From 5f655f3b9fff2f41754b9612ce178b495910f4d4 Mon Sep 17 00:00:00 2001 From: emkael Date: Wed, 7 Nov 2018 22:08:03 +0100 Subject: Moving app to separate directory, scanning for PBN files in a separate directory Fixes #2 --- tdd/.htaccess | 16 + tdd/tdd-bootstrap.php | 203 +++++++++ tdd/tdd-handrecord-tpl.php | 56 +++ tdd/tdd-protocol.php | 29 ++ tdd/tdd-simple-html-dom.php | 975 ++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 1279 insertions(+) create mode 100644 tdd/.htaccess create mode 100644 tdd/tdd-bootstrap.php create mode 100644 tdd/tdd-handrecord-tpl.php create mode 100644 tdd/tdd-protocol.php create mode 100644 tdd/tdd-simple-html-dom.php (limited to 'tdd') diff --git a/tdd/.htaccess b/tdd/.htaccess new file mode 100644 index 0000000..fad82c6 --- /dev/null +++ b/tdd/.htaccess @@ -0,0 +1,16 @@ + + # Apache 2.2 + Order allow,deny + Allow from all + + # Apache 2.4 + Require all granted + + + # Apache 2.2 + Order allow,deny + Deny from all + + # Apache 2.4 + Require all denied + diff --git a/tdd/tdd-bootstrap.php b/tdd/tdd-bootstrap.php new file mode 100644 index 0000000..f22cd8e --- /dev/null +++ b/tdd/tdd-bootstrap.php @@ -0,0 +1,203 @@ +prefix = $prefix; + $this->round = $round; + $this->board = $board; + $this->deals_by_tables = array(); + if(!file_exists($this->get_filename())) { + throw new Exception('file not found: ' . $this->get_filename()); + } + } + + function get_filename() { + return '..' . DIRECTORY_SEPARATOR . $this->prefix . $this->round . 'b-' . $this->board . '.html'; + } + + function set_deal($table, $deal) { + $this->deals_by_tables[$table] = $deal; + } + + function output() { + $content = file_get_contents($this->get_filename()); + + $dom = str_get_html($content); + $header_td1 = $dom->find("/html/body/table/tr/td[class=\"bdcc12\"]", 0); + $header_tr = $header_td1->parent; + $tr = @$header_tr->next_sibling(); + while($tr) { + $td = $tr->find('td/a', 0); + $table = trim($td->innertext); + $table = str_replace(' ', '', $table); + $table = (int)$table; + if($table && array_key_exists($table, $this->deals_by_tables)) { + $contract1 = trim(str_replace(' ', '', $tr->find('td[class="bdc"]', 0)->innertext)); + $score1 = trim(str_replace(' ', '', end($tr->find('td'))->innertext)); + $contract2 = trim(str_replace(' ', '', $tr->next_sibling()->find('td[class="bdc"]', 0)->innertext)); + $score2 = trim(str_replace(' ', '', end($tr->next_sibling()->find('td'))->innertext)); + + $deal = $this->deals_by_tables[$table]; + $insert = "

Stół $table – Rozdanie {$deal->deal_num}

"; + // if is played on both tables of a match + // note that the contract field for arbitral scores starts with 'A' (e.g. 'ARB' or 'AAA') + if(($score1 !== '' || strpos($contract1, 'A') === 0) + && ($score2 !== '' || strpos($contract2, 'A') === 0)) { + $insert .= $deal->html(); + } else { + $insert .= '

...

