3 * Create an ePub compatible book file.
5 * Please note, once finalized a book can no longer have chapters of data added or changed.
7 * License: GNU LGPL, Attribution required for commercial implementations, requested for everything else.
9 * Thanks to: Adam Schmalhofer and Kirstyn Fox for invaluable input and for "nudging" me in the right direction :)
11 * @author A. Grandt <php@grandt.com>
12 * @copyright 2009-2014 A. Grandt
13 * @license GNU LGPL 2.1
15 * @link http://www.phpclasses.org/package/6115
16 * @link https://github.com/Grandt/PHPePub
17 * @uses Zip.php version 1.50; http://www.phpclasses.org/browse/package/6110.html or https://github.com/Grandt/PHPZip
21 const REQ_ZIP_VERSION
= 1.60;
23 const IDENTIFIER_UUID
= 'UUID';
24 const IDENTIFIER_URI
= 'URI';
25 const IDENTIFIER_ISBN
= 'ISBN';
27 /** Ignore all external references, and do not process the file for these */
28 const EXTERNAL_REF_IGNORE
= 0;
29 /** Process the file for external references and add them to the book */
30 const EXTERNAL_REF_ADD
= 1;
31 /** Process the file for external references and add them to the book, but remove images, and img tags */
32 const EXTERNAL_REF_REMOVE_IMAGES
= 2;
33 /** Process the file for external references and add them to the book, but replace images, and img tags with [image] */
34 const EXTERNAL_REF_REPLACE_IMAGES
= 3;
36 const DIRECTION_LEFT_TO_RIGHT
= "ltr";
37 const DIRECTION_RIGHT_TO_LEFT
= "rtl";
39 const BOOK_VERSION_EPUB2
= "2.0";
40 const BOOK_VERSION_EPUB3
= "3.0";
42 private $bookVersion = EPub
::BOOK_VERSION_EPUB2
;
44 private $debugInside = FALSE;
46 public $maxImageWidth = 768;
47 public $maxImageHeight = 1024;
49 public $splitDefaultSize = 250000;
50 /** Gifs can crash some early ADE based readers, and are disabled by default.
51 * getImage will convert these if it can, unless this is set to TRUE.
53 public $isGifImagesEnabled = FALSE;
54 public $isReferencesAddedToToc = TRUE;
59 private $language = "en";
60 private $identifier = "";
61 private $identifierType = "";
62 private $description = "";
64 private $authorSortKey = "";
65 private $publisherName = "";
66 private $publisherURL = "";
69 private $coverage = "";
70 private $relation = "";
71 private $sourceURL = "";
73 private $chapterCount = 0;
76 private $isFinalized = FALSE;
77 private $isCoverImageSet = FALSE;
78 private $buildTOC = FALSE;
79 private $tocTitle = NULL;
80 private $tocFileName = NULL;
81 private $tocCSSClass = NULL;
82 private $tocAddReferences = FALSE;
83 private $tocCssFileName = NULL;
85 private $fileList = array();
86 private $writingDirection = EPub
::DIRECTION_LEFT_TO_RIGHT
;
87 private $languageCode = "en";
90 * Used for building the TOC.
91 * If this list is overwritten it MUST contain at least "text" as an element.
93 public $referencesOrder = NULL;
95 private $dateformat = 'Y-m-d\TH:i:s.000000P'; // ISO 8601 long
96 private $dateformatShort = 'Y-m-d'; // short date format to placate ePubChecker.
97 private $headerDateFormat = "D, d M Y H:i:s T";
99 protected $isCurlInstalled;
100 protected $isGdInstalled;
101 protected $isExifInstalled;
102 protected $isFileGetContentsInstalled;
103 protected $isFileGetContentsExtInstalled;
105 private $bookRoot = "OEBPS/";
106 private $docRoot = NULL;
107 private $EPubMark = TRUE;
108 private $generator = "";
111 public $isLogging = TRUE;
113 public $encodeHTML = FALSE;
115 private $mimetypes = array(
116 "js" => "application/x-javascript", "swf" => "application/x-shockwave-flash", "xht" => "application/xhtml+xml", "xhtml" => "application/xhtml+xml", "zip" => "application/zip",
117 "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",
118 "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",
119 "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",
120 "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");
122 // 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.
123 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");
125 private $opsContentTypes = array("application/xhtml+xml", "application/x-dtbook+xml", "application/xml", "application/x-dtbncx+xml", "text/x-oeb1-document");
127 private $forbiddenCharacters = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", "%");
129 private $htmlContentHeader = "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.1//EN\"\n \"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd\">\n<html xmlns=\"http://www.w3.org/1999/xhtml\">\n<head><meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n<title></title>\n</head>\n<body>\n";
130 private $htmlContentFooter = "</body>\n</html>\n";
137 function __construct($bookVersion = EPub
::BOOK_VERSION_EPUB2
, $debugInside = FALSE, $languageCode = "en", $writingDirection = EPub
::DIRECTION_LEFT_TO_RIGHT
) {
138 include_once("Zip.php");
139 include_once("Logger.php");
142 error_reporting(E_ERROR
| E_PARSE
);
145 $this->bookVersion
= $bookVersion;
146 $this->writingDirection
= $writingDirection;
147 $this->languageCode
= $languageCode;
149 $this->log
= new Logger("EPub", $this->isLogging
);
151 /* Prepare Logging. Just in case it's used. later */
152 if ($this->isLogging
) {
153 $this->log
->logLine("EPub class version....: " . self
::VERSION
);
154 $this->log
->logLine("EPub req. Zip version.: " . self
::REQ_ZIP_VERSION
);
155 $this->log
->logLine("Zip version...........: " . Zip
::VERSION
);
156 $this->log
->dumpInstalledModules();
159 if (!defined("Zip::VERSION") || Zip
::VERSION
< self
::REQ_ZIP_VERSION
) {
160 die("<p>EPub version " . self
::VERSION
. " requires Zip.php at version " . self
::REQ_ZIP_VERSION
. " or higher.<br />You can obtain the latest version from <a href=\"http://www.phpclasses.org/browse/package/6110.html\">http://www.phpclasses.org/browse/package/6110.html</a>.</p>");
163 include_once("EPubChapterSplitter.php");
164 include_once("EPub.HtmlEntities.php");
165 include_once("EPub.NCX.php");
166 include_once("EPub.OPF.php");
175 * @TODO make sure elements in the destructor match the current class elements
177 function __destruct() {
178 unset($this->bookVersion
, $this->maxImageWidth
, $this->maxImageHeight
);
179 unset($this->splitDefaultSize
, $this->isGifImagesEnabled
, $this->isReferencesAddedToToc
);
180 unset($this->zip
, $this->title
, $this->language
, $this->identifier
, $this->identifierType
);
181 unset($this->description
, $this->author
, $this->authorSortKey
, $this->publisherName
);
182 unset($this->publisherURL
, $this->date
, $this->rights
, $this->coverage
, $this->relation
);
183 unset($this->sourceURL
, $this->chapterCount
, $this->opf
, $this->ncx
, $this->isFinalized
);
184 unset($this->isCoverImageSet
, $this->fileList
, $this->writingDirection
, $this->languageCode
);
185 unset($this->referencesOrder
, $this->dateformat
, $this->dateformatShort
, $this->headerDateFormat
);
186 unset($this->isCurlInstalled
, $this->isGdInstalled
, $this->isExifInstalled
);
187 unset($this->isFileGetContentsInstalled
, $this->isFileGetContentsExtInstalled
, $this->bookRoot
);
188 unset($this->docRoot
, $this->EPubMark
, $this->generator
, $this->log
, $this->isLogging
);
189 unset($this->encodeHTML
, $this->mimetypes
, $this->coreMediaTypes
, $this->opsContentTypes
);
190 unset($this->forbiddenCharacters
, $this->htmlContentHeader
, $this->htmlContentFooter
);
191 unset($this->buildTOC
, $this->tocTitle
, $this->tocCSSClass
, $this->tocAddReferences
);
192 unset($this->tocFileName
, $this->tocCssFileName
);
196 * initialize defaults.
198 private function initialize() {
199 $this->referencesOrder
= array(
200 Reference
::COVER
=> "Cover Page",
201 Reference
::TITLE_PAGE
=> "Title Page",
202 Reference
::ACKNOWLEDGEMENTS
=> "Acknowledgements",
203 Reference
::BIBLIOGRAPHY
=> "Bibliography",
204 Reference
::COLOPHON
=> "Colophon",
205 Reference
::COPYRIGHT_PAGE
=> "Copyright",
206 Reference
::DEDICATION
=> "Dedication",
207 Reference
::EPIGRAPH
=> "Epigraph",
208 Reference
::FOREWORD
=> "Foreword",
209 Reference
::TABLE_OF_CONTENTS
=> "Table of Contents",
210 Reference
::NOTES
=> "Notes",
211 Reference
::PREFACE
=> "Preface",
212 Reference
::TEXT
=> "First Page",
213 Reference
::LIST_OF_ILLUSTRATIONS
=> "List of Illustrations",
214 Reference
::LIST_OF_TABLES
=> "List of Tables",
215 Reference
::GLOSSARY
=> "Glossary",
216 Reference
::INDEX
=> "Index");
218 $this->docRoot
= filter_input(INPUT_SERVER
, "DOCUMENT_ROOT") . "/";
220 $this->isCurlInstalled
= extension_loaded('curl') && function_exists('curl_version');
221 $this->isGdInstalled
= extension_loaded('gd') && function_exists('gd_info');
222 $this->isExifInstalled
= extension_loaded('exif') && function_exists('exif_imagetype');
223 $this->isFileGetContentsInstalled
= function_exists('file_get_contents');
224 $this->isFileGetContentsExtInstalled
= $this->isFileGetContentsInstalled
&& ini_get('allow_url_fopen');
226 $this->zip
= new Zip();
227 $this->zip
->setExtraField(FALSE);
228 $this->zip
->addFile("application/epub+zip", "mimetype");
229 $this->zip
->setExtraField(TRUE);
230 $this->zip
->addDirectory("META-INF");
232 $this->content
= "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<container version=\"1.0\" xmlns=\"urn:oasis:names:tc:opendocument:xmlns:container\">\n\t<rootfiles>\n\t\t<rootfile full-path=\"" . $this->bookRoot
. "book.opf\" media-type=\"application/oebps-package+xml\" />\n\t</rootfiles>\n</container>\n";
234 if (!$this->isEPubVersion2()) {
235 $this->htmlContentHeader
= "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n"
236 . "<html xmlns=\"http://www.w3.org/1999/xhtml\" xmlns:epub=\"http://www.idpf.org/2007/ops\">\n"
238 . "<meta http-equiv=\"Default-Style\" content=\"text/html; charset=utf-8\" />\n"
239 . "<title></title>\n"
244 $this->zip
->addFile($this->content
, "META-INF/container.xml", 0, NULL, FALSE);
245 $this->content
= NULL;
246 $this->ncx
= new Ncx(NULL, NULL, NULL, $this->languageCode
, $this->writingDirection
);
247 $this->opf
= new Opf();
248 $this->ncx
->setVersion($this->bookVersion
);
249 $this->opf
->setVersion($this->bookVersion
);
250 $this->opf
->addItem("ncx", "book.ncx", Ncx
::MIMETYPE
);
251 $this->chapterCount
= 0;
255 * Add dynamically generated data as a file to the book.
