Cleanup: Updated copyright comments
[Packages/TYPO3.CMS.git] / t3lib / class.t3lib_htmlmail.php
1 <?php
2 /***************************************************************
3 * Copyright notice
4 *
5 * (c) 1999-2011 Kasper Skårhøj (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 Skårhøj <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 Skårhøj <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 $recipient_blindcopy = ''; // This recipient (or list of...) will also receive the mail as a blind copy. Regard it as a copy.
188 var $subject = '';
189 var $from_email = '';
190 var $from_name = '';
191 var $replyto_email = '';
192 var $replyto_name = '';
193 var $organisation = '';
194 var $priority = 3; // 1 = highest, 5 = lowest, 3 = normal
195 var $mailer = ''; // X-mailer, set to TYPO3 Major.Minor in constructor
196 var $alt_base64 = 0;
197 var $alt_8bit = 0;
198 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.
199 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
200 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
201 var $http_password = '';
202 var $http_username = '';
203 var $postfix_version1 = FALSE;
204
205 // Internal
206 /*
207 This is how the $theParts-array is normally looking
208 var $theParts = array(
209 'plain' => array(
210 'content' => ''
211 ),
212 'html' => array(
213 'content' => '',
214 'path' => '',
215 'media' => array(),
216 'hrefs' => array()
217 ),
218 'attach' => array()
219 );
220 */
221 var $theParts = array();
222
223 var $messageid = '';
224 var $returnPath = '';
225 var $Xid = '';
226 var $dontEncodeHeader = FALSE; // If set, the header will not be encoded
227
228 var $headers = '';
229 var $message = '';
230 var $part = 0;
231 var $image_fullpath_list = '';
232 var $href_fullpath_list = '';
233
234 var $plain_text_header = '';
235 var $html_text_header = '';
236 var $charset = '';
237 var $defaultCharset = 'iso-8859-1';
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';
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 = LF;
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 $this->linebreak = CRLF;
276 }
277
278 // Sets the Charset
279 if (!$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 * Main functions
444 *
445 *****************************************/
446
447 /**
448 * Clears the header-string and sets the headers based on object-vars.
449 *
450 * @return void
451 */
452 public function setHeaders() {
453 $this->headers = '';
454 // Message_id
455 $this->add_header('Message-ID: <' . $this->messageid . '>');
456 // Return path
457 if ($this->returnPath) {
458 $this->add_header('Return-Path: ' . $this->returnPath);
459 $this->add_header('Errors-To: ' . $this->returnPath);
460 }
461 // X-id
462 if ($this->Xid) {
463 $this->add_header('X-Typo3MID: ' . $this->Xid);
464 }
465
466 // From
467 if ($this->from_email) {
468 if ($this->from_name && !t3lib_div::isBrokenEmailEnvironment()) {
469 $this->add_header('From: ' . $this->from_name . ' <' . $this->from_email . '>');
470 } else {
471 $this->add_header('From: ' . $this->from_email);
472 }
473 }
474
475 // Cc
476 if ($this->recipient_copy) {
477 $this->add_header('Cc: ' . $this->recipient_copy);
478 }
479
480 // Bcc
481 if ($this->recipient_blindcopy) {
482 $this->add_header('Bcc: ' . $this->recipient_blindcopy);
483 }
484
485 // Reply
486 if ($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: ' . $this->replyto_email);
491 }
492 }
493 // Organization, using american english spelling (organization / organisation) as defined in RFC 1036 / 2076
494 if ($this->organisation) {
495 $this->add_header('Organization: ' . $this->organisation);
496 }
497 // mailer
498 if ($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'])) {
549 // Generate (plain/HTML) / attachments
550 $this->add_header('Content-Type: multipart/mixed;');
551 $this->add_header(' boundary="' . $boundary . '"');
552 $this->add_message('This is a multi-part message in MIME format.' . LF);
553 $this->constructMixed($boundary);
554 } elseif ($this->theParts['html']['content']) {
555 // Generate plain/HTML mail
556 $this->add_header('Content-Type: ' . $this->getHTMLContentType() . ';');
557 $this->add_header(' boundary="' . $boundary . '"');
558 $this->add_message('This is a multi-part message in MIME format.' . LF);
559 $this->constructHTML($boundary);
560 } else {
561 // Generate plain only
562 $this->add_header($this->plain_text_header);
563 $this->add_message($this->getContent('plain'));
564 }
565 }
566
567
568 /**
569 * This functions combines the plain / HTML content with the attachments
570 *
571 * @param string $boundary: the mail boundary
572 * @return void
573 */
574 public function constructMixed($boundary) {
575 $this->add_message('--' . $boundary);
576
577 if ($this->theParts['html']['content']) {
578 // HTML and plain is added
579 $newBoundary = $this->getBoundary();
580 $this->add_message('Content-Type: ' . $this->getHTMLContentType() . ';');
581 $this->add_message(' boundary="' . $newBoundary . '"');
582 $this->add_message('');
583 $this->constructHTML($newBoundary);
584 } else {
585 // Purely plain
