Removed the tree filter toggle
[Packages/TYPO3.CMS.git] / t3lib / class.t3lib_htmlmail.php
1 <?php
2 /***************************************************************
3 * Copyright notice
4 *
5 * (c) 1999-2006 Kasper Skaarhoj (kasperYYYY@typo3.com)
6 * All rights reserved
7 *
8 * This script is part of the TYPO3 project. The TYPO3 project is
9 * free software; you can redistribute it and/or modify
10 * it under the terms of the GNU General Public License as published by
11 * the Free Software Foundation; either version 2 of the License, or
12 * (at your option) any later version.
13 *
14 * The GNU General Public License can be found at
15 * http://www.gnu.org/copyleft/gpl.html.
16 * A copy is found in the textfile GPL.txt and important notices to the license
17 * from the author is found in LICENSE.txt distributed with these scripts.
18 *
19 *
20 * This script is distributed in the hope that it will be useful,
21 * but WITHOUT ANY WARRANTY; without even the implied warranty of
22 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
23 * GNU General Public License for more details.
24 *
25 * This copyright notice MUST APPEAR in all copies of the script!
26 ***************************************************************/
27 /**
28 * HTML mail class
29 *
30 * $Id$
31 *
32 * @author Kasper Skaarhoj <kasperYYYY@typo3.com>
33 */
34 /**
35 * [CLASS/FUNCTION INDEX of SCRIPT]
36 *
37 *
38 *
39 * 193: class t3lib_htmlmail
40 * 261: function t3lib_htmlmail ()
41 * 268: function start ()
42 * 305: function useQuotedPrintable()
43 * 315: function useBase64()
44 * 326: function use8Bit()
45 * 338: function encodeMsg($content)
46 * 348: function addPlain ($content)
47 * 360: function addAttachment($file)
48 * 378: function addHTML ($file)
49 * 401: function extractHtmlInit($html,$url)
50 * 412: function send($recipient)
51 *
52 * SECTION: Main functions
53 * 441: function setHeaders()
54 * 500: function setRecipient ($recip)
55 * 518: function getHTMLContentType()
56 * 527: function setContent()
57 * 554: function constructMixed ($boundary)
58 * 593: function constructHTML ($boundary)
59 * 617: function constructAlternative($boundary)
60 * 638: function constructHTML_media ($boundary)
61 * 691: function sendTheMail ()
62 * 757: function getBoundary()
63 * 769: function setPlain ($content)
64 * 780: function setHtml ($content)
65 * 791: function add_header($header)
66 * 812: function add_message($string)
67 * 823: function getContent($type)
68 * 832: function preview()
69 *
70 * SECTION: Functions for acquiring attachments, HTML, analyzing and so on **
71 * 860: function fetchHTML($file)
72 * 878: function fetchHTMLMedia()
73 * 899: function extractMediaLinks()
74 * 976: function extractHyperLinks()
75 * 1025: function extractFramesInfo()
76 * 1051: function substMediaNamesInHTML($absolute)
77 * 1078: function substHREFsInHTML()
78 * 1106: function substHTTPurlsInPlainText($content)
79 * 1142: function fixRollOvers()
80 *
81 * SECTION: File and URL-functions
82 * 1189: function makeBase64($inputstr)
83 * 1200: function getExtendedURL($url)
84 * 1222: function addUserPass($url)
85 * 1238: function getURL($url)
86 * 1250: function getStrippedURL($url)
87 * 1271: function getMimeType($url)
88 * 1300: function absRef($ref)
89 * 1320: function split_fileref($fileref)
90 * 1347: function extParseUrl($path)
91 * 1362: function tag_regex($tagArray)
92 * 1384: function get_tag_attributes($tag)
93 * 1426: function quoted_printable($string)
94 * 1437: function convertName($name)
95 *
96 * TOTAL FUNCTIONS: 49
97 * (This index is automatically created/updated by the extension "extdeveval")
98 *
99 */
100 /**
101 * NOTES on MIME mail structures:
102 *
103 * Plain + HTML
104 * multipart/alternative (text, html)
105 * multipart/alternative (text, html)
106 *
107 * Plain + HTML + image
108 * multipart/related (m/a, cids)
109 * multipart/alternative (text, html)
110 *
111 * multipart/related (m/a, cids)
112 * multipart/alternative (text, html)
113 *
114 * plain + attachment
115 * multipart/mixed
116 *
117 * HTML + Attachment:
118 * multipart/mixed (text/html , attachments)
119 *
120 * Plain + HTML + Attachments:
121 * multipart/mixed (m/a, attachments)
122 * multipart/alternative (text, html)
123 *
124 * Plain + HTML + image + attachment
125 *
126 * Outlook expr.
127 * multipart/mixed (m/r, attachments)
128 * multipart/related (m/a, cids)
129 * multipart/alternative (text, html)
130 *
131 *
132 *
133 * FROM RFC 1521:
134 *
135 * 5.1 Quoted-Printable Content-Transfer-Encoding
136 * The Quoted-Printable encoding is intended to represent data that largely consists of octets that correspond to printable characters in the ASCII character set. It encodes the data in such a way that the resulting octets are unlikely to be modified by mail transport. If the data being encoded are mostly ASCII text, the encoded form of the data remains largely recognizable by humans. A body which is entirely ASCII may also be encoded in Quoted-Printable to ensure the integrity of the data should the message pass through a character- translating, and/or line-wrapping gateway.
137 *
138 * In this encoding, octets are to be represented as determined by the following rules:
139 * Rule #1: (General 8-bit representation) Any octet, except those indicating a line break according to the newline convention of the canonical (standard) form of the data being encoded, may be represented by an "=" followed by a two digit hexadecimal representation of the octet's value. The digits of the hexadecimal alphabet, for this purpose, are "0123456789ABCDEF". Uppercase letters must be used when sending hexadecimal data, though a robust implementation may choose to recognize lowercase letters on receipt. Thus, for example, the value 12 (ASCII form feed) can be represented by "=0C", and the value 61 (ASCII EQUAL SIGN) can be represented by "=3D". Except when the following rules allow an alternative encoding, this rule is mandatory.
140 * Rule #2: (Literal representation) Octets with decimal values of 33 through 60 inclusive, and 62 through 126, inclusive, MAY be represented as the ASCII characters which correspond to those octets (EXCLAMATION POINT through LESS THAN, and GREATER THAN through TILDE, respectively).
141 * Rule #3: (White Space): Octets with values of 9 and 32 MAY be represented as ASCII TAB (HT) and SPACE characters, respectively, but MUST NOT be so represented at the end of an encoded line. Any TAB (HT) or SPACE characters on an encoded line MUST thus be followed on that line by a printable character. In particular, an
142 * "=" at the end of an encoded line, indicating a soft line break (see rule #5) may follow one or more TAB (HT) or SPACE characters. It follows that an octet with value 9 or 32 appearing at the end of an encoded line must be represented according to Rule #1. This rule is necessary because some MTAs (Message Transport Agents, programs which transport messages from one user to another, or perform a part of such transfers) are known to pad lines of text with SPACEs, and others are known to remove "white space" characters from the end of a line. Therefore, when decoding a Quoted-Printable body, any trailing white space on a line must be deleted, as it will necessarily have been added by intermediate transport agents.