257 * @param string $fileName Filename to use for the file, must be unique for the book.
258 * @param string $fileId Unique identifier for the file.
259 * @param string $fileData File data
260 * @param string $mimetype file mime type
261 * @return bool $success
263 function addFile($fileName, $fileId, $fileData, $mimetype) {
264 if ($this->isFinalized
|| array_key_exists($fileName, $this->fileList
)) {
268 $fileName = $this->normalizeFileName($fileName);
270 $compress = (strpos($mimetype, "image/") !== 0);
272 $this->zip
->addFile($fileData, $this->bookRoot
.$fileName, 0, NULL, $compress);
273 $this->fileList
[$fileName] = $fileName;
274 $this->opf
->addItem($fileId, $fileName, $mimetype);
279 * Add a large file directly from the filestystem to the book.
281 * @param string $fileName Filename to use for the file, must be unique for the book.
282 * @param string $fileId Unique identifier for the file.
283 * @param string $filePath File path
284 * @param string $mimetype file mime type
285 * @return bool $success
287 function addLargeFile($fileName, $fileId, $filePath, $mimetype) {
288 if ($this->isFinalized
|| array_key_exists($fileName, $this->fileList
)) {
291 $fileName = $this->normalizeFileName($fileName);
293 if ($this->zip
->addLargeFile($filePath, $this->bookRoot
.$fileName)) {
294 $this->fileList
[$fileName] = $fileName;
295 $this->opf
->addItem($fileId, $fileName, $mimetype);
302 * Add a CSS file to the book.
304 * @param string $fileName Filename to use for the CSS file, must be unique for the book.
305 * @param string $fileId Unique identifier for the file.
306 * @param string $fileData CSS data
307 * @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>processCSSExternalReferences</code> for explanation. Default is EPub::EXTERNAL_REF_IGNORE.
308 * @param string $baseDir Default is "", meaning it is pointing to the document root. NOT used if $externalReferences is set to EPub::EXTERNAL_REF_IGNORE.
310 * @return bool $success
312 function addCSSFile($fileName, $fileId, $fileData, $externalReferences = EPub
::EXTERNAL_REF_IGNORE
, $baseDir = "") {
313 if ($this->isFinalized
|| array_key_exists($fileName, $this->fileList
)) {
316 $fileName = Zip
::getRelativePath($fileName);
317 $fileName = preg_replace('#^[/\.]+#i', "", $fileName);
319 if ($externalReferences !== EPub
::EXTERNAL_REF_IGNORE
) {
320 $cssDir = pathinfo($fileName);
321 $cssDir = preg_replace('#^[/\.]+#i', "", $cssDir["dirname"] . "/");
322 if (!empty($cssDir)) {
323 $cssDir = preg_replace('#[^/]+/#i', "../", $cssDir);
326 $this->processCSSExternalReferences($fileData, $externalReferences, $baseDir, $cssDir);
329 $this->addFile($fileName, "css_" . $fileId, $fileData, "text/css");
335 * Add a chapter to the book, as a chapter should not exceed 250kB, you can parse an array with multiple parts as $chapterData.
336 * These will still only show up as a single chapter in the book TOC.
338 * @param string $chapterName Name of the chapter, will be use din the TOC
339 * @param string $fileName Filename to use for the chapter, must be unique for the book.
340 * @param string $chapter Chapter text in XHTML or array $chapterData valid XHTML data for the chapter. File should NOT exceed 250kB.
341 * @param bool $autoSplit Should the chapter be split if it exceeds the default split size? Default=FALSE, only used if $chapterData is a string.
342 * @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.
343 * @param string $baseDir Default is "", meaning it is pointing to the document root. NOT used if $externalReferences is set to EPub::EXTERNAL_REF_IGNORE.
344 * @return mixed $success FALSE if the addition failed, else the new NavPoint.
346 function addChapter($chapterName, $fileName, $chapterData = NULL, $autoSplit = FALSE, $externalReferences = EPub
::EXTERNAL_REF_IGNORE
, $baseDir = "") {
347 if ($this->isFinalized
) {
350 $fileName = Zip
::getRelativePath($fileName);
351 $fileName = preg_replace('#^[/\.]+#i', "", $fileName);
352 $fileName = $this->sanitizeFileName($fileName);
354 $chapter = $chapterData;
355 if ($autoSplit && is_string($chapterData) && mb_strlen($chapterData) > $this->splitDefaultSize
) {
356 $splitter = new EPubChapterSplitter();
358 $chapterArray = $splitter->splitChapter($chapterData);
359 if (count($chapterArray) > 1) {
360 $chapter = $chapterArray;
364 if (!empty($chapter) && is_string($chapter)) {
365 if ($externalReferences !== EPub
::EXTERNAL_REF_IGNORE
) {
366 $htmlDirInfo = pathinfo($fileName);
367 $htmlDir = preg_replace('#^[/\.]+#i', "", $htmlDirInfo["dirname"] . "/");
368 $this->processChapterExternalReferences($chapter, $externalReferences, $baseDir, $htmlDir);
371 if ($this->encodeHTML
=== TRUE) {
372 $chapter = $this->encodeHtml($chapter);
375 $this->chapterCount++
;
376 $this->addFile($fileName, "chapter" . $this->chapterCount
, $chapter, "application/xhtml+xml");
377 $this->opf
->addItemRef("chapter" . $this->chapterCount
);
379 $navPoint = new NavPoint($this->decodeHtmlEntities($chapterName), $fileName, "chapter" . $this->chapterCount
);
380 $this->ncx
->addNavPoint($navPoint);
381 $this->ncx
->chapterList
[$chapterName] = $navPoint;
382 } else if (is_array($chapter)) {
383 $fileNameParts = pathinfo($fileName);
384 $extension = $fileNameParts['extension'];
385 $name = $fileNameParts['filename'];
388 $this->chapterCount++
;
390 $oneChapter = each($chapter);
391 while ($oneChapter) {
392 list($k, $v) = $oneChapter;
393 if ($this->encodeHTML
=== TRUE) {
394 $v = $this->encodeHtml($v);
397 if ($externalReferences !== EPub
::EXTERNAL_REF_IGNORE
) {
398 $this->processChapterExternalReferences($v, $externalReferences, $baseDir);
401 $partName = $name . "_" . $partCount;
402 $this->addFile($partName . "." . $extension, $partName, $v, "application/xhtml+xml");
403 $this->opf
->addItemRef($partName);
405 $oneChapter = each($chapter);
407 $partName = $name . "_1." . $extension;
408 $navPoint = new NavPoint($this->decodeHtmlEntities($chapterName), $partName, $partName);
409 $this->ncx
->addNavPoint($navPoint);
411 $this->ncx
->chapterList
[$chapterName] = $navPoint;
412 } else if (!isset($chapterData) && strpos($fileName, "#") > 0) {
413 $this->chapterCount++
;
414 //$this->opf->addItemRef("chapter" . $this->chapterCount);
416 $navPoint = new NavPoint($this->decodeHtmlEntities($chapterName), $fileName, "chapter" . $this->chapterCount
);
417 $this->ncx
->addNavPoint($navPoint);
418 $this->ncx
->chapterList
[$chapterName] = $navPoint;
419 } else if (!isset($chapterData) && $fileName=="TOC.xhtml") {
420 $this->chapterCount++
;
421 $this->opf
->addItemRef("toc");
423 $navPoint = new NavPoint($this->decodeHtmlEntities($chapterName), $fileName, "chapter" . $this->chapterCount
);
424 $this->ncx
->addNavPoint($navPoint);
425 $this->ncx
->chapterList
[$chapterName] = $navPoint;
431 * Add one chapter level.
433 * Subsequent chapters will be added to this level.
435 * @param string $navTitle
436 * @param string $navId
437 * @param string $navClass
438 * @param int $isNavHidden
439 * @param string $writingDirection
440 * @return NavPoint The new NavPoint for that level.
442 function subLevel($navTitle = NULL, $navId = NULL, $navClass = NULL, $isNavHidden = FALSE, $writingDirection = NULL) {
443 return $this->ncx
->subLevel($this->decodeHtmlEntities($navTitle), $navId, $navClass, $isNavHidden, $writingDirection);
447 * Step back one chapter level.
449 * Subsequent chapters will be added to this chapters parent level.
451 function backLevel() {
452 $this->ncx
->backLevel();
456 * Step back to the root level.
458 * Subsequent chapters will be added to the rooot NavMap.
460 function rootLevel() {
461 $this->ncx
->rootLevel();
465 * Step back to the given level.
466 * Useful for returning to a previous level from deep within the structure.
467 * Values below 2 will have the same effect as rootLevel()
469 * @param int $newLevel
471 function setCurrentLevel($newLevel) {
472 $this->ncx
->setCurrentLevel($newLevel);
476 * Get current level count.
477 * The indentation of the current structure point.
479 * @return current level count;
481 function getCurrentLevel() {
482 return $this->ncx
->getCurrentLevel();
486 * Wrap ChapterContent with Head and Footer
489 * @return string $content
491 private function wrapChapter($content) {
492 return $this->htmlContentHeader
. "\n" . $content . "\n" . $this->htmlContentFooter
;
496 * Reference pages is usually one or two pages for items such as Table of Contents, reference lists, Author notes or Acknowledgements.