'; + } + + $tr->outertext = '' . $insert . '' . $tr->outertext; + } + $tr = @$tr->next_sibling(); + } + + $header_tr2 = $header_tr->next_sibling(); + $header_tr->outertext = ''; + $header_tr2->outertext = ''; + $dom->find('/html/body/table/tr', 0)->outertext = ''; + + $head = $dom->find('/html/head', 0); + $head->innertext .= '' + . '' + . ''; + + // replacing meta http-equiv refresh with a javascript refresh to preserve hash in the result page + $meta = $head->find('meta'); + foreach ($meta as $metaTag) { + if ($metaTag->hasAttribute('http-equiv') && strtolower($metaTag->getAttribute('http-equiv')) == 'refresh') { + $head->innertext = str_replace($metaTag->outertext, '', $head->innertext) . ''; + break; + } + } + + print $dom->outertext; + } + +} + +class NoSuchDealNumber extends Exception { +} + +class Deal { + + function __construct($filename, $num_in_pbn) { + $this->deal_num = $num_in_pbn; + $this->_parse($filename, $num_in_pbn); + } + + function _parse($filename, $num_in_pbn) { + $pbn = file_get_contents($filename); + $start = strpos($pbn, '[Board "' . $num_in_pbn . '"]'); + if($start === false) { + throw new NoSuchDealNumber($num_in_pbn); + } + + $pbn = substr($pbn, $start + 5); + $stop = strpos($pbn,'[Board "'); + if($stop != false) { + $pbn = substr($pbn, 0, $stop); + } + + preg_match('|Dealer "([NESW])"|', $pbn, $m); + $this->dealer = $m[1]; + + preg_match('|Vulnerable "([^"]+)"|', $pbn, $m); + $this->vuln = $m[1]; + if($this->vuln == 'None') { + $this->vuln = '-'; + } else if($this->vuln == 'All') { + $this->vuln = 'Obie'; + } + + preg_match('|Ability "([^"]+)"|', $pbn, $m); + if($m[1]) { + $this->ability = explode(' ',$m[1]); + } + + preg_match('|Minimax "([^"]+)"|', $pbn, $m); + $this->minimax = $m[1]; + + preg_match('|Deal "(N:)?([^"]+)"|', $pbn, $m); + $this->hands = explode(' ',$m[2]); + } + + function html() { + ob_start(); + include('tdd-handrecord-tpl.php'); + return ob_get_clean(); + } + + function format_hand($hand_num) { + $hand = $this->hands[$hand_num]; + $hand = str_replace('T','10',$hand); + $suits = explode('.',$hand); + $str = 'S '.$suits[0].'
'; + $str .= 'H '.$suits[1].'
'; + $str .= 'D '.$suits[2].'
'; + $str .= 'C '.$suits[3]; + return $str; + } + + function format_ability($ability_num) { + $ability = $this->ability[$ability_num]; + $ab = array($ability[0], $ability[2], $ability[3], $ability[4], $ability[5], $ability[6]); + foreach($ab as $k=>$v) { + switch($v) { + case 'A': $ab[$k] = '10'; break; + case 'B': $ab[$k] = '11'; break; + case 'C': $ab[$k] = '12'; break; + case 'D': $ab[$k] = '13'; break; + } + } + return "{$ab[0]} + {$ab[1]} + {$ab[2]} + {$ab[3]} + {$ab[4]} + {$ab[5]}"; + } + + function format_minimax() { + $minimax = $this->minimax; + $minimax = preg_replace('|^(..)D(.+)|','$1x$2', $minimax); + $minimax = preg_replace('|^(..)R(.+)|','$1xx$2', $minimax); + $minimax = preg_replace('|^(.)N(.+)|','$1NT$2', $minimax); + $minimax = preg_replace('/(\d)([SHDCN])(T?)(x*)([NESW])(.*)/','$1 $2$3 $4 $5, $6', $minimax); + return $minimax; + } + +} + +function load_deals_for_tables($prefix, $round, $board_in_teamy) { + $deals_by_tables = array(); + + $prefix = preg_quote($prefix); + $filename_regex = "/$prefix-r$round-t(\d+)-b(\d+).pbn/"; + foreach(scandir('.') as $filename) { + if(preg_match($filename_regex, $filename, $match)) { + $file_table = $match[1]; + $file_start_board = $match[2]; + + $first_num_in_pbn = array(); + preg_match('/\[Board "(\d+)"\]/', file_get_contents($filename), $first_num_in_pbn); + $first_num_in_pbn = $first_num_in_pbn ? intval($first_num_in_pbn[1]) : 1; + + // 1 in teamy -> 1 in pbn; 24 in teamy -> 24 in pbn; 25 in teamy -> 1 in pbn + // if PBN doesn't start with Board 1, it's been adjusted + $num_in_pbn = $board_in_teamy - $file_start_board + $first_num_in_pbn; + + try { + $deal = new Deal($filename, $num_in_pbn); + $deals_by_tables[$file_table] = $deal; + } catch (NoSuchDealNumber $e) { + // ignore if the deal does not exist in the file + } + } + } + return $deals_by_tables; +} diff --git a/tdd/tdd-handrecord-tpl.php b/tdd/tdd-handrecord-tpl.php new file mode 100644 index 0000000..65836cf --- /dev/null +++ b/tdd/tdd-handrecord-tpl.php @@ -0,0 +1,56 @@ + + + + + + + + + + + + + + + + + ability): ?> + + +