586 $this->add_message($this->plain_text_header);
587 $this->add_message('');
588 $this->add_message($this->getContent('plain'));
589 }
590 // attachments are added
591 if (is_array($this->theParts['attach'])) {
592 foreach ($this->theParts['attach'] as $media) {
593 $this->add_message('--' . $boundary);
594 $this->add_message('Content-Type: ' . $media['content_type'] . ';');
595 $this->add_message(' name="' . $media['filename'] . '"');
596 $this->add_message('Content-Transfer-Encoding: base64');
597 $this->add_message('Content-Disposition: attachment;');
598 $this->add_message(' filename="' . $media['filename'] . '"');
599 $this->add_message('');
600 $this->add_message($this->makeBase64($media['content']));
601 }
602 }
603 $this->add_message('--' . $boundary . '--' . LF);
604 }
605
606
607 /**
608 * this function creates the HTML part of the mail
609 *
610 * @param string $boundary: the boundary to use
611 * @return void
612 */
613 public function constructHTML($boundary) {
614 // If media, then we know, the multipart/related content-type has been set before this function call
615 if (count($this->theParts['html']['media'])) {
616 $this->add_message('--' . $boundary);
617 // HTML has media
618 $newBoundary = $this->getBoundary();
619 $this->add_message('Content-Type: multipart/alternative;');
620 $this->add_message(' boundary="' . $newBoundary . '"');
621 $this->add_message('Content-Transfer-Encoding: 7bit');
622 $this->add_message('');
623
624 // Adding the plaintext/html mix, and use $newBoundary
625 $this->constructAlternative($newBoundary);
626 $this->constructHTML_media($boundary);
627 } else {
628 // if no media, just use the $boundary for adding plaintext/html mix
629 $this->constructAlternative($boundary);
630 }
631 }
632
633
634 /**
635 * Here plain is combined with HTML
636 *
637 * @param string $boundary: the boundary to use
638 * @return void
639 */
640 public function constructAlternative($boundary) {
641 $this->add_message('--' . $boundary);
642
643 // plain is added
644 $this->add_message($this->plain_text_header);
645 $this->add_message('');
646 $this->add_message($this->getContent('plain'));
647 $this->add_message('--' . $boundary);
648
649 // html is added
650 $this->add_message($this->html_text_header);
651 $this->add_message('');
652 $this->add_message($this->getContent('html'));
653 $this->add_message('--' . $boundary . '--' . LF);
654 }
655
656
657 /**
658 * Constructs the HTML-part of message if the HTML contains media
659 *
660 * @param string $boundary: the boundary to use
661 * @return void
662 */
663 public function constructHTML_media($boundary) {
664 // media is added
665 if (is_array($this->theParts['html']['media'])) {
666 foreach ($this->theParts['html']['media'] as $key => $media) {
667 if (!$this->mediaList || t3lib_div::inList($this->mediaList, $key)) {
668 $this->add_message('--' . $boundary);
669 $this->add_message('Content-Type: ' . $media['ctype']);
670 $this->add_message('Content-ID: <part' . $key . '.' . $this->messageid . '>');
671 $this->add_message('Content-Transfer-Encoding: base64');
672 $this->add_message('');
673 $this->add_message($this->makeBase64($media['content']));
674 }
675 }
676 }
677 $this->add_message('--' . $boundary . '--' . LF);
678 }
679
680
681 /**
682 * Sends the mail by calling the mail() function in php. On Linux systems this will invoke the MTA
683 * defined in php.ini (sendmail -t -i by default), on Windows a SMTP must be specified in the sys.ini.
684 * Most common MTA's on Linux has a Sendmail interface, including Postfix and Exim.
685 * For setting the return-path correctly, the parameter -f has to be added to the system call to sendmail.
686 * This obviously does not have any effect on Windows, but on Sendmail compliant systems this works. If safe mode
687 * is enabled, then extra parameters is not allowed, so a safe mode check is made before the mail() command is
688 * invoked. When using the -f parameter, some MTA's will put an X-AUTHENTICATION-WARNING saying that
689 * the return path was modified manually with the -f flag. To disable this warning make sure that the user running
690 * Apache is in the /etc/mail/trusted-users table.
691 *
692 * POSTFIX: With postfix version below 2.0 there is a problem that the -f parameter can not be used in conjunction
693 * with -t. Postfix will give an error in the maillog:
694 *
695 * cannot handle command-line recipients with -t
696 *
697 * The -f parameter is only enabled if the parameter forceReturnPath is enabled in the install tool.
698 *
699 * This whole problem of return-path turns out to be quite tricky. If you have a solution that works better, on all
700 * standard MTA's then we are very open for suggestions.
701 *
702 * With time this function should be made such that several ways of sending the mail is possible (local MTA, smtp other).
703 *
704 * @return boolean Returns whether the mail was sent (successfully accepted for delivery)
705 */
706 public function sendTheMail() {
707 $mailWasSent = FALSE;
708
709 // Sending the mail requires the recipient and message to be set.