497 * These do not show up in the regular navigation list.
499 * As they are supposed to be short.
501 * @param string $pageName Name of the chapter, will be use din the TOC
502 * @param string $fileName Filename to use for the chapter, must be unique for the book.
503 * @param string $pageData Page content in XHTML. File should NOT exceed 250kB.
504 * @param string $reference Reference key
505 * @param int $externalReferences How to handle external references. See documentation for <code>processChapterExternalReferences</code> for explanation. Default is EPub::EXTERNAL_REF_IGNORE.
506 * @param string $baseDir Default is "", meaning it is pointing to the document root. NOT used if $externalReferences is set to EPub::EXTERNAL_REF_IGNORE.
507 * @return bool $success
509 function addReferencePage($pageName, $fileName, $pageData, $reference, $externalReferences = EPub
::EXTERNAL_REF_IGNORE
, $baseDir = "") {
510 if ($this->isFinalized
) {
513 $fileName = Zip
::getRelativePath($fileName);
514 $fileName = preg_replace('#^[/\.]+#i', "", $fileName);
517 if (!empty($pageData) && is_string($pageData)) {
518 if ($this->encodeHTML
=== TRUE) {
519 $pageData = $this->encodeHtml($pageData);
522 $this->wrapChapter($pageData);
524 if ($externalReferences !== EPub
::EXTERNAL_REF_IGNORE
) {
525 $htmlDirInfo = pathinfo($fileName);
526 $htmlDir = preg_replace('#^[/\.]+#i', "", $htmlDirInfo["dirname"] . "/");
527 $this->processChapterExternalReferences($pageData, $externalReferences, $baseDir, $htmlDir);
530 $this->addFile($fileName, "ref_" . $reference, $pageData, "application/xhtml+xml");
532 if ($reference !== Reference
::TABLE_OF_CONTENTS
|| !isset($this->ncx
->referencesList
[$reference])) {
533 $this->opf
->addItemRef("ref_" . $reference, FALSE);
534 $this->opf
->addReference($reference, $pageName, $fileName);
536 $this->ncx
->referencesList
[$reference] = $fileName;
537 $this->ncx
->referencesName
[$reference] = $pageName;
545 * Add custom metadata to the book.
547 * It is up to the builder to make sure there are no collisions. Metadata are just key value pairs.
549 * @param string $name
550 * @param string $content
552 function addCustomMetadata($name, $content) {
553 $this->opf
->addMeta($name, $content);
557 * Add DublinCore metadata to the book
559 * Use the DublinCore constants included in EPub, ie DublinCore::DATE
561 * @param string $dublinCore name
562 * @param string $value
564 function addDublinCoreMetadata($dublinCoreConstant, $value) {
565 if ($this->isFinalized
) {
569 $this->opf
->addDCMeta($dublinCoreConstant, $this->decodeHtmlEntities($value));
573 * Add a cover image to the book.
574 * If the $imageData is not set, the function assumes the $fileName is the path to the image file.
576 * The styling and structure of the generated XHTML is heavily inspired by the XHTML generated by Calibre.
578 * @param string $fileName Filename to use for the image, must be unique for the book.
579 * @param string $imageData Binary image data
580 * @param string $mimetype Image mimetype, such as "image/jpeg" or "image/png".
581 * @return bool $success
583 function setCoverImage($fileName, $imageData = NULL, $mimetype = NULL,$bookTitle) {
584 if ($this->isFinalized
|| $this->isCoverImageSet
|| array_key_exists("CoverPage.html", $this->fileList
)) {
588 if ($imageData == NULL) {
589 // assume $fileName is the valid file path.
590 if (!file_exists($fileName)) {
591 // Attempt to locate the file using the doc root.
592 $rp = realpath($this->docRoot
. "/" . $fileName);
595 // only assign the docroot path if it actually exists there.
599 $image = $this->getImage($fileName);
600 $imageData = $image['image'];
601 $mimetype = $image['mime'];
602 $fileName = preg_replace("#\.[^\.]+$#", "." . $image['ext'], $fileName);
606 $path = pathinfo($fileName);
607 $imgPath = "images/" . $path["basename"];
609 if (empty($mimetype) && file_exists($fileName)) {
610 list($width, $height, $type, $attr) = getimagesize($fileName);
611 $mimetype = image_type_to_mime_type($type);
613 if (empty($mimetype)) {
614 $ext = strtolower($path['extension']);
618 $mimetype = "image/" . $ext;
623 if ($this->isEPubVersion2()) {
624 $coverPage = "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n"
625 . "<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.1//EN\"\n"
626 . " \"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd\">\n"
627 . "<html xmlns=\"http://www.w3.org/1999/xhtml\" xmlns:epub=\"http://www.idpf.org/2007/ops\" xml:lang=\"en\">\n"
629 . "\t\t<meta http-equiv=\"Content-Type\" content=\"text/html; charset=UTF-8\"/>\n"
630 . "\t\t<title>Cover Image</title>\n"
631 . "\t\t<link type=\"text/css\" rel=\"stylesheet\" href=\"Styles/CoverPage.css\" />\n"
634 . "\t" . $bookTitle . "\n"
636 . "\t\t\t<img src=\"" . $imgPath . "\" alt=\"Cover image\" style=\"height: 100%\"/>\n"
641 $coverPage = "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n"
642 . "<html xmlns=\"http://www.w3.org/1999/xhtml\" xmlns:epub=\"http://www.idpf.org/2007/ops\">\n"
644 . "\t<meta http-equiv=\"Default-Style\" content=\"text/html; charset=utf-8\" />\n"
645 . "\t\t<title>Cover Image</title>\n"
646 . "\t\t<link type=\"text/css\" rel=\"stylesheet\" href=\"Styles/CoverPage.css\" />\n"
649 . "\t\t<section epub:type=\"cover\">\n"
650 . "\t" . $bookTitle . "\n"
651 . "\t\t\t<img src=\"" . $imgPath . "\" alt=\"Cover image\" style=\"height: 30%\"/>\n"
656 $coverPageCss = "@page, body, div, img {\n"
657 . "\tpadding: 0pt;\n"
660 . "\ttext-align: center;\n"
663 $this->addCSSFile("Styles/CoverPage.css", "CoverPageCss", $coverPageCss);
664 $this->addFile($imgPath, "CoverImage", $imageData, $mimetype);
665 $this->addReferencePage("CoverPage", "CoverPage.xhtml", $coverPage, "cover");
666 $this->isCoverImageSet
= TRUE;
671 * Process external references from a HTML to the book. The chapter itself is not stored.
672 * the HTML is scanned for <link..., <style..., and <img tags.
673 * Embedded CSS styles and links will also be processed.
674 * Script tags are not processed, as scripting should be avoided in e-books.
676 * EPub keeps track of added files, and duplicate files referenced across multiple
677 * chapters, are only added once.
679 * If the $doc is a string, it is assumed to be the content of an HTML file,
680 * else is it assumes to be a DOMDocument.
682 * Basedir is the root dir the HTML is supposed to "live" in, used to resolve
683 * relative references such as <code><img src="../images/image.png"/></code>
685 * $externalReferences determines how the function will handle external references.
687 * @param mixed &$doc (referenced)
688 * @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.
689 * @param string $baseDir Default is "", meaning it is pointing to the document root.
690 * @param string $htmlDir The path to the parent HTML file's directory from the root of the archive.
692 * @return bool FALSE if uncuccessful (book is finalized or $externalReferences == EXTERNAL_REF_IGNORE).
694 protected function processChapterExternalReferences(&$doc, $externalReferences = EPub
::EXTERNAL_REF_ADD
, $baseDir = "", $htmlDir = "") {
695 if ($this->isFinalized
|| $externalReferences === EPub
::EXTERNAL_REF_IGNORE
) {
699 $backPath = preg_replace('#[^/]+/#i', "../", $htmlDir);
700 $isDocAString = is_string($doc);
704 $xmlDoc = new DOMDocument();
705 @$xmlDoc->loadHTML($doc);
710 $this->processChapterStyles($xmlDoc, $externalReferences, $baseDir, $htmlDir);
711 $this->processChapterLinks($xmlDoc, $externalReferences, $baseDir, $htmlDir, $backPath);
712 $this->processChapterImages($xmlDoc, $externalReferences, $baseDir, $htmlDir, $backPath);
713 $this->processChapterSources($xmlDoc, $externalReferences, $baseDir, $htmlDir, $backPath);
716 //$html = $xmlDoc->saveXML();
718 $htmlNode = $xmlDoc->getElementsByTagName("html");
719 $headNode = $xmlDoc->getElementsByTagName("head");
720 $bodyNode = $xmlDoc->getElementsByTagName("body");
723 for ($index = 0; $index < $htmlNode->item(0)->attributes
->length
; $index++
) {
724 $nodeName = $htmlNode->item(0)->attributes
->item($index)->nodeName
;
725 $nodeValue = $htmlNode->item(0)->attributes
->item($index)->nodeValue
;
727 if ($nodeName != "xmlns") {
728 $htmlNS .= " $nodeName=\"$nodeValue\"";
732 $xml = new DOMDocument('1.0', "utf-8");
733 $xml->lookupPrefix("http://www.w3.org/1999/xhtml");
734 $xml->preserveWhiteSpace
= FALSE;
735 $xml->formatOutput
= TRUE;
737 $xml2Doc = new DOMDocument('1.0', "utf-8");
738 $xml2Doc->lookupPrefix("http://www.w3.org/1999/xhtml");
739 $xml2Doc->loadXML("<?xml version=\"1.0\" encoding=\"utf-8\"?>\n<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.1//EN\"\n \"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd\">\n<html xmlns=\"http://www.w3.org/1999/xhtml\"$htmlNS>\n</html>\n");
740 $html = $xml2Doc->getElementsByTagName("html")->item(0);
741 $html->appendChild($xml2Doc->importNode($headNode->item(0), TRUE));
742 $html->appendChild($xml2Doc->importNode($bodyNode->item(0), TRUE));
744 // force pretty printing and correct formatting, should not be needed, but it is.
745 $xml->loadXML($xml2Doc->saveXML());
746 $doc = $xml->saveXML();
748 if (!$this->isEPubVersion2()) {
749 $doc = preg_replace('#^\s*<!DOCTYPE\ .+?>\s*#im', '', $doc);
756 * Process images referenced from an CSS file to the book.
