From 6212acfc813781501177674baa3139ceef62f78f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Tue, 15 Apr 2014 21:49:00 +0200 Subject: [fix] rss feed content type set to text/xml #636 --- inc/3rdparty/libraries/feedwriter/FeedWriter.php | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) (limited to 'inc/3rdparty/libraries') diff --git a/inc/3rdparty/libraries/feedwriter/FeedWriter.php b/inc/3rdparty/libraries/feedwriter/FeedWriter.php index df4c8b4b..79639c0c 100755 --- a/inc/3rdparty/libraries/feedwriter/FeedWriter.php +++ b/inc/3rdparty/libraries/feedwriter/FeedWriter.php @@ -89,18 +89,11 @@ define('JSONP', 3, true); */ public function genarateFeed() { - if ($this->version == RSS2) { -// header('Content-type: text/xml; charset=UTF-8'); - // this line prevents Chrome 20 from prompting download - // used by Google: https://news.google.com/news/feeds?ned=us&topic=b&output=rss -// header('X-content-type-options: nosniff'); - } elseif ($this->version == JSON) { -// header('Content-type: application/json; charset=UTF-8'); - $this->json = new stdClass(); - } elseif ($this->version == JSONP) { -// header('Content-type: application/javascript; charset=UTF-8'); - $this->json = new stdClass(); - } + header('Content-type: text/xml; charset=UTF-8'); + // this line prevents Chrome 20 from prompting download + // used by Google: https://news.google.com/news/feeds?ned=us&topic=b&output=rss + header('X-content-type-options: nosniff'); + $this->printHead(); $this->printChannels(); $this->printItems(); -- cgit v1.2.3 From 87090d8ae7582708d20f3c09fb37d780af860bcd Mon Sep 17 00:00:00 2001 From: tcit Date: Thu, 24 Apr 2014 03:04:02 +0200 Subject: Added epub export function --- .../libraries/PHPePub/EPub.HtmlEntities.php | 266 +++ inc/3rdparty/libraries/PHPePub/EPub.NCX.php | 782 +++++++ inc/3rdparty/libraries/PHPePub/EPub.OPF.php | 1226 ++++++++++ inc/3rdparty/libraries/PHPePub/EPub.php | 2429 ++++++++++++++++++++ .../libraries/PHPePub/EPubChapterSplitter.php | 201 ++ inc/3rdparty/libraries/PHPePub/Logger.php | 92 + inc/3rdparty/libraries/PHPePub/Zip.php | 818 +++++++ .../libraries/PHPePub/lib.uuid.LICENCE.txt | 31 + inc/3rdparty/libraries/PHPePub/lib.uuid.php | 314 +++ 9 files changed, 6159 insertions(+) create mode 100644 inc/3rdparty/libraries/PHPePub/EPub.HtmlEntities.php create mode 100644 inc/3rdparty/libraries/PHPePub/EPub.NCX.php create mode 100644 inc/3rdparty/libraries/PHPePub/EPub.OPF.php create mode 100644 inc/3rdparty/libraries/PHPePub/EPub.php create mode 100644 inc/3rdparty/libraries/PHPePub/EPubChapterSplitter.php create mode 100644 inc/3rdparty/libraries/PHPePub/Logger.php create mode 100644 inc/3rdparty/libraries/PHPePub/Zip.php create mode 100644 inc/3rdparty/libraries/PHPePub/lib.uuid.LICENCE.txt create mode 100644 inc/3rdparty/libraries/PHPePub/lib.uuid.php (limited to 'inc/3rdparty/libraries') diff --git a/inc/3rdparty/libraries/PHPePub/EPub.HtmlEntities.php b/inc/3rdparty/libraries/PHPePub/EPub.HtmlEntities.php new file mode 100644 index 00000000..376b6133 --- /dev/null +++ b/inc/3rdparty/libraries/PHPePub/EPub.HtmlEntities.php @@ -0,0 +1,266 @@ + \ No newline at end of file diff --git a/inc/3rdparty/libraries/PHPePub/EPub.NCX.php b/inc/3rdparty/libraries/PHPePub/EPub.NCX.php new file mode 100644 index 00000000..e5da05cd --- /dev/null +++ b/inc/3rdparty/libraries/PHPePub/EPub.NCX.php @@ -0,0 +1,782 @@ + + * @copyright 2009-2014 A. Grandt + * @license GNU LGPL, Attribution required for commercial implementations, requested for everything else. + * @version 3.20 + */ +class Ncx { + const _VERSION = 3.20; + + const MIMETYPE = "application/x-dtbncx+xml"; + + private $bookVersion = EPub::BOOK_VERSION_EPUB2; + + private $navMap = NULL; + private $uid = NULL; + private $meta = array(); + private $docTitle = NULL; + private $docAuthor = NULL; + + private $currentLevel = NULL; + private $lastLevel = NULL; + + private $languageCode = "en"; + private $writingDirection = EPub::DIRECTION_LEFT_TO_RIGHT; + + public $chapterList = array(); + public $referencesTitle = "Guide"; + public $referencesClass = "references"; + public $referencesId = "references"; + public $referencesList = array(); + public $referencesName = array(); + public $referencesOrder = NULL; + + /** + * Class constructor. + * + * @param string $uid + * @param string $docTitle + * @param string $docAuthor + * @param string $languageCode + * @param string $writingDirection + */ + function __construct($uid = NULL, $docTitle = NULL, $docAuthor = NULL, $languageCode = "en", $writingDirection = EPub::DIRECTION_LEFT_TO_RIGHT) { + $this->navMap = new NavMap($writingDirection); + $this->currentLevel = $this->navMap; + $this->setUid($uid); + $this->setDocTitle($docTitle); + $this->setDocAuthor($docAuthor); + $this->setLanguageCode($languageCode); + $this->setWritingDirection($writingDirection); + } + + /** + * Class destructor + * + * @return void + */ + function __destruct() { + unset($this->bookVersion, $this->navMap, $this->uid, $this->meta); + unset($this->docTitle, $this->docAuthor, $this->currentLevel, $this->lastLevel); + unset($this->languageCode, $this->writingDirection, $this->chapterList, $this->referencesTitle); + unset($this->referencesClass, $this->referencesId, $this->referencesList, $this->referencesName); + unset($this->referencesOrder); + } + + /** + * + * Enter description here ... + * + * @param string $bookVersion + */ + function setVersion($bookVersion) { + $this->bookVersion = is_string($bookVersion) ? trim($bookVersion) : EPub::BOOK_VERSION_EPUB2; + } + + /** + * + * @return bool TRUE if the book is set to type ePub 2 + */ + function isEPubVersion2() { + return $this->bookVersion === EPub::BOOK_VERSION_EPUB2; + } + + /** + * + * Enter description here ... + * + * @param string $uid + */ + function setUid($uid) { + $this->uid = is_string($uid) ? trim($uid) : NULL; + } + + /** + * + * Enter description here ... + * + * @param string $docTitle + */ + function setDocTitle($docTitle) { + $this->docTitle = is_string($docTitle) ? trim($docTitle) : NULL; + } + + /** + * + * Enter description here ... + * + * @param string $docAuthor + */ + function setDocAuthor($docAuthor) { + $this->docAuthor = is_string($docAuthor) ? trim($docAuthor) : NULL; + } + + /** + * + * Enter description here ... + * + * @param string $languageCode + */ + function setLanguageCode($languageCode) { + $this->languageCode = is_string($languageCode) ? trim($languageCode) : "en"; + } + + /** + * + * Enter description here ... + * + * @param string $writingDirection + */ + function setWritingDirection($writingDirection) { + $this->writingDirection = is_string($writingDirection) ? trim($writingDirection) : EPub::DIRECTION_LEFT_TO_RIGHT; + } + + /** + * + * Enter description here ... + * + * @param NavMap $navMap + */ + function setNavMap($navMap) { + if ($navMap != NULL && is_object($navMap) && get_class($navMap) === "NavMap") { + $this->navMap = $navMap; + } + } + + /** + * Add one chapter level. + * + * Subsequent chapters will be added to this level. + * + * @param string $navTitle + * @param string $navId + * @param string $navClass + * @param string $isNavHidden + * @param string $writingDirection + * @return NavPoint + */ + function subLevel($navTitle = NULL, $navId = NULL, $navClass = NULL, $isNavHidden = FALSE, $writingDirection = NULL) { + $navPoint = FALSE; + if (isset($navTitle) && isset($navClass)) { + $navPoint = new NavPoint($navTitle, NULL, $navId, $navClass, $isNavHidden, $writingDirection); + $this->addNavPoint($navPoint); + } + if ($this->lastLevel !== NULL) { + $this->currentLevel = $this->lastLevel; + } + return $navPoint; + } + + /** + * Step back one chapter level. + * + * Subsequent chapters will be added to this chapters parent level. + */ + function backLevel() { + $this->lastLevel = $this->currentLevel; + $this->currentLevel = $this->currentLevel->getParent(); + } + + /** + * Step back to the root level. + * + * Subsequent chapters will be added to the rooot NavMap. + */ + function rootLevel() { + $this->lastLevel = $this->currentLevel; + $this->currentLevel = $this->navMap; + } + + /** + * Step back to the given level. + * Useful for returning to a previous level from deep within the structure. + * Values below 2 will have the same effect as rootLevel() + * + * @param int $newLevel + */ + function setCurrentLevel($newLevel) { + if ($newLevel <= 1) { + $this->rootLevel(); + } else { + while ($this->currentLevel->getLevel() > $newLevel) { + $this->backLevel(); + } + } + } + + /** + * Get current level count. + * The indentation of the current structure point. + * + * @return current level count; + */ + function getCurrentLevel() { + return $this->currentLevel->getLevel(); + } + + /** + * Add child NavPoints to current level. + * + * @param NavPoint $navPoint + */ + function addNavPoint($navPoint) { + $this->lastLevel = $this->currentLevel->addNavPoint($navPoint); + } + + /** + * + * Enter description here ... + * + * @return NavMap + */ + function getNavMap() { + return $this->navMap; + } + + /** + * + * Enter description here ... + * + * @param string $name + * @param string $content + */ + function addMetaEntry($name, $content) { + $name = is_string($name) ? trim($name) : NULL; + $content = is_string($content) ? trim($content) : NULL; + + if ($name != NULL && $content != NULL) { + $this->meta[] = array($name => $content); + } + } + + /** + * + * Enter description here ... + * + * @return string + */ + function finalize() { + $nav = $this->navMap->finalize(); + + $ncx = "\n"; + if ($this->isEPubVersion2()) { + $ncx .= "\n"; + } + $ncx .= "languageCode . "\" dir=\"" . $this->writingDirection . "\">\n" + . "\t\n" + . "\t\tuid . "\" />\n" + . "\t\tnavMap->getNavLevels() . "\" />\n" + . "\t\t\n" + . "\t\t\n"; + + if (sizeof($this->meta)) { + foreach ($this->meta as $metaEntry) { + list($name, $content) = each($metaEntry); + $ncx .= "\t\t\n"; + } + } + + $ncx .= "\t\n\n\t\n\t\t" + . $this->docTitle + . "\n\t\n\n\t\n\t\t" + . $this->docAuthor + . "\n\t\n\n" + . $nav; + + return $ncx . "\n"; + } + + /** + * + * @param string $title + * @param string $cssFileName + * @return string + */ + function finalizeEPub3($title = "Table of Contents", $cssFileName = NULL) { + $end = "\n" + . "languageCode . "\" lang=\"" . $this->languageCode . "\" dir=\"" . $this->writingDirection . "\">\n" + . "\t\n" + . "\t\t" . $this->docTitle . "\n" + . "\t\t\n"; + if ($cssFileName !== NULL) { + $end .= "\t\t\n"; + } + $end .= "\t\n" + . "\t\n" + . "\t\t
\n" + . "\t\t\t

" . $title . "

\n" + . "\t\t
\n" + . $this->navMap->finalizeEPub3() + . $this->finalizeEPub3Landmarks() + . "\t\n" + . "\n"; + + return $end; + } + + /** + * Build the references for the ePub 2 toc. + * These are merely reference pages added to the end of the navMap though. + * + * @return string + */ + function finalizeReferences() { + if (isset($this->referencesList) && sizeof($this->referencesList) > 0) { + $this->rootLevel(); + $this->subLevel($this->referencesTitle, $this->referencesId, $this->referencesClass); + $refId = 1; + while (list($item, $descriptive) = each($this->referencesOrder)) { + if (array_key_exists($item, $this->referencesList)) { + $name = (empty($this->referencesName[$item]) ? $descriptive : $this->referencesName[$item]); + $navPoint = new NavPoint($name, $this->referencesList[$item], "ref-" . $refId++); + $this->addNavPoint($navPoint); + } + } + } + } + + /** + * Build the landmarks for the ePub 3 toc. + * @return string + */ + function finalizeEPub3Landmarks() { + $lm = ""; + if (isset($this->referencesList) && sizeof($this->referencesList) > 0) { + $lm = "\t\t\t\n"; + } + return $lm; + } +} + +/** + * ePub NavMap class + */ +class NavMap { + const _VERSION = 3.00; + + private $navPoints = array(); + private $navLevels = 0; + private $writingDirection = NULL; + + /** + * Class constructor. + * + * @return void + */ + function __construct($writingDirection = NULL) { + $this->setWritingDirection($writingDirection); + } + + /** + * Class destructor + * + * @return void + */ + function __destruct() { + unset($this->navPoints, $this->navLevels, $this->writingDirection); + } + + /** + * Set the writing direction to be used for this NavPoint. + * + * @param string $writingDirection + */ + function setWritingDirection($writingDirection) { + $this->writingDirection = isset($writingDirection) && is_string($writingDirection) ? trim($writingDirection) : NULL; + } + + function getWritingDirection() { + return $this->writingDirection; + } + + /** + * Add a navPoint to the root of the NavMap. + * + * @param NavPoint $navPoint + * @return NavMap + */ + function addNavPoint($navPoint) { + if ($navPoint != NULL && is_object($navPoint) && get_class($navPoint) === "NavPoint") { + $navPoint->setParent($this); + if ($navPoint->getWritingDirection() == NULL) { + $navPoint->setWritingDirection($this->writingDirection); + } + $this->navPoints[] = $navPoint; + return $navPoint; + } + return $this; + } + + /** + * The final max depth for the "dtb:depth" meta attribute + * Only available after finalize have been called. + * + * @return number + */ + function getNavLevels() { + return $this->navLevels+1; + } + + function getLevel() { + return 1; + } + + function getParent() { + return $this; + } + + /** + * Finalize the navMap, the final max depth for the "dtb:depth" meta attribute can be retrieved with getNavLevels after finalization + * + */ + function finalize() { + $playOrder = 0; + $this->navLevels = 0; + + $nav = "\t\n"; + if (sizeof($this->navPoints) > 0) { + $this->navLevels++; + foreach ($this->navPoints as $navPoint) { + $retLevel = $navPoint->finalize($nav, $playOrder, 0); + if ($retLevel > $this->navLevels) { + $this->navLevels = $retLevel; + } + } + } + return $nav . "\t\n"; + } + + /** + * Finalize the navMap, the final max depth for the "dtb:depth" meta attribute can be retrieved with getNavLevels after finalization + * + */ + function finalizeEPub3() { + $playOrder = 0; + $level = 0; + $this->navLevels = 0; + + $nav = "\t\t\n"; + } +} + +/** + * ePub NavPoint class + */ +class NavPoint { + const _VERSION = 3.00; + + private $label = NULL; + private $contentSrc = NULL; + private $id = NULL; + private $navClass = NULL; + private $isNavHidden = FALSE; + private $navPoints = array(); + private $parent = NULL; + + /** + * Class constructor. + * + * All three attributes are mandatory, though if ID is set to null (default) the value will be generated. + * + * @param string $label + * @param string $contentSrc + * @param string $id + * @param string $navClass + * @param bool $isNavHidden + * @param string $writingDirection + */ + function __construct($label, $contentSrc = NULL, $id = NULL, $navClass = NULL, $isNavHidden = FALSE, $writingDirection = NULL) { + $this->setLabel($label); + $this->setContentSrc($contentSrc); + $this->setId($id); + $this->setNavClass($navClass); + $this->setNavHidden($isNavHidden); + $this->setWritingDirection($writingDirection); + } + + /** + * Class destructor + * + * @return void + */ + function __destruct() { + unset($this->label, $this->contentSrc, $this->id, $this->navClass); + unset($this->isNavHidden, $this->navPoints, $this->parent); + } + + /** + * Set the Text label for the NavPoint. + * + * The label is mandatory. + * + * @param string $label + */ + function setLabel($label) { + $this->label = is_string($label) ? trim($label) : NULL; + } + + /** + * Get the Text label for the NavPoint. + * + * @return string Label + */ + function getLabel() { + return $this->label; + } + + /** + * Set the src reference for the NavPoint. + * + * The src is mandatory for ePub 2. + * + * @param string $contentSrc + */ + function setContentSrc($contentSrc) { + $this->contentSrc = isset($contentSrc) && is_string($contentSrc) ? trim($contentSrc) : NULL; + } + + /** + * Get the src reference for the NavPoint. + * + * @return string content src url. + */ + function getContentSrc() { + return $this->contentSrc; + } + /** + * Set the parent for this NavPoint. + * + * @param NavPoint or NavMap $parent + */ + function setParent($parent) { + if ($parent != NULL && is_object($parent) && + (get_class($parent) === "NavPoint" || get_class($parent) === "NavMap") ) { + $this->parent = $parent; + } + } + + /** + * Get the parent to this NavPoint. + * + * @return NavPoint, or NavMap if the parent is the root. + */ + function getParent() { + return $this->parent; + } + + /** + * Get the current level. 1 = document root. + * + * @return int level + */ + function getLevel() { + return $this->parent === NULL ? 1 : $this->parent->getLevel()+1; + } + + /** + * Set the id for the NavPoint. + * + * The id must be unique, and is mandatory. + * + * @param string $id + */ + function setId($id) { + $this->id = is_string($id) ? trim($id) : NULL; + } + + /** + * Set the class to be used for this NavPoint. + * + * @param string $navClass + */ + function setNavClass($navClass) { + $this->navClass = isset($navClass) && is_string($navClass) ? trim($navClass) : NULL; + } + + /** + * Set the class to be used for this NavPoint. + * + * @param string $navClass + */ + function setNavHidden($isNavHidden) { + $this->isNavHidden = $isNavHidden === TRUE; + } + + /** + * Set the writing direction to be used for this NavPoint. + * + * @param string $writingDirection + */ + function setWritingDirection($writingDirection) { + $this->writingDirection = isset($writingDirection) && is_string($writingDirection) ? trim($writingDirection) : NULL; + } + + function getWritingDirection() { + return $this->writingDirection; + } + + /** + * Add child NavPoints for multi level NavMaps. + * + * @param NavPoint $navPoint + */ + function addNavPoint($navPoint) { + if ($navPoint != NULL && is_object($navPoint) && get_class($navPoint) === "NavPoint") { + $navPoint->setParent($this); + if ($navPoint->getWritingDirection() == NULL) { + $navPoint->setWritingDirection($this->writingDirection); + } + $this->navPoints[] = $navPoint; + return $navPoint; + } + return $this; + } + + /** + * + * Enter description here ... + * + * @param string $nav + * @param int $playOrder + * @param int $level + * @return int + */ + function finalize(&$nav = "", &$playOrder = 0, $level = 0) { + $maxLevel = $level; + $levelAdjust = 0; + + if ($this->isNavHidden) { + return $maxLevel; + } + + if (isset($this->contentSrc)) { + $playOrder++; + + if ($this->id == NULL) { + $this->id = "navpoint-" . $playOrder; + } + $nav .= str_repeat("\t", $level) . "\t\tid . "\" playOrder=\"" . $playOrder . "\">\n" + . str_repeat("\t", $level) . "\t\t\t\n" + . str_repeat("\t", $level) . "\t\t\t\t" . $this->label . "\n" + . str_repeat("\t", $level) . "\t\t\t\n" + . str_repeat("\t", $level) . "\t\t\tcontentSrc . "\" />\n"; + } else { + $levelAdjust++; + } + + if (sizeof($this->navPoints) > 0) { + $maxLevel++; + foreach ($this->navPoints as $navPoint) { + $retLevel = $navPoint->finalize($nav, $playOrder, ($level+1+$levelAdjust)); + if ($retLevel > $maxLevel) { + $maxLevel = $retLevel; + } + } + } + + if (isset($this->contentSrc)) { + $nav .= str_repeat("\t", $level) . "\t\t\n"; + } + + return $maxLevel; + } + + /** + * + * Enter description here ... + * + * @param string $nav + * @param int $playOrder + * @param int $level + * @return int + */ + function finalizeEPub3(&$nav = "", &$playOrder = 0, $level = 0, $subLevelClass = NULL, $subLevelHidden = FALSE) { + $maxLevel = $level; + + if ($this->id == NULL) { + $this->id = "navpoint-" . $playOrder; + } + $indent = str_repeat("\t", $level) . "\t\t\t\t"; + + $nav .= $indent . "
  • id . "\""; + if (isset($this->writingDirection)) { + $nav .= " dir=\"" . $this->writingDirection . "\""; + } + $nav .= ">\n"; + + if (isset($this->contentSrc)) { + $nav .= $indent . "\tcontentSrc . "\">" . $this->label . "\n"; + } else { + $nav .= $indent . "\t" . $this->label . "\n"; + } + + if (sizeof($this->navPoints) > 0) { + $maxLevel++; + + $nav .= $indent . "\t
      navPoints as $navPoint) { + $retLevel = $navPoint->finalizeEPub3($nav, $playOrder, ($level+2), $subLevelClass, $subLevelHidden); + if ($retLevel > $maxLevel) { + $maxLevel = $retLevel; + } + } + $nav .= $indent . "\t
    \n"; + } + + $nav .= $indent . "
    • \n"; + + return $maxLevel; + } +} +?> \ No newline at end of file diff --git a/inc/3rdparty/libraries/PHPePub/EPub.OPF.php b/inc/3rdparty/libraries/PHPePub/EPub.OPF.php new file mode 100644 index 00000000..803a2108 --- /dev/null +++ b/inc/3rdparty/libraries/PHPePub/EPub.OPF.php @@ -0,0 +1,1226 @@ + + * @copyright 2009-2014 A. Grandt + * @license GNU LGPL, Attribution required for commercial implementations, requested for everything else. + * @version 3.20 + */ +class Opf { + const _VERSION = 3.20; + + /* Core Media types. + * These types are the only guaranteed mime types any ePub reader must understand. + * Any other type muse define a fall back whose fallback chain will end in one of these. + */ + const TYPE_GIF = "image/gif"; + const TYPE_JPEG = "image/jpeg"; + const TYPE_PNG = "image/png"; + const TYPE_SVG = "image/svg+xml"; + const TYPE_XHTML = "application/xhtml+xml"; + const TYPE_DTBOOK = "application/x-dtbook+xml"; + const TYPE_CSS = "text/css"; + const TYPE_XML = "application/xml"; + const TYPE_OEB1_DOC = "text/x-oeb1-document"; // Deprecated + const TYPE_OEB1_CSS = "text/x-oeb1-css"; // Deprecated + const TYPE_NCX = "application/x-dtbncx+xml"; + + private $bookVersion = EPub::BOOK_VERSION_EPUB2; + private $ident = "BookId"; + + public $date = NULL; + public $metadata = NULL; + public $manifest = NULL; + public $spine = NULL; + public $guide = NULL; + + /** + * Class constructor. + * + * @return void + */ + function __construct($ident = "BookId", $bookVersion = EPub::BOOK_VERSION_EPUB2) { + $this->setIdent($ident); + $this->setVersion($bookVersion); + $this->metadata = new Metadata(); + $this->manifest = new Manifest(); + $this->spine = new Spine(); + $this->guide = new Guide(); + } + + /** + * Class destructor + * + * @return void + */ + function __destruct() { + unset ($this->bookVersion, $this->ident, $this->date, $this->metadata, $this->manifest, $this->spine, $this->guide); + } + + /** + * + * Enter description here ... + * + * @param string $ident + */ + function setVersion($bookVersion) { + $this->bookVersion = is_string($bookVersion) ? trim($bookVersion) : EPub::BOOK_VERSION_EPUB2; + } + + function isEPubVersion2() { + return $this->bookVersion === EPub::BOOK_VERSION_EPUB2; + } + + /** + * + * Enter description here ... + * + * @param string $ident + */ + function setIdent($ident = "BookId") { + $this->ident = is_string($ident) ? trim($ident) : "BookId"; + } + + /** + * + * Enter description here ... + * + * @return string + */ + function finalize() { + $opf = "\n" + . "ident . "\" version=\"" . $this->bookVersion . "\">\n"; + + $opf .= $this->metadata->finalize($this->bookVersion, $this->date); + $opf .= $this->manifest->finalize($this->bookVersion); + $opf .= $this->spine->finalize(); + + if ($this->guide->length() > 0) { + $opf .= $this->guide->finalize(); + } + + return $opf . "\n"; + } + + // Convenience functions: + + /** + * + * Enter description here ... + * + * @param string $title + * @param string $language + * @param string $identifier + * @param string $identifierScheme + */ + function initialize($title, $language, $identifier, $identifierScheme) { + $this->metadata->addDublinCore(new DublinCore("title", $title)); + $this->metadata->addDublinCore(new DublinCore("language", $language)); + + $dc = new DublinCore("identifier", $identifier); + $dc->addAttr("id", $this->ident); + $dc->addOpfAttr("scheme", $identifierScheme); + $this->metadata->addDublinCore($dc); + } + + /** + * + * Enter description here ... + * + * @param string $id + * @param string $href + * @param string $mediaType + */ + function addItem($id, $href, $mediaType, $properties = NULL) { + $this->manifest->addItem(new Item($id, $href, $mediaType, $properties)); + } + + /** + * + * Enter description here ... + * + * @param string $idref + * @param bool $linear + */ + function addItemRef($idref, $linear = TRUE) { + $this->spine->addItemref(new Itemref($idref, $linear)); + } + + /** + * + * Enter description here ... + * + * @param string $type + * @param string $title + * @param string $href + */ + function addReference($type, $title, $href) { + $this->guide->addReference(new Reference($type, $title, $href)); + } + + /** + * + * Enter description here ... + * + * @param string $name + * @param string $value + */ + function addDCMeta($name, $value) { + $this->metadata->addDublinCore(new DublinCore($name, $value)); + } + + /** + * + * Enter description here ... + * + * @param string $name + * @param string $content + */ + function addMeta($name, $content) { + $this->metadata->addMeta($name, $content); + } + + /** + * + * Enter description here ... + * + * @param string $name + * @param string $fileAs + * @param string $role Use the MarcCode constants + */ + function addCreator($name, $fileAs = NULL, $role = NULL) { + $dc = new DublinCore(DublinCore::CREATOR, trim($name)); + + if ($fileAs !== NULL) { + $dc->addOpfAttr("file-as", trim($fileAs)); + } + + if ($role !== NULL) { + $dc->addOpfAttr("role", trim($role)); + } + + $this->metadata->addDublinCore($dc); + } + + /** + * + * Enter description here ... + * + * @param string $name + * @param string $fileAs + * @param string $role Use the MarcCode constants + */ + function addColaborator($name, $fileAs = NULL, $role = NULL) { + $dc = new DublinCore(DublinCore::CONTRIBUTOR, trim($name)); + + if ($fileAs !== NULL) { + $dc->addOpfAttr("file-as", trim($fileAs)); + } + + if ($role !== NULL) { + $dc->addOpfAttr("role", trim($role)); + } + + $this->metadata->addDublinCore($dc); + } +} + +/** + * ePub OPF Metadata structures + */ +class Metadata { + const _VERSION = 3.00; + + private $dc = array(); + private $meta = array(); + + /** + * Class constructor. + * + * @return void + */ + function __construct() { + } + + /** + * Class destructor + * + * @return void + */ + function __destruct() { + unset ($this->dc, $this->meta); + } + + /** + * + * Enter description here ... + * + * @param DublinCore $dc + */ + function addDublinCore($dc) { + if ($dc != NULL && is_object($dc) && get_class($dc) === "DublinCore") { + $this->dc[] = $dc; + } + } + + /** + * + * Enter description here ... + * + * @param string $name + * @param string $content + */ + function addMeta($name, $content) { + $name = is_string($name) ? trim($name) : NULL; + if (isset($name)) { + $content = is_string($content) ? trim($content) : NULL; + } + if (isset($content)) { + $this->meta[] = array ($name => $content); + } + } + + /** + * + * @param string $bookVersion + * @param int $date + * @return string + */ + function finalize($bookVersion = EPub::BOOK_VERSION_EPUB2, $date = NULL) { + $metadata = "\t\n"; + } else { + $metadata .= "\t\txmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\">\n"; + if (!isset($date)) { + $date = time(); + } + $metadata .= "\t\t" . gmdate("Y-m-d\TH:i:s\Z", $date) . "\n"; + } + + foreach ($this->dc as $dc) { + $metadata .= $dc->finalize($bookVersion); + } + + foreach ($this->meta as $data) { + list($name, $content) = each($data); + $metadata .= "\t\t\n"; + } + + return $metadata . "\t\n"; + } +} + +/** + * ePub OPF Dublin Core (dc:) Metadata structures + */ +class DublinCore { + const _VERSION = 3.00; + + const CONTRIBUTOR = "contributor"; + const COVERAGE = "coverage"; + const CREATOR = "creator"; + const DATE = "date"; + const DESCRIPTION = "description"; + const FORMAT = "format"; + const IDENTIFIER = "identifier"; + const LANGUAGE = "language"; + const PUBLISHER = "publisher"; + const RELATION = "relation"; + const RIGHTS = "rights"; + const SOURCE = "source"; + const SUBJECT = "subject"; + const TITLE = "title"; + const TYPE = "type"; + + private $dcName = NULL; + private $dcValue = NULL; + private $attr = array(); + private $opfAttr = array(); + + /** + * Class constructor. + * + * @return void + */ + function __construct($name, $value) { + $this->setDc($name, $value); + } + + /** + * Class destructor + * + * @return void + */ + function __destruct() { + unset ($this->dcName, $this->dcValue, $this->attr, $this->opfAttr); + } + + /** + * + * Enter description here ... + * + * @param string $name + * @param string $value + */ + function setDc($name, $value) { + $this->dcName = is_string($name) ? trim($name) : NULL; + if (isset($this->dcName)) { + $this->dcValue = isset($value) ? (string)$value : NULL; + } + if (! isset($this->dcValue)) { + $this->dcName = NULL; + } + } + + /** + * + * Enter description here ... + * + * @param string $attrName + * @param string $attrValue + */ + function addAttr($attrName, $attrValue) { + $attrName = is_string($attrName) ? trim($attrName) : NULL; + if (isset($attrName)) { + $attrValue = is_string($attrValue) ? trim($attrValue) : NULL; + } + if (isset($attrValue)) { + $this->attr[$attrName] = $attrValue; + } + } + + /** + * + * Enter description here ... + * + * @param string $opfAttrName + * @param string $opfAttrValue + */ + function addOpfAttr($opfAttrName, $opfAttrValue) { + $opfAttrName = is_string($opfAttrName) ? trim($opfAttrName) : NULL; + if (isset($opfAttrName)) { + $opfAttrValue = is_string($opfAttrValue) ? trim($opfAttrValue) : NULL; + } + if (isset($opfAttrValue)) { + $this->opfAttr[$opfAttrName] = $opfAttrValue; + } + } + + + /** + * + * @param string $bookVersion + * @return string + */ + function finalize($bookVersion = EPub::BOOK_VERSION_EPUB2) { + $dc = "\t\tdcName; + + if (sizeof($this->attr) > 0) { + while (list($name, $content) = each($this->attr)) { + $dc .= " " . $name . "=\"" . $content . "\""; + } + } + + if ($bookVersion === EPub::BOOK_VERSION_EPUB2 && sizeof($this->opfAttr) > 0) { + while (list($name, $content) = each($this->opfAttr)) { + $dc .= " opf:" . $name . "=\"" . $content . "\""; + } + } + + return $dc . ">" . $this->dcValue . "dcName . ">\n"; + } +} + +/** + * ePub OPF Manifest structure + */ +class Manifest { + const _VERSION = 3.00; + + private $items = array(); + + /** + * Class constructor. + * + * @return void + */ + function __construct() { + } + + /** + * Class destructor + * + * @return void + */ + function __destruct() { + unset ($this->items); + } + + /** + * + * Enter description here ... + * + * @param Item $item + */ + function addItem($item) { + if ($item != NULL && is_object($item) && get_class($item) === "Item") { + $this->items[] = $item; + } + } + + /** + * + * @param string $bookVersion + * @return string + */ + function finalize($bookVersion = EPub::BOOK_VERSION_EPUB2) { + $manifest = "\n\t\n"; + foreach ($this->items as $item) { + $manifest .= $item->finalize($bookVersion); + } + return $manifest . "\t\n"; + } +} + +/** + * ePub OPF Item structure + */ +class Item { + const _VERSION = 3.00; + + private $id = NULL; + private $href = NULL; + private $mediaType = NULL; + private $properties = NULL; + private $requiredNamespace = NULL; + private $requiredModules = NULL; + private $fallback = NULL; + private $fallbackStyle = NULL; + + /** + * Class constructor. + * + * @return void + */ + function __construct($id, $href, $mediaType, $properties = NULL) { + $this->setId($id); + $this->setHref($href); + $this->setMediaType($mediaType); + $this->setProperties($properties); + } + + /** + * Class destructor + * + * @return void + */ + function __destruct() { + unset ($this->id, $this->href, $this->mediaType); + unset ($this->properties, $this->requiredNamespace, $this->requiredModules, $this->fallback, $this->fallbackStyle); + } + + /** + * + * Enter description here ... + * + * @param string $id + */ + function setId($id) { + $this->id = is_string($id) ? trim($id) : NULL; + } + + /** + * + * Enter description here ... + * + * @param string $href + */ + function setHref($href) { + $this->href = is_string($href) ? trim($href) : NULL; + } + + /** + * + * Enter description here ... + * + * @param string $mediaType + */ + function setMediaType($mediaType) { + $this->mediaType = is_string($mediaType) ? trim($mediaType) : NULL; + } + + /** + * + * Enter description here ... + * + * @param string $properties + */ + function setProperties($properties) { + $this->properties = is_string($properties) ? trim($properties) : NULL; + } + + /** + * + * Enter description here ... + * + * @param string $requiredNamespace + */ + function setRequiredNamespace($requiredNamespace) { + $this->requiredNamespace = is_string($requiredNamespace) ? trim($requiredNamespace) : NULL; + } + + /** + * + * Enter description here ... + * + * @param string $requiredModules + */ + function setRequiredModules($requiredModules) { + $this->requiredModules = is_string($requiredModules) ? trim($requiredModules) : NULL; + } + + /** + * + * Enter description here ... + * + * @param string $fallback + */ + function setfallback($fallback) { + $this->fallback = is_string($fallback) ? trim($fallback) : NULL; + } + + /** + * + * Enter description here ... + * + * @param string $fallbackStyle + */ + function setFallbackStyle($fallbackStyle) { + $this->fallbackStyle = is_string($fallbackStyle) ? trim($fallbackStyle) : NULL; + } + + /** + * + * @param string $bookVersion + * @return string + */ + function finalize($bookVersion = EPub::BOOK_VERSION_EPUB2) { + $item = "\t\tid . "\" href=\"" . $this->href . "\" media-type=\"" . $this->mediaType . "\" "; + if ($bookVersion === EPub::BOOK_VERSION_EPUB3 && isset($this->properties)) { + $item .= "properties=\"" . $this->properties . "\" "; + } + if (isset($this->requiredNamespace)) { + $item .= "\n\t\t\trequired-namespace=\"" . $this->requiredNamespace . "\" "; + if (isset($this->requiredModules)) { + $item .= "required-modules=\"" . $this->requiredModules . "\" "; + } + } + if (isset($this->fallback)) { + $item .= "\n\t\t\tfallback=\"" . $this->fallback . "\" "; + } + if (isset($this->fallbackStyle)) { + $item .= "\n\t\t\tfallback-style=\"" . $this->fallbackStyle . "\" "; + } + return $item . "/>\n"; + } +} + +/** + * ePub OPF Spine structure + */ +class Spine { + const _VERSION = 1.00; + + private $itemrefs = array(); + private $toc = NULL; + + /** + * Class constructor. + * + * @return void + */ + function __construct($toc = "ncx") { + $this->setToc($toc); + } + + /** + * Class destructor + * + * @return void + */ + function __destruct() { + unset ($this->itemrefs, $this->toc); + } + + /** + * + * Enter description here ... + * + * @param string $toc + */ + function setToc($toc) { + $this->toc = is_string($toc) ? trim($toc) : NULL; + } + + /** + * + * Enter description here ... + * + * @param Itemref $itemref + */ + function addItemref($itemref) { + if ($itemref != NULL + && is_object($itemref) + && get_class($itemref) === "Itemref" + && !isset($this->itemrefs[$itemref->getIdref()])) { + $this->itemrefs[$itemref->getIdref()] = $itemref; + } + } + + /** + * + * Enter description here ... + * + * @return string + */ + function finalize() { + $spine = "\n\ttoc . "\">\n"; + foreach ($this->itemrefs as $itemref) { + $spine .= $itemref->finalize(); + } + return $spine . "\t\n"; + } +} + +/** + * ePub OPF ItemRef structure + */ +class Itemref { + const _VERSION = 3.00; + + private $idref = NULL; + private $linear = TRUE; + + /** + * Class constructor. + * + * @return void + */ + function __construct($idref, $linear = TRUE) { + $this->setIdref($idref); + $this->setLinear($linear); + } + + /** + * Class destructor + * + * @return void + */ + function __destruct() { + unset ($this->idref, $this->linear); + } + + /** + * + * Enter description here ... + * + * @param string $idref + */ + function setIdref($idref) { + $this->idref = is_string($idref) ? trim($idref) : NULL; + } + + /** + * + * Enter description here ... + * + * @return string $idref + */ + function getIdref() { + return $this->idref; + } + + /** + * + * Enter description here ... + * + * @param bool $linear + */ + function setLinear($linear = TRUE) { + $this->linear = $linear === TRUE; + } + + /** + * + * Enter description here ... + * + * @return string + */ + function finalize() { + $itemref = "\t\tidref . "\""; + if ($this->linear == FALSE) { + return $itemref .= " linear=\"no\" />\n"; + } + return $itemref . " />\n"; + } +} + +/** + * ePub OPF Guide structure + */ +class Guide { + const _VERSION = 3.00; + + private $references = array(); + + /** + * Class constructor. + * + * @return void + */ + function __construct() { + } + + /** + * Class destructor + * + * @return void + */ + function __destruct() { + unset ($this->references); + } + + /** + * + * Enter description here ... + * + */ + function length() { + return sizeof($this->references); + } + + /** + * + * Enter description here ... + * + * @param Reference $reference + */ + function addReference($reference) { + if ($reference != NULL && is_object($reference) && get_class($reference) === "Reference") { + $this->references[] = $reference; + } + } + + /** + * + * Enter description here ... + * + * @return string + */ + function finalize() { + $ref = ""; + if (sizeof($this->references) > 0) { + $ref = "\n\t\n"; + foreach ($this->references as $reference) { + $ref .= $reference->finalize(); + } + $ref .= "\t\n"; + } + return $ref; + } +} + +/** + * Reference constants + */ +class Reference { + const _VERSION = 1.00; + + /* REFERENCE types are derived from the "Chicago Manual of Style" + */ + + /** Acknowledgements page */ + const ACKNOWLEDGEMENTS = "acknowledgements"; + + /** Bibliography page */ + const BIBLIOGRAPHY = "bibliography"; + + /** Colophon page */ + const COLOPHON = "colophon"; + + /** Copyright page */ + const COPYRIGHT_PAGE = "copyright-page"; + + /** Dedication */ + const DEDICATION = "dedication"; + + /** Epigraph */ + const EPIGRAPH = "epigraph"; + + /** Foreword */ + const FOREWORD = "foreword"; + + /** Glossary page */ + const GLOSSARY = "glossary"; + + /** back-of-book style index */ + const INDEX = "index"; + + /** List of illustrations */ + const LIST_OF_ILLUSTRATIONS = "loi"; + + /** List of tables */ + const LIST_OF_TABLES = "lot"; + + /** Notes page */ + const NOTES = "notes"; + + /** Preface page */ + const PREFACE = "preface"; + + /** Table of contents */ + const TABLE_OF_CONTENTS = "toc"; + + /** Page with possibly title, author, publisher, and other metadata */ + const TITLE_PAGE = "titlepage"; + + /** First page of the book, ie. first page of the first chapter */ + const TEXT = "text"; + + // ****************** + // ePub3 constants + // ****************** + + // Document partitions + /** The publications cover(s), jacket information, etc. This is officially in ePub3, but works for ePub 2 as well */ + const COVER = "cover"; + + /** Preliminary material to the content body, such as tables of contents, dedications, etc. */ + const FRONTMATTER = "frontmatter"; + + /** The main (body) content of a document. */ + const BODYMATTER = "bodymatter"; + + /** Ancillary material occurring after the document body, such as indices, appendices, etc. */ + const BACKMATTER = "backmatter"; + + + private $type = NULL; + private $title = NULL; + private $href = NULL; + + /** + * Class constructor. + * + * @param string $type + * @param string $title + * @param string $href + */ + function __construct($type, $title, $href) { + $this->setType($type); + $this->setTitle($title); + $this->setHref($href); + } + + /** + * Class destructor + * + * @return void + */ + function __destruct() { + unset ($this->type, $this->title, $this->href); + } + + /** + * + * Enter description here ... + * + * @param string $type + */ + function setType($type) { + $this->type = is_string($type) ? trim($type) : NULL; + } + + /** + * + * Enter description here ... + * + * @param string $title + */ + function setTitle($title) { + $this->title = is_string($title) ? trim($title) : NULL; + } + + /** + * + * Enter description here ... + * + * @param string $href + */ + function setHref($href) { + $this->href = is_string($href) ? trim($href) : NULL; + } + + /** + * + * Enter description here ... + * + * @return string + */ + function finalize() { + return "\t\ttype . "\" title=\"" . $this->title . "\" href=\"" . $this->href . "\" />\n"; + } +} + +/** + * Common Marc codes. + * Ref: http://www.loc.gov/marc/relators/ + */ +class MarcCode { + const _VERSION = 3.00; + + /** + * Adapter + * + * Use for a person who + * 1) reworks a musical composition, usually for a different medium, or + * 2) rewrites novels or stories for motion pictures or other audiovisual medium. + */ + const ADAPTER = "adp"; + + /** + * Annotator + * + * Use for a person who writes manuscript annotations on a printed item. + */ + const ANNOTATOR = "ann"; + + /** + * Arranger + * + * Use for a person who transcribes a musical composition, usually for a different + * medium from that of the original; in an arrangement the musical substance remains + * essentially unchanged. + */ + const ARRANGER = "arr"; + + /** + * Artist + * + * Use for a person (e.g., a painter) who conceives, and perhaps also implements, + * an original graphic design or work of art, if specific codes (e.g., [egr], + * [etr]) are not desired. For book illustrators, prefer Illustrator [ill]. + */ + const ARTIST = "art"; + + /** + * Associated name + * + * Use as a general relator for a name associated with or found in an item or + * collection, or which cannot be determined to be that of a Former owner [fmo] + * or other designated relator indicative of provenance. + */ + const ASSOCIATED_NAME = "asn"; + + /** + * Author + * + * Use for a person or corporate body chiefly responsible for the intellectual + * or artistic content of a work. This term may also be used when more than one + * person or body bears such responsibility. + */ + const AUTHOR = "aut"; + + /** + * Author in quotations or text extracts + * + * Use for a person whose work is largely quoted or extracted in a works to which + * he or she did not contribute directly. Such quotations are found particularly + * in exhibition catalogs, collections of photographs, etc. + */ + const AUTHOR_IN_QUOTES = "aqt"; + + /** + * Author of afterword, colophon, etc. + * + * Use for a person or corporate body responsible for an afterword, postface, + * colophon, etc. but who is not the chief author of a work. + */ + const AUTHOR_OF_AFTERWORD = "aft"; + + /** + * Author of introduction, etc. + * + * Use for a person or corporate body responsible for an introduction, preface, + * foreword, or other critical matter, but who is not the chief author. + */ + const AUTHOR_OF_INTRO = "aui"; + + /** + * Bibliographic antecedent + * + * Use for the author responsible for a work upon which the work represented by + * the catalog record is based. This can be appropriate for adaptations, sequels, + * continuations, indexes, etc. + */ + const BIB_ANTECEDENT = "ant"; + + /** + * Book producer + * + * Use for the person or firm responsible for the production of books and other + * print media, if specific codes (e.g., [bkd], [egr], [tyd], [prt]) are not desired. + */ + const BOOK_PRODUCER = "bkp"; + + /** + * Collaborator + * + * Use for a person or corporate body that takes a limited part in the elaboration + * of a work of another author or that brings complements (e.g., appendices, notes) + * to the work of another author. + */ + const COLABORATOR = "clb"; + + /** + * Commentator + * + * Use for a person who provides interpretation, analysis, or a discussion of the + * subject matter on a recording, motion picture, or other audiovisual medium. + * Compiler [com] Use for a person who produces a work or publication by selecting + * and putting together material from the works of various persons or bodies. + */ + const COMMENTATOR = "cmm"; + + /** + * Designer + * + * Use for a person or organization responsible for design if specific codes (e.g., + * [bkd], [tyd]) are not desired. + */ + const DESIGNER = "dsr"; + + /** + * Editor + * + * Use for a person who prepares for publication a work not primarily his/her own, + * such as by elucidating text, adding introductory or other critical matter, or + * technically directing an editorial staff. + */ + const EDITORT = "edt"; + + /** + * Illustrator + * + * Use for the person who conceives, and perhaps also implements, a design or + * illustration, usually to accompany a written text. + */ + const ILLUSTRATOR = "ill"; + + /** + * Lyricist + * + * Use for the writer of the text of a song. + */ + const LYRICIST = "lyr"; + + /** + * Metadata contact + * + * Use for the person or organization primarily responsible for compiling and + * maintaining the original description of a metadata set (e.g., geospatial + * metadata set). + */ + const METADATA_CONTACT = "mdc"; + + /** + * Musician + * + * Use for the person who performs music or contributes to the musical content + * of a work when it is not possible or desirable to identify the function more + * precisely. + */ + const MUSICIAN = "mus"; + + /** + * Narrator + * + * Use for the speaker who relates the particulars of an act, occurrence, or + * course of events. + */ + const NARRATOR = "nrt"; + + /** + * Other + * + * Use for relator codes from other lists which have no equivalent in the MARC + * list or for terms which have not been assigned a code. + */ + const OTHER = "oth"; + + /** + * Photographer + * + * Use for the person or organization responsible for taking photographs, whether + * they are used in their original form or as reproductions. + */ + const PHOTOGRAPHER = "pht"; + + /** + * Printer + * + * Use for the person or organization who prints texts, whether from type or plates. + */ + const PRINTER = "prt"; + + /** + * Redactor + * + * Use for a person who writes or develops the framework for an item without + * being intellectually responsible for its content. + */ + const REDACTOR = "red"; + + /** + * Reviewer + * + * Use for a person or corporate body responsible for the review of book, motion + * picture, performance, etc. + */ + const REVIEWER = "rev"; + + /** + * Sponsor + * + * Use for the person or agency that issued a contract, or under whose auspices + * a work has been written, printed, published, etc. + */ + const SPONSOR = "spn"; + + /** + * Thesis advisor + * + * Use for the person under whose supervision a degree candidate develops and + * presents a thesis, memoir, or text of a dissertation. + */ + const THESIS_ADVISOR = "ths"; + + /** + * Transcriber + * + * Use for a person who prepares a handwritten or typewritten copy from original + * material, including from dictated or orally recorded material. + */ + const TRANSCRIBER = "trc"; + + /** + * Translator + * + * Use for a person who renders a text from one language into another, or from + * an older form of a language into the modern form. + */ + const TRANSLATOR = "trl"; +} +?> diff --git a/inc/3rdparty/libraries/PHPePub/EPub.php b/inc/3rdparty/libraries/PHPePub/EPub.php new file mode 100644 index 00000000..836c0512 --- /dev/null +++ b/inc/3rdparty/libraries/PHPePub/EPub.php @@ -0,0 +1,2429 @@ + + * @copyright 2009-2014 A. Grandt + * @license GNU LGPL 2.1 + * @version 3.20 + * @link http://www.phpclasses.org/package/6115 + * @link https://github.com/Grandt/PHPePub + * @uses Zip.php version 1.50; http://www.phpclasses.org/browse/package/6110.html or https://github.com/Grandt/PHPZip + */ +class EPub { + const VERSION = 3.20; + const REQ_ZIP_VERSION = 1.60; + + const IDENTIFIER_UUID = 'UUID'; + const IDENTIFIER_URI = 'URI'; + const IDENTIFIER_ISBN = 'ISBN'; + + /** Ignore all external references, and do not process the file for these */ + const EXTERNAL_REF_IGNORE = 0; + /** Process the file for external references and add them to the book */ + const EXTERNAL_REF_ADD = 1; + /** Process the file for external references and add them to the book, but remove images, and img tags */ + const EXTERNAL_REF_REMOVE_IMAGES = 2; + /** Process the file for external references and add them to the book, but replace images, and img tags with [image] */ + const EXTERNAL_REF_REPLACE_IMAGES = 3; + + const DIRECTION_LEFT_TO_RIGHT = "ltr"; + const DIRECTION_RIGHT_TO_LEFT = "rtl"; + + const BOOK_VERSION_EPUB2 = "2.0"; + const BOOK_VERSION_EPUB3 = "3.0"; + + private $bookVersion = EPub::BOOK_VERSION_EPUB2; + + public $maxImageWidth = 768; + public $maxImageHeight = 1024; + + public $splitDefaultSize = 250000; + /** Gifs can crash some early ADE based readers, and are disabled by default. + * getImage will convert these if it can, unless this is set to TRUE. + */ + public $isGifImagesEnabled = FALSE; + public $isReferencesAddedToToc = TRUE; + + private $zip; + + private $title = ""; + private $language = "en"; + private $identifier = ""; + private $identifierType = ""; + private $description = ""; + private $author = ""; + private $authorSortKey = ""; + private $publisherName = ""; + private $publisherURL = ""; + private $date = 0; + private $rights = ""; + private $coverage = ""; + private $relation = ""; + private $sourceURL = ""; + + private $chapterCount = 0; + private $opf = NULL; + private $ncx = NULL; + private $isFinalized = FALSE; + private $isCoverImageSet = FALSE; + private $buildTOC = FALSE; + private $tocTitle = NULL; + private $tocFileName = NULL; + private $tocCSSClass = NULL; + private $tocAddReferences = FALSE; + private $tocCssFileName = NULL; + + private $fileList = array(); + private $writingDirection = EPub::DIRECTION_LEFT_TO_RIGHT; + private $languageCode = "en"; + + /** + * Used for building the TOC. + * If this list is overwritten it MUST contain at least "text" as an element. + */ + public $referencesOrder = NULL; + + private $dateformat = 'Y-m-d\TH:i:s.000000P'; // ISO 8601 long + private $dateformatShort = 'Y-m-d'; // short date format to placate ePubChecker. + private $headerDateFormat = "D, d M Y H:i:s T"; + + protected $isCurlInstalled; + protected $isGdInstalled; + protected $isExifInstalled; + protected $isFileGetContentsInstalled; + protected $isFileGetContentsExtInstalled; + + private $bookRoot = "OEBPS/"; + private $docRoot = NULL; + private $EPubMark = TRUE; + private $generator = ""; + + private $log = NULL; + public $isLogging = TRUE; + + public $encodeHTML = FALSE; + + private $mimetypes = array( + "js" => "application/x-javascript", "swf" => "application/x-shockwave-flash", "xht" => "application/xhtml+xml", "xhtml" => "application/xhtml+xml", "zip" => "application/zip", + "aif" => "audio/x-aiff", "aifc" => "audio/x-aiff", "aiff" => "audio/x-aiff", "au" => "audio/basic", "kar" => "audio/midi", "m3u" => "audio/x-mpegurl", "mid" => "audio/midi", "midi" => "audio/midi", "mp2" => "audio/mpeg", "mp3" => "audio/mpeg", "mpga" => "audio/mpeg", "oga" => "audio/ogg", "ogg" => "audio/ogg", "ra" => "audio/x-realaudio", "ram" => "audio/x-pn-realaudio", "rm" => "audio/x-pn-realaudio", "rpm" => "audio/x-pn-realaudio-plugin", "snd" => "audio/basic", "wav" => "audio/x-wav", + "bmp" => "image/bmp", "djv" => "image/vnd.djvu", "djvu" => "image/vnd.djvu", "gif" => "image/gif", "ief" => "image/ief", "jpe" => "image/jpeg", "jpeg" => "image/jpeg", "jpg" => "image/jpeg", "pbm" => "image/x-portable-bitmap", "pgm" => "image/x-portable-graymap", "png" => "image/png", "pnm" => "image/x-portable-anymap", "ppm" => "image/x-portable-pixmap", "ras" => "image/x-cmu-raster", "rgb" => "image/x-rgb", "tif" => "image/tif", "tiff" => "image/tiff", "wbmp" => "image/vnd.wap.wbmp", "xbm" => "image/x-xbitmap", "xpm" => "image/x-xpixmap", "xwd" => "image/x-windowdump", + "asc" => "text/plain", "css" => "text/css", "etx" => "text/x-setext", "htm" => "text/html", "html" => "text/html", "rtf" => "text/rtf", "rtx" => "text/richtext", "sgm" => "text/sgml", "sgml" => "text/sgml", "tsv" => "text/tab-seperated-values", "txt" => "text/plain", "wml" => "text/vnd.wap.wml", "wmls" => "text/vnd.wap.wmlscript", "xml" => "text/xml", "xsl" => "text/xml", + "avi" => "video/x-msvideo", "mov" => "video/quicktime", "movie" => "video/x-sgi-movie", "mp4" => "video/mp4", "mpe" => "video/mpeg", "mpeg" => "video/mpeg", "mpg" => "video/mpeg", "mxu" => "video/vnd.mpegurl", "ogv" => "video/ogg", "qt" => "video/quicktime", "webm" => "video/webm"); + + // These are the ONLY allowed types in that these are the ones ANY reader must support, any other MUST have the fallback attribute pointing to one of these. + private $coreMediaTypes = array("image/gif", "image/jpeg", "image/png", "image/svg+xml", "application/xhtml+xml", "application/x-dtbook+xml", "application/xml", "application/x-dtbncx+xml", "text/css", "text/x-oeb1-css", "text/x-oeb1-document"); + + private $opsContentTypes = array("application/xhtml+xml", "application/x-dtbook+xml", "application/xml", "application/x-dtbncx+xml", "text/x-oeb1-document"); + + private $forbiddenCharacters = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", "%"); + + private $htmlContentHeader = "\n\n\n\n\n\n\n"; + private $htmlContentFooter = "\n\n"; + + /** + * Class constructor. + * + * @return void + */ + function __construct($bookVersion = EPub::BOOK_VERSION_EPUB2, $languageCode = "en", $writingDirection = EPub::DIRECTION_LEFT_TO_RIGHT) { + include_once("Zip.php"); + include_once("Logger.php"); + + $this->bookVersion = $bookVersion; + $this->writingDirection = $writingDirection; + $this->languageCode = $languageCode; + + $this->log = new Logger("EPub", $this->isLogging); + + /* Prepare Logging. Just in case it's used. later */ + if ($this->isLogging) { + $this->log->logLine("EPub class version....: " . self::VERSION); + $this->log->logLine("EPub req. Zip version.: " . self::REQ_ZIP_VERSION); + $this->log->logLine("Zip version...........: " . Zip::VERSION); + $this->log->dumpInstalledModules(); + } + + if (!defined("Zip::VERSION") || Zip::VERSION < self::REQ_ZIP_VERSION) { + die("

    EPub version " . self::VERSION . " requires Zip.php at version " . self::REQ_ZIP_VERSION . " or higher.
    You can obtain the latest version from http://www.phpclasses.org/browse/package/6110.html.