710 if (!trim($this->recipient) || !trim($this->message)) {
711 return FALSE;
712 }
713
714 // On windows the -f flag is not used (specific for Sendmail and Postfix),
715 // but instead the php.ini parameter sendmail_from is used.
716 $returnPath = ($this->forceReturnPath && strlen($this->returnPath) > 0) ? '-f ' . escapeshellarg($this->returnPath) : '';
717 if (TYPO3_OS == 'WIN' && $this->returnPath) {
718 @ini_set('sendmail_from', t3lib_div::normalizeMailAddress($this->returnPath));
719 }
720 $recipient = t3lib_div::normalizeMailAddress($this->recipient);
721
722 // If safe mode is on, the fifth parameter to mail is not allowed, so the fix wont work on unix with safe_mode=On
723 $returnPathPossible = (!t3lib_utility_PhpOptions::isSafeModeEnabled() && $this->forceReturnPath);
724 if ($returnPathPossible) {
725 $mailWasSent = t3lib_utility_Mail::mail(
726 $recipient,
727 $this->subject,
728 $this->message,
729 $this->headers,
730 $returnPath
731 );
732 } else {
733 $mailWasSent = t3lib_utility_Mail::mail(
734 $recipient,
735 $this->subject,
736 $this->message,
737 $this->headers
738 );
739 }
740
741 // Auto response
742 if ($this->auto_respond_msg) {
743 $theParts = explode('/', $this->auto_respond_msg, 2);
744 $theParts[0] = str_replace('###SUBJECT###', $this->subject, $theParts[0]);
745 $theParts[1] = str_replace("/", LF, $theParts[1]);
746 $theParts[1] = str_replace("###MESSAGE###", $this->getContent('plain'), $theParts[1]);
747 if ($returnPathPossible) {
748 $mailWasSent = t3lib_utility_Mail::mail(
749 $this->from_email,
750 $theParts[0],
751 $theParts[1],
752 'From: ' . $recipient . $this->linebreak . $this->plain_text_header,
753 $returnPath
754 );
755 } else {
756 $mailWasSent = t3lib_utility_Mail::mail(
757 $this->from_email,
758 $theParts[0],
759 $theParts[1],
760 'From: ' . $recipient . $this->linebreak . $this->plain_text_header
761 );
762 }
763 }
764 if ($this->returnPath) {
765 ini_restore('sendmail_from');
766 }
767 return $mailWasSent;
768 }
769
770
771 /**
772 * Returns boundaries
773 *
774 * @return string the boundary
775 */
776 public function getBoundary() {
777 $this->part++;
778 return "----------" . uniqid("part_" . $this->part . "_");
779 }
780
781
782 /**
783 * Sets the plain-text part. No processing done.
784 *
785 * @param string $content: the plain content
786 * @return void
787 */
788 public function setPlain($content) {
789 $this->theParts['plain']['content'] = $content;
790 }
791
792
793 /**
794 * Sets the HTML-part. No processing done.
795 *
796 * @param string $content: the HTML content
797 * @return void
798 */
799 public function setHtml($content) {
800 $this->theParts['html']['content'] = $content;
801 }
802
803
804 /**
805 * Adds a header to the mail. Use this AFTER the setHeaders()-function
806 *
807 * @param string $header: the header in form of "key: value"
808 * @return void
809 */
810 public function add_header($header) {
811 // Mail headers must be ASCII, therefore we convert the whole header to either base64 or quoted_printable
812 if (!$this->dontEncodeHeader && !stristr($header, 'Content-Type') && !stristr($header, 'Content-Transfer-Encoding')) {
813 // Field tags must not be encoded
814 $parts = explode(': ', $header, 2);
815 if (count($parts) == 2) {
816 $enc = $this->alt_base64 ? 'base64' : 'quoted_printable';
817 $parts[1] = t3lib_div::encodeHeader($parts[1], $enc, $this->charset);
818 $header = implode(': ', $parts);
819 }
820 }
821
822 $this->headers .= $header . LF;
823 }
824
825
826 /**
827 * Adds a line of text to the mail-body. Is normally used internally
828 *
829 * @param string $msg: the message to add
830 * @return void
831 */
832 public function add_message($msg) {
833 $this->message .= $msg . LF;
834 }
835
836
837 /**
838 * returns the content specified by the type (plain, html etc.)