+

+ dealer; ?>
+ vuln; ?> +

+ 		format_hand(0); ?> 
format_hand(3); ?><?php echo $this->dealer.'/'.$this->vuln; ?>format_hand(1); ?>
 format_hand(2); ?> 
+ Maksymalna liczba lew: + + + + + + + + + + + + + + + + + + format_ability(0); ?> + + format_ability(1); ?> + + + format_ability(2); ?> + + format_ability(3); ?> + +
 NTSHDC  NTSHDC
 
 
+ Minimax: format_minimax(); ?> +
diff --git a/tdd/tdd-protocol.php b/tdd/tdd-protocol.php new file mode 100644 index 0000000..3dcc0d8 --- /dev/null +++ b/tdd/tdd-protocol.php @@ -0,0 +1,29 @@ +get_filename(); +$len = strlen($html_filename); +$request_uri_ending = substr($_SERVER['REQUEST_URI'], -$len-1); +if($request_uri_ending != '/' . $html_filename) { + die('This script cannot be called directly!'); +} +// + +$deals_by_tables = load_deals_for_tables($prefix, $round, $board); +if (count($deals_by_tables) > 0) { + foreach($deals_by_tables as $table => $deal) { + $protocol->set_deal($table, $deal); + } + echo $protocol->output(); +} +else { + readfile($html_filename); +} diff --git a/tdd/tdd-simple-html-dom.php b/tdd/tdd-simple-html-dom.php new file mode 100644 index 0000000..b3b9ddd --- /dev/null +++ b/tdd/tdd-simple-html-dom.php @@ -0,0 +1,975 @@ + +Acknowledge: Jose Solorzano (https://sourceforge.net/projects/php-html/) +Contributions by: + Yousuke Kumakura (Attribute filters) + Vadim Voituk (Negative indexes supports of "find" method) + Antcs (Constructor with automatically load contents either text or file/url) +Licensed under The MIT License +Redistributions of files must retain the above copyright notice. +*******************************************************************************/ + +define('HDOM_TYPE_ELEMENT', 1); +define('HDOM_TYPE_COMMENT', 2); +define('HDOM_TYPE_TEXT', 3); +define('HDOM_TYPE_ENDTAG', 4); +define('HDOM_TYPE_ROOT', 5); +define('HDOM_TYPE_UNKNOWN', 6); +define('HDOM_QUOTE_DOUBLE', 0); +define('HDOM_QUOTE_SINGLE', 1); +define('HDOM_QUOTE_NO', 3); +define('HDOM_INFO_BEGIN', 0); +define('HDOM_INFO_END', 1); +define('HDOM_INFO_QUOTE', 2); +define('HDOM_INFO_SPACE', 3); +define('HDOM_INFO_TEXT', 4); +define('HDOM_INFO_INNER', 5); +define('HDOM_INFO_OUTER', 6); +define('HDOM_INFO_ENDSPACE',7); + +// helper functions +// ----------------------------------------------------------------------------- +// get html dom form file +function file_get_html() { + $dom = new simple_html_dom; + $args = func_get_args(); + $dom->load(call_user_func_array('file_get_contents', $args), true); + return $dom; +} + +// get html dom form string +function str_get_html($str, $lowercase=true) { + $dom = new simple_html_dom; + $dom->load($str, $lowercase); + return $dom; +} + +// dump html dom tree +function dump_html_tree($node, $show_attr=true, $deep=0) { + $lead = str_repeat(' ', $deep); + echo $lead.$node->tag; + if ($show_attr && count($node->attr)>0) { + echo '('; + foreach($node->attr as $k=>$v) + echo "[$k]=>\"".$node->$k.'", '; + echo ')'; + } + echo "\n"; + + foreach($node->nodes as $c) + dump_html_tree($c, $show_attr, $deep+1); +} + +// get dom form file (deprecated) +function file_get_dom() { + $dom = new simple_html_dom; + $args = func_get_args(); + $dom->load(call_user_func_array('file_get_contents', $args), true); + return $dom; +} + +// get dom form string (deprecated) +function str_get_dom($str, $lowercase=true) { + $dom = new simple_html_dom; + $dom->load($str, $lowercase); + return $dom; +} + +// simple html dom node +// ----------------------------------------------------------------------------- +class simple_html_dom_node { + public $nodetype = HDOM_TYPE_TEXT; + public $tag = 'text'; + public $attr = array(); + public $children = array(); + public $nodes = array(); + public $parent = null; + public $_ = array(); + private $dom = null; + + function __construct($dom) { + $this->dom = $dom; + $dom->nodes[] = $this; + } + + function __destruct() { + $this->clear(); + } + + function __toString() { + return $this->outertext(); + } + + // clean up memory due to php5 circular references memory leak... + function clear() { + $this->dom = null; + $this->nodes = null; + $this->parent = null; + $this->children = null; + } + + // dump node's tree + function dump($show_attr=true) { + dump_html_tree($this, $show_attr); + } + + // returns the parent of node + function parent() { + return $this->parent; + } + + // returns children of node + function children($idx=-1) { + if ($idx===-1) return $this->children; + if (isset($this->children[$idx])) return $this->children[$idx]; + return null; + } + + // returns the first child of node + function first_child() { + if (count($this->children)>0) return $this->children[0]; + return null; + } + + // returns the last child of node + function last_child() { + if (($count=count($this->children))>0) return $this->children[$count-1]; + return null; + } + + // returns the next sibling of node + function next_sibling() { + if ($this->parent===null) return null; + $idx = 0; + $count = count($this->parent->children); + while ($idx<$count && $this!==$this->parent->children[$idx]) + ++$idx; + if (++$idx>=$count) return null; + return $this->parent->children[$idx]; + } + + // returns the previous sibling of node + function prev_sibling() { + if ($this->parent===null) return null; + $idx = 0; + $count = count($this->parent->children); + while ($idx<$count && $this!==$this->parent->children[$idx]) + ++$idx; + if (--$idx<0) return null; + return $this->parent->children[$idx]; + } + + // get dom node's inner html + function innertext() { + if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER]; + if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + + $ret = ''; + foreach($this->nodes as $n) + $ret .= $n->outertext(); + return $ret; + } + + // get dom node's outer text (with tag) + function outertext() { + if ($this->tag==='root') return $this->innertext(); + + // trigger callback + if ($this->dom->callback!==null) + call_user_func_array($this->dom->callback, array($this)); + + if (isset($this->_[HDOM_INFO_OUTER])) return $this->_[HDOM_INFO_OUTER]; + if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + + // render begin tag + $ret = $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]->makeup(); + + // render inner text + if (isset($this->_[HDOM_INFO_INNER])) + $ret .= $this->_[HDOM_INFO_INNER]; + else { + foreach($this->nodes as $n) + $ret .= $n->outertext(); + } + + // render end tag + if(isset($this->_[HDOM_INFO_END]) && $this->_[HDOM_INFO_END]!=0) + $ret .= 'tag.'>'; + return $ret; + } + + // get dom node's plain text + function text() { + if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER]; + switch ($this->nodetype) { + case HDOM_TYPE_TEXT: return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + case HDOM_TYPE_COMMENT: return ''; + case HDOM_TYPE_UNKNOWN: return ''; + } + if (strcasecmp($this->tag, 'script')===0) return ''; + if (strcasecmp($this->tag, 'style')===0) return ''; + + $ret = ''; + foreach($this->nodes as $n) + $ret .= $n->text(); + return $ret; + } + + function xmltext() { + $ret = $this->innertext(); + $ret = str_ireplace('', '', $ret); + return $ret; + } + + // build node's text with tag + function makeup() { + // text, comment, unknown + if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + + $ret = '<'.$this->tag; + $i = -1; + + foreach($this->attr as $key=>$val) { + ++$i; + + // skip removed attribute + if ($val===null || $val===false) + continue; + + $ret .= $this->_[HDOM_INFO_SPACE][$i][0]; + //no value attr: nowrap, checked selected... + if ($val===true) + $ret .= $key; + else { + switch($this->_[HDOM_INFO_QUOTE][$i]) { + case HDOM_QUOTE_DOUBLE: $quote = '"'; break; + case HDOM_QUOTE_SINGLE: $quote = '\''; break; + default: $quote = ''; + } + $ret .= $key.$this->_[HDOM_INFO_SPACE][$i][1].'='.$this->_[HDOM_INFO_SPACE][$i][2].$quote.$val.