    "); + } + + include_once("EPubChapterSplitter.php"); + include_once("EPub.HtmlEntities.php"); + include_once("EPub.NCX.php"); + include_once("EPub.OPF.php"); + + $this->initialize(); + } + + /** + * Class destructor + * + * @return void + * @TODO make sure elements in the destructor match the current class elements + */ + function __destruct() { + unset($this->bookVersion, $this->maxImageWidth, $this->maxImageHeight); + unset($this->splitDefaultSize, $this->isGifImagesEnabled, $this->isReferencesAddedToToc); + unset($this->zip, $this->title, $this->language, $this->identifier, $this->identifierType); + unset($this->description, $this->author, $this->authorSortKey, $this->publisherName); + unset($this->publisherURL, $this->date, $this->rights, $this->coverage, $this->relation); + unset($this->sourceURL, $this->chapterCount, $this->opf, $this->ncx, $this->isFinalized); + unset($this->isCoverImageSet, $this->fileList, $this->writingDirection, $this->languageCode); + unset($this->referencesOrder, $this->dateformat, $this->dateformatShort, $this->headerDateFormat); + unset($this->isCurlInstalled, $this->isGdInstalled, $this->isExifInstalled); + unset($this->isFileGetContentsInstalled, $this->isFileGetContentsExtInstalled, $this->bookRoot); + unset($this->docRoot, $this->EPubMark, $this->generator, $this->log, $this->isLogging); + unset($this->encodeHTML, $this->mimetypes, $this->coreMediaTypes, $this->opsContentTypes); + unset($this->forbiddenCharacters, $this->htmlContentHeader, $this->htmlContentFooter); + unset($this->buildTOC, $this->tocTitle, $this->tocCSSClass, $this->tocAddReferences); + unset($this->tocFileName, $this->tocCssFileName); + } + + /** + * initialize defaults. + */ + private function initialize() { + $this->referencesOrder = array( + Reference::COVER => "Cover Page", + Reference::TITLE_PAGE => "Title Page", + Reference::ACKNOWLEDGEMENTS => "Acknowledgements", + Reference::BIBLIOGRAPHY => "Bibliography", + Reference::COLOPHON => "Colophon", + Reference::COPYRIGHT_PAGE => "Copyright", + Reference::DEDICATION => "Dedication", + Reference::EPIGRAPH => "Epigraph", + Reference::FOREWORD => "Foreword", + Reference::TABLE_OF_CONTENTS => "Table of Contents", + Reference::NOTES => "Notes", + Reference::PREFACE => "Preface", + Reference::TEXT => "First Page", + Reference::LIST_OF_ILLUSTRATIONS => "List of Illustrations", + Reference::LIST_OF_TABLES => "List of Tables", + Reference::GLOSSARY => "Glossary", + Reference::INDEX => "Index"); + + $this->docRoot = filter_input(INPUT_SERVER, "DOCUMENT_ROOT") . "/"; + + $this->isCurlInstalled = extension_loaded('curl') && function_exists('curl_version'); + $this->isGdInstalled = extension_loaded('gd') && function_exists('gd_info'); + $this->isExifInstalled = extension_loaded('exif') && function_exists('exif_imagetype'); + $this->isFileGetContentsInstalled = function_exists('file_get_contents'); + $this->isFileGetContentsExtInstalled = $this->isFileGetContentsInstalled && ini_get('allow_url_fopen'); + + $this->zip = new Zip(); + $this->zip->setExtraField(FALSE); + $this->zip->addFile("application/epub+zip", "mimetype"); + $this->zip->setExtraField(TRUE); + $this->zip->addDirectory("META-INF"); + + $this->content = "\n\n\t\n\t\tbookRoot . "book.opf\" media-type=\"application/oebps-package+xml\" />\n\t\n\n"; + + if (!$this->isEPubVersion2()) { + $this->htmlContentHeader = "\n" + . "\n" + . "" + . "\n" + . "\n" + . "\n" + . "\n"; + } + + $this->zip->addFile($this->content, "META-INF/container.xml", 0, NULL, FALSE); + $this->content = NULL; + $this->ncx = new Ncx(NULL, NULL, NULL, $this->languageCode, $this->writingDirection); + $this->opf = new Opf(); + $this->ncx->setVersion($this->bookVersion); + $this->opf->setVersion($this->bookVersion); + $this->opf->addItem("ncx", "book.ncx", Ncx::MIMETYPE); + $this->chapterCount = 0; + } + + /** + * Add dynamically generated data as a file to the book. + * + * @param string $fileName Filename to use for the file, must be unique for the book. + * @param string $fileId Unique identifier for the file. + * @param string $fileData File data + * @param string $mimetype file mime type + * @return bool $success + */ + function addFile($fileName, $fileId, $fileData, $mimetype) { + if ($this->isFinalized || array_key_exists($fileName, $this->fileList)) { + return FALSE; + } + + $fileName = $this->normalizeFileName($fileName); + + $compress = (strpos($mimetype, "image/") !== 0); + + $this->zip->addFile($fileData, $this->bookRoot.$fileName, 0, NULL, $compress); + $this->fileList[$fileName] = $fileName; + $this->opf->addItem($fileId, $fileName, $mimetype); + return TRUE; + } + + /** + * Add a large file directly from the filestystem to the book. + * + * @param string $fileName Filename to use for the file, must be unique for the book. + * @param string $fileId Unique identifier for the file. + * @param string $filePath File path + * @param string $mimetype file mime type + * @return bool $success + */ + function addLargeFile($fileName, $fileId, $filePath, $mimetype) { + if ($this->isFinalized || array_key_exists($fileName, $this->fileList)) { + return FALSE; + } + $fileName = $this->normalizeFileName($fileName); + + if ($this->zip->addLargeFile($filePath, $this->bookRoot.$fileName)) { + $this->fileList[$fileName] = $fileName; + $this->opf->addItem($fileId, $fileName, $mimetype); + return TRUE; + } + return FALSE; + } + + /** + * Add a CSS file to the book. + * + * @param string $fileName Filename to use for the CSS file, must be unique for the book. + * @param string $fileId Unique identifier for the file. + * @param string $fileData CSS data + * @param int $externalReferences How to handle external references, EPub::EXTERNAL_REF_IGNORE, EPub::EXTERNAL_REF_ADD or EPub::EXTERNAL_REF_REMOVE_IMAGES? See documentation for processCSSExternalReferences for explanation. Default is EPub::EXTERNAL_REF_IGNORE. + * @param string $baseDir Default is "", meaning it is pointing to the document root. NOT used if $externalReferences is set to EPub::EXTERNAL_REF_IGNORE. + * + * @return bool $success + */ + function addCSSFile($fileName, $fileId, $fileData, $externalReferences = EPub::EXTERNAL_REF_IGNORE, $baseDir = "") { + if ($this->isFinalized || array_key_exists($fileName, $this->fileList)) { + return FALSE; + } + $fileName = Zip::getRelativePath($fileName); + $fileName = preg_replace('#^[/\.]+#i', "", $fileName); + + if ($externalReferences !== EPub::EXTERNAL_REF_IGNORE) { + $cssDir = pathinfo($fileName); + $cssDir = preg_replace('#^[/\.]+#i', "", $cssDir["dirname"] . "/"); + if (!empty($cssDir)) { + $cssDir = preg_replace('#[^/]+/#i', "../", $cssDir); + } + + $this->processCSSExternalReferences($fileData, $externalReferences, $baseDir, $cssDir); + } + + $this->addFile($fileName, "css_" . $fileId, $fileData, "text/css"); + + return TRUE; + } + + /** + * Add a chapter to the book, as a chapter should not exceed 250kB, you can parse an array with multiple parts as $chapterData. + * These will still only show up as a single chapter in the book TOC. + * + * @param string $chapterName Name of the chapter, will be use din the TOC + * @param string $fileName Filename to use for the chapter, must be unique for the book. + * @param string $chapter Chapter text in XHTML or array $chapterData valid XHTML data for the chapter. File should NOT exceed 250kB. + * @param bool $autoSplit Should the chapter be split if it exceeds the default split size? Default=FALSE, only used if $chapterData is a string. + * @param int $externalReferences How to handle external references, EPub::EXTERNAL_REF_IGNORE, EPub::EXTERNAL_REF_ADD or EPub::EXTERNAL_REF_REMOVE_IMAGES? See documentation for processChapterExternalReferences for explanation. Default is EPub::EXTERNAL_REF_IGNORE. + * @param string $baseDir Default is "", meaning it is pointing to the document root. NOT used if $externalReferences is set to EPub::EXTERNAL_REF_IGNORE. + * @return mixed $success FALSE if the addition failed, else the new NavPoint. + */ + function addChapter($chapterName, $fileName, $chapterData = NULL, $autoSplit = FALSE, $externalReferences = EPub::EXTERNAL_REF_IGNORE, $baseDir = "") { + if ($this->isFinalized) { + return FALSE; + } + $fileName = Zip::getRelativePath($fileName); + $fileName = preg_replace('#^[/\.]+#i', "", $fileName); + + $chapter = $chapterData; + if ($autoSplit && is_string($chapterData) && mb_strlen($chapterData) > $this->splitDefaultSize) { + $splitter = new EPubChapterSplitter(); + + $chapterArray = $splitter->splitChapter($chapterData); + if (count($chapterArray) > 1) { + $chapter = $chapterArray; + } + } + + if (!empty($chapter) && is_string($chapter)) { + if ($externalReferences !== EPub::EXTERNAL_REF_IGNORE) { + $htmlDirInfo = pathinfo($fileName); + $htmlDir = preg_replace('#^[/\.]+#i', "", $htmlDirInfo["dirname"] . "/"); + $this->processChapterExternalReferences($chapter, $externalReferences, $baseDir, $htmlDir); + } + + if ($this->encodeHTML === TRUE) { + $chapter = $this->encodeHtml($chapter); + } + + $this->chapterCount++; + $this->addFile($fileName, "chapter" . $this->chapterCount, $chapter, "application/xhtml+xml"); + $this->opf->addItemRef("chapter" . $this->chapterCount); + + $navPoint = new NavPoint($this->decodeHtmlEntities($chapterName), $fileName, "chapter" . $this->chapterCount); + $this->ncx->addNavPoint($navPoint); + $this->ncx->chapterList[$chapterName] = $navPoint; + } else if (is_array($chapter)) { + $fileNameParts = pathinfo($fileName); + $extension = $fileNameParts['extension']; + $name = $fileNameParts['filename']; + + $partCount = 0; + $this->chapterCount++; + + $oneChapter = each($chapter); + while ($oneChapter) { + list($k, $v) = $oneChapter; + if ($this->encodeHTML === TRUE) { + $v = $this->encodeHtml($v); + } + + if ($externalReferences !== EPub::EXTERNAL_REF_IGNORE) { + $this->processChapterExternalReferences($v, $externalReferences, $baseDir); + } + $partCount++; + $partName = $name . "_" . $partCount; + $this->addFile($partName . "." . $extension, $partName, $v, "application/xhtml+xml"); + $this->opf->addItemRef($partName); + + $oneChapter = each($chapter); + } + $partName = $name . "_1." . $extension; + $navPoint = new NavPoint($this->decodeHtmlEntities($chapterName), $partName, $partName); + $this->ncx->addNavPoint($navPoint); + + $this->ncx->chapterList[$chapterName] = $navPoint; + } else if (!isset($chapterData) && strpos($fileName, "#") > 0) { + $this->chapterCount++; + //$this->opf->addItemRef("chapter" . $this->chapterCount); + + $navPoint = new NavPoint($this->decodeHtmlEntities($chapterName), $fileName, "chapter" . $this->chapterCount); + $this->ncx->addNavPoint($navPoint); + $this->ncx->chapterList[$chapterName] = $navPoint; + } else if (!isset($chapterData) && $fileName=="TOC.xhtml") { + $this->chapterCount++; + $this->opf->addItemRef("toc"); + + $navPoint = new NavPoint($this->decodeHtmlEntities($chapterName), $fileName, "chapter" . $this->chapterCount); + $this->ncx->addNavPoint($navPoint); + $this->ncx->chapterList[$chapterName] = $navPoint; + } + return $navPoint; + } + + /** + * Add one chapter level. + * + * Subsequent chapters will be added to this level. + * + * @param string $navTitle + * @param string $navId + * @param string $navClass + * @param int $isNavHidden + * @param string $writingDirection + * @return NavPoint The new NavPoint for that level. + */ + function subLevel($navTitle = NULL, $navId = NULL, $navClass = NULL, $isNavHidden = FALSE, $writingDirection = NULL) { + return $this->ncx->subLevel($this->decodeHtmlEntities($navTitle), $navId, $navClass, $isNavHidden, $writingDirection); + } + + /** + * Step back one chapter level. + * + * Subsequent chapters will be added to this chapters parent level. + */ + function backLevel() { + $this->ncx->backLevel(); + } + + /** + * Step back to the root level. + * + * Subsequent chapters will be added to the rooot NavMap. + */ + function rootLevel() { + $this->ncx->rootLevel(); + } + + /** + * Step back to the given level. + * Useful for returning to a previous level from deep within the structure. + * Values below 2 will have the same effect as rootLevel() + * + * @param int $newLevel + */ + function setCurrentLevel($newLevel) { + $this->ncx->setCurrentLevel($newLevel); + } + + /** + * Get current level count. + * The indentation of the current structure point. + * + * @return current level count; + */ + function getCurrentLevel() { + return $this->ncx->getCurrentLevel(); + } + + /** + * Wrap ChapterContent with Head and Footer + * + * @param $content + * @return string $content + */ + private function wrapChapter($content) { + return $this->htmlContentHeader . "\n" . $content . "\n" . $this->htmlContentFooter; + } + + /** + * Reference pages is usually one or two pages for items such as Table of Contents, reference lists, Author notes or Acknowledgements. + * These do not show up in the regular navigation list. + * + * As they are supposed to be short. + * + * @param string $pageName Name of the chapter, will be use din the TOC + * @param string $fileName Filename to use for the chapter, must be unique for the book. + * @param string $pageData Page content in XHTML. File should NOT exceed 250kB. + * @param string $reference Reference key + * @param int $externalReferences How to handle external references. See documentation for processChapterExternalReferences for explanation. Default is EPub::EXTERNAL_REF_IGNORE. + * @param string $baseDir Default is "", meaning it is pointing to the document root. NOT used if $externalReferences is set to EPub::EXTERNAL_REF_IGNORE. + * @return bool $success + */ + function addReferencePage($pageName, $fileName, $pageData, $reference, $externalReferences = EPub::EXTERNAL_REF_IGNORE, $baseDir = "") { + if ($this->isFinalized) { + return FALSE; + } + $fileName = Zip::getRelativePath($fileName); + $fileName = preg_replace('#^[/\.]+#i', "", $fileName); + + + if (!empty($pageData) && is_string($pageData)) { + if ($this->encodeHTML === TRUE) { + $pageData = $this->encodeHtml($pageData); + } + + $this->wrapChapter($pageData); + + if ($externalReferences !== EPub::EXTERNAL_REF_IGNORE) { + $htmlDirInfo = pathinfo($fileName); + $htmlDir = preg_replace('#^[/\.]+#i', "", $htmlDirInfo["dirname"] . "/"); + $this->processChapterExternalReferences($pageData, $externalReferences, $baseDir, $htmlDir); + } + + $this->addFile($fileName, "ref_" . $reference, $pageData, "application/xhtml+xml"); + + if ($reference !== Reference::TABLE_OF_CONTENTS || !isset($this->ncx->referencesList[$reference])) { + $this->opf->addItemRef("ref_" . $reference, FALSE); + $this->opf->addReference($reference, $pageName, $fileName); + + $this->ncx->referencesList[$reference] = $fileName; + $this->ncx->referencesName[$reference] = $pageName; + } + return TRUE; + } + return TRUE; + } + + /** + * Add custom metadata to the book. + * + * It is up to the builder to make sure there are no collisions. Metadata are just key value pairs. + * + * @param string $name + * @param string $content + */ + function addCustomMetadata($name, $content) { + $this->opf->addMeta($name, $content); + } + + /** + * Add DublinCore metadata to the book + * + * Use the DublinCore constants included in EPub, ie DublinCore::DATE + * + * @param string $dublinCore name + * @param string $value + */ + function addDublinCoreMetadata($dublinCoreConstant, $value) { + if ($this->isFinalized) { + return; + } + + $this->opf->addDCMeta($dublinCoreConstant, $this->decodeHtmlEntities($value)); + } + + /** + * Add a cover image to the book. + * If the $imageData is not set, the function assumes the $fileName is the path to the image file. + * + * The styling and structure of the generated XHTML is heavily inspired by the XHTML generated by Calibre. + * + * @param string $fileName Filename to use for the image, must be unique for the book. + * @param string $imageData Binary image data + * @param string $mimetype Image mimetype, such as "image/jpeg" or "image/png". + * @return bool $success + */ + function setCoverImage($fileName, $imageData = NULL, $mimetype = NULL) { + if ($this->isFinalized || $this->isCoverImageSet || array_key_exists("CoverPage.html", $this->fileList)) { + return FALSE; + } + + if ($imageData == NULL) { + // assume $fileName is the valid file path. + if (!file_exists($fileName)) { + // Attempt to locate the file using the doc root. + $rp = realpath($this->docRoot . "/" . $fileName); + + if ($rp !== FALSE) { + // only assign the docroot path if it actually exists there. + $fileName = $rp; + } + } + $image = $this->getImage($fileName); + $imageData = $image['image']; + $mimetype = $image['mime']; + $fileName = preg_replace("#\.[^\.]+$#", "." . $image['ext'], $fileName); + } + + + $path = pathinfo($fileName); + $imgPath = "images/" . $path["basename"]; + + if (empty($mimetype) && file_exists($fileName)) { + list($width, $height, $type, $attr) = getimagesize($fileName); + $mimetype = image_type_to_mime_type($type); + } + if (empty($mimetype)) { + $ext = strtolower($path['extension']); + if ($ext == "jpg") { + $ext = "jpeg"; + } + $mimetype = "image/" . $ext; + } + + $coverPage = ""; + + if ($this->isEPubVersion2()) { + $coverPage = "\n" + . "\n" + . "\n" + . "\t\n" + . "\t\t\n" + . "\t\tCover Image\n" + . "\t\t\n" + . "\t\n" + . "\t\n" + . "\t\t
    \n" + . "\t\t\t\"Cover\n" + . "\t\t
    \n" + . "\t\n" + . "\n"; + } else { + $coverPage = "\n" + . "\n" + . "" + . "\t\n" + . "\t\tCover Image\n" + . "\t\t\n" + . "\t\n" + . "\t\n" + . "\t\t
    \n" + . "\t\t\t\"Cover\n" + . "\t\t
    \n" + . "\t\n" + . "\n"; + } + $coverPageCss = "@page, body, div, img {\n" + . "\tpadding: 0pt;\n" + . "\tmargin:0pt;\n" + . "}\n\nbody {\n" + . "\ttext-align: center;\n" + . "}\n"; + + $this->addCSSFile("Styles/CoverPage.css", "CoverPageCss", $coverPageCss); + $this->addFile($imgPath, "CoverImage", $imageData, $mimetype); + $this->addReferencePage("CoverPage", "CoverPage.xhtml", $coverPage, "cover"); + $this->isCoverImageSet = TRUE; + return TRUE; + } + + /** + * Process external references from a HTML to the book. The chapter itself is not stored. + * the HTML is scanned for <link..., <style..., and <img tags. + * Embedded CSS styles and links will also be processed. + * Script tags are not processed, as scripting should be avoided in e-books. + * + * EPub keeps track of added files, and duplicate files referenced across multiple + * chapters, are only added once. + * + * If the $doc is a string, it is assumed to be the content of an HTML file, + * else is it assumes to be a DOMDocument. + * + * Basedir is the root dir the HTML is supposed to "live" in, used to resolve + * relative references such as <img src="../images/image.png"/> + * + * $externalReferences determines how the function will handle external references. + * + * @param mixed &$doc (referenced) + * @param int $externalReferences How to handle external references, EPub::EXTERNAL_REF_IGNORE, EPub::EXTERNAL_REF_ADD or EPub::EXTERNAL_REF_REMOVE_IMAGES? Default is EPub::EXTERNAL_REF_ADD. + * @param string $baseDir Default is "", meaning it is pointing to the document root. + * @param string $htmlDir The path to the parent HTML file's directory from the root of the archive. + * + * @return bool FALSE if uncuccessful (book is finalized or $externalReferences == EXTERNAL_REF_IGNORE). + */ + protected function processChapterExternalReferences(&$doc, $externalReferences = EPub::EXTERNAL_REF_ADD, $baseDir = "", $htmlDir = "") { + if ($this->isFinalized || $externalReferences === EPub::EXTERNAL_REF_IGNORE) { + return FALSE; + } + + $backPath = preg_replace('#[^/]+/#i', "../", $htmlDir); + $isDocAString = is_string($doc); + $xmlDoc = NULL; + + if ($isDocAString) { + $xmlDoc = new DOMDocument(); + @$xmlDoc->loadHTML($doc); + } else { + $xmlDoc = $doc; + } + + $this->processChapterStyles($xmlDoc, $externalReferences, $baseDir, $htmlDir); + $this->processChapterLinks($xmlDoc, $externalReferences, $baseDir, $htmlDir, $backPath); + $this->processChapterImages($xmlDoc, $externalReferences, $baseDir, $htmlDir, $backPath); + $this->processChapterSources($xmlDoc, $externalReferences, $baseDir, $htmlDir, $backPath); + + if ($isDocAString) { + //$html = $xmlDoc->saveXML(); + + $htmlNode = $xmlDoc->getElementsByTagName("html"); + $headNode = $xmlDoc->getElementsByTagName("head"); + $bodyNode = $xmlDoc->getElementsByTagName("body"); + + $htmlNS = ""; + for ($index = 0; $index < $htmlNode->item(0)->attributes->length; $index++) { + $nodeName = $htmlNode->item(0)->attributes->item($index)->nodeName; + $nodeValue = $htmlNode->item(0)->attributes->item($index)->nodeValue; + + if ($nodeName != "xmlns") { + $htmlNS .= " $nodeName=\"$nodeValue\""; + } + } + + $xml = new DOMDocument('1.0', "utf-8"); + $xml->lookupPrefix("http://www.w3.org/1999/xhtml"); + $xml->preserveWhiteSpace = FALSE; + $xml->formatOutput = TRUE; + + $xml2Doc = new DOMDocument('1.0', "utf-8"); + $xml2Doc->lookupPrefix("http://www.w3.org/1999/xhtml"); + $xml2Doc->loadXML("\n\n\n\n"); + $html = $xml2Doc->getElementsByTagName("html")->item(0); + $html->appendChild($xml2Doc->importNode($headNode->item(0), TRUE)); + $html->appendChild($xml2Doc->importNode($bodyNode->item(0), TRUE)); + + // force pretty printing and correct formatting, should not be needed, but it is. + $xml->loadXML($xml2Doc->saveXML()); + $doc = $xml->saveXML(); + + if (!$this->isEPubVersion2()) { + $doc = preg_replace('#^\s*\s*#im', '', $doc); + } + } + return TRUE; + } + + /** + * Process images referenced from an CSS file to the book. + * + * $externalReferences determins how the function will handle external references. + * + * @param string &$cssFile (referenced) + * @param int $externalReferences How to handle external references, EPub::EXTERNAL_REF_IGNORE, EPub::EXTERNAL_REF_ADD or EPub::EXTERNAL_REF_REMOVE_IMAGES? Default is EPub::EXTERNAL_REF_ADD. + * @param string $baseDir Default is "", meaning it is pointing to the document root. + * @param string $cssDir The of the CSS file's directory from the root of the archive. + * + * @return bool FALSE if unsuccessful (book is finalized or $externalReferences == EXTERNAL_REF_IGNORE). + */ + protected function processCSSExternalReferences(&$cssFile, $externalReferences = EPub::EXTERNAL_REF_ADD, $baseDir = "", $cssDir = "") { + if ($this->isFinalized || $externalReferences === EPub::EXTERNAL_REF_IGNORE) { + return FALSE; + } + + $backPath = preg_replace('#[^/]+/#i', "../", $cssDir); + $imgs = null; + preg_match_all('#url\s*\([\'\"\s]*(.+?)[\'\"\s]*\)#im', $cssFile, $imgs, PREG_SET_ORDER); + + $itemCount = count($imgs); + for ($idx = 0; $idx < $itemCount; $idx++) { + $img = $imgs[$idx]; + if ($externalReferences === EPub::EXTERNAL_REF_REMOVE_IMAGES || $externalReferences === EPub::EXTERNAL_REF_REPLACE_IMAGES) { + $cssFile = str_replace($img[0], "", $cssFile); + } else { + $source = $img[1]; + + $pathData = pathinfo($source); + $internalSrc = $pathData['basename']; + $internalPath = ""; + $isSourceExternal = FALSE; + + if ($this->resolveImage($source, $internalPath, $internalSrc, $isSourceExternal, $baseDir, $cssDir, $backPath)) { + $cssFile = str_replace($img[0], "url('" . $backPath . $internalPath . "')", $cssFile); + } else if ($isSourceExternal) { + $cssFile = str_replace($img[0], "", $cssFile); // External image is missing + } // else do nothing, if the image is local, and missing, assume it's been generated. + } + } + return TRUE; + } + + /** + * Process style tags in a DOMDocument. Styles will be passed as CSS files and reinserted into the document. + * + * @param DOMDocument &$xmlDoc (referenced) + * @param int $externalReferences How to handle external references, EPub::EXTERNAL_REF_IGNORE, EPub::EXTERNAL_REF_ADD or EPub::EXTERNAL_REF_REMOVE_IMAGES? Default is EPub::EXTERNAL_REF_ADD. + * @param string $baseDir Default is "", meaning it is pointing to the document root. + * @param string $htmlDir The path to the parent HTML file's directory from the root of the archive. + * + * @return bool FALSE if uncuccessful (book is finalized or $externalReferences == EXTERNAL_REF_IGNORE). + */ + protected function processChapterStyles(&$xmlDoc, $externalReferences = EPub::EXTERNAL_REF_ADD, $baseDir = "", $htmlDir = "") { + if ($this->isFinalized || $externalReferences === EPub::EXTERNAL_REF_IGNORE) { + return FALSE; + } + // process inlined CSS styles in style tags. + $styles = $xmlDoc->getElementsByTagName("style"); + $styleCount = $styles->length; + for ($styleIdx = 0; $styleIdx < $styleCount; $styleIdx++) { + $style = $styles->item($styleIdx); + + $styleData = preg_replace('#[/\*\s]*\<\!\[CDATA\[[\s\*/]*#im', "", $style->nodeValue); + $styleData = preg_replace('#[/\*\s]*\]\]\>[\s\*/]*#im', "", $styleData); + + $this->processCSSExternalReferences($styleData, $externalReferences, $baseDir, $htmlDir); + $style->nodeValue = "\n" . trim($styleData) . "\n"; + } + return TRUE; + } + + /** + * Process link tags in a DOMDocument. Linked files will be loaded into the archive, and the link src will be rewritten to point to that location. + * Link types text/css will be passed as CSS files. + * + * @param DOMDocument &$xmlDoc (referenced) + * @param int $externalReferences How to handle external references, EPub::EXTERNAL_REF_IGNORE, EPub::EXTERNAL_REF_ADD or EPub::EXTERNAL_REF_REMOVE_IMAGES? Default is EPub::EXTERNAL_REF_ADD. + * @param string $baseDir Default is "", meaning it is pointing to the document root. + * @param string $htmlDir The path to the parent HTML file's directory from the root of the archive. + * @param string $backPath The path to get back to the root of the archive from $htmlDir. + * + * @return bool FALSE if uncuccessful (book is finalized or $externalReferences == EXTERNAL_REF_IGNORE). + */ + protected function processChapterLinks(&$xmlDoc, $externalReferences = EPub::EXTERNAL_REF_ADD, $baseDir = "", $htmlDir = "", $backPath = "") { + if ($this->isFinalized || $externalReferences === EPub::EXTERNAL_REF_IGNORE) { + return FALSE; + } + // process link tags. + $links = $xmlDoc->getElementsByTagName("link"); + $linkCount = $links->length; + for ($linkIdx = 0; $linkIdx < $linkCount; $linkIdx++) { + $link = $links->item($linkIdx); + $source = $link->attributes->getNamedItem("href")->nodeValue; + $sourceData = NULL; + + $pathData = pathinfo($source); + $internalSrc = $pathData['basename']; + + if (preg_match('#^(http|ftp)s?://#i', $source) == 1) { + $urlinfo = parse_url($source); + + if (strpos($urlinfo['path'], $baseDir."/") !== FALSE) { + $internalSrc = substr($urlinfo['path'], strpos($urlinfo['path'], $baseDir."/") + strlen($baseDir) + 1); + } + + @$sourceData = getFileContents($source); + } else if (strpos($source, "/") === 0) { + @$sourceData = file_get_contents($this->docRoot . $source); + } else { + @$sourceData = file_get_contents($this->docRoot . $baseDir . "/" . $source); + } + + if (!empty($sourceData)) { + if (!array_key_exists($internalSrc, $this->fileList)) { + $mime = $link->attributes->getNamedItem("type")->nodeValue; + if (empty($mime)) { + $mime = "text/plain"; + } + if ($mime == "text/css") { + $this->processCSSExternalReferences($sourceData, $externalReferences, $baseDir, $htmlDir); + $this->addCSSFile($internalSrc, $internalSrc, $sourceData, EPub::EXTERNAL_REF_IGNORE, $baseDir); + $link->setAttribute("href", $backPath . $internalSrc); + } else { + $this->addFile($internalSrc, $internalSrc, $sourceData, $mime); + } + $this->fileList[$internalSrc] = $source; + } else { + $link->setAttribute("href", $backPath . $internalSrc); + } + } // else do nothing, if the link is local, and missing, assume it's been generated. + } + return TRUE; + } + + /** + * Process img tags in a DOMDocument. + * $externalReferences will determine what will happen to these images, and the img src will be rewritten accordingly. + * + * @param DOMDocument &$xmlDoc (referenced) + * @param int $externalReferences How to handle external references, EPub::EXTERNAL_REF_IGNORE, EPub::EXTERNAL_REF_ADD or EPub::EXTERNAL_REF_REMOVE_IMAGES? Default is EPub::EXTERNAL_REF_ADD. + * @param string $baseDir Default is "", meaning it is pointing to the document root. + * @param string $htmlDir The path to the parent HTML file's directory from the root of the archive. + * @param string $backPath The path to get back to the root of the archive from $htmlDir. + * + * @return bool FALSE if uncuccessful (book is finalized or $externalReferences == EXTERNAL_REF_IGNORE). + */ + protected function processChapterImages(&$xmlDoc, $externalReferences = EPub::EXTERNAL_REF_ADD, $baseDir = "", $htmlDir = "", $backPath = "") { + if ($this->isFinalized || $externalReferences === EPub::EXTERNAL_REF_IGNORE) { + return FALSE; + } + // process img tags. + $postProcDomElememts = array(); + $images = $xmlDoc->getElementsByTagName("img"); + $itemCount = $images->length; + + for ($idx = 0; $idx < $itemCount; $idx++) { + $img = $images->item($idx); + + if ($externalReferences === EPub::EXTERNAL_REF_REMOVE_IMAGES) { + $postProcDomElememts[] = $img; + } else if ($externalReferences === EPub::EXTERNAL_REF_REPLACE_IMAGES) { + $altNode = $img->attributes->getNamedItem("alt"); + $alt = "image"; + if ($altNode !== NULL && strlen($altNode->nodeValue) > 0) { + $alt = $altNode->nodeValue; + } + $postProcDomElememts[] = array($img, $this->createDomFragment($xmlDoc, "[" . $alt . "]")); + } else { + $source = $img->attributes->getNamedItem("src")->nodeValue; + + $parsedSource = parse_url($source); + $internalSrc = $this->sanitizeFileName(urldecode(pathinfo($parsedSource['path'], PATHINFO_BASENAME))); + $internalPath = ""; + $isSourceExternal = FALSE; + + if ($this->resolveImage($source, $internalPath, $internalSrc, $isSourceExternal, $baseDir, $htmlDir, $backPath)) { + $img->setAttribute("src", $backPath . $internalPath); + } else if ($isSourceExternal) { + $postProcDomElememts[] = $img; // External image is missing + } // else do nothing, if the image is local, and missing, assume it's been generated. + } + } + + foreach ($postProcDomElememts as $target) { + if (is_array($target)) { + $target[0]->parentNode->replaceChild($target[1], $target[0]); + } else { + $target->parentNode->removeChild($target); + } + } + return TRUE; + } + + /** + * Process source tags in a DOMDocument. + * $externalReferences will determine what will happen to these images, and the img src will be rewritten accordingly. + * + * @param DOMDocument &$xmlDoc (referenced) + * @param int $externalReferences How to handle external references, EPub::EXTERNAL_REF_IGNORE, EPub::EXTERNAL_REF_ADD or EPub::EXTERNAL_REF_REMOVE_IMAGES? Default is EPub::EXTERNAL_REF_ADD. + * @param string $baseDir Default is "", meaning it is pointing to the document root. + * @param string $htmlDir The path to the parent HTML file's directory from the root of the archive. + * @param string $backPath The path to get back to the root of the archive from $htmlDir. + * + * @return bool FALSE if uncuccessful (book is finalized or $externalReferences == EXTERNAL_REF_IGNORE). + */ + protected function processChapterSources(&$xmlDoc, $externalReferences = EPub::EXTERNAL_REF_ADD, $baseDir = "", $htmlDir = "", $backPath = "") { + if ($this->isFinalized || $externalReferences === EPub::EXTERNAL_REF_IGNORE) { + return FALSE; + } + + if ($this->bookVersion !== EPub::BOOK_VERSION_EPUB3) { + // ePub 2 does not support multimedia formats, and they must be removed. + $externalReferences = EPub::EXTERNAL_REF_REMOVE_IMAGES; + } + + $postProcDomElememts = array(); + $images = $xmlDoc->getElementsByTagName("source"); + $itemCount = $images->length; + for ($idx = 0; $idx < $itemCount; $idx++) { + $img = $images->item($idx); + if ($externalReferences === EPub::EXTERNAL_REF_REMOVE_IMAGES) { + $postProcDomElememts[] = $img; + } else if ($externalReferences === EPub::EXTERNAL_REF_REPLACE_IMAGES) { + $altNode = $img->attributes->getNamedItem("alt"); + $alt = "image"; + if ($altNode !== NULL && strlen($altNode->nodeValue) > 0) { + $alt = $altNode->nodeValue; + } + $postProcDomElememts[] = array($img, $this->createDomFragment($xmlDoc, "[" . $alt . "]")); + } else { + $source = $img->attributes->getNamedItem("src")->nodeValue; + + $parsedSource = parse_url($source); + $internalSrc = $this->sanitizeFileName(urldecode(pathinfo($parsedSource['path'], PATHINFO_BASENAME))); + $internalPath = ""; + $isSourceExternal = FALSE; + + if ($this->resolveMedia($source, $internalPath, $internalSrc, $isSourceExternal, $baseDir, $htmlDir, $backPath)) { + $img->setAttribute("src", $backPath . $internalPath); + } else if ($isSourceExternal) { + $postProcDomElememts[] = $img; // External image is missing + } // else do nothing, if the image is local, and missing, assume it's been generated. + } + } + } + + /** + * Resolve an image src and determine it's target location and add it to the book. + * + * @param string $source Image Source link. + * @param string &$internalPath (referenced) Return value, will be set to the target path and name in the book. + * @param string &$internalSrc (referenced) Return value, will be set to the target name in the book. + * @param string &$isSourceExternal (referenced) Return value, will be set to TRUE if the image originated from a full URL. + * @param string $baseDir Default is "", meaning it is pointing to the document root. + * @param string $htmlDir The path to the parent HTML file's directory from the root of the archive. + * @param string $backPath The path to get back to the root of the archive from $htmlDir. + */ + protected function resolveImage($source, &$internalPath, &$internalSrc, &$isSourceExternal, $baseDir = "", $htmlDir = "", $backPath = "") { + if ($this->isFinalized) { + return FALSE; + } + $imageData = NULL; + + if (preg_match('#^(http|ftp)s?://#i', $source) == 1) { + $urlinfo = parse_url($source); + $urlPath = pathinfo($urlinfo['path']); + + if (strpos($urlinfo['path'], $baseDir."/") !== FALSE) { + $internalSrc = $this->sanitizeFileName(urldecode(substr($urlinfo['path'], strpos($urlinfo['path'], $baseDir."/") + strlen($baseDir) + 1))); + } + $internalPath = $urlinfo["scheme"] . "/" . $urlinfo["host"] . "/" . pathinfo($urlinfo["path"], PATHINFO_DIRNAME); + $isSourceExternal = TRUE; + $imageData = $this->getImage($source); + } else if (strpos($source, "/") === 0) { + $internalPath = pathinfo($source, PATHINFO_DIRNAME); + + $path = $source; + if (!file_exists($path)) { + $path = $this->docRoot . $path; + } + + $imageData = $this->getImage($path); + } else { + $internalPath = $htmlDir . "/" . preg_replace('#^[/\.]+#', '', pathinfo($source, PATHINFO_DIRNAME)); + + $path = $baseDir . "/" . $source; + if (!file_exists($path)) { + $path = $this->docRoot . $path; + } + + $imageData = $this->getImage($path); + } + if ($imageData !== FALSE) { + $iSrcInfo = pathinfo($internalSrc); + if (!empty($imageData['ext']) && $imageData['ext'] != $iSrcInfo['extension']) { + $internalSrc = $iSrcInfo['filename'] . "." . $imageData['ext']; + } + $internalPath = Zip::getRelativePath("images/" . $internalPath . "/" . $internalSrc); + if (!array_key_exists($internalPath, $this->fileList)) { + $this->addFile($internalPath, "i_" . $internalSrc, $imageData['image'], $imageData['mime']); + $this->fileList[$internalPath] = $source; + } + return TRUE; + } + return FALSE; + } + + /** + * Resolve a media src and determine it's target location and add it to the book. + * + * @param string $source Source link. + * @param string $internalPath (referenced) Return value, will be set to the target path and name in the book. + * @param string $internalSrc (referenced) Return value, will be set to the target name in the book. + * @param string $isSourceExternal (referenced) Return value, will be set to TRUE if the image originated from a full URL. + * @param string $baseDir Default is "", meaning it is pointing to the document root. + * @param string $htmlDir The path to the parent HTML file's directory from the root of the archive. + * @param string $backPath The path to get back to the root of the archive from $htmlDir. + */ + protected function resolveMedia($source, &$internalPath, &$internalSrc, &$isSourceExternal, $baseDir = "", $htmlDir = "", $backPath = "") { + if ($this->isFinalized) { + return FALSE; + } + $mediaPath = NULL; + $tmpFile; + + if (preg_match('#^(http|ftp)s?://#i', $source) == 1) { + $urlinfo = parse_url($source); + + if (strpos($urlinfo['path'], $baseDir."/") !== FALSE) { + $internalSrc = substr($urlinfo['path'], strpos($urlinfo['path'], $baseDir."/") + strlen($baseDir) + 1); + } + $internalPath = $urlinfo["scheme"] . "/" . $urlinfo["host"] . "/" . pathinfo($urlinfo["path"], PATHINFO_DIRNAME); + $isSourceExternal = TRUE; + $mediaPath = $this->getFileContents($source, true); + $tmpFile = $mediaPath; + } else if (strpos($source, "/") === 0) { + $internalPath = pathinfo($source, PATHINFO_DIRNAME); + + $mediaPath = $source; + if (!file_exists($mediaPath)) { + $mediaPath = $this->docRoot . $mediaPath; + } + } else { + $internalPath = $htmlDir . "/" . preg_replace('#^[/\.]+#', '', pathinfo($source, PATHINFO_DIRNAME)); + + $mediaPath = $baseDir . "/" . $source; + if (!file_exists($mediaPath)) { + $mediaPath = $this->docRoot . $mediaPath; + } + } + + if ($mediaPath !== FALSE) { + $mime = $this->getMime($source); + $internalPath = Zip::getRelativePath("media/" . $internalPath . "/" . $internalSrc); + + if (!array_key_exists($internalPath, $this->fileList) && + $this->addLargeFile($internalPath, "m_" . $internalSrc, $mediaPath, $mime)) { + $this->fileList[$internalPath] = $source; + } + if (isset($tmpFile)) { + unlink($tmpFile); + } + return TRUE; + } + return FALSE; + } + + /** + * Get Book Chapter count. + * + * @access public + * @return number of chapters + */ + function getChapterCount() { + return $this->chapterCount; + } + + /** + * Book title, mandatory. + * + * Used for the dc:title metadata parameter in the OPF file as well as the DocTitle attribute in the NCX file. + * + * @param string $title + * @access public + * @return bool $success + */ + function setTitle($title) { + if ($this->isFinalized) { + return FALSE; + } + $this->title = $title; + return TRUE; + } + + /** + * Get Book title. + * + * @access public + * @return $title + */ + function getTitle() { + return $this->title; + } + + /** + * Book language, mandatory + * + * Use the RFC3066 Language codes, such as "en", "da", "fr" etc. + * Defaults to "en". + * + * Used for the dc:language metadata parameter in the OPF file. + * + * @param string $language + * @access public + * @return bool $success + */ + function setLanguage($language) { + if ($this->isFinalized || mb_strlen($language) != 2) { + return FALSE; + } + $this->language = $language; + return TRUE; + } + + /** + * Get Book language. + * + * @access public + * @return $language + */ + function getLanguage() { + return $this->language; + } + + /** + * Unique book identifier, mandatory. + * Use the URI, or ISBN if available. + * + * An unambiguous reference to the resource within a given context. + * + * Recommended best practice is to identify the resource by means of a + * string conforming to a formal identification system. + * + * Used for the dc:identifier metadata parameter in the OPF file, as well + * as dtb:uid in the NCX file. + * + * Identifier type should only be: + * EPub::IDENTIFIER_URI + * EPub::IDENTIFIER_ISBN + * EPub::IDENTIFIER_UUID + * + * @param string $identifier + * @param string $identifierType + * @access public + * @return bool $success + */ + function setIdentifier($identifier, $identifierType) { + if ($this->isFinalized || ($identifierType !== EPub::IDENTIFIER_URI && $identifierType !== EPub::IDENTIFIER_ISBN && $identifierType !== EPub::IDENTIFIER_UUID)) { + return FALSE; + } + $this->identifier = $identifier; + $this->identifierType = $identifierType; + return TRUE; + } + + /** + * Get Book identifier. + * + * @access public + * @return $identifier + */ + function getIdentifier() { + return $this->identifier; + } + + /** + * Get Book identifierType. + * + * @access public + * @return $identifierType + */ + function getIdentifierType() { + return $this->identifierType; + } + + /** + * Book description, optional. + * + * An account of the resource. + * + * Description may include but is not limited to: an abstract, a table of + * contents, a graphical representation, or a free-text account of the + * resource. + * + * Used for the dc:source metadata parameter in the OPF file + * + * @param string $description + * @access public + * @return bool $success + */ + function setDescription($description) { + if ($this->isFinalized) { + return FALSE; + } + $this->description = $description; + return TRUE; + } + + /** + * Get Book description. + * + * @access public + * @return $description + */ + function getDescription() { + return $this->description; + } + + /** + * Book author or creator, optional. + * The $authorSortKey is basically how the name is to be sorted, usually + * it's "Lastname, First names" where the $author is the straight + * "Firstnames Lastname" + * + * An entity primarily responsible for making the resource. + * + * Examples of a Creator include a person, an organization, or a service. + * Typically, the name of a Creator should be used to indicate the entity. + * + * Used for the dc:creator metadata parameter in the OPF file and the + * docAuthor attribure in the NCX file. + * The sort key is used for the opf:file-as attribute in dc:creator. + * + * @param string $author + * @param string $authorSortKey + * @access public + * @return bool $success + */ + function setAuthor($author, $authorSortKey) { + if ($this->isFinalized) { + return FALSE; + } + $this->author = $author; + $this->authorSortKey = $authorSortKey; + return TRUE; + } + + /** + * Get Book author. + * + * @access public + * @return $author + */ + function getAuthor() { + return $this->author; + } + + /** + * Publisher Information, optional. + * + * An entity responsible for making the resource available. + * + * Examples of a Publisher include a person, an organization, or a service. + * Typically, the name of a Publisher should be used to indicate the entity. + * + * Used for the dc:publisher and dc:relation metadata parameters in the OPF file. + * + * @param string $publisherName + * @param string $publisherURL + * @access public + * @return bool $success + */ + function setPublisher($publisherName, $publisherURL) { + if ($this->isFinalized) { + return FALSE; + } + $this->publisherName = $publisherName; + $this->publisherURL = $publisherURL; + return TRUE; + } + + /** + * Get Book publisherName. + * + * @access public + * @return $publisherName + */ + function getPublisherName() { + return $this->publisherName; + } + + /** + * Get Book publisherURL. + * + * @access public + * @return $publisherURL + */ + function getPublisherURL() { + return $this->publisherURL; + } + + /** + * Release date, optional. If left blank, the time of the finalization will + * be used. + * + * A point or period of time associated with an event in the lifecycle of + * the resource. + * + * Date may be used to express temporal information at any level of + * granularity. Recommended best practice is to use an encoding scheme, + * such as the W3CDTF profile of ISO 8601 [W3CDTF]. + * + * Used for the dc:date metadata parameter in the OPF file + * + * @param long $timestamp + * @access public + * @return bool $success + */ + function setDate($timestamp) { + if ($this->isFinalized) { + return FALSE; + } + $this->date = $timestamp; + $this->opf->date = $timestamp; + return TRUE; + } + + /** + * Get Book date. + * + * @access public + * @return $date + */ + function getDate() { + return $this->date; + } + + /** + * Book (copy)rights, optional. + * + * Information about rights held in and over the resource. + * + * Typically, rights information includes a statement about various + * property rights associated with the resource, including intellectual + * property rights. + * + * Used for the dc:rights metadata parameter in the OPF file + * + * @param string $rightsText + * @access public + * @return bool $success + */ + function setRights($rightsText) { + if ($this->isFinalized) { + return FALSE; + } + $this->rights = $rightsText; + return TRUE; + } + + /** + * Get Book rights. + * + * @access public + * @return $rights + */ + function getRights() { + return $this->rights; + } + + /** + * Add book Subject. + * + * The topic of the resource. + * + * Typically, the subject will be represented using keywords, key phrases, + * or classification codes. Recommended best practice is to use a + * controlled vocabulary. To describe the spatial or temporal topic of the + * resource, use the Coverage element. + * + * @param string $subject + */ + function setSubject($subject) { + if ($this->isFinalized) { + return; + } + $this->opf->addDCMeta(DublinCore::SUBJECT, $this->decodeHtmlEntities($subject)); + } + + /** + * Book source URL, optional. + * + * A related resource from which the described resource is derived. + * + * The described resource may be derived from the related resource in whole + * or in part. Recommended best practice is to identify the related + * resource by means of a string conforming to a formal identification system. + * + * Used for the dc:source metadata parameter in the OPF file + * + * @param string $sourceURL + * @access public + * @return bool $success + */ + function setSourceURL($sourceURL) { + if ($this->isFinalized) { + return FALSE; + } + $this->sourceURL = $sourceURL; + return TRUE; + } + + /** + * Get Book sourceURL. + * + * @access public + * @return $sourceURL + */ + function getSourceURL() { + return $this->sourceURL; + } + + /** + * Coverage, optional. + * + * The spatial or temporal topic of the resource, the spatial applicability + * of the resource, or the jurisdiction under which the resource is relevant. + * + * Spatial topic and spatial applicability may be a named place or a location + * specified by its geographic coordinates. Temporal topic may be a named + * period, date, or date range. A jurisdiction may be a named administrative + * entity or a geographic place to which the resource applies. Recommended + * best practice is to use a controlled vocabulary such as the Thesaurus of + * Geographic Names [TGN]. Where appropriate, named places or time periods + * can be used in preference to numeric identifiers such as sets of + * coordinates or date ranges. + * + * Used for the dc:coverage metadata parameter in the OPF file + * + * Same as ->addDublinCoreMetadata(DublinCore::COVERAGE, $coverage); + * + * @param string $coverage + * @access public + * @return bool $success + */ + function setCoverage($coverage) { + if ($this->isFinalized) { + return FALSE; + } + $this->coverage = $coverage; + return TRUE; + } + + /** + * Get Book coverage. + * + * @access public + * @return $coverage + */ + function getCoverage() { + return $this->coverage; + } + + /** + * Set book Relation. + * + * A related resource. + * + * Recommended best practice is to identify the related resource by means + * of a string conforming to a formal identification system. + * + * @param string $relation + */ + function setRelation($relation) { + if ($this->isFinalized) { + return; + } + $this->relation = $relation; + } + + /** + * Get the book relation. + * + * @return string The relation. + */ + function getRelation() { + return $this->relation; + } + + /** + * Set book Generator. + * + * The generator is a meta tag added to the ncx file, it is not visible + * from within the book, but is a kind of electronic watermark. + * + * @param string $generator + */ + function setGenerator($generator) { + if ($this->isFinalized) { + return; + } + $this->generator = $generator; + } + + /** + * Get the book relation. + * + * @return string The generator identity string. + */ + function getGenerator() { + return $this->generator; + } + + /** + * Set ePub date formate to the short yyyy-mm-dd form, for compliance with + * a bug in EpubCheck, prior to its version 1.1. + * + * The latest version of ePubCheck can be obtained here: + * http://code.google.com/p/epubcheck/ + * + * @access public + * @return bool $success + */ + function setShortDateFormat() { + if ($this->isFinalized) { + return FALSE; + } + $this->dateformat = $this->dateformatShort; + return TRUE; + } + + /** + * @Deprecated + */ + function setIgnoreEmptyBuffer($ignoreEmptyBuffer = TRUE) { + die ("Function was deprecated, functionality is no longer needed."); + } + + /** + * Set the references title for the ePub 3 landmarks section + * + * @param string $referencesTitle + * @param string $referencesId + * @param string $referencesClass + * @return bool + */ + function setReferencesTitle($referencesTitle = "Guide", $referencesId = "", $referencesClass = "references") { + if ($this->isFinalized) { + return FALSE; + } + $this->ncx->referencesTitle = is_string($referencesTitle) ? trim($referencesTitle) : "Guide"; + $this->ncx->referencesId = is_string($referencesId) ? trim($referencesId) : "references"; + $this->ncx->referencesClass = is_string($referencesClass) ? trim($referencesClass) : "references"; + return TRUE; + } + + /** + * Set the references title for the ePub 3 landmarks section + * + * @param bool $referencesTitle + */ + function setisReferencesAddedToToc($isReferencesAddedToToc = TRUE) { + if ($this->isFinalized) { + return FALSE; + } + $this->isReferencesAddedToToc = $isReferencesAddedToToc === TRUE; + return TRUE; + } + + /** + * Get Book status. + * + * @access public + * @return bool + */ + function isFinalized() { + return $this->isFinalized; + } + + /** + * Build the Table of Contents. This is not strictly necessary, as most eReaders will build it from the navigation structure in the .ncx file. + * + * @param string $cssFileName Include a link to this css file in the TOC html. + * @param string $tocCSSClass The TOC is a
    , if you need special formatting, you can add a css class for that div. Default is "toc". + * @param string $title Title of the Table of contents. Default is "Table of Contents". Use this for ie. languages other than English. + * @param bool $addReferences include reference pages in the TOC, using the $referencesOrder array to determine the order of the pages in the TOC. Default is TRUE. + * @param bool $addToIndex Add the TOC to the NCX index at the current leve/position. Default is FALSE + * @param string $tocFileName Change teh default name of the TOC file. The default is "TOC.xhtml" + */ + function buildTOC($cssFileName = NULL, $tocCSSClass = "toc", $title = "Table of Contents", $addReferences = TRUE, $addToIndex = FALSE, $tocFileName = "TOC.xhtml") { + if ($this->isFinalized) { + return FALSE; + } + $this->buildTOC = TRUE; + $this->tocTitle = $title; + $this->tocFileName = $this->normalizeFileName($tocFileName); + if (!empty($cssFileName)) { + $this->tocCSSFileName = $this->normalizeFileName($cssFileName); + } + $this->tocCSSClass = $tocCSSClass; + $this->tocAddReferences = $addReferences; + + $this->opf->addItemRef("ref_" . Reference::TABLE_OF_CONTENTS, FALSE); + $this->opf->addReference(Reference::TABLE_OF_CONTENTS, $title, $this->tocFileName); + + if ($addToIndex) { + $navPoint = new NavPoint($this->decodeHtmlEntities($title), $this->tocFileName, "ref_" . Reference::TABLE_OF_CONTENTS); + $this->ncx->addNavPoint($navPoint); + } else { + $this->ncx->referencesList[Reference::TABLE_OF_CONTENTS] = $this->tocFileName; + $this->ncx->referencesName[Reference::TABLE_OF_CONTENTS] = $title; + } + } + + private function finalizeTOC() { + if (!$this->buildTOC) { + return FALSE; + } + + if (empty($this->tocTitle)) { + $this->tocTitle = "Table of Contents"; + } + + $tocData = "\n"; + + if ($this->isEPubVersion2()) { + $tocData .= "\n" + . "\n" + . "\n\n"; + } else { + $tocData .= "\n" + . "\n\n"; + } + + if (!empty($this->tocCssFileName)) { + $tocData .= "tocCssFileName . "\" />\n"; + } + + $tocData .= "" . $this->tocTitle . "\n" + . "\n" + . "\n" + . "

    " . $this->tocTitle . "

    \ntocCSSClass)) { + $tocData .= " class=\"" . $this->tocCSSClass . "\""; + } + $tocData .= ">\n"; + + while (list($item, $descriptive) = each($this->referencesOrder)) { + if ($item === "text") { + while (list($chapterName, $navPoint) = each($this->ncx->chapterList)) { + $fileName = $navPoint->getContentSrc(); + $level = $navPoint->getLevel() -2; + $tocData .= "\t

    " . str_repeat("      ", $level) . "" . $chapterName . "

    \n"; + } + } else if ($this->tocAddReferences === TRUE) { + if (array_key_exists($item, $this->ncx->referencesList)) { + $tocData .= "\t

    ncx->referencesList[$item] . "\">" . $descriptive . "

    \n"; + } else if ($item === "toc") { + $tocData .= "\t

    " . $this->tocTitle . "

    \n"; + } else if ($item === "cover" && $this->isCoverImageSet) { + $tocData .= "\t

    " . $descriptive . "

    \n"; + } + } + } + $tocData .= "
    \n\n\n"; + + $this->addReferencePage($this->tocTitle, $this->tocFileName, $tocData, Reference::TABLE_OF_CONTENTS); + + } + + /** + * @return bool + */ + function isEPubVersion2() { + return $this->bookVersion === EPub::BOOK_VERSION_EPUB2; + } + + /** + * @param string $cssFileName + * @param string $title + * @return string + */ + function buildEPub3TOC($cssFileName = NULL, $title = "Table of Contents") { + $this->ncx->referencesOrder = $this->referencesOrder; + $this->ncx->setDocTitle($this->decodeHtmlEntities($this->title)); + return $this->ncx->finalizeEPub3($title, $cssFileName); + } + + /** + * @param string $fileName + * @param string $tocData + * @return bool + */ + function addEPub3TOC($fileName, $tocData) { + if ($this->isEPubVersion2() || $this->isFinalized || array_key_exists($fileName, $this->fileList)) { + return FALSE; + } + $fileName = Zip::getRelativePath($fileName); + $fileName = preg_replace('#^[/\.]+#i', "", $fileName); + + $this->zip->addFile($tocData, $this->bookRoot.$fileName); + + $this->fileList[$fileName] = $fileName; + $this->opf->addItem("toc", $fileName, "application/xhtml+xml", "nav"); + return TRUE; + } + + /** + * Check for mandatory parameters and finalize the e-book. + * Once finalized, the book is locked for further additions. + * + * @return bool $success + */ + function finalize() { + if ($this->isFinalized || $this->chapterCount == 0 || empty($this->title) || empty($this->language)) { + return FALSE; + } + + if (empty($this->identifier) || empty($this->identifierType)) { + $this->setIdentifier($this->createUUID(4), EPub::IDENTIFIER_UUID); + } + + if ($this->date == 0) { + $this->date = time(); + } + + if (empty($this->sourceURL)) { + $this->sourceURL = $this->getCurrentPageURL(); + } + + if (empty($this->publisherURL)) { + $this->sourceURL = $this->getCurrentServerURL(); + } + + // Generate OPF data: + $this->opf->setIdent("BookId"); + $this->opf->initialize($this->title, $this->language, $this->identifier, $this->identifierType); + + $DCdate = new DublinCore(DublinCore::DATE, gmdate($this->dateformat, $this->date)); + $DCdate->addOpfAttr("event", "publication"); + $this->opf->metadata->addDublinCore($DCdate); + + if (!empty($this->description)) { + $this->opf->addDCMeta(DublinCore::DESCRIPTION, $this->decodeHtmlEntities($this->description)); + } + + if (!empty($this->publisherName)) { + $this->opf->addDCMeta(DublinCore::PUBLISHER, $this->decodeHtmlEntities($this->publisherName)); + } + + if (!empty($this->publisherURL)) { + $this->opf->addDCMeta(DublinCore::RELATION, $this->decodeHtmlEntities($this->publisherURL)); + } + + if (!empty($this->author)) { + $author = $this->decodeHtmlEntities($this->author); + $this->opf->addCreator($author, $this->decodeHtmlEntities($this->authorSortKey), MarcCode::AUTHOR); + $this->ncx->setDocAuthor($author); + } + + if (!empty($this->rights)) { + $this->opf->addDCMeta(DublinCore::RIGHTS, $this->decodeHtmlEntities($this->rights)); + } + + if (!empty($this->coverage)) { + $this->opf->addDCMeta(DublinCore::COVERAGE, $this->decodeHtmlEntities($this->coverage)); + } + + if (!empty($this->sourceURL)) { + $this->opf->addDCMeta(DublinCore::SOURCE, $this->sourceURL); + } + + if (!empty($this->relation)) { + $this->opf->addDCMeta(DublinCore::RELATION, $this->decodeHtmlEntities($this->relation)); + } + + if ($this->isCoverImageSet) { + $this->opf->addMeta("cover", "coverImage"); + } + + if (!empty($this->generator)) { + $gen = $this->decodeHtmlEntities($this->generator); + $this->opf->addMeta("generator", $gen); + $this->ncx->addMetaEntry("dtb:generator", $gen); + } + + if ($this->EPubMark) { + $this->opf->addMeta("generator", "EPub (Version " . self::VERSION . ") by A. Grandt, http://www.phpclasses.org/package/6115"); + } + + reset($this->ncx->chapterList); + list($firstChapterName, $firstChapterNavPoint) = each($this->ncx->chapterList); + $firstChapterFileName = $firstChapterNavPoint->getContentSrc(); + $this->opf->addReference(Reference::TEXT, $this->decodeHtmlEntities($firstChapterName), $firstChapterFileName); + + $this->ncx->setUid($this->identifier); + + $this->ncx->setDocTitle($this->decodeHtmlEntities($this->title)); + + $this->ncx->referencesOrder = $this->referencesOrder; + if ($this->isReferencesAddedToToc) { + $this->ncx->finalizeReferences(); + } + + $this->finalizeTOC(); + + if (!$this->isEPubVersion2()) { + $this->addEPub3TOC("epub3toc.xhtml", $this->buildEPub3TOC()); + } + + $opfFinal = $this->fixEncoding($this->opf->finalize()); + $ncxFinal = $this->fixEncoding($this->ncx->finalize()); + + if (mb_detect_encoding($opfFinal, 'UTF-8', true) === "UTF-8") { + $this->zip->addFile($opfFinal, $this->bookRoot."book.opf"); + } else { + $this->zip->addFile(mb_convert_encoding($opfFinal, "UTF-8"), $this->bookRoot."book.opf"); + } + + if (mb_detect_encoding($ncxFinal, 'UTF-8', true) === "UTF-8") { + $this->zip->addFile($ncxFinal, $this->bookRoot."book.ncx"); + } else { + $this->zip->addFile(mb_convert_encoding($ncxFinal, "UTF-8"), $this->bookRoot."book.ncx"); + } + + $this->opf = NULL; + $this->ncx = NULL; + + $this->isFinalized = TRUE; + return TRUE; + } + + /** + * Ensure the encoded string is a valid UTF-8 string. + * + * Note, that a mb_detect_encoding on the returned string will still return ASCII if the entire string is comprized of characters in the 1-127 range. + * + * @link: http://snippetdb.com/php/convert-string-to-utf-8-for-mysql + * @param string $in_str + * @return string converted string. + */ + function fixEncoding($in_str) { + if (mb_detect_encoding($in_str) == "UTF-8" && mb_check_encoding($in_str,"UTF-8")) { + return $in_str; + } else { + return utf8_encode($in_str); + } + } + + /** + * Return the finalized book. + * + * @return string with the book in binary form. + */ + function getBook() { + if (!$this->isFinalized) { + $this->finalize(); + } + + return $this->zip->getZipData(); + } + + /** + * Remove disallowed characters from string to get a nearly safe filename + * + * @param string $fileName + * @return mixed|string + */ + function sanitizeFileName($fileName) { + $fileName1 = str_replace($this->forbiddenCharacters, '', $fileName); + $fileName2 = preg_replace('/[\s-]+/', '-', $fileName1); + return trim($fileName2, '.-_'); + + } + + /** + * Cleanup the filepath, and remove leading . and / characters. + * + * Sometimes, when a path is generated from multiple fragments, + * you can get something like "../data/html/../images/image.jpeg" + * ePub files don't work well with that, this will normalize that + * example path to "data/images/image.jpeg" + * + * @param string $fileName + * @return string normalized filename + */ + function normalizeFileName($fileName) { + return preg_replace('#^[/\.]+#i', "", Zip::getRelativePath($fileName)); + } + + /** + * Save the ePub file to local disk. + * + * @param string $fileName + * @param string $baseDir If empty baseDir is absolute to server path, if omitted it's relative to script path + * @return The sent file name if successfull, FALSE if it failed. + */ + function saveBook($fileName, $baseDir = '.') { + + // Make fileName safe + $fileName = $this->sanitizeFileName($fileName); + + // Finalize book, if it's not done already + if (!$this->isFinalized) { + $this->finalize(); + } + + if (stripos(strrev($fileName), "bupe.") !== 0) { + $fileName .= ".epub"; + } + + // Try to open file access + $fh = fopen($baseDir.'/'.$fileName, "w"); + + if ($fh) { + fputs($fh, $this->getBook()); + fclose($fh); + + // if file is written return TRUE + return $fileName; + } + + // return FALSE by default + return FALSE; + } + + /** + * Return the finalized book size. + * + * @return string + */ + function getBookSize() { + if (!$this->isFinalized) { + $this->finalize(); + } + + return $this->zip->getArchiveSize(); + } + + /** + * Send the book as a zip download + * + * Sending will fail if the output buffer is in use. You can override this limit by + * calling setIgnoreEmptyBuffer(TRUE), though the function will still fail if that + * buffer is not empty. + * + * @param string $fileName The name of the book without the .epub at the end. + * @return The sent file name if successfull, FALSE if it failed. + */ + function sendBook($fileName) { + if (!$this->isFinalized) { + $this->finalize(); + } + + if (stripos(strrev($fileName), "bupe.") !== 0) { + $fileName .= ".epub"; + } + + if (TRUE === $this->zip->sendZip($fileName, "application/epub+zip")) { + return $fileName; + } + return FALSE; + } + + /** + * Generates an UUID. + * + * Default version (4) will generate a random UUID, version 3 will URL based UUID. + * + * Added for convinience + * + * @param int $bookVersion UUID version to retrieve, See lib.uuid.manual.html for details. + * @param string $url + * @return string The formatted uuid + */ + function createUUID($bookVersion = 4, $url = NULL) { + include_once("lib.uuid.php"); + return UUID::mint($bookVersion, $url, UUID::nsURL); + } + + /** + * Get the url of the current page. + * Example use: Default Source URL + * + * $return string Page URL. + */ + function getCurrentPageURL() { + $pageURL = $this->getCurrentServerURL() . filter_input(INPUT_SERVER, "REQUEST_URI"); + return $pageURL; + } + + /** + * Get the url of the server. + * Example use: Default Publisher URL + * + * $return string Server URL. + */ + function getCurrentServerURL() { + $serverURL = 'http'; + $https = filter_input(INPUT_SERVER, "HTTPS"); + $port = filter_input(INPUT_SERVER, "SERVER_PORT"); + + if ($https === "on") { + $serverURL .= "s"; + } + $serverURL .= "://" . filter_input(INPUT_SERVER, "SERVER_NAME"); + if ($port != "80") { + $serverURL .= ":" . $port; + } + return $serverURL . '/'; + } + + /** + * Try to determine the mimetype of the file path. + * + * @param string $source Path + * @return string mimetype, or FALSE. + */ + function getMime($source) { + return $this->mimetypes[pathinfo($source, PATHINFO_EXTENSION)]; + } + + /** + * Get an image from a file or url, return it resized if the image exceeds the $maxImageWidth or $maxImageHeight directives. + * + * The return value is an array. + * ['width'] is the width of the image. + * ['height'] is the height of the image. + * ['mime'] is the mime type of the image. Resized images are always in jpeg format. + * ['image'] is the image data. + * ['ext'] is the extension of the image file. + * + * @param string $source path or url to file. + * $return array + */ + function getImage($source) { + $width = -1; + $height = -1; + $mime = "application/octet-stream"; + $type = FALSE; + $ext = ""; + + + $image = $this->getFileContents($source); + + if ($image !== FALSE && strlen($image) > 0) { + $imageFile = imagecreatefromstring($image); + if ($imageFile !== false) { + $width = ImageSX($imageFile); + $height = ImageSY($imageFile); + } + if ($this->isExifInstalled) { + @$type = exif_imagetype($source); + $mime = image_type_to_mime_type($type); + } + if ($mime === "application/octet-stream") { + $mime = $this->image_file_type_from_binary($image); + } + if ($mime === "application/octet-stream") { + $mime = $this->getMimeTypeFromUrl($source); + } + } else { + return FALSE; + } + + if ($width <= 0 || $height <= 0) { + return FALSE; + } + + $ratio = 1; + + if ($this->isGdInstalled) { + if ($width > $this->maxImageWidth) { + $ratio = $this->maxImageWidth/$width; + } + if ($height*$ratio > $this->maxImageHeight) { + $ratio = $this->maxImageHeight/$height; + } + + if ($ratio < 1 || empty($mime) || ($this->isGifImagesEnabled !== FALSE && $mime == "image/gif")) { + $image_o = imagecreatefromstring($image); + $image_p = imagecreatetruecolor($width*$ratio, $height*$ratio); + + if ($mime == "image/png") { + imagealphablending($image_p, false); + imagesavealpha($image_p, true); + imagealphablending($image_o, true); + + imagecopyresampled($image_p, $image_o, 0, 0, 0, 0, ($width*$ratio), ($height*$ratio), $width, $height); + ob_start(); + imagepng($image_p, NULL, 9); + $image = ob_get_contents(); + ob_end_clean(); + + $ext = "png"; + } else { + imagecopyresampled($image_p, $image_o, 0, 0, 0, 0, ($width*$ratio), ($height*$ratio), $width, $height); + ob_start(); + imagejpeg($image_p, NULL, 80); + $image = ob_get_contents(); + ob_end_clean(); + + $mime = "image/jpeg"; + $ext = "jpg"; + } + imagedestroy($image_o); + imagedestroy($image_p); + } + } + + if ($ext === "") { + static $mimeToExt = array ( + 'image/jpeg' => 'jpg', + 'image/gif' => 'gif', + 'image/png' => 'png' + ); + + if (isset($mimeToExt[$mime])) { + $ext = $mimeToExt[$mime]; + } + } + + $rv = array(); + $rv['width'] = $width*$ratio; + $rv['height'] = $height*$ratio; + $rv['mime'] = $mime; + $rv['image'] = $image; + $rv['ext'] = $ext; + + return $rv; + } + + /** + * Get file contents, using curl if available, else file_get_contents + * + * @param string $source + * @return bool + */ + function getFileContents($source, $toTempFile = FALSE) { + $isExternal = preg_match('#^(http|ftp)s?://#i', $source) == 1; + + if ($isExternal && $this->isCurlInstalled) { + $ch = curl_init(); + $outFile = NULL; + $fp = NULL; + $res = FALSE; + $info = array('http_code' => 500); + + curl_setopt($ch, CURLOPT_HEADER, 0); + curl_setopt($ch, CURLOPT_URL, str_replace(" ","%20",$source)); + curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); + curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true); + curl_setopt($ch, CURLOPT_BUFFERSIZE, 4096); + + if ($toTempFile) { + $outFile = tempnam(sys_get_temp_dir(), "EPub_v" . EPub::VERSION . "_"); + $fp = fopen($outFile, "w+b"); + curl_setopt($ch, CURLOPT_FILE, $fp); + + $res = curl_exec($ch); + $info = curl_getinfo($ch); + + curl_close($ch); + fclose($fp); + } else { + $res = curl_exec($ch); + $info = curl_getinfo($ch); + + curl_close($ch); + } + + if ($info['http_code'] == 200 && $res != false) { + if ($toTempFile) { + return $outFile; + } + return $res; + } + return FALSE; + } + + if ($this->isFileGetContentsInstalled && (!$isExternal || $this->isFileGetContentsExtInstalled)) { + @$data = file_get_contents($source); + return $data; + } + return FALSE; + } + + /** + * get mime type from image data + * + * By fireweasel found on http://stackoverflow.com/questions/2207095/get-image-mimetype-from-resource-in-php-gd + * @staticvar array $type + * @param object $binary + * @return string + */ + function image_file_type_from_binary($binary) { + $hits = 0; + if (!preg_match( + '/\A(?:(\xff\xd8\xff)|(GIF8[79]a)|(\x89PNG\x0d\x0a)|(BM)|(\x49\x49(?:\x2a\x00|\x00\x4a))|(FORM.{4}ILBM))/', + $binary, $hits)) { + return 'application/octet-stream'; + } + static $type = array ( + 1 => 'image/jpeg', + 2 => 'image/gif', + 3 => 'image/png', + 4 => 'image/x-windows-bmp', + 5 => 'image/tiff', + 6 => 'image/x-ilbm', + ); + return $type[count($hits) - 1]; + } + + /** + * @param string $source URL Source + * @return string MimeType + */ + function getMimeTypeFromUrl($source) { + $ext = FALSE; + + $srev = strrev($source); + $pos = strpos($srev, "?"); + if ($pos !== FALSE) { + $srev = substr($srev, $pos+1); + } + + $pos = strpos($srev, "."); + if ($pos !== FALSE) { + $ext = strtolower(strrev(substr($srev, 0, $pos))); + } + + if ($ext !== FALSE) { + return $this->getMimeTypeFromExtension($ext); + } + return "application/octet-stream"; + } + + /** + * @param string $ext Extension + * @return string MimeType + */ + function getMimeTypeFromExtension($ext) { + switch ($ext) { + case "jpg": + case "jpe": + case "jpeg": + return 'image/jpeg'; + case "gif": + return 'image/gif'; + case "png": + return 'image/png'; + case "bmp": + return 'image/x-windows-bmp'; + case "tif": + case "tiff": + case "cpt": + return 'image/tiff'; + case "lbm": + case "ilbm": + return 'image/x-ilbm'; + default: + return "application/octet-stream"; + } + } + + /** + * Encode html code to use html entities, safeguarding it from potential character encoding peoblems + * This function is a bit different from the vanilla htmlentities function in that it does not encode html tags. + * + * The regexp is taken from the PHP Manual discussion, it was written by user "busbyjon". + * http://www.php.net/manual/en/function.htmlentities.php#90111 + * + * @param string $string string to encode. + */ + public function encodeHtml($string) { + $string = strtr($string, $this->html_encoding_characters); + + //return preg_replace("/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,5};)/", "&\\1", $string); + //return preg_replace("/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,5};)/", "&", $string); + return $string; + } + + /** + * Helper function to create a DOM fragment with given markup. + * + * @author Adam Schmalhofer + * + * @param DOMDocument $dom + * @param string $markup + * @return DOMNode fragment in a node. + */ + protected function createDomFragment($dom, $markup) { + $node = $dom->createDocumentFragment(); + $node->appendXML($markup); + return $node; + } + + /** + * Retrieve an array of file names currently added to the book. + * $key is the filename used in the book + * $value is the original filename, will be the same as $key for most entries + * + * @return array file list + */ + function getFileList() { + return $this->fileList; + } + + /** + * @deprecated Use Zip::getRelativePath($relPath) instead. + */ + function relPath($relPath) { + die ("Function was deprecated, use Zip::getRelativePath(\$relPath); instead"); + } + + /** + * Set default chapter target size. + * Default is 250000 bytes, and minimum is 10240 bytes. + * + * @param int $size segment size in bytes + * @return void + */ + function setSplitSize($size) { + $this->splitDefaultSize = (int)$size; + if ($size < 10240) { + $this->splitDefaultSize = 10240; // Making the file smaller than 10k is not a good idea. + } + } + + /** + * Get the chapter target size. + * + * @return $size + */ + function getSplitSize() { + return $this->splitDefaultSize; + } + + /** + * Remove all non essential html tags and entities. + * + * @global type $htmlEntities + * @param string $string + * @return string with the stripped entities. + */ + function decodeHtmlEntities($string) { + global $htmlEntities; + + $string = preg_replace('~\s*\s*~i', "\n", $string); + $string = preg_replace('~\s*\s*~i', "\n\n", $string); + $string = preg_replace('~<[^>]*>~', '', $string); + + $string = strtr($string, $htmlEntities); + + $string = str_replace('&', '&', $string); + $string = str_replace('&amp;', '&', $string); + $string = preg_replace('~&(#x*[a-fA-F0-9]+;)~', '&\1', $string); + $string = str_replace('<', '<', $string); + $string = str_replace('>', '>', $string); + + return $string; + } + + /** + * Simply remove all HTML tags, brute force and no finesse. + * + * @param string $string html + * @return string + */ + function html2text($string) { + return preg_replace('~<[^>]*>~', '', $string); + } + + /** + * @return string + */ + function getLog() { + return $this->log->getLog(); + } +} diff --git a/inc/3rdparty/libraries/PHPePub/EPubChapterSplitter.php b/inc/3rdparty/libraries/PHPePub/EPubChapterSplitter.php new file mode 100644 index 00000000..1d44f238 --- /dev/null +++ b/inc/3rdparty/libraries/PHPePub/EPubChapterSplitter.php @@ -0,0 +1,201 @@ + + * @copyright 2009-2014 A. Grandt + * @license GNU LGPL 2.1 + * @link http://www.phpclasses.org/package/6115 + * @link https://github.com/Grandt/PHPePub + * @version 3.20 + */ +class EPubChapterSplitter { + const VERSION = 3.20; + + private $splitDefaultSize = 250000; + private $bookVersion = EPub::BOOK_VERSION_EPUB2; + + /** + * + * Enter description here ... + * + * @param unknown_type $ident + */ + function setVersion($bookVersion) { + $this->bookVersion = is_string($bookVersion) ? trim($bookVersion) : EPub::BOOK_VERSION_EPUB2; + } + + /** + * Set default chapter target size. + * Default is 250000 bytes, and minimum is 10240 bytes. + * + * @param $size segment size in bytes + * @return void + */ + function setSplitSize($size) { + $this->splitDefaultSize = (int)$size; + if ($size < 10240) { + $this->splitDefaultSize = 10240; // Making the file smaller than 10k is not a good idea. + } + } + + /** + * Get the chapter target size. + * + * @return $size + */ + function getSplitSize() { + return $this->splitDefaultSize; + } + + /** + * Split $chapter into multiple parts. + * + * The search string can either be a regular string or a PHP PECL Regular Expression pattern as defined here: http://www.php.net/manual/en/pcre.pattern.php + * If the search string is a regular string, the matching will be for lines in the HTML starting with the string given + * + * @param String $chapter XHTML file + * @param Bool $splitOnSearchString Split on chapter boundaries, Splitting on search strings disables the split size check. + * @param String $searchString Chapter string to search for can be fixed text, or a regular expression pattern. + * + * @return array with 1 or more parts + */ + function splitChapter($chapter, $splitOnSearchString = false, $searchString = '/^Chapter\\ /i') { + $chapterData = array(); + $isSearchRegexp = $splitOnSearchString && (preg_match('#^(\D|\S|\W).+\1[imsxeADSUXJu]*$#m', $searchString) == 1); + if ($splitOnSearchString && !$isSearchRegexp) { + $searchString = '#^<.+?>' . preg_quote($searchString, '#') . "#"; + } + + if (!$splitOnSearchString && strlen($chapter) <= $this->splitDefaultSize) { + return array($chapter); + } + + $xmlDoc = new DOMDocument(); + @$xmlDoc->loadHTML($chapter); + + $head = $xmlDoc->getElementsByTagName("head"); + $body = $xmlDoc->getElementsByTagName("body"); + + $htmlPos = stripos($chapter, "", $htmlPos); + $newXML = substr($chapter, 0, $htmlEndPos+1) . "\n"; + if (strpos(trim($newXML), "\n" . $newXML; + } + $headerLength = strlen($newXML); + + $files = array(); + $chapterNames = array(); + $domDepth = 0; + $domPath = array(); + $domClonedPath = array(); + + $curFile = $xmlDoc->createDocumentFragment(); + $files[] = $curFile; + $curParent = $curFile; + $curSize = 0; + + $bodyLen = strlen($xmlDoc->saveXML($body->item(0))); + $headLen = strlen($xmlDoc->saveXML($head->item(0))) + $headerLength; + + $partSize = $this->splitDefaultSize - $headLen; + + if ($bodyLen > $partSize) { + $parts = ceil($bodyLen / $partSize); + $partSize = ($bodyLen / $parts) - $headLen; + } + + $node = $body->item(0)->firstChild; + + do { + $nodeData = $xmlDoc->saveXML($node); + $nodeLen = strlen($nodeData); + + if ($nodeLen > $partSize && $node->hasChildNodes()) { + $domPath[] = $node; + $domClonedPath[] = $node->cloneNode(false); + $domDepth++; + + $node = $node->firstChild; + } + + $node2 = $node->nextSibling; + + if ($node != null && $node->nodeName != "#text") { + $doSplit = false; + if ($splitOnSearchString) { + $doSplit = preg_match($searchString, $nodeData) == 1; + if ($doSplit) { + $chapterNames[] = trim($nodeData); + } + } + + if ($curSize > 0 && ($doSplit || (!$splitOnSearchString && $curSize + $nodeLen > $partSize))) { + $curFile = $xmlDoc->createDocumentFragment(); + $files[] = $curFile; + $curParent = $curFile; + if ($domDepth > 0) { + reset($domPath); + reset($domClonedPath); + $oneDomClonedPath = each($domClonedPath); + while ($oneDomClonedPath) { + list($k, $v) = $oneDomClonedPath; + $newParent = $v->cloneNode(false); + $curParent->appendChild($newParent); + $curParent = $newParent; + $oneDomClonedPath = each($domClonedPath); + } + } + $curSize = strlen($xmlDoc->saveXML($curFile)); + } + $curParent->appendChild($node->cloneNode(true)); + $curSize += $nodeLen; + } + + $node = $node2; + while ($node == null && $domDepth > 0) { + $domDepth--; + $node = end($domPath)->nextSibling; + array_pop($domPath); + array_pop($domClonedPath); + $curParent = $curParent->parentNode; + } + } while ($node != null); + + $curFile = null; + $curSize = 0; + + $xml = new DOMDocument('1.0', $xmlDoc->xmlEncoding); + $xml->lookupPrefix("http://www.w3.org/1999/xhtml"); + $xml->preserveWhiteSpace = false; + $xml->formatOutput = true; + + for ($idx = 0; $idx < count($files); $idx++) { + $xml2Doc = new DOMDocument('1.0', $xmlDoc->xmlEncoding); + $xml2Doc->lookupPrefix("http://www.w3.org/1999/xhtml"); + $xml2Doc->loadXML($newXML); + $html = $xml2Doc->getElementsByTagName("html")->item(0); + $html->appendChild($xml2Doc->importNode($head->item(0), true)); + $body = $xml2Doc->createElement("body"); + $html->appendChild($body); + $body->appendChild($xml2Doc->importNode($files[$idx], true)); + + // force pretty printing and correct formatting, should not be needed, but it is. + $xml->loadXML($xml2Doc->saveXML()); + + $doc = $xml->saveXML(); + + if ($this->bookVersion === EPub::BOOK_VERSION_EPUB3) { + $doc = preg_replace('#^\s*\s*#im', '', $doc); + } + + $chapterData[$splitOnSearchString ? $chapterNames[$idx] : $idx] = $doc; + } + + return $chapterData; + } +} +?> diff --git a/inc/3rdparty/libraries/PHPePub/Logger.php b/inc/3rdparty/libraries/PHPePub/Logger.php new file mode 100644 index 00000000..314019cb --- /dev/null +++ b/inc/3rdparty/libraries/PHPePub/Logger.php @@ -0,0 +1,92 @@ + + * @copyright 2012-2013 A. Grandt + * @license GNU LGPL, Attribution required for commercial implementations, requested for everything else. + * @version 1.00 + */ +class Logger { + const VERSION = 1.00; + + private $log = ""; + private $tStart; + private $tLast; + private $name = NULL; + private $isLogging = FALSE; + private $isDebugging = FALSE; + + /** + * Class constructor. + * + * @return void + */ + function __construct($name = NULL, $isLogging = FALSE) { + if ($name === NULL) { + $this->name = ""; + } else { + $this->name = $name . " : "; + } + $this->isLogging = $isLogging; + $this->start(); + } + + /** + * Class destructor + * + * @return void + * @TODO make sure elements in the destructor match the current class elements + */ + function __destruct() { + unset($this->log); + } + + function start() { + /* Prepare Logging. Just in case it's used. later */ + if ($this->isLogging) { + $this->tStart = gettimeofday(); + $this->tLast = $this->tStart; + $this->log = "