839 *
840 * @param string $type: the content type, can either plain or html
841 * @return void
842 */
843 public function getContent($type) {
844 return $this->theParts[$type]['content'];
845 }
846
847
848 /**
849 * shows a preview of the email of the headers and the message
850 *
851 * @return void
852 */
853 public function preview() {
854 echo nl2br(htmlspecialchars($this->headers));
855 echo "<BR>";
856 echo nl2br(htmlspecialchars($this->message));
857 }
858
859
860 /****************************************************
861 *
862 * Functions for acquiring attachments, HTML, analyzing and so on **
863 *
864 ***************************************************/
865
866 /**
867 * Fetches the HTML-content from either url og local serverfile
868 *
869 * @param string $file: the file to load
870 * @return boolean whether the data was fetched or not
871 */
872 public function fetchHTML($file) {
873 // Fetches the content of the page
874 $this->theParts['html']['content'] = $this->getURL($file);
875 if ($this->theParts['html']['content']) {
876 $addr = $this->extParseUrl($file);
877 $path = ($addr['scheme']) ? $addr['scheme'] . '://' . $addr['host'] . (($addr['port']) ? ':' . $addr['port'] : '') . (($addr['filepath']) ? $addr['filepath'] : '/') : $addr['filepath'];
878 $this->theParts['html']['path'] = $path;
879 return TRUE;
880 } else {
881 return FALSE;
882 }
883 }
884
885
886 /**
887 * Fetches the mediafiles which are found by extractMediaLinks()
888 *
889 * @return void
890 */
891 public function fetchHTMLMedia() {
892 if (!is_array($this->theParts['html']['media']) || !count($this->theParts['html']['media'])) {
893 return;
894 }
895 foreach ($this->theParts['html']['media'] as $key => $media) {
896 // fetching the content and the mime-type
897 $picdata = $this->getExtendedURL($this->theParts['html']['media'][$key]['absRef']);
898 if (is_array($picdata)) {
899 $this->theParts['html']['media'][$key]['content'] = $picdata['content'];
900 $this->theParts['html']['media'][$key]['ctype'] = $picdata['content_type'];
901 }
902 }
903 }
904
905
906 /**
907 * extracts all media-links from $this->theParts['html']['content']
908 *
909 * @return void
910 */
911 public function extractMediaLinks() {
912 $html_code = $this->theParts['html']['content'];
913 $attribRegex = $this->tag_regex(array('img', 'table', 'td', 'tr', 'body', 'iframe', 'script', 'input', 'embed'));
914
915 // split the document by the beginning of the above tags
916 $codepieces = preg_split($attribRegex, $html_code);
917 $len = strlen($codepieces[0]);
918 $pieces = count($codepieces);
919 $reg = array();
920 for ($i = 1; $i < $pieces; $i++) {
921 $tag = strtolower(strtok(substr($html_code, $len + 1, 10), ' '));
922 $len += strlen($tag) + strlen($codepieces[$i]) + 2;
923 $dummy = preg_match('/[^>]*/', $codepieces[$i], $reg);
924 $attributes = $this->get_tag_attributes($reg[0]); // Fetches the attributes for the tag
925 $imageData = array();
926
927 // Finds the src or background attribute
928 $imageData['ref'] = ($attributes['src'] ? $attributes['src'] : $attributes['background']);
929 if ($imageData['ref']) {
930 // find out if the value had quotes around it
931 $imageData['quotes'] = (substr($codepieces[$i], strpos($codepieces[$i], $imageData['ref']) - 1, 1) == '"') ? '"' : '';
932 // subst_str is the string to look for, when substituting lateron
933 $imageData['subst_str'] = $imageData['quotes'] . $imageData['ref'] . $imageData['quotes'];
934 if ($imageData['ref'] && !strstr($this->image_fullpath_list, "|" . $imageData["subst_str"] . "|")) {
935 $this->image_fullpath_list .= "|" . $imageData['subst_str'] . "|";
936 $imageData['absRef'] = $this->absRef($imageData['ref']);
937 $imageData['tag'] = $tag;
938 $imageData['use_jumpurl'] = $attributes['dmailerping'] ? 1 : 0;
939 $this->theParts['html']['media'][] = $imageData;
940 }
941 }
942 }
943
944 // Extracting stylesheets
945 $attribRegex = $this->tag_regex(array('link'));
946 // Split the document by the beginning of the above tags
947 $codepieces = preg_split($attribRegex, $html_code);
948 $pieces = count($codepieces);
949 for ($i = 1; $i < $pieces; $i++) {
950 $dummy = preg_match('/[^>]*/', $codepieces[$i], $reg);
951 // fetches the attributes for the tag
952 $attributes = $this->get_tag_attributes($reg[0]);
953 $imageData = array();
954 if (strtolower($attributes['rel']) == 'stylesheet' && $attributes['href']) {
955 // Finds the src or background attribute
956 $imageData['ref'] = $attributes['href'];
957 // Finds out if the value had quotes around it
958 $imageData['quotes'] = (substr($codepieces[$i], strpos($codepieces[$i], $imageData['ref']) - 1, 1) == '"') ? '"' : '';
959 // subst_str is the string to look for, when substituting lateron
960 $imageData['subst_str'] = $imageData['quotes'] . $imageData['ref'] . $imageData['quotes'];
961 if ($imageData['ref'] && !strstr($this->image_fullpath_list, "|" . $imageData["subst_str"] . "|")) {
962 $this->image_fullpath_list .= "|" . $imageData["subst_str"] . "|";
