/**
* 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 <code>processChapterExternalReferences</code> 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 $success
*/
function addChapter($chapterName, $fileName, $chapterData, $autoSplit = FALSE, $externalReferences = EPub::EXTERNAL_REF_IGNORE, $baseDir = "")
{
if ($this->isFinalized) {
return FALSE;
}
$fileName = preg_replace('#\\\\#i', "/", $fileName);
$fileName = preg_replace('#^[/\\.]+#i', "", $fileName);
$htmlDir = pathinfo($fileName);
$htmlDir = preg_replace('#^[/\\.]+#i', "", $htmlDir["dirname"] . "/");
$chapter = $chapterData;
if ($autoSplit && is_string($chapterData) && strlen($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) {
$this->processChapterExternalReferences($chapter, $externalReferences, $baseDir, $htmlDir);
}
$this->zip->addFile($chapter, $fileName);
$this->fileList[$fileName] = $fileName;
$this->chapterCount++;
$this->opf_manifest .= "\t\t<item id=\"chapter" . $this->chapterCount . "\" href=\"" . $fileName . "\" media-type=\"application/xhtml+xml\" />\n";
$this->opf_spine .= "\t\t<itemref idref=\"chapter" . $this->chapterCount . "\" />\n";
$this->ncx_navmap .= "\n\t\t<navPoint id=\"chapter" . $this->chapterCount . "\" playOrder=\"" . $this->chapterCount . "\">\n\t\t\t<navLabel><text>" . $chapterName . "</text></navLabel>\n\t\t\t<content src=\"" . $fileName . "\" />\n\t\t</navPoint>\n";
} else {
if (is_array($chapter)) {
$partCount = 0;
$this->chapterCount++;
$oneChapter = each($chapter);
while ($oneChapter) {
list($k, $v) = $oneChapter;
$c = $v;
if ($externalReferences !== EPub::EXTERNAL_REF_IGNORE) {
$this->processChapterExternalReferences($c, $externalReferences, $baseDir);
}
$partCount++;
$this->zip->addFile($c, $fileName . "-" . $partCount);
$this->fileList[$fileName . "-" . $partCount] = $fileName . "-" . $partCount;
$this->opf_manifest .= "\t\t<item id=\"chapter" . $this->chapterCount . "-" . $partCount . "\" href=\"" . $fileName . "-" . $partCount . "\" media-type=\"application/xhtml+xml\" />\n";
$this->opf_spine .= "\t\t<itemref idref=\"chapter" . $this->chapterCount . "-" . $partCount . "\" />\n";
$oneChapter = each($chapter);
}
$this->ncx_navmap .= "\n\t\t<navPoint id=\"chapter" . $this->chapterCount . "-1\" playOrder=\"" . $this->chapterCount . "\">\n\t\t\t<navLabel><text>" . $chapterName . "</text></navLabel>\n\t\t\t<content src=\"" . $fileName . "-1\" />\n\t\t</navPoint>\n";
}
}
return TRUE;
}
// Still using Chapter 4, but as you can see, "Chapter 4" also contains a header for Chapter 5.
require_once 'EPubChapterSplitter.php';
$log->logLine("include EPubChapterSplitter.php");
$splitter = new EPubChapterSplitter();
$splitter->setSplitSize(15000);
// For this test, we split at approx 15k. Default is 250000 had we left it alone.
$log->logLine("new EPubChapterSplitter()");
/* Using the # as regexp delimiter here, it makes writing the regexp easier.
* in this case we could have just searched for "Chapter ", or if we were using regexp '#^<h1>Chapter #i',
* using regular text (no regexp delimiters) will look for the text after the first tag. Meaning had we used
* "Chapter ", any paragraph or header starting with "Chapter " would have matched. The regexp equivalent of
* "Chapter " is '#^<.+?>Chapter #'
* Essentially, the search strnig is looking for lines starting with...