758 * $externalReferences determins how the function will handle external references.
760 * @param string &$cssFile (referenced)
761 * @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.
762 * @param string $baseDir Default is "", meaning it is pointing to the document root.
763 * @param string $cssDir The of the CSS file's directory from the root of the archive.
765 * @return bool FALSE if unsuccessful (book is finalized or $externalReferences == EXTERNAL_REF_IGNORE).
767 protected function processCSSExternalReferences(&$cssFile, $externalReferences = EPub
::EXTERNAL_REF_ADD
, $baseDir = "", $cssDir = "") {
768 if ($this->isFinalized
|| $externalReferences === EPub
::EXTERNAL_REF_IGNORE
) {
772 $backPath = preg_replace('#[^/]+/#i', "../", $cssDir);
774 preg_match_all('#url\s*\([\'\"\s]*(.+?)[\'\"\s]*\)#im', $cssFile, $imgs, PREG_SET_ORDER
);
776 $itemCount = count($imgs);
777 for ($idx = 0; $idx < $itemCount; $idx++
) {
779 if ($externalReferences === EPub
::EXTERNAL_REF_REMOVE_IMAGES
|| $externalReferences === EPub
::EXTERNAL_REF_REPLACE_IMAGES
) {
780 $cssFile = str_replace($img[0], "", $cssFile);
784 $pathData = pathinfo($source);
785 $internalSrc = $pathData['basename'];
787 $isSourceExternal = FALSE;
789 if ($this->resolveImage($source, $internalPath, $internalSrc, $isSourceExternal, $baseDir, $cssDir, $backPath)) {
790 $cssFile = str_replace($img[0], "url('" . $backPath . $internalPath . "')", $cssFile);
791 } else if ($isSourceExternal) {
792 $cssFile = str_replace($img[0], "", $cssFile); // External image is missing
793 } // else do nothing, if the image is local, and missing, assume it's been generated.
800 * Process style tags in a DOMDocument. Styles will be passed as CSS files and reinserted into the document.
802 * @param DOMDocument &$xmlDoc (referenced)
803 * @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.
804 * @param string $baseDir Default is "", meaning it is pointing to the document root.
805 * @param string $htmlDir The path to the parent HTML file's directory from the root of the archive.
807 * @return bool FALSE if uncuccessful (book is finalized or $externalReferences == EXTERNAL_REF_IGNORE).
809 protected function processChapterStyles(&$xmlDoc, $externalReferences = EPub
::EXTERNAL_REF_ADD
, $baseDir = "", $htmlDir = "") {
810 if ($this->isFinalized
|| $externalReferences === EPub
::EXTERNAL_REF_IGNORE
) {
813 // process inlined CSS styles in style tags.
814 $styles = $xmlDoc->getElementsByTagName("style");
815 $styleCount = $styles->length
;
816 for ($styleIdx = 0; $styleIdx < $styleCount; $styleIdx++
) {
817 $style = $styles->item($styleIdx);
819 $styleData = preg_replace('#[/\*\s]*\<\!\[CDATA\[[\s\*/]*#im', "", $style->nodeValue
);
820 $styleData = preg_replace('#[/\*\s]*\]\]\>[\s\*/]*#im', "", $styleData);
822 $this->processCSSExternalReferences($styleData, $externalReferences, $baseDir, $htmlDir);
823 $style->nodeValue
= "\n" . trim($styleData) . "\n";
829 * 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.
830 * Link types text/css will be passed as CSS files.
832 * @param DOMDocument &$xmlDoc (referenced)
833 * @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.
834 * @param string $baseDir Default is "", meaning it is pointing to the document root.
835 * @param string $htmlDir The path to the parent HTML file's directory from the root of the archive.
836 * @param string $backPath The path to get back to the root of the archive from $htmlDir.
838 * @return bool FALSE if uncuccessful (book is finalized or $externalReferences == EXTERNAL_REF_IGNORE).
840 protected function processChapterLinks(&$xmlDoc, $externalReferences = EPub
::EXTERNAL_REF_ADD
, $baseDir = "", $htmlDir = "", $backPath = "") {
841 if ($this->isFinalized
|| $externalReferences === EPub
::EXTERNAL_REF_IGNORE
) {
844 // process link tags.
845 $links = $xmlDoc->getElementsByTagName("link");
846 $linkCount = $links->length
;
847 for ($linkIdx = 0; $linkIdx < $linkCount; $linkIdx++
) {
848 $link = $links->item($linkIdx);
849 $source = $link->attributes
->getNamedItem("href")->nodeValue
;
852 $pathData = pathinfo($source);
853 $internalSrc = $pathData['basename'];
855 if (preg_match('#^(http|ftp)s?://#i', $source) == 1) {
856 $urlinfo = parse_url($source);
858 if (strpos($urlinfo['path'], $baseDir."/") !== FALSE) {
859 $internalSrc = substr($urlinfo['path'], strpos($urlinfo['path'], $baseDir."/") +
strlen($baseDir) +
1);
862 @$sourceData = getFileContents($source);
863 } else if (strpos($source, "/") === 0) {
864 @$sourceData = file_get_contents($this->docRoot
. $source);
866 @$sourceData = file_get_contents($this->docRoot
. $baseDir . "/" . $source);
869 if (!empty($sourceData)) {
870 if (!array_key_exists($internalSrc, $this->fileList
)) {
871 $mime = $link->attributes
->getNamedItem("type")->nodeValue
;
873 $mime = "text/plain";
875 if ($mime == "text/css") {
876 $this->processCSSExternalReferences($sourceData, $externalReferences, $baseDir, $htmlDir);
877 $this->addCSSFile($internalSrc, $internalSrc, $sourceData, EPub
::EXTERNAL_REF_IGNORE
, $baseDir);
878 $link->setAttribute("href", $backPath . $internalSrc);
880 $this->addFile($internalSrc, $internalSrc, $sourceData, $mime);
882 $this->fileList
[$internalSrc] = $source;
884 $link->setAttribute("href", $backPath . $internalSrc);
886 } // else do nothing, if the link is local, and missing, assume it's been generated.
892 * Process img tags in a DOMDocument.
893 * $externalReferences will determine what will happen to these images, and the img src will be rewritten accordingly.
895 * @param DOMDocument &$xmlDoc (referenced)
896 * @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.
897 * @param string $baseDir Default is "", meaning it is pointing to the document root.
898 * @param string $htmlDir The path to the parent HTML file's directory from the root of the archive.
899 * @param string $backPath The path to get back to the root of the archive from $htmlDir.
901 * @return bool FALSE if uncuccessful (book is finalized or $externalReferences == EXTERNAL_REF_IGNORE).
903 protected function processChapterImages(&$xmlDoc, $externalReferences = EPub
::EXTERNAL_REF_ADD
, $baseDir = "", $htmlDir = "", $backPath = "") {
904 if ($this->isFinalized
|| $externalReferences === EPub
::EXTERNAL_REF_IGNORE
) {
908 $postProcDomElememts = array();
909 $images = $xmlDoc->getElementsByTagName("img");
910 $itemCount = $images->length
;
912 for ($idx = 0; $idx < $itemCount; $idx++
) {
913 $img = $images->item($idx);
915 if ($externalReferences === EPub
::EXTERNAL_REF_REMOVE_IMAGES
) {
916 $postProcDomElememts[] = $img;
917 } else if ($externalReferences === EPub
::EXTERNAL_REF_REPLACE_IMAGES
) {
918 $altNode = $img->attributes
->getNamedItem("alt");
920 if ($altNode !== NULL && strlen($altNode->nodeValue
) > 0) {
921 $alt = $altNode->nodeValue
;
923 $postProcDomElememts[] = array($img, $this->createDomFragment($xmlDoc, "<em>[" . $alt . "]</em>"));
925 $source = $img->attributes
->getNamedItem("src")->nodeValue
;
927 $parsedSource = parse_url($source);
928 $internalSrc = $this->sanitizeFileName(urldecode(pathinfo($parsedSource['path'], PATHINFO_BASENAME
)));
930 $isSourceExternal = FALSE;
932 if ($this->resolveImage($source, $internalPath, $internalSrc, $isSourceExternal, $baseDir, $htmlDir, $backPath)) {
933 $img->setAttribute("src", $backPath . $internalPath);
934 } else if ($isSourceExternal) {
935 $postProcDomElememts[] = $img; // External image is missing
936 } // else do nothing, if the image is local, and missing, assume it's been generated.
940 foreach ($postProcDomElememts as $target) {
941 if (is_array($target)) {
942 $target[0]->parentNode
->replaceChild($target[1], $target[0]);
944 $target->parentNode
->removeChild($target);
951 * Process source tags in a DOMDocument.
952 * $externalReferences will determine what will happen to these images, and the img src will be rewritten accordingly.
954 * @param DOMDocument &$xmlDoc (referenced)
955 * @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.
956 * @param string $baseDir Default is "", meaning it is pointing to the document root.
957 * @param string $htmlDir The path to the parent HTML file's directory from the root of the archive.
958 * @param string $backPath The path to get back to the root of the archive from $htmlDir.
960 * @return bool FALSE if uncuccessful (book is finalized or $externalReferences == EXTERNAL_REF_IGNORE).
962 protected function processChapterSources(&$xmlDoc, $externalReferences = EPub
::EXTERNAL_REF_ADD
, $baseDir = "", $htmlDir = "", $backPath = "") {
963 if ($this->isFinalized
|| $externalReferences === EPub
::EXTERNAL_REF_IGNORE
) {
967 if ($this->bookVersion
!== EPub
::BOOK_VERSION_EPUB3
) {
968 // ePub 2 does not support multimedia formats, and they must be removed.