    Log: " . $this->name . "

    \n
    Started: " . gmdate("D, d M Y H:i:s T", $this->tStart['sec']) . "\n Δ Start ;  Δ Last  ;";
+			$this->logLine("Start");
+		}
+    }
+
+    function dumpInstalledModules() {
+        if ($this->isLogging) {
+            $isCurlInstalled = extension_loaded('curl') && function_exists('curl_version');
+            $isGdInstalled = extension_loaded('gd') && function_exists('gd_info');
+            $isExifInstalled = extension_loaded('exif') && function_exists('exif_imagetype');
+            $isFileGetContentsInstalled = function_exists('file_get_contents');
+            $isFileGetContentsExtInstalled = $isFileGetContentsInstalled && ini_get('allow_url_fopen');
+
+            $this->logLine("isCurlInstalled...............: " . ($isCurlInstalled ? "Yes" : "No"));
+            $this->logLine("isGdInstalled.................: " . ($isGdInstalled ? "Yes" : "No"));
+            $this->logLine("isExifInstalled...............: " . ($isExifInstalled ? "Yes" : "No"));
+            $this->logLine("isFileGetContentsInstalled....: " . ($isFileGetContentsInstalled ? "Yes" : "No"));
+            $this->logLine("isFileGetContentsExtInstalled.: " . ($isFileGetContentsExtInstalled ? "Yes" : "No"));
+        }
+    }
+
+    function logLine($line) {
+        if ($this->isLogging) {
+            $tTemp = gettimeofday();
+            $tS = $this->tStart['sec'] + (((int)($this->tStart['usec']/100))/10000);
+            $tL = $this->tLast['sec'] + (((int)($this->tLast['usec']/100))/10000);
+            $tT = $tTemp['sec'] + (((int)($tTemp['usec']/100))/10000);
+
+			$logline = sprintf("\n+%08.04f; +%08.04f; ", ($tT-$tS), ($tT-$tL)) . $this->name . $line;
+            $this->log .= $logline;
+            $this->tLast = $tTemp;
+
+		    if ($this->isDebugging) {
+				echo "
    " . $logline . "\n
    \n";
+			}
+        }
+    }
+
+    function getLog() {
+        return $this->log;
+    }
+}
+?>
\ No newline at end of file
diff --git a/inc/3rdparty/libraries/PHPePub/Zip.php b/inc/3rdparty/libraries/PHPePub/Zip.php
new file mode 100644
index 00000000..01e03566
--- /dev/null
+++ b/inc/3rdparty/libraries/PHPePub/Zip.php
@@ -0,0 +1,818 @@
+
+ * @copyright 2009-2014 A. Grandt
+ * @license GNU LGPL 2.1
+ * @link http://www.phpclasses.org/package/6110
+ * @link https://github.com/Grandt/PHPZip
+ * @version 1.60
+ */
+class Zip {
+    const VERSION = 1.60;
+
+    const ZIP_LOCAL_FILE_HEADER = "\x50\x4b\x03\x04"; // Local file header signature
+    const ZIP_CENTRAL_FILE_HEADER = "\x50\x4b\x01\x02"; // Central file header signature
+    const ZIP_END_OF_CENTRAL_DIRECTORY = "\x50\x4b\x05\x06\x00\x00\x00\x00"; //end of Central directory record
+
+    const EXT_FILE_ATTR_DIR = 010173200020;  // Permission 755 drwxr-xr-x = (((S_IFDIR | 0755) << 16) | S_DOS_D);
+    const EXT_FILE_ATTR_FILE = 020151000040; // Permission 644 -rw-r--r-- = (((S_IFREG | 0644) << 16) | S_DOS_A);
+
+    const ATTR_VERSION_TO_EXTRACT = "\x14\x00"; // Version needed to extract
+    const ATTR_MADE_BY_VERSION = "\x1E\x03"; // Made By Version
+
+	// Unix file types
+	const S_IFIFO  = 0010000; // named pipe (fifo)
+	const S_IFCHR  = 0020000; // character special
+	const S_IFDIR  = 0040000; // directory
+	const S_IFBLK  = 0060000; // block special
+	const S_IFREG  = 0100000; // regular
+	const S_IFLNK  = 0120000; // symbolic link
+	const S_IFSOCK = 0140000; // socket
+
+	// setuid/setgid/sticky bits, the same as for chmod:
+
+	const S_ISUID  = 0004000; // set user id on execution
+	const S_ISGID  = 0002000; // set group id on execution
+	const S_ISTXT  = 0001000; // sticky bit
+
+	// And of course, the other 12 bits are for the permissions, the same as for chmod:
+	// When addding these up, you can also just write the permissions as a simgle octal number
+	// ie. 0755. The leading 0 specifies octal notation.
+	const S_IRWXU  = 0000700; // RWX mask for owner
+	const S_IRUSR  = 0000400; // R for owner
+	const S_IWUSR  = 0000200; // W for owner
+	const S_IXUSR  = 0000100; // X for owner
+	const S_IRWXG  = 0000070; // RWX mask for group
+	const S_IRGRP  = 0000040; // R for group
+	const S_IWGRP  = 0000020; // W for group
+	const S_IXGRP  = 0000010; // X for group
+	const S_IRWXO  = 0000007; // RWX mask for other
+	const S_IROTH  = 0000004; // R for other
+	const S_IWOTH  = 0000002; // W for other
+	const S_IXOTH  = 0000001; // X for other
+	const S_ISVTX  = 0001000; // save swapped text even after use
+
+	// Filetype, sticky and permissions are added up, and shifted 16 bits left BEFORE adding the DOS flags.
+
+	// DOS file type flags, we really only use the S_DOS_D flag.
+
+	const S_DOS_A  = 0000040; // DOS flag for Archive
+	const S_DOS_D  = 0000020; // DOS flag for Directory
+	const S_DOS_V  = 0000010; // DOS flag for Volume
+	const S_DOS_S  = 0000004; // DOS flag for System
+	const S_DOS_H  = 0000002; // DOS flag for Hidden
+	const S_DOS_R  = 0000001; // DOS flag for Read Only
+
+    private $zipMemoryThreshold = 1048576; // Autocreate tempfile if the zip data exceeds 1048576 bytes (1 MB)
+
+    private $zipData = NULL;
+    private $zipFile = NULL;
+    private $zipComment = NULL;
+    private $cdRec = array(); // central directory
+    private $offset = 0;
+    private $isFinalized = FALSE;
+    private $addExtraField = TRUE;
+
+    private $streamChunkSize = 65536;
+    private $streamFilePath = NULL;
+    private $streamTimestamp = NULL;
+    private $streamFileComment = NULL;
+    private $streamFile = NULL;
+    private $streamData = NULL;
+    private $streamFileLength = 0;
+	private $streamExtFileAttr = null;
+
+    /**
+     * Constructor.
+     *
+     * @param boolean $useZipFile Write temp zip data to tempFile? Default FALSE
+     */
+    function __construct($useZipFile = FALSE) {
+        if ($useZipFile) {
+            $this->zipFile = tmpfile();
+        } else {
+            $this->zipData = "";
+        }
+    }
+
+    function __destruct() {
+        if (is_resource($this->zipFile)) {
+            fclose($this->zipFile);
+        }
+        $this->zipData = NULL;
+    }
+
+    /**
+     * Extra fields on the Zip directory records are Unix time codes needed for compatibility on the default Mac zip archive tool.
+     * These are enabled as default, as they do no harm elsewhere and only add 26 bytes per file added.
+     *
+     * @param bool $setExtraField TRUE (default) will enable adding of extra fields, anything else will disable it.
+     */
+    function setExtraField($setExtraField = TRUE) {
+        $this->addExtraField = ($setExtraField === TRUE);
+    }
+
+    /**
+     * Set Zip archive comment.
+     *
+     * @param string $newComment New comment. NULL to clear.
+     * @return bool $success
+     */
+    public function setComment($newComment = NULL) {
+        if ($this->isFinalized) {
+            return FALSE;
+        }
+        $this->zipComment = $newComment;
+
+        return TRUE;
+    }
+
+    /**
+     * Set zip file to write zip data to.
+     * This will cause all present and future data written to this class to be written to this file.
+     * This can be used at any time, even after the Zip Archive have been finalized. Any previous file will be closed.
+     * Warning: If the given file already exists, it will be overwritten.
+     *
+     * @param string $fileName
+     * @return bool $success
+     */
+    public function setZipFile($fileName) {
+        if (is_file($fileName)) {
+            unlink($fileName);
+        }
+        $fd=fopen($fileName, "x+b");
+        if (is_resource($this->zipFile)) {
+            rewind($this->zipFile);
+            while (!feof($this->zipFile)) {
+                fwrite($fd, fread($this->zipFile, $this->streamChunkSize));
+            }
+
+            fclose($this->zipFile);
+        } else {
+            fwrite($fd, $this->zipData);
+            $this->zipData = NULL;
+        }
+        $this->zipFile = $fd;
+
+        return TRUE;
+    }
+
+    /**
+     * Add an empty directory entry to the zip archive.
+     * Basically this is only used if an empty directory is added.
+     *
+     * @param string $directoryPath Directory Path and name to be added to the archive.
+     * @param int    $timestamp     (Optional) Timestamp for the added directory, if omitted or set to 0, the current time will be used.
+     * @param string $fileComment   (Optional) Comment to be added to the archive for this directory. To use fileComment, timestamp must be given.
+	 * @param int    $extFileAttr   (Optional) The external file reference, use generateExtAttr to generate this.
+     * @return bool $success
+     */
+    public function addDirectory($directoryPath, $timestamp = 0, $fileComment = NULL, $extFileAttr = self::EXT_FILE_ATTR_DIR) {
+        if ($this->isFinalized) {
+            return FALSE;
+        }
+        $directoryPath = str_replace("\\", "/", $directoryPath);
+        $directoryPath = rtrim($directoryPath, "/");
+
+        if (strlen($directoryPath) > 0) {
+            $this->buildZipEntry($directoryPath.'/', $fileComment, "\x00\x00", "\x00\x00", $timestamp, "\x00\x00\x00\x00", 0, 0, $extFileAttr);
+            return TRUE;
+        }
+        return FALSE;
+    }
+
+    /**
+     * Add a file to the archive at the specified location and file name.
+     *
+     * @param string $data        File data.
+     * @param string $filePath    Filepath and name to be used in the archive.
+     * @param int    $timestamp   (Optional) Timestamp for the added file, if omitted or set to 0, the current time will be used.
+     * @param string $fileComment (Optional) Comment to be added to the archive for this file. To use fileComment, timestamp must be given.
+     * @param bool   $compress    (Optional) Compress file, if set to FALSE the file will only be stored. Default TRUE.
+	 * @param int    $extFileAttr (Optional) The external file reference, use generateExtAttr to generate this.
+     * @return bool $success
+     */
+    public function addFile($data, $filePath, $timestamp = 0, $fileComment = NULL, $compress = TRUE, $extFileAttr = self::EXT_FILE_ATTR_FILE) {
+        if ($this->isFinalized) {
+            return FALSE;
+        }
+
+        if (is_resource($data) && get_resource_type($data) == "stream") {
+            $this->addLargeFile($data, $filePath, $timestamp, $fileComment, $extFileAttr);
+            return FALSE;
+        }
+
+        $gzData = "";
+        $gzType = "\x08\x00"; // Compression type 8 = deflate
+        $gpFlags = "\x00\x00"; // General Purpose bit flags for compression type 8 it is: 0=Normal, 1=Maximum, 2=Fast, 3=super fast compression.
+        $dataLength = strlen($data);
+        $fileCRC32 = pack("V", crc32($data));
+
+        if ($compress) {
+            $gzTmp = gzcompress($data);
+            $gzData = substr(substr($gzTmp, 0, strlen($gzTmp) - 4), 2); // gzcompress adds a 2 byte header and 4 byte CRC we can't use.
+            // The 2 byte header does contain useful data, though in this case the 2 parameters we'd be interrested in will always be 8 for compression type, and 2 for General purpose flag.
+            $gzLength = strlen($gzData);
+        } else {
+            $gzLength = $dataLength;
+        }
+
+        if ($gzLength >= $dataLength) {
+            $gzLength = $dataLength;
+            $gzData = $data;
+            $gzType = "\x00\x00"; // Compression type 0 = stored
+            $gpFlags = "\x00\x00"; // Compression type 0 = stored
+        }
+
+        if (!is_resource($this->zipFile) && ($this->offset + $gzLength) > $this->zipMemoryThreshold) {
+            $this->zipflush();
+        }
+
+        $this->buildZipEntry($filePath, $fileComment, $gpFlags, $gzType, $timestamp, $fileCRC32, $gzLength, $dataLength, $extFileAttr);
+
+        $this->zipwrite($gzData);
+
+        return TRUE;
+    }
+
+    /**
+     * Add the content to a directory.
+     *
+     * @author Adam Schmalhofer 
+     * @author A. Grandt
+     *
+     * @param string $realPath       Path on the file system.
+     * @param string $zipPath        Filepath and name to be used in the archive.
+     * @param bool   $recursive      Add content recursively, default is TRUE.
+     * @param bool   $followSymlinks Follow and add symbolic links, if they are accessible, default is TRUE.
+     * @param array &$addedFiles     Reference to the added files, this is used to prevent duplicates, efault is an empty array.
+     *                               If you start the function by parsing an array, the array will be populated with the realPath
+     *                               and zipPath kay/value pairs added to the archive by the function.
+	 * @param bool   $overrideFilePermissions Force the use of the file/dir permissions set in the $extDirAttr
+	 *							     and $extFileAttr parameters.
+	 * @param int    $extDirAttr     Permissions for directories.
+	 * @param int    $extFileAttr    Permissions for files.
+     */
+    public function addDirectoryContent($realPath, $zipPath, $recursive = TRUE, $followSymlinks = TRUE, &$addedFiles = array(),
+					$overrideFilePermissions = FALSE, $extDirAttr = self::EXT_FILE_ATTR_DIR, $extFileAttr = self::EXT_FILE_ATTR_FILE) {
+        if (file_exists($realPath) && !isset($addedFiles[realpath($realPath)])) {
+            if (is_dir($realPath)) {
+				if ($overrideFilePermissions) {
+	                $this->addDirectory($zipPath, 0, null, $extDirAttr);
+				} else {
+					$this->addDirectory($zipPath, 0, null, self::getFileExtAttr($realPath));
+				}
+            }
+
+            $addedFiles[realpath($realPath)] = $zipPath;
+
+            $iter = new DirectoryIterator($realPath);
+            foreach ($iter as $file) {
+                if ($file->isDot()) {
+                    continue;
+                }
+                $newRealPath = $file->getPathname();
+                $newZipPath = self::pathJoin($zipPath, $file->getFilename());
+
+                if (file_exists($newRealPath) && ($followSymlinks === TRUE || !is_link($newRealPath))) {
+                    if ($file->isFile()) {
+                        $addedFiles[realpath($newRealPath)] = $newZipPath;
+						if ($overrideFilePermissions) {
+							$this->addLargeFile($newRealPath, $newZipPath, 0, null, $extFileAttr);
+						} else {
+							$this->addLargeFile($newRealPath, $newZipPath, 0, null, self::getFileExtAttr($newRealPath));
+						}
+                    } else if ($recursive === TRUE) {
+                        $this->addDirectoryContent($newRealPath, $newZipPath, $recursive, $followSymlinks, $addedFiles, $overrideFilePermissions, $extDirAttr, $extFileAttr);
+                    } else {
+						if ($overrideFilePermissions) {
+							$this->addDirectory($zipPath, 0, null, $extDirAttr);
+						} else {
+							$this->addDirectory($zipPath, 0, null, self::getFileExtAttr($newRealPath));
+						}
+                    }
+                }
+            }
+        }
+    }
+
+    /**
+     * Add a file to the archive at the specified location and file name.
+     *
+     * @param string $dataFile    File name/path.
+     * @param string $filePath    Filepath and name to be used in the archive.
+     * @param int    $timestamp   (Optional) Timestamp for the added file, if omitted or set to 0, the current time will be used.
+     * @param string $fileComment (Optional) Comment to be added to the archive for this file. To use fileComment, timestamp must be given.
+	 * @param int    $extFileAttr (Optional) The external file reference, use generateExtAttr to generate this.
+     * @return bool $success
+     */
+    public function addLargeFile($dataFile, $filePath, $timestamp = 0, $fileComment = NULL, $extFileAttr = self::EXT_FILE_ATTR_FILE)   {
+        if ($this->isFinalized) {
+            return FALSE;
+        }
+
+        if (is_string($dataFile) && is_file($dataFile)) {
+            $this->processFile($dataFile, $filePath, $timestamp, $fileComment, $extFileAttr);
+        } else if (is_resource($dataFile) && get_resource_type($dataFile) == "stream") {
+            $fh = $dataFile;
+            $this->openStream($filePath, $timestamp, $fileComment, $extFileAttr);
+
+            while (!feof($fh)) {
+                $this->addStreamData(fread($fh, $this->streamChunkSize));
+            }
+            $this->closeStream($this->addExtraField);
+        }
+        return TRUE;
+    }
+
+    /**
+     * Create a stream to be used for large entries.
+     *
+     * @param string $filePath    Filepath and name to be used in the archive.
+     * @param int    $timestamp   (Optional) Timestamp for the added file, if omitted or set to 0, the current time will be used.
+     * @param string $fileComment (Optional) Comment to be added to the archive for this file. To use fileComment, timestamp must be given.
+	 * @param int    $extFileAttr (Optional) The external file reference, use generateExtAttr to generate this.
+     * @return bool $success
+     */
+    public function openStream($filePath, $timestamp = 0, $fileComment = null, $extFileAttr = self::EXT_FILE_ATTR_FILE)   {
+        if (!function_exists('sys_get_temp_dir')) {
+            die ("ERROR: Zip " . self::VERSION . " requires PHP version 5.2.1 or above if large files are used.");
+        }
+
+        if ($this->isFinalized) {
+            return FALSE;
+        }
+
+        $this->zipflush();
+
+        if (strlen($this->streamFilePath) > 0) {
+            $this->closeStream();
+        }
+
+        $this->streamFile = tempnam(sys_get_temp_dir(), 'Zip');
+        $this->streamData = fopen($this->streamFile, "wb");
+        $this->streamFilePath = $filePath;
+        $this->streamTimestamp = $timestamp;
+        $this->streamFileComment = $fileComment;
+        $this->streamFileLength = 0;
+		$this->streamExtFileAttr = $extFileAttr;
+
+        return TRUE;
+    }
+
+    /**
+     * Add data to the open stream.
+     *
+     * @param string $data
+     * @return mixed length in bytes added or FALSE if the archive is finalized or there are no open stream.
+     */
+    public function addStreamData($data) {
+        if ($this->isFinalized || strlen($this->streamFilePath) == 0) {
+            return FALSE;
+        }
+
+        $length = fwrite($this->streamData, $data, strlen($data));
+        if ($length != strlen($data)) {
+            die ("
    Length mismatch
    \n");
+        }
+        $this->streamFileLength += $length;
+
+        return $length;
+    }
+
+    /**
+     * Close the current stream.
+     *
+     * @return bool $success
+     */
+    public function closeStream() {
+        if ($this->isFinalized || strlen($this->streamFilePath) == 0) {
+            return FALSE;
+        }
+
+        fflush($this->streamData);
+        fclose($this->streamData);
+
+        $this->processFile($this->streamFile, $this->streamFilePath, $this->streamTimestamp, $this->streamFileComment, $this->streamExtFileAttr);
+
+        $this->streamData = null;
+        $this->streamFilePath = null;
+        $this->streamTimestamp = null;
+        $this->streamFileComment = null;
+        $this->streamFileLength = 0;
+		$this->streamExtFileAttr = null;
+
+        // Windows is a little slow at times, so a millisecond later, we can unlink this.
+        unlink($this->streamFile);
+
+        $this->streamFile = null;
+
+        return TRUE;
+    }
+
+    private function processFile($dataFile, $filePath, $timestamp = 0, $fileComment = null, $extFileAttr = self::EXT_FILE_ATTR_FILE) {
+        if ($this->isFinalized) {
+            return FALSE;
+        }
+
+        $tempzip = tempnam(sys_get_temp_dir(), 'ZipStream');
+
+        $zip = new ZipArchive;
+        if ($zip->open($tempzip) === TRUE) {
+            $zip->addFile($dataFile, 'file');
+            $zip->close();
+        }
+
+        $file_handle = fopen($tempzip, "rb");
+        $stats = fstat($file_handle);
+        $eof = $stats['size']-72;
+
+        fseek($file_handle, 6);
+
+        $gpFlags = fread($file_handle, 2);
+        $gzType = fread($file_handle, 2);
+        fread($file_handle, 4);
+        $fileCRC32 = fread($file_handle, 4);
+        $v = unpack("Vval", fread($file_handle, 4));
+        $gzLength = $v['val'];
+        $v = unpack("Vval", fread($file_handle, 4));
+        $dataLength = $v['val'];
+
+        $this->buildZipEntry($filePath, $fileComment, $gpFlags, $gzType, $timestamp, $fileCRC32, $gzLength, $dataLength, $extFileAttr);
+
+        fseek($file_handle, 34);
+        $pos = 34;
+
+        while (!feof($file_handle) && $pos < $eof) {
+            $datalen = $this->streamChunkSize;
+            if ($pos + $this->streamChunkSize > $eof) {
+                $datalen = $eof-$pos;
+            }
+            $data = fread($file_handle, $datalen);
+            $pos += $datalen;
+
+            $this->zipwrite($data);
+        }
+
+        fclose($file_handle);
+
+        unlink($tempzip);
+    }
+
+    /**
+     * Close the archive.
+     * A closed archive can no longer have new files added to it.
+     *
+     * @return bool $success
+     */
+    public function finalize() {
+        if (!$this->isFinalized) {
+            if (strlen($this->streamFilePath) > 0) {
+                $this->closeStream();
+            }
+            $cd = implode("", $this->cdRec);
+
+            $cdRecSize = pack("v", sizeof($this->cdRec));
+            $cdRec = $cd . self::ZIP_END_OF_CENTRAL_DIRECTORY
+            . $cdRecSize . $cdRecSize
+            . pack("VV", strlen($cd), $this->offset);
+            if (!empty($this->zipComment)) {
+                $cdRec .= pack("v", strlen($this->zipComment)) . $this->zipComment;
+            } else {
+                $cdRec .= "\x00\x00";
+            }
+
+            $this->zipwrite($cdRec);
+
+            $this->isFinalized = TRUE;
+            $this->cdRec = NULL;
+
+            return TRUE;
+        }
+        return FALSE;
+    }
+
+    /**
+     * Get the handle ressource for the archive zip file.
+     * If the zip haven't been finalized yet, this will cause it to become finalized
+     *
+     * @return zip file handle
+     */
+    public function getZipFile() {
+        if (!$this->isFinalized) {
+            $this->finalize();
+        }
+
+        $this->zipflush();
+
+        rewind($this->zipFile);
+
+        return $this->zipFile;
+    }
+
+    /**
+     * Get the zip file contents
+     * If the zip haven't been finalized yet, this will cause it to become finalized
+     *
+     * @return zip data
+     */
+    public function getZipData() {
+        if (!$this->isFinalized) {
+            $this->finalize();
+        }
+        if (!is_resource($this->zipFile)) {
+            return $this->zipData;
+        } else {
+            rewind($this->zipFile);
+            $filestat = fstat($this->zipFile);
+            return fread($this->zipFile, $filestat['size']);
+        }
+    }
+
+    /**
+     * Send the archive as a zip download
+     *
+     * @param String $fileName The name of the Zip archive, in ISO-8859-1 (or ASCII) encoding, ie. "archive.zip". Optional, defaults to NULL, which means that no ISO-8859-1 encoded file name will be specified.
+     * @param String $contentType Content mime type. Optional, defaults to "application/zip".
+     * @param String $utf8FileName The name of the Zip archive, in UTF-8 encoding. Optional, defaults to NULL, which means that no UTF-8 encoded file name will be specified.
+     * @param bool $inline Use Content-Disposition with "inline" instead of "attached". Optional, defaults to FALSE.
+     * @return bool $success
+     */
+    function sendZip($fileName = null, $contentType = "application/zip", $utf8FileName = null, $inline = false) {
+        if (!$this->isFinalized) {
+            $this->finalize();
+        }
+
+        $headerFile = null;
+        $headerLine = null;
+        if (!headers_sent($headerFile, $headerLine) or die("
    Error: Unable to send file $fileName. HTML Headers have already been sent from $headerFile in line $headerLine
    ")) {
+            if ((ob_get_contents() === FALSE || ob_get_contents() == '') or die("\n
    Error: Unable to send file $fileName. Output buffer contains the following text (typically warnings or errors):
    " . htmlentities(ob_get_contents()) . "
    ")) {
+                if (ini_get('zlib.output_compression')) {
+                    ini_set('zlib.output_compression', 'Off');
+                }
+
+                header("Pragma: public");
+                header("Last-Modified: " . gmdate("D, d M Y H:i:s T"));
+                header("Expires: 0");
+                header("Accept-Ranges: bytes");
+                header("Connection: close");
+                header("Content-Type: " . $contentType);
+                $cd = "Content-Disposition: ";
+                if ($inline) {
+                    $cd .= "inline";
+				} else{
+                    $cd .= "attached";
+				}
+                if ($fileName) {
+                    $cd .= '; filename="' . $fileName . '"';
+				}
+                if ($utf8FileName) {
+                    $cd .= "; filename*=UTF-8''" . rawurlencode($utf8FileName);
+				}
+                header($cd);
+                header("Content-Length: ". $this->getArchiveSize());
+
+                if (!is_resource($this->zipFile)) {
+                    echo $this->zipData;
+                } else {
+                    rewind($this->zipFile);
+
+                    while (!feof($this->zipFile)) {
+                        echo fread($this->zipFile, $this->streamChunkSize);
+                    }
+                }
+            }
+            return TRUE;
+        }
+        return FALSE;
+    }
+
+    /**
+     * Return the current size of the archive
+     *
+     * @return $size Size of the archive
+     */
+    public function getArchiveSize() {
+        if (!is_resource($this->zipFile)) {
+            return strlen($this->zipData);
+        }
+        $filestat = fstat($this->zipFile);
+
+        return $filestat['size'];
+    }
+
+    /**
+     * Calculate the 2 byte dostime used in the zip entries.
+     *
+     * @param int $timestamp
+     * @return 2-byte encoded DOS Date
+     */
+    private function getDosTime($timestamp = 0) {
+        $timestamp = (int)$timestamp;
+        $oldTZ = @date_default_timezone_get();
+        date_default_timezone_set('UTC');
+        $date = ($timestamp == 0 ? getdate() : getdate($timestamp));
+        date_default_timezone_set($oldTZ);
+        if ($date["year"] >= 1980) {
+            return pack("V", (($date["mday"] + ($date["mon"] << 5) + (($date["year"]-1980) << 9)) << 16) |
+                    (($date["seconds"] >> 1) + ($date["minutes"] << 5) + ($date["hours"] << 11)));
+        }
+        return "\x00\x00\x00\x00";
+    }
+
+    /**
+     * Build the Zip file structures
+     *
+     * @param string $filePath
+     * @param string $fileComment
+     * @param string $gpFlags
+     * @param string $gzType
+     * @param int    $timestamp
+     * @param string $fileCRC32
+     * @param int    $gzLength
+     * @param int    $dataLength
+     * @param int    $extFileAttr Use self::EXT_FILE_ATTR_FILE for files, self::EXT_FILE_ATTR_DIR for Directories.
+     */
+    private function buildZipEntry($filePath, $fileComment, $gpFlags, $gzType, $timestamp, $fileCRC32, $gzLength, $dataLength, $extFileAttr) {
+        $filePath = str_replace("\\", "/", $filePath);
+        $fileCommentLength = (empty($fileComment) ? 0 : strlen($fileComment));
+        $timestamp = (int)$timestamp;
+        $timestamp = ($timestamp == 0 ? time() : $timestamp);
+
+        $dosTime = $this->getDosTime($timestamp);
+        $tsPack = pack("V", $timestamp);
+
+        $ux = "\x75\x78\x0B\x00\x01\x04\xE8\x03\x00\x00\x04\x00\x00\x00\x00";
+
+        if (!isset($gpFlags) || strlen($gpFlags) != 2) {
+            $gpFlags = "\x00\x00";
+        }
+
+        $isFileUTF8 = mb_check_encoding($filePath, "UTF-8") && !mb_check_encoding($filePath, "ASCII");
+        $isCommentUTF8 = !empty($fileComment) && mb_check_encoding($fileComment, "UTF-8") && !mb_check_encoding($fileComment, "ASCII");
+        if ($isFileUTF8 || $isCommentUTF8) {
+            $flag = 0;
+            $gpFlagsV = unpack("vflags", $gpFlags);
+            if (isset($gpFlagsV['flags'])) {
+                $flag = $gpFlagsV['flags'];
+            }
+            $gpFlags = pack("v", $flag | (1 << 11));
+        }
+
+        $header = $gpFlags . $gzType . $dosTime. $fileCRC32
+        . pack("VVv", $gzLength, $dataLength, strlen($filePath)); // File name length
+
+        $zipEntry  = self::ZIP_LOCAL_FILE_HEADER;
+        $zipEntry .= self::ATTR_VERSION_TO_EXTRACT;
+        $zipEntry .= $header;
+        $zipEntry .= pack("v", ($this->addExtraField ? 28 : 0)); // Extra field length
+        $zipEntry .= $filePath; // FileName
+        // Extra fields
+        if ($this->addExtraField) {
+            $zipEntry .= "\x55\x54\x09\x00\x03" . $tsPack . $tsPack . $ux;
+        }
+        $this->zipwrite($zipEntry);
+
+        $cdEntry  = self::ZIP_CENTRAL_FILE_HEADER;
+        $cdEntry .= self::ATTR_MADE_BY_VERSION;
+        $cdEntry .= ($dataLength === 0 ? "\x0A\x00" : self::ATTR_VERSION_TO_EXTRACT);
+        $cdEntry .= $header;
+        $cdEntry .= pack("v", ($this->addExtraField ? 24 : 0)); // Extra field length
+        $cdEntry .= pack("v", $fileCommentLength); // File comment length
+        $cdEntry .= "\x00\x00"; // Disk number start
+        $cdEntry .= "\x00\x00"; // internal file attributes
+        $cdEntry .= pack("V", $extFileAttr); // External file attributes
+        $cdEntry .= pack("V", $this->offset); // Relative offset of local header
+        $cdEntry .= $filePath; // FileName
+        // Extra fields
+        if ($this->addExtraField) {
+            $cdEntry .= "\x55\x54\x05\x00\x03" . $tsPack . $ux;
+        }
+        if (!empty($fileComment)) {
+            $cdEntry .= $fileComment; // Comment
+        }
+
+        $this->cdRec[] = $cdEntry;
+        $this->offset += strlen($zipEntry) + $gzLength;
+    }
+
+    private function zipwrite($data) {
+        if (!is_resource($this->zipFile)) {
+            $this->zipData .= $data;
+        } else {
+            fwrite($this->zipFile, $data);
+            fflush($this->zipFile);
+        }
+    }
+
+    private function zipflush() {
+        if (!is_resource($this->zipFile)) {
+            $this->zipFile = tmpfile();
+            fwrite($this->zipFile, $this->zipData);
+            $this->zipData = NULL;
+        }
+    }
+
+    /**
+     * Join $file to $dir path, and clean up any excess slashes.
+     *
+     * @param string $dir
+     * @param string $file
+     */
+    public static function pathJoin($dir, $file) {
+        if (empty($dir) || empty($file)) {
+            return self::getRelativePath($dir . $file);
+        }
+        return self::getRelativePath($dir . '/' . $file);
+    }
+
+    /**
+     * Clean up a path, removing any unnecessary elements such as /./, // or redundant ../ segments.
+     * If the path starts with a "/", it is deemed an absolute path and any /../ in the beginning is stripped off.
+     * The returned path will not end in a "/".
+	 *
+	 * Sometimes, when a path is generated from multiple fragments, 
+	 *  you can get something like "../data/html/../images/image.jpeg"
+	 * This will normalize that example path to "../data/images/image.jpeg"
+     *
+     * @param string $path The path to clean up
+     * @return string the clean path
+     */
+    public static function getRelativePath($path) {
+        $path = preg_replace("#/+\.?/+#", "/", str_replace("\\", "/", $path));
+        $dirs = explode("/", rtrim(preg_replace('#^(?:\./)+#', '', $path), '/'));
+
+        $offset = 0;
+        $sub = 0;
+        $subOffset = 0;
+        $root = "";
+
+        if (empty($dirs[0])) {
+            $root = "/";
+            $dirs = array_splice($dirs, 1);
+        } else if (preg_match("#[A-Za-z]:#", $dirs[0])) {
+            $root = strtoupper($dirs[0]) . "/";
+            $dirs = array_splice($dirs, 1);
+        }
+
+        $newDirs = array();
+        foreach ($dirs as $dir) {
+            if ($dir !== "..") {
+                $subOffset--;
+                $newDirs[++$offset] = $dir;
+            } else {
+                $subOffset++;
+                if (--$offset < 0) {
+                    $offset = 0;
+                    if ($subOffset > $sub) {
+                        $sub++;
+                    }
+                }
+            }
+        }
+
+        if (empty($root)) {
+            $root = str_repeat("../", $sub);
+        }
+        return $root . implode("/", array_slice($newDirs, 0, $offset));
+    }
+
+	/**
+	 * Create the file permissions for a file or directory, for use in the extFileAttr parameters.
+	 *
+	 * @param int   $owner Unix permisions for owner (octal from 00 to 07)
+	 * @param int   $group Unix permisions for group (octal from 00 to 07)
+	 * @param int   $other Unix permisions for others (octal from 00 to 07)
+	 * @param bool  $isFile
+	 * @return EXTRERNAL_REF field.
+	 */
+	public static function generateExtAttr($owner = 07, $group = 05, $other = 05, $isFile = true) {
+		$fp = $isFile ? self::S_IFREG : self::S_IFDIR;
+		$fp |= (($owner & 07) << 6) | (($group & 07) << 3) | ($other & 07);
+
+		return ($fp << 16) | ($isFile ? self::S_DOS_A : self::S_DOS_D);
+	}
+
+	/**
+	 * Get the file permissions for a file or directory, for use in the extFileAttr parameters.
+	 *
+	 * @param string $filename
+	 * @return external ref field, or FALSE if the file is not found.
+	 */
+	public static function getFileExtAttr($filename) {
+		if (file_exists($filename)) {
+			$fp = fileperms($filename) << 16;
+			return $fp | (is_dir($filename) ? self::S_DOS_D : self::S_DOS_A);
+		}
+		return FALSE;
+	}
+}
+?>
diff --git a/inc/3rdparty/libraries/PHPePub/lib.uuid.LICENCE.txt b/inc/3rdparty/libraries/PHPePub/lib.uuid.LICENCE.txt
new file mode 100644
index 00000000..9424a83e
--- /dev/null
+++ b/inc/3rdparty/libraries/PHPePub/lib.uuid.LICENCE.txt
@@ -0,0 +1,31 @@
+   DrUUID RFC4122 library for PHP5
+    by J. King (http://jkingweb.ca/)
+   Licensed under MIT license
+
+   See http://jkingweb.ca/code/php/lib.uuid/
+    for documentation
+    
+   Last revised 2010-02-15
+
+Copyright (c) 2009 J. King
+
+Permission is hereby granted, free of charge, to any person
+obtaining a copy of this software and associated documentation
+files (the "Software"), to deal in the Software without
+restriction, including without limitation the rights to use,
+copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the
+Software is furnished to do so, subject to the following
+conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.
diff --git a/inc/3rdparty/libraries/PHPePub/lib.uuid.php b/inc/3rdparty/libraries/PHPePub/lib.uuid.php
new file mode 100644
index 00000000..c6a8de52
--- /dev/null
+++ b/inc/3rdparty/libraries/PHPePub/lib.uuid.php
@@ -0,0 +1,314 @@
+string;
+	}
+
+	public function __get($var) {
+		switch($var) {
+			case "bytes":
+				return $this->bytes;
+			case "hex":
+				return bin2hex($this->bytes);
+			case "string":
+				return $this->__toString();
+			case "urn":
+				return "urn:uuid:".$this->__toString();
+			case "version":
+				return ord($this->bytes[6]) >> 4;
+			case "variant":
+				$byte = ord($this->bytes[8]);
+				if ($byte >= self::varRes) {
+					return 3;
+				}
+				if ($byte >= self::varMS) {
+					return 2;
+				}
+				if ($byte >= self::varRFC) {
+					return 1;
+				}
+				return 0;
+			case "node":
+				if (ord($this->bytes[6])>>4==1) {
+					return bin2hex(substr($this->bytes,10));
+				} else {
+					return NULL;
+				}
+			case "time":
+				if (ord($this->bytes[6])>>4==1) {
+					// Restore contiguous big-endian byte order
+					$time = bin2hex($this->bytes[6].$this->bytes[7].$this->bytes[4].$this->bytes[5].$this->bytes[0].$this->bytes[1].$this->bytes[2].$this->bytes[3]);
+					// Clear version flag
+					$time[0] = "0";
+					// Do some reverse arithmetic to get a Unix timestamp
+					$time = (hexdec($time) - self::interval) / 10000000;
+					return $time;
+				} else {
+					return NULL;
+				}
+			default:
+				return NULL;
+		}
+	}
+
+	protected function __construct($uuid) {
+		if (strlen($uuid) != 16) {
+			throw new UUIDException("Input must be a 128-bit integer.");
+		}
+		$this->bytes  = $uuid;
+		// Optimize the most common use
+		$this->string =
+		bin2hex(substr($uuid,0,4))."-".
+		bin2hex(substr($uuid,4,2))."-".
+		bin2hex(substr($uuid,6,2))."-".
+		bin2hex(substr($uuid,8,2))."-".
+		bin2hex(substr($uuid,10,6));
+	}
+
+	protected static function mintTime($node = NULL) {
+		/* Generates a Version 1 UUID.
+		 These are derived from the time at which they were generated. */
+		// Get time since Gregorian calendar reform in 100ns intervals
+		// This is exceedingly difficult because of PHP's (and pack()'s)
+		//  integer size limits.
+		// Note that this will never be more accurate than to the microsecond.
+		$time = microtime(1) * 10000000 + self::interval;
+		// Convert to a string representation
+		$time = sprintf("%F", $time);
+		preg_match("/^\d+/", $time, $time); //strip decimal point
+		// And now to a 64-bit binary representation
+		$time = base_convert($time[0], 10, 16);
+		$time = pack("H*", str_pad($time, 16, "0", STR_PAD_LEFT));
+		// Reorder bytes to their proper locations in the UUID
+		$uuid  = $time[4].$time[5].$time[6].$time[7].$time[2].$time[3].$time[0].$time[1];
+		// Generate a random clock sequence
+		$uuid .= self::randomBytes(2);
+		// set variant
+		$uuid[8] = chr(ord($uuid[8]) & self::clearVar | self::varRFC);
+		// set version
+		$uuid[6] = chr(ord($uuid[6]) & self::clearVer | self::version1);
+		// Set the final 'node' parameter, a MAC address
+		if ($node) {
+			$node = self::makeBin($node, 6);
+		}
+		if (!$node) {
+			// If no node was provided or if the node was invalid,
+			//  generate a random MAC address and set the multicast bit
+			$node = self::randomBytes(6);
+			$node[0] = pack("C", ord($node[0]) | 1);
+		}
+		$uuid .= $node;
+		return $uuid;
+	}
+
+	protected static function mintRand() {
+		/* Generate a Version 4 UUID.
+		 These are derived soly from random numbers. */
+		// generate random fields
+		$uuid = self::randomBytes(16);
+		// set variant
+		$uuid[8] = chr(ord($uuid[8]) & self::clearVar | self::varRFC);
+		// set version
+		$uuid[6] = chr(ord($uuid[6]) & self::clearVer | self::version4);
+		return $uuid;
+	}
+
+	protected static function mintName($ver, $node, $ns) {
+		/* Generates a Version 3 or Version 5 UUID.
+		 These are derived from a hash of a name and its namespace, in binary form. */
+		if (!$node) {
+			throw new UUIDException("A name-string is required for Version 3 or 5 UUIDs.");
+		}
+		// if the namespace UUID isn't binary, make it so
+		$ns = self::makeBin($ns, 16);
+		if (!$ns) {
+			throw new UUIDException("A binary namespace is required for Version 3 or 5 UUIDs.");
+		}
+		$uuid = null;
+		$version =  self::version3;
+		switch($ver) {
+			case self::MD5:
+				$version = self::version3;
+				$uuid = md5($ns.$node,1);
+				break;
+			case self::SHA1:
+				$version = self::version5;
+				$uuid = substr(sha1($ns.$node,1),0, 16);
+				break;
+		}
+		// set variant
+		$uuid[8] = chr(ord($uuid[8]) & self::clearVar | self::varRFC);
+		// set version
+		$uuid[6] = chr(ord($uuid[6]) & self::clearVer | $version);
+		return ($uuid);
+	}
+
+	protected static function makeBin($str, $len) {
+		/* Insure that an input string is either binary or hexadecimal.
+		 Returns binary representation, or false on failure. */
+		if ($str instanceof self) {
+			return $str->bytes;
+		}
+		if (strlen($str)==$len) {
+			return $str;
+		} else {
+			$str = preg_replace("/^urn:uuid:/is", "", $str); // strip URN scheme and namespace
+		}
+		$str = preg_replace("/[^a-f0-9]/is", "", $str);  // strip non-hex characters
+		if (strlen($str) != ($len * 2)) {
+			return FALSE;
+		} else {
+			return pack("H*", $str);
+		}
+	}
+
+	public static function initRandom() {
+		/* Look for a system-provided source of randomness, which is usually crytographically secure.
+		 /dev/urandom is tried first simply out of bias for Linux systems. */
+		if (is_readable('/dev/urandom')) {
+			self::$randomSource = fopen('/dev/urandom', 'rb');
+			self::$randomFunc = 'randomFRead';
+		}
+		else if (class_exists('COM', 0)) {
+			try {
+				self::$randomSource = new COM('CAPICOM.Utilities.1');  // See http://msdn.microsoft.com/en-us/library/aa388182(VS.85).aspx
+				self::$randomFunc = 'randomCOM';
+			}
+			catch(Exception $e) {
+			}
+		}
+		return self::$randomFunc;
+	}
+
+	public static function randomBytes($bytes) {
+		return call_user_func(array('self', self::$randomFunc), $bytes);
+	}
+
+	protected static function randomTwister($bytes) {
+		/* Get the specified number of random bytes, using mt_rand().
+		 Randomness is returned as a string of bytes. */
+		$rand = "";
+		for ($a = 0; $a < $bytes; $a++) {
+			$rand .= chr(mt_rand(0, 255));
+		}
+		return $rand;
+	}
+
+	protected static function randomFRead($bytes) {
+		/* Get the specified number of random bytes using a file handle
+		 previously opened with UUID::initRandom().
+		Randomness is returned as a string of bytes. */
+		return fread(self::$randomSource, $bytes);
+	}
+
+	protected static function randomCOM($bytes) {
+		/* Get the specified number of random bytes using Windows'
+		 randomness source via a COM object previously created by UUID::initRandom().
+		Randomness is returned as a string of bytes. */
+		return base64_decode(self::$randomSource->GetRandom($bytes,0)); // straight binary mysteriously doesn't work, hence the base64
+	}
+}
+
+class UUIDException extends Exception {
+}
-- 
cgit v1.2.3


From 72a857158c187206dae2eed08143d5743322cb0c Mon Sep 17 00:00:00 2001
From: tcit 
Date: Thu, 24 Apr 2014 03:08:31 +0200
Subject: Fixed a bug into PHPePub with special caracters

---
 inc/3rdparty/libraries/PHPePub/EPub.php | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'inc/3rdparty/libraries')

diff --git a/inc/3rdparty/libraries/PHPePub/EPub.php b/inc/3rdparty/libraries/PHPePub/EPub.php
index 836c0512..0260ce4f 100644
--- a/inc/3rdparty/libraries/PHPePub/EPub.php
+++ b/inc/3rdparty/libraries/PHPePub/EPub.php
@@ -343,6 +343,7 @@ class EPub {
         }
         $fileName = Zip::getRelativePath($fileName);
         $fileName = preg_replace('#^[/\.]+#i', "", $fileName);
+        $fileName = $this->sanitizeFileName($fileName);
 
         $chapter = $chapterData;
         if ($autoSplit && is_string($chapterData) && mb_strlen($chapterData) > $this->splitDefaultSize) {
@@ -1699,7 +1700,7 @@ class EPub {
                 while (list($chapterName, $navPoint) = each($this->ncx->chapterList)) {
 					$fileName = $navPoint->getContentSrc();
 					$level = $navPoint->getLevel() -2;
-					$tocData .= "\t
    " . str_repeat("        ", $level) . "" . $chapterName . "
    \n";
+					$tocData .= "\t
    " . str_repeat("        ", $level) . "sanitizeFileName($fileName) . "\">" . $chapterName . "
    \n";
                 }
             } else if ($this->tocAddReferences === TRUE) {
                 if (array_key_exists($item, $this->ncx->referencesList)) {
-- 
cgit v1.2.3


From ef17914960191c6008fc70891544ae2182d70582 Mon Sep 17 00:00:00 2001
From: tcit 
Date: Thu, 24 Apr 2014 09:39:50 +0200
Subject: Fix for #664 - Missing source url attribute in RSS feeds

---
 inc/3rdparty/libraries/feedwriter/FeedItem.php | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'inc/3rdparty/libraries')

diff --git a/inc/3rdparty/libraries/feedwriter/FeedItem.php b/inc/3rdparty/libraries/feedwriter/FeedItem.php
index 3487423f..54a56f22 100644
--- a/inc/3rdparty/libraries/feedwriter/FeedItem.php
+++ b/inc/3rdparty/libraries/feedwriter/FeedItem.php
@@ -174,7 +174,8 @@
     */
     public function setSource($link) 
     {
-        $this->setElement('source', $link);
+        $attributes = array('url'=>$link);
+        $this->setElement('source', "wallabag",$attributes);
     }
     
     /**
-- 
cgit v1.2.3


From 827f5b42a667a9ac2ab68701c23885ae6e617907 Mon Sep 17 00:00:00 2001
From: Maryana Rozhankivska 
Date: Thu, 24 Apr 2014 11:48:00 +0300
Subject: fix of rss headers problem

---
 inc/3rdparty/libraries/feedwriter/FeedWriter.php | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

(limited to 'inc/3rdparty/libraries')

diff --git a/inc/3rdparty/libraries/feedwriter/FeedWriter.php b/inc/3rdparty/libraries/feedwriter/FeedWriter.php
index 79639c0c..d708e99b 100755
--- a/inc/3rdparty/libraries/feedwriter/FeedWriter.php
+++ b/inc/3rdparty/libraries/feedwriter/FeedWriter.php
@@ -87,12 +87,25 @@ define('JSONP', 3, true);
     * @access   public
     * @return   void
     */
-    public function genarateFeed()
+    public function genarateFeed($withHeaders = true)
     {
-        header('Content-type: text/xml; charset=UTF-8');
-        // this line prevents Chrome 20 from prompting download
-        // used by Google: https://news.google.com/news/feeds?ned=us&topic=b&output=rss
-        header('X-content-type-options: nosniff');
+        if ($withHeaders) {
+          if ($this->version == RSS2) {
+              header('Content-type: text/xml; charset=UTF-8');
+              // this line prevents Chrome 20 from prompting download
+              // used by Google: https://news.google.com/news/feeds?ned=us&topic=b&output=rss
+              header('X-content-type-options: nosniff');
+          } elseif ($this->version == JSON) {
+              header('Content-type: application/json; charset=UTF-8');
+          } elseif ($this->version == JSONP) {
+              header('Content-type: application/javascript; charset=UTF-8');
+          }
+        }
+      
+        if ($this->version == JSON || $this->version == JSONP) {
+          $this->json = new stdClass();
+        }
+      
 
         $this->printHead();
         $this->printChannels();
-- 
cgit v1.2.3


From 4877836b12cde621a9c6200ec460ce025384ea35 Mon Sep 17 00:00:00 2001
From: tcit 
Date: Wed, 7 May 2014 12:40:09 +0200
Subject: Many improvements to epub produced : better cover, better tags

---
 inc/3rdparty/libraries/PHPePub/EPub.php | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

(limited to 'inc/3rdparty/libraries')

diff --git a/inc/3rdparty/libraries/PHPePub/EPub.php b/inc/3rdparty/libraries/PHPePub/EPub.php
index 0260ce4f..e120b341 100644
--- a/inc/3rdparty/libraries/PHPePub/EPub.php
+++ b/inc/3rdparty/libraries/PHPePub/EPub.php
@@ -574,7 +574,7 @@ class EPub {
      * @param string $mimetype Image mimetype, such as "image/jpeg" or "image/png".
      * @return bool $success
      */
-    function setCoverImage($fileName, $imageData = NULL, $mimetype = NULL) {
+    function setCover($fileName, $imageData = NULL, $mimetype = NULL, $coverText=NULL) {
         if ($this->isFinalized || $this->isCoverImageSet || array_key_exists("CoverPage.html", $this->fileList)) {
             return FALSE;
         }
@@ -621,12 +621,13 @@ class EPub {
 				. "\n"
 				. "\t\n"
 				. "\t\t\n"
-				. "\t\tCover Image\n"
+				. "\t\tCover\n"
 				. "\t\t\n"
 				. "\t\n"
 				. "\t\n"
+                . "\t\t" . $coverText . "\n"
 				. "\t\t
    \n"
-				. "\t\t\t\"Cover\n"
+				. "\t\t\t\"Cover\n"
 				. "\t\t
    \n"
 				. "\t\n"
 				. "\n";
@@ -635,12 +636,13 @@ class EPub {
 				. "\n"
 				. ""
 				. "\t\n"
-				. "\t\tCover Image\n"
+				. "\t\tCover\n"
 				. "\t\t\n"
 				. "\t\n"
 				. "\t\n"
 				. "\t\t
    \n"
-				. "\t\t\t\"Cover\n"
+                . "\t\t" . $coverText . "\n"
+				. "\t\t\t\"Cover\n"
 				. "\t\t
    \n"
 				. "\t\n"
 				. "\n";
-- 
cgit v1.2.3


From f2b6b4e23064c40cde9e2ad5327499589dee503b Mon Sep 17 00:00:00 2001
From: tcit 
Date: Wed, 14 May 2014 22:03:16 +0200
Subject: Fix bugs and improved epub rendering

---
 inc/3rdparty/libraries/PHPePub/EPub.php | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'inc/3rdparty/libraries')

diff --git a/inc/3rdparty/libraries/PHPePub/EPub.php b/inc/3rdparty/libraries/PHPePub/EPub.php
index e120b341..f1f41bd5 100644
--- a/inc/3rdparty/libraries/PHPePub/EPub.php
+++ b/inc/3rdparty/libraries/PHPePub/EPub.php
@@ -574,7 +574,7 @@ class EPub {
      * @param string $mimetype Image mimetype, such as "image/jpeg" or "image/png".
      * @return bool $success
      */
-    function setCover($fileName, $imageData = NULL, $mimetype = NULL, $coverText=NULL) {
+    function setCoverImage($fileName, $imageData = NULL, $mimetype = NULL,$bookTitle) {
         if ($this->isFinalized || $this->isCoverImageSet || array_key_exists("CoverPage.html", $this->fileList)) {
             return FALSE;
         }
@@ -621,13 +621,13 @@ class EPub {
 				. "\n"
 				. "\t\n"
 				. "\t\t\n"
-				. "\t\tCover\n"
+				. "\t\tCover Image\n"
 				. "\t\t\n"
 				. "\t\n"
 				. "\t\n"
-                . "\t\t" . $coverText . "\n"
+                . "\t" . $bookTitle . "\n"
 				. "\t\t
    \n"
-				. "\t\t\t\"Cover\n"
+				. "\t\t\t\"Cover\n"
 				. "\t\t
    \n"
 				. "\t\n"
 				. "\n";
@@ -636,13 +636,13 @@ class EPub {
 				. "\n"
 				. ""
 				. "\t\n"
-				. "\t\tCover\n"
+				. "\t\tCover Image\n"
 				. "\t\t\n"
 				. "\t\n"
 				. "\t\n"
 				. "\t\t
    \n"
-                . "\t\t" . $coverText . "\n"
-				. "\t\t\t\"Cover\n"
+                . "\t" . $bookTitle . "\n"
+				. "\t\t\t\"Cover\n"
 				. "\t\t
    \n"
 				. "\t\n"
 				. "\n";
-- 
cgit v1.2.3


From 3ec62cf95ab4436923d4c665fad7aef226cbb822 Mon Sep 17 00:00:00 2001
From: Maryana Rozhankivska 
Date: Thu, 22 May 2014 17:16:38 +0300
Subject: update to 3.2 version of full-text-rss, issue #694

---
 .../content-extractor/ContentExtractor.php         | 1455 +++++++------
 .../libraries/content-extractor/SiteConfig.php     |  681 +++---
 inc/3rdparty/libraries/feedwriter/FeedItem.php     |  100 +-
 inc/3rdparty/libraries/feedwriter/FeedWriter.php   |   17 +-
 inc/3rdparty/libraries/html5/TreeBuilder.php       |   13 +-
 .../libraries/humble-http-agent/CookieJar.php      |  807 ++++---
 .../humble-http-agent/HumbleHttpAgent.php          | 1589 +++++++-------
 .../SimplePie_HumbleHttpAgent.php                  |  157 +-
 .../libraries/language-detect/LanguageDetect.php   |  992 +++++----
 inc/3rdparty/libraries/readability/Readability.php | 2274 ++++++++++----------
 10 files changed, 4097 insertions(+), 3988 deletions(-)
 mode change 100644 => 100755 inc/3rdparty/libraries/feedwriter/FeedItem.php