143 * Rule #4 (Line Breaks): A line break in a text body, independent of what its representation is following the canonical representation of the data being encoded, must be represented by a (RFC 822) line break, which is a CRLF sequence, in the Quoted-Printable encoding. Since the canonical representation of types other than text do not generally include the representation of line breaks, no hard line breaks (i.e. line breaks that are intended to be meaningful and to be displayed to the user) should occur in the quoted-printable encoding of such types. Of course, occurrences of "=0D", "=0A", "0A=0D" and "=0D=0A" will eventually be encountered. In general, however, base64 is preferred over quoted-printable for binary data.
144 * Note that many implementations may elect to encode the local representation of various content types directly, as described in Appendix G. In particular, this may apply to plain text material on systems that use newline conventions other than CRLF delimiters. Such an implementation is permissible, but the generation of line breaks must be generalized to account for the case where alternate representations of newline sequences are used.
145 * Rule #5 (Soft Line Breaks): The Quoted-Printable encoding REQUIRES that encoded lines be no more than 76 characters long. If longer lines are to be encoded with the Quoted-Printable encoding, 'soft' line breaks must be used. An equal sign as the last character on a encoded line indicates such a non-significant ('soft') line break in the encoded text. Thus if the "raw" form of the line is a single unencoded line that says:
146 * Now's the time for all folk to come to the aid of their country.
147 *
148 * This can be represented, in the Quoted-Printable encoding, as
149 *
150 * Now's the time =
151 * for all folk to come=
152 * to the aid of their country.
153 *
154 * This provides a mechanism with which long lines are encoded in such a way as to be restored by the user agent. The 76 character limit does not count the trailing CRLF, but counts all other characters, including any equal signs.
155 * Since the hyphen character ("-") is represented as itself in the Quoted-Printable encoding, care must be taken, when encapsulating a quoted-printable encoded body in a multipart entity, to ensure that the encapsulation boundary does not appear anywhere in the encoded body. (A good strategy is to choose a boundary that includes a character sequence such as "=_" which can never appear in a quoted- printable body. See the definition of multipart messages later in this document.)
156 * NOTE: The quoted-printable encoding represents something of a compromise between readability and reliability in transport. Bodies encoded with the quoted-printable encoding will work reliably over most mail gateways, but may not work perfectly over a few gateways, notably those involving translation into EBCDIC. (In theory, an EBCDIC gateway could decode a quoted-printable body and re-encode it using base64, but such gateways do not yet exist.) A higher level of confidence is offered by the base64 Content-Transfer-Encoding. A way to get reasonably reliable transport through EBCDIC gateways is to also quote the ASCII characters
157 * !"#$@[\]^`{|}~
158 * according to rule #1. See Appendix B for more information.
159 * Because quoted-printable data is generally assumed to be line- oriented, it is to be expected that the representation of the breaks between the lines of quoted printable data may be altered in transport, in the same manner that plain text mail has always been altered in Internet mail when passing between systems with differing newline conventions. If such alterations are likely to constitute a corruption of the data, it is probably more sensible to use the base64 encoding rather than the quoted-printable encoding.
160 * WARNING TO IMPLEMENTORS: If binary data are encoded in quoted- printable, care must be taken to encode CR and LF characters as "=0D" and "=0A", respectively. In particular, a CRLF sequence in binary data should be encoded as "=0D=0A". Otherwise, if CRLF were represented as a hard line break, it might be incorrectly decoded on
161 * platforms with different line break conventions.
162 * For formalists, the syntax of quoted-printable data is described by the following grammar:
163 *
164 * quoted-printable := ([*(ptext / SPACE / TAB) ptext] ["="] CRLF)
165 * ; Maximum line length of 76 characters excluding CRLF
166 *
167 * ptext := octet /<any ASCII character except "=", SPACE, or TAB>
168 * ; characters not listed as "mail-safe" in Appendix B
169 * ; are also not recommended.
170 *
171 * octet := "=" 2(DIGIT / "A" / "B" / "C" / "D" / "E" / "F")
172 * ; octet must be used for characters > 127, =, SPACE, or TAB,
173 * ; and is recommended for any characters not listed in
174 * ; Appendix B as "mail-safe".
175 */
176 /**
177 * HTML mail class
178 *
179 * @author Kasper Skaarhoj <kasperYYYY@typo3.com>
180 * @package TYPO3
181 * @subpackage t3lib
182 */
183 class t3lib_htmlmail {
184 // Headerinfo:
185 var $recipient = '';
186 var $recipient_copy = ''; // This recipient (or list of...) will also receive the mail. Regard it as a copy.
187 var $subject = '';
188 var $from_email = '';
189 var $from_name = '';
190 var $replyto_email = '';
191 var $replyto_name = '';
192 var $organisation = '';
193 var $priority = 3; // 1 = highest, 5 = lowest, 3 = normal
194 var $mailer = ''; // X-mailer, set to TYPO3 Major.Minor in constructor
195 var $alt_base64 = 0;
196 var $alt_8bit = 0;
197 var $jumperURL_prefix = ''; // This is a prefix that will be added to all links in the mail. Example: 'http://www.mydomain.com/jump?userid=###FIELD_uid###&url='. if used, anything after url= is urlencoded.
198 var $jumperURL_useId = 0; // If set, then the array-key of the urls are inserted instead of the url itself. Smart in order to reduce link-length
199 var $mediaList = ''; // If set, this is a list of the media-files (index-keys to the array) that should be represented in the html-mail
200 var $http_password = '';
201 var $http_username = '';
202 var $postfix_version1 = false;
203
204 // Internal
205 /*
206 This is how the $theParts-array is normally looking
207 var $theParts = array(
208 'plain' => array(
209 'content' => ''
210 ),
211 'html' => array(
212 'content' => '',
213 'path' => '',
214 'media' => array(),
215 'hrefs' => array()
216 ),
217 'attach' => array()
218 );
219 */
220 var $theParts = array();
221
222 var $messageid = '';
223 var $returnPath = '';
224 var $Xid = '';
225 var $dontEncodeHeader = false; // If set, the header will not be encoded
226
227 var $headers = '';
228 var $message = '';
229 var $part = 0;
230 var $image_fullpath_list = '';
231 var $href_fullpath_list = '';
232
233 var $plain_text_header = '';
234 var $html_text_header = '';
235 var $charset = '';
236 var $defaultCharset = 'iso-8859-1';
237
238
239
240 /**
241 * Constructor. If the configuration variable forceReturnPath is set,
242 * calls to mail will be called with a 5th parameter.
243 * See function sendTheMail for more info
244 *
245 * @return void
246 */
247 public function t3lib_htmlmail() {
248 $this->forceReturnPath = $GLOBALS['TYPO3_CONF_VARS']['SYS']['forceReturnPath'];
249
250 $this->mailer = 'TYPO3 '.TYPO3_version;
251 }
252
253
254 /**
255 * start action that sets the message ID and the charset
256 *
257 * @return void
258 */
259 public function start() {
260 global $TYPO3_CONF_VARS;
261
262 // Sets the message id
263 $host = t3lib_div::getHostname();
264 if (!$host || $host == '127.0.0.1' || $host == 'localhost' || $host == 'localhost.localdomain') {
265 $host = ($TYPO3_CONF_VARS['SYS']['sitename'] ? preg_replace('/[^A-Za-z0-9_\-]/', '_', $TYPO3_CONF_VARS['SYS']['sitename']) : 'localhost') . '.TYPO3';
266 }
267 $this->messageid = md5(microtime()) . '@' . $host;
268
269
270 // Default line break for Unix systems.
271 $this->linebreak = chr(10);
272 // Line break for Windows. This is needed because PHP on Windows systems
273 // send mails via SMTP instead of using sendmail, and thus the linebreak needs to be \r\n.
