From c8a859265b6241be4cda3bac636650fd81ef97d1 Mon Sep 17 00:00:00 2001 From: Craig Davis Date: Sun, 4 Mar 2012 13:35:34 -0600 Subject: [PATCH] Update with initial style implementation --- assets/css/elements.less | 136 +++ assets/css/resume.css | 2 - assets/css/style.css | 177 +++- assets/templates/default.html | 4 +- build/build.php | 12 +- resume/resume.html | 222 +++- resume/resume.md | 56 +- vendor/simpledom/simple_html_dom.php | 1393 ++++++++++++++++++++++++++ 8 files changed, 1984 insertions(+), 18 deletions(-) create mode 100755 assets/css/elements.less delete mode 100644 assets/css/resume.css create mode 100755 vendor/simpledom/simple_html_dom.php diff --git a/assets/css/elements.less b/assets/css/elements.less new file mode 100755 index 0000000..e0a3fb5 --- /dev/null +++ b/assets/css/elements.less @@ -0,0 +1,136 @@ +/*--------------------------------------------------- + LESS Elements 0.6 + --------------------------------------------------- + A set of useful LESS mixins by Dmitry Fadeyev + Special thanks for mixin suggestions to: + Kris Van Herzeele, + Benoit Adam, + Portenart Emile-Victor, + Ryan Faerman + + More info at: http://lesselements.com +-----------------------------------------------------*/ + +.gradient(@color: #F5F5F5, @start: #EEE, @stop: #FFF) { + background: @color; + background: -webkit-gradient(linear, + left bottom, + left top, + color-stop(0, @start), + color-stop(1, @stop)); + background: -ms-linear-gradient(bottom, + @start, + @stop); + background: -moz-linear-gradient(center bottom, + @start 0%, + @stop 100%); +} +.bw-gradient(@color: #F5F5F5, @start: 0, @stop: 255) { + background: @color; + background: -webkit-gradient(linear, + left bottom, + left top, + color-stop(0, rgb(@start,@start,@start)), + color-stop(1, rgb(@stop,@stop,@stop))); + background: -ms-linear-gradient(bottom, + rgb(@start,@start,@start) 0%, + rgb(@start,@start,@start) 100%); + background: -moz-linear-gradient(center bottom, + rgb(@start,@start,@start) 0%, + rgb(@stop,@stop,@stop) 100%); +} +.bordered(@top-color: #EEE, @right-color: #EEE, @bottom-color: #EEE, @left-color: #EEE) { + border-top: solid 1px @top-color; + border-left: solid 1px @left-color; + border-right: solid 1px @right-color; + border-bottom: solid 1px @bottom-color; +} +.drop-shadow(@x-axis: 0, @y-axis: 1px, @blur: 2px, @alpha: 0.1) { + -webkit-box-shadow: @x-axis @y-axis @blur rgba(0, 0, 0, @alpha); + -moz-box-shadow: @x-axis @y-axis @blur rgba(0, 0, 0, @alpha); + box-shadow: @x-axis @y-axis @blur rgba(0, 0, 0, @alpha); +} +.rounded(@radius: 2px) { + -webkit-border-radius: @radius; + -moz-border-radius: @radius; + border-radius: @radius; + -moz-background-clip: padding; -webkit-background-clip: padding-box; background-clip: padding-box; +} +.border-radius(@topright: 0, @bottomright: 0, @bottomleft: 0, @topleft: 0) { + -webkit-border-top-right-radius: @topright; + -webkit-border-bottom-right-radius: @bottomright; + -webkit-border-bottom-left-radius: @bottomleft; + -webkit-border-top-left-radius: @topleft; + -moz-border-radius-topright: @topright; + -moz-border-radius-bottomright: @bottomright; + -moz-border-radius-bottomleft: @bottomleft; + -moz-border-radius-topleft: @topleft; + border-top-right-radius: @topright; + border-bottom-right-radius: @bottomright; + border-bottom-left-radius: @bottomleft; + border-top-left-radius: @topleft; + -moz-background-clip: padding; -webkit-background-clip: padding-box; background-clip: padding-box; +} +.opacity(@opacity: 0.5) { + -moz-opacity: @opacity; + -khtml-opacity: @opacity; + -webkit-opacity: @opacity; + opacity: @opacity; +} +.transition-duration(@duration: 0.2s) { + -moz-transition-duration: @duration; + -webkit-transition-duration: @duration; + transition-duration: @duration; +} +.rotation(@deg:5deg){ + -webkit-transform: rotate(@deg); + -moz-transform: rotate(@deg); + transform: rotate(@deg); +} +.scale(@ratio:1.5){ + -webkit-transform:scale(@ratio); + -moz-transform:scale(@ratio); + transform:scale(@ratio); +} +.transition(@duration:0.2s, @ease:ease-out) { + -webkit-transition: all @duration @ease; + -moz-transition: all @duration @ease; + transition: all @duration @ease; +} +.inner-shadow(@horizontal:0, @vertical:1px, @blur:2px, @alpha: 0.4) { + -webkit-box-shadow: inset @horizontal @vertical @blur rgba(0, 0, 0, @alpha); + -moz-box-shadow: inset @horizontal @vertical @blur rgba(0, 0, 0, @alpha); + box-shadow: inset @horizontal @vertical @blur rgba(0, 0, 0, @alpha); +} +.box-shadow(@arguments) { + -webkit-box-shadow: @arguments; + -moz-box-shadow: @arguments; + box-shadow: @arguments; +} +.columns(@colwidth: 250px, @colcount: 0, @colgap: 50px, @columnRuleColor: #EEE, @columnRuleStyle: solid, @columnRuleWidth: 1px) { + -moz-column-width: @colwidth; + -moz-column-count: @colcount; + -moz-column-gap: @colgap; + -moz-column-rule-color: @columnRuleColor; + -moz-column-rule-style: @columnRuleStyle; + -moz-column-rule-width: @columnRuleWidth; + -webkit-column-width: @colwidth; + -webkit-column-count: @colcount; + -webkit-column-gap: @colgap; + -webkit-column-rule-color: @columnRuleColor; + -webkit-column-rule-style: @columnRuleStyle; + -webkit-column-rule-width: @columnRuleWidth; + column-width: @colwidth; + column-count: @colcount; + column-gap: @colgap; + column-rule-color: @columnRuleColor; + column-rule-style: @columnRuleStyle; + column-rule-width: @columnRuleWidth; +} +.translate(@x:0, @y:0) { + -moz-transform: translate(@x, @y); + -webkit-transform: translate(@x, @y); + -o-transform: translate(@x, @y); + -ms-transform: translate(@x, @y); + transform: translate(@x, @y); +} diff --git a/assets/css/resume.css b/assets/css/resume.css deleted file mode 100644 index 5b9bab2..0000000 --- a/assets/css/resume.css +++ /dev/null @@ -1,2 +0,0 @@ -@import url("css/normalize.css"); -@import url("css/style.css"); \ No newline at end of file diff --git a/assets/css/style.css b/assets/css/style.css index 51ff1c6..9af9bb1 100644 --- a/assets/css/style.css +++ b/assets/css/style.css @@ -1 +1,176 @@ -body { font-family: Georgia; color: #444; } \ No newline at end of file +.clearfix { + zoom: 1; + &:after { + display: block; + visibility: hidden; + height: 0; + clear: both; + content: "."; + } +} + + +body { + font-family: Georgia; + color: #444; + padding: 2em 0; +} + +.container { + width: 1000px; + margin: 0 auto; + padding: 0; + background: whiteSmoke; + border: solid #666; + border-width: 8px 0 2px 0; + text-align: left; +} + +.resume { + position:relative; + padding: 40px 80px; +} + +a { + color: #990003; +} + +a[href$='.pdf'] { + display: inline-block; + background: #666; + color: white; + padding: 6px 50px 6px 12px; + margin-bottom: 6px; + text-decoration: none; +} + +blockquote { + top: 