(limited to 'inc/3rdparty/libraries')

diff --git a/inc/3rdparty/libraries/content-extractor/ContentExtractor.php b/inc/3rdparty/libraries/content-extractor/ContentExtractor.php
index ddd33bb5..21e693e7 100644
--- a/inc/3rdparty/libraries/content-extractor/ContentExtractor.php
+++ b/inc/3rdparty/libraries/content-extractor/ContentExtractor.php
@@ -1,728 +1,727 @@
- true,
-				 'output-xhtml' => true,
-				 'logical-emphasis' => true,
-				 'show-body-only' => false,
-				 'new-blocklevel-tags' => 'article, aside, footer, header, hgroup, menu, nav, section, details, datagrid',
-				 'new-inline-tags' => 'mark, time, meter, progress, data',
-				 'wrap' => 0,
-				 'drop-empty-paras' => true,
-				 'drop-proprietary-attributes' => false,
-				 'enclose-text' => true,
-				 'enclose-block-text' => true,
-				 'merge-divs' => true,
-				 'merge-spans' => true,
-				 'char-encoding' => 'utf8',
-				 'hide-comments' => true
-				 );
-	protected $html;
-	protected $config;
-	protected $title;
-	protected $author = array();
-	protected $language;
-	protected $date;
-	protected $body;
-	protected $success = false;
-	protected $nextPageUrl;
-	public $allowedParsers = array('libxml', 'html5lib');
-	public $fingerprints = array();
-	public $readability;
-	public $debug = false;
-	public $debugVerbose = false;
-
-	function __construct($path, $fallback=null) {
-		SiteConfig::set_config_path($path, $fallback);	
-	}
-	
-	protected function debug($msg) {
-		if ($this->debug) {
-			$mem = round(memory_get_usage()/1024, 2);
-			$memPeak = round(memory_get_peak_usage()/1024, 2);
-			echo '* ',$msg;
-			if ($this->debugVerbose) echo ' - mem used: ',$mem," (peak: $memPeak)";
-			echo "\n";
-			ob_flush();
-			flush();
-		}
-	}
-	
-	public function reset() {
-		$this->html = null;
-		$this->readability = null;
-		$this->config = null;
-		$this->title = null;
-		$this->body = null;
-		$this->author = array();
-		$this->language = null;
-		$this->date = null;
-		$this->nextPageUrl = null;
-		$this->success = false;
-	}
-
-	public function findHostUsingFingerprints($html) {
-		$this->debug('Checking fingerprints...');
-		$head = substr($html, 0, 8000);
-		foreach ($this->fingerprints as $_fp => $_fphost) {
-			$lookin = 'html';
-			if (is_array($_fphost)) {
-				if (isset($_fphost['head']) && $_fphost['head']) {
-					$lookin = 'head';
-				}
-				$_fphost = $_fphost['hostname'];
-			}
-			if (strpos($$lookin, $_fp) !== false) {
-				$this->debug("Found match: $_fphost");
-				return $_fphost;
-			}
-		}
-		$this->debug('No fingerprint matches');
-		return false;
-	}
-	
-	// returns SiteConfig instance (joined in order: exact match, wildcard, fingerprint, global, default)
-	public function buildSiteConfig($url, $html='', $add_to_cache=true) {
-		// extract host name
-		$host = @parse_url($url, PHP_URL_HOST);
-		$host = strtolower($host);
-		if (substr($host, 0, 4) == 'www.') $host = substr($host, 4);
-		// is merged version already cached?
-		if (SiteConfig::is_cached("$host.merged")) {
-			$this->debug("Returning cached and merged site config for $host");
-			return SiteConfig::build("$host.merged");
-		}
-		// let's build from site_config/custom/ and standard/
-		$config = SiteConfig::build($host);
-		if ($add_to_cache && $config && !SiteConfig::is_cached("$host")) {
-			SiteConfig::add_to_cache($host, $config);
-		}
-		// if no match, use defaults
-		if (!$config) $config = new SiteConfig();
-		// load fingerprint config?
-		if ($config->autodetect_on_failure()) {
-			// check HTML for fingerprints
-			if (!empty($this->fingerprints) && ($_fphost = $this->findHostUsingFingerprints($html))) {
-				if ($config_fingerprint = SiteConfig::build($_fphost)) {
-					$this->debug("Appending site config settings from $_fphost (fingerprint match)");
-					$config->append($config_fingerprint);
-					if ($add_to_cache && !SiteConfig::is_cached($_fphost)) {
-						//$config_fingerprint->cache_in_apc = true;
-						SiteConfig::add_to_cache($_fphost, $config_fingerprint);
-					}
-				}
-			}
-		}
-		// load global config?
-		if ($config->autodetect_on_failure()) {
-			if ($config_global = SiteConfig::build('global', true)) {
-				$this->debug('Appending site config settings from global.txt');
-				$config->append($config_global);
-				if ($add_to_cache && !SiteConfig::is_cached('global')) {
-					//$config_global->cache_in_apc = true;
-					SiteConfig::add_to_cache('global', $config_global);
-				}
-			}
-		}
-		// store copy of merged config
-		if ($add_to_cache) {
-			// do not store in APC if wildcard match
-			$use_apc = ($host == $config->cache_key);
-			$config->cache_key = null;
-			SiteConfig::add_to_cache("$host.merged", $config, $use_apc);
-		}
-		return $config;
-	}
-	
-	// returns true on success, false on failure
-	// $smart_tidy indicates that if tidy is used and no results are produced, we will
-	// try again without it. Tidy helps us deal with PHP's patchy HTML parsing most of the time
-	// but it has problems of its own which we try to avoid with this option.
-	public function process($html, $url, $smart_tidy=true) {
-		$this->reset();
-		$this->config = $this->buildSiteConfig($url, $html);
-		
-		// do string replacements
-		if (!empty($this->config->find_string)) {
-			if (count($this->config->find_string) == count($this->config->replace_string)) {
-				$html = str_replace($this->config->find_string, $this->config->replace_string, $html, $_count);
-				$this->debug("Strings replaced: $_count (find_string and/or replace_string)");
-			} else {
-				$this->debug('Skipped string replacement - incorrect number of find-replace strings in site config');
-			}
-			unset($_count);
-		}
-		
-		// use tidy (if it exists)?
-		// This fixes problems with some sites which would otherwise
-		// trouble DOMDocument's HTML parsing. (Although sometimes it
-		// makes matters worse, which is why you can override it in site config files.)
-		$tidied = false;
-		if ($this->config->tidy() && function_exists('tidy_parse_string') && $smart_tidy) {
-			$this->debug('Using Tidy');
-			$tidy = tidy_parse_string($html, self::$tidy_config, 'UTF8');
-			if (tidy_clean_repair($tidy)) {
-				$original_html = $html;
-				$tidied = true;
-				$html = $tidy->value;
-			}
-			unset($tidy);
-		}
-		
-		// load and parse html
-		$_parser = $this->config->parser();
-		if (!in_array($_parser, $this->allowedParsers)) {
-			$this->debug("HTML parser $_parser not listed, using libxml instead");
-			$_parser = 'libxml';
-		}
-		$this->debug("Attempting to parse HTML with $_parser");
-		$this->readability = new Readability($html, $url, $_parser);
-		
-		// we use xpath to find elements in the given HTML document
-		// see http://en.wikipedia.org/wiki/XPath_1.0
-		$xpath = new DOMXPath($this->readability->dom);
-
-		// try to get next page link
-		foreach ($this->config->next_page_link as $pattern) {
-			$elems = @$xpath->evaluate($pattern, $this->readability->dom);
-			if (is_string($elems)) {
-				$this->nextPageUrl = trim($elems);
-				break;
-			} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
-				foreach ($elems as $item) {
-					if ($item instanceof DOMElement && $item->hasAttribute('href')) {
-						$this->nextPageUrl = $item->getAttribute('href');
-						break 2;
-					} elseif ($item instanceof DOMAttr && $item->value) {
-						$this->nextPageUrl = $item->value;
-						break 2;
-					}
-				}
-			}
-		}
-		
-		// try to get title
-		foreach ($this->config->title as $pattern) {
-			// $this->debug("Trying $pattern");
-			$elems = @$xpath->evaluate($pattern, $this->readability->dom);
-			if (is_string($elems)) {
-				$this->title = trim($elems);
-				$this->debug('Title expression evaluated as string: '.$this->title);
-				$this->debug("...XPath match: $pattern");
-				break;
-			} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
-				$this->title = $elems->item(0)->textContent;
-				$this->debug('Title matched: '.$this->title);
-				$this->debug("...XPath match: $pattern");
-				// remove title from document
-				try {
-					$elems->item(0)->parentNode->removeChild($elems->item(0));
-				} catch (DOMException $e) {
-					// do nothing
-				}
-				break;
-			}
-		}
-		
-		// try to get author (if it hasn't already been set)
-		if (empty($this->author)) {
-			foreach ($this->config->author as $pattern) {
-				$elems = @$xpath->evaluate($pattern, $this->readability->dom);
-				if (is_string($elems)) {
-					if (trim($elems) != '') {
-						$this->author[] = trim($elems);
-						$this->debug('Author expression evaluated as string: '.trim($elems));
-						$this->debug("...XPath match: $pattern");
-						break;
-					}
-				} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
-					foreach ($elems as $elem) {
-						if (!isset($elem->parentNode)) continue;
-						$this->author[] = trim($elem->textContent);
-						$this->debug('Author matched: '.trim($elem->textContent));
-					}
-					if (!empty($this->author)) {
-						$this->debug("...XPath match: $pattern");
-						break;
-					}
-				}
-			}
-		}
-		
-		// try to get language
-		$_lang_xpath = array('//html[@lang]/@lang', '//meta[@name="DC.language"]/@content');
-		foreach ($_lang_xpath as $pattern) {
-			$elems = @$xpath->evaluate($pattern, $this->readability->dom);
-			if (is_string($elems)) {
-				if (trim($elems) != '') {
-					$this->language = trim($elems);
-					$this->debug('Language matched: '.$this->language);
-					break;
-				}
-			} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
-				foreach ($elems as $elem) {
-					if (!isset($elem->parentNode)) continue;
-					$this->language = trim($elem->textContent);
-					$this->debug('Language matched: '.$this->language);					
-				}
-				if ($this->language) break;
-			}
-		}
-		
-		// try to get date
-		foreach ($this->config->date as $pattern) {
-			$elems = @$xpath->evaluate($pattern, $this->readability->dom);
-			if (is_string($elems)) {
-				$this->date = strtotime(trim($elems, "; \t\n\r\0\x0B"));				
-			} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
-				$this->date = $elems->item(0)->textContent;
-				$this->date = strtotime(trim($this->date, "; \t\n\r\0\x0B"));
-				// remove date from document
-				// $elems->item(0)->parentNode->removeChild($elems->item(0));
-			}
-			if (!$this->date) {
-				$this->date = null;
-			} else {
-				$this->debug('Date matched: '.date('Y-m-d H:i:s', $this->date));
-				$this->debug("...XPath match: $pattern");
-				break;
-			}
-		}
-
-		// strip elements (using xpath expressions)
-		foreach ($this->config->strip as $pattern) {
-			$elems = @$xpath->query($pattern, $this->readability->dom);
-			// check for matches
-			if ($elems && $elems->length > 0) {
-				$this->debug('Stripping '.$elems->length.' elements (strip)');
-				for ($i=$elems->length-1; $i >= 0; $i--) {
-					$elems->item($i)->parentNode->removeChild($elems->item($i));
-				}
-			}
-		}
-		
-		// strip elements (using id and class attribute values)
-		foreach ($this->config->strip_id_or_class as $string) {
-			$string = strtr($string, array("'"=>'', '"'=>''));
-			$elems = @$xpath->query("//*[contains(@class, '$string') or contains(@id, '$string')]", $this->readability->dom);
-			// check for matches
-			if ($elems && $elems->length > 0) {
-				$this->debug('Stripping '.$elems->length.' elements (strip_id_or_class)');
-				for ($i=$elems->length-1; $i >= 0; $i--) {
-					$elems->item($i)->parentNode->removeChild($elems->item($i));
-				}
-			}
-		}
-		
-		// strip images (using src attribute values)
-		foreach ($this->config->strip_image_src as $string) {
-			$string = strtr($string, array("'"=>'', '"'=>''));
-			$elems = @$xpath->query("//img[contains(@src, '$string')]", $this->readability->dom);
-			// check for matches
-			if ($elems && $elems->length > 0) {
-				$this->debug('Stripping '.$elems->length.' image elements');
-				for ($i=$elems->length-1; $i >= 0; $i--) {
-					$elems->item($i)->parentNode->removeChild($elems->item($i));
-				}
-			}
-		}
-		// strip elements using Readability.com and Instapaper.com ignore class names
-		// .entry-unrelated and .instapaper_ignore
-		// See https://www.readability.com/publishers/guidelines/#view-plainGuidelines
-		// and http://blog.instapaper.com/post/730281947
-		$elems = @$xpath->query("//*[contains(concat(' ',normalize-space(@class),' '),' entry-unrelated ') or contains(concat(' ',normalize-space(@class),' '),' instapaper_ignore ')]", $this->readability->dom);
-		// check for matches
-		if ($elems && $elems->length > 0) {
-			$this->debug('Stripping '.$elems->length.' .entry-unrelated,.instapaper_ignore elements');
-			for ($i=$elems->length-1; $i >= 0; $i--) {
-				$elems->item($i)->parentNode->removeChild($elems->item($i));
-			}
-		}
-		
-		// strip elements that contain style="display: none;"
-		$elems = @$xpath->query("//*[contains(@style,'display:none')]", $this->readability->dom);
-		// check for matches
-		if ($elems && $elems->length > 0) {
-			$this->debug('Stripping '.$elems->length.' elements with inline display:none style');
-			for ($i=$elems->length-1; $i >= 0; $i--) {
-				$elems->item($i)->parentNode->removeChild($elems->item($i));
-			}
-		}
-		
-		// try to get body
-		foreach ($this->config->body as $pattern) {
-			$elems = @$xpath->query($pattern, $this->readability->dom);
-			// check for matches
-			if ($elems && $elems->length > 0) {
-				$this->debug('Body matched');
-				$this->debug("...XPath match: $pattern");
-				if ($elems->length == 1) {				
-					$this->body = $elems->item(0);
-					// prune (clean up elements that may not be content)
-					if ($this->config->prune()) {
-						$this->debug('...pruning content');
-						$this->readability->prepArticle($this->body);
-					}
-					break;
-				} else {
-					$this->body = $this->readability->dom->createElement('div');
-					$this->debug($elems->length.' body elems found');
-					foreach ($elems as $elem) {
-						if (!isset($elem->parentNode)) continue;
-						$isDescendant = false;
-						foreach ($this->body->childNodes as $parent) {
-							if ($this->isDescendant($parent, $elem)) {
-								$isDescendant = true;
-								break;
-							}
-						}
-						if ($isDescendant) {
-							$this->debug('...element is child of another body element, skipping.');
-						} else {
-							// prune (clean up elements that may not be content)
-							if ($this->config->prune()) {
-								$this->debug('Pruning content');
-								$this->readability->prepArticle($elem);
-							}
-							$this->debug('...element added to body');
-							$this->body->appendChild($elem);
-						}
-					}
-					if ($this->body->hasChildNodes()) break;
-				}
-			}
-		}		
-		
-		// auto detect?
-		$detect_title = $detect_body = $detect_author = $detect_date = false;
-		// detect title?
-		if (!isset($this->title)) {
-			if (empty($this->config->title) || $this->config->autodetect_on_failure()) {
-				$detect_title = true;
-			}
-		}
-		// detect body?
-		if (!isset($this->body)) {
-			if (empty($this->config->body) || $this->config->autodetect_on_failure()) {
-				$detect_body = true;
-			}
-		}
-		// detect author?
-		if (empty($this->author)) {
-			if (empty($this->config->author) || $this->config->autodetect_on_failure()) {
-				$detect_author = true;
-			}
-		}
-		// detect date?
-		if (!isset($this->date)) {
-			if (empty($this->config->date) || $this->config->autodetect_on_failure()) {
-				$detect_date = true;
-			}
-		}
-
-		// check for hNews
-		if ($detect_title || $detect_body) {
-			// check for hentry
-			$elems = @$xpath->query("//*[contains(concat(' ',normalize-space(@class),' '),' hentry ')]", $this->readability->dom);
-			if ($elems && $elems->length > 0) {
-				$this->debug('hNews: found hentry');
-				$hentry = $elems->item(0);
-				
-				if ($detect_title) {
-					// check for entry-title
-					$elems = @$xpath->query(".//*[contains(concat(' ',normalize-space(@class),' '),' entry-title ')]", $hentry);
-					if ($elems && $elems->length > 0) {
-						$this->title = $elems->item(0)->textContent;
-						$this->debug('hNews: found entry-title: '.$this->title);
-						// remove title from document
-						$elems->item(0)->parentNode->removeChild($elems->item(0));
-						$detect_title = false;
-					}
-				}
-				
-				if ($detect_date) {
-					// check for time element with pubdate attribute
-					$elems = @$xpath->query(".//time[@pubdate] | .//abbr[contains(concat(' ',normalize-space(@class),' '),' published ')]", $hentry);
-					if ($elems && $elems->length > 0) {
-						$this->date = strtotime(trim($elems->item(0)->textContent));
-						// remove date from document
-						//$elems->item(0)->parentNode->removeChild($elems->item(0));
-						if ($this->date) {
-							$this->debug('hNews: found publication date: '.date('Y-m-d H:i:s', $this->date));
-							$detect_date = false;
-						} else {
-							$this->date = null;
-						}
-					}
-				}
-
-				if ($detect_author) {
-					// check for time element with pubdate attribute
-					$elems = @$xpath->query(".//*[contains(concat(' ',normalize-space(@class),' '),' vcard ') and (contains(concat(' ',normalize-space(@class),' '),' author ') or contains(concat(' ',normalize-space(@class),' '),' byline '))]", $hentry);
-					if ($elems && $elems->length > 0) {
-						$author = $elems->item(0);
-						$fn = @$xpath->query(".//*[contains(concat(' ',normalize-space(@class),' '),' fn ')]", $author);
-						if ($fn && $fn->length > 0) {
-							foreach ($fn as $_fn) {
-								if (trim($_fn->textContent) != '') {
-									$this->author[] = trim($_fn->textContent);
-									$this->debug('hNews: found author: '.trim($_fn->textContent));
-								}
-							}
-						} else {
-							if (trim($author->textContent) != '') {
-								$this->author[] = trim($author->textContent);
-								$this->debug('hNews: found author: '.trim($author->textContent));
-							}
-						}
-						$detect_author = empty($this->author);
-					}
-				}
-				
-				// check for entry-content.
-				// according to hAtom spec, if there are multiple elements marked entry-content,
-				// we include all of these in the order they appear - see http://microformats.org/wiki/hatom#Entry_Content
-				if ($detect_body) {
-					$elems = @$xpath->query(".//*[contains(concat(' ',normalize-space(@class),' '),' entry-content ')]", $hentry);
-					if ($elems && $elems->length > 0) {
-						$this->debug('hNews: found entry-content');
-						if ($elems->length == 1) {
-							// what if it's empty? (some sites misuse hNews - place their content outside an empty entry-content element)
-							$e = $elems->item(0);
-							if (($e->tagName == 'img') || (trim($e->textContent) != '')) {
-								$this->body = $elems->item(0);
-								// prune (clean up elements that may not be content)
-								if ($this->config->prune()) {
-									$this->debug('Pruning content');
-									$this->readability->prepArticle($this->body);
-								}
-								$detect_body = false;
-							} else {
-								$this->debug('hNews: skipping entry-content - appears not to contain content');
-							}
-							unset($e);
-						} else {
-							$this->body = $this->readability->dom->createElement('div');
-							$this->debug($elems->length.' entry-content elems found');
-							foreach ($elems as $elem) {
-								if (!isset($elem->parentNode)) continue;
-								$isDescendant = false;
-								foreach ($this->body->childNodes as $parent) {
-									if ($this->isDescendant($parent, $elem)) {
-										$isDescendant = true;
-										break;
-									}
-								}
-								if ($isDescendant) {
-									$this->debug('Element is child of another body element, skipping.');
-								} else {
-									// prune (clean up elements that may not be content)
-									if ($this->config->prune()) {
-										$this->debug('Pruning content');
-										$this->readability->prepArticle($elem);
-									}								
-									$this->debug('Element added to body');									
-									$this->body->appendChild($elem);
-								}
-							}
-							$detect_body = false;
-						}
-					}
-				}
-			}
-		}
-
-		// check for elements marked with instapaper_title
-		if ($detect_title) {
-			// check for instapaper_title
-			$elems = @$xpath->query("//*[contains(concat(' ',normalize-space(@class),' '),' instapaper_title ')]", $this->readability->dom);
-			if ($elems && $elems->length > 0) {
-				$this->title = $elems->item(0)->textContent;
-				$this->debug('Title found (.instapaper_title): '.$this->title);
-				// remove title from document
-				$elems->item(0)->parentNode->removeChild($elems->item(0));
-				$detect_title = false;
-			}
-		}
-		// check for elements marked with instapaper_body
-		if ($detect_body) {
-			$elems = @$xpath->query("//*[contains(concat(' ',normalize-space(@class),' '),' instapaper_body ')]", $this->readability->dom);
-			if ($elems && $elems->length > 0) {
-				$this->debug('body found (.instapaper_body)');
-				$this->body = $elems->item(0);
-				// prune (clean up elements that may not be content)
-				if ($this->config->prune()) {
-					$this->debug('Pruning content');
-					$this->readability->prepArticle($this->body);
-				}
-				$detect_body = false;
-			}
-		}
-		
-		// Find author in rel="author" marked element
-		// We only use this if there's exactly one.
-		// If there's more than one, it could indicate more than
-		// one author, but it could also indicate that we're processing
-		// a page listing different articles with different authors.
-		if ($detect_author) {
-			$elems = @$xpath->query("//a[contains(concat(' ',normalize-space(@rel),' '),' author ')]", $this->readability->dom);
-			if ($elems && $elems->length == 1) {
-				$author = trim($elems->item(0)->textContent);
-				if ($author != '') {
-					$this->debug("Author found (rel=\"author\"): $author");
-					$this->author[] = $author;
-					$detect_author = false;
-				}
-			}
-		}
-
-		// Find date in pubdate marked time element
-		// For the same reason given above, we only use this
-		// if there's exactly one element.
-		if ($detect_date) {
-			$elems = @$xpath->query("//time[@pubdate]", $this->readability->dom);
-			if ($elems && $elems->length == 1) {
-				$this->date = strtotime(trim($elems->item(0)->textContent));
-				// remove date from document
-				//$elems->item(0)->parentNode->removeChild($elems->item(0));
-				if ($this->date) {
-					$this->debug('Date found (pubdate marked time element): '.date('Y-m-d H:i:s', $this->date));
-					$detect_date = false;
-				} else {
-					$this->date = null;
-				}
-			}
-		}
-
-		// still missing title or body, so we detect using Readability
-		if ($detect_title || $detect_body) {
-			$this->debug('Using Readability');
-			// clone body if we're only using Readability for title (otherwise it may interfere with body element)
-			if (isset($this->body)) $this->body = $this->body->cloneNode(true);
-			$success = $this->readability->init();
-		}
-		if ($detect_title) {
-			$this->debug('Detecting title');
-			$this->title = $this->readability->getTitle()->textContent;
-		}
-		if ($detect_body && $success) {
-			$this->debug('Detecting body');
-			$this->body = $this->readability->getContent();
-			if ($this->body->childNodes->length == 1 && $this->body->firstChild->nodeType === XML_ELEMENT_NODE) {
-				$this->body = $this->body->firstChild;
-			}
-			// prune (clean up elements that may not be content)
-			if ($this->config->prune()) {
-				$this->debug('Pruning content');
-				$this->readability->prepArticle($this->body);
-			}
-		}
-		if (isset($this->body)) {
-			// remove scripts
-			$this->readability->removeScripts($this->body);
-			// remove any h1-h6 elements that appear as first thing in the body
-			// and which match our title
-			if (isset($this->title) && ($this->title != '')) {
-				$firstChild = $this->body->firstChild;
-				while ($firstChild->nodeType && ($firstChild->nodeType !== XML_ELEMENT_NODE)) {
-					$firstChild = $firstChild->nextSibling;
-				}
-				if (($firstChild->nodeType === XML_ELEMENT_NODE)
-					&& in_array(strtolower($firstChild->tagName), array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))
-					&& (strtolower(trim($firstChild->textContent)) == strtolower(trim($this->title)))) {
-						$this->body->removeChild($firstChild);
-				}
-			}
-			// prevent self-closing iframes
-			$elems = $this->body->getElementsByTagName('iframe');
-			for ($i = $elems->length-1; $i >= 0; $i--) {
-				$e = $elems->item($i);
-				if (!$e->hasChildNodes()) {
-					$e->appendChild($this->body->ownerDocument->createTextNode('[embedded content]'));
-				}
-			}
-			// remove image lazy loading - WordPress plugin http://wordpress.org/extend/plugins/lazy-load/
-			// the plugin replaces the src attribute to point to a 1x1 gif and puts the original src
-			// inside the data-lazy-src attribute. It also places the original image inside a noscript element 
-			// next to the amended one.
-			$elems = @$xpath->query("//img[@data-lazy-src]", $this->body);
-			for ($i = $elems->length-1; $i >= 0; $i--) {
-				$e = $elems->item($i);
-				// let's see if we can grab image from noscript
-				if ($e->nextSibling !== null && $e->nextSibling->nodeName === 'noscript') {
-					$_new_elem = $e->ownerDocument->createDocumentFragment();
-					@$_new_elem->appendXML($e->nextSibling->innerHTML);
-					$e->nextSibling->parentNode->replaceChild($_new_elem, $e->nextSibling);
-					$e->parentNode->removeChild($e);
-				} else {
-					// Use data-lazy-src as src value
-					$e->setAttribute('src', $e->getAttribute('data-lazy-src'));
-					$e->removeAttribute('data-lazy-src');
-				}
-			}
-		
-			$this->success = true;
-		}
-		
-		// if we've had no success and we've used tidy, there's a chance
-		// that tidy has messed up. So let's try again without tidy...
-		if (!$this->success && $tidied && $smart_tidy) {
-			$this->debug('Trying again without tidy');
-			$this->process($original_html, $url, false);
-		}
-
-		return $this->success;
-	}
-	
-	private function isDescendant(DOMElement $parent, DOMElement $child) {
-		$node = $child->parentNode;
-		while ($node != null) {
-			if ($node->isSameNode($parent))	return true;
-			$node = $node->parentNode;
-		}
-		return false;
-	}
-
-	public function getContent() {
-		return $this->body;
-	}
-	
-	public function getTitle() {
-		return $this->title;
-	}
-	
-	public function getAuthors() {
-		return $this->author;
-	}
-	
-	public function getLanguage() {
-		return $this->language;
-	}
-	
-	public function getDate() {
-		return $this->date;
-	}
-	
-	public function getSiteConfig() {
-		return $this->config;
-	}
-	
-	public function getNextPageUrl() {
-		return $this->nextPageUrl;
-	}
-}
-?>
\ No newline at end of file
+ true,
+				 'output-xhtml' => true,
+				 'logical-emphasis' => true,
+				 'show-body-only' => false,
+				 'new-blocklevel-tags' => 'article, aside, footer, header, hgroup, menu, nav, section, details, datagrid',
+				 'new-inline-tags' => 'mark, time, meter, progress, data',
+				 'wrap' => 0,
+				 'drop-empty-paras' => true,
+				 'drop-proprietary-attributes' => false,
+				 'enclose-text' => true,
+				 'enclose-block-text' => true,
+				 'merge-divs' => true,
+				 'merge-spans' => true,
+				 'char-encoding' => 'utf8',
+				 'hide-comments' => true
+				 );
+	protected $html;
+	protected $config;
+	protected $title;
+	protected $author = array();
+	protected $language;
+	protected $date;
+	protected $body;
+	protected $success = false;
+	protected $nextPageUrl;
+	public $allowedParsers = array('libxml', 'html5lib');
+	public $fingerprints = array();
+	public $readability;
+	public $debug = false;
+	public $debugVerbose = false;
+
+	function __construct($path, $fallback=null) {
+		SiteConfig::set_config_path($path, $fallback);	
+	}
+	
+	protected function debug($msg) {
+		if ($this->debug) {
+			$mem = round(memory_get_usage()/1024, 2);
+			$memPeak = round(memory_get_peak_usage()/1024, 2);
+			echo '* ',$msg;
+			if ($this->debugVerbose) echo ' - mem used: ',$mem," (peak: $memPeak)";
+			echo "\n";
+			ob_flush();
+			flush();
+		}
+	}
+	
+	public function reset() {
+		$this->html = null;
+		$this->readability = null;
+		$this->config = null;
+		$this->title = null;
+		$this->body = null;
+		$this->author = array();
+		$this->language = null;
+		$this->date = null;
+		$this->nextPageUrl = null;
+		$this->success = false;
+	}
+
+	public function findHostUsingFingerprints($html) {
+		$this->debug('Checking fingerprints...');
+		$head = substr($html, 0, 8000);
+		foreach ($this->fingerprints as $_fp => $_fphost) {
+			$lookin = 'html';
+			if (is_array($_fphost)) {
+				if (isset($_fphost['head']) && $_fphost['head']) {
+					$lookin = 'head';
+				}
+				$_fphost = $_fphost['hostname'];
+			}
+			if (strpos($$lookin, $_fp) !== false) {
+				$this->debug("Found match: $_fphost");
+				return $_fphost;
+			}
+		}
+		$this->debug('No fingerprint matches');
+		return false;
+	}
+	
+	// returns SiteConfig instance (joined in order: exact match, wildcard, fingerprint, global, default)
+	public function buildSiteConfig($url, $html='', $add_to_cache=true) {
+		// extract host name
+		$host = @parse_url($url, PHP_URL_HOST);
+		$host = strtolower($host);
+		if (substr($host, 0, 4) == 'www.') $host = substr($host, 4);
+		// is merged version already cached?
+		if (SiteConfig::is_cached("$host.merged")) {
+			$this->debug("Returning cached and merged site config for $host");
+			return SiteConfig::build("$host.merged");
+		}
+		// let's build from site_config/custom/ and standard/
+		$config = SiteConfig::build($host);
+		if ($add_to_cache && $config && !SiteConfig::is_cached("$host")) {
+			SiteConfig::add_to_cache($host, $config);
+		}
+		// if no match, use defaults
+		if (!$config) $config = new SiteConfig();
+		// load fingerprint config?
+		if ($config->autodetect_on_failure()) {
+			// check HTML for fingerprints
+			if (!empty($this->fingerprints) && ($_fphost = $this->findHostUsingFingerprints($html))) {
+				if ($config_fingerprint = SiteConfig::build($_fphost)) {
+					$this->debug("Appending site config settings from $_fphost (fingerprint match)");
+					$config->append($config_fingerprint);
+					if ($add_to_cache && !SiteConfig::is_cached($_fphost)) {
+						//$config_fingerprint->cache_in_apc = true;
+						SiteConfig::add_to_cache($_fphost, $config_fingerprint);
+					}
+				}
+			}
+		}
+		// load global config?
+		if ($config->autodetect_on_failure()) {
+			if ($config_global = SiteConfig::build('global', true)) {
+				$this->debug('Appending site config settings from global.txt');
+				$config->append($config_global);
+				if ($add_to_cache && !SiteConfig::is_cached('global')) {
+					//$config_global->cache_in_apc = true;
+					SiteConfig::add_to_cache('global', $config_global);
+				}
+			}
+		}
+		// store copy of merged config
+		if ($add_to_cache) {
+			// do not store in APC if wildcard match
+			$use_apc = ($host == $config->cache_key);
+			$config->cache_key = null;
+			SiteConfig::add_to_cache("$host.merged", $config, $use_apc);
+		}
+		return $config;
+	}
+	
+	// returns true on success, false on failure
+	// $smart_tidy indicates that if tidy is used and no results are produced, we will
+	// try again without it. Tidy helps us deal with PHP's patchy HTML parsing most of the time
+	// but it has problems of its own which we try to avoid with this option.
+	public function process($html, $url, $smart_tidy=true) {
+		$this->reset();
+		$this->config = $this->buildSiteConfig($url, $html);
+		
+		// do string replacements
+		if (!empty($this->config->find_string)) {
+			if (count($this->config->find_string) == count($this->config->replace_string)) {
+				$html = str_replace($this->config->find_string, $this->config->replace_string, $html, $_count);
+				$this->debug("Strings replaced: $_count (find_string and/or replace_string)");
+			} else {
+				$this->debug('Skipped string replacement - incorrect number of find-replace strings in site config');
+			}
+			unset($_count);
+		}
+		
+		// use tidy (if it exists)?
+		// This fixes problems with some sites which would otherwise
+		// trouble DOMDocument's HTML parsing. (Although sometimes it
+		// makes matters worse, which is why you can override it in site config files.)
+		$tidied = false;
+		if ($this->config->tidy() && function_exists('tidy_parse_string') && $smart_tidy) {
+			$this->debug('Using Tidy');
+			$tidy = tidy_parse_string($html, self::$tidy_config, 'UTF8');
+			if (tidy_clean_repair($tidy)) {
+				$original_html = $html;
+				$tidied = true;
+				$html = $tidy->value;
+			}
+			unset($tidy);
+		}
+		
+		// load and parse html
+		$_parser = $this->config->parser();
+		if (!in_array($_parser, $this->allowedParsers)) {
+			$this->debug("HTML parser $_parser not listed, using libxml instead");
+			$_parser = 'libxml';
+		}
+		$this->debug("Attempting to parse HTML with $_parser");
+		$this->readability = new Readability($html, $url, $_parser);
+		
+		// we use xpath to find elements in the given HTML document
+		// see http://en.wikipedia.org/wiki/XPath_1.0
+		$xpath = new DOMXPath($this->readability->dom);
+
+		// try to get next page link
+		foreach ($this->config->next_page_link as $pattern) {
+			$elems = @$xpath->evaluate($pattern, $this->readability->dom);
+			if (is_string($elems)) {
+				$this->nextPageUrl = trim($elems);
+				break;
+			} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
+				foreach ($elems as $item) {
+					if ($item instanceof DOMElement && $item->hasAttribute('href')) {
+						$this->nextPageUrl = $item->getAttribute('href');
+						break 2;
+					} elseif ($item instanceof DOMAttr && $item->value) {
+						$this->nextPageUrl = $item->value;
+						break 2;
+					}
+				}
+			}
+		}
+		
+		// try to get title
+		foreach ($this->config->title as $pattern) {
+			// $this->debug("Trying $pattern");
+			$elems = @$xpath->evaluate($pattern, $this->readability->dom);
+			if (is_string($elems)) {
+				$this->title = trim($elems);
+				$this->debug('Title expression evaluated as string: '.$this->title);
+				$this->debug("...XPath match: $pattern");
+				break;
+			} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
+				$this->title = $elems->item(0)->textContent;
+				$this->debug('Title matched: '.$this->title);
+				$this->debug("...XPath match: $pattern");
+				// remove title from document
+				try {
+					@$elems->item(0)->parentNode->removeChild($elems->item(0));
+				} catch (DOMException $e) {
+					// do nothing
+				}
+				break;
+			}
+		}
+		
+		// try to get author (if it hasn't already been set)
+		if (empty($this->author)) {
+			foreach ($this->config->author as $pattern) {
+				$elems = @$xpath->evaluate($pattern, $this->readability->dom);
+				if (is_string($elems)) {
+					if (trim($elems) != '') {
+						$this->author[] = trim($elems);
+						$this->debug('Author expression evaluated as string: '.trim($elems));
+						$this->debug("...XPath match: $pattern");
+						break;
+					}
+				} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
+					foreach ($elems as $elem) {
+						if (!isset($elem->parentNode)) continue;
+						$this->author[] = trim($elem->textContent);
+						$this->debug('Author matched: '.trim($elem->textContent));
+					}
+					if (!empty($this->author)) {
+						$this->debug("...XPath match: $pattern");
+						break;
+					}
+				}
+			}
+		}
+		
+		// try to get language
+		$_lang_xpath = array('//html[@lang]/@lang', '//meta[@name="DC.language"]/@content');
+		foreach ($_lang_xpath as $pattern) {
+			$elems = @$xpath->evaluate($pattern, $this->readability->dom);
+			if (is_string($elems)) {
+				if (trim($elems) != '') {
+					$this->language = trim($elems);
+					$this->debug('Language matched: '.$this->language);
+					break;
+				}
+			} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
+				foreach ($elems as $elem) {
+					if (!isset($elem->parentNode)) continue;
+					$this->language = trim($elem->textContent);
+					$this->debug('Language matched: '.$this->language);					
+				}
+				if ($this->language) break;
+			}
+		}
+		
+		// try to get date
+		foreach ($this->config->date as $pattern) {
+			$elems = @$xpath->evaluate($pattern, $this->readability->dom);
+			if (is_string($elems)) {
+				$this->date = strtotime(trim($elems, "; \t\n\r\0\x0B"));				
+			} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
+				$this->date = $elems->item(0)->textContent;
+				$this->date = strtotime(trim($this->date, "; \t\n\r\0\x0B"));
+				// remove date from document
+				// $elems->item(0)->parentNode->removeChild($elems->item(0));
+			}
+			if (!$this->date) {
+				$this->date = null;
+			} else {
+				$this->debug('Date matched: '.date('Y-m-d H:i:s', $this->date));
+				$this->debug("...XPath match: $pattern");
+				break;
+			}
+		}
+
+		// strip elements (using xpath expressions)
+		foreach ($this->config->strip as $pattern) {
+			$elems = @$xpath->query($pattern, $this->readability->dom);
+			// check for matches
+			if ($elems && $elems->length > 0) {
+				$this->debug('Stripping '.$elems->length.' elements (strip)');
+				for ($i=$elems->length-1; $i >= 0; $i--) {
+					$elems->item($i)->parentNode->removeChild($elems->item($i));
+				}
+			}
+		}
+		
+		// strip elements (using id and class attribute values)
+		foreach ($this->config->strip_id_or_class as $string) {
+			$string = strtr($string, array("'"=>'', '"'=>''));
+			$elems = @$xpath->query("//*[contains(@class, '$string') or contains(@id, '$string')]", $this->readability->dom);
+			// check for matches
+			if ($elems && $elems->length > 0) {
+				$this->debug('Stripping '.$elems->length.' elements (strip_id_or_class)');
+				for ($i=$elems->length-1; $i >= 0; $i--) {
+					$elems->item($i)->parentNode->removeChild($elems->item($i));
+				}
+			}
+		}
+		
+		// strip images (using src attribute values)
+		foreach ($this->config->strip_image_src as $string) {
+			$string = strtr($string, array("'"=>'', '"'=>''));
+			$elems = @$xpath->query("//img[contains(@src, '$string')]", $this->readability->dom);
+			// check for matches
+			if ($elems && $elems->length > 0) {
+				$this->debug('Stripping '.$elems->length.' image elements');
+				for ($i=$elems->length-1; $i >= 0; $i--) {
+					$elems->item($i)->parentNode->removeChild($elems->item($i));
+				}
+			}
+		}
+		// strip elements using Readability.com and Instapaper.com ignore class names
+		// .entry-unrelated and .instapaper_ignore
+		// See https://www.readability.com/publishers/guidelines/#view-plainGuidelines
+		// and http://blog.instapaper.com/post/730281947
+		$elems = @$xpath->query("//*[contains(concat(' ',normalize-space(@class),' '),' entry-unrelated ') or contains(concat(' ',normalize-space(@class),' '),' instapaper_ignore ')]", $this->readability->dom);
+		// check for matches
+		if ($elems && $elems->length > 0) {
+			$this->debug('Stripping '.$elems->length.' .entry-unrelated,.instapaper_ignore elements');
+			for ($i=$elems->length-1; $i >= 0; $i--) {
+				$elems->item($i)->parentNode->removeChild($elems->item($i));
+			}
+		}
+		
+		// strip elements that contain style="display: none;"
+		$elems = @$xpath->query("//*[contains(@style,'display:none')]", $this->readability->dom);
+		// check for matches
+		if ($elems && $elems->length > 0) {
+			$this->debug('Stripping '.$elems->length.' elements with inline display:none style');
+			for ($i=$elems->length-1; $i >= 0; $i--) {
+				$elems->item($i)->parentNode->removeChild($elems->item($i));
+			}
+		}
+		
+		// try to get body
+		foreach ($this->config->body as $pattern) {
+			$elems = @$xpath->query($pattern, $this->readability->dom);
+			// check for matches
+			if ($elems && $elems->length > 0) {
+				$this->debug('Body matched');
+				$this->debug("...XPath match: $pattern");
+				if ($elems->length == 1) {				
+					$this->body = $elems->item(0);
+					// prune (clean up elements that may not be content)
+					if ($this->config->prune()) {
+						$this->debug('...pruning content');
+						$this->readability->prepArticle($this->body);
+					}
+					break;
+				} else {
+					$this->body = $this->readability->dom->createElement('div');
+					$this->debug($elems->length.' body elems found');
+					foreach ($elems as $elem) {
+						if (!isset($elem->parentNode)) continue;
+						$isDescendant = false;
+						foreach ($this->body->childNodes as $parent) {
+							if ($this->isDescendant($parent, $elem)) {
+								$isDescendant = true;
+								break;
+							}
+						}
+						if ($isDescendant) {
+							$this->debug('...element is child of another body element, skipping.');
+						} else {
+							// prune (clean up elements that may not be content)
+							if ($this->config->prune()) {
+								$this->debug('Pruning content');
+								$this->readability->prepArticle($elem);
+							}
+							$this->debug('...element added to body');
+							$this->body->appendChild($elem);
+						}
+					}
+					if ($this->body->hasChildNodes()) break;
+				}
+			}
+		}		
+		
+		// auto detect?
+		$detect_title = $detect_body = $detect_author = $detect_date = false;
+		// detect title?
+		if (!isset($this->title)) {
+			if (empty($this->config->title) || $this->config->autodetect_on_failure()) {
+				$detect_title = true;
+			}
+		}
+		// detect body?
+		if (!isset($this->body)) {
+			if (empty($this->config->body) || $this->config->autodetect_on_failure()) {
+				$detect_body = true;
+			}
+		}
+		// detect author?
+		if (empty($this->author)) {
+			if (empty($this->config->author) || $this->config->autodetect_on_failure()) {
+				$detect_author = true;
+			}
+		}
+		// detect date?
+		if (!isset($this->date)) {
+			if (empty($this->config->date) || $this->config->autodetect_on_failure()) {
+				$detect_date = true;
+			}
+		}
+
+		// check for hNews
+		if ($detect_title || $detect_body) {
+			// check for hentry
+			$elems = @$xpath->query("//*[contains(concat(' ',normalize-space(@class),' '),' hentry ')]", $this->readability->dom);
+			if ($elems && $elems->length > 0) {
+				$this->debug('hNews: found hentry');
+				$hentry = $elems->item(0);
+				
+				if ($detect_title) {
+					// check for entry-title
+					$elems = @$xpath->query(".//*[contains(concat(' ',normalize-space(@class),' '),' entry-title ')]", $hentry);
+					if ($elems && $elems->length > 0) {
+						$this->title = $elems->item(0)->textContent;
+						$this->debug('hNews: found entry-title: '.$this->title);
+						// remove title from document
+						$elems->item(0)->parentNode->removeChild($elems->item(0));
+						$detect_title = false;
+					}
+				}
+				
+				if ($detect_date) {
+					// check for time element with pubdate attribute
+					$elems = @$xpath->query(".//time[@pubdate] | .//abbr[contains(concat(' ',normalize-space(@class),' '),' published ')]", $hentry);
+					if ($elems && $elems->length > 0) {
+						$this->date = strtotime(trim($elems->item(0)->textContent));
+						// remove date from document
+						//$elems->item(0)->parentNode->removeChild($elems->item(0));
+						if ($this->date) {
+							$this->debug('hNews: found publication date: '.date('Y-m-d H:i:s', $this->date));
+							$detect_date = false;
+						} else {
+							$this->date = null;
+						}
+					}
+				}
+
+				if ($detect_author) {
+					// check for time element with pubdate attribute
+					$elems = @$xpath->query(".//*[contains(concat(' ',normalize-space(@class),' '),' vcard ') and (contains(concat(' ',normalize-space(@class),' '),' author ') or contains(concat(' ',normalize-space(@class),' '),' byline '))]", $hentry);
+					if ($elems && $elems->length > 0) {
+						$author = $elems->item(0);
+						$fn = @$xpath->query(".//*[contains(concat(' ',normalize-space(@class),' '),' fn ')]", $author);
+						if ($fn && $fn->length > 0) {
+							foreach ($fn as $_fn) {
+								if (trim($_fn->textContent) != '') {
+									$this->author[] = trim($_fn->textContent);
+									$this->debug('hNews: found author: '.trim($_fn->textContent));
+								}
+							}
+						} else {
+							if (trim($author->textContent) != '') {
+								$this->author[] = trim($author->textContent);
+								$this->debug('hNews: found author: '.trim($author->textContent));
+							}
+						}
+						$detect_author = empty($this->author);
+					}
+				}
+				
+				// check for entry-content.
+				// according to hAtom spec, if there are multiple elements marked entry-content,
+				// we include all of these in the order they appear - see http://microformats.org/wiki/hatom#Entry_Content
+				if ($detect_body) {
+					$elems = @$xpath->query(".//*[contains(concat(' ',normalize-space(@class),' '),' entry-content ')]", $hentry);
+					if ($elems && $elems->length > 0) {
+						$this->debug('hNews: found entry-content');
+						if ($elems->length == 1) {
+							// what if it's empty? (some sites misuse hNews - place their content outside an empty entry-content element)
+							$e = $elems->item(0);
+							if (($e->tagName == 'img') || (trim($e->textContent) != '')) {
+								$this->body = $elems->item(0);
+								// prune (clean up elements that may not be content)
+								if ($this->config->prune()) {
+									$this->debug('Pruning content');
+									$this->readability->prepArticle($this->body);
+								}
+								$detect_body = false;
+							} else {
+								$this->debug('hNews: skipping entry-content - appears not to contain content');
+							}
+							unset($e);
+						} else {
+							$this->body = $this->readability->dom->createElement('div');
+							$this->debug($elems->length.' entry-content elems found');
+							foreach ($elems as $elem) {
+								if (!isset($elem->parentNode)) continue;
+								$isDescendant = false;
+								foreach ($this->body->childNodes as $parent) {
+									if ($this->isDescendant($parent, $elem)) {
+										$isDescendant = true;
+										break;
+									}
+								}
+								if ($isDescendant) {
+									$this->debug('Element is child of another body element, skipping.');
+								} else {
+									// prune (clean up elements that may not be content)
+									if ($this->config->prune()) {
+										$this->debug('Pruning content');
+										$this->readability->prepArticle($elem);
+									}								
+									$this->debug('Element added to body');									
+									$this->body->appendChild($elem);
+								}
+							}
+							$detect_body = false;
+						}
+					}
+				}
+			}
+		}
+
+		// check for elements marked with instapaper_title
+		if ($detect_title) {
+			// check for instapaper_title
+			$elems = @$xpath->query("//*[contains(concat(' ',normalize-space(@class),' '),' instapaper_title ')]", $this->readability->dom);
+			if ($elems && $elems->length > 0) {
+				$this->title = $elems->item(0)->textContent;
+				$this->debug('Title found (.instapaper_title): '.$this->title);
+				// remove title from document
+				$elems->item(0)->parentNode->removeChild($elems->item(0));
+				$detect_title = false;
+			}
+		}
+		// check for elements marked with instapaper_body
+		if ($detect_body) {
+			$elems = @$xpath->query("//*[contains(concat(' ',normalize-space(@class),' '),' instapaper_body ')]", $this->readability->dom);
+			if ($elems && $elems->length > 0) {
+				$this->debug('body found (.instapaper_body)');
+				$this->body = $elems->item(0);
+				// prune (clean up elements that may not be content)
+				if ($this->config->prune()) {
+					$this->debug('Pruning content');
+					$this->readability->prepArticle($this->body);
+				}
+				$detect_body = false;
+			}
+		}
+		
+		// Find author in rel="author" marked element
+		// We only use this if there's exactly one.
+		// If there's more than one, it could indicate more than
+		// one author, but it could also indicate that we're processing
+		// a page listing different articles with different authors.
+		if ($detect_author) {
+			$elems = @$xpath->query("//a[contains(concat(' ',normalize-space(@rel),' '),' author ')]", $this->readability->dom);
+			if ($elems && $elems->length == 1) {
+				$author = trim($elems->item(0)->textContent);
+				if ($author != '') {
+					$this->debug("Author found (rel=\"author\"): $author");
+					$this->author[] = $author;
+					$detect_author = false;
+				}
+			}
+		}
+
+		// Find date in pubdate marked time element
+		// For the same reason given above, we only use this
+		// if there's exactly one element.
+		if ($detect_date) {
+			$elems = @$xpath->query("//time[@pubdate]", $this->readability->dom);
+			if ($elems && $elems->length == 1) {
+				$this->date = strtotime(trim($elems->item(0)->textContent));
+				// remove date from document
+				//$elems->item(0)->parentNode->removeChild($elems->item(0));
+				if ($this->date) {
+					$this->debug('Date found (pubdate marked time element): '.date('Y-m-d H:i:s', $this->date));
+					$detect_date = false;
+				} else {
+					$this->date = null;
+				}
+			}
+		}
+
+		// still missing title or body, so we detect using Readability
+		if ($detect_title || $detect_body) {
+			$this->debug('Using Readability');
+			// clone body if we're only using Readability for title (otherwise it may interfere with body element)
+			if (isset($this->body)) $this->body = $this->body->cloneNode(true);
+			$success = $this->readability->init();
+		}
+		if ($detect_title) {
+			$this->debug('Detecting title');
+			$this->title = $this->readability->getTitle()->textContent;
+		}
+		if ($detect_body && $success) {
+			$this->debug('Detecting body');
+			$this->body = $this->readability->getContent();
+			if ($this->body->childNodes->length == 1 && $this->body->firstChild->nodeType === XML_ELEMENT_NODE) {
+				$this->body = $this->body->firstChild;
+			}
+			// prune (clean up elements that may not be content)
+			if ($this->config->prune()) {
+				$this->debug('Pruning content');
+				$this->readability->prepArticle($this->body);
+			}
+		}
+		if (isset($this->body)) {
+			// remove scripts
+			$this->readability->removeScripts($this->body);
+			// remove any h1-h6 elements that appear as first thing in the body
+			// and which match our title
+			if (isset($this->title) && ($this->title != '')) {
+				$firstChild = $this->body->firstChild;
+				while ($firstChild->nodeType && ($firstChild->nodeType !== XML_ELEMENT_NODE)) {
+					$firstChild = $firstChild->nextSibling;
+				}
+				if (($firstChild->nodeType === XML_ELEMENT_NODE)
+					&& in_array(strtolower($firstChild->tagName), array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))
+					&& (strtolower(trim($firstChild->textContent)) == strtolower(trim($this->title)))) {
+						$this->body->removeChild($firstChild);
+				}
+			}
+			// prevent self-closing iframes
+			$elems = $this->body->getElementsByTagName('iframe');
+			for ($i = $elems->length-1; $i >= 0; $i--) {
+				$e = $elems->item($i);
+				if (!$e->hasChildNodes()) {
+					$e->appendChild($this->body->ownerDocument->createTextNode('[embedded content]'));
+				}
+			}
+			// remove image lazy loading - WordPress plugin http://wordpress.org/extend/plugins/lazy-load/
+			// the plugin replaces the src attribute to point to a 1x1 gif and puts the original src
+			// inside the data-lazy-src attribute. It also places the original image inside a noscript element 
+			// next to the amended one.
+			$elems = @$xpath->query("//img[@data-lazy-src]", $this->body);
+			for ($i = $elems->length-1; $i >= 0; $i--) {
+				$e = $elems->item($i);
+				// let's see if we can grab image from noscript
+				if ($e->nextSibling !== null && $e->nextSibling->nodeName === 'noscript') {
+					$_new_elem = $e->ownerDocument->createDocumentFragment();
+					@$_new_elem->appendXML($e->nextSibling->innerHTML);
+					$e->nextSibling->parentNode->replaceChild($_new_elem, $e->nextSibling);
+					$e->parentNode->removeChild($e);
+				} else {
+					// Use data-lazy-src as src value
+					$e->setAttribute('src', $e->getAttribute('data-lazy-src'));
+					$e->removeAttribute('data-lazy-src');
+				}
+			}
+		
+			$this->success = true;
+		}
+		
+		// if we've had no success and we've used tidy, there's a chance
+		// that tidy has messed up. So let's try again without tidy...
+		if (!$this->success && $tidied && $smart_tidy) {
+			$this->debug('Trying again without tidy');
+			$this->process($original_html, $url, false);
+		}
+
+		return $this->success;
+	}
+	
+	private function isDescendant(DOMElement $parent, DOMElement $child) {
+		$node = $child->parentNode;
+		while ($node != null) {
+			if ($node->isSameNode($parent))	return true;
+			$node = $node->parentNode;
+		}
+		return false;
+	}
+
+	public function getContent() {
+		return $this->body;
+	}
+	
+	public function getTitle() {
+		return $this->title;
+	}
+	
+	public function getAuthors() {
+		return $this->author;
+	}
+	
+	public function getLanguage() {
+		return $this->language;
+	}
+	
+	public function getDate() {
+		return $this->date;
+	}
+	
+	public function getSiteConfig() {
+		return $this->config;
+	}
+	
+	public function getNextPageUrl() {
+		return $this->nextPageUrl;
+	}
+}
\ No newline at end of file
diff --git a/inc/3rdparty/libraries/content-extractor/SiteConfig.php b/inc/3rdparty/libraries/content-extractor/SiteConfig.php
index c5e300d7..1f6a7603 100644
--- a/inc/3rdparty/libraries/content-extractor/SiteConfig.php
+++ b/inc/3rdparty/libraries/content-extractor/SiteConfig.php
@@ -1,338 +1,343 @@
-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
+tidy)) ? $this->tidy : $this->default_tidy;
+		return $this->tidy;
+	}
+	
+	// return bool or null
+	public function prune($use_default=true) {
+		if ($use_default) return (isset($this->prune)) ? $this->prune : $this->default_prune;
+		return $this->prune;
+	}
+	
+	// return string or null
+	public function parser($use_default=true) {
+		if ($use_default) return (isset($this->parser)) ? $this->parser : $this->default_parser;
+		return $this->parser;
+	}
+
+	// return bool or null
+	public function autodetect_on_failure($use_default=true) {
+		if ($use_default) return (isset($this->autodetect_on_failure)) ? $this->autodetect_on_failure : $this->default_autodetect_on_failure;
+		return $this->autodetect_on_failure;
+	}
+	
+	public static function set_config_path($path, $fallback=null) {
+		self::$config_path = $path;
+		self::$config_path_fallback = $fallback;
+	}
+	
+	public static function add_to_cache($key, SiteConfig $config, $use_apc=true) {
+		$key = strtolower($key);
+		if (substr($key, 0, 4) == 'www.') $key = substr($key, 4);
+		if ($config->cache_key) $key = $config->cache_key;
+		self::$config_cache[$key] = $config;
+		if (self::$apc && $use_apc) {
+			self::debug("Adding site config to APC cache with key sc.$key");
+			apc_add("sc.$key", $config);
+		}
+		self::debug("Cached site config with key $key");
+	}
+	
+	public static function is_cached($key) {
+		$key = strtolower($key);
+		if (substr($key, 0, 4) == 'www.') $key = substr($key, 4);
+		if (array_key_exists($key, self::$config_cache)) {
+			return true;
+		} elseif (self::$apc && (bool)apc_fetch("sc.$key")) {
+			return true;
+		}
+		return false;
+	}
+	
+	public function append(SiteConfig $newconfig) {
+		// check for commands where we accept multiple statements (no test_url)
+		foreach (array('title', 'body', 'author', 'date', 'strip', 'strip_id_or_class', 'strip_image_src', 'single_page_link', 'single_page_link_in_feed', 'next_page_link', 'http_header') as $var) {
+			// append array elements for this config variable from $newconfig to this config
+			//$this->$var = $this->$var + $newconfig->$var;
+			$this->$var = array_unique(array_merge($this->$var, $newconfig->$var));
+		}
+		// check for single statement commands
+		// we do not overwrite existing non null values
+		foreach (array('tidy', 'prune', 'parser', 'autodetect_on_failure') as $var) {
+			if ($this->$var === null) $this->$var = $newconfig->$var;
+		}
+		// treat find_string and replace_string separately (don't apply array_unique) (thanks fabrizio!)
+		foreach (array('find_string', 'replace_string') as $var) {
+			// append array elements for this config variable from $newconfig to this config
+			//$this->$var = $this->$var + $newconfig->$var;
+			$this->$var = array_merge($this->$var, $newconfig->$var);
+		}
+	}
+	
+	// returns SiteConfig instance if an appropriate one is found, false otherwise
+	// if $exact_host_match is true, we will not look for wildcard config matches
+	// by default if host is 'test.example.org' we will look for and load '.example.org.txt' if it exists
+	public static function build($host, $exact_host_match=false) {
+		$host = strtolower($host);
+		if (substr($host, 0, 4) == 'www.') $host = substr($host, 4);
+		if (!$host || (strlen($host) > 200) || !preg_match(self::HOSTNAME_REGEX, ltrim($host, '.'))) return false;
+		// check for site configuration
+		$try = array($host);
+		// should we look for wildcard matches 
+		if (!$exact_host_match) {
+			$split = explode('.', $host);
+			if (count($split) > 1) {
+				array_shift($split);
+				$try[] = '.'.implode('.', $split);
+			}
+		}
+		
+		// look for site config file in primary folder
+		self::debug(". looking for site config for $host in primary folder");
+		foreach ($try as $h) {
+			if (array_key_exists($h, self::$config_cache)) {
+				self::debug("... site config for $h already loaded in this request");
+				return self::$config_cache[$h];
+			} elseif (self::$apc && ($sconfig = apc_fetch("sc.$h"))) {
+				self::debug("... site config for $h in APC cache");
+				return $sconfig;
+			} elseif (file_exists(self::$config_path."/$h.txt")) {
+				self::debug("... found site config ($h.txt)");
+				$file_primary = self::$config_path."/$h.txt";
+				$matched_name = $h;
+				break;
+			}
+		}
+		
+		// if we found site config, process it
+		if (isset($file_primary)) {
+			$config_lines = file($file_primary, FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
+			if (!$config_lines || !is_array($config_lines)) return false;
+			$config = self::build_from_array($config_lines);
+			// if APC caching is available and enabled, mark this for cache
+			//$config->cache_in_apc = true;
+			$config->cache_key = $matched_name;
+			
+			// if autodetec on failure is off (on by default) we do not need to look
+			// in secondary folder
+			if (!$config->autodetect_on_failure()) {
+				self::debug('... autodetect on failure is disabled (no other site config files will be loaded)');
+				return $config;
+			}
+		}
+		
+		// look for site config file in secondary folder
+		if (isset(self::$config_path_fallback)) {
+			self::debug(". looking for site config for $host in secondary folder");
+			foreach ($try as $h) {
+				if (file_exists(self::$config_path_fallback."/$h.txt")) {
+					self::debug("... found site config in secondary folder ($h.txt)");
+					$file_secondary = self::$config_path_fallback."/$h.txt";
+					$matched_name = $h;
+					break;
+				}
+			}
+			if (!isset($file_secondary)) {
+				self::debug("... no site config match in secondary folder");
+			}
+		}
+		
+		// return false if no config file found
+		if (!isset($file_primary) && !isset($file_secondary)) {
+			self::debug("... no site config match for $host");
+			return false;
+		}
+		
+		// return primary config if secondary not found
+		if (!isset($file_secondary) && isset($config)) {
+			return $config;
+		}
+		
+		// process secondary config file
+		$config_lines = file($file_secondary, FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
+		if (!$config_lines || !is_array($config_lines)) {
+			// failed to process secondary
+			if (isset($config)) {
+				// return primary config
+				return $config;
+			} else {
+				return false;
+			}
+		}
+		
+		// merge with primary and return
+		if (isset($config)) {
+			self::debug('. merging config files');
+			$config->append(self::build_from_array($config_lines));
+			return $config;
+		} else {
+			// return just secondary
+			$config = self::build_from_array($config_lines);
+			// if APC caching is available and enabled, mark this for cache
+			//$config->cache_in_apc = true;
+			$config->cache_key = $matched_name;
+			return $config;
+		}
+	}
+	
+	public static function build_from_array(array $lines) {
+		$config = new SiteConfig();
+		foreach ($lines as $line) {
+			$line = trim($line);
+			
+			// skip comments, empty lines
+			if ($line == '' || $line[0] == '#') continue;
+			
+			// get command
+			$command = explode(':', $line, 2);
+			// if there's no colon ':', skip this line
+			if (count($command) != 2) continue;
+			$val = trim($command[1]);
+			$command = trim($command[0]);
+			if ($command == '' || $val == '') continue;
+			
+			// check for commands where we accept multiple statements
+			if (in_array($command, array('title', 'body', 'author', 'date', 'strip', 'strip_id_or_class', 'strip_image_src', 'single_page_link', 'single_page_link_in_feed', 'next_page_link', 'http_header', 'test_url', 'find_string', 'replace_string'))) {
+				array_push($config->$command, $val);
+			// check for single statement commands that evaluate to true or false
+			} elseif (in_array($command, array('tidy', 'prune', 'autodetect_on_failure'))) {
+				$config->$command = ($val == 'yes');
+			// check for single statement commands stored as strings
+			} elseif (in_array($command, array('parser'))) {
+				$config->$command = $val;
+			// check for replace_string(find): replace
+			} elseif ((substr($command, -1) == ')') && preg_match('!^([a-z0-9_]+)\((.*?)\)$!i', $command, $match)) {
+				if (in_array($match[1], array('replace_string'))) {
+					$command = $match[1];
+					array_push($config->find_string, $match[2]);
+					array_push($config->$command, $val);
+				}
+			}
+		}
+		return $config;
+	}
+}
\ No newline at end of file
diff --git a/inc/3rdparty/libraries/feedwriter/FeedItem.php b/inc/3rdparty/libraries/feedwriter/FeedItem.php
old mode 100644
new mode 100755
index 54a56f22..40786598
--- a/inc/3rdparty/libraries/feedwriter/FeedItem.php
+++ b/inc/3rdparty/libraries/feedwriter/FeedItem.php
@@ -1,7 +1,7 @@
 version = $version;
     }
 
     /**
     * Set element (overwrites existing elements with $elementName)
-    * 
+    *
     * @access   public
     * @param    srting  The tag name of an element
     * @param    srting  The content of tag
@@ -38,11 +38,11 @@
             unset($this->elements[$elementName]);
         }
         $this->addElement($elementName, $content, $attributes);
-    }    
-    
+    }
+
     /**
     * Add an element to elements array
-    * 
+    *
     * @access   public
     * @param    srting  The tag name of an element
     * @param    srting  The content of tag
@@ -61,11 +61,11 @@
         $this->elements[$elementName][$i]['content']    = $content;
         $this->elements[$elementName][$i]['attributes'] = $attributes;
     }
-    
+
     /**
-    * Set multiple feed elements from an array. 
+    * Set multiple feed elements from an array.
     * Elements which have attributes cannot be added by this method
-    * 
+    *
     * @access   public
     * @param    array   array of elements in 'tagName' => 'tagContent' format.
     * @return   void
@@ -73,15 +73,15 @@
     public function addElementArray($elementArray)
     {
         if(! is_array($elementArray)) return;
-        foreach ($elementArray as $elementName => $content) 
+        foreach ($elementArray as $elementName => $content)
         {
             $this->addElement($elementName, $content);
         }
     }
-    
+
     /**
     * Return the collection of elements in this feed item
-    * 
+    *
     * @access   public
     * @return   array
     */
@@ -89,68 +89,74 @@
     {
         return $this->elements;
     }
-    
+
     // Wrapper functions ------------------------------------------------------
-    
+
     /**
     * Set the 'dscription' element of feed item
-    * 
+    *
     * @access   public
     * @param    string  The content of 'description' element
     * @return   void
     */
-    public function setDescription($description) 
+    public function setDescription($description)
     {
-        $this->setElement('description', $description);
+        $tag = ($this->version == ATOM)? 'summary' : 'description';
+        $this->setElement($tag, $description);
     }
-    
+
     /**
     * @desc     Set the 'title' element of feed item
     * @access   public
     * @param    string  The content of 'title' element
     * @return   void
     */
-    public function setTitle($title) 
+    public function setTitle($title)
     {
-        $this->setElement('title', $title);      
+        $this->setElement('title', $title);
     }
-    
+
     /**
     * Set the 'date' element of feed item
-    * 
+    *
     * @access   public
     * @param    string  The content of 'date' element
     * @return   void
     */
-    public function setDate($date) 
+    public function setDate($date)
     {
         if(! is_numeric($date))
         {
             $date = strtotime($date);
         }
-      
-        if($this->version == RSS2) 
+
+        if($this->version == ATOM)
+        {
+        	$tag    = 'updated';
+        	$value  = date(DATE_ATOM, $date);
+        }
+        elseif($this->version == RSS2)
         {
-            $tag    = 'pubDate';
-            $value  = date(DATE_RSS, $date);
+        	$tag    = 'pubDate';
+        	$value  = date(DATE_RSS, $date);
         }
-        else                                
+        else
         {
-            $tag    = 'dc:date';
-            $value  = date("Y-m-d", $date);
+        	$tag    = 'dc:date';
+        	$value  = date("Y-m-d", $date);
         }
-        
-        $this->setElement($tag, $value);    
+
+        $this->setElement($tag, $value);
     }
-    
+
     /**
     * Set the 'link' element of feed item
-    * 
+    *
     * @access   public
     * @param    string  The content of 'link' element
     * @return   void
     */
-    public function setLink($link) 
+    public function setLink($link)
     {
         if($this->version == RSS2 || $this->version == RSS1)
         {
@@ -161,27 +167,27 @@
         {
             $this->setElement('link','',array('href'=>$link));
             $this->setElement('id', FeedWriter::uuid($link,'urn:uuid:'));
-        } 
-        
+        }
+
     }
 
     /**
     * Set the 'source' element of feed item
-    * 
+    *
     * @access   public
     * @param    string  The content of 'source' element
     * @return   void
     */
-    public function setSource($link) 
+    public function setSource($link)
     {
         $attributes = array('url'=>$link);
         $this->setElement('source', "wallabag",$attributes);
     }
-    
+
     /**
     * Set the 'encloser' element of feed item
     * For RSS 2.0 only
-    * 
+    *
     * @access   public
     * @param    string  The url attribute of encloser tag
     * @param    string  The length attribute of encloser tag
@@ -193,6 +199,6 @@
         $attributes = array('url'=>$url, 'length'=>$length, 'type'=>$type);
         $this->setElement('enclosure','',$attributes);
     }
-    
+
  } // end of class FeedItem
 ?>
\ No newline at end of file
diff --git a/inc/3rdparty/libraries/feedwriter/FeedWriter.php b/inc/3rdparty/libraries/feedwriter/FeedWriter.php
index d708e99b..77755690 100755
--- a/inc/3rdparty/libraries/feedwriter/FeedWriter.php
+++ b/inc/3rdparty/libraries/feedwriter/FeedWriter.php
@@ -97,15 +97,12 @@ define('JSONP', 3, true);
               header('X-content-type-options: nosniff');
           } elseif ($this->version == JSON) {
               header('Content-type: application/json; charset=UTF-8');
+              $this->json = new stdClass();
           } elseif ($this->version == JSONP) {
               header('Content-type: application/javascript; charset=UTF-8');
+              $this->json = new stdClass();
           }
         }
-      
-        if ($this->version == JSON || $this->version == JSONP) {
-          $this->json = new stdClass();
-        }
-      
 
         $this->printHead();
         $this->printChannels();
@@ -116,6 +113,11 @@ define('JSONP', 3, true);
         }
     }
 
+    public function &getItems()
+    {
+    	return $this->items;
+    }
+
     /**
     * Create a new FeedItem.
     *
@@ -199,7 +201,8 @@ define('JSONP', 3, true);
     */
     public function setDescription($description)
     {
-        $this->setChannelElement('description', $description);
+        $tag = ($this->version == ATOM)? 'subtitle' : 'description';
+        $this->setChannelElement($tag, $desciption);
     }
 
     /**
@@ -244,7 +247,7 @@ define('JSONP', 3, true);
         {
             $out  = ''."\n";
             if ($this->xsl) $out .= 'xsl).'"?>' . PHP_EOL;
-            $out .= '' . PHP_EOL;
+            $out .= '' . PHP_EOL;
             echo $out;
         }
         elseif ($this->version == JSON || $this->version == JSONP)
diff --git a/inc/3rdparty/libraries/html5/TreeBuilder.php b/inc/3rdparty/libraries/html5/TreeBuilder.php
index 2f5244f9..c4a48b21 100644
--- a/inc/3rdparty/libraries/html5/TreeBuilder.php
+++ b/inc/3rdparty/libraries/html5/TreeBuilder.php
@@ -134,6 +134,7 @@ class HTML5_TreeBuilder {
 
