4 * Copyright(c) 2008-2010 Internet Archive. Software license AGPL version 3.
6 * This file is part of BookReader. The full source code can be found at GitHub:
7 * http://github.com/openlibrary/bookreader
9 * Note: Edits to this file must pass through github. To submit a patch to this
10 * file please contact mang via http://github.com/mangtronix or mang at archive dot org
11 * Direct changes to this file may get clobbered when the code is synchronized
18 // Operators recognized in BookReader download URLs
19 public static $downloadOperators = array('page');
21 // Returns true if can display the book in item with a given prefix (typically the item identifier)
22 public static function canDisplay($item, $prefix, $checkOldScandata = false)
25 // A "book" is an image stack and scandata.
26 // 1. Old items may have scandata.xml or scandata.zip and itemid_{imageformat}.{zip,tar}
27 // 2. Newer items may have multiple {arbitraryname}_scandata.xml and {arbitraryname}_{imageformat}.{zip,tar}
29 $foundScandata = false;
30 $foundImageStack = false;
32 $targetScandata = $prefix . "_scandata.xml";
34 // $$$ TODO add support for jpg and tar stacks
35 // https://bugs.edge.launchpad.net/gnubook/+bug/323003
36 // https://bugs.edge.launchpad.net/gnubook/+bug/385397
37 $imageFormatRegex = '@' . preg_quote($prefix, '@') . '_(jp2|tif|jpg)\.(zip|tar)$@';
39 $baseLength = strlen($item->metadataGrabber->mainDir . '/');
40 foreach ($item->getFiles() as $location => $fileInfo) {
41 $filename = substr($location, $baseLength);
43 if ($checkOldScandata) {
44 if ($filename == 'scandata.xml' || $filename == 'scandata.zip') {
45 $foundScandata = $filename;
49 if ($filename == $targetScandata) {
50 $foundScandata = $filename;
53 if (preg_match($imageFormatRegex, $filename)) {
54 $foundImageStack = $filename;
58 if ($foundScandata && $foundImageStack) {
65 // Finds the prefix to use for the book given the part of the URL trailing after /stream/
66 public static function findPrefix($urlPortion)
68 if (!preg_match('#[^/&?]+#', $urlPortion, $matches)) {
69 // URL portion was empty or started with /, &, or ? -- no item identifier
73 $prefix = $matches[0]; // item identifier
75 // $$$ Currently swallows the rest of the URL.
76 // If we want to support e.g. /stream/itemid/subdir/prefix/page/23 will need to adjust.
77 if (preg_match('#[^/&?]+/([^&?]+)#', $urlPortion, $matches)) {
78 // Match is everything after item identifier and slash, up to end or ? or &
79 // e.g. itemid/{match/these/parts}?foo=bar
80 $prefix = $matches[1]; // sub prefix --
86 // $$$ would be cleaner to use different templates instead of the uiMode param
88 // @param subprefix Optional prefix to display a book inside an item (e.g. if does not match identifier)
89 public static function draw($server, $mainDir, $identifier, $subPrefix, $title,
90 $coverLeaf=null, $titleStart='Internet Archive', $uiMode='full')
92 // Set title to default if not set
94 $title = 'BookReader';
99 // manually update with Launchpad version number at each checkin so that browsers
100 // do not use old cached version
101 // see https://bugs.launchpad.net/gnubook/+bug/330748
104 if (BookReader::getDevHost($server)) {
105 // On dev host - add time to force reload
106 // If debugging on IE, remove this line otherwise breakpoints will be invalid after reload
107 $version .= '_' . time();
111 echo "No identifier specified!";
115 $metaURL = BookReader::jsMetadataURL($server, $identifier, $mainDir, $subPrefix);
116 $locateURL = BookReader::jsLocateURL($identifier, $subPrefix);
117 $coverThumb = 'http://www.archive.org/download/' . $identifier . '/'. $subPrefix . '/page/cover_w114.jpg';
118 // startup-up-image must be exactly 320x460
119 //$startupImage = 'http://www.archive.org/download/' . $identifier . '/'. $subPrefix . '/page/cover_w512.jpg';
122 <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
125 <meta name="viewport" content="width=device-width, maximum-scale=1.0" />
126 <meta name="apple-mobile-web-app-capable" content="yes" />
127 <meta name="apple-mobile-web-app-status-bar-style" content="black" />
128 <link rel="apple-touch-icon" href="<? echo($coverThumb); ?>" />
129 <title><? echo $title; ?></title>
131 <meta http-equiv="refresh" content="2; URL=/bookreader/browserunsupported.php?id=<? echo($id); ?>">
133 <link rel="stylesheet" type="text/css" href="/bookreader/BookReader.css?v=<? echo($version); ?>">
134 <? if ($uiMode == "embed") { ?>