0; + right: 0; + position: absolute; +} + +hr { + display: block; + position: relative; + padding: 0; + margin: 18px auto; + width: 100%; + clear: both; + border: none; + border-top: 1px solid #CCC; + font-size: 1px; + line-height: 0; + overflow: visible; +} + +h1 { + margin: 0; + padding: 0; + font-size: 48px; + text-transform: uppercase; + letter-spacing: 3px; + font-weight: normal; +} +h2 { + margin: 0; + padding: 0; + text-transform: uppercase; + font-style: italic; + letter-spacing: 2px; + font-weight: normal; +} + +h3 { + float: left; + width: 25%; + margin: 0; + padding: 0; + font-style: italic; + font-weight: normal; +} + +h3+p { + margin: 0 0 16px; padding: 0; + float: left; + width: 75%; + display: block; + font-size: 104%; + line-height: 24px; +} + + +ul { + margin: 0; + padding: 0; + list-style: none; +} +ul li { + width: 25%; + margin: 0; + padding: 0; + float: left; +} + +ul dl { + margin: 0; + padding: 0; + dt { + font-size: 122%; + margin-bottom: .25em; + } + dd { + margin: 0 0 1em; + padding: .5em 3em 0 0; + font-size: .8em; + line-height: 1.5em; + } +} + +ol { + margin: 0; + padding: 0; + width: 75%; + display: inline-block; +} + +ol li { + margin: 0; + padding: 0; + border-top: 1px solid #CCCCCC; + width: 33%; + float: left; + list-style: none; + line-height: 24px; + font-size: 14px; +} + +ol li:nth-child(1), ol li:nth-child(2), ol li:nth-child(3) { + border-top: none; +} + + + +dl { + display: inline-block; + width: 75%; + dt { + font-size: 150%; + } + dd { + margin: 0 0 1.5em; + padding: 0; + font-size: 80%; + } + strong { + float: right; + margin-top: -3em; + } + em { + display: block; + font-size: 130%; + margin-bottom: .5em; + font-style: normal; + } + +} \ No newline at end of file diff --git a/assets/templates/default.html b/assets/templates/default.html index 6c143b8..e5f99fd 100644 --- a/assets/templates/default.html +++ b/assets/templates/default.html @@ -15,7 +15,9 @@
-{{{resume}}} +
+ {{{resume}}} +
diff --git a/build/build.php b/build/build.php index bf5066a..989cd42 100644 --- a/build/build.php +++ b/build/build.php @@ -20,6 +20,8 @@ include_once APPLICATION_BASE_PATH . '/vendor/Mustache/Mustache.php'; include_once APPLICATION_BASE_PATH . '/vendor/smartypants/smartypants.php'; include_once APPLICATION_BASE_PATH . '/vendor/markdown-extra/markdown.php'; include_once APPLICATION_BASE_PATH . '/vendor/lessphp/lessc.inc.php'; +include_once APPLICATION_BASE_PATH . '/vendor/simpledom/simple_html_dom.php'; + use Assetic\Asset\AssetCollection; use Assetic\Asset\FileAsset; @@ -56,15 +58,21 @@ $style = $css->dump(); $template = file_get_contents(APPLICATION_BASE_PATH . '/assets/templates/default.html'); $resume = file_get_contents(APPLICATION_BASE_PATH . '/resume/resume.md'); - $resume = Markdown($resume); $resume = SmartyPants($resume); +$html = str_get_html($resume); +$title = sprintf( + '%s | %s', + $html->find('h1', 0)->innertext, + $html->find('h2', 0)->innertext +); + $m = new Mustache; $rendered = $m->render( $template, array( - 'title' => 'TITLE', + 'title' => $title, 'style' => $style, 'resume' => $resume, 'reload' => $refresh_dev diff --git a/resume/resume.html b/resume/resume.html index 67fa036..e78210b 100644 --- a/resume/resume.html +++ b/resume/resume.html @@ -2,9 +2,8 @@ - -TITLE +Craig Davis | Senior PHP Developer, UX Director @@ -158,13 +298,77 @@ body {
-