     // Namespaces for foreign content
     const NS_HTML   = null; // to prevent DOM from requiring NS on everything
+    const NS_XHTML  = 'http://www.w3.org/1999/xhtml';
     const NS_MATHML = 'http://www.w3.org/1998/Math/MathML';
     const NS_SVG    = 'http://www.w3.org/2000/svg';
     const NS_XLINK  = 'http://www.w3.org/1999/xlink';
@@ -3157,11 +3158,19 @@ class HTML5_TreeBuilder {
         }
 
     private function insertElement($token, $append = true) {
-        $el = $this->dom->createElementNS(self::NS_HTML, $token['name']);
+        //$el = $this->dom->createElementNS(self::NS_HTML, $token['name']);
+        $namespaceURI = strpos($token['name'], ':') ? self::NS_XHTML : self::NS_HTML;
+        $el = $this->dom->createElementNS($namespaceURI, $token['name']);
 
         if (!empty($token['attr'])) {
             foreach($token['attr'] as $attr) {
-                if(!$el->hasAttribute($attr['name'])) {
+
+				// mike@macgirvin.com 2011-11-17, check attribute name for
+				// validity (ignoring extenders and combiners) as illegal chars in names
+				// causes everything to abort
+
+ 				$valid = preg_match('/^[a-zA-Z\_\:]([\-a-zA-Z0-9\_\:\.]+$)/',$attr['name']);
+                if($attr['name'] && (!$el->hasAttribute($attr['name'])) && ($valid)) {
                     $el->setAttribute($attr['name'], $attr['value']);
                 }
             }
diff --git a/inc/3rdparty/libraries/humble-http-agent/CookieJar.php b/inc/3rdparty/libraries/humble-http-agent/CookieJar.php
index 83e94f14..e4d5f495 100644
--- a/inc/3rdparty/libraries/humble-http-agent/CookieJar.php
+++ b/inc/3rdparty/libraries/humble-http-agent/CookieJar.php
@@ -1,404 +1,403 @@
-
- *
- * This class should be used to handle cookies (storing cookies from HTTP response messages, and
- * sending out cookies in HTTP request messages). This has been adapted for FiveFilters.org 
- * from the original version used in HTTP Navigator. See http://www.keyvan.net/code/http-navigator/
- * 
- * This class is mainly based on Cookies.pm  from the libwww-perl collection .
- * Unlike Cookies.pm, this class only supports the Netscape cookie spec, not RFC 2965.
- * 
- * @version 0.5
- * @date 2011-03-15
- * @see http://php.net/HttpRequestPool
- * @author Keyvan Minoukadeh
- * @copyright 2011 Keyvan Minoukadeh
- * @license http://www.gnu.org/licenses/agpl-3.0.html AGPL v3
- */
-
-class CookieJar
-{
-    /**
-    * Cookies - array containing all cookies.
-    *
-    * 
    -    * Cookies are stored like this:
-    *   [domain][path][name] = array
-    * where array is:
-    *   0 => value, 1 => secure, 2 => expires
-    * 
    
-    * @var array
-    * @access private
-    */
-    public $cookies = array();
-	public $debug = false;
-
-    /**
-    * Constructor
-    */
-    function __construct() {
-    }
-
-	protected function debug($msg, $file=null, $line=null) {
-		if ($this->debug) {
-			$mem = round(memory_get_usage()/1024, 2);
-			$memPeak = round(memory_get_peak_usage()/1024, 2);
-			echo '* ',$msg;
-			if (isset($file, $line)) echo " ($file line $line)";
-			echo ' - mem used: ',$mem," (peak: $memPeak)\n";	
-			ob_flush();
-			flush();
-		}
-	}	
-	
-    /**
-    * Get matching cookies
-    *
-    * Only use this method if you cannot use add_cookie_header(), for example, if you want to use
-    * this cookie jar class without using the request class.
-    *
-    * @param array $param associative array containing 'domain', 'path', 'secure' keys
-    * @return string
-    * @see add_cookie_header()
-    */
-    public function getMatchingCookies($url)
-    {
-		if (($parts = @parse_url($url)) && isset($parts['scheme'], $parts['host'], $parts['path'])) {
-			$param['domain'] = $parts['host'];
-			$param['path'] = $parts['path'];
-			$param['secure'] = (strtolower($parts['scheme']) == 'https');
-			unset($parts);
-		} else {
-			return false;
-		}
-        // RFC 2965 notes:
-        //  If multiple cookies satisfy the criteria above, they are ordered in
-        //  the Cookie header such that those with more specific Path attributes
-        //  precede those with less specific.  Ordering with respect to other
-        //  attributes (e.g., Domain) is unspecified.
-        $domain = $param['domain'];
-        if (strpos($domain, '.') === false) $domain .= '.local';
-        $request_path = $param['path'];
-        if ($request_path == '') $request_path = '/';
-        $request_secure = $param['secure'];
-        $now = time();
-        $matched_cookies = array();
-        // domain - find matching domains
-        $this->debug('Finding matching domains for '.$domain, __FILE__, __LINE__);
-        while (strpos($domain, '.') !== false) {
-            if (isset($this->cookies[$domain])) {
-                $this->debug(' domain match found: '.$domain);
-                $cookies =& $this->cookies[$domain];
-            } else {
-                $domain = $this->_reduce_domain($domain);
-                continue;
-            }
-            // paths - find matching paths starting from most specific
-            $this->debug('  - Finding matching paths for '.$request_path);
-            $paths = array_keys($cookies);
-            usort($paths, array($this, '_cmp_length'));
-            foreach ($paths as $path) {
-                // continue to next cookie if request path does not path-match cookie path
-                if (!$this->_path_match($request_path, $path)) continue;
-                // loop through cookie names
-                $this->debug('     path match found: '.$path);
-                foreach ($cookies[$path] as $name => $values) {
-                    // if this cookie is secure but request isn't, continue to next cookie
-                    if ($values[1] && !$request_secure) continue;
-                    // if cookie is not a session cookie and has expired, continue to next cookie
-                    if (is_int($values[2]) && ($values[2] < $now)) continue;
-                    // cookie matches request
-                    $this->debug('      cookie match: '.$name.'='.$values[0]);
-                    $matched_cookies[] = $name.'='.$values[0];
-                }
-            }
-            $domain = $this->_reduce_domain($domain);
-        }
-        // return cookies
-        return implode('; ', $matched_cookies);
-    }
-
-    /**
-    * Parse Set-Cookie values.
-    *
-    * Only use this method if you cannot use extract_cookies(), for example, if you want to use
-    * this cookie jar class without using the response class.
-    *
-    * @param array $set_cookies array holding 1 or more "Set-Cookie" header values
-    * @param array $param associative array containing 'host', 'path' keys
-    * @return void
-    * @see extract_cookies()
-    */
-    public function storeCookies($url, $set_cookies)
-    {
-        if (count($set_cookies) == 0) return;
-		$param = @parse_url($url);
-		if (!is_array($param) || !isset($param['host'])) return;
-        $request_host = $param['host'];
-        if (strpos($request_host, '.') === false) $request_host .= '.local';
-        $request_path = @$param['path'];
-        if ($request_path == '') $request_path = '/';
-        //
-        // loop through set-cookie headers
-        //
-        foreach ($set_cookies as $set_cookie) {
-            $this->debug('Parsing: '.$set_cookie);
-            // temporary cookie store (before adding to jar)
-            $tmp_cookie = array();
-            $param = explode(';', $set_cookie);
-            // loop through params
-            for ($x=0; $x$key, 'value'=>$val);
-                    continue;
-                }
-                $key = strtolower($key);
-                if (in_array($key, array('expires', 'path', 'domain', 'secure'))) {
-                    $tmp_cookie[$key] = $val;
-                }
-            }
-            //
-            // set cookie
-            //
-            // check domain
-            if (isset($tmp_cookie['domain']) && ($tmp_cookie['domain'] != $request_host) &&
-                    ($tmp_cookie['domain'] != ".$request_host")) {
-                $domain = $tmp_cookie['domain'];
-                if ((strpos($domain, '.') === false) && ($domain != 'local')) {
-                    $this->debug(' - domain "'.$domain.'" has no dot and is not a local domain');
-                    continue;
-                }
-                if (preg_match('/\.[0-9]+$/', $domain)) {
-                    $this->debug(' - domain "'.$domain.'" appears to be an ip address');
-                    continue;
-                }
-                if (substr($domain, 0, 1) != '.') $domain = ".$domain";
-                if (!$this->_domain_match($request_host, $domain)) {
-                    $this->debug(' - request host "'.$request_host.'" does not domain-match "'.$domain.'"');
-                    continue;
-                }
-            } else {
-                // if domain is not specified in the set-cookie header, domain will default to
-                // the request host
-                $domain = $request_host;
-            }
-            // check path
-            if (isset($tmp_cookie['path']) && ($tmp_cookie['path'] != '')) {
-                $path = urldecode($tmp_cookie['path']);
-                if (!$this->_path_match($request_path, $path)) {
-                    $this->debug(' - request path "'.$request_path.'" does not path-match "'.$path.'"');
-                    continue;
-                }
-            } else {
-                $path = $request_path;
-                $path = substr($path, 0, strrpos($path, '/'));
-                if ($path == '') $path = '/';
-            }
-            // check if secure
-            $secure = (isset($tmp_cookie['secure'])) ? true : false;
-            // check expiry
-            if (isset($tmp_cookie['expires'])) {
-                if (($expires = strtotime($tmp_cookie['expires'])) < 0) {
-                    $expires = null;
-                }
-            } else {
-                $expires = null;
-            }
-            // set cookie
-            $this->set_cookie($domain, $path, $tmp_cookie['name'], $tmp_cookie['value'], $secure, $expires);
-        }
-    }
-	
-	// return array of set-cookie values extracted from HTTP response headers (string $h)
-	public function extractCookies($h) {
-        $x = 0;
-        $lines = 0;
-        $headers = array();
-        $last_match = false;
-		$h = explode("\n", $h);
-        foreach ($h as $line) {
-			$line = rtrim($line);
-            $lines++;
-
-            $trimmed_line = trim($line);
-            if (isset($line_last)) {
-                // check if we have \r\n\r\n (indicating the end of headers)
-                // some servers will not use CRLF (\r\n), so we make CR (\r) optional.
-                // if (preg_match('/\015?\012\015?\012/', $line_last.$line)) {
-                //     break;
-                // }
-                // As an alternative, we can check if the current trimmed line is empty
-                if ($trimmed_line == '') {
-                    break;
-                }
-
-                // check for continuation line...
-                // RFC 2616 Section 2.2 "Basic Rules":
-                // HTTP/1.1 header field values can be folded onto multiple lines if the
-                // continuation line begins with a space or horizontal tab. All linear
-                // white space, including folding, has the same semantics as SP. A
-                // recipient MAY replace any linear white space with a single SP before
-                // interpreting the field value or forwarding the message downstream.
-                if ($last_match && preg_match('/^\s+(.*)/', $line, $match)) {
-                    // append to previous header value
-                    $headers[$x-1] .= ' '.rtrim($match[1]);
-                    continue;
-                }
-            }
-            $line_last = $line;
-
-            // split header name and value
-            if (preg_match('/^Set-Cookie\s*:\s*(.*)/i', $line, $match)) {
-                $headers[$x++] = rtrim($match[1]);
-                $last_match = true;
-            } else {
-                $last_match = false;
-            }
-        }
-        return $headers;
-	}
-
-    /**
-    * Set Cookie
-    * @param string $domain
-    * @param string $path
-    * @param string $name cookie name
-    * @param string $value cookie value
-    * @param bool $secure
-    * @param int $expires expiry time (null if session cookie, <= 0 will delete cookie)
-    * @return void
-    */
-    function set_cookie($domain, $path, $name, $value, $secure=false, $expires=null)
-    {
-        if ($domain == '') return;
-        if ($path == '') return;
-        if ($name == '') return;
-        // check if cookie needs to go
-        if (isset($expires) && ($expires <= 0)) {
-            if (isset($this->cookies[$domain][$path][$name])) unset($this->cookies[$domain][$path][$name]);
-            return;
-        }
-        if ($value == '') return;
-        $this->cookies[$domain][$path][$name] = array($value, $secure, $expires);
-        return;
-    }
-
-    /**
-    * Clear cookies - [domain [,path [,name]]] - call method with no arguments to clear all cookies.
-    * @param string $domain
-    * @param string $path
-    * @param string $name
-    * @return void
-    */
-    function clear($domain=null, $path=null, $name=null)
-    {
-        if (!isset($domain)) {
-            $this->cookies = array();
-        } elseif (!isset($path)) {
-            if (isset($this->cookies[$domain])) unset($this->cookies[$domain]);
-        } elseif (!isset($name)) {
-            if (isset($this->cookies[$domain][$path])) unset($this->cookies[$domain][$path]);
-        } elseif (isset($name)) {
-            if (isset($this->cookies[$domain][$path][$name])) unset($this->cookies[$domain][$path][$name]);
-        }
-    }
-
-    /**
-    * Compare string length - used for sorting
-    * @access private
-    * @return int
-    */
-    function _cmp_length($a, $b)
-    {
-        $la = strlen($a); $lb = strlen($b);
-        if ($la == $lb) return 0;
-        return ($la > $lb) ? -1 : 1;
-    }
-
-    /**
-    * Reduce domain
-    * @param string $domain
-    * @return string
-    * @access private
-    */
-    function _reduce_domain($domain)
-    {
-        if ($domain == '') return '';
-        if (substr($domain, 0, 1) == '.') return substr($domain, 1);
-        return substr($domain, strpos($domain, '.'));
-    }
-
-    /**
-    * Path match - check if path1 path-matches path2
-    *
-    * From RFC 2965: 
-    *   For two strings that represent paths, P1 and P2, P1 path-matches P2
-    *   if P2 is a prefix of P1 (including the case where P1 and P2 string-
-    *   compare equal).  Thus, the string /tec/waldo path-matches /tec.
-    * @param string $path1
-    * @param string $path2
-    * @return bool
-    * @access private
-    */
-    function _path_match($path1, $path2)
-    {
-        return (substr($path1, 0, strlen($path2)) == $path2);
-    }
-
-    /**
-    * Domain match - check if domain1 domain-matches domain2
-    *
-    * A few extracts from RFC 2965: 
-    *  -  A Set-Cookie2 from request-host y.x.foo.com for Domain=.foo.com
-    *     would be rejected, because H is y.x and contains a dot.
-    *
-    *  -  A Set-Cookie2 from request-host x.foo.com for Domain=.foo.com
-    *     would be accepted.
-    *
-    *  -  A Set-Cookie2 with Domain=.com or Domain=.com., will always be
-    *     rejected, because there is no embedded dot.
-    *
-    *  -  A Set-Cookie2 from request-host example for Domain=.local will
-    *     be accepted, because the effective host name for the request-
-    *     host is example.local, and example.local domain-matches .local.
-    *
-    * I'm ignoring the first point for now (must check to see how other browsers handle
-    * this rule for Set-Cookie headers)
-    *
-    * @param string $domain1
-    * @param string $domain2
-    * @return bool
-    * @access private
-    */
-    function _domain_match($domain1, $domain2)
-    {
-        $domain1 = strtolower($domain1);
-        $domain2 = strtolower($domain2);
-        while (strpos($domain1, '.') !== false) {
-            if ($domain1 == $domain2) return true;
-            $domain1 = $this->_reduce_domain($domain1);
-            continue;
-        }
-        return false;
-    }
-}
-?>
\ No newline at end of file
+
+ *
+ * This class should be used to handle cookies (storing cookies from HTTP response messages, and
+ * sending out cookies in HTTP request messages). This has been adapted for FiveFilters.org 
+ * from the original version used in HTTP Navigator. See http://www.keyvan.net/code/http-navigator/
+ * 
+ * This class is mainly based on Cookies.pm  from the libwww-perl collection .
+ * Unlike Cookies.pm, this class only supports the Netscape cookie spec, not RFC 2965.
+ * 
+ * @version 0.5
+ * @date 2011-03-15
+ * @see http://php.net/HttpRequestPool
+ * @author Keyvan Minoukadeh
+ * @copyright 2011 Keyvan Minoukadeh
+ * @license http://www.gnu.org/licenses/agpl-3.0.html AGPL v3
+ */
+
+class CookieJar
+{
+    /**
+    * Cookies - array containing all cookies.
+    *
+    * 
    +    * Cookies are stored like this:
+    *   [domain][path][name] = array
+    * where array is:
+    *   0 => value, 1 => secure, 2 => expires
+    * 
    
+    * @var array
+    * @access private
+    */
+    public $cookies = array();
+	public $debug = false;
+
+    /**
+    * Constructor
+    */
+    function __construct() {
+    }
+
+	protected function debug($msg, $file=null, $line=null) {
+		if ($this->debug) {
+			$mem = round(memory_get_usage()/1024, 2);
+			$memPeak = round(memory_get_peak_usage()/1024, 2);
+			echo '* ',$msg;
+			if (isset($file, $line)) echo " ($file line $line)";
+			echo ' - mem used: ',$mem," (peak: $memPeak)\n";	
+			ob_flush();
+			flush();
+		}
+	}	
+	
+    /**
+    * Get matching cookies
+    *
+    * Only use this method if you cannot use add_cookie_header(), for example, if you want to use
+    * this cookie jar class without using the request class.
+    *
+    * @param array $param associative array containing 'domain', 'path', 'secure' keys
+    * @return string
+    * @see add_cookie_header()
+    */
+    public function getMatchingCookies($url)
+    {
+		if (($parts = @parse_url($url)) && isset($parts['scheme'], $parts['host'], $parts['path'])) {
+			$param['domain'] = $parts['host'];
+			$param['path'] = $parts['path'];
+			$param['secure'] = (strtolower($parts['scheme']) == 'https');
+			unset($parts);
+		} else {
+			return false;
+		}
+        // RFC 2965 notes:
+        //  If multiple cookies satisfy the criteria above, they are ordered in
+        //  the Cookie header such that those with more specific Path attributes
+        //  precede those with less specific.  Ordering with respect to other
+        //  attributes (e.g., Domain) is unspecified.
+        $domain = $param['domain'];
+        if (strpos($domain, '.') === false) $domain .= '.local';
+        $request_path = $param['path'];
+        if ($request_path == '') $request_path = '/';
+        $request_secure = $param['secure'];
+        $now = time();
+        $matched_cookies = array();
+        // domain - find matching domains
+        $this->debug('Finding matching domains for '.$domain, __FILE__, __LINE__);
+        while (strpos($domain, '.') !== false) {
+            if (isset($this->cookies[$domain])) {
+                $this->debug(' domain match found: '.$domain);
+                $cookies =& $this->cookies[$domain];
+            } else {
+                $domain = $this->_reduce_domain($domain);
+                continue;
+            }
+            // paths - find matching paths starting from most specific
+            $this->debug('  - Finding matching paths for '.$request_path);
+            $paths = array_keys($cookies);
+            usort($paths, array($this, '_cmp_length'));
+            foreach ($paths as $path) {
+                // continue to next cookie if request path does not path-match cookie path
+                if (!$this->_path_match($request_path, $path)) continue;
+                // loop through cookie names
+                $this->debug('     path match found: '.$path);
+                foreach ($cookies[$path] as $name => $values) {
+                    // if this cookie is secure but request isn't, continue to next cookie
+                    if ($values[1] && !$request_secure) continue;
+                    // if cookie is not a session cookie and has expired, continue to next cookie
+                    if (is_int($values[2]) && ($values[2] < $now)) continue;
+                    // cookie matches request
+                    $this->debug('      cookie match: '.$name.'='.$values[0]);
+                    $matched_cookies[] = $name.'='.$values[0];
+                }
+            }
+            $domain = $this->_reduce_domain($domain);
+        }
+        // return cookies
+        return implode('; ', $matched_cookies);
+    }
+
+    /**
+    * Parse Set-Cookie values.
+    *
+    * Only use this method if you cannot use extract_cookies(), for example, if you want to use
+    * this cookie jar class without using the response class.
+    *
+    * @param array $set_cookies array holding 1 or more "Set-Cookie" header values
+    * @param array $param associative array containing 'host', 'path' keys
+    * @return void
+    * @see extract_cookies()
+    */
+    public function storeCookies($url, $set_cookies)
+    {
+        if (count($set_cookies) == 0) return;
+		$param = @parse_url($url);
+		if (!is_array($param) || !isset($param['host'])) return;
+        $request_host = $param['host'];
+        if (strpos($request_host, '.') === false) $request_host .= '.local';
+        $request_path = @$param['path'];
+        if ($request_path == '') $request_path = '/';
+        //
+        // loop through set-cookie headers
+        //
+        foreach ($set_cookies as $set_cookie) {
+            $this->debug('Parsing: '.$set_cookie);
+            // temporary cookie store (before adding to jar)
+            $tmp_cookie = array();
+            $param = explode(';', $set_cookie);
+            // loop through params
+            for ($x=0; $x$key, 'value'=>$val);
+                    continue;
+                }
+                $key = strtolower($key);
+                if (in_array($key, array('expires', 'path', 'domain', 'secure'))) {
+                    $tmp_cookie[$key] = $val;
+                }
+            }
+            //
+            // set cookie
+            //
+            // check domain
+            if (isset($tmp_cookie['domain']) && ($tmp_cookie['domain'] != $request_host) &&
+                    ($tmp_cookie['domain'] != ".$request_host")) {
+                $domain = $tmp_cookie['domain'];
+                if ((strpos($domain, '.') === false) && ($domain != 'local')) {
+                    $this->debug(' - domain "'.$domain.'" has no dot and is not a local domain');
+                    continue;
+                }
+                if (preg_match('/\.[0-9]+$/', $domain)) {
+                    $this->debug(' - domain "'.$domain.'" appears to be an ip address');
+                    continue;
+                }
+                if (substr($domain, 0, 1) != '.') $domain = ".$domain";
+                if (!$this->_domain_match($request_host, $domain)) {
+                    $this->debug(' - request host "'.$request_host.'" does not domain-match "'.$domain.'"');
+                    continue;
+                }
+            } else {
+                // if domain is not specified in the set-cookie header, domain will default to
+                // the request host
+                $domain = $request_host;
+            }
+            // check path
+            if (isset($tmp_cookie['path']) && ($tmp_cookie['path'] != '')) {
+                $path = urldecode($tmp_cookie['path']);
+                if (!$this->_path_match($request_path, $path)) {
+                    $this->debug(' - request path "'.$request_path.'" does not path-match "'.$path.'"');
+                    continue;
+                }
+            } else {
+                $path = $request_path;
+                $path = substr($path, 0, strrpos($path, '/'));
+                if ($path == '') $path = '/';
+            }
+            // check if secure
+            $secure = (isset($tmp_cookie['secure'])) ? true : false;
+            // check expiry
+            if (isset($tmp_cookie['expires'])) {
+                if (($expires = strtotime($tmp_cookie['expires'])) < 0) {
+                    $expires = null;
+                }
+            } else {
+                $expires = null;
+            }
+            // set cookie
+            $this->set_cookie($domain, $path, $tmp_cookie['name'], $tmp_cookie['value'], $secure, $expires);
+        }
+    }
+	
+	// return array of set-cookie values extracted from HTTP response headers (string $h)
+	public function extractCookies($h) {
+        $x = 0;
+        $lines = 0;
+        $headers = array();
+        $last_match = false;
+		$h = explode("\n", $h);
+        foreach ($h as $line) {
+			$line = rtrim($line);
+            $lines++;
+
+            $trimmed_line = trim($line);
+            if (isset($line_last)) {
+                // check if we have \r\n\r\n (indicating the end of headers)
+                // some servers will not use CRLF (\r\n), so we make CR (\r) optional.
+                // if (preg_match('/\015?\012\015?\012/', $line_last.$line)) {
+                //     break;
+                // }
+                // As an alternative, we can check if the current trimmed line is empty
+                if ($trimmed_line == '') {
+                    break;
+                }
+
+                // check for continuation line...
+                // RFC 2616 Section 2.2 "Basic Rules":
+                // HTTP/1.1 header field values can be folded onto multiple lines if the
+                // continuation line begins with a space or horizontal tab. All linear
+                // white space, including folding, has the same semantics as SP. A
+                // recipient MAY replace any linear white space with a single SP before
+                // interpreting the field value or forwarding the message downstream.
+                if ($last_match && preg_match('/^\s+(.*)/', $line, $match)) {
+                    // append to previous header value
+                    $headers[$x-1] .= ' '.rtrim($match[1]);
+                    continue;
+                }
+            }
+            $line_last = $line;
+
+            // split header name and value
+            if (preg_match('/^Set-Cookie\s*:\s*(.*)/i', $line, $match)) {
+                $headers[$x++] = rtrim($match[1]);
+                $last_match = true;
+            } else {
+                $last_match = false;
+            }
+        }
+        return $headers;
+	}
+
+    /**
+    * Set Cookie
+    * @param string $domain
+    * @param string $path
+    * @param string $name cookie name
+    * @param string $value cookie value
+    * @param bool $secure
+    * @param int $expires expiry time (null if session cookie, <= 0 will delete cookie)
+    * @return void
+    */
+    function set_cookie($domain, $path, $name, $value, $secure=false, $expires=null)
+    {
+        if ($domain == '') return;
+        if ($path == '') return;
+        if ($name == '') return;
+        // check if cookie needs to go
+        if (isset($expires) && ($expires <= 0)) {
+            if (isset($this->cookies[$domain][$path][$name])) unset($this->cookies[$domain][$path][$name]);
+            return;
+        }
+        if ($value == '') return;
+        $this->cookies[$domain][$path][$name] = array($value, $secure, $expires);
+        return;
+    }
+
+    /**
+    * Clear cookies - [domain [,path [,name]]] - call method with no arguments to clear all cookies.
+    * @param string $domain
+    * @param string $path
+    * @param string $name
+    * @return void
+    */
+    function clear($domain=null, $path=null, $name=null)
+    {
+        if (!isset($domain)) {
+            $this->cookies = array();
+        } elseif (!isset($path)) {
+            if (isset($this->cookies[$domain])) unset($this->cookies[$domain]);
+        } elseif (!isset($name)) {
+            if (isset($this->cookies[$domain][$path])) unset($this->cookies[$domain][$path]);
+        } elseif (isset($name)) {
+            if (isset($this->cookies[$domain][$path][$name])) unset($this->cookies[$domain][$path][$name]);
+        }
+    }
+
+    /**
+    * Compare string length - used for sorting
+    * @access private
+    * @return int
+    */
+    function _cmp_length($a, $b)
+    {
+        $la = strlen($a); $lb = strlen($b);
+        if ($la == $lb) return 0;
+        return ($la > $lb) ? -1 : 1;
+    }
+
+    /**
+    * Reduce domain
+    * @param string $domain
+    * @return string
+    * @access private
+    */
+    function _reduce_domain($domain)
+    {
+        if ($domain == '') return '';
+        if (substr($domain, 0, 1) == '.') return substr($domain, 1);
+        return substr($domain, strpos($domain, '.'));
+    }
+
+    /**
+    * Path match - check if path1 path-matches path2
+    *
+    * From RFC 2965: 
+    *   For two strings that represent paths, P1 and P2, P1 path-matches P2
+    *   if P2 is a prefix of P1 (including the case where P1 and P2 string-
+    *   compare equal).  Thus, the string /tec/waldo path-matches /tec.
+    * @param string $path1
+    * @param string $path2
+    * @return bool
+    * @access private
+    */
+    function _path_match($path1, $path2)
+    {
+        return (substr($path1, 0, strlen($path2)) == $path2);
+    }
+
+    /**
+    * Domain match - check if domain1 domain-matches domain2
+    *
+    * A few extracts from RFC 2965: 
+    *  -  A Set-Cookie2 from request-host y.x.foo.com for Domain=.foo.com
+    *     would be rejected, because H is y.x and contains a dot.
+    *
+    *  -  A Set-Cookie2 from request-host x.foo.com for Domain=.foo.com
+    *     would be accepted.
+    *
+    *  -  A Set-Cookie2 with Domain=.com or Domain=.com., will always be
+    *     rejected, because there is no embedded dot.
+    *
+    *  -  A Set-Cookie2 from request-host example for Domain=.local will
+    *     be accepted, because the effective host name for the request-
+    *     host is example.local, and example.local domain-matches .local.
+    *
+    * I'm ignoring the first point for now (must check to see how other browsers handle
+    * this rule for Set-Cookie headers)
+    *
+    * @param string $domain1
+    * @param string $domain2
+    * @return bool
+    * @access private
+    */
+    function _domain_match($domain1, $domain2)
+    {
+        $domain1 = strtolower($domain1);
+        $domain2 = strtolower($domain2);
+        while (strpos($domain1, '.') !== false) {
+            if ($domain1 == $domain2) return true;
+            $domain1 = $this->_reduce_domain($domain1);
+            continue;
+        }
+        return false;
+    }
+}
\ No newline at end of file
diff --git a/inc/3rdparty/libraries/humble-http-agent/HumbleHttpAgent.php b/inc/3rdparty/libraries/humble-http-agent/HumbleHttpAgent.php
index e4f1b3b3..963f0c05 100644
--- a/inc/3rdparty/libraries/humble-http-agent/HumbleHttpAgent.php
+++ b/inc/3rdparty/libraries/humble-http-agent/HumbleHttpAgent.php
@@ -1,779 +1,810 @@
-userAgentDefault = self::UA_BROWSER;
-		$this->referer = self::REF_GOOGLE;
-		// set the request method
-		if (in_array($method, array(1,2,4))) {
-			$this->method = $method;
-		} else {
-			if (class_exists('HttpRequestPool')) {
-				$this->method = self::METHOD_REQUEST_POOL;
-			} elseif (function_exists('curl_multi_init')) {
-				$this->method = self::METHOD_CURL_MULTI;
-			} else {
-				$this->method = self::METHOD_FILE_GET_CONTENTS;
-			}
-		}
-		if ($this->method == self::METHOD_CURL_MULTI) {
-			require_once(dirname(__FILE__).'/RollingCurl.php');
-		}
-		// create cookie jar
-		$this->cookieJar = new CookieJar();
-		// set request options (redirect must be 0)
-		$this->requestOptions = array(
-			'timeout' => 15,
-			'redirect' => 0 // we handle redirects manually so we can rewrite the new hashbang URLs that are creeping up over the web
-			// TODO: test onprogress?
-		);
-		if (is_array($requestOptions)) {
-			$this->requestOptions = array_merge($this->requestOptions, $requestOptions);
-		}
-		$this->httpContext = array(
-			'http' => array(
-				'ignore_errors' => true,
-				'timeout' => $this->requestOptions['timeout'],
-				'max_redirects' => $this->requestOptions['redirect'],
-				'header' => "Accept: */*\r\n"
-				)
-			);
-	}
-	
-	protected function debug($msg) {
-		if ($this->debug) {
-			$mem = round(memory_get_usage()/1024, 2);
-			$memPeak = round(memory_get_peak_usage()/1024, 2);
-			echo '* ',$msg;
-			if ($this->debugVerbose) echo ' - mem used: ',$mem," (peak: $memPeak)";
-			echo "\n";
-			ob_flush();
-			flush();
-		}
-	}
-	
-	protected function getUserAgent($url, $asArray=false) {
-		$host = @parse_url($url, PHP_URL_HOST);
-		if (strtolower(substr($host, 0, 4)) == 'www.') {
-			$host = substr($host, 4);
-		}
-		if ($host) {
-			$try = array($host);
-			$split = explode('.', $host);
-			if (count($split) > 1) {
-				array_shift($split);
-				$try[] = '.'.implode('.', $split);
-			}
-			foreach ($try as $h) {
-				if (isset($this->userAgentMap[$h])) {
-					$ua = $this->userAgentMap[$h];
-					break;
-				}
-			}
-		}
-		if (!isset($ua)) $ua = $this->userAgentDefault;
-		if ($asArray) {
-			return array('User-Agent' => $ua);
-		} else {
-			return 'User-Agent: '.$ua;
-		}
-	}
-	
-	public function rewriteHashbangFragment($url) {
-		// return $url if there's no '#!'
-		if (strpos($url, '#!') === false) return $url;
-		// split $url and rewrite
-		// TODO: is SimplePie_IRI included?
-		$iri = new SimplePie_IRI($url);
-		$fragment = substr($iri->fragment, 1); // strip '!'
-		$iri->fragment = null;
-		if (isset($iri->query)) {
-			parse_str($iri->query, $query);
-		} else {
-			$query = array();
-		}
-		$query['_escaped_fragment_'] = (string)$fragment;
-		$iri->query = str_replace('%2F', '/', http_build_query($query)); // needed for some sites
-		return $iri->get_iri();
-	}
-	
-	public function getUglyURL($url, $html) {
-		if ($html == '') return false;
-		$found = false;
-		foreach ($this->ajaxTriggers as $string) {
-			if (stripos($html, $string)) {
-				$found = true;
-				break;
-			}
-		}
-		if (!$found) return false;
-		$iri = new SimplePie_IRI($url);
-		if (isset($iri->query)) {
-			parse_str($iri->query, $query);
-		} else {
-			$query = array();
-		}
-		$query['_escaped_fragment_'] = '';
-		$iri->query = str_replace('%2F', '/', http_build_query($query)); // needed for some sites
-		return $iri->get_iri();
-	}
-	
-	public function removeFragment($url) {
-		$pos = strpos($url, '#');
-		if ($pos === false) {
-			return $url;
-		} else {
-			return substr($url, 0, $pos);
-		}
-	}
-	
-	public function rewriteUrls($url) {
-		foreach ($this->rewriteUrls as $find => $action) {
-			if (strpos($url, $find) !== false) {
-				if (is_array($action)) {
-					return strtr($url, $action);
-				}
-			}
-		}
-		return $url;
-	}
-	
-	public function enableDebug($bool=true) {
-		$this->debug = (bool)$bool;
-	}
-	
-	public function minimiseMemoryUse($bool = true) {
-		$this->minimiseMemoryUse = $bool;
-	}
-	
-	public function setMaxParallelRequests($max) {
-		$this->maxParallelRequests = $max;
-	}
-	
-	public function validateUrl($url) {
-		$url = filter_var($url, FILTER_SANITIZE_URL);
-		$test = filter_var($url, FILTER_VALIDATE_URL, FILTER_FLAG_SCHEME_REQUIRED);
-		// deal with bug http://bugs.php.net/51192 (present in PHP 5.2.13 and PHP 5.3.2)
-		if ($test === false) {
-			$test = filter_var(strtr($url, '-', '_'), FILTER_VALIDATE_URL, FILTER_FLAG_SCHEME_REQUIRED);
-		}
-		if ($test !== false && $test !== null && preg_match('!^https?://!', $url)) {
-			return $url;
-		} else {
-			return false;
-		}
-	}
-	
-	public function fetchAll(array $urls) {
-		$this->fetchAllOnce($urls, $isRedirect=false);
-		$redirects = 0;
-		while (!empty($this->redirectQueue) && ++$redirects <= $this->maxRedirects) {
-			$this->debug("Following redirects #$redirects...");
-			$this->fetchAllOnce($this->redirectQueue, $isRedirect=true);
-		}
-	}
-	
-	// fetch all URLs without following redirects
-	public function fetchAllOnce(array $urls, $isRedirect=false) {
-		if (!$isRedirect) $urls = array_unique($urls);
-		if (empty($urls)) return;
-		
-		//////////////////////////////////////////////////////
-		// parallel (HttpRequestPool)
-		if ($this->method == self::METHOD_REQUEST_POOL) {
-			$this->debug('Starting parallel fetch (HttpRequestPool)');
-			try {
-				while (count($urls) > 0) {
-					$this->debug('Processing set of '.min($this->maxParallelRequests, count($urls)));
-					$subset = array_splice($urls, 0, $this->maxParallelRequests);
-					$pool = new HttpRequestPool();
-					foreach ($subset as $orig => $url) {
-						if (!$isRedirect) $orig = $url;
-						unset($this->redirectQueue[$orig]);
-						$this->debug("...$url");
-						if (!$isRedirect && isset($this->requests[$url])) {
-							$this->debug("......in memory");
-						/*
-						} elseif ($this->isCached($url)) {
-							$this->debug("......is cached");
-							if (!$this->minimiseMemoryUse) {
-								$this->requests[$url] = $this->getCached($url);
-							}
-						*/
-						} else {
-							$this->debug("......adding to pool");
-							$req_url = $this->rewriteUrls($url);
-							$req_url = ($this->rewriteHashbangFragment) ? $this->rewriteHashbangFragment($req_url) : $req_url;
-							$req_url = $this->removeFragment($req_url);
-							if (!empty($this->headerOnlyTypes) && !isset($this->requests[$orig]['wrongGuess']) && $this->possibleUnsupportedType($req_url)) {
-								$_meth = HttpRequest::METH_HEAD;
-							} else {
-								$_meth = HttpRequest::METH_GET;
-								unset($this->requests[$orig]['wrongGuess']);
-							}
-							$httpRequest = new HttpRequest($req_url, $_meth, $this->requestOptions);
-							// send cookies, if we have any
-							if ($cookies = $this->cookieJar->getMatchingCookies($req_url)) {
-								$this->debug("......sending cookies: $cookies");
-								$httpRequest->addHeaders(array('Cookie' => $cookies));
-							}
-							//$httpRequest->addHeaders(array('User-Agent' => $this->userAgent));
-							$httpRequest->addHeaders($this->getUserAgent($req_url, true));
-							// add referer for picky sites
-							$httpRequest->addheaders(array('Referer' => $this->referer));
-							$this->requests[$orig] = array('headers'=>null, 'body'=>null, 'httpRequest'=>$httpRequest);
-							$this->requests[$orig]['original_url'] = $orig;
-							$pool->attach($httpRequest);
-						}
-					}
-					// did we get anything into the pool?
-					if (count($pool) > 0) {
-						$this->debug('Sending request...');
-						try {
-							$pool->send();
-						} catch (HttpRequestPoolException $e) {
-							// do nothing
-						}
-						$this->debug('Received responses');
-						foreach($subset as $orig => $url) {
-							if (!$isRedirect) $orig = $url;
-							$request = $this->requests[$orig]['httpRequest'];
-							//$this->requests[$orig]['headers'] = $this->headersToString($request->getResponseHeader());
-							// getResponseHeader() doesn't return status line, so, for consistency...
-							$this->requests[$orig]['headers'] = substr($request->getRawResponseMessage(), 0, $request->getResponseInfo('header_size'));
-							// check content type
-							// TODO: use getResponseHeader('content-type') or getResponseInfo()
-							if ($this->headerOnlyType($this->requests[$orig]['headers'])) {
-								$this->requests[$orig]['body'] = '';
-								$_header_only_type = true;
-								$this->debug('Header only type returned');
-							} else {
-								$this->requests[$orig]['body'] = $request->getResponseBody();
-								$_header_only_type = false;
-							}
-							$this->requests[$orig]['effective_url'] = $request->getResponseInfo('effective_url');
-							$this->requests[$orig]['status_code'] = $status_code = $request->getResponseCode();
-							// is redirect?
-							if ((in_array($status_code, array(300, 301, 302, 303, 307)) || $status_code > 307 && $status_code < 400) && $request->getResponseHeader('location')) {
-								$redirectURL = $request->getResponseHeader('location');
-								if (!preg_match('!^https?://!i', $redirectURL)) {
-									$redirectURL = SimplePie_Misc::absolutize_url($redirectURL, $url);
-								}
-								if ($this->validateURL($redirectURL)) {
-									$this->debug('Redirect detected. Valid URL: '.$redirectURL);
-									// store any cookies
-									$cookies = $request->getResponseHeader('set-cookie');
-									if ($cookies && !is_array($cookies)) $cookies = array($cookies);
-									if ($cookies) $this->cookieJar->storeCookies($url, $cookies);
-									$this->redirectQueue[$orig] = $redirectURL;
-								} else {
-									$this->debug('Redirect detected. Invalid URL: '.$redirectURL);
-								}
-							} elseif (!$_header_only_type && $request->getMethod() === HttpRequest::METH_HEAD) {
-								// the response content-type did not match our 'header only' types, 
-								// but we'd issues a HEAD request because we assumed it would. So
-								// let's queue a proper GET request for this item...
-								$this->debug('Wrong guess at content-type, queing GET request');
-								$this->requests[$orig]['wrongGuess'] = true;
-								$this->redirectQueue[$orig] = $this->requests[$orig]['effective_url'];
-							} elseif (strpos($this->requests[$orig]['effective_url'], '_escaped_fragment_') === false) {
-								// check for 
-								// for AJAX sites, e.g. Blogger with its dynamic views templates.
-								// Based on Google's spec: https://developers.google.com/webmasters/ajax-crawling/docs/specification
-								if (isset($this->requests[$orig]['body'])) {
-									$redirectURL = $this->getUglyURL($this->requests[$orig]['effective_url'], substr($this->requests[$orig]['body'], 0, 4000));
-									if ($redirectURL) {
-										$this->debug('AJAX trigger (meta name="fragment" content="!") found. Queueing '.$redirectURL);
-										$this->redirectQueue[$orig] = $redirectURL;
-									}
-								}
-							}
-							//die($url.' -multi- '.$request->getResponseInfo('effective_url'));
-							$pool->detach($request);
-							unset($this->requests[$orig]['httpRequest'], $request);
-							/*
-							if ($this->minimiseMemoryUse) {
-								if ($this->cache($url)) {
-									unset($this->requests[$url]);
-								}
-							}
-							*/
-						}
-					}
-				}
-			} catch (HttpException $e) {
-				$this->debug($e);
-				return false;
-			}
-		}
-		
-		//////////////////////////////////////////////////////////
-		// parallel (curl_multi_*)
-		elseif ($this->method == self::METHOD_CURL_MULTI) {
-			$this->debug('Starting parallel fetch (curl_multi_*)');
-			while (count($urls) > 0) {
-				$this->debug('Processing set of '.min($this->maxParallelRequests, count($urls)));
-				$subset = array_splice($urls, 0, $this->maxParallelRequests);
-				$pool = new RollingCurl(array($this, 'handleCurlResponse'));
-				$pool->window_size = count($subset);		
-				
-				foreach ($subset as $orig => $url) {
-					if (!$isRedirect) $orig = $url;
-					unset($this->redirectQueue[$orig]);
-					$this->debug("...$url");
-					if (!$isRedirect && isset($this->requests[$url])) {
-						$this->debug("......in memory");
-					/*
-					} elseif ($this->isCached($url)) {
-						$this->debug("......is cached");
-						if (!$this->minimiseMemoryUse) {
-							$this->requests[$url] = $this->getCached($url);
-						}
-					*/
-					} else {
-						$this->debug("......adding to pool");
-						$req_url = $this->rewriteUrls($url);
-						$req_url = ($this->rewriteHashbangFragment) ? $this->rewriteHashbangFragment($req_url) : $req_url;
-						$req_url = $this->removeFragment($req_url);
-						if (!empty($this->headerOnlyTypes) && !isset($this->requests[$orig]['wrongGuess']) && $this->possibleUnsupportedType($req_url)) {
-							$_meth = 'HEAD';
-						} else {
-							$_meth = 'GET';
-							unset($this->requests[$orig]['wrongGuess']);
-						}						
-						$headers = array();
-						//$headers[] = 'User-Agent: '.$this->userAgent;
-						$headers[] = $this->getUserAgent($req_url);
-						// add referer for picky sites
-						$headers[] = 'Referer: '.$this->referer;
-						// send cookies, if we have any
-						if ($cookies = $this->cookieJar->getMatchingCookies($req_url)) {
-							$this->debug("......sending cookies: $cookies");
-							$headers[] = 'Cookie: '.$cookies;
-						}
-						$httpRequest = new RollingCurlRequest($req_url, $_meth, null, $headers, array(
-							CURLOPT_CONNECTTIMEOUT => $this->requestOptions['timeout'],
-							CURLOPT_TIMEOUT => $this->requestOptions['timeout']
-							));
-						$httpRequest->set_original_url($orig);
-						$this->requests[$orig] = array('headers'=>null, 'body'=>null, 'httpRequest'=>$httpRequest);
-						$this->requests[$orig]['original_url'] = $orig; // TODO: is this needed anymore?
-						$pool->add($httpRequest);
-					}
-				}
-				// did we get anything into the pool?
-				if (count($pool) > 0) {
-					$this->debug('Sending request...');
-					$pool->execute(); // this will call handleCurlResponse() and populate $this->requests[$orig]
-					$this->debug('Received responses');
-					foreach($subset as $orig => $url) {
-						if (!$isRedirect) $orig = $url;
-						// $this->requests[$orig]['headers']
-						// $this->requests[$orig]['body']
-						// $this->requests[$orig]['effective_url']
-						// check content type
-						if ($this->headerOnlyType($this->requests[$orig]['headers'])) {
-							$this->requests[$orig]['body'] = '';
-							$_header_only_type = true;
-							$this->debug('Header only type returned');
-						} else {
-							$_header_only_type = false;
-						}
-						$status_code = $this->requests[$orig]['status_code'];
-						if ((in_array($status_code, array(300, 301, 302, 303, 307)) || $status_code > 307 && $status_code < 400) && isset($this->requests[$orig]['location'])) {
-							$redirectURL = $this->requests[$orig]['location'];
-							if (!preg_match('!^https?://!i', $redirectURL)) {
-								$redirectURL = SimplePie_Misc::absolutize_url($redirectURL, $url);
-							}
-							if ($this->validateURL($redirectURL)) {
-								$this->debug('Redirect detected. Valid URL: '.$redirectURL);
-								// store any cookies
-								$cookies = $this->cookieJar->extractCookies($this->requests[$orig]['headers']);
-								if (!empty($cookies)) $this->cookieJar->storeCookies($url, $cookies);							
-								$this->redirectQueue[$orig] = $redirectURL;
-							} else {
-								$this->debug('Redirect detected. Invalid URL: '.$redirectURL);
-							}
-						} elseif (!$_header_only_type && $this->requests[$orig]['method'] == 'HEAD') {
-							// the response content-type did not match our 'header only' types, 
-							// but we'd issues a HEAD request because we assumed it would. So
-							// let's queue a proper GET request for this item...
-							$this->debug('Wrong guess at content-type, queing GET request');
-							$this->requests[$orig]['wrongGuess'] = true;
-							$this->redirectQueue[$orig] = $this->requests[$orig]['effective_url'];
-						} elseif (strpos($this->requests[$orig]['effective_url'], '_escaped_fragment_') === false) {
-							// check for 
-							// for AJAX sites, e.g. Blogger with its dynamic views templates.
-							// Based on Google's spec: https://developers.google.com/webmasters/ajax-crawling/docs/specification
-							if (isset($this->requests[$orig]['body'])) {
-								$redirectURL = $this->getUglyURL($this->requests[$orig]['effective_url'], substr($this->requests[$orig]['body'], 0, 4000));
-								if ($redirectURL) {
-									$this->debug('AJAX trigger (meta name="fragment" content="!") found. Queueing '.$redirectURL);
-									$this->redirectQueue[$orig] = $redirectURL;
-								}
-							}
-						}
-						// die($url.' -multi- '.$request->getResponseInfo('effective_url'));
-						unset($this->requests[$orig]['httpRequest'], $this->requests[$orig]['method']);
-					}
-				}
-			}
-		}
-
-		//////////////////////////////////////////////////////
-		// sequential (file_get_contents)
-		else {
-			$this->debug('Starting sequential fetch (file_get_contents)');
-			$this->debug('Processing set of '.count($urls));
-			foreach ($urls as $orig => $url) {
-				if (!$isRedirect) $orig = $url;
-				unset($this->redirectQueue[$orig]);
-				$this->debug("...$url");
-				if (!$isRedirect && isset($this->requests[$url])) {
-					$this->debug("......in memory");
-				/*
-				} elseif ($this->isCached($url)) {
-					$this->debug("......is cached");
-					if (!$this->minimiseMemoryUse) {
-						$this->requests[$url] = $this->getCached($url);
-					}
-				*/
-				} else {
-					$this->debug("Sending request for $url");
-					$this->requests[$orig]['original_url'] = $orig;
-					$req_url = $this->rewriteUrls($url);
-					$req_url = ($this->rewriteHashbangFragment) ? $this->rewriteHashbangFragment($req_url) : $req_url;
-					$req_url = $this->removeFragment($req_url);
-					// send cookies, if we have any
-					$httpContext = $this->httpContext;
-					$httpContext['http']['header'] .= $this->getUserAgent($req_url)."\r\n";
-					// add referer for picky sites
-					$httpContext['http']['header'] .= 'Referer: '.$this->referer."\r\n";
-					if ($cookies = $this->cookieJar->getMatchingCookies($req_url)) {
-						$this->debug("......sending cookies: $cookies");
-						$httpContext['http']['header'] .= 'Cookie: '.$cookies."\r\n";
-					}
-					if (false !== ($html = @file_get_contents($req_url, false, stream_context_create($httpContext)))) {
-						$this->debug('Received response');
-						// get status code
-						if (!isset($http_response_header[0]) || !preg_match('!^HTTP/\d+\.\d+\s+(\d+)!', trim($http_response_header[0]), $match)) {
-							$this->debug('Error: no status code found');
-							// TODO: handle error - no status code
-						} else {
-							$this->requests[$orig]['headers'] = $this->headersToString($http_response_header, false);
-							// check content type
-							if ($this->headerOnlyType($this->requests[$orig]['headers'])) {
-								$this->requests[$orig]['body'] = '';
-							} else {
-								$this->requests[$orig]['body'] = $html;
-							}
-							$this->requests[$orig]['effective_url'] = $req_url;
-							$this->requests[$orig]['status_code'] = $status_code = (int)$match[1];
-							unset($match);
-							// handle redirect
-							if (preg_match('/^Location:(.*?)$/mi', $this->requests[$orig]['headers'], $match)) {
-								$this->requests[$orig]['location'] =  trim($match[1]);
-							}
-							if ((in_array($status_code, array(300, 301, 302, 303, 307)) || $status_code > 307 && $status_code < 400) && isset($this->requests[$orig]['location'])) {
-								$redirectURL = $this->requests[$orig]['location'];
-								if (!preg_match('!^https?://!i', $redirectURL)) {
-									$redirectURL = SimplePie_Misc::absolutize_url($redirectURL, $url);
-								}
-								if ($this->validateURL($redirectURL)) {
-									$this->debug('Redirect detected. Valid URL: '.$redirectURL);
-									// store any cookies
-									$cookies = $this->cookieJar->extractCookies($this->requests[$orig]['headers']);
-									if (!empty($cookies)) $this->cookieJar->storeCookies($url, $cookies);
-									$this->redirectQueue[$orig] = $redirectURL;
-								} else {
-									$this->debug('Redirect detected. Invalid URL: '.$redirectURL);
-								}
-							} elseif (strpos($this->requests[$orig]['effective_url'], '_escaped_fragment_') === false) {
-								// check for 
-								// for AJAX sites, e.g. Blogger with its dynamic views templates.
-								// Based on Google's spec: https://developers.google.com/webmasters/ajax-crawling/docs/specification
-								if (isset($this->requests[$orig]['body'])) {
-									$redirectURL = $this->getUglyURL($this->requests[$orig]['effective_url'], substr($this->requests[$orig]['body'], 0, 4000));
-									if ($redirectURL) {
-										$this->debug('AJAX trigger (meta name="fragment" content="!") found. Queueing '.$redirectURL);
-										$this->redirectQueue[$orig] = $redirectURL;
-									}
-								}
-							}
-						}
-					} else {
-						$this->debug('Error retrieving URL');
-						//print_r($req_url);
-						//print_r($http_response_header);
-						//print_r($html);
-						
-						// TODO: handle error - failed to retrieve URL
-					}
-				}
-			}
-		}
-	}
-	
-	public function handleCurlResponse($response, $info, $request) {
-		$orig = $request->url_original;
-		$this->requests[$orig]['headers'] = substr($response, 0, $info['header_size']);
-		$this->requests[$orig]['body'] = substr($response, $info['header_size']);
-		$this->requests[$orig]['method'] = $request->method;
-		$this->requests[$orig]['effective_url'] = $info['url'];
-		$this->requests[$orig]['status_code'] = (int)$info['http_code'];
-		if (preg_match('/^Location:(.*?)$/mi', $this->requests[$orig]['headers'], $match)) {
-			$this->requests[$orig]['location'] =  trim($match[1]);
-		}
-	}
-	
-	protected function headersToString(array $headers, $associative=true) {
-		if (!$associative) {
-			return implode("\n", $headers);
-		} else {
-			$str = '';
-			foreach ($headers as $key => $val) {
-				if (is_array($val)) {
-					foreach ($val as $v) $str .= "$key: $v\n";
-				} else {
-					$str .= "$key: $val\n";
-				}
-			}
-			return rtrim($str);
-		}
-	}
-	
-	public function get($url, $remove=false, $gzdecode=true) {
-		$url = "$url";
-		if (isset($this->requests[$url]) && isset($this->requests[$url]['body'])) {
-			$this->debug("URL already fetched - in memory ($url, effective: {$this->requests[$url]['effective_url']})");
-			$response = $this->requests[$url];
-		/*
-		} elseif ($this->isCached($url)) {
-			$this->debug("URL already fetched - in disk cache ($url)");
-			$response = $this->getCached($url);
-			$this->requests[$url] = $response;
-		*/
-		} else {
-			$this->debug("Fetching URL ($url)");
-			$this->fetchAll(array($url));
-			if (isset($this->requests[$url]) && isset($this->requests[$url]['body'])) {
-				$response = $this->requests[$url];
-			} else {
-				$this->debug("Request failed");
-				$response = false;
-			}
-		}
-		/*
-		if ($this->minimiseMemoryUse && $response) {
-			$this->cache($url);
-			unset($this->requests[$url]);
-		}
-		*/
-		if ($remove && $response) unset($this->requests[$url]);
-		if ($gzdecode && stripos($response['headers'], 'Content-Encoding: gzip')) {
-			if ($html = gzdecode($response['body'])) {
-				$response['body'] = $html;
-			}
-		}
-		return $response;
-	}
-	
-	public function parallelSupport() {
-		return class_exists('HttpRequestPool') || function_exists('curl_multi_init');
-	}
-	
-	private function headerOnlyType($headers) {
-		if (preg_match('!^Content-Type:\s*(([a-z-]+)/([^;\r\n ]+))!im', $headers, $match)) {
-			// look for full mime type (e.g. image/jpeg) or just type (e.g. image)
-			$match[1] = strtolower(trim($match[1]));
-			$match[2] = strtolower(trim($match[2]));
-			foreach (array($match[1], $match[2]) as $mime) {
-				if (in_array($mime, $this->headerOnlyTypes)) return true;
-			}
-		}
-		return false;
-	}
-	
-	private function possibleUnsupportedType($url) {
-		$path = @parse_url($url, PHP_URL_PATH);
-		if ($path && strpos($path, '.') !== false) {
-			$ext = strtolower(trim(pathinfo($path, PATHINFO_EXTENSION)));
-			return in_array($ext, $this->headerOnlyClues);
-		}
-		return false;
-	}
-}
-
-// gzdecode from http://www.php.net/manual/en/function.gzdecode.php#82930
-if (!function_exists('gzdecode')) {
-	function gzdecode($data,&$filename='',&$error='',$maxlength=null) 
-	{
-		$len = strlen($data);
-		if ($len < 18 || strcmp(substr($data,0,2),"\x1f\x8b")) {
-			$error = "Not in GZIP format.";
-			return null;  // Not GZIP format (See RFC 1952)
-		}
-		$method = ord(substr($data,2,1));  // Compression method
-		$flags  = ord(substr($data,3,1));  // Flags
-		if ($flags & 31 != $flags) {
-			$error = "Reserved bits not allowed.";
-			return null;
-		}
-		// NOTE: $mtime may be negative (PHP integer limitations)
-		$mtime = unpack("V", substr($data,4,4));
-		$mtime = $mtime[1];
-		$xfl   = substr($data,8,1);
-		$os    = substr($data,8,1);
-		$headerlen = 10;
-		$extralen  = 0;
-		$extra     = "";
-		if ($flags & 4) {
-			// 2-byte length prefixed EXTRA data in header
-			if ($len - $headerlen - 2 < 8) {
-				return false;  // invalid
-			}
-			$extralen = unpack("v",substr($data,8,2));
-			$extralen = $extralen[1];
-			if ($len - $headerlen - 2 - $extralen < 8) {
-				return false;  // invalid
-			}
-			$extra = substr($data,10,$extralen);
-			$headerlen += 2 + $extralen;
-		}
-		$filenamelen = 0;
-		$filename = "";
-		if ($flags & 8) {
-			// C-style string
-			if ($len - $headerlen - 1 < 8) {
-				return false; // invalid
-			}
-			$filenamelen = strpos(substr($data,$headerlen),chr(0));
-			if ($filenamelen === false || $len - $headerlen - $filenamelen - 1 < 8) {
-				return false; // invalid
-			}
-			$filename = substr($data,$headerlen,$filenamelen);
-			$headerlen += $filenamelen + 1;
-		}
-		$commentlen = 0;
-		$comment = "";
-		if ($flags & 16) {
-			// C-style string COMMENT data in header
-			if ($len - $headerlen - 1 < 8) {
-				return false;    // invalid
-			}
-			$commentlen = strpos(substr($data,$headerlen),chr(0));
-			if ($commentlen === false || $len - $headerlen - $commentlen - 1 < 8) {
-				return false;    // Invalid header format
-			}
-			$comment = substr($data,$headerlen,$commentlen);
-			$headerlen += $commentlen + 1;
-		}
-		$headercrc = "";
-		if ($flags & 2) {
-			// 2-bytes (lowest order) of CRC32 on header present
-			if ($len - $headerlen - 2 < 8) {
-				return false;    // invalid
-			}
-			$calccrc = crc32(substr($data,0,$headerlen)) & 0xffff;
-			$headercrc = unpack("v", substr($data,$headerlen,2));
-			$headercrc = $headercrc[1];
-			if ($headercrc != $calccrc) {
-				$error = "Header checksum failed.";
-				return false;    // Bad header CRC
-			}
-			$headerlen += 2;
-		}
-		// GZIP FOOTER
-		$datacrc = unpack("V",substr($data,-8,4));
-		$datacrc = sprintf('%u',$datacrc[1] & 0xFFFFFFFF);
-		$isize = unpack("V",substr($data,-4));
-		$isize = $isize[1];
-		// decompression:
-		$bodylen = $len-$headerlen-8;
-		if ($bodylen < 1) {
-			// IMPLEMENTATION BUG!
-			return null;
-		}
-		$body = substr($data,$headerlen,$bodylen);
-		$data = "";
-		if ($bodylen > 0) {
-			switch ($method) {
-			case 8:
-				// Currently the only supported compression method:
-				$data = gzinflate($body,$maxlength);
-				break;
-			default:
-				$error = "Unknown compression method.";
-				return false;
-			}
-		}  // zero-byte body content is allowed
-		// Verifiy CRC32
-		$crc   = sprintf("%u",crc32($data));
-		$crcOK = $crc == $datacrc;
-		$lenOK = $isize == strlen($data);
-		if (!$lenOK || !$crcOK) {
-			$error = ( $lenOK ? '' : 'Length check FAILED. ') . ( $crcOK ? '' : 'Checksum FAILED.');
-			return false;
-		}
-		return $data;
-	}
-}
-?>
\ No newline at end of file
+userAgentDefault = self::UA_BROWSER;
+		$this->referer = self::REF_GOOGLE;
+		// set the request method
+		if (in_array($method, array(1,2,4))) {
+			$this->method = $method;
+		} else {
+			if (class_exists('HttpRequestPool')) {
+				$this->method = self::METHOD_REQUEST_POOL;
+			} elseif (function_exists('curl_multi_init')) {
+				$this->method = self::METHOD_CURL_MULTI;
+			} else {
+				$this->method = self::METHOD_FILE_GET_CONTENTS;
+			}
+		}
+		if ($this->method == self::METHOD_CURL_MULTI) {
+			require_once(dirname(__FILE__).'/RollingCurl.php');
+		}
+		// create cookie jar
+		$this->cookieJar = new CookieJar();
+		// set request options (redirect must be 0)
+		$this->requestOptions = array(
+			'timeout' => 15,
+			'connecttimeout' => 15,
+			'dns_cache_timeout' => 300,
+			'redirect' => 0 // we handle redirects manually so we can rewrite the new hashbang URLs that are creeping up over the web
+			// TODO: test onprogress?
+		);
+		if (is_array($requestOptions)) {
+			$this->requestOptions = array_merge($this->requestOptions, $requestOptions);
+		}
+		$this->httpContext = array(
+			'http' => array(
+				'ignore_errors' => true,
+				'timeout' => $this->requestOptions['timeout'],
+				'max_redirects' => $this->requestOptions['redirect'],
+				'header' => "Accept: */*\r\n"
+				)
+			);
+	}
+	
+	protected function debug($msg) {
+		if ($this->debug) {
+			$mem = round(memory_get_usage()/1024, 2);
+			$memPeak = round(memory_get_peak_usage()/1024, 2);
+			echo '* ',$msg;
+			if ($this->debugVerbose) echo ' - mem used: ',$mem," (peak: $memPeak)";
+			echo "\n";
+			ob_flush();
+			flush();
+		}
+	}
+	
+	protected function getUserAgent($url, $asArray=false) {
+		$host = @parse_url($url, PHP_URL_HOST);
+		if (strtolower(substr($host, 0, 4)) == 'www.') {
+			$host = substr($host, 4);
+		}
+		if ($host) {
+			$try = array($host);
+			$split = explode('.', $host);
+			if (count($split) > 1) {
+				array_shift($split);
+				$try[] = '.'.implode('.', $split);
+			}
+			foreach ($try as $h) {
+				if (isset($this->userAgentMap[$h])) {
+					$ua = $this->userAgentMap[$h];
+					break;
+				}
+			}
+		}
+		if (!isset($ua)) $ua = $this->userAgentDefault;
+		if ($asArray) {
+			return array('User-Agent' => $ua);
+		} else {
+			return 'User-Agent: '.$ua;
+		}
+	}
+	
+	public function rewriteHashbangFragment($url) {
+		// return $url if there's no '#!'
+		if (strpos($url, '#!') === false) return $url;
+		// split $url and rewrite
+		// TODO: is SimplePie_IRI included?
+		$iri = new SimplePie_IRI($url);
+		$fragment = substr($iri->fragment, 1); // strip '!'
+		$iri->fragment = null;
+		if (isset($iri->query)) {
+			parse_str($iri->query, $query);
+		} else {
+			$query = array();
+		}
+		$query['_escaped_fragment_'] = (string)$fragment;
+		$iri->query = str_replace('%2F', '/', http_build_query($query)); // needed for some sites
+		return $iri->get_iri();
+	}
+	
+	public function getRedirectURLfromHTML($url, $html) {
+		$redirect_url = $this->getMetaRefreshURL($url, $html);
+		if (!$redirect_url) {
+			$redirect_url = $this->getUglyURL($url, $html);
+		}
+		return $redirect_url;
+	}
+	
+	public function getMetaRefreshURL($url, $html) {
+		if ($html == '') return false;
+		// 
+		if (!preg_match('!]+)["\']*>!i', $html, $match)) {
+			return false;
+		}
+		$redirect_url = $match[1];
+		if (preg_match('!^https?://!i', $redirect_url)) {
+			// already absolute
+			$this->debug('Meta refresh redirect found (http-equiv="refresh"), new URL: '.$redirect_url);
+			return $redirect_url;
+		}
+		// absolutize redirect URL
+		$base = new SimplePie_IRI($url);
+		// remove '//' in URL path (causes URLs not to resolve properly)
+		if (isset($base->path)) $base->path = preg_replace('!//+!', '/', $base->path);
+		if ($absolute = SimplePie_IRI::absolutize($base, $redirect_url)) {
+			$this->debug('Meta refresh redirect found (http-equiv="refresh"), new URL: '.$absolute);
+			return $absolute;
+		}
+		return false;
+	}	
+	
+	public function getUglyURL($url, $html) {
+		if ($html == '') return false;
+		$found = false;
+		foreach ($this->ajaxTriggers as $string) {
+			if (stripos($html, $string)) {
+				$found = true;
+				break;
+			}
+		}
+		if (!$found) return false;
+		$iri = new SimplePie_IRI($url);
+		if (isset($iri->query)) {
+			parse_str($iri->query, $query);
+		} else {
+			$query = array();
+		}
+		$query['_escaped_fragment_'] = '';
+		$iri->query = str_replace('%2F', '/', http_build_query($query)); // needed for some sites
+		$ugly_url = $iri->get_iri();
+		$this->debug('AJAX trigger (meta name="fragment" content="!") found, new URL: '.$ugly_url);
+		return $ugly_url;
+	}
+	
+	public function removeFragment($url) {
+		$pos = strpos($url, '#');
+		if ($pos === false) {
+			return $url;
+		} else {
+			return substr($url, 0, $pos);
+		}
+	}
+	
+	public function rewriteUrls($url) {
+		foreach ($this->rewriteUrls as $find => $action) {
+			if (strpos($url, $find) !== false) {
+				if (is_array($action)) {
+					return strtr($url, $action);
+				}
+			}
+		}
+		return $url;
+	}
+	
+	public function enableDebug($bool=true) {
+		$this->debug = (bool)$bool;
+	}
+	
+	public function minimiseMemoryUse($bool = true) {
+		$this->minimiseMemoryUse = $bool;
+	}
+	
+	public function setMaxParallelRequests($max) {
+		$this->maxParallelRequests = $max;
+	}
+	
+	public function validateUrl($url) {
+		$url = filter_var($url, FILTER_SANITIZE_URL);
+		$test = filter_var($url, FILTER_VALIDATE_URL, FILTER_FLAG_SCHEME_REQUIRED);
+		// deal with bug http://bugs.php.net/51192 (present in PHP 5.2.13 and PHP 5.3.2)
+		if ($test === false) {
+			$test = filter_var(strtr($url, '-', '_'), FILTER_VALIDATE_URL, FILTER_FLAG_SCHEME_REQUIRED);
+		}
+		if ($test !== false && $test !== null && preg_match('!^https?://!', $url)) {
+			return $url;
+		} else {
+			return false;
+		}
+	}
+	
+	public function fetchAll(array $urls) {
+		$this->fetchAllOnce($urls, $isRedirect=false);
+		$redirects = 0;
+		while (!empty($this->redirectQueue) && ++$redirects <= $this->maxRedirects) {
+			$this->debug("Following redirects #$redirects...");
+			$this->fetchAllOnce($this->redirectQueue, $isRedirect=true);
+		}
+	}
+	
+	// fetch all URLs without following redirects
+	public function fetchAllOnce(array $urls, $isRedirect=false) {
+		if (!$isRedirect) $urls = array_unique($urls);
+		if (empty($urls)) return;
+		
+		//////////////////////////////////////////////////////
+		// parallel (HttpRequestPool)
+		if ($this->method == self::METHOD_REQUEST_POOL) {
+			$this->debug('Starting parallel fetch (HttpRequestPool)');
+			try {
+				while (count($urls) > 0) {
+					$this->debug('Processing set of '.min($this->maxParallelRequests, count($urls)));
+					$subset = array_splice($urls, 0, $this->maxParallelRequests);
+					$pool = new HttpRequestPool();
+					foreach ($subset as $orig => $url) {
+						if (!$isRedirect) $orig = $url;
+						unset($this->redirectQueue[$orig]);
+						$this->debug("...$url");
+						if (!$isRedirect && isset($this->requests[$url])) {
+							$this->debug("......in memory");
+						/*
+						} elseif ($this->isCached($url)) {
+							$this->debug("......is cached");
+							if (!$this->minimiseMemoryUse) {
+								$this->requests[$url] = $this->getCached($url);
+							}
+						*/
+						} else {
+							$this->debug("......adding to pool");
+							$req_url = $this->rewriteUrls($url);
+							$req_url = ($this->rewriteHashbangFragment) ? $this->rewriteHashbangFragment($req_url) : $req_url;
+							$req_url = $this->removeFragment($req_url);
+							if (!empty($this->headerOnlyTypes) && !isset($this->requests[$orig]['wrongGuess']) && $this->possibleUnsupportedType($req_url)) {
+								$_meth = HttpRequest::METH_HEAD;
+							} else {
+								$_meth = HttpRequest::METH_GET;
+								unset($this->requests[$orig]['wrongGuess']);
+							}
+							$httpRequest = new HttpRequest($req_url, $_meth, $this->requestOptions);
+							// send cookies, if we have any
+							if ($cookies = $this->cookieJar->getMatchingCookies($req_url)) {
+								$this->debug("......sending cookies: $cookies");
+								$httpRequest->addHeaders(array('Cookie' => $cookies));
+							}
+							//$httpRequest->addHeaders(array('User-Agent' => $this->userAgent));
+							$httpRequest->addHeaders($this->getUserAgent($req_url, true));
+							// add referer for picky sites
+							$httpRequest->addheaders(array('Referer' => $this->referer));
+							$this->requests[$orig] = array('headers'=>null, 'body'=>null, 'httpRequest'=>$httpRequest);
+							$this->requests[$orig]['original_url'] = $orig;
+							$pool->attach($httpRequest);
+						}
+					}
+					// did we get anything into the pool?
+					if (count($pool) > 0) {
+						$this->debug('Sending request...');
+						try {
+							$pool->send();
+						} catch (HttpRequestPoolException $e) {
+							// do nothing
+						}
+						$this->debug('Received responses');
+						foreach($subset as $orig => $url) {
+							if (!$isRedirect) $orig = $url;
+							$request = $this->requests[$orig]['httpRequest'];
+							//$this->requests[$orig]['headers'] = $this->headersToString($request->getResponseHeader());
+							// getResponseHeader() doesn't return status line, so, for consistency...
+							$this->requests[$orig]['headers'] = substr($request->getRawResponseMessage(), 0, $request->getResponseInfo('header_size'));
+							// check content type
+							// TODO: use getResponseHeader('content-type') or getResponseInfo()
+							if ($this->headerOnlyType($this->requests[$orig]['headers'])) {
+								$this->requests[$orig]['body'] = '';
+								$_header_only_type = true;
+								$this->debug('Header only type returned');
+							} else {
+								$this->requests[$orig]['body'] = $request->getResponseBody();
+								$_header_only_type = false;
+							}
+							$this->requests[$orig]['effective_url'] = $request->getResponseInfo('effective_url');
+							$this->requests[$orig]['status_code'] = $status_code = $request->getResponseCode();
+							// is redirect?
+							if ((in_array($status_code, array(300, 301, 302, 303, 307)) || $status_code > 307 && $status_code < 400) && $request->getResponseHeader('location')) {
+								$redirectURL = $request->getResponseHeader('location');
+								if (!preg_match('!^https?://!i', $redirectURL)) {
+									$redirectURL = SimplePie_Misc::absolutize_url($redirectURL, $url);
+								}
+								if ($this->validateURL($redirectURL)) {
+									$this->debug('Redirect detected. Valid URL: '.$redirectURL);
+									// store any cookies
+									$cookies = $request->getResponseHeader('set-cookie');
+									if ($cookies && !is_array($cookies)) $cookies = array($cookies);
+									if ($cookies) $this->cookieJar->storeCookies($url, $cookies);
+									$this->redirectQueue[$orig] = $redirectURL;
+								} else {
+									$this->debug('Redirect detected. Invalid URL: '.$redirectURL);
+								}
+							} elseif (!$_header_only_type && $request->getMethod() === HttpRequest::METH_HEAD) {
+								// the response content-type did not match our 'header only' types, 
+								// but we'd issues a HEAD request because we assumed it would. So
+								// let's queue a proper GET request for this item...
+								$this->debug('Wrong guess at content-type, queing GET request');
+								$this->requests[$orig]['wrongGuess'] = true;
+								$this->redirectQueue[$orig] = $this->requests[$orig]['effective_url'];
+							} elseif (strpos($this->requests[$orig]['effective_url'], '_escaped_fragment_') === false) {
+								// check for 
+								// for AJAX sites, e.g. Blogger with its dynamic views templates.
+								// Based on Google's spec: https://developers.google.com/webmasters/ajax-crawling/docs/specification
+								if (isset($this->requests[$orig]['body'])) {
+									$redirectURL = $this->getRedirectURLfromHTML($this->requests[$orig]['effective_url'], substr($this->requests[$orig]['body'], 0, 4000));
+									if ($redirectURL) {
+										$this->redirectQueue[$orig] = $redirectURL;
+									}
+								}
+							}
+							//die($url.' -multi- '.$request->getResponseInfo('effective_url'));
+							$pool->detach($request);
+							unset($this->requests[$orig]['httpRequest'], $request);
+							/*
+							if ($this->minimiseMemoryUse) {
+								if ($this->cache($url)) {
+									unset($this->requests[$url]);
+								}
+							}
+							*/
+						}
+					}
+				}
+			} catch (HttpException $e) {
+				$this->debug($e);
+				return false;
+			}
+		}
+		
+		//////////////////////////////////////////////////////////
+		// parallel (curl_multi_*)
+		elseif ($this->method == self::METHOD_CURL_MULTI) {
+			$this->debug('Starting parallel fetch (curl_multi_*)');
+			while (count($urls) > 0) {
+				$this->debug('Processing set of '.min($this->maxParallelRequests, count($urls)));
+				$subset = array_splice($urls, 0, $this->maxParallelRequests);
+				$pool = new RollingCurl(array($this, 'handleCurlResponse'));
+				$pool->window_size = count($subset);		
+				
+				foreach ($subset as $orig => $url) {
+					if (!$isRedirect) $orig = $url;
+					unset($this->redirectQueue[$orig]);
+					$this->debug("...$url");
+					if (!$isRedirect && isset($this->requests[$url])) {
+						$this->debug("......in memory");
+					/*
+					} elseif ($this->isCached($url)) {
+						$this->debug("......is cached");
+						if (!$this->minimiseMemoryUse) {
+							$this->requests[$url] = $this->getCached($url);
+						}
+					*/
+					} else {
+						$this->debug("......adding to pool");
+						$req_url = $this->rewriteUrls($url);
+						$req_url = ($this->rewriteHashbangFragment) ? $this->rewriteHashbangFragment($req_url) : $req_url;
+						$req_url = $this->removeFragment($req_url);
+						if (!empty($this->headerOnlyTypes) && !isset($this->requests[$orig]['wrongGuess']) && $this->possibleUnsupportedType($req_url)) {
+							$_meth = 'HEAD';
+						} else {
+							$_meth = 'GET';
+							unset($this->requests[$orig]['wrongGuess']);
+						}						
+						$headers = array();
+						//$headers[] = 'User-Agent: '.$this->userAgent;
+						$headers[] = $this->getUserAgent($req_url);
+						// add referer for picky sites
+						$headers[] = 'Referer: '.$this->referer;
+						// send cookies, if we have any
+						if ($cookies = $this->cookieJar->getMatchingCookies($req_url)) {
+							$this->debug("......sending cookies: $cookies");
+							$headers[] = 'Cookie: '.$cookies;
+						}
+						$httpRequest = new RollingCurlRequest($req_url, $_meth, null, $headers, array(
+							CURLOPT_CONNECTTIMEOUT => $this->requestOptions['timeout'],
+							CURLOPT_TIMEOUT => $this->requestOptions['timeout']
+							));
+						$httpRequest->set_original_url($orig);
+						$this->requests[$orig] = array('headers'=>null, 'body'=>null, 'httpRequest'=>$httpRequest);
+						$this->requests[$orig]['original_url'] = $orig; // TODO: is this needed anymore?
+						$pool->add($httpRequest);
+					}
+				}
+				// did we get anything into the pool?
+				if (count($pool) > 0) {
+					$this->debug('Sending request...');
+					$pool->execute(); // this will call handleCurlResponse() and populate $this->requests[$orig]
+					$this->debug('Received responses');
+					foreach($subset as $orig => $url) {
+						if (!$isRedirect) $orig = $url;
+						// $this->requests[$orig]['headers']
+						// $this->requests[$orig]['body']
+						// $this->requests[$orig]['effective_url']
+						// check content type
+						if ($this->headerOnlyType($this->requests[$orig]['headers'])) {
+							$this->requests[$orig]['body'] = '';
+							$_header_only_type = true;
+							$this->debug('Header only type returned');
+						} else {
+							$_header_only_type = false;
+						}
+						$status_code = $this->requests[$orig]['status_code'];
+						if ((in_array($status_code, array(300, 301, 302, 303, 307)) || $status_code > 307 && $status_code < 400) && isset($this->requests[$orig]['location'])) {
+							$redirectURL = $this->requests[$orig]['location'];
+							if (!preg_match('!^https?://!i', $redirectURL)) {
+								$redirectURL = SimplePie_Misc::absolutize_url($redirectURL, $url);
+							}
+							if ($this->validateURL($redirectURL)) {
+								$this->debug('Redirect detected. Valid URL: '.$redirectURL);
+								// store any cookies
+								$cookies = $this->cookieJar->extractCookies($this->requests[$orig]['headers']);
+								if (!empty($cookies)) $this->cookieJar->storeCookies($url, $cookies);							
+								$this->redirectQueue[$orig] = $redirectURL;
+							} else {
+								$this->debug('Redirect detected. Invalid URL: '.$redirectURL);
+							}
+						} elseif (!$_header_only_type && $this->requests[$orig]['method'] == 'HEAD') {
+							// the response content-type did not match our 'header only' types, 
+							// but we'd issues a HEAD request because we assumed it would. So
+							// let's queue a proper GET request for this item...
+							$this->debug('Wrong guess at content-type, queing GET request');
+							$this->requests[$orig]['wrongGuess'] = true;
+							$this->redirectQueue[$orig] = $this->requests[$orig]['effective_url'];
+						} elseif (strpos($this->requests[$orig]['effective_url'], '_escaped_fragment_') === false) {
+							// check for 
+							// for AJAX sites, e.g. Blogger with its dynamic views templates.
+							// Based on Google's spec: https://developers.google.com/webmasters/ajax-crawling/docs/specification
+							if (isset($this->requests[$orig]['body'])) {
+								$redirectURL = $this->getRedirectURLfromHTML($this->requests[$orig]['effective_url'], substr($this->requests[$orig]['body'], 0, 4000));
+								if ($redirectURL) {
+									$this->redirectQueue[$orig] = $redirectURL;
+								}
+							}
+						}
+						// die($url.' -multi- '.$request->getResponseInfo('effective_url'));
+						unset($this->requests[$orig]['httpRequest'], $this->requests[$orig]['method']);
+					}
+				}
+			}
+		}
+
+		//////////////////////////////////////////////////////
+		// sequential (file_get_contents)
+		else {
+			$this->debug('Starting sequential fetch (file_get_contents)');
+			$this->debug('Processing set of '.count($urls));
+			foreach ($urls as $orig => $url) {
+				if (!$isRedirect) $orig = $url;
+				unset($this->redirectQueue[$orig]);
+				$this->debug("...$url");
+				if (!$isRedirect && isset($this->requests[$url])) {
+					$this->debug("......in memory");
+				/*
+				} elseif ($this->isCached($url)) {
+					$this->debug("......is cached");
+					if (!$this->minimiseMemoryUse) {
+						$this->requests[$url] = $this->getCached($url);
+					}
+				*/
+				} else {
+					$this->debug("Sending request for $url");
+					$this->requests[$orig]['original_url'] = $orig;
+					$req_url = $this->rewriteUrls($url);
+					$req_url = ($this->rewriteHashbangFragment) ? $this->rewriteHashbangFragment($req_url) : $req_url;
+					$req_url = $this->removeFragment($req_url);
+					// send cookies, if we have any
+					$httpContext = $this->httpContext;
+					$httpContext['http']['header'] .= $this->getUserAgent($req_url)."\r\n";
+					// add referer for picky sites
+					$httpContext['http']['header'] .= 'Referer: '.$this->referer."\r\n";
+					if ($cookies = $this->cookieJar->getMatchingCookies($req_url)) {
+						$this->debug("......sending cookies: $cookies");
+						$httpContext['http']['header'] .= 'Cookie: '.$cookies."\r\n";
+					}
+					if (false !== ($html = @file_get_contents($req_url, false, stream_context_create($httpContext)))) {
+						$this->debug('Received response');
+						// get status code
+						if (!isset($http_response_header[0]) || !preg_match('!^HTTP/\d+\.\d+\s+(\d+)!', trim($http_response_header[0]), $match)) {
+							$this->debug('Error: no status code found');
+							// TODO: handle error - no status code
+						} else {
+							$this->requests[$orig]['headers'] = $this->headersToString($http_response_header, false);
+							// check content type
+							if ($this->headerOnlyType($this->requests[$orig]['headers'])) {
+								$this->requests[$orig]['body'] = '';
+							} else {
+								$this->requests[$orig]['body'] = $html;
+							}
+							$this->requests[$orig]['effective_url'] = $req_url;
+							$this->requests[$orig]['status_code'] = $status_code = (int)$match[1];
+							unset($match);
+							// handle redirect
+							if (preg_match('/^Location:(.*?)$/mi', $this->requests[$orig]['headers'], $match)) {
+								$this->requests[$orig]['location'] =  trim($match[1]);
+							}
+							if ((in_array($status_code, array(300, 301, 302, 303, 307)) || $status_code > 307 && $status_code < 400) && isset($this->requests[$orig]['location'])) {
+								$redirectURL = $this->requests[$orig]['location'];
+								if (!preg_match('!^https?://!i', $redirectURL)) {
+									$redirectURL = SimplePie_Misc::absolutize_url($redirectURL, $url);
+								}
+								if ($this->validateURL($redirectURL)) {
+									$this->debug('Redirect detected. Valid URL: '.$redirectURL);
+									// store any cookies
+									$cookies = $this->cookieJar->extractCookies($this->requests[$orig]['headers']);
+									if (!empty($cookies)) $this->cookieJar->storeCookies($url, $cookies);
+									$this->redirectQueue[$orig] = $redirectURL;
+								} else {
+									$this->debug('Redirect detected. Invalid URL: '.$redirectURL);
+								}
+							} elseif (strpos($this->requests[$orig]['effective_url'], '_escaped_fragment_') === false) {
+								// check for 
+								// for AJAX sites, e.g. Blogger with its dynamic views templates.
+								// Based on Google's spec: https://developers.google.com/webmasters/ajax-crawling/docs/specification
+								if (isset($this->requests[$orig]['body'])) {
+									$redirectURL = $this->getRedirectURLfromHTML($this->requests[$orig]['effective_url'], substr($this->requests[$orig]['body'], 0, 4000));
+									if ($redirectURL) {
+										$this->redirectQueue[$orig] = $redirectURL;
+									}
+								}
+							}
+						}
+					} else {
+						$this->debug('Error retrieving URL');
+						//print_r($req_url);
+						//print_r($http_response_header);
+						//print_r($html);
+						
+						// TODO: handle error - failed to retrieve URL
+					}
+				}
+			}
+		}
+	}
+	
+	public function handleCurlResponse($response, $info, $request) {
+		$orig = $request->url_original;
+		$this->requests[$orig]['headers'] = substr($response, 0, $info['header_size']);
+		$this->requests[$orig]['body'] = substr($response, $info['header_size']);
+		$this->requests[$orig]['method'] = $request->method;
+		$this->requests[$orig]['effective_url'] = $info['url'];
+		$this->requests[$orig]['status_code'] = (int)$info['http_code'];
+		if (preg_match('/^Location:(.*?)$/mi', $this->requests[$orig]['headers'], $match)) {
+			$this->requests[$orig]['location'] =  trim($match[1]);
+		}
+	}
+	
+	protected function headersToString(array $headers, $associative=true) {
+		if (!$associative) {
+			return implode("\n", $headers);
+		} else {
+			$str = '';
+			foreach ($headers as $key => $val) {
+				if (is_array($val)) {
+					foreach ($val as $v) $str .= "$key: $v\n";
+				} else {
+					$str .= "$key: $val\n";
+				}
+			}
+			return rtrim($str);
+		}
+	}
+	
+	public function get($url, $remove=false, $gzdecode=true) {
+		$url = "$url";
+		if (isset($this->requests[$url]) && isset($this->requests[$url]['body'])) {
+			$this->debug("URL already fetched - in memory ($url, effective: {$this->requests[$url]['effective_url']})");
+			$response = $this->requests[$url];
+		/*
+		} elseif ($this->isCached($url)) {
+			$this->debug("URL already fetched - in disk cache ($url)");
+			$response = $this->getCached($url);
+			$this->requests[$url] = $response;
+		*/
+		} else {
+			$this->debug("Fetching URL ($url)");
+			$this->fetchAll(array($url));
+			if (isset($this->requests[$url]) && isset($this->requests[$url]['body'])) {
+				$response = $this->requests[$url];
+			} else {
+				$this->debug("Request failed");
+				$response = false;
+			}
+		}
+		/*
+		if ($this->minimiseMemoryUse && $response) {
+			$this->cache($url);
+			unset($this->requests[$url]);
+		}
+		*/
+		if ($remove && $response) unset($this->requests[$url]);
+		if ($gzdecode && stripos($response['headers'], 'Content-Encoding: gzip')) {
+			if ($html = gzdecode($response['body'])) {
+				$response['body'] = $html;
+			}
+		}
+		return $response;
+	}
+	
+	public function parallelSupport() {
+		return class_exists('HttpRequestPool') || function_exists('curl_multi_init');
+	}
+	
+	private function headerOnlyType($headers) {
+		if (preg_match('!^Content-Type:\s*(([a-z-]+)/([^;\r\n ]+))!im', $headers, $match)) {
+			// look for full mime type (e.g. image/jpeg) or just type (e.g. image)
+			$match[1] = strtolower(trim($match[1]));
+			$match[2] = strtolower(trim($match[2]));
+			foreach (array($match[1], $match[2]) as $mime) {
+				if (in_array($mime, $this->headerOnlyTypes)) return true;
+			}
+		}
+		return false;
+	}
+	
+	private function possibleUnsupportedType($url) {
+		$path = @parse_url($url, PHP_URL_PATH);
+		if ($path && strpos($path, '.') !== false) {
+			$ext = strtolower(trim(pathinfo($path, PATHINFO_EXTENSION)));
+			return in_array($ext, $this->headerOnlyClues);
+		}
+		return false;
+	}
+}
+
+// gzdecode from http://www.php.net/manual/en/function.gzdecode.php#82930
+if (!function_exists('gzdecode')) {
+	function gzdecode($data,&$filename='',&$error='',$maxlength=null) 
+	{
+		$len = strlen($data);
+		if ($len < 18 || strcmp(substr($data,0,2),"\x1f\x8b")) {
+			$error = "Not in GZIP format.";
+			return null;  // Not GZIP format (See RFC 1952)
+		}
+		$method = ord(substr($data,2,1));  // Compression method
+		$flags  = ord(substr($data,3,1));  // Flags
+		if ($flags & 31 != $flags) {
+			$error = "Reserved bits not allowed.";
+			return null;
+		}
+		// NOTE: $mtime may be negative (PHP integer limitations)
+		$mtime = unpack("V", substr($data,4,4));
+		$mtime = $mtime[1];
+		$xfl   = substr($data,8,1);
+		$os    = substr($data,8,1);
+		$headerlen = 10;
+		$extralen  = 0;
+		$extra     = "";
+		if ($flags & 4) {
+			// 2-byte length prefixed EXTRA data in header
+			if ($len - $headerlen - 2 < 8) {
+				return false;  // invalid
+			}
+			$extralen = unpack("v",substr($data,8,2));
+			$extralen = $extralen[1];
+			if ($len - $headerlen - 2 - $extralen < 8) {
+				return false;  // invalid
+			}
+			$extra = substr($data,10,$extralen);
+			$headerlen += 2 + $extralen;
+		}
+		$filenamelen = 0;
+		$filename = "";
+		if ($flags & 8) {
+			// C-style string
+			if ($len - $headerlen - 1 < 8) {
+				return false; // invalid
+			}
+			$filenamelen = strpos(substr($data,$headerlen),chr(0));
+			if ($filenamelen === false || $len - $headerlen - $filenamelen - 1 < 8) {
+				return false; // invalid
+			}
+			$filename = substr($data,$headerlen,$filenamelen);
+			$headerlen += $filenamelen + 1;
+		}
+		$commentlen = 0;
+		$comment = "";
+		if ($flags & 16) {
+			// C-style string COMMENT data in header
+			if ($len - $headerlen - 1 < 8) {
+				return false;    // invalid
+			}
+			$commentlen = strpos(substr($data,$headerlen),chr(0));
+			if ($commentlen === false || $len - $headerlen - $commentlen - 1 < 8) {
+				return false;    // Invalid header format
+			}
+			$comment = substr($data,$headerlen,$commentlen);
+			$headerlen += $commentlen + 1;
+		}
+		$headercrc = "";
+		if ($flags & 2) {
+			// 2-bytes (lowest order) of CRC32 on header present
+			if ($len - $headerlen - 2 < 8) {
+				return false;    // invalid
+			}
+			$calccrc = crc32(substr($data,0,$headerlen)) & 0xffff;
+			$headercrc = unpack("v", substr($data,$headerlen,2));
+			$headercrc = $headercrc[1];
+			if ($headercrc != $calccrc) {
+				$error = "Header checksum failed.";
+				return false;    // Bad header CRC
+			}
+			$headerlen += 2;
+		}
+		// GZIP FOOTER
+		$datacrc = unpack("V",substr($data,-8,4));
+		$datacrc = sprintf('%u',$datacrc[1] & 0xFFFFFFFF);
+		$isize = unpack("V",substr($data,-4));
+		$isize = $isize[1];
+		// decompression:
+		$bodylen = $len-$headerlen-8;
+		if ($bodylen < 1) {
+			// IMPLEMENTATION BUG!
+			return null;
+		}
+		$body = substr($data,$headerlen,$bodylen);
+		$data = "";
+		if ($bodylen > 0) {
+			switch ($method) {
+			case 8:
+				// Currently the only supported compression method:
+				$data = gzinflate($body,$maxlength);
+				break;
+			default:
+				$error = "Unknown compression method.";
+				return false;
+			}
+		}  // zero-byte body content is allowed
+		// Verifiy CRC32
+		$crc   = sprintf("%u",crc32($data));
+		$crcOK = $crc == $datacrc;
+		$lenOK = $isize == strlen($data);
+		if (!$lenOK || !$crcOK) {
+			$error = ( $lenOK ? '' : 'Length check FAILED. ') . ( $crcOK ? '' : 'Checksum FAILED.');
+			return false;
+		}
+		return $data;
+	}
+}
\ No newline at end of file
diff --git a/inc/3rdparty/libraries/humble-http-agent/SimplePie_HumbleHttpAgent.php b/inc/3rdparty/libraries/humble-http-agent/SimplePie_HumbleHttpAgent.php
index ecd46d5f..c524a1ee 100644
--- a/inc/3rdparty/libraries/humble-http-agent/SimplePie_HumbleHttpAgent.php
+++ b/inc/3rdparty/libraries/humble-http-agent/SimplePie_HumbleHttpAgent.php
@@ -1,79 +1,78 @@
-encode($parsed['authority']), $parsed['path'], $parsed['query'], $parsed['fragment']);
-		}
-		$this->url = $url;
-		$this->useragent = $useragent;
-		if (preg_match('/^http(s)?:\/\//i', $url))
-		{
-			if (!is_array($headers))
-			{
-				$headers = array();
-			}
-			$this->method = SIMPLEPIE_FILE_SOURCE_REMOTE | SIMPLEPIE_FILE_SOURCE_CURL;
-			$headers2 = array();
-			foreach ($headers as $key => $value) {
-				$headers2[] = "$key: $value";
-			}
-			//TODO: allow for HTTP headers
-			// curl_setopt($fp, CURLOPT_HTTPHEADER, $headers2);
-
-			$response = self::$agent->get($url);
-			
-			if ($response === false || !isset($response['status_code'])) {
-				$this->error = 'failed to fetch URL';
-				$this->success = false;
-			} else {
-				// The extra lines at the end are there to satisfy SimplePie's HTTP parser.
-				// The class expects a full HTTP message, whereas we're giving it only
-				// headers - the new lines indicate the start of the body.
-				$parser = new SimplePie_HTTP_Parser($response['headers']."\r\n\r\n");
-				if ($parser->parse()) {
-					$this->headers = $parser->headers;
-					//$this->body = $parser->body;
-					$this->body = $response['body'];
-					$this->status_code = $parser->status_code;
-				}
-			}
-		}
-		else
-		{
-			$this->error = 'invalid URL';
-			$this->success = false;
-		}
-	}
-}
-?>
\ No newline at end of file
+encode($parsed['authority']), $parsed['path'], $parsed['query'], $parsed['fragment']);
+		}
+		$this->url = $url;
+		$this->useragent = $useragent;
+		if (preg_match('/^http(s)?:\/\//i', $url))
+		{
+			if (!is_array($headers))
+			{
+				$headers = array();
+			}
+			$this->method = SIMPLEPIE_FILE_SOURCE_REMOTE | SIMPLEPIE_FILE_SOURCE_CURL;
+			$headers2 = array();
+			foreach ($headers as $key => $value) {
+				$headers2[] = "$key: $value";
+			}
+			//TODO: allow for HTTP headers
+			// curl_setopt($fp, CURLOPT_HTTPHEADER, $headers2);
+
+			$response = self::$agent->get($url);
+			
+			if ($response === false || !isset($response['status_code'])) {
+				$this->error = 'failed to fetch URL';
+				$this->success = false;
+			} else {
+				// The extra lines at the end are there to satisfy SimplePie's HTTP parser.
+				// The class expects a full HTTP message, whereas we're giving it only
+				// headers - the new lines indicate the start of the body.
+				$parser = new SimplePie_HTTP_Parser($response['headers']."\r\n\r\n");
+				if ($parser->parse()) {
+					$this->headers = $parser->headers;
+					//$this->body = $parser->body;
+					$this->body = $response['body'];
+					$this->status_code = $parser->status_code;
+				}
+			}
+		}
+		else
+		{
+			$this->error = 'invalid URL';
+			$this->success = false;
+		}
+	}
+}
\ No newline at end of file
diff --git a/inc/3rdparty/libraries/language-detect/LanguageDetect.php b/inc/3rdparty/libraries/language-detect/LanguageDetect.php
index 09b11546..382d869c 100644
--- a/inc/3rdparty/libraries/language-detect/LanguageDetect.php
+++ b/inc/3rdparty/libraries/language-detect/LanguageDetect.php
@@ -6,23 +6,24 @@
  * Attempts to detect the language of a sample of text by correlating ranked
  * 3-gram frequencies to a table of 3-gram frequencies of known languages.
  *
- * Implements a version of a technique originally proposed by Cavnar & Trenkle 
- * (1994): "N-Gram-Based Text Categorization" 
+ * Implements a version of a technique originally proposed by Cavnar & Trenkle
+ * (1994): "N-Gram-Based Text Categorization"
  *
- * PHP versions 4 and 5
+ * PHP version 5
  *
- * @category   Text
- * @package    Text_LanguageDetect
- * @author     Nicholas Pisarro 
- * @copyright  2005-2006 Nicholas Pisarro
- * @license    http://www.debian.org/misc/bsd.license BSD
- * @version    CVS: $Id: LanguageDetect.php,v 1.20 2008/07/01 02:09:15 taak Exp $
- * @link       http://pear.php.net/package/Text_LanguageDetect/
- * @link       http://langdetect.blogspot.com/
+ * @category  Text
+ * @package   Text_LanguageDetect
+ * @author    Nicholas Pisarro 
+ * @copyright 2005-2006 Nicholas Pisarro
+ * @license   http://www.debian.org/misc/bsd.license BSD
+ * @version   SVN: $Id: LanguageDetect.php 322353 2012-01-16 08:41:43Z cweiske $
+ * @link      http://pear.php.net/package/Text_LanguageDetect/
+ * @link      http://langdetect.blogspot.com/
  */
 