*/
$log->logLine("Add Chapter 5");
$html2 = $splitter->splitChapter($chapter5, true, "Chapter ");
/* '#^<.+?>Chapter \d*#i'); */
$log->logLine("Split chapter 5");
$idx = 0;
while (list($k, $v) = each($html2)) {
$idx++;
// Because we used a string search in the splitter, the returned hits are put in the key part of the array.
// The entire HTML tag of the line matching the chapter search.
// find the text inside the tags
preg_match('#^<(\\w+)\\ *.*?>(.+)</\\ *\\1>$#i', $k, $cName);
// because of the back reference, the tag name is in $cName[1], and the content is in $cName[2]
// Change any line breakes in the chapter name to " - "
$cName = preg_replace('#<br.+?>#i', " - ", $cName[2]);
// Remove any other tags
$cName = preg_replace('#<.+?>#i', " ", $cName);
// clean the chapter name by removing any double spaces left behind to single space.
/**
* Create an EPUB and export to defined path
* @param $dir str directory of the source file to convert
* @param $src str filename of the source file to convert
* @param $path str path to export the resultant EPUB to
* @param $chapters array chapters to convert into a single EPUB
* @param $journalId int Id of the journal(imprint)
* @param $args array arguments for the conversion (e.g. Description, cover image, etc)
*/
function createEpub($dir = null, $src, $path, $chapters = array(), $journalId, $args = array())
{
$book = new EPub();
if (isset($args['title'])) {
$book->setTitle($args['title']);
} else {
$book->setTitle("No Title");
}
$book->setLanguage("en");
$book->setPublisher(Config::getVar('general', 'base_url'), Config::getVar('general', 'base_url'));
$book->setDate(time());
$book->setRights("Copyright and licence information specific for the book.");
//TODO: import specific copyright/licence information
$book->setSourceURL(Config::getVar('general', 'base_url'));
$CBPPlatformDao =& DAORegistry::getDAO('CBPPlatformDAO');
$imprintType = $CBPPlatformDao->getImprintType($journalId);
$stylesheet = $CBPPlatformDao->getImprintStylesheet($journalId);
$book->addCSSFile("styles.css", "css1", file_get_contents($this->stylesheetDir . "{$stylesheet}.css"));
isset($args['description']) ? $book->setDescription($args['description']) : $book->setDescription("No description");
isset($args['author']) ? $book->setAuthor($args['author'], $args['author']) : $book->setAuthor("No author", "No author");
$args['isbn'] != null ? $book->setIdentifier($args['isbn'], EPub::IDENTIFIER_URI) : $book->setIdentifier(Config::getVar('general', 'base_url'), EPub::IDENTIFIER_URI);
if (isset($args['cover'])) {
$cover = $args['cover'];
$coverSrc = "\n\t\t\t\t\t<svg version='1.1' xmlns='http://www.w3.org/2000/svg' xmlns:xlink='http://www.w3.org/1999/xlink' width='100%' height='100%' viewBox='0 0 410 597' preserveAspectRatio='xMidYMid meet'>\n\t\t\t\t\t\t<image width='410' height='597' xlink:href='images/Cover.jpg' />\n\t\t\t\t\t</svg>";
$book->addChapter("Cover Page", "Cover.html", $this->contentStart . "{$coverSrc}</body>\n</html>\n", false, EPub::EXTERNAL_REF_ADD, $this->fileDir);
$book->setCoverImage("Cover.jpg", file_get_contents($args['cover']));
} else {
$book->addChapter("Cover Page", "Cover.html", $this->contentStart . "<h1>" . $book->getTitle() . "</h1><h3>" . $book->getAuthor() . "</h3></body>\n</html>\n", false, EPub::EXTERNAL_REF_ADD, $this->fileDir);
}
$copyrightStatement = $CBPPlatformDao->getJournalCopyrightStatement($journalId);
if (!empty($copyrightStatement)) {
$copyrightStatement = reset($copyrightStatement);
$copyrightStatement = "<div style='width: 75%; text-align: center; margin: 0 auto;'><p>" . $copyrightStatement . "</p></div>";