135 <link rel="stylesheet" type="text/css" href="/bookreader/BookReaderEmbed.css?v=<? echo($version); ?>">
136 <? } elseif ($uiMode == "touch") { ?>
137 <link rel="stylesheet" type="text/css" href="/bookreader/touch/BookReaderTouch.css?v=<? echo($version); ?>">
139 <script src="/includes/jquery-1.4.2.min.js" type="text/javascript"></script>
140 <script type="text/javascript" src="/bookreader/jquery-ui-1.8.5.custom.min.js?v=<? echo($version); ?>"></script>
141 <script type="text/javascript" src="http://www.archive.org/includes/analytics.js?v=2"></script>
142 <script type="text/javascript" src="/bookreader/dragscrollable.js?v=<? echo($version); ?>"></script>
143 <script type="text/javascript" src="/bookreader/jquery.colorbox-min.js"></script>
144 <script type="text/javascript" src="/bookreader/jquery.ui.ipad.js"></script>
145 <!-- THIS ALLOWS BEAUTYTIPS TO WORK ON IE -->
147 <script type="text/javascript" src="/includes/excanvas.compiled.js"></script>
149 <script type="text/javascript" src="/bookreader/jquery.bt.min.js"></script>
150 <script type="text/javascript" src="/bookreader/BookReader.js?v=<? echo($version); ?>"></script>
151 <? if ( !preg_match("/mobile/i", $_SERVER['HTTP_USER_AGENT']) ) { ?>
152 <script type="text/javascript" src="/bookreader/soundmanager/soundmanager2-ia.js?v=<? echo($version); ?>"></script>
154 soundManager.debugMode = false;
155 soundManager.url = '/bookreader/soundmanager/swf/';
156 soundManager.useHTML5Audio = true;
157 soundManager.flashVersion = 9; //flash 8 version of swf is buggy when calling play() on a sound that is still loading
159 <? } /* mobile user agent */ ?>
161 <body style="background-color: ##939598;">
165 // <? if ($uiMode == 'full') { ?>
166 // <div id="BookReader" style="left:10px; right:200px; top:10px; bottom:2em;">Internet Archive BookReader <noscript>requires JavaScript to be enabled.</noscript></div>
168 // <div id="BookReader" style="left:0; right:0; top:0; bottom:0; border:0">Internet Archive Bookreader <noscript>requires JavaScript to be enabled.</noscript></div>
173 <div id="BookReader">Internet Archive BookReader <noscript>requires JavaScript to be enabled.</noscript></div>
175 <script type="text/javascript">
176 // Set some config variables -- $$$ NB: Config object format has not been finalized
178 <? if ($uiMode == 'embed') { ?>
179 brConfig["mode"] = 1;
180 brConfig["ui"] = "embed";
182 brConfig["mode"] = 2;
185 <!-- The script included below is dynamically generated JavaScript that includes the book metadata and page image access functions.
186 The ia{number}.us.archive.org server referenced below can and does change, so this URL should NOT be used for permanent access. -->
187 <script type="text/javascript" src="<? echo($metaURL); ?>"></script>
188 <!-- This URL will find the item and redirect to the correct server. Remove the line above and use the URL below for stable access. -->
189 <!-- <script type="text/javascript" src="<? echo($locateURL); ?>"></script> -->
191 <script type="text/javascript">
193 if(window.archive_analytics) { window.archive_analytics.values['bookreader'] = 'open'};
199 // Returns the user part of dev host from URL, or null
200 public static function getDevHost($server)
202 if (preg_match("/^www-(\w+)/", $_SERVER["SERVER_NAME"], $match)) {
210 public static function serverBaseURL($server)
212 // Check if we're on a dev vhost and point to JSIA in the user's public_html
214 // $$$ the remapping isn't totally automatic yet and requires user to
215 // ln -s ~/petabox/www/datanode/BookReader ~/public_html/BookReader
216 // so we enable it only for known hosts
217 $devhost = BookReader::getDevHost($server);
218 $devhosts = array('mang', 'testflip', 'rkumar');
219 if (in_array($devhost, $devhosts)) {
220 $server = $server . "/~" . $devhost;
226 public static function jsMetadataURL($server, $identifier, $mainDir, $subPrefix = '')
228 $serverBaseURL = BookReader::serverBaseURL($server);
230 $params = array( 'id' => $identifier, 'itemPath' => $mainDir, 'server' => $server );
232 $params['subPrefix'] = $subPrefix;
235 $keys = array_keys($params);
236 $lastParam = end($keys);
237 $url = "http://{$serverBaseURL}/BookReader/BookReaderJSIA.php?";
238 foreach($params as $param=>$value) {
239 $url .= $param . '=' . $value;
240 if ($param != $lastParam) {
248 // This returns a URL that finds the item then returns a redirect to BookReaderJSIA.php
249 // on the item's server.