-//require_once 'PEAR.php';
-require_once 'Parser.php';
+require_once 'LanguageDetect/Exception.php';
+require_once 'LanguageDetect/Parser.php';
+require_once 'LanguageDetect/ISO639.php';
 
 /**
  * Language detection class
@@ -41,9 +42,10 @@ require_once 'Parser.php';
  *
  * echo "Supported languages:\n";
  *
- * $langs = $l->getLanguages();
- * if (PEAR::isError($langs)) {
- *     die($langs->getMessage());
+ * try {
+ *     $langs = $l->getLanguages();
+ * } catch (Text_LanguageDetect_Exception $e) {
+ *     die($e->getMessage());
  * }
  *
  * sort($langs);
@@ -54,38 +56,38 @@ require_once 'Parser.php';
  * }
  * 
  *
- * @category   Text
- * @package    Text_LanguageDetect
- * @author     Nicholas Pisarro 
- * @copyright  2005 Nicholas Pisarro
- * @license    http://www.debian.org/misc/bsd.license BSD
- * @version    Release: @package_version@
- * @todo       allow users to generate their own language models
+ * @category  Text
+ * @package   Text_LanguageDetect
+ * @author    Nicholas Pisarro 
+ * @copyright 2005 Nicholas Pisarro
+ * @license   http://www.debian.org/misc/bsd.license BSD
+ * @version   Release: @package_version@
+ * @link      http://pear.php.net/package/Text_LanguageDetect/
+ * @todo      allow users to generate their own language models
  */
- 
 class Text_LanguageDetect
 {
-    /** 
+    /**
      * The filename that stores the trigram data for the detector
      *
-     * If this value starts with a slash (/) or a dot (.) the value of 
+     * If this value starts with a slash (/) or a dot (.) the value of
      * $this->_data_dir will be ignored
-     * 
+     *
      * @var      string
      * @access   private
      */
-    var $_db_filename = './lang.dat';
+    var $_db_filename = 'lang.dat';
 
     /**
      * The filename that stores the unicode block definitions
      *
-     * If this value starts with a slash (/) or a dot (.) the value of 
+     * If this value starts with a slash (/) or a dot (.) the value of
      * $this->_data_dir will be ignored
-     * 
+     *
      * @var string
      * @access private
      */
-    var $_unicode_db_filename = './unicode_blocks.dat';
+    var $_unicode_db_filename = 'unicode_blocks.dat';
 
     /**
      * The data directory
@@ -99,11 +101,8 @@ class Text_LanguageDetect
 
     /**
      * The trigram data for comparison
-     * 
-     * Will be loaded on start from $this->_db_filename
      *
-     * May be set to a PEAR_Error object if there is an error during its 
-     * initialization
+     * Will be loaded on start from $this->_db_filename
      *
      * @var      array
      * @access   private
@@ -120,7 +119,7 @@ class Text_LanguageDetect
 
     /**
      * The size of the trigram data arrays
-     * 
+     *
      * @var      int
      * @access   private
      */
@@ -140,7 +139,7 @@ class Text_LanguageDetect
 
     /**
      * Whether or not to simulate perl's Language::Guess exactly
-     * 
+     *
      * @access  private
      * @var     bool
      * @see     setPerlCompatible()
@@ -164,19 +163,25 @@ class Text_LanguageDetect
      */
     var $_clusters;
 
+    /**
+     * Which type of "language names" are accepted and returned:
+     *
+     * 0 - language name ("english")
+     * 2 - 2-letter ISO 639-1 code ("en")
+     * 3 - 3-letter ISO 639-2 code ("eng")
+     */
+    var $_name_mode = 0;
+
     /**
      * Constructor
      *
      * Will attempt to load the language database. If it fails, you will get
-     * a PEAR_Error object returned when you try to use detect()
-     *
+     * an exception.
      */
-    function Text_LanguageDetect($db=null, $unicode_db=null)
+    function __construct()
     {
-		if (isset($db)) $this->_db_filename = $db;
-		if (isset($unicode_db)) $this->_unicode_db_filename = $unicode_db;
-		
         $data = $this->_readdb($this->_db_filename);
+        $this->_checkTrigram($data['trigram']);
         $this->_lang_db = $data['trigram'];
 
         if (isset($data['trigram-unicodemap'])) {
@@ -186,29 +191,32 @@ class Text_LanguageDetect
         // Not yet implemented:
         if (isset($data['trigram-clusters'])) {
             $this->_clusters = $data['trigram-clusters'];
-        }		
+        }
     }
 
     /**
      * Returns the path to the location of the database
      *
-     * @access    private
-     * @return    string    expected path to the language model database
+     * @param string $fname File name to load
+     *
+     * @return string expected path to the language model database
+     * @access private
      */
     function _get_data_loc($fname)
     {
-        return $fname;
+        return dirname(__FILE__).'/'.$fname;
     }
 
     /**
      * Loads the language trigram database from filename
      *
      * Trigram datbase should be a serialize()'d array
-     * 
-     * @access    private
-     * @param     string      $fname   the filename where the data is stored
-     * @return    array                the language model data
-     * @throws    PEAR_Error
+     *
+     * @param string $fname the filename where the data is stored
+     *
+     * @return array the language model data
+     * @throws Text_LanguageDetect_Exception
+     * @access private
      */
     function _readdb($fname)
     {
@@ -217,79 +225,74 @@ class Text_LanguageDetect
 
         // input check
         if (!file_exists($fname)) {
-            throw new Exception('Language database does not exist.');
+            throw new Text_LanguageDetect_Exception(
+                'Language database does not exist: ' . $fname,
+                Text_LanguageDetect_Exception::DB_NOT_FOUND
+            );
         } elseif (!is_readable($fname)) {
-            throw new Exception('Language database is not readable.');
+            throw new Text_LanguageDetect_Exception(
+                'Language database is not readable: ' . $fname,
+                Text_LanguageDetect_Exception::DB_NOT_READABLE
+            );
         }
 
-        if (function_exists('file_get_contents')) {
-            return unserialize(file_get_contents($fname));
-        } else {
-            // if you don't have file_get_contents(), 
-            // then this is the next fastest way
-            ob_start();
-            readfile($fname);
-            $contents = ob_get_contents();
-            ob_end_clean();
-            return unserialize($contents);
-        }
+        return unserialize(file_get_contents($fname));
     }
 
 
     /**
      * Checks if this object is ready to detect languages
-     * 
-     * @access   private
-     * @param    mixed   &$err  error object to be returned by reference, if any
-     * @return   bool           true if no errors
+     *
+     * @param array $trigram Trigram data from database
+     *
+     * @return void
+     * @access private
      */
-    function _setup_ok(&$err)
+    function _checkTrigram($trigram)
     {
-        if (!is_array($this->_lang_db)) {
+        if (!is_array($trigram)) {
             if (ini_get('magic_quotes_runtime')) {
-                throw new Exception('Error loading database. Try turning magic_quotes_runtime off.');
-            } else {
-                throw new Exception('Language database is not an array.');
+                throw new Text_LanguageDetect_Exception(
+                    'Error loading database. Try turning magic_quotes_runtime off.',
+                    Text_LanguageDetect_Exception::MAGIC_QUOTES
+                );
             }
-            return false;
-
-        } elseif (empty($this->_lang_db)) {
-            throw new Exception('Language database has no elements.');
-            return false;
-
-        } else {
-            return true;
+            throw new Text_LanguageDetect_Exception(
+                'Language database is not an array.',
+                Text_LanguageDetect_Exception::DB_NOT_ARRAY
+            );
+        } elseif (empty($trigram)) {
+            throw new Text_LanguageDetect_Exception(
+                'Language database has no elements.',
+                Text_LanguageDetect_Exception::DB_EMPTY
+            );
         }
     }
 
     /**
      * Omits languages
      *
-     * Pass this function the name of or an array of names of 
+     * Pass this function the name of or an array of names of
      * languages that you don't want considered
      *
-     * If you're only expecting a limited set of languages, this can greatly 
+     * If you're only expecting a limited set of languages, this can greatly
      * speed up processing
      *
-     * @access   public
-     * @param    mixed  $omit_list      language name or array of names to omit
-     * @param    bool   $include_only   if true will include (rather than 
-     *                                  exclude) only those in the list
-     * @return   int                    number of languages successfully deleted
-     * @throws   PEAR_Error
+     * @param mixed $omit_list    language name or array of names to omit
+     * @param bool  $include_only if true will include (rather than
+     *                            exclude) only those in the list
+     *
+     * @return int number of languages successfully deleted
+     * @throws Text_LanguageDetect_Exception
      */
-    function omitLanguages($omit_list, $include_only = false)
+    public function omitLanguages($omit_list, $include_only = false)
     {
-
-        // setup check
-        if (!$this->_setup_ok($err)) {
-            return $err;
-        }
-
         $deleted = 0;
 
-        // deleting the given languages
+        $omit_list = $this->_convertFromNameMode($omit_list);
+
         if (!$include_only) {
+            // deleting the given languages
             if (!is_array($omit_list)) {
                 $omit_list = strtolower($omit_list); // case desensitize
                 if (isset($this->_lang_db[$omit_list])) {
@@ -301,12 +304,12 @@ class Text_LanguageDetect
                     if (isset($this->_lang_db[$omit_lang])) {
                         unset($this->_lang_db[$omit_lang]);
                         $deleted++;
-                    } 
+                    }
                 }
             }
 
-        // deleting all except the given languages
         } else {
+            // deleting all except the given languages
             if (!is_array($omit_list)) {
                 $omit_list = array($omit_list);
             }
@@ -327,7 +330,7 @@ class Text_LanguageDetect
         // reset the cluster cache if the number of languages changes
         // this will then have to be recalculated
         if (isset($this->_clusters) && $deleted > 0) {
-            unset($this->_clusters);
+            $this->_clusters = null;
         }
 
         return $deleted;
@@ -339,49 +342,40 @@ class Text_LanguageDetect
      *
      * @access public
      * @return int            the number of languages
-     * @throws PEAR_Error
+     * @throws   Text_LanguageDetect_Exception
      */
     function getLanguageCount()
     {
-        if (!$this->_setup_ok($err)) {
-            return $err;
-        } else {
-            return count($this->_lang_db);
-        }
+        return count($this->_lang_db);
     }
 
     /**
-     * Returns true if a given language exists
+     * Checks if the language with the given name exists in the database
      *
-     * If passed an array of names, will return true only if all exist
+     * @param mixed $lang Language name or array of language names
      *
-     * @access    public
-     * @param     mixed       $lang    language name or array of language names
-     * @return    bool                 true if language model exists
-     * @throws    PEAR_Error
+     * @return bool true if language model exists
      */
-    function languageExists($lang)
+    public function languageExists($lang)
     {
-        if (!$this->_setup_ok($err)) {
-            return $err;
-        } else {
-            // string
-            if (is_string($lang)) {
-                return isset($this->_lang_db[strtolower($lang)]);
-
-            // array
-            } elseif (is_array($lang)) {
-                foreach ($lang as $test_lang) {
-                    if (!isset($this->_lang_db[strtolower($test_lang)])) {
-                        return false;
-                    } 
-                }
-                return true;
+        $lang = $this->_convertFromNameMode($lang);
 
-            // other (error)
-            } else {
-                throw new Exception('Unknown type passed to languageExists()');
+        if (is_string($lang)) {
+            return isset($this->_lang_db[strtolower($lang)]);
+
+        } elseif (is_array($lang)) {
+            foreach ($lang as $test_lang) {
+                if (!isset($this->_lang_db[strtolower($test_lang)])) {
+                    return false;
+                }
             }
+            return true;
+
+        } else {
+            throw new Text_LanguageDetect_Exception(
+                'Unsupported parameter type passed to languageExists()',
+                Text_LanguageDetect_Exception::PARAM_TYPE
+            );
         }
     }
 
@@ -389,25 +383,24 @@ class Text_LanguageDetect
      * Returns the list of detectable languages
      *
      * @access public
-     * @return array        the names of the languages known to this object
-     * @throws PEAR_Error
+     * @return array        the names of the languages known to this object<<<<<<<
+     * @throws   Text_LanguageDetect_Exception
      */
     function getLanguages()
     {
-        if (!$this->_setup_ok($err)) {
-            return $err;
-        } else {
-            return array_keys($this->_lang_db);
-        }
+        return $this->_convertToNameMode(
+            array_keys($this->_lang_db)
+        );
     }
 
     /**
      * Make this object behave like Language::Guess
-     * 
-     * @access    public
-     * @param     bool     $setting     false to turn off perl compatibility
+     *
+     * @param bool $setting false to turn off perl compatibility
+     *
+     * @return void
      */
-    function setPerlCompatible($setting = true)
+    public function setPerlCompatible($setting = true)
     {
         if (is_bool($setting)) { // input check
             $this->_perl_compatible = $setting;
@@ -421,6 +414,21 @@ class Text_LanguageDetect
 
     }
 
+    /**
+     * Sets the way how language names are accepted and returned.
+     *
+     * @param integer $name_mode One of the following modes:
+     *                           0 - language name ("english")
+     *                           2 - 2-letter ISO 639-1 code ("en")
+     *                           3 - 3-letter ISO 639-2 code ("eng")
+     *
+     * @return void
+     */
+    function setNameMode($name_mode)
+    {
+        $this->_name_mode = $name_mode;
+    }
+
     /**
      * Whether to use unicode block ranges in detection
      *
@@ -429,10 +437,11 @@ class Text_LanguageDetect
      * in languages that use latin scripts. In other cases it should speed up
      * detection noticeably.
      *
-     * @access  public
-     * @param   bool    $setting    false to turn off
+     * @param bool $setting false to turn off
+     *
+     * @return void
      */
-    function useUnicodeBlocks($setting = true)
+    public function useUnicodeBlocks($setting = true)
     {
         if (is_bool($setting)) {
             $this->_use_unicode_narrowing = $setting;
@@ -442,15 +451,15 @@ class Text_LanguageDetect
     /**
      * Converts a piece of text into trigrams
      *
-     * Superceded by the Text_LanguageDetect_Parser class 
+     * @param string $text text to convert
      *
-     * @access    private
-     * @param     string    $text    text to convert
-     * @return    array              array of trigram frequencies
+     * @return     array array of trigram frequencies
+     * @access     private
+     * @deprecated Superceded by the Text_LanguageDetect_Parser class
      */
     function _trigram($text)
     {
-        $s = new Text_LanguageDetect_Parser($text, $this->_db_filename, $this->_unicode_db_filename);
+        $s = new Text_LanguageDetect_Parser($text);
         $s->prepareTrigram();
         $s->prepareUnicode(false);
         $s->setPadStart(!$this->_perl_compatible);
@@ -463,11 +472,12 @@ class Text_LanguageDetect
      *
      * Thresholds (cuts off) the list at $this->_threshold
      *
-     * @access    protected
-     * @param     array     $arr     array of trgram 
-     * @return    array              ranks of trigrams
+     * @param array $arr array of trigram
+     *
+     * @return array ranks of trigrams
+     * @access protected
      */
-    function _arr_rank(&$arr)
+    function _arr_rank($arr)
     {
 
         // sorts alphabetically first as a standard way of breaking rank ties
@@ -494,14 +504,17 @@ class Text_LanguageDetect
 
     /**
      * Sorts an array by value breaking ties alphabetically
-     * 
-     * @access   private
-     * @param    array     &$arr     the array to sort
+     *
+     * @param array &$arr the array to sort
+     *
+     * @return void
+     * @access private
      */
     function _bub_sort(&$arr)
     {
         // should do the same as this perl statement:
-        // sort { $trigrams{$b} == $trigrams{$a} ?  $a cmp $b : $trigrams{$b} <=> $trigrams{$a} }
+        // sort { $trigrams{$b} == $trigrams{$a}
+        //   ?  $a cmp $b : $trigrams{$b} <=> $trigrams{$a} }
 
         // needs to sort by both key and value at once
         // using the key to break ties for the value
@@ -528,13 +541,14 @@ class Text_LanguageDetect
     /**
      * Sort function used by bubble sort
      *
-     * Callback function for usort(). 
+     * Callback function for usort().
      *
-     * @access   private
-     * @param    array        first param passed by usort()
-     * @param    array        second param passed by usort()
-     * @return   int          1 if $a is greater, -1 if not
-     * @see      _bub_sort()
+     * @param array $a first param passed by usort()
+     * @param array $b second param passed by usort()
+     *
+     * @return int 1 if $a is greater, -1 if not
+     * @see    _bub_sort()
+     * @access private
      */
     function _sort_func($a, $b)
     {
@@ -542,12 +556,12 @@ class Text_LanguageDetect
         list($a_key, $a_value) = $a;
         list($b_key, $b_value) = $b;
 
-        // if the values are the same, break ties using the key
         if ($a_value == $b_value) {
+            // if the values are the same, break ties using the key
             return strcmp($a_key, $b_key);
 
-        // if not, just sort normally
         } else {
+            // if not, just sort normally
             if ($a_value > $b_value) {
                 return -1;
             } else {
@@ -559,23 +573,24 @@ class Text_LanguageDetect
     }
 
     /**
-     * Calculates a linear rank-order distance statistic between two sets of 
+     * Calculates a linear rank-order distance statistic between two sets of
      * ranked trigrams
      *
-     * Sums the differences in rank for each trigram. If the trigram does not 
+     * Sums the differences in rank for each trigram. If the trigram does not
      * appear in both, consider it a difference of $this->_threshold.
      *
      * This distance measure was proposed by Cavnar & Trenkle (1994). Despite
      * its simplicity it has been shown to be highly accurate for language
      * identification tasks.
      *
-     * @access  private
-     * @param   array    $arr1  the reference set of trigram ranks
-     * @param   array    $arr2  the target set of trigram ranks
-     * @return  int             the sum of the differences between the ranks of
-     *                          the two trigram sets
+     * @param array $arr1 the reference set of trigram ranks
+     * @param array $arr2 the target set of trigram ranks
+     *
+     * @return int the sum of the differences between the ranks of
+     *             the two trigram sets
+     * @access private
      */
-    function _distance(&$arr1, &$arr2)
+    function _distance($arr1, $arr2)
     {
         $sumdist = 0;
 
@@ -598,14 +613,15 @@ class Text_LanguageDetect
 
     /**
      * Normalizes the score returned by _distance()
-     * 
+     *
      * Different if perl compatible or not
      *
-     * @access    private
-     * @param     int    $score          the score from _distance()
-     * @param     int    $base_count     the number of trigrams being considered
-     * @return    float                  the normalized score
-     * @see       _distance()
+     * @param int $score      the score from _distance()
+     * @param int $base_count the number of trigrams being considered
+     *
+     * @return float the normalized score
+     * @see    _distance()
+     * @access private
      */
     function _normalize_score($score, $base_count = null)
     {
@@ -630,29 +646,24 @@ class Text_LanguageDetect
      *
      * If perl compatible, the score is 300-0, 0 being most similar.
      * Otherwise, it's 0-1 with 1 being most similar.
-     * 
+     *
      * The $sample text should be at least a few sentences in length;
      * should be ascii-7 or utf8 encoded, if another and the mbstring extension
      * is present it will try to detect and convert. However, experience has
-     * shown that mb_detect_encoding() *does not work very well* with at least 
+     * shown that mb_detect_encoding() *does not work very well* with at least
      * some types of encoding.
      *
-     * @access  public
-     * @param   string  $sample a sample of text to compare.
-     * @param   int     $limit  if specified, return an array of the most likely
-     *                           $limit languages and their scores.
-     * @return  mixed       sorted array of language scores, blank array if no 
-     *                      useable text was found, or PEAR_Error if error 
-     *                      with the object setup
-     * @see     _distance()
-     * @throws  PEAR_Error
+     * @param string $sample a sample of text to compare.
+     * @param int    $limit  if specified, return an array of the most likely
+     *                       $limit languages and their scores.
+     *
+     * @return mixed sorted array of language scores, blank array if no
+     *               useable text was found
+     * @see    _distance()
+     * @throws Text_LanguageDetect_Exception
      */
-    function detect($sample, $limit = 0)
+    public function detect($sample, $limit = 0)
     {
-        if (!$this->_setup_ok($err)) {
-            return $err;
-        }
-
         // input check
         if (!Text_LanguageDetect_Parser::validateString($sample)) {
             return array();
@@ -660,36 +671,27 @@ class Text_LanguageDetect
 
         // check char encoding
         // (only if mbstring extension is compiled and PHP > 4.0.6)
-        if (function_exists('mb_detect_encoding') 
-            && function_exists('mb_convert_encoding')) {
-
+        if (function_exists('mb_detect_encoding')
+            && function_exists('mb_convert_encoding')
+        ) {
             // mb_detect_encoding isn't very reliable, to say the least
-            // detection should still work with a sufficient sample of ascii characters
+            // detection should still work with a sufficient sample
+            //  of ascii characters
             $encoding = mb_detect_encoding($sample);
 
             // mb_detect_encoding() will return FALSE if detection fails
             // don't attempt conversion if that's the case
-            if ($encoding != 'ASCII' && $encoding != 'UTF-8' && $encoding !== false) {
-            
-                if (function_exists('mb_list_encodings')) {
- 
-                    // verify the encoding exists in mb_list_encodings
-                    if (in_array($encoding, mb_list_encodings())) {
-                        $sample = mb_convert_encoding($sample, 'UTF-8', $encoding);
-                    }
-
-                    // if the previous condition failed:
-                    // somehow we detected an encoding that also we don't support
-
-                } else {
-                    // php 4 doesnt have mb_list_encodings()
-                    // so attempt with error suppression
-                    $sample = @mb_convert_encoding($sample, 'UTF-8', $encoding);
+            if ($encoding != 'ASCII' && $encoding != 'UTF-8'
+                && $encoding !== false
+            ) {
+                // verify the encoding exists in mb_list_encodings
+                if (in_array($encoding, mb_list_encodings())) {
+                    $sample = mb_convert_encoding($sample, 'UTF-8', $encoding);
                 }
             }
         }
 
-        $sample_obj = new Text_LanguageDetect_Parser($sample, $this->_db_filename, $this->_unicode_db_filename);
+        $sample_obj = new Text_LanguageDetect_Parser($sample);
         $sample_obj->prepareTrigram();
         if ($this->_use_unicode_narrowing) {
             $sample_obj->prepareUnicode();
@@ -713,7 +715,10 @@ class Text_LanguageDetect
             if (is_array($blocks)) {
                 $present_blocks = array_keys($blocks);
             } else {
-                throw new Exception('Error during block detection');
+                throw new Text_LanguageDetect_Exception(
+                    'Error during block detection',
+                    Text_LanguageDetect_Exception::BLOCK_DETECTION
+                );
             }
 
             $possible_langs = array();
@@ -731,30 +736,30 @@ class Text_LanguageDetect
             }
 
             // could also try an intersect operation rather than a union
-            // in other words, choose languages whose trigrams contain 
+            // in other words, choose languages whose trigrams contain
             // ALL of the unicode blocks found in this sample
             // would improve speed but would be completely thrown off by an
             // unexpected character, like an umlaut appearing in english text
 
             $possible_langs = array_intersect(
-                        array_keys($this->_lang_db),
-                        array_unique($possible_langs)
+                array_keys($this->_lang_db),
+                array_unique($possible_langs)
             );
 
-            // needs to intersect it with the keys of _lang_db in case 
+            // needs to intersect it with the keys of _lang_db in case
             // languages have been omitted
 
-        // or just try 'em all
         } else {
+            // or just try 'em all
             $possible_langs = array_keys($this->_lang_db);
         }
 
 
         foreach ($possible_langs as $lang) {
-            $scores[$lang] =
-                $this->_normalize_score(
-                        $this->_distance($this->_lang_db[$lang], $trigram_freqs),
-                        $trigram_count);
+            $scores[$lang] = $this->_normalize_score(
+                $this->_distance($this->_lang_db[$lang], $trigram_freqs),
+                $trigram_count
+            );
         }
 
         unset($sample_obj);
@@ -772,7 +777,6 @@ class Text_LanguageDetect
             $limited_scores = array();
 
             $i = 0;
-
             foreach ($scores as $key => $value) {
                 if ($i++ >= $limit) {
                     break;
@@ -781,9 +785,9 @@ class Text_LanguageDetect
                 $limited_scores[$key] = $value;
             }
 
-            return $limited_scores;
+            return $this->_convertToNameMode($limited_scores, true);
         } else {
-            return $scores;
+            return $this->_convertToNameMode($scores, true);
         }
     }
 
@@ -791,35 +795,33 @@ class Text_LanguageDetect
      * Returns only the most similar language to the text sample
      *
      * Calls $this->detect() and returns only the top result
-     * 
-     * @access   public
-     * @param    string    $sample    text to detect the language of
-     * @return   string               the name of the most likely language
-     *                                or null if no language is similar
-     * @see      detect()
-     * @throws   PEAR_Error
+     *
+     * @param string $sample text to detect the language of
+     *
+     * @return string the name of the most likely language
+     *                or null if no language is similar
+     * @see    detect()
+     * @throws Text_LanguageDetect_Exception
      */
-    function detectSimple($sample)
+    public function detectSimple($sample)
     {
         $scores = $this->detect($sample, 1);
 
         // if top language has the maximum possible score,
         // then the top score will have been picked at random
-        if (    !is_array($scores) 
-                || empty($scores) 
-                || current($scores) == $this->_max_score) {
-
+        if (!is_array($scores) || empty($scores)
+            || current($scores) == $this->_max_score
+        ) {
             return null;
-
         } else {
-            return ucfirst(key($scores));
+            return key($scores);
         }
     }
 
     /**
      * Returns an array containing the most similar language and a confidence
      * rating
-     * 
+     *
      * Confidence is a simple measure calculated from the similarity score
      * minus the similarity score from the next most similar language
      * divided by the highest possible score. Languages that have closely
@@ -827,46 +829,43 @@ class Text_LanguageDetect
      * confidence scores.
      *
      * The similarity score answers the question "How likely is the text the
-     * returned language regardless of the other languages considered?" The 
+     * returned language regardless of the other languages considered?" The
      * confidence score is one way of answering the question "how likely is the
      * text the detected language relative to the rest of the language model
      * set?"
      *
      * To see how similar languages are a priori, see languageSimilarity()
-     * 
-     * @access   public
-     * @param    string    $sample    text for which language will be detected
-     * @return   array     most similar language, score and confidence rating
-     *                     or null if no language is similar
-     * @see      detect()
-     * @throws   PEAR_Error
+     *
+     * @param string $sample text for which language will be detected
+     *
+     * @return array most similar language, score and confidence rating
+     *               or null if no language is similar
+     * @see    detect()
+     * @throws Text_LanguageDetect_Exception
      */
-    function detectConfidence($sample)
+    public function detectConfidence($sample)
     {
         $scores = $this->detect($sample, 2);
 
-        // if most similar language has the max score, it 
+        // if most similar language has the max score, it
         // will have been picked at random
-        if (    !is_array($scores) 
-                || empty($scores) 
-                || current($scores) == $this->_max_score) {
-
+        if (!is_array($scores) || empty($scores)
+            || current($scores) == $this->_max_score
+        ) {
             return null;
         }
 
-        $arr['language'] = ucfirst(key($scores));
+        $arr['language'] = key($scores);
         $arr['similarity'] = current($scores);
         if (next($scores) !== false) { // if false then no next element
             // the goal is to return a higher value if the distance between
             // the similarity of the first score and the second score is high
 
             if ($this->_perl_compatible) {
-
-                $arr['confidence'] =
-                    (current($scores) - $arr['similarity']) / $this->_max_score;
+                $arr['confidence'] = (current($scores) - $arr['similarity'])
+                    / $this->_max_score;
 
             } else {
-
                 $arr['confidence'] = $arr['similarity'] - current($scores);
 
             }
@@ -882,32 +881,26 @@ class Text_LanguageDetect
      * Returns the distribution of unicode blocks in a given utf8 string
      *
      * For the block name of a single char, use unicodeBlockName()
-     * 
-     * @access public
-     * @param string $str input string. Must be ascii or utf8
-     * @param bool $skip_symbols if true, skip ascii digits, symbols and 
-     *                           non-printing characters. Includes spaces,
-     *                           newlines and common punctutation characters.
+     *
+     * @param string $str          input string. Must be ascii or utf8
+     * @param bool   $skip_symbols if true, skip ascii digits, symbols and
+     *                             non-printing characters. Includes spaces,
+     *                             newlines and common punctutation characters.
+     *
      * @return array
-     * @throws PEAR_Error
+     * @throws Text_LanguageDetect_Exception
      */
-    function detectUnicodeBlocks($str, $skip_symbols)
+    public function detectUnicodeBlocks($str, $skip_symbols)
     {
-        // input check
-        if (!is_bool($skip_symbols)) {
-            throw new Exception('Second parameter must be boolean');
-        } 
-
-        if (!is_string($str)) {
-            throw new Exception('First parameter was not a string');
-        }
+        $skip_symbols = (bool)$skip_symbols;
+        $str          = (string)$str;
 
-        $sample_obj = new Text_LanguageDetect_Parser($str, $this->_db_filename, $this->_unicode_db_filename);
+        $sample_obj = new Text_LanguageDetect_Parser($str);
         $sample_obj->prepareUnicode();
         $sample_obj->prepareTrigram(false);
         $sample_obj->setUnicodeSkipSymbols($skip_symbols);
         $sample_obj->analyze();
-        $blocks =& $sample_obj->getUnicodeBlocks();
+        $blocks = $sample_obj->getUnicodeBlocks();
         unset($sample_obj);
         return $blocks;
     }
@@ -915,38 +908,37 @@ class Text_LanguageDetect
     /**
      * Returns the block name for a given unicode value
      *
-     * If passed a string, will assume it is being passed a UTF8-formatted 
+     * If passed a string, will assume it is being passed a UTF8-formatted
      * character and will automatically convert. Otherwise it will assume it
      * is being passed a numeric unicode value.
      *
      * Make sure input is of the correct type!
      *
-     * @access public
      * @param mixed $unicode unicode value or utf8 char
+     *
      * @return mixed the block name string or false if not found
-     * @throws PEAR_Error
+     * @throws Text_LanguageDetect_Exception
      */
-    function unicodeBlockName($unicode) {
+    public function unicodeBlockName($unicode)
+    {
         if (is_string($unicode)) {
             // assume it is being passed a utf8 char, so convert it
-
-            // input check
-            if ($this->utf8strlen($unicode) > 1) {
-                throw new Exception('Pass this function only a single char');
+            if (self::utf8strlen($unicode) > 1) {
+                throw new Text_LanguageDetect_Exception(
+                    'Pass a single char only to this method',
+                    Text_LanguageDetect_Exception::PARAM_TYPE
+                );
             }
-
             $unicode = $this->_utf8char2unicode($unicode);
 
-            if ($unicode == -1) {
-                throw new Exception('Malformatted char');
-            }
-
-        // input check
         } elseif (!is_int($unicode)) {
-            throw new Exception('Input must be of type string or int.');
+            throw new Text_LanguageDetect_Exception(
+                'Input must be of type string or int.',
+                Text_LanguageDetect_Exception::PARAM_TYPE
+            );
         }
 
-        $blocks =& $this->_read_unicode_block_db();
+        $blocks = $this->_read_unicode_block_db();
 
         $result = $this->_unicode_block_name($unicode, $blocks);
 
@@ -964,14 +956,17 @@ class Text_LanguageDetect
      * the public interface for this function, which does input checks which
      * this function omits for speed.
      *
-     * @access  protected
-     * @param   int     $unicode the unicode value
-     * @param   array   &$blocks the block database
-     * @param   int     $block_count the number of defined blocks in the database
-     * @see     unicodeBlockName()
+     * @param int   $unicode     the unicode value
+     * @param array $blocks      the block database
+     * @param int   $block_count the number of defined blocks in the database
+     *
+     * @return mixed Block name, -1 if it failed
+     * @see    unicodeBlockName()
+     * @access protected
      */
-    function _unicode_block_name($unicode, &$blocks, $block_count = -1) {
-        // for a reference, see 
+    function _unicode_block_name($unicode, $blocks, $block_count = -1)
+    {
+        // for a reference, see
         // http://www.unicode.org/Public/UNIDATA/Blocks.txt
 
         // assume that ascii characters are the most common
@@ -994,35 +989,36 @@ class Text_LanguageDetect
         while ($low <= $high) {
             $mid = floor(($low + $high) / 2);
 
-            // if it's lower than the lower bound
             if ($unicode < $blocks[$mid][0]) {
+                // if it's lower than the lower bound
                 $high = $mid - 1;
 
-            // if it's higher than the upper bound
             } elseif ($unicode > $blocks[$mid][1]) {
+                // if it's higher than the upper bound
                 $low = $mid + 1;
 
-            // found it
             } else {
+                // found it
                 return $blocks[$mid];
             }
         }
 
-        // failed to find the block 
+        // failed to find the block
         return -1;
 
-        // todo: differentiate when it's out of range or when it falls 
+        // todo: differentiate when it's out of range or when it falls
         //       into an unassigned range?
     }
 
     /**
      * Brings up the unicode block database
      *
-     * @access protected
      * @return array the database of unicode block definitions
-     * @throws PEAR_Error
+     * @throws Text_LanguageDetect_Exception
+     * @access protected
      */
-    function &_read_unicode_block_db() {
+    function _read_unicode_block_db()
+    {
         // since the unicode definitions are always going to be the same,
         // might as well share the memory for the db with all other instances
         // of this class
@@ -1037,29 +1033,27 @@ class Text_LanguageDetect
 
     /**
      * Calculate the similarities between the language models
-     * 
+     *
      * Use this function to see how similar languages are to each other.
      *
      * If passed 2 language names, will return just those languages compared.
      * If passed 1 language name, will return that language compared to
      * all others.
-     * If passed none, will return an array of every language model compared 
+     * If passed none, will return an array of every language model compared
      * to every other one.
      *
-     * @access  public
-     * @param   string   $lang1   the name of the first language to be compared
-     * @param   string   $lang2   the name of the second language to be compared
-     * @return  array    scores of every language compared
-     *                   or the score of just the provided languages
-     *                   or null if one of the supplied languages does not exist
-     * @throws  PEAR_Error
+     * @param string $lang1 the name of the first language to be compared
+     * @param string $lang2 the name of the second language to be compared
+     *
+     * @return array scores of every language compared
+     *               or the score of just the provided languages
+     *               or null if one of the supplied languages does not exist
+     * @throws Text_LanguageDetect_Exception
      */
-    function languageSimilarity($lang1 = null, $lang2 = null)
+    public function languageSimilarity($lang1 = null, $lang2 = null)
     {
-        if (!$this->_setup_ok($err)) {
-            return $err;
-        }
-
+        $lang1 = $this->_convertFromNameMode($lang1);
+        $lang2 = $this->_convertFromNameMode($lang2);
         if ($lang1 != null) {
             $lang1 = strtolower($lang1);
 
@@ -1069,12 +1063,8 @@ class Text_LanguageDetect
             }
 
             if ($lang2 != null) {
-
-                // can't only set the second param
-                if ($lang1 == null) {
-                    return null;
-                // check if language model exists
-                } elseif (!isset($this->_lang_db[$lang2])) {
+                if (!isset($this->_lang_db[$lang2])) {
+                    // check if language model exists
                     return null;
                 }
 
@@ -1088,14 +1078,15 @@ class Text_LanguageDetect
                     )
                 );
 
-
-            // compare just $lang1 to all languages
             } else {
+                // compare just $lang1 to all languages
                 $return_arr = array();
                 foreach ($this->_lang_db as $key => $value) {
-                    if ($key != $lang1) { // don't compare a language to itself
+                    if ($key != $lang1) {
+                        // don't compare a language to itself
                         $return_arr[$key] = $this->_normalize_score(
-                            $this->_distance($this->_lang_db[$lang1], $value));
+                            $this->_distance($this->_lang_db[$lang1], $value)
+                        );
                     }
                 }
                 asort($return_arr);
@@ -1104,30 +1095,27 @@ class Text_LanguageDetect
             }
 
 
-        // compare all languages to each other
         } else {
+            // compare all languages to each other
             $return_arr = array();
             foreach (array_keys($this->_lang_db) as $lang1) {
                 foreach (array_keys($this->_lang_db) as $lang2) {
-
                     // skip comparing languages to themselves
-                    if ($lang1 != $lang2) { 
-                    
-                        // don't re-calculate what's already been done
-                        if (isset($return_arr[$lang2][$lang1])) {
+                    if ($lang1 != $lang2) {
 