274 if (TYPO3_OS == 'WIN') {
275 $this->linebreak = chr(13).chr(10);
276 }
277
278 // Sets the Charset
279 if (!$this->charset) {
280 if (is_object($GLOBALS['TSFE']) && $GLOBALS['TSFE']->renderCharset) {
281 $this->charset = $GLOBALS['TSFE']->renderCharset;
282 } elseif (is_object($GLOBALS['LANG']) && $GLOBALS['LANG']->charSet) {
283 $this->charset = $GLOBALS['LANG']->charSet;
284 } elseif ($GLOBALS['TYPO3_CONF_VARS']['BE']['forceCharset']) {
285 $this->charset = $GLOBALS['TYPO3_CONF_VARS']['BE']['forceCharset'];
286 } else {
287 $this->charset = $this->defaultCharset;
288 }
289 }
290
291 // Use quoted-printable headers by default
292 $this->useQuotedPrintable();
293 }
294
295
296 /**
297 * sets the header of both Plain Text and HTML mails to quoted printable
298 *
299 * @return void
300 */
301 public function useQuotedPrintable() {
302 $this->plain_text_header = 'Content-Type: text/plain; charset='.$this->charset.$this->linebreak.'Content-Transfer-Encoding: quoted-printable';
303 $this->html_text_header = 'Content-Type: text/html; charset='.$this->charset.$this->linebreak.'Content-Transfer-Encoding: quoted-printable';
304 }
305
306 /**
307 * sets the encoding headers to base64 for both the Plain Text and HTML mail
308 *
309 * @return void
310 */
311 public function useBase64() {
312 $this->plain_text_header = 'Content-Type: text/plain; charset='.$this->charset.$this->linebreak.'Content-Transfer-Encoding: base64';
313 $this->html_text_header = 'Content-Type: text/html; charset='.$this->charset.$this->linebreak.'Content-Transfer-Encoding: base64';
314 $this->alt_base64 = 1;
315 }
316
317
318 /**
319 * sets the encoding to 8bit and the current charset of both the Plain Text and the HTML mail
320 *
321 * @return void
322 */
323 public function use8Bit() {
324 $this->plain_text_header = 'Content-Type: text/plain; charset='.$this->charset.$this->linebreak.'Content-Transfer-Encoding: 8bit';
325 $this->html_text_header = 'Content-Type: text/html; charset='.$this->charset.$this->linebreak.'Content-Transfer-Encoding: 8bit';
326 $this->alt_8bit = 1;
327 }
328
329
330 /**
331 * Encodes the message content according to the options "alt_base64" and "alt_8bit" (no need to encode here)
332 * or to "quoted_printable" if no option is set.
333 *
334 * @param string $content the content that will be encoded
335 * @return string the encoded content
336 */
337 public function encodeMsg($content) {
338 if ($this->alt_base64) {
339 return $this->makeBase64($content);
340 } elseif ($this->alt_8bit) {
341 return $content;
342 } else {
343 return t3lib_div::quoted_printable($content);
344 }
345 }
346
347
348 /**
349 * Adds plain-text, replaces the HTTP urls in the plain text and then encodes it
350 *
351 * @param string $content that will be added
352 * @return void
353 */
354 public function addPlain($content) {
355 $content = $this->substHTTPurlsInPlainText($content);
356 $this->setPlain($this->encodeMsg($content));
357 }
358
359
360 /**
361 * Adds an attachment to the mail
362 *
363 * @param string $file: the filename to add
364 * @return boolean whether the attachment was added or not
365 */
366 public function addAttachment($file) {
367 // Fetching the content and the mime-type
368 $fileInfo = $this->getExtendedURL($file);
369 if ($fileInfo) {
370 if (!$fileInfo['content_type']) {
371 $fileInfo['content_type'] = 'application/octet-stream';
372 }
373 $temp = $this->split_fileref($file);
374 if ($temp['file']) {
375 $fileInfo['filename'] = $temp['file'];
376 } elseif (strpos(' '.$fileInfo['content_type'], 'htm')) {
377 $fileInfo['filename'] = 'index.html';
378 } else {
379 $fileInfo['filename'] = 'unknown';
380 }
381 $this->theParts['attach'][] = $fileInfo;
382 return true;
383 }
384 return false;
385 }
386
387
388 /**
389 * Adds HTML and media, encodes it from a URL or file
390 *
391 * @param string $file: the filename to add
392 * @return boolean whether the attachment was added or not
393 */
394 public function addHTML($file) {
395 $status = $this->fetchHTML($file);
396 if (!$status) {
397 return false;
398 }
399 if ($this->extractFramesInfo()) {
400 return 'Document was a frameset. Stopped';
401 }
402 $this->extractMediaLinks();
403 $this->extractHyperLinks();
404 $this->fetchHTMLMedia();
405 $this->substMediaNamesInHTML(0); // 0 = relative
406 $this->substHREFsInHTML();
407 $this->setHtml($this->encodeMsg($this->theParts['html']['content']));
408 }
409
410
411 /**
412 * Extract HTML-parts, used externally
413 *
414 * @param string $html: will be added to the html "content" part
415 * @param string $url: will be added to the html "path" part
416 * @return void
417 */
418 public function extractHtmlInit($html,$url) {
419 $this->theParts['html']['content'] = $html;
420 $this->theParts['html']['path'] = $url;
421 }
422
423
424 /**
425 * Assembles the message by headers and content and finally send it to the provided recipient.
426 *
427 * @param string $recipient: The recipient the message should be delivered to (if blank, $this->recipient will be used instead)
428 * @return boolean Returns whether the mail was sent (successfully accepted for delivery)
429 */
430 public function send($recipient) {
431 if ($recipient) {
432 $this->recipient = $recipient;
433 }
434 $this->setHeaders();
435 $this->setContent();
436 $mailWasSent = $this->sendTheMail();
437 return $mailWasSent;
438 }
439
440
441
442
443
444
445
446
447
448
449
450
451
452 /*****************************************
453 *
454 * Main functions
455 *
456 *****************************************/
457
458 /**
459 * Clears the header-string and sets the headers based on object-vars.
460 *
461 * @return void
462 */
463 public function setHeaders() {
464 $this->headers = '';
465 // Message_id
466 $this->add_header('Message-ID: <'.$this->messageid.'>');
467 // Return path
468 if ($this->returnPath) {
469 $this->add_header('Return-Path: '.$this->returnPath);
470 $this->add_header('Errors-To: '.$this->returnPath);
471 }
472 // X-id
473 if ($this->Xid) {
474 $this->add_header('X-Typo3MID: '.$this->Xid);
475 }
476
477 // From
478 if ($this->from_email) {
479 if ($this->from_name) {
480 $this->add_header('From: '.$this->from_name.' <'.$this->from_email.'>');
481 } else {
482 $this->add_header('From: '.$this->from_email);
483 }
484 }
485 // Reply
486 if ($this->replyto_email) {
487 if ($this->replyto_name) {
488 $this->add_header('Reply-To: '.$this->replyto_name.' <'.$this->replyto_email.'>');
489 } else {
490 $this->add_header('Reply-To: '.$this->replyto_email);
491 }
492 }
493 // Organisation
494 if ($this->organisation) {
495 $this->add_header('Organisation: '.$this->organisation);
496 }
497 // mailer
498 if ($this->mailer) {
499 $this->add_header('X-Mailer: '.$this->mailer);
500 }
501 // priority
502 if ($this->priority) {
503 $this->add_header('X-Priority: '.$this->priority);
504 }
505 $this->add_header('Mime-Version: 1.0');
506
507 if (!$this->dontEncodeHeader) {
508 $enc = $this->alt_base64 ? 'base64' : 'quoted_printable'; // Header must be ASCII, therefore only base64 or quoted_printable are allowed!