Craig Davis

+
+

Craig Davis

-

Senior PHP Developer

+

Senior PHP Developer, UX Director

-

craig@there4development.com -(704) 724-3235

+
+

Download PDF
+ craig@there4development.com
+ (999) 888-7777

+
+
+ +

Profile

+ +

Progressively evolve cross-platform ideas before impactful infomediaries. Energistically visualize tactical initiatives before cross-media catalysts for change.

+ +
+ +

Skills

+ +
    +
  • +
    Web Design
    +
    Assertively exploit wireless initiatives rather than synergistic core competencies.
    +
    • +
  • +
    Interface Design
    +
    Credibly streamline mission-critical value with multifunctional functionalities.
    +
    • +
  • +
    Project Direction
    +
    Proven ability to lead and manage a wide variety of design and development projects in team and independent situations.
    +
    • +
+ +
+ +

Technical

+ +
    +
  1. XHTML
    2. +
  2. CSS
    3. +
  3. Javascript
    4. +
  4. Jquery
    5. +
  5. PHP
    6. +
  6. CVS / Subversion
    7. +
  7. OS X
    8. +
  8. Windows XP/Vista
    9. +
  9. Linux
    10. +
+ +
+ +

Experience

+ +
+
Microsoft
+
Principal and Creative Lead +2004-2005 +Intrinsicly transform flexible manufactured products without excellent intellectual capital. Energistically evisculate orthogonal architectures through covalent action items. Assertively incentivize sticky platforms without synergistic materials.
+ +
International Business Machines (IBM)
+
Lead Web Designer +2001-2004 +Globally re-engineer cross-media schemas through viral methods of empowerment. Proactively grow long-term high-impact human capital and highly efficient innovation. Intrinsicly iterate excellent e-tailers with timely e-markets.
+
+ +
+ +
diff --git a/resume/resume.md b/resume/resume.md index b2c6cd6..325b0cf 100644 --- a/resume/resume.md +++ b/resume/resume.md @@ -1,5 +1,55 @@ # Craig Davis -## Senior PHP Developer +## Senior PHP Developer, UX Director -craig@there4development.com -(704) 724-3235 \ No newline at end of file +> [Download PDF](resume.pdf) +> [craig@there4development.com](craig@there4development.com) +> (999) 888-7777 + +------ + +### Profile {#profile} + +Progressively evolve cross-platform ideas before impactful infomediaries. Energistically visualize tactical initiatives before cross-media catalysts for change. + +------ + +### Skills {#skills} + +* Web Design + : Assertively exploit wireless initiatives rather than synergistic core competencies. + +* Interface Design + : Credibly streamline mission-critical value with multifunctional functionalities. + +* Project Direction + : Proven ability to lead and manage a wide variety of design and development projects in team and independent situations. + +------- + +### Technical {#technical} + +1. XHTML +1. CSS +1. Javascript +1. Jquery +1. PHP +1. CVS / Subversion +1. OS X +1. Windows XP/Vista +1. Linux + +------ + +### Experience {#experience} + +Microsoft +: *Principal and Creative Lead* + __2004-2005__ + Intrinsicly transform flexible manufactured products without excellent intellectual capital. Energistically evisculate orthogonal architectures through covalent action items. Assertively incentivize sticky platforms without synergistic materials. + +International Business Machines (IBM) +: *Lead Web Designer* + __2001-2004__ + Globally re-engineer cross-media schemas through viral methods of empowerment. Proactively grow long-term high-impact human capital and highly efficient innovation. Intrinsicly iterate excellent e-tailers with timely e-markets. + +------ \ No newline at end of file diff --git a/vendor/simpledom/simple_html_dom.php b/vendor/simpledom/simple_html_dom.php new file mode 100755 index 0000000..7e50641 --- /dev/null +++ b/vendor/simpledom/simple_html_dom.php @@ -0,0 +1,1393 @@ +size is the "real" number of bytes the dom was created from. + * but for most purposes, it's a really good estimation. + * Paperg - Added the forceTagsClosed to the dom constructor. Forcing tags closed is great for malformed html, but it CAN lead to parsing errors. + * Allow the user to tell us how much they trust the html. + * Paperg add the text and plaintext to the selectors for the find syntax. plaintext implies text in the innertext of a node. text implies that the tag is a text node. + * This allows for us to find tags based on the text they contain. + * Create find_ancestor_tag to see if a tag is - at any level - inside of another specific tag. + * Paperg: added parse_charset so that we know about the character set of the source document. + * NOTE: If the user's system has a routine called get_last_retrieve_url_contents_content_type