969 $externalReferences = EPub
::EXTERNAL_REF_REMOVE_IMAGES
;
972 $postProcDomElememts = array();
973 $images = $xmlDoc->getElementsByTagName("source");
974 $itemCount = $images->length
;
975 for ($idx = 0; $idx < $itemCount; $idx++
) {
976 $img = $images->item($idx);
977 if ($externalReferences === EPub
::EXTERNAL_REF_REMOVE_IMAGES
) {
978 $postProcDomElememts[] = $img;
979 } else if ($externalReferences === EPub
::EXTERNAL_REF_REPLACE_IMAGES
) {
980 $altNode = $img->attributes
->getNamedItem("alt");
982 if ($altNode !== NULL && strlen($altNode->nodeValue
) > 0) {
983 $alt = $altNode->nodeValue
;
985 $postProcDomElememts[] = array($img, $this->createDomFragment($xmlDoc, "[" . $alt . "]"));
987 $source = $img->attributes
->getNamedItem("src")->nodeValue
;
989 $parsedSource = parse_url($source);
990 $internalSrc = $this->sanitizeFileName(urldecode(pathinfo($parsedSource['path'], PATHINFO_BASENAME
)));
992 $isSourceExternal = FALSE;
994 if ($this->resolveMedia($source, $internalPath, $internalSrc, $isSourceExternal, $baseDir, $htmlDir, $backPath)) {
995 $img->setAttribute("src", $backPath . $internalPath);
996 } else if ($isSourceExternal) {
997 $postProcDomElememts[] = $img; // External image is missing
998 } // else do nothing, if the image is local, and missing, assume it's been generated.
1004 * Resolve an image src and determine it's target location and add it to the book.
1006 * @param string $source Image Source link.
1007 * @param string &$internalPath (referenced) Return value, will be set to the target path and name in the book.
1008 * @param string &$internalSrc (referenced) Return value, will be set to the target name in the book.
1009 * @param string &$isSourceExternal (referenced) Return value, will be set to TRUE if the image originated from a full URL.
1010 * @param string $baseDir Default is "", meaning it is pointing to the document root.
1011 * @param string $htmlDir The path to the parent HTML file's directory from the root of the archive.
1012 * @param string $backPath The path to get back to the root of the archive from $htmlDir.
1014 protected function resolveImage($source, &$internalPath, &$internalSrc, &$isSourceExternal, $baseDir = "", $htmlDir = "", $backPath = "") {
1015 if ($this->isFinalized
) {
1020 if (preg_match('#^(http|ftp)s?://#i', $source) == 1) {
1021 $urlinfo = parse_url($source);
1022 $urlPath = pathinfo($urlinfo['path']);
1024 if (strpos($urlinfo['path'], $baseDir."/") !== FALSE) {
1025 $internalSrc = $this->sanitizeFileName(urldecode(substr($urlinfo['path'], strpos($urlinfo['path'], $baseDir."/") +
strlen($baseDir) +
1)));
1027 $internalPath = $urlinfo["scheme"] . "/" . $urlinfo["host"] . "/" . pathinfo($urlinfo["path"], PATHINFO_DIRNAME
);
1028 $isSourceExternal = TRUE;
1029 $imageData = $this->getImage($source);
1030 } else if (strpos($source, "/") === 0) {
1031 $internalPath = pathinfo($source, PATHINFO_DIRNAME
);
1034 if (!file_exists($path)) {
1035 $path = $this->docRoot
. $path;
1038 $imageData = $this->getImage($path);
1040 $internalPath = $htmlDir . "/" . preg_replace('#^[/\.]+#', '', pathinfo($source, PATHINFO_DIRNAME
));
1042 $path = $baseDir . "/" . $source;
1043 if (!file_exists($path)) {
1044 $path = $this->docRoot
. $path;
1047 $imageData = $this->getImage($path);
1049 if ($imageData !== FALSE) {
1050 $iSrcInfo = pathinfo($internalSrc);
1051 if (!empty($imageData['ext']) && $imageData['ext'] != $iSrcInfo['extension']) {
1052 $internalSrc = $iSrcInfo['filename'] . "." . $imageData['ext'];
1054 $internalPath = Zip
::getRelativePath("images/" . $internalPath . "/" . $internalSrc);
1055 if (!array_key_exists($internalPath, $this->fileList
)) {
1056 $this->addFile($internalPath, "i_" . $internalSrc, $imageData['image'], $imageData['mime']);
1057 $this->fileList
[$internalPath] = $source;
1065 * Resolve a media src and determine it's target location and add it to the book.
1067 * @param string $source Source link.
1068 * @param string $internalPath (referenced) Return value, will be set to the target path and name in the book.
1069 * @param string $internalSrc (referenced) Return value, will be set to the target name in the book.
1070 * @param string $isSourceExternal (referenced) Return value, will be set to TRUE if the image originated from a full URL.
1071 * @param string $baseDir Default is "", meaning it is pointing to the document root.
1072 * @param string $htmlDir The path to the parent HTML file's directory from the root of the archive.
1073 * @param string $backPath The path to get back to the root of the archive from $htmlDir.
1075 protected function resolveMedia($source, &$internalPath, &$internalSrc, &$isSourceExternal, $baseDir = "", $htmlDir = "", $backPath = "") {
1076 if ($this->isFinalized
) {
1082 if (preg_match('#^(http|ftp)s?://#i', $source) == 1) {
1083 $urlinfo = parse_url($source);
1085 if (strpos($urlinfo['path'], $baseDir."/") !== FALSE) {
1086 $internalSrc = substr($urlinfo['path'], strpos($urlinfo['path'], $baseDir."/") +
strlen($baseDir) +
1);
1088 $internalPath = $urlinfo["scheme"] . "/" . $urlinfo["host"] . "/" . pathinfo($urlinfo["path"], PATHINFO_DIRNAME
);
1089 $isSourceExternal = TRUE;
1090 $mediaPath = $this->getFileContents($source, true);
1091 $tmpFile = $mediaPath;
1092 } else if (strpos($source, "/") === 0) {
1093 $internalPath = pathinfo($source, PATHINFO_DIRNAME
);
1095 $mediaPath = $source;
1096 if (!file_exists($mediaPath)) {
1097 $mediaPath = $this->docRoot
. $mediaPath;
1100 $internalPath = $htmlDir . "/" . preg_replace('#^[/\.]+#', '', pathinfo($source, PATHINFO_DIRNAME
));
1102 $mediaPath = $baseDir . "/" . $source;
1103 if (!file_exists($mediaPath)) {
1104 $mediaPath = $this->docRoot
. $mediaPath;
1108 if ($mediaPath !== FALSE) {
1109 $mime = $this->getMime($source);
1110 $internalPath = Zip
::getRelativePath("media/" . $internalPath . "/" . $internalSrc);
1112 if (!array_key_exists($internalPath, $this->fileList
) &&
1113 $this->addLargeFile($internalPath, "m_" . $internalSrc, $mediaPath, $mime)) {
1114 $this->fileList
[$internalPath] = $source;
1116 if (isset($tmpFile)) {
1125 * Get Book Chapter count.
1128 * @return number of chapters
1130 function getChapterCount() {
1131 return $this->chapterCount
;
1135 * Book title, mandatory.
1137 * Used for the dc:title metadata parameter in the OPF file as well as the DocTitle attribute in the NCX file.
1139 * @param string $title
1141 * @return bool $success
1143 function setTitle($title) {
1144 if ($this->isFinalized
) {
1147 $this->title
= $title;
1157 function getTitle() {
1158 return $this->title
;
1162 * Book language, mandatory
1164 * Use the RFC3066 Language codes, such as "en", "da", "fr" etc.
1167 * Used for the dc:language metadata parameter in the OPF file.
1169 * @param string $language
1171 * @return bool $success
1173 function setLanguage($language) {
1174 if ($this->isFinalized
|| mb_strlen($language) != 2) {
1177 $this->language
= $language;
1182 * Get Book language.
1187 function getLanguage() {
1188 return $this->language
;
1192 * Unique book identifier, mandatory.
1193 * Use the URI, or ISBN if available.
1195 * An unambiguous reference to the resource within a given context.
1197 * Recommended best practice is to identify the resource by means of a
1198 * string conforming to a formal identification system.
1200 * Used for the dc:identifier metadata parameter in the OPF file, as well
1201 * as dtb:uid in the NCX file.
1203 * Identifier type should only be:
1204 * EPub::IDENTIFIER_URI
1205 * EPub::IDENTIFIER_ISBN
1206 * EPub::IDENTIFIER_UUID
1208 * @param string $identifier
1209 * @param string $identifierType
1211 * @return bool $success
1213 function setIdentifier($identifier, $identifierType) {
1214 if ($this->isFinalized
|| ($identifierType !== EPub
::IDENTIFIER_URI
&& $identifierType !== EPub
::IDENTIFIER_ISBN
&& $identifierType !== EPub
::IDENTIFIER_UUID
)) {
1217 $this->identifier
= $identifier;
1218 $this->identifierType
= $identifierType;
1223 * Get Book identifier.
1226 * @return $identifier
1228 function getIdentifier() {
1229 return $this->identifier
;
1233 * Get Book identifierType.
1236 * @return $identifierType
1238 function getIdentifierType() {
1239 return $this->identifierType
;
1243 * Book description, optional.
1245 * An account of the resource.
1247 * Description may include but is not limited to: an abstract, a table of
1248 * contents, a graphical representation, or a free-text account of the
1251 * Used for the dc:source metadata parameter in the OPF file
1253 * @param string $description
1255 * @return bool $success
1257 function setDescription($description) {
1258 if ($this->isFinalized
) {
1261 $this->description
= $description;
1266 * Get Book description.
1269 * @return $description
1271 function getDescription() {
1272 return $this->description
;
1276 * Book author or creator, optional.
1277 * The $authorSortKey is basically how the name is to be sorted, usually
1278 * it's "Lastname, First names" where the $author is the straight
1279 * "Firstnames Lastname"
1281 * An entity primarily responsible for making the resource.
1283 * Examples of a Creator include a person, an organization, or a service.
1284 * Typically, the name of a Creator should be used to indicate the entity.
1286 * Used for the dc:creator metadata parameter in the OPF file and the
1287 * docAuthor attribure in the NCX file.
1288 * The sort key is used for the opf:file-as attribute in dc:creator.
1290 * @param string $author
1291 * @param string $authorSortKey
1293 * @return bool $success
1295 function setAuthor($author, $authorSortKey) {
1296 if ($this->isFinalized
) {
1299 $this->author
= $author;
1300 $this->authorSortKey
= $authorSortKey;
1310 function getAuthor() {
1311 return $this->author
;
1315 * Publisher Information, optional.
1317 * An entity responsible for making the resource available.
1319 * Examples of a Publisher include a person, an organization, or a service.
1320 * Typically, the name of a Publisher should be used to indicate the entity.
1322 * Used for the dc:publisher and dc:relation metadata parameters in the OPF file.