963 $imageData['absRef'] = $this->absRef($imageData["ref"]);
964 $this->theParts['html']['media'][] = $imageData;
965 }
966 }
967 }
968
969 // fixes javascript rollovers
970 $codepieces = explode('.src', $html_code);
971 $pieces = count($codepieces);
972 $expr = '/^[^' . quotemeta('"') . quotemeta("'") . ']*/';
973 for ($i = 1; $i < $pieces; $i++) {
974 $temp = $codepieces[$i];
975 $temp = trim(str_replace('=', '', trim($temp)));
976 preg_match($expr, substr($temp, 1, strlen($temp)), $reg);
977 $imageData['ref'] = $reg[0];
978 $imageData['quotes'] = substr($temp, 0, 1);
979 // subst_str is the string to look for, when substituting lateron
980 $imageData['subst_str'] = $imageData['quotes'] . $imageData['ref'] . $imageData['quotes'];
981 $theInfo = $this->split_fileref($imageData['ref']);
982
983 switch ($theInfo['fileext']) {
984 case 'gif':
985 case 'jpeg':
986 case 'jpg':
987 if ($imageData['ref'] && !strstr($this->image_fullpath_list, "|" . $imageData["subst_str"] . "|")) {
988 $this->image_fullpath_list .= "|" . $imageData['subst_str'] . "|";
989 $imageData['absRef'] = $this->absRef($imageData['ref']);
990 $this->theParts['html']['media'][] = $imageData;
991 }
992 break;
993 }
994 }
995 }
996
997
998 /**
999 * extracts all hyper-links from $this->theParts["html"]["content"]
1000 *
1001 * @return void
1002 */
1003 public function extractHyperLinks() {
1004 $html_code = $this->theParts['html']['content'];
1005 $attribRegex = $this->tag_regex(array('a', 'form', 'area'));
1006 $codepieces = preg_split($attribRegex, $html_code); // Splits the document by the beginning of the above tags
1007 $len = strlen($codepieces[0]);
1008 $pieces = count($codepieces);
1009 for ($i = 1; $i < $pieces; $i++) {
1010 $tag = strtolower(strtok(substr($html_code, $len + 1, 10), " "));
1011 $len += strlen($tag) + strlen($codepieces[$i]) + 2;
1012
1013 $dummy = preg_match('/[^>]*/', $codepieces[$i], $reg);
1014 // Fetches the attributes for the tag
1015 $attributes = $this->get_tag_attributes($reg[0]);
1016 $hrefData = array();
1017 $hrefData['ref'] = ($attributes['href'] ? $attributes['href'] : $hrefData['ref'] = $attributes['action']);
1018 if ($hrefData['ref']) {
1019 // Finds out if the value had quotes around it
1020 $hrefData['quotes'] = (substr($codepieces[$i], strpos($codepieces[$i], $hrefData["ref"]) - 1, 1) == '"') ? '"' : '';
1021 // subst_str is the string to look for, when substituting lateron
1022 $hrefData['subst_str'] = $hrefData['quotes'] . $hrefData['ref'] . $hrefData['quotes'];
1023 if ($hrefData['ref'] && substr(trim($hrefData['ref']), 0, 1) != "#" && !strstr($this->href_fullpath_list, "|" . $hrefData['subst_str'] . "|")) {
1024 $this->href_fullpath_list .= "|" . $hrefData['subst_str'] . "|";
1025 $hrefData['absRef'] = $this->absRef($hrefData['ref']);
1026 $hrefData['tag'] = $tag;
1027 $this->theParts['html']['hrefs'][] = $hrefData;
1028 }
1029 }
1030 }
1031 // Extracts TYPO3 specific links made by the openPic() JS function
1032 $codepieces = explode("onClick=\"openPic('", $html_code);
1033 $pieces = count($codepieces);
1034 for ($i = 1; $i < $pieces; $i++) {
1035 $showpic_linkArr = explode("'", $codepieces[$i]);
1036 $hrefData['ref'] = $showpic_linkArr[0];
1037 if ($hrefData['ref']) {
1038 $hrefData['quotes'] = "'";
1039 // subst_str is the string to look for, when substituting lateron
1040 $hrefData['subst_str'] = $hrefData['quotes'] . $hrefData['ref'] . $hrefData['quotes'];
1041 if ($hrefData['ref'] && !strstr($this->href_fullpath_list, "|" . $hrefData['subst_str'] . "|")) {
1042 $this->href_fullpath_list .= "|" . $hrefData['subst_str'] . "|";
1043 $hrefData['absRef'] = $this->absRef($hrefData['ref']);
1044 $this->theParts['html']['hrefs'][] = $hrefData;
1045 }
1046 }
1047 }
1048 }
1049
1050
1051 /**
1052 * extracts all media-links from $this->theParts["html"]["content"]
1053 *
1054 * @return array two-dimensional array with information about each frame
1055 */
1056 public function extractFramesInfo() {
1057 $htmlCode = $this->theParts['html']['content'];
1058 $info = array();
1059 if (strpos(' ' . $htmlCode, '<frame ')) {
1060 $attribRegex = $this->tag_regex('frame');
1061 // Splits the document by the beginning of the above tags
1062 $codepieces = preg_split($attribRegex, $htmlCode, 1000000);
1063 $pieces = count($codepieces);
1064 for ($i = 1; $i < $pieces; $i++) {
1065 $dummy = preg_match('/[^>]*/', $codepieces[$i], $reg);
1066 // Fetches the attributes for the tag
1067 $attributes = $this->get_tag_attributes($reg[0]);
1068 $frame = array();
1069 $frame['src'] = $attributes['src'];
1070 $frame['name'] = $attributes['name'];
1071 $frame['absRef'] = $this->absRef($frame['src']);
1072 $info[] = $frame;
1073 }
1074 return $info;
1075 }
1076 }
1077
1078
1079 /**
1080 * This function substitutes the media-references in $this->theParts["html"]["content"]
1081 *
1082 * @param boolean $absolute: If true, then the refs are substituted with http:// ref's indstead of Content-ID's (cid).