509 // Quote recipient and subject
510 $this->recipient = t3lib_div::encodeHeader($this->recipient,$enc,$this->charset);
511 $this->subject = t3lib_div::encodeHeader($this->subject,$enc,$this->charset);
512 }
513 }
514
515
516 /**
517 * Sets the recipient(s). If you supply a string, you set one recipient.
518 * If you supply an array, every value is added as a recipient.
519 *
520 * @param mixed $recipient: the recipient(s) to set
521 * @return void
522 */
523 public function setRecipient($recipient) {
524 $this->recipient = (is_array($recipient) ? implode(',', $recipient) : $recipient);
525 }
526
527
528 /**
529 * Returns the content type based on whether the mail has media / attachments or no
530 *
531 * @return string the content type
532 */
533 public function getHTMLContentType() {
534 return (count($this->theParts['html']['media']) ? 'multipart/related;' : 'multipart/alternative;');
535 }
536
537
538 /**
539 * Begins building the message-body
540 *
541 * @return void
542 */
543 public function setContent() {
544 $this->message = '';
545 $boundary = $this->getBoundary();
546
547 // Setting up headers
548 if (count($this->theParts['attach'])) { // Generate (plain/HTML) / attachments
549 $this->add_header('Content-Type: multipart/mixed;');
550 $this->add_header(' boundary="'.$boundary.'"');
551 $this->add_message("This is a multi-part message in MIME format.\n");
552 $this->constructMixed($boundary);
553 } elseif ($this->theParts['html']['content']) { // Generate plain/HTML mail
554 $this->add_header('Content-Type: '.$this->getHTMLContentType());
555 $this->add_header(' boundary="'.$boundary.'"');
556 $this->add_message("This is a multi-part message in MIME format.\n");
557 $this->constructHTML($boundary);
558 } else { // Generate plain only
559 $this->add_header($this->plain_text_header);
560 $this->add_message($this->getContent('plain'));
561 }
562 }
563
564
565 /**
566 * This functions combines the plain / HTML content with the attachments
567 *
568 * @param string $boundary: the mail boundary
569 * @return void
570 */
571 public function constructMixed($boundary) {
572 $this->add_message("--".$boundary);
573
574 if ($this->theParts['html']['content']) { // HTML and plain is added
575 $newBoundary = $this->getBoundary();
576 $this->add_message("Content-Type: ".$this->getHTMLContentType());
577 $this->add_message(' boundary="'.$newBoundary.'"');
578 $this->add_message('');
579 $this->constructHTML($newBoundary);
580 } else { // Purely plain
581 $this->add_message($this->plain_text_header);
582 $this->add_message('');
583 $this->add_message($this->getContent('plain'));
584 }
585 // attachments are added
586 if (is_array($this->theParts['attach'])) {
587 foreach($this->theParts['attach'] as $media) {
588 $this->add_message("--".$boundary);
589 $this->add_message("Content-Type: ".$media['content_type']);
590 $this->add_message(' name="'.$media['filename'].'"');
591 $this->add_message('Content-Transfer-Encoding: base64');
592 $this->add_message('Content-Disposition: attachment;');
593 $this->add_message(' filename="'.$media['filename'].'"');
594 $this->add_message('');
595 $this->add_message($this->makeBase64($media['content']));
596 }
597 }
598 $this->add_message("--".$boundary."--\n");
599 }
600
601
602 /**
603 * this function creates the HTML part of the mail
604 *
605 * @param string $boundary: the boundary to use
606 * @return void
607 */
608 public function constructHTML($boundary) {
609 // If media, then we know, the multipart/related content-type has been set before this function call
610 if (count($this->theParts['html']['media'])) {
611 $this->add_message("--".$boundary);
612 // HTML has media
613 $newBoundary = $this->getBoundary();
614 $this->add_message('Content-Type: multipart/alternative;');
615 $this->add_message(' boundary="'.$newBoundary.'"');
616 $this->add_message('Content-Transfer-Encoding: 7bit');
617 $this->add_message('');
618
619 // Adding the plaintext/html mix, and use $newBoundary
620 $this->constructAlternative($newBoundary);
621 $this->constructHTML_media($boundary);
622 } else {
623 // if no media, just use the $boundary for adding plaintext/html mix
624 $this->constructAlternative($boundary);
625 }
626 }
627
628
629 /**
630 * Here plain is combined with HTML
631 *
632 * @param string $boundary: the boundary to use
633 * @return void
634 */
635 public function constructAlternative($boundary) {
636 $this->add_message("--".$boundary);
637
638 // plain is added
639 $this->add_message($this->plain_text_header);
640 $this->add_message('');
641 $this->add_message($this->getContent('plain'));
642 $this->add_message("--".$boundary);
643
644 // html is added
645 $this->add_message($this->html_text_header);
646 $this->add_message('');
647 $this->add_message($this->getContent('html'));
648 $this->add_message("--".$boundary."--\n");
649 }
650
651
652 /**
653 * Constructs the HTML-part of message if the HTML contains media
654 *
655 * @param string $boundary: the boundary to use
656 * @return void
657 */
658 public function constructHTML_media($boundary) {
659 // media is added
660 if (is_array($this->theParts['html']['media'])) {
661 foreach($this->theParts['html']['media'] as $key => $media) {
662 if (!$this->mediaList || t3lib_div::inList($this->mediaList,$key)) {
663 $this->add_message("--".$boundary);
664 $this->add_message('Content-Type: '.$media['ctype']);
665 $this->add_message('Content-ID: <part'.$key.'.'.$this->messageid.'>');
666 $this->add_message('Content-Transfer-Encoding: base64');
667 $this->add_message('');
668 $this->add_message($this->makeBase64($media['content']));
669 }
670 }
671 }
672 $this->add_message("--".$boundary."--\n");
673 }
674
675
676 /**
677 * Sends the mail by calling the mail() function in php. On Linux systems this will invoke the MTA
678 * defined in php.ini (sendmail -t -i by default), on Windows a SMTP must be specified in the sys.ini.
679 * Most common MTA's on Linux has a Sendmail interface, including Postfix and Exim.
680 * For setting the return-path correctly, the parameter -f has to be added to the system call to sendmail.
681 * This obviously does not have any effect on Windows, but on Sendmail compliant systems this works. If safe mode
682 * is enabled, then extra parameters is not allowed, so a safe mode check is made before the mail() command is
683 * invoked. When using the -f parameter, some MTA's will put an X-AUTHENTICATION-WARNING saying that
684 * the return path was modified manually with the -f flag. To disable this warning make sure that the user running
685 * Apache is in the /etc/mail/trusted-users table.
686 *
687 * POSTFIX: With postfix version below 2.0 there is a problem that the -f parameter can not be used in conjunction
688 * with -t. Postfix will give an error in the maillog:
689 *
690 * cannot handle command-line recipients with -t
691 *
692 * The -f parameter is only enabled if the parameter forceReturnPath is enabled in the install tool.
693 *
694 * This whole problem of return-path turns out to be quite tricky. If you have a solution that works better, on all
695 * standard MTA's then we are very open for suggestions.
696 *
697 * With time this function should be made such that several ways of sending the mail is possible (local MTA, smtp other).
698 *
699 * @return boolean Returns whether the mail was sent (successfully accepted for delivery)
700 */
701 public function sendTheMail() {
702 $mailWasSent = false;
703
704 // Sending the mail requires the recipient and message to be set.