1324 * @param string $publisherName
1325 * @param string $publisherURL
1327 * @return bool $success
1329 function setPublisher($publisherName, $publisherURL) {
1330 if ($this->isFinalized
) {
1333 $this->publisherName
= $publisherName;
1334 $this->publisherURL
= $publisherURL;
1339 * Get Book publisherName.
1342 * @return $publisherName
1344 function getPublisherName() {
1345 return $this->publisherName
;
1349 * Get Book publisherURL.
1352 * @return $publisherURL
1354 function getPublisherURL() {
1355 return $this->publisherURL
;
1359 * Release date, optional. If left blank, the time of the finalization will
1362 * A point or period of time associated with an event in the lifecycle of
1365 * Date may be used to express temporal information at any level of
1366 * granularity. Recommended best practice is to use an encoding scheme,
1367 * such as the W3CDTF profile of ISO 8601 [W3CDTF].
1369 * Used for the dc:date metadata parameter in the OPF file
1371 * @param long $timestamp
1373 * @return bool $success
1375 function setDate($timestamp) {
1376 if ($this->isFinalized
) {
1379 $this->date
= $timestamp;
1380 $this->opf
->date
= $timestamp;
1390 function getDate() {
1395 * Book (copy)rights, optional.
1397 * Information about rights held in and over the resource.
1399 * Typically, rights information includes a statement about various
1400 * property rights associated with the resource, including intellectual
1403 * Used for the dc:rights metadata parameter in the OPF file
1405 * @param string $rightsText
1407 * @return bool $success
1409 function setRights($rightsText) {
1410 if ($this->isFinalized
) {
1413 $this->rights
= $rightsText;
1423 function getRights() {
1424 return $this->rights
;
1430 * The topic of the resource.
1432 * Typically, the subject will be represented using keywords, key phrases,
1433 * or classification codes. Recommended best practice is to use a
1434 * controlled vocabulary. To describe the spatial or temporal topic of the
1435 * resource, use the Coverage element.
1437 * @param string $subject
1439 function setSubject($subject) {
1440 if ($this->isFinalized
) {
1443 $this->opf
->addDCMeta(DublinCore
::SUBJECT
, $this->decodeHtmlEntities($subject));
1447 * Book source URL, optional.
1449 * A related resource from which the described resource is derived.
1451 * The described resource may be derived from the related resource in whole
1452 * or in part. Recommended best practice is to identify the related
1453 * resource by means of a string conforming to a formal identification system.
1455 * Used for the dc:source metadata parameter in the OPF file
1457 * @param string $sourceURL
1459 * @return bool $success
1461 function setSourceURL($sourceURL) {
1462 if ($this->isFinalized
) {
1465 $this->sourceURL
= $sourceURL;
1470 * Get Book sourceURL.
1473 * @return $sourceURL
1475 function getSourceURL() {
1476 return $this->sourceURL
;
1480 * Coverage, optional.
1482 * The spatial or temporal topic of the resource, the spatial applicability
1483 * of the resource, or the jurisdiction under which the resource is relevant.
1485 * Spatial topic and spatial applicability may be a named place or a location
1486 * specified by its geographic coordinates. Temporal topic may be a named
1487 * period, date, or date range. A jurisdiction may be a named administrative
1488 * entity or a geographic place to which the resource applies. Recommended
1489 * best practice is to use a controlled vocabulary such as the Thesaurus of
1490 * Geographic Names [TGN]. Where appropriate, named places or time periods
1491 * can be used in preference to numeric identifiers such as sets of
1492 * coordinates or date ranges.
1494 * Used for the dc:coverage metadata parameter in the OPF file
1496 * Same as ->addDublinCoreMetadata(DublinCore::COVERAGE, $coverage);
1498 * @param string $coverage
1500 * @return bool $success
1502 function setCoverage($coverage) {
1503 if ($this->isFinalized
) {
1506 $this->coverage
= $coverage;
1511 * Get Book coverage.
1516 function getCoverage() {
1517 return $this->coverage
;
1521 * Set book Relation.
1523 * A related resource.
1525 * Recommended best practice is to identify the related resource by means
1526 * of a string conforming to a formal identification system.
1528 * @param string $relation
1530 function setRelation($relation) {
1531 if ($this->isFinalized
) {
1534 $this->relation
= $relation;
1538 * Get the book relation.
1540 * @return string The relation.
1542 function getRelation() {
1543 return $this->relation
;
1547 * Set book Generator.
1549 * The generator is a meta tag added to the ncx file, it is not visible
1550 * from within the book, but is a kind of electronic watermark.
1552 * @param string $generator
1554 function setGenerator($generator) {
1555 if ($this->isFinalized
) {
1558 $this->generator
= $generator;
1562 * Get the book relation.
1564 * @return string The generator identity string.
1566 function getGenerator() {
1567 return $this->generator
;
1571 * Set ePub date formate to the short yyyy-mm-dd form, for compliance with
1572 * a bug in EpubCheck, prior to its version 1.1.
1574 * The latest version of ePubCheck can be obtained here:
1575 * http://code.google.com/p/epubcheck/
1578 * @return bool $success
1580 function setShortDateFormat() {
1581 if ($this->isFinalized
) {
1584 $this->dateformat
= $this->dateformatShort
;
1591 function setIgnoreEmptyBuffer($ignoreEmptyBuffer = TRUE) {
1592 die ("Function was deprecated, functionality is no longer needed.");
1596 * Set the references title for the ePub 3 landmarks section
1598 * @param string $referencesTitle
1599 * @param string $referencesId
1600 * @param string $referencesClass
1603 function setReferencesTitle($referencesTitle = "Guide", $referencesId = "", $referencesClass = "references") {
1604 if ($this->isFinalized
) {
1607 $this->ncx
->referencesTitle
= is_string($referencesTitle) ? trim($referencesTitle) : "Guide";
1608 $this->ncx
->referencesId
= is_string($referencesId) ? trim($referencesId) : "references";
1609 $this->ncx
->referencesClass
= is_string($referencesClass) ? trim($referencesClass) : "references";
1614 * Set the references title for the ePub 3 landmarks section
1616 * @param bool $referencesTitle
1618 function setisReferencesAddedToToc($isReferencesAddedToToc = TRUE) {
1619 if ($this->isFinalized
) {
1622 $this->isReferencesAddedToToc
= $isReferencesAddedToToc === TRUE;
1632 function isFinalized() {
1633 return $this->isFinalized
;
1637 * Build the Table of Contents. This is not strictly necessary, as most eReaders will build it from the navigation structure in the .ncx file.
1639 * @param string $cssFileName Include a link to this css file in the TOC html.
1640 * @param string $tocCSSClass The TOC is a <div>, if you need special formatting, you can add a css class for that div. Default is "toc".
1641 * @param string $title Title of the Table of contents. Default is "Table of Contents". Use this for ie. languages other than English.
1642 * @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.
1643 * @param bool $addToIndex Add the TOC to the NCX index at the current leve/position. Default is FALSE
1644 * @param string $tocFileName Change teh default name of the TOC file. The default is "TOC.xhtml"
1646 function buildTOC($cssFileName = NULL, $tocCSSClass = "toc", $title = "Table of Contents", $addReferences = TRUE, $addToIndex = FALSE, $tocFileName = "TOC.xhtml") {
1647 if ($this->isFinalized
) {
1650 $this->buildTOC
= TRUE;
1651 $this->tocTitle
= $title;
1652 $this->tocFileName
= $this->normalizeFileName($tocFileName);
1653 if (!empty($cssFileName)) {
1654 $this->tocCSSFileName
= $this->normalizeFileName($cssFileName);
1656 $this->tocCSSClass
= $tocCSSClass;
1657 $this->tocAddReferences
= $addReferences;
1659 $this->opf
->addItemRef("ref_" . Reference
::TABLE_OF_CONTENTS
, FALSE);
1660 $this->opf
->addReference(Reference
::TABLE_OF_CONTENTS
, $title, $this->tocFileName
);
1663 $navPoint = new NavPoint($this->decodeHtmlEntities($title), $this->tocFileName
, "ref_" . Reference
::TABLE_OF_CONTENTS
);
1664 $this->ncx
->addNavPoint($navPoint);
1666 $this->ncx
->referencesList
[Reference
::TABLE_OF_CONTENTS
] = $this->tocFileName
;
1667 $this->ncx
->referencesName
[Reference
::TABLE_OF_CONTENTS
] = $title;
1671 private function finalizeTOC() {
1672 if (!$this->buildTOC
) {
1676 if (empty($this->tocTitle
)) {
1677 $this->tocTitle
= "Table of Contents";
1680 $tocData = "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n";
1682 if ($this->isEPubVersion2()) {
1683 $tocData .= "<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.1//EN\"\n"
1684 . " \"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd\">\n"
1685 . "<html xmlns=\"http://www.w3.org/1999/xhtml\">\n"
1686 . "<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n";
1688 $tocData .= "<html xmlns=\"http://www.w3.org/1999/xhtml\" xmlns:epub=\"http://www.idpf.org/2007/ops\">\n"
1689 . "<head>\n<meta http-equiv=\"Default-Style\" content=\"text/html; charset=utf-8\" />\n";
1692 if (!empty($this->tocCssFileName
)) {
1693 $tocData .= "<link rel=\"stylesheet\" type=\"text/css\" href=\"" . $this->tocCssFileName
. "\" />\n";
1696 $tocData .= "<title>" . $this->tocTitle
. "</title>\n"
1699 . "<h3>" . $this->tocTitle
. "</h3>\n<div";
1701 if (!empty($this->tocCSSClass
)) {
1702 $tocData .= " class=\"" . $this->tocCSSClass
. "\"";
1706 while (list($item, $descriptive) = each($this->referencesOrder
)) {
1707 if ($item === "text") {
1708 while (list($chapterName, $navPoint) = each($this->ncx
->chapterList
)) {
1709 $fileName = $navPoint->getContentSrc();
1710 $level = $navPoint->getLevel() -2;
1711 $tocData .= "\t<p>" . str_repeat("      ", $level) . "<a href=\"" . $this->sanitizeFileName($fileName) . "\">" . $chapterName . "</a></p>\n";
1713 } else if ($this->tocAddReferences
=== TRUE) {
1714 if (array_key_exists($item, $this->ncx
->referencesList
)) {
1715 $tocData .= "\t<p><a href=\"" . $this->ncx
->referencesList
[$item] . "\">" . $descriptive . "</a></p>\n";
1716 } else if ($item === "toc") {
1717 $tocData .= "\t<p><a href=\"TOC.xhtml\">" . $this->tocTitle
. "</a></p>\n";
1718 } else if ($item === "cover" && $this->isCoverImageSet
) {
1719 $tocData .= "\t<p><a href=\"CoverPage.xhtml\">" . $descriptive . "</a></p>\n";
1723 $tocData .= "</div>\n</body>\n</html>\n";
1725 $this->addReferencePage($this->tocTitle
, $this->tocFileName
, $tocData, Reference
::TABLE_OF_CONTENTS
);
1732 function isEPubVersion2() {
1733 return $this->bookVersion
=== EPub
::BOOK_VERSION_EPUB2
;
1737 * @param string $cssFileName
1738 * @param string $title
1741 function buildEPub3TOC($cssFileName = NULL, $title = "Table of Contents") {
1742 $this->ncx
->referencesOrder
= $this->referencesOrder
;
1743 $this->ncx
->setDocTitle($this->decodeHtmlEntities($this->title
));
1744 return $this->ncx
->finalizeEPub3($title, $cssFileName);
1748 * @param string $fileName
1749 * @param string $tocData
1752 function addEPub3TOC($fileName, $tocData) {
1753 if ($this->isEPubVersion2() || $this->isFinalized
|| array_key_exists($fileName, $this->fileList
)) {
1756 $fileName = Zip
::getRelativePath($fileName);
1757 $fileName = preg_replace('#^[/\.]+#i', "", $fileName);
1759 $this->zip
->addFile($tocData, $this->bookRoot
.$fileName);
1761 $this->fileList
[$fileName] = $fileName;
1762 $this->opf
->addItem("toc", $fileName, "application/xhtml+xml", "nav");
1767 * Check for mandatory parameters and finalize the e-book.