250 public static function jsLocateURL($identifier, $subPrefix = '')
252 $locateURL = 'http://www.archive.org/bookreader/BookReaderJSLocate.php?id=' . $identifier;
254 $locateURL .= '&subPrefix=' . $subPrefix;
259 // Return the URL for the requested /download/$path, or null
260 public static function getURL($path, $item) {
261 // $path should look like {itemId}/{operator}/{filename}
262 // Other operators may be added
264 $urlParts = BookReader::parsePath($path);
266 // Check for non-handled cases
267 $required = array('identifier', 'operator', 'operand');
268 foreach ($required as $key) {
269 if (!array_key_exists($key, $urlParts)) {
274 $identifier = $urlParts['identifier'];
275 $operator = $urlParts['operator'];
276 $filename = $urlParts['operand'];
277 $subPrefix = $urlParts['subPrefix'];
279 $serverBaseURL = BookReader::serverBaseURL($item->getServer());
281 // Baseline query params
284 'itemPath' => $item->getMainDir(),
285 'server' => $serverBaseURL
288 $query['subPrefix'] = $subPrefix;
294 // Look for old-style preview request - e.g. {identifier}_cover.jpg
295 if (preg_match('/^(.*)_((cover|title|preview).*)/', $filename, $matches) === 1) {
296 // Serve preview image
298 $query['page'] = $page;
299 return 'http://' . $serverBaseURL . '/BookReader/BookReaderPreview.php?' . http_build_query($query, '', '&');
302 // New-style preview request - e.g. cover_thumb.jpg
303 if (preg_match('/^(cover|title|preview)/', $filename, $matches) === 1) {
304 $query['page'] = $filename;
305 return 'http://' . $serverBaseURL . '/BookReader/BookReaderPreview.php?' . http_build_query($query, '', '&');
308 // Asking for a non-preview page
309 $query['page'] = $filename;
310 return 'http://' . $serverBaseURL . '/BookReader/BookReaderImages.php?' . http_build_query($query, '', '&');
317 return null; // was not handled
320 public static function browserFromUserAgent($userAgent) {
321 $browserPatterns = array(
323 'iphone' => '/iPhone/', // Also cover iPod Touch
324 'android' => '/Android/',
327 foreach ($browserPatterns as $browser => $pattern) {
328 if (preg_match($pattern, $userAgent)) {
336 // $$$ Ideally we will not rely on user agent, but for the moment we do
337 public static function paramsFromUserAgent($userAgent) {
338 // $$$ using 'embed' here for devices with assumed small screens -- really should just use CSS3 media queries
339 $browserParams = array(
340 'ipad' => array( 'ui' => 'touch' ),
341 'iphone' => array( 'ui' => 'embed', 'mode' => '1up' ),
342 'android' => array( 'ui' => 'embed', 'mode' => '1up' ),
345 $browser = BookReader::browserFromUserAgent($userAgent);
347 return $browserParams[$browser];
352 public static function parsePath($path) {
353 // Parse the BookReader path and return the parts
354 // e.g. itemid/some/sub/dir/page/cover.jpg -> array( 'identifier' => 'itemid', 'subPrefix' => 'some/sub/dir',
355 // 'operator' => 'page', 'filename' => 'cover.jpg')
359 // Pull off query, e.g. ?foo=bar
360 if (preg_match('#(.*?)(\?.*)#', $path, $matches) === 1) {
361 $parts['query'] = $matches[2];
365 // Pull off identifier
366 if (preg_match('#[^/&?]+#', $path, $matches) === 0) {
370 $parts['identifier'] = $matches[0];
371 $path = substr($path, strlen($matches[0]));
373 // Look for operators
374 // The sub-prefix can be arbitrary, so we match up until the first operator
375 $operators = '(' . join('|', self::$downloadOperators) . ')';
376 $pattern = '#(?P<subPrefix>.*?)/(?P<operator>' . $operators . ')/(?P<operand>.*)#';
377 if (preg_match($pattern, $path, $matches) === 1) {
378 $parts['subPrefix'] = substr($matches['subPrefix'], 1); // remove leading '/'
379 $parts['operator'] = $matches['operator'];
380 $parts['operand'] = $matches['operand'];
382 $parts['subPrefix'] = $path;