availalbe, we will assume it's returning the content-type header from the + * last transfer or curl_exec, and we will parse that and use it in preference to any other method of charset detection. + * + * Licensed under The MIT License + * Redistributions of files must retain the above copyright notice. + * + * @author S.C. Chen + * @author John Schlick + * @author Rus Carroll + * @version 1.11 ($Rev: 184 $) + * @package PlaceLocalInclude + * @subpackage simple_html_dom + */ + +/** + * All of the Defines for the classes below. + * @author S.C. Chen + */ +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); +define('DEFAULT_TARGET_CHARSET', 'UTF-8'); +define('DEFAULT_BR_TEXT', "\r\n"); +// helper functions +// ----------------------------------------------------------------------------- +// get html dom from file +// $maxlen is defined in the code as PHP_STREAM_COPY_ALL which is defined as -1. +function file_get_html($url, $use_include_path = false, $context=null, $offset = -1, $maxLen=-1, $lowercase = true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT) +{ + // We DO force the tags to be terminated. + $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $defaultBRText); + // For sourceforge users: uncomment the next line and comment the retreive_url_contents line 2 lines down if it is not already done. + $contents = file_get_contents($url, $use_include_path, $context, $offset); + // Paperg - use our own mechanism for getting the contents as we want to control the timeout. +// $contents = retrieve_url_contents($url); + if (empty($contents)) + { + return false; + } + // The second parameter can force the selectors to all be lowercase. + $dom->load($contents, $lowercase, $stripRN); + return $dom; +} + +// get html dom from string +function str_get_html($str, $lowercase=true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT) +{ + $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $defaultBRText); + if (empty($str)) + { + $dom->clear(); + return false; + } + $dom->load($str, $lowercase, $stripRN); + return $dom; +} + +// dump html dom tree +function dump_html_tree($node, $show_attr=true, $deep=0) +{ + $node->dump($node); +} + +/** + * simple html dom node + * PaperG - added ability for "find" routine to lowercase the value of the selector. + * PaperG - added $tag_start to track the start position of the tag in the total byte index + * + * @package PlaceLocalInclude + */ +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(); + public $tag_start = 0; + 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, $deep=0) + { + $lead = str_repeat(' ', $deep); + + echo $lead.$this->tag; + if ($show_attr && count($this->attr)>0) + { + echo '('; + foreach ($this->attr as $k=>$v) + echo "[$k]=>\"".$this->$k.'", '; + echo ')'; + } + echo "\n"; + + foreach ($this->nodes as $c) + $c->dump($show_attr, $deep+1); + } + + + // Debugging function to dump a single dom node with a bunch of information about it. + function dump_node() + { + echo $this->tag; + if (count($this->attr)>0) + { + echo '('; + foreach ($this->attr as $k=>$v) + { + echo "[$k]=>\"".$this->$k.'", '; + } + echo ')'; + } + if (count($this->attr)>0) + { + echo ' $_ ('; + foreach ($this->_ as $k=>$v) + { + if (is_array($v)) + { + echo "[$k]=>("; + foreach ($v as $k2=>$v2) + { + echo "[$k2]=>\"".$v2.'", '; + } + echo ")"; + } else { + echo "[$k]=>\"".$v.'", '; + } + } + echo ")"; + } + + if (isset($this->text)) + { + echo " text: (" . $this->text . ")"; + } + + echo " children: " . count($this->children); + echo " nodes: " . count($this->nodes); + echo " tag_start: " . $this->tag_start; + echo "\n"; + + } + + // 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]; + } + + // function to locate a specific ancestor tag in the path to the root. + function find_ancestor_tag($tag) + { + global $debugObject; + if (is_object($debugObject)) + { + $debugObject->debugLogEntry(1); + } + + // Start by including ourselves in the comparison. + $returnDom = $this; + + while (!is_null($returnDom)) + { + if (is_object($debugObject)) + { + $debugObject->debugLog(2, "Current tag is: " . $returnDom->tag); + } + + if ($returnDom->tag == $tag) + { + break; + } + $returnDom = $returnDom->parent; + } + return $returnDom; + } + + // get dom node's inner html + function innertext() + { + if (isset($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() + { + global $debugObject; + if (is_object($debugObject)) + { + $text = ''; + if ($this->tag == 'text') + { + if (!empty($this->text)) + { + $text = " with text: " . $this->text; + } + } + $debugObject->debugLog(1, 'Innertext of tag: ' . $this->tag . $text); + } + + if ($this->tag==='root') return $this->innertext(); + + // trigger callback + if ($this->dom && $this->dom->callback!