1768 * Once finalized, the book is locked for further additions.
1770 * @return bool $success
1772 function finalize() {
1773 if ($this->isFinalized
|| $this->chapterCount
== 0 || empty($this->title
) || empty($this->language
)) {
1777 if (empty($this->identifier
) || empty($this->identifierType
)) {
1778 $this->setIdentifier($this->createUUID(4), EPub
::IDENTIFIER_UUID
);
1781 if ($this->date
== 0) {
1782 $this->date
= time();
1785 if (empty($this->sourceURL
)) {
1786 $this->sourceURL
= $this->getCurrentPageURL();
1789 if (empty($this->publisherURL
)) {
1790 $this->sourceURL
= $this->getCurrentServerURL();
1793 // Generate OPF data:
1794 $this->opf
->setIdent("BookId");
1795 $this->opf
->initialize($this->title
, $this->language
, $this->identifier
, $this->identifierType
);
1797 $DCdate = new DublinCore(DublinCore
::DATE
, gmdate($this->dateformat
, $this->date
));
1798 $DCdate->addOpfAttr("event", "publication");
1799 $this->opf
->metadata
->addDublinCore($DCdate);
1801 if (!empty($this->description
)) {
1802 $this->opf
->addDCMeta(DublinCore
::DESCRIPTION
, $this->decodeHtmlEntities($this->description
));
1805 if (!empty($this->publisherName
)) {
1806 $this->opf
->addDCMeta(DublinCore
::PUBLISHER
, $this->decodeHtmlEntities($this->publisherName
));
1809 if (!empty($this->publisherURL
)) {
1810 $this->opf
->addDCMeta(DublinCore
::RELATION
, $this->decodeHtmlEntities($this->publisherURL
));
1813 if (!empty($this->author
)) {
1814 $author = $this->decodeHtmlEntities($this->author
);
1815 $this->opf
->addCreator($author, $this->decodeHtmlEntities($this->authorSortKey
), MarcCode
::AUTHOR
);
1816 $this->ncx
->setDocAuthor($author);
1819 if (!empty($this->rights
)) {
1820 $this->opf
->addDCMeta(DublinCore
::RIGHTS
, $this->decodeHtmlEntities($this->rights
));
1823 if (!empty($this->coverage
)) {
1824 $this->opf
->addDCMeta(DublinCore
::COVERAGE
, $this->decodeHtmlEntities($this->coverage
));
1827 if (!empty($this->sourceURL
)) {
1828 $this->opf
->addDCMeta(DublinCore
::SOURCE
, $this->sourceURL
);
1831 if (!empty($this->relation
)) {
1832 $this->opf
->addDCMeta(DublinCore
::RELATION
, $this->decodeHtmlEntities($this->relation
));
1835 if ($this->isCoverImageSet
) {
1836 $this->opf
->addMeta("cover", "coverImage");
1839 if (!empty($this->generator
)) {
1840 $gen = $this->decodeHtmlEntities($this->generator
);
1841 $this->opf
->addMeta("generator", $gen);
1842 $this->ncx
->addMetaEntry("dtb:generator", $gen);
1845 if ($this->EPubMark
) {
1846 $this->opf
->addMeta("generator", "EPub (Version " . self
::VERSION
. ") by A. Grandt, http://www.phpclasses.org/package/6115");
1849 reset($this->ncx
->chapterList
);
1850 list($firstChapterName, $firstChapterNavPoint) = each($this->ncx
->chapterList
);
1851 $firstChapterFileName = $firstChapterNavPoint->getContentSrc();
1852 $this->opf
->addReference(Reference
::TEXT
, $this->decodeHtmlEntities($firstChapterName), $firstChapterFileName);
1854 $this->ncx
->setUid($this->identifier
);
1856 $this->ncx
->setDocTitle($this->decodeHtmlEntities($this->title
));
1858 $this->ncx
->referencesOrder
= $this->referencesOrder
;
1859 if ($this->isReferencesAddedToToc
) {
1860 $this->ncx
->finalizeReferences();
1863 $this->finalizeTOC();
1865 if (!$this->isEPubVersion2()) {
1866 $this->addEPub3TOC("epub3toc.xhtml", $this->buildEPub3TOC());
1869 $opfFinal = $this->fixEncoding($this->opf
->finalize());
1870 $ncxFinal = $this->fixEncoding($this->ncx
->finalize());
1872 if (mb_detect_encoding($opfFinal, 'UTF-8', true) === "UTF-8") {
1873 $this->zip
->addFile($opfFinal, $this->bookRoot
."book.opf");
1875 $this->zip
->addFile(mb_convert_encoding($opfFinal, "UTF-8"), $this->bookRoot
."book.opf");
1878 if (mb_detect_encoding($ncxFinal, 'UTF-8', true) === "UTF-8") {
1879 $this->zip
->addFile($ncxFinal, $this->bookRoot
."book.ncx");
1881 $this->zip
->addFile(mb_convert_encoding($ncxFinal, "UTF-8"), $this->bookRoot
."book.ncx");
1887 $this->isFinalized
= TRUE;
1892 * Ensure the encoded string is a valid UTF-8 string.
1894 * 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.
1896 * @link: http://snippetdb.com/php/convert-string-to-utf-8-for-mysql
1897 * @param string $in_str
1898 * @return string converted string.
1900 function fixEncoding($in_str) {
1901 if (mb_detect_encoding($in_str) == "UTF-8" && mb_check_encoding($in_str,"UTF-8")) {
1904 return utf8_encode($in_str);
1909 * Return the finalized book.
1911 * @return string with the book in binary form.
1913 function getBook() {
1914 if (!$this->isFinalized
) {
1918 return $this->zip
->getZipData();
1922 * Remove disallowed characters from string to get a nearly safe filename
1924 * @param string $fileName
1925 * @return mixed|string
1927 function sanitizeFileName($fileName) {
1928 $fileName1 = str_replace($this->forbiddenCharacters
, '', $fileName);
1929 $fileName2 = preg_replace('/[\s-]+/', '-', $fileName1);
1930 return trim($fileName2, '.-_');
1935 * Cleanup the filepath, and remove leading . and / characters.
1937 * Sometimes, when a path is generated from multiple fragments,
1938 * you can get something like "../data/html/../images/image.jpeg"
1939 * ePub files don't work well with that, this will normalize that
1940 * example path to "data/images/image.jpeg"
1942 * @param string $fileName
1943 * @return string normalized filename
1945 function normalizeFileName($fileName) {
1946 return preg_replace('#^[/\.]+#i', "", Zip
::getRelativePath($fileName));
1950 * Save the ePub file to local disk.
1952 * @param string $fileName
1953 * @param string $baseDir If empty baseDir is absolute to server path, if omitted it's relative to script path
1954 * @return The sent file name if successfull, FALSE if it failed.
1956 function saveBook($fileName, $baseDir = '.') {
1958 // Make fileName safe
1959 $fileName = $this->sanitizeFileName($fileName);
1961 // Finalize book, if it's not done already
1962 if (!$this->isFinalized
) {
1966 if (stripos(strrev($fileName), "bupe.") !== 0) {
1967 $fileName .= ".epub";
1970 // Try to open file access
1971 $fh = fopen($baseDir.'/'.$fileName, "w");
1974 fputs($fh, $this->getBook());
1977 // if file is written return TRUE
1981 // return FALSE by default
1986 * Return the finalized book size.
1990 function getBookSize() {
1991 if (!$this->isFinalized
) {
1995 return $this->zip
->getArchiveSize();
1999 * Send the book as a zip download
2001 * Sending will fail if the output buffer is in use. You can override this limit by
2002 * calling setIgnoreEmptyBuffer(TRUE), though the function will still fail if that
2003 * buffer is not empty.
2005 * @param string $fileName The name of the book without the .epub at the end.
2006 * @return The sent file name if successfull, FALSE if it failed.
2008 function sendBook($fileName) {
2009 if (!$this->isFinalized
) {
2013 if (stripos(strrev($fileName), "bupe.") !== 0) {
2014 $fileName .= ".epub";
2017 if (TRUE === $this->zip
->sendZip($fileName, "application/epub+zip")) {
2024 * Generates an UUID.
2026 * Default version (4) will generate a random UUID, version 3 will URL based UUID.
2028 * Added for convinience
2030 * @param int $bookVersion UUID version to retrieve, See lib.uuid.manual.html for details.