-                            $return_arr[$lang1][$lang2] =
-                                $return_arr[$lang2][$lang1];
+                        if (isset($return_arr[$lang2][$lang1])) {
+                            // don't re-calculate what's already been done
+                            $return_arr[$lang1][$lang2]
+                                = $return_arr[$lang2][$lang1];
 
-                        // calculate
                         } else {
-
-                            $return_arr[$lang1][$lang2] = 
-                                $this->_normalize_score(
-                                        $this->_distance(
-                                            $this->_lang_db[$lang1],
-                                            $this->_lang_db[$lang2]
-                                        )
+                            // calculate
+                            $return_arr[$lang1][$lang2]
+                                = $this->_normalize_score(
+                                    $this->_distance(
+                                        $this->_lang_db[$lang1],
+                                        $this->_lang_db[$lang2]
+                                    )
                                 );
 
                         }
@@ -1150,20 +1138,14 @@ class Text_LanguageDetect
      *
      * @access      public
      * @return      array language cluster data
-     * @throws      PEAR_Error
+     * @throws      Text_LanguageDetect_Exception
      * @see         languageSimilarity()
-     * @deprecated  this function will eventually be removed and placed into 
+     * @deprecated  this function will eventually be removed and placed into
      *              the model generation class
      */
     function clusterLanguages()
     {
         // todo: set the maximum number of clusters
-
-        // setup check
-        if (!$this->_setup_ok($err)) {
-            return $err;
-        }
-
         // return cached result, if any
         if (isset($this->_clusters)) {
             return $this->_clusters;
@@ -1177,7 +1159,10 @@ class Text_LanguageDetect
 
         foreach ($langs as $lang) {
             if (!isset($this->_lang_db[$lang])) {
-                throw new Exception("missing $lang!\n");
+                throw new Text_LanguageDetect_Exception(
+                    "missing $lang!",
+                    Text_LanguageDetect_Exception::UNKNOWN_LANGUAGE
+                );
             }
         }
 
@@ -1186,7 +1171,9 @@ class Text_LanguageDetect
             $langs[$lang1] = $lang1;
             unset($langs[$old_key]);
         }
-        
+
+        $result_data = $really_map = array();
+
         $i = 0;
         while (count($langs) > 2 && $i++ < 200) {
             $highest_score = -1;
@@ -1194,18 +1181,22 @@ class Text_LanguageDetect
             $highest_key2 = '';
             foreach ($langs as $lang1) {
                 foreach ($langs as $lang2) {
-                    if (    $lang1 != $lang2 
-                            && $arr[$lang1][$lang2] > $highest_score) {
+                    if ($lang1 != $lang2
+                        && $arr[$lang1][$lang2] > $highest_score
+                    ) {
                         $highest_score = $arr[$lang1][$lang2];
                         $highest_key1 = $lang1;
                         $highest_key2 = $lang2;
                     }
                 }
             }
-            
+
             if (!$highest_key1) {
                 // should not ever happen
-                throw new Exception("no highest key? (step: $i)");
+                throw new Text_LanguageDetect_Exception(
+                    "no highest key? (step: $i)",
+                    Text_LanguageDetect_Exception::NO_HIGHEST_KEY
+                );
             }
 
             if ($highest_score == 0) {
@@ -1217,7 +1208,7 @@ class Text_LanguageDetect
             $sum1 = array_sum($arr[$highest_key1]);
             $sum2 = array_sum($arr[$highest_key2]);
 
-            // use the score for the one that is most similar to the rest of 
+            // use the score for the one that is most similar to the rest of
             // the field as the score for the group
             // todo: could try averaging or "centroid" method instead
             // seems like that might make more sense
@@ -1248,7 +1239,7 @@ class Text_LanguageDetect
             $really_lang = $replaceme;
             while (isset($really_map[$really_lang])) {
                 $really_lang = $really_map[$really_lang];
-            } 
+            }
             $really_map[$newkey] = $really_lang;
 
 
@@ -1259,8 +1250,8 @@ class Text_LanguageDetect
                         $arr[$key1][$newkey] = $arr[$key1][$key2];
                         unset($arr[$key1][$key2]);
                         // replacing $arr[$key1][$key2] with $arr[$key1][$newkey]
-                    } 
-                    
+                    }
+
                     if ($key1 == $replaceme) {
                         $arr[$newkey][$key2] = $arr[$key1][$key2];
                         unset($arr[$key1][$key2]);
@@ -1273,7 +1264,7 @@ class Text_LanguageDetect
                     }
                 }
             }
-                        
+
 
             unset($langs[$highest_key1]);
             unset($langs[$highest_key2]);
@@ -1293,7 +1284,7 @@ class Text_LanguageDetect
         }
 
         $return_val = array(
-                'open_forks' => $langs, 
+                'open_forks' => $langs,
                         // the top level of clusters
                         // clusters that are mutually exclusive
                         // or specified by a specific maximum
@@ -1323,11 +1314,11 @@ class Text_LanguageDetect
      * use, and it may disappear or its functionality may change in future
      * releases without notice.
      *
-     * This compares the sample text to top the top level of clusters. If the 
+     * This compares the sample text to top the top level of clusters. If the
      * sample is similar to the cluster it will drop down and compare it to the
      * languages in the cluster, and so on until it hits a leaf node.
      *
-     * this should find the language in considerably fewer compares 
+     * this should find the language in considerably fewer compares
      * (the equivalent of a binary search), however clusterLanguages() is costly
      * and the loss of accuracy from this technique is significant.
      *
@@ -1337,15 +1328,14 @@ class Text_LanguageDetect
      * was very large, however in such cases some method of Bayesian inference
      * might be more helpful.
      *
-     * @see     clusterLanguages()
-     * @access  public
-     * @param   string $str input string
-     * @return  array language scores (only those compared)
-     * @throws  PEAR_Error
+     * @param string $str input string
+     *
+     * @return array language scores (only those compared)
+     * @throws Text_LanguageDetect_Exception
+     * @see    clusterLanguages()
      */
-    function clusteredSearch($str)
+    public function clusteredSearch($str)
     {
-
         // input check
         if (!Text_LanguageDetect_Parser::validateString($str)) {
             return array();
@@ -1359,7 +1349,7 @@ class Text_LanguageDetect
         $dendogram_data  = $result['fork_data'];
         $dendogram_alias = $result['name_map'];
 
-        $sample_obj = new Text_LanguageDetect_Parser($str, $this->_db_filename, $this->_unicode_db_filename);
+        $sample_obj = new Text_LanguageDetect_Parser($str);
         $sample_obj->prepareTrigram();
         $sample_obj->setPadStart(!$this->_perl_compatible);
         $sample_obj->analyze();
@@ -1372,7 +1362,7 @@ class Text_LanguageDetect
         }
 
         $i = 0; // counts the number of steps
-        
+
         foreach ($dendogram_start as $lang) {
             if (isset($dendogram_alias[$lang])) {
                 $lang_key = $dendogram_alias[$lang];
@@ -1382,7 +1372,8 @@ class Text_LanguageDetect
 
             $scores[$lang] = $this->_normalize_score(
                 $this->_distance($this->_lang_db[$lang_key], $sample_result),
-                $sample_count);
+                $sample_count
+            );
 
             $i++;
         }
@@ -1411,7 +1402,8 @@ class Text_LanguageDetect
 
                 $scores[$lang] = $this->_normalize_score(
                     $this->_distance($this->_lang_db[$lang_key], $sample_result),
-                    $sample_count);
+                    $sample_count
+                );
 
                 //todo: does not need to do same comparison again
             }
@@ -1428,8 +1420,8 @@ class Text_LanguageDetect
 
             $diff = $scores[$cur_key] - $scores[$loser_key];
 
-            // $cur_key ({$dendogram_alias[$cur_key]}) wins 
-            // over $loser_key ({$dendogram_alias[$loser_key]}) 
+            // $cur_key ({$dendogram_alias[$cur_key]}) wins
+            // over $loser_key ({$dendogram_alias[$loser_key]})
             // with a difference of $diff
         }
 
@@ -1439,9 +1431,9 @@ class Text_LanguageDetect
         // which paths the algorithm decided to take along the tree
 
         // but sometimes the last item is only the second highest
-        if (   ($this->_perl_compatible  && (end($scores) > prev($scores)))
-            || (!$this->_perl_compatible && (end($scores) < prev($scores)))) {
-
+        if (($this->_perl_compatible  && (end($scores) > prev($scores)))
+            || (!$this->_perl_compatible && (end($scores) < prev($scores)))
+        ) {
             $real_last_score = current($scores);
             $real_last_key = key($scores);
 
@@ -1449,7 +1441,7 @@ class Text_LanguageDetect
             unset($scores[$real_last_key]);
             $scores[$real_last_key] = $real_last_score;
         }
-            
+
 
         if (!$this->_perl_compatible) {
             $scores = array_reverse($scores, true);
@@ -1464,12 +1456,11 @@ class Text_LanguageDetect
      *
      * Returns the numbers of characters (not bytes) in a utf8 string
      *
-     * @static
-     * @access  public
-     * @param   string $str string to get the length of
-     * @return  int         number of chars
+     * @param string $str string to get the length of
+     *
+     * @return int number of chars
      */
-    function utf8strlen($str)
+    public static function utf8strlen($str)
     {
         // utf8_decode() will convert unknown chars to '?', which is actually
         // ideal for counting.
@@ -1482,53 +1473,45 @@ class Text_LanguageDetect
     /**
      * Returns the unicode value of a utf8 char
      *
-     * @access  protected
-     * @param   string $char a utf8 (possibly multi-byte) char
-     * @return  int          unicode value or -1 if malformatted
+     * @param string $char a utf8 (possibly multi-byte) char
+     *
+     * @return int unicode value
+     * @access protected
+     * @link   http://en.wikipedia.org/wiki/UTF-8
      */
-    function _utf8char2unicode($char) {
-
+    function _utf8char2unicode($char)
+    {
         // strlen() here will actually get the binary length of a single char
         switch (strlen($char)) {
-
-            // for a reference, see http://en.wikipedia.org/wiki/UTF-8
-
-            case 1:
-                // normal ASCII-7 byte
-                // 0xxxxxxx -->  0xxxxxxx
-                return ord($char{0});
-
-            case 2:
-                // 2 byte unicode
-                // 110zzzzx 10xxxxxx --> 00000zzz zxxxxxxx
-                $z = (ord($char{0}) & 0x000001F) << 6;
-                $x = (ord($char{1}) & 0x0000003F);
-
-                return ($z | $x);
-
-            case 3:
-                // 3 byte unicode
-                // 1110zzzz 10zxxxxx 10xxxxxx --> zzzzzxxx xxxxxxxx 
-                $z =  (ord($char{0}) & 0x0000000F) << 12;
-                $x1 = (ord($char{1}) & 0x0000003F) << 6;
-                $x2 = (ord($char{2}) & 0x0000003F);
-
-                return ($z | $x1 | $x2);
-
-            case 4:
-                // 4 byte unicode
-                // 11110zzz 10zzxxxx 10xxxxxx 10xxxxxx -->
-                // 000zzzzz xxxxxxxx xxxxxxxx
-                $z1 = (ord($char{0}) & 0x00000007) << 18;
-                $z2 = (ord($char{1}) & 0x0000003F) << 12;
-                $x1 = (ord($char{2}) & 0x0000003F) << 6;
-                $x2 = (ord($char{3}) & 0x0000003F);
-
-                return ($z1 | $z2 | $x1 | $x2);
-
-            default:
-                // error: malformatted char?
-                return -1;
+        case 1:
+            // normal ASCII-7 byte
+            // 0xxxxxxx -->  0xxxxxxx
+            return ord($char{0});
+
+        case 2:
+            // 2 byte unicode
+            // 110zzzzx 10xxxxxx --> 00000zzz zxxxxxxx
+            $z = (ord($char{0}) & 0x000001F) << 6;
+            $x = (ord($char{1}) & 0x0000003F);
+            return ($z | $x);
+
+        case 3:
+            // 3 byte unicode
+            // 1110zzzz 10zxxxxx 10xxxxxx --> zzzzzxxx xxxxxxxx
+            $z =  (ord($char{0}) & 0x0000000F) << 12;
+            $x1 = (ord($char{1}) & 0x0000003F) << 6;
+            $x2 = (ord($char{2}) & 0x0000003F);
+            return ($z | $x1 | $x2);
+
+        case 4:
+            // 4 byte unicode
+            // 11110zzz 10zzxxxx 10xxxxxx 10xxxxxx -->
+            // 000zzzzz xxxxxxxx xxxxxxxx
+            $z1 = (ord($char{0}) & 0x00000007) << 18;
+            $z2 = (ord($char{1}) & 0x0000003F) << 12;
+            $x1 = (ord($char{2}) & 0x0000003F) << 6;
+            $x2 = (ord($char{3}) & 0x0000003F);
+            return ($z1 | $z2 | $x1 | $x2);
         }
     }
 
@@ -1536,18 +1519,18 @@ class Text_LanguageDetect
      * utf8-safe fast character iterator
      *
      * Will get the next character starting from $counter, which will then be
-     * incremented. If a multi-byte char the bytes will be concatenated and 
+     * incremented. If a multi-byte char the bytes will be concatenated and
      * $counter will be incremeted by the number of bytes in the char.
      *
-     * @access  private
-     * @param   string  &$str        the string being iterated over
-     * @param   int     &$counter    the iterator, will increment by reference
-     * @param   bool    $special_convert whether to do special conversions
-     * @return  char    the next (possibly multi-byte) char from $counter
+     * @param string $str             the string being iterated over
+     * @param int    &$counter        the iterator, will increment by reference
+     * @param bool   $special_convert whether to do special conversions
+     *
+     * @return char the next (possibly multi-byte) char from $counter
+     * @access private
      */
-    function _next_char(&$str, &$counter, $special_convert = false)
+    static function _next_char($str, &$counter, $special_convert = false)
     {
-
         $char = $str{$counter++};
         $ord = ord($char);
 
@@ -1556,7 +1539,6 @@ class Text_LanguageDetect
 
         // normal ascii one byte char
         if ($ord <= 127) {
-
             // special conversions needed for this package
             // (that only apply to regular ascii characters)
             // lower case, and convert all non-alphanumeric characters
@@ -1571,8 +1553,8 @@ class Text_LanguageDetect
 
             return $char;
 
-        // multi-byte chars
         } elseif ($ord >> 5 == 6) { // two-byte char
+            // multi-byte chars
             $nextchar = $str{$counter++}; // get next byte
 
             // lower-casing of non-ascii characters is still incomplete
@@ -1582,27 +1564,27 @@ class Text_LanguageDetect
                 if ($ord == 195) {
                     $nextord = ord($nextchar);
                     $nextord_adj = $nextord + 64;
-                    // for a reference, see 
+                    // for a reference, see
                     // http://www.ramsch.org/martin/uni/fmi-hp/iso8859-1.html
 
                     // À - Þ but not ×
-                    if (    $nextord_adj >= 192
-                            && $nextord_adj <= 222 
-                            && $nextord_adj != 215) {
-
-                        $nextchar = chr($nextord + 32); 
+                    if ($nextord_adj >= 192
+                        && $nextord_adj <= 222
+                        && $nextord_adj != 215
+                    ) {
+                        $nextchar = chr($nextord + 32);
                     }
 
-                // lower case cyrillic alphabet
                 } elseif ($ord == 208) {
+                    // lower case cyrillic alphabet
                     $nextord = ord($nextchar);
                     // if A - Pe
                     if ($nextord >= 144 && $nextord <= 159) {
                         // lower case
                         $nextchar = chr($nextord + 32);
 
-                    // if Er - Ya
                     } elseif ($nextord >= 160 && $nextord <= 175) {
+                        // if Er - Ya
                         // lower case
                         $char = chr(209); // == $ord++
                         $nextchar = chr($nextord - 32);
@@ -1611,12 +1593,11 @@ class Text_LanguageDetect
             }
 
             // tag on next byte
-            return $char . $nextchar; 
-
+            return $char . $nextchar;
         } elseif ($ord >> 4  == 14) { // three-byte char
-            
+
             // tag on next 2 bytes
-            return $char . $str{$counter++} . $str{$counter++}; 
+            return $char . $str{$counter++} . $str{$counter++};
 
         } elseif ($ord >> 3 == 30) { // four-byte char
 
@@ -1628,8 +1609,85 @@ class Text_LanguageDetect
         }
     }
 
-}
+    /**
+     * Converts an $language input parameter from the configured mode
+     * to the language name that is used internally.
+     *
+     * Works for strings and arrays.
+     *
+     * @param string|array $lang       A language description ("english"/"en"/"eng")
+     * @param boolean      $convertKey If $lang is an array, setting $key
+     *                                 converts the keys to the language name.
+     *
+     * @return string|array Language name
+     */
+    function _convertFromNameMode($lang, $convertKey = false)
+    {
+        if ($this->_name_mode == 0) {
+            return $lang;
+        }
+
+        if ($this->_name_mode == 2) {
+            $method = 'code2ToName';
+        } else {
+            $method = 'code3ToName';
+        }
+
+        if (is_string($lang)) {
+            return (string)Text_LanguageDetect_ISO639::$method($lang);
+        }
+
+        $newlang = array();
+        foreach ($lang as $key => $val) {
+            if ($convertKey) {
+                $newkey = (string)Text_LanguageDetect_ISO639::$method($key);
+                $newlang[$newkey] = $val;
+            } else {
+                $newlang[$key] = (string)Text_LanguageDetect_ISO639::$method($val);
+            }
+        }
+        return $newlang;
+    }
 
-/* vim: set expandtab tabstop=4 shiftwidth=4 softtabstop=4: */
+    /**
+     * Converts an $language output parameter from the language name that is
+     * used internally to the configured mode.
+     *
+     * Works for strings and arrays.
+     *
+     * @param string|array $lang       A language description ("english"/"en"/"eng")
+     * @param boolean      $convertKey If $lang is an array, setting $key
+     *                                 converts the keys to the language name.
+     *
+     * @return string|array Language name
+     */
+    function _convertToNameMode($lang, $convertKey = false)
+    {
+        if ($this->_name_mode == 0) {
+            return $lang;
+        }
+
+        if ($this->_name_mode == 2) {
+            $method = 'nameToCode2';
+        } else {
+            $method = 'nameToCode3';
+        }
+
+        if (is_string($lang)) {
+            return Text_LanguageDetect_ISO639::$method($lang);
+        }
+
+        $newlang = array();
+        foreach ($lang as $key => $val) {
+            if ($convertKey) {
+                $newkey = Text_LanguageDetect_ISO639::$method($key);
+                $newlang[$newkey] = $val;
+            } else {
+                $newlang[$key] = Text_LanguageDetect_ISO639::$method($val);
+            }
+        }
+        return $newlang;
+    }
+}
 
-?>
+/* vim: set expandtab tabstop=4 shiftwidth=4 softtabstop=4: */
\ No newline at end of file
diff --git a/inc/3rdparty/libraries/readability/Readability.php b/inc/3rdparty/libraries/readability/Readability.php
index 2e8991cc..d0f09d74 100644
--- a/inc/3rdparty/libraries/readability/Readability.php
+++ b/inc/3rdparty/libraries/readability/Readability.php
@@ -1,1138 +1,1138 @@
-init();
-echo $r->articleContent->innerHTML;
-*/
-
-class Readability
-{
-	public $version = '1.7.1-without-multi-page';
-	public $convertLinksToFootnotes = false;
-	public $revertForcedParagraphElements = true;
-	public $articleTitle;
-	public $articleContent;
-	public $dom;
-	public $url = null; // optional - URL where HTML was retrieved
-	public $debug = false;
-	public $lightClean = true; // preserves more content (experimental) added 2012-09-19
-	protected $body = null; // 
-	protected $bodyCache = null; // Cache the body HTML in case we need to re-use it later
-	protected $flags = 7; // 1 | 2 | 4;   // Start with all flags set.
-	protected $success = false; // indicates whether we were able to extract or not
-	
-	/**
-	* All of the regular expressions in use within readability.
-	* Defined up here so we don't instantiate them repeatedly in loops.
-	**/
-	public $regexps = array(
-		'unlikelyCandidates' => '/combx|comment|community|disqus|extra|foot|header|menu|remark|rss|shoutbox|sidebar|sponsor|ad-break|agegate|pagination|pager|popup/i',
-		'okMaybeItsACandidate' => '/and|article|body|column|main|shadow/i',
-		'positive' => '/article|body|content|entry|hentry|main|page|attachment|pagination|post|text|blog|story/i',
-		'negative' => '/combx|comment|com-|contact|foot|footer|_nav|footnote|masthead|media|meta|outbrain|promo|related|scroll|shoutbox|sidebar|sponsor|shopping|tags|tool|widget/i',
-		'divToPElements' => '/<(a|blockquote|dl|div|img|ol|p|pre|table|ul)/i',
-		'replaceBrs' => '/(]*>[ \n\r\t]*){2,}/i',
-		'replaceFonts' => '/<(\/?)font[^>]*>/i',
-		// 'trimRe' => '/^\s+|\s+$/g', // PHP has trim()
-		'normalize' => '/\s{2,}/',
-		'killBreaks' => '/((\s| ?)*){1,}/',
-		'video' => '!//(player\.|www\.)?(youtube|vimeo|viddler)\.com!i',
-		'skipFootnoteLink' => '/^\s*(\[?[a-z0-9]{1,2}\]?|^|edit|citation needed)\s*$/i'
-	);	
-	
-	/* constants */
-	const FLAG_STRIP_UNLIKELYS = 1;
-	const FLAG_WEIGHT_CLASSES = 2;
-	const FLAG_CLEAN_CONDITIONALLY = 4;
-	
-	/**
-	* Create instance of Readability
-	* @param string UTF-8 encoded string
-	* @param string (optional) URL associated with HTML (used for footnotes)
-	* @param string which parser to use for turning raw HTML into a DOMDocument (either 'libxml' or 'html5lib')
-	*/	
-	function __construct($html, $url=null, $parser='libxml')
-	{
-		$this->url = $url;
-		/* Turn all double br's into p's */
-		$html = preg_replace($this->regexps['replaceBrs'], '
    ', $html);
-		$html = preg_replace($this->regexps['replaceFonts'], '<$1span>', $html);
-		$html = mb_convert_encoding($html, 'HTML-ENTITIES', "UTF-8");
-		if (trim($html) == '') $html = '';
-		if ($parser=='html5lib' && ($this->dom = HTML5_Parser::parse($html))) {
-			// all good
-		} else {
-			$this->dom = new DOMDocument();
-			$this->dom->preserveWhiteSpace = false;
-			@$this->dom->loadHTML($html);
-		}
-		$this->dom->registerNodeClass('DOMElement', 'JSLikeHTMLElement');
-	}
-
-	/**
-	* Get article title element
-	* @return DOMElement
-	*/
-	public function getTitle() {
-		return $this->articleTitle;
-	}
-	
-	/**
-	* Get article content element
-	* @return DOMElement
-	*/
-	public function getContent() {
-		return $this->articleContent;
-	}	
-	
-	/**
-	* Runs readability.
-	* 
-	* Workflow:
-	*  1. Prep the document by removing script tags, css, etc.
-	*  2. Build readability's DOM tree.
-	*  3. Grab the article content from the current dom tree.
-	*  4. Replace the current DOM tree with the new one.
-	*  5. Read peacefully.
-	*
-	* @return boolean true if we found content, false otherwise
-	**/
-	public function init()
-	{
-		if (!isset($this->dom->documentElement)) return false;
-		$this->removeScripts($this->dom);
-		//die($this->getInnerHTML($this->dom->documentElement));
-		
-		// Assume successful outcome
-		$this->success = true;
-
-		$bodyElems = $this->dom->getElementsByTagName('body');
-		if ($bodyElems->length > 0) {
-			if ($this->bodyCache == null) {
-				$this->bodyCache = $bodyElems->item(0)->innerHTML;
-			}
-			if ($this->body == null) {
-				$this->body = $bodyElems->item(0);
-			}
-		}
-
-		$this->prepDocument();
-		
-		//die($this->dom->documentElement->parentNode->nodeType);
-		//$this->setInnerHTML($this->dom->documentElement, $this->getInnerHTML($this->dom->documentElement));
-		//die($this->getInnerHTML($this->dom->documentElement));
-
-		/* Build readability's DOM tree */
-		$overlay        = $this->dom->createElement('div');
-		$innerDiv       = $this->dom->createElement('div');
-		$articleTitle   = $this->getArticleTitle();
-		$articleContent = $this->grabArticle();
-
-		if (!$articleContent) {
-			$this->success = false;
-			$articleContent = $this->dom->createElement('div');
-			$articleContent->setAttribute('id', 'readability-content');
-			$articleContent->innerHTML = '
    Sorry, Readability was unable to parse this page for content.
    ';		
-		}
-		
-		$overlay->setAttribute('id', 'readOverlay');
-		$innerDiv->setAttribute('id', 'readInner');
-
-		/* Glue the structure of our document together. */
-		$innerDiv->appendChild($articleTitle);
-		$innerDiv->appendChild($articleContent);
-		$overlay->appendChild($innerDiv);
-		
-		/* Clear the old HTML, insert the new content. */
-		$this->body->innerHTML = '';
-		$this->body->appendChild($overlay);
-		//document.body.insertBefore(overlay, document.body.firstChild);
-		$this->body->removeAttribute('style');
-
-		$this->postProcessContent($articleContent);
-		
-		// Set title and content instance variables
-		$this->articleTitle = $articleTitle;
-		$this->articleContent = $articleContent;
-		
-		return $this->success;
-	}
-	
-	/**
-	* Debug
-	*/
-	protected function dbg($msg) {
-		if ($this->debug) echo '* ',$msg, "\n";
-	}
-	
-	/**
-	* Run any post-process modifications to article content as necessary.
-	*
-	* @param DOMElement
-	* @return void
-	*/
-	public function postProcessContent($articleContent) {
-		if ($this->convertLinksToFootnotes && !preg_match('/wikipedia\.org/', @$this->url)) { 
-			$this->addFootnotes($articleContent);
-		}
-	}
-	
-	/**
-	* Get the article title as an H1.
-	*
-	* @return DOMElement
-	*/
-	protected function getArticleTitle() {
-		$curTitle = '';
-		$origTitle = '';
-
-		try {
-			$curTitle = $origTitle = $this->getInnerText($this->dom->getElementsByTagName('title')->item(0));
-		} catch(Exception $e) {}
-		
-		if (preg_match('/ [\|\-] /', $curTitle))
-		{
-			$curTitle = preg_replace('/(.*)[\|\-] .*/i', '$1', $origTitle);
-			
-			if (count(explode(' ', $curTitle)) < 3) {
-				$curTitle = preg_replace('/[^\|\-]*[\|\-](.*)/i', '$1', $origTitle);
-			}
-		}
-		else if (strpos($curTitle, ': ') !== false)
-		{
-			$curTitle = preg_replace('/.*:(.*)/i', '$1', $origTitle);
-
-			if (count(explode(' ', $curTitle)) < 3) {
-				$curTitle = preg_replace('/[^:]*[:](.*)/i','$1', $origTitle);
-			}
-		}
-		else if(strlen($curTitle) > 150 || strlen($curTitle) < 15)
-		{
-			$hOnes = $this->dom->getElementsByTagName('h1');
-			if($hOnes->length == 1)
-			{
-				$curTitle = $this->getInnerText($hOnes->item(0));
-			}
-		}
-
-		$curTitle = trim($curTitle);
-
-		if (count(explode(' ', $curTitle)) <= 4) {
-			$curTitle = $origTitle;
-		}
-		
-		$articleTitle = $this->dom->createElement('h1');
-		$articleTitle->innerHTML = $curTitle;
-		
-		return $articleTitle;
-	}
-	
-	/**
-	* Prepare the HTML document for readability to scrape it.
-	* This includes things like stripping javascript, CSS, and handling terrible markup.
-	* 
-	* @return void
-	**/
-	protected function prepDocument() {
-		/**
-		* In some cases a body element can't be found (if the HTML is totally hosed for example)
-		* so we create a new body node and append it to the document.
-		*/
-		if ($this->body == null)
-		{
-			$this->body = $this->dom->createElement('body');
-			$this->dom->documentElement->appendChild($this->body);
-		}
-		$this->body->setAttribute('id', 'readabilityBody');
-
-		/* Remove all style tags in head */
-		$styleTags = $this->dom->getElementsByTagName('style');
-		for ($i = $styleTags->length-1; $i >= 0; $i--)
-		{
-			$styleTags->item($i)->parentNode->removeChild($styleTags->item($i));
-		}
-
-		/* Turn all double br's into p's */
-		/* Note, this is pretty costly as far as processing goes. Maybe optimize later. */
-		//document.body.innerHTML = document.body.innerHTML.replace(readability.regexps.replaceBrs, '
    ').replace(readability.regexps.replaceFonts, '<$1span>');
-		// We do this in the constructor for PHP as that's when we have raw HTML - before parsing it into a DOM tree.
-		// Manipulating innerHTML as it's done in JS is not possible in PHP.
-	}
-
-	/**
-	* For easier reading, convert this document to have footnotes at the bottom rather than inline links.
-	* @see http://www.roughtype.com/archives/2010/05/experiments_in.php
-	*
-	* @return void
-	**/
-	public function addFootnotes($articleContent) {
-		$footnotesWrapper = $this->dom->createElement('div');
-		$footnotesWrapper->setAttribute('id', 'readability-footnotes');
-		$footnotesWrapper->innerHTML = '
    References
    ';
-		
-		$articleFootnotes = $this->dom->createElement('ol');
-		$articleFootnotes->setAttribute('id', 'readability-footnotes-list');
-		$footnotesWrapper->appendChild($articleFootnotes);
-		
-		$articleLinks = $articleContent->getElementsByTagName('a');
-		
-		$linkCount = 0;
-		for ($i = 0; $i < $articleLinks->length; $i++)
-		{
-			$articleLink  = $articleLinks->item($i);
-			$footnoteLink = $articleLink->cloneNode(true);
-			$refLink      = $this->dom->createElement('a');
-			$footnote     = $this->dom->createElement('li');
-			$linkDomain   = @parse_url($footnoteLink->getAttribute('href'), PHP_URL_HOST);
-			if (!$linkDomain && isset($this->url)) $linkDomain = @parse_url($this->url, PHP_URL_HOST);
-			//linkDomain   = footnoteLink.host ? footnoteLink.host : document.location.host,
-			$linkText     = $this->getInnerText($articleLink);
-			
-			if ((strpos($articleLink->getAttribute('class'), 'readability-DoNotFootnote') !== false) || preg_match($this->regexps['skipFootnoteLink'], $linkText)) {
-				continue;
-			}
-			
-			$linkCount++;
-
-			/** Add a superscript reference after the article link */
-			$refLink->setAttribute('href', '#readabilityFootnoteLink-' . $linkCount);
-			$refLink->innerHTML = '[' . $linkCount . ']';
-			$refLink->setAttribute('class', 'readability-DoNotFootnote');
-			$refLink->setAttribute('style', 'color: inherit;');
-			
-			//TODO: does this work or should we use DOMNode.isSameNode()?
-			if ($articleLink->parentNode->lastChild == $articleLink) {
-				$articleLink->parentNode->appendChild($refLink);
-			} else {
-				$articleLink->parentNode->insertBefore($refLink, $articleLink->nextSibling);
-			}
-
-			$articleLink->setAttribute('style', 'color: inherit; text-decoration: none;');
-			$articleLink->setAttribute('name', 'readabilityLink-' . $linkCount);
-
-			$footnote->innerHTML = '^ ';
-
-			$footnoteLink->innerHTML = ($footnoteLink->getAttribute('title') != '' ? $footnoteLink->getAttribute('title') : $linkText);
-			$footnoteLink->setAttribute('name', 'readabilityFootnoteLink-' . $linkCount);
-			
-			$footnote->appendChild($footnoteLink);
-			if ($linkDomain) $footnote->innerHTML = $footnote->innerHTML . ' (' . $linkDomain . ')';
-			
-			$articleFootnotes->appendChild($footnote);
-		}
-
-		if ($linkCount > 0) {
-			$articleContent->appendChild($footnotesWrapper);           
-		}
-	}
-
-	/**
-	* Reverts P elements with class 'readability-styled'
-	* to text nodes - which is what they were before.
-	*
-	* @param DOMElement
-	* @return void
-	*/
-	function revertReadabilityStyledElements($articleContent) {
-		$xpath = new DOMXPath($articleContent->ownerDocument);
-		$elems = $xpath->query('.//p[@class="readability-styled"]', $articleContent);
-		//$elems = $articleContent->getElementsByTagName('p');
-		for ($i = $elems->length-1; $i >= 0; $i--) {
-			$e = $elems->item($i);
-			$e->parentNode->replaceChild($articleContent->ownerDocument->createTextNode($e->textContent), $e);
-			//if ($e->hasAttribute('class') && $e->getAttribute('class') == 'readability-styled') {
-			//	$e->parentNode->replaceChild($this->dom->createTextNode($e->textContent), $e);
-			//}
-		}
-	}
-	
-	/**
-	* Prepare the article node for display. Clean out any inline styles,
-	* iframes, forms, strip extraneous 
     tags, etc.
-	*
-	* @param DOMElement
-	* @return void
-	*/
-	function prepArticle($articleContent) {
-		$this->cleanStyles($articleContent);
-		$this->killBreaks($articleContent);
-		if ($this->revertForcedParagraphElements) {
-			$this->revertReadabilityStyledElements($articleContent);
-		}
-
-		/* Clean out junk from the article content */
-		$this->cleanConditionally($articleContent, 'form');
-		$this->clean($articleContent, 'object');
-		$this->clean($articleContent, 'h1');
-
-		/**
-		* If there is only one h2, they are probably using it
-		* as a header and not a subheader, so remove it since we already have a header.
-		***/
-		if (!$this->lightClean && ($articleContent->getElementsByTagName('h2')->length == 1)) {
-			$this->clean($articleContent, 'h2'); 
-		}
-		$this->clean($articleContent, 'iframe');
-
-		$this->cleanHeaders($articleContent);
-
-		/* Do these last as the previous stuff may have removed junk that will affect these */
-		$this->cleanConditionally($articleContent, 'table');
-		$this->cleanConditionally($articleContent, 'ul');
-		$this->cleanConditionally($articleContent, 'div');
-
-		/* Remove extra paragraphs */
-		$articleParagraphs = $articleContent->getElementsByTagName('p');
-		for ($i = $articleParagraphs->length-1; $i >= 0; $i--)
-		{
-			$imgCount    = $articleParagraphs->item($i)->getElementsByTagName('img')->length;
-			$embedCount  = $articleParagraphs->item($i)->getElementsByTagName('embed')->length;
-			$objectCount = $articleParagraphs->item($i)->getElementsByTagName('object')->length;
-			$iframeCount = $articleParagraphs->item($i)->getElementsByTagName('iframe')->length;
-			
-			if ($imgCount === 0 && $embedCount === 0 && $objectCount === 0 && $iframeCount === 0 && $this->getInnerText($articleParagraphs->item($i), false) == '')
-			{
-				$articleParagraphs->item($i)->parentNode->removeChild($articleParagraphs->item($i));
-			}
-		}
-
-		try {
-			$articleContent->innerHTML = preg_replace('/]*>\s*
    innerHTML);
-			//articleContent.innerHTML = articleContent.innerHTML.replace(/]*>\s*
    dbg("Cleaning innerHTML of breaks failed. This is an IE strict-block-elements bug. Ignoring.: " . $e);
-		}
-	}
-	
-	/**
-	* Initialize a node with the readability object. Also checks the
-	* className/id for special names to add to its score.
-	*
-	* @param Element
-	* @return void
-	**/
-	protected function initializeNode($node) {
-		$readability = $this->dom->createAttribute('readability');
-		$readability->value = 0; // this is our contentScore
-		$node->setAttributeNode($readability);		         
-
-		switch (strtoupper($node->tagName)) { // unsure if strtoupper is needed, but using it just in case
-			case 'DIV':
-				$readability->value += 5;
-				break;
-
-			case 'PRE':
-			case 'TD':
-			case 'BLOCKQUOTE':
-				$readability->value += 3;
-				break;
-				
-			case 'ADDRESS':
-			case 'OL':
-			case 'UL':
-			case 'DL':
-			case 'DD':
-			case 'DT':
-			case 'LI':
-			case 'FORM':
-				$readability->value -= 3;
-				break;
-
-			case 'H1':
-			case 'H2':
-			case 'H3':
-			case 'H4':
-			case 'H5':
-			case 'H6':
-			case 'TH':
-				$readability->value -= 5;
-				break;
-		}
-		$readability->value += $this->getClassWeight($node);
-	}
-	
-	/***
-	* grabArticle - Using a variety of metrics (content score, classname, element types), find the content that is
-	*               most likely to be the stuff a user wants to read. Then return it wrapped up in a div.
-	*
-	* @return DOMElement
-	**/
-	protected function grabArticle($page=null) {
-		$stripUnlikelyCandidates = $this->flagIsActive(self::FLAG_STRIP_UNLIKELYS);
-		if (!$page) $page = $this->dom;
-		$allElements = $page->getElementsByTagName('*');
-		/**
-		* First, node prepping. Trash nodes that look cruddy (like ones with the class name "comment", etc), and turn divs
-		* into P tags where they have been used inappropriately (as in, where they contain no other block level elements.)
-		*
-		* Note: Assignment from index for performance. See http://www.peachpit.com/articles/article.aspx?p=31567&seqNum=5
-		* TODO: Shouldn't this be a reverse traversal?
-		**/
-		$node = null;
-		$nodesToScore = array();
-		for ($nodeIndex = 0; ($node = $allElements->item($nodeIndex)); $nodeIndex++) {
-		//for ($nodeIndex=$targetList->length-1; $nodeIndex >= 0; $nodeIndex--) {
-			//$node = $targetList->item($nodeIndex);
-			$tagName = strtoupper($node->tagName);
-			/* Remove unlikely candidates */
-			if ($stripUnlikelyCandidates) {
-				$unlikelyMatchString = $node->getAttribute('class') . $node->getAttribute('id');
-				if (
-					preg_match($this->regexps['unlikelyCandidates'], $unlikelyMatchString) &&
-					!preg_match($this->regexps['okMaybeItsACandidate'], $unlikelyMatchString) &&
-					$tagName != 'BODY'
-				)
-				{
-					$this->dbg('Removing unlikely candidate - ' . $unlikelyMatchString);
-					//$nodesToRemove[] = $node;
-					$node->parentNode->removeChild($node);
-					$nodeIndex--;
-					continue;
-				}               
-			}
-
-			if ($tagName == 'P' || $tagName == 'TD' || $tagName == 'PRE') {
-				$nodesToScore[] = $node;
-			}
-
-			/* Turn all divs that don't have children block level elements into p's */
-			if ($tagName == 'DIV') {
-				if (!preg_match($this->regexps['divToPElements'], $node->innerHTML)) {
-					//$this->dbg('Altering div to p');
-					$newNode = $this->dom->createElement('p');
-					try {
-						$newNode->innerHTML = $node->innerHTML;
-						//$nodesToReplace[] = array('new'=>$newNode, 'old'=>$node);
-						$node->parentNode->replaceChild($newNode, $node);
-						$nodeIndex--;
-						$nodesToScore[] = $node; // or $newNode?
-					}
-					catch(Exception $e) {
-						$this->dbg('Could not alter div to p, reverting back to div.: ' . $e);
-					}
-				}
-				else
-				{
-					/* EXPERIMENTAL */
-					// TODO: change these p elements back to text nodes after processing
-					for ($i = 0, $il = $node->childNodes->length; $i < $il; $i++) {
-						$childNode = $node->childNodes->item($i);
-						if ($childNode->nodeType == 3) { // XML_TEXT_NODE
-							//$this->dbg('replacing text node with a p tag with the same content.');
-							$p = $this->dom->createElement('p');
-							$p->innerHTML = $childNode->nodeValue;
-							$p->setAttribute('style', 'display: inline;');
-							$p->setAttribute('class', 'readability-styled');
-							$childNode->parentNode->replaceChild($p, $childNode);
-						}
-					}
-				}
-			}
-		}
-		
-		/**
-		* Loop through all paragraphs, and assign a score to them based on how content-y they look.
-		* Then add their score to their parent node.
-		*
-		* A score is determined by things like number of commas, class names, etc. Maybe eventually link density.
-		**/
-		$candidates = array();
-		for ($pt=0; $pt < count($nodesToScore); $pt++) {
-			$parentNode      = $nodesToScore[$pt]->parentNode;
-			// $grandParentNode = $parentNode ? $parentNode->parentNode : null;
-			$grandParentNode = !$parentNode ? null : (($parentNode->parentNode instanceof DOMElement) ? $parentNode->parentNode : null);
-			$innerText       = $this->getInnerText($nodesToScore[$pt]);
-
-			if (!$parentNode || !isset($parentNode->tagName)) {
-				continue;
-			}
-
-			/* If this paragraph is less than 25 characters, don't even count it. */
-			if(strlen($innerText) < 25) {
-				continue;
-			}
-
-			/* Initialize readability data for the parent. */
-			if (!$parentNode->hasAttribute('readability')) 
-			{
-				$this->initializeNode($parentNode);
-				$candidates[] = $parentNode;
-			}
-
-			/* Initialize readability data for the grandparent. */
-			if ($grandParentNode && !$grandParentNode->hasAttribute('readability') && isset($grandParentNode->tagName))
-			{
-				$this->initializeNode($grandParentNode);
-				$candidates[] = $grandParentNode;
-			}
-
-			$contentScore = 0;
-
-			/* Add a point for the paragraph itself as a base. */
-			$contentScore++;
-
-			/* Add points for any commas within this paragraph */
-			$contentScore += count(explode(',', $innerText));
-			
-			/* For every 100 characters in this paragraph, add another point. Up to 3 points. */
-			$contentScore += min(floor(strlen($innerText) / 100), 3);
-			
-			/* Add the score to the parent. The grandparent gets half. */
-			$parentNode->getAttributeNode('readability')->value += $contentScore;
-
-			if ($grandParentNode) {
-				$grandParentNode->getAttributeNode('readability')->value += $contentScore/2;             
-			}
-		}
-
-		/**
-		* After we've calculated scores, loop through all of the possible candidate nodes we found
-		* and find the one with the highest score.
-		**/
-		$topCandidate = null;
-		for ($c=0, $cl=count($candidates); $c < $cl; $c++)
-		{
-			/**
-			* Scale the final candidates score based on link density. Good content should have a
-			* relatively small link density (5% or less) and be mostly unaffected by this operation.
-			**/
-			$readability = $candidates[$c]->getAttributeNode('readability');
-			$readability->value = $readability->value * (1-$this->getLinkDensity($candidates[$c]));
-
-			$this->dbg('Candidate: ' . $candidates[$c]->tagName . ' (' . $candidates[$c]->getAttribute('class') . ':' . $candidates[$c]->getAttribute('id') . ') with score ' . $readability->value);
-
-			if (!$topCandidate || $readability->value > (int)$topCandidate->getAttribute('readability')) {
-				$topCandidate = $candidates[$c];
-			}
-		}
-
-		/**
-		* If we still have no top candidate, just use the body as a last resort.
-		* We also have to copy the body node so it is something we can modify.
-		**/
-		if ($topCandidate === null || strtoupper($topCandidate->tagName) == 'BODY')
-		{
-			$topCandidate = $this->dom->createElement('div');
-			if ($page instanceof DOMDocument) {
-				if (!isset($page->documentElement)) {
-					// we don't have a body either? what a mess! :)
-				} else {
-					$topCandidate->innerHTML = $page->documentElement->innerHTML;
-					$page->documentElement->innerHTML = '';
-					$page->documentElement->appendChild($topCandidate);
-				}
-			} else {
-				$topCandidate->innerHTML = $page->innerHTML;
-				$page->innerHTML = '';
-				$page->appendChild($topCandidate);
-			}
-			$this->initializeNode($topCandidate);
-		}
-
-		/**
-		* Now that we have the top candidate, look through its siblings for content that might also be related.
-		* Things like preambles, content split by ads that we removed, etc.
-		**/
-		$articleContent        = $this->dom->createElement('div');
-		$articleContent->setAttribute('id', 'readability-content');
-		$siblingScoreThreshold = max(10, ((int)$topCandidate->getAttribute('readability')) * 0.2);
-		$siblingNodes          = $topCandidate->parentNode->childNodes;
-		if (!isset($siblingNodes)) {
-			$siblingNodes = new stdClass;
-			$siblingNodes->length = 0;
-		}
-
-		for ($s=0, $sl=$siblingNodes->length; $s < $sl; $s++)
-		{
-			$siblingNode = $siblingNodes->item($s);
-			$append      = false;
-
-			$this->dbg('Looking at sibling node: ' . $siblingNode->nodeName . (($siblingNode->nodeType === XML_ELEMENT_NODE && $siblingNode->hasAttribute('readability')) ? (' with score ' . $siblingNode->getAttribute('readability')) : ''));
-
-			//dbg('Sibling has score ' . ($siblingNode->readability ? siblingNode.readability.contentScore : 'Unknown'));
-
-			if ($siblingNode === $topCandidate)
-			// or if ($siblingNode->isSameNode($topCandidate))
-			{
-				$append = true;
-			}
-
-			$contentBonus = 0;
-			/* Give a bonus if sibling nodes and top candidates have the example same classname */
-			if ($siblingNode->nodeType === XML_ELEMENT_NODE && $siblingNode->getAttribute('class') == $topCandidate->getAttribute('class') && $topCandidate->getAttribute('class') != '') {
-				$contentBonus += ((int)$topCandidate->getAttribute('readability')) * 0.2;
-			}
-
-			if ($siblingNode->nodeType === XML_ELEMENT_NODE && $siblingNode->hasAttribute('readability') && (((int)$siblingNode->getAttribute('readability')) + $contentBonus) >= $siblingScoreThreshold)
-			{
-				$append = true;
-			}
-			
-			if (strtoupper($siblingNode->nodeName) == 'P') {
-				$linkDensity = $this->getLinkDensity($siblingNode);
-				$nodeContent = $this->getInnerText($siblingNode);
-				$nodeLength  = strlen($nodeContent);
-				
-				if ($nodeLength > 80 && $linkDensity < 0.25)
-				{
-					$append = true;
-				}
-				else if ($nodeLength < 80 && $linkDensity === 0 && preg_match('/\.( |$)/', $nodeContent))
-				{
-					$append = true;
-				}
-			}
-
-			if ($append)
-			{
-				$this->dbg('Appending node: ' . $siblingNode->nodeName);
-
-				$nodeToAppend = null;
-				$sibNodeName = strtoupper($siblingNode->nodeName);
-				if ($sibNodeName != 'DIV' && $sibNodeName != 'P') {
-					/* We have a node that isn't a common block level element, like a form or td tag. Turn it into a div so it doesn't get filtered out later by accident. */
-					
-					$this->dbg('Altering siblingNode of ' . $sibNodeName . ' to div.');
-					$nodeToAppend = $this->dom->createElement('div');
-					try {
-						$nodeToAppend->setAttribute('id', $siblingNode->getAttribute('id'));
-						$nodeToAppend->innerHTML = $siblingNode->innerHTML;
-					}
-					catch(Exception $e)
-					{
-						$this->dbg('Could not alter siblingNode to div, reverting back to original.');
-						$nodeToAppend = $siblingNode;
-						$s--;
-						$sl--;
-					}
-				} else {
-					$nodeToAppend = $siblingNode;
-					$s--;
-					$sl--;
-				}
-				
-				/* To ensure a node does not interfere with readability styles, remove its classnames */
-				$nodeToAppend->removeAttribute('class');
-
-				/* Append sibling and subtract from our list because it removes the node when you append to another node */
-				$articleContent->appendChild($nodeToAppend);
-			}
-		}
-
-		/**
-		* So we have all of the content that we need. Now we clean it up for presentation.
-		**/
-		$this->prepArticle($articleContent);
-
-		/**
-		* Now that we've gone through the full algorithm, check to see if we got any meaningful content.
-		* If we didn't, we may need to re-run grabArticle with different flags set. This gives us a higher
-		* likelihood of finding the content, and the sieve approach gives us a higher likelihood of
-		* finding the -right- content.
-		**/
-		if (strlen($this->getInnerText($articleContent, false)) < 250)
-		{
-			// TODO: find out why element disappears sometimes, e.g. for this URL http://www.businessinsider.com/6-hedge-fund-etfs-for-average-investors-2011-7
-			// in the meantime, we check and create an empty element if it's not there.
-			if (!isset($this->body->childNodes)) $this->body = $this->dom->createElement('body');
-			$this->body->innerHTML = $this->bodyCache;
-			
-			if ($this->flagIsActive(self::FLAG_STRIP_UNLIKELYS)) {
-				$this->removeFlag(self::FLAG_STRIP_UNLIKELYS);
-				return $this->grabArticle($this->body);
-			}
-			else if ($this->flagIsActive(self::FLAG_WEIGHT_CLASSES)) {
-				$this->removeFlag(self::FLAG_WEIGHT_CLASSES);
-				return $this->grabArticle($this->body);              
-			}
-			else if ($this->flagIsActive(self::FLAG_CLEAN_CONDITIONALLY)) {
-				$this->removeFlag(self::FLAG_CLEAN_CONDITIONALLY);
-				return $this->grabArticle($this->body);
-			}
-			else {
-				return false;
-			}
-		}
-		return $articleContent;
-	}
-	
-	/**
-	* Remove script tags from document
-	*
-	* @param DOMElement
-	* @return void
-	*/
-	public function removeScripts($doc) {
-		$scripts = $doc->getElementsByTagName('script');
-		for($i = $scripts->length-1; $i >= 0; $i--)
-		{
-			$scripts->item($i)->parentNode->removeChild($scripts->item($i));
-		}
-	}
-	
-	/**
-	* Get the inner text of a node.
-	* This also strips out any excess whitespace to be found.
-	*
-	* @param DOMElement $
-	* @param boolean $normalizeSpaces (default: true)
-	* @return string
-	**/
-	public function getInnerText($e, $normalizeSpaces=true) {
-		$textContent = '';
-
-		if (!isset($e->textContent) || $e->textContent == '') {
-			return '';
-		}
-
-		$textContent = trim($e->textContent);
-
-		if ($normalizeSpaces) {
-			return preg_replace($this->regexps['normalize'], ' ', $textContent);
-		} else {
-			return $textContent;
-		}
-	}
-
-	/**
-	* Get the number of times a string $s appears in the node $e.
-	*
-	* @param DOMElement $e
-	* @param string - what to count. Default is ","
-	* @return number (integer)
-	**/
-	public function getCharCount($e, $s=',') {
-		return substr_count($this->getInnerText($e), $s);
-	}
-
-	/**
-	* Remove the style attribute on every $e and under.
-	*
-	* @param DOMElement $e
-	* @return void
-	*/
-	public function cleanStyles($e) {
-		if (!is_object($e)) return;
-		$elems = $e->getElementsByTagName('*');
-		foreach ($elems as $elem) {
-			$elem->removeAttribute('style');
-		}
-	}
-	
-	/**
-	* Get the density of links as a percentage of the content
-	* This is the amount of text that is inside a link divided by the total text in the node.
-	* 
-	* @param DOMElement $e
-	* @return number (float)
-	*/
-	public function getLinkDensity($e) {
-		$links      = $e->getElementsByTagName('a');
-		$textLength = strlen($this->getInnerText($e));
-		$linkLength = 0;
-		for ($i=0, $il=$links->length; $i < $il; $i++)
-		{
-			$linkLength += strlen($this->getInnerText($links->item($i)));
-		}
-		if ($textLength > 0) {
-			return $linkLength / $textLength;
-		} else {
-			return 0;
-		}
-	}
-	
-	/**
-	* Get an elements class/id weight. Uses regular expressions to tell if this 
-	* element looks good or bad.
-	*
-	* @param DOMElement $e
-	* @return number (Integer)
-	*/
-	public function getClassWeight($e) {
-		if(!$this->flagIsActive(self::FLAG_WEIGHT_CLASSES)) {
-			return 0;
-		}
-
-		$weight = 0;
-
-		/* Look for a special classname */
-		if ($e->hasAttribute('class') && $e->getAttribute('class') != '')
-		{
-			if (preg_match($this->regexps['negative'], $e->getAttribute('class'))) {
-				$weight -= 25;
-			}
-			if (preg_match($this->regexps['positive'], $e->getAttribute('class'))) {
-				$weight += 25;
-			}
-		}
-
-		/* Look for a special ID */
-		if ($e->hasAttribute('id') && $e->getAttribute('id') != '')
-		{
-			if (preg_match($this->regexps['negative'], $e->getAttribute('id'))) {
-				$weight -= 25;
-			}
-			if (preg_match($this->regexps['positive'], $e->getAttribute('id'))) {
-				$weight += 25;
-			}
-		}
-		return $weight;
-	}
-
-	/**
-	* Remove extraneous break tags from a node.
-	*
-	* @param DOMElement $node
-	* @return void
-	*/
-	public function killBreaks($node) {
-		$html = $node->innerHTML;
-		$html = preg_replace($this->regexps['killBreaks'], '
    ', $html);
-		$node->innerHTML = $html;
-	}
-
-	/**
-	* Clean a node of all elements of type "tag".
-	* (Unless it's a youtube/vimeo video. People love movies.)
-	*
-	* Updated 2012-09-18 to preserve youtube/vimeo iframes
-	*
-	* @param DOMElement $e
-	* @param string $tag
-	* @return void
-	*/
-	public function clean($e, $tag) {
-		$targetList = $e->getElementsByTagName($tag);
-		$isEmbed = ($tag == 'iframe' || $tag == 'object' || $tag == 'embed');
-		
-		for ($y=$targetList->length-1; $y >= 0; $y--) {
-			/* Allow youtube and vimeo videos through as people usually want to see those. */
-			if ($isEmbed) {
-				$attributeValues = '';
-				for ($i=0, $il=$targetList->item($y)->attributes->length; $i < $il; $i++) {
-					$attributeValues .= $targetList->item($y)->attributes->item($i)->value . '|'; // DOMAttr? (TODO: test)
-				}
-				
-				/* First, check the elements attributes to see if any of them contain youtube or vimeo */
-				if (preg_match($this->regexps['video'], $attributeValues)) {
-					continue;
-				}
-
-				/* Then check the elements inside this element for the same. */
-				if (preg_match($this->regexps['video'], $targetList->item($y)->innerHTML)) {
-					continue;
-				}
-			}
-			$targetList->item($y)->parentNode->removeChild($targetList->item($y));
-		}
-	}
-	
-	/**
-	* Clean an element of all tags of type "tag" if they look fishy.
-	* "Fishy" is an algorithm based on content length, classnames, 
-	* link density, number of images & embeds, etc.
-	*
-	* @param DOMElement $e
-	* @param string $tag
-	* @return void
-	*/
-	public function cleanConditionally($e, $tag) {
-		if (!$this->flagIsActive(self::FLAG_CLEAN_CONDITIONALLY)) {
-			return;
-		}
-
-		$tagsList = $e->getElementsByTagName($tag);
-		$curTagsLength = $tagsList->length;
-
-		/**
-		* Gather counts for other typical elements embedded within.
-		* Traverse backwards so we can remove nodes at the same time without effecting the traversal.
-		*
-		* TODO: Consider taking into account original contentScore here.
-		*/
-		for ($i=$curTagsLength-1; $i >= 0; $i--) {
-			$weight = $this->getClassWeight($tagsList->item($i));
-			$contentScore = ($tagsList->item($i)->hasAttribute('readability')) ? (int)$tagsList->item($i)->getAttribute('readability') : 0;
-			
-			$this->dbg('Cleaning Conditionally ' . $tagsList->item($i)->tagName . ' (' . $tagsList->item($i)->getAttribute('class') . ':' . $tagsList->item($i)->getAttribute('id') . ')' . (($tagsList->item($i)->hasAttribute('readability')) ? (' with score ' . $tagsList->item($i)->getAttribute('readability')) : ''));
-
-			if ($weight + $contentScore < 0) {
-				$tagsList->item($i)->parentNode->removeChild($tagsList->item($i));
-			}
-			else if ( $this->getCharCount($tagsList->item($i), ',') < 10) {
-				/**
-				* If there are not very many commas, and the number of
-				* non-paragraph elements is more than paragraphs or other ominous signs, remove the element.
-				**/
-				$p      = $tagsList->item($i)->getElementsByTagName('p')->length;
-				$img    = $tagsList->item($i)->getElementsByTagName('img')->length;
-				$li     = $tagsList->item($i)->getElementsByTagName('li')->length-100;
-				$input  = $tagsList->item($i)->getElementsByTagName('input')->length;
-				$a 		= $tagsList->item($i)->getElementsByTagName('a')->length;
-
-				$embedCount = 0;
-				$embeds = $tagsList->item($i)->getElementsByTagName('embed');
-				for ($ei=0, $il=$embeds->length; $ei < $il; $ei++) {
-					if (preg_match($this->regexps['video'], $embeds->item($ei)->getAttribute('src'))) {
-						$embedCount++; 
-					}
-				}
-				$embeds = $tagsList->item($i)->getElementsByTagName('iframe');
-				for ($ei=0, $il=$embeds->length; $ei < $il; $ei++) {
-					if (preg_match($this->regexps['video'], $embeds->item($ei)->getAttribute('src'))) {
-						$embedCount++; 
-					}
-				}
-
-				$linkDensity   = $this->getLinkDensity($tagsList->item($i));
-				$contentLength = strlen($this->getInnerText($tagsList->item($i)));
-				$toRemove      = false;
-
-				if ($this->lightClean) {
-					$this->dbg('Light clean...');
-					if ( ($img > $p) && ($img > 4) ) {
-						$this->dbg(' more than 4 images and more image elements than paragraph elements');
-						$toRemove = true;
-					} else if ($li > $p && $tag != 'ul' && $tag != 'ol') {
-						$this->dbg(' too many 
  •  elements, and parent is not 
       or 
        ');
-						$toRemove = true;
-					} else if ( $input > floor($p/3) ) {
-						$this->dbg(' too many  elements');
-						$toRemove = true; 
-					} else if ($contentLength < 25 && ($embedCount === 0 && ($img === 0 || $img > 2))) {
-						$this->dbg(' content length less than 25 chars, 0 embeds and either 0 images or more than 2 images');
-						$toRemove = true;
-					} else if($weight < 25 && $linkDensity > 0.2) {
-						$this->dbg(' weight smaller than 25 and link density above 0.2');
-						$toRemove = true;
-					} else if($a > 2 && ($weight >= 25 && $linkDensity > 0.5)) {
-						$this->dbg(' more than 2 links and weight above 25 but link density greater than 0.5');
-						$toRemove = true;
-					} else if($embedCount > 3) {
-						$this->dbg(' more than 3 embeds');
-						$toRemove = true;
-					}
-				} else {
-					$this->dbg('Standard clean...');
-					if ( $img > $p ) {
-						$this->dbg(' more image elements than paragraph elements');
-						$toRemove = true;
-					} else if ($li > $p && $tag != 'ul' && $tag != 'ol') {
-						$this->dbg(' too many 
      1.  elements, and parent is not 
           or 
            ');
-						$toRemove = true;
-					} else if ( $input > floor($p/3) ) {
-						$this->dbg(' too many  elements');
-						$toRemove = true; 
-					} else if ($contentLength < 25 && ($img === 0 || $img > 2) ) {
-						$this->dbg(' content length less than 25 chars and 0 images, or more than 2 images');
-						$toRemove = true;
-					} else if($weight < 25 && $linkDensity > 0.2) {
-						$this->dbg(' weight smaller than 25 and link density above 0.2');
-						$toRemove = true;
-					} else if($weight >= 25 && $linkDensity > 0.5) {
-						$this->dbg(' weight above 25 but link density greater than 0.5');
-						$toRemove = true;
-					} else if(($embedCount == 1 && $contentLength < 75) || $embedCount > 1) {
-						$this->dbg(' 1 embed and content length smaller than 75 chars, or more than one embed');
-						$toRemove = true;
-					}
-				}
-
-				if ($toRemove) {
-					//$this->dbg('Removing: '.$tagsList->item($i)->innerHTML);
-					$tagsList->item($i)->parentNode->removeChild($tagsList->item($i));
-				}
-			}
-		}
-	}
-
-	/**
-	* Clean out spurious headers from an Element. Checks things like classnames and link density.
-	*
-	* @param DOMElement $e
-	* @return void
-	*/
-	public function cleanHeaders($e) {
-		for ($headerIndex = 1; $headerIndex < 3; $headerIndex++) {
-			$headers = $e->getElementsByTagName('h' . $headerIndex);
-			for ($i=$headers->length-1; $i >=0; $i--) {
-				if ($this->getClassWeight($headers->item($i)) < 0 || $this->getLinkDensity($headers->item($i)) > 0.33) {
-					$headers->item($i)->parentNode->removeChild($headers->item($i));
-				}
-			}
-		}
-	}
-
-	public function flagIsActive($flag) {
-		return ($this->flags & $flag) > 0;
-	}
-	
-	public function addFlag($flag) {
-		$this->flags = $this->flags | $flag;
-	}
-	
-	public function removeFlag($flag) {
-		$this->flags = $this->flags & ~$flag;
-	}
-}
+init();
+echo $r->articleContent->innerHTML;
+*/
+
+class Readability
+{
+	public $version = '1.7.1-without-multi-page';
+	public $convertLinksToFootnotes = false;
+	public $revertForcedParagraphElements = true;
+	public $articleTitle;
+	public $articleContent;
+	public $dom;
+	public $url = null; // optional - URL where HTML was retrieved
+	public $debug = false;
+	public $lightClean = true; // preserves more content (experimental) added 2012-09-19
+	protected $body = null; // 
+	protected $bodyCache = null; // Cache the body HTML in case we need to re-use it later
+	protected $flags = 7; // 1 | 2 | 4;   // Start with all flags set.
+	protected $success = false; // indicates whether we were able to extract or not
+	
+	/**
+	* All of the regular expressions in use within readability.
+	* Defined up here so we don't instantiate them repeatedly in loops.
+	**/
+	public $regexps = array(
+		'unlikelyCandidates' => '/combx|comment|community|disqus|extra|foot|header|menu|remark|rss|shoutbox|sidebar|sponsor|ad-break|agegate|pagination|pager|popup/i',
+		'okMaybeItsACandidate' => '/and|article|body|column|main|shadow/i',
+		'positive' => '/article|body|content|entry|hentry|main|page|attachment|pagination|post|text|blog|story/i',
+		'negative' => '/combx|comment|com-|contact|foot|footer|_nav|footnote|masthead|media|meta|outbrain|promo|related|scroll|shoutbox|sidebar|sponsor|shopping|tags|tool|widget/i',
+		'divToPElements' => '/<(a|blockquote|dl|div|img|ol|p|pre|table|ul)/i',
+		'replaceBrs' => '/(]*>[ \n\r\t]*){2,}/i',
+		'replaceFonts' => '/<(\/?)font[^>]*>/i',
+		// 'trimRe' => '/^\s+|\s+$/g', // PHP has trim()
+		'normalize' => '/\s{2,}/',
+		'killBreaks' => '/((\s| ?)*){1,}/',
+		'video' => '!//(player\.|www\.)?(youtube|vimeo|viddler)\.com!i',
+		'skipFootnoteLink' => '/^\s*(\[?[a-z0-9]{1,2}\]?|^|edit|citation needed)\s*$/i'
+	);	
+	
+	/* constants */
+	const FLAG_STRIP_UNLIKELYS = 1;
+	const FLAG_WEIGHT_CLASSES = 2;
+	const FLAG_CLEAN_CONDITIONALLY = 4;
+	
+	/**
+	* Create instance of Readability
+	* @param string UTF-8 encoded string
+	* @param string (optional) URL associated with HTML (used for footnotes)
+	* @param string which parser to use for turning raw HTML into a DOMDocument (either 'libxml' or 'html5lib')
+	*/	
+	function __construct($html, $url=null, $parser='libxml')
+	{
+		$this->url = $url;
+		/* Turn all double br's into p's */
+		$html = preg_replace($this->regexps['replaceBrs'], '
            ', $html);
+		$html = preg_replace($this->regexps['replaceFonts'], '<$1span>', $html);
+		$html = mb_convert_encoding($html, 'HTML-ENTITIES', "UTF-8");
+		if (trim($html) == '') $html = '';
+		if ($parser=='html5lib' && ($this->dom = HTML5_Parser::parse($html))) {
+			// all good
+		} else {
+			$this->dom = new DOMDocument();
+			$this->dom->preserveWhiteSpace = false;
+			@$this->dom->loadHTML($html);
+		}
+		$this->dom->registerNodeClass('DOMElement', 'JSLikeHTMLElement');
+	}
+
+	/**
+	* Get article title element
+	* @return DOMElement
+	*/
+	public function getTitle() {
+		return $this->articleTitle;
+	}
+	
+	/**
+	* Get article content element
+	* @return DOMElement
+	*/
+	public function getContent() {
+		return $this->articleContent;
+	}	
+	
+	/**
+	* Runs readability.
+	* 
+	* Workflow:
+	*  1. Prep the document by removing script tags, css, etc.
+	*  2. Build readability's DOM tree.
+	*  3. Grab the article content from the current dom tree.
+	*  4. Replace the current DOM tree with the new one.
+	*  5. Read peacefully.
+	*
+	* @return boolean true if we found content, false otherwise
+	**/
+	public function init()
+	{
+		if (!isset($this->dom->documentElement)) return false;
+		$this->removeScripts($this->dom);
+		//die($this->getInnerHTML($this->dom->documentElement));
+		
+		// Assume successful outcome
+		$this->success = true;
+
+		$bodyElems = $this->dom->getElementsByTagName('body');
+		if ($bodyElems->length > 0) {
+			if ($this->bodyCache == null) {
+				$this->bodyCache = $bodyElems->item(0)->innerHTML;
+			}
+			if ($this->body == null) {
+				$this->body = $bodyElems->item(0);
+			}
+		}
+
+		$this->prepDocument();
+		
+		//die($this->dom->documentElement->parentNode->nodeType);
+		//$this->setInnerHTML($this->dom->documentElement, $this->getInnerHTML($this->dom->documentElement));
+		//die($this->getInnerHTML($this->dom->documentElement));
+
+		/* Build readability's DOM tree */
+		$overlay        = $this->dom->createElement('div');
+		$innerDiv       = $this->dom->createElement('div');
+		$articleTitle   = $this->getArticleTitle();
+		$articleContent = $this->grabArticle();
+
+		if (!$articleContent) {
+			$this->success = false;
+			$articleContent = $this->dom->createElement('div');
+			$articleContent->setAttribute('id', 'readability-content');
+			$articleContent->innerHTML = '
            Sorry, Readability was unable to parse this page for content.
            ';		
+		}
+		
+		$overlay->setAttribute('id', 'readOverlay');
+		$innerDiv->setAttribute('id', 'readInner');
+
+		/* Glue the structure of our document together. */
+		$innerDiv->appendChild($articleTitle);
+		$innerDiv->appendChild($articleContent);
+		$overlay->appendChild($innerDiv);
+		
+		/* Clear the old HTML, insert the new content. */
+		$this->body->innerHTML = '';
+		$this->body->appendChild($overlay);
+		//document.body.insertBefore(overlay, document.body.firstChild);
+		$this->body->removeAttribute('style');
+
+		$this->postProcessContent($articleContent);
+		
+		// Set title and content instance variables
+		$this->articleTitle = $articleTitle;
+		$this->articleContent = $articleContent;
+		
+		return $this->success;
+	}
+	
+	/**
+	* Debug
+	*/
+	protected function dbg($msg) {
+		if ($this->debug) echo '* ',$msg, "\n";
+	}
+	
+	/**
+	* Run any post-process modifications to article content as necessary.
+	*
+	* @param DOMElement
+	* @return void
+	*/
+	public function postProcessContent($articleContent) {
+		if ($this->convertLinksToFootnotes && !preg_match('/wikipedia\.org/', @$this->url)) { 
+			$this->addFootnotes($articleContent);
+		}
+	}
+	
+	/**
+	* Get the article title as an H1.
+	*
+	* @return DOMElement
+	*/
+	protected function getArticleTitle() {
+		$curTitle = '';
+		$origTitle = '';
+
+		try {
+			$curTitle = $origTitle = $this->getInnerText($this->dom->getElementsByTagName('title')->item(0));
+		} catch(Exception $e) {}
+		
+		if (preg_match('/ [\|\-] /', $curTitle))
+		{
+			$curTitle = preg_replace('/(.*)[\|\-] .*/i', '$1', $origTitle);
+			
+			if (count(explode(' ', $curTitle)) < 3) {
+				$curTitle = preg_replace('/[^\|\-]*[\|\-](.*)/i', '$1', $origTitle);
+			}
+		}
+		else if (strpos($curTitle, ': ') !== false)
+		{
+			$curTitle = preg_replace('/.*:(.*)/i', '$1', $origTitle);
+
+			if (count(explode(' ', $curTitle)) < 3) {
+				$curTitle = preg_replace('/[^:]*[:](.*)/i','$1', $origTitle);
+			}
+		}
+		else if(strlen($curTitle) > 150 || strlen($curTitle) < 15)
+		{
+			$hOnes = $this->dom->getElementsByTagName('h1');
+			if($hOnes->length == 1)
+			{
+				$curTitle = $this->getInnerText($hOnes->item(0));
+			}
+		}
+
+		$curTitle = trim($curTitle);
+
+		if (count(explode(' ', $curTitle)) <= 4) {
+			$curTitle = $origTitle;
+		}
+		
+		$articleTitle = $this->dom->createElement('h1');
+		$articleTitle->innerHTML = $curTitle;
+		
+		return $articleTitle;
+	}
+	
+	/**
+	* Prepare the HTML document for readability to scrape it.
+	* This includes things like stripping javascript, CSS, and handling terrible markup.
+	* 
+	* @return void
+	**/
+	protected function prepDocument() {
+		/**
+		* In some cases a body element can't be found (if the HTML is totally hosed for example)
+		* so we create a new body node and append it to the document.
+		*/
+		if ($this->body == null)
+		{
+			$this->body = $this->dom->createElement('body');
+			$this->dom->documentElement->appendChild($this->body);
+		}
+		$this->body->setAttribute('id', 'readabilityBody');
+
+		/* Remove all style tags in head */
+		$styleTags = $this->dom->getElementsByTagName('style');
+		for ($i = $styleTags->length-1; $i >= 0; $i--)
+		{
+			$styleTags->item($i)->parentNode->removeChild($styleTags->item($i));
+		}
+
+		/* Turn all double br's into p's */
+		/* Note, this is pretty costly as far as processing goes. Maybe optimize later. */
+		//document.body.innerHTML = document.body.innerHTML.replace(readability.regexps.replaceBrs, '
            ').replace(readability.regexps.replaceFonts, '<$1span>');
+		// We do this in the constructor for PHP as that's when we have raw HTML - before parsing it into a DOM tree.
+		// Manipulating innerHTML as it's done in JS is not possible in PHP.
+	}
+
+	/**
+	* For easier reading, convert this document to have footnotes at the bottom rather than inline links.
+	* @see http://www.roughtype.com/archives/2010/05/experiments_in.php
+	*
+	* @return void
+	**/
+	public function addFootnotes($articleContent) {
+		$footnotesWrapper = $this->dom->createElement('div');
+		$footnotesWrapper->setAttribute('id', 'readability-footnotes');
+		$footnotesWrapper->innerHTML = '
            References
            ';
+		
+		$articleFootnotes = $this->dom->createElement('ol');
+		$articleFootnotes->setAttribute('id', 'readability-footnotes-list');
+		$footnotesWrapper->appendChild($articleFootnotes);
+		
+		$articleLinks = $articleContent->getElementsByTagName('a');
+		
+		$linkCount = 0;
+		for ($i = 0; $i < $articleLinks->length; $i++)
+		{
+			$articleLink  = $articleLinks->item($i);
+			$footnoteLink = $articleLink->cloneNode(true);
+			$refLink      = $this->dom->createElement('a');
+			$footnote     = $this->dom->createElement('li');
+			$linkDomain   = @parse_url($footnoteLink->getAttribute('href'), PHP_URL_HOST);
+			if (!$linkDomain && isset($this->url)) $linkDomain = @parse_url($this->url, PHP_URL_HOST);
+			//linkDomain   = footnoteLink.host ? footnoteLink.host : document.location.host,
+			$linkText     = $this->getInnerText($articleLink);
+			
+			if ((strpos($articleLink->getAttribute('class'), 'readability-DoNotFootnote') !== false) || preg_match($this->regexps['skipFootnoteLink'], $linkText)) {
+				continue;
+			}
+			
+			$linkCount++;
+
+			/** Add a superscript reference after the article link */
+			$refLink->setAttribute('href', '#readabilityFootnoteLink-' . $linkCount);
+			$refLink->innerHTML = '[' . $linkCount . ']';
+			$refLink->setAttribute('class', 'readability-DoNotFootnote');
+			$refLink->setAttribute('style', 'color: inherit;');
+			
+			//TODO: does this work or should we use DOMNode.isSameNode()?
+			if ($articleLink->parentNode->lastChild == $articleLink) {
+				$articleLink->parentNode->appendChild($refLink);
+			} else {
+				$articleLink->parentNode->insertBefore($refLink, $articleLink->nextSibling);
+			}
+
+			$articleLink->setAttribute('style', 'color: inherit; text-decoration: none;');
+			$articleLink->setAttribute('name', 'readabilityLink-' . $linkCount);
+
+			$footnote->innerHTML = '^ ';
+
+			$footnoteLink->innerHTML = ($footnoteLink->getAttribute('title') != '' ? $footnoteLink->getAttribute('title') : $linkText);
+			$footnoteLink->setAttribute('name', 'readabilityFootnoteLink-' . $linkCount);
+			
+			$footnote->appendChild($footnoteLink);
+			if ($linkDomain) $footnote->innerHTML = $footnote->innerHTML . ' (' . $linkDomain . ')';
+			
+			$articleFootnotes->appendChild($footnote);
+		}
+
+		if ($linkCount > 0) {
+			$articleContent->appendChild($footnotesWrapper);           
+		}
+	}
+
+	/**
+	* Reverts P elements with class 'readability-styled'
+	* to text nodes - which is what they were before.
+	*
+	* @param DOMElement
+	* @return void
+	*/
+	function revertReadabilityStyledElements($articleContent) {
+		$xpath = new DOMXPath($articleContent->ownerDocument);
+		$elems = $xpath->query('.//p[@class="readability-styled"]', $articleContent);
+		//$elems = $articleContent->getElementsByTagName('p');
+		for ($i = $elems->length-1; $i >= 0; $i--) {
+			$e = $elems->item($i);
+			$e->parentNode->replaceChild($articleContent->ownerDocument->createTextNode($e->textContent), $e);
+			//if ($e->hasAttribute('class') && $e->getAttribute('class') == 'readability-styled') {
+			//	$e->parentNode->replaceChild($this->dom->createTextNode($e->textContent), $e);
+			//}
+		}
+	}
+	
+	/**
+	* Prepare the article node for display. Clean out any inline styles,
+	* iframes, forms, strip extraneous 
             tags, etc.
+	*
+	* @param DOMElement
+	* @return void
+	*/
+	function prepArticle($articleContent) {
+		$this->cleanStyles($articleContent);
+		$this->killBreaks($articleContent);
+		if ($this->revertForcedParagraphElements) {
+			$this->revertReadabilityStyledElements($articleContent);
+		}
+
+		/* Clean out junk from the article content */
+		$this->cleanConditionally($articleContent, 'form');
+		$this->clean($articleContent, 'object');
+		$this->clean($articleContent, 'h1');
+
+		/**
+		* If there is only one h2, they are probably using it
+		* as a header and not a subheader, so remove it since we already have a header.
+		***/
+		if (!$this->lightClean && ($articleContent->getElementsByTagName('h2')->length == 1)) {
+			$this->clean($articleContent, 'h2'); 
+		}
+		$this->clean($articleContent, 'iframe');
+
+		$this->cleanHeaders($articleContent);
+
+		/* Do these last as the previous stuff may have removed junk that will affect these */
+		$this->cleanConditionally($articleContent, 'table');
+		$this->cleanConditionally($articleContent, 'ul');
+		$this->cleanConditionally($articleContent, 'div');
+
+		/* Remove extra paragraphs */
+		$articleParagraphs = $articleContent->getElementsByTagName('p');
+		for ($i = $articleParagraphs->length-1; $i >= 0; $i--)
+		{
+			$imgCount    = $articleParagraphs->item($i)->getElementsByTagName('img')->length;
+			$embedCount  = $articleParagraphs->item($i)->getElementsByTagName('embed')->length;
+			$objectCount = $articleParagraphs->item($i)->getElementsByTagName('object')->length;
+			$iframeCount = $articleParagraphs->item($i)->getElementsByTagName('iframe')->length;
+			
+			if ($imgCount === 0 && $embedCount === 0 && $objectCount === 0 && $iframeCount === 0 && $this->getInnerText($articleParagraphs->item($i), false) == '')
+			{
+				$articleParagraphs->item($i)->parentNode->removeChild($articleParagraphs->item($i));
+			}
+		}
+
+		try {
+			$articleContent->innerHTML = preg_replace('/]*>\s*
            innerHTML);
+			//articleContent.innerHTML = articleContent.innerHTML.replace(/]*>\s*
            dbg("Cleaning innerHTML of breaks failed. This is an IE strict-block-elements bug. Ignoring.: " . $e);
+		}
+	}
+	
+	/**
+	* Initialize a node with the readability object. Also checks the
+	* className/id for special names to add to its score.
+	*
+	* @param Element
+	* @return void
+	**/
+	protected function initializeNode($node) {
+		$readability = $this->dom->createAttribute('readability');
+		$readability->value = 0; // this is our contentScore
+		$node->setAttributeNode($readability);		         
+
+		switch (strtoupper($node->tagName)) { // unsure if strtoupper is needed, but using it just in case
+			case 'DIV':
+				$readability->value += 5;
+				break;
+
+			case 'PRE':
+			case 'TD':
+			case 'BLOCKQUOTE':
+				$readability->value += 3;
+				break;
+				
+			case 'ADDRESS':
+			case 'OL':
+			case 'UL':
+			case 'DL':
+			case 'DD':
+			case 'DT':
+			case 'LI':
+			case 'FORM':
+				$readability->value -= 3;
+				break;
+
+			case 'H1':
+			case 'H2':
+			case 'H3':
+			case 'H4':
+			case 'H5':
+			case 'H6':
+			case 'TH':
+				$readability->value -= 5;
+				break;
+		}
+		$readability->value += $this->getClassWeight($node);
+	}
+	
+	/***
+	* grabArticle - Using a variety of metrics (content score, classname, element types), find the content that is
+	*               most likely to be the stuff a user wants to read. Then return it wrapped up in a div.
+	*
+	* @return DOMElement
+	**/
+	protected function grabArticle($page=null) {
+		$stripUnlikelyCandidates = $this->flagIsActive(self::FLAG_STRIP_UNLIKELYS);
+		if (!$page) $page = $this->dom;
+		$allElements = $page->getElementsByTagName('*');
+		/**
+		* First, node prepping. Trash nodes that look cruddy (like ones with the class name "comment", etc), and turn divs
+		* into P tags where they have been used inappropriately (as in, where they contain no other block level elements.)
+		*
+		* Note: Assignment from index for performance. See http://www.peachpit.com/articles/article.aspx?p=31567&seqNum=5
+		* TODO: Shouldn't this be a reverse traversal?
+		**/
+		$node = null;
+		$nodesToScore = array();
+		for ($nodeIndex = 0; ($node = $allElements->item($nodeIndex)); $nodeIndex++) {
+		//for ($nodeIndex=$targetList->length-1; $nodeIndex >= 0; $nodeIndex--) {
+			//$node = $targetList->item($nodeIndex);
+			$tagName = strtoupper($node->tagName);
+			/* Remove unlikely candidates */
+			if ($stripUnlikelyCandidates) {
+				$unlikelyMatchString = $node->getAttribute('class') . $node->getAttribute('id');
+				if (
+					preg_match($this->regexps['unlikelyCandidates'], $unlikelyMatchString) &&
+					!preg_match($this->regexps['okMaybeItsACandidate'], $unlikelyMatchString) &&
+					$tagName != 'BODY'
+				)
+				{
+					$this->dbg('Removing unlikely candidate - ' . $unlikelyMatchString);
+					//$nodesToRemove[] = $node;
+					$node->parentNode->removeChild($node);
+					$nodeIndex--;
+					continue;
+				}               
+			}
+
+			if ($tagName == 'P' || $tagName == 'TD' || $tagName == 'PRE') {
+				$nodesToScore[] = $node;
+			}
+
+			/* Turn all divs that don't have children block level elements into p's */
+			if ($tagName == 'DIV') {
+				if (!preg_match($this->regexps['divToPElements'], $node->innerHTML)) {
+					//$this->dbg('Altering div to p');
+					$newNode = $this->dom->createElement('p');
+					try {
+						$newNode->innerHTML = $node->innerHTML;
+						//$nodesToReplace[] = array('new'=>$newNode, 'old'=>$node);
+						$node->parentNode->replaceChild($newNode, $node);
+						$nodeIndex--;
+						$nodesToScore[] = $node; // or $newNode?
+					}
+					catch(Exception $e) {
+						$this->dbg('Could not alter div to p, reverting back to div.: ' . $e);
+					}
+				}
+				else
+				{
+					/* EXPERIMENTAL */
+					// TODO: change these p elements back to text nodes after processing
+					for ($i = 0, $il = $node->childNodes->length; $i < $il; $i++) {
+						$childNode = $node->childNodes->item($i);
+						if ($childNode->nodeType == 3) { // XML_TEXT_NODE
+							//$this->dbg('replacing text node with a p tag with the same content.');
+							$p = $this->dom->createElement('p');
+							$p->innerHTML = $childNode->nodeValue;
+							$p->setAttribute('style', 'display: inline;');
+							$p->setAttribute('class', 'readability-styled');
+							$childNode->parentNode->replaceChild($p, $childNode);
+						}
+					}
+				}
+			}
+		}
+		
+		/**
+		* Loop through all paragraphs, and assign a score to them based on how content-y they look.
+		* Then add their score to their parent node.
+		*
+		* A score is determined by things like number of commas, class names, etc. Maybe eventually link density.
+		**/
+		$candidates = array();
+		for ($pt=0; $pt < count($nodesToScore); $pt++) {
+			$parentNode      = $nodesToScore[$pt]->parentNode;
+			// $grandParentNode = $parentNode ? $parentNode->parentNode : null;
+			$grandParentNode = !$parentNode ? null : (($parentNode->parentNode instanceof DOMElement) ? $parentNode->parentNode : null);
+			$innerText       = $this->getInnerText($nodesToScore[$pt]);
+
+			if (!$parentNode || !isset($parentNode->tagName)) {
+				continue;
+			}
+
+			/* If this paragraph is less than 25 characters, don't even count it. */
+			if(strlen($innerText) < 25) {
+				continue;
+			}
+
+			/* Initialize readability data for the parent. */
+			if (!$parentNode->hasAttribute('readability')) 
+			{
+				$this->initializeNode($parentNode);
+				$candidates[] = $parentNode;
+			}
+
+			/* Initialize readability data for the grandparent. */
+			if ($grandParentNode && !$grandParentNode->hasAttribute('readability') && isset($grandParentNode->tagName))
+			{
+				$this->initializeNode($grandParentNode);
+				$candidates[] = $grandParentNode;
+			}
+
+			$contentScore = 0;
+
+			/* Add a point for the paragraph itself as a base. */
+			$contentScore++;
+
+			/* Add points for any commas within this paragraph */
+			$contentScore += count(explode(',', $innerText));
+			
+			/* For every 100 characters in this paragraph, add another point. Up to 3 points. */
+			$contentScore += min(floor(strlen($innerText) / 100), 3);
+			
+			/* Add the score to the parent. The grandparent gets half. */
+			$parentNode->getAttributeNode('readability')->value += $contentScore;
+
+			if ($grandParentNode) {
+				$grandParentNode->getAttributeNode('readability')->value += $contentScore/2;             
+			}
+		}
+
+		/**
+		* After we've calculated scores, loop through all of the possible candidate nodes we found
+		* and find the one with the highest score.
+		**/
+		$topCandidate = null;
+		for ($c=0, $cl=count($candidates); $c < $cl; $c++)
+		{
+			/**
+			* Scale the final candidates score based on link density. Good content should have a
+			* relatively small link density (5% or less) and be mostly unaffected by this operation.
+			**/
+			$readability = $candidates[$c]->getAttributeNode('readability');
+			$readability->value = $readability->value * (1-$this->getLinkDensity($candidates[$c]));
+
+			$this->dbg('Candidate: ' . $candidates[$c]->tagName . ' (' . $candidates[$c]->getAttribute('class') . ':' . $candidates[$c]->getAttribute('id') . ') with score ' . $readability->value);
+
+			if (!$topCandidate || $readability->value > (int)$topCandidate->getAttribute('readability')) {
+				$topCandidate = $candidates[$c];
+			}
+		}
+
+		/**
+		* If we still have no top candidate, just use the body as a last resort.
+		* We also have to copy the body node so it is something we can modify.
+		**/
+		if ($topCandidate === null || strtoupper($topCandidate->tagName) == 'BODY')
+		{
+			$topCandidate = $this->dom->createElement('div');
+			if ($page instanceof DOMDocument) {
+				if (!isset($page->documentElement)) {
+					// we don't have a body either? what a mess! :)
+				} else {
+					$topCandidate->innerHTML = $page->documentElement->innerHTML;
+					$page->documentElement->innerHTML = '';
+					$page->documentElement->appendChild($topCandidate);
+				}
+			} else {
+				$topCandidate->innerHTML = $page->innerHTML;
+				$page->innerHTML = '';
+				$page->appendChild($topCandidate);
+			}
+			$this->initializeNode($topCandidate);
+		}
+
+		/**
+		* Now that we have the top candidate, look through its siblings for content that might also be related.
+		* Things like preambles, content split by ads that we removed, etc.
+		**/
+		$articleContent        = $this->dom->createElement('div');
+		$articleContent->setAttribute('id', 'readability-content');
+		$siblingScoreThreshold = max(10, ((int)$topCandidate->getAttribute('readability')) * 0.2);
+		$siblingNodes          = $topCandidate->parentNode->childNodes;
+		if (!isset($siblingNodes)) {
+			$siblingNodes = new stdClass;
+			$siblingNodes->length = 0;
+		}
+
+		for ($s=0, $sl=$siblingNodes->length; $s < $sl; $s++)
+		{
+			$siblingNode = $siblingNodes->item($s);
+			$append      = false;
+
+			$this->dbg('Looking at sibling node: ' . $siblingNode->nodeName . (($siblingNode->nodeType === XML_ELEMENT_NODE && $siblingNode->hasAttribute('readability')) ? (' with score ' . $siblingNode->getAttribute('readability')) : ''));
+
+			//dbg('Sibling has score ' . ($siblingNode->readability ? siblingNode.readability.contentScore : 'Unknown'));
+
+			if ($siblingNode === $topCandidate)
+			// or if ($siblingNode->isSameNode($topCandidate))
+			{
+				$append = true;
+			}
+
+			$contentBonus = 0;
+			/* Give a bonus if sibling nodes and top candidates have the example same classname */
+			if ($siblingNode->nodeType === XML_ELEMENT_NODE && $siblingNode->getAttribute('class') == $topCandidate->getAttribute('class') && $topCandidate->getAttribute('class') != '') {
+				$contentBonus += ((int)$topCandidate->getAttribute('readability')) * 0.2;
+			}
+
+			if ($siblingNode->nodeType === XML_ELEMENT_NODE && $siblingNode->hasAttribute('readability') && (((int)$siblingNode->getAttribute('readability')) + $contentBonus) >= $siblingScoreThreshold)
+			{
+				$append = true;
+			}
+			
+			if (strtoupper($siblingNode->nodeName) == 'P') {
+				$linkDensity = $this->getLinkDensity($siblingNode);
+				$nodeContent = $this->getInnerText($siblingNode);
+				$nodeLength  = strlen($nodeContent);
+				
+				if ($nodeLength > 80 && $linkDensity < 0.25)
+				{
+					$append = true;
+				}
+				else if ($nodeLength < 80 && $linkDensity === 0 && preg_match('/\.( |$)/', $nodeContent))
+				{
+					$append = true;
+				}
+			}
+
+			if ($append)
+			{
+				$this->dbg('Appending node: ' . $siblingNode->nodeName);
+
+				$nodeToAppend = null;
+				$sibNodeName = strtoupper($siblingNode->nodeName);
+				if ($sibNodeName != 'DIV' && $sibNodeName != 'P') {
+					/* We have a node that isn't a common block level element, like a form or td tag. Turn it into a div so it doesn't get filtered out later by accident. */
+					
+					$this->dbg('Altering siblingNode of ' . $sibNodeName . ' to div.');
+					$nodeToAppend = $this->dom->createElement('div');
+					try {
+						$nodeToAppend->setAttribute('id', $siblingNode->getAttribute('id'));
+						$nodeToAppend->innerHTML = $siblingNode->innerHTML;
+					}
+					catch(Exception $e)
+					{
+						$this->dbg('Could not alter siblingNode to div, reverting back to original.');
+						$nodeToAppend = $siblingNode;
+						$s--;
+						$sl--;
+					}
+				} else {
+					$nodeToAppend = $siblingNode;
+					$s--;
+					$sl--;
+				}
+				
+				/* To ensure a node does not interfere with readability styles, remove its classnames */
+				$nodeToAppend->removeAttribute('class');
+
+				/* Append sibling and subtract from our list because it removes the node when you append to another node */
+				$articleContent->appendChild($nodeToAppend);
+			}
+		}
+
+		/**
+		* So we have all of the content that we need. Now we clean it up for presentation.
+		**/
+		$this->prepArticle($articleContent);
+
+		/**
+		* Now that we've gone through the full algorithm, check to see if we got any meaningful content.
+		* If we didn't, we may need to re-run grabArticle with different flags set. This gives us a higher
+		* likelihood of finding the content, and the sieve approach gives us a higher likelihood of
+		* finding the -right- content.
+		**/
+		if (strlen($this->getInnerText($articleContent, false)) < 250)
+		{
+			// TODO: find out why element disappears sometimes, e.g. for this URL http://www.businessinsider.com/6-hedge-fund-etfs-for-average-investors-2011-7
+			// in the meantime, we check and create an empty element if it's not there.
+			if (!isset($this->body->childNodes)) $this->body = $this->dom->createElement('body');
+			$this->body->innerHTML = $this->bodyCache;
+			
+			if ($this->flagIsActive(self::FLAG_STRIP_UNLIKELYS)) {
+				$this->removeFlag(self::FLAG_STRIP_UNLIKELYS);
+				return $this->grabArticle($this->body);
+			}
+			else if ($this->flagIsActive(self::FLAG_WEIGHT_CLASSES)) {
+				$this->removeFlag(self::FLAG_WEIGHT_CLASSES);
+				return $this->grabArticle($this->body);              
+			}
+			else if ($this->flagIsActive(self::FLAG_CLEAN_CONDITIONALLY)) {
+				$this->removeFlag(self::FLAG_CLEAN_CONDITIONALLY);
+				return $this->grabArticle($this->body);
+			}
+			else {
+				return false;
+			}
+		}
+		return $articleContent;
+	}
+	
+	/**
+	* Remove script tags from document
+	*
+	* @param DOMElement
+	* @return void
+	*/
+	public function removeScripts($doc) {
+		$scripts = $doc->getElementsByTagName('script');
+		for($i = $scripts->length-1; $i >= 0; $i--)
+		{
+			$scripts->item($i)->parentNode->removeChild($scripts->item($i));
+		}
+	}
+	
+	/**
+	* Get the inner text of a node.
+	* This also strips out any excess whitespace to be found.
+	*
+	* @param DOMElement $
+	* @param boolean $normalizeSpaces (default: true)
+	* @return string
+	**/
+	public function getInnerText($e, $normalizeSpaces=true) {
+		$textContent = '';
+
+		if (!isset($e->textContent) || $e->textContent == '') {
+			return '';
+		}
+
+		$textContent = trim($e->textContent);
+
+		if ($normalizeSpaces) {
+			return preg_replace($this->regexps['normalize'], ' ', $textContent);
+		} else {
+			return $textContent;
+		}
+	}
+
+	/**
+	* Get the number of times a string $s appears in the node $e.
+	*
+	* @param DOMElement $e
+	* @param string - what to count. Default is ","
+	* @return number (integer)
+	**/
+	public function getCharCount($e, $s=',') {
+		return substr_count($this->getInnerText($e), $s);
+	}
+
+	/**
+	* Remove the style attribute on every $e and under.
+	*
+	* @param DOMElement $e
+	* @return void
+	*/
+	public function cleanStyles($e) {
+		if (!is_object($e)) return;
+		$elems = $e->getElementsByTagName('*');
+		foreach ($elems as $elem) {
+			$elem->removeAttribute('style');
+		}
+	}
+	
+	/**
+	* Get the density of links as a percentage of the content
+	* This is the amount of text that is inside a link divided by the total text in the node.
+	* 
+	* @param DOMElement $e
+	* @return number (float)
+	*/
+	public function getLinkDensity($e) {
+		$links      = $e->getElementsByTagName('a');
+		$textLength = strlen($this->getInnerText($e));
+		$linkLength = 0;
+		for ($i=0, $il=$links->length; $i < $il; $i++)
+		{
+			$linkLength += strlen($this->getInnerText($links->item($i)));
+		}
+		if ($textLength > 0) {
+			return $linkLength / $textLength;
+		} else {
+			return 0;
+		}
+	}
+	
+	/**
+	* Get an elements class/id weight. Uses regular expressions to tell if this 
+	* element looks good or bad.
+	*
+	* @param DOMElement $e
+	* @return number (Integer)
+	*/
+	public function getClassWeight($e) {
+		if(!$this->flagIsActive(self::FLAG_WEIGHT_CLASSES)) {
+			return 0;
+		}
+
+		$weight = 0;
+
+		/* Look for a special classname */
+		if ($e->hasAttribute('class') && $e->getAttribute('class') != '')
+		{
+			if (preg_match($this->regexps['negative'], $e->getAttribute('class'))) {
+				$weight -= 25;
+			}
+			if (preg_match($this->regexps['positive'], $e->getAttribute('class'))) {
+				$weight += 25;
+			}
+		}
+
+		/* Look for a special ID */
+		if ($e->hasAttribute('id') && $e->getAttribute('id') != '')
+		{
+			if (preg_match($this->regexps['negative'], $e->getAttribute('id'))) {
+				$weight -= 25;
+			}
+			if (preg_match($this->regexps['positive'], $e->getAttribute('id'))) {
+				$weight += 25;
+			}
+		}
+		return $weight;
+	}
+
+	/**
+	* Remove extraneous break tags from a node.
+	*
+	* @param DOMElement $node
+	* @return void
+	*/
+	public function killBreaks($node) {
+		$html = $node->innerHTML;
+		$html = preg_replace($this->regexps['killBreaks'], '
            ', $html);
+		$node->innerHTML = $html;
+	}
+
+	/**
+	* Clean a node of all elements of type "tag".
+	* (Unless it's a youtube/vimeo video. People love movies.)
+	*
+	* Updated 2012-09-18 to preserve youtube/vimeo iframes
+	*
+	* @param DOMElement $e
+	* @param string $tag
+	* @return void
+	*/
+	public function clean($e, $tag) {
+		$targetList = $e->getElementsByTagName($tag);
+		$isEmbed = ($tag == 'iframe' || $tag == 'object' || $tag == 'embed');
+		
+		for ($y=$targetList->length-1; $y >= 0; $y--) {
+			/* Allow youtube and vimeo videos through as people usually want to see those. */
+			if ($isEmbed) {
+				$attributeValues = '';
+				for ($i=0, $il=$targetList->item($y)->attributes->length; $i < $il; $i++) {
+					$attributeValues .= $targetList->item($y)->attributes->item($i)->value . '|'; // DOMAttr? (TODO: test)
+				}
+				
+				/* First, check the elements attributes to see if any of them contain youtube or vimeo */
+				if (preg_match($this->regexps['video'], $attributeValues)) {
+					continue;
+				}
+
+				/* Then check the elements inside this element for the same. */
+				if (preg_match($this->regexps['video'], $targetList->item($y)->innerHTML)) {
+					continue;
+				}
+			}
+			$targetList->item($y)->parentNode->removeChild($targetList->item($y));
+		}
+	}
+	
+	/**
+	* Clean an element of all tags of type "tag" if they look fishy.
+	* "Fishy" is an algorithm based on content length, classnames, 
+	* link density, number of images & embeds, etc.
+	*
+	* @param DOMElement $e
+	* @param string $tag
+	* @return void
+	*/
+	public function cleanConditionally($e, $tag) {
+		if (!$this->flagIsActive(self::FLAG_CLEAN_CONDITIONALLY)) {
+			return;
+		}
+
+		$tagsList = $e->getElementsByTagName($tag);
+		$curTagsLength = $tagsList->length;
+
+		/**
+		* Gather counts for other typical elements embedded within.
+		* Traverse backwards so we can remove nodes at the same time without effecting the traversal.
+		*
+		* TODO: Consider taking into account original contentScore here.
+		*/
+		for ($i=$curTagsLength-1; $i >= 0; $i--) {
+			$weight = $this->getClassWeight($tagsList->item($i));
+			$contentScore = ($tagsList->item($i)->hasAttribute('readability')) ? (int)$tagsList->item($i)->getAttribute('readability') : 0;
+			
+			$this->dbg('Cleaning Conditionally ' . $tagsList->item($i)->tagName . ' (' . $tagsList->item($i)->getAttribute('class') . ':' . $tagsList->item($i)->getAttribute('id') . ')' . (($tagsList->item($i)->hasAttribute('readability')) ? (' with score ' . $tagsList->item($i)->getAttribute('readability')) : ''));
+
+			if ($weight + $contentScore < 0) {
+				$tagsList->item($i)->parentNode->removeChild($tagsList->item($i));
+			}
+			else if ( $this->getCharCount($tagsList->item($i), ',') < 10) {
+				/**
+				* If there are not very many commas, and the number of
+				* non-paragraph elements is more than paragraphs or other ominous signs, remove the element.
+				**/
+				$p      = $tagsList->item($i)->getElementsByTagName('p')->length;
+				$img    = $tagsList->item($i)->getElementsByTagName('img')->length;
+				$li     = $tagsList->item($i)->getElementsByTagName('li')->length-100;
+				$input  = $tagsList->item($i)->getElementsByTagName('input')->length;
+				$a 		= $tagsList->item($i)->getElementsByTagName('a')->length;
+
+				$embedCount = 0;
+				$embeds = $tagsList->item($i)->getElementsByTagName('embed');
+				for ($ei=0, $il=$embeds->length; $ei < $il; $ei++) {
+					if (preg_match($this->regexps['video'], $embeds->item($ei)->getAttribute('src'))) {
+						$embedCount++; 
+					}
+				}
+				$embeds = $tagsList->item($i)->getElementsByTagName('iframe');
+				for ($ei=0, $il=$embeds->length; $ei < $il; $ei++) {
+					if (preg_match($this->regexps['video'], $embeds->item($ei)->getAttribute('src'))) {
+						$embedCount++; 
+					}
+				}
+
+				$linkDensity   = $this->getLinkDensity($tagsList->item($i));
+				$contentLength = strlen($this->getInnerText($tagsList->item($i)));
+				$toRemove      = false;
+
+				if ($this->lightClean) {
+					$this->dbg('Light clean...');
+					if ( ($img > $p) && ($img > 4) ) {
+						$this->dbg(' more than 4 images and more image elements than paragraph elements');
+						$toRemove = true;
+					} else if ($li > $p && $tag != 'ul' && $tag != 'ol') {
+						$this->dbg(' too many 
          1.  elements, and parent is not 
               or 
                ');
+						$toRemove = true;
+					} else if ( $input > floor($p/3) ) {
+						$this->dbg(' too many  elements');
+						$toRemove = true; 
+					} else if ($contentLength < 10 && ($embedCount === 0 && ($img === 0 || $img > 2))) {
+						$this->dbg(' content length less than 10 chars, 0 embeds and either 0 images or more than 2 images');
+						$toRemove = true;
+					} else if($weight < 25 && $linkDensity > 0.2) {
+						$this->dbg(' weight smaller than 25 and link density above 0.2');
+						$toRemove = true;
+					} else if($a > 2 && ($weight >= 25 && $linkDensity > 0.5)) {
+						$this->dbg(' more than 2 links and weight above 25 but link density greater than 0.5');
+						$toRemove = true;
+					} else if($embedCount > 3) {
+						$this->dbg(' more than 3 embeds');
+						$toRemove = true;
+					}
+				} else {
+					$this->dbg('Standard clean...');
+					if ( $img > $p ) {
+						$this->dbg(' more image elements than paragraph elements');
+						$toRemove = true;
+					} else if ($li > $p && $tag != 'ul' && $tag != 'ol') {
+						$this->dbg(' too many 
              1.  elements, and parent is not 
                   or 
                    ');
+						$toRemove = true;
+					} else if ( $input > floor($p/3) ) {
+						$this->dbg(' too many  elements');
+						$toRemove = true; 
+					} else if ($contentLength < 25 && ($img === 0 || $img > 2) ) {
+						$this->dbg(' content length less than 25 chars and 0 images, or more than 2 images');
+						$toRemove = true;
+					} else if($weight < 25 && $linkDensity > 0.2) {
+						$this->dbg(' weight smaller than 25 and link density above 0.2');
+						$toRemove = true;
+					} else if($weight >= 25 && $linkDensity > 0.5) {
+						$this->dbg(' weight above 25 but link density greater than 0.5');
+						$toRemove = true;
+					} else if(($embedCount == 1 && $contentLength < 75) || $embedCount > 1) {
+						$this->dbg(' 1 embed and content length smaller than 75 chars, or more than one embed');
+						$toRemove = true;
+					}
+				}
+
+				if ($toRemove) {
+					//$this->dbg('Removing: '.$tagsList->item($i)->innerHTML);
+					$tagsList->item($i)->parentNode->removeChild($tagsList->item($i));
+				}
+			}
+		}
+	}
+
+	/**
+	* Clean out spurious headers from an Element. Checks things like classnames and link density.
+	*
+	* @param DOMElement $e
+	* @return void
+	*/
+	public function cleanHeaders($e) {
+		for ($headerIndex = 1; $headerIndex < 3; $headerIndex++) {
+			$headers = $e->getElementsByTagName('h' . $headerIndex);
+			for ($i=$headers->length-1; $i >=0; $i--) {
+				if ($this->getClassWeight($headers->item($i)) < 0 || $this->getLinkDensity($headers->item($i)) > 0.33) {
+					$headers->item($i)->parentNode->removeChild($headers->item($i));
+				}
+			}
+		}
+	}
+
+	public function flagIsActive($flag) {
+		return ($this->flags & $flag) > 0;
+	}
+	
+	public function addFlag($flag) {
+		$this->flags = $this->flags | $flag;
+	}
+	
+	public function removeFlag($flag) {
+		$this->flags = $this->flags & ~$flag;
+	}
+}
 ?>
\ No newline at end of file
-- 
cgit v1.2.3