$book->addChapter("Copyright Notice", "notice.html", $this->contentStart . $copyrightStatement, false, EPub::EXTERNAL_REF_ADD, $this->fileDir);
}
if (!empty($chapters)) {
$chapterCount = 0;
foreach ($chapters as $chapter) {
if (!isset($chapter['type']) && $chapter['type'] != "supp") {
$chapterCount++;
} else {
$suppChapters = true;
}
}
for ($i = 0; $i < count($chapters); $i++) {
$document = new TransformDoc();
$document->setStrFile($chapters[$i]['src'], $chapters[$i]['dir']);
$document->generateXHTML();
//problem, here
$document->validatorXHTML();
$contentPreg = $this->stripTags($document->getStrXHTML());
if ($chapterCount == 1) {
$splitter = new EPubChapterSplitter();
$xhtml = $this->contentStart . $contentPreg . "</body></html>";
$html2 = $splitter->splitChapter($xhtml, true, '@<h1[^>]*?.*?</h1>@siu');
/* '#^<.+?>Chapter \d*#i'); */
foreach ($html2 as $key => $value) {
$cTitles[] = $key;
$cContent[] = $value;
}
for ($i = 0; $i < count($cContent); $i++) {
$html3[$cTitles[$i]] = $cContent[$i];
}
$idx = 0;
if (!empty($html3)) {
foreach ($html3 as $k => $v) {
$idx++;
$cName = preg_replace('#<br.+?>#i', " - ", $k);
// Remove any other tags
$cName = preg_replace('/<[^>]*>/', '', $cName);
// clean the chapter name by removing any double spaces left behind to single space.
$cName = preg_replace('#\\s+#i', " ", $cName);
$book->addChapter($cName, "Chapter" . $idx . ".html", $v, false, EPub::EXTERNAL_REF_ADD, $fileDir);
}
}
if ($suppChapters == true) {
$i = 0;
foreach ($chapters as $chapter) {
if (isset($chapter['type']) && $chapter['type'] == "supp") {
$document = new TransformDoc();
$document->setStrFile($chapter['src'], $chapter['dir']);
$document->generateXHTML();
$document->validatorXHTML();
$contentPreg = $this->stripTags($document->getStrXHTML());
$book->addChapter($chapter['name'], "Chapter{$i}.html", $this->contentStart . $contentPreg . "</body></html>", false, EPub::EXTERNAL_REF_ADD, $this->fileDir);
}
}
$i++;
}
break;
} else {
if ($imprintType == "atomistic") {
$book->addChapter($cName, "Chapter" . $i . ".html", $this->contentStart . $contentPreg . "</body></html>", false, EPub::EXTERNAL_REF_ADD, $fileDir);
} elseif ($imprintType == "collection") {
if ($chapters[$i]['description'] != "") {
$book->addChapter("Introduction to " . $chapters[$i]['name'] . " by " . $chapters[$i]['author'], "Chapter" . "{$i}-I" . ".html", $this->contentStart . "<div class='submissionIntroEpub'><h1>" . $chapters[$i]['author'] . "</h1>" . $this->stripTags($chapters[$i]['description'], true) . "</div></body></html>", false, EPub::EXTERNAL_REF_ADD, $fileDir, false);
}
$book->addChapter($chapters[$i]['name'] . " by " . $chapters[$i]['author'], "Chapter" . $i . ".html", $this->contentStart . "{$contentPreg}</body></html>", false, EPub::EXTERNAL_REF_ADD, $fileDir);
}
}
}
} else {
$content = new TransformDoc();
$splitter = new EPubChapterSplitter();
$content->setStrFile($src, $dir);
$content->generateXHTML();
$content->validatorXHTML();
$contentPreg = $this->stripTags($content->getStrXHTML());
$xhtml = $this->contentStart . $contentPreg . "</body></html>";
$html2 = $splitter->splitChapter($xhtml, true, '@<h1[^>]*?.*?</h1>@siu');
foreach ($html2 as $key => $value) {
$cTitles[] = $key;
$cContent[] = $value;
}
array_shift($cContent);
for ($i = 0; $i < count($cContent); $i++) {
$html3[$cTitles[$i]] = $cContent[$i];
}
$idx = 0;
if (!empty($html3)) {
foreach ($html3 as $k => $v) {
$idx++;
$cName = preg_replace('#<br.+?>#i', " - ", $k);
// Remove any other tags
$cName = preg_replace('/<[^>]*>/', '', $cName);
//clean the chapter name by removing any double spaces left behind to single space.
