, 4) == 'www.') $key = substr($key, 4);
	161	if ($config->cache_key) $key = $config->cache_key;
	162	self::$config_cache[$key] = $config;
	163	if (self::$apc && $use_apc) {
	164	self::debug("Adding site config to APC cache with key sc.$key");
	165	apc_add("sc.$key", $config);
	166	}
	167	self::debug("Cached site config with key $key");
	168	}
	169
	170	public static function is_cached($key) {
	171	$key = strtolower($key);
	172	if (substr($key, 0, 4) == 'www.') $key = substr($key, 4);
	173	if (array_key_exists($key, self::$config_cache)) {
	174	return true;
	175	} elseif (self::$apc && (bool)apc_fetch("sc.$key")) {
	176	return true;
	177	}
	178	return false;
	179	}
	180
	181	public function append(SiteConfig $newconfig) {
	182	// check for commands where we accept multiple statements (no test_url)
	183	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) {
	184	// append array elements for this config variable from $newconfig to this config
	185	//$this->$var = $this->$var + $newconfig->$var;
	186	$this->$var = array_unique(array_merge($this->$var, $newconfig->$var));
	187	}
	188	// check for single statement commands
	189	// we do not overwrite existing non null values
	190	foreach (array('tidy', 'prune', 'parser', 'autodetect_on_failure') as $var) {
	191	if ($this->$var === null) $this->$var = $newconfig->$var;
	192	}
	193	}
	194
	195	// returns SiteConfig instance if an appropriate one is found, false otherwise
	196	// if $exact_host_match is true, we will not look for wildcard config matches
	197	// by default if host is 'test.example.org' we will look for and load '.example.org.txt' if it exists
	198	public static function build($host, $exact_host_match=false) {
	199	$host = strtolower($host);
	200	if (substr($host, 0, 4) == 'www.') $host = substr($host, 4);
	201	if (!$host \|\| (strlen($host) > 200) \|\| !preg_match(self::HOSTNAME_REGEX, ltrim($host, '.'))) return false;
	202	// check for site configuration
	203	$try = array($host);
	204	// should we look for wildcard matches
	205	if (!$exact_host_match) {
	206	$split = explode('.', $host);
	207	if (count($split) > 1) {
	208	array_shift($split);
	209	$try[] = '.'.implode('.', $split);
	210	}
	211	}
	212
	213	// look for site config file in primary folder
	214	self::debug(". looking for site config for $host in primary folder");
	215	foreach ($try as $h) {
	216	if (array_key_exists($h, self::$config_cache)) {
	217	self::debug("... site config for $h already loaded in this request");
	218	return self::$config_cache[$h];
	219	} elseif (self::$apc && ($sconfig = apc_fetch("sc.$h"))) {
	220	self::debug("... site config for $h in APC cache");
	221	return $sconfig;
	222	} elseif (file_exists(self::$config_path."/$h.txt")) {
	223	self::debug("... found site config ($h.txt)");
	224	$file_primary = self::$config_path."/$h.txt";
	225	$matched_name = $h;
	226	break;
	227	}
	228	}
	229
	230	// if we found site config, process it
	231	if (isset($file_primary)) {
	232	$config_lines = file($file_primary, FILE_IGNORE_NEW_LINES \| FILE_SKIP_EMPTY_LINES);
	233	if (!$config_lines \|\| !is_array($config_lines)) return false;
	234	$config = self::build_from_array($config_lines);
	235	// if APC caching is available and enabled, mark this for cache
	236	//$config->cache_in_apc = true;
	237	$config->cache_key = $matched_name;
	238
	239	// if autodetec on failure is off (on by default) we do not need to look
	240	// in secondary folder
	241	if (!$config->autodetect_on_failure()) {
	242	self::debug('... autodetect on failure is disabled (no other site config files will be loaded)');
	243	return $config;
	244	}
	245	}
	246
	247	// look for site config file in secondary folder
	248	if (isset(self::$config_path_fallback)) {
	249	self::debug(". looking for site config for $host in secondary folder");
	250	foreach ($try as $h) {
	251	if (file_exists(self::$config_path_fallback."/$h.txt")) {
	252	self::debug("... found site config in secondary folder ($h.txt)");
	253	$file_secondary = self::$config_path_fallback."/$h.txt";
	254	$matched_name = $h;
	255	break;
	256	}
	257	}
	258	if (!isset($file_secondary)) {
	259	self::debug("... no site config match in secondary folder");
	260	}
	261	}
	262
	263	// return false if no config file found
	264	if (!isset($file_primary) && !isset($file_secondary)) {
	265	self::debug("... no site config match for $host");
	266	return false;
	267	}
	268
	269	// return primary config if secondary not found
	270	if (!isset($file_secondary) && isset($config)) {
	271	return $config;
	272	}
	273
	274	// process secondary config file
	275	$config_lines = file($file_secondary, FILE_IGNORE_NEW_LINES \| FILE_SKIP_EMPTY_LINES);
	276	if (!$config_lines \|\| !is_array($config_lines)) {
	277	// failed to process secondary
	278	if (isset($config)) {
	279	// return primary config
	280	return $config;
	281	} else {
	282	return false;
	283	}
	284	}
	285
	286	// merge with primary and return
	287	if (isset($config)) {
	288	self::debug('. merging config files');
	289	$config->append(self::build_from_array($config_lines));
	290	return $config;
	291	} else {
	292	// return just secondary
	293	$config = self::build_from_array($config_lines);
	294	// if APC caching is available and enabled, mark this for cache
	295	//$config->cache_in_apc = true;
	296	$config->cache_key = $matched_name;
	297	return $config;
	298	}
	299	}
	300
	301	public static function build_from_array(array $lines) {
	302	$config = new SiteConfig();
	303	foreach ($lines as $line) {
	304	$line = trim($line);
	305
	306	// skip comments, empty lines
	307	if ($line == '' \|\| $line[0] == '#') continue;
	308
	309	// get command
	310	$command = explode(':', $line, 2);
	311	// if there's no colon ':', skip this line
	312	if (count($command) != 2) continue;
	313	$val = trim($command[1]);
	314	$command = trim($command[0]);
	315	if ($command == '' \|\| $val == '') continue;
	316
	317	// check for commands where we accept multiple statements
	318	if (in_array($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'))) {
	319	array_push($config->$command, $val);
	320	// check for single statement commands that evaluate to true or false
	321	} elseif (in_array($command, array('tidy', 'prune', 'autodetect_on_failure'))) {
	322	$config->$command = ($val == 'yes');
	323	// check for single statement commands stored as strings
	324	} elseif (in_array($command, array('parser'))) {
	325	$config->$command = $val;
	326	// check for replace_string(find): replace
	327	} elseif ((substr($command, -1) == ')') && preg_match('!^([a-z0-9_]+)\((.*?)\)$!i', $command, $match)) {
	328	if (in_array($match[1], array('replace_string'))) {
	329	$command = $match[1];
	330	array_push($config->find_string, $match[2]);
	331	array_push($config->$command, $val);
	332	}
	333	}
	334	}
	335	return $config;
	336	}
	337	}
	338	?> \ No newline at end of file