$quote; + } + } + $ret = $this->dom->restore_noise($ret); + return $ret . $this->_[HDOM_INFO_ENDSPACE] . '>'; + } + + // find elements by css selector + function find($selector, $idx=null) { + $selectors = $this->parse_selector($selector); + if (($count=count($selectors))===0) return array(); + $found_keys = array(); + + // find each selector + for ($c=0; $c<$count; ++$c) { + if (($levle=count($selectors[0]))===0) return array(); + if (!isset($this->_[HDOM_INFO_BEGIN])) return array(); + + $head = array($this->_[HDOM_INFO_BEGIN]=>1); + + // handle descendant selectors, no recursive! + for ($l=0; $l<$levle; ++$l) { + $ret = array(); + foreach($head as $k=>$v) { + $n = ($k===-1) ? $this->dom->root : $this->dom->nodes[$k]; + $n->seek($selectors[$c][$l], $ret); + } + $head = $ret; + } + + foreach($head as $k=>$v) { + if (!isset($found_keys[$k])) + $found_keys[$k] = 1; + } + } + + // sort keys + ksort($found_keys); + + $found = array(); + foreach($found_keys as $k=>$v) + $found[] = $this->dom->nodes[$k]; + + // return nth-element or array + if (is_null($idx)) return $found; + else if ($idx<0) $idx = count($found) + $idx; + return (isset($found[$idx])) ? $found[$idx] : null; + } + + // seek for given conditions + protected function seek($selector, &$ret) { + list($tag, $key, $val, $exp, $no_key) = $selector; + + // xpath index + if ($tag && $key && is_numeric($key)) { + $count = 0; + foreach ($this->children as $c) { + if ($tag==='*' || $tag===$c->tag) { + if (++$count==$key) { + $ret[$c->_[HDOM_INFO_BEGIN]] = 1; + return; + } + } + } + return; + } + + $end = (!empty($this->_[HDOM_INFO_END])) ? $this->_[HDOM_INFO_END] : 0; + if ($end==0) { + $parent = $this->parent; + while (!isset($parent->_[HDOM_INFO_END]) && $parent!==null) { + $end -= 1; + $parent = $parent->parent; + } + $end += $parent->_[HDOM_INFO_END]; + } + + for($i=$this->_[HDOM_INFO_BEGIN]+1; $i<$end; ++$i) { + $node = $this->dom->nodes[$i]; + $pass = true; + + if ($tag==='*' && !$key) { + if (in_array($node, $this->children, true)) + $ret[$i] = 1; + continue; + } + + // compare tag + if ($tag && $tag!=$node->tag && $tag!=='*') {$pass=false;} + // compare key + if ($pass && $key) { + if ($no_key) { + if (isset($node->attr[$key])) $pass=false; + } + else if (!isset($node->attr[$key])) $pass=false; + } + // compare value + if ($pass && $key && $val && $val!=='*') { + $check = $this->match($exp, $val, $node->attr[$key]); + // handle multiple class + if (!$check && strcasecmp($key, 'class')===0) { + foreach(explode(' ',$node->attr[$key]) as $k) { + $check = $this->match($exp, $val, $k); + if ($check) break; + } + } + if (!$check) $pass = false; + } + if ($pass) $ret[$i] = 1; + unset($node); + } + } + + protected function match($exp, $pattern, $value) { + switch ($exp) { + case '=': + return ($value===$pattern); + case '!=': + return ($value!==$pattern); + case '^=': + return preg_match("/^".preg_quote($pattern,'/')."/", $value); + case '$=': + return preg_match("/".preg_quote($pattern,'/')."$/", $value); + case '*=': + if ($pattern[0]=='/') + return preg_match($pattern, $value); + return preg_match("/".$pattern."/i", $value); + } + return false; + } + + protected function parse_selector($selector_string) { + // pattern of CSS selectors, modified from mootools + $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; + preg_match_all($pattern, trim($selector_string).' ', $matches, PREG_SET_ORDER); + $selectors = array(); + $result = array(); + //print_r($matches); + + foreach ($matches as $m) { + $m[0] = trim($m[0]); + if ($m[0]==='' || $m[0]==='/' || $m[0]==='//') continue; + // for borwser grnreated xpath + if ($m[1]==='tbody') continue; + + list($tag, $key, $val, $exp, $no_key) = array($m[1], null, null, '=', false); + if(!empty($m[2])) {$key='id'; $val=$m[2];} + if(!empty($m[3])) {$key='class'; $val=$m[3];} + if(!empty($m[4])) {$key=$m[4];} + if(!empty($m[5])) {$exp=$m[5];} + if(!empty($m[6])) {$val=$m[6];} + + // convert to lowercase + if ($this->dom->lowercase) {$tag=strtolower($tag); $key=strtolower($key);} + //elements that do NOT have the specified attribute + if (isset($key[0]) && $key[0]==='!') {$key=substr($key, 