705 if (!trim($this->recipient) || !trim($this->message)) {
706 return false;
707 }
708
709 // On windows the -f flag is not used (specific for Sendmail and Postfix),
710 // but instead the php.ini parameter sendmail_from is used.
711 $returnPath = (strlen($this->returnPath) > 0) ? '-f'.$this->returnPath : '';
712 if($this->returnPath) {
713 ini_set(sendmail_from, $this->returnPath);
714 }
715 // If safe mode is on, the fifth parameter to mail is not allowed, so the fix wont work on unix with safe_mode=On
716 $returnPathPossible = (!ini_get('safe_mode') && $this->forceReturnPath);
717 if ($returnPathPossible) {
718 $mailWasSent = mail($this->recipient,
719 $this->subject,
720 $this->message,
721 $this->headers,
722 $returnPath);
723 } else {
724 $mailWasSent = mail($this->recipient,
725 $this->subject,
726 $this->message,
727 $this->headers);
728 }
729
730 // Sending a copy
731 if ($this->recipient_copy) {
732 if ($returnPathPossible) {
733 $mailWasSent = mail($this->recipient_copy,
734 $this->subject,
735 $this->message,
736 $this->headers,
737 $returnPath);
738 } else {
739 $mailWasSent = mail($this->recipient_copy,
740 $this->subject,
741 $this->message,
742 $this->headers);
743 }
744 }
745 // Auto response
746 if ($this->auto_respond_msg) {
747 $theParts = explode('/',$this->auto_respond_msg,2);
748 $theParts[1] = str_replace("/",chr(10),$theParts[1]);
749 if ($returnPathPossible) {
750 $mailWasSent = mail($this->from_email,
751 $theParts[0],
752 $theParts[1],
753 "From: ".$this->recipient,
754 $returnPath);
755 } else {
756 $mailWasSent = mail($this->from_email,
757 $theParts[0],
758 $theParts[1],
759 "From: ".$this->recipient);
760 }
761 }
762 if ($this->returnPath) {
763 ini_restore(sendmail_from);
764 }
765 return $mailWasSent;
766 }
767
768
769 /**
770 * Returns boundaries
771 *
772 * @return string the boundary
773 */
774 public function getBoundary() {
775 $this->part++;
776 return "----------".uniqid("part_".$this->part."_");
777 }
778
779
780 /**
781 * Sets the plain-text part. No processing done.
782 *
783 * @param string $content: the plain content
784 * @return void
785 */
786 public function setPlain($content) {
787 $this->theParts['plain']['content'] = $content;
788 }
789
790
791 /**
792 * Sets the HTML-part. No processing done.
793 *
794 * @param string $content: the HTML content
795 * @return void
796 */
797 public function setHtml($content) {
798 $this->theParts['html']['content'] = $content;
799 }
800
801
802 /**
803 * Adds a header to the mail. Use this AFTER the setHeaders()-function
804 *
805 * @param string $header: the header in form of "key: value"
806 * @return void
807 */
808 public function add_header($header) {
809 // Mail headers must be ASCII, therefore we convert the whole header to either base64 or quoted_printable
810 if (!$this->dontEncodeHeader && !stristr($header,'Content-Type') && !stristr($header,'Content-Transfer-Encoding')) {
811 // Field tags must not be encoded
812 $parts = explode(': ',$header,2);
813 if (count($parts) == 2) {
814 $enc = $this->alt_base64 ? 'base64' : 'quoted_printable';
815 $parts[1] = t3lib_div::encodeHeader($parts[1], $enc, $this->charset);
816 $header = implode(': ', $parts);
817 }
818 }
819
820 $this->headers .= $header."\n";
821 }
822
823
824 /**
825 * Adds a line of text to the mail-body. Is normally used internally
826 *
827 * @param string $msg: the message to add
828 * @return void
829 */
830 public function add_message($msg) {
831 $this->message .= $msg."\n";
832 }
833
834
835 /**
836 * returns the content specified by the type (plain, html etc.)
837 *
838 * @param string $type: the content type, can either plain or html
839 * @return void
840 */
841 public function getContent($type) {
842 return $this->theParts[$type]['content'];
843 }
844
845
846 /**
847 * shows a preview of the email of the headers and the message
848 *
849 * @return void
850 */
851 public function preview() {
852 echo nl2br(htmlspecialchars($this->headers));
853 echo "<BR>";
854 echo nl2br(htmlspecialchars($this->message));
855 }
856
857
858
859
860
861
862
863
864 /****************************************************
865 *
866 * Functions for acquiring attachments, HTML, analyzing and so on **
867 *
868 ***************************************************/
869
870 /**
871 * Fetches the HTML-content from either url og local serverfile
872 *
873 * @param string $file: the file to load
874 * @return boolean whether the data was fetched or not
875 */
876 public function fetchHTML($file) {
877 // Fetches the content of the page
878 $this->theParts['html']['content'] = $this->getURL($file);
879 if ($this->theParts['html']['content']) {
880 $addr = $this->extParseUrl($file);
881 $path = ($addr['scheme']) ? $addr['scheme'].'://'.$addr['host'].(($addr['port'])?':'.$addr['port']:'').(($addr['filepath'])?$addr['filepath']:'/') : $addr['filepath'];
882 $this->theParts['html']['path'] = $path;
883 return true;
884 } else {
885 return false;
886 }
887 }
888
889
890 /**
891 * Fetches the mediafiles which are found by extractMediaLinks()
892 *
893 * @return void
894 */
895 public function fetchHTMLMedia() {
896 if (!is_array($this->theParts['html']['media']) || !count($this->theParts['html']['media'])) return;
897 foreach ($this->theParts['html']['media'] as $key => $media) {
898 // fetching the content and the mime-type
899 $picdata = $this->getExtendedURL($this->theParts['html']['media'][$key]['absRef']);
900 if (is_array($picdata)) {
901 $this->theParts['html']['media'][$key]['content'] = $picdata['content'];
902 $this->theParts['html']['media'][$key]['ctype'] = $picdata['content_type'];
903 }
904 }
905 }
906
907
908 /**
909 * extracts all media-links from $this->theParts['html']['content']
910 *
911 * @return void
912 */
913 public function extractMediaLinks() {
914 $html_code = $this->theParts['html']['content'];
915 $attribRegex = $this->tag_regex(array('img','table','td','tr','body','iframe','script','input','embed'));
916
917 // split the document by the beginning of the above tags
918 $codepieces = split($attribRegex, $html_code);
919 $len = strlen($codepieces[0]);
920 $pieces = count($codepieces);
921 $reg = array();
922 for ($i = 1; $i < $pieces; $i++) {
923 $tag = strtolower(strtok(substr($html_code,$len+1,10),' '));
924 $len += strlen($tag)+strlen($codepieces[$i])+2;
925 $dummy = eregi("[^>]*", $codepieces[$i], $reg);
926 $attributes = $this->get_tag_attributes($reg[0]); // Fetches the attributes for the tag
927 $imageData = array();
928
929 // Finds the src or background attribute
930 $imageData['ref'] = ($attributes['src'] ? $attributes['src'] : $attributes['background']);
931 if ($imageData['ref']) {