$cName = preg_replace('#\\s+#i', " ", $cName);
$book->addChapter($cName, "Chapter" . $idx . ".html", $v, false, EPub::EXTERNAL_REF_ADD, $fileDir);
}
} else {
$book->addChapter("Body Text", "Chapter1.html", $xhtml, false, EPub::EXTERNAL_REF_ADD, $fileDir);
}
}
$book->finalize();
$zipData = $book->getBook();
file_put_contents($path, $zipData);
}
/**
* 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 <code>processChapterExternalReferences</code> 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);
$fileName = $this->sanitizeFileName($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 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 250kB? Default=false, only used if $chapterData is a String.
* @return void
*/
function addChapter($chapterName, $fileName, $chapterData, $autoSplit = false)
{
if ($this->isFinalized) {
return;
}
$chapter = $chapterData;
if (is_string($chapterData) && strlen($chapterData) > 100000 && $autoSplit) {
include_once "EPubChapterSplitter.php";
$splitter = new EPubChapterSplitter();
$chapterArray = $splitter->splitChapter($chapterData);
if (count($chapterArray) > 1) {
$chapter = $chapterArray;
}
}
if (is_string($chapter) && strlen($chapter) > 0) {
$this->zip->addFile($chapter, $fileName);
$this->chapterCount++;
/*
Keiko:
Warning toc.xhtml hardcoded here. Not a good style, but that's all
what we need on the other hand.
*/
if ($fileName === 'toc.xhtml') {
$this->opf_manifest .= "\t\t<item id=\"chapter" . $this->chapterCount . "\" href=\"" . $fileName . "\" properties=\"nav\" media-type=\"application/xhtml+xml\" />\n";
} else {
$this->opf_manifest .= "\t\t<item id=\"chapter" . $this->chapterCount . "\" href=\"" . $fileName . "\" media-type=\"application/xhtml+xml\" />\n";
}
$this->opf_spine .= "\t\t<itemref idref=\"chapter" . $this->chapterCount . "\" />\n";
$this->ncx_navmap .= "\n\t\t<navPoint id=\"chapter" . $this->chapterCount . "\" playOrder=\"" . $this->chapterCount . "\">\n" . "\t\t\t<navLabel><text>" . $chapterName . "</text></navLabel>\n" . "\t\t\t<content src=\"" . $fileName . "\" />\n" . "\t\t</navPoint>\n";
} else {
if (is_array($chapter)) {
$partCount = 0;
$this->chapterCount++;
while (list($k, $v) = each($chapter)) {
$partCount++;
$this->zip->addFile($v, $fileName . "-" . $partCount . ".xhtml");
$this->opf_manifest .= "\t\t<item id=\"chapter" . $this->chapterCount . "-" . $partCount . "\" href=\"" . $fileName . "-" . $partCount . ".xhtml\" media-type=\"application/xhtml+xml\" />\n";
$this->opf_spine .= "\t\t<itemref idref=\"chapter" . $this->chapterCount . "-" . $partCount . "\" />\n";
}
$this->ncx_navmap .= "\n\t\t<navPoint id=\"chapter" . $this->chapterCount . "-1\" playOrder=\"" . $this->chapterCount . "\">\n" . "\t\t\t<navLabel><text>" . $chapterName . "</text></navLabel>\n" . "\t\t\t<content src=\"" . $fileName . "-1.xhtml\" />\n" . "\t\t</navPoint>\n";
}
}
}