From d18ff7d9565f982bc15c5930123992d44614e1e2 Mon Sep 17 00:00:00 2001
From: Maryana Rozhankivska 
Date: Fri, 23 May 2014 19:25:48 +0300
Subject: two small unimportant forgotten changes to 3.2 version of
 full-text-rss, issue #694

---
 inc/3rdparty/libraries/language-detect/Parser.php | 354 ----------------------
 1 file changed, 354 deletions(-)
 delete mode 100644 inc/3rdparty/libraries/language-detect/Parser.php

(limited to 'inc/3rdparty/libraries')

diff --git a/inc/3rdparty/libraries/language-detect/Parser.php b/inc/3rdparty/libraries/language-detect/Parser.php
deleted file mode 100644
index 7f15fa98..00000000
--- a/inc/3rdparty/libraries/language-detect/Parser.php
+++ /dev/null
@@ -1,354 +0,0 @@
-_db_filename = $db;
-		if (isset($unicode_db)) $this->_unicode_db_filename = $unicode_db;	
-        $this->_string = $string;
-    }
-
-    /**
-     * Returns true if a string is suitable for parsing
-     *
-     * @static
-     * @access  public
-     * @param   string  $str    input string to test
-     * @return  bool            true if acceptable, false if not
-     */
-    function validateString($str) {
-        if (!empty($str) && strlen($str) > 3 && preg_match('/\S/', $str)) {
-            return true;
-        } else {
-            return false;
-        }
-    }
-
-    /**
-     * turn on/off trigram counting
-     *
-     * @access  public
-     * @param   bool    $bool true for on, false for off
-     */
-    function prepareTrigram($bool = true)
-    {
-        $this->_compile_trigram = $bool;
-    }
-
-    /**
-     * turn on/off unicode block counting
-     *
-     * @access  public
-     * @param   bool    $bool true for on, false for off
-     */
-    function prepareUnicode($bool = true)
-    {
-        $this->_compile_unicode = $bool;
-    }
-
-    /**
-     * turn on/off padding the beginning of the sample string
-     *
-     * @access  public
-     * @param   bool    $bool true for on, false for off
-     */
-    function setPadStart($bool = true)
-    {
-        $this->_trigram_pad_start = $bool;
-    }
-
-    /**
-     * Should the unicode block counter skip non-alphabetical ascii chars?
-     *
-     * @access  public
-     * @param   bool    $bool true for on, false for off
-     */
-    function setUnicodeSkipSymbols($bool = true)
-    {
-        $this->_unicode_skip_symbols = $bool;
-    }
-
-    /**
-     * Returns the trigram ranks for the text sample
-     *
-     * @access  public
-     * @return  array    trigram ranks in the text sample
-     */
-    function &getTrigramRanks()
-    {
-        return $this->_trigram_ranks;
-    }
-
-    /**
-     * Return the trigram freqency table
-     *
-     * only used in testing to make sure the parser is working
-     *
-     * @access  public
-     * @return  array    trigram freqencies in the text sample
-     */
-    function &getTrigramFreqs()
-    {
-        return $this->_trigram;
-    }
-
-    /**
-     * returns the array of unicode blocks
-     *
-     * @access  public
-     * @return  array   unicode blocks in the text sample
-     */
-    function &getUnicodeBlocks()
-    {
-        return $this->_unicode_blocks;
-    }
-
-    /**
-     * Executes the parsing operation
-     * 
-     * Be sure to call the set*() functions to set options and the 
-     * prepare*() functions first to tell it what kind of data to compute
-     *
-     * Afterwards the get*() functions can be used to access the compiled
-     * information.
-     *
-     * @access public
-     */
-    function analyze()
-    {
-        $len = strlen($this->_string);
-        $byte_counter = 0;
-
-
-        // unicode startup
-        if ($this->_compile_unicode) {
-            $blocks =& $this->_read_unicode_block_db();
-
-            $block_count = count($blocks);
-
-            $skipped_count = 0;
-            $unicode_chars = array();
-        }
-
-        // trigram startup
-        if ($this->_compile_trigram) {
-            // initialize them as blank so the parser will skip the first two
-            // (since it skips trigrams with more than  2 contiguous spaces)
-            $a = ' ';
-            $b = ' ';
-
-            // kludge
-            // if it finds a valid trigram to start and the start pad option is
-            // off, then set a variable that will be used to reduce this
-            // trigram after parsing has finished
-            if (!$this->_trigram_pad_start) {
-                $a = $this->_next_char($this->_string, $byte_counter, true);
-
-                if ($a != ' ') {
-                    $b = $this->_next_char($this->_string, $byte_counter, true);
-                    $dropone = " $a$b";
-                }
-
-                $byte_counter = 0;
-                $a = ' ';
-                $b = ' ';
-            }
-        }
-
-        while ($byte_counter < $len) {
-            $char = $this->_next_char($this->_string, $byte_counter, true);
-
-
-            // language trigram detection
-            if ($this->_compile_trigram) {
-                if (!($b == ' ' && ($a == ' ' || $char == ' '))) {
-                    if (!isset($this->_trigram[$a . $b . $char])) {
-                       $this->_trigram[$a . $b . $char] = 1;
-                    } else {
-                       $this->_trigram[$a . $b . $char]++;
-                    }
-                }
-
-                $a = $b;
-                $b = $char;
-            }
-
-            // unicode block detection
-            if ($this->_compile_unicode) {
-                if ($this->_unicode_skip_symbols
-                        && strlen($char) == 1
-                        && ($char < 'A' || $char > 'z'
-                        || ($char > 'Z' && $char < 'a'))
-                        && $char != "'") {  // does not skip the apostrophe
-                                            // since it's included in the language
-                                            // models
-
-                    $skipped_count++;
-                    continue;
-                }
-
-                // build an array of all the characters
-                if (isset($unicode_chars[$char])) {
-                    $unicode_chars[$char]++;
-                } else {
-                    $unicode_chars[$char] = 1;
-                }
-            }
-
-            // todo: add byte detection here
-        }
-
-        // unicode cleanup
-        if ($this->_compile_unicode) {
-            foreach ($unicode_chars as $utf8_char => $count) {
-                $search_result = $this->_unicode_block_name(
-                        $this->_utf8char2unicode($utf8_char), $blocks, $block_count);
-
-                if ($search_result != -1) {
-                    $block_name = $search_result[2];
-                } else {
-                    $block_name = '[Malformatted]';
-                }
-
-                if (isset($this->_unicode_blocks[$block_name])) {
-                    $this->_unicode_blocks[$block_name] += $count;
-                } else {
-                    $this->_unicode_blocks[$block_name] = $count;
-                }
-            }
-        }
-
-
-        // trigram cleanup
-        if ($this->_compile_trigram) {
-            // pad the end
-            if ($b != ' ') {
-                if (!isset($this->_trigram["$a$b "])) {
-                    $this->_trigram["$a$b "] = 1;
-                } else {
-                    $this->_trigram["$a$b "]++;
-                }
-            }
-
-            // perl compatibility; Language::Guess does not pad the beginning
-            // kludge
-            if (isset($dropone)) {
-                if ($this->_trigram[$dropone] == 1) {
-                    unset($this->_trigram[$dropone]);
-                } else {
-                    $this->_trigram[$dropone]--;
-                }
-            }
-
-            if (!empty($this->_trigram)) {
-                $this->_trigram_ranks = $this->_arr_rank($this->_trigram);
-            } else {
-                $this->_trigram_ranks = array();
-            }
-        }
-    }
-}
-
-/* vim: set expandtab tabstop=4 shiftwidth=4 softtabstop=4: */
-
-?>
-- 
cgit v1.2.3


From a50583fb97615f4c26cc84ee95d62f867a84b4e6 Mon Sep 17 00:00:00 2001
From: Maryana Rozhankivska 
Date: Fri, 23 May 2014 19:27:17 +0300
Subject: last 3 important changes to 3.2 version of full-text-rss, issue #694

---
 .../language-detect/LanguageDetect/Exception.php   |  57 ++++
 .../language-detect/LanguageDetect/ISO639.php      | 339 ++++++++++++++++++++
 .../language-detect/LanguageDetect/Parser.php      | 347 +++++++++++++++++++++
 3 files changed, 743 insertions(+)
 create mode 100644 inc/3rdparty/libraries/language-detect/LanguageDetect/Exception.php
 create mode 100644 inc/3rdparty/libraries/language-detect/LanguageDetect/ISO639.php
 create mode 100644 inc/3rdparty/libraries/language-detect/LanguageDetect/Parser.php

(limited to 'inc/3rdparty/libraries')

diff --git a/inc/3rdparty/libraries/language-detect/LanguageDetect/Exception.php b/inc/3rdparty/libraries/language-detect/LanguageDetect/Exception.php
new file mode 100644
index 00000000..196d994f
--- /dev/null
+++ b/inc/3rdparty/libraries/language-detect/LanguageDetect/Exception.php
@@ -0,0 +1,57 @@
+
+ * @copyright 2011 Christian Weiske 
+ * @license   http://www.debian.org/misc/bsd.license BSD
+ * @version   SVN: $Id$
+ * @link      http://pear.php.net/package/Text_LanguageDetect/
+ */
+
+/**
+ * Provides a mapping between the languages from lang.dat and the
+ * ISO 639-1 and ISO-639-2 codes.
+ *
+ * Note that this class contains only languages that exist in lang.dat.
+ *
+ * @category  Text
+ * @package   Text_LanguageDetect
+ * @author    Christian Weiske 
+ * @copyright 2011 Christian Weiske 
+ * @license   http://www.debian.org/misc/bsd.license BSD
+ * @link      http://www.loc.gov/standards/iso639-2/php/code_list.php
+ */
+class Text_LanguageDetect_ISO639
+{
+    /**
+     * Maps all language names from the language database to the
+     * ISO 639-1 2-letter language code.
+     *
+     * NULL indicates that there is no 2-letter code.
+     *
+     * @var array
+     */
+    public static $nameToCode2 = array(
+        'albanian'   => 'sq',
+        'arabic'     => 'ar',
+        'azeri'      => 'az',
+        'bengali'    => 'bn',
+        'bulgarian'  => 'bg',
+        'cebuano'    => null,
+        'croatian'   => 'hr',
+        'czech'      => 'cs',
+        'danish'     => 'da',
+        'dutch'      => 'nl',
+        'english'    => 'en',
+        'estonian'   => 'et',
+        'farsi'      => 'fa',
+        'finnish'    => 'fi',
+        'french'     => 'fr',
+        'german'     => 'de',
+        'hausa'      => 'ha',
+        'hawaiian'   => null,
+        'hindi'      => 'hi',
+        'hungarian'  => 'hu',
+        'icelandic'  => 'is',
+        'indonesian' => 'id',
+        'italian'    => 'it',
+        'kazakh'     => 'kk',
+        'kyrgyz'     => 'ky',
+        'latin'      => 'la',
+        'latvian'    => 'lv',
+        'lithuanian' => 'lt',
+        'macedonian' => 'mk',
+        'mongolian'  => 'mn',
+        'nepali'     => 'ne',
+        'norwegian'  => 'no',
+        'pashto'     => 'ps',
+        'pidgin'     => null,
+        'polish'     => 'pl',
+        'portuguese' => 'pt',
+        'romanian'   => 'ro',
+        'russian'    => 'ru',
+        'serbian'    => 'sr',
+        'slovak'     => 'sk',
+        'slovene'    => 'sl',
+        'somali'     => 'so',
+        'spanish'    => 'es',
+        'swahili'    => 'sw',
+        'swedish'    => 'sv',
+        'tagalog'    => 'tl',
+        'turkish'    => 'tr',
+        'ukrainian'  => 'uk',
+        'urdu'       => 'ur',
+        'uzbek'      => 'uz',
+        'vietnamese' => 'vi',
+        'welsh'      => 'cy',
+    );
+
+    /**
+     * Maps all language names from the language database to the
+     * ISO 639-2 3-letter language code.
+     *
+     * @var array
+     */
+    public static $nameToCode3 = array(
+        'albanian'   => 'sqi',
+        'arabic'     => 'ara',
+        'azeri'      => 'aze',
+        'bengali'    => 'ben',
+        'bulgarian'  => 'bul',
+        'cebuano'    => 'ceb',
+        'croatian'   => 'hrv',
+        'czech'      => 'ces',
+        'danish'     => 'dan',
+        'dutch'      => 'nld',
+        'english'    => 'eng',
+        'estonian'   => 'est',
+        'farsi'      => 'fas',
+        'finnish'    => 'fin',
+        'french'     => 'fra',
+        'german'     => 'deu',
+        'hausa'      => 'hau',
+        'hawaiian'   => 'haw',
+        'hindi'      => 'hin',
+        'hungarian'  => 'hun',
+        'icelandic'  => 'isl',
+        'indonesian' => 'ind',
+        'italian'    => 'ita',
+        'kazakh'     => 'kaz',
+        'kyrgyz'     => 'kir',
+        'latin'      => 'lat',
+        'latvian'    => 'lav',
+        'lithuanian' => 'lit',
+        'macedonian' => 'mkd',
+        'mongolian'  => 'mon',
+        'nepali'     => 'nep',
+        'norwegian'  => 'nor',
+        'pashto'     => 'pus',
+        'pidgin'     => 'crp',
+        'polish'     => 'pol',
+        'portuguese' => 'por',
+        'romanian'   => 'ron',
+        'russian'    => 'rus',
+        'serbian'    => 'srp',
+        'slovak'     => 'slk',
+        'slovene'    => 'slv',
+        'somali'     => 'som',
+        'spanish'    => 'spa',
+        'swahili'    => 'swa',
+        'swedish'    => 'swe',
+        'tagalog'    => 'tgl',
+        'turkish'    => 'tur',
+        'ukrainian'  => 'ukr',
+        'urdu'       => 'urd',
+        'uzbek'      => 'uzb',
+        'vietnamese' => 'vie',
+        'welsh'      => 'cym',
+    );
+
+    /**
+     * Maps ISO 639-1 2-letter language codes to the language names
+     * in the language database
+     *
+     * Not all languages have a 2 letter code, so some are missing
+     *
+     * @var array
+     */
+    public static $code2ToName = array(
+        'ar' => 'arabic',
+        'az' => 'azeri',
+        'bg' => 'bulgarian',
+        'bn' => 'bengali',
+        'cs' => 'czech',
+        'cy' => 'welsh',
+        'da' => 'danish',
+        'de' => 'german',
+        'en' => 'english',
+        'es' => 'spanish',
+        'et' => 'estonian',
+        'fa' => 'farsi',
+        'fi' => 'finnish',
+        'fr' => 'french',
+        'ha' => 'hausa',
+        'hi' => 'hindi',
+        'hr' => 'croatian',
+        'hu' => 'hungarian',
+        'id' => 'indonesian',
+        'is' => 'icelandic',
+        'it' => 'italian',
+        'kk' => 'kazakh',
+        'ky' => 'kyrgyz',
+        'la' => 'latin',
+        'lt' => 'lithuanian',
+        'lv' => 'latvian',
+        'mk' => 'macedonian',
+        'mn' => 'mongolian',
+        'ne' => 'nepali',
+        'nl' => 'dutch',
+        'no' => 'norwegian',
+        'pl' => 'polish',
+        'ps' => 'pashto',
+        'pt' => 'portuguese',
+        'ro' => 'romanian',
+        'ru' => 'russian',
+        'sk' => 'slovak',
+        'sl' => 'slovene',
+        'so' => 'somali',
+        'sq' => 'albanian',
+        'sr' => 'serbian',
+        'sv' => 'swedish',
+        'sw' => 'swahili',
+        'tl' => 'tagalog',
+        'tr' => 'turkish',
+        'uk' => 'ukrainian',
+        'ur' => 'urdu',
+        'uz' => 'uzbek',
+        'vi' => 'vietnamese',
+    );
+
+    /**
+     * Maps ISO 639-2 3-letter language codes to the language names
+     * in the language database.
+     *
+     * @var array
+     */
+    public static $code3ToName = array(
+        'ara' => 'arabic',
+        'aze' => 'azeri',
+        'ben' => 'bengali',
+        'bul' => 'bulgarian',
+        'ceb' => 'cebuano',
+        'ces' => 'czech',
+        'crp' => 'pidgin',
+        'cym' => 'welsh',
+        'dan' => 'danish',
+        'deu' => 'german',
+        'eng' => 'english',
+        'est' => 'estonian',
+        'fas' => 'farsi',
+        'fin' => 'finnish',
+        'fra' => 'french',
+        'hau' => 'hausa',
+        'haw' => 'hawaiian',
+        'hin' => 'hindi',
+        'hrv' => 'croatian',
+        'hun' => 'hungarian',
+        'ind' => 'indonesian',
+        'isl' => 'icelandic',
+        'ita' => 'italian',
+        'kaz' => 'kazakh',
+        'kir' => 'kyrgyz',
+        'lat' => 'latin',
+        'lav' => 'latvian',
+        'lit' => 'lithuanian',
+        'mkd' => 'macedonian',
+        'mon' => 'mongolian',
+        'nep' => 'nepali',
+        'nld' => 'dutch',
+        'nor' => 'norwegian',
+        'pol' => 'polish',
+        'por' => 'portuguese',
+        'pus' => 'pashto',
+        'rom' => 'romanian',
+        'rus' => 'russian',
+        'slk' => 'slovak',
+        'slv' => 'slovene',
+        'som' => 'somali',
+        'spa' => 'spanish',
+        'sqi' => 'albanian',
+        'srp' => 'serbian',
+        'swa' => 'swahili',
+        'swe' => 'swedish',
+        'tgl' => 'tagalog',
+        'tur' => 'turkish',
+        'ukr' => 'ukrainian',
+        'urd' => 'urdu',
+        'uzb' => 'uzbek',
+        'vie' => 'vietnamese',
+    );
+
+    /**
+     * Returns the 2-letter ISO 639-1 code for the given language name.
+     *
+     * @param string $lang English language name like "swedish"
+     *
+     * @return string Two-letter language code (e.g. "sv") or NULL if not found
+     */
+    public static function nameToCode2($lang)
+    {
+        $lang = strtolower($lang);
+        if (!isset(self::$nameToCode2[$lang])) {
+            return null;
+        }
+        return self::$nameToCode2[$lang];
+    }
+
+    /**
+     * Returns the 3-letter ISO 639-2 code for the given language name.
+     *
+     * @param string $lang English language name like "swedish"
+     *
+     * @return string Three-letter language code (e.g. "swe") or NULL if not found
+     */
+    public static function nameToCode3($lang)
+    {
+        $lang = strtolower($lang);
+        if (!isset(self::$nameToCode3[$lang])) {
+            return null;
+        }
+        return self::$nameToCode3[$lang];
+    }
+
+    /**
+     * Returns the language name for the given 2-letter ISO 639-1 code.
+     *
+     * @param string $code Two-letter language code (e.g. "sv")
+     *
+     * @return string English language name like "swedish"
+     */
+    public static function code2ToName($code)
+    {
+        $lang = strtolower($code);
+        if (!isset(self::$code2ToName[$code])) {
+            return null;
+        }
+        return self::$code2ToName[$code];
+    }
+
+    /**
+     * Returns the language name for the given 3-letter ISO 639-2 code.
+     *
+     * @param string $code Three-letter language code (e.g. "swe")
+     *
+     * @return string English language name like "swedish"
+     */
+    public static function code3ToName($code)
+    {
+        $lang = strtolower($code);
+        if (!isset(self::$code3ToName[$code])) {
+            return null;
+        }
+        return self::$code3ToName[$code];
+    }
+}
\ No newline at end of file
diff --git a/inc/3rdparty/libraries/language-detect/LanguageDetect/Parser.php b/inc/3rdparty/libraries/language-detect/LanguageDetect/Parser.php
new file mode 100644
index 00000000..fb0e1e20
--- /dev/null
+++ b/inc/3rdparty/libraries/language-detect/LanguageDetect/Parser.php
@@ -0,0 +1,347 @@
+_string = $string;
+    }
+
+    /**
+     * Returns true if a string is suitable for parsing
+     *
+     * @param   string  $str    input string to test
+     * @return  bool            true if acceptable, false if not
+     */
+    public static function validateString($str) {
+        if (!empty($str) && strlen($str) > 3 && preg_match('/\S/', $str)) {
+            return true;
+        } else {
+            return false;
+        }
+    }
+
+    /**
+     * turn on/off trigram counting
+     *
+     * @access  public
+     * @param   bool    $bool true for on, false for off
+     */
+    function prepareTrigram($bool = true)
+    {
+        $this->_compile_trigram = $bool;
+    }
+
+    /**
+     * turn on/off unicode block counting
+     *
+     * @access  public
+     * @param   bool    $bool true for on, false for off
+     */
+    function prepareUnicode($bool = true)
+    {
+        $this->_compile_unicode = $bool;
+    }
+
+    /**
+     * turn on/off padding the beginning of the sample string
+     *
+     * @access  public
+     * @param   bool    $bool true for on, false for off
+     */
+    function setPadStart($bool = true)
+    {
+        $this->_trigram_pad_start = $bool;
+    }
+
+    /**
+     * Should the unicode block counter skip non-alphabetical ascii chars?
+     *
+     * @access  public
+     * @param   bool    $bool true for on, false for off
+     */
+    function setUnicodeSkipSymbols($bool = true)
+    {
+        $this->_unicode_skip_symbols = $bool;
+    }
+
+    /**
+     * Returns the trigram ranks for the text sample
+     *
+     * @access  public
+     * @return  array    trigram ranks in the text sample
+     */
+    function &getTrigramRanks()
+    {
+        return $this->_trigram_ranks;
+    }
+
+    /**
+     * Return the trigram freqency table
+     *
+     * only used in testing to make sure the parser is working
+     *
+     * @access  public
+     * @return  array    trigram freqencies in the text sample
+     */
+    function &getTrigramFreqs()
+    {
+        return $this->_trigram;
+    }
+
+    /**
+     * returns the array of unicode blocks
+     *
+     * @access  public
+     * @return  array   unicode blocks in the text sample
+     */
+    function &getUnicodeBlocks()
+    {
+        return $this->_unicode_blocks;
+    }
+
+    /**
+     * Executes the parsing operation
+     * 
+     * Be sure to call the set*() functions to set options and the 
+     * prepare*() functions first to tell it what kind of data to compute
+     *
+     * Afterwards the get*() functions can be used to access the compiled
+     * information.
+     *
+     * @access public
+     */
+    function analyze()
+    {
+        $len = strlen($this->_string);
+        $byte_counter = 0;
+
+
+        // unicode startup
+        if ($this->_compile_unicode) {
+            $blocks = $this->_read_unicode_block_db();
+            $block_count = count($blocks);
+
+            $skipped_count = 0;
+            $unicode_chars = array();
+        }
+
+        // trigram startup
+        if ($this->_compile_trigram) {
+            // initialize them as blank so the parser will skip the first two
+            // (since it skips trigrams with more than  2 contiguous spaces)
+            $a = ' ';
+            $b = ' ';
+
+            // kludge
+            // if it finds a valid trigram to start and the start pad option is
+            // off, then set a variable that will be used to reduce this
+            // trigram after parsing has finished
+            if (!$this->_trigram_pad_start) {
+                $a = $this->_next_char($this->_string, $byte_counter, true);
+
+                if ($a != ' ') {
+                    $b = $this->_next_char($this->_string, $byte_counter, true);
+                    $dropone = " $a$b";
+                }
+
+                $byte_counter = 0;
+                $a = ' ';
+                $b = ' ';
+            }
+        }
+
+        while ($byte_counter < $len) {
+            $char = $this->_next_char($this->_string, $byte_counter, true);
+
+
+            // language trigram detection
+            if ($this->_compile_trigram) {
+                if (!($b == ' ' && ($a == ' ' || $char == ' '))) {
+                    if (!isset($this->_trigram[$a . $b . $char])) {
+                       $this->_trigram[$a . $b . $char] = 1;
+                    } else {
+                       $this->_trigram[$a . $b . $char]++;
+                    }
+                }
+
+                $a = $b;
+                $b = $char;
+            }
+
+            // unicode block detection
+            if ($this->_compile_unicode) {
+                if ($this->_unicode_skip_symbols
+                        && strlen($char) == 1
+                        && ($char < 'A' || $char > 'z'
+                        || ($char > 'Z' && $char < 'a'))
+                        && $char != "'") {  // does not skip the apostrophe
+                                            // since it's included in the language
+                                            // models
+
+                    $skipped_count++;
+                    continue;
+                }
+
+                // build an array of all the characters
+                if (isset($unicode_chars[$char])) {
+                    $unicode_chars[$char]++;
+                } else {
+                    $unicode_chars[$char] = 1;
+                }
+            }
+
+            // todo: add byte detection here
+        }
+
+        // unicode cleanup
+        if ($this->_compile_unicode) {
+            foreach ($unicode_chars as $utf8_char => $count) {
+                $search_result = $this->_unicode_block_name(
+                        $this->_utf8char2unicode($utf8_char), $blocks, $block_count);
+
+                if ($search_result != -1) {
+                    $block_name = $search_result[2];
+                } else {
+                    $block_name = '[Malformatted]';
+                }
+
+                if (isset($this->_unicode_blocks[$block_name])) {
+                    $this->_unicode_blocks[$block_name] += $count;
+                } else {
+                    $this->_unicode_blocks[$block_name] = $count;
+                }
+            }
+        }
+
+
+        // trigram cleanup
+        if ($this->_compile_trigram) {
+            // pad the end
+            if ($b != ' ') {
+                if (!isset($this->_trigram["$a$b "])) {
+                    $this->_trigram["$a$b "] = 1;
+                } else {
+                    $this->_trigram["$a$b "]++;
+                }
+            }
+
+            // perl compatibility; Language::Guess does not pad the beginning
+            // kludge
+            if (isset($dropone)) {
+                if ($this->_trigram[$dropone] == 1) {
+                    unset($this->_trigram[$dropone]);
+                } else {
+                    $this->_trigram[$dropone]--;
+                }
+            }
+
+            if (!empty($this->_trigram)) {
+                $this->_trigram_ranks = $this->_arr_rank($this->_trigram);
+            } else {
+                $this->_trigram_ranks = array();
+            }
+        }
+    }
+}
+
+/* vim: set expandtab tabstop=4 shiftwidth=4 softtabstop=4: */
\ No newline at end of file
-- 
cgit v1.2.3


From 3dc8d84229ed0f3ccd40b44420ed6e818a6edea9 Mon Sep 17 00:00:00 2001
From: Maryana Rozhankivska 
Date: Thu, 29 May 2014 16:35:00 +0300
Subject: fix of uninitialized object warning, issue #710

---
 inc/3rdparty/libraries/feedwriter/FeedWriter.php | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'inc/3rdparty/libraries')

diff --git a/inc/3rdparty/libraries/feedwriter/FeedWriter.php b/inc/3rdparty/libraries/feedwriter/FeedWriter.php
index 77755690..aa064afb 100755
--- a/inc/3rdparty/libraries/feedwriter/FeedWriter.php
+++ b/inc/3rdparty/libraries/feedwriter/FeedWriter.php
@@ -97,13 +97,16 @@ define('JSONP', 3, true);
               header('X-content-type-options: nosniff');
           } elseif ($this->version == JSON) {
               header('Content-type: application/json; charset=UTF-8');
-              $this->json = new stdClass();
           } elseif ($this->version == JSONP) {
               header('Content-type: application/javascript; charset=UTF-8');
-              $this->json = new stdClass();
           }
         }
 
+        if ($this->version == JSON || $this->version == JSONP) {
+          $this->json = new stdClass();
+        }
+
+
         $this->printHead();
         $this->printChannels();
         $this->printItems();
@@ -202,7 +205,7 @@ define('JSONP', 3, true);
     public function setDescription($description)
     {
         $tag = ($this->version == ATOM)? 'subtitle' : 'description';
-        $this->setChannelElement($tag, $desciption);
+        $this->setChannelElement($tag, $description);
     }
 
     /**
-- 
cgit v1.2.3