1083 * @return void
1084 */
1085 public function substMediaNamesInHTML($absolute) {
1086 if (is_array($this->theParts['html']['media'])) {
1087 foreach ($this->theParts['html']['media'] as $key => $val) {
1088 if ($val['use_jumpurl'] && $this->jumperURL_prefix) {
1089 $subst = $this->jumperURL_prefix . t3lib_div::rawUrlEncodeFP($val['absRef']);
1090 } else {
1091 $subst = ($absolute) ? $val['absRef'] : 'cid:part' . $key . '.' . $this->messageid;
1092 }
1093 $this->theParts['html']['content'] = str_replace(
1094 $val['subst_str'],
1095 $val['quotes'] . $subst . $val['quotes'],
1096 $this->theParts['html']['content']);
1097 }
1098 }
1099 if (!$absolute) {
1100 $this->fixRollOvers();
1101 }
1102 }
1103
1104
1105 /**
1106 * This function substitutes the hrefs in $this->theParts["html"]["content"]
1107 *
1108 * @return void
1109 */
1110 public function substHREFsInHTML() {
1111 if (!is_array($this->theParts['html']['hrefs'])) {
1112 return;
1113 }
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 $substVal = $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) {
1141 return $content;
1142 }
1143
1144 $textpieces = explode("http://", $content);
1145 $pieces = count($textpieces);
1146 $textstr = $textpieces[0];
1147 for ($i = 1; $i < $pieces; $i++) {
1148 $len = strcspn($textpieces[$i], chr(32) . TAB . CRLF);
1149 if (trim(substr($textstr, -1)) == '' && $len) {
1150 $lastChar = substr($textpieces[$i], $len - 1, 1);
1151 if (!preg_match('/[A-Za-z0-9\/#]/', $lastChar)) {
1152 $len--;
1153 }
1154
1155 $parts = array();
1156 $parts[0] = "http://" . substr($textpieces[$i], 0, $len);
1157 $parts[1] = substr($textpieces[$i], $len);
1158
1159 if ($this->jumperURL_useId) {
1160 $this->theParts['plain']['link_ids'][$i] = $parts[0];
1161 $parts[0] = $this->jumperURL_prefix . '-' . $i;
1162 } else {
1163 $parts[0] = $this->jumperURL_prefix . t3lib_div::rawUrlEncodeFP($parts[0]);
1164 }
1165 $textstr .= $parts[0] . $parts[1];
1166 } else {
1167 $textstr .= 'http://' . $textpieces[$i];
1168 }
1169 }
1170 return $textstr;
1171 }
1172
1173
1174 /**
1175 * JavaScript rollOvers cannot support graphics inside of mail.
1176 * If these exists we must let them refer to the absolute url. By the way:
1177 * Roll-overs seems to work only on some mail-readers and so far I've seen it
1178 * work on Netscape 4 message-center (but not 4.5!!)
1179 *
1180 * @return void
1181 */
1182 public function fixRollOvers() {
1183 $newContent = '';
1184 $items = explode('.src', $this->theParts['html']['content']);
1185 if (count($items) <= 1) {
1186 return;
1187 }
1188
1189 foreach ($items as $key => $part) {
1190 $sub = substr($part, 0, 200);
1191 if (preg_match('/cid:part[^ "\']*/', $sub, $reg)) {
1192 // The position of the string
1193 $thePos = strpos($part, $reg[0]);
1194 // Finds the id of the media...