932 // find out if the value had quotes around it
933 $imageData['quotes'] = (substr($codepieces[$i], strpos($codepieces[$i], $imageData['ref'])-1,1) == '"') ? '"' : '';
934 // subst_str is the string to look for, when substituting lateron
935 $imageData['subst_str'] = $imageData['quotes'].$imageData['ref'].$imageData['quotes'];
936 if ($imageData['ref'] && !strstr($this->image_fullpath_list,"|".$imageData["subst_str"]."|")) {
937 $this->image_fullpath_list .= "|".$imageData['subst_str']."|";
938 $imageData['absRef'] = $this->absRef($imageData['ref']);
939 $imageData['tag'] = $tag;
940 $imageData['use_jumpurl'] = $attributes['dmailerping']?1:0;
941 $this->theParts['html']['media'][] = $imageData;
942 }
943 }
944 }
945
946 // Extracting stylesheets
947 $attribRegex = $this->tag_regex(array('link'));
948 // Split the document by the beginning of the above tags
949 $codepieces = split($attribRegex, $html_code);
950 $pieces = count($codepieces);
951 for ($i = 1; $i < $pieces; $i++) {
952 $dummy = eregi("[^>]*", $codepieces[$i], $reg);
953 // fetches the attributes for the tag
954 $attributes = $this->get_tag_attributes($reg[0]);
955 $imageData = array();
956 if (strtolower($attributes['rel']) == 'stylesheet' && $attributes['href']) {
957 // Finds the src or background attribute
958 $imageData['ref'] = $attributes['href'];
959 // Finds out if the value had quotes around it
960 $imageData['quotes'] = (substr($codepieces[$i],strpos($codepieces[$i], $imageData['ref'])-1,1) == '"') ? '"' : '';
961 // subst_str is the string to look for, when substituting lateron
962 $imageData['subst_str'] = $imageData['quotes'].$imageData['ref'].$imageData['quotes'];
963 if ($imageData['ref'] && !strstr($this->image_fullpath_list,"|".$imageData["subst_str"]."|")) {
964 $this->image_fullpath_list .= "|".$imageData["subst_str"]."|";
965 $imageData['absRef'] = $this->absRef($imageData["ref"]);
966 $this->theParts['html']['media'][] = $imageData;
967 }
968 }
969 }
970
971 // fixes javascript rollovers
972 $codepieces = split(quotemeta(".src"), $html_code);
973 $pieces = count($codepieces);
974 $expr = "^[^".quotemeta("\"").quotemeta("'")."]*";
975 for($i = 1; $i < $pieces; $i++) {
976 $temp = $codepieces[$i];
977 $temp = trim(ereg_replace("=","",trim($temp)));
978 ereg($expr,substr($temp,1,strlen($temp)),$reg);
979 $imageData['ref'] = $reg[0];
980 $imageData['quotes'] = substr($temp,0,1);
981 // subst_str is the string to look for, when substituting lateron
982 $imageData['subst_str'] = $imageData['quotes'].$imageData['ref'].$imageData['quotes'];
983 $theInfo = $this->split_fileref($imageData['ref']);
984
985 switch ($theInfo['fileext']) {
986 case 'gif':
987 case 'jpeg':
988 case 'jpg':
989 if ($imageData['ref'] && !strstr($this->image_fullpath_list,"|".$imageData["subst_str"]."|")) {
990 $this->image_fullpath_list .= "|".$imageData['subst_str']."|";
991 $imageData['absRef'] = $this->absRef($imageData['ref']);
992 $this->theParts['html']['media'][] = $imageData;
993 }
994 break;
995 }
996 }
997 }
998
999
1000 /**
1001 * extracts all hyper-links from $this->theParts["html"]["content"]
1002 *
1003 * @return void
1004 */
1005 public function extractHyperLinks() {
1006 $html_code = $this->theParts['html']['content'];
1007 $attribRegex = $this->tag_regex(array('a','form','area'));
1008 $codepieces = split($attribRegex, $html_code); // Splits the document by the beginning of the above tags
1009 $len = strlen($codepieces[0]);
1010 $pieces = count($codepieces);
1011 for($i = 1; $i < $pieces; $i++) {
1012 $tag = strtolower(strtok(substr($html_code,$len+1,10)," "));
1013 $len += strlen($tag) + strlen($codepieces[$i]) + 2;
1014
1015 $dummy = eregi("[^>]*", $codepieces[$i], $reg);
1016 // Fetches the attributes for the tag
1017 $attributes = $this->get_tag_attributes($reg[0]);
1018 $hrefData = array();
1019 $hrefData['ref'] = ($attributes['href'] ? $attributes['href'] : $hrefData['ref'] = $attributes['action']);
1020 if ($hrefData['ref']) {
1021 // Finds out if the value had quotes around it
1022 $hrefData['quotes'] = (substr($codepieces[$i],strpos($codepieces[$i], $hrefData["ref"])-1,1) == '"') ? '"' : '';
1023 // subst_str is the string to look for, when substituting lateron
1024 $hrefData['subst_str'] = $hrefData['quotes'].$hrefData['ref'].$hrefData['quotes'];
1025 if ($hrefData['ref'] && substr(trim($hrefData['ref']),0,1) != "#" && !strstr($this->href_fullpath_list,"|".$hrefData['subst_str']."|")) {
1026 $this->href_fullpath_list .= "|".$hrefData['subst_str']."|";
1027 $hrefData['absRef'] = $this->absRef($hrefData['ref']);
1028 $hrefData['tag'] = $tag;
1029 $this->theParts['html']['hrefs'][] = $hrefData;
1030 }
1031 }
1032 }
1033 // Extracts TYPO3 specific links made by the openPic() JS function
1034 $codepieces = explode("onClick=\"openPic('", $html_code);
1035 $pieces = count($codepieces);
1036 for($i = 1; $i < $pieces; $i++) {
1037 $showpic_linkArr = explode("'",$codepieces[$i]);
1038 $hrefData['ref'] = $showpic_linkArr[0];
1039 if ($hrefData['ref']) {
1040 $hrefData['quotes'] = "'";
1041 // subst_str is the string to look for, when substituting lateron
1042 $hrefData['subst_str'] = $hrefData['quotes'].$hrefData['ref'].$hrefData['quotes'];
1043 if ($hrefData['ref'] && !strstr($this->href_fullpath_list,"|".$hrefData['subst_str']."|")) {
1044 $this->href_fullpath_list .= "|".$hrefData['subst_str']."|";
1045 $hrefData['absRef'] = $this->absRef($hrefData['ref']);
1046 $this->theParts['html']['hrefs'][] = $hrefData;
1047 }
1048 }
1049 }
1050 }
1051
1052
1053 /**
1054 * extracts all media-links from $this->theParts["html"]["content"]
1055 *
1056 * @return array two-dimensional array with information about each frame
1057 */
1058 public function extractFramesInfo() {
1059 $htmlCode = $this->theParts['html']['content'];
1060 $info = array();
1061 if (strpos(' '.$htmlCode,'<frame ')) {
1062 $attribRegex = $this->tag_regex('frame');
1063 // Splits the document by the beginning of the above tags
1064 $codepieces = split($attribRegex, $htmlCode, 1000000);
1065 $pieces = count($codepieces);
1066 for($i = 1; $i < $pieces; $i++) {
1067 $dummy = eregi("[^>]*", $codepieces[$i], $reg);
1068 // Fetches the attributes for the tag
1069 $attributes = $this->get_tag_attributes($reg[0]);
1070 $frame = array();
1071 $frame['src'] = $attributes['src'];
1072 $frame['name'] = $attributes['name'];
1073 $frame['absRef'] = $this->absRef($frame['src']);
1074 $info[] = $frame;
1075 }
1076 return $info;
1077 }
1078 }
1079
1080
1081 /**
1082 * This function substitutes the media-references in $this->theParts["html"]["content"]
1083 *
1084 * @param boolean $absolute: If true, then the refs are substituted with http:// ref's indstead of Content-ID's (cid).