==null) + { + call_user_func_array($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 + if ($this->dom && $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]) + { + $ret = $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]->makeup(); + } else { + $ret = ""; + } + + // render inner text + if (isset($this->_[HDOM_INFO_INNER])) + { + // If it's a br tag... don't return the HDOM_INNER_INFO that we may or may not have added. + if ($this->tag != "br") + { + $ret .= $this->_[HDOM_INFO_INNER]; + } + } else { + if ($this->nodes) + { + foreach ($this->nodes as $n) + { + $ret .= $this->convert_text($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 = ''; + // In rare cases, (always node type 1 or HDOM_TYPE_ELEMENT - observed for some span tags, and some p tags) $this->nodes is set to NULL. + // NOTE: This indicates that there is a problem where it's set to NULL without a clear happening. + // WHY is this happening? + if (!is_null($this->nodes)) + { + foreach ($this->nodes as $n) + { + $ret .= $this->convert_text($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 . $this->_[HDOM_INFO_ENDSPACE] . '>'; + } + + // find elements by css selector + //PaperG - added ability for find to lowercase the value of the selector. + function find($selector, $idx=null, $lowercase=false) + { + $selectors = $this->parse_selector($selector); + if (($count=count($selectors))===0) return array(); + $found_keys = array(); + + // find each selector + for ($c=0; $c<$count; ++$c) + { + // The change on the below line was documented on the sourceforge code tracker id 2788009 + // used to be: if (($levle=count($selectors[0]))===0) return array(); + if (($levle=count($selectors[$c]))===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]; + //PaperG - Pass this optional parameter on to the seek function. + $n->seek($selectors[$c][$l], $ret, $lowercase); + } + $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 + // PaperG - added parameter to allow for case insensitive testing of the value of a selector. + protected function seek($selector, &$ret, $lowercase=false) + { + global $debugObject; + if (is_object($debugObject)) + { + $debugObject->debugLogEntry(1); + } + + list($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])) $pass=false; + } else { + if (($key != "plaintext") && !isset($node->attr[$key])) $pass=false; + } + } + // compare value + if ($pass && $key && $val && $val!=='*') { + // If they have told us that this is a "plaintext" search then we want the plaintext of the node - right? + if ($key == "plaintext") { + // $node->plaintext actually returns $node->text(); + $nodeKeyValue = $node->text(); + } else { + // this is a normal search, we want the value of that attribute of the tag. + $nodeKeyValue = $node->attr[$key]; + } + if (is_object($debugObject)) {$debugObject->debugLog(2, "testing node: " . $node->tag . " for attribute: " . $key . $exp . $val . " where nodes value is: " . $nodeKeyValue);} + + //PaperG - If lowercase is set, do a case insensitive test of the value of the selector. + if ($lowercase) { + $check = $this->match($exp, strtolower($val), strtolower($nodeKeyValue)); + } else { + $check = $this->match($exp, $val, $nodeKeyValue); + } + if (is_object($debugObject)) {$debugObject->debugLog(2, "after match: " . ($check ? "true" : "false"));} + + // handle multiple class + if (!$check && strcasecmp($key, 'class')===0) { + foreach (explode(' ',$node->attr[$key]) as $k) { + // Without this, there were cases where leading, trailing, or double spaces lead to our comparing blanks - bad form. + if (!empty($k)) { + if ($lowercase) { + $check = $this->match($exp, strtolower($val), strtolower($k)); + } else { + $check = $this->match($exp, $val, $k); + } + if ($check) break; + } + } + } + if (!$check) $pass = false; + } + if ($pass) $ret[$i] = 1; + unset($node); + } + // It's passed by reference so this is actually what this function returns. + if (is_object($debugObject)) {$debugObject->debugLog(1, "EXIT - ret: ", $ret);} + } + + protected function match($exp, $pattern, $value) { + global $debugObject; + if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} + + switch ($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) { + global $debugObject; + if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} + + // pattern of CSS selectors, modified from mootools + // Paperg: Add the colon to the attrbute, so that it properly finds like google does. + // Note: if you try to look at this attribute, yo MUST use getAttribute since $dom->x:y will fail