1195 preg_match('/cid:part([^\.]*).*/', $sub, $reg2);
1196 $theSubStr = $this->theParts['html']['media'][intval($reg2[1])]['absRef'];
1197 if ($thePos && $theSubStr) {
1198 // ... and substitutes the javaScript rollover image with this instead
1199 // If the path is NOT and url, the reference is set to nothing
1200 if (!strpos(' ' . $theSubStr, 'http://')) {
1201 $theSubStr = 'http://';
1202 }
1203 $part = substr($part, 0, $thePos) . $theSubStr . substr($part, $thePos + strlen($reg[0]), strlen($part));
1204 }
1205 }
1206 $newContent .= $part . ((($key + 1) != count($items)) ? '.src' : '');
1207 }
1208 $this->theParts['html']['content'] = $newContent;
1209 }
1210
1211
1212 /*******************************************
1213 *
1214 * File and URL-functions
1215 *
1216 *******************************************/
1217
1218 /**
1219 * Returns base64-encoded content, which is broken every 76 character
1220 *
1221 * @param string $inputstr: the string to encode
1222 * @return string the encoded string
1223 */
1224 public function makeBase64($inputstr) {
1225 return chunk_split(base64_encode($inputstr));
1226 }
1227
1228
1229 /**
1230 * reads the URL or file and determines the Content-type by either guessing or opening a connection to the host
1231 *
1232 * @param string $url: the URL to get information of
1233 * @return mixed either false or the array with information
1234 */
1235 public function getExtendedURL($url) {
1236 $res = array();
1237 $res['content'] = $this->getURL($url);
1238 if (!$res['content']) {
1239 return FALSE;
1240 }
1241 $pathInfo = parse_url($url);
1242 $fileInfo = $this->split_fileref($pathInfo['path']);
1243 switch ($fileInfo['fileext']) {
1244 case 'gif':
1245 case 'png':
1246 $res['content_type'] = 'image/' . $fileInfo['fileext'];
1247 break;
1248 case 'jpg':
1249 case 'jpeg':
1250 $res['content_type'] = 'image/jpeg';
1251 break;
1252 case 'html':
1253 case 'htm':
1254 $res['content_type'] = 'text/html';
1255 break;
1256 case 'css':
1257 $res['content_type'] = 'text/css';
1258 break;
1259 case 'swf':
1260 $res['content_type'] = 'application/x-shockwave-flash';
1261 break;
1262 default:
1263 $res['content_type'] = $this->getMimeType($url);
1264 }
1265 return $res;
1266 }
1267
1268
1269 /**
1270 * Adds HTTP user and password (from $this->http_username) to a URL
1271 *
1272 * @param string $url: the URL
1273 * @return string the URL with the added values
1274 */
1275 public function addUserPass($url) {
1276 $user = $this->http_username;
1277 $pass = $this->http_password;
1278 $matches = array();
1279 if ($user && $pass && preg_match('/^(https?:\/\/)/', $url, $matches)) {
1280 return $matches[1] . $user . ':' . $pass . '@' . substr($url, strlen($matches[1]));
1281 }
1282 return $url;
1283 }
1284
1285
1286 /**
1287 * reads a url or file
1288 *
1289 * @param string $url: the URL to fetch
1290 * @return string the content of the URL
1291 */
1292 public function getURL($url) {
1293 $url = $this->addUserPass($url);
1294 return t3lib_div::getURL($url);
1295 }
1296
1297
1298 /**
1299 * reads a url or file and strips the HTML-tags AND removes all
1300 * empty lines. This is used to read plain-text out of a HTML-page
1301 *
1302 * @param string $url: the URL to load
1303 * @return the content
1304 */
1305 public function getStrippedURL($url) {
1306 $content = '';
1307 if ($fd = fopen($url, "rb")) {
1308 while (!feof($fd)) {
1309 $line = fgetss($fd, 5000);
1310 if (trim($line)) {
1311 $content .= trim($line) . LF;
1312 }
1313 }
1314 fclose($fd);
1315 }
1316 return $content;
1317 }
1318
1319
1320 /**
1321 * This function returns the mime type of the file specified by the url
1322 *
1323 * @param string $url: the url
1324 * @return string $mimeType: the mime type found in the header
1325 */
1326 public function getMimeType($url) {
1327 $mimeType = '';
1328 $headers = trim(t3lib_div::getURL($url, 2));
1329 if ($headers) {
1330 $matches = array();
1331 if (preg_match('/(Content-Type:[\s]*)([a-zA-Z_0-9\/\-\.\+]*)([\s]|$)/', $headers, $matches)) {
1332 $mimeType = trim($matches[2]);
1333 }
1334 }
1335 return $mimeType;
1336 }
1337
1338
1339 /**
1340 * Returns the absolute address of a link. This is based on
1341 * $this->theParts["html"]["path"] being the root-address
1342 *
1343 * @param string $ref: address to use
1344 * @return string the absolute address
1345 */
1346 public function absRef($ref) {
1347 $ref = trim($ref);
1348 $info = parse_url($ref);
1349 if ($info['scheme']) {
1350 return $ref;
1351 } elseif (preg_match('/^\//', $ref)) {
1352 $addr = parse_url($this->theParts['html']['path']);