1085 * @return void
1086 */
1087 public function substMediaNamesInHTML($absolute) {
1088 if (is_array($this->theParts['html']['media'])) {
1089 foreach ($this->theParts['html']['media'] as $key => $val) {
1090 if ($val['use_jumpurl'] && $this->jumperURL_prefix) {
1091 $subst = $this->jumperURL_prefix.t3lib_div::rawUrlEncodeFP($val['absRef']);
1092 } else {
1093 $subst = ($absolute) ? $val['absRef'] : 'cid:part'.$key.'.'.$this->messageid;
1094 }
1095 $this->theParts['html']['content'] = str_replace(
1096 $val['subst_str'],
1097 $val['quotes'] . $subst . $val['quotes'],
1098 $this->theParts['html']['content']);
1099 }
1100 }
1101 if (!$absolute) {
1102 $this->fixRollOvers();
1103 }
1104 }
1105
1106
1107 /**
1108 * This function substitutes the hrefs in $this->theParts["html"]["content"]
1109 *
1110 * @return void
1111 */
1112 public function substHREFsInHTML() {
1113 if (!is_array($this->theParts['html']['hrefs'])) return;
1114 foreach ($this->theParts['html']['hrefs'] as $key => $val) {
1115 // Form elements cannot use jumpurl!
1116 if ($this->jumperURL_prefix && $val['tag'] != 'form') {
1117 if ($this->jumperURL_useId) {
1118 $substVal = $this->jumperURL_prefix.$key;
1119 } else {
1120 $substVal = $this->jumperURL_prefix.t3lib_div::rawUrlEncodeFP($val['absRef']);
1121 }
1122 } else {
1123 $theSubstVal = $val['absRef'];
1124 }
1125 $this->theParts['html']['content'] = str_replace(
1126 $val['subst_str'],
1127 $val['quotes'] . $substVal . $val['quotes'],
1128 $this->theParts['html']['content']);
1129 }
1130 }
1131
1132
1133 /**
1134 * This substitutes the http:// urls in plain text with links
1135 *
1136 * @param string $content: the content to use to substitute
1137 * @return string the changed content
1138 */
1139 public function substHTTPurlsInPlainText($content) {
1140 if (!$this->jumperURL_prefix) return $content;
1141
1142 $textpieces = explode("http://", $content);
1143 $pieces = count($textpieces);
1144 $textstr = $textpieces[0];
1145 for($i = 1; $i<$pieces; $i++) {
1146 $len = strcspn($textpieces[$i],chr(32).chr(9).chr(13).chr(10));
1147 if (trim(substr($textstr,-1)) == '' && $len) {
1148 $lastChar = substr($textpieces[$i],$len-1,1);
1149 if (!ereg("[A-Za-z0-9\/#]",$lastChar)) {
1150 // Included "\/" 3/12
1151 $len--;
1152 }
1153
1154 $parts = array();
1155 $parts[0] = "http://".substr($textpieces[$i],0,$len);
1156 $parts[1] = substr($textpieces[$i],$len);
1157
1158 if ($this->jumperURL_useId) {
1159 $this->theParts['plain']['link_ids'][$i] = $parts[0];
1160 $parts[0] = $this->jumperURL_prefix.'-'.$i;
1161 } else {
1162 $parts[0] = $this->jumperURL_prefix.t3lib_div::rawUrlEncodeFP($parts[0]);
1163 }
1164 $textstr .= $parts[0].$parts[1];
1165 } else {
1166 $textstr .= 'http://'.$textpieces[$i];
1167 }
1168 }
1169 return $textstr;
1170 }
1171
1172
1173 /**
1174 * JavaScript rollOvers cannot support graphics inside of mail.
1175 * If these exists we must let them refer to the absolute url. By the way:
1176 * Roll-overs seems to work only on some mail-readers and so far I've seen it
1177 * work on Netscape 4 message-center (but not 4.5!!)
1178 *
1179 * @return void
1180 */
1181 public function fixRollOvers() {
1182 $newContent = '';
1183 $items = explode('.src',$this->theParts['html']['content']);
1184 if (count($items) <= 1) return;
1185
1186 foreach($items as $key => $part) {
1187 $sub = substr($part, 0, 200);
1188 if (ereg("cid:part[^ \"']*",$sub,$reg)) {
1189 // The position of the string
1190 $thePos = strpos($part,$reg[0]);
1191 // Finds the id of the media...
1192 ereg("cid:part([^\.]*).*",$sub,$reg2);
1193 $theSubStr = $this->theParts['html']['media'][intval($reg2[1])]['absRef'];
1194 if ($thePos && $theSubStr) {
1195 // ... and substitutes the javaScript rollover image with this instead
1196 // If the path is NOT and url, the reference is set to nothing
1197 if (!strpos(' '.$theSubStr, 'http://')) {
1198 $theSubStr = 'http://';
1199 }
1200 $part = substr($part, 0, $thePos) . $theSubStr . substr($part,$thePos+strlen($reg[0]),strlen($part));
1201 }
1202 }
1203 $newContent .= $part . ((($key+1) != count($items)) ? '.src' : '');
1204 }
1205 $this->theParts['html']['content'] = $newContent;
1206 }
1207
1208
1209
1210
1211
1212
1213
1214
1215 /*******************************************
1216 *
1217 * File and URL-functions
1218 *
1219 *******************************************/
1220
1221 /**
1222 * Returns base64-encoded content, which is broken every 76 character
1223 *
1224 * @param string $inputstr: the string to encode
1225 * @return string the encoded string
1226 */
1227 public function makeBase64($inputstr) {
1228 return chunk_split(base64_encode($inputstr));
1229 }
1230
1231
1232 /**
1233 * reads the URL or file and determines the Content-type by either guessing or opening a connection to the host
1234 *
1235 * @param string $url: the URL to get information of
1236 * @return mixed either false or the array with information
1237 */
1238 public function getExtendedURL($url) {
1239 $res = array();
1240 $res['content'] = $this->getURL($url);
1241 if (!$res['content']) return false;
1242 $pathInfo = parse_url($url);
1243 $fileInfo = $this->split_fileref($pathInfo['path']);
1244 switch ($fileInfo['fileext']) {
1245 case 'gif':
1246 case 'png':
1247 $res['content_type'] = 'image/'.$fileInfo['fileext'];
1248 break;
1249 case 'jpg':
1250 case 'jpeg':
1251 $res['content_type'] = 'image/jpeg';
1252 break;
1253 case 'html':
1254 case 'htm':
1255 $res['content_type'] = 'text/html';
1256 break;
1257 case 'css':
1258 $res['content_type'] = 'text/css';
1259 break;
1260 case 'swf':
1261 $res['content_type'] = 'application/x-shockwave-flash';
1262 break;
1263 default:
1264 $res['content_type'] = $this->getMimeType($url);
1265 }
1266 return $res;
1267 }
1268
1269
1270 /**
1271 * Adds HTTP user and password (from $this->http_username) to a URL
1272 *
1273 * @param string $url: the URL
1274 * @return string the URL with the added values
1275 */
1276 public function addUserPass($url) {
1277 $user = $this->http_username;
1278 $pass = $this->http_password;
1279 $matches = array();
1280 if ($user && $pass && preg_match('/^(https?:\/\/)/', $url, $matches)) {