2031 * @param string $url
2032 * @return string The formatted uuid
2034 function createUUID($bookVersion = 4, $url = NULL) {
2035 include_once("lib.uuid.php");
2036 return UUID
::mint($bookVersion, $url, UUID
::nsURL
);
2040 * Get the url of the current page.
2041 * Example use: Default Source URL
2043 * $return string Page URL.
2045 function getCurrentPageURL() {
2046 $pageURL = $this->getCurrentServerURL() . filter_input(INPUT_SERVER
, "REQUEST_URI");
2051 * Get the url of the server.
2052 * Example use: Default Publisher URL
2054 * $return string Server URL.
2056 function getCurrentServerURL() {
2057 $serverURL = 'http';
2058 $https = filter_input(INPUT_SERVER
, "HTTPS");
2059 $port = filter_input(INPUT_SERVER
, "SERVER_PORT");
2061 if ($https === "on") {
2064 $serverURL .= "://" . filter_input(INPUT_SERVER
, "SERVER_NAME");
2065 if ($port != "80") {
2066 $serverURL .= ":" . $port;
2068 return $serverURL . '/';
2072 * Try to determine the mimetype of the file path.
2074 * @param string $source Path
2075 * @return string mimetype, or FALSE.
2077 function getMime($source) {
2078 return $this->mimetypes
[pathinfo($source, PATHINFO_EXTENSION
)];
2082 * Get an image from a file or url, return it resized if the image exceeds the $maxImageWidth or $maxImageHeight directives.
2084 * The return value is an array.
2085 * ['width'] is the width of the image.
2086 * ['height'] is the height of the image.
2087 * ['mime'] is the mime type of the image. Resized images are always in jpeg format.
2088 * ['image'] is the image data.
2089 * ['ext'] is the extension of the image file.
2091 * @param string $source path or url to file.
2094 function getImage($source) {
2097 $mime = "application/octet-stream";
2102 $image = $this->getFileContents($source);
2104 if ($image !== FALSE && strlen($image) > 0) {
2105 $imageFile = imagecreatefromstring($image);
2106 if ($imageFile !== false) {
2107 $width = ImageSX($imageFile);
2108 $height = ImageSY($imageFile);
2110 if ($this->isExifInstalled
) {
2111 @$type = exif_imagetype($source);
2112 $mime = image_type_to_mime_type($type);
2114 if ($mime === "application/octet-stream") {
2115 $mime = $this->image_file_type_from_binary($image);
2117 if ($mime === "application/octet-stream") {
2118 $mime = $this->getMimeTypeFromUrl($source);
2124 if ($width <= 0 || $height <= 0) {
2130 if ($this->isGdInstalled
) {
2131 if ($width > $this->maxImageWidth
) {
2132 $ratio = $this->maxImageWidth
/$width;
2134 if ($height*$ratio > $this->maxImageHeight
) {
2135 $ratio = $this->maxImageHeight
/$height;
2138 if ($ratio < 1 || empty($mime) || ($this->isGifImagesEnabled
!== FALSE && $mime == "image/gif")) {
2139 $image_o = imagecreatefromstring($image);
2140 $image_p = imagecreatetruecolor($width*$ratio, $height*$ratio);
2142 if ($mime == "image/png") {
2143 imagealphablending($image_p, false);
2144 imagesavealpha($image_p, true);
2145 imagealphablending($image_o, true);
2147 imagecopyresampled($image_p, $image_o, 0, 0, 0, 0, ($width*$ratio), ($height*$ratio), $width, $height);
2149 imagepng($image_p, NULL, 9);
2150 $image = ob_get_contents();
2155 imagecopyresampled($image_p, $image_o, 0, 0, 0, 0, ($width*$ratio), ($height*$ratio), $width, $height);
2157 imagejpeg($image_p, NULL, 80);
2158 $image = ob_get_contents();
2161 $mime = "image/jpeg";
2164 imagedestroy($image_o);
2165 imagedestroy($image_p);
2170 static $mimeToExt = array (
2171 'image/jpeg' => 'jpg',
2172 'image/gif' => 'gif',
2173 'image/png' => 'png'
2176 if (isset($mimeToExt[$mime])) {
2177 $ext = $mimeToExt[$mime];
2182 $rv['width'] = $width*$ratio;
2183 $rv['height'] = $height*$ratio;
2184 $rv['mime'] = $mime;
2185 $rv['image'] = $image;
2192 * Get file contents, using curl if available, else file_get_contents
2194 * @param string $source
2197 function getFileContents($source, $toTempFile = FALSE) {
2198 $isExternal = preg_match('#^(http|ftp)s?://#i', $source) == 1;
2200 if ($isExternal && $this->isCurlInstalled
) {
2205 $info = array('http_code' => 500);
2207 curl_setopt($ch, CURLOPT_HEADER
, 0);
2208 curl_setopt($ch, CURLOPT_URL
, str_replace(" ","%20",$source));
2209 curl_setopt($ch, CURLOPT_RETURNTRANSFER
, true);
2210 curl_setopt($ch, CURLOPT_FOLLOWLOCATION
, true);
2211 curl_setopt($ch, CURLOPT_BUFFERSIZE
, 4096);
2214 $outFile = tempnam(sys_get_temp_dir(), "EPub_v" . EPub
::VERSION
. "_");
2215 $fp = fopen($outFile, "w+b");
2216 curl_setopt($ch, CURLOPT_FILE
, $fp);
2218 $res = curl_exec($ch);
2219 $info = curl_getinfo($ch);
2224 $res = curl_exec($ch);
2225 $info = curl_getinfo($ch);
2230 if ($info['http_code'] == 200 && $res != false) {
2239 if ($this->isFileGetContentsInstalled
&& (!$isExternal || $this->isFileGetContentsExtInstalled
)) {
2240 @$data = file_get_contents($source);
2247 * get mime type from image data
2249 * By fireweasel found on http://stackoverflow.com/questions/2207095/get-image-mimetype-from-resource-in-php-gd
2250 * @staticvar array $type
2251 * @param object $binary
2254 function image_file_type_from_binary($binary) {
2257 '/\A(?:(\xff\xd8\xff)|(GIF8[79]a)|(\x89PNG\x0d\x0a)|(BM)|(\x49\x49(?:\x2a\x00|\x00\x4a))|(FORM.{4}ILBM))/',
2259 return 'application/octet-stream';
2261 static $type = array (
2265 4 => 'image/x-windows-bmp',
2267 6 => 'image/x-ilbm',
2269 return $type[count($hits) - 1];
2273 * @param string $source URL Source
2274 * @return string MimeType
2276 function getMimeTypeFromUrl($source) {
2279 $srev = strrev($source);
2280 $pos = strpos($srev, "?");
2281 if ($pos !== FALSE) {
2282 $srev = substr($srev, $pos+
1);
2285 $pos = strpos($srev, ".");
2286 if ($pos !== FALSE) {
2287 $ext = strtolower(strrev(substr($srev, 0, $pos)));
2290 if ($ext !== FALSE) {
2291 return $this->getMimeTypeFromExtension($ext);
2293 return "application/octet-stream";
2297 * @param string $ext Extension
2298 * @return string MimeType
2300 function getMimeTypeFromExtension($ext) {
2305 return 'image/jpeg';
2311 return 'image/x-windows-bmp';
2315 return 'image/tiff';
2318 return 'image/x-ilbm';
2320 return "application/octet-stream";
2325 * Encode html code to use html entities, safeguarding it from potential character encoding peoblems
2326 * This function is a bit different from the vanilla htmlentities function in that it does not encode html tags.
2328 * The regexp is taken from the PHP Manual discussion, it was written by user "busbyjon".
2329 * http://www.php.net/manual/en/function.htmlentities.php#90111
2331 * @param string $string string to encode.
2333 public function encodeHtml($string) {
2334 $string = strtr($string, $this->html_encoding_characters
);
2336 //return preg_replace("/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,5};)/", "&\\1", $string);
2337 //return preg_replace("/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,5};)/", "&", $string);
2342 * Helper function to create a DOM fragment with given markup.
2344 * @author Adam Schmalhofer
2346 * @param DOMDocument $dom
2347 * @param string $markup
2348 * @return DOMNode fragment in a node.
2350 protected function createDomFragment($dom, $markup) {
2351 $node = $dom->createDocumentFragment();
2352 $node->appendXML($markup);
2357 * Retrieve an array of file names currently added to the book.
2358 * $key is the filename used in the book
2359 * $value is the original filename, will be the same as $key for most entries
2361 * @return array file list
2363 function getFileList() {
2364 return $this->fileList
;
2368 * @deprecated Use Zip::getRelativePath($relPath) instead.
2370 function relPath($relPath) {
2371 die ("Function was deprecated, use Zip::getRelativePath(\$relPath); instead");
2375 * Set default chapter target size.
2376 * Default is 250000 bytes, and minimum is 10240 bytes.
2378 * @param int $size segment size in bytes
2381 function setSplitSize($size) {
2382 $this->splitDefaultSize
= (int)$size;
2383 if ($size < 10240) {
2384 $this->splitDefaultSize
= 10240; // Making the file smaller than 10k is not a good idea.
2389 * Get the chapter target size.
2393 function getSplitSize() {
2394 return $this->splitDefaultSize
;
2398 * Remove all non essential html tags and entities.
2400 * @global type $htmlEntities
2401 * @param string $string
2402 * @return string with the stripped entities.
2404 function decodeHtmlEntities($string) {
2405 global $htmlEntities;
2407 $string = preg_replace('~\s*<br\s*/*\s*>\s*~i', "\n", $string);
2408 $string = preg_replace('~\s*</(p|div)\s*>\s*~i', "\n\n", $string);
2409 $string = preg_replace('~<[^>]*>~', '', $string);
2411 $string = strtr($string, $htmlEntities);
2413 $string = str_replace('&', '&', $string);
2414 $string = str_replace('&amp;', '&', $string);
2415 $string = preg_replace('~&(#x*[a-fA-F0-9]+;)~', '&\1', $string);
2416 $string = str_replace('<', '<', $string);
2417 $string = str_replace('>', '>', $string);
2423 * Simply remove all HTML tags, brute force and no finesse.
2425 * @param string $string html
2428 function html2text($string) {
2429 return preg_replace('~<[^>]*>~', '', $string);
2436 return $this->log
->getLog();