* @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