the php syntax check. +// Notice the \[ starting the attbute? and the @? following? This implies that an attribute can begin with an @ sign that is not captured. +// This implies that an html attribute specifier may start with an @ sign that is NOT captured by the expression. +// farther study is required to determine of this should be documented or removed. +// $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; + $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-:]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; + preg_match_all($pattern, trim($selector_string).' ', $matches, PREG_SET_ORDER); + if (is_object($debugObject)) {$debugObject->debugLog(2, "Matches Array: ", $matches);} + + $selectors = array(); + $result = array(); + //print_r($matches); + + foreach ($matches as $m) { + $m[0] = trim($m[0]); + if ($m[0]==='' || $m[0]==='/' || $m[0]==='//') continue; + // for browser generated xpath + if ($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 $this->convert_text($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]); + } + + // PaperG - Function to convert the text from one character set to another if the two sets are not the same. + function convert_text($text) { + global $debugObject; + if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} + + $converted_text = $text; + + $sourceCharset = ""; + $targetCharset = ""; + if ($this->dom) { + $sourceCharset = strtoupper($this->dom->_charset); + $targetCharset = strtoupper($this->dom->_target_charset); + } + if (is_object($debugObject)) {$debugObject->debugLog(3, "source charset: " . $sourceCharset . " target charaset: " . $targetCharset);} + + if (!empty($sourceCharset) && !empty($targetCharset) && (strcasecmp($sourceCharset, $targetCharset) != 0)) + { + // Check if the reported encoding could have been incorrect and the text is actually already UTF-8 + if ((strcasecmp($targetCharset, 'UTF-8') == 0) && ($this->is_utf8($text))) + { + $converted_text = $text; + } + else + { + $converted_text = iconv($sourceCharset, $targetCharset, $text); + } + } + + return $converted_text; + } + + function is_utf8($string) + { + return (utf8_encode(utf8_decode($string)) == $string); + } + + // 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 + * Paperg - in the find routine: allow us to specify that we want case insensitive testing of the value of the selector. + * Paperg - change $size from protected to public so we can easily access it + * Paperg - added ForceTagsClosed in the constructor which tells us whether we trust the html or not. Default is to NOT trust it. + * + * @package PlaceLocalInclude + */ +class simple_html_dom { + public $root = null; + public $nodes = array(); + public $callback = null; + public $lowercase = false; + public $size; + protected $pos; + protected $doc; + protected $char; + 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 = ' >'; + protected $_charset = ''; + protected $_target_charset = ''; + protected $default_br_text = ""; + + // 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); + // Known sourceforge issue #2977341 + // B tags that are not closed cause us to return everything to the end of the document. + protected $optional_closing_tags = array( + 'tr'=>array('tr'=>1, 'td'=>1, 'th'=>1), + 'th'=>array('th'=>1), + 'td'=>array('td'=>1), + 'li'=>array('li'=>1), + 'dt'=>array('dt'=>1, 'dd'=>1), + 'dd'=>array('dd'=>1, 'dt'=>1), + 'dl'=>array('dd'=>1, 'dt'=>1), + 'p'=>array('p'=>1), + 'nobr'=>array('nobr'=>1), + 'b'=>array('b'=>1), + ); + + function __construct($str=null, $lowercase=true, $forceTagsClosed=true, $target_charset=DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT) { + if ($str) { + if (preg_match("/^http:\/\//i",$str) || is_file($str)) + $this->load_file($str); + else + $this->load($str, $lowercase, $stripRN, $defaultBRText); + } + // Forcing tags to be closed implies that we don't trust the html, but it can lead to parsing errors if we SHOULD trust the html. + if (!$forceTagsClosed) { + $this->optional_closing_array=array(); + } + $this->_target_charset = $target_charset; + } + + function __destruct() { + $this->clear(); + } + + // load html from string + function load($str, $lowercase=true, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT) { + global $debugObject; + + // prepare + $this->prepare($str, $lowercase, $stripRN, $defaultBRText); + // strip out comments + $this->remove_noise("''is"); + // strip out cdata + $this->remove_noise("''is", true); + // Per sourceforge http://sourceforge.net/tracker/?func=detail&aid=2949097&group_id=218559&atid=1044037 + // Script tags removal now preceeds style tag removal. + // strip out