1281 return $matches[1].$user.':'.$pass.'@'.substr($url,strlen($matches[1]));
1282 }
1283 return $url;
1284 }
1285
1286
1287 /**
1288 * reads a url or file
1289 *
1290 * @param string $url: the URL to fetch
1291 * @return string the content of the URL
1292 */
1293 public function getURL($url) {
1294 $url = $this->addUserPass($url);
1295 return t3lib_div::getURL($url);
1296 }
1297
1298
1299 /**
1300 * reads a url or file and strips the HTML-tags AND removes all
1301 * empty lines. This is used to read plain-text out of a HTML-page
1302 *
1303 * @param string $url: the URL to load
1304 * @return the content
1305 */
1306 public function getStrippedURL($url) {
1307 $content = '';
1308 if ($fd = fopen($url, "rb")) {
1309 while (!feof($fd)) {
1310 $line = fgetss($fd, 5000);
1311 if (trim($line)) {
1312 $content .= trim($line) . "\n";
1313 }
1314 }
1315 fclose($fd);
1316 }
1317 return $content;
1318 }
1319
1320
1321 /**
1322 * This function returns the mime type of the file specified by the url
1323 *
1324 * @param string $url: the url
1325 * @return string $mimeType: the mime type found in the header
1326 */
1327 public function getMimeType($url) {
1328 $mimeType = '';
1329 $headers = trim(t3lib_div::getURL($url, 2));
1330 if ($headers) {
1331 $matches = array();
1332 if (preg_match('/(Content-Type:[\s]*)([a-zA-Z_0-9\/\-\.\+]*)([\s]|$)/', $headers, $matches)) {
1333 $mimeType = trim($matches[2]);
1334 }
1335 }
1336 return $mimeType;
1337 }
1338
1339
1340 /**
1341 * Returns the absolute address of a link. This is based on
1342 * $this->theParts["html"]["path"] being the root-address
1343 *
1344 * @param string $ref: address to use
1345 * @return string the absolute address
1346 */
1347 public function absRef($ref) {
1348 $ref = trim($ref);
1349 $info = parse_url($ref);
1350 if ($info['scheme']) {
1351 return $ref;
1352 } elseif (eregi("^/",$ref)) {
1353 $addr = parse_url($this->theParts['html']['path']);
1354 return $addr['scheme'].'://'.$addr['host'].($addr['port']?':'.$addr['port']:'').$ref;
1355 } else {
1356 // If the reference is relative, the path is added, in order for us to fetch the content
1357 return $this->theParts['html']['path'] . $ref;
1358 }
1359 }
1360
1361
1362 /**
1363 * Returns information about a file reference
1364 *
1365 * @param string $fileref: the file to use
1366 * @return array path, filename, filebody, fileext
1367 */
1368 public function split_fileref($fileref) {
1369 $info = array();
1370 if (ereg("(.*/)(.*)$", $fileref, $reg)) {
1371 $info['path'] = $reg[1];
1372 $info['file'] = $reg[2];
1373 } else {
1374 $info['path'] = '';
1375 $info['file'] = $fileref;
1376 }
1377 $reg = '';
1378 if (ereg("(.*)\.([^\.]*$)", $info['file'], $reg)) {
1379 $info['filebody'] = $reg[1];
1380 $info['fileext'] = strtolower($reg[2]);
1381 $info['realFileext'] = $reg[2];
1382 } else {
1383 $info['filebody'] = $info['file'];
1384 $info['fileext'] = '';
1385 }
1386 return $info;
1387 }
1388
1389
1390 /**
1391 * Returns an array with file or url-information
1392 *
1393 * @param string $path: url to check
1394 * @return array information about the path / URL
1395 */
1396 public function extParseUrl($path) {
1397 $res = parse_url($path);
1398 ereg("(.*/)([^/]*)$", $res['path'], $reg);
1399 $res['filepath'] = $reg[1];
1400 $res['filename'] = $reg[2];
1401 return $res;
1402 }
1403
1404
1405 /**
1406 * Creates a regular expression out of a list of tags
1407 *
1408 * @param mixed $tagArray: the list of tags (either as array or string if it is one tag)
1409 * @return string the regular expression
1410 */
1411 public function tag_regex($tags) {
1412 $tags = (!is_array($tags) ? array($tags) : $tags);
1413 $regexp = '';
1414 $c = count($tags);
1415 foreach($tags as $tag) {
1416 $c--;
1417 $regexp .= '<' . sql_regcase($tag) . "[[:space:]]" . (($c) ? '|' : '');
1418 }
1419 return $regexp;
1420 }
1421
1422
1423 /**
1424 * This function analyzes a HTML tag
1425 * If an attribute is empty (like OPTION) the value of that key is just empty. Check it with is_set();
1426 *
1427 * @param string $tag: is either like this "<TAG OPTION ATTRIB=VALUE>" or
1428 * this " OPTION ATTRIB=VALUE>" which means you can omit the tag-name
1429 * @return array array with attributes as keys in lower-case
1430 */
1431 public function get_tag_attributes($tag) {
1432 $attributes = array();
1433 $tag = ltrim(eregi_replace ("^<[^ ]*","",trim($tag)));
1434 $tagLen = strlen($tag);
1435 $safetyCounter = 100;
1436 // Find attribute
1437 while ($tag) {
1438 $value = '';
1439 $reg = split("[[:space:]=>]",$tag,2);
1440 $attrib = $reg[0];
1441
1442 $tag = ltrim(substr($tag,strlen($attrib),$tagLen));
1443 if (substr($tag,0,1) == '=') {
1444 $tag = ltrim(substr($tag,1,$tagLen));
1445 if (substr($tag,0,1) == '"') {
1446 // Quotes around the value
1447 $reg = explode('"',substr($tag,1,$tagLen),2);
1448 $tag = ltrim($reg[1]);
1449 $value = $reg[0];
1450 } else {
1451 // No quotes around value
1452 ereg("^([^[:space:]>]*)(.*)",$tag,$reg);
1453 $value = trim($reg[1]);
1454 $tag = ltrim($reg[2]);
1455 if (substr($tag,0,1) == '>') {
1456 $tag = '';
1457 }
1458 }
1459 }
1460 $attributes[strtolower($attrib)] = $value;
1461 $safetyCounter--;
1462 if ($safetyCounter < 0) break;
1463 }
1464 return $attributes;
1465 }
1466
1467
1468 /**
1469 * Implementation of quoted-printable encode.
1470 * This function was a duplicate of t3lib_div::quoted_printable, thus it's going to be removed.
1471 * Deprecated since TYPO3 4.0
1472 *
1473 * @param string Content to encode
1474 * @return string The QP encoded string
1475 * @deprecated since TYPO3 4.0, remove in TYPO 4.3
1476 */
1477 public function quoted_printable($string) {
1478 return t3lib_div::quoted_printable($string, 76);
1479 }
1480
1481
1482 /**
1483 * Converts a name field
1484 * Deprecated since TYPO3 4.0
1485 *
1486 * @param string $name: the name
1487 * @return string the name
1488 * @deprecated since TYPO3 4.0, remove in TYPO3 4.3
1489 */
1490 public function convertName($name) {
1491 return $name;
1492 }
1493 }
1494
1495 if (defined('TYPO3_MODE') && $TYPO3_CONF_VARS[TYPO3_MODE]['XCLASS']['t3lib/class.t3lib_htmlmail.php']) {
1496 include_once($TYPO3_CONF_VARS[TYPO3_MODE]['XCLASS']['t3lib/class.t3lib_htmlmail.php']);
1497 }
1498 ?>