1353 return $addr['scheme'] . '://' . $addr['host'] . ($addr['port'] ? ':' . $addr['port'] : '') . $ref;
1354 } else {
1355 // If the reference is relative, the path is added, in order for us to fetch the content
1356 return $this->theParts['html']['path'] . $ref;
1357 }
1358 }
1359
1360
1361 /**
1362 * Returns information about a file reference
1363 *
1364 * @param string $fileref: the file to use
1365 * @return array path, filename, filebody, fileext
1366 */
1367 public function split_fileref($fileref) {
1368 $info = array();
1369 if (preg_match('/(.*\/)(.*)$/', $fileref, $reg)) {
1370 $info['path'] = $reg[1];
1371 $info['file'] = $reg[2];
1372 } else {
1373 $info['path'] = '';
1374 $info['file'] = $fileref;
1375 }
1376 $reg = '';
1377 if (preg_match('/(.*)\.([^\.]*$)/', $info['file'], $reg)) {
1378 $info['filebody'] = $reg[1];
1379 $info['fileext'] = strtolower($reg[2]);
1380 $info['realFileext'] = $reg[2];
1381 } else {
1382 $info['filebody'] = $info['file'];
1383 $info['fileext'] = '';
1384 }
1385 return $info;
1386 }
1387
1388
1389 /**
1390 * Returns an array with file or url-information
1391 *
1392 * @param string $path: url to check
1393 * @return array information about the path / URL
1394 */
1395 public function extParseUrl($path) {
1396 $res = parse_url($path);
1397 preg_match('/(.*\/)([^\/]*)$/', $res['path'], $reg);
1398 $res['filepath'] = $reg[1];
1399 $res['filename'] = $reg[2];
1400 return $res;
1401 }
1402
1403
1404 /**
1405 * Creates a regular expression out of a list of tags
1406 *
1407 * @param mixed $tagArray: the list of tags (either as array or string if it is one tag)
1408 * @return string the regular expression
1409 */
1410 public function tag_regex($tags) {
1411 $tags = (!is_array($tags) ? array($tags) : $tags);
1412 $regexp = '/';
1413 $c = count($tags);
1414 foreach ($tags as $tag) {
1415 $c--;
1416 $regexp .= '<' . $tag . '[[:space:]]' . (($c) ? '|' : '');
1417 }
1418 return $regexp . '/i';
1419 }
1420
1421
1422 /**
1423 * This function analyzes a HTML tag
1424 * If an attribute is empty (like OPTION) the value of that key is just empty. Check it with is_set();
1425 *
1426 * @param string $tag: is either like this "<TAG OPTION ATTRIB=VALUE>" or
1427 * this " OPTION ATTRIB=VALUE>" which means you can omit the tag-name
1428 * @return array array with attributes as keys in lower-case
1429 */
1430 public function get_tag_attributes($tag) {
1431 $attributes = array();
1432 $tag = ltrim(preg_replace('/^<[^ ]*/', '', trim($tag)));
1433 $tagLen = strlen($tag);
1434 $safetyCounter = 100;
1435 // Find attribute
1436 while ($tag) {
1437 $value = '';
1438 $reg = preg_split('/[[:space:]=>]/', $tag, 2);
1439 $attrib = $reg[0];
1440
1441 $tag = ltrim(substr($tag, strlen($attrib), $tagLen));
1442 if (substr($tag, 0, 1) == '=') {
1443 $tag = ltrim(substr($tag, 1, $tagLen));
1444 if (substr($tag, 0, 1) == '"') {
1445 // Quotes around the value
1446 $reg = explode('"', substr($tag, 1, $tagLen), 2);
1447 $tag = ltrim($reg[1]);
1448 $value = $reg[0];
1449 } else {
1450 // No quotes around value
1451 preg_match('/^([^[:space:]>]*)(.*)/', $tag, $reg);
1452 $value = trim($reg[1]);
1453 $tag = ltrim($reg[2]);
1454 if (substr($tag, 0, 1) == '>') {
1455 $tag = '';
1456 }
1457 }
1458 }
1459 $attributes[strtolower($attrib)] = $value;
1460 $safetyCounter--;
1461 if ($safetyCounter < 0) {
1462 break;
1463 }
1464 }
1465 return $attributes;
1466 }
1467
1468
1469 /**
1470 * Implementation of quoted-printable encode.
1471 * This function was a duplicate of t3lib_div::quoted_printable, thus it's going to be removed.
1472 * Deprecated since TYPO3 4.0
1473 *
1474 * @param string Content to encode
1475 * @return string The QP encoded string
1476 * @deprecated since TYPO3 4.0, will be removed in TYPO3 4.6
1477 */
1478 public function quoted_printable($string) {
1479 t3lib_div::logDeprecatedFunction();
1480
1481 return t3lib_div::quoted_printable($string, 76);
1482 }
1483
1484
1485 /**
1486 * Converts a name field
1487 * Deprecated since TYPO3 4.0
1488 *
1489 * @param string $name: the name
1490 * @return string the name
1491 * @deprecated since TYPO3 4.0, will be removed in TYPO3 4.6
1492 */
1493 public function convertName($name) {
1494 t3lib_div::logDeprecatedFunction();
1495
1496 return $name;
1497 }
1498 }
1499
1500 if (defined('TYPO3_MODE') && isset($GLOBALS['TYPO3_CONF_VARS'][TYPO3_MODE]['XCLASS']['t3lib/class.t3lib_htmlmail.php'])) {
1501 include_once($GLOBALS['TYPO3_CONF_VARS'][TYPO3_MODE]['XCLASS']['t3lib/class.t3lib_htmlmail.php']);
1502 }
1503
1504 ?>