1); $no_key=true;} + + $result[] = array($tag, $key, $val, $exp, $no_key); + if (trim($m[7])===',') { + $selectors[] = $result; + $result = array(); + } + } + if (count($result)>0) + $selectors[] = $result; + return $selectors; + } + + function __get($name) { + if (isset($this->attr[$name])) return $this->attr[$name]; + switch($name) { + case 'outertext': return $this->outertext(); + case 'innertext': return $this->innertext(); + case 'plaintext': return $this->text(); + case 'xmltext': return $this->xmltext(); + default: return array_key_exists($name, $this->attr); + } + } + + function __set($name, $value) { + switch($name) { + case 'outertext': return $this->_[HDOM_INFO_OUTER] = $value; + case 'innertext': + if (isset($this->_[HDOM_INFO_TEXT])) return $this->_[HDOM_INFO_TEXT] = $value; + return $this->_[HDOM_INFO_INNER] = $value; + } + if (!isset($this->attr[$name])) { + $this->_[HDOM_INFO_SPACE][] = array(' ', '', ''); + $this->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_DOUBLE; + } + $this->attr[$name] = $value; + } + + function __isset($name) { + switch($name) { + case 'outertext': return true; + case 'innertext': return true; + case 'plaintext': return true; + } + //no value attr: nowrap, checked selected... + return (array_key_exists($name, $this->attr)) ? true : isset($this->attr[$name]); + } + + function __unset($name) { + if (isset($this->attr[$name])) + unset($this->attr[$name]); + } + + // camel naming conventions + function getAllAttributes() {return $this->attr;} + function getAttribute($name) {return $this->__get($name);} + function setAttribute($name, $value) {$this->__set($name, $value);} + function hasAttribute($name) {return $this->__isset($name);} + function removeAttribute($name) {$this->__set($name, null);} + function getElementById($id) {return $this->find("#$id", 0);} + function getElementsById($id, $idx=null) {return $this->find("#$id", $idx);} + function getElementByTagName($name) {return $this->find($name, 0);} + function getElementsByTagName($name, $idx=null) {return $this->find($name, $idx);} + function parentNode() {return $this->parent();} + function childNodes($idx=-1) {return $this->children($idx);} + function firstChild() {return $this->first_child();} + function lastChild() {return $this->last_child();} + function nextSibling() {return $this->next_sibling();} + function previousSibling() {return $this->prev_sibling();} +} + +// simple html dom parser +// ----------------------------------------------------------------------------- +class simple_html_dom { + public $root = null; + public $nodes = array(); + public $callback = null; + public $lowercase = false; + protected $pos; + protected $doc; + protected $char; + protected $size; + protected $cursor; + protected $parent; + protected $noise = array(); + protected $token_blank = " \t\r\n"; + protected $token_equal = ' =/>'; + protected $token_slash = " />\r\n\t"; + protected $token_attr = ' >'; + // use isset instead of in_array, performance boost about 30%... + protected $self_closing_tags = array('img'=>1, 'br'=>1, 'input'=>1, 'meta'=>1, 'link'=>1, 'hr'=>1, 'base'=>1, 'embed'=>1, 'spacer'=>1); + protected $block_tags = array('root'=>1, 'body'=>1, 'form'=>1, 'div'=>1, 'span'=>1, 'table'=>1); + protected $optional_closing_tags = array( + 'tr'=>array('tr'=>1, 'td'=>1, 'th'=>1), + 'th'=>array('th'=>1), + 'td'=>array('td'=>1), + 'li'=>array('li'=>1), + 'dt'=>array('dt'=>1, 'dd'=>1), + 'dd'=>array('dd'=>1, 'dt'=>1), + 'dl'=>array('dd'=>1, 'dt'=>1), + 'p'=>array('p'=>1), + 'nobr'=>array('nobr'=>1), + ); + + function __construct($str=null) { + if ($str) { + if (preg_match("/^http:\/\//i",$str) || is_file($str)) + $this->load_file($str); + else + $this->load($str); + } + } + + function __destruct() { + $this->clear(); + } + + // load html from string + function load($str, $lowercase=true) { + // prepare + $this->prepare($str, $lowercase); + // strip out comments + $this->remove_noise("''is"); + // strip out cdata + $this->remove_noise("''is", true); + // strip out